diff --git a/spaces/1acneusushi/gradio-2dmoleculeeditor/data/1 nenokkadine movie download blu-ray rip moviesinstmank Everything you need to know about the plot cast and director of the film.md b/spaces/1acneusushi/gradio-2dmoleculeeditor/data/1 nenokkadine movie download blu-ray rip moviesinstmank Everything you need to know about the plot cast and director of the film.md
deleted file mode 100644
index c31f081cde8b8ef26e01f3f086f6dd2103548540..0000000000000000000000000000000000000000
--- a/spaces/1acneusushi/gradio-2dmoleculeeditor/data/1 nenokkadine movie download blu-ray rip moviesinstmank Everything you need to know about the plot cast and director of the film.md	
+++ /dev/null
@@ -1,94 +0,0 @@
-<br />
-<h1>1 Nenokkadine Movie Download Blu-Ray Rip Moviesinstmank: A Guide for Telugu Movie Fans</h1>
- <p>If you are a fan of Telugu movies, you might have heard of <strong>1 Nenokkadine</strong>, a psychological action thriller film starring Mahesh Babu and Kriti Sanon. The film was released in 2014 and received critical acclaim for its innovative plot, stunning visuals, and thrilling action sequences. The film also won several awards and became one of the highest-grossing Telugu films at the US box office.</p>
- <p>But if you missed watching this film in theatres, or if you want to watch it again in high quality, you might be wondering how to download 1 Nenokkadine in Blu-Ray rip quality. In this article, we will guide you through the process of downloading 1 Nenokkadine in Blu-Ray rip quality, as well as explain why you should choose this format over others. We will also discuss some legal and ethical issues related to downloading movies online.</p>
-<h2>1 nenokkadine movie download blu-ray rip moviesinstmank</h2><br /><p><b><b>Download</b> ===== <a href="https://byltly.com/2uKzy8">https://byltly.com/2uKzy8</a></b></p><br /><br />
- <h2>What is 1 Nenokkadine?</h2>
- <p>Before we get into the details of downloading 1 Nenokkadine, let us first give you a brief overview of what this film is about.</p>
- <h3>Plot summary</h3>
- <p>1 Nenokkadine revolves around the search by Gautham, a rock musician with schizophrenia, missing 25 percent of his brain's grey matter, for his parents with the help of Sameera, a journalist. Gautham was convinced that he was an orphan and assumes that his parents are dead; he does not remember their names or what they looked like. He hallucinates a mysterious person he believes is one of the three murderers of his parents. As he unravels the truth behind his past, he also faces danger from various enemies who want to stop him.</p>
- <h3>Cast and crew</h3>
- <p>The film was directed by Sukumar, who also co-wrote the story with Hari Prasad Jakka. The screenplay was written by Jeremy Zimmerman, Arjun Y.K., and Thota Srinivas. The film was produced by Ram Achanta, Gopichand Achanta, and Anil Sunkara on 14 Reels Entertainment banner and was distributed by Eros International.</p>
- <p>The film stars Mahesh Babu as Gautham, Kriti Sanon as Sameera, Nassar as Chandrashekar's friend, Pradeep Rawat as Taxi Driver, Anuradha Hasan as Kalyani, Kelly Dorji as Antonio Rosarius, Sayaji Shinde as John Baasha, Krishna Murali Posani as Gulab Singh, Srinivasa Reddy as Police Constable, Ravi Varma as Michael, Anand as Chandra Sekhar (Gautham's Father), Supreeth Reddy as Sophiya Chaudhary in Item number, Gautham Ghattamaneni as Young Gautham.</p>
- <h3>Awards and accolades</h3>
- <p>The film received positive reviews from critics who praised its originality, cinematography, music, and performances. The film also won three awards from eight nominations at the 4th South Indian International Movie Awards, and two awards at the 11th CineMAA Awards. The film is considered one of the "25 Greatest Telugu Films Of The Decade" by Film Companion.</p>
- <h2>Why download 1 Nenokkadine in Blu-Ray quality?</h2>
- <p>Now that you know what 1 Nenokkadine is about, you might be wondering why you should download it in Blu-Ray quality. Here are some reasons why Blu-Ray is the best format for watching movies.</p>
-<p>1 nenokkadine telugu full movie torrent yts<br />
-1 nenokkadine 2014 hindi dubbed 720p zflix co<br />
-1 nenokkadine 2014 bluray rip makemkv<br />
-1 nenokkadine movie watch online amazon prime<br />
-1 nenokkadine telugu action thriller mahesh babu<br />
-1 nenokkadine 2014 dual audio hindi telugu<br />
-1 nenokkadine movie review rating imdb<br />
-1 nenokkadine movie songs download mp3<br />
-1 nenokkadine movie subtitles download srt<br />
-1 nenokkadine movie trailer youtube<br />
-1 nenokkadine movie plot summary wikipedia<br />
-1 nenokkadine movie box office collection<br />
-1 nenokkadine movie director sukumar<br />
-1 nenokkadine movie heroine kriti sanon<br />
-1 nenokkadine movie psychological disorder amnesia<br />
-1 nenokkadine movie climax twist spoiler<br />
-1 nenokkadine movie best scenes video<br />
-1 nenokkadine movie awards and nominations<br />
-1 nenokkadine movie behind the scenes making<br />
-1 nenokkadine movie fan art posters wallpapers<br />
-1 nenokkadine movie quotes dialogues<br />
-1 nenokkadine movie memes funny jokes<br />
-1 nenokkadine movie trivia facts did you know<br />
-1 nenokkadine movie comparison with ghajini memento<br />
-1 nenokkadine movie analysis themes symbols motifs<br />
-1 nenokkadine movie streaming platforms netflix hotstar<br />
-1 nenokkadine movie download hd quality tamilrockers movierulz<br />
-1 nenokkadine movie download free no sign up filmywap filmyzilla<br />
-1 nenokkadine movie download google drive link telegram channel<br />
-1 nenokkadine movie download in parts part 1 part 2 part 3 part 4 part 5 part 6 part7 part8 part9 part10 part11 part12 part13 part14 part15 part16 part17 part18 part19 part20</p>
- <h3>Benefits of Blu-Ray format</h3>
- <ul>
-<li>Blu-Ray discs can store up to 50 GB of data, which means they can contain more information and higher resolution than DVDs or CDs.</li>
-<li>Blu-Ray discs can support up to 1080p HD video quality, which means they can deliver sharper images and more details than standard definition or even HD DVDs.</li>
-<li>Blu-Ray discs can support up to 7.1 surround sound audio quality, which means they can provide richer sound effects and more immersive audio experience than stereo or Dolby Digital sound.</li>
-<li>Blu-Ray discs can also offer interactive features such as menus, subtitles, bonus features, and online connectivity that enhance the viewing experience.</li>
-</ul>
- <h3>Comparison with other formats</h3>
- <table>
-<tr>
-<th>Format</th>
-<th>Data capacity</th>
-<th>Video resolution</th>
-<th>Audio quality</th>
-<th>Interactive features</th>
-</tr>
-<tr>
-<td>DVD</td>
-<td>4.7 GB (single layer) or 8.5 GB (dual layer)</td>
-<td>480p (SD) or 576p (PAL)</td>
-<td>Stereo or Dolby Digital 5.1</td>
-<td>Limited menus and subtitles</td>
-</tr>
-<tr>
-<td>HD DVD</td>
-<td>15 GB (single layer) or 30 GB (dual layer)</td>
-<td>720p or 1080i (HD)</td>
-<td>Dolby Digital Plus or Dolby TrueHD</td>
-<td>Limited menus and subtitles</td>
-</tr>
-<tr>
-<td>Blu-Ray</td>
-<td>25 GB (single layer) or 50 GB (dual layer)</td>
-<td>1080p (HD)</td>
-<td>Dolby Digital Plus or Dolby TrueHD or DTS-HD Master Audio</td>
-<td>Advanced menus and subtitles, bonus features, online connectivity</td>
-</tr>
-</table>
- <h3>How to play Blu-Ray discs on your devices</h3>
- <p>To play Blu-Ray discs on your devices, you will need a Blu-Ray player or a Blu-Ray drive on your computer. You will also need a compatible TV or monitor that can support HD resolution and a sound system that can support surround sound. You will also need an HDMI cable to connect your Blu-Ray player or computer to your TV or monitor.</p>
- <p>If you don't have a Blu-Ray player or drive on your computer, you can also use a software program that can play Blu-Ray discs on your computer. Some examples of such software are VLC Media Player , PowerDVD , WinDVD , etc. However, you will still need a compatible TV or monitor and a sound system to enjoy the full benefits of Blu-Ray quality.</p>
- <h2>How to download 1 Nenokkadine in Blu-Ray rip quality?</h2>
- <p>If you want to download 1 Nenokkadine in Blu-Ray rip quality instead of buying or renting a Blu-Ray disc , you will need to follow some steps and tips. However, before we get into that , we want to warn you about some legal and ethical issues related to downloading movies online.</p>
- <h3>Legal and ethical issues of downloading movies</h3>
- <p>Downloading movies online without paying for them is illegal in most countries. It is considered a form of piracy , which violates the intellectual property rights of the creators and distributors of the movies. Piracy can result in legal consequences such as fines , lawsuits , or even jail time . It can also harm the movie industry by reducing its revenue and discouraging its creativity . Therefore , we do not encourage or endorse downloading movies illegally . We only provide this information for educational purposes . If you decide to download movies online , you do so at your own risk . We are not responsible for any legal or ethical problems that may arise from your actions . </p>
- <p>The best way to watch movies legally online is to use legitimate streaming services such as Netflix , Amazon Prime Video , Hulu , Disney+ , etc . These services offer a wide range of movies and</p> 0a6ba089eb<br />
-<br />
-<br />
\ No newline at end of file
diff --git a/spaces/1acneusushi/gradio-2dmoleculeeditor/data/Descargar Pelicula Completa Iq Formula Para Amar.epub no te pierdas esta pelcula llena de humor y emocin.md b/spaces/1acneusushi/gradio-2dmoleculeeditor/data/Descargar Pelicula Completa Iq Formula Para Amar.epub no te pierdas esta pelcula llena de humor y emocin.md
deleted file mode 100644
index f5b8b114688e3cfb6c6c2a28e998de971eb938ca..0000000000000000000000000000000000000000
--- a/spaces/1acneusushi/gradio-2dmoleculeeditor/data/Descargar Pelicula Completa Iq Formula Para Amar.epub no te pierdas esta pelcula llena de humor y emocin.md	
+++ /dev/null
@@ -1,147 +0,0 @@
-<br />
-<h1>Descargar Pelicula Completa Iq Formula Para Amar.epub: Una comedia romántica con un toque de genialidad</h1>
- <p>Si te gustan las comedias románticas con un poco de ciencia y humor, te recomendamos que descargues la película completa Iq Formula Para Amar.epub. Esta película, estrenada en 1994, cuenta la historia de un mecánico que se enamora de la sobrina de Albert Einstein, y cómo el famoso científico y sus amigos intentan ayudarlo a conquistarla. Te contamos todo lo que necesitas saber sobre esta divertida y entrañable película, y cómo puedes descargarla en formato epub para disfrutarla en tu dispositivo favorito.</p>
- <h2>¿De qué trata la película?</h2>
- <h3>La trama: un mecánico se enamora de la sobrina de Einstein</h3>
- <p>La película se ambienta en los años 50, en Princeton, Nueva Jersey. Ed Walters (Tim Robbins) es un mecánico de automóviles que se queda prendado de Catherine Boyd (Meg Ryan), una bella y brillante matemática que resulta ser la sobrina de Albert Einstein (Walter Matthau). Ed se las arregla para conocerla y entablar una amistad con ella, pero pronto se da cuenta de que tiene un problema: Catherine está comprometida con James Moreland (Stephen Fry), un profesor arrogante y pretencioso que no la valora ni la respeta.</p>
-<h2>Descargar Pelicula Completa Iq Formula Para Amar.epub</h2><br /><p><b><b>Download</b> >> <a href="https://byltly.com/2uKwmm">https://byltly.com/2uKwmm</a></b></p><br /><br />
- <p>Ed no se rinde y decide luchar por el amor de Catherine, pero no está solo. Resulta que Einstein y sus colegas científicos (Lou Jacobi, Gene Saks y Joseph Maher) también están hartos de Moreland y quieren que Catherine sea feliz con alguien más. Así que deciden intervenir en el asunto y hacer pasar a Ed por un genio de la física, usando sus conocimientos y sus trucos para impresionar a Catherine y a su familia. Pero el plan no será tan fácil como parece, y habrá muchos obstáculos y enredos por el camino.</p>
- <h3>Los personajes: Tim Robbins, Meg Ryan y Walter Matthau</h3>
- <p>La película cuenta con un reparto de lujo, encabezado por Tim Robbins, Meg Ryan y Walter Matthau. Tim Robbins interpreta a Ed Walters, el simpático y honesto mecánico que se enamora perdidamente de Catherine. Robbins logra transmitir el carisma y la ternura de su personaje, así como su ingenio y su valentía para enfrentarse a los desafíos que le plantea el amor. Meg Ryan interpreta a Catherine Boyd, la inteligente y hermosa matemática que vive a la sombra de su tío Einstein. Ryan consigue darle a su personaje una mezcla de dulzura y determinación, así como una evolución desde la inseguridad hasta la confianza en sí misma. Walter Matthau interpreta a Albert Einstein, el genial y excéntrico científico que quiere lo mejor para su sobrina. Matthau hace una magnífica interpretación del famoso físico, mostrando su humor, su sabiduría y su humanidad.</p>
- <h3>El director: Fred Schepisi</h3>
- <p>La película está dirigida por Fred Schepisi, un cineasta australiano que ha trabajado en diversos géneros y países. Schepisi ha dirigido películas como Roxanne (1987), Seis grados de separación (1993) o La última orden (2011), entre otras. Schepisi demuestra su habilidad para combinar el romance, la comedia y el drama en esta película, creando una atmósfera cálida y divertida, pero también emotiva y profunda. Schepisi también cuida los aspectos técnicos de la película, como la fotografía, el vestuario o la música, recreando con fidelidad la época en la que se ambienta.</p>
- <h2>¿Por qué descargar la película en formato epub?</h2>
- <h3>Las ventajas del formato epub</h3>
- <p>Si quieres ver esta película en tu dispositivo móvil o tu ordenador, te recomendamos que la descargues en formato epub. El formato epub es un formato estándar para libros electrónicos que tiene muchas ventajas sobre otros formatos como el pdf o el mp4. Algunas de estas ventajas son:</p>
- <ul>
-<li>El formato epub es compatible con casi todos los dispositivos y aplicaciones de lectura electrónica.</li>
-<li>El formato epub permite ajustar el tamaño y el tipo de letra, el brillo, el contraste o el color de fondo según tus preferencias.</li>
-<li>El formato epub se adapta al tamaño y la orientación de tu pantalla, lo que facilita la lectura y evita tener que hacer zoom o desplazarte.</li>
-<li>El formato epub tiene una menor ocupación de espacio que otros formatos, lo que te permite almacenar más archivos en tu memoria.</li>
-<li>El formato epub conserva mejor la calidad de imagen y sonido que otros formatos comprimidos.</li>
-</ul>
- <h3>Los sitios web donde se puede descargar la película</h3>
- <p>Ahora que ya sabes las ventajas del formato epub, te preguntarás dónde puedes descargar la película completa Iq Formula Para Amar.epub. Hay muchos sitios web donde puedes encontrar esta película en este formato, pero no todos son seguros ni legales. Por eso te recomendamos que uses solo sitios web confiables y autorizados para descargar esta película. Algunos de estos sitios web son:</p>
- <table>
-<tr>
-<th>Sitio web</th>
-<th>Ventajas</th>
-<th>Inconvenientes</th>
-</tr>
-<tr>
-<td><a href="https://www.amazon.com/I-Q-Tim-Robbins/dp/B000I9TY5W">Amazon.com</a></td>
-<td>- Es uno de los sitios web más populares y fiables para comprar libros electrónicos.<br>- Ofrece una gran variedad de títulos y géneros.<br>- Tiene precios competitivos y ofertas frecuentes.<br>- Permite leer los libros electrónicos en cualquier dispositivo con la aplicación Kindle.</td>
-<td>- Hay que pagar por cada libro electrónico que se quiera descargar.<br>- No todos los libros electrónicos están disponibles en todos los países.<br>- No todos los libros electrónicos tienen una buena calidad o una buena traducción.</td>
-</tr>
-<tr>
-<td><a href="https://www.bajui.com/descarga/13363/iq-formula-para-amar">Bajui.com</a></td>
-<td>- Es uno de los sitios web más conocidos y usados para descargar películas gratis.<br>- Ofrece una gran cantidad de películas en diferentes formatos e idiomas.<br>- Tiene una interfaz sencilla e intuitiva.<br>- Permite ver las películas online o descargarlas al ordenador.</td>
-<td>- No es un sitio web legal ni seguro.<br>- Puede contener virus o malware.<br>- Puede violar los derechos de autor o las normas de propiedad intelectual.<br>- Puede tener problemas con las descargas o las reproducciones.</td>
-</tr>
-<tr>
-<h3>Los requisitos para ver la película en epub</h3>
- <p>Para poder ver la película completa Iq Formula Para Amar.epub en tu dispositivo, necesitas cumplir algunos requisitos. Estos son:</p>
- <ul>
-<li>Tener un dispositivo compatible con el formato epub, como un ordenador, una tablet, un smartphone o un lector de libros electrónicos.</li>
-<li>Tener una aplicación o un programa que pueda reproducir archivos epub, como Calibre, Adobe Digital Editions, iBooks o Kindle.</li>
-<li>Tener una conexión a internet para poder descargar la película desde el sitio web que elijas.</li>
-<li>Tener espacio suficiente en tu memoria para almacenar el archivo epub, que suele tener un tamaño de unos pocos megabytes.</li>
-</ul>
- <p>Si cumples estos requisitos, podrás disfrutar de la película en formato epub sin problemas.</p>
-<p>Descargar I.Q. El Genio del Amor en Latino<br />
-Ver IQ Fórmula para amar Online HD<br />
-El genio del amor 1994 Película Online Gratis HD<br />
-Formula Para Amar 1994 Comedia Romántica<br />
-I.Q. 1994 Película Completa en Castellano<br />
-Descargar El genio del amor Torrent<br />
-Ver Película I.Q. Fórmula para amar Gratis<br />
-El genio del amor película de Meg Ryan y Tim Robbins<br />
-I.Q. El Genio del Amor Fred Schepisi<br />
-Descargar Película I.Q. en Español Latino<br />
-Ver IQ Fórmula para amar Subtitulada<br />
-El genio del amor con Walter Matthau como Einstein<br />
-I.Q. 1994 Película de Amor y Ciencia<br />
-Descargar El genio del amor Mega<br />
-Ver Película I.Q. Online Sin Cortes<br />
-El genio del amor 1994 DVDrip Latino<br />
-I.Q. Fórmula para amar Película Completa<br />
-El genio del amor Descarga Directa<br />
-Ver Película I.Q. Gratis en HD<br />
-El genio del amor 1994 Audio Latino<br />
-I.Q. El Genio del Amor Película de Comedia<br />
-Descargar El genio del amor por Mediafire<br />
-Ver Película I.Q. Fórmula para amar en Netflix<br />
-El genio del amor 1994 Reparto y Sinopsis<br />
-I.Q. El Genio del Amor Crítica y Opiniones<br />
-Descargar El genio del amor 1080p Latino<br />
-Ver Película I.Q. Fórmula para amar en Youtube<br />
-El genio del amor 1994 Trailer Oficial<br />
-I.Q. El Genio del Amor Banda Sonora Original<br />
-Descargar El genio del amor 720p Latino<br />
-Ver Película I.Q. Fórmula para amar en Amazon Prime Video<br />
-El genio del amor 1994 Curiosidades y Anécdotas<br />
-I.Q. El Genio del Amor Premios y Nominaciones<br />
-Descargar El genio del amor DVDRip Latino<br />
-Ver Película I.Q. Fórmula para amar en Hulu<br />
-El genio del amor 1994 Escenas Eliminadas<br />
-I.Q. El Genio del Amor Frases y Diálogos<br />
-Descargar El genio del amor BluRay Rip Latino<br />
-Ver Película I.Q. Fórmula para amar en Disney Plus<br />
-El genio del amor 1994 Imágenes y Fotos<br />
-I.Q. El Genio del Amor Guion Original<br />
-Descargar El genio del amor HD Latino<br />
-Ver Película I.Q. Fórmula para amar en HBO Max<br />
-El genio del amor 1994 Cartel y Póster<br />
-I.Q. El Genio del Amor Edición Especial</p>
- <h2>¿Qué opinan los críticos y el público de la película?</h2>
- <h3>Las reseñas positivas de la película</h3>
- <p>La película Iq Formula Para Amar ha recibido muchas reseñas positivas de los críticos y el público que la han visto. Algunas de estas reseñas son:</p>
- <blockquote>
-<p>"Una comedia romántica inteligente y encantadora, con un reparto estelar y una historia original y divertida. Tim Robbins y Meg Ryan tienen una química irresistible, y Walter Matthau está genial como Einstein. Una película que te hará reír y soñar".</p>
-<cite>Roger Ebert, Chicago Sun-Times</cite>
-</blockquote>
- <blockquote>
-<p>"Una película deliciosa y entrañable, que combina el humor, el amor y la ciencia de una forma magistral. La película tiene un ritmo ágil y una dirección impecable, y los actores están fantásticos en sus papeles. Una película que te hará pasar un buen rato".</p>
-<cite>Janet Maslin, The New York Times</cite>
-</blockquote>
- <blockquote>
-<p>"Una película que te sorprenderá por su originalidad y su ternura. La película tiene un guion ingenioso y unos diálogos chispeantes, y los actores hacen un trabajo maravilloso. Walter Matthau está sublime como Einstein, y Tim Robbins y Meg Ryan forman una pareja adorable. Una película que te enamorará".</p>
-<cite>Leonard Maltin, Entertainment Tonight</cite>
-</blockquote>
- <h3>Las reseñas negativas de la película</h3>
- <p>La película Iq Formula Para Amar también ha recibido algunas reseñas negativas de los críticos y el público que la han visto. Algunas de estas reseñas son:</p>
- <blockquote>
-<p>"Una comedia romántica tonta y aburrida, con un argumento absurdo y unos personajes planos. Tim Robbins y Meg Ryan no tienen ninguna gracia ni carisma, y Walter Matthau está desaprovechado como Einstein. Una película que te hará bostezar y mirar el reloj".</p>
-<cite>Peter Travers, Rolling Stone</cite>
-</blockquote>
- <blockquote>
-<p>"Una película decepcionante y predecible, que desperdicia una idea interesante y un reparto de lujo. La película tiene un tono cursi e infantil, y los actores están sobreactuados y poco creíbles. Walter Matthau hace una caricatura de Einstein, y Tim Robbins y Meg Ryan no tienen química ni encanto. Una película que te hará perder el tiempo".</p>
-<cite>Rita Kempley, The Washington Post</cite>
-</blockquote>
- <blockquote>
-<p>"Una película mediocre y olvidable, que no aprovecha ni el humor ni el romance ni la ciencia. La película tiene un guion flojo y unos diálogos insulsos, y los actores están desganados y sin gracia. Walter Matthau está irreconocible como Einstein, y Tim Robbins y Meg Ryan no tienen ni chispa ni emoción. Una película que te hará arrepentirte de haberla visto".</p>
-<cite>Owen Gleiberman, Entertainment Weekly</cite>
-</blockquote>
- <h3>El impacto cultural de la película</h3>
- <p>A pesar de las reseñas negativas, la película Iq Formula Para Amar ha tenido un impacto cultural considerable desde su estreno. La película ha sido vista por millones de personas en todo el mundo, y ha sido nominada a varios premios, como el Globo de Oro al mejor actor de comedia o musical para Walter Matthau. La película también ha sido referenciada o parodiada en otros medios, como series de televisión, cómics o videojuegos. Algunos ejemplos son:</p>
- <ul>
-<li>En la serie Los Simpson, en el episodio "La guerra secreta de Lisa Simpson", Bart ve la película en clase de ciencias y se burla de ella.</li>
-<li>En la serie Futurama, en el episodio "El gran golpe de Bender", Bender se disfraza de Einstein para engañar a Fry.</li>
-<li>En el cómic Calvin y Hobbes, en la tira del 15 de febrero de 1995, Calvin le pregunta a Hobbes si cree que Einstein se enamoró alguna vez.</li>
-<li>En el videojuego Half-Life 2, en el capítulo "Una trampa rota", hay un científico llamado Isaac Kleiner que tiene un aspecto similar al de Einstein.</li>
-</ul>
- <h2>Conclusión</h2>
- <p>Iq Formula Para Amar es una comedia romántica con un toque de genialidad que te hará pasar un rato divertido y emocionante. La película cuenta la historia de un mecánico que se enamora de la sobrina de Einstein, y cómo el científico y sus amigos intentan ayudarlo a conquistarla. La película tiene un reparto excelente encabezado por Tim Robbins, Meg Ryan y Walter Matthau, y una dirección impecable por parte de Fred Schepisi. La película ha recibido tanto reseñas positivas como negativas por parte de los críticos y el público, pero ha tenido un impacto cultural notable desde su estreno.</p>
- <p>Si quieres ver esta película en tu dispositivo móvil o tu ordenador, te recomendamos que la descargues en formato epub desde alguno de los sitios web confiables y autorizados que te hemos mencionado. El formato epub tiene muchas ventajas sobre otros formatos como el pdf o el mp4, ya que te permite ajustar la lectura a tus preferencias y conserva mejor la calidad de imagen y sonido.</p>
- <p>No esperes más y descarga ya la película completa Iq Formula Para Amar.epub para disfrutarla cuando quieras.</p>
- <h2>Preguntas frecuentes</h2>
- <ul>
-<li><strong>¿Qué significa el título Iq Formula Para Amar?</strong><br>El título hace referencia al coeficiente intelectual (IQ) que se supone que mide la inteligencia de las personas. En la película se juega con la idea de que Ed tiene un IQ muy alto gracias a las ayudas de Einstein y sus amigos.</li>
-<li><strong>¿Qué relación tiene Einstein con Catherine?</strong><br>Einstein es el tío materno de Catherine. Su madre era hermana del científico.</li>
-<li><strong>¿Qué es un magnet link?</strong><br>Un magnet link es un tipo especial de enlace que permite descargar archivos torrent sin necesidad de tener un archivo físico. Los magnet links contienen información sobre el nombre del archivo, su tamaño o su código hash.</li>
-<li><strong>¿Qué es Calibre?</strong><br>Calibre es una aplicación gratuita y multiplataforma que permite gestionar libros electrónicos en diferentes formatos. Con Calibre se puede organizar una biblioteca digital, convertir libros a otros formatos o sincronizarlos con dispositivos externos.</li>
-<li><strong>¿Qué otros libros o películas hay sobre Einstein?</strong><br>Einstein ha sido protagonista o personaje secundario de muchos libros o películas a lo largo de la historia. Algunos ejemplos son: El universo en una cáscara de nuez (Stephen Hawking), Einstein: su vida y su universo (Walter Isaacson), Genius (serie biográfica), El joven Einstein (película cómica) o IQ (película romántica).</li>
-</ul>
- </p> 0a6ba089eb<br />
-<br />
-<br />
\ No newline at end of file
diff --git a/spaces/1gistliPinn/ChatGPT4/Examples/Aescripts StageTool 1.3.md b/spaces/1gistliPinn/ChatGPT4/Examples/Aescripts StageTool 1.3.md
deleted file mode 100644
index 2e09112299242a7246f1d13940cdd972c553bf1f..0000000000000000000000000000000000000000
--- a/spaces/1gistliPinn/ChatGPT4/Examples/Aescripts StageTool 1.3.md	
+++ /dev/null
@@ -1,39 +0,0 @@
-<br />
-`<h1>Aescripts StageTool 1.3: A Powerful Tool for Creating Pixel Mappings in After Effects</h1>`
-
-`<p>If you are a VJ who wants to create stunning pixel mappings for your performances, you might be interested in Aescripts StageTool 1.3. This is a plugin for Adobe After Effects that lets you easily create and position LED slices to match your stage, and export them to Resolume Arena 5, 6 and 7.</p>`
-
-`<p>With Aescripts StageTool 1.3, you can:</p>
-<h2>Aescripts StageTool 1.3</h2><br /><p><b><b>Download</b> &rArr; <a href="https://imgfil.com/2uxZyY">https://imgfil.com/2uxZyY</a></b></p><br /><br />`
-
-`<ul>`
-`<li>Create multiple output compositions with different resolutions and aspect ratios.</li>`
-`<li>Specify the properties of each slice, such as width, height, gap, rotation, color and logo.</li>`
-`<li>Use negative tiles to remove unwanted parts from your slice.</li>`
-`<li>Get live feedback of your slice with checkerboard, outlines, cross indicator and more.</li>`
-`<li>Screenshot your mask, input and output compositions for easy reference.</li>`
-`<li>Export XML files to Resolume Arena with rectangle masks included.</li>`
-`</ul>`
-
-`<p>Aescripts StageTool 1.3 is compatible with After Effects CC 2018 and above. It requires a license that costs $56.00. You can also try it for free with some limitations, such as a maximum of 3 slices and no export function.</p>`
-
-`<p>To learn more about Aescripts StageTool 1.3 and see some examples of pixel mappings created with it, you can visit the official website[^1^] or watch the tutorial video[^2^].</p>`
-
-`<p>Pixel mapping is a technique that allows you to control individual pixels or groups of pixels on a LED screen or panel. By using pixel mapping, you can create dynamic and colorful patterns, animations and effects that enhance your VJ performances and visuals.</p>`
-
-`<p>Pixel mapping can be done in 2D or 3D, depending on the shape and layout of your LED screen or panel. You can use pixel mapping to create flat or curved surfaces, as well as volumetric shapes and structures. Pixel mapping can also be combined with video mapping, projection mapping and lighting effects to create immersive and interactive environments.</p>`
-
-`<p>To use pixel mapping, you need a software that can generate and send pixel data to your LED screen or panel. Aescripts StageTool 1.3 is one of the best options for pixel mapping in After Effects. It allows you to create pixel mappings with ease and flexibility, and export them to Resolume Arena, a popular VJ software that can play back your pixel mappings in real time.</p>`
-
-`<p>Some examples of pixel mapping applications are:</p>
-<p></p>`
-
-`<ul>`
-`<li>Creating 1:1 pixel mappings for LCD monitors and plasma displays, which avoids loss of sharpness and incorrect aspect ratio due to scaling and stretching[^1^].</li>`
-`<li>Creating DMX pixel mappings for LED screens and panels, which enables users to control individual pixels or groups of pixels with different colors and effects[^2^].</li>`
-`<li>Creating bitmap pixel mappings for digital images, which allows users to store and manipulate pixels with different bits and channels[^3^].</li>`
-`</ul>`
-
-`<p>Pixel mapping is a versatile and creative technique that can be used for various purposes and projects. Whether you want to create simple or complex pixel mappings, Aescripts StageTool 1.3 can help you achieve your goals with ease and efficiency.</p>` d5da3c52bf<br />
-<br />
-<br />
\ No newline at end of file
diff --git a/spaces/1pelhydcardo/ChatGPT-prompt-generator/assets/Aprende a conseguir gemas infinitas en Clash Royale con Apkteca. com.md b/spaces/1pelhydcardo/ChatGPT-prompt-generator/assets/Aprende a conseguir gemas infinitas en Clash Royale con Apkteca. com.md
deleted file mode 100644
index 7d2441d9c76cb87ea23fbd9f279940d3fd399ceb..0000000000000000000000000000000000000000
--- a/spaces/1pelhydcardo/ChatGPT-prompt-generator/assets/Aprende a conseguir gemas infinitas en Clash Royale con Apkteca. com.md	
+++ /dev/null
@@ -1,158 +0,0 @@
-<br />
-<h1>Clash Royale: A Guide to the Ultimate Strategy Game</h1>
-<p>If you are looking for a fun, addictive, and competitive multiplayer game that combines strategy, cards, and real-time battles, then you should definitely try Clash Royale. This game is developed by Supercell, the same company that created the popular Clash of Clans. In this guide, we will tell you everything you need to know about Clash Royale, from the basics of the game to the advanced tips and tricks that will help you win more battles and trophies. We will also show you how to use Clash Royale mod apk to get unlimited gems and coins, as well as the benefits and risks of doing so. Let's get started!</p>
-<h2>apkteca. com clash royale gemas infinitas</h2><br /><p><b><b>Download File</b> &#8250;&#8250;&#8250;&#8250;&#8250; <a href="https://urlin.us/2uSTfI">https://urlin.us/2uSTfI</a></b></p><br /><br />
- <h2>What is Clash Royale?</h2>
-<p>Clash Royale is a real-time strategy game that features your favorite characters from Clash of Clans, as well as many new ones. The game is set in a fantasy world where you can collect and upgrade dozens of cards that represent different troops, spells, buildings, and heroes. You can use these cards to build your own battle deck and challenge other players from around the world in fast-paced matches that last for three minutes. The goal is to destroy your opponent's three crown towers, or at least more than they destroy yours, before the time runs out.</p>
- <h3>The basics of the game</h3>
-<p>The game is divided into several arenas, each with a different theme and difficulty level. You start in the Training Camp, where you can learn the basic mechanics of the game and unlock some common cards. As you win battles and trophies, you can progress to higher arenas and unlock more cards, as well as chests, gold, gems, and other rewards. You can also lose trophies if you lose battles, so be careful not to drop too low.</p>
-<p>The game uses a resource called elixir, which is generated automatically over time. You need elixir to play cards from your hand, which have different costs depending on their rarity and power. You can have up to four cards in your hand at a time, and you can draw a new card from your deck whenever you play one. You can also cycle your cards by playing them in the back of your arena, but be careful not to waste elixir or leave yourself vulnerable.</p>
- <h3>The main features of the game</h3>
-<p>Clash Royale has many features that make it an exciting and diverse game. Some of them are:</p>
-<p>apkteca. com clash royale hack gemas ilimitadas<br />
-apkteca. com clash royale mod apk gemas gratis<br />
-apkteca. com clash royale descargar con gemas infinitas<br />
-apkteca. com clash royale trucos para conseguir gemas<br />
-apkteca. com clash royale como tener gemas infinitas<br />
-apkteca. com clash royale actualizado con gemas infinitas<br />
-apkteca. com clash royale servidor privado gemas infinitas<br />
-apkteca. com clash royale apk modificado con gemas infinitas<br />
-apkteca. com clash royale generador de gemas online<br />
-apkteca. com clash royale hackear el juego con gemas infinitas<br />
-apkteca. com clash royale descargar ultima version con gemas infinitas<br />
-apkteca. com clash royale obtener gemas gratis sin verificacion<br />
-apkteca. com clash royale como hackear el juego con gemas infinitas<br />
-apkteca. com clash royale descargar gratis para android con gemas infinitas<br />
-apkteca. com clash royale como conseguir gemas rapido y facil<br />
-apkteca. com clash royale descargar mod apk con gemas ilimitadas<br />
-apkteca. com clash royale como instalar el juego con gemas infinitas<br />
-apkteca. com clash royale como jugar con gemas infinitas sin root<br />
-apkteca. com clash royale descargar hack apk con gemas ilimitadas<br />
-apkteca. com clash royale como ganar gemas gratis en el juego<br />
-apkteca. com clash royale descargar para pc con gemas infinitas<br />
-apkteca. com clash royale como descargar el juego con gemas infinitas<br />
-apkteca. com clash royale como obtener gemas infinitas sin hack<br />
-apkteca. com clash royale descargar para ios con gemas infinitas<br />
-apkteca. com clash royale como tener gemas gratis sin descargar nada<br />
-apkteca. com clash royale descargar apk hackeado con gemas ilimitadas<br />
-apkteca. com clash royale como conseguir gemas gratis sin encuestas<br />
-apkteca. com clash royale descargar para tablet con gemas infinitas<br />
-apkteca. com clash royale como tener gemas infinitas en el juego<br />
-apkteca. com clash royale descargar apk mod con gemas ilimitadas<br />
-apkteca. com clash royale como conseguir gemas gratis sin root<br />
-apkteca. com clash royale descargar para celular con gemas infinitas<br />
-apkteca. com clash royale como tener gemas gratis en el juego<br />
-apkteca. com clash royale descargar apk original con gemas infinitas<br />
-apkteca. com clash royale como conseguir gemas gratis sin hackear<br />
-apkteca. com clash royale descargar para laptop con gemas infinitas<br />
-apkteca. com clash royale como tener gemas gratis y rapido<br />
-apkteca. com clash royale descargar apk actualizado con gemas ilimitadas<br />
-apkteca. com clash royale como conseguir gemas gratis sin descargar nada<br />
-apkteca. com clash royale descargar para windows con gemas infinitas<br />
-apkteca. com clash royale como tener gemas gratis y facilmente</p>
-<ul>
-<li><b>Real-time multiplayer battles:</b> You can battle against players from all over the world in real-time matches that are fast, fun, and unpredictable. You can also play friendly matches with your clanmates or practice against bots.</li>
-<li><b>Card collection and upgrade:</b> You can collect over 100 cards that feature different types of units, such as melee, ranged, flying, building-targeting, splash-damaging, etc. You can also upgrade your cards to make them stronger and unlock new abilities.</li>
-<li><b>Deck building and customization:</b> You can build your own battle deck with eight cards of your choice, depending on your preferred playstyle and strategy. You can also create different decks for different game modes and situations.</li>
-<li><b>Game modes and challenges:</b> You can play different game modes and challenges that offer variety and rewards. Some of them are:</li>
-<ul>
-that contain cards, gold, gems, and other items. The higher your arena, the better the chests.</li>
-<li><b>2v2:</b> This is a mode where you can team up with another player or a friend and battle against another pair of players. You can share elixir and cards with your teammate and coordinate your moves.</li>
-<li><b>Special events:</b> These are temporary modes that have different rules and objectives, such as draft, triple elixir, sudden death, etc. You can earn special rewards and tokens by participating in these events.</li>
-<li><b>Tournaments:</b> These are custom matches that you can create or join with other players. You can set the rules, prizes, and duration of the tournaments.</li>
-<li><b>Clan wars:</b> These are clan-based competitions that last for two days. On the first day, you can play different game modes to earn clan cards and war trophies. On the second day, you can use the clan cards to build your war deck and battle against other clans.</li>
-</ul>
-</ul>
- <h2>How to play Clash Royale?</h2>
-<p>Now that you know what Clash Royale is and what it offers, let's see how you can play it and become a better player. Here are some of the most important aspects of the game that you need to master:</p>
- <h3>How to build your deck</h3>
-<p>Your deck is your main tool for winning battles. It consists of eight cards that you can choose from your card collection. You can have up to five different decks at a time, and you can switch between them before each battle. Building a good deck is not easy, but it is not impossible either. Here are some tips to help you:</p>
-<ul>
-<li><b>Balance your elixir cost:</b> Your elixir cost is the average amount of elixir that you need to play your cards. You want to have a balanced elixir cost that allows you to play your cards efficiently and not run out of elixir or have too much elixir. A good range for your elixir cost is between 3.0 and 4.5.</li>
-<li><b>Balance your card types:</b> Your card types are the categories that your cards belong to, such as troops, spells, buildings, etc. You want to have a balanced mix of card types that can deal with different situations and threats. A good rule of thumb is to have at least two spells, one building, and five troops in your deck.</li>
-<li><b>Balance your roles and synergies:</b> Your roles are the functions that your cards perform in your deck, such as win condition, support, defense, etc. You want to have a clear win condition that can deal damage to your opponent's towers, as well as support and defense cards that can protect and enhance your win condition. You also want to have synergies between your cards, which are combinations that work well together and create positive elixir trades or tower damage.</li>
-</ul>
- <h4>The best cards for each arena</h4>
-<p>The game has 13 arenas, each with its own theme and card pool. As you progress through the arenas, you will unlock new cards that can improve your deck and gameplay. However, not all cards are equally good in every arena. Some cards are more effective in lower arenas, while others are more useful in higher arenas. Here are some of the best cards for each arena:</p>
- | Arena | Best Cards | | --- | --- | | Training Camp | Giant, Musketeer, Fireball | | Goblin Stadium | Goblin Barrel, Valkyrie, Skeleton Army | | Bone Pit | Baby Dragon, Tombstone, Balloon | | Barbarian Bowl | Hog Rider, Barbarians, Cannon | | P.E.K.K.A's Playhouse | P.E.K.K.A., Wizard, Zap | | Spell Valley | Fire Spirits, Furnace, Poison | | Builder's Workshop | Miner, Mortar, Tesla | | Royal Arena | Elite Barbarians, Royal Giant, Mega Minion | | Frozen Peak | Ice Spirit, Ice Golem, Bowler | Executioner | | Hog Mountain | Tornado, Royal Hogs, Inferno Dragon | | Electro Valley | Electro Wizard, Sparky, Zappies | | Spooky Town | Skeleton Barrel, Witch, Graveyard | | Legendary Arena | Lava Hound, Night Witch, The Log | <h4>The best decks for different game modes</h4>
-<p>The game has different game modes that require different strategies and decks. Some of the most popular game modes are:</p>
-<ul>
-<li><b>Classic and Grand Challenges:</b> These are modes where you can pay gems to enter and win up to 12 matches before losing three. You can win huge rewards and cards by completing these challenges. The best decks for these modes are usually meta decks that are proven to be effective and consistent in the current game state. You can find these decks on websites like <a href="">RoyaleAPI</a> or <a href="">Deck Shop</a>.</li>
-<li><b>Draft:</b> This is a mode where you and your opponent take turns to choose from four cards each. You have to build your deck on the spot with the cards that you pick. The best decks for this mode are usually balanced decks that have a good mix of card types, roles, and synergies. You also have to pay attention to what cards your opponent picks and try to counter them.</li>
-<li><b>Triple Elixir:</b> This is a mode where you and your opponent generate elixir three times faster than normal. You have to play your cards quickly and aggressively to overwhelm your opponent. The best decks for this mode are usually heavy decks that have high-cost and high-impact cards, such as Golem, P.E.K.K.A., or Three Musketeers.</li>
-</ul>
- <h3>How to win battles</h3>
-<p>Winning battles in Clash Royale is not only about having a good deck, but also about knowing how to play it well. You have to be smart, fast, and adaptable to the changing situations of the game. Here are some tips to help you win more battles:</p>
-<ul>
-<li><b>Know your win condition:</b> Your win condition is the card or combination of cards that can deal the most damage to your opponent's towers. You have to know what your win condition is and how to use it effectively. You also have to know what your opponent's win condition is and how to stop it or prevent it.</li>
-<li><b>Manage your elixir:</b> Your elixir is your most valuable resource in the game. You have to use it wisely and efficiently. You have to avoid wasting elixir or overcommitting elixir on unnecessary or risky moves. You also have to try to gain an elixir advantage over your opponent by making positive elixir trades or applying pressure.</li>
-<li><b>Control the tempo:</b> The tempo is the pace and rhythm of the game. You have to control the tempo by dictating when and where the action happens. You have to adapt your tempo according to your deck and your opponent's deck. You can play fast or slow, aggressive or defensive, depending on what suits you best.</li>
-<li><b>Use the right placement and timing:</b> The placement and timing of your cards can make a huge difference in the outcome of the game. You have to use the right placement and timing for your cards to maximize their potential and minimize their weaknesses. You also have to use the right placement and timing for your spells to hit as many targets as possible or avoid hitting your own units.</li>
-</ul>
- <h4>The best tips and tricks for attacking and defending</h4>
-<p>Attacking and defending are the two main aspects of the game that you have to master. Here are some of the best tips and tricks for attacking and defending:</p>
-<ul>
-<li><b>Attacking tips:</b></li>
-<ul>
-<li><b>Use split pushes:</b> A split push is when you attack both lanes at the same time with different units. This can confuse your opponent and force them to split their defense or choose one lane to defend.</li>
-<li><b>Use counter pushes:</b> A counter push is when you use the surviving units from your defense to launch an attack on the opposite lane. This can catch your opponent off guard and create a strong push with minimal elixir.</li>
-<li><b>Use prediction spells:</b> A prediction spell is when you cast a spell on a spot where you expect your opponent to play a card before they actually do. This can surprise your opponent and give you an edge in the battle.</li>
-</ul>
-<li><b>Defending tips:</b></li>
-<ul>
-Use kiting and pulling:</b> Kiting and pulling are techniques that involve using a low-cost or fast-moving unit to lure your opponent's units away from your tower or into the range of your other units or spells. This can help you deal with high-damage or tanky units more easily.</li>
-<li><b>Use distractions and diversions:</b> Distractions and diversions are techniques that involve using a cheap or expendable unit to distract your opponent's units from attacking your tower or your main defense. This can help you buy time or reduce damage from your opponent's push.</li>
-<li><b>Use the king tower activation:</b> The king tower activation is when you use a card or a spell to make your opponent's unit hit your king tower, which is normally inactive until it is damaged. This can help you activate your king tower, which will provide extra damage and defense for the rest of the game.</li>
-</ul>
-</ul>
- <h4>The best strategies for different archetypes and matchups</h4>
-<p>The game has different archetypes, which are categories of decks that have similar characteristics and playstyles. Some of the most common archetypes are:</p>
-<ul>
-<li><b>Beatdown:</b> These are decks that rely on building a big push with a tanky unit, such as Golem or Giant, and supporting it with other units and spells. They are good at breaking through defenses and taking down towers, but they are weak against fast and cheap decks that can outcycle and pressure them.</li>
-<li><b>Cycle:</b> These are decks that rely on cycling through their cards quickly and playing them at the right moment. They are good at applying constant pressure and chip damage, but they are weak against heavy and splash decks that can counter their units easily.</li>
-<li><b>Control:</b> These are decks that rely on controlling the tempo and elixir of the game and playing defensively until they can launch a counterattack. They are good at defending and making positive elixir trades, but they are weak against siege and spell decks that can bypass their defense.</li>
-<li><b>Siege:</b> These are decks that rely on using long-range units, such as X-Bow or Mortar, to attack the opponent's towers from their side of the arena. They are good at keeping a distance and punishing mistakes, but they are weak against beatdown and swarm decks that can overwhelm them.</li>
-</ul>
-<p>The game also has different matchups, which are combinations of archetypes that face each other in a battle. Some matchups are favorable, meaning that one archetype has an advantage over another, while others are unfavorable, meaning that one archetype has a disadvantage over another. Here are some examples of favorable and unfavorable matchups:</p>
- | Favorable Matchups | Unfavorable Matchups | | --- | --- | | Beatdown vs Control | Beatdown vs Cycle | | Cycle vs Siege | Cycle vs Control | | Control vs Siege | Control vs Beatdown | | Siege vs Beatdown | Siege vs Cycle | <h2>How to get more out of Clash Royale?</h2>
-<p>Clash Royale is a game that offers a lot of content and features for its players. However, there are some ways to get even more out of the game, such as joining a clan, unlocking seasonal rewards, and using magic items. There is also a way to get unlimited gems and coins by using Clash Royale mod apk, which is a modified version of the game that allows you to access premium features for free. Let's see how you can do these things:</p>
- <h3>How to join a clan and participate in clan wars</h3>
-<p>A clan is a group of players that can chat, donate cards, request cards, and play together in clan wars. Joining a clan is one of the best ways to improve your skills, make friends, and get more rewards. You can join a clan by searching for one in the game or by accepting an invitation from another player. You can also create your own clan if you have enough gems.</p>
-<p>A clan war is a clan-based competition that lasts for two days. On the first day, you can play different game modes to earn clan cards and war trophies. On the second day, you can use the clan cards to build your war deck and battle against other clans. You can earn war chests, gold, gems, and other rewards by winning clan wars.</p>
- <h3>How to unlock and use seasonal rewards and magic items</h3>
-royale, which is a premium feature that gives you access to exclusive rewards and perks, such as unlimited entries, queue chests, and strike chests.</p>
-<p>A magic item is a special item that can help you upgrade your cards faster and easier. There are different types of magic items, such as books, chests, tokens, and wild cards. You can get magic items by opening chests, completing quests, participating in events, or buying them with gems.</p>
- <h3>How to use Clash Royale mod apk for unlimited gems and coins</h3>
-<p>Gems and coins are the two main currencies in the game. Gems can be used to buy chests, cards, gold, passes, emotes, and other items. Coins can be used to upgrade your cards and buy cards from the shop. You can earn gems and coins by playing the game, opening chests, completing quests, or buying them with real money.</p>
-<p>However, if you want to get unlimited gems and coins for free, you can use Clash Royale mod apk, which is a modified version of the game that gives you access to unlimited resources and features. Here are some of the benefits and risks of using mod apk:</p>
- <h4>The benefits and risks of using mod apk</h4>
-<p>Using mod apk can have some benefits, such as:</p>
-<ul>
-<li><b>You can get unlimited gems and coins:</b> This can help you unlock and upgrade all the cards in the game, as well as buy anything you want from the shop or the pass royale.</li>
-<li><b>You can get unlimited resources and features:</b> This can help you enjoy the game without any limitations or restrictions. You can play any game mode or challenge as many times as you want, as well as use any card or deck that you like.</li>
-<li><b>You can have more fun and excitement:</b> This can help you explore the game in a new way and experience new things that you might not be able to do in the original version of the game.</li>
-</ul>
-<p>However, using mod apk can also have some risks, such as:</p>
-<ul>
-<li><b>You can get banned from the game:</b> This is the most serious risk of using mod apk. Supercell, the developer of the game, has a strict policy against cheating and hacking. If they detect that you are using mod apk or any other unauthorized software, they can ban your account permanently and prevent you from playing the game ever again.</li>
-<li><b>You can get viruses or malware on your device:</b> This is another serious risk of using mod apk. Some of the sources that provide mod apk may not be safe or reliable. They may contain viruses or malware that can harm your device or steal your personal information.</li>
-<li><b>You can lose the fun and challenge of the game:</b> This is a personal risk of using mod apk. Some of the players may feel that using mod apk takes away the fun and challenge of the game. They may feel that it is not fair or rewarding to play with unlimited resources and features that give them an unfair advantage over other players.</li>
-</ul>
- <h4>The best sources and steps for downloading and installing mod apk</h4>
-<p>If you still want to use mod apk despite the risks, you have to be careful and smart about it. You have to find a trustworthy source that provides a safe and working mod apk file. You also have to follow the right steps for downloading and installing mod apk on your device. Here are some of the best sources and steps for doing so:</p>
- | Source | Steps | | --- | --- | | <a href="">Apkteca.com</a> | 1. Go to <a href="">apkteca.com</a> on your browser.<br>2. Search for Clash Royale mod apk.<br>3. Choose the latest version of the mod apk file.<br>4. Click on the download button and wait for it to finish.<br>5. Go to your device settings and enable unknown sources.<br>6. Go to your file manager and locate the downloaded mod apk file.<br>7. Tap on it and follow the instructions to install it.<br>8. Enjoy the game with unlimited gems and coins. | the latest version of the mod apk file.<br>4. Click on the download button and wait for it to finish.<br>5. Go to your device settings and enable unknown sources.<br>6. Go to your file manager and locate the downloaded mod apk file.<br>7. Tap on it and follow the instructions to install it.<br>8. Enjoy the game with unlimited gems and coins. | | <a href="">Apkmodhub.com</a> | 1. Go to <a href="">apkmodhub.com</a> on your browser.<br>2. Search for Clash Royale mod apk.<br>3. Choose the latest version of the mod apk file.<br>4. Click on the download button and wait for it to finish.<br>5. Go to your device settings and enable unknown sources.<br>6. Go to your file manager and locate the downloaded mod apk file.<br>7. Tap on it and follow the instructions to install it.<br>8. Enjoy the game with unlimited gems and coins. | <h2>Conclusion</h2>
-<p>Clash Royale is a game that can provide you with hours of fun and entertainment, as well as challenge and satisfaction. It is a game that requires skill, strategy, and creativity, as well as luck and patience. It is a game that can be enjoyed by anyone, regardless of age, gender, or background.</p>
-<p>In this guide, we have covered everything you need to know about Clash Royale, from the basics of the game to the advanced tips and tricks that will help you win more battles and trophies. We have also shown you how to use Clash Royale mod apk to get unlimited gems and coins, as well as the benefits and risks of doing so.</p>
-<p>We hope that this guide has been helpful and informative for you, and that you have learned something new and useful from it. We also hope that you have enjoyed reading it as much as we have enjoyed writing it.</p>
-<p>Now that you have read this guide, you are ready to play Clash Royale like a pro and have a blast with it. So what are you waiting for? Download Clash Royale now and join the millions of players who are already hooked on this amazing game!</p>
- <h2>Frequently Asked Questions</h2>
-<p>Here are some of the most frequently asked questions about Clash Royale:</p>
-<ul>
-<li><b>Q: Is Clash Royale free to play?</b><br>A: Yes, Clash Royale is free to play and download on both Android and iOS devices. However, it also offers in-app purchases that can enhance your gameplay and experience.</li>
-<li><b>Q: Is Clash Royale a pay-to-win game?</b><br>A: No, Clash Royale is not a pay-to-win game. Although paying money can help you progress faster and unlock more cards and features, it does not guarantee you victory or success. You still need skill, strategy, and practice to win battles and trophies.</li>
-<li><b>Q: Is Clash Royale a fair game?</b><br>A: Yes, Clash Royale is a fair game. The game uses a matchmaking system that pairs you with players who have similar levels of trophies and cards as you. The game also uses a random card generator that ensures that both you and your opponent have equal chances of getting good or bad cards.</li>
-<li><b>Q: Is Clash Royale an online game?</b><br>A: Yes, Clash Royale is an online game that requires an internet connection to play. You cannot play Clash Royale offline or without wifi.</li>
-<li><b>Q: Is Clash Royale a safe game?</b><br>A: Yes, Clash Royale is a safe game that does not contain any harmful or inappropriate content or ads. However, you should be careful when using mod apk or other third-party software that may compromise your device or account security.</li>
-</ul></p> 197e85843d<br />
-<br />
-<br />
\ No newline at end of file
diff --git a/spaces/1pelhydcardo/ChatGPT-prompt-generator/assets/Download Garena Blockman GO and Join Millions of Players in Various Minigames.md b/spaces/1pelhydcardo/ChatGPT-prompt-generator/assets/Download Garena Blockman GO and Join Millions of Players in Various Minigames.md
deleted file mode 100644
index 0822a2ba94d9915b87b97f43f1936d4635b64c01..0000000000000000000000000000000000000000
--- a/spaces/1pelhydcardo/ChatGPT-prompt-generator/assets/Download Garena Blockman GO and Join Millions of Players in Various Minigames.md	
+++ /dev/null
@@ -1,116 +0,0 @@
-
-<h1>How to Download Garena Blockman GO on Your Device</h1>
-<p>If you are looking for a fun and creative sandbox game that lets you play, craft, and share your experiences with your friends, then you should check out Garena Blockman GO. This is a free-to-play game that offers a variety of minigames from different genres, as well as a powerful editor mode that allows you to create and publish your own minigames. In this article, we will show you how to download Garena Blockman GO on your device, as well as some tips and tricks to play it like a pro.</p>
- <h2>What is Garena Blockman GO?</h2>
-<p>Garena Blockman GO is the first sandbox game from Garena, a leading global online games developer and publisher. It was released in July 2021 and has already attracted millions of players from all over the world. Garena Blockman GO is inspired by popular games like Minecraft and Roblox, but it has its own unique features and style.</p>
-<h2>download garena blockman go</h2><br /><p><b><b>Download File</b> &#8230; <a href="https://urlin.us/2uT2H1">https://urlin.us/2uT2H1</a></b></p><br /><br />
-<p>In Garena Blockman GO, you can explore a wonderland of minigames that are created by other players or by yourself using the editor mode. You can join the adventures and venture into the countless minigames from all the different genres, such as action, adventure, role-playing, strategy, simulation, and more. You can also customize your avatar with creative selections of fashionable accessories, and show off your unique style to the world.</p>
-<p>Garena Blockman GO is not only a game, but also a platform where you can make friends and chat with other players. You can join a party or a clan to team up with other players, or create your own clan and invite your friends. You can also upgrade your VIP membership to enjoy more benefits and rewards, such as exclusive items, skins, badges, and more.</p>
- <h2>Features of Garena Blockman GO</h2>
-<p>Some of the features that make Garena Blockman GO stand out from other sandbox games are:</p>
-<ul>
-<li><b>Wonderland of minigames</b>: In Garena Blockman GO, there is always something new and exciting for you to discover every day. You can join the adventures and venture into the countless minigames from all the different genres. Some of the popular minigames are:   <ul>
-  <li><b>Party Street</b>: Collect graffitis from all over the city and spray it to your heart's content. You can experience this super cool street style in the Party Street and hop into a random party with all the other cool guys.</li>
-  <li><b>The Exorcists</b>: A game of survival and betrayal. As one of the 4 exorcists, you must perform an exorcism in an abandoned school. But wait! There is an imposter hidden among you… Look for clues to find the imposter and complete the exorcism ritual through various missions. Meanwhile, the imposter must hide their real identity, mislead the other exorcists with the wrong clues and summon the devil to kill all the exorcists.</li>
-  <li><b>Frontline</b>: A 30 vs 30 multiplayer battlefield shooting game. You'll take on a soldier's duty and participate in a simulated battle. To win the game, you can shoot, drive tanks and armored vehicles, direct your comrades to occupy the core areas, and cooperate with other players to secure the final victory for your team.</li>
-  <li><b>Bed Wars</b>: A popular team-based PVP game that has drawn a large number of players from all over the world. You and your teammates need to protect your bed at all costs, while trying to destroy the beds of other teams. You can collect resources, buy items, upgrade weapons, and build bridges to attack other teams. The last team standing wins the game.</li>
-  </ul>
-</li>
-<li><b>Editor mode</b>: In Garena Blockman GO, you can unleash your creativity and imagination by creating your own minigames using the editor mode. You can design the map, the rules, the characters, the items, and everything else you want. You can also share your minigames with other players and let them play and rate your creations.</li>
-<li><b>Avatar customization</b>: In Garena Blockman GO, you can customize your avatar with creative selections of fashionable accessories, such as hats, glasses, masks, clothes, shoes, and more. You can also change your avatar's appearance, such as hair color, eye color, skin tone, and more. You can show off your unique style to the world and express yourself in different ways.</li>
-<li><b>Party and clan system</b>: In Garena Blockman GO, you can make friends and chat with other players from all over the world. You can join a party or a clan to team up with other players and enjoy the minigames together. You can also create your own clan and invite your friends to join. You can chat with your clan members, send gifts, participate in clan events, and compete with other clans for glory and rewards.</li>
-<li><b>VIP membership</b>: In Garena Blockman GO, you can upgrade your VIP membership to enjoy more benefits and rewards. As a VIP member, you can get exclusive items, skins, badges, and more. You can also get more golds, diamonds, coupons, and other resources every day. You can also enjoy faster loading speed, priority access to minigames, and more privileges in the game.</li>
-</ul>
- <h2>How to Download Garena Blockman GO on Your Device</h2>
-<p>Garena Blockman GO is available for Android, iOS, and PC devices. You can download it for free from the official website or from the app stores. Here are the steps to download Garena Blockman GO on your device:</p>
- <h3>How to Download Garena Blockman GO on Android</h3>
-<p>If you have an Android device, you can download Garena Blockman GO from the Google Play Store or from the official website. Here are the steps to download Garena Blockman GO on Android:</p>
-<p>How to download garena blockman go on android<br />
-Garena blockman go apk download latest version<br />
-Garena blockman go free download for pc<br />
-Garena blockman go mod apk unlimited money download<br />
-Download garena blockman go and play with friends<br />
-Garena blockman go online game download<br />
-Garena blockman go hack download no root<br />
-Garena blockman go sandbox game download<br />
-Download garena blockman go from google play store<br />
-Garena blockman go minigames download<br />
-Garena blockman go bed wars download<br />
-Garena blockman go egg wars download<br />
-Garena blockman go sky block download<br />
-Garena blockman go party street download<br />
-Garena blockman go the exorcists download<br />
-Garena blockman go frontline download<br />
-Garena blockman go free city rp download<br />
-Download garena blockman go for ios<br />
-Download garena blockman go for windows 10<br />
-Download garena blockman go for mac<br />
-Download garena blockman go for laptop<br />
-Download garena blockman go for chromebook<br />
-Download garena blockman go for fire tablet<br />
-Download garena blockman go for kindle fire<br />
-Download garena blockman go for xbox one<br />
-Download garena blockman go for ps4<br />
-Download garena blockman go for nintendo switch<br />
-Download garena blockman go offline mode<br />
-Download garena blockman go without wifi<br />
-Download garena blockman go without ads<br />
-Download garena blockman go without vip subscription<br />
-Download garena blockman go with unlimited coins and gems<br />
-Download garena blockman go with all skins unlocked<br />
-Download garena blockman go with custom maps and mods<br />
-Download garena blockman go with voice chat and emojis<br />
-Download garena blockman go with new updates and features<br />
-Download garena blockman go with best graphics and performance<br />
-Download garena blockman go with low storage and battery usage<br />
-Download garena blockman go with easy controls and settings<br />
-Download garena blockman go with fun and creative gameplay<br />
-Garena blockman go app download review and rating<br />
-Garena blockman go game download guide and tips<br />
-Garena blockman go download error and solution<br />
-Garena blockman go download link and qr code<br />
-Garena blockman go official website and social media download<br />
-Garena blockman go alternative games to download</p>
-<ol>
-<li>Open the Google Play Store app on your Android device.</li>
-<li>Search for "Garena Blockman GO" in the search bar.</li>
-<li>Select the app from the search results and tap on "Install".</li>
-<li>Wait for the app to download and install on your device.</li>
-<li>Once the app is installed, tap on "Open" to launch it.</li>
-<li>Enjoy playing Garena Blockman GO on your Android device.</li>
-</ol>
-<p>Alternatively, you can download Garena Blockman GO from the official website by following these steps:</p>
-<ol>
-<li>Open a web browser on your Android device and go to <a href="">https://blockmango.net/</a>.</li>
-<li>Tap on the "Download" button at the top right corner of the website.</li>
-<li>Select "Android" from the options and tap on "Download APK".</li>
-<li>Wait for the APK file to download on your device.</li>
-<li>Once the APK file is downloaded, tap on it to install it.</li>
-<li>You may need to enable "Unknown sources" in your device settings to allow the installation of apps from outside sources.</li>
-<li>Once the app is installed, tap on it to launch it.</li>
-<li>Enjoy playing Garena Blockman GO on your Android device.</li>
-</ol>
- <h3>How to Download Garena Blockman GO on iOS</h3>
-<p>If you have an iOS device, you can download Garena Blockman GO from the App Store or from the official website. Here are the steps to download Garena Blockman GO on iOS:</p>
-<ol>
-<li>Open the App Store app on your iOS device.</li>
-<li>Search for "Garena Blockman GO" in the search bar.</li>
-<li>Select the app from the search results and tap on "Get".</li>
-<li>Wait for the app to download and install on your device.</li>
-<li>Once the app is installed, tap on it to launch it.</li>
-<li>Enjoy playing Garena Blockman GO on your iOS device.</li>
-</ol>
-<p>Alternatively, you can download Garena Blockman GO from the official website by following Garena Blockman GO from the official website for Android, iOS, or PC devices, you can update it by opening the app and tapping on the "Update" button at the bottom of the screen.</li>
-<li>If you have downloaded Garena Blockman GO from an emulator for PC devices, you can update it by opening the Google Play Store app in the emulator and tapping on the "Update" button next to the app name.</li>
-</ol>
-<li><b>Q: How do I delete Garena Blockman GO?</b></li>
-<li><b>A: If you want to delete Garena Blockman GO from your device, you can follow these steps:</b></li>
-<ol>
-<li>If you have downloaded Garena Blockman GO from the app stores for Android or iOS devices, you can delete it by holding down the app icon on your device screen and tapping on the "Uninstall" or "Delete" option.</li>
-<li>If you have downloaded Garena Blockman GO from the official website for Android, iOS, or PC devices, you can delete it by opening the app and tapping on the "Settings" icon at the top right corner of the screen. Then, tap on the "Uninstall" option and confirm your choice.</li>
-<li>If you have downloaded Garena Blockman GO from an emulator for PC devices, you can delete it by opening the emulator and holding down the app icon on the emulator screen. Then, tap on the "Uninstall" or "Delete" option and confirm your choice.</li>
-</ol>
-</ul>
- <p>I hope this article has helped you learn more about Garena Blockman GO and how to download it on your device. If you have any feedback or suggestions, please feel free to leave a comment below. Thank you for reading and have a great day!</p> 197e85843d<br />
-<br />
-<br />
\ No newline at end of file
diff --git a/spaces/1phancelerku/anime-remove-background/Download Raid Shadow Legends Mod APK from BlackMod and Dominate the Game.md b/spaces/1phancelerku/anime-remove-background/Download Raid Shadow Legends Mod APK from BlackMod and Dominate the Game.md
deleted file mode 100644
index c9e4cce6e11ef988578e0a34846181507217a613..0000000000000000000000000000000000000000
--- a/spaces/1phancelerku/anime-remove-background/Download Raid Shadow Legends Mod APK from BlackMod and Dominate the Game.md	
+++ /dev/null
@@ -1,96 +0,0 @@
-<br />
-<h1>Raid Shadow Legends Mod APK Blackmod: How to Download and Play</h1>
-<p>If you are a fan of fantasy RPG games, you might have heard of Raid Shadow Legends. It is a popular game that lets you collect and customize hundreds of champions, fight epic battles, and explore a vast world. But what if you want to enhance your gaming experience with some extra features? That's where Raid Shadow Legends Mod APK Blackmod comes in. In this article, we will tell you what this mod is, how to download and install it, and how to play it. Let's get started!</p>
-<h2>raid shadow legends mod apk blackmod</h2><br /><p><b><b>Download Zip</b> &#11088; <a href="https://jinyurl.com/2uNTZ0">https://jinyurl.com/2uNTZ0</a></b></p><br /><br />
-<h2>What is Raid Shadow Legends?</h2>
-<p>Raid Shadow Legends is a free-to-play mobile game developed by Plarium Global Ltd. It was released in 2018 and has since gained millions of players worldwide. The game is set in the fantasy realm of Teleria, where you can recruit and train over 500 champions from 16 factions, each with their own skills and abilities. You can use your champions to fight in various modes, such as campaign, dungeons, arena, clan boss, faction wars, and more. You can also join clans, chat with other players, and participate in events and tournaments.</p>
-<p>The game features stunning 3D graphics, realistic animations, and immersive sound effects. It also has a rich story and lore that unfolds as you progress through the game. You can play the game on your Android or iOS device, or on your PC using an emulator.</p>
-<h2>What is Blackmod?</h2>
-<p>Blackmod is a website that provides modded APKs for various games. A modded APK is a modified version of the original game file that has some changes or additions to the game features. For example, some modded APKs may offer unlimited money, gems, coins, or resources. Others may unlock all levels, characters, items, or skills. Some may even give you access to cheats, hacks, or bots.</p>
-<p>Blackmod is one of the most trusted and reliable sources of modded APKs on the internet. It has a large collection of games from different genres and categories. You can browse through the website and find the game you want to download. You can also read the description, features, screenshots, and reviews of each modded APK before downloading it.</p>
-<h2>What is Raid Shadow Legends Mod APK Blackmod?</h2>
-<p>Raid Shadow Legends Mod APK Blackmod is a modded version of Raid Shadow Legends that offers two main features: menu mod and increased battle speed. Menu mod is a feature that allows you to access a menu in the game that lets you toggle on or off various options, such as auto win, god mode, weak enemies, etc. Increased battle speed is a feature that allows you to speed up the battles by 1-10 times, which can be useful for farming, grinding, or saving time.</p>
-<p>raid shadow legends mod apk blackmod free download<br />
-raid shadow legends mod apk blackmod unlimited gems<br />
-raid shadow legends mod apk blackmod latest version<br />
-raid shadow legends mod apk blackmod no root<br />
-raid shadow legends mod apk blackmod menu mod<br />
-raid shadow legends mod apk blackmod increases battle speed<br />
-raid shadow legends mod apk blackmod reddit<br />
-raid shadow legends mod apk blackmod hack<br />
-raid shadow legends mod apk blackmod online<br />
-raid shadow legends mod apk blackmod android<br />
-raid shadow legends mod apk blackmod ios<br />
-raid shadow legends mod apk blackmod 2023<br />
-raid shadow legends mod apk blackmod update<br />
-raid shadow legends mod apk blackmod installation guide<br />
-raid shadow legends mod apk blackmod gameplay<br />
-raid shadow legends mod apk blackmod review<br />
-raid shadow legends mod apk blackmod cheats<br />
-raid shadow legends mod apk blackmod tips and tricks<br />
-raid shadow legends mod apk blackmod best champions<br />
-raid shadow legends mod apk blackmod tier list<br />
-raid shadow legends mod apk blackmod clan boss<br />
-raid shadow legends mod apk blackmod dungeons<br />
-raid shadow legends mod apk blackmod arena<br />
-raid shadow legends mod apk blackmod faction wars<br />
-raid shadow legends mod apk blackmod doom tower<br />
-raid shadow legends mod apk blackmod events and tournaments<br />
-raid shadow legends mod apk blackmod fusion guide<br />
-raid shadow legends mod apk blackmod masteries guide<br />
-raid shadow legends mod apk blackmod artifacts guide<br />
-raid shadow legends mod apk blackmod affinity guide<br />
-raid shadow legends mod apk blackmod roles guide<br />
-raid shadow legends mod apk blackmod skills guide<br />
-raid shadow legends mod apk blackmod stats guide<br />
-raid shadow legends mod apk blackmod gear guide<br />
-raid shadow legends mod apk blackmod sets guide<br />
-raid shadow legends mod apk blackmod farming guide<br />
-raid shadow legends mod apk blackmod leveling guide<br />
-raid shadow legends mod apk blackmod beginners guide<br />
-raid shadow legends mod apk blackmod advanced guide<br />
-raid shadow legends mod apk blackmod strategy guide<br />
-raid shadow legends mod apk blackmod secrets and hidden features<br />
-raid shadow legends mod apk blackmod support and feedback<br />
-raid shadow legends mod apk blackmod bugs and issues<br />
-raid shadow legends mod apk blackmod news and updates<br />
-raid shadow legends mod apk blackmod community and forums<br />
-raid shadow legends mod apk blackmod discord server<br />
-raid shadow legends mod apk blackmod youtube channel<br />
-raid shadow legends mod apk blackmod facebook page</p>
-<p>With these features, you can enjoy the game more easily and conveniently. You can breeze through the campaign mode, defeat the bosses faster, dominate the arena, and collect more rewards. You can also experiment with different champions and strategies without worrying about losing or wasting resources.</p>
-<h2>How to download and install Raid Shadow Legends Mod APK Blackmod?</h2>
-<p>To download and install Raid Shadow Legends Mod APK Blackmod, you need to follow these steps:</p>
-<ol>
-<li>Go to <a href="(^1^)">this link</a> and click on the download button.</li>
-<li>Wait for the download to finish and then open the file.</li>
-<li>If you have the original version of Raid Shadow Legends installed on your device, you need to uninstall it first. You can do this by going to your settings, apps, and selecting Raid Shadow Legends. Then, tap on uninstall and confirm.</li>
-<li>After uninstalling the original version, you need to enable the installation of unknown sources on your device. You can do this by going to your settings, security, and toggling on the unknown sources option.</li>
-<li>Now, you can install the modded APK by tapping on it and following the instructions.</li>
-<li>Once the installation is done, you can open the game and enjoy the mod features.</li>
-</ol>
-<p>Note: You may need to grant some permissions to the game, such as storage, phone, etc. You may also need to verify your device by completing a captcha or a short survey. This is to prevent bots and spam from abusing the mod.</p>
-<h2>How to play Raid Shadow Legends Mod APK Blackmod?</h2>
-<p>To play Raid Shadow Legends Mod APK Blackmod, you need to follow these tips and tricks:</p>
-<ul>
-<li>When you start the game, you will see a menu icon on the top left corner of the screen. Tap on it to open the menu mod. Here, you can enable or disable the options you want, such as auto win, god mode, weak enemies, etc. You can also adjust the battle speed by sliding the bar from 1x to 10x.</li>
-<li>Be careful when using the menu mod options, as some of them may cause the game to crash or freeze. For example, if you use auto win in arena mode, you may get stuck in a loop of winning and losing. To avoid this, you can turn off auto win before entering the arena mode.</li>
-<li>Also, be aware that using the menu mod may get you banned from the game if you are detected by the developers or reported by other players. To avoid this, you can use the menu mod sparingly and only for personal use. Do not abuse the mod features or brag about them in public chat or forums.</li>
-<li>Enjoy the game with the mod features and have fun collecting and upgrading your champions, fighting epic battles, and exploring Teleria.</li>
-</ul>
-<h2>Conclusion</h2>
-<p>Raid Shadow Legends Mod APK Blackmod is a great way to enhance your gaming experience with some extra features. You can download and install it easily from the link provided in this article. You can also play it with some tips and tricks that we shared with you. However, you should also be careful when using the mod features, as they may cause some issues or get you banned from the game. Therefore, use the mod at your own risk and discretion.</p>
-<p>If you liked this article, please share it with your friends and fellow gamers. Also, let us know what you think about Raid Shadow Legends Mod APK Blackmod in the comments below. Have fun!</p>
- <h2>FAQs</h2>
-<h3>Q: Is Raid Shadow Legends Mod APK Blackmod safe to use?</h3>
-<p>A: Raid Shadow Legends Mod APK Blackmod is safe to use as long as you download it from a trusted source and scan it with an antivirus before installing it. However, using any modded APK may pose some risks to your device or account, so use it at your own risk and discretion.</p>
-<h3>Q: Is Raid Shadow Legends Mod APK Blackmod compatible with my device?</h3>
-<p>A: Raid Shadow Legends Mod APK Blackmod is compatible with most Android devices that have Android 5.0 or higher. However, some devices may not support the mod features or run smoothly with them. Therefore, you may need to try different devices or settings to find the best performance.</p>
-<h3>Q: Can I update Raid Shadow Legends Mod APK Blackmod?</h3>
-<p>A: No, you cannot update Raid Shadow Legends Mod APK Blackmod from the Google Play Store or any other source. If you do so, you will lose the mod features and revert back to the original version of the game. To update the modded APK, you need to wait for a new version of it to be released by Blackmod or another modder.</p>
-<h3>Q: Can I play Raid Shadow Legends Mod APK Blackmod online with other players?</h3>
-<p>A: Yes, you can play Raid Shadow Legends Mod APK Blackmod online with other players who have the same version of the modded APK as you. However, you may not be able to play with players who have the original version of the game or a different version of the modded APK. Also, be careful when playing online with other players, as they may report you for using the mod features or cheat detection systems may catch you.</p>
-<h3>Q: Can I request more features for Raid Shadow Legends Mod APK Blackmod?</h3>
-<p>A A: You can request more features for Raid Shadow Legends Mod APK Blackmod by contacting the modder or the website that provides the modded APK. However, there is no guarantee that your request will be fulfilled or that the modder will update the modded APK regularly. Therefore, you may need to be patient and appreciate the features that are already available.</p> 401be4b1e0<br />
-<br />
-<br />
\ No newline at end of file
diff --git a/spaces/1phancelerku/anime-remove-background/Enjoy Retro Gaming on Your Smartphone with These Arcade Emulators for Android.md b/spaces/1phancelerku/anime-remove-background/Enjoy Retro Gaming on Your Smartphone with These Arcade Emulators for Android.md
deleted file mode 100644
index a5bf5fed825c4ea920a59198c63436b4881f4711..0000000000000000000000000000000000000000
--- a/spaces/1phancelerku/anime-remove-background/Enjoy Retro Gaming on Your Smartphone with These Arcade Emulators for Android.md	
+++ /dev/null
@@ -1,231 +0,0 @@
-
-<h1>How to Play Arcade Games on Your Android Device with Emulators</h1>
- <p>If you are a fan of retro gaming or just want to relive some of your childhood memories, you might be interested in playing arcade games on your Android device. Arcade games are video games that were originally played in coin-operated machines installed in public places such as restaurants, bars, amusement parks, etc. Some of the most popular arcade games are Pac-Man, Street Fighter II, Mortal Kombat, Donkey Kong, Space Invaders, Galaga, Metal Slug, Double Dragon, and many more. These games are known for their simple yet addictive gameplay, colorful graphics, catchy sound effects, and high scores. They are also part of the history and culture of video gaming and have influenced many modern games and genres.</p>
- <p>But how can you play these arcade games on your Android device? The answer is emulators. Emulators are software programs that can mimic the hardware and software of different systems, such as arcade machines, consoles, computers, etc. By using emulators, you can run games that were designed for other platforms on your Android device. In this article, we will show you how to use emulators to play arcade games on your Android device, what are the benefits of using emulators, what are some of the best arcade emulators for Android, how to install and use them, and what are some of the best arcade games to play on your Android device. Let's get started!</p>
-<h2>arcade emulator android</h2><br /><p><b><b>Download</b> - <a href="https://jinyurl.com/2uNJQC">https://jinyurl.com/2uNJQC</a></b></p><br /><br />
- <h2>What Are Emulators and How Do They Work?</h2>
- <p>Emulators are software programs that can simulate the hardware and software of different systems, such as arcade machines, consoles, computers, etc. Emulators can run on various devices, such as PCs, smartphones, tablets, etc. Emulators can allow you to play games that were designed for other platforms on your device. For example, you can use an emulator to play a Nintendo game on your PC or an arcade game on your Android device.</p>
- <p>But how do emulators work? Emulators work by translating the instructions and data of the original system into a format that your device can understand and execute. For example, an arcade emulator can translate the code and graphics of an arcade game into a format that your Android device can run. Emulators also have to emulate the input and output devices of the original system, such as joysticks, buttons, speakers, etc.</p>
- <p>However, emulators alone are not enough to play games. You also need ROMs and BIOS files. ROMs are files that contain the data of the game itself, such as code, graphics, sound effects, etc. BIOS files are files that contain the data of the system itself, such as firmware, settings, etc. ROMs and BIOS files are usually extracted from the original cartridges or discs of the games or systems by using special devices or software. However, you should only download ROMs and BIOS files from legal sources or dump them from your own original cartridges or discs if you own them. Downloading ROMs and BIOS files from illegal sources or without owning the original games or systems is considered piracy and may violate intellectual property rights.</p>
- <h2>What Are the Benefits of Using Emulators for Android?</h2>
- <p>Using emulators for Android has many benefits for retro gamers who want to play arcade games on their devices. Here are some of them:</p>
- <ul>
-<li><b>Convenience:</b> You don't need to buy or maintain a physical arcade machine or console to play arcade games on your Android device. You just need to download an emulator app and some ROMs and BIOS files and you are good to go. You can also play arcade games anytime and anywhere with your Android device.</li>
-<li><b>Cost-effectiveness:</b> You don't need to spend money on coins or tokens to play arcade games on your Android device. You also don't need to buy expensive cartridges or discs of arcade games or systems. You just need to download some free or cheap emulator apps and some ROMs and BIOS files from legal sources or dump them from your own original cartridges or discs if you own them.</li>
-<li><b>Nostalgia:</b> You can relive some of your childhood memories or experience some of the classic arcade games that you missed out on by playing them on your Android device. You can also enjoy the retro graphics, sound effects, and gameplay of arcade games that may not be available on modern platforms.</li>
-<li><b>Customization:</b> You can customize your gaming experience by using different emulator apps and settings. You can adjust the screen size, resolution, orientation, aspect ratio, filters, frameskip, sound volume, etc. of your emulator app according to your preferences. You can also configure the controls and buttons of your emulator app according to your comfort and convenience.</li>
-<li><b>Preservation:</b> You can preserve some of the history and culture of video gaming by playing arcade games on your Android device. Arcade games are part of the heritage and legacy of video gaming and have influenced many modern games and genres. By using emulators for Android, you can help keep these arcade games alive and accessible for future generations.</li>
-</ul>
- <h2>What Are the Best Arcade Emulators for Android?</h2>
- <p>There are many arcade emulators for Android that you can choose from, but not all of them are equally good. Some of them may have better compatibility, performance, features, or user interface than others. To help you find the best arcade emulator for your Android device, we have selected some of the most popular and reliable ones and compared their features, pros, cons, and compatibility. Here are some of the best arcade emulators for Android:</p>
- <h3>MAME4droid</h3>
- <p>MAME4droid is one of the most popular and widely used arcade emulators for Android. MAME stands for Multiple Arcade Machine Emulator, and it is a project that aims to emulate as many arcade games as possible. MAME4droid is based on the MAME 0.139u1 version, which supports over 8,000 arcade games from various systems, such as Neo Geo, CPS1, CPS2, CPS3, Sega System 16, etc. MAME4droid also supports some console games that use similar hardware as arcade games, such as Sega Genesis, Sega Master System, etc.</p>
- <p>Some of the features of MAME4droid are:</p>
- <ul>
-<li>It supports native resolution and aspect ratio for each game.</li>
-<li>It supports various input methods, such as touch screen, keyboard, gamepad, accelerometer, etc.</li>
-<li>It supports cheat codes and save states.</li>
-<li>It supports multiplayer mode via Bluetooth or Wi-Fi.</li>
-<li>It has a user-friendly interface that allows you to browse and search games by category, name, year, manufacturer, etc.</li>
-</ul>
- <p>Some of the pros of MAME4droid are:</p>
-<p>arcade emulator android app<br />
-arcade emulator android apk<br />
-arcade emulator android download<br />
-arcade emulator android games<br />
-arcade emulator android reddit<br />
-arcade emulator android roms<br />
-arcade emulator android tv<br />
-arcade emulator android 2023<br />
-arcade emulator android best<br />
-arcade emulator android free<br />
-arcade emulator android mame<br />
-arcade emulator android offline<br />
-arcade emulator android online<br />
-arcade emulator android ps2<br />
-arcade emulator android snes<br />
-best arcade emulators for android devices<br />
-best arcade emulators for android pocket gamer<br />
-best arcade emulators for android phones<br />
-best arcade emulators for android tablets<br />
-best arcade emulators for android tv box<br />
-classicboy arcade emulator for android<br />
-dolphin arcade emulator for android<br />
-drastic ds arcade emulator for android<br />
-epsxe for android arcade emulator<br />
-gba.emu arcade emulator for android<br />
-m64plus fz arcade emulator for android<br />
-my boy! arcade emulator for android<br />
-nostalgia.nes arcade emulator for android<br />
-pizza boy gbc arcade emulator for android<br />
-retroarch arcade emulator for android<br />
-aethersx2 ps2 arcade emulator for android<br />
-best game emulators for android digital trends<br />
-best emulators for android 2023 android central<br />
-best emulators for android to run old pc console and arcade classics<br />
-how to play old school games on your phone with an arcade emulator app<br />
-how to install and use an arcade emulator on your android device<br />
-how to find and download roms for your favorite arcade games on android<br />
-how to set up and configure a gamepad for your arcade emulator on android<br />
-how to adjust per-game settings and optimize performance for your arcade emulator on android<br />
-how to save and load states and cheats for your arcade games on android<br />
-the best free and affordable arcade emulators for android in 2023<br />
-the most popular and compatible arcade emulators for android in 2023<br />
-the most accurate and authentic arcade emulators for android in 2023<br />
-the most user-friendly and easy-to-use arcade emulators for android in 2023<br />
-the most feature-rich and customizable arcade emulators for android in 2023</p>
- <ul>
-<li>It has a high compatibility rate with many arcade games.</li>
-<li>It has a good performance and speed with most games.</li>
-<li>It has a lot of options and settings to customize your gaming experience.</li>
-<li>It is free and open source.</li>
-</ul>
- <p>Some of the cons of MAME4droid are:</p>
- <ul>
-<li>It may not support some newer or more complex arcade games.</li>
-<li>It may require a powerful device to run some games smoothly.</li>
-<li>It may have some bugs or glitches with some games or features.</li>
-</ul>
- <p>MAME4droid is compatible with Android devices running Android 2.3 or higher. You can download it from Google Play Store or other sources. You will also need to download ROMs and BIOS files from legal sources or dump them from your own original cartridges or discs if you own them. You can load ROMs into MAME4droid by placing them in the ROMs folder of your device's internal storage or external SD card.</p>
- <h3>RetroArch</h3>
- <p>RetroArch is another popular and versatile arcade emulator for Android. RetroArch is not just an emulator, but a platform that can run various emulators called cores. RetroArch can run emulators for many systems, such as arcade machines, consoles, computers, handhelds, etc. RetroArch can also run games that are not emulated but ported to the platform, such as Doom , Quake , Cave Story , etc.</p>
- <p>Some of the features of RetroArch are:</p>
- <ul>
-<li>It supports high-resolution graphics and shaders for each game.</li>
-<li>It supports various input methods, such as touch screen, keyboard, gamepad, mouse, etc.</li>
-<li>It supports cheat codes and save states.</li>
-<li>It supports multiplayer mode via Bluetooth or Wi-Fi.</li>
-<li>It has a user-friendly interface that allows you to browse and search games by category, name, system, core, etc.</li>
-</ul>
- <p>Some of the pros of RetroArch are:</p>
- <ul>
-<li>It has a high compatibility rate with many arcade games and other systems.</li>
-<li>It has a good performance and speed with most games.</li>
-<li>It has a lot of options and settings to customize your gaming experience.</li>
-<li>It is free and open source.</li>
-</ul>
- <p>Some of the cons of RetroArch are:</p>
- <ul>
-<li>It may not support some newer or more complex arcade games or systems.</li>
-<li>It may require a powerful device to run some games smoothly.</li>
-<li>It may have some bugs or glitches with some games or features.</li>
-</ul>
- <p>RetroArch is compatible with Android devices running Android 2.3 or higher. You can download it from Google Play Store or other sources. You will also need to download cores from within the app or from other sources. You will also need to download ROMs and BIOS files from legal sources or dump them from your own original cartridges or discs if you own them. sources. You will also need to download ROMs and BIOS files from legal sources or dump them from your own original cartridges or discs if you own them. You can load ROMs into Tiger Arcade by placing them in the ROMs folder of your device's internal storage or external SD card.</p>
- <h3>Arcade Games</h3>
- <p>Arcade Games is another arcade emulator for Android that offers a collection of classic arcade games that you can play online or offline. Arcade Games features over 200 arcade games from various systems, such as Atari, Nintendo, Sega, Capcom, etc. Some of the games included are Asteroids , Centipede , Frogger , Pac-Man , Space Invaders , Super Mario Bros , Tetris , etc.</p>
- <p>Some of the features of Arcade Games are:</p>
- <ul>
-<li>It supports native resolution and aspect ratio for each game.</li>
-<li>It supports touch screen and gamepad input methods.</li>
-<li>It supports cheat codes and save states.</li>
-<li>It has a simple and intuitive interface that allows you to browse and search games by category, name, year, manufacturer, etc.</li>
-</ul>
- <p>Some of the pros of Arcade Games are:</p>
- <ul>
-<li>It has a high compatibility rate with many classic arcade games.</li>
-<li>It has a good performance and speed with most games.</li>
-<li>It has a minimalistic and user-friendly design.</li>
-<li>It is free and ad-free.</li>
-</ul>
- <p>Some of the cons of Arcade Games are:</p>
- <ul>
-<li>It may not support some newer or more complex arcade games or systems.</li>
-<li>It may require a stable internet connection to play some games online.</li>
-<li>It may have some bugs or glitches with some games or features.</li>
-</ul>
- <p>Arcade Games is compatible with Android devices running Android 4.1 or higher. You can download it from Google Play Store or other sources. You will also need to download ROMs and BIOS files from legal sources or dump them from your own original cartridges or discs if you own them. You can load ROMs into Arcade Games by placing them in the ROMs folder of your device's internal storage or external SD card.</p>
- <h4>Comparison Table of Arcade Emulators for Android</h4>
- <table>
-<tr>
-<th>Name</th>
-<th>Supported Systems</th>
-<th>Number of Games</th>
-<th>Online/Offline Mode</th>
-<th>User Rating</th>
-</tr>
-<tr>
-<td>MAME4droid</td>
-<td>Arcade machines, consoles</td>
-<td>Over 8,000</td>
-<td>Offline</td>
-<td>4.2/5</td>
-</tr>
-<tr>
-<td>RetroArch</td>
-<td>Arcade machines, consoles, computers, handhelds, etc.</td>
-<td>Over 10,000</td>
-<td>Offline</td>
-<td>4.1/5</td>
-</tr>
-<tr>
-<td>Nostalgia.Arcade</td>
-<td>Arcade machines, consoles</td>
-<td>Over 8,000</td>
-<td>Offline</td>
-<td>4.0/5</td>
-</tr>
-<tr>
-<td>Tiger Arcade</td>
-<td>Neo Geo games</td>
-<td>Over 1,000</td>
-<td>Offline</td>
-<td>3.9/5</td>
-</tr>
-<tr>
-<td>Arcade Games</td>
-<td>Arcade machines, consoles</td>
-<td>Over 200</td>
-<td>Online/Offline</td>
-<td>3.8/5</td>
-</tr> <h2>How to Install and Use Emulators for Android?</h2>
- <p>Now that you know some of the best arcade emulators for Android, you might be wondering how to install and use them. The process is not very complicated, but it may vary slightly depending on the emulator app and the source of the ROMs and BIOS files. Here are some general steps that you can follow to install and use emulators for Android:</p>
- <ol>
-<li>Download an emulator app from Google Play Store or other sources. Make sure that the app is compatible with your device and the games that you want to play.</li>
-<li>Download ROMs and BIOS files from legal sources or dump them from your own original cartridges or discs if you own them. Make sure that the ROMs and BIOS files are compatible with the emulator app and the games that you want to play.</li>
-<li>Load ROMs into the emulator app by placing them in the ROMs folder of your device's internal storage or external SD card. Some emulator apps may have different folders for different systems or games, so make sure that you place the ROMs in the correct folder.</li>
-<li>Load BIOS files into the emulator app by placing them in the BIOS folder of your device's internal storage or external SD card. Some emulator apps may require BIOS files for some systems or games, so make sure that you have the correct BIOS files.</li>
-<li>Launch the emulator app and browse and select the game that you want to play. Some emulator apps may have a built-in game browser, while others may require you to manually locate and select the game file.</li>
-<li>Configure settings and controls according to your preferences. You can adjust the screen size, resolution, orientation, aspect ratio, filters, frameskip, sound volume, etc. of your emulator app. You can also configure the controls and buttons of your emulator app according to your comfort and convenience. You can use touch screen, keyboard, gamepad, accelerometer, etc. as input methods.</li>
-<li>Enjoy your favorite arcade games on your Android device!</li>
-</ol>
- <h2>What Are Some of the Best Arcade Games to Play on Your Android Device?</h2>
- <p>There are thousands of arcade games that you can play on your Android device with emulators, but not all of them are equally fun and enjoyable. Some of them may be more popular, more challenging, more appealing, or more nostalgic than others. To help you find some of the best arcade games to play on your Android device, we have selected some of them based on their popularity, genre, graphics, gameplay, and nostalgia factor. Here are some of the best arcade games to play on your Android device:</p>
- <ul>
-<li><b>Pac-Man:</b> Pac-Man is one of the most iconic and influential arcade games of all time. It was released by Namco in 1980 and became a worldwide phenomenon. The game involves controlling a yellow circle with a mouth that eats dots and fruits while avoiding four ghosts that chase it in a maze. The game is simple yet addictive and has spawned many sequels, spin-offs, remakes, and adaptations.</li>
-<li><b>Street Fighter II:</b> Street Fighter II is one of the most popular and influential fighting games of all time. It was released by Capcom in 1991 and revolutionized the genre with its fast-paced gameplay, diverse characters, special moves, combos, and competitive multiplayer mode. The game involves selecting one of eight fighters from different countries and fighting against other fighters in various stages until reaching the final boss.</li>
-<li><b>Mortal Kombat:</b> Mortal Kombat is another fighting game that became famous for its violent and bloody gameplay, realistic graphics, digitized actors, and controversial fatalities. It was released by Midway in 1992 and sparked a lot of controversy and censorship issues. The game involves selecting one of seven fighters from different realms and fighting against other fighters in various stages until reaching the final boss.</li>
-<li><b>Donkey Kong:</b> Donkey Kong is one of the first platform games that introduced Mario, one of the most famous video game characters of all time. It was released by Nintendo in 1981 and became a huge success. The game involves controlling Mario as he tries to rescue his girlfriend Pauline from a giant ape named Donkey Kong who throws barrels at him.</li>
-<li><b>Space Invaders:</b> Space Invaders is one of the first shooting games that started the space shooter genre. It was released by Taito in 1978 and became a cultural phenomenon. The game involves controlling a laser cannon that shoots at waves of alien invaders who descend from the top of the screen.</li>
-<li><b>Galaga:</b> Galaga is another shooting game that improved on Space Invaders with its colorful graphics, dynamic gameplay, bonus stages, and enemy formations. It was released by Namco in 1981 and became one of the most successful arcade games of all time. The game involves controlling a starship that shoots at waves of alien insects who fly in various patterns and formations.</li>
-<li><b>Metal Slug:</b> Metal Slug is a series of run and gun games that are known for their humorous and cartoonish graphics, explosive gameplay, and cooperative multiplayer mode. The first game was released by SNK in 1996 and became a cult classic. The game involves controlling one of four soldiers who fight against a rebel army and various enemies using various weapons, vehicles, and items.</li>
-<li><b>Double Dragon:</b> Double Dragon is one of the first beat 'em up games that popularized the genre with its cooperative multiplayer mode, branching paths, and weapon usage. It was released by Technos Japan in 1987 and became a hit. The game involves controlling one of two brothers who fight against a gang of thugs who kidnapped their girlfriend.</li>
-</ul>
- <h2>Conclusion</h2>
- <p>Arcade games are video games that were originally played in coin-operated machines installed in public places such as restaurants, bars, amusement parks, etc. They are popular among retro gamers who want to relive some of their childhood memories or experience some of the classic games that they missed out on. By using emulators, you can play arcade games on your Android device. Emulators are software programs that can mimic the hardware and software of different systems, such as arcade machines, consoles, computers, etc. By using emulators, you can run games that were designed for other platforms on your Android device.</p>
- <p>Using emulators for Android has many benefits, such as convenience, cost-effectiveness, nostalgia, customization, and preservation. You can play arcade games anytime and anywhere with your Android device without spending money on coins or tokens or buying or maintaining a physical arcade machine or console. You can also enjoy the retro graphics, sound effects, and gameplay of arcade games that may not be available on modern platforms. You can also customize your gaming experience by using different emulator apps and settings. You can also preserve some of the history and culture of video gaming by playing arcade games on your Android device.</p>
- <p>There are many arcade emulators for Android that you can choose from, but some of the best ones are MAME4droid, RetroArch, Nostalgia.Arcade, Tiger Arcade, and Arcade Games. These emulator apps have high compatibility rates with many arcade games from various systems, good performance and speed with most games, user-friendly interfaces and designs, and various features and options to enhance your gaming experience. You can download these emulator apps from Google Play Store or other sources. You will also need to download ROMs and BIOS files from legal sources or dump them from your own original cartridges or discs if you own them. You can load ROMs into these emulator apps by placing them in the ROMs folder of your device's internal storage or external SD card.</p>
- <p>There are thousands of arcade games that you can play on your Android device with emulators, but some of the best ones are Pac-Man , Street Fighter II , Mortal Kombat , Donkey Kong , Space Invaders , Galaga , Metal Slug , Double Dragon , etc. These games are known for their simple yet addictive gameplay, colorful graphics, catchy sound effects, and high scores. They are also part of the history and culture of video gaming and have influenced many modern games and genres.</p>
- <p>If you are a fan of retro gaming or just want to have some fun with arcade games on your Android device, you should definitely try out some of the best arcade emulators for Android. You will not regret it!</p>
- <h2>FAQs</h2>
- <p>Here are some frequently asked questions that you might have about arcade emulators for Android:</p>
- <ol>
-<li><b>Are arcade emulators for Android legal?</b></li>
-<p>Arcade emulators for Android are legal as long as you use them for personal and non-commercial purposes. However, downloading ROMs and BIOS files from illegal sources or without owning the original games or systems is considered piracy and may violate intellectual property rights. You should only download ROMs and BIOS files from legal sources or dump them from your own original cartridges or discs if you own them.</p>
-<li><b>Are arcade emulators for Android safe?</b></li>
-<p>Arcade emulators for Android are safe as long as you download them from reputable sources such as Google Play Store or official websites. However, downloading ROMs and BIOS files from unknown or untrusted sources may contain viruses or malware that may harm your device or compromise your privacy. You should only download ROMs and BIOS files from legal sources or dump them from your own original cartridges or discs if you own them.</p>
-<li><b>Are arcade emulators for Android free?</b></li>
-<p>Arcade emulators for Android are free as long as you download them from legal sources or dump them from your own original cartridges or discs if you own them. However, some emulator apps may have in-app purchases or ads that may require you to pay money or watch ads to access some features or games. You can choose to pay or not depending on your preference.</p>
-<li><b>Which arcade emulator for Android is the best?</b></li>
-<p>There is no definitive answer to this question, as different arcade emulators for Android may have different advantages and disadvantages depending on your device, the games that you want to play, and your personal preference. However, some of the most popular and reliable arcade emulators for Android are MAME4droid, RetroArch, Nostalgia.Arcade, Tiger Arcade, and Arcade Games. You can try them out and see which one suits you best.</p>
-<li><b>How can I improve the performance and speed of arcade emulators for Android?</b></li>
-<p>There are some factors that may affect the performance and speed of arcade emulators for Android, such as your device's specifications, the emulator app's settings, the game's complexity, etc. Here are some tips that may help you improve the performance and speed of arcade emulators for Android:</p>
-<ul>
-<li>Use a powerful device that has a high CPU, RAM, GPU, and storage capacity.</li>
-<li>Use a stable and fast internet connection if you play online games.</li>
-<li>Use a compatible and updated emulator app that supports the games that you want to play.</li>
-<li>Use compatible and legal ROMs and BIOS files that match the emulator app and the games that you want to play.</li>
-<li>Adjust the emulator app's settings according to your device's specifications and your gaming preferences. You can lower the screen resolution, aspect ratio, filters, frameskip, sound volume, etc. to improve the performance and speed of the emulator app.</li>
-<li>Close other apps and processes that may consume your device's resources or interfere with the emulator app.</li>
-</ul></p> 401be4b1e0<br />
-<br />
-<br />
\ No newline at end of file
diff --git a/spaces/1phancelerku/anime-remove-background/Farm Town Village Build Story Enjoy the Rural Life and Grow Your Own Crops.md b/spaces/1phancelerku/anime-remove-background/Farm Town Village Build Story Enjoy the Rural Life and Grow Your Own Crops.md
deleted file mode 100644
index 676badbf821fd85b914d156af7ff669655e3d295..0000000000000000000000000000000000000000
--- a/spaces/1phancelerku/anime-remove-background/Farm Town Village Build Story Enjoy the Rural Life and Grow Your Own Crops.md	
+++ /dev/null
@@ -1,108 +0,0 @@
-
-<h1>Farm Town Village Build Story: A Fun and Relaxing Farming Game</h1>
-<p>Do you love farming games? Do you want to experience the quiet charm of rural life? Do you want to build your own dream village with a view to a river? If you answered yes to any of these questions, then you should definitely check out Farm Town Village Build Story, a unique blend of farming and city-building simulation game. In this article, we will tell you everything you need to know about this game, including its features, tips and tricks, and how to download it for free.</p>
-<h2>farm town village build story</h2><br /><p><b><b>Download</b> ---> <a href="https://jinyurl.com/2uNS2E">https://jinyurl.com/2uNS2E</a></b></p><br /><br />
- <h2>Introduction</h2>
-<p>Farm Town Village Build Story is a game developed by Foranj Games, a leading developer of casual games for mobile devices. The game was released in 2019 and has since gained over 10 million downloads and 4.5 stars rating on Google Play Store. The game is available for both Android and iOS devices, and you can play it offline or online.</p>
- <h3>What is Farm Town Village Build Story?</h3>
-<p>Farm Town Village Build Story is a game that combines the elements of farming and city-building. You start with a small farm near a township, where you can grow hay, corn, vegetables, fruits, berries, and flowers. You can also craft dozens of different treats from your harvest, such as lollipop, cookie, birthday cake, and more. You can then sell your goods to the townsfolk and friendly neighbors, who will give you cash and XP in return.</p>
-<p>But farming is not the only thing you can do in this game. You can also build your own village with various buildings, such as houses, factories, community buildings, and a seaside trading port. You can also manage the distribution center of your village, where you can receive orders from different customers. You can also expand your village by repairing a circus and inviting tourists to visit your farm. You can also build a zoo and adopt lovely pets, such as pony, sheep, cow, pig, chicken, duck, dog, cat, and more.</p>
-<p>farm town village build story game<br />
-farm town village build story apk<br />
-farm town village build story download<br />
-farm town village build story mod apk<br />
-farm town village build story cheats<br />
-farm town village build story hack<br />
-farm town village build story for pc<br />
-farm town village build story online<br />
-farm town village build story app<br />
-farm town village build story free<br />
-farm town village build story review<br />
-farm town village build story tips<br />
-farm town village build story guide<br />
-farm town village build story walkthrough<br />
-farm town village build story update<br />
-farm town village build story play store<br />
-farm town village build story facebook<br />
-farm town village build story forum<br />
-farm town village build story wiki<br />
-farm town village build story reddit<br />
-farm town village build story gameplay<br />
-farm town village build story trailer<br />
-farm town village build story video<br />
-farm town village build story android<br />
-farm town village build story ios<br />
-farm town village build story iphone<br />
-farm town village build story ipad<br />
-farm town village build story windows<br />
-farm town village build story mac<br />
-farm town village build story laptop<br />
-farm town village build story chromebook<br />
-farm town village build story simulator<br />
-farm town village build story casual game<br />
-farm town village build story farming game<br />
-farm town village build story management game<br />
-farm town village build story simulation game<br />
-farm town village build story relaxing game<br />
-farm town village build story fun game<br />
-farm town village build story cute game<br />
-farm town village build story cartoon game<br />
-farm town village build story 3d game<br />
-farm town village build story offline game<br />
-farm town village build story single player game<br />
-farm town village build story family game<br />
-farm town village build story kids game<br />
-how to play farm town village build story <br />
-how to install farm town village build story <br />
-how to hack farm town village build story <br />
-how to update farm town village build story</p>
- <h3>Why should you play Farm Town Village Build Story?</h3>
-<p>There are many reasons why you should play Farm Town Village Build Story. Here are some of them:</p>
-<ul>
-<li>It is fun and relaxing. You can enjoy the simple pleasures of farming and village life, such as planting seeds, watering crops, harvesting fruits, feeding animals, baking cakes, making friends, and more.</li>
-<li>It is colorful and cartoonish. The game has bright graphics and cute animations that will make you smile. The game also has cheerful music and sound effects that will enhance your mood.</li>
-<li>It is challenging and rewarding. You can complete various tasks and quests that will test your skills and creativity. You can also earn coins and gems that you can use to upgrade your buildings and buy new items.</li>
-<li>It is social and interactive. You can connect with other players from around the world through Facebook or Google Play Games. You can visit their farms, help them out, chat with them, send them gifts, or compete with them in leaderboards.</li>
-<li>It is free and accessible. You can download the game for free from Google Play Store or App Store. You can also play the game offline or online, depending on your preference.</li>
-</ul>
- <h2>Features of Farm Town Village Build Story</h2>
-<p>Farm Town Village Build Story has many features that make it an enjoyable game to play. Here are some of them:</p <h3>Build a zoo and invite lovely pets to your farm</h3>
-<p>Another feature of Farm Town Village Build Story is the zoo aspect. You can build a zoo on your farm and invite lovely pets to live there. You can adopt animals such as pony, sheep, cow, pig, chicken, duck, dog, cat, and more. You can also unlock exotic animals such as panda, tiger, lion, elephant, giraffe, and more. You can feed your animals, play with them, and watch them grow. You can also breed your animals and get baby animals that are even cuter.</p>
-<p>But building a zoo is not enough. You can also decorate your zoo with various items, such as fences, paths, benches, lamps, statues, and more. You can also create habitats for your animals, such as grassland, forest, savanna, desert, and more. You can also attract visitors to your zoo and earn money from them. You can also complete zoo quests and get rewards.</p>
- <h3>Repair a circus and attract tourists to your village</h3>
-<p>Another feature of Farm Town Village Build Story is the circus aspect. You can repair a circus on your village and attract tourists to visit it. You can restore the circus tent, the stage, the seats, the lights, and the decorations. You can also hire performers for your circus, such as clowns, acrobats, magicians, and more. You can also train your animals to perform tricks for the audience.</p>
-<p>But repairing a circus is not enough. You can also upgrade your circus with new equipment, such as trampoline, cannon, ball pool, and more. You can also create shows for your circus and earn applause from the spectators. You can also complete circus quests and get rewards.</p> <h3>Enlist the support of your friends and neighbors</h3>
-<p>Another feature of Farm Town Village Build Story is the social aspect. You can enlist the support of your friends and neighbors in your farming and village life. You can connect with other players through Facebook or Google Play Games. You can visit their farms and villages, help them out, chat with them, send them gifts, or compete with them in leaderboards. You can also trade goods with them through the market or the port. You can also join a group on Facebook to share your stories and get updates.</p>
-<p>But enlisting the support of your friends and neighbors is not enough. You can also make new friends and neighbors in the game. You can meet different characters, such as Tom, Alice, Bob, Lisa, and more. You can also interact with them, learn their stories, complete their quests, and earn their trust. You can also unlock new areas and buildings by befriending them.</p>
- <h3>Decorate your farm with beautiful flowers and decorations</h3>
-<p>Another feature of Farm Town Village Build Story is the decoration aspect. You can decorate your farm with beautiful flowers and decorations. You can grow flowers, such as rose, tulip, sunflower, daisy, and more. You can also buy decorations, such as fences, paths, benches, lamps, statues, and more. You can also customize your farm with different themes, such as fairy tale, Halloween, Christmas, and more.</p>
-<p>But decorating your farm is not enough. You can also decorate your village with various items. You can build houses, factories, community buildings, and a seaside trading port. You can also upgrade your buildings and make them more attractive. You can also create a unique landscape for your village with different terrains, such as grassland, forest, savanna, desert, and more.</p>
- <h2>Tips and tricks for playing Farm Town Village Build Story</h2>
-<p>Farm Town Village Build Story is a game that requires strategy and planning. Here are some tips and tricks that will help you play the game better:</p> <h3>Upgrade your storage and factories regularly</h3>
-<p>One of the tips for playing Farm Town Village Build Story is to upgrade your storage and factories regularly. You will need a lot of space to store your crops, fruits, flowers, and products. You will also need efficient factories to craft your goods faster and better. You can upgrade your storage and factories by using coins, gems, or materials. You can get coins by selling your goods, completing orders and quests, or visiting other players' farms. You can get gems by watching ads, leveling up, or buying them with real money. You can get materials by harvesting crops, opening chests, or requesting them from your friends.</p>
- <h3>Complete orders and quests to earn cash and XP</h3>
-<p>Another tip for playing Farm Town Village Build Story is to complete orders and quests to earn cash and XP. You can receive orders from different customers, such as townsfolk, neighbors, circus visitors, or port traders. You can also receive quests from different characters, such as Tom, Alice, Bob, Lisa, and more. You can complete orders and quests by delivering the required goods or performing the required actions. You can earn cash and XP by completing orders and quests. You can use cash to buy new items or upgrade your buildings. You can use XP to level up and unlock new features.</p>
- <h3>Use the market to buy and sell goods</h3>
-<p>Another tip for playing Farm Town Village Build Story is to use the market to buy and sell goods. You can access the market by tapping on the market stall on your farm. You can buy goods from other players or sell your own goods to them. You can set the price and quantity of your goods as you wish. You can also use the market to trade goods with your friends or neighbors. You can use the market to get the goods you need or make some extra cash.</p> <h3>Visit other players' farms and help them out</h3>
-<p>Another tip for playing Farm Town Village Build Story is to visit other players' farms and help them out. You can visit other players' farms by tapping on the map icon on the bottom right corner of the screen. You can see the farms of your friends, neighbors, or random players. You can help them out by watering their crops, feeding their animals, or harvesting their goods. You can also chat with them, send them gifts, or rate their farms. You can earn coins, XP, and materials by visiting other players' farms.</p>
- <h3>Join a group on Facebook to share your stories and get updates</h3>
-<p>Another tip for playing Farm Town Village Build Story is to join a group on Facebook to share your stories and get updates. You can join the official group of Farm Town Village Build Story by tapping on the Facebook icon on the top left corner of the screen. You can also search for other groups related to the game on Facebook. You can share your stories, screenshots, tips, and tricks with other players in the group. You can also get updates, news, events, and giveaways from the developers of the game.</p>
- <h2>Conclusion</h2>
-<p>Farm Town Village Build Story is a fun and relaxing farming game that you can play on your mobile device. You can grow a variety of crops and craft delicious treats. You can build a zoo and invite lovely pets to your farm. You can repair a circus and attract tourists to your village. You can enlist the support of your friends and neighbors. You can decorate your farm with beautiful flowers and decorations. You can also complete orders and quests to earn cash and XP. You can also use the market to buy and sell goods. You can also visit other players' farms and help them out. You can also join a group on Facebook to share your stories and get updates.</p>
-<p>If you are looking for a game that combines the elements of farming and city-building, then you should definitely try Farm Town Village Build Story. It is free to download and play, and you can enjoy it offline or online. It is colorful and cartoonish, challenging and rewarding, social and interactive. It is a game that will make you smile and relax.</p>
- <h2>FAQs</h2>
-<p>Here are some frequently asked questions about Farm Town Village Build Story:</p>
-<ul>
-<li><b>How do I download Farm Town Village Build Story?</b></li>
-<p>You can download Farm Town Village Build Story from Google Play Store or App Store for free. Just search for the game name and tap on the install button.</p>
-<li><b>How do I play Farm Town Village Build Story offline?</b></li>
-<p>You can play Farm Town Village Build Story offline by turning off your internet connection before launching the game. However, some features may not be available offline, such as visiting other players' farms or connecting with Facebook.</p>
-<li><b>How do I get more gems in Farm Town Village Build Story?</b></li>
-<p>You can get more gems in Farm Town Village Build Story by watching ads, leveling up, or buying them with real money.</p>
-<li><b>How do I unlock new areas and buildings in Farm Town Village Build Story?</b></li>
-<p>You can unlock new areas and buildings in Farm Town Village Build Story by leveling up, befriending characters, completing quests, or using gems.</p>
-<li><b>How do I contact the developers of Farm Town Village Build Story?</b></li>
-<p>You can contact the developers of Farm Town Village Build Story by sending them an email at support@foranj.com or by joining their Facebook group.</p>
-</ul></p> 197e85843d<br />
-<br />
-<br />
\ No newline at end of file
diff --git a/spaces/1toTree/lora_test/ppdiffusers/pipelines/stable_diffusion/pipeline_stable_diffusion_inpaint.py b/spaces/1toTree/lora_test/ppdiffusers/pipelines/stable_diffusion/pipeline_stable_diffusion_inpaint.py
deleted file mode 100644
index 6a9d5e8322d0ae060ec71314b3f7ed5476e83500..0000000000000000000000000000000000000000
--- a/spaces/1toTree/lora_test/ppdiffusers/pipelines/stable_diffusion/pipeline_stable_diffusion_inpaint.py
+++ /dev/null
@@ -1,694 +0,0 @@
-# Copyright (c) 2022 PaddlePaddle Authors. All Rights Reserved.
-# Copyright 2022 The HuggingFace Team. All rights reserved.
-#
-# Licensed under the Apache License, Version 2.0 (the "License");
-# you may not use this file except in compliance with the License.
-# You may obtain a copy of the License at
-#
-#     http://www.apache.org/licenses/LICENSE-2.0
-#
-# Unless required by applicable law or agreed to in writing, software
-# distributed under the License is distributed on an "AS IS" BASIS,
-# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
-# See the License for the specific language governing permissions and
-# limitations under the License.
-
-import inspect
-from typing import Callable, List, Optional, Union
-
-import numpy as np
-import paddle
-import paddle.nn.functional as F
-import PIL
-from packaging import version
-
-from paddlenlp.transformers import CLIPFeatureExtractor, CLIPTextModel, CLIPTokenizer
-
-from ...configuration_utils import FrozenDict
-from ...models import AutoencoderKL, UNet2DConditionModel
-from ...pipeline_utils import DiffusionPipeline
-from ...schedulers import (
-    DDIMScheduler,
-    DPMSolverMultistepScheduler,
-    EulerAncestralDiscreteScheduler,
-    EulerDiscreteScheduler,
-    LMSDiscreteScheduler,
-    PNDMScheduler,
-)
-from ...utils import deprecate, logging
-from . import StableDiffusionPipelineOutput
-from .safety_checker import StableDiffusionSafetyChecker
-
-logger = logging.get_logger(__name__)  # pylint: disable=invalid-name
-
-
-def prepare_mask_and_masked_image(image, mask):
-    """
-    Prepares a pair (image, mask) to be consumed by the Stable Diffusion pipeline. This means that those inputs will be
-    converted to ``paddle.Tensor`` with shapes ``batch x channels x height x width`` where ``channels`` is ``3`` for the
-    ``image`` and ``1`` for the ``mask``.
-    The ``image`` will be converted to ``paddle.float32`` and normalized to be in ``[-1, 1]``. The ``mask`` will be
-    binarized (``mask > 0.5``) and cast to ``paddle.float32`` too.
-    Args:
-        image (Union[np.array, PIL.Image, paddle.Tensor]): The image to inpaint.
-            It can be a ``PIL.Image``, or a ``height x width x 3`` ``np.array`` or a ``channels x height x width``
-            ``paddle.Tensor`` or a ``batch x channels x height x width`` ``paddle.Tensor``.
-        mask (_type_): The mask to apply to the image, i.e. regions to inpaint.
-            It can be a ``PIL.Image``, or a ``height x width`` ``np.array`` or a ``1 x height x width``
-            ``paddle.Tensor`` or a ``batch x 1 x height x width`` ``paddle.Tensor``.
-    Raises:
-        ValueError: ``paddle.Tensor`` images should be in the ``[-1, 1]`` range. ValueError: ``paddle.Tensor`` mask
-        should be in the ``[0, 1]`` range. ValueError: ``mask`` and ``image`` should have the same spatial dimensions.
-        TypeError: ``mask`` is a ``paddle.Tensor`` but ``image`` is not
-            (ot the other way around).
-    Returns:
-        tuple[paddle.Tensor]: The pair (mask, masked_image) as ``paddle.Tensor`` with 4
-            dimensions: ``batch x channels x height x width``.
-    """
-    if isinstance(image, paddle.Tensor):
-        if not isinstance(mask, paddle.Tensor):
-            raise TypeError(f"`image` is a paddle.Tensor but `mask` (type: {type(mask)} is not")
-
-        # Batch single image
-        if image.ndim == 3:
-            assert image.shape[0] == 3, "Image outside a batch should be of shape (3, H, W)"
-            image = image.unsqueeze(0)
-
-        # Batch and add channel dim for single mask
-        if mask.ndim == 2:
-            mask = mask.unsqueeze(0).unsqueeze(0)
-
-        # Batch single mask or add channel dim
-        if mask.ndim == 3:
-            # Single batched mask, no channel dim or single mask not batched but channel dim
-            if mask.shape[0] == 1:
-                mask = mask.unsqueeze(0)
-
-            # Batched masks no channel dim
-            else:
-                mask = mask.unsqueeze(1)
-
-        assert image.ndim == 4 and mask.ndim == 4, "Image and Mask must have 4 dimensions"
-        assert image.shape[-2:] == mask.shape[-2:], "Image and Mask must have the same spatial dimensions"
-        assert image.shape[0] == mask.shape[0], "Image and Mask must have the same batch size"
-
-        # Check image is in [-1, 1]
-        if image.min() < -1 or image.max() > 1:
-            raise ValueError("Image should be in [-1, 1] range")
-
-        # Check mask is in [0, 1]
-        if mask.min() < 0 or mask.max() > 1:
-            raise ValueError("Mask should be in [0, 1] range")
-
-        # Binarize mask
-        mask[mask < 0.5] = 0
-        mask[mask >= 0.5] = 1
-
-        # Image as float32
-        image = image.cast(paddle.float32)
-    elif isinstance(mask, paddle.Tensor):
-        raise TypeError(f"`mask` is a paddle.Tensor but `image` (type: {type(image)} is not")
-    else:
-        # preprocess image
-        if isinstance(image, (PIL.Image.Image, np.ndarray)):
-            image = [image]
-
-        if isinstance(image, list) and isinstance(image[0], PIL.Image.Image):
-            image = [np.array(i.convert("RGB"))[None, :] for i in image]
-            image = np.concatenate(image, axis=0)
-        elif isinstance(image, list) and isinstance(image[0], np.ndarray):
-            image = np.concatenate([i[None, :] for i in image], axis=0)
-
-        image = image.transpose(0, 3, 1, 2)
-        image = paddle.to_tensor(image).cast(paddle.float32) / 127.5 - 1.0
-
-        # preprocess mask
-        if isinstance(mask, (PIL.Image.Image, np.ndarray)):
-            mask = [mask]
-
-        if isinstance(mask, list) and isinstance(mask[0], PIL.Image.Image):
-            mask = np.concatenate([np.array(m.convert("L"))[None, None, :] for m in mask], axis=0)
-            mask = mask.astype(np.float32) / 255.0
-        elif isinstance(mask, list) and isinstance(mask[0], np.ndarray):
-            mask = np.concatenate([m[None, None, :] for m in mask], axis=0)
-
-        mask[mask < 0.5] = 0
-        mask[mask >= 0.5] = 1
-        mask = paddle.to_tensor(mask)
-
-    masked_image = image * (mask < 0.5)
-
-    return mask, masked_image
-
-
-class StableDiffusionInpaintPipeline(DiffusionPipeline):
-    r"""
-    Pipeline for text-guided image inpainting using Stable Diffusion. *This is an experimental feature*.
-
-    This model inherits from [`DiffusionPipeline`]. Check the superclass documentation for the generic methods the
-    library implements for all the pipelines (such as downloading or saving, running on a particular xxxx, etc.)
-
-    Args:
-        vae ([`AutoencoderKL`]):
-            Variational Auto-Encoder (VAE) Model to encode and decode images to and from latent representations.
-        text_encoder ([`CLIPTextModel`]):
-            Frozen text-encoder. Stable Diffusion uses the text portion of
-            [CLIP](https://huggingface.co/docs/transformers/model_doc/clip#transformers.CLIPTextModel), specifically
-            the [clip-vit-large-patch14](https://huggingface.co/openai/clip-vit-large-patch14) variant.
-        tokenizer (`CLIPTokenizer`):
-            Tokenizer of class
-            [CLIPTokenizer](https://huggingface.co/docs/transformers/v4.21.0/en/model_doc/clip#transformers.CLIPTokenizer).
-        unet ([`UNet2DConditionModel`]): Conditional U-Net architecture to denoise the encoded image latents.
-        scheduler ([`SchedulerMixin`]):
-            A scheduler to be used in combination with `unet` to denoise the encoded image latents. Can be one of
-            [`DDIMScheduler`], [`LMSDiscreteScheduler`], [`PNDMScheduler`], [`EulerDiscreteScheduler`], [`EulerAncestralDiscreteScheduler`]
-            or [`DPMSolverMultistepScheduler`].
-        safety_checker ([`StableDiffusionSafetyChecker`]):
-            Classification module that estimates whether generated images could be considered offensive or harmful.
-            Please, refer to the [model card](https://huggingface.co/runwayml/stable-diffusion-v1-5) for details.
-        feature_extractor ([`CLIPFeatureExtractor`]):
-            Model that extracts features from generated images to be used as inputs for the `safety_checker`.
-    """
-    _optional_components = ["safety_checker", "feature_extractor"]
-
-    def __init__(
-        self,
-        vae: AutoencoderKL,
-        text_encoder: CLIPTextModel,
-        tokenizer: CLIPTokenizer,
-        unet: UNet2DConditionModel,
-        scheduler: Union[
-            DDIMScheduler,
-            PNDMScheduler,
-            LMSDiscreteScheduler,
-            EulerDiscreteScheduler,
-            EulerAncestralDiscreteScheduler,
-            DPMSolverMultistepScheduler,
-        ],
-        safety_checker: StableDiffusionSafetyChecker,
-        feature_extractor: CLIPFeatureExtractor,
-        requires_safety_checker: bool = True,
-    ):
-        super().__init__()
-
-        if hasattr(scheduler.config, "steps_offset") and scheduler.config.steps_offset != 1:
-            deprecation_message = (
-                f"The configuration file of this scheduler: {scheduler} is outdated. `steps_offset`"
-                f" should be set to 1 instead of {scheduler.config.steps_offset}. Please make sure "
-                "to update the config accordingly as leaving `steps_offset` might led to incorrect results"
-                " in future versions. If you have downloaded this checkpoint from the Hugging Face Hub,"
-                " it would be very nice if you could open a Pull request for the `scheduler/scheduler_config.json`"
-                " file"
-            )
-            deprecate("steps_offset!=1", "1.0.0", deprecation_message, standard_warn=False)
-            new_config = dict(scheduler.config)
-            new_config["steps_offset"] = 1
-            scheduler._internal_dict = FrozenDict(new_config)
-
-        if hasattr(scheduler.config, "skip_prk_steps") and scheduler.config.skip_prk_steps is False:
-            deprecation_message = (
-                f"The configuration file of this scheduler: {scheduler} has not set the configuration"
-                " `skip_prk_steps`. `skip_prk_steps` should be set to True in the configuration file. Please make"
-                " sure to update the config accordingly as not setting `skip_prk_steps` in the config might lead to"
-                " incorrect results in future versions. If you have downloaded this checkpoint from the Hugging Face"
-                " Hub, it would be very nice if you could open a Pull request for the"
-                " `scheduler/scheduler_config.json` file"
-            )
-            deprecate("skip_prk_steps not set", "1.0.0", deprecation_message, standard_warn=False)
-            new_config = dict(scheduler.config)
-            new_config["skip_prk_steps"] = True
-            scheduler._internal_dict = FrozenDict(new_config)
-
-        if safety_checker is None and requires_safety_checker:
-            logger.warning(
-                f"You have disabled the safety checker for {self.__class__} by passing `safety_checker=None`. Ensure"
-                " that you abide to the conditions of the Stable Diffusion license and do not expose unfiltered"
-                " results in services or applications open to the public. PaddleNLP team, diffusers team and Hugging Face"
-                " strongly recommend to keep the safety filter enabled in all public facing circumstances, disabling"
-                " it only for use-cases that involve analyzing network behavior or auditing its results. For more"
-                " information, please have a look at https://github.com/huggingface/diffusers/pull/254 ."
-            )
-        if safety_checker is not None and feature_extractor is None:
-            raise ValueError(
-                "Make sure to define a feature extractor when loading {self.__class__} if you want to use the safety"
-                " checker. If you do not want to use the safety checker, you can pass `'safety_checker=None'` instead."
-            )
-        is_unet_version_less_0_9_0 = hasattr(unet.config, "_ppdiffusers_version") and version.parse(
-            version.parse(unet.config._ppdiffusers_version).base_version
-        ) < version.parse("0.9.0.dev0")
-        is_unet_sample_size_less_64 = hasattr(unet.config, "sample_size") and unet.config.sample_size < 64
-        if is_unet_version_less_0_9_0 and is_unet_sample_size_less_64:
-            deprecation_message = (
-                "The configuration file of the unet has set the default `sample_size` to smaller than"
-                " 64 which seems highly unlikely. If your checkpoint is a fine-tuned version of any of the"
-                " following: \n- CompVis/stable-diffusion-v1-4 \n- CompVis/stable-diffusion-v1-3 \n-"
-                " CompVis/stable-diffusion-v1-2 \n- CompVis/stable-diffusion-v1-1 \n- runwayml/stable-diffusion-v1-5"
-                " \n- runwayml/stable-diffusion-inpainting \n you should change 'sample_size' to 64 in the"
-                " configuration file. Please make sure to update the config accordingly as leaving `sample_size=32`"
-                " in the config might lead to incorrect results in future versions. If you have downloaded this"
-                " checkpoint from the Hugging Face Hub, it would be very nice if you could open a Pull request for"
-                " the `unet/config.json` file"
-            )
-            deprecate("sample_size<64", "1.0.0", deprecation_message, standard_warn=False)
-            new_config = dict(unet.config)
-            new_config["sample_size"] = 64
-            unet._internal_dict = FrozenDict(new_config)
-        self.register_modules(
-            vae=vae,
-            text_encoder=text_encoder,
-            tokenizer=tokenizer,
-            unet=unet,
-            scheduler=scheduler,
-            safety_checker=safety_checker,
-            feature_extractor=feature_extractor,
-        )
-        self.vae_scale_factor = 2 ** (len(self.vae.config.block_out_channels) - 1)
-        self.register_to_config(requires_safety_checker=requires_safety_checker)
-
-    # Copied from diffusers.pipelines.stable_diffusion.pipeline_stable_diffusion.StableDiffusionPipeline._encode_prompt
-    def _encode_prompt(self, prompt, num_images_per_prompt, do_classifier_free_guidance, negative_prompt):
-        r"""
-        Encodes the prompt into text encoder hidden states.
-
-        Args:
-            prompt (`str` or `list(int)`):
-                prompt to be encoded
-            num_images_per_prompt (`int`):
-                number of images that should be generated per prompt
-            do_classifier_free_guidance (`bool`):
-                whether to use classifier free guidance or not
-            negative_prompt (`str` or `List[str]`):
-                The prompt or prompts not to guide the image generation. Ignored when not using guidance (i.e., ignored
-                if `guidance_scale` is less than `1`).
-        """
-        batch_size = len(prompt) if isinstance(prompt, list) else 1
-
-        text_inputs = self.tokenizer(
-            prompt,
-            padding="max_length",
-            max_length=self.tokenizer.model_max_length,
-            truncation=True,
-            return_tensors="pd",
-        )
-        text_input_ids = text_inputs.input_ids
-        untruncated_ids = self.tokenizer(prompt, padding="longest", return_tensors="pd").input_ids
-
-        if untruncated_ids.shape[-1] >= text_input_ids.shape[-1] and not paddle.equal_all(
-            text_input_ids, untruncated_ids
-        ):
-            removed_text = self.tokenizer.batch_decode(untruncated_ids[:, self.tokenizer.model_max_length - 1 : -1])
-            logger.warning(
-                "The following part of your input was truncated because CLIP can only handle sequences up to"
-                f" {self.tokenizer.model_max_length} tokens: {removed_text}"
-            )
-
-        config = (
-            self.text_encoder.config
-            if isinstance(self.text_encoder.config, dict)
-            else self.text_encoder.config.to_dict()
-        )
-        if config.get("use_attention_mask", None) is not None and config["use_attention_mask"]:
-            attention_mask = text_inputs.attention_mask
-        else:
-            attention_mask = None
-
-        text_embeddings = self.text_encoder(
-            text_input_ids,
-            attention_mask=attention_mask,
-        )
-        text_embeddings = text_embeddings[0]
-
-        # duplicate text embeddings for each generation per prompt, using mps friendly method
-        bs_embed, seq_len, _ = text_embeddings.shape
-        text_embeddings = text_embeddings.tile([1, num_images_per_prompt, 1])
-        text_embeddings = text_embeddings.reshape([bs_embed * num_images_per_prompt, seq_len, -1])
-
-        # get unconditional embeddings for classifier free guidance
-        if do_classifier_free_guidance:
-            uncond_tokens: List[str]
-            if negative_prompt is None:
-                uncond_tokens = [""] * batch_size
-            elif type(prompt) is not type(negative_prompt):
-                raise TypeError(
-                    f"`negative_prompt` should be the same type to `prompt`, but got {type(negative_prompt)} !="
-                    f" {type(prompt)}."
-                )
-            elif isinstance(negative_prompt, str):
-                uncond_tokens = [negative_prompt]
-            elif batch_size != len(negative_prompt):
-                raise ValueError(
-                    f"`negative_prompt`: {negative_prompt} has batch size {len(negative_prompt)}, but `prompt`:"
-                    f" {prompt} has batch size {batch_size}. Please make sure that passed `negative_prompt` matches"
-                    " the batch size of `prompt`."
-                )
-            else:
-                uncond_tokens = negative_prompt
-
-            max_length = text_input_ids.shape[-1]
-            uncond_input = self.tokenizer(
-                uncond_tokens,
-                padding="max_length",
-                max_length=max_length,
-                truncation=True,
-                return_tensors="pd",
-            )
-
-            if config.get("use_attention_mask", None) is not None and config["use_attention_mask"]:
-                attention_mask = uncond_input.attention_mask
-            else:
-                attention_mask = None
-
-            uncond_embeddings = self.text_encoder(
-                uncond_input.input_ids,
-                attention_mask=attention_mask,
-            )
-            uncond_embeddings = uncond_embeddings[0]
-
-            # duplicate unconditional embeddings for each generation per prompt, using mps friendly method
-            seq_len = uncond_embeddings.shape[1]
-            uncond_embeddings = uncond_embeddings.tile([1, num_images_per_prompt, 1])
-            uncond_embeddings = uncond_embeddings.reshape([batch_size * num_images_per_prompt, seq_len, -1])
-
-            # For classifier free guidance, we need to do two forward passes.
-            # Here we concatenate the unconditional and text embeddings into a single batch
-            # to avoid doing two forward passes
-            text_embeddings = paddle.concat([uncond_embeddings, text_embeddings])
-
-        return text_embeddings
-
-    # Copied from diffusers.pipelines.stable_diffusion.pipeline_stable_diffusion.StableDiffusionPipeline.run_safety_checker
-    def run_safety_checker(self, image, dtype):
-        if self.safety_checker is not None:
-            safety_checker_input = self.feature_extractor(self.numpy_to_pil(image), return_tensors="pd")
-            image, has_nsfw_concept = self.safety_checker(
-                images=image, clip_input=safety_checker_input.pixel_values.cast(dtype)
-            )
-        else:
-            has_nsfw_concept = None
-        return image, has_nsfw_concept
-
-    # Copied from diffusers.pipelines.stable_diffusion.pipeline_stable_diffusion.StableDiffusionPipeline.prepare_extra_step_kwargs
-    def prepare_extra_step_kwargs(self, generator, eta):
-        # prepare extra kwargs for the scheduler step, since not all schedulers have the same signature
-        # eta (η) is only used with the DDIMScheduler, it will be ignored for other schedulers.
-        # eta corresponds to η in DDIM paper: https://arxiv.org/abs/2010.02502
-        # and should be between [0, 1]
-
-        accepts_eta = "eta" in set(inspect.signature(self.scheduler.step).parameters.keys())
-        extra_step_kwargs = {}
-        if accepts_eta:
-            extra_step_kwargs["eta"] = eta
-
-        # check if the scheduler accepts generator
-        accepts_generator = "generator" in set(inspect.signature(self.scheduler.step).parameters.keys())
-        if accepts_generator:
-            extra_step_kwargs["generator"] = generator
-        return extra_step_kwargs
-
-    # Copied from diffusers.pipelines.stable_diffusion.pipeline_stable_diffusion.StableDiffusionPipeline.decode_latents
-    def decode_latents(self, latents):
-        latents = 1 / 0.18215 * latents
-        image = self.vae.decode(latents).sample
-        image = (image / 2 + 0.5).clip(0, 1)
-        # we always cast to float32 as this does not cause significant overhead and is compatible with bfloa16
-        image = image.transpose([0, 2, 3, 1]).cast("float32").numpy()
-        return image
-
-    # Copied from diffusers.pipelines.stable_diffusion.pipeline_stable_diffusion.StableDiffusionPipeline.check_inputs
-    def check_inputs(self, prompt, height, width, callback_steps):
-        if not isinstance(prompt, str) and not isinstance(prompt, list):
-            raise ValueError(f"`prompt` has to be of type `str` or `list` but is {type(prompt)}")
-
-        if height % 8 != 0 or width % 8 != 0:
-            raise ValueError(f"`height` and `width` have to be divisible by 8 but are {height} and {width}.")
-
-        if (callback_steps is None) or (
-            callback_steps is not None and (not isinstance(callback_steps, int) or callback_steps <= 0)
-        ):
-            raise ValueError(
-                f"`callback_steps` has to be a positive integer but is {callback_steps} of type"
-                f" {type(callback_steps)}."
-            )
-
-    # Copied from diffusers.pipelines.stable_diffusion.pipeline_stable_diffusion.StableDiffusionPipeline.prepare_latents
-    def prepare_latents(self, batch_size, num_channels_latents, height, width, dtype, generator, latents=None):
-        shape = [batch_size, num_channels_latents, height // self.vae_scale_factor, width // self.vae_scale_factor]
-        if isinstance(generator, list) and len(generator) != batch_size:
-            raise ValueError(
-                f"You have passed a list of generators of length {len(generator)}, but requested an effective batch"
-                f" size of {batch_size}. Make sure the batch size matches the length of the generators."
-            )
-
-        if latents is None:
-            if isinstance(generator, list):
-                shape = [
-                    1,
-                ] + shape[1:]
-                latents = [paddle.randn(shape, generator=generator[i], dtype=dtype) for i in range(batch_size)]
-                latents = paddle.concat(latents, axis=0)
-            else:
-                latents = paddle.randn(shape, generator=generator, dtype=dtype)
-        else:
-            if latents.shape != shape:
-                raise ValueError(f"Unexpected latents shape, got {latents.shape}, expected {shape}")
-
-        # scale the initial noise by the standard deviation required by the scheduler
-        latents = latents * self.scheduler.init_noise_sigma
-        return latents
-
-    def prepare_mask_latents(
-        self, mask, masked_image, batch_size, height, width, dtype, generator, do_classifier_free_guidance
-    ):
-        # resize the mask to latents shape as we concatenate the mask to the latents
-        # we do that before converting to dtype to avoid breaking in case we're using cpu_offload
-        # and half precision
-        mask = F.interpolate(mask, size=(height // self.vae_scale_factor, width // self.vae_scale_factor))
-        mask = mask.cast(dtype=dtype)
-
-        masked_image = masked_image.cast(dtype)
-
-        # encode the mask image into latents space so we can concatenate it to the latents
-        if isinstance(generator, list):
-            masked_image_latents = [
-                self.vae.encode(masked_image[i : i + 1]).latent_dist.sample(generator=generator[i])
-                for i in range(batch_size)
-            ]
-            masked_image_latents = paddle.concat(masked_image_latents, axis=0)
-        else:
-            masked_image_latents = self.vae.encode(masked_image).latent_dist.sample(generator=generator)
-        masked_image_latents = 0.18215 * masked_image_latents
-
-        # duplicate mask and masked_image_latents for each generation per prompt, using mps friendly method
-        if mask.shape[0] < batch_size:
-            if not batch_size % mask.shape[0] == 0:
-                raise ValueError(
-                    "The passed mask and the required batch size don't match. Masks are supposed to be duplicated to"
-                    f" a total batch size of {batch_size}, but {mask.shape[0]} masks were passed. Make sure the number"
-                    " of masks that you pass is divisible by the total requested batch size."
-                )
-            mask = mask.tile([batch_size // mask.shape[0], 1, 1, 1])
-        if masked_image_latents.shape[0] < batch_size:
-            if not batch_size % masked_image_latents.shape[0] == 0:
-                raise ValueError(
-                    "The passed images and the required batch size don't match. Images are supposed to be duplicated"
-                    f" to a total batch size of {batch_size}, but {masked_image_latents.shape[0]} images were passed."
-                    " Make sure the number of images that you pass is divisible by the total requested batch size."
-                )
-            masked_image_latents = masked_image_latents.tile([batch_size // masked_image_latents.shape[0], 1, 1, 1])
-
-        mask = paddle.concat([mask] * 2) if do_classifier_free_guidance else mask
-        masked_image_latents = (
-            paddle.concat([masked_image_latents] * 2) if do_classifier_free_guidance else masked_image_latents
-        )
-
-        masked_image_latents = masked_image_latents.cast(dtype)
-        return mask, masked_image_latents
-
-    @paddle.no_grad()
-    def __call__(
-        self,
-        prompt: Union[str, List[str]],
-        image: Union[paddle.Tensor, PIL.Image.Image],
-        mask_image: Union[paddle.Tensor, PIL.Image.Image],
-        height: Optional[int] = None,
-        width: Optional[int] = None,
-        num_inference_steps: int = 50,
-        guidance_scale: float = 7.5,
-        negative_prompt: Optional[Union[str, List[str]]] = None,
-        num_images_per_prompt: Optional[int] = 1,
-        eta: float = 0.0,
-        generator: Optional[Union[paddle.Generator, List[paddle.Generator]]] = None,
-        latents: Optional[paddle.Tensor] = None,
-        output_type: Optional[str] = "pil",
-        return_dict: bool = True,
-        callback: Optional[Callable[[int, int, paddle.Tensor], None]] = None,
-        callback_steps: Optional[int] = 1,
-    ):
-        r"""
-        Function invoked when calling the pipeline for generation.
-
-        Args:
-            prompt (`str` or `List[str]`):
-                The prompt or prompts to guide the image generation.
-            image (`PIL.Image.Image`):
-                `Image`, or tensor representing an image batch which will be inpainted, *i.e.* parts of the image will
-                be masked out with `mask_image` and repainted according to `prompt`.
-            mask_image (`PIL.Image.Image`):
-                `Image`, or tensor representing an image batch, to mask `image`. White pixels in the mask will be
-                repainted, while black pixels will be preserved. If `mask_image` is a PIL image, it will be converted
-                to a single channel (luminance) before use. If it's a tensor, it should contain one color channel (L)
-                instead of 3, so the expected shape would be `(B, H, W, 1)`.
-            height (`int`, *optional*, defaults to self.unet.config.sample_size * self.vae_scale_factor):
-                The height in pixels of the generated image.
-            width (`int`, *optional*, defaults to self.unet.config.sample_size * self.vae_scale_factor):
-                The width in pixels of the generated image.
-            num_inference_steps (`int`, *optional*, defaults to 50):
-                The number of denoising steps. More denoising steps usually lead to a higher quality image at the
-                expense of slower inference.
-            guidance_scale (`float`, *optional*, defaults to 7.5):
-                Guidance scale as defined in [Classifier-Free Diffusion Guidance](https://arxiv.org/abs/2207.12598).
-                `guidance_scale` is defined as `w` of equation 2. of [Imagen
-                Paper](https://arxiv.org/pdf/2205.11487.pdf). Guidance scale is enabled by setting `guidance_scale >
-                1`. Higher guidance scale encourages to generate images that are closely linked to the text `prompt`,
-                usually at the expense of lower image quality.
-            negative_prompt (`str` or `List[str]`, *optional*):
-                The prompt or prompts not to guide the image generation. Ignored when not using guidance (i.e., ignored
-                if `guidance_scale` is less than `1`).
-            num_images_per_prompt (`int`, *optional*, defaults to 1):
-                The number of images to generate per prompt.
-            eta (`float`, *optional*, defaults to 0.0):
-                Corresponds to parameter eta (η) in the DDIM paper: https://arxiv.org/abs/2010.02502. Only applies to
-                [`schedulers.DDIMScheduler`], will be ignored for others.
-            generator (`paddle.Generator`, *optional*):
-                One or a list of paddle generator(s) to make generation deterministic.
-            latents (`paddle.Tensor`, *optional*):
-                Pre-generated noisy latents, sampled from a Gaussian distribution, to be used as inputs for image
-                generation. Can be used to tweak the same generation with different prompts. If not provided, a latents
-                tensor will ge generated by sampling using the supplied random `generator`.
-            output_type (`str`, *optional*, defaults to `"pil"`):
-                The output format of the generate image. Choose between
-                [PIL](https://pillow.readthedocs.io/en/stable/): `PIL.Image.Image` or `np.array`.
-            return_dict (`bool`, *optional*, defaults to `True`):
-                Whether or not to return a [`~pipelines.stable_diffusion.StableDiffusionPipelineOutput`] instead of a
-                plain tuple.
-            callback (`Callable`, *optional*):
-                A function that will be called every `callback_steps` steps during inference. The function will be
-                called with the following arguments: `callback(step: int, timestep: int, latents: paddle.Tensor)`.
-            callback_steps (`int`, *optional*, defaults to 1):
-                The frequency at which the `callback` function will be called. If not specified, the callback will be
-                called at every step.
-
-        Returns:
-            [`~pipelines.stable_diffusion.StableDiffusionPipelineOutput`] or `tuple`:
-            [`~pipelines.stable_diffusion.StableDiffusionPipelineOutput`] if `return_dict` is True, otherwise a `tuple.
-            When returning a tuple, the first element is a list with the generated images, and the second element is a
-            list of `bool`s denoting whether the corresponding generated image likely represents "not-safe-for-work"
-            (nsfw) content, according to the `safety_checker`.
-        """
-        # 0. Default height and width to unet
-        height = height or self.unet.config.sample_size * self.vae_scale_factor
-        width = width or self.unet.config.sample_size * self.vae_scale_factor
-
-        # 1. Check inputs
-        self.check_inputs(prompt, height, width, callback_steps)
-
-        # 2. Define call parameters
-        batch_size = 1 if isinstance(prompt, str) else len(prompt)
-        # here `guidance_scale` is defined analog to the guidance weight `w` of equation (2)
-        # of the Imagen paper: https://arxiv.org/pdf/2205.11487.pdf . `guidance_scale = 1`
-        # corresponds to doing no classifier free guidance.
-        do_classifier_free_guidance = guidance_scale > 1.0
-
-        # 3. Encode input prompt
-        text_embeddings = self._encode_prompt(
-            prompt, num_images_per_prompt, do_classifier_free_guidance, negative_prompt
-        )
-
-        # 4. Preprocess mask and image
-        mask, masked_image = prepare_mask_and_masked_image(image, mask_image)
-
-        # 5. set timesteps
-        self.scheduler.set_timesteps(num_inference_steps)
-        timesteps = self.scheduler.timesteps
-
-        # 6. Prepare latent variables
-        num_channels_latents = self.vae.config.latent_channels
-        latents = self.prepare_latents(
-            batch_size * num_images_per_prompt,
-            num_channels_latents,
-            height,
-            width,
-            text_embeddings.dtype,
-            generator,
-            latents,
-        )
-
-        # 7. Prepare mask latent variables
-        mask, masked_image_latents = self.prepare_mask_latents(
-            mask,
-            masked_image,
-            batch_size * num_images_per_prompt,
-            height,
-            width,
-            text_embeddings.dtype,
-            generator,
-            do_classifier_free_guidance,
-        )
-
-        # 8. Check that sizes of mask, masked image and latents match
-        num_channels_mask = mask.shape[1]
-        num_channels_masked_image = masked_image_latents.shape[1]
-        if num_channels_latents + num_channels_mask + num_channels_masked_image != self.unet.config.in_channels:
-            raise ValueError(
-                f"Incorrect configuration settings! The config of `pipeline.unet`: {self.unet.config} expects"
-                f" {self.unet.config.in_channels} but received `num_channels_latents`: {num_channels_latents} +"
-                f" `num_channels_mask`: {num_channels_mask} + `num_channels_masked_image`: {num_channels_masked_image}"
-                f" = {num_channels_latents+num_channels_masked_image+num_channels_mask}. Please verify the config of"
-                " `pipeline.unet` or your `mask_image` or `image` input."
-            )
-
-        # 9. Prepare extra step kwargs. TODO: Logic should ideally just be moved out of the pipeline
-        extra_step_kwargs = self.prepare_extra_step_kwargs(generator, eta)
-
-        # 10. Denoising loop
-        num_warmup_steps = len(timesteps) - num_inference_steps * self.scheduler.order
-        with self.progress_bar(total=num_inference_steps) as progress_bar:
-            for i, t in enumerate(timesteps):
-                # expand the latents if we are doing classifier free guidance
-                latent_model_input = paddle.concat([latents] * 2) if do_classifier_free_guidance else latents
-
-                # concat latents, mask, masked_image_latents in the channel dimension
-                latent_model_input = self.scheduler.scale_model_input(latent_model_input, t)
-                latent_model_input = paddle.concat([latent_model_input, mask, masked_image_latents], axis=1)
-
-                # predict the noise residual
-                noise_pred = self.unet(latent_model_input, t, encoder_hidden_states=text_embeddings).sample
-
-                # perform guidance
-                if do_classifier_free_guidance:
-                    noise_pred_uncond, noise_pred_text = noise_pred.chunk(2)
-                    noise_pred = noise_pred_uncond + guidance_scale * (noise_pred_text - noise_pred_uncond)
-
-                # compute the previous noisy sample x_t -> x_t-1
-                latents = self.scheduler.step(noise_pred, t, latents, **extra_step_kwargs).prev_sample
-
-                # call the callback, if provided
-                if i == len(timesteps) - 1 or ((i + 1) > num_warmup_steps and (i + 1) % self.scheduler.order == 0):
-                    progress_bar.update()
-                    if callback is not None and i % callback_steps == 0:
-                        callback(i, t, latents)
-
-        # 11. Post-processing
-        image = self.decode_latents(latents)
-
-        # 12. Run safety checker
-        image, has_nsfw_concept = self.run_safety_checker(image, text_embeddings.dtype)
-
-        # 13. Convert to PIL
-        if output_type == "pil":
-            image = self.numpy_to_pil(image)
-
-        if not return_dict:
-            return (image, has_nsfw_concept)
-
-        return StableDiffusionPipelineOutput(images=image, nsfw_content_detected=has_nsfw_concept)
diff --git a/spaces/2023Liu2023/bingo/src/components/ui/alert-dialog.tsx b/spaces/2023Liu2023/bingo/src/components/ui/alert-dialog.tsx
deleted file mode 100644
index 17fec4d16510328deacc1416569173c97761ef72..0000000000000000000000000000000000000000
--- a/spaces/2023Liu2023/bingo/src/components/ui/alert-dialog.tsx
+++ /dev/null
@@ -1,150 +0,0 @@
-'use client'
-
-import * as React from 'react'
-import * as AlertDialogPrimitive from '@radix-ui/react-alert-dialog'
-
-import { cn } from '@/lib/utils'
-import { buttonVariants } from '@/components/ui/button'
-
-const AlertDialog = AlertDialogPrimitive.Root
-
-const AlertDialogTrigger = AlertDialogPrimitive.Trigger
-
-const AlertDialogPortal = ({
-  className,
-  children,
-  ...props
-}: AlertDialogPrimitive.AlertDialogPortalProps) => (
-  <AlertDialogPrimitive.Portal className={cn(className)} {...props}>
-    <div className="fixed inset-0 z-50 flex items-end justify-center sm:items-center">
-      {children}
-    </div>
-  </AlertDialogPrimitive.Portal>
-)
-AlertDialogPortal.displayName = AlertDialogPrimitive.Portal.displayName
-
-const AlertDialogOverlay = React.forwardRef<
-  React.ElementRef<typeof AlertDialogPrimitive.Overlay>,
-  React.ComponentPropsWithoutRef<typeof AlertDialogPrimitive.Overlay>
->(({ className, children, ...props }, ref) => (
-  <AlertDialogPrimitive.Overlay
-    className={cn(
-      'fixed inset-0 z-50 bg-background/80 backdrop-blur-sm transition-opacity animate-in fade-in',
-      className
-    )}
-    {...props}
-    ref={ref}
-  />
-))
-AlertDialogOverlay.displayName = AlertDialogPrimitive.Overlay.displayName
-
-const AlertDialogContent = React.forwardRef<
-  React.ElementRef<typeof AlertDialogPrimitive.Content>,
-  React.ComponentPropsWithoutRef<typeof AlertDialogPrimitive.Content>
->(({ className, ...props }, ref) => (
-  <AlertDialogPortal>
-    <AlertDialogOverlay />
-    <AlertDialogPrimitive.Content
-      ref={ref}
-      className={cn(
-        'fixed z-50 grid w-full max-w-lg scale-100 gap-4 border bg-background p-6 opacity-100 shadow-lg animate-in fade-in-90 slide-in-from-bottom-10 sm:rounded-lg sm:zoom-in-90 sm:slide-in-from-bottom-0 md:w-full',
-        className
-      )}
-      {...props}
-    />
-  </AlertDialogPortal>
-))
-AlertDialogContent.displayName = AlertDialogPrimitive.Content.displayName
-
-const AlertDialogHeader = ({
-  className,
-  ...props
-}: React.HTMLAttributes<HTMLDivElement>) => (
-  <div
-    className={cn(
-      'flex flex-col space-y-2 text-center sm:text-left',
-      className
-    )}
-    {...props}
-  />
-)
-AlertDialogHeader.displayName = 'AlertDialogHeader'
-
-const AlertDialogFooter = ({
-  className,
-  ...props
-}: React.HTMLAttributes<HTMLDivElement>) => (
-  <div
-    className={cn(
-      'flex flex-col-reverse sm:flex-row sm:justify-end sm:space-x-2',
-      className
-    )}
-    {...props}
-  />
-)
-AlertDialogFooter.displayName = 'AlertDialogFooter'
-
-const AlertDialogTitle = React.forwardRef<
-  React.ElementRef<typeof AlertDialogPrimitive.Title>,
-  React.ComponentPropsWithoutRef<typeof AlertDialogPrimitive.Title>
->(({ className, ...props }, ref) => (
-  <AlertDialogPrimitive.Title
-    ref={ref}
-    className={cn('text-lg font-semibold', className)}
-    {...props}
-  />
-))
-AlertDialogTitle.displayName = AlertDialogPrimitive.Title.displayName
-
-const AlertDialogDescription = React.forwardRef<
-  React.ElementRef<typeof AlertDialogPrimitive.Description>,
-  React.ComponentPropsWithoutRef<typeof AlertDialogPrimitive.Description>
->(({ className, ...props }, ref) => (
-  <AlertDialogPrimitive.Description
-    ref={ref}
-    className={cn('text-sm text-muted-foreground', className)}
-    {...props}
-  />
-))
-AlertDialogDescription.displayName =
-  AlertDialogPrimitive.Description.displayName
-
-const AlertDialogAction = React.forwardRef<
-  React.ElementRef<typeof AlertDialogPrimitive.Action>,
-  React.ComponentPropsWithoutRef<typeof AlertDialogPrimitive.Action>
->(({ className, ...props }, ref) => (
-  <AlertDialogPrimitive.Action
-    ref={ref}
-    className={cn(buttonVariants(), className)}
-    {...props}
-  />
-))
-AlertDialogAction.displayName = AlertDialogPrimitive.Action.displayName
-
-const AlertDialogCancel = React.forwardRef<
-  React.ElementRef<typeof AlertDialogPrimitive.Cancel>,
-  React.ComponentPropsWithoutRef<typeof AlertDialogPrimitive.Cancel>
->(({ className, ...props }, ref) => (
-  <AlertDialogPrimitive.Cancel
-    ref={ref}
-    className={cn(
-      buttonVariants({ variant: 'outline' }),
-      'mt-2 sm:mt-0',
-      className
-    )}
-    {...props}
-  />
-))
-AlertDialogCancel.displayName = AlertDialogPrimitive.Cancel.displayName
-
-export {
-  AlertDialog,
-  AlertDialogTrigger,
-  AlertDialogContent,
-  AlertDialogHeader,
-  AlertDialogFooter,
-  AlertDialogTitle,
-  AlertDialogDescription,
-  AlertDialogAction,
-  AlertDialogCancel
-}
diff --git a/spaces/AIFILMS/generate_human_motion/VQ-Trans/dataset/dataset_TM_train.py b/spaces/AIFILMS/generate_human_motion/VQ-Trans/dataset/dataset_TM_train.py
deleted file mode 100644
index 0b0223effb01c1cf57fa6b2b6fb8d9d01b83f84a..0000000000000000000000000000000000000000
--- a/spaces/AIFILMS/generate_human_motion/VQ-Trans/dataset/dataset_TM_train.py
+++ /dev/null
@@ -1,161 +0,0 @@
-import torch
-from torch.utils import data
-import numpy as np
-from os.path import join as pjoin
-import random
-import codecs as cs
-from tqdm import tqdm
-import utils.paramUtil as paramUtil
-from torch.utils.data._utils.collate import default_collate
-
-
-def collate_fn(batch):
-    batch.sort(key=lambda x: x[3], reverse=True)
-    return default_collate(batch)
-
-
-'''For use of training text-2-motion generative model'''
-class Text2MotionDataset(data.Dataset):
-    def __init__(self, dataset_name, feat_bias = 5, unit_length = 4, codebook_size = 1024, tokenizer_name=None):
-        
-        self.max_length = 64
-        self.pointer = 0
-        self.dataset_name = dataset_name
-
-        self.unit_length = unit_length
-        # self.mot_start_idx = codebook_size
-        self.mot_end_idx = codebook_size
-        self.mot_pad_idx = codebook_size + 1
-        if dataset_name == 't2m':
-            self.data_root = './dataset/HumanML3D'
-            self.motion_dir = pjoin(self.data_root, 'new_joint_vecs')
-            self.text_dir = pjoin(self.data_root, 'texts')
-            self.joints_num = 22
-            radius = 4
-            fps = 20
-            self.max_motion_length = 26 if unit_length == 8 else 51
-            dim_pose = 263
-            kinematic_chain = paramUtil.t2m_kinematic_chain
-        elif dataset_name == 'kit':
-            self.data_root = './dataset/KIT-ML'
-            self.motion_dir = pjoin(self.data_root, 'new_joint_vecs')
-            self.text_dir = pjoin(self.data_root, 'texts')
-            self.joints_num = 21
-            radius = 240 * 8
-            fps = 12.5
-            dim_pose = 251
-            self.max_motion_length = 26 if unit_length == 8 else 51
-            kinematic_chain = paramUtil.kit_kinematic_chain
-
-        split_file = pjoin(self.data_root, 'train.txt')
-
-
-        id_list = []
-        with cs.open(split_file, 'r') as f:
-            for line in f.readlines():
-                id_list.append(line.strip())
-
-        new_name_list = []
-        data_dict = {}
-        for name in tqdm(id_list):
-            try:
-                m_token_list = np.load(pjoin(self.data_root, tokenizer_name, '%s.npy'%name))
-
-                # Read text
-                with cs.open(pjoin(self.text_dir, name + '.txt')) as f:
-                    text_data = []
-                    flag = False
-                    lines = f.readlines()
-
-                    for line in lines:
-                        try:
-                            text_dict = {}
-                            line_split = line.strip().split('#')
-                            caption = line_split[0]
-                            t_tokens = line_split[1].split(' ')
-                            f_tag = float(line_split[2])
-                            to_tag = float(line_split[3])
-                            f_tag = 0.0 if np.isnan(f_tag) else f_tag
-                            to_tag = 0.0 if np.isnan(to_tag) else to_tag
-
-                            text_dict['caption'] = caption
-                            text_dict['tokens'] = t_tokens
-                            if f_tag == 0.0 and to_tag == 0.0:
-                                flag = True
-                                text_data.append(text_dict)
-                            else:
-                                m_token_list_new = [tokens[int(f_tag*fps/unit_length) : int(to_tag*fps/unit_length)] for tokens in m_token_list if int(f_tag*fps/unit_length) < int(to_tag*fps/unit_length)]
-
-                                if len(m_token_list_new) == 0:
-                                    continue
-                                new_name = '%s_%f_%f'%(name, f_tag, to_tag)
-
-                                data_dict[new_name] = {'m_token_list': m_token_list_new,
-                                                       'text':[text_dict]}
-                                new_name_list.append(new_name)
-                        except:
-                            pass
-
-                if flag:
-                    data_dict[name] = {'m_token_list': m_token_list,
-                                       'text':text_data}
-                    new_name_list.append(name)
-            except:
-                pass
-        self.data_dict = data_dict
-        self.name_list = new_name_list
-
-    def __len__(self):
-        return len(self.data_dict)
-
-    def __getitem__(self, item):
-        data = self.data_dict[self.name_list[item]]
-        m_token_list, text_list = data['m_token_list'], data['text']
-        m_tokens = random.choice(m_token_list)
-
-        text_data = random.choice(text_list)
-        caption= text_data['caption']
-
-        
-        coin = np.random.choice([False, False, True])
-        # print(len(m_tokens))
-        if coin:
-            # drop one token at the head or tail
-            coin2 = np.random.choice([True, False])
-            if coin2:
-                m_tokens = m_tokens[:-1]
-            else:
-                m_tokens = m_tokens[1:]
-        m_tokens_len = m_tokens.shape[0]
-
-        if m_tokens_len+1 < self.max_motion_length:
-            m_tokens = np.concatenate([m_tokens, np.ones((1), dtype=int) * self.mot_end_idx, np.ones((self.max_motion_length-1-m_tokens_len), dtype=int) * self.mot_pad_idx], axis=0)
-        else:
-            m_tokens = np.concatenate([m_tokens, np.ones((1), dtype=int) * self.mot_end_idx], axis=0)
-
-        return caption, m_tokens.reshape(-1), m_tokens_len
-
-
-
-
-def DATALoader(dataset_name,
-                batch_size, codebook_size, tokenizer_name, unit_length=4,
-                num_workers = 8) : 
-
-    train_loader = torch.utils.data.DataLoader(Text2MotionDataset(dataset_name, codebook_size = codebook_size, tokenizer_name = tokenizer_name, unit_length=unit_length),
-                                              batch_size,
-                                              shuffle=True,
-                                              num_workers=num_workers,
-                                              #collate_fn=collate_fn,
-                                              drop_last = True)
-    
-
-    return train_loader
-
-
-def cycle(iterable):
-    while True:
-        for x in iterable:
-            yield x
-
-
diff --git a/spaces/AIFILMS/generate_human_motion/VQ-Trans/options/get_eval_option.py b/spaces/AIFILMS/generate_human_motion/VQ-Trans/options/get_eval_option.py
deleted file mode 100644
index d0989ba1a8116068753ada2cb1806744e4512447..0000000000000000000000000000000000000000
--- a/spaces/AIFILMS/generate_human_motion/VQ-Trans/options/get_eval_option.py
+++ /dev/null
@@ -1,83 +0,0 @@
-from argparse import Namespace
-import re
-from os.path import join as pjoin
-
-
-def is_float(numStr):
-    flag = False
-    numStr = str(numStr).strip().lstrip('-').lstrip('+')
-    try:
-        reg = re.compile(r'^[-+]?[0-9]+\.[0-9]+$')
-        res = reg.match(str(numStr))
-        if res:
-            flag = True
-    except Exception as ex:
-        print("is_float() - error: " + str(ex))
-    return flag
-
-
-def is_number(numStr):
-    flag = False
-    numStr = str(numStr).strip().lstrip('-').lstrip('+')
-    if str(numStr).isdigit():
-        flag = True
-    return flag
-
-
-def get_opt(opt_path, device):
-    opt = Namespace()
-    opt_dict = vars(opt)
-
-    skip = ('-------------- End ----------------',
-            '------------ Options -------------',
-            '\n')
-    print('Reading', opt_path)
-    with open(opt_path) as f:
-        for line in f:
-            if line.strip() not in skip:
-                # print(line.strip())
-                key, value = line.strip().split(': ')
-                if value in ('True', 'False'):
-                    opt_dict[key] = (value == 'True')
-                #     print(key, value)
-                elif is_float(value):
-                    opt_dict[key] = float(value)
-                elif is_number(value):
-                    opt_dict[key] = int(value)
-                else:
-                    opt_dict[key] = str(value)
-
-    # print(opt)
-    opt_dict['which_epoch'] = 'finest'
-    opt.save_root = pjoin(opt.checkpoints_dir, opt.dataset_name, opt.name)
-    opt.model_dir = pjoin(opt.save_root, 'model')
-    opt.meta_dir = pjoin(opt.save_root, 'meta')
-
-    if opt.dataset_name == 't2m':
-        opt.data_root = './dataset/HumanML3D/'
-        opt.motion_dir = pjoin(opt.data_root, 'new_joint_vecs')
-        opt.text_dir = pjoin(opt.data_root, 'texts')
-        opt.joints_num = 22
-        opt.dim_pose = 263
-        opt.max_motion_length = 196
-        opt.max_motion_frame = 196
-        opt.max_motion_token = 55
-    elif opt.dataset_name == 'kit':
-        opt.data_root = './dataset/KIT-ML/'
-        opt.motion_dir = pjoin(opt.data_root, 'new_joint_vecs')
-        opt.text_dir = pjoin(opt.data_root, 'texts')
-        opt.joints_num = 21
-        opt.dim_pose = 251
-        opt.max_motion_length = 196
-        opt.max_motion_frame = 196
-        opt.max_motion_token = 55
-    else:
-        raise KeyError('Dataset not recognized')
-
-    opt.dim_word = 300
-    opt.num_classes = 200 // opt.unit_length
-    opt.is_train = False
-    opt.is_continue = False
-    opt.device = device
-
-    return opt
\ No newline at end of file
diff --git a/spaces/AIGC-Audio/AudioGPT/text_to_audio/Make_An_Audio/ldm/models/diffusion/sampling_util.py b/spaces/AIGC-Audio/AudioGPT/text_to_audio/Make_An_Audio/ldm/models/diffusion/sampling_util.py
deleted file mode 100644
index 7eff02be6d7c54d43ee6680636ac0698dd3b3f33..0000000000000000000000000000000000000000
--- a/spaces/AIGC-Audio/AudioGPT/text_to_audio/Make_An_Audio/ldm/models/diffusion/sampling_util.py
+++ /dev/null
@@ -1,22 +0,0 @@
-import torch
-import numpy as np
-
-
-def append_dims(x, target_dims):
-    """Appends dimensions to the end of a tensor until it has target_dims dimensions.
-    From https://github.com/crowsonkb/k-diffusion/blob/master/k_diffusion/utils.py"""
-    dims_to_append = target_dims - x.ndim
-    if dims_to_append < 0:
-        raise ValueError(f'input has {x.ndim} dims but target_dims is {target_dims}, which is less')
-    return x[(...,) + (None,) * dims_to_append]
-
-
-def norm_thresholding(x0, value):
-    s = append_dims(x0.pow(2).flatten(1).mean(1).sqrt().clamp(min=value), x0.ndim)
-    return x0 * (value / s)
-
-
-def spatial_norm_thresholding(x0, value):
-    # b c h w
-    s = x0.pow(2).mean(1, keepdim=True).sqrt().clamp(min=value)
-    return x0 * (value / s)
\ No newline at end of file
diff --git a/spaces/AIWaves/SOP_Generation-single/utils.py b/spaces/AIWaves/SOP_Generation-single/utils.py
deleted file mode 100644
index 275e6280a80187f9656987ee702e5719a0944e08..0000000000000000000000000000000000000000
--- a/spaces/AIWaves/SOP_Generation-single/utils.py
+++ /dev/null
@@ -1,482 +0,0 @@
-# coding=utf-8
-# Copyright 2023  The AIWaves Inc. team.
-
-#
-# Licensed under the Apache License, Version 2.0 (the "License");
-# you may not use this file except in compliance with the License.
-# You may obtain a copy of the License at
-#
-#     http://www.apache.org/licenses/LICENSE-2.0
-#
-# Unless required by applicable law or agreed to in writing, software
-# distributed under the License is distributed on an "AS IS" BASIS,
-# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
-# See the License for the specific language governing permissions and
-# limitations under the License.
-"""helper functions for an LLM autonoumous agent"""
-import csv
-import random
-import json
-import pandas
-import numpy as np
-import requests
-import torch
-from tqdm import tqdm
-import re
-import datetime
-import string
-import random
-import os
-import openai
-from text2vec import semantic_search
-import re
-import datetime
-from langchain.document_loaders import UnstructuredFileLoader
-from langchain.text_splitter import CharacterTextSplitter
-from sentence_transformers import SentenceTransformer
-
-embed_model_name = os.environ["Embed_Model"] if "Embed_Model" in os.environ else "text-embedding-ada-002"
-if embed_model_name in ["text-embedding-ada-002"]:
-    pass
-else:
-    embedding_model = SentenceTransformer(
-                embed_model_name, device=torch.device("cpu")
-            )
-
-def get_embedding(sentence):
-    if embed_model_name in ["text-embedding-ada-002"]:
-        openai.api_key = os.environ["API_KEY"]
-        if "PROXY" in os.environ:
-            assert "http:" in os.environ["PROXY"] or "socks" in os.environ["PROXY"],"PROXY error,PROXY must be http or socks"
-            openai.proxy = os.environ["PROXY"]
-        if "API_BASE" in os.environ:
-            openai.api_base = os.environ["API_BASE"]
-        embedding_model = openai.Embedding
-        embed = embedding_model.create(
-        model=embed_model_name,
-        input=sentence
-    )
-        embed = embed["data"][0]["embedding"]
-        embed = torch.tensor(embed,dtype=torch.float32)
-    else:
-        embed = embedding_model.encode(sentence,convert_to_tensor=True)
-    if len(embed.shape)==1:
-        embed = embed.unsqueeze(0)
-    return embed
-
-
-def get_code():
-    return "".join(random.sample(string.ascii_letters + string.digits, 8))
-
-
-def get_content_between_a_b(start_tag, end_tag, text):
-    """
-
-    Args:
-        start_tag (str): start_tag
-        end_tag (str): end_tag
-        text (str): complete sentence
-
-    Returns:
-        str: the content between start_tag and end_tag
-    """
-    extracted_text = ""
-    start_index = text.find(start_tag)
-    while start_index != -1:
-        end_index = text.find(end_tag, start_index + len(start_tag))
-        if end_index != -1:
-            extracted_text += text[start_index +
-                                   len(start_tag):end_index] + " "
-            start_index = text.find(start_tag, end_index + len(end_tag))
-        else:
-            break
-
-    return extracted_text.strip()
-
-
-def extract(text, type):
-    """extract the content between <type></type>
-
-    Args:
-        text (str): complete sentence
-        type (str): tag
-
-    Returns:
-        str: content between <type></type>
-    """
-    target_str = get_content_between_a_b(f"<{type}>", f"</{type}>", text)
-    return target_str
-
-def count_files_in_directory(directory):
-    # 获取指定目录下的文件数目
-    file_count = len([f for f in os.listdir(directory) if os.path.isfile(os.path.join(directory, f))])
-    return file_count
-
-def delete_oldest_files(directory, num_to_keep):
-    # 获取目录下文件列表，并按修改时间排序
-    files = [(f, os.path.getmtime(os.path.join(directory, f))) for f in os.listdir(directory) if os.path.isfile(os.path.join(directory, f))]
-
-    # 删除最开始的 num_to_keep 个文件
-    for i in range(min(num_to_keep, len(files))):
-        file_to_delete = os.path.join(directory, files[i][0])
-        os.remove(file_to_delete)
-
-def delete_files_if_exceed_threshold(directory, threshold, num_to_keep):
-    # 获取文件数目并进行处理
-    file_count = count_files_in_directory(directory)
-    if file_count > threshold:
-        delete_count = file_count - num_to_keep
-        delete_oldest_files(directory, delete_count)
-
-def save_logs(log_path, messages, response):
-    if not os.path.exists(log_path):
-        os.mkdir(log_path)
-    delete_files_if_exceed_threshold(log_path, 20, 10)
-    log_path = log_path if log_path else "logs"
-    log = {}
-    log["input"] = messages
-    log["output"] = response
-    os.makedirs(log_path, exist_ok=True)
-    log_file = os.path.join(
-        log_path,
-        datetime.datetime.now().strftime("%Y-%m-%d-%H-%M-%S") + ".json")
-    with open(log_file, "w", encoding="utf-8") as f:
-        json.dump(log, f, ensure_ascii=False, indent=2)
-
-
-
-def semantic_search_word2vec(query_embedding, kb_embeddings, top_k):
-    return semantic_search(query_embedding, kb_embeddings, top_k=top_k)
-
-
-def cut_sent(para):
-    para = re.sub("([。！？\?])([^”’])", r"\1\n\2", para)
-    para = re.sub("(\.{6})([^”’])", r"\1\n\2", para)
-    para = re.sub("(\…{2})([^”’])", r"\1\n\2", para)
-    para = re.sub("([。！？\?][”’])([^，。！？\?])", r"\1\n\2", para)
-    para = para.rstrip()
-    pieces = [i for i in para.split("\n") if i]
-    batch_size = 3
-    chucks = [
-        " ".join(pieces[i:i + batch_size])
-        for i in range(0, len(pieces), batch_size)
-    ]
-    return chucks
-
-
-def process_document(file_path):
-    """
-    Save QA_csv to json.
-    Args:
-        model: LLM to generate embeddings
-        qa_dict: A dict contains Q&A
-        save_path: where to save the json file.
-    Json format:
-        Dict[num,Dict[q:str,a:str,chunk:str,emb:List[float]]
-    """
-    final_dict = {}
-    count = 0
-    if file_path.endswith(".csv"):
-        dataset = pandas.read_csv(file_path)
-        questions = dataset["question"]
-        answers = dataset["answer"]
-        # embedding q+chunk
-        for q, a in zip(questions, answers):
-            for text in cut_sent(a):
-                temp_dict = {}
-                temp_dict["q"] = q
-                temp_dict["a"] = a
-                temp_dict["chunk"] = text
-                temp_dict["emb"] = get_embedding(q + text).tolist()
-                final_dict[count] = temp_dict
-                count += 1
-        # embedding chunk
-        for q, a in zip(questions, answers):
-            for text in cut_sent(a):
-                temp_dict = {}
-                temp_dict["q"] = q
-                temp_dict["a"] = a
-                temp_dict["chunk"] = text
-                temp_dict["emb"] = get_embedding(text).tolist()
-                final_dict[count] = temp_dict
-                count += 1
-        # embedding q
-        for q, a in zip(questions, answers):
-            temp_dict = {}
-            temp_dict["q"] = q
-            temp_dict["a"] = a
-            temp_dict["chunk"] = a
-            temp_dict["emb"] = get_embedding(q).tolist()
-            final_dict[count] = temp_dict
-            count += 1
-        # embedding q+a
-        for q, a in zip(questions, answers):
-            temp_dict = {}
-            temp_dict["q"] = q
-            temp_dict["a"] = a
-            temp_dict["chunk"] = a
-            temp_dict["emb"] = get_embedding(q + a).tolist()
-            final_dict[count] = temp_dict
-            count += 1
-        # embedding a
-        for q, a in zip(questions, answers):
-            temp_dict = {}
-            temp_dict["q"] = q
-            temp_dict["a"] = a
-            temp_dict["chunk"] = a
-            temp_dict["emb"] = get_embedding(a).tolist()
-            final_dict[count] = temp_dict
-            count += 1
-        print(f"finish updating {len(final_dict)} data!")
-        os.makedirs("temp_database", exist_ok=True)
-        save_path = os.path.join(
-            "temp_database/",
-            file_path.split("/")[-1].replace("." + file_path.split(".")[1],
-                                             ".json"),
-        )
-        print(save_path)
-        with open(save_path, "w") as f:
-            json.dump(final_dict, f, ensure_ascii=False, indent=2)
-        return {"knowledge_base": save_path, "type": "QA"}
-    else:
-        loader = UnstructuredFileLoader(file_path)
-        docs = loader.load()
-        text_spiltter = CharacterTextSplitter(chunk_size=200,
-                                              chunk_overlap=100)
-        docs = text_spiltter.split_text(docs[0].page_content)
-        os.makedirs("temp_database", exist_ok=True)
-        save_path = os.path.join(
-            "temp_database/",
-            file_path.replace("." + file_path.split(".")[1], ".json"))
-        final_dict = {}
-        count = 0
-        for c in tqdm(docs):
-            temp_dict = {}
-            temp_dict["chunk"] = c
-            temp_dict["emb"] = get_embedding(c).tolist()
-            final_dict[count] = temp_dict
-            count += 1
-        print(f"finish updating {len(final_dict)} data!")
-        with open(save_path, "w") as f:
-            json.dump(final_dict, f, ensure_ascii=False, indent=2)
-        return {"knowledge_base": save_path, "type": "UnstructuredFile"}
-
-def load_knowledge_base_qa(path):
-    """
-    Load json format knowledge base.
-    """
-    print("path", path)
-    with open(path, "r") as f:
-        data = json.load(f)
-    embeddings = []
-    questions = []
-    answers = []
-    chunks = []
-    for idx in range(len(data.keys())):
-        embeddings.append(data[str(idx)]["emb"])
-        questions.append(data[str(idx)]["q"])
-        answers.append(data[str(idx)]["a"])
-        chunks.append(data[str(idx)]["chunk"])
-    embeddings = np.array(embeddings, dtype=np.float32)
-    embeddings = torch.from_numpy(embeddings).squeeze()
-    return embeddings, questions, answers, chunks
-
-
-def load_knowledge_base_UnstructuredFile(path):
-    """
-    Load json format knowledge base.
-    """
-    with open(path, "r") as f:
-        data = json.load(f)
-    embeddings = []
-    chunks = []
-    for idx in range(len(data.keys())):
-        embeddings.append(data[str(idx)]["emb"])
-        chunks.append(data[str(idx)]["chunk"])
-    embeddings = np.array(embeddings, dtype=np.float32)
-    embeddings = torch.from_numpy(embeddings).squeeze()
-    return embeddings, chunks
-
-
-def cos_sim(a: torch.Tensor, b: torch.Tensor):
-    """
-    Computes the cosine similarity cos_sim(a[i], b[j]) for all i and j.
-    :return: Matrix with res[i][j]  = cos_sim(a[i], b[j])
-    """
-    if not isinstance(a, torch.Tensor):
-        a = torch.tensor(a)
-
-    if not isinstance(b, torch.Tensor):
-        b = torch.tensor(b)
-
-    if len(a.shape) == 1:
-        a = a.unsqueeze(0)
-
-    if len(b.shape) == 1:
-        b = b.unsqueeze(0)
-
-    a_norm = torch.nn.functional.normalize(a, p=2, dim=1)
-    b_norm = torch.nn.functional.normalize(b, p=2, dim=1)
-    return torch.mm(a_norm, b_norm.transpose(0, 1))
-
-
-def matching_a_b(a, b, requirements=None):
-    a_embedder = get_embedding(a)
-    # 获取embedder
-    b_embeder = get_embedding(b)
-    sim_scores = cos_sim(a_embedder, b_embeder)[0]
-    return sim_scores
-
-
-def matching_category(inputtext,
-                      forest_name,
-                      requirements=None,
-                      cat_embedder=None,
-                      top_k=3):
-    """
-    Args:
-        inputtext: the category name to be matched
-        forest: search tree
-        top_k: the default three highest scoring results
-    Return：
-        topk matching_result. List[List] [[top1_name,top2_name,top3_name],[top1_score,top2_score,top3_score]]
-    """
-
-    sim_scores = torch.zeros([100])
-    if inputtext:
-        input_embeder = get_embedding(inputtext)
-        sim_scores = cos_sim(input_embeder, cat_embedder)[0]
-
-    if requirements:
-        requirements = requirements.split(" ")
-        requirements_embedder = get_embedding(requirements)
-        req_scores = cos_sim(requirements_embedder, cat_embedder)
-        req_scores = torch.mean(req_scores, dim=0)
-        total_scores = req_scores
-    else:
-        total_scores = sim_scores
-
-    top_k_cat = torch.topk(total_scores, k=top_k)
-    top_k_score, top_k_idx = top_k_cat[0], top_k_cat[1]
-    top_k_name = [forest_name[top_k_idx[i]] for i in range(0, top_k)]
-
-    return [top_k_name, top_k_score.tolist(), top_k_idx]
-
-
-def sample_with_order_preserved(lst, num):
-    """Randomly sample from the list while maintaining the original order."""
-    indices = list(range(len(lst)))
-    sampled_indices = random.sample(indices, num)
-    sampled_indices.sort()  # 保持原顺序
-    return [lst[i] for i in sampled_indices]
-
-
-def limit_values(data, max_values):
-    """Reduce each key-value list in the dictionary to the specified size, keeping the order of the original list unchanged."""
-    for key, values in data.items():
-        if len(values) > max_values:
-            data[key] = sample_with_order_preserved(values, max_values)
-    return data
-
-
-def limit_keys(data, max_keys):
-    """Reduce the dictionary to the specified number of keys."""
-    keys = list(data.keys())
-    if len(keys) > max_keys:
-        keys = sample_with_order_preserved(keys, max_keys)
-        data = {key: data[key] for key in keys}
-    return data
-
-
-def flatten_dict(nested_dict):
-    """
-    flatten the dictionary
-    """
-    flattened_dict = {}
-    for key, value in nested_dict.items():
-        if isinstance(value, dict):
-            flattened_subdict = flatten_dict(value)
-            flattened_dict.update(flattened_subdict)
-        else:
-            flattened_dict[key] = value
-    return flattened_dict
-
-
-def merge_list(list1, list2):
-    for l in list2:
-        if l not in list1:
-            list1.append(l)
-    return list1
-
-
-def Search_Engines(req):
-    FETSIZE = eval(os.environ["FETSIZE"]) if "FETSIZE" in os.environ else 5
-
-    new_dict = {"keyword": req, "catLeafName": "", "fetchSize": FETSIZE}
-    url = os.environ["SHOPPING_SEARCH"]
-    res = requests.post(
-        url= url,
-        json=new_dict,
-    )
-    user_dict = json.loads(res.text)
-    if "data" in user_dict.keys():
-        request_items = user_dict["data"]["items"]  # 查询到的商品信息JSON
-        top_category = user_dict["data"]["topCategories"]
-        return request_items, top_category
-    else:
-        return []
-
-
-def search_with_api(requirements, categery):
-    
-    FETSIZE = eval(os.environ["FETSIZE"]) if "FETSIZE" in os.environ else 5
-
-    request_items = []
-    all_req_list = requirements.split(" ")  
-    count = 0  
-
-    while len(request_items) < FETSIZE and len(all_req_list) > 0:
-        if count: 
-            all_req_list.pop(0)  
-        all_req = (" ").join(all_req_list)  
-        if categery not in all_req_list:
-            all_req = all_req + " " + categery
-        now_request_items, top_category = Search_Engines(all_req)  
-        request_items = merge_list(request_items, now_request_items)
-        count += 1
-    new_top = []
-    for category in top_category:
-        if "其它" in category or "其它" in category:
-            continue
-        else:
-            new_top.append(category)
-    if len(request_items) > FETSIZE:
-        request_items = request_items[:FETSIZE]
-    return request_items, new_top
-
-
-
-def get_relevant_history(query,history,embeddings):
-    """
-    Retrieve a list of key history entries based on a query using semantic search.
-
-    Args:
-        query (str): The input query for which key history is to be retrieved.
-        history (list): A list of historical key entries.
-        embeddings (numpy.ndarray): An array of embedding vectors for historical entries.
-
-    Returns:
-        list: A list of key history entries most similar to the query.
-    """
-    TOP_K = eval(os.environ["TOP_K"]) if "TOP_K" in os.environ else 2
-    relevant_history = []
-    query_embedding = get_embedding(query)
-    hits = semantic_search(query_embedding, embeddings, top_k=min(TOP_K,embeddings.shape[0]))
-    hits = hits[0]
-    for hit in hits:
-        matching_idx = hit["corpus_id"]
-        try:
-            relevant_history.append(history[matching_idx])
-        except:
-            return []
-    return relevant_history
diff --git a/spaces/AMR-KELEG/ALDi/constants.py b/spaces/AMR-KELEG/ALDi/constants.py
deleted file mode 100644
index cbd591771f4d7d64b7e5b3fa6547aec41eb2183f..0000000000000000000000000000000000000000
--- a/spaces/AMR-KELEG/ALDi/constants.py
+++ /dev/null
@@ -1,4 +0,0 @@
-CHOICE_TEXT = "Input Text"
-CHOICE_FILE = "Upload File"
-TITLE = "ALDi: Arabic Level of Dialectness"
-MODEL_NAME = "AMR-KELEG/Sentence-ALDi"
diff --git a/spaces/Abhilashvj/planogram-compliance/utils/segment/loss.py b/spaces/Abhilashvj/planogram-compliance/utils/segment/loss.py
deleted file mode 100644
index effaadebd0d6f1b10846ec82cd93356cb3129624..0000000000000000000000000000000000000000
--- a/spaces/Abhilashvj/planogram-compliance/utils/segment/loss.py
+++ /dev/null
@@ -1,275 +0,0 @@
-import torch
-import torch.nn as nn
-import torch.nn.functional as F
-
-from ..general import xywh2xyxy
-from ..loss import FocalLoss, smooth_BCE
-from ..metrics import bbox_iou
-from ..torch_utils import de_parallel
-from .general import crop_mask
-
-
-class ComputeLoss:
-    # Compute losses
-    def __init__(self, model, autobalance=False, overlap=False):
-        self.sort_obj_iou = False
-        self.overlap = overlap
-        device = next(model.parameters()).device  # get model device
-        h = model.hyp  # hyperparameters
-        self.device = device
-
-        # Define criteria
-        BCEcls = nn.BCEWithLogitsLoss(
-            pos_weight=torch.tensor([h["cls_pw"]], device=device)
-        )
-        BCEobj = nn.BCEWithLogitsLoss(
-            pos_weight=torch.tensor([h["obj_pw"]], device=device)
-        )
-
-        # Class label smoothing https://arxiv.org/pdf/1902.04103.pdf eqn 3
-        self.cp, self.cn = smooth_BCE(
-            eps=h.get("label_smoothing", 0.0)
-        )  # positive, negative BCE targets
-
-        # Focal loss
-        g = h["fl_gamma"]  # focal loss gamma
-        if g > 0:
-            BCEcls, BCEobj = FocalLoss(BCEcls, g), FocalLoss(BCEobj, g)
-
-        m = de_parallel(model).model[-1]  # Detect() module
-        self.balance = {3: [4.0, 1.0, 0.4]}.get(
-            m.nl, [4.0, 1.0, 0.25, 0.06, 0.02]
-        )  # P3-P7
-        self.ssi = (
-            list(m.stride).index(16) if autobalance else 0
-        )  # stride 16 index
-        self.BCEcls, self.BCEobj, self.gr, self.hyp, self.autobalance = (
-            BCEcls,
-            BCEobj,
-            1.0,
-            h,
-            autobalance,
-        )
-        self.na = m.na  # number of anchors
-        self.nc = m.nc  # number of classes
-        self.nl = m.nl  # number of layers
-        self.nm = m.nm  # number of masks
-        self.anchors = m.anchors
-        self.device = device
-
-    def __call__(self, preds, targets, masks):  # predictions, targets, model
-        p, proto = preds
-        (
-            bs,
-            nm,
-            mask_h,
-            mask_w,
-        ) = proto.shape  # batch size, number of masks, mask height, mask width
-        lcls = torch.zeros(1, device=self.device)
-        lbox = torch.zeros(1, device=self.device)
-        lobj = torch.zeros(1, device=self.device)
-        lseg = torch.zeros(1, device=self.device)
-        tcls, tbox, indices, anchors, tidxs, xywhn = self.build_targets(
-            p, targets
-        )  # targets
-
-        # Losses
-        for i, pi in enumerate(p):  # layer index, layer predictions
-            b, a, gj, gi = indices[i]  # image, anchor, gridy, gridx
-            tobj = torch.zeros(
-                pi.shape[:4], dtype=pi.dtype, device=self.device
-            )  # target obj
-
-            n = b.shape[0]  # number of targets
-            if n:
-                pxy, pwh, _, pcls, pmask = pi[b, a, gj, gi].split(
-                    (2, 2, 1, self.nc, nm), 1
-                )  # subset of predictions
-
-                # Box regression
-                pxy = pxy.sigmoid() * 2 - 0.5
-                pwh = (pwh.sigmoid() * 2) ** 2 * anchors[i]
-                pbox = torch.cat((pxy, pwh), 1)  # predicted box
-                iou = bbox_iou(
-                    pbox, tbox[i], CIoU=True
-                ).squeeze()  # iou(prediction, target)
-                lbox += (1.0 - iou).mean()  # iou loss
-
-                # Objectness
-                iou = iou.detach().clamp(0).type(tobj.dtype)
-                if self.sort_obj_iou:
-                    j = iou.argsort()
-                    b, a, gj, gi, iou = b[j], a[j], gj[j], gi[j], iou[j]
-                if self.gr < 1:
-                    iou = (1.0 - self.gr) + self.gr * iou
-                tobj[b, a, gj, gi] = iou  # iou ratio
-
-                # Classification
-                if self.nc > 1:  # cls loss (only if multiple classes)
-                    t = torch.full_like(
-                        pcls, self.cn, device=self.device
-                    )  # targets
-                    t[range(n), tcls[i]] = self.cp
-                    lcls += self.BCEcls(pcls, t)  # BCE
-
-                # Mask regression
-                if tuple(masks.shape[-2:]) != (mask_h, mask_w):  # downsample
-                    masks = F.interpolate(
-                        masks[None], (mask_h, mask_w), mode="nearest"
-                    )[0]
-                marea = xywhn[i][:, 2:].prod(
-                    1
-                )  # mask width, height normalized
-                mxyxy = xywh2xyxy(
-                    xywhn[i]
-                    * torch.tensor(
-                        [mask_w, mask_h, mask_w, mask_h], device=self.device
-                    )
-                )
-                for bi in b.unique():
-                    j = b == bi  # matching index
-                    if self.overlap:
-                        mask_gti = torch.where(
-                            masks[bi][None] == tidxs[i][j].view(-1, 1, 1),
-                            1.0,
-                            0.0,
-                        )
-                    else:
-                        mask_gti = masks[tidxs[i]][j]
-                    lseg += self.single_mask_loss(
-                        mask_gti, pmask[j], proto[bi], mxyxy[j], marea[j]
-                    )
-
-            obji = self.BCEobj(pi[..., 4], tobj)
-            lobj += obji * self.balance[i]  # obj loss
-            if self.autobalance:
-                self.balance[i] = (
-                    self.balance[i] * 0.9999 + 0.0001 / obji.detach().item()
-                )
-
-        if self.autobalance:
-            self.balance = [x / self.balance[self.ssi] for x in self.balance]
-        lbox *= self.hyp["box"]
-        lobj *= self.hyp["obj"]
-        lcls *= self.hyp["cls"]
-        lseg *= self.hyp["box"] / bs
-
-        loss = lbox + lobj + lcls + lseg
-        return loss * bs, torch.cat((lbox, lseg, lobj, lcls)).detach()
-
-    def single_mask_loss(self, gt_mask, pred, proto, xyxy, area):
-        # Mask loss for one image
-        pred_mask = (pred @ proto.view(self.nm, -1)).view(
-            -1, *proto.shape[1:]
-        )  # (n,32) @ (32,80,80) -> (n,80,80)
-        loss = F.binary_cross_entropy_with_logits(
-            pred_mask, gt_mask, reduction="none"
-        )
-        return (crop_mask(loss, xyxy).mean(dim=(1, 2)) / area).mean()
-
-    def build_targets(self, p, targets):
-        # Build targets for compute_loss(), input targets(image,class,x,y,w,h)
-        na, nt = self.na, targets.shape[0]  # number of anchors, targets
-        tcls, tbox, indices, anch, tidxs, xywhn = [], [], [], [], [], []
-        gain = torch.ones(
-            8, device=self.device
-        )  # normalized to gridspace gain
-        ai = (
-            torch.arange(na, device=self.device)
-            .float()
-            .view(na, 1)
-            .repeat(1, nt)
-        )  # same as .repeat_interleave(nt)
-        if self.overlap:
-            batch = p[0].shape[0]
-            ti = []
-            for i in range(batch):
-                num = (
-                    targets[:, 0] == i
-                ).sum()  # find number of targets of each image
-                ti.append(
-                    torch.arange(num, device=self.device)
-                    .float()
-                    .view(1, num)
-                    .repeat(na, 1)
-                    + 1
-                )  # (na, num)
-            ti = torch.cat(ti, 1)  # (na, nt)
-        else:
-            ti = (
-                torch.arange(nt, device=self.device)
-                .float()
-                .view(1, nt)
-                .repeat(na, 1)
-            )
-        targets = torch.cat(
-            (targets.repeat(na, 1, 1), ai[..., None], ti[..., None]), 2
-        )  # append anchor indices
-
-        g = 0.5  # bias
-        off = (
-            torch.tensor(
-                [
-                    [0, 0],
-                    [1, 0],
-                    [0, 1],
-                    [-1, 0],
-                    [0, -1],  # j,k,l,m
-                    # [1, 1], [1, -1], [-1, 1], [-1, -1],  # jk,jm,lk,lm
-                ],
-                device=self.device,
-            ).float()
-            * g
-        )  # offsets
-
-        for i in range(self.nl):
-            anchors, shape = self.anchors[i], p[i].shape
-            gain[2:6] = torch.tensor(shape)[[3, 2, 3, 2]]  # xyxy gain
-
-            # Match targets to anchors
-            t = targets * gain  # shape(3,n,7)
-            if nt:
-                # Matches
-                r = t[..., 4:6] / anchors[:, None]  # wh ratio
-                j = (
-                    torch.max(r, 1 / r).max(2)[0] < self.hyp["anchor_t"]
-                )  # compare
-                # j = wh_iou(anchors, t[:, 4:6]) > model.hyp['iou_t']  # iou(3,n)=wh_iou(anchors(3,2), gwh(n,2))
-                t = t[j]  # filter
-
-                # Offsets
-                gxy = t[:, 2:4]  # grid xy
-                gxi = gain[[2, 3]] - gxy  # inverse
-                j, k = ((gxy % 1 < g) & (gxy > 1)).T
-                l, m = ((gxi % 1 < g) & (gxi > 1)).T
-                j = torch.stack((torch.ones_like(j), j, k, l, m))
-                t = t.repeat((5, 1, 1))[j]
-                offsets = (torch.zeros_like(gxy)[None] + off[:, None])[j]
-            else:
-                t = targets[0]
-                offsets = 0
-
-            # Define
-            bc, gxy, gwh, at = t.chunk(
-                4, 1
-            )  # (image, class), grid xy, grid wh, anchors
-            (a, tidx), (b, c) = (
-                at.long().T,
-                bc.long().T,
-            )  # anchors, image, class
-            gij = (gxy - offsets).long()
-            gi, gj = gij.T  # grid indices
-
-            # Append
-            indices.append(
-                (b, a, gj.clamp_(0, shape[2] - 1), gi.clamp_(0, shape[3] - 1))
-            )  # image, anchor, grid
-            tbox.append(torch.cat((gxy - gij, gwh), 1))  # box
-            anch.append(anchors[a])  # anchors
-            tcls.append(c)  # class
-            tidxs.append(tidx)
-            xywhn.append(
-                torch.cat((gxy, gwh), 1) / gain[2:6]
-            )  # xywh normalized
-
-        return tcls, tbox, indices, anch, tidxs, xywhn
diff --git a/spaces/AchyuthGamer/OpenGPT/g4f/Provider/GetGpt.py b/spaces/AchyuthGamer/OpenGPT/g4f/Provider/GetGpt.py
deleted file mode 100644
index b96efaac78d8c2443d53e584b8bc9fae50de3114..0000000000000000000000000000000000000000
--- a/spaces/AchyuthGamer/OpenGPT/g4f/Provider/GetGpt.py
+++ /dev/null
@@ -1,88 +0,0 @@
-from __future__ import annotations
-
-import json
-import os
-import uuid
-
-import requests
-from Crypto.Cipher import AES
-
-from ..typing import Any, CreateResult
-from .base_provider import BaseProvider
-
-
-class GetGpt(BaseProvider):
-    url                   = 'https://chat.getgpt.world/'
-    supports_stream       = True
-    working               = False
-    supports_gpt_35_turbo = True
-
-    @staticmethod
-    def create_completion(
-        model: str,
-        messages: list[dict[str, str]],
-        stream: bool, **kwargs: Any) -> CreateResult:
-        
-        headers = {
-            'Content-Type'  : 'application/json',
-            'Referer'       : 'https://chat.getgpt.world/',
-            'user-agent'    : 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/114.0.0.0 Safari/537.36',
-        }
-        
-        data = json.dumps(
-            {
-                'messages'          : messages,
-                'frequency_penalty' : kwargs.get('frequency_penalty', 0),
-                'max_tokens'        : kwargs.get('max_tokens', 4000),
-                'model'             : 'gpt-3.5-turbo',
-                'presence_penalty'  : kwargs.get('presence_penalty', 0),
-                'temperature'       : kwargs.get('temperature', 1),
-                'top_p'             : kwargs.get('top_p', 1),
-                'stream'            : True,
-                'uuid'              : str(uuid.uuid4())
-            }
-        )
-
-        res = requests.post('https://chat.getgpt.world/api/chat/stream',
-            headers=headers, json={'signature': _encrypt(data)}, stream=True)
-
-        res.raise_for_status()
-        for line in res.iter_lines():
-            if b'content' in line:
-                line_json = json.loads(line.decode('utf-8').split('data: ')[1])
-                yield (line_json['choices'][0]['delta']['content'])
-
-    @classmethod
-    @property
-    def params(cls):
-        params = [
-            ('model', 'str'),
-            ('messages', 'list[dict[str, str]]'),
-            ('stream', 'bool'),
-            ('temperature', 'float'),
-            ('presence_penalty', 'int'),
-            ('frequency_penalty', 'int'),
-            ('top_p', 'int'),
-            ('max_tokens', 'int'),
-        ]
-        param = ', '.join([': '.join(p) for p in params])
-        return f'g4f.provider.{cls.__name__} supports: ({param})'
-
-
-def _encrypt(e: str):
-    t = os.urandom(8).hex().encode('utf-8')
-    n = os.urandom(8).hex().encode('utf-8')
-    r = e.encode('utf-8')
-    
-    cipher     = AES.new(t, AES.MODE_CBC, n)
-    ciphertext = cipher.encrypt(_pad_data(r))
-    
-    return ciphertext.hex() + t.decode('utf-8') + n.decode('utf-8')
-
-
-def _pad_data(data: bytes) -> bytes:
-    block_size   = AES.block_size
-    padding_size = block_size - len(data) % block_size
-    padding      = bytes([padding_size] * padding_size)
-    
-    return data + padding
diff --git a/spaces/AgentVerse/agentVerse/ui/src/phaser3-rex-plugins/plugins/imagebox-plugin.js b/spaces/AgentVerse/agentVerse/ui/src/phaser3-rex-plugins/plugins/imagebox-plugin.js
deleted file mode 100644
index b13dd39dad69a765abecc3f310e66cc7c3df0e24..0000000000000000000000000000000000000000
--- a/spaces/AgentVerse/agentVerse/ui/src/phaser3-rex-plugins/plugins/imagebox-plugin.js
+++ /dev/null
@@ -1,23 +0,0 @@
-import Factory from './gameobjects/container/imagebox/Factory.js';
-import Creator from './gameobjects/container/imagebox/Creator.js';
-import ImageBox from './gameobjects/container/imagebox/ImageBox.js';
-import SetValue from './utils/object/SetValue.js';
-
-class ImageBoxPlugin extends Phaser.Plugins.BasePlugin {
-
-    constructor(pluginManager) {
-        super(pluginManager);
-
-        //  Register our new Game Object type
-        pluginManager.registerGameObject('rexImageBox', Factory, Creator);
-    }
-
-    start() {
-        var eventEmitter = this.game.events;
-        eventEmitter.on('destroy', this.destroy, this);
-    }
-}
-
-SetValue(window, 'RexPlugins.GameObjects.ImageBox', ImageBox);
-
-export default ImageBoxPlugin;
\ No newline at end of file
diff --git a/spaces/AgentVerse/agentVerse/ui/src/phaser3-rex-plugins/templates/ui/canvasinput/CanvasInput.js b/spaces/AgentVerse/agentVerse/ui/src/phaser3-rex-plugins/templates/ui/canvasinput/CanvasInput.js
deleted file mode 100644
index 318c7182fb69ed5562fe4e8017c0dc3584fa6e24..0000000000000000000000000000000000000000
--- a/spaces/AgentVerse/agentVerse/ui/src/phaser3-rex-plugins/templates/ui/canvasinput/CanvasInput.js
+++ /dev/null
@@ -1,2 +0,0 @@
-import CanvasInput from '../../../plugins/canvasinput.js';
-export default CanvasInput;
\ No newline at end of file
diff --git a/spaces/AiMimicry/sovits-models/onnxexport/model_onnx.py b/spaces/AiMimicry/sovits-models/onnxexport/model_onnx.py
deleted file mode 100644
index e28bae95ec1e53aa05d06fc784ff86d55f228d60..0000000000000000000000000000000000000000
--- a/spaces/AiMimicry/sovits-models/onnxexport/model_onnx.py
+++ /dev/null
@@ -1,335 +0,0 @@
-import torch
-from torch import nn
-from torch.nn import functional as F
-
-import modules.attentions as attentions
-import modules.commons as commons
-import modules.modules as modules
-
-from torch.nn import Conv1d, ConvTranspose1d, AvgPool1d, Conv2d
-from torch.nn.utils import weight_norm, remove_weight_norm, spectral_norm
-
-import utils
-from modules.commons import init_weights, get_padding
-from vdecoder.hifigan.models import Generator
-from utils import f0_to_coarse
-
-
-class ResidualCouplingBlock(nn.Module):
-    def __init__(self,
-                 channels,
-                 hidden_channels,
-                 kernel_size,
-                 dilation_rate,
-                 n_layers,
-                 n_flows=4,
-                 gin_channels=0):
-        super().__init__()
-        self.channels = channels
-        self.hidden_channels = hidden_channels
-        self.kernel_size = kernel_size
-        self.dilation_rate = dilation_rate
-        self.n_layers = n_layers
-        self.n_flows = n_flows
-        self.gin_channels = gin_channels
-
-        self.flows = nn.ModuleList()
-        for i in range(n_flows):
-            self.flows.append(
-                modules.ResidualCouplingLayer(channels, hidden_channels, kernel_size, dilation_rate, n_layers,
-                                              gin_channels=gin_channels, mean_only=True))
-            self.flows.append(modules.Flip())
-
-    def forward(self, x, x_mask, g=None, reverse=False):
-        if not reverse:
-            for flow in self.flows:
-                x, _ = flow(x, x_mask, g=g, reverse=reverse)
-        else:
-            for flow in reversed(self.flows):
-                x = flow(x, x_mask, g=g, reverse=reverse)
-        return x
-
-
-class Encoder(nn.Module):
-    def __init__(self,
-                 in_channels,
-                 out_channels,
-                 hidden_channels,
-                 kernel_size,
-                 dilation_rate,
-                 n_layers,
-                 gin_channels=0):
-        super().__init__()
-        self.in_channels = in_channels
-        self.out_channels = out_channels
-        self.hidden_channels = hidden_channels
-        self.kernel_size = kernel_size
-        self.dilation_rate = dilation_rate
-        self.n_layers = n_layers
-        self.gin_channels = gin_channels
-
-        self.pre = nn.Conv1d(in_channels, hidden_channels, 1)
-        self.enc = modules.WN(hidden_channels, kernel_size, dilation_rate, n_layers, gin_channels=gin_channels)
-        self.proj = nn.Conv1d(hidden_channels, out_channels * 2, 1)
-
-    def forward(self, x, x_lengths, g=None):
-        # print(x.shape,x_lengths.shape)
-        x_mask = torch.unsqueeze(commons.sequence_mask(x_lengths, x.size(2)), 1).to(x.dtype)
-        x = self.pre(x) * x_mask
-        x = self.enc(x, x_mask, g=g)
-        stats = self.proj(x) * x_mask
-        m, logs = torch.split(stats, self.out_channels, dim=1)
-        z = (m + torch.randn_like(m) * torch.exp(logs)) * x_mask
-        return z, m, logs, x_mask
-
-
-class TextEncoder(nn.Module):
-    def __init__(self,
-                 out_channels,
-                 hidden_channels,
-                 kernel_size,
-                 n_layers,
-                 gin_channels=0,
-                 filter_channels=None,
-                 n_heads=None,
-                 p_dropout=None):
-        super().__init__()
-        self.out_channels = out_channels
-        self.hidden_channels = hidden_channels
-        self.kernel_size = kernel_size
-        self.n_layers = n_layers
-        self.gin_channels = gin_channels
-        self.proj = nn.Conv1d(hidden_channels, out_channels * 2, 1)
-        self.f0_emb = nn.Embedding(256, hidden_channels)
-
-        self.enc_ = attentions.Encoder(
-            hidden_channels,
-            filter_channels,
-            n_heads,
-            n_layers,
-            kernel_size,
-            p_dropout)
-
-    def forward(self, x, x_mask, f0=None, z=None):
-        x = x + self.f0_emb(f0).transpose(1, 2)
-        x = self.enc_(x * x_mask, x_mask)
-        stats = self.proj(x) * x_mask
-        m, logs = torch.split(stats, self.out_channels, dim=1)
-        z = (m + z * torch.exp(logs)) * x_mask
-        return z, m, logs, x_mask
-
-
-class DiscriminatorP(torch.nn.Module):
-    def __init__(self, period, kernel_size=5, stride=3, use_spectral_norm=False):
-        super(DiscriminatorP, self).__init__()
-        self.period = period
-        self.use_spectral_norm = use_spectral_norm
-        norm_f = weight_norm if use_spectral_norm == False else spectral_norm
-        self.convs = nn.ModuleList([
-            norm_f(Conv2d(1, 32, (kernel_size, 1), (stride, 1), padding=(get_padding(kernel_size, 1), 0))),
-            norm_f(Conv2d(32, 128, (kernel_size, 1), (stride, 1), padding=(get_padding(kernel_size, 1), 0))),
-            norm_f(Conv2d(128, 512, (kernel_size, 1), (stride, 1), padding=(get_padding(kernel_size, 1), 0))),
-            norm_f(Conv2d(512, 1024, (kernel_size, 1), (stride, 1), padding=(get_padding(kernel_size, 1), 0))),
-            norm_f(Conv2d(1024, 1024, (kernel_size, 1), 1, padding=(get_padding(kernel_size, 1), 0))),
-        ])
-        self.conv_post = norm_f(Conv2d(1024, 1, (3, 1), 1, padding=(1, 0)))
-
-    def forward(self, x):
-        fmap = []
-
-        # 1d to 2d
-        b, c, t = x.shape
-        if t % self.period != 0:  # pad first
-            n_pad = self.period - (t % self.period)
-            x = F.pad(x, (0, n_pad), "reflect")
-            t = t + n_pad
-        x = x.view(b, c, t // self.period, self.period)
-
-        for l in self.convs:
-            x = l(x)
-            x = F.leaky_relu(x, modules.LRELU_SLOPE)
-            fmap.append(x)
-        x = self.conv_post(x)
-        fmap.append(x)
-        x = torch.flatten(x, 1, -1)
-
-        return x, fmap
-
-
-class DiscriminatorS(torch.nn.Module):
-    def __init__(self, use_spectral_norm=False):
-        super(DiscriminatorS, self).__init__()
-        norm_f = weight_norm if use_spectral_norm == False else spectral_norm
-        self.convs = nn.ModuleList([
-            norm_f(Conv1d(1, 16, 15, 1, padding=7)),
-            norm_f(Conv1d(16, 64, 41, 4, groups=4, padding=20)),
-            norm_f(Conv1d(64, 256, 41, 4, groups=16, padding=20)),
-            norm_f(Conv1d(256, 1024, 41, 4, groups=64, padding=20)),
-            norm_f(Conv1d(1024, 1024, 41, 4, groups=256, padding=20)),
-            norm_f(Conv1d(1024, 1024, 5, 1, padding=2)),
-        ])
-        self.conv_post = norm_f(Conv1d(1024, 1, 3, 1, padding=1))
-
-    def forward(self, x):
-        fmap = []
-
-        for l in self.convs:
-            x = l(x)
-            x = F.leaky_relu(x, modules.LRELU_SLOPE)
-            fmap.append(x)
-        x = self.conv_post(x)
-        fmap.append(x)
-        x = torch.flatten(x, 1, -1)
-
-        return x, fmap
-
-
-class F0Decoder(nn.Module):
-    def __init__(self,
-                 out_channels,
-                 hidden_channels,
-                 filter_channels,
-                 n_heads,
-                 n_layers,
-                 kernel_size,
-                 p_dropout,
-                 spk_channels=0):
-        super().__init__()
-        self.out_channels = out_channels
-        self.hidden_channels = hidden_channels
-        self.filter_channels = filter_channels
-        self.n_heads = n_heads
-        self.n_layers = n_layers
-        self.kernel_size = kernel_size
-        self.p_dropout = p_dropout
-        self.spk_channels = spk_channels
-
-        self.prenet = nn.Conv1d(hidden_channels, hidden_channels, 3, padding=1)
-        self.decoder = attentions.FFT(
-            hidden_channels,
-            filter_channels,
-            n_heads,
-            n_layers,
-            kernel_size,
-            p_dropout)
-        self.proj = nn.Conv1d(hidden_channels, out_channels, 1)
-        self.f0_prenet = nn.Conv1d(1, hidden_channels, 3, padding=1)
-        self.cond = nn.Conv1d(spk_channels, hidden_channels, 1)
-
-    def forward(self, x, norm_f0, x_mask, spk_emb=None):
-        x = torch.detach(x)
-        if spk_emb is not None:
-            x = x + self.cond(spk_emb)
-        x += self.f0_prenet(norm_f0)
-        x = self.prenet(x) * x_mask
-        x = self.decoder(x * x_mask, x_mask)
-        x = self.proj(x) * x_mask
-        return x
-
-
-class SynthesizerTrn(nn.Module):
-    """
-  Synthesizer for Training
-  """
-
-    def __init__(self,
-                 spec_channels,
-                 segment_size,
-                 inter_channels,
-                 hidden_channels,
-                 filter_channels,
-                 n_heads,
-                 n_layers,
-                 kernel_size,
-                 p_dropout,
-                 resblock,
-                 resblock_kernel_sizes,
-                 resblock_dilation_sizes,
-                 upsample_rates,
-                 upsample_initial_channel,
-                 upsample_kernel_sizes,
-                 gin_channels,
-                 ssl_dim,
-                 n_speakers,
-                 sampling_rate=44100,
-                 **kwargs):
-        super().__init__()
-        self.spec_channels = spec_channels
-        self.inter_channels = inter_channels
-        self.hidden_channels = hidden_channels
-        self.filter_channels = filter_channels
-        self.n_heads = n_heads
-        self.n_layers = n_layers
-        self.kernel_size = kernel_size
-        self.p_dropout = p_dropout
-        self.resblock = resblock
-        self.resblock_kernel_sizes = resblock_kernel_sizes
-        self.resblock_dilation_sizes = resblock_dilation_sizes
-        self.upsample_rates = upsample_rates
-        self.upsample_initial_channel = upsample_initial_channel
-        self.upsample_kernel_sizes = upsample_kernel_sizes
-        self.segment_size = segment_size
-        self.gin_channels = gin_channels
-        self.ssl_dim = ssl_dim
-        self.emb_g = nn.Embedding(n_speakers, gin_channels)
-
-        self.pre = nn.Conv1d(ssl_dim, hidden_channels, kernel_size=5, padding=2)
-
-        self.enc_p = TextEncoder(
-            inter_channels,
-            hidden_channels,
-            filter_channels=filter_channels,
-            n_heads=n_heads,
-            n_layers=n_layers,
-            kernel_size=kernel_size,
-            p_dropout=p_dropout
-        )
-        hps = {
-            "sampling_rate": sampling_rate,
-            "inter_channels": inter_channels,
-            "resblock": resblock,
-            "resblock_kernel_sizes": resblock_kernel_sizes,
-            "resblock_dilation_sizes": resblock_dilation_sizes,
-            "upsample_rates": upsample_rates,
-            "upsample_initial_channel": upsample_initial_channel,
-            "upsample_kernel_sizes": upsample_kernel_sizes,
-            "gin_channels": gin_channels,
-        }
-        self.dec = Generator(h=hps)
-        self.enc_q = Encoder(spec_channels, inter_channels, hidden_channels, 5, 1, 16, gin_channels=gin_channels)
-        self.flow = ResidualCouplingBlock(inter_channels, hidden_channels, 5, 1, 4, gin_channels=gin_channels)
-        self.f0_decoder = F0Decoder(
-            1,
-            hidden_channels,
-            filter_channels,
-            n_heads,
-            n_layers,
-            kernel_size,
-            p_dropout,
-            spk_channels=gin_channels
-        )
-        self.emb_uv = nn.Embedding(2, hidden_channels)
-        self.predict_f0 = False
-
-    def forward(self, c, f0, mel2ph, uv, noise=None, g=None):
-
-        decoder_inp = F.pad(c, [0, 0, 1, 0])
-        mel2ph_ = mel2ph.unsqueeze(2).repeat([1, 1, c.shape[-1]])
-        c = torch.gather(decoder_inp, 1, mel2ph_).transpose(1, 2)  # [B, T, H]
-
-        c_lengths = (torch.ones(c.size(0)) * c.size(-1)).to(c.device)
-        g = g.unsqueeze(0)
-        g = self.emb_g(g).transpose(1, 2)
-        x_mask = torch.unsqueeze(commons.sequence_mask(c_lengths, c.size(2)), 1).to(c.dtype)
-        x = self.pre(c) * x_mask + self.emb_uv(uv.long()).transpose(1, 2)
-
-        if self.predict_f0:
-            lf0 = 2595. * torch.log10(1. + f0.unsqueeze(1) / 700.) / 500
-            norm_lf0 = utils.normalize_f0(lf0, x_mask, uv, random_scale=False)
-            pred_lf0 = self.f0_decoder(x, norm_lf0, x_mask, spk_emb=g)
-            f0 = (700 * (torch.pow(10, pred_lf0 * 500 / 2595) - 1)).squeeze(1)
-
-        z_p, m_p, logs_p, c_mask = self.enc_p(x, x_mask, f0=f0_to_coarse(f0), z=noise)
-        z = self.flow(z_p, c_mask, g=g, reverse=True)
-        o = self.dec(z * c_mask, g=g, f0=f0)
-        return o
diff --git a/spaces/AlekseyKorshuk/rugpt3/app.py b/spaces/AlekseyKorshuk/rugpt3/app.py
deleted file mode 100644
index 2fc87527a16fe9d99d182452eb93005c461beca9..0000000000000000000000000000000000000000
--- a/spaces/AlekseyKorshuk/rugpt3/app.py
+++ /dev/null
@@ -1,30 +0,0 @@
-import gradio as gr
-from gradio import mix
-
-title = "RUGPT3"
-description = "Gradio Demo for RUGPT3. To use it, simply add your text, or click one of the examples to load them. Read more at the links below."
-
-
-examples = [
-    ['Меня зовут Томас и мой основной']
-]
-
-io = gr.Interface.load("models/sberbank-ai/rugpt3large_based_on_gpt2")
-
-
-
-def inference(text):
-
-    return io(text)
-    
-     
-
-gr.Interface(
-    inference, 
-    [gr.inputs.Textbox(label="Input")], 
-    gr.outputs.Textbox(label="Output"),
-    examples=examples,
-    # article=article,
-    title=title,
-    description=description).launch(enable_queue=True, cache_examples=True)
-  
\ No newline at end of file
diff --git a/spaces/Alpaca233/SadTalker/webui.bat b/spaces/Alpaca233/SadTalker/webui.bat
deleted file mode 100644
index 6ff83231242ac2260c38a2a4a7ba030aa707b1a3..0000000000000000000000000000000000000000
--- a/spaces/Alpaca233/SadTalker/webui.bat
+++ /dev/null
@@ -1,17 +0,0 @@
-@echo off
-
-IF NOT EXIST venv (
-python -m venv venv
-) ELSE (
-echo venv folder already exists, skipping creation...
-)
-call .\venv\Scripts\activate.bat
-
-set PYTHON="venv\Scripts\Python.exe"
-echo venv %PYTHON%
-
-%PYTHON% Launcher.py
-
-echo.
-echo Launch unsuccessful. Exiting.
-pause
\ No newline at end of file
diff --git a/spaces/Amon1/ChatGPTForAcadamic/crazy_functions/__init__.py b/spaces/Amon1/ChatGPTForAcadamic/crazy_functions/__init__.py
deleted file mode 100644
index e69de29bb2d1d6434b8b29ae775ad8c2e48c5391..0000000000000000000000000000000000000000
diff --git a/spaces/Androidonnxfork/CivitAi-to-Diffusers/diffusers/docs/source/en/api/pipelines/text_to_video_zero.md b/spaces/Androidonnxfork/CivitAi-to-Diffusers/diffusers/docs/source/en/api/pipelines/text_to_video_zero.md
deleted file mode 100644
index b64d72db0187a4619751ec777d3b7c40f938ec6f..0000000000000000000000000000000000000000
--- a/spaces/Androidonnxfork/CivitAi-to-Diffusers/diffusers/docs/source/en/api/pipelines/text_to_video_zero.md
+++ /dev/null
@@ -1,260 +0,0 @@
-<!--Copyright 2023 The HuggingFace Team. All rights reserved.
-
-Licensed under the Apache License, Version 2.0 (the "License"); you may not use this file except in compliance with
-the License. You may obtain a copy of the License at
-
-http://www.apache.org/licenses/LICENSE-2.0
-
-Unless required by applicable law or agreed to in writing, software distributed under the License is distributed on
-an "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. See the License for the
-specific language governing permissions and limitations under the License.
--->
-
-# Text2Video-Zero
-
-[Text2Video-Zero: Text-to-Image Diffusion Models are Zero-Shot Video Generators](https://huggingface.co/papers/2303.13439) is by
-Levon Khachatryan,
-Andranik Movsisyan,
-Vahram Tadevosyan,
-Roberto Henschel,
-[Zhangyang Wang](https://www.ece.utexas.edu/people/faculty/atlas-wang), Shant Navasardyan, [Humphrey Shi](https://www.humphreyshi.com).
-
-Text2Video-Zero enables zero-shot video generation using either:
-1. A textual prompt
-2. A prompt combined with guidance from poses or edges
-3. Video Instruct-Pix2Pix (instruction-guided video editing)
-
-Results are temporally consistent and closely follow the guidance and textual prompts.
-
-![teaser-img](https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/t2v_zero_teaser.png)
-
-The abstract from the paper is:
-
-*Recent text-to-video generation approaches rely on computationally heavy training and require large-scale video datasets. In this paper, we introduce a new task of zero-shot text-to-video generation and propose a low-cost approach (without any training or optimization) by leveraging the power of existing text-to-image synthesis methods (e.g., Stable Diffusion), making them suitable for the video domain.
-Our key modifications include (i) enriching the latent codes of the generated frames with motion dynamics to keep the global scene and the background time consistent; and (ii) reprogramming frame-level self-attention using a new cross-frame attention of each frame on the first frame, to preserve the context, appearance, and identity of the foreground object.
-Experiments show that this leads to low overhead, yet high-quality and remarkably consistent video generation. Moreover, our approach is not limited to text-to-video synthesis but is also applicable to other tasks such as conditional and content-specialized video generation, and Video Instruct-Pix2Pix, i.e., instruction-guided video editing.
-As experiments show, our method performs comparably or sometimes better than recent approaches, despite not being trained on additional video data.*
-
-You can find additional information about Text-to-Video Zero on the [project page](https://text2video-zero.github.io/), [paper](https://arxiv.org/abs/2303.13439), and [original codebase](https://github.com/Picsart-AI-Research/Text2Video-Zero).
-
-## Usage example
-
-### Text-To-Video
-
-To generate a video from prompt, run the following python command
-```python
-import torch
-import imageio
-from diffusers import TextToVideoZeroPipeline
-
-model_id = "runwayml/stable-diffusion-v1-5"
-pipe = TextToVideoZeroPipeline.from_pretrained(model_id, torch_dtype=torch.float16).to("cuda")
-
-prompt = "A panda is playing guitar on times square"
-result = pipe(prompt=prompt).images
-result = [(r * 255).astype("uint8") for r in result]
-imageio.mimsave("video.mp4", result, fps=4)
-```
-You can change these parameters in the pipeline call:
-* Motion field strength (see the [paper](https://arxiv.org/abs/2303.13439), Sect. 3.3.1):
-    * `motion_field_strength_x` and `motion_field_strength_y`. Default: `motion_field_strength_x=12`, `motion_field_strength_y=12`
-* `T` and `T'` (see the [paper](https://arxiv.org/abs/2303.13439), Sect. 3.3.1)
-    * `t0` and `t1` in the range `{0, ..., num_inference_steps}`. Default: `t0=45`, `t1=48`
-* Video length:
-    * `video_length`, the number of frames video_length to be generated. Default: `video_length=8`
-
-We an also generate longer videos by doing the processing in a chunk-by-chunk manner:
-```python
-import torch
-import imageio
-from diffusers import TextToVideoZeroPipeline
-import numpy as np
-
-model_id = "runwayml/stable-diffusion-v1-5"
-pipe = TextToVideoZeroPipeline.from_pretrained(model_id, torch_dtype=torch.float16).to("cuda")
-seed = 0
-video_length = 8
-chunk_size = 4
-prompt = "A panda is playing guitar on times square"
-
-# Generate the video chunk-by-chunk
-result = []
-chunk_ids = np.arange(0, video_length, chunk_size - 1)
-generator = torch.Generator(device="cuda")
-for i in range(len(chunk_ids)):
-    print(f"Processing chunk {i + 1} / {len(chunk_ids)}")
-    ch_start = chunk_ids[i]
-    ch_end = video_length if i == len(chunk_ids) - 1 else chunk_ids[i + 1]
-    # Attach the first frame for Cross Frame Attention
-    frame_ids = [0] + list(range(ch_start, ch_end))
-    # Fix the seed for the temporal consistency
-    generator.manual_seed(seed)
-    output = pipe(prompt=prompt, video_length=len(frame_ids), generator=generator, frame_ids=frame_ids)
-    result.append(output.images[1:])
-
-# Concatenate chunks and save
-result = np.concatenate(result)
-result = [(r * 255).astype("uint8") for r in result]
-imageio.mimsave("video.mp4", result, fps=4)
-```
-
-
-### Text-To-Video with Pose Control
-To generate a video from prompt with additional pose control
-
-1. Download a demo video
-
-    ```python
-    from huggingface_hub import hf_hub_download
-
-    filename = "__assets__/poses_skeleton_gifs/dance1_corr.mp4"
-    repo_id = "PAIR/Text2Video-Zero"
-    video_path = hf_hub_download(repo_type="space", repo_id=repo_id, filename=filename)
-    ```
-
-
-2. Read video containing extracted pose images
-    ```python
-    from PIL import Image
-    import imageio
-
-    reader = imageio.get_reader(video_path, "ffmpeg")
-    frame_count = 8
-    pose_images = [Image.fromarray(reader.get_data(i)) for i in range(frame_count)]
-    ```
-    To extract pose from actual video, read [ControlNet documentation](./stable_diffusion/controlnet).
-
-3. Run `StableDiffusionControlNetPipeline` with our custom attention processor
-
-    ```python
-    import torch
-    from diffusers import StableDiffusionControlNetPipeline, ControlNetModel
-    from diffusers.pipelines.text_to_video_synthesis.pipeline_text_to_video_zero import CrossFrameAttnProcessor
-
-    model_id = "runwayml/stable-diffusion-v1-5"
-    controlnet = ControlNetModel.from_pretrained("lllyasviel/sd-controlnet-openpose", torch_dtype=torch.float16)
-    pipe = StableDiffusionControlNetPipeline.from_pretrained(
-        model_id, controlnet=controlnet, torch_dtype=torch.float16
-    ).to("cuda")
-
-    # Set the attention processor
-    pipe.unet.set_attn_processor(CrossFrameAttnProcessor(batch_size=2))
-    pipe.controlnet.set_attn_processor(CrossFrameAttnProcessor(batch_size=2))
-
-    # fix latents for all frames
-    latents = torch.randn((1, 4, 64, 64), device="cuda", dtype=torch.float16).repeat(len(pose_images), 1, 1, 1)
-
-    prompt = "Darth Vader dancing in a desert"
-    result = pipe(prompt=[prompt] * len(pose_images), image=pose_images, latents=latents).images
-    imageio.mimsave("video.mp4", result, fps=4)
-    ```
-
-
-### Text-To-Video with Edge Control
-
-To generate a video from prompt with additional pose control,
-follow the steps described above for pose-guided generation using [Canny edge ControlNet model](https://huggingface.co/lllyasviel/sd-controlnet-canny).
-
-
-### Video Instruct-Pix2Pix
-
-To perform text-guided video editing (with [InstructPix2Pix](./stable_diffusion/pix2pix)):
-
-1. Download a demo video
-
-    ```python
-    from huggingface_hub import hf_hub_download
-
-    filename = "__assets__/pix2pix video/camel.mp4"
-    repo_id = "PAIR/Text2Video-Zero"
-    video_path = hf_hub_download(repo_type="space", repo_id=repo_id, filename=filename)
-    ```
-
-2. Read video from path
-    ```python
-    from PIL import Image
-    import imageio
-
-    reader = imageio.get_reader(video_path, "ffmpeg")
-    frame_count = 8
-    video = [Image.fromarray(reader.get_data(i)) for i in range(frame_count)]
-    ```
-
-3. Run `StableDiffusionInstructPix2PixPipeline` with our custom attention processor
-    ```python
-    import torch
-    from diffusers import StableDiffusionInstructPix2PixPipeline
-    from diffusers.pipelines.text_to_video_synthesis.pipeline_text_to_video_zero import CrossFrameAttnProcessor
-
-    model_id = "timbrooks/instruct-pix2pix"
-    pipe = StableDiffusionInstructPix2PixPipeline.from_pretrained(model_id, torch_dtype=torch.float16).to("cuda")
-    pipe.unet.set_attn_processor(CrossFrameAttnProcessor(batch_size=3))
-
-    prompt = "make it Van Gogh Starry Night style"
-    result = pipe(prompt=[prompt] * len(video), image=video).images
-    imageio.mimsave("edited_video.mp4", result, fps=4)
-    ```
-
-
-### DreamBooth specialization 
-
-Methods **Text-To-Video**, **Text-To-Video with Pose Control** and **Text-To-Video with Edge Control**
-can run with custom [DreamBooth](../training/dreambooth) models, as shown below for
-[Canny edge ControlNet model](https://huggingface.co/lllyasviel/sd-controlnet-canny) and
-[Avatar style DreamBooth](https://huggingface.co/PAIR/text2video-zero-controlnet-canny-avatar) model
-
-1. Download a demo video
-
-    ```python
-    from huggingface_hub import hf_hub_download
-
-    filename = "__assets__/canny_videos_mp4/girl_turning.mp4"
-    repo_id = "PAIR/Text2Video-Zero"
-    video_path = hf_hub_download(repo_type="space", repo_id=repo_id, filename=filename)
-    ```
-
-2. Read video from path
-    ```python
-    from PIL import Image
-    import imageio
-
-    reader = imageio.get_reader(video_path, "ffmpeg")
-    frame_count = 8
-    canny_edges = [Image.fromarray(reader.get_data(i)) for i in range(frame_count)]
-    ```
-
-3. Run `StableDiffusionControlNetPipeline` with custom trained DreamBooth model
-    ```python
-    import torch
-    from diffusers import StableDiffusionControlNetPipeline, ControlNetModel
-    from diffusers.pipelines.text_to_video_synthesis.pipeline_text_to_video_zero import CrossFrameAttnProcessor
-
-    # set model id to custom model
-    model_id = "PAIR/text2video-zero-controlnet-canny-avatar"
-    controlnet = ControlNetModel.from_pretrained("lllyasviel/sd-controlnet-canny", torch_dtype=torch.float16)
-    pipe = StableDiffusionControlNetPipeline.from_pretrained(
-        model_id, controlnet=controlnet, torch_dtype=torch.float16
-    ).to("cuda")
-
-    # Set the attention processor
-    pipe.unet.set_attn_processor(CrossFrameAttnProcessor(batch_size=2))
-    pipe.controlnet.set_attn_processor(CrossFrameAttnProcessor(batch_size=2))
-
-    # fix latents for all frames
-    latents = torch.randn((1, 4, 64, 64), device="cuda", dtype=torch.float16).repeat(len(canny_edges), 1, 1, 1)
-
-    prompt = "oil painting of a beautiful girl avatar style"
-    result = pipe(prompt=[prompt] * len(canny_edges), image=canny_edges, latents=latents).images
-    imageio.mimsave("video.mp4", result, fps=4)
-    ```
-
-You can filter out some available DreamBooth-trained models with [this link](https://huggingface.co/models?search=dreambooth).
-
-
-## TextToVideoZeroPipeline
-[[autodoc]] TextToVideoZeroPipeline
-	- all
-	- __call__
-
-## TextToVideoPipelineOutput
-[[autodoc]] pipelines.text_to_video_synthesis.pipeline_text_to_video_zero.TextToVideoPipelineOutput
\ No newline at end of file
diff --git a/spaces/Androidonnxfork/CivitAi-to-Diffusers/diffusers/src/diffusers/pipelines/semantic_stable_diffusion/__init__.py b/spaces/Androidonnxfork/CivitAi-to-Diffusers/diffusers/src/diffusers/pipelines/semantic_stable_diffusion/__init__.py
deleted file mode 100644
index 95d3604bcf090366bef5083dc916b499346cd3aa..0000000000000000000000000000000000000000
--- a/spaces/Androidonnxfork/CivitAi-to-Diffusers/diffusers/src/diffusers/pipelines/semantic_stable_diffusion/__init__.py
+++ /dev/null
@@ -1,36 +0,0 @@
-from dataclasses import dataclass
-from enum import Enum
-from typing import List, Optional, Union
-
-import numpy as np
-import PIL
-from PIL import Image
-
-from ...utils import BaseOutput, OptionalDependencyNotAvailable, is_torch_available, is_transformers_available
-
-
-@dataclass
-class SemanticStableDiffusionPipelineOutput(BaseOutput):
-    """
-    Output class for Stable Diffusion pipelines.
-
-    Args:
-        images (`List[PIL.Image.Image]` or `np.ndarray`)
-            List of denoised PIL images of length `batch_size` or NumPy array of shape `(batch_size, height, width,
-            num_channels)`.
-        nsfw_content_detected (`List[bool]`)
-            List indicating whether the corresponding generated image contains “not-safe-for-work” (nsfw) content or
-            `None` if safety checking could not be performed.
-    """
-
-    images: Union[List[PIL.Image.Image], np.ndarray]
-    nsfw_content_detected: Optional[List[bool]]
-
-
-try:
-    if not (is_transformers_available() and is_torch_available()):
-        raise OptionalDependencyNotAvailable()
-except OptionalDependencyNotAvailable:
-    from ...utils.dummy_torch_and_transformers_objects import *  # noqa F403
-else:
-    from .pipeline_semantic_stable_diffusion import SemanticStableDiffusionPipeline
diff --git a/spaces/Androidonnxfork/CivitAi-to-Diffusers/diffusers/src/diffusers/schedulers/scheduling_dpmsolver_singlestep.py b/spaces/Androidonnxfork/CivitAi-to-Diffusers/diffusers/src/diffusers/schedulers/scheduling_dpmsolver_singlestep.py
deleted file mode 100644
index 93975a27fc6e3899c009b5576ed74753ea62abbb..0000000000000000000000000000000000000000
--- a/spaces/Androidonnxfork/CivitAi-to-Diffusers/diffusers/src/diffusers/schedulers/scheduling_dpmsolver_singlestep.py
+++ /dev/null
@@ -1,737 +0,0 @@
-# Copyright 2023 TSAIL Team and The HuggingFace Team. All rights reserved.
-#
-# Licensed under the Apache License, Version 2.0 (the "License");
-# you may not use this file except in compliance with the License.
-# You may obtain a copy of the License at
-#
-#     http://www.apache.org/licenses/LICENSE-2.0
-#
-# Unless required by applicable law or agreed to in writing, software
-# distributed under the License is distributed on an "AS IS" BASIS,
-# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
-# See the License for the specific language governing permissions and
-# limitations under the License.
-
-# DISCLAIMER: This file is strongly influenced by https://github.com/LuChengTHU/dpm-solver
-
-import math
-from typing import List, Optional, Tuple, Union
-
-import numpy as np
-import torch
-
-from ..configuration_utils import ConfigMixin, register_to_config
-from ..utils import logging
-from .scheduling_utils import KarrasDiffusionSchedulers, SchedulerMixin, SchedulerOutput
-
-
-logger = logging.get_logger(__name__)  # pylint: disable=invalid-name
-
-
-# Copied from diffusers.schedulers.scheduling_ddpm.betas_for_alpha_bar
-def betas_for_alpha_bar(
-    num_diffusion_timesteps,
-    max_beta=0.999,
-    alpha_transform_type="cosine",
-):
-    """
-    Create a beta schedule that discretizes the given alpha_t_bar function, which defines the cumulative product of
-    (1-beta) over time from t = [0,1].
-
-    Contains a function alpha_bar that takes an argument t and transforms it to the cumulative product of (1-beta) up
-    to that part of the diffusion process.
-
-
-    Args:
-        num_diffusion_timesteps (`int`): the number of betas to produce.
-        max_beta (`float`): the maximum beta to use; use values lower than 1 to
-                     prevent singularities.
-        alpha_transform_type (`str`, *optional*, default to `cosine`): the type of noise schedule for alpha_bar.
-                     Choose from `cosine` or `exp`
-
-    Returns:
-        betas (`np.ndarray`): the betas used by the scheduler to step the model outputs
-    """
-    if alpha_transform_type == "cosine":
-
-        def alpha_bar_fn(t):
-            return math.cos((t + 0.008) / 1.008 * math.pi / 2) ** 2
-
-    elif alpha_transform_type == "exp":
-
-        def alpha_bar_fn(t):
-            return math.exp(t * -12.0)
-
-    else:
-        raise ValueError(f"Unsupported alpha_tranform_type: {alpha_transform_type}")
-
-    betas = []
-    for i in range(num_diffusion_timesteps):
-        t1 = i / num_diffusion_timesteps
-        t2 = (i + 1) / num_diffusion_timesteps
-        betas.append(min(1 - alpha_bar_fn(t2) / alpha_bar_fn(t1), max_beta))
-    return torch.tensor(betas, dtype=torch.float32)
-
-
-class DPMSolverSinglestepScheduler(SchedulerMixin, ConfigMixin):
-    """
-    DPM-Solver (and the improved version DPM-Solver++) is a fast dedicated high-order solver for diffusion ODEs with
-    the convergence order guarantee. Empirically, sampling by DPM-Solver with only 20 steps can generate high-quality
-    samples, and it can generate quite good samples even in only 10 steps.
-
-    For more details, see the original paper: https://arxiv.org/abs/2206.00927 and https://arxiv.org/abs/2211.01095
-
-    Currently, we support the singlestep DPM-Solver for both noise prediction models and data prediction models. We
-    recommend to use `solver_order=2` for guided sampling, and `solver_order=3` for unconditional sampling.
-
-    We also support the "dynamic thresholding" method in Imagen (https://arxiv.org/abs/2205.11487). For pixel-space
-    diffusion models, you can set both `algorithm_type="dpmsolver++"` and `thresholding=True` to use the dynamic
-    thresholding. Note that the thresholding method is unsuitable for latent-space diffusion models (such as
-    stable-diffusion).
-
-    [`~ConfigMixin`] takes care of storing all config attributes that are passed in the scheduler's `__init__`
-    function, such as `num_train_timesteps`. They can be accessed via `scheduler.config.num_train_timesteps`.
-    [`SchedulerMixin`] provides general loading and saving functionality via the [`SchedulerMixin.save_pretrained`] and
-    [`~SchedulerMixin.from_pretrained`] functions.
-
-    Args:
-        num_train_timesteps (`int`): number of diffusion steps used to train the model.
-        beta_start (`float`): the starting `beta` value of inference.
-        beta_end (`float`): the final `beta` value.
-        beta_schedule (`str`):
-            the beta schedule, a mapping from a beta range to a sequence of betas for stepping the model. Choose from
-            `linear`, `scaled_linear`, or `squaredcos_cap_v2`.
-        trained_betas (`np.ndarray`, optional):
-            option to pass an array of betas directly to the constructor to bypass `beta_start`, `beta_end` etc.
-        solver_order (`int`, default `2`):
-            the order of DPM-Solver; can be `1` or `2` or `3`. We recommend to use `solver_order=2` for guided
-            sampling, and `solver_order=3` for unconditional sampling.
-        prediction_type (`str`, default `epsilon`):
-            indicates whether the model predicts the noise (epsilon), or the data / `x0`. One of `epsilon`, `sample`,
-            or `v-prediction`.
-        thresholding (`bool`, default `False`):
-            whether to use the "dynamic thresholding" method (introduced by Imagen, https://arxiv.org/abs/2205.11487).
-            For pixel-space diffusion models, you can set both `algorithm_type=dpmsolver++` and `thresholding=True` to
-            use the dynamic thresholding. Note that the thresholding method is unsuitable for latent-space diffusion
-            models (such as stable-diffusion).
-        dynamic_thresholding_ratio (`float`, default `0.995`):
-            the ratio for the dynamic thresholding method. Default is `0.995`, the same as Imagen
-            (https://arxiv.org/abs/2205.11487).
-        sample_max_value (`float`, default `1.0`):
-            the threshold value for dynamic thresholding. Valid only when `thresholding=True` and
-            `algorithm_type="dpmsolver++`.
-        algorithm_type (`str`, default `dpmsolver++`):
-            the algorithm type for the solver. Either `dpmsolver` or `dpmsolver++`. The `dpmsolver` type implements the
-            algorithms in https://arxiv.org/abs/2206.00927, and the `dpmsolver++` type implements the algorithms in
-            https://arxiv.org/abs/2211.01095. We recommend to use `dpmsolver++` with `solver_order=2` for guided
-            sampling (e.g. stable-diffusion).
-        solver_type (`str`, default `midpoint`):
-            the solver type for the second-order solver. Either `midpoint` or `heun`. The solver type slightly affects
-            the sample quality, especially for small number of steps. We empirically find that `midpoint` solvers are
-            slightly better, so we recommend to use the `midpoint` type.
-        lower_order_final (`bool`, default `True`):
-            whether to use lower-order solvers in the final steps. For singlestep schedulers, we recommend to enable
-            this to use up all the function evaluations.
-        use_karras_sigmas (`bool`, *optional*, defaults to `False`):
-             This parameter controls whether to use Karras sigmas (Karras et al. (2022) scheme) for step sizes in the
-             noise schedule during the sampling process. If True, the sigmas will be determined according to a sequence
-             of noise levels {σi} as defined in Equation (5) of the paper https://arxiv.org/pdf/2206.00364.pdf.
-        lambda_min_clipped (`float`, default `-inf`):
-            the clipping threshold for the minimum value of lambda(t) for numerical stability. This is critical for
-            cosine (squaredcos_cap_v2) noise schedule.
-        variance_type (`str`, *optional*):
-            Set to "learned" or "learned_range" for diffusion models that predict variance. For example, OpenAI's
-            guided-diffusion (https://github.com/openai/guided-diffusion) predicts both mean and variance of the
-            Gaussian distribution in the model's output. DPM-Solver only needs the "mean" output because it is based on
-            diffusion ODEs. whether the model's output contains the predicted Gaussian variance. For example, OpenAI's
-            guided-diffusion (https://github.com/openai/guided-diffusion) predicts both mean and variance of the
-            Gaussian distribution in the model's output. DPM-Solver only needs the "mean" output because it is based on
-            diffusion ODEs.
-
-    """
-
-    _compatibles = [e.name for e in KarrasDiffusionSchedulers]
-    order = 1
-
-    @register_to_config
-    def __init__(
-        self,
-        num_train_timesteps: int = 1000,
-        beta_start: float = 0.0001,
-        beta_end: float = 0.02,
-        beta_schedule: str = "linear",
-        trained_betas: Optional[np.ndarray] = None,
-        solver_order: int = 2,
-        prediction_type: str = "epsilon",
-        thresholding: bool = False,
-        dynamic_thresholding_ratio: float = 0.995,
-        sample_max_value: float = 1.0,
-        algorithm_type: str = "dpmsolver++",
-        solver_type: str = "midpoint",
-        lower_order_final: bool = True,
-        use_karras_sigmas: Optional[bool] = False,
-        lambda_min_clipped: float = -float("inf"),
-        variance_type: Optional[str] = None,
-    ):
-        if trained_betas is not None:
-            self.betas = torch.tensor(trained_betas, dtype=torch.float32)
-        elif beta_schedule == "linear":
-            self.betas = torch.linspace(beta_start, beta_end, num_train_timesteps, dtype=torch.float32)
-        elif beta_schedule == "scaled_linear":
-            # this schedule is very specific to the latent diffusion model.
-            self.betas = (
-                torch.linspace(beta_start**0.5, beta_end**0.5, num_train_timesteps, dtype=torch.float32) ** 2
-            )
-        elif beta_schedule == "squaredcos_cap_v2":
-            # Glide cosine schedule
-            self.betas = betas_for_alpha_bar(num_train_timesteps)
-        else:
-            raise NotImplementedError(f"{beta_schedule} does is not implemented for {self.__class__}")
-
-        self.alphas = 1.0 - self.betas
-        self.alphas_cumprod = torch.cumprod(self.alphas, dim=0)
-        # Currently we only support VP-type noise schedule
-        self.alpha_t = torch.sqrt(self.alphas_cumprod)
-        self.sigma_t = torch.sqrt(1 - self.alphas_cumprod)
-        self.lambda_t = torch.log(self.alpha_t) - torch.log(self.sigma_t)
-
-        # standard deviation of the initial noise distribution
-        self.init_noise_sigma = 1.0
-
-        # settings for DPM-Solver
-        if algorithm_type not in ["dpmsolver", "dpmsolver++"]:
-            if algorithm_type == "deis":
-                self.register_to_config(algorithm_type="dpmsolver++")
-            else:
-                raise NotImplementedError(f"{algorithm_type} does is not implemented for {self.__class__}")
-        if solver_type not in ["midpoint", "heun"]:
-            if solver_type in ["logrho", "bh1", "bh2"]:
-                self.register_to_config(solver_type="midpoint")
-            else:
-                raise NotImplementedError(f"{solver_type} does is not implemented for {self.__class__}")
-
-        # setable values
-        self.num_inference_steps = None
-        timesteps = np.linspace(0, num_train_timesteps - 1, num_train_timesteps, dtype=np.float32)[::-1].copy()
-        self.timesteps = torch.from_numpy(timesteps)
-        self.model_outputs = [None] * solver_order
-        self.sample = None
-        self.order_list = self.get_order_list(num_train_timesteps)
-
-    def get_order_list(self, num_inference_steps: int) -> List[int]:
-        """
-        Computes the solver order at each time step.
-
-        Args:
-            num_inference_steps (`int`):
-                the number of diffusion steps used when generating samples with a pre-trained model.
-        """
-        steps = num_inference_steps
-        order = self.config.solver_order
-        if self.config.lower_order_final:
-            if order == 3:
-                if steps % 3 == 0:
-                    orders = [1, 2, 3] * (steps // 3 - 1) + [1, 2] + [1]
-                elif steps % 3 == 1:
-                    orders = [1, 2, 3] * (steps // 3) + [1]
-                else:
-                    orders = [1, 2, 3] * (steps // 3) + [1, 2]
-            elif order == 2:
-                if steps % 2 == 0:
-                    orders = [1, 2] * (steps // 2)
-                else:
-                    orders = [1, 2] * (steps // 2) + [1]
-            elif order == 1:
-                orders = [1] * steps
-        else:
-            if order == 3:
-                orders = [1, 2, 3] * (steps // 3)
-            elif order == 2:
-                orders = [1, 2] * (steps // 2)
-            elif order == 1:
-                orders = [1] * steps
-        return orders
-
-    def set_timesteps(self, num_inference_steps: int, device: Union[str, torch.device] = None):
-        """
-        Sets the timesteps used for the diffusion chain. Supporting function to be run before inference.
-
-        Args:
-            num_inference_steps (`int`):
-                the number of diffusion steps used when generating samples with a pre-trained model.
-            device (`str` or `torch.device`, optional):
-                the device to which the timesteps should be moved to. If `None`, the timesteps are not moved.
-        """
-        self.num_inference_steps = num_inference_steps
-        # Clipping the minimum of all lambda(t) for numerical stability.
-        # This is critical for cosine (squaredcos_cap_v2) noise schedule.
-        clipped_idx = torch.searchsorted(torch.flip(self.lambda_t, [0]), self.config.lambda_min_clipped)
-        timesteps = (
-            np.linspace(0, self.config.num_train_timesteps - 1 - clipped_idx, num_inference_steps + 1)
-            .round()[::-1][:-1]
-            .copy()
-            .astype(np.int64)
-        )
-
-        sigmas = np.array(((1 - self.alphas_cumprod) / self.alphas_cumprod) ** 0.5)
-        if self.config.use_karras_sigmas:
-            log_sigmas = np.log(sigmas)
-            sigmas = self._convert_to_karras(in_sigmas=sigmas, num_inference_steps=num_inference_steps)
-            timesteps = np.array([self._sigma_to_t(sigma, log_sigmas) for sigma in sigmas]).round()
-            timesteps = np.flip(timesteps).copy().astype(np.int64)
-
-        self.sigmas = torch.from_numpy(sigmas)
-
-        self.timesteps = torch.from_numpy(timesteps).to(device)
-        self.model_outputs = [None] * self.config.solver_order
-        self.sample = None
-
-        if not self.config.lower_order_final and num_inference_steps % self.config.solver_order != 0:
-            logger.warn(
-                "Changing scheduler {self.config} to have `lower_order_final` set to True to handle uneven amount of inference steps. Please make sure to always use an even number of `num_inference steps when using `lower_order_final=True`."
-            )
-            self.register_to_config(lower_order_final=True)
-
-        self.order_list = self.get_order_list(num_inference_steps)
-
-    # Copied from diffusers.schedulers.scheduling_ddpm.DDPMScheduler._threshold_sample
-    def _threshold_sample(self, sample: torch.FloatTensor) -> torch.FloatTensor:
-        """
-        "Dynamic thresholding: At each sampling step we set s to a certain percentile absolute pixel value in xt0 (the
-        prediction of x_0 at timestep t), and if s > 1, then we threshold xt0 to the range [-s, s] and then divide by
-        s. Dynamic thresholding pushes saturated pixels (those near -1 and 1) inwards, thereby actively preventing
-        pixels from saturation at each step. We find that dynamic thresholding results in significantly better
-        photorealism as well as better image-text alignment, especially when using very large guidance weights."
-
-        https://arxiv.org/abs/2205.11487
-        """
-        dtype = sample.dtype
-        batch_size, channels, height, width = sample.shape
-
-        if dtype not in (torch.float32, torch.float64):
-            sample = sample.float()  # upcast for quantile calculation, and clamp not implemented for cpu half
-
-        # Flatten sample for doing quantile calculation along each image
-        sample = sample.reshape(batch_size, channels * height * width)
-
-        abs_sample = sample.abs()  # "a certain percentile absolute pixel value"
-
-        s = torch.quantile(abs_sample, self.config.dynamic_thresholding_ratio, dim=1)
-        s = torch.clamp(
-            s, min=1, max=self.config.sample_max_value
-        )  # When clamped to min=1, equivalent to standard clipping to [-1, 1]
-
-        s = s.unsqueeze(1)  # (batch_size, 1) because clamp will broadcast along dim=0
-        sample = torch.clamp(sample, -s, s) / s  # "we threshold xt0 to the range [-s, s] and then divide by s"
-
-        sample = sample.reshape(batch_size, channels, height, width)
-        sample = sample.to(dtype)
-
-        return sample
-
-    # Copied from diffusers.schedulers.scheduling_euler_discrete.EulerDiscreteScheduler._sigma_to_t
-    def _sigma_to_t(self, sigma, log_sigmas):
-        # get log sigma
-        log_sigma = np.log(sigma)
-
-        # get distribution
-        dists = log_sigma - log_sigmas[:, np.newaxis]
-
-        # get sigmas range
-        low_idx = np.cumsum((dists >= 0), axis=0).argmax(axis=0).clip(max=log_sigmas.shape[0] - 2)
-        high_idx = low_idx + 1
-
-        low = log_sigmas[low_idx]
-        high = log_sigmas[high_idx]
-
-        # interpolate sigmas
-        w = (low - log_sigma) / (low - high)
-        w = np.clip(w, 0, 1)
-
-        # transform interpolation to time range
-        t = (1 - w) * low_idx + w * high_idx
-        t = t.reshape(sigma.shape)
-        return t
-
-    # Copied from diffusers.schedulers.scheduling_euler_discrete.EulerDiscreteScheduler._convert_to_karras
-    def _convert_to_karras(self, in_sigmas: torch.FloatTensor, num_inference_steps) -> torch.FloatTensor:
-        """Constructs the noise schedule of Karras et al. (2022)."""
-
-        sigma_min: float = in_sigmas[-1].item()
-        sigma_max: float = in_sigmas[0].item()
-
-        rho = 7.0  # 7.0 is the value used in the paper
-        ramp = np.linspace(0, 1, num_inference_steps)
-        min_inv_rho = sigma_min ** (1 / rho)
-        max_inv_rho = sigma_max ** (1 / rho)
-        sigmas = (max_inv_rho + ramp * (min_inv_rho - max_inv_rho)) ** rho
-        return sigmas
-
-    def convert_model_output(
-        self, model_output: torch.FloatTensor, timestep: int, sample: torch.FloatTensor
-    ) -> torch.FloatTensor:
-        """
-        Convert the model output to the corresponding type that the algorithm (DPM-Solver / DPM-Solver++) needs.
-
-        DPM-Solver is designed to discretize an integral of the noise prediction model, and DPM-Solver++ is designed to
-        discretize an integral of the data prediction model. So we need to first convert the model output to the
-        corresponding type to match the algorithm.
-
-        Note that the algorithm type and the model type is decoupled. That is to say, we can use either DPM-Solver or
-        DPM-Solver++ for both noise prediction model and data prediction model.
-
-        Args:
-            model_output (`torch.FloatTensor`): direct output from learned diffusion model.
-            timestep (`int`): current discrete timestep in the diffusion chain.
-            sample (`torch.FloatTensor`):
-                current instance of sample being created by diffusion process.
-
-        Returns:
-            `torch.FloatTensor`: the converted model output.
-        """
-        # DPM-Solver++ needs to solve an integral of the data prediction model.
-        if self.config.algorithm_type == "dpmsolver++":
-            if self.config.prediction_type == "epsilon":
-                # DPM-Solver and DPM-Solver++ only need the "mean" output.
-                if self.config.variance_type in ["learned_range"]:
-                    model_output = model_output[:, :3]
-                alpha_t, sigma_t = self.alpha_t[timestep], self.sigma_t[timestep]
-                x0_pred = (sample - sigma_t * model_output) / alpha_t
-            elif self.config.prediction_type == "sample":
-                x0_pred = model_output
-            elif self.config.prediction_type == "v_prediction":
-                alpha_t, sigma_t = self.alpha_t[timestep], self.sigma_t[timestep]
-                x0_pred = alpha_t * sample - sigma_t * model_output
-            else:
-                raise ValueError(
-                    f"prediction_type given as {self.config.prediction_type} must be one of `epsilon`, `sample`, or"
-                    " `v_prediction` for the DPMSolverSinglestepScheduler."
-                )
-
-            if self.config.thresholding:
-                x0_pred = self._threshold_sample(x0_pred)
-
-            return x0_pred
-        # DPM-Solver needs to solve an integral of the noise prediction model.
-        elif self.config.algorithm_type == "dpmsolver":
-            if self.config.prediction_type == "epsilon":
-                # DPM-Solver and DPM-Solver++ only need the "mean" output.
-                if self.config.variance_type in ["learned_range"]:
-                    model_output = model_output[:, :3]
-                return model_output
-            elif self.config.prediction_type == "sample":
-                alpha_t, sigma_t = self.alpha_t[timestep], self.sigma_t[timestep]
-                epsilon = (sample - alpha_t * model_output) / sigma_t
-                return epsilon
-            elif self.config.prediction_type == "v_prediction":
-                alpha_t, sigma_t = self.alpha_t[timestep], self.sigma_t[timestep]
-                epsilon = alpha_t * model_output + sigma_t * sample
-                return epsilon
-            else:
-                raise ValueError(
-                    f"prediction_type given as {self.config.prediction_type} must be one of `epsilon`, `sample`, or"
-                    " `v_prediction` for the DPMSolverSinglestepScheduler."
-                )
-
-    def dpm_solver_first_order_update(
-        self,
-        model_output: torch.FloatTensor,
-        timestep: int,
-        prev_timestep: int,
-        sample: torch.FloatTensor,
-    ) -> torch.FloatTensor:
-        """
-        One step for the first-order DPM-Solver (equivalent to DDIM).
-
-        See https://arxiv.org/abs/2206.00927 for the detailed derivation.
-
-        Args:
-            model_output (`torch.FloatTensor`): direct output from learned diffusion model.
-            timestep (`int`): current discrete timestep in the diffusion chain.
-            prev_timestep (`int`): previous discrete timestep in the diffusion chain.
-            sample (`torch.FloatTensor`):
-                current instance of sample being created by diffusion process.
-
-        Returns:
-            `torch.FloatTensor`: the sample tensor at the previous timestep.
-        """
-        lambda_t, lambda_s = self.lambda_t[prev_timestep], self.lambda_t[timestep]
-        alpha_t, alpha_s = self.alpha_t[prev_timestep], self.alpha_t[timestep]
-        sigma_t, sigma_s = self.sigma_t[prev_timestep], self.sigma_t[timestep]
-        h = lambda_t - lambda_s
-        if self.config.algorithm_type == "dpmsolver++":
-            x_t = (sigma_t / sigma_s) * sample - (alpha_t * (torch.exp(-h) - 1.0)) * model_output
-        elif self.config.algorithm_type == "dpmsolver":
-            x_t = (alpha_t / alpha_s) * sample - (sigma_t * (torch.exp(h) - 1.0)) * model_output
-        return x_t
-
-    def singlestep_dpm_solver_second_order_update(
-        self,
-        model_output_list: List[torch.FloatTensor],
-        timestep_list: List[int],
-        prev_timestep: int,
-        sample: torch.FloatTensor,
-    ) -> torch.FloatTensor:
-        """
-        One step for the second-order singlestep DPM-Solver.
-
-        It computes the solution at time `prev_timestep` from the time `timestep_list[-2]`.
-
-        Args:
-            model_output_list (`List[torch.FloatTensor]`):
-                direct outputs from learned diffusion model at current and latter timesteps.
-            timestep (`int`): current and latter discrete timestep in the diffusion chain.
-            prev_timestep (`int`): previous discrete timestep in the diffusion chain.
-            sample (`torch.FloatTensor`):
-                current instance of sample being created by diffusion process.
-
-        Returns:
-            `torch.FloatTensor`: the sample tensor at the previous timestep.
-        """
-        t, s0, s1 = prev_timestep, timestep_list[-1], timestep_list[-2]
-        m0, m1 = model_output_list[-1], model_output_list[-2]
-        lambda_t, lambda_s0, lambda_s1 = self.lambda_t[t], self.lambda_t[s0], self.lambda_t[s1]
-        alpha_t, alpha_s1 = self.alpha_t[t], self.alpha_t[s1]
-        sigma_t, sigma_s1 = self.sigma_t[t], self.sigma_t[s1]
-        h, h_0 = lambda_t - lambda_s1, lambda_s0 - lambda_s1
-        r0 = h_0 / h
-        D0, D1 = m1, (1.0 / r0) * (m0 - m1)
-        if self.config.algorithm_type == "dpmsolver++":
-            # See https://arxiv.org/abs/2211.01095 for detailed derivations
-            if self.config.solver_type == "midpoint":
-                x_t = (
-                    (sigma_t / sigma_s1) * sample
-                    - (alpha_t * (torch.exp(-h) - 1.0)) * D0
-                    - 0.5 * (alpha_t * (torch.exp(-h) - 1.0)) * D1
-                )
-            elif self.config.solver_type == "heun":
-                x_t = (
-                    (sigma_t / sigma_s1) * sample
-                    - (alpha_t * (torch.exp(-h) - 1.0)) * D0
-                    + (alpha_t * ((torch.exp(-h) - 1.0) / h + 1.0)) * D1
-                )
-        elif self.config.algorithm_type == "dpmsolver":
-            # See https://arxiv.org/abs/2206.00927 for detailed derivations
-            if self.config.solver_type == "midpoint":
-                x_t = (
-                    (alpha_t / alpha_s1) * sample
-                    - (sigma_t * (torch.exp(h) - 1.0)) * D0
-                    - 0.5 * (sigma_t * (torch.exp(h) - 1.0)) * D1
-                )
-            elif self.config.solver_type == "heun":
-                x_t = (
-                    (alpha_t / alpha_s1) * sample
-                    - (sigma_t * (torch.exp(h) - 1.0)) * D0
-                    - (sigma_t * ((torch.exp(h) - 1.0) / h - 1.0)) * D1
-                )
-        return x_t
-
-    def singlestep_dpm_solver_third_order_update(
-        self,
-        model_output_list: List[torch.FloatTensor],
-        timestep_list: List[int],
-        prev_timestep: int,
-        sample: torch.FloatTensor,
-    ) -> torch.FloatTensor:
-        """
-        One step for the third-order singlestep DPM-Solver.
-
-        It computes the solution at time `prev_timestep` from the time `timestep_list[-3]`.
-
-        Args:
-            model_output_list (`List[torch.FloatTensor]`):
-                direct outputs from learned diffusion model at current and latter timesteps.
-            timestep (`int`): current and latter discrete timestep in the diffusion chain.
-            prev_timestep (`int`): previous discrete timestep in the diffusion chain.
-            sample (`torch.FloatTensor`):
-                current instance of sample being created by diffusion process.
-
-        Returns:
-            `torch.FloatTensor`: the sample tensor at the previous timestep.
-        """
-        t, s0, s1, s2 = prev_timestep, timestep_list[-1], timestep_list[-2], timestep_list[-3]
-        m0, m1, m2 = model_output_list[-1], model_output_list[-2], model_output_list[-3]
-        lambda_t, lambda_s0, lambda_s1, lambda_s2 = (
-            self.lambda_t[t],
-            self.lambda_t[s0],
-            self.lambda_t[s1],
-            self.lambda_t[s2],
-        )
-        alpha_t, alpha_s2 = self.alpha_t[t], self.alpha_t[s2]
-        sigma_t, sigma_s2 = self.sigma_t[t], self.sigma_t[s2]
-        h, h_0, h_1 = lambda_t - lambda_s2, lambda_s0 - lambda_s2, lambda_s1 - lambda_s2
-        r0, r1 = h_0 / h, h_1 / h
-        D0 = m2
-        D1_0, D1_1 = (1.0 / r1) * (m1 - m2), (1.0 / r0) * (m0 - m2)
-        D1 = (r0 * D1_0 - r1 * D1_1) / (r0 - r1)
-        D2 = 2.0 * (D1_1 - D1_0) / (r0 - r1)
-        if self.config.algorithm_type == "dpmsolver++":
-            # See https://arxiv.org/abs/2206.00927 for detailed derivations
-            if self.config.solver_type == "midpoint":
-                x_t = (
-                    (sigma_t / sigma_s2) * sample
-                    - (alpha_t * (torch.exp(-h) - 1.0)) * D0
-                    + (alpha_t * ((torch.exp(-h) - 1.0) / h + 1.0)) * D1_1
-                )
-            elif self.config.solver_type == "heun":
-                x_t = (
-                    (sigma_t / sigma_s2) * sample
-                    - (alpha_t * (torch.exp(-h) - 1.0)) * D0
-                    + (alpha_t * ((torch.exp(-h) - 1.0) / h + 1.0)) * D1
-                    - (alpha_t * ((torch.exp(-h) - 1.0 + h) / h**2 - 0.5)) * D2
-                )
-        elif self.config.algorithm_type == "dpmsolver":
-            # See https://arxiv.org/abs/2206.00927 for detailed derivations
-            if self.config.solver_type == "midpoint":
-                x_t = (
-                    (alpha_t / alpha_s2) * sample
-                    - (sigma_t * (torch.exp(h) - 1.0)) * D0
-                    - (sigma_t * ((torch.exp(h) - 1.0) / h - 1.0)) * D1_1
-                )
-            elif self.config.solver_type == "heun":
-                x_t = (
-                    (alpha_t / alpha_s2) * sample
-                    - (sigma_t * (torch.exp(h) - 1.0)) * D0
-                    - (sigma_t * ((torch.exp(h) - 1.0) / h - 1.0)) * D1
-                    - (sigma_t * ((torch.exp(h) - 1.0 - h) / h**2 - 0.5)) * D2
-                )
-        return x_t
-
-    def singlestep_dpm_solver_update(
-        self,
-        model_output_list: List[torch.FloatTensor],
-        timestep_list: List[int],
-        prev_timestep: int,
-        sample: torch.FloatTensor,
-        order: int,
-    ) -> torch.FloatTensor:
-        """
-        One step for the singlestep DPM-Solver.
-
-        Args:
-            model_output_list (`List[torch.FloatTensor]`):
-                direct outputs from learned diffusion model at current and latter timesteps.
-            timestep (`int`): current and latter discrete timestep in the diffusion chain.
-            prev_timestep (`int`): previous discrete timestep in the diffusion chain.
-            sample (`torch.FloatTensor`):
-                current instance of sample being created by diffusion process.
-            order (`int`):
-                the solver order at this step.
-
-        Returns:
-            `torch.FloatTensor`: the sample tensor at the previous timestep.
-        """
-        if order == 1:
-            return self.dpm_solver_first_order_update(model_output_list[-1], timestep_list[-1], prev_timestep, sample)
-        elif order == 2:
-            return self.singlestep_dpm_solver_second_order_update(
-                model_output_list, timestep_list, prev_timestep, sample
-            )
-        elif order == 3:
-            return self.singlestep_dpm_solver_third_order_update(
-                model_output_list, timestep_list, prev_timestep, sample
-            )
-        else:
-            raise ValueError(f"Order must be 1, 2, 3, got {order}")
-
-    def step(
-        self,
-        model_output: torch.FloatTensor,
-        timestep: int,
-        sample: torch.FloatTensor,
-        return_dict: bool = True,
-    ) -> Union[SchedulerOutput, Tuple]:
-        """
-        Step function propagating the sample with the singlestep DPM-Solver.
-
-        Args:
-            model_output (`torch.FloatTensor`): direct output from learned diffusion model.
-            timestep (`int`): current discrete timestep in the diffusion chain.
-            sample (`torch.FloatTensor`):
-                current instance of sample being created by diffusion process.
-            return_dict (`bool`): option for returning tuple rather than SchedulerOutput class
-
-        Returns:
-            [`~scheduling_utils.SchedulerOutput`] or `tuple`: [`~scheduling_utils.SchedulerOutput`] if `return_dict` is
-            True, otherwise a `tuple`. When returning a tuple, the first element is the sample tensor.
-
-        """
-        if self.num_inference_steps is None:
-            raise ValueError(
-                "Number of inference steps is 'None', you need to run 'set_timesteps' after creating the scheduler"
-            )
-
-        if isinstance(timestep, torch.Tensor):
-            timestep = timestep.to(self.timesteps.device)
-        step_index = (self.timesteps == timestep).nonzero()
-        if len(step_index) == 0:
-            step_index = len(self.timesteps) - 1
-        else:
-            step_index = step_index.item()
-        prev_timestep = 0 if step_index == len(self.timesteps) - 1 else self.timesteps[step_index + 1]
-
-        model_output = self.convert_model_output(model_output, timestep, sample)
-        for i in range(self.config.solver_order - 1):
-            self.model_outputs[i] = self.model_outputs[i + 1]
-        self.model_outputs[-1] = model_output
-
-        order = self.order_list[step_index]
-
-        #  For img2img denoising might start with order>1 which is not possible
-        #  In this case make sure that the first two steps are both order=1
-        while self.model_outputs[-order] is None:
-            order -= 1
-
-        # For single-step solvers, we use the initial value at each time with order = 1.
-        if order == 1:
-            self.sample = sample
-
-        timestep_list = [self.timesteps[step_index - i] for i in range(order - 1, 0, -1)] + [timestep]
-        prev_sample = self.singlestep_dpm_solver_update(
-            self.model_outputs, timestep_list, prev_timestep, self.sample, order
-        )
-
-        if not return_dict:
-            return (prev_sample,)
-
-        return SchedulerOutput(prev_sample=prev_sample)
-
-    def scale_model_input(self, sample: torch.FloatTensor, *args, **kwargs) -> torch.FloatTensor:
-        """
-        Ensures interchangeability with schedulers that need to scale the denoising model input depending on the
-        current timestep.
-
-        Args:
-            sample (`torch.FloatTensor`): input sample
-
-        Returns:
-            `torch.FloatTensor`: scaled input sample
-        """
-        return sample
-
-    # Copied from diffusers.schedulers.scheduling_ddpm.DDPMScheduler.add_noise
-    def add_noise(
-        self,
-        original_samples: torch.FloatTensor,
-        noise: torch.FloatTensor,
-        timesteps: torch.IntTensor,
-    ) -> torch.FloatTensor:
-        # Make sure alphas_cumprod and timestep have same device and dtype as original_samples
-        alphas_cumprod = self.alphas_cumprod.to(device=original_samples.device, dtype=original_samples.dtype)
-        timesteps = timesteps.to(original_samples.device)
-
-        sqrt_alpha_prod = alphas_cumprod[timesteps] ** 0.5
-        sqrt_alpha_prod = sqrt_alpha_prod.flatten()
-        while len(sqrt_alpha_prod.shape) < len(original_samples.shape):
-            sqrt_alpha_prod = sqrt_alpha_prod.unsqueeze(-1)
-
-        sqrt_one_minus_alpha_prod = (1 - alphas_cumprod[timesteps]) ** 0.5
-        sqrt_one_minus_alpha_prod = sqrt_one_minus_alpha_prod.flatten()
-        while len(sqrt_one_minus_alpha_prod.shape) < len(original_samples.shape):
-            sqrt_one_minus_alpha_prod = sqrt_one_minus_alpha_prod.unsqueeze(-1)
-
-        noisy_samples = sqrt_alpha_prod * original_samples + sqrt_one_minus_alpha_prod * noise
-        return noisy_samples
-
-    def __len__(self):
-        return self.config.num_train_timesteps
diff --git a/spaces/Andy1621/uniformer_image_detection/configs/_base_/datasets/coco_instance_semantic.py b/spaces/Andy1621/uniformer_image_detection/configs/_base_/datasets/coco_instance_semantic.py
deleted file mode 100644
index f7c072ec92731af85952840128f6527bc799913a..0000000000000000000000000000000000000000
--- a/spaces/Andy1621/uniformer_image_detection/configs/_base_/datasets/coco_instance_semantic.py
+++ /dev/null
@@ -1,53 +0,0 @@
-dataset_type = 'CocoDataset'
-data_root = 'data/coco/'
-img_norm_cfg = dict(
-    mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True)
-train_pipeline = [
-    dict(type='LoadImageFromFile'),
-    dict(
-        type='LoadAnnotations', with_bbox=True, with_mask=True, with_seg=True),
-    dict(type='Resize', img_scale=(1333, 800), keep_ratio=True),
-    dict(type='RandomFlip', flip_ratio=0.5),
-    dict(type='Normalize', **img_norm_cfg),
-    dict(type='Pad', size_divisor=32),
-    dict(type='SegRescale', scale_factor=1 / 8),
-    dict(type='DefaultFormatBundle'),
-    dict(
-        type='Collect',
-        keys=['img', 'gt_bboxes', 'gt_labels', 'gt_masks', 'gt_semantic_seg']),
-]
-test_pipeline = [
-    dict(type='LoadImageFromFile'),
-    dict(
-        type='MultiScaleFlipAug',
-        img_scale=(1333, 800),
-        flip=False,
-        transforms=[
-            dict(type='Resize', keep_ratio=True),
-            dict(type='RandomFlip', flip_ratio=0.5),
-            dict(type='Normalize', **img_norm_cfg),
-            dict(type='Pad', size_divisor=32),
-            dict(type='ImageToTensor', keys=['img']),
-            dict(type='Collect', keys=['img']),
-        ])
-]
-data = dict(
-    samples_per_gpu=2,
-    workers_per_gpu=2,
-    train=dict(
-        type=dataset_type,
-        ann_file=data_root + 'annotations/instances_train2017.json',
-        img_prefix=data_root + 'train2017/',
-        seg_prefix=data_root + 'stuffthingmaps/train2017/',
-        pipeline=train_pipeline),
-    val=dict(
-        type=dataset_type,
-        ann_file=data_root + 'annotations/instances_val2017.json',
-        img_prefix=data_root + 'val2017/',
-        pipeline=test_pipeline),
-    test=dict(
-        type=dataset_type,
-        ann_file=data_root + 'annotations/instances_val2017.json',
-        img_prefix=data_root + 'val2017/',
-        pipeline=test_pipeline))
-evaluation = dict(metric=['bbox', 'segm'])
diff --git a/spaces/Andy1621/uniformer_image_detection/configs/atss/atss_r101_fpn_1x_coco.py b/spaces/Andy1621/uniformer_image_detection/configs/atss/atss_r101_fpn_1x_coco.py
deleted file mode 100644
index 695779ab31b5f848f8c85c13cc4ca637c8590ba7..0000000000000000000000000000000000000000
--- a/spaces/Andy1621/uniformer_image_detection/configs/atss/atss_r101_fpn_1x_coco.py
+++ /dev/null
@@ -1,5 +0,0 @@
-_base_ = './atss_r50_fpn_1x_coco.py'
-model = dict(
-    pretrained='torchvision://resnet101',
-    backbone=dict(depth=101),
-)
diff --git a/spaces/Andy1621/uniformer_image_segmentation/configs/gcnet/gcnet_r50-d8_512x512_80k_ade20k.py b/spaces/Andy1621/uniformer_image_segmentation/configs/gcnet/gcnet_r50-d8_512x512_80k_ade20k.py
deleted file mode 100644
index 89d5e1ae0f3ef44626f3b5534c504cbce7389a32..0000000000000000000000000000000000000000
--- a/spaces/Andy1621/uniformer_image_segmentation/configs/gcnet/gcnet_r50-d8_512x512_80k_ade20k.py
+++ /dev/null
@@ -1,6 +0,0 @@
-_base_ = [
-    '../_base_/models/gcnet_r50-d8.py', '../_base_/datasets/ade20k.py',
-    '../_base_/default_runtime.py', '../_base_/schedules/schedule_80k.py'
-]
-model = dict(
-    decode_head=dict(num_classes=150), auxiliary_head=dict(num_classes=150))
diff --git a/spaces/Anonymous-sub/Rerender/ControlNet/annotator/uniformer/mmcv/video/io.py b/spaces/Anonymous-sub/Rerender/ControlNet/annotator/uniformer/mmcv/video/io.py
deleted file mode 100644
index 9879154227f640c262853b92c219461c6f67ee8e..0000000000000000000000000000000000000000
--- a/spaces/Anonymous-sub/Rerender/ControlNet/annotator/uniformer/mmcv/video/io.py
+++ /dev/null
@@ -1,318 +0,0 @@
-# Copyright (c) OpenMMLab. All rights reserved.
-import os.path as osp
-from collections import OrderedDict
-
-import cv2
-from cv2 import (CAP_PROP_FOURCC, CAP_PROP_FPS, CAP_PROP_FRAME_COUNT,
-                 CAP_PROP_FRAME_HEIGHT, CAP_PROP_FRAME_WIDTH,
-                 CAP_PROP_POS_FRAMES, VideoWriter_fourcc)
-
-from annotator.uniformer.mmcv.utils import (check_file_exist, mkdir_or_exist, scandir,
-                        track_progress)
-
-
-class Cache:
-
-    def __init__(self, capacity):
-        self._cache = OrderedDict()
-        self._capacity = int(capacity)
-        if capacity <= 0:
-            raise ValueError('capacity must be a positive integer')
-
-    @property
-    def capacity(self):
-        return self._capacity
-
-    @property
-    def size(self):
-        return len(self._cache)
-
-    def put(self, key, val):
-        if key in self._cache:
-            return
-        if len(self._cache) >= self.capacity:
-            self._cache.popitem(last=False)
-        self._cache[key] = val
-
-    def get(self, key, default=None):
-        val = self._cache[key] if key in self._cache else default
-        return val
-
-
-class VideoReader:
-    """Video class with similar usage to a list object.
-
-    This video warpper class provides convenient apis to access frames.
-    There exists an issue of OpenCV's VideoCapture class that jumping to a
-    certain frame may be inaccurate. It is fixed in this class by checking
-    the position after jumping each time.
-    Cache is used when decoding videos. So if the same frame is visited for
-    the second time, there is no need to decode again if it is stored in the
-    cache.
-
-    :Example:
-
-    >>> import annotator.uniformer.mmcv as mmcv
-    >>> v = mmcv.VideoReader('sample.mp4')
-    >>> len(v)  # get the total frame number with `len()`
-    120
-    >>> for img in v:  # v is iterable
-    >>>     mmcv.imshow(img)
-    >>> v[5]  # get the 6th frame
-    """
-
-    def __init__(self, filename, cache_capacity=10):
-        # Check whether the video path is a url
-        if not filename.startswith(('https://', 'http://')):
-            check_file_exist(filename, 'Video file not found: ' + filename)
-        self._vcap = cv2.VideoCapture(filename)
-        assert cache_capacity > 0
-        self._cache = Cache(cache_capacity)
-        self._position = 0
-        # get basic info
-        self._width = int(self._vcap.get(CAP_PROP_FRAME_WIDTH))
-        self._height = int(self._vcap.get(CAP_PROP_FRAME_HEIGHT))
-        self._fps = self._vcap.get(CAP_PROP_FPS)
-        self._frame_cnt = int(self._vcap.get(CAP_PROP_FRAME_COUNT))
-        self._fourcc = self._vcap.get(CAP_PROP_FOURCC)
-
-    @property
-    def vcap(self):
-        """:obj:`cv2.VideoCapture`: The raw VideoCapture object."""
-        return self._vcap
-
-    @property
-    def opened(self):
-        """bool: Indicate whether the video is opened."""
-        return self._vcap.isOpened()
-
-    @property
-    def width(self):
-        """int: Width of video frames."""
-        return self._width
-
-    @property
-    def height(self):
-        """int: Height of video frames."""
-        return self._height
-
-    @property
-    def resolution(self):
-        """tuple: Video resolution (width, height)."""
-        return (self._width, self._height)
-
-    @property
-    def fps(self):
-        """float: FPS of the video."""
-        return self._fps
-
-    @property
-    def frame_cnt(self):
-        """int: Total frames of the video."""
-        return self._frame_cnt
-
-    @property
-    def fourcc(self):
-        """str: "Four character code" of the video."""
-        return self._fourcc
-
-    @property
-    def position(self):
-        """int: Current cursor position, indicating frame decoded."""
-        return self._position
-
-    def _get_real_position(self):
-        return int(round(self._vcap.get(CAP_PROP_POS_FRAMES)))
-
-    def _set_real_position(self, frame_id):
-        self._vcap.set(CAP_PROP_POS_FRAMES, frame_id)
-        pos = self._get_real_position()
-        for _ in range(frame_id - pos):
-            self._vcap.read()
-        self._position = frame_id
-
-    def read(self):
-        """Read the next frame.
-
-        If the next frame have been decoded before and in the cache, then
-        return it directly, otherwise decode, cache and return it.
-
-        Returns:
-            ndarray or None: Return the frame if successful, otherwise None.
-        """
-        # pos = self._position
-        if self._cache:
-            img = self._cache.get(self._position)
-            if img is not None:
-                ret = True
-            else:
-                if self._position != self._get_real_position():
-                    self._set_real_position(self._position)
-                ret, img = self._vcap.read()
-                if ret:
-                    self._cache.put(self._position, img)
-        else:
-            ret, img = self._vcap.read()
-        if ret:
-            self._position += 1
-        return img
-
-    def get_frame(self, frame_id):
-        """Get frame by index.
-
-        Args:
-            frame_id (int): Index of the expected frame, 0-based.
-
-        Returns:
-            ndarray or None: Return the frame if successful, otherwise None.
-        """
-        if frame_id < 0 or frame_id >= self._frame_cnt:
-            raise IndexError(
-                f'"frame_id" must be between 0 and {self._frame_cnt - 1}')
-        if frame_id == self._position:
-            return self.read()
-        if self._cache:
-            img = self._cache.get(frame_id)
-            if img is not None:
-                self._position = frame_id + 1
-                return img
-        self._set_real_position(frame_id)
-        ret, img = self._vcap.read()
-        if ret:
-            if self._cache:
-                self._cache.put(self._position, img)
-            self._position += 1
-        return img
-
-    def current_frame(self):
-        """Get the current frame (frame that is just visited).
-
-        Returns:
-            ndarray or None: If the video is fresh, return None, otherwise
-                return the frame.
-        """
-        if self._position == 0:
-            return None
-        return self._cache.get(self._position - 1)
-
-    def cvt2frames(self,
-                   frame_dir,
-                   file_start=0,
-                   filename_tmpl='{:06d}.jpg',
-                   start=0,
-                   max_num=0,
-                   show_progress=True):
-        """Convert a video to frame images.
-
-        Args:
-            frame_dir (str): Output directory to store all the frame images.
-            file_start (int): Filenames will start from the specified number.
-            filename_tmpl (str): Filename template with the index as the
-                placeholder.
-            start (int): The starting frame index.
-            max_num (int): Maximum number of frames to be written.
-            show_progress (bool): Whether to show a progress bar.
-        """
-        mkdir_or_exist(frame_dir)
-        if max_num == 0:
-            task_num = self.frame_cnt - start
-        else:
-            task_num = min(self.frame_cnt - start, max_num)
-        if task_num <= 0:
-            raise ValueError('start must be less than total frame number')
-        if start > 0:
-            self._set_real_position(start)
-
-        def write_frame(file_idx):
-            img = self.read()
-            if img is None:
-                return
-            filename = osp.join(frame_dir, filename_tmpl.format(file_idx))
-            cv2.imwrite(filename, img)
-
-        if show_progress:
-            track_progress(write_frame, range(file_start,
-                                              file_start + task_num))
-        else:
-            for i in range(task_num):
-                write_frame(file_start + i)
-
-    def __len__(self):
-        return self.frame_cnt
-
-    def __getitem__(self, index):
-        if isinstance(index, slice):
-            return [
-                self.get_frame(i)
-                for i in range(*index.indices(self.frame_cnt))
-            ]
-        # support negative indexing
-        if index < 0:
-            index += self.frame_cnt
-            if index < 0:
-                raise IndexError('index out of range')
-        return self.get_frame(index)
-
-    def __iter__(self):
-        self._set_real_position(0)
-        return self
-
-    def __next__(self):
-        img = self.read()
-        if img is not None:
-            return img
-        else:
-            raise StopIteration
-
-    next = __next__
-
-    def __enter__(self):
-        return self
-
-    def __exit__(self, exc_type, exc_value, traceback):
-        self._vcap.release()
-
-
-def frames2video(frame_dir,
-                 video_file,
-                 fps=30,
-                 fourcc='XVID',
-                 filename_tmpl='{:06d}.jpg',
-                 start=0,
-                 end=0,
-                 show_progress=True):
-    """Read the frame images from a directory and join them as a video.
-
-    Args:
-        frame_dir (str): The directory containing video frames.
-        video_file (str): Output filename.
-        fps (float): FPS of the output video.
-        fourcc (str): Fourcc of the output video, this should be compatible
-            with the output file type.
-        filename_tmpl (str): Filename template with the index as the variable.
-        start (int): Starting frame index.
-        end (int): Ending frame index.
-        show_progress (bool): Whether to show a progress bar.
-    """
-    if end == 0:
-        ext = filename_tmpl.split('.')[-1]
-        end = len([name for name in scandir(frame_dir, ext)])
-    first_file = osp.join(frame_dir, filename_tmpl.format(start))
-    check_file_exist(first_file, 'The start frame not found: ' + first_file)
-    img = cv2.imread(first_file)
-    height, width = img.shape[:2]
-    resolution = (width, height)
-    vwriter = cv2.VideoWriter(video_file, VideoWriter_fourcc(*fourcc), fps,
-                              resolution)
-
-    def write_frame(file_idx):
-        filename = osp.join(frame_dir, filename_tmpl.format(file_idx))
-        img = cv2.imread(filename)
-        vwriter.write(img)
-
-    if show_progress:
-        track_progress(write_frame, range(start, end))
-    else:
-        for i in range(start, end):
-            write_frame(i)
-    vwriter.release()
diff --git a/spaces/ArtificialWF/Voice-Recognition/app.py b/spaces/ArtificialWF/Voice-Recognition/app.py
deleted file mode 100644
index 19ec8816c4aae0051f9919d11d485a42b5880bf9..0000000000000000000000000000000000000000
--- a/spaces/ArtificialWF/Voice-Recognition/app.py
+++ /dev/null
@@ -1,109 +0,0 @@
-import whisper
-import gradio as gr
-import datetime
-
-import subprocess
-
-import torch
-import pyannote.audio
-from pyannote.audio.pipelines.speaker_verification import PretrainedSpeakerEmbedding
-
-from pyannote.audio import Audio
-from pyannote.core import Segment
-
-import wave
-import contextlib
-
-from sklearn.cluster import AgglomerativeClustering
-import numpy as np
-
-model = whisper.load_model("large-v2")
-embedding_model = PretrainedSpeakerEmbedding( 
-    "speechbrain/spkrec-ecapa-voxceleb",
-    device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
-)
-
-def transcribe(audio, num_speakers):
-  path, error = convert_to_wav(audio)
-  if error is not None:
-    return error
-
-  duration = get_duration(path)
-  if duration > 4 * 60 * 60:
-    return "Audio duration too long"
-
-  result = model.transcribe(path)
-  segments = result["segments"]
-
-  num_speakers = min(max(round(num_speakers), 1), len(segments))
-  if len(segments) == 1:
-    segments[0]['speaker'] = 'SPEAKER 1'
-  else:
-    embeddings = make_embeddings(path, segments, duration)
-    add_speaker_labels(segments, embeddings, num_speakers)
-  output = get_output(segments)
-  return output
-
-def convert_to_wav(path):
-  if path[-3:] != 'wav':
-    new_path = '.'.join(path.split('.')[:-1]) + '.wav'
-    try:
-      subprocess.call(['ffmpeg', '-i', path, new_path, '-y'])
-    except:
-      return path, 'Error: Could not convert file to .wav'
-    path = new_path
-  return path, None
-
-def get_duration(path):
-  with contextlib.closing(wave.open(path,'r')) as f:
-    frames = f.getnframes()
-    rate = f.getframerate()
-    return frames / float(rate)
-
-def make_embeddings(path, segments, duration):
-  embeddings = np.zeros(shape=(len(segments), 192))
-  for i, segment in enumerate(segments):
-    embeddings[i] = segment_embedding(path, segment, duration)
-  return np.nan_to_num(embeddings)
-
-audio = Audio()
-
-def segment_embedding(path, segment, duration):
-  start = segment["start"]
-  # Whisper overshoots the end timestamp in the last segment
-  end = min(duration, segment["end"])
-  clip = Segment(start, end)
-  waveform, sample_rate = audio.crop(path, clip)
-  return embedding_model(waveform[None])
-
-def add_speaker_labels(segments, embeddings, num_speakers):
-  clustering = AgglomerativeClustering(num_speakers).fit(embeddings)
-  labels = clustering.labels_
-  for i in range(len(segments)):
-    segments[i]["speaker"] = 'SPEAKER ' + str(labels[i] + 1)
-
-def time(secs):
-  return datetime.timedelta(seconds=round(secs))
-
-def get_output(segments):
-  output = ''
-  for (i, segment) in enumerate(segments):
-    if i == 0 or segments[i - 1]["speaker"] != segment["speaker"]:
-      if i != 0:
-        output += '\n\n'
-      output += segment["speaker"] + ' ' + str(time(segment["start"])) + '\n\n'
-    output += segment["text"][1:] + ' '
-  return output
-
-gr.Interface(
-    title = 'AI Voice to Text', 
-    fn=transcribe, 
-    inputs=[
-        gr.inputs.Audio(source="upload", type="filepath"),
-        gr.inputs.Number(default=2, label="Number of Speakers")
-
-    ],
-    outputs=[
-        gr.outputs.Textbox(label='Transcript')
-    ]
-  ).launch()
\ No newline at end of file
diff --git a/spaces/Ataturk-Chatbot/HuggingFaceChat/venv/lib/python3.11/site-packages/pip/_internal/operations/__init__.py b/spaces/Ataturk-Chatbot/HuggingFaceChat/venv/lib/python3.11/site-packages/pip/_internal/operations/__init__.py
deleted file mode 100644
index e69de29bb2d1d6434b8b29ae775ad8c2e48c5391..0000000000000000000000000000000000000000
diff --git a/spaces/AutoGeneralAI/voice-assistant/README.md b/spaces/AutoGeneralAI/voice-assistant/README.md
deleted file mode 100644
index 39cfcc5905469bfddbed391458f4d7b896c512f8..0000000000000000000000000000000000000000
--- a/spaces/AutoGeneralAI/voice-assistant/README.md
+++ /dev/null
@@ -1,12 +0,0 @@
----
-title: Voice Assistant
-emoji: 🐠
-colorFrom: yellow
-colorTo: red
-sdk: gradio
-sdk_version: 3.27.0
-app_file: app.py
-pinned: false
----
-
-Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
diff --git a/spaces/Awesimo/jojogan/e4e/utils/train_utils.py b/spaces/Awesimo/jojogan/e4e/utils/train_utils.py
deleted file mode 100644
index 0c55177f7442010bc1fcc64de3d142585c22adc0..0000000000000000000000000000000000000000
--- a/spaces/Awesimo/jojogan/e4e/utils/train_utils.py
+++ /dev/null
@@ -1,13 +0,0 @@
-
-def aggregate_loss_dict(agg_loss_dict):
-	mean_vals = {}
-	for output in agg_loss_dict:
-		for key in output:
-			mean_vals[key] = mean_vals.setdefault(key, []) + [output[key]]
-	for key in mean_vals:
-		if len(mean_vals[key]) > 0:
-			mean_vals[key] = sum(mean_vals[key]) / len(mean_vals[key])
-		else:
-			print('{} has no value'.format(key))
-			mean_vals[key] = 0
-	return mean_vals
diff --git a/spaces/Bart92/RVC_HF/diffq/utils.py b/spaces/Bart92/RVC_HF/diffq/utils.py
deleted file mode 100644
index be6ab5253c38564140bc202077292bb99f9f397b..0000000000000000000000000000000000000000
--- a/spaces/Bart92/RVC_HF/diffq/utils.py
+++ /dev/null
@@ -1,37 +0,0 @@
-# Copyright (c) Facebook, Inc. and its affiliates.
-# All rights reserved.
-#
-# This source code is licensed under the license found in the
-# LICENSE file in the root directory of this source tree.
-
-import inspect
-from typing import Optional, List
-
-
-def simple_repr(obj, attrs: Optional[List[str]] = None, overrides={}):
-    """
-    Return a simple representation string for `obj`.
-    If `attrs` is not None, it should be a list of attributes to include.
-    """
-    params = inspect.signature(obj.__class__).parameters
-    attrs_repr = []
-    if attrs is None:
-        attrs = params.keys()
-    for attr in attrs:
-        display = False
-        if attr in overrides:
-            value = overrides[attr]
-        elif hasattr(obj, attr):
-            value = getattr(obj, attr)
-        else:
-            continue
-        if attr in params:
-            param = params[attr]
-            if param.default is inspect._empty or value != param.default:
-                display = True
-        else:
-            display = True
-
-        if display:
-            attrs_repr.append(f"{attr}={value}")
-    return f"{obj.__class__.__name__}({','.join(attrs_repr)})"
diff --git a/spaces/Benson/text-generation/Examples/Descargar 3utools Para Mac Air.md b/spaces/Benson/text-generation/Examples/Descargar 3utools Para Mac Air.md
deleted file mode 100644
index cf906b56a053245f1b300c87db163272c7f46d8b..0000000000000000000000000000000000000000
--- a/spaces/Benson/text-generation/Examples/Descargar 3utools Para Mac Air.md	
+++ /dev/null
@@ -1,58 +0,0 @@
-
-<h1>Cómo descargar 3uTools para Mac Air</h1>
-<p>Si tiene un dispositivo iOS y un Mac Air, es posible que se pregunte cómo descargar 3uTools para Mac Air. 3uTools es un gestor de dispositivos iOS gratuito que te permite conectar tu iPhone o iPad a tu Mac Air y administrar diferentes configuraciones y características. También puedes acceder a miles de tonos de llamada, fondos de pantalla, juegos, aplicaciones y otro contenido que Apple normalmente no te permite instalar. Además, puede usar algunas funciones de jailbreak si necesita desbloquear su dispositivo o obtener más control sobre él. </p>
-<h2>descargar 3utools para mac air</h2><br /><p><b><b>Download File</b> >>> <a href="https://bltlly.com/2v6K8A">https://bltlly.com/2v6K8A</a></b></p><br /><br />
-<p>En este artículo, explicaremos qué es 3uTools, por qué es posible que desee descargarlo para su Mac Air, cómo descargarlo e instalarlo utilizando un software de terceros llamado WineBottler, y cómo usarlo en su Mac Air. ¡Vamos a empezar! </p>
- <h2>¿Qué es 3uTools? </h2>
-<p>3uTools es un gestor de dispositivos iOS gratuito que te permite conectar tu dispositivo iOS a tu PC o Mac y administrar diferentes configuraciones y características. Puede usar 3uTools para hacer copias de seguridad y restaurar sus datos, transferir archivos, actualizar o degradar su firmware, flashear ROMs personalizados, hacer jailbreak a su dispositivo, cambiar su ubicación, optimizar su batería y más. </p>
-<p>Una de las principales ventajas de 3uTools es que te da acceso a un montón de contenido que Apple suele restringir o no ofrece en la App Store. Puede descargar e instalar miles de tonos de llamada, fondos de pantalla, juegos, aplicaciones, temas y otros artículos de la tienda en línea de 3uTools. También puedes personalizar la apariencia y funcionalidad de tu dispositivo con varios ajustes y mods. </p>
-<p>Otro beneficio de 3uTools es que tiene algunas características de jailbreak que pueden ayudarle a desbloquear su dispositivo o ganar más control sobre él. Puede usar 3uTools para liberar el dispositivo con un solo clic, eliminar el bloqueo de activación de iCloud, omitir la pantalla de bloqueo de código de acceso, entrar o salir del modo de recuperación, solucionar problemas comunes de iOS y más. </p>
- <h2>¿Por qué descargar 3uTools para Mac Air? </h2>
-
-<ul>
-<li>Es gratis. A diferencia de otros administradores de dispositivos iOS que cobran una tarifa o tienen características limitadas en sus versiones gratuitas, 3uTools es completamente gratuito y no tiene costos ocultos o anuncios. </li>
-<li>Es fácil de usar. A diferencia de otros administradores de dispositivos iOS que tienen interfaces complicadas o requieren habilidades técnicas, 3uTools tiene una interfaz simple y fácil de usar que cualquiera puede usar sin ningún tipo de molestia. </li>
-<li>Es muy versátil. A diferencia de otros administradores de dispositivos iOS que solo ofrecen funciones básicas o se centran en aspectos específicos de la gestión de iOS, 3uTools ofrece una amplia gama de funciones y características que cubren casi todos los aspectos de la gestión de iOS. </li>
-<li pasos para descargar e instalar 3uTools en tu Mac Air usando WineBottler:</p>
-<ol>
-<li>Descargar WineBottler desde <a href="">este enlace</a> e instalarlo en su Mac Air. Puede elegir la versión estable o la versión de desarrollo, dependiendo de su preferencia. </li>
-<li>Descargue 3uTools desde <a href="">este enlace</a> y guárdelo en su Mac Air. Asegúrese de descargar la última versión de 3uTools para Windows.</li>
-<li>Inicie WineBottler y haga clic en la pestaña "Avanzado". Luego, haga clic en el botón "Seleccionar archivo..." y elija el archivo 3uTools.exe que descargó en el paso anterior. </li>
-<li>En la sección "Modo de instalación", elija "Copiar archivo (Programa) y todos los archivos de la carpeta al paquete de aplicaciones". Esto creará una aplicación independiente para 3uTools que puede ejecutar en su Mac Air.</li>
-<li>En la sección "Winetricks", marque la casilla para "dotnet40". Esto instalará el . NET Framework 4.0, que es necesario para que 3uTools funcione correctamente. </li>
-<li>En la sección "Info.plist", introduzca un nombre para su aplicación, como "3uTools for Mac". También puede cambiar el icono si lo desea. </li>
-<li>Haga clic en el botón "Instalar" y elija una ubicación para guardar su aplicación. WineBottler comenzará a crear el envoltorio para 3uTools e instalarlo en su Mac Air.</li>
-
-</ol>
- <h2>¿Cómo usar 3uTools en Mac Air? </h2>
-<p>Ahora que ha descargado e instalado 3uTools en su Mac Air usando WineBottler, puede comenzar a usarlo para administrar su dispositivo iOS. Aquí hay algunos consejos sobre cómo usar 3uTools en Mac Air:</p>
-<p></p>
-<ul>
-<li>Conecte su dispositivo iOS a su Mac Air utilizando un cable USB. Asegúrese de confiar en su ordenador en el dispositivo y habilitar el modo de depuración USB. </li>
-<li>Abra 3uTools en su Mac Air y espere a que detecte su dispositivo. Debería ver información básica sobre su dispositivo, como modelo, número de serie, nivel de batería, etc.</li>
-<li>En el lado izquierdo de la interfaz 3uTools, verá diferentes categorías de funciones y características que puede usar. Por ejemplo, puede hacer clic en "ToolBox" para acceder a varias herramientas, como copias de seguridad y restauración, migración de datos, conmutador de firmware, etc.</li>
-<li>También puede hacer clic en "Flash & JB" para acceder a algunas características de jailbreak, como jailbreak de un solo clic, desbloqueo de iCloud, bypass de código de acceso, etc. Sin embargo, tenga cuidado al usar estas características, ya que podrían anular la garantía o dañar su dispositivo. </li>
-<li>También puede hacer clic en "Easy Flash" para actualizar o bajar el firmware fácilmente. Puede elegir entre diferentes versiones de iOS que están disponibles para su dispositivo. Sin embargo, asegúrese de hacer una copia de seguridad de sus datos antes de flashear el dispositivo. </li>
-<li>También puede hacer clic en "Aplicaciones" para acceder a miles de tonos de llamada, fondos de pantalla, juegos, aplicaciones, temas y otro contenido que puede descargar e instalar en su dispositivo. Puedes navegar por categorías o buscar por palabras clave. También puedes previsualizar el contenido antes de descargarlo. </li>
-<li>Para descargar e instalar cualquier contenido de 3uTools, simplemente haga clic en el botón "Descargar" junto a él. Una vez completada la descarga, haga clic en el botón "Instalar" para transferirlo a su dispositivo. Es posible que necesite introducir su ID de Apple y contraseña si se le solicita. </li>
-</ul>
- <h2>Conclusión</h2>
-
-<p>Si quieres probar 3uTools por ti mismo, puedes descargarlo desde <a href="">este enlace</a> y seguir los pasos que hemos descrito anteriormente. Podrás conectar tu dispositivo iOS a tu Mac Air y administrar diferentes configuraciones y características. También podrás acceder a un montón de contenido que Apple normalmente no te permite instalar. Además, podrás usar algunas funciones de jailbreak si necesitas desbloquear tu dispositivo o obtener más control sobre él. </p>
-<p>Entonces, ¿qué estás esperando? Descargar 3uTools para Mac Air hoy y disfrutar de un nuevo nivel de gestión de iOS con 3uTools! </p>
- <h2>Preguntas frecuentes</h2>
-<p>Aquí hay algunas preguntas y respuestas frecuentes sobre 3uTools para Mac Air:</p>
-<ol>
-<li><b>¿Es seguro usar 3uTools? </b><br>
-Sí, 3uTools es seguro de usar siempre y cuando lo descargue desde el sitio web oficial o una fuente confiable. Sin embargo, debe tener cuidado al usar algunas de las funciones de jailbreak o descargar contenido de fuentes desconocidas, ya que podrían dañar su dispositivo o comprometer su seguridad. </li>
-<li><b>¿Es legal usar 3uTools? </b><br>
-Sí, 3uTools es legal de usar ya que no viola ninguna ley o reglamento. Sin embargo, debes saber que el uso de algunas de las funciones de jailbreak o la descarga de contenido que no está autorizado por Apple podría anular tu garantía o violar sus términos de servicio. </li>
-<li><b> ¿3uTools funciona en otros modelos de Mac? </b><br>
-Sí, 3uTools funciona en otros modelos de Mac siempre y cuando tengan Mac OS X 10.6 o posterior. Puede utilizar el mismo método que hemos descrito anteriormente para descargar e instalar 3uTools en su Mac usando WineBottler.</li>
-<li><b> ¿3uTools funciona en otros dispositivos iOS? </b><br>
-Sí, 3uTools funciona en otros dispositivos iOS, como iPhone, iPad, iPod Touch, Apple TV, etc. Puede conectar cualquier dispositivo iOS a su Mac Air y usar 3uTools para administrarlo. </li>
-<li><b>¿Cómo puedo actualizar 3uTools en mi Mac Air? </b><br>
-
-</ol></p> 64aa2da5cf<br />
-<br />
-<br />
\ No newline at end of file
diff --git a/spaces/Benson/text-generation/Examples/Descargar Arthdal Chronicles Temporada 2.md b/spaces/Benson/text-generation/Examples/Descargar Arthdal Chronicles Temporada 2.md
deleted file mode 100644
index d1ae165d5f51e2911af04f302f7156b4d109b7f9..0000000000000000000000000000000000000000
--- a/spaces/Benson/text-generation/Examples/Descargar Arthdal Chronicles Temporada 2.md	
+++ /dev/null
@@ -1,77 +0,0 @@
-<br />
-<h1>Cómo descargar Arthdal Chronicles Temporada 2</h1>
-<p>Si eres un fan de los dramas históricos de fantasía ambientados en la antigua Corea, probablemente hayas oído hablar de <strong>Arthdal Chronicles</strong>. Esta serie épica cuenta la historia de tres héroes que luchan por el poder, el amor y la supervivencia en una tierra mítica llamada Arth. Arthdal Chronicles se ha convertido en uno de los dramas coreanos más populares de todos los tiempos, con su rica construcción del mundo, su reparto estelar, sus impresionantes imágenes y su cautivadora banda sonora. </p>
-<h2>descargar arthdal chronicles temporada 2</h2><br /><p><b><b>Download Zip</b> &mdash;&mdash;&mdash;&mdash;&mdash; <a href="https://bltlly.com/2v6MBI">https://bltlly.com/2v6MBI</a></b></p><br /><br />
- <p>Pero si ya has visto la primera temporada de Arthdal Chronicles, te estarás preguntando: <em>¿Cuándo saldrá la temporada 2? ¿Y cómo puedo descargarlo? </em> Bueno, estás de suerte, porque en este artículo, responderemos estas preguntas y más. Le daremos una visión general de lo que puede esperar de la temporada 2, y le mostraremos los mejores servicios de streaming y plataformas para verlo en línea o fuera de línea. Así que, sin más preámbulos, ¡empecemos! </p>
- <h2>Introducción</h2>
-<p><strong>¿Qué es Arthdal Chronicles? </strong></p>
-<p>Arthdal Chronicles es una serie de drama de fantasía histórica que se estrenó el 1 de junio de 2019, en tvN y Netflix. Está dirigida por Kim Won-seok, quien también dirigió los aclamados dramas Signal y Misaeng, y escrita por Kim Young-hyun y Park Sang-yeon, quien también escribió los dramas de éxito Queen Seondeok y Six Flying Dragons. La serie tiene un presupuesto de más de 54 mil millones de won (unos 46 millones de dólares), por lo que es uno de los dramas coreanos más caros jamás producidos. </p>
-
- <p><strong>¿Por qué deberías verlo? </strong></p>
-<p>Si estás buscando un drama que tenga una historia épica, un mundo rico, un reparto estelar, imágenes impresionantes y una banda sonora cautivadora, entonces Arthdal Chronicles es para ti. Estas son algunas de las razones por las que deberías verlo:</p>
-<p></p>
-<ul>
-<li><strong>Historia épica:</strong> Arthdal Chronicles tiene una trama compleja e intrigante que abarca diferentes épocas y regiones. Explora temas como la política, la religión, la cultura, la identidad, la guerra, el amor y el destino. También tiene muchos giros y vueltas que te mantendrán en el borde de tu asiento. </li>
-<li><strong>Rich worldbuilding:</strong> Arthdal Chronicles tiene un escenario detallado e inmersivo que se inspira en varias fuentes históricas y míticas. Crea un mundo único y diverso donde existen diferentes tribus, razas, idiomas, costumbres, creencias y leyendas. También tiene mucho simbolismo y referencias que añaden profundidad y significado a la historia. </li>
-<li><strong>Reparto estelar:</strong> Arthdal Chronicles tiene un impresionante elenco de actores talentosos que ofrecen actuaciones excepcionales. Song Joong-ki interpreta dos papeles: Eunseom y su hermano gemelo Saya, que tienen personalidades y destinos contrastantes. Kim Ji-won interpreta a Tanya, que pasa de ser una niña ingenua a una poderosa chaman. Jang Dong-gun interpreta a Ta-gon, que es ambicioso, carismático y despiadado. El reparto incluye a Kim Ok-bin como Taealha, el amante y aliado de Ta-gon; Park Hae-joon como Moo-baek, el amigo leal de Ta-gon; Kim Eui-sung como San-woong, el padre de Ta-gon; Choi Moo-sung como Yeol-son, el padre de Tanya; y muchos más. </li>
-<li><strong>Impresionantes efectos visuales:</strong> Arthdal Chronicles tiene un alto valor de producción que muestra la belleza y diversidad de Arth. Tiene paisajes impresionantes, trajes, accesorios y efectos especiales que crean una atmósfera realista e inmersiva. También tiene muchas escenas de acción, como batallas, persecuciones y escapes, que son emocionantes y emocionantes. </li>
-
-</ul>
-<p>Como puedes ver, Arthdal Chronicles es un drama que tiene algo para todos. Si eres un fan de la historia, la fantasía, el romance, la acción o el misterio, encontrarás algo para disfrutar en esta serie. </p>
- <h2>Resumen de la temporada 2</h2>
-<p><strong>¿Qué esperar de la trama? </strong></p>
-<p>La temporada 1 de Arthdal Chronicles terminó con un cliffhanger que dejó a muchos fans ansiosos por más. El último episodio reveló que Eunseom y Saya son gemelos que fueron separados al nacer por el esquema de Tagon. Eunseom escapó de Arthdal con la ayuda de los neandertales y conoció a una nueva tribu llamada Ago. Saya creció en Arthdal como hijo de Tagon y se convirtió en el amante de Tanya. Tagon se convirtió en el rey de Arthdal después de matar a su padre y sus rivales. Tanya se convirtió en la alta sacerdotisa de Arthdal después de heredar el poder de Aramun. Y Taealha quedó embarazada del hijo de Tagon, que podría ser el niño profetizado del desastre. </p>
- <p>Entonces, ¿qué pasará en la temporada 2? Según fuentes oficiales y tráileres, la temporada 2 continuará la historia de los tres héroes y sus destinos. Eunseom tratará de unir a las tribus de Iark contra Arthdal. Saya tratará de descubrir los secretos de su pasado y su verdadera identidad. Tanya tratará de proteger a su pueblo y a su amor de la tiranía de Tagon. Y Tagon tratará de mantener su poder y su visión de Arthdal. La temporada 2 también presentará nuevos personajes y conflictos, como el misterioso Asa Ron (interpretado por Lee Do-hyun), que es el líder de la tribu Hwinsan y el primo de Tanya; el poderoso Nihon (interpretado por Kim Nam-gil), que es el rey de otra tierra y enemigo de Tagon; y la misteriosa voz (interpretada por Park Bo-gum), que es el narrador de la historia y podría tener una conexión con Aramun.</p>
- <p><strong>¿Qué esperar del reparto? </strong></p>
-
-<ul>
-<li><strong>Song Joong-ki como Eunseom/Saya:</strong> Song Joong-ki interpreta dos papeles: Eunseom, que es un medio-neandertal medio humano con un corazón puro y una voluntad fuerte; y Saya, que es el hermano gemelo de Eunseom con una mente astuta y un lado oscuro. </li>
-<li><strong>Kim Ji-won como Tanya:</strong> Kim Ji-won interpreta a Tanya, que es un chaman y el heredero de la tribu Wahan. Es amiga de la infancia de Eunseom y amante de Saya. También se convierte en la alta sacerdotisa de Arthdal después de heredar el poder de Aramun.</li>
-<li><strong>Jang Dong-gun como Ta-gon:</strong> Jang Dong-gun interpreta a Ta-gon, que es un guerrero carismático y el líder de la tribu Saenyeok. Es el amante de Taealha y el padre adoptivo de Saya. También se convierte en el rey de Arthdal después de matar a su padre y a sus rivales. </li>
-<li><strong>Kim Ok-bin como Taealha:</strong> Kim Ok-bin juega Taealha, que es una mujer hermosa y ambiciosa y la hija del líder de la tribu Hae. Ella es la amante y aliada de Ta-gon. También queda embarazada del hijo de Ta-gon, que podría ser el niño profetizado del desastre. </li>
-<li><strong>Park Hae-joon como Moo-baek:</strong> Park Hae-joon interpreta a Moo-baek, que es un guerrero leal y valiente y el líder de las fuerzas Daekan. Es amigo y partidario de Ta-gon. </li>
-<li><strong>Kim Eui-sung como San-woong:</strong> Kim Eui-sung interpreta a San-woong, quien es el antiguo líder de la tribu Saenyeok y el padre de Ta-gon. Es asesinado por Ta-gon en la temporada 1.</li>
-<li><strong>Choi Moo-sung como Yeol-son:</strong> Choi Moo-sung interpreta a Yeol-son, quien es el líder de la tribu Wahan y el padre de Tanya. Es capturado por Ta-gon en la temporada 1.</li>
-<li><strong>Lee Do-hyun como Asa Ron:</strong> Lee Do-hyun interpreta a Asa Ron, quien es el líder de la tribu Hwinsan y primo de Tanya. Es un personaje misterioso y poderoso que tiene una conexión con Aramun.</li>
-
-<li><strong>Park Bo-gum como la voz:</strong> Park Bo-gum toca la voz, quien es el narrador de la historia y podría tener una conexión con Aramun. Es un personaje misterioso y misterioso que guía a los espectadores a través de la historia. </li>
-</ul>
- <p><strong>¿Qué esperar de la fecha de lanzamiento? </strong></p>
-<p>La fecha de lanzamiento de la temporada 2 de Arthdal Chronicles aún no se ha confirmado oficialmente, pero hay algunas pistas y rumores que sugieren cuándo podría salir. Según algunas fuentes, se suponía que la temporada 2 comenzaría a filmarse a principios de 2020, pero se retrasó debido a la pandemia COVID-19. Sin embargo, algunos informes afirman que el rodaje se ha reanudado a finales de 2020 o principios de 2021, y que el reparto y el equipo han sido vistos en varios lugares. Según esta información, algunos fans especulan que la temporada 2 podría estrenarse a finales de 2021 o principios de 2022. Sin embargo, esto aún no está confirmado, por lo que tenemos que esperar un anuncio oficial de tvN o Netflix.</p>
- <p>En cuanto al número y duración de los episodios, la temporada 2 podría seguir el mismo formato que la temporada 1, que tenía 18 episodios divididos en tres partes: Parte 1 (episodios 1-6), Parte 2 (episodios 7-12), y Parte 3 (episodios 13-18). Cada episodio duró aproximadamente una hora, excepto el primero y el último, que duraron unos 90 minutos. Por lo tanto, podemos esperar que la temporada 2 tenga una estructura y duración similares. </p>
- <h2>Cómo descargar la temporada 2</h2>
-<p><strong>Los mejores servicios de streaming</strong></p>
-<p>Si quieres ver la temporada 2 de Arthdal Chronicles online, tienes varias opciones para elegir. Los mejores servicios de streaming que ofrecen Arthdal Chronicles temporada 2 son:</p>
-<ul>
-
-<li><strong>tvN:</strong> tvN es la emisora original de Arthdal Chronicles en Corea, lo que significa que tiene los primeros derechos para emitir la serie en Corea. tvN ofrece opciones de transmisión y reproducción en directo, así como clips y entrevistas entre bastidores. Puedes ver la temporada 2 de Arthdal Chronicles en tvN con una suscripción por cable o satélite que incluye el canal tvN. </li>
-<li><strong>Viki:</strong> Viki es un servicio de streaming especializado en dramas y películas asiáticas, incluyendo dramas coreanos. Viki ofrece subtítulos en varios idiomas, comentarios y valoraciones de los fans, y funciones interactivas. Puedes ver la temporada 2 de Arthdal Chronicles en Viki con un plan de suscripción que comienza desde $4.99 al mes. </li>
-</ul>
- <p><strong>Las mejores plataformas</strong></p>
-<p>Si quieres ver la temporada 2 de Arthdal Chronicles sin conexión, tienes varias opciones para elegir. Las mejores plataformas que te permiten descargar Arthdal Chronicles temporada 2 son:</p>
- | Plataforma | Dispositivo | Aplicación | Pros | Contras | | -- - - - | -- - - - - - - - - - - - | Netflix | Netflix | Smartphone, tableta, ordenador portátil, Smart TV, etc. | Aplicación de Netflix | - Vídeo y audio de alta calidad - Subtítulos y doblaje en varios idiomas - Opciones de visualización fuera de línea Gran biblioteca de contenido | - Requiere un plan de suscripción - Cuota de descarga limitada y fecha de vencimiento - No disponible en algunas regiones | | tvN | Smartphone, tableta, ordenador portátil, etc. | tvN aplicación o sitio web | - Live streaming and replay options - Detrás de cámaras clips y entrevistas - Emisora original de Arthdal Chronicles | - Requiere una suscripción por cable o satélite - Solo disponible en Corea - No hay opciones de visualización sin conexión | | Viki | Smartphone, tableta, ordenador portátil, smart TV, etc. | Viki aplicación o sitio web | - Subtítulos en varios idiomas - Comentarios y valoraciones de los fans Características interactivas - Opciones de visualización fuera de línea | - Requiere un plan de suscripción - Disponibilidad retrasada de episodios - Biblioteca limitada de contenido | <p><strong>Los mejores consejos</strong></p>
-
-<ul>
-<li><strong>Elija el servicio de streaming adecuado:</strong> Dependiendo de su ubicación, preferencias y presupuesto, es posible que desee elegir el servicio de streaming que más le convenga. Por ejemplo, si vive fuera de Corea y desea ver la temporada 2 de Arthdal Chronicles lo antes posible, es posible que desee elegir Netflix. Si vives en Corea y quieres ver la temporada 2 de Arthdal Chronicles en vivo o reproducida, quizás quieras elegir tvN. Y si quieres ver Arthdal Chronicles temporada 2 con subtítulos en tu idioma e interactuar con otros fans, es posible que desee elegir Viki.</li>
-<li><strong>Elija la plataforma correcta:</strong> Dependiendo de su dispositivo, aplicación y conexión a Internet, es posible que desee elegir la plataforma que funciona mejor para usted. Por ejemplo, si tienes un smartphone o tablet con suficiente espacio de almacenamiento y una buena conexión wifi, es posible que quieras descargar Arthdal Chronicles temporada 2 en tu dispositivo móvil. Si usted tiene un ordenador portátil o smart TV con una pantalla grande y una conexión rápida a Internet, es posible que desee transmitir Arthdal Chronicles temporada 2 en su computadora o TV.</li>
-<li><strong>Elija el momento adecuado:</strong> Dependiendo de su horario, disponibilidad y paciencia, es posible que desee elegir el momento que sea más conveniente para usted. Por ejemplo, si quieres ver la segunda temporada de Arthdal Chronicles tan pronto como salga al mercado, quizás quieras quedarte despierto hasta tarde o levantarte temprano para ver el estreno. Si quieres ver Arthdal Chronicles temporada 2 sin interrupciones o spoilers, es posible que desee esperar hasta que todos los episodios están disponibles y atracón de verlos. Y si quieres ver Arthdal Chronicles temporada 2 sin gastar demasiado dinero, es posible que desee esperar a una prueba gratuita o una oferta de descuento del servicio de streaming. </li>
-</ul>
- <h2>Conclusión</h2>
-
- Entonces, ¿qué estás esperando? Si eres un fan de los dramas históricos de fantasía ambientados en la antigua Corea, no deberías perderte la temporada 2 de Arthdal Chronicles. Es un drama que tiene algo para todos. Ya sea que esté buscando historia, fantasía, romance, acción o misterio, encontrará algo para disfrutar en esta serie. Así que no dudes en ver la segunda temporada de Arthdal Chronicles lo antes posible. Y no olvides compartir tus pensamientos y opiniones con otros fans. ¡No te arrepentirás! </p>
- <h2>Preguntas frecuentes</h2>
-<p>Aquí están algunas de las preguntas y respuestas más comunes sobre la temporada 2 de Arthdal Chronicles:</p>
-<ol>
-<li><strong>Q1: ¿Está Arthdal Chronicles basado en una historia real? </strong></li>
-<li>A1: No, Arthdal Chronicles no se basa en una historia real. Es una historia ficticia inspirada en varias fuentes históricas y míticas, como la Edad del Bronce, la era Gojoseon, la civilización sumeria, la mitología nórdica y el folclore coreano. Sin embargo, algunos de los nombres, lugares y eventos de la serie podrían tener algunas similitudes o referencias a los reales. </li>
-<li><strong>Q2: ¿Cuántas temporadas hay en Arthdal Chronicles? </strong></li>
-<li>A2: Hay dos temporadas en Arthdal Chronicles hasta ahora. La temporada 1 tiene 18 episodios que se emitieron del 1 de junio al 22 de septiembre de 2019. La temporada 2 aún no se ha confirmado oficialmente, pero se espera que tenga un número similar de episodios y aire a finales de 2021 o principios de 2022. </li>
-<li><strong>Q3: ¿Quiénes son los gemelos Eunseom y Saya? </strong></li>
-<li>A3: Eunseom y Saya son gemelos que nacieron de una madre humana y un padre neandertal. Fueron separados al nacer por el esquema de Ta-gon. Eunseom creció con la tribu Wahan y tiene un corazón puro y una voluntad fuerte. Saya creció con Ta-gon y tiene una mente astuta y un lado oscuro. Ambos tienen habilidades especiales, como comunicarse con los animales y ver el futuro. </li>
-<li><strong>Q4: ¿Cuál es el significado de la espada de Aramun? </strong></li>
-
-<li><strong>Q5: ¿Habrá una temporada 3 de Arthdal Chronicles? </strong></li>
-<li>A5: Todavía no hay confirmación oficial, pero existe la posibilidad de que haya una temporada 3 de Arthdal Chronicles. La serie tiene mucho potencial y popularidad, y la historia aún no se ha resuelto por completo. Los creadores también han insinuado que tienen planes para más temporadas en el futuro. Sin embargo, esto dependerá de varios factores, como las calificaciones, el presupuesto, la disponibilidad del reparto y la demanda de los fans. </li>
-</ol></p> 64aa2da5cf<br />
-<br />
-<br />
\ No newline at end of file
diff --git a/spaces/Big-Web/MMSD/env/Lib/site-packages/botocore/vendored/requests/packages/urllib3/__init__.py b/spaces/Big-Web/MMSD/env/Lib/site-packages/botocore/vendored/requests/packages/urllib3/__init__.py
deleted file mode 100644
index 88697016b41f8da46f726a38ac8ac914ebc65bbc..0000000000000000000000000000000000000000
--- a/spaces/Big-Web/MMSD/env/Lib/site-packages/botocore/vendored/requests/packages/urllib3/__init__.py
+++ /dev/null
@@ -1,10 +0,0 @@
-"""
-urllib3 - Thread-safe connection pooling and re-using.
-"""
-
-__author__ = 'Andrey Petrov (andrey.petrov@shazow.net)'
-__license__ = 'MIT'
-__version__ = ''
-
-
-from . import exceptions
diff --git a/spaces/Big-Web/MMSD/env/Lib/site-packages/pip/_vendor/chardet/johabfreq.py b/spaces/Big-Web/MMSD/env/Lib/site-packages/pip/_vendor/chardet/johabfreq.py
deleted file mode 100644
index c12969990d73388f61a6ab98fb4ee8f0f5cbc44f..0000000000000000000000000000000000000000
--- a/spaces/Big-Web/MMSD/env/Lib/site-packages/pip/_vendor/chardet/johabfreq.py
+++ /dev/null
@@ -1,2382 +0,0 @@
-######################## BEGIN LICENSE BLOCK ########################
-# The Original Code is Mozilla Communicator client code.
-#
-# The Initial Developer of the Original Code is
-# Netscape Communications Corporation.
-# Portions created by the Initial Developer are Copyright (C) 1998
-# the Initial Developer. All Rights Reserved.
-#
-# Contributor(s):
-#   Mark Pilgrim - port to Python
-#
-# This library is free software; you can redistribute it and/or
-# modify it under the terms of the GNU Lesser General Public
-# License as published by the Free Software Foundation; either
-# version 2.1 of the License, or (at your option) any later version.
-#
-# This library is distributed in the hope that it will be useful,
-# but WITHOUT ANY WARRANTY; without even the implied warranty of
-# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
-# Lesser General Public License for more details.
-#
-# You should have received a copy of the GNU Lesser General Public
-# License along with this library; if not, write to the Free Software
-# Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA
-# 02110-1301  USA
-######################### END LICENSE BLOCK #########################
-
-# The frequency data itself is the same as euc-kr.
-# This is just a mapping table to euc-kr.
-
-JOHAB_TO_EUCKR_ORDER_TABLE = {
-    0x8861: 0,
-    0x8862: 1,
-    0x8865: 2,
-    0x8868: 3,
-    0x8869: 4,
-    0x886A: 5,
-    0x886B: 6,
-    0x8871: 7,
-    0x8873: 8,
-    0x8874: 9,
-    0x8875: 10,
-    0x8876: 11,
-    0x8877: 12,
-    0x8878: 13,
-    0x8879: 14,
-    0x887B: 15,
-    0x887C: 16,
-    0x887D: 17,
-    0x8881: 18,
-    0x8882: 19,
-    0x8885: 20,
-    0x8889: 21,
-    0x8891: 22,
-    0x8893: 23,
-    0x8895: 24,
-    0x8896: 25,
-    0x8897: 26,
-    0x88A1: 27,
-    0x88A2: 28,
-    0x88A5: 29,
-    0x88A9: 30,
-    0x88B5: 31,
-    0x88B7: 32,
-    0x88C1: 33,
-    0x88C5: 34,
-    0x88C9: 35,
-    0x88E1: 36,
-    0x88E2: 37,
-    0x88E5: 38,
-    0x88E8: 39,
-    0x88E9: 40,
-    0x88EB: 41,
-    0x88F1: 42,
-    0x88F3: 43,
-    0x88F5: 44,
-    0x88F6: 45,
-    0x88F7: 46,
-    0x88F8: 47,
-    0x88FB: 48,
-    0x88FC: 49,
-    0x88FD: 50,
-    0x8941: 51,
-    0x8945: 52,
-    0x8949: 53,
-    0x8951: 54,
-    0x8953: 55,
-    0x8955: 56,
-    0x8956: 57,
-    0x8957: 58,
-    0x8961: 59,
-    0x8962: 60,
-    0x8963: 61,
-    0x8965: 62,
-    0x8968: 63,
-    0x8969: 64,
-    0x8971: 65,
-    0x8973: 66,
-    0x8975: 67,
-    0x8976: 68,
-    0x8977: 69,
-    0x897B: 70,
-    0x8981: 71,
-    0x8985: 72,
-    0x8989: 73,
-    0x8993: 74,
-    0x8995: 75,
-    0x89A1: 76,
-    0x89A2: 77,
-    0x89A5: 78,
-    0x89A8: 79,
-    0x89A9: 80,
-    0x89AB: 81,
-    0x89AD: 82,
-    0x89B0: 83,
-    0x89B1: 84,
-    0x89B3: 85,
-    0x89B5: 86,
-    0x89B7: 87,
-    0x89B8: 88,
-    0x89C1: 89,
-    0x89C2: 90,
-    0x89C5: 91,
-    0x89C9: 92,
-    0x89CB: 93,
-    0x89D1: 94,
-    0x89D3: 95,
-    0x89D5: 96,
-    0x89D7: 97,
-    0x89E1: 98,
-    0x89E5: 99,
-    0x89E9: 100,
-    0x89F3: 101,
-    0x89F6: 102,
-    0x89F7: 103,
-    0x8A41: 104,
-    0x8A42: 105,
-    0x8A45: 106,
-    0x8A49: 107,
-    0x8A51: 108,
-    0x8A53: 109,
-    0x8A55: 110,
-    0x8A57: 111,
-    0x8A61: 112,
-    0x8A65: 113,
-    0x8A69: 114,
-    0x8A73: 115,
-    0x8A75: 116,
-    0x8A81: 117,
-    0x8A82: 118,
-    0x8A85: 119,
-    0x8A88: 120,
-    0x8A89: 121,
-    0x8A8A: 122,
-    0x8A8B: 123,
-    0x8A90: 124,
-    0x8A91: 125,
-    0x8A93: 126,
-    0x8A95: 127,
-    0x8A97: 128,
-    0x8A98: 129,
-    0x8AA1: 130,
-    0x8AA2: 131,
-    0x8AA5: 132,
-    0x8AA9: 133,
-    0x8AB6: 134,
-    0x8AB7: 135,
-    0x8AC1: 136,
-    0x8AD5: 137,
-    0x8AE1: 138,
-    0x8AE2: 139,
-    0x8AE5: 140,
-    0x8AE9: 141,
-    0x8AF1: 142,
-    0x8AF3: 143,
-    0x8AF5: 144,
-    0x8B41: 145,
-    0x8B45: 146,
-    0x8B49: 147,
-    0x8B61: 148,
-    0x8B62: 149,
-    0x8B65: 150,
-    0x8B68: 151,
-    0x8B69: 152,
-    0x8B6A: 153,
-    0x8B71: 154,
-    0x8B73: 155,
-    0x8B75: 156,
-    0x8B77: 157,
-    0x8B81: 158,
-    0x8BA1: 159,
-    0x8BA2: 160,
-    0x8BA5: 161,
-    0x8BA8: 162,
-    0x8BA9: 163,
-    0x8BAB: 164,
-    0x8BB1: 165,
-    0x8BB3: 166,
-    0x8BB5: 167,
-    0x8BB7: 168,
-    0x8BB8: 169,
-    0x8BBC: 170,
-    0x8C61: 171,
-    0x8C62: 172,
-    0x8C63: 173,
-    0x8C65: 174,
-    0x8C69: 175,
-    0x8C6B: 176,
-    0x8C71: 177,
-    0x8C73: 178,
-    0x8C75: 179,
-    0x8C76: 180,
-    0x8C77: 181,
-    0x8C7B: 182,
-    0x8C81: 183,
-    0x8C82: 184,
-    0x8C85: 185,
-    0x8C89: 186,
-    0x8C91: 187,
-    0x8C93: 188,
-    0x8C95: 189,
-    0x8C96: 190,
-    0x8C97: 191,
-    0x8CA1: 192,
-    0x8CA2: 193,
-    0x8CA9: 194,
-    0x8CE1: 195,
-    0x8CE2: 196,
-    0x8CE3: 197,
-    0x8CE5: 198,
-    0x8CE9: 199,
-    0x8CF1: 200,
-    0x8CF3: 201,
-    0x8CF5: 202,
-    0x8CF6: 203,
-    0x8CF7: 204,
-    0x8D41: 205,
-    0x8D42: 206,
-    0x8D45: 207,
-    0x8D51: 208,
-    0x8D55: 209,
-    0x8D57: 210,
-    0x8D61: 211,
-    0x8D65: 212,
-    0x8D69: 213,
-    0x8D75: 214,
-    0x8D76: 215,
-    0x8D7B: 216,
-    0x8D81: 217,
-    0x8DA1: 218,
-    0x8DA2: 219,
-    0x8DA5: 220,
-    0x8DA7: 221,
-    0x8DA9: 222,
-    0x8DB1: 223,
-    0x8DB3: 224,
-    0x8DB5: 225,
-    0x8DB7: 226,
-    0x8DB8: 227,
-    0x8DB9: 228,
-    0x8DC1: 229,
-    0x8DC2: 230,
-    0x8DC9: 231,
-    0x8DD6: 232,
-    0x8DD7: 233,
-    0x8DE1: 234,
-    0x8DE2: 235,
-    0x8DF7: 236,
-    0x8E41: 237,
-    0x8E45: 238,
-    0x8E49: 239,
-    0x8E51: 240,
-    0x8E53: 241,
-    0x8E57: 242,
-    0x8E61: 243,
-    0x8E81: 244,
-    0x8E82: 245,
-    0x8E85: 246,
-    0x8E89: 247,
-    0x8E90: 248,
-    0x8E91: 249,
-    0x8E93: 250,
-    0x8E95: 251,
-    0x8E97: 252,
-    0x8E98: 253,
-    0x8EA1: 254,
-    0x8EA9: 255,
-    0x8EB6: 256,
-    0x8EB7: 257,
-    0x8EC1: 258,
-    0x8EC2: 259,
-    0x8EC5: 260,
-    0x8EC9: 261,
-    0x8ED1: 262,
-    0x8ED3: 263,
-    0x8ED6: 264,
-    0x8EE1: 265,
-    0x8EE5: 266,
-    0x8EE9: 267,
-    0x8EF1: 268,
-    0x8EF3: 269,
-    0x8F41: 270,
-    0x8F61: 271,
-    0x8F62: 272,
-    0x8F65: 273,
-    0x8F67: 274,
-    0x8F69: 275,
-    0x8F6B: 276,
-    0x8F70: 277,
-    0x8F71: 278,
-    0x8F73: 279,
-    0x8F75: 280,
-    0x8F77: 281,
-    0x8F7B: 282,
-    0x8FA1: 283,
-    0x8FA2: 284,
-    0x8FA5: 285,
-    0x8FA9: 286,
-    0x8FB1: 287,
-    0x8FB3: 288,
-    0x8FB5: 289,
-    0x8FB7: 290,
-    0x9061: 291,
-    0x9062: 292,
-    0x9063: 293,
-    0x9065: 294,
-    0x9068: 295,
-    0x9069: 296,
-    0x906A: 297,
-    0x906B: 298,
-    0x9071: 299,
-    0x9073: 300,
-    0x9075: 301,
-    0x9076: 302,
-    0x9077: 303,
-    0x9078: 304,
-    0x9079: 305,
-    0x907B: 306,
-    0x907D: 307,
-    0x9081: 308,
-    0x9082: 309,
-    0x9085: 310,
-    0x9089: 311,
-    0x9091: 312,
-    0x9093: 313,
-    0x9095: 314,
-    0x9096: 315,
-    0x9097: 316,
-    0x90A1: 317,
-    0x90A2: 318,
-    0x90A5: 319,
-    0x90A9: 320,
-    0x90B1: 321,
-    0x90B7: 322,
-    0x90E1: 323,
-    0x90E2: 324,
-    0x90E4: 325,
-    0x90E5: 326,
-    0x90E9: 327,
-    0x90EB: 328,
-    0x90EC: 329,
-    0x90F1: 330,
-    0x90F3: 331,
-    0x90F5: 332,
-    0x90F6: 333,
-    0x90F7: 334,
-    0x90FD: 335,
-    0x9141: 336,
-    0x9142: 337,
-    0x9145: 338,
-    0x9149: 339,
-    0x9151: 340,
-    0x9153: 341,
-    0x9155: 342,
-    0x9156: 343,
-    0x9157: 344,
-    0x9161: 345,
-    0x9162: 346,
-    0x9165: 347,
-    0x9169: 348,
-    0x9171: 349,
-    0x9173: 350,
-    0x9176: 351,
-    0x9177: 352,
-    0x917A: 353,
-    0x9181: 354,
-    0x9185: 355,
-    0x91A1: 356,
-    0x91A2: 357,
-    0x91A5: 358,
-    0x91A9: 359,
-    0x91AB: 360,
-    0x91B1: 361,
-    0x91B3: 362,
-    0x91B5: 363,
-    0x91B7: 364,
-    0x91BC: 365,
-    0x91BD: 366,
-    0x91C1: 367,
-    0x91C5: 368,
-    0x91C9: 369,
-    0x91D6: 370,
-    0x9241: 371,
-    0x9245: 372,
-    0x9249: 373,
-    0x9251: 374,
-    0x9253: 375,
-    0x9255: 376,
-    0x9261: 377,
-    0x9262: 378,
-    0x9265: 379,
-    0x9269: 380,
-    0x9273: 381,
-    0x9275: 382,
-    0x9277: 383,
-    0x9281: 384,
-    0x9282: 385,
-    0x9285: 386,
-    0x9288: 387,
-    0x9289: 388,
-    0x9291: 389,
-    0x9293: 390,
-    0x9295: 391,
-    0x9297: 392,
-    0x92A1: 393,
-    0x92B6: 394,
-    0x92C1: 395,
-    0x92E1: 396,
-    0x92E5: 397,
-    0x92E9: 398,
-    0x92F1: 399,
-    0x92F3: 400,
-    0x9341: 401,
-    0x9342: 402,
-    0x9349: 403,
-    0x9351: 404,
-    0x9353: 405,
-    0x9357: 406,
-    0x9361: 407,
-    0x9362: 408,
-    0x9365: 409,
-    0x9369: 410,
-    0x936A: 411,
-    0x936B: 412,
-    0x9371: 413,
-    0x9373: 414,
-    0x9375: 415,
-    0x9377: 416,
-    0x9378: 417,
-    0x937C: 418,
-    0x9381: 419,
-    0x9385: 420,
-    0x9389: 421,
-    0x93A1: 422,
-    0x93A2: 423,
-    0x93A5: 424,
-    0x93A9: 425,
-    0x93AB: 426,
-    0x93B1: 427,
-    0x93B3: 428,
-    0x93B5: 429,
-    0x93B7: 430,
-    0x93BC: 431,
-    0x9461: 432,
-    0x9462: 433,
-    0x9463: 434,
-    0x9465: 435,
-    0x9468: 436,
-    0x9469: 437,
-    0x946A: 438,
-    0x946B: 439,
-    0x946C: 440,
-    0x9470: 441,
-    0x9471: 442,
-    0x9473: 443,
-    0x9475: 444,
-    0x9476: 445,
-    0x9477: 446,
-    0x9478: 447,
-    0x9479: 448,
-    0x947D: 449,
-    0x9481: 450,
-    0x9482: 451,
-    0x9485: 452,
-    0x9489: 453,
-    0x9491: 454,
-    0x9493: 455,
-    0x9495: 456,
-    0x9496: 457,
-    0x9497: 458,
-    0x94A1: 459,
-    0x94E1: 460,
-    0x94E2: 461,
-    0x94E3: 462,
-    0x94E5: 463,
-    0x94E8: 464,
-    0x94E9: 465,
-    0x94EB: 466,
-    0x94EC: 467,
-    0x94F1: 468,
-    0x94F3: 469,
-    0x94F5: 470,
-    0x94F7: 471,
-    0x94F9: 472,
-    0x94FC: 473,
-    0x9541: 474,
-    0x9542: 475,
-    0x9545: 476,
-    0x9549: 477,
-    0x9551: 478,
-    0x9553: 479,
-    0x9555: 480,
-    0x9556: 481,
-    0x9557: 482,
-    0x9561: 483,
-    0x9565: 484,
-    0x9569: 485,
-    0x9576: 486,
-    0x9577: 487,
-    0x9581: 488,
-    0x9585: 489,
-    0x95A1: 490,
-    0x95A2: 491,
-    0x95A5: 492,
-    0x95A8: 493,
-    0x95A9: 494,
-    0x95AB: 495,
-    0x95AD: 496,
-    0x95B1: 497,
-    0x95B3: 498,
-    0x95B5: 499,
-    0x95B7: 500,
-    0x95B9: 501,
-    0x95BB: 502,
-    0x95C1: 503,
-    0x95C5: 504,
-    0x95C9: 505,
-    0x95E1: 506,
-    0x95F6: 507,
-    0x9641: 508,
-    0x9645: 509,
-    0x9649: 510,
-    0x9651: 511,
-    0x9653: 512,
-    0x9655: 513,
-    0x9661: 514,
-    0x9681: 515,
-    0x9682: 516,
-    0x9685: 517,
-    0x9689: 518,
-    0x9691: 519,
-    0x9693: 520,
-    0x9695: 521,
-    0x9697: 522,
-    0x96A1: 523,
-    0x96B6: 524,
-    0x96C1: 525,
-    0x96D7: 526,
-    0x96E1: 527,
-    0x96E5: 528,
-    0x96E9: 529,
-    0x96F3: 530,
-    0x96F5: 531,
-    0x96F7: 532,
-    0x9741: 533,
-    0x9745: 534,
-    0x9749: 535,
-    0x9751: 536,
-    0x9757: 537,
-    0x9761: 538,
-    0x9762: 539,
-    0x9765: 540,
-    0x9768: 541,
-    0x9769: 542,
-    0x976B: 543,
-    0x9771: 544,
-    0x9773: 545,
-    0x9775: 546,
-    0x9777: 547,
-    0x9781: 548,
-    0x97A1: 549,
-    0x97A2: 550,
-    0x97A5: 551,
-    0x97A8: 552,
-    0x97A9: 553,
-    0x97B1: 554,
-    0x97B3: 555,
-    0x97B5: 556,
-    0x97B6: 557,
-    0x97B7: 558,
-    0x97B8: 559,
-    0x9861: 560,
-    0x9862: 561,
-    0x9865: 562,
-    0x9869: 563,
-    0x9871: 564,
-    0x9873: 565,
-    0x9875: 566,
-    0x9876: 567,
-    0x9877: 568,
-    0x987D: 569,
-    0x9881: 570,
-    0x9882: 571,
-    0x9885: 572,
-    0x9889: 573,
-    0x9891: 574,
-    0x9893: 575,
-    0x9895: 576,
-    0x9896: 577,
-    0x9897: 578,
-    0x98E1: 579,
-    0x98E2: 580,
-    0x98E5: 581,
-    0x98E9: 582,
-    0x98EB: 583,
-    0x98EC: 584,
-    0x98F1: 585,
-    0x98F3: 586,
-    0x98F5: 587,
-    0x98F6: 588,
-    0x98F7: 589,
-    0x98FD: 590,
-    0x9941: 591,
-    0x9942: 592,
-    0x9945: 593,
-    0x9949: 594,
-    0x9951: 595,
-    0x9953: 596,
-    0x9955: 597,
-    0x9956: 598,
-    0x9957: 599,
-    0x9961: 600,
-    0x9976: 601,
-    0x99A1: 602,
-    0x99A2: 603,
-    0x99A5: 604,
-    0x99A9: 605,
-    0x99B7: 606,
-    0x99C1: 607,
-    0x99C9: 608,
-    0x99E1: 609,
-    0x9A41: 610,
-    0x9A45: 611,
-    0x9A81: 612,
-    0x9A82: 613,
-    0x9A85: 614,
-    0x9A89: 615,
-    0x9A90: 616,
-    0x9A91: 617,
-    0x9A97: 618,
-    0x9AC1: 619,
-    0x9AE1: 620,
-    0x9AE5: 621,
-    0x9AE9: 622,
-    0x9AF1: 623,
-    0x9AF3: 624,
-    0x9AF7: 625,
-    0x9B61: 626,
-    0x9B62: 627,
-    0x9B65: 628,
-    0x9B68: 629,
-    0x9B69: 630,
-    0x9B71: 631,
-    0x9B73: 632,
-    0x9B75: 633,
-    0x9B81: 634,
-    0x9B85: 635,
-    0x9B89: 636,
-    0x9B91: 637,
-    0x9B93: 638,
-    0x9BA1: 639,
-    0x9BA5: 640,
-    0x9BA9: 641,
-    0x9BB1: 642,
-    0x9BB3: 643,
-    0x9BB5: 644,
-    0x9BB7: 645,
-    0x9C61: 646,
-    0x9C62: 647,
-    0x9C65: 648,
-    0x9C69: 649,
-    0x9C71: 650,
-    0x9C73: 651,
-    0x9C75: 652,
-    0x9C76: 653,
-    0x9C77: 654,
-    0x9C78: 655,
-    0x9C7C: 656,
-    0x9C7D: 657,
-    0x9C81: 658,
-    0x9C82: 659,
-    0x9C85: 660,
-    0x9C89: 661,
-    0x9C91: 662,
-    0x9C93: 663,
-    0x9C95: 664,
-    0x9C96: 665,
-    0x9C97: 666,
-    0x9CA1: 667,
-    0x9CA2: 668,
-    0x9CA5: 669,
-    0x9CB5: 670,
-    0x9CB7: 671,
-    0x9CE1: 672,
-    0x9CE2: 673,
-    0x9CE5: 674,
-    0x9CE9: 675,
-    0x9CF1: 676,
-    0x9CF3: 677,
-    0x9CF5: 678,
-    0x9CF6: 679,
-    0x9CF7: 680,
-    0x9CFD: 681,
-    0x9D41: 682,
-    0x9D42: 683,
-    0x9D45: 684,
-    0x9D49: 685,
-    0x9D51: 686,
-    0x9D53: 687,
-    0x9D55: 688,
-    0x9D57: 689,
-    0x9D61: 690,
-    0x9D62: 691,
-    0x9D65: 692,
-    0x9D69: 693,
-    0x9D71: 694,
-    0x9D73: 695,
-    0x9D75: 696,
-    0x9D76: 697,
-    0x9D77: 698,
-    0x9D81: 699,
-    0x9D85: 700,
-    0x9D93: 701,
-    0x9D95: 702,
-    0x9DA1: 703,
-    0x9DA2: 704,
-    0x9DA5: 705,
-    0x9DA9: 706,
-    0x9DB1: 707,
-    0x9DB3: 708,
-    0x9DB5: 709,
-    0x9DB7: 710,
-    0x9DC1: 711,
-    0x9DC5: 712,
-    0x9DD7: 713,
-    0x9DF6: 714,
-    0x9E41: 715,
-    0x9E45: 716,
-    0x9E49: 717,
-    0x9E51: 718,
-    0x9E53: 719,
-    0x9E55: 720,
-    0x9E57: 721,
-    0x9E61: 722,
-    0x9E65: 723,
-    0x9E69: 724,
-    0x9E73: 725,
-    0x9E75: 726,
-    0x9E77: 727,
-    0x9E81: 728,
-    0x9E82: 729,
-    0x9E85: 730,
-    0x9E89: 731,
-    0x9E91: 732,
-    0x9E93: 733,
-    0x9E95: 734,
-    0x9E97: 735,
-    0x9EA1: 736,
-    0x9EB6: 737,
-    0x9EC1: 738,
-    0x9EE1: 739,
-    0x9EE2: 740,
-    0x9EE5: 741,
-    0x9EE9: 742,
-    0x9EF1: 743,
-    0x9EF5: 744,
-    0x9EF7: 745,
-    0x9F41: 746,
-    0x9F42: 747,
-    0x9F45: 748,
-    0x9F49: 749,
-    0x9F51: 750,
-    0x9F53: 751,
-    0x9F55: 752,
-    0x9F57: 753,
-    0x9F61: 754,
-    0x9F62: 755,
-    0x9F65: 756,
-    0x9F69: 757,
-    0x9F71: 758,
-    0x9F73: 759,
-    0x9F75: 760,
-    0x9F77: 761,
-    0x9F78: 762,
-    0x9F7B: 763,
-    0x9F7C: 764,
-    0x9FA1: 765,
-    0x9FA2: 766,
-    0x9FA5: 767,
-    0x9FA9: 768,
-    0x9FB1: 769,
-    0x9FB3: 770,
-    0x9FB5: 771,
-    0x9FB7: 772,
-    0xA061: 773,
-    0xA062: 774,
-    0xA065: 775,
-    0xA067: 776,
-    0xA068: 777,
-    0xA069: 778,
-    0xA06A: 779,
-    0xA06B: 780,
-    0xA071: 781,
-    0xA073: 782,
-    0xA075: 783,
-    0xA077: 784,
-    0xA078: 785,
-    0xA07B: 786,
-    0xA07D: 787,
-    0xA081: 788,
-    0xA082: 789,
-    0xA085: 790,
-    0xA089: 791,
-    0xA091: 792,
-    0xA093: 793,
-    0xA095: 794,
-    0xA096: 795,
-    0xA097: 796,
-    0xA098: 797,
-    0xA0A1: 798,
-    0xA0A2: 799,
-    0xA0A9: 800,
-    0xA0B7: 801,
-    0xA0E1: 802,
-    0xA0E2: 803,
-    0xA0E5: 804,
-    0xA0E9: 805,
-    0xA0EB: 806,
-    0xA0F1: 807,
-    0xA0F3: 808,
-    0xA0F5: 809,
-    0xA0F7: 810,
-    0xA0F8: 811,
-    0xA0FD: 812,
-    0xA141: 813,
-    0xA142: 814,
-    0xA145: 815,
-    0xA149: 816,
-    0xA151: 817,
-    0xA153: 818,
-    0xA155: 819,
-    0xA156: 820,
-    0xA157: 821,
-    0xA161: 822,
-    0xA162: 823,
-    0xA165: 824,
-    0xA169: 825,
-    0xA175: 826,
-    0xA176: 827,
-    0xA177: 828,
-    0xA179: 829,
-    0xA181: 830,
-    0xA1A1: 831,
-    0xA1A2: 832,
-    0xA1A4: 833,
-    0xA1A5: 834,
-    0xA1A9: 835,
-    0xA1AB: 836,
-    0xA1B1: 837,
-    0xA1B3: 838,
-    0xA1B5: 839,
-    0xA1B7: 840,
-    0xA1C1: 841,
-    0xA1C5: 842,
-    0xA1D6: 843,
-    0xA1D7: 844,
-    0xA241: 845,
-    0xA245: 846,
-    0xA249: 847,
-    0xA253: 848,
-    0xA255: 849,
-    0xA257: 850,
-    0xA261: 851,
-    0xA265: 852,
-    0xA269: 853,
-    0xA273: 854,
-    0xA275: 855,
-    0xA281: 856,
-    0xA282: 857,
-    0xA283: 858,
-    0xA285: 859,
-    0xA288: 860,
-    0xA289: 861,
-    0xA28A: 862,
-    0xA28B: 863,
-    0xA291: 864,
-    0xA293: 865,
-    0xA295: 866,
-    0xA297: 867,
-    0xA29B: 868,
-    0xA29D: 869,
-    0xA2A1: 870,
-    0xA2A5: 871,
-    0xA2A9: 872,
-    0xA2B3: 873,
-    0xA2B5: 874,
-    0xA2C1: 875,
-    0xA2E1: 876,
-    0xA2E5: 877,
-    0xA2E9: 878,
-    0xA341: 879,
-    0xA345: 880,
-    0xA349: 881,
-    0xA351: 882,
-    0xA355: 883,
-    0xA361: 884,
-    0xA365: 885,
-    0xA369: 886,
-    0xA371: 887,
-    0xA375: 888,
-    0xA3A1: 889,
-    0xA3A2: 890,
-    0xA3A5: 891,
-    0xA3A8: 892,
-    0xA3A9: 893,
-    0xA3AB: 894,
-    0xA3B1: 895,
-    0xA3B3: 896,
-    0xA3B5: 897,
-    0xA3B6: 898,
-    0xA3B7: 899,
-    0xA3B9: 900,
-    0xA3BB: 901,
-    0xA461: 902,
-    0xA462: 903,
-    0xA463: 904,
-    0xA464: 905,
-    0xA465: 906,
-    0xA468: 907,
-    0xA469: 908,
-    0xA46A: 909,
-    0xA46B: 910,
-    0xA46C: 911,
-    0xA471: 912,
-    0xA473: 913,
-    0xA475: 914,
-    0xA477: 915,
-    0xA47B: 916,
-    0xA481: 917,
-    0xA482: 918,
-    0xA485: 919,
-    0xA489: 920,
-    0xA491: 921,
-    0xA493: 922,
-    0xA495: 923,
-    0xA496: 924,
-    0xA497: 925,
-    0xA49B: 926,
-    0xA4A1: 927,
-    0xA4A2: 928,
-    0xA4A5: 929,
-    0xA4B3: 930,
-    0xA4E1: 931,
-    0xA4E2: 932,
-    0xA4E5: 933,
-    0xA4E8: 934,
-    0xA4E9: 935,
-    0xA4EB: 936,
-    0xA4F1: 937,
-    0xA4F3: 938,
-    0xA4F5: 939,
-    0xA4F7: 940,
-    0xA4F8: 941,
-    0xA541: 942,
-    0xA542: 943,
-    0xA545: 944,
-    0xA548: 945,
-    0xA549: 946,
-    0xA551: 947,
-    0xA553: 948,
-    0xA555: 949,
-    0xA556: 950,
-    0xA557: 951,
-    0xA561: 952,
-    0xA562: 953,
-    0xA565: 954,
-    0xA569: 955,
-    0xA573: 956,
-    0xA575: 957,
-    0xA576: 958,
-    0xA577: 959,
-    0xA57B: 960,
-    0xA581: 961,
-    0xA585: 962,
-    0xA5A1: 963,
-    0xA5A2: 964,
-    0xA5A3: 965,
-    0xA5A5: 966,
-    0xA5A9: 967,
-    0xA5B1: 968,
-    0xA5B3: 969,
-    0xA5B5: 970,
-    0xA5B7: 971,
-    0xA5C1: 972,
-    0xA5C5: 973,
-    0xA5D6: 974,
-    0xA5E1: 975,
-    0xA5F6: 976,
-    0xA641: 977,
-    0xA642: 978,
-    0xA645: 979,
-    0xA649: 980,
-    0xA651: 981,
-    0xA653: 982,
-    0xA661: 983,
-    0xA665: 984,
-    0xA681: 985,
-    0xA682: 986,
-    0xA685: 987,
-    0xA688: 988,
-    0xA689: 989,
-    0xA68A: 990,
-    0xA68B: 991,
-    0xA691: 992,
-    0xA693: 993,
-    0xA695: 994,
-    0xA697: 995,
-    0xA69B: 996,
-    0xA69C: 997,
-    0xA6A1: 998,
-    0xA6A9: 999,
-    0xA6B6: 1000,
-    0xA6C1: 1001,
-    0xA6E1: 1002,
-    0xA6E2: 1003,
-    0xA6E5: 1004,
-    0xA6E9: 1005,
-    0xA6F7: 1006,
-    0xA741: 1007,
-    0xA745: 1008,
-    0xA749: 1009,
-    0xA751: 1010,
-    0xA755: 1011,
-    0xA757: 1012,
-    0xA761: 1013,
-    0xA762: 1014,
-    0xA765: 1015,
-    0xA769: 1016,
-    0xA771: 1017,
-    0xA773: 1018,
-    0xA775: 1019,
-    0xA7A1: 1020,
-    0xA7A2: 1021,
-    0xA7A5: 1022,
-    0xA7A9: 1023,
-    0xA7AB: 1024,
-    0xA7B1: 1025,
-    0xA7B3: 1026,
-    0xA7B5: 1027,
-    0xA7B7: 1028,
-    0xA7B8: 1029,
-    0xA7B9: 1030,
-    0xA861: 1031,
-    0xA862: 1032,
-    0xA865: 1033,
-    0xA869: 1034,
-    0xA86B: 1035,
-    0xA871: 1036,
-    0xA873: 1037,
-    0xA875: 1038,
-    0xA876: 1039,
-    0xA877: 1040,
-    0xA87D: 1041,
-    0xA881: 1042,
-    0xA882: 1043,
-    0xA885: 1044,
-    0xA889: 1045,
-    0xA891: 1046,
-    0xA893: 1047,
-    0xA895: 1048,
-    0xA896: 1049,
-    0xA897: 1050,
-    0xA8A1: 1051,
-    0xA8A2: 1052,
-    0xA8B1: 1053,
-    0xA8E1: 1054,
-    0xA8E2: 1055,
-    0xA8E5: 1056,
-    0xA8E8: 1057,
-    0xA8E9: 1058,
-    0xA8F1: 1059,
-    0xA8F5: 1060,
-    0xA8F6: 1061,
-    0xA8F7: 1062,
-    0xA941: 1063,
-    0xA957: 1064,
-    0xA961: 1065,
-    0xA962: 1066,
-    0xA971: 1067,
-    0xA973: 1068,
-    0xA975: 1069,
-    0xA976: 1070,
-    0xA977: 1071,
-    0xA9A1: 1072,
-    0xA9A2: 1073,
-    0xA9A5: 1074,
-    0xA9A9: 1075,
-    0xA9B1: 1076,
-    0xA9B3: 1077,
-    0xA9B7: 1078,
-    0xAA41: 1079,
-    0xAA61: 1080,
-    0xAA77: 1081,
-    0xAA81: 1082,
-    0xAA82: 1083,
-    0xAA85: 1084,
-    0xAA89: 1085,
-    0xAA91: 1086,
-    0xAA95: 1087,
-    0xAA97: 1088,
-    0xAB41: 1089,
-    0xAB57: 1090,
-    0xAB61: 1091,
-    0xAB65: 1092,
-    0xAB69: 1093,
-    0xAB71: 1094,
-    0xAB73: 1095,
-    0xABA1: 1096,
-    0xABA2: 1097,
-    0xABA5: 1098,
-    0xABA9: 1099,
-    0xABB1: 1100,
-    0xABB3: 1101,
-    0xABB5: 1102,
-    0xABB7: 1103,
-    0xAC61: 1104,
-    0xAC62: 1105,
-    0xAC64: 1106,
-    0xAC65: 1107,
-    0xAC68: 1108,
-    0xAC69: 1109,
-    0xAC6A: 1110,
-    0xAC6B: 1111,
-    0xAC71: 1112,
-    0xAC73: 1113,
-    0xAC75: 1114,
-    0xAC76: 1115,
-    0xAC77: 1116,
-    0xAC7B: 1117,
-    0xAC81: 1118,
-    0xAC82: 1119,
-    0xAC85: 1120,
-    0xAC89: 1121,
-    0xAC91: 1122,
-    0xAC93: 1123,
-    0xAC95: 1124,
-    0xAC96: 1125,
-    0xAC97: 1126,
-    0xACA1: 1127,
-    0xACA2: 1128,
-    0xACA5: 1129,
-    0xACA9: 1130,
-    0xACB1: 1131,
-    0xACB3: 1132,
-    0xACB5: 1133,
-    0xACB7: 1134,
-    0xACC1: 1135,
-    0xACC5: 1136,
-    0xACC9: 1137,
-    0xACD1: 1138,
-    0xACD7: 1139,
-    0xACE1: 1140,
-    0xACE2: 1141,
-    0xACE3: 1142,
-    0xACE4: 1143,
-    0xACE5: 1144,
-    0xACE8: 1145,
-    0xACE9: 1146,
-    0xACEB: 1147,
-    0xACEC: 1148,
-    0xACF1: 1149,
-    0xACF3: 1150,
-    0xACF5: 1151,
-    0xACF6: 1152,
-    0xACF7: 1153,
-    0xACFC: 1154,
-    0xAD41: 1155,
-    0xAD42: 1156,
-    0xAD45: 1157,
-    0xAD49: 1158,
-    0xAD51: 1159,
-    0xAD53: 1160,
-    0xAD55: 1161,
-    0xAD56: 1162,
-    0xAD57: 1163,
-    0xAD61: 1164,
-    0xAD62: 1165,
-    0xAD65: 1166,
-    0xAD69: 1167,
-    0xAD71: 1168,
-    0xAD73: 1169,
-    0xAD75: 1170,
-    0xAD76: 1171,
-    0xAD77: 1172,
-    0xAD81: 1173,
-    0xAD85: 1174,
-    0xAD89: 1175,
-    0xAD97: 1176,
-    0xADA1: 1177,
-    0xADA2: 1178,
-    0xADA3: 1179,
-    0xADA5: 1180,
-    0xADA9: 1181,
-    0xADAB: 1182,
-    0xADB1: 1183,
-    0xADB3: 1184,
-    0xADB5: 1185,
-    0xADB7: 1186,
-    0xADBB: 1187,
-    0xADC1: 1188,
-    0xADC2: 1189,
-    0xADC5: 1190,
-    0xADC9: 1191,
-    0xADD7: 1192,
-    0xADE1: 1193,
-    0xADE5: 1194,
-    0xADE9: 1195,
-    0xADF1: 1196,
-    0xADF5: 1197,
-    0xADF6: 1198,
-    0xAE41: 1199,
-    0xAE45: 1200,
-    0xAE49: 1201,
-    0xAE51: 1202,
-    0xAE53: 1203,
-    0xAE55: 1204,
-    0xAE61: 1205,
-    0xAE62: 1206,
-    0xAE65: 1207,
-    0xAE69: 1208,
-    0xAE71: 1209,
-    0xAE73: 1210,
-    0xAE75: 1211,
-    0xAE77: 1212,
-    0xAE81: 1213,
-    0xAE82: 1214,
-    0xAE85: 1215,
-    0xAE88: 1216,
-    0xAE89: 1217,
-    0xAE91: 1218,
-    0xAE93: 1219,
-    0xAE95: 1220,
-    0xAE97: 1221,
-    0xAE99: 1222,
-    0xAE9B: 1223,
-    0xAE9C: 1224,
-    0xAEA1: 1225,
-    0xAEB6: 1226,
-    0xAEC1: 1227,
-    0xAEC2: 1228,
-    0xAEC5: 1229,
-    0xAEC9: 1230,
-    0xAED1: 1231,
-    0xAED7: 1232,
-    0xAEE1: 1233,
-    0xAEE2: 1234,
-    0xAEE5: 1235,
-    0xAEE9: 1236,
-    0xAEF1: 1237,
-    0xAEF3: 1238,
-    0xAEF5: 1239,
-    0xAEF7: 1240,
-    0xAF41: 1241,
-    0xAF42: 1242,
-    0xAF49: 1243,
-    0xAF51: 1244,
-    0xAF55: 1245,
-    0xAF57: 1246,
-    0xAF61: 1247,
-    0xAF62: 1248,
-    0xAF65: 1249,
-    0xAF69: 1250,
-    0xAF6A: 1251,
-    0xAF71: 1252,
-    0xAF73: 1253,
-    0xAF75: 1254,
-    0xAF77: 1255,
-    0xAFA1: 1256,
-    0xAFA2: 1257,
-    0xAFA5: 1258,
-    0xAFA8: 1259,
-    0xAFA9: 1260,
-    0xAFB0: 1261,
-    0xAFB1: 1262,
-    0xAFB3: 1263,
-    0xAFB5: 1264,
-    0xAFB7: 1265,
-    0xAFBC: 1266,
-    0xB061: 1267,
-    0xB062: 1268,
-    0xB064: 1269,
-    0xB065: 1270,
-    0xB069: 1271,
-    0xB071: 1272,
-    0xB073: 1273,
-    0xB076: 1274,
-    0xB077: 1275,
-    0xB07D: 1276,
-    0xB081: 1277,
-    0xB082: 1278,
-    0xB085: 1279,
-    0xB089: 1280,
-    0xB091: 1281,
-    0xB093: 1282,
-    0xB096: 1283,
-    0xB097: 1284,
-    0xB0B7: 1285,
-    0xB0E1: 1286,
-    0xB0E2: 1287,
-    0xB0E5: 1288,
-    0xB0E9: 1289,
-    0xB0EB: 1290,
-    0xB0F1: 1291,
-    0xB0F3: 1292,
-    0xB0F6: 1293,
-    0xB0F7: 1294,
-    0xB141: 1295,
-    0xB145: 1296,
-    0xB149: 1297,
-    0xB185: 1298,
-    0xB1A1: 1299,
-    0xB1A2: 1300,
-    0xB1A5: 1301,
-    0xB1A8: 1302,
-    0xB1A9: 1303,
-    0xB1AB: 1304,
-    0xB1B1: 1305,
-    0xB1B3: 1306,
-    0xB1B7: 1307,
-    0xB1C1: 1308,
-    0xB1C2: 1309,
-    0xB1C5: 1310,
-    0xB1D6: 1311,
-    0xB1E1: 1312,
-    0xB1F6: 1313,
-    0xB241: 1314,
-    0xB245: 1315,
-    0xB249: 1316,
-    0xB251: 1317,
-    0xB253: 1318,
-    0xB261: 1319,
-    0xB281: 1320,
-    0xB282: 1321,
-    0xB285: 1322,
-    0xB289: 1323,
-    0xB291: 1324,
-    0xB293: 1325,
-    0xB297: 1326,
-    0xB2A1: 1327,
-    0xB2B6: 1328,
-    0xB2C1: 1329,
-    0xB2E1: 1330,
-    0xB2E5: 1331,
-    0xB357: 1332,
-    0xB361: 1333,
-    0xB362: 1334,
-    0xB365: 1335,
-    0xB369: 1336,
-    0xB36B: 1337,
-    0xB370: 1338,
-    0xB371: 1339,
-    0xB373: 1340,
-    0xB381: 1341,
-    0xB385: 1342,
-    0xB389: 1343,
-    0xB391: 1344,
-    0xB3A1: 1345,
-    0xB3A2: 1346,
-    0xB3A5: 1347,
-    0xB3A9: 1348,
-    0xB3B1: 1349,
-    0xB3B3: 1350,
-    0xB3B5: 1351,
-    0xB3B7: 1352,
-    0xB461: 1353,
-    0xB462: 1354,
-    0xB465: 1355,
-    0xB466: 1356,
-    0xB467: 1357,
-    0xB469: 1358,
-    0xB46A: 1359,
-    0xB46B: 1360,
-    0xB470: 1361,
-    0xB471: 1362,
-    0xB473: 1363,
-    0xB475: 1364,
-    0xB476: 1365,
-    0xB477: 1366,
-    0xB47B: 1367,
-    0xB47C: 1368,
-    0xB481: 1369,
-    0xB482: 1370,
-    0xB485: 1371,
-    0xB489: 1372,
-    0xB491: 1373,
-    0xB493: 1374,
-    0xB495: 1375,
-    0xB496: 1376,
-    0xB497: 1377,
-    0xB4A1: 1378,
-    0xB4A2: 1379,
-    0xB4A5: 1380,
-    0xB4A9: 1381,
-    0xB4AC: 1382,
-    0xB4B1: 1383,
-    0xB4B3: 1384,
-    0xB4B5: 1385,
-    0xB4B7: 1386,
-    0xB4BB: 1387,
-    0xB4BD: 1388,
-    0xB4C1: 1389,
-    0xB4C5: 1390,
-    0xB4C9: 1391,
-    0xB4D3: 1392,
-    0xB4E1: 1393,
-    0xB4E2: 1394,
-    0xB4E5: 1395,
-    0xB4E6: 1396,
-    0xB4E8: 1397,
-    0xB4E9: 1398,
-    0xB4EA: 1399,
-    0xB4EB: 1400,
-    0xB4F1: 1401,
-    0xB4F3: 1402,
-    0xB4F4: 1403,
-    0xB4F5: 1404,
-    0xB4F6: 1405,
-    0xB4F7: 1406,
-    0xB4F8: 1407,
-    0xB4FA: 1408,
-    0xB4FC: 1409,
-    0xB541: 1410,
-    0xB542: 1411,
-    0xB545: 1412,
-    0xB549: 1413,
-    0xB551: 1414,
-    0xB553: 1415,
-    0xB555: 1416,
-    0xB557: 1417,
-    0xB561: 1418,
-    0xB562: 1419,
-    0xB563: 1420,
-    0xB565: 1421,
-    0xB569: 1422,
-    0xB56B: 1423,
-    0xB56C: 1424,
-    0xB571: 1425,
-    0xB573: 1426,
-    0xB574: 1427,
-    0xB575: 1428,
-    0xB576: 1429,
-    0xB577: 1430,
-    0xB57B: 1431,
-    0xB57C: 1432,
-    0xB57D: 1433,
-    0xB581: 1434,
-    0xB585: 1435,
-    0xB589: 1436,
-    0xB591: 1437,
-    0xB593: 1438,
-    0xB595: 1439,
-    0xB596: 1440,
-    0xB5A1: 1441,
-    0xB5A2: 1442,
-    0xB5A5: 1443,
-    0xB5A9: 1444,
-    0xB5AA: 1445,
-    0xB5AB: 1446,
-    0xB5AD: 1447,
-    0xB5B0: 1448,
-    0xB5B1: 1449,
-    0xB5B3: 1450,
-    0xB5B5: 1451,
-    0xB5B7: 1452,
-    0xB5B9: 1453,
-    0xB5C1: 1454,
-    0xB5C2: 1455,
-    0xB5C5: 1456,
-    0xB5C9: 1457,
-    0xB5D1: 1458,
-    0xB5D3: 1459,
-    0xB5D5: 1460,
-    0xB5D6: 1461,
-    0xB5D7: 1462,
-    0xB5E1: 1463,
-    0xB5E2: 1464,
-    0xB5E5: 1465,
-    0xB5F1: 1466,
-    0xB5F5: 1467,
-    0xB5F7: 1468,
-    0xB641: 1469,
-    0xB642: 1470,
-    0xB645: 1471,
-    0xB649: 1472,
-    0xB651: 1473,
-    0xB653: 1474,
-    0xB655: 1475,
-    0xB657: 1476,
-    0xB661: 1477,
-    0xB662: 1478,
-    0xB665: 1479,
-    0xB669: 1480,
-    0xB671: 1481,
-    0xB673: 1482,
-    0xB675: 1483,
-    0xB677: 1484,
-    0xB681: 1485,
-    0xB682: 1486,
-    0xB685: 1487,
-    0xB689: 1488,
-    0xB68A: 1489,
-    0xB68B: 1490,
-    0xB691: 1491,
-    0xB693: 1492,
-    0xB695: 1493,
-    0xB697: 1494,
-    0xB6A1: 1495,
-    0xB6A2: 1496,
-    0xB6A5: 1497,
-    0xB6A9: 1498,
-    0xB6B1: 1499,
-    0xB6B3: 1500,
-    0xB6B6: 1501,
-    0xB6B7: 1502,
-    0xB6C1: 1503,
-    0xB6C2: 1504,
-    0xB6C5: 1505,
-    0xB6C9: 1506,
-    0xB6D1: 1507,
-    0xB6D3: 1508,
-    0xB6D7: 1509,
-    0xB6E1: 1510,
-    0xB6E2: 1511,
-    0xB6E5: 1512,
-    0xB6E9: 1513,
-    0xB6F1: 1514,
-    0xB6F3: 1515,
-    0xB6F5: 1516,
-    0xB6F7: 1517,
-    0xB741: 1518,
-    0xB742: 1519,
-    0xB745: 1520,
-    0xB749: 1521,
-    0xB751: 1522,
-    0xB753: 1523,
-    0xB755: 1524,
-    0xB757: 1525,
-    0xB759: 1526,
-    0xB761: 1527,
-    0xB762: 1528,
-    0xB765: 1529,
-    0xB769: 1530,
-    0xB76F: 1531,
-    0xB771: 1532,
-    0xB773: 1533,
-    0xB775: 1534,
-    0xB777: 1535,
-    0xB778: 1536,
-    0xB779: 1537,
-    0xB77A: 1538,
-    0xB77B: 1539,
-    0xB77C: 1540,
-    0xB77D: 1541,
-    0xB781: 1542,
-    0xB785: 1543,
-    0xB789: 1544,
-    0xB791: 1545,
-    0xB795: 1546,
-    0xB7A1: 1547,
-    0xB7A2: 1548,
-    0xB7A5: 1549,
-    0xB7A9: 1550,
-    0xB7AA: 1551,
-    0xB7AB: 1552,
-    0xB7B0: 1553,
-    0xB7B1: 1554,
-    0xB7B3: 1555,
-    0xB7B5: 1556,
-    0xB7B6: 1557,
-    0xB7B7: 1558,
-    0xB7B8: 1559,
-    0xB7BC: 1560,
-    0xB861: 1561,
-    0xB862: 1562,
-    0xB865: 1563,
-    0xB867: 1564,
-    0xB868: 1565,
-    0xB869: 1566,
-    0xB86B: 1567,
-    0xB871: 1568,
-    0xB873: 1569,
-    0xB875: 1570,
-    0xB876: 1571,
-    0xB877: 1572,
-    0xB878: 1573,
-    0xB881: 1574,
-    0xB882: 1575,
-    0xB885: 1576,
-    0xB889: 1577,
-    0xB891: 1578,
-    0xB893: 1579,
-    0xB895: 1580,
-    0xB896: 1581,
-    0xB897: 1582,
-    0xB8A1: 1583,
-    0xB8A2: 1584,
-    0xB8A5: 1585,
-    0xB8A7: 1586,
-    0xB8A9: 1587,
-    0xB8B1: 1588,
-    0xB8B7: 1589,
-    0xB8C1: 1590,
-    0xB8C5: 1591,
-    0xB8C9: 1592,
-    0xB8E1: 1593,
-    0xB8E2: 1594,
-    0xB8E5: 1595,
-    0xB8E9: 1596,
-    0xB8EB: 1597,
-    0xB8F1: 1598,
-    0xB8F3: 1599,
-    0xB8F5: 1600,
-    0xB8F7: 1601,
-    0xB8F8: 1602,
-    0xB941: 1603,
-    0xB942: 1604,
-    0xB945: 1605,
-    0xB949: 1606,
-    0xB951: 1607,
-    0xB953: 1608,
-    0xB955: 1609,
-    0xB957: 1610,
-    0xB961: 1611,
-    0xB965: 1612,
-    0xB969: 1613,
-    0xB971: 1614,
-    0xB973: 1615,
-    0xB976: 1616,
-    0xB977: 1617,
-    0xB981: 1618,
-    0xB9A1: 1619,
-    0xB9A2: 1620,
-    0xB9A5: 1621,
-    0xB9A9: 1622,
-    0xB9AB: 1623,
-    0xB9B1: 1624,
-    0xB9B3: 1625,
-    0xB9B5: 1626,
-    0xB9B7: 1627,
-    0xB9B8: 1628,
-    0xB9B9: 1629,
-    0xB9BD: 1630,
-    0xB9C1: 1631,
-    0xB9C2: 1632,
-    0xB9C9: 1633,
-    0xB9D3: 1634,
-    0xB9D5: 1635,
-    0xB9D7: 1636,
-    0xB9E1: 1637,
-    0xB9F6: 1638,
-    0xB9F7: 1639,
-    0xBA41: 1640,
-    0xBA45: 1641,
-    0xBA49: 1642,
-    0xBA51: 1643,
-    0xBA53: 1644,
-    0xBA55: 1645,
-    0xBA57: 1646,
-    0xBA61: 1647,
-    0xBA62: 1648,
-    0xBA65: 1649,
-    0xBA77: 1650,
-    0xBA81: 1651,
-    0xBA82: 1652,
-    0xBA85: 1653,
-    0xBA89: 1654,
-    0xBA8A: 1655,
-    0xBA8B: 1656,
-    0xBA91: 1657,
-    0xBA93: 1658,
-    0xBA95: 1659,
-    0xBA97: 1660,
-    0xBAA1: 1661,
-    0xBAB6: 1662,
-    0xBAC1: 1663,
-    0xBAE1: 1664,
-    0xBAE2: 1665,
-    0xBAE5: 1666,
-    0xBAE9: 1667,
-    0xBAF1: 1668,
-    0xBAF3: 1669,
-    0xBAF5: 1670,
-    0xBB41: 1671,
-    0xBB45: 1672,
-    0xBB49: 1673,
-    0xBB51: 1674,
-    0xBB61: 1675,
-    0xBB62: 1676,
-    0xBB65: 1677,
-    0xBB69: 1678,
-    0xBB71: 1679,
-    0xBB73: 1680,
-    0xBB75: 1681,
-    0xBB77: 1682,
-    0xBBA1: 1683,
-    0xBBA2: 1684,
-    0xBBA5: 1685,
-    0xBBA8: 1686,
-    0xBBA9: 1687,
-    0xBBAB: 1688,
-    0xBBB1: 1689,
-    0xBBB3: 1690,
-    0xBBB5: 1691,
-    0xBBB7: 1692,
-    0xBBB8: 1693,
-    0xBBBB: 1694,
-    0xBBBC: 1695,
-    0xBC61: 1696,
-    0xBC62: 1697,
-    0xBC65: 1698,
-    0xBC67: 1699,
-    0xBC69: 1700,
-    0xBC6C: 1701,
-    0xBC71: 1702,
-    0xBC73: 1703,
-    0xBC75: 1704,
-    0xBC76: 1705,
-    0xBC77: 1706,
-    0xBC81: 1707,
-    0xBC82: 1708,
-    0xBC85: 1709,
-    0xBC89: 1710,
-    0xBC91: 1711,
-    0xBC93: 1712,
-    0xBC95: 1713,
-    0xBC96: 1714,
-    0xBC97: 1715,
-    0xBCA1: 1716,
-    0xBCA5: 1717,
-    0xBCB7: 1718,
-    0xBCE1: 1719,
-    0xBCE2: 1720,
-    0xBCE5: 1721,
-    0xBCE9: 1722,
-    0xBCF1: 1723,
-    0xBCF3: 1724,
-    0xBCF5: 1725,
-    0xBCF6: 1726,
-    0xBCF7: 1727,
-    0xBD41: 1728,
-    0xBD57: 1729,
-    0xBD61: 1730,
-    0xBD76: 1731,
-    0xBDA1: 1732,
-    0xBDA2: 1733,
-    0xBDA5: 1734,
-    0xBDA9: 1735,
-    0xBDB1: 1736,
-    0xBDB3: 1737,
-    0xBDB5: 1738,
-    0xBDB7: 1739,
-    0xBDB9: 1740,
-    0xBDC1: 1741,
-    0xBDC2: 1742,
-    0xBDC9: 1743,
-    0xBDD6: 1744,
-    0xBDE1: 1745,
-    0xBDF6: 1746,
-    0xBE41: 1747,
-    0xBE45: 1748,
-    0xBE49: 1749,
-    0xBE51: 1750,
-    0xBE53: 1751,
-    0xBE77: 1752,
-    0xBE81: 1753,
-    0xBE82: 1754,
-    0xBE85: 1755,
-    0xBE89: 1756,
-    0xBE91: 1757,
-    0xBE93: 1758,
-    0xBE97: 1759,
-    0xBEA1: 1760,
-    0xBEB6: 1761,
-    0xBEB7: 1762,
-    0xBEE1: 1763,
-    0xBF41: 1764,
-    0xBF61: 1765,
-    0xBF71: 1766,
-    0xBF75: 1767,
-    0xBF77: 1768,
-    0xBFA1: 1769,
-    0xBFA2: 1770,
-    0xBFA5: 1771,
-    0xBFA9: 1772,
-    0xBFB1: 1773,
-    0xBFB3: 1774,
-    0xBFB7: 1775,
-    0xBFB8: 1776,
-    0xBFBD: 1777,
-    0xC061: 1778,
-    0xC062: 1779,
-    0xC065: 1780,
-    0xC067: 1781,
-    0xC069: 1782,
-    0xC071: 1783,
-    0xC073: 1784,
-    0xC075: 1785,
-    0xC076: 1786,
-    0xC077: 1787,
-    0xC078: 1788,
-    0xC081: 1789,
-    0xC082: 1790,
-    0xC085: 1791,
-    0xC089: 1792,
-    0xC091: 1793,
-    0xC093: 1794,
-    0xC095: 1795,
-    0xC096: 1796,
-    0xC097: 1797,
-    0xC0A1: 1798,
-    0xC0A5: 1799,
-    0xC0A7: 1800,
-    0xC0A9: 1801,
-    0xC0B1: 1802,
-    0xC0B7: 1803,
-    0xC0E1: 1804,
-    0xC0E2: 1805,
-    0xC0E5: 1806,
-    0xC0E9: 1807,
-    0xC0F1: 1808,
-    0xC0F3: 1809,
-    0xC0F5: 1810,
-    0xC0F6: 1811,
-    0xC0F7: 1812,
-    0xC141: 1813,
-    0xC142: 1814,
-    0xC145: 1815,
-    0xC149: 1816,
-    0xC151: 1817,
-    0xC153: 1818,
-    0xC155: 1819,
-    0xC157: 1820,
-    0xC161: 1821,
-    0xC165: 1822,
-    0xC176: 1823,
-    0xC181: 1824,
-    0xC185: 1825,
-    0xC197: 1826,
-    0xC1A1: 1827,
-    0xC1A2: 1828,
-    0xC1A5: 1829,
-    0xC1A9: 1830,
-    0xC1B1: 1831,
-    0xC1B3: 1832,
-    0xC1B5: 1833,
-    0xC1B7: 1834,
-    0xC1C1: 1835,
-    0xC1C5: 1836,
-    0xC1C9: 1837,
-    0xC1D7: 1838,
-    0xC241: 1839,
-    0xC245: 1840,
-    0xC249: 1841,
-    0xC251: 1842,
-    0xC253: 1843,
-    0xC255: 1844,
-    0xC257: 1845,
-    0xC261: 1846,
-    0xC271: 1847,
-    0xC281: 1848,
-    0xC282: 1849,
-    0xC285: 1850,
-    0xC289: 1851,
-    0xC291: 1852,
-    0xC293: 1853,
-    0xC295: 1854,
-    0xC297: 1855,
-    0xC2A1: 1856,
-    0xC2B6: 1857,
-    0xC2C1: 1858,
-    0xC2C5: 1859,
-    0xC2E1: 1860,
-    0xC2E5: 1861,
-    0xC2E9: 1862,
-    0xC2F1: 1863,
-    0xC2F3: 1864,
-    0xC2F5: 1865,
-    0xC2F7: 1866,
-    0xC341: 1867,
-    0xC345: 1868,
-    0xC349: 1869,
-    0xC351: 1870,
-    0xC357: 1871,
-    0xC361: 1872,
-    0xC362: 1873,
-    0xC365: 1874,
-    0xC369: 1875,
-    0xC371: 1876,
-    0xC373: 1877,
-    0xC375: 1878,
-    0xC377: 1879,
-    0xC3A1: 1880,
-    0xC3A2: 1881,
-    0xC3A5: 1882,
-    0xC3A8: 1883,
-    0xC3A9: 1884,
-    0xC3AA: 1885,
-    0xC3B1: 1886,
-    0xC3B3: 1887,
-    0xC3B5: 1888,
-    0xC3B7: 1889,
-    0xC461: 1890,
-    0xC462: 1891,
-    0xC465: 1892,
-    0xC469: 1893,
-    0xC471: 1894,
-    0xC473: 1895,
-    0xC475: 1896,
-    0xC477: 1897,
-    0xC481: 1898,
-    0xC482: 1899,
-    0xC485: 1900,
-    0xC489: 1901,
-    0xC491: 1902,
-    0xC493: 1903,
-    0xC495: 1904,
-    0xC496: 1905,
-    0xC497: 1906,
-    0xC4A1: 1907,
-    0xC4A2: 1908,
-    0xC4B7: 1909,
-    0xC4E1: 1910,
-    0xC4E2: 1911,
-    0xC4E5: 1912,
-    0xC4E8: 1913,
-    0xC4E9: 1914,
-    0xC4F1: 1915,
-    0xC4F3: 1916,
-    0xC4F5: 1917,
-    0xC4F6: 1918,
-    0xC4F7: 1919,
-    0xC541: 1920,
-    0xC542: 1921,
-    0xC545: 1922,
-    0xC549: 1923,
-    0xC551: 1924,
-    0xC553: 1925,
-    0xC555: 1926,
-    0xC557: 1927,
-    0xC561: 1928,
-    0xC565: 1929,
-    0xC569: 1930,
-    0xC571: 1931,
-    0xC573: 1932,
-    0xC575: 1933,
-    0xC576: 1934,
-    0xC577: 1935,
-    0xC581: 1936,
-    0xC5A1: 1937,
-    0xC5A2: 1938,
-    0xC5A5: 1939,
-    0xC5A9: 1940,
-    0xC5B1: 1941,
-    0xC5B3: 1942,
-    0xC5B5: 1943,
-    0xC5B7: 1944,
-    0xC5C1: 1945,
-    0xC5C2: 1946,
-    0xC5C5: 1947,
-    0xC5C9: 1948,
-    0xC5D1: 1949,
-    0xC5D7: 1950,
-    0xC5E1: 1951,
-    0xC5F7: 1952,
-    0xC641: 1953,
-    0xC649: 1954,
-    0xC661: 1955,
-    0xC681: 1956,
-    0xC682: 1957,
-    0xC685: 1958,
-    0xC689: 1959,
-    0xC691: 1960,
-    0xC693: 1961,
-    0xC695: 1962,
-    0xC697: 1963,
-    0xC6A1: 1964,
-    0xC6A5: 1965,
-    0xC6A9: 1966,
-    0xC6B7: 1967,
-    0xC6C1: 1968,
-    0xC6D7: 1969,
-    0xC6E1: 1970,
-    0xC6E2: 1971,
-    0xC6E5: 1972,
-    0xC6E9: 1973,
-    0xC6F1: 1974,
-    0xC6F3: 1975,
-    0xC6F5: 1976,
-    0xC6F7: 1977,
-    0xC741: 1978,
-    0xC745: 1979,
-    0xC749: 1980,
-    0xC751: 1981,
-    0xC761: 1982,
-    0xC762: 1983,
-    0xC765: 1984,
-    0xC769: 1985,
-    0xC771: 1986,
-    0xC773: 1987,
-    0xC777: 1988,
-    0xC7A1: 1989,
-    0xC7A2: 1990,
-    0xC7A5: 1991,
-    0xC7A9: 1992,
-    0xC7B1: 1993,
-    0xC7B3: 1994,
-    0xC7B5: 1995,
-    0xC7B7: 1996,
-    0xC861: 1997,
-    0xC862: 1998,
-    0xC865: 1999,
-    0xC869: 2000,
-    0xC86A: 2001,
-    0xC871: 2002,
-    0xC873: 2003,
-    0xC875: 2004,
-    0xC876: 2005,
-    0xC877: 2006,
-    0xC881: 2007,
-    0xC882: 2008,
-    0xC885: 2009,
-    0xC889: 2010,
-    0xC891: 2011,
-    0xC893: 2012,
-    0xC895: 2013,
-    0xC896: 2014,
-    0xC897: 2015,
-    0xC8A1: 2016,
-    0xC8B7: 2017,
-    0xC8E1: 2018,
-    0xC8E2: 2019,
-    0xC8E5: 2020,
-    0xC8E9: 2021,
-    0xC8EB: 2022,
-    0xC8F1: 2023,
-    0xC8F3: 2024,
-    0xC8F5: 2025,
-    0xC8F6: 2026,
-    0xC8F7: 2027,
-    0xC941: 2028,
-    0xC942: 2029,
-    0xC945: 2030,
-    0xC949: 2031,
-    0xC951: 2032,
-    0xC953: 2033,
-    0xC955: 2034,
-    0xC957: 2035,
-    0xC961: 2036,
-    0xC965: 2037,
-    0xC976: 2038,
-    0xC981: 2039,
-    0xC985: 2040,
-    0xC9A1: 2041,
-    0xC9A2: 2042,
-    0xC9A5: 2043,
-    0xC9A9: 2044,
-    0xC9B1: 2045,
-    0xC9B3: 2046,
-    0xC9B5: 2047,
-    0xC9B7: 2048,
-    0xC9BC: 2049,
-    0xC9C1: 2050,
-    0xC9C5: 2051,
-    0xC9E1: 2052,
-    0xCA41: 2053,
-    0xCA45: 2054,
-    0xCA55: 2055,
-    0xCA57: 2056,
-    0xCA61: 2057,
-    0xCA81: 2058,
-    0xCA82: 2059,
-    0xCA85: 2060,
-    0xCA89: 2061,
-    0xCA91: 2062,
-    0xCA93: 2063,
-    0xCA95: 2064,
-    0xCA97: 2065,
-    0xCAA1: 2066,
-    0xCAB6: 2067,
-    0xCAC1: 2068,
-    0xCAE1: 2069,
-    0xCAE2: 2070,
-    0xCAE5: 2071,
-    0xCAE9: 2072,
-    0xCAF1: 2073,
-    0xCAF3: 2074,
-    0xCAF7: 2075,
-    0xCB41: 2076,
-    0xCB45: 2077,
-    0xCB49: 2078,
-    0xCB51: 2079,
-    0xCB57: 2080,
-    0xCB61: 2081,
-    0xCB62: 2082,
-    0xCB65: 2083,
-    0xCB68: 2084,
-    0xCB69: 2085,
-    0xCB6B: 2086,
-    0xCB71: 2087,
-    0xCB73: 2088,
-    0xCB75: 2089,
-    0xCB81: 2090,
-    0xCB85: 2091,
-    0xCB89: 2092,
-    0xCB91: 2093,
-    0xCB93: 2094,
-    0xCBA1: 2095,
-    0xCBA2: 2096,
-    0xCBA5: 2097,
-    0xCBA9: 2098,
-    0xCBB1: 2099,
-    0xCBB3: 2100,
-    0xCBB5: 2101,
-    0xCBB7: 2102,
-    0xCC61: 2103,
-    0xCC62: 2104,
-    0xCC63: 2105,
-    0xCC65: 2106,
-    0xCC69: 2107,
-    0xCC6B: 2108,
-    0xCC71: 2109,
-    0xCC73: 2110,
-    0xCC75: 2111,
-    0xCC76: 2112,
-    0xCC77: 2113,
-    0xCC7B: 2114,
-    0xCC81: 2115,
-    0xCC82: 2116,
-    0xCC85: 2117,
-    0xCC89: 2118,
-    0xCC91: 2119,
-    0xCC93: 2120,
-    0xCC95: 2121,
-    0xCC96: 2122,
-    0xCC97: 2123,
-    0xCCA1: 2124,
-    0xCCA2: 2125,
-    0xCCE1: 2126,
-    0xCCE2: 2127,
-    0xCCE5: 2128,
-    0xCCE9: 2129,
-    0xCCF1: 2130,
-    0xCCF3: 2131,
-    0xCCF5: 2132,
-    0xCCF6: 2133,
-    0xCCF7: 2134,
-    0xCD41: 2135,
-    0xCD42: 2136,
-    0xCD45: 2137,
-    0xCD49: 2138,
-    0xCD51: 2139,
-    0xCD53: 2140,
-    0xCD55: 2141,
-    0xCD57: 2142,
-    0xCD61: 2143,
-    0xCD65: 2144,
-    0xCD69: 2145,
-    0xCD71: 2146,
-    0xCD73: 2147,
-    0xCD76: 2148,
-    0xCD77: 2149,
-    0xCD81: 2150,
-    0xCD89: 2151,
-    0xCD93: 2152,
-    0xCD95: 2153,
-    0xCDA1: 2154,
-    0xCDA2: 2155,
-    0xCDA5: 2156,
-    0xCDA9: 2157,
-    0xCDB1: 2158,
-    0xCDB3: 2159,
-    0xCDB5: 2160,
-    0xCDB7: 2161,
-    0xCDC1: 2162,
-    0xCDD7: 2163,
-    0xCE41: 2164,
-    0xCE45: 2165,
-    0xCE61: 2166,
-    0xCE65: 2167,
-    0xCE69: 2168,
-    0xCE73: 2169,
-    0xCE75: 2170,
-    0xCE81: 2171,
-    0xCE82: 2172,
-    0xCE85: 2173,
-    0xCE88: 2174,
-    0xCE89: 2175,
-    0xCE8B: 2176,
-    0xCE91: 2177,
-    0xCE93: 2178,
-    0xCE95: 2179,
-    0xCE97: 2180,
-    0xCEA1: 2181,
-    0xCEB7: 2182,
-    0xCEE1: 2183,
-    0xCEE5: 2184,
-    0xCEE9: 2185,
-    0xCEF1: 2186,
-    0xCEF5: 2187,
-    0xCF41: 2188,
-    0xCF45: 2189,
-    0xCF49: 2190,
-    0xCF51: 2191,
-    0xCF55: 2192,
-    0xCF57: 2193,
-    0xCF61: 2194,
-    0xCF65: 2195,
-    0xCF69: 2196,
-    0xCF71: 2197,
-    0xCF73: 2198,
-    0xCF75: 2199,
-    0xCFA1: 2200,
-    0xCFA2: 2201,
-    0xCFA5: 2202,
-    0xCFA9: 2203,
-    0xCFB1: 2204,
-    0xCFB3: 2205,
-    0xCFB5: 2206,
-    0xCFB7: 2207,
-    0xD061: 2208,
-    0xD062: 2209,
-    0xD065: 2210,
-    0xD069: 2211,
-    0xD06E: 2212,
-    0xD071: 2213,
-    0xD073: 2214,
-    0xD075: 2215,
-    0xD077: 2216,
-    0xD081: 2217,
-    0xD082: 2218,
-    0xD085: 2219,
-    0xD089: 2220,
-    0xD091: 2221,
-    0xD093: 2222,
-    0xD095: 2223,
-    0xD096: 2224,
-    0xD097: 2225,
-    0xD0A1: 2226,
-    0xD0B7: 2227,
-    0xD0E1: 2228,
-    0xD0E2: 2229,
-    0xD0E5: 2230,
-    0xD0E9: 2231,
-    0xD0EB: 2232,
-    0xD0F1: 2233,
-    0xD0F3: 2234,
-    0xD0F5: 2235,
-    0xD0F7: 2236,
-    0xD141: 2237,
-    0xD142: 2238,
-    0xD145: 2239,
-    0xD149: 2240,
-    0xD151: 2241,
-    0xD153: 2242,
-    0xD155: 2243,
-    0xD157: 2244,
-    0xD161: 2245,
-    0xD162: 2246,
-    0xD165: 2247,
-    0xD169: 2248,
-    0xD171: 2249,
-    0xD173: 2250,
-    0xD175: 2251,
-    0xD176: 2252,
-    0xD177: 2253,
-    0xD181: 2254,
-    0xD185: 2255,
-    0xD189: 2256,
-    0xD193: 2257,
-    0xD1A1: 2258,
-    0xD1A2: 2259,
-    0xD1A5: 2260,
-    0xD1A9: 2261,
-    0xD1AE: 2262,
-    0xD1B1: 2263,
-    0xD1B3: 2264,
-    0xD1B5: 2265,
-    0xD1B7: 2266,
-    0xD1BB: 2267,
-    0xD1C1: 2268,
-    0xD1C2: 2269,
-    0xD1C5: 2270,
-    0xD1C9: 2271,
-    0xD1D5: 2272,
-    0xD1D7: 2273,
-    0xD1E1: 2274,
-    0xD1E2: 2275,
-    0xD1E5: 2276,
-    0xD1F5: 2277,
-    0xD1F7: 2278,
-    0xD241: 2279,
-    0xD242: 2280,
-    0xD245: 2281,
-    0xD249: 2282,
-    0xD253: 2283,
-    0xD255: 2284,
-    0xD257: 2285,
-    0xD261: 2286,
-    0xD265: 2287,
-    0xD269: 2288,
-    0xD273: 2289,
-    0xD275: 2290,
-    0xD281: 2291,
-    0xD282: 2292,
-    0xD285: 2293,
-    0xD289: 2294,
-    0xD28E: 2295,
-    0xD291: 2296,
-    0xD295: 2297,
-    0xD297: 2298,
-    0xD2A1: 2299,
-    0xD2A5: 2300,
-    0xD2A9: 2301,
-    0xD2B1: 2302,
-    0xD2B7: 2303,
-    0xD2C1: 2304,
-    0xD2C2: 2305,
-    0xD2C5: 2306,
-    0xD2C9: 2307,
-    0xD2D7: 2308,
-    0xD2E1: 2309,
-    0xD2E2: 2310,
-    0xD2E5: 2311,
-    0xD2E9: 2312,
-    0xD2F1: 2313,
-    0xD2F3: 2314,
-    0xD2F5: 2315,
-    0xD2F7: 2316,
-    0xD341: 2317,
-    0xD342: 2318,
-    0xD345: 2319,
-    0xD349: 2320,
-    0xD351: 2321,
-    0xD355: 2322,
-    0xD357: 2323,
-    0xD361: 2324,
-    0xD362: 2325,
-    0xD365: 2326,
-    0xD367: 2327,
-    0xD368: 2328,
-    0xD369: 2329,
-    0xD36A: 2330,
-    0xD371: 2331,
-    0xD373: 2332,
-    0xD375: 2333,
-    0xD377: 2334,
-    0xD37B: 2335,
-    0xD381: 2336,
-    0xD385: 2337,
-    0xD389: 2338,
-    0xD391: 2339,
-    0xD393: 2340,
-    0xD397: 2341,
-    0xD3A1: 2342,
-    0xD3A2: 2343,
-    0xD3A5: 2344,
-    0xD3A9: 2345,
-    0xD3B1: 2346,
-    0xD3B3: 2347,
-    0xD3B5: 2348,
-    0xD3B7: 2349,
-}
diff --git a/spaces/Big-Web/MMSD/env/Lib/site-packages/pip/_vendor/rich/prompt.py b/spaces/Big-Web/MMSD/env/Lib/site-packages/pip/_vendor/rich/prompt.py
deleted file mode 100644
index 2bd0a7724f4375a5272cb7c101be5b6a582dc031..0000000000000000000000000000000000000000
--- a/spaces/Big-Web/MMSD/env/Lib/site-packages/pip/_vendor/rich/prompt.py
+++ /dev/null
@@ -1,376 +0,0 @@
-from typing import Any, Generic, List, Optional, TextIO, TypeVar, Union, overload
-
-from . import get_console
-from .console import Console
-from .text import Text, TextType
-
-PromptType = TypeVar("PromptType")
-DefaultType = TypeVar("DefaultType")
-
-
-class PromptError(Exception):
-    """Exception base class for prompt related errors."""
-
-
-class InvalidResponse(PromptError):
-    """Exception to indicate a response was invalid. Raise this within process_response() to indicate an error
-    and provide an error message.
-
-    Args:
-        message (Union[str, Text]): Error message.
-    """
-
-    def __init__(self, message: TextType) -> None:
-        self.message = message
-
-    def __rich__(self) -> TextType:
-        return self.message
-
-
-class PromptBase(Generic[PromptType]):
-    """Ask the user for input until a valid response is received. This is the base class, see one of
-    the concrete classes for examples.
-
-    Args:
-        prompt (TextType, optional): Prompt text. Defaults to "".
-        console (Console, optional): A Console instance or None to use global console. Defaults to None.
-        password (bool, optional): Enable password input. Defaults to False.
-        choices (List[str], optional): A list of valid choices. Defaults to None.
-        show_default (bool, optional): Show default in prompt. Defaults to True.
-        show_choices (bool, optional): Show choices in prompt. Defaults to True.
-    """
-
-    response_type: type = str
-
-    validate_error_message = "[prompt.invalid]Please enter a valid value"
-    illegal_choice_message = (
-        "[prompt.invalid.choice]Please select one of the available options"
-    )
-    prompt_suffix = ": "
-
-    choices: Optional[List[str]] = None
-
-    def __init__(
-        self,
-        prompt: TextType = "",
-        *,
-        console: Optional[Console] = None,
-        password: bool = False,
-        choices: Optional[List[str]] = None,
-        show_default: bool = True,
-        show_choices: bool = True,
-    ) -> None:
-        self.console = console or get_console()
-        self.prompt = (
-            Text.from_markup(prompt, style="prompt")
-            if isinstance(prompt, str)
-            else prompt
-        )
-        self.password = password
-        if choices is not None:
-            self.choices = choices
-        self.show_default = show_default
-        self.show_choices = show_choices
-
-    @classmethod
-    @overload
-    def ask(
-        cls,
-        prompt: TextType = "",
-        *,
-        console: Optional[Console] = None,
-        password: bool = False,
-        choices: Optional[List[str]] = None,
-        show_default: bool = True,
-        show_choices: bool = True,
-        default: DefaultType,
-        stream: Optional[TextIO] = None,
-    ) -> Union[DefaultType, PromptType]:
-        ...
-
-    @classmethod
-    @overload
-    def ask(
-        cls,
-        prompt: TextType = "",
-        *,
-        console: Optional[Console] = None,
-        password: bool = False,
-        choices: Optional[List[str]] = None,
-        show_default: bool = True,
-        show_choices: bool = True,
-        stream: Optional[TextIO] = None,
-    ) -> PromptType:
-        ...
-
-    @classmethod
-    def ask(
-        cls,
-        prompt: TextType = "",
-        *,
-        console: Optional[Console] = None,
-        password: bool = False,
-        choices: Optional[List[str]] = None,
-        show_default: bool = True,
-        show_choices: bool = True,
-        default: Any = ...,
-        stream: Optional[TextIO] = None,
-    ) -> Any:
-        """Shortcut to construct and run a prompt loop and return the result.
-
-        Example:
-            >>> filename = Prompt.ask("Enter a filename")
-
-        Args:
-            prompt (TextType, optional): Prompt text. Defaults to "".
-            console (Console, optional): A Console instance or None to use global console. Defaults to None.
-            password (bool, optional): Enable password input. Defaults to False.
-            choices (List[str], optional): A list of valid choices. Defaults to None.
-            show_default (bool, optional): Show default in prompt. Defaults to True.
-            show_choices (bool, optional): Show choices in prompt. Defaults to True.
-            stream (TextIO, optional): Optional text file open for reading to get input. Defaults to None.
-        """
-        _prompt = cls(
-            prompt,
-            console=console,
-            password=password,
-            choices=choices,
-            show_default=show_default,
-            show_choices=show_choices,
-        )
-        return _prompt(default=default, stream=stream)
-
-    def render_default(self, default: DefaultType) -> Text:
-        """Turn the supplied default in to a Text instance.
-
-        Args:
-            default (DefaultType): Default value.
-
-        Returns:
-            Text: Text containing rendering of default value.
-        """
-        return Text(f"({default})", "prompt.default")
-
-    def make_prompt(self, default: DefaultType) -> Text:
-        """Make prompt text.
-
-        Args:
-            default (DefaultType): Default value.
-
-        Returns:
-            Text: Text to display in prompt.
-        """
-        prompt = self.prompt.copy()
-        prompt.end = ""
-
-        if self.show_choices and self.choices:
-            _choices = "/".join(self.choices)
-            choices = f"[{_choices}]"
-            prompt.append(" ")
-            prompt.append(choices, "prompt.choices")
-
-        if (
-            default != ...
-            and self.show_default
-            and isinstance(default, (str, self.response_type))
-        ):
-            prompt.append(" ")
-            _default = self.render_default(default)
-            prompt.append(_default)
-
-        prompt.append(self.prompt_suffix)
-
-        return prompt
-
-    @classmethod
-    def get_input(
-        cls,
-        console: Console,
-        prompt: TextType,
-        password: bool,
-        stream: Optional[TextIO] = None,
-    ) -> str:
-        """Get input from user.
-
-        Args:
-            console (Console): Console instance.
-            prompt (TextType): Prompt text.
-            password (bool): Enable password entry.
-
-        Returns:
-            str: String from user.
-        """
-        return console.input(prompt, password=password, stream=stream)
-
-    def check_choice(self, value: str) -> bool:
-        """Check value is in the list of valid choices.
-
-        Args:
-            value (str): Value entered by user.
-
-        Returns:
-            bool: True if choice was valid, otherwise False.
-        """
-        assert self.choices is not None
-        return value.strip() in self.choices
-
-    def process_response(self, value: str) -> PromptType:
-        """Process response from user, convert to prompt type.
-
-        Args:
-            value (str): String typed by user.
-
-        Raises:
-            InvalidResponse: If ``value`` is invalid.
-
-        Returns:
-            PromptType: The value to be returned from ask method.
-        """
-        value = value.strip()
-        try:
-            return_value: PromptType = self.response_type(value)
-        except ValueError:
-            raise InvalidResponse(self.validate_error_message)
-
-        if self.choices is not None and not self.check_choice(value):
-            raise InvalidResponse(self.illegal_choice_message)
-
-        return return_value
-
-    def on_validate_error(self, value: str, error: InvalidResponse) -> None:
-        """Called to handle validation error.
-
-        Args:
-            value (str): String entered by user.
-            error (InvalidResponse): Exception instance the initiated the error.
-        """
-        self.console.print(error)
-
-    def pre_prompt(self) -> None:
-        """Hook to display something before the prompt."""
-
-    @overload
-    def __call__(self, *, stream: Optional[TextIO] = None) -> PromptType:
-        ...
-
-    @overload
-    def __call__(
-        self, *, default: DefaultType, stream: Optional[TextIO] = None
-    ) -> Union[PromptType, DefaultType]:
-        ...
-
-    def __call__(self, *, default: Any = ..., stream: Optional[TextIO] = None) -> Any:
-        """Run the prompt loop.
-
-        Args:
-            default (Any, optional): Optional default value.
-
-        Returns:
-            PromptType: Processed value.
-        """
-        while True:
-            self.pre_prompt()
-            prompt = self.make_prompt(default)
-            value = self.get_input(self.console, prompt, self.password, stream=stream)
-            if value == "" and default != ...:
-                return default
-            try:
-                return_value = self.process_response(value)
-            except InvalidResponse as error:
-                self.on_validate_error(value, error)
-                continue
-            else:
-                return return_value
-
-
-class Prompt(PromptBase[str]):
-    """A prompt that returns a str.
-
-    Example:
-        >>> name = Prompt.ask("Enter your name")
-
-
-    """
-
-    response_type = str
-
-
-class IntPrompt(PromptBase[int]):
-    """A prompt that returns an integer.
-
-    Example:
-        >>> burrito_count = IntPrompt.ask("How many burritos do you want to order")
-
-    """
-
-    response_type = int
-    validate_error_message = "[prompt.invalid]Please enter a valid integer number"
-
-
-class FloatPrompt(PromptBase[int]):
-    """A prompt that returns a float.
-
-    Example:
-        >>> temperature = FloatPrompt.ask("Enter desired temperature")
-
-    """
-
-    response_type = float
-    validate_error_message = "[prompt.invalid]Please enter a number"
-
-
-class Confirm(PromptBase[bool]):
-    """A yes / no confirmation prompt.
-
-    Example:
-        >>> if Confirm.ask("Continue"):
-                run_job()
-
-    """
-
-    response_type = bool
-    validate_error_message = "[prompt.invalid]Please enter Y or N"
-    choices: List[str] = ["y", "n"]
-
-    def render_default(self, default: DefaultType) -> Text:
-        """Render the default as (y) or (n) rather than True/False."""
-        yes, no = self.choices
-        return Text(f"({yes})" if default else f"({no})", style="prompt.default")
-
-    def process_response(self, value: str) -> bool:
-        """Convert choices to a bool."""
-        value = value.strip().lower()
-        if value not in self.choices:
-            raise InvalidResponse(self.validate_error_message)
-        return value == self.choices[0]
-
-
-if __name__ == "__main__":  # pragma: no cover
-
-    from pip._vendor.rich import print
-
-    if Confirm.ask("Run [i]prompt[/i] tests?", default=True):
-        while True:
-            result = IntPrompt.ask(
-                ":rocket: Enter a number between [b]1[/b] and [b]10[/b]", default=5
-            )
-            if result >= 1 and result <= 10:
-                break
-            print(":pile_of_poo: [prompt.invalid]Number must be between 1 and 10")
-        print(f"number={result}")
-
-        while True:
-            password = Prompt.ask(
-                "Please enter a password [cyan](must be at least 5 characters)",
-                password=True,
-            )
-            if len(password) >= 5:
-                break
-            print("[prompt.invalid]password too short")
-        print(f"password={password!r}")
-
-        fruit = Prompt.ask("Enter a fruit", choices=["apple", "orange", "pear"])
-        print(f"fruit={fruit!r}")
-
-    else:
-        print("[b]OK :loudly_crying_face:")
diff --git a/spaces/CVPR/Dual-Key_Backdoor_Attacks/datagen/detectron2/detectron2/evaluation/evaluator.py b/spaces/CVPR/Dual-Key_Backdoor_Attacks/datagen/detectron2/detectron2/evaluation/evaluator.py
deleted file mode 100644
index d6ce655f529d3346cc76858d39a22d7c23c8c26a..0000000000000000000000000000000000000000
--- a/spaces/CVPR/Dual-Key_Backdoor_Attacks/datagen/detectron2/detectron2/evaluation/evaluator.py
+++ /dev/null
@@ -1,196 +0,0 @@
-# Copyright (c) Facebook, Inc. and its affiliates. All Rights Reserved
-import datetime
-import logging
-import time
-from collections import OrderedDict
-from contextlib import contextmanager
-import torch
-
-from detectron2.utils.comm import get_world_size, is_main_process
-from detectron2.utils.logger import log_every_n_seconds
-
-
-class DatasetEvaluator:
-    """
-    Base class for a dataset evaluator.
-
-    The function :func:`inference_on_dataset` runs the model over
-    all samples in the dataset, and have a DatasetEvaluator to process the inputs/outputs.
-
-    This class will accumulate information of the inputs/outputs (by :meth:`process`),
-    and produce evaluation results in the end (by :meth:`evaluate`).
-    """
-
-    def reset(self):
-        """
-        Preparation for a new round of evaluation.
-        Should be called before starting a round of evaluation.
-        """
-        pass
-
-    def process(self, inputs, outputs):
-        """
-        Process the pair of inputs and outputs.
-        If they contain batches, the pairs can be consumed one-by-one using `zip`:
-
-        .. code-block:: python
-
-            for input_, output in zip(inputs, outputs):
-                # do evaluation on single input/output pair
-                ...
-
-        Args:
-            inputs (list): the inputs that's used to call the model.
-            outputs (list): the return value of `model(inputs)`
-        """
-        pass
-
-    def evaluate(self):
-        """
-        Evaluate/summarize the performance, after processing all input/output pairs.
-
-        Returns:
-            dict:
-                A new evaluator class can return a dict of arbitrary format
-                as long as the user can process the results.
-                In our train_net.py, we expect the following format:
-
-                * key: the name of the task (e.g., bbox)
-                * value: a dict of {metric name: score}, e.g.: {"AP50": 80}
-        """
-        pass
-
-
-class DatasetEvaluators(DatasetEvaluator):
-    """
-    Wrapper class to combine multiple :ref:`DatasetEvaluator` instances.
-
-    This class dispatches every evaluation call to
-    all of its :ref:`DatasetEvaluator`s.
-    """
-
-    def __init__(self, evaluators):
-        """
-        Args:
-            evaluators (list): the evaluators to combine.
-        """
-        super().__init__()
-        self._evaluators = evaluators
-
-    def reset(self):
-        for evaluator in self._evaluators:
-            evaluator.reset()
-
-    def process(self, inputs, outputs):
-        for evaluator in self._evaluators:
-            evaluator.process(inputs, outputs)
-
-    def evaluate(self):
-        results = OrderedDict()
-        for evaluator in self._evaluators:
-            result = evaluator.evaluate()
-            if is_main_process() and result is not None:
-                for k, v in result.items():
-                    assert (
-                        k not in results
-                    ), "Different evaluators produce results with the same key {}".format(k)
-                    results[k] = v
-        return results
-
-
-def inference_on_dataset(model, data_loader, evaluator):
-    """
-    Run model on the data_loader and evaluate the metrics with evaluator.
-    Also benchmark the inference speed of `model.forward` accurately.
-    The model will be used in eval mode.
-
-    Args:
-        model (nn.Module): a module which accepts an object from
-            `data_loader` and returns some outputs. It will be temporarily set to `eval` mode.
-
-            If you wish to evaluate a model in `training` mode instead, you can
-            wrap the given model and override its behavior of `.eval()` and `.train()`.
-        data_loader: an iterable object with a length.
-            The elements it generates will be the inputs to the model.
-        evaluator (DatasetEvaluator): the evaluator to run. Use `None` if you only want
-            to benchmark, but don't want to do any evaluation.
-
-    Returns:
-        The return value of `evaluator.evaluate()`
-    """
-    num_devices = get_world_size()
-    logger = logging.getLogger(__name__)
-    logger.info("Start inference on {} images".format(len(data_loader)))
-
-    total = len(data_loader)  # inference data loader must have a fixed length
-    if evaluator is None:
-        # create a no-op evaluator
-        evaluator = DatasetEvaluators([])
-    evaluator.reset()
-
-    num_warmup = min(5, total - 1)
-    start_time = time.perf_counter()
-    total_compute_time = 0
-    with inference_context(model), torch.no_grad():
-        for idx, inputs in enumerate(data_loader):
-            if idx == num_warmup:
-                start_time = time.perf_counter()
-                total_compute_time = 0
-
-            start_compute_time = time.perf_counter()
-            outputs = model(inputs)
-            if torch.cuda.is_available():
-                torch.cuda.synchronize()
-            total_compute_time += time.perf_counter() - start_compute_time
-            evaluator.process(inputs, outputs)
-
-            iters_after_start = idx + 1 - num_warmup * int(idx >= num_warmup)
-            seconds_per_img = total_compute_time / iters_after_start
-            if idx >= num_warmup * 2 or seconds_per_img > 5:
-                total_seconds_per_img = (time.perf_counter() - start_time) / iters_after_start
-                eta = datetime.timedelta(seconds=int(total_seconds_per_img * (total - idx - 1)))
-                log_every_n_seconds(
-                    logging.INFO,
-                    "Inference done {}/{}. {:.4f} s / img. ETA={}".format(
-                        idx + 1, total, seconds_per_img, str(eta)
-                    ),
-                    n=5,
-                )
-
-    # Measure the time only for this worker (before the synchronization barrier)
-    total_time = time.perf_counter() - start_time
-    total_time_str = str(datetime.timedelta(seconds=total_time))
-    # NOTE this format is parsed by grep
-    logger.info(
-        "Total inference time: {} ({:.6f} s / img per device, on {} devices)".format(
-            total_time_str, total_time / (total - num_warmup), num_devices
-        )
-    )
-    total_compute_time_str = str(datetime.timedelta(seconds=int(total_compute_time)))
-    logger.info(
-        "Total inference pure compute time: {} ({:.6f} s / img per device, on {} devices)".format(
-            total_compute_time_str, total_compute_time / (total - num_warmup), num_devices
-        )
-    )
-
-    results = evaluator.evaluate()
-    # An evaluator may return None when not in main process.
-    # Replace it by an empty dict instead to make it easier for downstream code to handle
-    if results is None:
-        results = {}
-    return results
-
-
-@contextmanager
-def inference_context(model):
-    """
-    A context where the model is temporarily changed to eval mode,
-    and restored to previous mode afterwards.
-
-    Args:
-        model: a torch Module
-    """
-    training_mode = model.training
-    model.eval()
-    yield
-    model.train(training_mode)
diff --git a/spaces/CVPR/LIVE/pydiffvg/__init__.py b/spaces/CVPR/LIVE/pydiffvg/__init__.py
deleted file mode 100644
index 24f3dd14e9a7f2da7b6fa7e731b6fd698fb45821..0000000000000000000000000000000000000000
--- a/spaces/CVPR/LIVE/pydiffvg/__init__.py
+++ /dev/null
@@ -1,9 +0,0 @@
-from .device import *
-from .shape import *
-from .pixel_filter import *
-from .render_pytorch import *
-from .image import *
-from .parse_svg import *
-from .color import *
-from .optimize_svg import *
-from .save_svg import *
\ No newline at end of file
diff --git a/spaces/CVPR/LIVE/thrust/thrust/iterator/iterator_traits.h b/spaces/CVPR/LIVE/thrust/thrust/iterator/iterator_traits.h
deleted file mode 100644
index 5a33658c22bba60783c0b3c5a422a48c7bb2a2f1..0000000000000000000000000000000000000000
--- a/spaces/CVPR/LIVE/thrust/thrust/iterator/iterator_traits.h
+++ /dev/null
@@ -1,114 +0,0 @@
-/*
- *  Copyright 2008-2013 NVIDIA Corporation
- *
- *  Licensed under the Apache License, Version 2.0 (the "License");
- *  you may not use this file except in compliance with the License.
- *  You may obtain a copy of the License at
- *
- *      http://www.apache.org/licenses/LICENSE-2.0
- *
- *  Unless required by applicable law or agreed to in writing, software
- *  distributed under the License is distributed on an "AS IS" BASIS,
- *  WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
- *  See the License for the specific language governing permissions and
- *  limitations under the License.
- */
-
-
-/*! \file thrust/iterator/iterator_traits.h
- *  \brief Traits and metafunctions for reasoning about the traits of iterators
- */
-
-/*
- * (C) Copyright David Abrahams 2003.
- * 
- * Distributed under the Boost Software License, Version 1.0.
- * (See accompanying NOTICE file for the complete license)
- *
- * For more information, see http://www.boost.org
- */
-
-#pragma once
-
-#include <thrust/detail/config.h>
-#include <thrust/type_traits/void_t.h>
-
-#include <iterator>
-
-namespace thrust
-{
-
-namespace detail
-{
-
-template <typename T, typename = void>
-struct iterator_traits_impl {};
-
-template <typename T>
-struct iterator_traits_impl<
-  T
-, typename voider<
-    typename T::difference_type
-  , typename T::value_type
-  , typename T::pointer
-  , typename T::reference
-  , typename T::iterator_category
-  >::type 
->
-{
-  typedef typename T::difference_type difference_type;
-  typedef typename T::value_type value_type;
-  typedef typename T::pointer pointer;
-  typedef typename T::reference reference;
-  typedef typename T::iterator_category iterator_category;
-};
-
-} // namespace detail
-
-/*! \p iterator_traits is a type trait class that provides a uniform
- *  interface for querying the properties of iterators at compile-time.
- */
-template <typename T>
-struct iterator_traits : detail::iterator_traits_impl<T> {};
-
-// traits are specialized for pointer types
-template<typename T>
-  struct iterator_traits<T*>
-{
-  typedef std::ptrdiff_t difference_type;
-  typedef T value_type;
-  typedef T* pointer;
-  typedef T& reference;
-  typedef std::random_access_iterator_tag iterator_category;
-};
-
-template<typename T>
-  struct iterator_traits<const T*>
-{
-  typedef std::ptrdiff_t difference_type;
-  typedef T value_type;
-  typedef const T* pointer;
-  typedef const T& reference;
-  typedef std::random_access_iterator_tag iterator_category;
-}; // end iterator_traits
-
-template<typename Iterator> struct iterator_value;
-
-template<typename Iterator> struct iterator_pointer;
-
-template<typename Iterator> struct iterator_reference;
-
-template<typename Iterator> struct iterator_difference;
-
-template<typename Iterator> struct iterator_traversal;
-
-template<typename Iterator> struct iterator_system;
-
-} // namespace thrust
-
-#include <thrust/iterator/detail/iterator_traversal_tags.h>
-#include <thrust/iterator/detail/host_system_tag.h>
-#include <thrust/iterator/detail/device_system_tag.h>
-#include <thrust/iterator/detail/any_system_tag.h>
-#include <thrust/iterator/detail/iterator_traits.inl>
-
diff --git a/spaces/CVPR/transfiner/configs/common/models/mask_rcnn_c4.py b/spaces/CVPR/transfiner/configs/common/models/mask_rcnn_c4.py
deleted file mode 100644
index a3dcf8be42a39c6e5f6e76e3ab23adeccb33085d..0000000000000000000000000000000000000000
--- a/spaces/CVPR/transfiner/configs/common/models/mask_rcnn_c4.py
+++ /dev/null
@@ -1,88 +0,0 @@
-from detectron2.config import LazyCall as L
-from detectron2.layers import ShapeSpec
-from detectron2.modeling.meta_arch import GeneralizedRCNN
-from detectron2.modeling.anchor_generator import DefaultAnchorGenerator
-from detectron2.modeling.backbone import BasicStem, BottleneckBlock, ResNet
-from detectron2.modeling.box_regression import Box2BoxTransform
-from detectron2.modeling.matcher import Matcher
-from detectron2.modeling.poolers import ROIPooler
-from detectron2.modeling.proposal_generator import RPN, StandardRPNHead
-from detectron2.modeling.roi_heads import (
-    FastRCNNOutputLayers,
-    MaskRCNNConvUpsampleHead,
-    Res5ROIHeads,
-)
-
-model = L(GeneralizedRCNN)(
-    backbone=L(ResNet)(
-        stem=L(BasicStem)(in_channels=3, out_channels=64, norm="FrozenBN"),
-        stages=L(ResNet.make_default_stages)(
-            depth=50,
-            stride_in_1x1=True,
-            norm="FrozenBN",
-        ),
-        out_features=["res4"],
-    ),
-    proposal_generator=L(RPN)(
-        in_features=["res4"],
-        head=L(StandardRPNHead)(in_channels=1024, num_anchors=15),
-        anchor_generator=L(DefaultAnchorGenerator)(
-            sizes=[[32, 64, 128, 256, 512]],
-            aspect_ratios=[0.5, 1.0, 2.0],
-            strides=[16],
-            offset=0.0,
-        ),
-        anchor_matcher=L(Matcher)(
-            thresholds=[0.3, 0.7], labels=[0, -1, 1], allow_low_quality_matches=True
-        ),
-        box2box_transform=L(Box2BoxTransform)(weights=[1.0, 1.0, 1.0, 1.0]),
-        batch_size_per_image=256,
-        positive_fraction=0.5,
-        pre_nms_topk=(12000, 6000),
-        post_nms_topk=(2000, 1000),
-        nms_thresh=0.7,
-    ),
-    roi_heads=L(Res5ROIHeads)(
-        num_classes=80,
-        batch_size_per_image=512,
-        positive_fraction=0.25,
-        proposal_matcher=L(Matcher)(
-            thresholds=[0.5], labels=[0, 1], allow_low_quality_matches=False
-        ),
-        in_features=["res4"],
-        pooler=L(ROIPooler)(
-            output_size=14,
-            scales=(1.0 / 16,),
-            sampling_ratio=0,
-            pooler_type="ROIAlignV2",
-        ),
-        res5=L(ResNet.make_stage)(
-            block_class=BottleneckBlock,
-            num_blocks=3,
-            stride_per_block=[2, 1, 1],
-            in_channels=1024,
-            bottleneck_channels=512,
-            out_channels=2048,
-            norm="FrozenBN",
-            stride_in_1x1=True,
-        ),
-        box_predictor=L(FastRCNNOutputLayers)(
-            input_shape=L(ShapeSpec)(channels="${...res5.out_channels}", height=1, width=1),
-            test_score_thresh=0.05,
-            box2box_transform=L(Box2BoxTransform)(weights=(10, 10, 5, 5)),
-            num_classes="${..num_classes}",
-        ),
-        mask_head=L(MaskRCNNConvUpsampleHead)(
-            input_shape=L(ShapeSpec)(
-                channels="${...res5.out_channels}",
-                width="${...pooler.output_size}",
-                height="${...pooler.output_size}",
-            ),
-            num_classes="${..num_classes}",
-            conv_dims=[256],
-        ),
-    ),
-    pixel_mean=[103.530, 116.280, 123.675],
-    pixel_std=[1.0, 1.0, 1.0],
-    input_format="BGR",
-)
diff --git a/spaces/ChanceFocus/FLARE/app.py b/spaces/ChanceFocus/FLARE/app.py
deleted file mode 100644
index 97af741db65a18d909d6eff253f55021e5890fde..0000000000000000000000000000000000000000
--- a/spaces/ChanceFocus/FLARE/app.py
+++ /dev/null
@@ -1,309 +0,0 @@
-import pandas as pd
-import numpy as np
-import matplotlib
-# matplotlib.use('macosx')
-import gradio as gr
-import matplotlib.pyplot as plt
-import plotly.graph_objects as go
-from apscheduler.schedulers.background import BackgroundScheduler
-
-ENG_COLS = [
-    ("Model", "str"),
-    ("FPB-acc", "number"),
-    ("FPB-F1", "number"),
-    ("FPB-missing", "number"),
-    ("FiQA-SA-F1", "number"),
-    ("FiQA-SA-missing", "number"),
-    ("Headline-AvgF1", "number"),
-    ("NER-EntityF1", "number"),
-    ("ConvFinQA-EmAcc", "number"),
-    ("FinQA-EmAcc", "number"),
-    ("BigData22-Acc", "number"),
-    ("BigData22-MCC", "number"),
-    ("BigData22-missing", "number"),
-    ("ACL18-Acc", "number"),
-    ("ACL18-MCC", "number"),
-    ("ACL18-missing", "number"),
-    ("CIKM18-Acc", "number"),
-    ("CIKM18-MCC", "number"),
-    ("CIKM18-missing", "number"),
-    ("FOMC-acc", "number"),
-    ("FOMC-F1", "number"),
-    ("FOMC-missing", "number"),
-    ("FinerOrd-EntityF1", "number"),
-    ("FinerOrd-F1", "number"),
-    ("German-Acc", "number"),
-    ("German-MCC", "number"),
-    ("German-missing", "number"),
-    ("Australian-Acc", "number"),
-    ("Australian-MCC", "number"),
-    ("Australian-missing", "number"),
-    ("TSA-RMSE", "number"),
-    ("TSA-missing", "number"),
-    ("MLESG-F1", "number"),
-    ("MLESG-missing", "number"),
-    ("FSRL-entity-F1", "number"),
-    ("FSRL-F1", "number"),
-    ("CFA-acc", "number"),
-    ("CFA-F1", "number"),
-    ("CFA-missing", "number"),
-    ("Finarg-ECCAUC-F1", "number"),
-    ("Finarg-ECCAUC-missing", "number"),
-    ("Finarg-ECCARC-F1", "number"),
-    ("Finarg_ECCARC-missing", "number"),
-    ("CD-Entity-F1", "number"),
-    ("CD-F1", "number"),
-    ("MultiFin-EN-acc", "number"),
-    ("MultiFin-EN-F1", "number"),
-    ("MultiFin-EN-missing", "number"),
-    ("MA-acc", "number"),
-    ("MA-F1", "number"),
-    ("MA-missing", "number"),
-    ("Causal20-sc-acc", "number"),
-    ("Causal20-sc-F1", "number"),
-    ("Causal20-sc-missing", "number"),
-    ("TATQA-EmAcc", "number"),
-    ("FNXL-entity-F1", "number"),
-    ("FNXL-F1", "number"),
-    ("FinRED-precision", "number"),
-    ("FinRED-recall", "number"),
-    ("FinRED-F1", "number"),
-    ("ECTSUM-Rouge1", "number"),
-    ("ECTSUM-Rouge2", "number"),
-    ("ECTSUM-RougeL", "number"),
-    ("ECTSUM-BertScore", "number"),
-    ("ECTSUM-BARTScore", "number"),
-    ("EDTSUM-Rouge1", "number"),
-    ("EDTSUM-Rouge2", "number"),
-    ("EDTSUM-RougeL", "number"),
-    ("EDTSUM-BertScore", "number"),
-    ("EDTSUM-BARTScore", "number"),
-]
-
-SPA_COLS = [
-    ("Model", "str"),
-    ("MultiFin-F1", "number"),
-    ("MultiFin-Acc", "number"),
-    ("FNS-Rouge1", "number"),
-    ("FNS-Rouge2", "number"),
-    ("FNS-RougeL", "number"),
-    ("EFP-F1", "number"),
-    ("EFP-Acc", "number"),
-    ("EFPA-F1", "number"),
-    ("EFPA-Acc", "number"),
-    ("TSA-F1", "number"),
-    ("TSA-Acc", "number"),
-    ("FinanceES-F1", "number"),
-    ("FinanceES-Acc", "number"),
-]
-
-CHI_COLS = [
-    ("Model", "str"),
-    ("AFQMC-Acc", "number"),
-    ("AFQMC-F1", "number"),
-    ("corpus-Acc", "number"),
-    ("corpus-F1", "number"),
-    ("stockA-Acc", "number"),
-    ("stockA-F1", "number"),
-    ("Fineval-Acc", "number"),
-    ("Fineval-F1", "number"),
-    ("NL-Acc", "number"),
-    ("NL-F1", "number"),
-    ("NL2-Acc", "number"),
-    ("NL2-F1", "number"),
-    ("NSP-Acc", "number"),
-    ("NSP-F1", "number"),
-    ("RE-Acc", "number"),
-    ("RE-F1", "number"),
-    ("FE-Acc", "number"),
-    ("FE-F1", "number"),
-    ("stockB-Acc", "number"),
-    ("stockB-F1", "number"),
-    ("19CCKS-Precision", "number"),
-    ("19CCKS-F1", "number"),
-    ("20CCKS-Precision", "number"),
-    ("20CCKS-F1", "number"),
-    ("21CCKS-Precision", "number"),
-    ("21CCKS-F1", "number"),
-    ("22CCKS-Precision", "number"),
-    ("22CCKS-F1", "number"),
-    ("QA-Acc", "number"),
-    ("NA-Rouge1", "number"),
-    ("NA-Rouge2", "number"),
-    ("NA-RougeL", "number"),
-    ("NER-EntityF1", "number"),
-]
-
-
-# Extract column names
-eng_cols = [col_name for col_name, _ in ENG_COLS]
-eng_cates = {
-    "Sentiment Analysis": ["Model", "FPB-acc", "FPB-F1", "FPB-missing",
-        "FiQA-SA-F1", "FiQA-SA-missing", "Headline-AvgF1", "TSA-RMSE",
-        "TSA-missing", "FOMC-acc", "FOMC-F1", "FOMC-missing"],
-    "NER": ["Model", "NER-EntityF1", "FinerOrd-EntityF1", "FinerOrd-F1"],
-    "Number Understanding": ["Model", "FinQA-EmAcc", "ConvFinQA-EmAcc"],
-    "Text Summarization": ["Model", "ECTSUM-Rouge1", "ECTSUM-Rouge2",
-        "ECTSUM-RougeL", "ECTSUM-BertScore", "ECTSUM-BARTScore",
-        "EDTSUM-Rouge1", "EDTSUM-Rouge2", "EDTSUM-RougeL", "EDTSUM-BertScore", "EDTSUM-BARTScore",],
-    "Stock Movement Prediction": ["Model", "BigData22-Acc",
-        "BigData22-MCC", "BigData22-missing", "ACL18-Acc", "ACL18-MCC",
-        "ACL18-missing", "CIKM18-Acc", "CIKM18-MCC", "CIKM18-missing", ],
-    "Credit Scoring": ["Model", "German-Acc", "German-MCC",
-        "German-missing", "Australian-Acc", "Australian-MCC", "Australian-missing"],
-}
-
-spa_cols = [col_name for col_name, _ in SPA_COLS]
-spa_cates = {
-    "Sentiment Analysis": ["Model", "TSA-Acc", "TSA-F1", "FinanceES-Acc", "FinanceES-F1"],
-    "Examination": ["Model", "EFP-Acc", "EFP-F1", "EFPA-Acc", "EFPA-F1"],
-    "Classification": ["Model", "MultiFin-Acc", "MultiFin-F1"],
-    "Text Summarization": ["Model", "FNS-Rouge1", "FNS-Rouge2", "FNS-RougeL",],
-}
-
-chi_cols = [col_name for col_name, _ in CHI_COLS]
-chi_cates = {
-    "Semantic matching": ["Model", "AFQMC-Acc", "AFQMC-F1", "corpus-Acc", "corpus-F1"],
-    "Classification": ["Model", "NL-Acc", "NL-F1","NL2-Acc", "NL2-F1","NSP-Acc", "NSP-F1"],
-    "Stock Movement Prediction": ["Model", "stockA-Acc", "stockA-F1"],
-    "Examination": ["Model", "Fineval-Acc", "Fineval-F1"],
-    "Relation Extraction": ["Model", "RE-Acc", "RE-F1", "19CCKS-Precision", "19CCKS-F1", "20CCKS-Precision", "20CCKS-F1", "21CCKS-Precision", "21CCKS-F1", "22CCKS-Precision", "22CCKS-F1"],
-    "Sentiment Analysis": ["Model", "FE-Acc", "FE-F1", "stockB-Acc", "stockB-F1"],
-    "NER": ["Model", "NER-EntityF1"],
-    "Text Summarization": ["Model", "NA-Rouge1", "NA-Rouge2", "NA-RougeL"],
-    "Question Answering": ["Model", "QA-Acc"],
-}
-
-def create_df_dict(lang, lang_cols, cates):
-    # Load leaderboard data with column names
-    leaderboard_df = pd.read_csv(f'{lang}_result.csv', names=lang_cols)
-    leaderboard_df = leaderboard_df.sort_index(axis=1)
-    # Move 'key' column to the front
-    leaderboard_df = leaderboard_df[ ['Model'] + [ col for col in leaderboard_df.columns if col != 'Model' ] ]
-    cols = leaderboard_df.columns
-    types = ["str"] + ["number"] * (len(lang_cols)-1)
-
-    # Split merged_df into subtask dataframes
-    df_dict = {}
-    for key, selected_columns in cates.items():
-        df_dict[key] = leaderboard_df[selected_columns]
-    return df_dict
-
-df_lang = {
-    "English": create_df_dict("english", eng_cols, eng_cates),
-    "Spanish": create_df_dict("spanish", spa_cols, spa_cates),
-    "Chinese": create_df_dict("chinese", chi_cols, chi_cates),
-}
-
-
-# Constants
-TITLE = '<h1 align="center" id="space-title">🐲 PIXIU FLARE Leaderboard</h1>'
-# TITLE = "Financial Natural Language Understanding and Prediction Evaluation Benchmark (FLARE) Leaderboard"
-INTRODUCTION_TEXT = """📊 The PIXIU FLARE Leaderboard is designed to rigorously track, rank, and evaluate state-of-the-art models in financial Natural Language Understanding and Prediction. 
-
-📈 Unique to FLARE, our leaderboard not only covers standard NLP tasks but also incorporates financial prediction tasks such as stock movement and credit scoring, offering a more comprehensive evaluation for real-world financial applications.
-
-📚 Our evaluation metrics include, but are not limited to, Accuracy, F1 Score, ROUGE score, BERTScore, and Matthews correlation coefficient (MCC), providing a multidimensional assessment of model performance.
-
-🔗 For more details, refer to our GitHub page [here](https://github.com/ChanceFocus/PIXIU).
-"""
-
-
-def create_data_interface(df):
-    headers = df.columns
-    types = ["str"] + ["number"] * (len(headers) - 1)
-
-    return gr.components.Dataframe(
-        value=df.values.tolist(),
-        headers=[col_name for col_name in headers],
-        datatype=types,
-        max_rows=10,
-    )
-
-def plot_radar_chart(df, attributes, category_name):
-    fig = go.Figure()
-
-    for index, row in df.iterrows():
-        model = row['Model']
-        values = row[attributes].tolist()
-        fig.add_trace(go.Scatterpolar(
-            r=values,
-            theta=attributes,
-            fill='toself',
-            name=model
-        ))
-
-    fig.update_layout(
-        title="FLARE",
-        polar=dict(
-            radialaxis=dict(
-                visible=True,
-                range=[0, 0.9]
-            )),
-        showlegend=True
-    )
-
-    return fig
-
-def create_data_interface_for_aggregated(df, category_name):
-    attributes = df.columns[1:]
-    print (attributes)
-    plt = plot_radar_chart(df, attributes, category_name)
-    return plt
-
-def create_lang_leaderboard(df_dict):
-    new_df = pd.DataFrame()
-    for key, df in df_dict.items():
-        new_df["Model"] = df["Model"]
-        tdf = df.replace('', 0)
-        tdf = tdf[[val for val in tdf.columns if "Model" not in val]]
-        if key == "Sentiment Analysis":
-            tdf = tdf[[val for val in tdf.columns if "F1" in val]]
-        elif key == "Classification":
-            tdf = tdf[[val for val in tdf.columns if "F1" in val]]
-        elif key == "Examination":
-            tdf = tdf[[val for val in tdf.columns if "F1" in val]]
-        elif key == "Stock Movement Prediction":
-            tdf = tdf[[val for val in tdf.columns if "Acc" in val]]
-        elif key == "Credit Scoring":
-            tdf = tdf[[val for val in tdf.columns if "Acc" in val]]
-        elif key == "Text Summarization":
-            tdf = tdf[[val for val in tdf.columns if "Bert" in val or "Rouge" in val]]
-        elif key == "Semantic matching":
-            tdf = tdf[[val for val in tdf.columns if "Acc" in val]]
-        elif key == "Relation Extraction":
-            tdf = tdf[[val for val in tdf.columns if "Acc" in val]]
-        elif key == "Q&A":
-            tdf = tdf[[val for val in tdf.columns if "Acc" in val]]
-        elif key == "NER":
-            tdf = tdf[[val for val in tdf.columns if "EntityF1" in val]]
-        print ("tdf")
-        print (tdf)
-        new_df[key] = tdf.values.mean(axis=1)
-    print (new_df.values)
-
-    plot = create_data_interface_for_aggregated(new_df, key)
-    gr.Plot(plot)
-
-    for key, df in df_dict.items():
-        with gr.Tab(key):
-            create_data_interface(df)
-
-def launch_gradio():
-    demo = gr.Blocks()
-
-    with demo:
-        gr.HTML(TITLE)
-        gr.Markdown(INTRODUCTION_TEXT, elem_classes="markdown-text")
-        for key, df_dict in df_lang.items():
-            with gr.Tab(key):
-                create_lang_leaderboard(df_dict)
-        
-    demo.launch()
-
-scheduler = BackgroundScheduler()
-scheduler.add_job(launch_gradio, "interval", seconds=3600)
-scheduler.start()
-
-# Launch immediately
-launch_gradio()
diff --git a/spaces/ChandraMohanNayal/AutoGPT/autogpt/memory/redismem.py b/spaces/ChandraMohanNayal/AutoGPT/autogpt/memory/redismem.py
deleted file mode 100644
index 082a812c5362cc9f19e35bf1bb10269b558f7724..0000000000000000000000000000000000000000
--- a/spaces/ChandraMohanNayal/AutoGPT/autogpt/memory/redismem.py
+++ /dev/null
@@ -1,156 +0,0 @@
-"""Redis memory provider."""
-from __future__ import annotations
-
-from typing import Any
-
-import numpy as np
-import redis
-from colorama import Fore, Style
-from redis.commands.search.field import TextField, VectorField
-from redis.commands.search.indexDefinition import IndexDefinition, IndexType
-from redis.commands.search.query import Query
-
-from autogpt.llm_utils import create_embedding_with_ada
-from autogpt.logs import logger
-from autogpt.memory.base import MemoryProviderSingleton
-
-SCHEMA = [
-    TextField("data"),
-    VectorField(
-        "embedding",
-        "HNSW",
-        {"TYPE": "FLOAT32", "DIM": 1536, "DISTANCE_METRIC": "COSINE"},
-    ),
-]
-
-
-class RedisMemory(MemoryProviderSingleton):
-    def __init__(self, cfg):
-        """
-        Initializes the Redis memory provider.
-
-        Args:
-            cfg: The config object.
-
-        Returns: None
-        """
-        redis_host = cfg.redis_host
-        redis_port = cfg.redis_port
-        redis_password = cfg.redis_password
-        self.dimension = 1536
-        self.redis = redis.Redis(
-            host=redis_host,
-            port=redis_port,
-            password=redis_password,
-            db=0,  # Cannot be changed
-        )
-        self.cfg = cfg
-
-        # Check redis connection
-        try:
-            self.redis.ping()
-        except redis.ConnectionError as e:
-            logger.typewriter_log(
-                "FAILED TO CONNECT TO REDIS",
-                Fore.RED,
-                Style.BRIGHT + str(e) + Style.RESET_ALL,
-            )
-            logger.double_check(
-                "Please ensure you have setup and configured Redis properly for use. "
-                + f"You can check out {Fore.CYAN + Style.BRIGHT}"
-                f"https://github.com/Torantulino/Auto-GPT#redis-setup{Style.RESET_ALL}"
-                " to ensure you've set up everything correctly."
-            )
-            exit(1)
-
-        if cfg.wipe_redis_on_start:
-            self.redis.flushall()
-        try:
-            self.redis.ft(f"{cfg.memory_index}").create_index(
-                fields=SCHEMA,
-                definition=IndexDefinition(
-                    prefix=[f"{cfg.memory_index}:"], index_type=IndexType.HASH
-                ),
-            )
-        except Exception as e:
-            print("Error creating Redis search index: ", e)
-        existing_vec_num = self.redis.get(f"{cfg.memory_index}-vec_num")
-        self.vec_num = int(existing_vec_num.decode("utf-8")) if existing_vec_num else 0
-
-    def add(self, data: str) -> str:
-        """
-        Adds a data point to the memory.
-
-        Args:
-            data: The data to add.
-
-        Returns: Message indicating that the data has been added.
-        """
-        if "Command Error:" in data:
-            return ""
-        vector = create_embedding_with_ada(data)
-        vector = np.array(vector).astype(np.float32).tobytes()
-        data_dict = {b"data": data, "embedding": vector}
-        pipe = self.redis.pipeline()
-        pipe.hset(f"{self.cfg.memory_index}:{self.vec_num}", mapping=data_dict)
-        _text = (
-            f"Inserting data into memory at index: {self.vec_num}:\n" f"data: {data}"
-        )
-        self.vec_num += 1
-        pipe.set(f"{self.cfg.memory_index}-vec_num", self.vec_num)
-        pipe.execute()
-        return _text
-
-    def get(self, data: str) -> list[Any] | None:
-        """
-        Gets the data from the memory that is most relevant to the given data.
-
-        Args:
-            data: The data to compare to.
-
-        Returns: The most relevant data.
-        """
-        return self.get_relevant(data, 1)
-
-    def clear(self) -> str:
-        """
-        Clears the redis server.
-
-        Returns: A message indicating that the memory has been cleared.
-        """
-        self.redis.flushall()
-        return "Obliviated"
-
-    def get_relevant(self, data: str, num_relevant: int = 5) -> list[Any] | None:
-        """
-        Returns all the data in the memory that is relevant to the given data.
-        Args:
-            data: The data to compare to.
-            num_relevant: The number of relevant data to return.
-
-        Returns: A list of the most relevant data.
-        """
-        query_embedding = create_embedding_with_ada(data)
-        base_query = f"*=>[KNN {num_relevant} @embedding $vector AS vector_score]"
-        query = (
-            Query(base_query)
-            .return_fields("data", "vector_score")
-            .sort_by("vector_score")
-            .dialect(2)
-        )
-        query_vector = np.array(query_embedding).astype(np.float32).tobytes()
-
-        try:
-            results = self.redis.ft(f"{self.cfg.memory_index}").search(
-                query, query_params={"vector": query_vector}
-            )
-        except Exception as e:
-            print("Error calling Redis search: ", e)
-            return None
-        return [result.data for result in results.docs]
-
-    def get_stats(self):
-        """
-        Returns: The stats of the memory index.
-        """
-        return self.redis.ft(f"{self.cfg.memory_index}").info()
diff --git a/spaces/Cropinky/hana_hanak_houses/realesrgan/archs/__init__.py b/spaces/Cropinky/hana_hanak_houses/realesrgan/archs/__init__.py
deleted file mode 100644
index f3fbbf3b78e33b61fd4c33a564a9a617010d90de..0000000000000000000000000000000000000000
--- a/spaces/Cropinky/hana_hanak_houses/realesrgan/archs/__init__.py
+++ /dev/null
@@ -1,10 +0,0 @@
-import importlib
-from basicsr.utils import scandir
-from os import path as osp
-
-# automatically scan and import arch modules for registry
-# scan all the files that end with '_arch.py' under the archs folder
-arch_folder = osp.dirname(osp.abspath(__file__))
-arch_filenames = [osp.splitext(osp.basename(v))[0] for v in scandir(arch_folder) if v.endswith('_arch.py')]
-# import all the arch modules
-_arch_modules = [importlib.import_module(f'realesrgan.archs.{file_name}') for file_name in arch_filenames]
diff --git a/spaces/DQChoi/gpt-demo/venv/lib/python3.11/site-packages/aiofiles/threadpool/text.py b/spaces/DQChoi/gpt-demo/venv/lib/python3.11/site-packages/aiofiles/threadpool/text.py
deleted file mode 100644
index 1323009ac25f10cfa6908318e0fcb387f85fb99c..0000000000000000000000000000000000000000
--- a/spaces/DQChoi/gpt-demo/venv/lib/python3.11/site-packages/aiofiles/threadpool/text.py
+++ /dev/null
@@ -1,68 +0,0 @@
-from ..base import AsyncBase, AsyncIndirectBase
-from .utils import (
-    delegate_to_executor,
-    proxy_method_directly,
-    proxy_property_directly,
-)
-
-
-@delegate_to_executor(
-    "close",
-    "flush",
-    "isatty",
-    "read",
-    "readable",
-    "readline",
-    "readlines",
-    "seek",
-    "seekable",
-    "tell",
-    "truncate",
-    "write",
-    "writable",
-    "writelines",
-)
-@proxy_method_directly("detach", "fileno", "readable")
-@proxy_property_directly(
-    "buffer",
-    "closed",
-    "encoding",
-    "errors",
-    "line_buffering",
-    "newlines",
-    "name",
-    "mode",
-)
-class AsyncTextIOWrapper(AsyncBase):
-    """The asyncio executor version of io.TextIOWrapper."""
-
-
-@delegate_to_executor(
-    "close",
-    "flush",
-    "isatty",
-    "read",
-    "readable",
-    "readline",
-    "readlines",
-    "seek",
-    "seekable",
-    "tell",
-    "truncate",
-    "write",
-    "writable",
-    "writelines",
-)
-@proxy_method_directly("detach", "fileno", "readable")
-@proxy_property_directly(
-    "buffer",
-    "closed",
-    "encoding",
-    "errors",
-    "line_buffering",
-    "newlines",
-    "name",
-    "mode",
-)
-class AsyncTextIndirectIOWrapper(AsyncIndirectBase):
-    """The indirect asyncio executor version of io.TextIOWrapper."""
diff --git a/spaces/DQChoi/gpt-demo/venv/lib/python3.11/site-packages/fontTools/pens/wxPen.py b/spaces/DQChoi/gpt-demo/venv/lib/python3.11/site-packages/fontTools/pens/wxPen.py
deleted file mode 100644
index c790641a23c0950d492df2082b7a9b6a9d53cb53..0000000000000000000000000000000000000000
--- a/spaces/DQChoi/gpt-demo/venv/lib/python3.11/site-packages/fontTools/pens/wxPen.py
+++ /dev/null
@@ -1,29 +0,0 @@
-from fontTools.pens.basePen import BasePen
-
-
-__all__ = ["WxPen"]
-
-
-class WxPen(BasePen):
-    def __init__(self, glyphSet, path=None):
-        BasePen.__init__(self, glyphSet)
-        if path is None:
-            import wx
-
-            path = wx.GraphicsRenderer.GetDefaultRenderer().CreatePath()
-        self.path = path
-
-    def _moveTo(self, p):
-        self.path.MoveToPoint(*p)
-
-    def _lineTo(self, p):
-        self.path.AddLineToPoint(*p)
-
-    def _curveToOne(self, p1, p2, p3):
-        self.path.AddCurveToPoint(*p1 + p2 + p3)
-
-    def _qCurveToOne(self, p1, p2):
-        self.path.AddQuadCurveToPoint(*p1 + p2)
-
-    def _closePath(self):
-        self.path.CloseSubpath()
diff --git a/spaces/DQChoi/gpt-demo/venv/lib/python3.11/site-packages/fontTools/ttLib/tables/T_S_I__2.py b/spaces/DQChoi/gpt-demo/venv/lib/python3.11/site-packages/fontTools/ttLib/tables/T_S_I__2.py
deleted file mode 100644
index 43a17f6f1ffa82cd803a44ab61832c99259c9ea9..0000000000000000000000000000000000000000
--- a/spaces/DQChoi/gpt-demo/venv/lib/python3.11/site-packages/fontTools/ttLib/tables/T_S_I__2.py
+++ /dev/null
@@ -1,15 +0,0 @@
-""" TSI{0,1,2,3,5} are private tables used by Microsoft Visual TrueType (VTT)
-tool to store its hinting source data.
-
-TSI2 is the index table containing the lengths and offsets for the glyph
-programs that are contained in the TSI3 table. It uses the same format as
-the TSI0 table.
-"""
-from fontTools import ttLib
-
-superclass = ttLib.getTableClass("TSI0")
-
-
-class table_T_S_I__2(superclass):
-
-    dependencies = ["TSI3"]
diff --git a/spaces/Daimon/translation_demo/README.md b/spaces/Daimon/translation_demo/README.md
deleted file mode 100644
index 602bdb6c0c28aa62c6623a15ced47c4b7cd2155f..0000000000000000000000000000000000000000
--- a/spaces/Daimon/translation_demo/README.md
+++ /dev/null
@@ -1,13 +0,0 @@
----
-title: Translation Demo
-emoji: 👀
-colorFrom: indigo
-colorTo: gray
-sdk: streamlit
-sdk_version: 1.17.0
-app_file: app.py
-pinned: false
-license: afl-3.0
----
-
-Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
\ No newline at end of file
diff --git a/spaces/Dana19/outfit_color_guide/app.py b/spaces/Dana19/outfit_color_guide/app.py
deleted file mode 100644
index fbd23a68c7c796a8c109e7f61c0bebaca2c1069e..0000000000000000000000000000000000000000
--- a/spaces/Dana19/outfit_color_guide/app.py
+++ /dev/null
@@ -1,38 +0,0 @@
-from fastai.vision.all import *
-import fastai
-import streamlit as st
-
-st.header("Outfit Color Guide")
-
-learn = load_learner('export.pkl')
-labels = learn.dls.vocab
-
-col1, col2 = st.columns([3,3])
-
-def predict(img):
-  img = PILImage.create(img)
-  pred, pred_idx, probs = learn.predict(img)
-  highest_prob = probs.argmax()
-  file_name = f"{labels[highest_prob].split(' ')[0]}_sugg.png"
-  img_sugg = PILImage.create(file_name)
-  return f'Is this {labels[highest_prob]}?', img_sugg
-
-with col1:
-  st.subheader("Take a photo of your outfit or upload the photo.")
-  st.write("Please stay in natural light or any light reflecting the original color of your outfit.")
-  camera = st.camera_input("Take a picture")
-  upload  = st.file_uploader("Upload a photo of your outfit")
-
-with col2:
-  if camera or upload:
-     if camera:
-        img = camera
-     if upload:
-        img = upload
-  
-     st.image(img, width = 400)
-     result, sugg = predict(img)      
-     st.subheader(result)
-     st.subheader('Pair your outfit with these colors.')
-     st.image(sugg, width = 400)
-
diff --git a/spaces/DataSage/Book_Recommend/README.md b/spaces/DataSage/Book_Recommend/README.md
deleted file mode 100644
index f9291769109ea5b7dbc5483d2a2dcb1482b7f959..0000000000000000000000000000000000000000
--- a/spaces/DataSage/Book_Recommend/README.md
+++ /dev/null
@@ -1,13 +0,0 @@
----
-title: Book Recommend
-emoji: 🏃
-colorFrom: yellow
-colorTo: red
-sdk: gradio
-sdk_version: 3.29.0
-app_file: app.py
-pinned: false
-license: apache-2.0
----
-
-Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
diff --git a/spaces/DragGan/DragGan-Inversion/PTI/utils/models_utils.py b/spaces/DragGan/DragGan-Inversion/PTI/utils/models_utils.py
deleted file mode 100644
index 836151dcc405d62fa435a3cc3b3a0bd3472eeb03..0000000000000000000000000000000000000000
--- a/spaces/DragGan/DragGan-Inversion/PTI/utils/models_utils.py
+++ /dev/null
@@ -1,25 +0,0 @@
-import pickle
-import functools
-import torch
-from PTI.configs import paths_config, global_config
-
-
-def toogle_grad(model, flag=True):
-    for p in model.parameters():
-        p.requires_grad = flag
-
-
-def load_tuned_G(run_id, type):
-    new_G_path = f'{paths_config.checkpoints_dir}/model_{run_id}_{type}.pt'
-    with open(new_G_path, 'rb') as f:
-        new_G = torch.load(f).to(global_config.device).eval()
-    new_G = new_G.float()
-    toogle_grad(new_G, False)
-    return new_G
-
-
-def load_old_G():
-    with open(paths_config.stylegan2_ada_ffhq, 'rb') as f:
-        old_G = pickle.load(f)['G_ema'].to(global_config.device).eval()
-        old_G = old_G.float()
-    return old_G
diff --git a/spaces/DragGan/DragGan/stylegan_human/utils/models_utils.py b/spaces/DragGan/DragGan/stylegan_human/utils/models_utils.py
deleted file mode 100644
index 53b2c3fa9d7035364dd34384fcdab78c1ae5c6af..0000000000000000000000000000000000000000
--- a/spaces/DragGan/DragGan/stylegan_human/utils/models_utils.py
+++ /dev/null
@@ -1,28 +0,0 @@
-# Copyright (c) SenseTime Research. All rights reserved.
-
-
-import pickle
-import functools
-import torch
-from pti.pti_configs import paths_config, global_config
-
-
-def toogle_grad(model, flag=True):
-    for p in model.parameters():
-        p.requires_grad = flag
-
-
-def load_tuned_G(run_id, type):
-    new_G_path = f'{paths_config.checkpoints_dir}/model_{run_id}_{type}.pt'
-    with open(new_G_path, 'rb') as f:
-        new_G = torch.load(f).to(global_config.device).eval()
-    new_G = new_G.float()
-    toogle_grad(new_G, False)
-    return new_G
-
-
-def load_old_G():
-    with open(paths_config.stylegan2_ada_shhq, 'rb') as f:
-        old_G = pickle.load(f)['G_ema'].to(global_config.device).eval()
-        old_G = old_G.float()
-    return old_G
diff --git a/spaces/Dragonnnext/Drago-Proxy/README.md b/spaces/Dragonnnext/Drago-Proxy/README.md
deleted file mode 100644
index 9eb4a7457c03ea6b1c2e909cebbf5bd268541676..0000000000000000000000000000000000000000
--- a/spaces/Dragonnnext/Drago-Proxy/README.md
+++ /dev/null
@@ -1,10 +0,0 @@
----
-title: Drago OAI Proxy
-emoji: 🐲
-colorFrom: green
-colorTo: red
-sdk: docker
-pinned: false
----
-Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference 
-
diff --git a/spaces/Dusan/clickbaitonator/fudge/predict_formality.py b/spaces/Dusan/clickbaitonator/fudge/predict_formality.py
deleted file mode 100644
index 5cd409262ce2880724ab7d8c736fa985a1eefc28..0000000000000000000000000000000000000000
--- a/spaces/Dusan/clickbaitonator/fudge/predict_formality.py
+++ /dev/null
@@ -1,404 +0,0 @@
-import os
-import random
-import time
-import pickle
-import math
-from argparse import ArgumentParser
-
-from typing import Iterable, List, Optional, Tuple
-
-from tqdm import tqdm
-import numpy as np
-import torch
-import torch.nn as nn
-import torch.nn.functional as F
-from transformers import AutoTokenizer, AutoModelWithLMHead, pipeline, set_seed, GPT2Tokenizer, GPT2Model, MarianTokenizer, MarianMTModel
-from torch import Tensor
-
-from data import Dataset
-from model import Model
-from util import save_checkpoint, ProgressMeter, AverageMeter, num_params
-from constants import *
-
-def main(args):
-    with open(args.dataset_info, 'rb') as rf:
-        dataset_info = pickle.load(rf)
-    tokenizer = MarianTokenizer.from_pretrained(args.model_string)
-    tokenizer.add_special_tokens({'pad_token': PAD_TOKEN})
-    pad_id = tokenizer.encode(PAD_TOKEN)[0]
-    model = MarianMTModel.from_pretrained(args.model_string, return_dict=True).to(args.device)
-    model.eval()
-
-    checkpoint = torch.load(args.ckpt, map_location=args.device)
-    model_args = checkpoint['args']
-    conditioning_model = Model(model_args, pad_id, len(dataset_info.index2word)) # no need to get the glove embeddings when reloading since they're saved in model ckpt anyway
-    conditioning_model.load_state_dict(checkpoint['state_dict'])
-    conditioning_model = conditioning_model.to(args.device)
-    conditioning_model.eval()
-    print("=> loaded checkpoint '{}' (epoch {})"
-            .format(args.ckpt, checkpoint['epoch']))
-    print('num params', num_params(conditioning_model))
-
-    while True:
-        results = predict_formality(model, 
-                        tokenizer, 
-                        conditioning_model, 
-                        [args.input_text], 
-                        dataset_info, 
-                        precondition_topk=args.precondition_topk,
-                        do_sample=args.do_sample,
-                        length_cutoff=args.length_cutoff,
-                        condition_lambda=args.condition_lambda,
-                        device=args.device)
-        print(results)
-        import pdb; pdb.set_trace()
-
-
-def predict_formality(model, tokenizer, conditioning_model, input_text, dataset_info, precondition_topk=200, do_sample=False, length_cutoff=512, condition_lambda=1.0, device='cuda'):
-    with torch.no_grad():
-        batch_size = len(input_text)
-
-        # assumes initially all same length.
-        # encode every x_i i \in [seq] word to respectable embedding 
-        encoded_input = [tokenizer.encode(it, return_tensors='pt').to(device) for it in input_text] # batch x seq
-        encoded_input = torch.cat(encoded_input, dim=0)
-
-        input_ids = torch.LongTensor([[58100]]).to(device)
-        cur_len = 1
-        max_length = length_cutoff
-        min_length = 0
-        temperature = 1.0
-        top_k = 50
-        top_p = 1.0
-        repetition_penalty = 1.0
-        no_repeat_ngram_size = 0
-        bad_words_ids = [[58100]]
-        pad_token_id = 58100
-        eos_token_id = 0
-        effective_batch_size = batch_size
-        attention_mask = encoded_input.new_ones(encoded_input.shape)
-        use_cache = True
-        model_specific_kwargs = {'encoder_outputs': model.get_encoder()(encoded_input, attention_mask=attention_mask)}
-
-        output = _generate_no_beam_search(model,
-                                        conditioning_model,
-                                        condition_lambda,
-                                        precondition_topk,
-                                        input_ids,
-                                        cur_len,
-                                        max_length,
-                                        min_length,
-                                        do_sample,
-                                        temperature,
-                                        top_k,
-                                        top_p,
-                                        repetition_penalty,
-                                        no_repeat_ngram_size,
-                                        bad_words_ids,
-                                        pad_token_id,
-                                        eos_token_id,
-                                        batch_size,
-                                        attention_mask,
-                                        use_cache,
-                                        model_specific_kwargs)
-
-        return [tokenizer.decode(s[1:]) for s in output] # 1: to delete the pad token
-
-
-# hack of code from transformers/generation_utils.py
-# to get our conditioning
-def postprocess_next_token_scores(
-    model,
-    scores,
-    input_ids,
-    no_repeat_ngram_size,
-    bad_words_ids,
-    cur_len,
-    min_length,
-    max_length,
-    eos_token_id,
-    repetition_penalty,
-    batch_size,
-    num_beams,
-):
-    # repetition penalty (from CTRL paper https://arxiv.org/abs/1909.05858)
-    if repetition_penalty != 1.0:
-        model.enforce_repetition_penalty_(
-            scores,
-            batch_size,
-            num_beams,
-            input_ids,
-            repetition_penalty,
-        )
-
-    # set eos token prob to zero if min_length is not reached
-    if eos_token_id is not None and cur_len < min_length:
-        scores[:, eos_token_id] = -float("inf")
-
-    if no_repeat_ngram_size > 0:
-        # calculate a list of banned tokens to prevent repetitively generating the same ngrams
-        num_batch_hypotheses = batch_size * num_beams
-        # from fairseq: https://github.com/pytorch/fairseq/blob/a07cb6f40480928c9e0548b737aadd36ee66ac76/fairseq/sequence_generator.py#L345
-        banned_batch_tokens = calc_banned_ngram_tokens(
-            input_ids, num_batch_hypotheses, no_repeat_ngram_size, cur_len
-        )
-        for i, banned_tokens in enumerate(banned_batch_tokens):
-            scores[i, banned_tokens] = -float("inf")
-
-    if bad_words_ids is not None:
-        # Exclude EOS token (already processed)
-        bad_words_ids = list(filter(lambda bad_token_seq: bad_token_seq != [eos_token_id], bad_words_ids))
-        # calculate a list of banned tokens according to bad words
-        banned_tokens = calc_banned_bad_words_ids(input_ids.tolist(), bad_words_ids)
-        # Modify the scores in place by setting the banned tokens logits to `-inf`
-        set_scores_to_inf_for_banned_tokens(scores, banned_tokens)
-
-    return scores
-
-def calc_banned_ngram_tokens(prev_input_ids: Tensor, num_hypos: int, no_repeat_ngram_size: int, cur_len: int) -> None:
-    """Copied from fairseq for no_repeat_ngram in beam_search"""
-    if cur_len + 1 < no_repeat_ngram_size:
-        # return no banned tokens if we haven't generated no_repeat_ngram_size tokens yet
-        return [[] for _ in range(num_hypos)]
-    generated_ngrams = [{} for _ in range(num_hypos)]
-    for idx in range(num_hypos):
-        gen_tokens = prev_input_ids[idx].tolist()
-        generated_ngram = generated_ngrams[idx]
-        for ngram in zip(*[gen_tokens[i:] for i in range(no_repeat_ngram_size)]):
-            prev_ngram_tuple = tuple(ngram[:-1])
-            generated_ngram[prev_ngram_tuple] = generated_ngram.get(prev_ngram_tuple, []) + [ngram[-1]]
-
-    def _get_generated_ngrams(hypo_idx):
-        # Before decoding the next token, prevent decoding of ngrams that have already appeared
-        start_idx = cur_len + 1 - no_repeat_ngram_size
-        ngram_idx = tuple(prev_input_ids[hypo_idx, start_idx:cur_len].tolist())
-        return generated_ngrams[hypo_idx].get(ngram_idx, [])
-
-    banned_tokens = [_get_generated_ngrams(hypo_idx) for hypo_idx in range(num_hypos)]
-    return banned_tokens
-
-
-def calc_banned_bad_words_ids(prev_input_ids: Iterable[int], bad_words_ids: Iterable[int]) -> Iterable[int]:
-    banned_tokens = []
-
-    def _tokens_match(prev_tokens, tokens):
-        if len(tokens) == 0:
-            # if bad word tokens is just one token always ban it
-            return True
-        if len(tokens) > len(prev_tokens):
-            # if bad word tokens are longer than prev tokens they can't be equal
-            return False
-
-        if prev_tokens[-len(tokens) :] == tokens:
-            # if tokens match
-            return True
-        else:
-            return False
-
-    for prev_input_ids_slice in prev_input_ids:
-        banned_tokens_slice = []
-
-        for banned_token_seq in bad_words_ids:
-            assert len(banned_token_seq) > 0, "Banned words token sequences {} cannot have an empty list".format(
-                bad_words_ids
-            )
-
-            if _tokens_match(prev_input_ids_slice, banned_token_seq[:-1]) is False:
-                # if tokens do not match continue
-                continue
-
-            banned_tokens_slice.append(banned_token_seq[-1])
-
-        banned_tokens.append(banned_tokens_slice)
-
-    return banned_tokens
-
-def set_scores_to_inf_for_banned_tokens(scores: torch.Tensor, banned_tokens: List[List[int]]) -> None:
-    """Modifies the scores in place by setting the banned token positions to `-inf`. Banned token is expected to be
-    a list of list of banned tokens to ban in the format [[batch index, vocabulary position],...]
-        Args:
-            scores: logits distribution of shape (batch size, vocabulary size)
-            banned_tokens: list of list of tokens to ban of length (batch_size)
-    """
-    banned_mask_list = []
-    for idx, batch_banned_tokens in enumerate(banned_tokens):
-        for token in batch_banned_tokens:
-            banned_mask_list.append([idx, token])
-    if not banned_mask_list:
-        return
-    banned_mask = torch.LongTensor(banned_mask_list)
-    indices = torch.ones(len(banned_mask))
-    # A sparse tensor is generated from a list of coordinates: [[0, 1], [0, 2], [2, 0]]. A conversion to dense tensor generates:
-    # [ 0  1  1 ]
-    # [ 0  0  0 ]
-    # [ 1  0  0 ]
-
-    banned_mask = torch.sparse.LongTensor(banned_mask.t(), indices, scores.size()).to(scores.device).to_dense().bool()
-    scores.masked_fill_(banned_mask, -float("inf"))
-    
-def _generate_no_beam_search(
-        model,
-        conditioning_model,
-        condition_lambda,
-        precondition_topk,
-        input_ids,
-        cur_len,
-        max_length,
-        min_length,
-        do_sample,
-        temperature,
-        top_k,
-        top_p,
-        repetition_penalty,
-        no_repeat_ngram_size,
-        bad_words_ids,
-        pad_token_id,
-        eos_token_id,
-        batch_size,
-        attention_mask,
-        use_cache,
-        model_kwargs,
-    ):
-        """Generate sequences for each example without beam search (num_beams == 1).
-        All returned sequence are generated independantly.
-        """
-        # length of generated sentences / unfinished sentences
-        unfinished_sents = input_ids.new(batch_size).fill_(1)
-        sent_lengths = input_ids.new(batch_size).fill_(max_length)
-        past = None
-        while cur_len < max_length:
-            model_inputs = model.prepare_inputs_for_generation(
-                input_ids, past=past, attention_mask=attention_mask, use_cache=use_cache, **model_kwargs
-            )
-
-            outputs = model(**model_inputs, return_dict=True)
-            next_token_logits = outputs.logits[:, -1, :]
-
-            # scores = model.postprocess_next_token_scores(
-            #     scores=next_token_logits,
-            #     input_ids=input_ids,
-            #     no_repeat_ngram_size=no_repeat_ngram_size,
-            #     bad_words_ids=bad_words_ids,
-            #     cur_len=cur_len,
-            #     min_length=min_length,
-            #     max_length=max_length,
-            #     eos_token_id=eos_token_id,
-            #     repetition_penalty=repetition_penalty,
-            #     batch_size=batch_size,
-            #     num_beams=1,
-            # )
-
-            scores = postprocess_next_token_scores(
-                model=model,
-                scores=next_token_logits,
-                input_ids=input_ids,
-                no_repeat_ngram_size=no_repeat_ngram_size,
-                bad_words_ids=bad_words_ids,
-                cur_len=cur_len,
-                min_length=min_length,
-                max_length=max_length,
-                eos_token_id=eos_token_id,
-                repetition_penalty=repetition_penalty,
-                batch_size=batch_size,
-                num_beams=1,
-            )
-
-            # if model has past, then set the past variable to speed up decoding
-            if "past_key_values" in outputs:
-                past = outputs.past_key_values
-            elif "mems" in outputs:
-                past = outputs.mems
-
-            top_logits, top_indices = scores.topk(precondition_topk, dim=1) # batch x topk
-            tplus1_candidates = torch.cat([input_ids.unsqueeze(1).expand(-1, precondition_topk, -1), top_indices.unsqueeze(2)], dim=2)[:, :, 1:] # batch x topk x seq+1, with pad dropped
-            expanded_lengths = torch.LongTensor([[cur_len for _ in range(precondition_topk)] for _ in range(batch_size)]).to(scores.device)
-            if condition_lambda == 0:
-                condition_logits = torch.zeros_like(top_logits).float()
-            else:
-                condition_logits = conditioning_model(tplus1_candidates.flatten(0, 1), # batch*topk x seq+1
-                                                    expanded_lengths.flatten(0, 1), # batch*topk
-                                                    None,
-                                                    None,
-                                                    None)
-                condition_logits = condition_logits.view(batch_size, precondition_topk, -1)[:, :, -1] # batch x topk of last formality pred
-                condition_logits = condition_logits - torch.log(1 + torch.exp(condition_logits)) # get correct log probs
-                # condition_logits = - torch.log(1 + torch.exp(condition_logits)) # for informal
-            full_logits = top_logits + condition_lambda * condition_logits
-            if do_sample:
-                raise NotImplementedError
-            else:
-                # Greedy decoding
-                next_token = top_indices[torch.arange(batch_size).to(top_indices.device), torch.argmax(full_logits, dim=-1)]
-
-            # if do_sample:
-            #     # Temperature (higher temperature => more likely to sample low probability tokens)
-            #     if temperature != 1.0:
-            #         scores = scores / temperature
-            #     # Top-p/top-k filtering
-            #     next_token_logscores = top_k_top_p_filtering(scores, top_k=top_k, top_p=top_p)
-            #     # Sample
-            #     probs = F.softmax(next_token_logscores, dim=-1)
-            #     next_token = torch.multinomial(probs, num_samples=1).squeeze(1)
-            # else:
-            #     # Greedy decoding
-            #     next_token = torch.argmax(next_token_logits, dim=-1)
-
-            # update generations and finished sentences
-            if eos_token_id is not None:
-                # pad finished sentences if eos_token_id exist
-                tokens_to_add = next_token * unfinished_sents + (pad_token_id) * (1 - unfinished_sents)
-            else:
-                tokens_to_add = next_token
-            
-            # add token and increase length by one
-            input_ids = torch.cat([input_ids, tokens_to_add.unsqueeze(-1)], dim=-1)
-            cur_len = cur_len + 1
-
-            if eos_token_id is not None:
-                eos_in_sents = tokens_to_add == eos_token_id
-                # if sentence is unfinished and the token to add is eos, sent_lengths is filled with current length
-                is_sents_unfinished_and_token_to_add_is_eos = unfinished_sents.mul(eos_in_sents.long()).bool()
-                sent_lengths.masked_fill_(is_sents_unfinished_and_token_to_add_is_eos, cur_len)
-                # unfinished_sents is set to zero if eos in sentence
-                unfinished_sents.mul_((~eos_in_sents).long())
-
-            # stop when there is a </s> in each sentence, or if we exceed the maximul length
-            if unfinished_sents.max() == 0:
-                break
-
-            # extend attention_mask for new generated input if only decoder
-            if model.config.is_encoder_decoder is False:
-                attention_mask = torch.cat(
-                    [attention_mask, attention_mask.new_ones((attention_mask.shape[0], 1))], dim=-1
-                )
-
-        return input_ids
-
-if __name__=='__main__':
-    parser = ArgumentParser()
-
-    # DATA
-    parser.add_argument('--ckpt', type=str, required=True)
-    parser.add_argument('--dataset_info', type=str, required=True, help='saved dataset info')
-    parser.add_argument('--model_string', type=str, default='Helsinki-NLP/opus-mt-es-en')
-
-    parser.add_argument('--input_text', type=str, default=None, required=True, help='text to run pred on')
-
-    parser.add_argument('--precondition_topk', type=int, default=200, help='consider top k outputs from gpt at each step before conditioning and re-pruning')
-    parser.add_argument('--do_sample', action='store_true', default=False, help='sample instead of greedy')
-    parser.add_argument('--condition_lambda', type=float, default=1.0, help='lambda weight on conditioning model')
-    parser.add_argument('--length_cutoff', type=int, default=512, help='max length')
-
-    parser.add_argument('--seed', type=int, default=1, help='random seed')
-    parser.add_argument('--device', type=str, default='cuda', choices=['cpu', 'cuda'])
-    parser.add_argument('--debug', action='store_true', default=False)
-
-    args = parser.parse_args()
-
-    random.seed(args.seed)
-    np.random.seed(args.seed)
-    torch.manual_seed(args.seed)
-
-    main(args)
-
-
diff --git a/spaces/Ebo010/hot-dog/README.md b/spaces/Ebo010/hot-dog/README.md
deleted file mode 100644
index 4c7415819a2885b21b7cfca05236c2f56e520553..0000000000000000000000000000000000000000
--- a/spaces/Ebo010/hot-dog/README.md
+++ /dev/null
@@ -1,13 +0,0 @@
----
-title: Hot Dog
-emoji: 😻
-colorFrom: gray
-colorTo: blue
-sdk: gradio
-sdk_version: 3.19.1
-app_file: app.py
-pinned: false
-license: lgpl-3.0
----
-
-Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
diff --git a/spaces/Enderfga/mtCNN_sysu/app.py b/spaces/Enderfga/mtCNN_sysu/app.py
deleted file mode 100644
index 2d5a890e1225af3f968d613e8103d02b948ba8df..0000000000000000000000000000000000000000
--- a/spaces/Enderfga/mtCNN_sysu/app.py
+++ /dev/null
@@ -1,52 +0,0 @@
-import gradio as gr
-import cv2
-from utils.detect import create_mtcnn_net, MtcnnDetector
-from utils.vision import vis_face
-import argparse
-from PIL import Image
-import numpy as np
-
-MIN_FACE_SIZE = 24
-
-def parse_args():
-    parser = argparse.ArgumentParser(description='Test MTCNN',
-                                     formatter_class=argparse.ArgumentDefaultsHelpFormatter)
-
-    parser.add_argument('--net', default='onet', help='which net to show', type=str)
-    parser.add_argument('--pnet_path', default="./model_store/pnet_epoch_20.pt",help='path to pnet model', type=str)
-    parser.add_argument('--rnet_path', default="./model_store/rnet_epoch_20.pt",help='path to rnet model', type=str)
-    parser.add_argument('--onet_path', default="./model_store/onet_epoch_20.pt",help='path to onet model', type=str)
-    parser.add_argument('--path', default="./img/mid.png",help='path to image', type=str)
-    parser.add_argument('--min_face_size', default=MIN_FACE_SIZE,help='min face size', type=int)
-    parser.add_argument('--use_cuda', default=False,help='use cuda', type=bool)
-    parser.add_argument('--thresh', default='[0.6, 0.7, 0.7]',help='thresh', type=str)
-    parser.add_argument('--save_name', default="result.jpg",help='save name', type=str)
-    parser.add_argument('--input_mode', default=1,help='image or video', type=int)
-    args = parser.parse_args()
-    return args
-def greet(请上传待检测人脸图片):
-    args = parse_args()
-    thresh = [float(i) for i in (args.thresh).split('[')[1].split(']')[0].split(',')]
-    pnet, rnet, onet = create_mtcnn_net(p_model_path=args.pnet_path, r_model_path=args.rnet_path,o_model_path=args.onet_path, use_cuda=args.use_cuda)
-    mtcnn_detector = MtcnnDetector(pnet=pnet, rnet=rnet, onet=onet, min_face_size=args.min_face_size,threshold=thresh)
-    img = cv2.imread(请上传待检测人脸图片)
-    b,g,r = cv2.split(img)
-    img_bg = cv2.merge([r,g,b])
-    p_bboxs, r_bboxs, bboxs, landmarks = mtcnn_detector.detect_face(img)
-    save_name = args.save_name
-    fig = vis_face(img_bg, bboxs, landmarks, MIN_FACE_SIZE, save_name)
-    fig.canvas.draw()
-
-    # Get the RGB buffer from the figure
-    w, h = fig.canvas.get_width_height()
-    buf = np.fromstring(fig.canvas.tostring_rgb(), dtype=np.uint8)
-    buf.shape = (h, w, 3)
-
-    # canvas.tostring_rgb give pixmap in RGB mode. 
-    # Roll the ALPHA channel to have it in RGBA mode
-    buf = np.roll(buf, 3, axis=2)
-    return Image.fromarray(buf)
-iface = gr.Interface(fn=greet, 
-                    inputs=gr.Image(type="filepath"),
-                    outputs="image")
-iface.launch()
\ No newline at end of file
diff --git a/spaces/EronSamez/RVC_HFmeu/utils/backups_test.py b/spaces/EronSamez/RVC_HFmeu/utils/backups_test.py
deleted file mode 100644
index f3edf15811b5035ee82f21e54e87b7e87ce413eb..0000000000000000000000000000000000000000
--- a/spaces/EronSamez/RVC_HFmeu/utils/backups_test.py
+++ /dev/null
@@ -1,138 +0,0 @@
-
-import os
-import shutil
-import hashlib
-import time
-
-LOGS_FOLDER = '/content/Applio-RVC-Fork/logs'
-WEIGHTS_FOLDER = '/content/Applio-RVC-Fork/weights'
-GOOGLE_DRIVE_PATH = '/content/drive/MyDrive/RVC_Backup'
-
-def import_google_drive_backup():
-    print("Importing Google Drive backup...")
-    GOOGLE_DRIVE_PATH = '/content/drive/MyDrive/RVC_Backup'  # change this to your Google Drive path
-    LOGS_FOLDER = '/content/Applio-RVC-Fork/logs'
-    WEIGHTS_FOLDER = '/content/Applio-RVC-Fork/weights'
-    weights_exist = False
-    files_to_copy = []
-    weights_to_copy = []
-    
-    def handle_files(root, files, is_weight_files=False):
-        for filename in files:
-            filepath = os.path.join(root, filename)
-            if filename.endswith('.pth') and is_weight_files:
-                weights_exist = True
-                backup_filepath = os.path.join(WEIGHTS_FOLDER, os.path.relpath(filepath, GOOGLE_DRIVE_PATH))
-            else:
-                backup_filepath = os.path.join(LOGS_FOLDER, os.path.relpath(filepath, GOOGLE_DRIVE_PATH))
-            backup_folderpath = os.path.dirname(backup_filepath)
-            if not os.path.exists(backup_folderpath):
-                os.makedirs(backup_folderpath)
-                print(f'Created folder: {backup_folderpath}', flush=True)
-            if is_weight_files:
-                weights_to_copy.append((filepath, backup_filepath))
-            else:
-                files_to_copy.append((filepath, backup_filepath))
-
-    for root, dirs, files in os.walk(os.path.join(GOOGLE_DRIVE_PATH, 'logs')):
-        handle_files(root, files)
-    
-    for root, dirs, files in os.walk(os.path.join(GOOGLE_DRIVE_PATH, 'weights')):
-        handle_files(root, files, True)
-
-    # Copy files in batches
-    total_files = len(files_to_copy)
-    start_time = time.time()
-    for i, (source, dest) in enumerate(files_to_copy, start=1):
-        with open(source, 'rb') as src, open(dest, 'wb') as dst:
-            shutil.copyfileobj(src, dst, 1024*1024)  # 1MB buffer size
-        # Report progress every 5 seconds or after every 100 files, whichever is less frequent
-        if time.time() - start_time > 5 or i % 100 == 0:
-            print(f'\rCopying file {i} of {total_files} ({i * 100 / total_files:.2f}%)', end="")
-            start_time = time.time()
-    print(f'\nImported {len(files_to_copy)} files from Google Drive backup')
-
-    # Copy weights in batches
-    total_weights = len(weights_to_copy)
-    start_time = time.time()
-    for i, (source, dest) in enumerate(weights_to_copy, start=1):
-        with open(source, 'rb') as src, open(dest, 'wb') as dst:
-            shutil.copyfileobj(src, dst, 1024*1024)  # 1MB buffer size
-        # Report progress every 5 seconds or after every 100 files, whichever is less frequent
-        if time.time() - start_time > 5 or i % 100 == 0:
-            print(f'\rCopying weight file {i} of {total_weights} ({i * 100 / total_weights:.2f}%)', end="")
-            start_time = time.time()
-    if weights_exist:
-        print(f'\nImported {len(weights_to_copy)} weight files')
-        print("Copied weights from Google Drive backup to local weights folder.")
-    else:
-        print("\nNo weights found in Google Drive backup.")
-    print("Google Drive backup import completed.")
-
-def backup_files():
-    print("\n Starting backup loop...")
-    last_backup_timestamps_path = os.path.join(LOGS_FOLDER, 'last_backup_timestamps.txt')
-    fully_updated = False  # boolean to track if all files are up to date
-    try:
-        with open(last_backup_timestamps_path, 'r') as f:
-            last_backup_timestamps = dict(line.strip().split(':') for line in f)
-    except:
-        last_backup_timestamps = {}
-
-    while True:
-        updated = False
-        files_to_copy = []
-        files_to_delete = []
-
-        for root, dirs, files in os.walk(LOGS_FOLDER):
-            for filename in files:
-                if filename != 'last_backup_timestamps.txt':
-                    filepath = os.path.join(root, filename)
-                    if os.path.isfile(filepath):
-                        backup_filepath = os.path.join(GOOGLE_DRIVE_PATH, os.path.relpath(filepath, LOGS_FOLDER))
-                        backup_folderpath = os.path.dirname(backup_filepath)
-
-                        if not os.path.exists(backup_folderpath):
-                            os.makedirs(backup_folderpath)
-                            print(f'Created backup folder: {backup_folderpath}', flush=True)
-
-                        # check if file has changed since last backup
-                        last_backup_timestamp = last_backup_timestamps.get(filepath)
-                        current_timestamp = os.path.getmtime(filepath)
-                        if last_backup_timestamp is None or float(last_backup_timestamp) < current_timestamp:
-                            files_to_copy.append((filepath, backup_filepath))  # add to list of files to copy
-                            last_backup_timestamps[filepath] = str(current_timestamp)  # update last backup timestamp
-                            updated = True
-                            fully_updated = False  # if a file is updated, all files are not up to date
-
-        # check if any files were deleted in Colab and delete them from the backup drive
-        for filepath in list(last_backup_timestamps.keys()):
-            if not os.path.exists(filepath):
-                backup_filepath = os.path.join(GOOGLE_DRIVE_PATH, os.path.relpath(filepath, LOGS_FOLDER))
-                if os.path.exists(backup_filepath):
-                    files_to_delete.append(backup_filepath)  # add to list of files to delete
-                del last_backup_timestamps[filepath]
-                updated = True
-                fully_updated = False  # if a file is deleted, all files are not up to date
-
-        # Copy files in batches
-        if files_to_copy:
-            for source, dest in files_to_copy:
-                shutil.copy2(source, dest)
-            print(f'Copied or updated {len(files_to_copy)} files')
-
-        # Delete files in batches
-        if files_to_delete:
-            for file in files_to_delete:
-                os.remove(file)
-            print(f'Deleted {len(files_to_delete)} files')
-
-        if not updated and not fully_updated:
-            print("Files are up to date.")
-            fully_updated = True  # if all files are up to date, set the boolean to True
-            copy_weights_folder_to_drive()
-
-        with open(last_backup_timestamps_path, 'w') as f:
-            for filepath, timestamp in last_backup_timestamps.items():
-                f.write(f'{filepath}:{timestamp}\n')
-        time.sleep(15)  # wait for 15 seconds before checking again
diff --git a/spaces/EuroPython2022/mmocr-demo/configs/_base_/recog_pipelines/crnn_tps_pipeline.py b/spaces/EuroPython2022/mmocr-demo/configs/_base_/recog_pipelines/crnn_tps_pipeline.py
deleted file mode 100644
index 3a2eea55a739206c11ae876ba82e9c2f6ea1ff6d..0000000000000000000000000000000000000000
--- a/spaces/EuroPython2022/mmocr-demo/configs/_base_/recog_pipelines/crnn_tps_pipeline.py
+++ /dev/null
@@ -1,37 +0,0 @@
-img_norm_cfg = dict(mean=[0.5], std=[0.5])
-
-train_pipeline = [
-    dict(type='LoadImageFromFile', color_type='grayscale'),
-    dict(
-        type='ResizeOCR',
-        height=32,
-        min_width=100,
-        max_width=100,
-        keep_aspect_ratio=False),
-    dict(type='ToTensorOCR'),
-    dict(type='NormalizeOCR', **img_norm_cfg),
-    dict(
-        type='Collect',
-        keys=['img'],
-        meta_keys=[
-            'filename', 'ori_shape', 'resize_shape', 'text', 'valid_ratio'
-        ]),
-]
-test_pipeline = [
-    dict(type='LoadImageFromFile', color_type='grayscale'),
-    dict(
-        type='ResizeOCR',
-        height=32,
-        min_width=32,
-        max_width=100,
-        keep_aspect_ratio=False),
-    dict(type='ToTensorOCR'),
-    dict(type='NormalizeOCR', **img_norm_cfg),
-    dict(
-        type='Collect',
-        keys=['img'],
-        meta_keys=[
-            'filename', 'ori_shape', 'resize_shape', 'valid_ratio',
-            'img_norm_cfg', 'ori_filename', 'img_shape'
-        ]),
-]
diff --git a/spaces/Ferion/image-matting-app/ppmatting/utils/utils.py b/spaces/Ferion/image-matting-app/ppmatting/utils/utils.py
deleted file mode 100644
index 13513cb193757b63043f44a2c145b3e9b6fad82e..0000000000000000000000000000000000000000
--- a/spaces/Ferion/image-matting-app/ppmatting/utils/utils.py
+++ /dev/null
@@ -1,71 +0,0 @@
-# Copyright (c) 2021 PaddlePaddle Authors. All Rights Reserved.
-#
-# Licensed under the Apache License, Version 2.0 (the "License");
-# you may not use this file except in compliance with the License.
-# You may obtain a copy of the License at
-#
-#    http://www.apache.org/licenses/LICENSE-2.0
-#
-# Unless required by applicable law or agreed to in writing, software
-# distributed under the License is distributed on an "AS IS" BASIS,
-# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
-# See the License for the specific language governing permissions and
-# limitations under the License.
-
-import os
-
-
-def get_files(root_path):
-    res = []
-    for root, dirs, files in os.walk(root_path, followlinks=True):
-        for f in files:
-            if f.endswith(('.jpg', '.png', '.jpeg', 'JPG')):
-                res.append(os.path.join(root, f))
-    return res
-
-
-def get_image_list(image_path):
-    """Get image list"""
-    valid_suffix = [
-        '.JPEG', '.jpeg', '.JPG', '.jpg', '.BMP', '.bmp', '.PNG', '.png'
-    ]
-    image_list = []
-    image_dir = None
-    if os.path.isfile(image_path):
-        image_dir = None
-        if os.path.splitext(image_path)[-1] in valid_suffix:
-            image_list.append(image_path)
-        else:
-            image_dir = os.path.dirname(image_path)
-            with open(image_path, 'r') as f:
-                for line in f:
-                    line = line.strip()
-                    if len(line.split()) > 1:
-                        raise RuntimeError(
-                            'There should be only one image path per line in `image_path` file. Wrong line: {}'
-                            .format(line))
-                    image_list.append(os.path.join(image_dir, line))
-    elif os.path.isdir(image_path):
-        image_dir = image_path
-        for root, dirs, files in os.walk(image_path):
-            for f in files:
-                if '.ipynb_checkpoints' in root:
-                    continue
-                if os.path.splitext(f)[-1] in valid_suffix:
-                    image_list.append(os.path.join(root, f))
-        image_list.sort()
-    else:
-        raise FileNotFoundError(
-            '`image_path` is not found. it should be an image file or a directory including images'
-        )
-
-    if len(image_list) == 0:
-        raise RuntimeError('There are not image file in `image_path`')
-
-    return image_list, image_dir
-
-
-def mkdir(path):
-    sub_dir = os.path.dirname(path)
-    if not os.path.exists(sub_dir):
-        os.makedirs(sub_dir)
diff --git a/spaces/FrankZxShen/so-vits-svc-models-ba/vdecoder/hifigan/nvSTFT.py b/spaces/FrankZxShen/so-vits-svc-models-ba/vdecoder/hifigan/nvSTFT.py
deleted file mode 100644
index 88597d62a505715091f9ba62d38bf0a85a31b95a..0000000000000000000000000000000000000000
--- a/spaces/FrankZxShen/so-vits-svc-models-ba/vdecoder/hifigan/nvSTFT.py
+++ /dev/null
@@ -1,111 +0,0 @@
-import math
-import os
-os.environ["LRU_CACHE_CAPACITY"] = "3"
-import random
-import torch
-import torch.utils.data
-import numpy as np
-import librosa
-from librosa.util import normalize
-from librosa.filters import mel as librosa_mel_fn
-from scipy.io.wavfile import read
-import soundfile as sf
-
-def load_wav_to_torch(full_path, target_sr=None, return_empty_on_exception=False):
-    sampling_rate = None
-    try:
-        data, sampling_rate = sf.read(full_path, always_2d=True)# than soundfile.
-    except Exception as ex:
-        print(f"'{full_path}' failed to load.\nException:")
-        print(ex)
-        if return_empty_on_exception:
-            return [], sampling_rate or target_sr or 32000
-        else:
-            raise Exception(ex)
-    
-    if len(data.shape) > 1:
-        data = data[:, 0]
-        assert len(data) > 2# check duration of audio file is > 2 samples (because otherwise the slice operation was on the wrong dimension)
-    
-    if np.issubdtype(data.dtype, np.integer): # if audio data is type int
-        max_mag = -np.iinfo(data.dtype).min # maximum magnitude = min possible value of intXX
-    else: # if audio data is type fp32
-        max_mag = max(np.amax(data), -np.amin(data))
-        max_mag = (2**31)+1 if max_mag > (2**15) else ((2**15)+1 if max_mag > 1.01 else 1.0) # data should be either 16-bit INT, 32-bit INT or [-1 to 1] float32
-    
-    data = torch.FloatTensor(data.astype(np.float32))/max_mag
-    
-    if (torch.isinf(data) | torch.isnan(data)).any() and return_empty_on_exception:# resample will crash with inf/NaN inputs. return_empty_on_exception will return empty arr instead of except
-        return [], sampling_rate or target_sr or 32000
-    if target_sr is not None and sampling_rate != target_sr:
-        data = torch.from_numpy(librosa.core.resample(data.numpy(), orig_sr=sampling_rate, target_sr=target_sr))
-        sampling_rate = target_sr
-    
-    return data, sampling_rate
-
-def dynamic_range_compression(x, C=1, clip_val=1e-5):
-    return np.log(np.clip(x, a_min=clip_val, a_max=None) * C)
-
-def dynamic_range_decompression(x, C=1):
-    return np.exp(x) / C
-
-def dynamic_range_compression_torch(x, C=1, clip_val=1e-5):
-    return torch.log(torch.clamp(x, min=clip_val) * C)
-
-def dynamic_range_decompression_torch(x, C=1):
-    return torch.exp(x) / C
-
-class STFT():
-    def __init__(self, sr=22050, n_mels=80, n_fft=1024, win_size=1024, hop_length=256, fmin=20, fmax=11025, clip_val=1e-5):
-        self.target_sr = sr
-        
-        self.n_mels     = n_mels
-        self.n_fft      = n_fft
-        self.win_size   = win_size
-        self.hop_length = hop_length
-        self.fmin     = fmin
-        self.fmax     = fmax
-        self.clip_val = clip_val
-        self.mel_basis = {}
-        self.hann_window = {}
-    
-    def get_mel(self, y, center=False):
-        sampling_rate = self.target_sr
-        n_mels     = self.n_mels
-        n_fft      = self.n_fft
-        win_size   = self.win_size
-        hop_length = self.hop_length
-        fmin       = self.fmin
-        fmax       = self.fmax
-        clip_val   = self.clip_val
-        
-        if torch.min(y) < -1.:
-            print('min value is ', torch.min(y))
-        if torch.max(y) > 1.:
-            print('max value is ', torch.max(y))
-        
-        if fmax not in self.mel_basis:
-            mel = librosa_mel_fn(sr=sampling_rate, n_fft=n_fft, n_mels=n_mels, fmin=fmin, fmax=fmax)
-            self.mel_basis[str(fmax)+'_'+str(y.device)] = torch.from_numpy(mel).float().to(y.device)
-            self.hann_window[str(y.device)] = torch.hann_window(self.win_size).to(y.device)
-        
-        y = torch.nn.functional.pad(y.unsqueeze(1), (int((n_fft-hop_length)/2), int((n_fft-hop_length)/2)), mode='reflect')
-        y = y.squeeze(1)
-        
-        spec = torch.stft(y, n_fft, hop_length=hop_length, win_length=win_size, window=self.hann_window[str(y.device)],
-                          center=center, pad_mode='reflect', normalized=False, onesided=True)
-        # print(111,spec)
-        spec = torch.sqrt(spec.pow(2).sum(-1)+(1e-9))
-        # print(222,spec)
-        spec = torch.matmul(self.mel_basis[str(fmax)+'_'+str(y.device)], spec)
-        # print(333,spec)
-        spec = dynamic_range_compression_torch(spec, clip_val=clip_val)
-        # print(444,spec)
-        return spec
-    
-    def __call__(self, audiopath):
-        audio, sr = load_wav_to_torch(audiopath, target_sr=self.target_sr)
-        spect = self.get_mel(audio.unsqueeze(0)).squeeze(0)
-        return spect
-
-stft = STFT()
diff --git a/spaces/FrankZxShen/so-vits-svc-models-pcr/vencoder/whisper/decoding.py b/spaces/FrankZxShen/so-vits-svc-models-pcr/vencoder/whisper/decoding.py
deleted file mode 100644
index 603546d4c9ff67514d2567576935b974fe373bef..0000000000000000000000000000000000000000
--- a/spaces/FrankZxShen/so-vits-svc-models-pcr/vencoder/whisper/decoding.py
+++ /dev/null
@@ -1,712 +0,0 @@
-from dataclasses import dataclass, field
-from typing import Dict, List, Tuple, Iterable, Optional, Sequence, Union, TYPE_CHECKING
-
-import numpy as np
-import torch
-import torch.nn.functional as F
-from torch import Tensor
-from torch.distributions import Categorical
-
-from .audio import CHUNK_LENGTH
-from .tokenizer import Tokenizer, get_tokenizer
-from .utils import compression_ratio
-
-if TYPE_CHECKING:
-    from .model import Whisper
-
-
-@torch.no_grad()
-def detect_language(model: "Whisper", mel: Tensor, tokenizer: Tokenizer = None) -> Tuple[Tensor, List[dict]]:
-    """
-    Detect the spoken language in the audio, and return them as list of strings, along with the ids
-    of the most probable language tokens and the probability distribution over all language tokens.
-    This is performed outside the main decode loop in order to not interfere with kv-caching.
-
-    Returns
-    -------
-    language_tokens : Tensor, shape = (n_audio,)
-        ids of the most probable language tokens, which appears after the startoftranscript token.
-    language_probs : List[Dict[str, float]], length = n_audio
-        list of dictionaries containing the probability distribution over all languages.
-    """
-    if tokenizer is None:
-        tokenizer = get_tokenizer(model.is_multilingual)
-    if tokenizer.language is None or tokenizer.language_token not in tokenizer.sot_sequence:
-        raise ValueError(f"This model doesn't have language tokens so it can't perform lang id")
-
-    single = mel.ndim == 2
-    if single:
-        mel = mel.unsqueeze(0)
-
-    # skip encoder forward pass if already-encoded audio features were given
-    if mel.shape[-2:] != (model.dims.n_audio_ctx, model.dims.n_audio_state):
-        mel = model.encoder(mel)
-
-    # forward pass using a single token, startoftranscript
-    n_audio = mel.shape[0]
-    x = torch.tensor([[tokenizer.sot]] * n_audio).to(mel.device)  # [n_audio, 1]
-    logits = model.logits(x, mel)[:, 0]
-
-    # collect detected languages; suppress all non-language tokens
-    mask = torch.ones(logits.shape[-1], dtype=torch.bool)
-    mask[list(tokenizer.all_language_tokens)] = False
-    logits[:, mask] = -np.inf
-    language_tokens = logits.argmax(dim=-1)
-    language_token_probs = logits.softmax(dim=-1).cpu()
-    language_probs = [
-        {
-            c: language_token_probs[i, j].item()
-            for j, c in zip(tokenizer.all_language_tokens, tokenizer.all_language_codes)
-        }
-        for i in range(n_audio)
-    ]
-
-    if single:
-        language_tokens = language_tokens[0]
-        language_probs = language_probs[0]
-
-    return language_tokens, language_probs
-
-
-@dataclass(frozen=True)
-class DecodingOptions:
-    task: str = "transcribe"  # whether to perform X->X "transcribe" or X->English "translate"
-    language: Optional[str] = None  # language that the audio is in; uses detected language if None
-
-    # sampling-related options
-    temperature: float = 0.0
-    sample_len: Optional[int] = None  # maximum number of tokens to sample
-    best_of: Optional[int] = None     # number of independent samples to collect, when t > 0
-    beam_size: Optional[int] = None   # number of beams in beam search, when t == 0
-    patience: Optional[float] = None  # patience in beam search (https://arxiv.org/abs/2204.05424)
-
-    # options for ranking generations (either beams or best-of-N samples)
-    length_penalty: Optional[float] = None   # "alpha" in Google NMT, None defaults to length norm
-
-    # prompt, prefix, and token suppression
-    prompt: Optional[Union[str, List[int]]] = None   # text or tokens for the previous context
-    prefix: Optional[Union[str, List[int]]] = None   # text or tokens to prefix the current context
-    suppress_blank: bool = True                      # this will suppress blank outputs
-
-    # list of tokens ids (or comma-separated token ids) to suppress
-    # "-1" will suppress a set of symbols as defined in `tokenizer.non_speech_tokens()`
-    suppress_tokens: Optional[Union[str, Iterable[int]]] = "-1"
-
-    # timestamp sampling options
-    without_timestamps: bool = False              # use <|notimestamps|> to sample text tokens only
-    max_initial_timestamp: Optional[float] = 1.0  # the initial timestamp cannot be later than this
-
-    # implementation details
-    fp16: bool = True  # use fp16 for most of the calculation
-
-
-@dataclass(frozen=True)
-class DecodingResult:
-    audio_features: Tensor
-    language: str
-    language_probs: Optional[Dict[str, float]] = None
-    tokens: List[int] = field(default_factory=list)
-    text: str = ""
-    avg_logprob: float = np.nan
-    no_speech_prob: float = np.nan
-    temperature: float = np.nan
-    compression_ratio: float = np.nan
-
-
-class Inference:
-    def logits(self, tokens: Tensor, audio_features: Tensor) -> Tensor:
-        """Perform a forward pass on the decoder and return per-token logits"""
-        raise NotImplementedError
-
-    def rearrange_kv_cache(self, source_indices) -> None:
-        """Update the key-value cache according to the updated beams"""
-        raise NotImplementedError
-
-    def cleanup_caching(self) -> None:
-        """Clean up any resources or hooks after decoding is finished"""
-        pass
-
-
-class PyTorchInference(Inference):
-    def __init__(self, model: "Whisper", initial_token_length: int):
-        self.model: "Whisper" = model
-        self.initial_token_length = initial_token_length
-        self.kv_cache = {}
-        self.hooks = []
-
-    def logits(self, tokens: Tensor, audio_features: Tensor) -> Tensor:
-        if not self.kv_cache:
-            self.kv_cache, self.hooks = self.model.install_kv_cache_hooks()
-
-        if tokens.shape[-1] > self.initial_token_length:
-            # only need to use the last token except in the first forward pass
-            tokens = tokens[:, -1:]
-
-        return self.model.decoder(tokens, audio_features, kv_cache=self.kv_cache)
-
-    def cleanup_caching(self):
-        for hook in self.hooks:
-            hook.remove()
-
-        self.kv_cache = {}
-        self.hooks = []
-
-    def rearrange_kv_cache(self, source_indices):
-        for module, tensor in self.kv_cache.items():
-            # update the key/value cache to contain the selected sequences
-            self.kv_cache[module] = tensor[source_indices].detach()
-
-
-class SequenceRanker:
-    def rank(self, tokens: List[List[Tensor]], sum_logprobs: List[List[float]]) -> List[int]:
-        """
-        Given a list of groups of samples and their cumulative log probabilities,
-        return the indices of the samples in each group to select as the final result
-        """
-        raise NotImplementedError
-
-
-class MaximumLikelihoodRanker(SequenceRanker):
-    """
-    Select the sample with the highest log probabilities, penalized using either
-    a simple length normalization or Google NMT paper's length penalty
-    """
-
-    def __init__(self, length_penalty: Optional[float]):
-        self.length_penalty = length_penalty
-
-    def rank(self, tokens: List[List[Tensor]], sum_logprobs: List[List[float]]):
-        def scores(logprobs, lengths):
-            result = []
-            for logprob, length in zip(logprobs, lengths):
-                if self.length_penalty is None:
-                    penalty = length
-                else:
-                    # from the Google NMT paper
-                    penalty = ((5 + length) / 6) ** self.length_penalty
-                result.append(logprob / penalty)
-            return result
-
-        # get the sequence with the highest score
-        lengths = [[len(t) for t in s] for s in tokens]
-        return [np.argmax(scores(p, l)) for p, l in zip(sum_logprobs, lengths)]
-
-
-class TokenDecoder:
-    def reset(self):
-        """Initialize any stateful variables for decoding a new sequence"""
-
-    def update(self, tokens: Tensor, logits: Tensor, sum_logprobs: Tensor) -> Tuple[Tensor, bool]:
-        """Specify how to select the next token, based on the current trace and logits
-
-        Parameters
-        ----------
-        tokens : Tensor, shape = (n_batch, current_sequence_length)
-            all tokens in the context so far, including the prefix and sot_sequence tokens
-
-        logits : Tensor, shape = (n_batch, vocab_size)
-            per-token logits of the probability distribution at the current step
-
-        sum_logprobs : Tensor, shape = (n_batch)
-            cumulative log probabilities for each sequence
-
-        Returns
-        -------
-        tokens : Tensor, shape = (n_batch, current_sequence_length + 1)
-            the tokens, appended with the selected next token
-
-        completed : bool
-            True if all sequences has reached the end of text
-
-        """
-        raise NotImplementedError
-
-    def finalize(
-        self, tokens: Tensor, sum_logprobs: Tensor
-    ) -> Tuple[Sequence[Sequence[Tensor]], List[List[float]]]:
-        """Finalize search and return the final candidate sequences
-
-        Parameters
-        ----------
-        tokens : Tensor, shape = (n_audio, n_group, current_sequence_length)
-            all tokens in the context so far, including the prefix and sot_sequence
-
-        sum_logprobs : Tensor, shape = (n_audio, n_group)
-            cumulative log probabilities for each sequence
-
-        Returns
-        -------
-        tokens : Sequence[Sequence[Tensor]], length = n_audio
-            sequence of Tensors containing candidate token sequences, for each audio input
-
-        sum_logprobs : List[List[float]], length = n_audio
-            sequence of cumulative log probabilities corresponding to the above
-
-        """
-        raise NotImplementedError
-
-
-class GreedyDecoder(TokenDecoder):
-    def __init__(self, temperature: float, eot: int):
-        self.temperature = temperature
-        self.eot = eot
-
-    def update(self, tokens: Tensor, logits: Tensor, sum_logprobs: Tensor) -> Tuple[Tensor, bool]:
-        temperature = self.temperature
-        if temperature == 0:
-            next_tokens = logits.argmax(dim=-1)
-        else:
-            next_tokens = Categorical(logits=logits / temperature).sample()
-
-        logprobs = F.log_softmax(logits.float(), dim=-1)
-        current_logprobs = logprobs[torch.arange(logprobs.shape[0]), next_tokens]
-        sum_logprobs += current_logprobs * (tokens[:, -1] != self.eot)
-
-        next_tokens[tokens[:, -1] == self.eot] = self.eot
-        tokens = torch.cat([tokens, next_tokens[:, None]], dim=-1)
-
-        completed = (tokens[:, -1] == self.eot).all()
-        return tokens, completed
-
-    def finalize(self, tokens: Tensor, sum_logprobs: Tensor):
-        # make sure each sequence has at least one EOT token at the end
-        tokens = F.pad(tokens, (0, 1), value=self.eot)
-        return tokens, sum_logprobs.tolist()
-
-
-class BeamSearchDecoder(TokenDecoder):
-    def __init__(self, beam_size: int, eot: int, inference: Inference, patience: Optional[float] = None):
-        self.beam_size = beam_size
-        self.eot = eot
-        self.inference = inference
-        self.patience = patience or 1.0
-        self.max_candidates: int = round(beam_size * self.patience)
-        self.finished_sequences = None
-
-        assert self.max_candidates > 0, f"Invalid beam size ({beam_size}) or patience ({patience})"
-
-    def reset(self):
-        self.finished_sequences = None
-
-    def update(self, tokens: Tensor, logits: Tensor, sum_logprobs: Tensor) -> Tuple[Tensor, bool]:
-        if tokens.shape[0] % self.beam_size != 0:
-            raise ValueError(f"{tokens.shape}[0] % {self.beam_size} != 0")
-
-        n_audio = tokens.shape[0] // self.beam_size
-        if self.finished_sequences is None:  # for the first update
-            self.finished_sequences = [{} for _ in range(n_audio)]
-
-        logprobs = F.log_softmax(logits.float(), dim=-1)
-        next_tokens, source_indices, finished_sequences = [], [], []
-        for i in range(n_audio):
-            scores, sources, finished = {}, {}, {}
-
-            # STEP 1: calculate the cumulative log probabilities for possible candidates
-            for j in range(self.beam_size):
-                idx = i * self.beam_size + j
-                prefix = tokens[idx].tolist()
-                for logprob, token in zip(*logprobs[idx].topk(self.beam_size + 1)):
-                    new_logprob = (sum_logprobs[idx] + logprob).item()
-                    sequence = tuple(prefix + [token.item()])
-                    scores[sequence] = new_logprob
-                    sources[sequence] = idx
-
-            # STEP 2: rank the candidates and keep the top beam_size sequences for each audio
-            saved = 0
-            for sequence in sorted(scores, key=scores.get, reverse=True):
-                if sequence[-1] == self.eot:
-                    finished[sequence] = scores[sequence]
-                else:
-                    sum_logprobs[len(next_tokens)] = scores[sequence]
-                    next_tokens.append(sequence)
-                    source_indices.append(sources[sequence])
-
-                    saved += 1
-                    if saved == self.beam_size:
-                        break
-
-            finished_sequences.append(finished)
-
-        tokens = torch.tensor(next_tokens, device=tokens.device)
-        self.inference.rearrange_kv_cache(source_indices)
-
-        # add newly finished sequences to self.finished_sequences
-        assert len(self.finished_sequences) == len(finished_sequences)
-        for previously_finished, newly_finished in zip(self.finished_sequences, finished_sequences):
-            for seq in sorted(newly_finished, key=newly_finished.get, reverse=True):
-                if len(previously_finished) >= self.max_candidates:
-                    break  # the candidate list is full
-                previously_finished[seq] = newly_finished[seq]
-
-        # mark as completed if all audio has enough number of samples
-        completed = all(
-            len(sequences) >= self.max_candidates for sequences in self.finished_sequences
-        )
-        return tokens, completed
-
-    def finalize(self, preceding_tokens: Tensor, sum_logprobs: Tensor):
-        # collect all finished sequences, including patience, and add unfinished ones if not enough
-        sum_logprobs = sum_logprobs.cpu()
-        for i, sequences in enumerate(self.finished_sequences):
-            if len(sequences) < self.beam_size:  # when not enough sequences are finished
-                for j in list(np.argsort(sum_logprobs[i]))[::-1]:
-                    sequence = preceding_tokens[i, j].tolist() + [self.eot]
-                    sequences[tuple(sequence)] = sum_logprobs[i][j].item()
-                    if len(sequences) >= self.beam_size:
-                        break
-
-        tokens: List[List[Tensor]] = [
-            [torch.tensor(seq) for seq in sequences.keys()] for sequences in self.finished_sequences
-        ]
-        sum_logprobs: List[List[float]] = [
-            list(sequences.values()) for sequences in self.finished_sequences
-        ]
-        return tokens, sum_logprobs
-
-
-class LogitFilter:
-    def apply(self, logits: Tensor, tokens: Tensor) -> None:
-        """Apply any filtering or masking to logits in-place
-
-        Parameters
-        ----------
-        logits : Tensor, shape = (n_batch, vocab_size)
-            per-token logits of the probability distribution at the current step
-
-        tokens : Tensor, shape = (n_batch, current_sequence_length)
-            all tokens in the context so far, including the prefix and sot_sequence tokens
-
-        """
-        raise NotImplementedError
-
-
-class SuppressBlank(LogitFilter):
-    def __init__(self, tokenizer: Tokenizer, sample_begin: int):
-        self.tokenizer = tokenizer
-        self.sample_begin = sample_begin
-
-    def apply(self, logits: Tensor, tokens: Tensor):
-        if tokens.shape[1] == self.sample_begin:
-            logits[:, self.tokenizer.encode(" ") + [self.tokenizer.eot]] = -np.inf
-
-
-class SuppressTokens(LogitFilter):
-    def __init__(self, suppress_tokens: Sequence[int]):
-        self.suppress_tokens = list(suppress_tokens)
-
-    def apply(self, logits: Tensor, tokens: Tensor):
-        logits[:, self.suppress_tokens] = -np.inf
-
-
-class ApplyTimestampRules(LogitFilter):
-    def __init__(
-        self, tokenizer: Tokenizer, sample_begin: int, max_initial_timestamp_index: Optional[int]
-    ):
-        self.tokenizer = tokenizer
-        self.sample_begin = sample_begin
-        self.max_initial_timestamp_index = max_initial_timestamp_index
-
-    def apply(self, logits: Tensor, tokens: Tensor):
-        # suppress <|notimestamps|> which is handled by without_timestamps
-        if self.tokenizer.no_timestamps is not None:
-            logits[:, self.tokenizer.no_timestamps] = -np.inf
-
-        # timestamps have to appear in pairs, except directly before EOT; mask logits accordingly
-        for k in range(tokens.shape[0]):
-            seq = [t for t in tokens[k, self.sample_begin :].tolist()]
-            last_was_timestamp = len(seq) >= 1 and seq[-1] >= self.tokenizer.timestamp_begin
-            penultimate_was_timestamp = len(seq) < 2 or seq[-2] >= self.tokenizer.timestamp_begin
-
-            if last_was_timestamp:
-                if penultimate_was_timestamp:  # has to be non-timestamp
-                    logits[k, self.tokenizer.timestamp_begin :] = -np.inf
-                else:  # cannot be normal text tokens
-                    logits[k, : self.tokenizer.eot] = -np.inf
-
-        if tokens.shape[1] == self.sample_begin:
-            # suppress generating non-timestamp tokens at the beginning
-            logits[:, : self.tokenizer.timestamp_begin] = -np.inf
-
-            # apply the `max_initial_timestamp` option
-            if self.max_initial_timestamp_index is not None:
-                last_allowed = self.tokenizer.timestamp_begin + self.max_initial_timestamp_index
-                logits[:, last_allowed + 1 :] = -np.inf
-
-        # if sum of probability over timestamps is above any other token, sample timestamp
-        logprobs = F.log_softmax(logits.float(), dim=-1)
-        for k in range(tokens.shape[0]):
-            timestamp_logprob = logprobs[k, self.tokenizer.timestamp_begin :].logsumexp(dim=-1)
-            max_text_token_logprob = logprobs[k, : self.tokenizer.timestamp_begin].max()
-            if timestamp_logprob > max_text_token_logprob:
-                logits[k, : self.tokenizer.timestamp_begin] = -np.inf
-
-
-class DecodingTask:
-    inference: Inference
-    sequence_ranker: SequenceRanker
-    decoder: TokenDecoder
-    logit_filters: List[LogitFilter]
-
-    def __init__(self, model: "Whisper", options: DecodingOptions):
-        self.model = model
-
-        language = options.language or "en"
-        tokenizer = get_tokenizer(model.is_multilingual, language=language, task=options.task)
-        self.tokenizer: Tokenizer = tokenizer
-        self.options: DecodingOptions = self._verify_options(options)
-
-        self.n_group: int = options.beam_size or options.best_of or 1
-        self.n_ctx: int = model.dims.n_text_ctx
-        self.sample_len: int = options.sample_len or model.dims.n_text_ctx // 2
-
-        self.sot_sequence: Tuple[int] = tokenizer.sot_sequence
-        if self.options.without_timestamps:
-            self.sot_sequence = tokenizer.sot_sequence_including_notimestamps
-
-        self.initial_tokens: Tuple[int] = self._get_initial_tokens()
-        self.sample_begin: int = len(self.initial_tokens)
-        self.sot_index: int = self.initial_tokens.index(tokenizer.sot)
-
-        # inference: implements the forward pass through the decoder, including kv caching
-        self.inference = PyTorchInference(model, len(self.initial_tokens))
-
-        # sequence ranker: implements how to rank a group of sampled sequences
-        self.sequence_ranker = MaximumLikelihoodRanker(options.length_penalty)
-
-        # decoder: implements how to select the next tokens, given the autoregressive distribution
-        if options.beam_size is not None:
-            self.decoder = BeamSearchDecoder(
-                options.beam_size, tokenizer.eot, self.inference, options.patience
-            )
-        else:
-            self.decoder = GreedyDecoder(options.temperature, tokenizer.eot)
-
-        # logit filters: applies various rules to suppress or penalize certain tokens
-        self.logit_filters = []
-        if self.options.suppress_blank:
-            self.logit_filters.append(SuppressBlank(self.tokenizer, self.sample_begin))
-        if self.options.suppress_tokens:
-            self.logit_filters.append(SuppressTokens(self._get_suppress_tokens()))
-        if not options.without_timestamps:
-            precision = CHUNK_LENGTH / model.dims.n_audio_ctx  # usually 0.02 seconds
-            max_initial_timestamp_index = None
-            if options.max_initial_timestamp:
-                max_initial_timestamp_index = round(self.options.max_initial_timestamp / precision)
-            self.logit_filters.append(
-                ApplyTimestampRules(tokenizer, self.sample_begin, max_initial_timestamp_index)
-            )
-
-    def _verify_options(self, options: DecodingOptions) -> DecodingOptions:
-        if options.beam_size is not None and options.best_of is not None:
-            raise ValueError("beam_size and best_of can't be given together")
-        if options.temperature == 0:
-            if options.best_of is not None:
-                raise ValueError("best_of with greedy sampling (T=0) is not compatible")
-        if options.patience is not None and options.beam_size is None:
-            raise ValueError("patience requires beam_size to be given")
-        if options.length_penalty is not None and not (0 <= options.length_penalty <= 1):
-            raise ValueError("length_penalty (alpha) should be a value between 0 and 1")
-
-        return options
-
-    def _get_initial_tokens(self) -> Tuple[int]:
-        tokens = list(self.sot_sequence)
-        prefix = self.options.prefix
-        prompt = self.options.prompt
-
-        if prefix:
-            prefix_tokens = (
-                self.tokenizer.encode(" " + prefix.strip()) if isinstance(prefix, str) else prefix
-            )
-            if self.sample_len is not None:
-                max_prefix_len = self.n_ctx // 2 - self.sample_len
-                prefix_tokens = prefix_tokens[-max_prefix_len:]
-            tokens = tokens + prefix_tokens
-
-        if prompt:
-            prompt_tokens = (
-                self.tokenizer.encode(" " + prompt.strip()) if isinstance(prompt, str) else prompt
-            )
-            tokens = [self.tokenizer.sot_prev] + prompt_tokens[-(self.n_ctx // 2 - 1) :] + tokens
-
-        return tuple(tokens)
-
-    def _get_suppress_tokens(self) -> Tuple[int]:
-        suppress_tokens = self.options.suppress_tokens
-
-        if isinstance(suppress_tokens, str):
-            suppress_tokens = [int(t) for t in suppress_tokens.split(",")]
-
-        if -1 in suppress_tokens:
-            suppress_tokens = [t for t in suppress_tokens if t >= 0]
-            suppress_tokens.extend(self.tokenizer.non_speech_tokens)
-        elif suppress_tokens is None or len(suppress_tokens) == 0:
-            suppress_tokens = []  # interpret empty string as an empty list
-        else:
-            assert isinstance(suppress_tokens, list), "suppress_tokens must be a list"
-
-        suppress_tokens.extend(
-            [self.tokenizer.sot, self.tokenizer.sot_prev, self.tokenizer.sot_lm]
-        )
-        if self.tokenizer.no_speech is not None:
-            # no-speech probability is collected separately
-            suppress_tokens.append(self.tokenizer.no_speech)
-
-        return tuple(sorted(set(suppress_tokens)))
-
-    def _get_audio_features(self, mel: Tensor):
-        if self.options.fp16:
-            mel = mel.half()
-
-        if mel.shape[-2:] == (self.model.dims.n_audio_ctx, self.model.dims.n_audio_state):
-            # encoded audio features are given; skip audio encoding
-            print("encoded audio features are given; skip audio encoding")
-            audio_features = mel
-        else:
-            print(mel.shape)
-            print("===============================")
-            audio_features = self.model.encoder(mel)
-
-        if audio_features.dtype != (torch.float16 if self.options.fp16 else torch.float32):
-            return TypeError(f"audio_features has an incorrect dtype: {audio_features.dtype}")
-
-        return audio_features
-
-    def _detect_language(self, audio_features: Tensor, tokens: Tensor):
-        languages = [self.options.language] * audio_features.shape[0]
-        lang_probs = None
-
-        if self.options.language is None or self.options.task == "lang_id":
-            lang_tokens, lang_probs = self.model.detect_language(audio_features, self.tokenizer)
-            languages = [max(probs, key=probs.get) for probs in lang_probs]
-            if self.options.language is None:
-                tokens[:, self.sot_index + 1] = lang_tokens  # write language tokens
-
-        return languages, lang_probs
-
-    def _main_loop(self, audio_features: Tensor, tokens: Tensor):
-        assert audio_features.shape[0] == tokens.shape[0]
-        n_batch = tokens.shape[0]
-        sum_logprobs: Tensor = torch.zeros(n_batch, device=audio_features.device)
-        no_speech_probs = [np.nan] * n_batch
-
-        try:
-            for i in range(self.sample_len):
-                logits = self.inference.logits(tokens, audio_features)
-
-                if i == 0 and self.tokenizer.no_speech is not None:  # save no_speech_probs
-                    probs_at_sot = logits[:, self.sot_index].float().softmax(dim=-1)
-                    no_speech_probs = probs_at_sot[:, self.tokenizer.no_speech].tolist()
-
-                # now we need to consider the logits at the last token only
-                logits = logits[:, -1]
-
-                # apply the logit filters, e.g. for suppressing or applying penalty to
-                for logit_filter in self.logit_filters:
-                    logit_filter.apply(logits, tokens)
-
-                # expand the tokens tensor with the selected next tokens
-                tokens, completed = self.decoder.update(tokens, logits, sum_logprobs)
-
-                if completed or tokens.shape[-1] > self.n_ctx:
-                    break
-        finally:
-            self.inference.cleanup_caching()
-
-        return tokens, sum_logprobs, no_speech_probs
-
-    @torch.no_grad()
-    def run(self, mel: Tensor) -> List[DecodingResult]:
-        self.decoder.reset()
-        tokenizer: Tokenizer = self.tokenizer
-        n_audio: int = mel.shape[0]
-
-        audio_features: Tensor = self._get_audio_features(mel)  # encoder forward pass
-        tokens: Tensor = torch.tensor([self.initial_tokens]).repeat(n_audio, 1)
-
-        # detect language if requested, overwriting the language token
-        languages, language_probs = self._detect_language(audio_features, tokens)
-        if self.options.task == "lang_id":
-            return [
-                DecodingResult(audio_features=features, language=language, language_probs=probs)
-                for features, language, probs in zip(audio_features, languages, language_probs)
-            ]
-
-        # repeat the audio & text tensors by the group size, for beam search or best-of-n sampling
-        audio_features = audio_features.repeat_interleave(self.n_group, dim=0)
-        tokens = tokens.repeat_interleave(self.n_group, dim=0).to(audio_features.device)
-
-        # call the main sampling loop
-        tokens, sum_logprobs, no_speech_probs = self._main_loop(audio_features, tokens)
-
-        # reshape the tensors to have (n_audio, n_group) as the first two dimensions
-        audio_features = audio_features[:: self.n_group]
-        no_speech_probs = no_speech_probs[:: self.n_group]
-        assert audio_features.shape[0] == len(no_speech_probs) == n_audio
-
-        tokens = tokens.reshape(n_audio, self.n_group, -1)
-        sum_logprobs = sum_logprobs.reshape(n_audio, self.n_group)
-
-        # get the final candidates for each group, and slice between the first sampled token and EOT
-        tokens, sum_logprobs = self.decoder.finalize(tokens, sum_logprobs)
-        tokens: List[List[Tensor]] = [
-            [t[self.sample_begin : (t == tokenizer.eot).nonzero()[0, 0]] for t in s] for s in tokens
-        ]
-
-        # select the top-ranked sample in each group
-        selected = self.sequence_ranker.rank(tokens, sum_logprobs)
-        tokens: List[List[int]] = [t[i].tolist() for i, t in zip(selected, tokens)]
-        texts: List[str] = [tokenizer.decode(t).strip() for t in tokens]
-
-        sum_logprobs: List[float] = [lp[i] for i, lp in zip(selected, sum_logprobs)]
-        avg_logprobs: List[float] = [lp / (len(t) + 1) for t, lp in zip(tokens, sum_logprobs)]
-
-        fields = (texts, languages, tokens, audio_features, avg_logprobs, no_speech_probs)
-        if len(set(map(len, fields))) != 1:
-            raise RuntimeError(f"inconsistent result lengths: {list(map(len, fields))}")
-
-        return [
-            DecodingResult(
-                audio_features=features,
-                language=language,
-                tokens=tokens,
-                text=text,
-                avg_logprob=avg_logprob,
-                no_speech_prob=no_speech_prob,
-                temperature=self.options.temperature,
-                compression_ratio=compression_ratio(text),
-            )
-            for text, language, tokens, features, avg_logprob, no_speech_prob in zip(*fields)
-        ]
-
-
-@torch.no_grad()
-def decode(model: "Whisper", mel: Tensor, options: DecodingOptions = DecodingOptions()) -> Union[DecodingResult, List[DecodingResult]]:
-    """
-    Performs decoding of 30-second audio segment(s), provided as Mel spectrogram(s).
-
-    Parameters
-    ----------
-    model: Whisper
-        the Whisper model instance
-
-    mel: torch.Tensor, shape = (80, 3000) or (*, 80, 3000)
-        A tensor containing the Mel spectrogram(s)
-
-    options: DecodingOptions
-        A dataclass that contains all necessary options for decoding 30-second segments
-
-    Returns
-    -------
-    result: Union[DecodingResult, List[DecodingResult]]
-        The result(s) of decoding contained in `DecodingResult` dataclass instance(s)
-    """
-    single = mel.ndim == 2
-    if single:
-        mel = mel.unsqueeze(0)
-    result = DecodingTask(model, options).run(mel)
-    
-    if single:
-        result = result[0]
-
-    return result
diff --git a/spaces/GXSA/bingo/src/components/chat-panel.tsx b/spaces/GXSA/bingo/src/components/chat-panel.tsx
deleted file mode 100644
index 56b2112bd75ba08134383871177851fa2e3f43a4..0000000000000000000000000000000000000000
--- a/spaces/GXSA/bingo/src/components/chat-panel.tsx
+++ /dev/null
@@ -1,153 +0,0 @@
-'use client'
-
-import * as React from 'react'
-import Image from 'next/image'
-import Textarea from 'react-textarea-autosize'
-import { useAtomValue } from 'jotai'
-import { useEnterSubmit } from '@/lib/hooks/use-enter-submit'
-import { cn } from '@/lib/utils'
-
-import BrushIcon from '@/assets/images/brush.svg'
-import ChatIcon from '@/assets/images/chat.svg'
-import VisualSearchIcon from '@/assets/images/visual-search.svg'
-import SendIcon from '@/assets/images/send.svg'
-import PinIcon from '@/assets/images/pin.svg'
-import PinFillIcon from '@/assets/images/pin-fill.svg'
-
-import { useBing } from '@/lib/hooks/use-bing'
-import { voiceListenAtom } from '@/state'
-import Voice from './voice'
-import { ChatImage } from './chat-image'
-import { ChatAttachments } from './chat-attachments'
-
-export interface ChatPanelProps
-  extends Pick<
-    ReturnType<typeof useBing>,
-    | 'generating'
-    | 'input'
-    | 'setInput'
-    | 'sendMessage'
-    | 'resetConversation'
-    | 'isSpeaking'
-    | 'attachmentList'
-    | 'uploadImage'
-    | 'setAttachmentList'
-  > {
-  id?: string
-  className?: string
-}
-
-export function ChatPanel({
-  isSpeaking,
-  generating,
-  input,
-  setInput,
-  className,
-  sendMessage,
-  resetConversation,
-  attachmentList,
-  uploadImage,
-  setAttachmentList
-}: ChatPanelProps) {
-  const inputRef = React.useRef<HTMLTextAreaElement>(null)
-  const {formRef, onKeyDown} = useEnterSubmit()
-  const [focused, setFocused] = React.useState(false)
-  const [active, setActive] = React.useState(false)
-  const [pin, setPin] = React.useState(false)
-  const [tid, setTid] = React.useState<any>()
-  const voiceListening = useAtomValue(voiceListenAtom)
-
-  const setBlur = React.useCallback(() => {
-    clearTimeout(tid)
-    setActive(false)
-    const _tid = setTimeout(() => setFocused(false), 2000);
-    setTid(_tid)
-  }, [tid])
-
-  const setFocus = React.useCallback(() => {
-    setFocused(true)
-    setActive(true)
-    clearTimeout(tid)
-    inputRef.current?.focus()
-  }, [tid])
-
-  React.useEffect(() => {
-    if (input) {
-      setFocus()
-    }
-  }, [input, setFocus])
-
-  return (
-    <form
-      className={cn('chat-panel', className)}
-      onSubmit={async e => {
-        e.preventDefault()
-        if (generating) {
-          return;
-        }
-        if (!input?.trim()) {
-          return
-        }
-        setInput('')
-        setPin(false)
-        await sendMessage(input)
-      }}
-      ref={formRef}
-    >
-      <div className="action-bar pb-4">
-        <div className={cn('action-root', { focus: active || pin })} speech-state="hidden" visual-search="" drop-target="">
-          <div className="fade bottom">
-            <div className="background"></div>
-          </div>
-          <div className={cn('outside-left-container', { collapsed: focused })}>
-            <div className="button-compose-wrapper">
-              <button className="body-2 button-compose" type="button" aria-label="新主题" onClick={resetConversation}>
-                <div className="button-compose-content">
-                  <Image className="pl-2" alt="brush" src={BrushIcon} width={40} />
-                  <div className="button-compose-text">新主题</div>
-                </div>
-              </button>
-            </div>
-          </div>
-          <div
-            className={cn('main-container', { active: active || pin })}
-            style={{ minHeight: pin ? '360px' : undefined }}
-            onClick={setFocus}
-            onBlur={setBlur}
-          >
-            <div className="main-bar">
-              <Image alt="chat" src={ChatIcon} width={20} color="blue" />
-              <Textarea
-                ref={inputRef}
-                tabIndex={0}
-                onKeyDown={onKeyDown}
-                rows={1}
-                value={input}
-                onChange={e => setInput(e.target.value.slice(0, 4000))}
-                placeholder={voiceListening ? '持续对话中...对话完成说“发送”即可' : 'Shift + Enter 换行'}
-                spellCheck={false}
-                className="message-input min-h-[24px] -mx-1 w-full text-base resize-none bg-transparent focus-within:outline-none"
-              />
-              <ChatImage uploadImage={uploadImage}>
-                <Image alt="visual-search" src={VisualSearchIcon} width={24} />
-              </ChatImage>
-              <Voice setInput={setInput} sendMessage={sendMessage} isSpeaking={isSpeaking} input={input} />
-              <button type="submit">
-                <Image alt="send" src={SendIcon} width={20} style={{ marginTop: '2px' }} />
-              </button>
-            </div>
-            <ChatAttachments attachmentList={attachmentList} setAttachmentList={setAttachmentList} uploadImage={uploadImage} />
-            <div className="body-1 bottom-bar">
-              <div className="letter-counter"><span>{input.length}</span>/4000</div>
-              <button onClick={() => {
-                setPin(!pin)
-              }} className="pr-2">
-               <Image alt="pin" src={pin ? PinFillIcon : PinIcon} width={20} />
-              </button>
-            </div>
-          </div>
-        </div>
-      </div>
-    </form>
-  )
-}
diff --git a/spaces/GastonMazzei/escher-inpaint-project/glide_text2im/nn.py b/spaces/GastonMazzei/escher-inpaint-project/glide_text2im/nn.py
deleted file mode 100644
index 1a5b2f19e692dace9ade33d845632cea0479cc88..0000000000000000000000000000000000000000
--- a/spaces/GastonMazzei/escher-inpaint-project/glide_text2im/nn.py
+++ /dev/null
@@ -1,105 +0,0 @@
-"""
-Various utilities for neural networks.
-"""
-
-import math
-
-import torch as th
-import torch.nn as nn
-import torch.nn.functional as F
-
-
-class GroupNorm32(nn.GroupNorm):
-    def __init__(self, num_groups, num_channels, swish, eps=1e-5):
-        super().__init__(num_groups=num_groups, num_channels=num_channels, eps=eps)
-        self.swish = swish
-
-    def forward(self, x):
-        y = super().forward(x.float()).to(x.dtype)
-        if self.swish == 1.0:
-            y = F.silu(y)
-        elif self.swish:
-            y = y * F.sigmoid(y * float(self.swish))
-        return y
-
-
-def conv_nd(dims, *args, **kwargs):
-    """
-    Create a 1D, 2D, or 3D convolution module.
-    """
-    if dims == 1:
-        return nn.Conv1d(*args, **kwargs)
-    elif dims == 2:
-        return nn.Conv2d(*args, **kwargs)
-    elif dims == 3:
-        return nn.Conv3d(*args, **kwargs)
-    raise ValueError(f"unsupported dimensions: {dims}")
-
-
-def linear(*args, **kwargs):
-    """
-    Create a linear module.
-    """
-    return nn.Linear(*args, **kwargs)
-
-
-def avg_pool_nd(dims, *args, **kwargs):
-    """
-    Create a 1D, 2D, or 3D average pooling module.
-    """
-    if dims == 1:
-        return nn.AvgPool1d(*args, **kwargs)
-    elif dims == 2:
-        return nn.AvgPool2d(*args, **kwargs)
-    elif dims == 3:
-        return nn.AvgPool3d(*args, **kwargs)
-    raise ValueError(f"unsupported dimensions: {dims}")
-
-
-def zero_module(module):
-    """
-    Zero out the parameters of a module and return it.
-    """
-    for p in module.parameters():
-        p.detach().zero_()
-    return module
-
-
-def scale_module(module, scale):
-    """
-    Scale the parameters of a module and return it.
-    """
-    for p in module.parameters():
-        p.detach().mul_(scale)
-    return module
-
-
-def normalization(channels, swish=0.0):
-    """
-    Make a standard normalization layer, with an optional swish activation.
-
-    :param channels: number of input channels.
-    :return: an nn.Module for normalization.
-    """
-    return GroupNorm32(num_channels=channels, num_groups=32, swish=swish)
-
-
-def timestep_embedding(timesteps, dim, max_period=10000):
-    """
-    Create sinusoidal timestep embeddings.
-
-    :param timesteps: a 1-D Tensor of N indices, one per batch element.
-                      These may be fractional.
-    :param dim: the dimension of the output.
-    :param max_period: controls the minimum frequency of the embeddings.
-    :return: an [N x dim] Tensor of positional embeddings.
-    """
-    half = dim // 2
-    freqs = th.exp(
-        -math.log(max_period) * th.arange(start=0, end=half, dtype=th.float32) / half
-    ).to(device=timesteps.device)
-    args = timesteps[:, None].float() * freqs[None]
-    embedding = th.cat([th.cos(args), th.sin(args)], dim=-1)
-    if dim % 2:
-        embedding = th.cat([embedding, th.zeros_like(embedding[:, :1])], dim=-1)
-    return embedding
diff --git "a/spaces/Gmq-x/gpt-academic/crazy_functions/\351\253\230\347\272\247\345\212\237\350\203\275\345\207\275\346\225\260\346\250\241\346\235\277.py" "b/spaces/Gmq-x/gpt-academic/crazy_functions/\351\253\230\347\272\247\345\212\237\350\203\275\345\207\275\346\225\260\346\250\241\346\235\277.py"
deleted file mode 100644
index 7c6a7ffb5cb2c42e6543c75d6ad9dd643f412cd9..0000000000000000000000000000000000000000
--- "a/spaces/Gmq-x/gpt-academic/crazy_functions/\351\253\230\347\272\247\345\212\237\350\203\275\345\207\275\346\225\260\346\250\241\346\235\277.py"
+++ /dev/null
@@ -1,29 +0,0 @@
-from toolbox import CatchException, update_ui
-from .crazy_utils import request_gpt_model_in_new_thread_with_ui_alive
-import datetime
-@CatchException
-def 高阶功能模板函数(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, web_port):
-    """
-    txt             输入栏用户输入的文本，例如需要翻译的一段话，再例如一个包含了待处理文件的路径
-    llm_kwargs      gpt模型参数，如温度和top_p等，一般原样传递下去就行
-    plugin_kwargs   插件模型的参数，暂时没有用武之地
-    chatbot         聊天显示框的句柄，用于显示给用户
-    history         聊天历史，前情提要
-    system_prompt   给gpt的静默提醒
-    web_port        当前软件运行的端口号
-    """
-    history = []    # 清空历史，以免输入溢出
-    chatbot.append(("这是什么功能？", "[Local Message] 请注意，您正在调用一个[函数插件]的模板，该函数面向希望实现更多有趣功能的开发者，它可以作为创建新功能函数的模板（该函数只有20多行代码）。此外我们也提供可同步处理大量文件的多线程Demo供您参考。您若希望分享新的功能模组，请不吝PR！"))
-    yield from update_ui(chatbot=chatbot, history=history) # 刷新界面 # 由于请求gpt需要一段时间，我们先及时地做一次界面更新
-    for i in range(5):
-        currentMonth = (datetime.date.today() + datetime.timedelta(days=i)).month
-        currentDay = (datetime.date.today() + datetime.timedelta(days=i)).day
-        i_say = f'历史中哪些事件发生在{currentMonth}月{currentDay}日？列举两条并发送相关图片。发送图片时，请使用Markdown，将Unsplash API中的PUT_YOUR_QUERY_HERE替换成描述该事件的一个最重要的单词。'
-        gpt_say = yield from request_gpt_model_in_new_thread_with_ui_alive(
-            inputs=i_say, inputs_show_user=i_say, 
-            llm_kwargs=llm_kwargs, chatbot=chatbot, history=[], 
-            sys_prompt="当你想发送一张照片时，请使用Markdown, 并且不要有反斜线, 不要用代码块。使用 Unsplash API (https://source.unsplash.com/1280x720/? < PUT_YOUR_QUERY_HERE >)。"
-        )
-        chatbot[-1] = (i_say, gpt_say)
-        history.append(i_say);history.append(gpt_say)
-        yield from update_ui(chatbot=chatbot, history=history) # 刷新界面 # 界面更新
diff --git a/spaces/GookProxy/Gyul/README.md b/spaces/GookProxy/Gyul/README.md
deleted file mode 100644
index 8672fdd9098d06c411f7a735bdab9641db317d83..0000000000000000000000000000000000000000
--- a/spaces/GookProxy/Gyul/README.md
+++ /dev/null
@@ -1,11 +0,0 @@
----
-title: Gyul
-emoji: 😻
-colorFrom: blue
-colorTo: yellow
-sdk: docker
-pinned: false
----
-
-와 씹련들 어떻게 쳐기어들어와서 키 소진하고 있네<br />
-한남이 만든거 안쓴다면서 키 쓰는거 ㄹㅇ 정병 있음?
\ No newline at end of file
diff --git a/spaces/Gradio-Blocks/Hip_Hop_gRadio/README.md b/spaces/Gradio-Blocks/Hip_Hop_gRadio/README.md
deleted file mode 100644
index 53b93d40ef2bf462add9c6211dfe9f429c5aea8a..0000000000000000000000000000000000000000
--- a/spaces/Gradio-Blocks/Hip_Hop_gRadio/README.md
+++ /dev/null
@@ -1,12 +0,0 @@
----
-title: Hip_Hop_gRadio
-emoji: 🏃
-colorFrom: red
-colorTo: indigo
-sdk: gradio
-sdk_version: 3.0.5
-app_file: app.py
-pinned: false
----
-
-Check out the configuration reference at https://huggingface.co/docs/hub/spaces#reference
diff --git a/spaces/Gradio-Blocks/uniformer_image_detection/configs/faster_rcnn/faster_rcnn_r50_fpn_ohem_1x_coco.py b/spaces/Gradio-Blocks/uniformer_image_detection/configs/faster_rcnn/faster_rcnn_r50_fpn_ohem_1x_coco.py
deleted file mode 100644
index f897e7c55c8b8f0ef7a5db92f29ef1c2415965db..0000000000000000000000000000000000000000
--- a/spaces/Gradio-Blocks/uniformer_image_detection/configs/faster_rcnn/faster_rcnn_r50_fpn_ohem_1x_coco.py
+++ /dev/null
@@ -1,2 +0,0 @@
-_base_ = './faster_rcnn_r50_fpn_1x_coco.py'
-model = dict(train_cfg=dict(rcnn=dict(sampler=dict(type='OHEMSampler'))))
diff --git a/spaces/Gradio-Blocks/uniformer_image_detection/mmdet/core/bbox/samplers/base_sampler.py b/spaces/Gradio-Blocks/uniformer_image_detection/mmdet/core/bbox/samplers/base_sampler.py
deleted file mode 100644
index 9ea35def115b49dfdad8a1f7c040ef3cd983b0d1..0000000000000000000000000000000000000000
--- a/spaces/Gradio-Blocks/uniformer_image_detection/mmdet/core/bbox/samplers/base_sampler.py
+++ /dev/null
@@ -1,101 +0,0 @@
-from abc import ABCMeta, abstractmethod
-
-import torch
-
-from .sampling_result import SamplingResult
-
-
-class BaseSampler(metaclass=ABCMeta):
-    """Base class of samplers."""
-
-    def __init__(self,
-                 num,
-                 pos_fraction,
-                 neg_pos_ub=-1,
-                 add_gt_as_proposals=True,
-                 **kwargs):
-        self.num = num
-        self.pos_fraction = pos_fraction
-        self.neg_pos_ub = neg_pos_ub
-        self.add_gt_as_proposals = add_gt_as_proposals
-        self.pos_sampler = self
-        self.neg_sampler = self
-
-    @abstractmethod
-    def _sample_pos(self, assign_result, num_expected, **kwargs):
-        """Sample positive samples."""
-        pass
-
-    @abstractmethod
-    def _sample_neg(self, assign_result, num_expected, **kwargs):
-        """Sample negative samples."""
-        pass
-
-    def sample(self,
-               assign_result,
-               bboxes,
-               gt_bboxes,
-               gt_labels=None,
-               **kwargs):
-        """Sample positive and negative bboxes.
-
-        This is a simple implementation of bbox sampling given candidates,
-        assigning results and ground truth bboxes.
-
-        Args:
-            assign_result (:obj:`AssignResult`): Bbox assigning results.
-            bboxes (Tensor): Boxes to be sampled from.
-            gt_bboxes (Tensor): Ground truth bboxes.
-            gt_labels (Tensor, optional): Class labels of ground truth bboxes.
-
-        Returns:
-            :obj:`SamplingResult`: Sampling result.
-
-        Example:
-            >>> from mmdet.core.bbox import RandomSampler
-            >>> from mmdet.core.bbox import AssignResult
-            >>> from mmdet.core.bbox.demodata import ensure_rng, random_boxes
-            >>> rng = ensure_rng(None)
-            >>> assign_result = AssignResult.random(rng=rng)
-            >>> bboxes = random_boxes(assign_result.num_preds, rng=rng)
-            >>> gt_bboxes = random_boxes(assign_result.num_gts, rng=rng)
-            >>> gt_labels = None
-            >>> self = RandomSampler(num=32, pos_fraction=0.5, neg_pos_ub=-1,
-            >>>                      add_gt_as_proposals=False)
-            >>> self = self.sample(assign_result, bboxes, gt_bboxes, gt_labels)
-        """
-        if len(bboxes.shape) < 2:
-            bboxes = bboxes[None, :]
-
-        bboxes = bboxes[:, :4]
-
-        gt_flags = bboxes.new_zeros((bboxes.shape[0], ), dtype=torch.uint8)
-        if self.add_gt_as_proposals and len(gt_bboxes) > 0:
-            if gt_labels is None:
-                raise ValueError(
-                    'gt_labels must be given when add_gt_as_proposals is True')
-            bboxes = torch.cat([gt_bboxes, bboxes], dim=0)
-            assign_result.add_gt_(gt_labels)
-            gt_ones = bboxes.new_ones(gt_bboxes.shape[0], dtype=torch.uint8)
-            gt_flags = torch.cat([gt_ones, gt_flags])
-
-        num_expected_pos = int(self.num * self.pos_fraction)
-        pos_inds = self.pos_sampler._sample_pos(
-            assign_result, num_expected_pos, bboxes=bboxes, **kwargs)
-        # We found that sampled indices have duplicated items occasionally.
-        # (may be a bug of PyTorch)
-        pos_inds = pos_inds.unique()
-        num_sampled_pos = pos_inds.numel()
-        num_expected_neg = self.num - num_sampled_pos
-        if self.neg_pos_ub >= 0:
-            _pos = max(1, num_sampled_pos)
-            neg_upper_bound = int(self.neg_pos_ub * _pos)
-            if num_expected_neg > neg_upper_bound:
-                num_expected_neg = neg_upper_bound
-        neg_inds = self.neg_sampler._sample_neg(
-            assign_result, num_expected_neg, bboxes=bboxes, **kwargs)
-        neg_inds = neg_inds.unique()
-
-        sampling_result = SamplingResult(pos_inds, neg_inds, bboxes, gt_bboxes,
-                                         assign_result, gt_flags)
-        return sampling_result
diff --git a/spaces/Gradio-Blocks/uniformer_image_detection/mmdet/models/dense_heads/anchor_free_head.py b/spaces/Gradio-Blocks/uniformer_image_detection/mmdet/models/dense_heads/anchor_free_head.py
deleted file mode 100644
index 1814a0cc4f577f470f74f025440073a0aaa1ebd0..0000000000000000000000000000000000000000
--- a/spaces/Gradio-Blocks/uniformer_image_detection/mmdet/models/dense_heads/anchor_free_head.py
+++ /dev/null
@@ -1,340 +0,0 @@
-from abc import abstractmethod
-
-import torch
-import torch.nn as nn
-from mmcv.cnn import ConvModule, bias_init_with_prob, normal_init
-from mmcv.runner import force_fp32
-
-from mmdet.core import multi_apply
-from ..builder import HEADS, build_loss
-from .base_dense_head import BaseDenseHead
-from .dense_test_mixins import BBoxTestMixin
-
-
-@HEADS.register_module()
-class AnchorFreeHead(BaseDenseHead, BBoxTestMixin):
-    """Anchor-free head (FCOS, Fovea, RepPoints, etc.).
-
-    Args:
-        num_classes (int): Number of categories excluding the background
-            category.
-        in_channels (int): Number of channels in the input feature map.
-        feat_channels (int): Number of hidden channels. Used in child classes.
-        stacked_convs (int): Number of stacking convs of the head.
-        strides (tuple): Downsample factor of each feature map.
-        dcn_on_last_conv (bool): If true, use dcn in the last layer of
-            towers. Default: False.
-        conv_bias (bool | str): If specified as `auto`, it will be decided by
-            the norm_cfg. Bias of conv will be set as True if `norm_cfg` is
-            None, otherwise False. Default: "auto".
-        loss_cls (dict): Config of classification loss.
-        loss_bbox (dict): Config of localization loss.
-        conv_cfg (dict): Config dict for convolution layer. Default: None.
-        norm_cfg (dict): Config dict for normalization layer. Default: None.
-        train_cfg (dict): Training config of anchor head.
-        test_cfg (dict): Testing config of anchor head.
-    """  # noqa: W605
-
-    _version = 1
-
-    def __init__(self,
-                 num_classes,
-                 in_channels,
-                 feat_channels=256,
-                 stacked_convs=4,
-                 strides=(4, 8, 16, 32, 64),
-                 dcn_on_last_conv=False,
-                 conv_bias='auto',
-                 loss_cls=dict(
-                     type='FocalLoss',
-                     use_sigmoid=True,
-                     gamma=2.0,
-                     alpha=0.25,
-                     loss_weight=1.0),
-                 loss_bbox=dict(type='IoULoss', loss_weight=1.0),
-                 conv_cfg=None,
-                 norm_cfg=None,
-                 train_cfg=None,
-                 test_cfg=None):
-        super(AnchorFreeHead, self).__init__()
-        self.num_classes = num_classes
-        self.cls_out_channels = num_classes
-        self.in_channels = in_channels
-        self.feat_channels = feat_channels
-        self.stacked_convs = stacked_convs
-        self.strides = strides
-        self.dcn_on_last_conv = dcn_on_last_conv
-        assert conv_bias == 'auto' or isinstance(conv_bias, bool)
-        self.conv_bias = conv_bias
-        self.loss_cls = build_loss(loss_cls)
-        self.loss_bbox = build_loss(loss_bbox)
-        self.train_cfg = train_cfg
-        self.test_cfg = test_cfg
-        self.conv_cfg = conv_cfg
-        self.norm_cfg = norm_cfg
-        self.fp16_enabled = False
-
-        self._init_layers()
-
-    def _init_layers(self):
-        """Initialize layers of the head."""
-        self._init_cls_convs()
-        self._init_reg_convs()
-        self._init_predictor()
-
-    def _init_cls_convs(self):
-        """Initialize classification conv layers of the head."""
-        self.cls_convs = nn.ModuleList()
-        for i in range(self.stacked_convs):
-            chn = self.in_channels if i == 0 else self.feat_channels
-            if self.dcn_on_last_conv and i == self.stacked_convs - 1:
-                conv_cfg = dict(type='DCNv2')
-            else:
-                conv_cfg = self.conv_cfg
-            self.cls_convs.append(
-                ConvModule(
-                    chn,
-                    self.feat_channels,
-                    3,
-                    stride=1,
-                    padding=1,
-                    conv_cfg=conv_cfg,
-                    norm_cfg=self.norm_cfg,
-                    bias=self.conv_bias))
-
-    def _init_reg_convs(self):
-        """Initialize bbox regression conv layers of the head."""
-        self.reg_convs = nn.ModuleList()
-        for i in range(self.stacked_convs):
-            chn = self.in_channels if i == 0 else self.feat_channels
-            if self.dcn_on_last_conv and i == self.stacked_convs - 1:
-                conv_cfg = dict(type='DCNv2')
-            else:
-                conv_cfg = self.conv_cfg
-            self.reg_convs.append(
-                ConvModule(
-                    chn,
-                    self.feat_channels,
-                    3,
-                    stride=1,
-                    padding=1,
-                    conv_cfg=conv_cfg,
-                    norm_cfg=self.norm_cfg,
-                    bias=self.conv_bias))
-
-    def _init_predictor(self):
-        """Initialize predictor layers of the head."""
-        self.conv_cls = nn.Conv2d(
-            self.feat_channels, self.cls_out_channels, 3, padding=1)
-        self.conv_reg = nn.Conv2d(self.feat_channels, 4, 3, padding=1)
-
-    def init_weights(self):
-        """Initialize weights of the head."""
-        for m in self.cls_convs:
-            if isinstance(m.conv, nn.Conv2d):
-                normal_init(m.conv, std=0.01)
-        for m in self.reg_convs:
-            if isinstance(m.conv, nn.Conv2d):
-                normal_init(m.conv, std=0.01)
-        bias_cls = bias_init_with_prob(0.01)
-        normal_init(self.conv_cls, std=0.01, bias=bias_cls)
-        normal_init(self.conv_reg, std=0.01)
-
-    def _load_from_state_dict(self, state_dict, prefix, local_metadata, strict,
-                              missing_keys, unexpected_keys, error_msgs):
-        """Hack some keys of the model state dict so that can load checkpoints
-        of previous version."""
-        version = local_metadata.get('version', None)
-        if version is None:
-            # the key is different in early versions
-            # for example, 'fcos_cls' become 'conv_cls' now
-            bbox_head_keys = [
-                k for k in state_dict.keys() if k.startswith(prefix)
-            ]
-            ori_predictor_keys = []
-            new_predictor_keys = []
-            # e.g. 'fcos_cls' or 'fcos_reg'
-            for key in bbox_head_keys:
-                ori_predictor_keys.append(key)
-                key = key.split('.')
-                conv_name = None
-                if key[1].endswith('cls'):
-                    conv_name = 'conv_cls'
-                elif key[1].endswith('reg'):
-                    conv_name = 'conv_reg'
-                elif key[1].endswith('centerness'):
-                    conv_name = 'conv_centerness'
-                else:
-                    assert NotImplementedError
-                if conv_name is not None:
-                    key[1] = conv_name
-                    new_predictor_keys.append('.'.join(key))
-                else:
-                    ori_predictor_keys.pop(-1)
-            for i in range(len(new_predictor_keys)):
-                state_dict[new_predictor_keys[i]] = state_dict.pop(
-                    ori_predictor_keys[i])
-        super()._load_from_state_dict(state_dict, prefix, local_metadata,
-                                      strict, missing_keys, unexpected_keys,
-                                      error_msgs)
-
-    def forward(self, feats):
-        """Forward features from the upstream network.
-
-        Args:
-            feats (tuple[Tensor]): Features from the upstream network, each is
-                a 4D-tensor.
-
-        Returns:
-            tuple: Usually contain classification scores and bbox predictions.
-                cls_scores (list[Tensor]): Box scores for each scale level,
-                    each is a 4D-tensor, the channel number is
-                    num_points * num_classes.
-                bbox_preds (list[Tensor]): Box energies / deltas for each scale
-                    level, each is a 4D-tensor, the channel number is
-                    num_points * 4.
-        """
-        return multi_apply(self.forward_single, feats)[:2]
-
-    def forward_single(self, x):
-        """Forward features of a single scale level.
-
-        Args:
-            x (Tensor): FPN feature maps of the specified stride.
-
-        Returns:
-            tuple: Scores for each class, bbox predictions, features
-                after classification and regression conv layers, some
-                models needs these features like FCOS.
-        """
-        cls_feat = x
-        reg_feat = x
-
-        for cls_layer in self.cls_convs:
-            cls_feat = cls_layer(cls_feat)
-        cls_score = self.conv_cls(cls_feat)
-
-        for reg_layer in self.reg_convs:
-            reg_feat = reg_layer(reg_feat)
-        bbox_pred = self.conv_reg(reg_feat)
-        return cls_score, bbox_pred, cls_feat, reg_feat
-
-    @abstractmethod
-    @force_fp32(apply_to=('cls_scores', 'bbox_preds'))
-    def loss(self,
-             cls_scores,
-             bbox_preds,
-             gt_bboxes,
-             gt_labels,
-             img_metas,
-             gt_bboxes_ignore=None):
-        """Compute loss of the head.
-
-        Args:
-            cls_scores (list[Tensor]): Box scores for each scale level,
-                each is a 4D-tensor, the channel number is
-                num_points * num_classes.
-            bbox_preds (list[Tensor]): Box energies / deltas for each scale
-                level, each is a 4D-tensor, the channel number is
-                num_points * 4.
-            gt_bboxes (list[Tensor]): Ground truth bboxes for each image with
-                shape (num_gts, 4) in [tl_x, tl_y, br_x, br_y] format.
-            gt_labels (list[Tensor]): class indices corresponding to each box
-            img_metas (list[dict]): Meta information of each image, e.g.,
-                image size, scaling factor, etc.
-            gt_bboxes_ignore (None | list[Tensor]): specify which bounding
-                boxes can be ignored when computing the loss.
-        """
-
-        raise NotImplementedError
-
-    @abstractmethod
-    @force_fp32(apply_to=('cls_scores', 'bbox_preds'))
-    def get_bboxes(self,
-                   cls_scores,
-                   bbox_preds,
-                   img_metas,
-                   cfg=None,
-                   rescale=None):
-        """Transform network output for a batch into bbox predictions.
-
-        Args:
-            cls_scores (list[Tensor]): Box scores for each scale level
-                Has shape (N, num_points * num_classes, H, W)
-            bbox_preds (list[Tensor]): Box energies / deltas for each scale
-                level with shape (N, num_points * 4, H, W)
-            img_metas (list[dict]): Meta information of each image, e.g.,
-                image size, scaling factor, etc.
-            cfg (mmcv.Config): Test / postprocessing configuration,
-                if None, test_cfg would be used
-            rescale (bool): If True, return boxes in original image space
-        """
-
-        raise NotImplementedError
-
-    @abstractmethod
-    def get_targets(self, points, gt_bboxes_list, gt_labels_list):
-        """Compute regression, classification and centerness targets for points
-        in multiple images.
-
-        Args:
-            points (list[Tensor]): Points of each fpn level, each has shape
-                (num_points, 2).
-            gt_bboxes_list (list[Tensor]): Ground truth bboxes of each image,
-                each has shape (num_gt, 4).
-            gt_labels_list (list[Tensor]): Ground truth labels of each box,
-                each has shape (num_gt,).
-        """
-        raise NotImplementedError
-
-    def _get_points_single(self,
-                           featmap_size,
-                           stride,
-                           dtype,
-                           device,
-                           flatten=False):
-        """Get points of a single scale level."""
-        h, w = featmap_size
-        x_range = torch.arange(w, dtype=dtype, device=device)
-        y_range = torch.arange(h, dtype=dtype, device=device)
-        y, x = torch.meshgrid(y_range, x_range)
-        if flatten:
-            y = y.flatten()
-            x = x.flatten()
-        return y, x
-
-    def get_points(self, featmap_sizes, dtype, device, flatten=False):
-        """Get points according to feature map sizes.
-
-        Args:
-            featmap_sizes (list[tuple]): Multi-level feature map sizes.
-            dtype (torch.dtype): Type of points.
-            device (torch.device): Device of points.
-
-        Returns:
-            tuple: points of each image.
-        """
-        mlvl_points = []
-        for i in range(len(featmap_sizes)):
-            mlvl_points.append(
-                self._get_points_single(featmap_sizes[i], self.strides[i],
-                                        dtype, device, flatten))
-        return mlvl_points
-
-    def aug_test(self, feats, img_metas, rescale=False):
-        """Test function with test time augmentation.
-
-        Args:
-            feats (list[Tensor]): the outer list indicates test-time
-                augmentations and inner Tensor should have a shape NxCxHxW,
-                which contains features for all images in the batch.
-            img_metas (list[list[dict]]): the outer list indicates test-time
-                augs (multiscale, flip, etc.) and the inner list indicates
-                images in a batch. each dict has image information.
-            rescale (bool, optional): Whether to rescale the results.
-                Defaults to False.
-
-        Returns:
-            list[ndarray]: bbox results of each class
-        """
-        return self.aug_test_bboxes(feats, img_metas, rescale=rescale)
diff --git a/spaces/Gradio-Blocks/uniformer_image_segmentation/configs/_base_/datasets/pascal_voc12_aug.py b/spaces/Gradio-Blocks/uniformer_image_segmentation/configs/_base_/datasets/pascal_voc12_aug.py
deleted file mode 100644
index 3f23b6717d53ad29f02dd15046802a2631a5076b..0000000000000000000000000000000000000000
--- a/spaces/Gradio-Blocks/uniformer_image_segmentation/configs/_base_/datasets/pascal_voc12_aug.py
+++ /dev/null
@@ -1,9 +0,0 @@
-_base_ = './pascal_voc12.py'
-# dataset settings
-data = dict(
-    train=dict(
-        ann_dir=['SegmentationClass', 'SegmentationClassAug'],
-        split=[
-            'ImageSets/Segmentation/train.txt',
-            'ImageSets/Segmentation/aug.txt'
-        ]))
diff --git a/spaces/HaloMaster/chinesesummary/fengshen/data/megatron_dataloader/bart_dataset.py b/spaces/HaloMaster/chinesesummary/fengshen/data/megatron_dataloader/bart_dataset.py
deleted file mode 100644
index 82a22aa21eba9ac4794305c72efe3c25e2bdefb7..0000000000000000000000000000000000000000
--- a/spaces/HaloMaster/chinesesummary/fengshen/data/megatron_dataloader/bart_dataset.py
+++ /dev/null
@@ -1,443 +0,0 @@
-"""BART Style dataset. Modified from fairseq."""
-
-import numpy as np
-import torch
-import math
-import re
-
-from fengshen.data.megatron_dataloader.dataset_utils import (
-    get_samples_mapping
-)
-
-
-class BartDataset(torch.utils.data.Dataset):
-    def __init__(self, name, indexed_dataset, data_prefix,
-                 num_epochs, max_num_samples, masked_lm_prob,
-                 max_seq_length, short_seq_prob, seed, tokenizer, zh_tokenizer):
-
-        # Params to store.
-        self.name = name
-        self.seed = seed
-        self.masked_lm_prob = masked_lm_prob
-        self.max_seq_length = max_seq_length
-
-        # Dataset.
-        self.indexed_dataset = indexed_dataset
-
-        # Build the samples mapping.
-        self.samples_mapping = get_samples_mapping(self.indexed_dataset,
-                                                   data_prefix,
-                                                   num_epochs,
-                                                   max_num_samples,
-                                                   self.max_seq_length - 3,  # account for added tokens
-                                                   short_seq_prob,
-                                                   self.seed,
-                                                   self.name,
-                                                   False)
-
-        # Vocab stuff.
-        self.vocab_size = tokenizer.vocab_size
-        inv_vocab = {v: k for k, v in tokenizer.vocab.items()}
-        self.vocab_id_list = list(inv_vocab.keys())
-        self.vocab_id_to_token_dict = inv_vocab
-        self.cls_id = tokenizer.cls_token_id
-        self.sep_id = tokenizer.sep_token_id
-        self.mask_id = tokenizer.mask_token_id
-        self.pad_id = tokenizer.pad_token_id
-        self.tokenizer = tokenizer
-
-        seg_tokens = ['。', ';', '；', '!', '！', '?', '？']
-        seg_token_ids = []
-        for t in seg_tokens:
-            if t in tokenizer.vocab:
-                seg_token_ids.append(tokenizer.vocab[t])
-            else:
-                print('seg_token "{}" not in vocab'.format(t))
-        self.seg_token_ids = set(seg_token_ids)
-
-        self.zh_tokenizer = zh_tokenizer
-
-        # Denoising ratios
-        self.permute_sentence_ratio = 1.0
-        self.mask_ratio = masked_lm_prob  # 0.15
-        self.random_ratio = 0.1
-        self.insert_ratio = 0.0
-        self.rotate_ratio = 0.0
-        self.mask_whole_word = 1
-        self.item_transform_func = None
-
-        self.mask_span_distribution = None
-        if False:
-            _lambda = 3  # Poisson lambda
-
-            lambda_to_the_k = 1
-            e_to_the_minus_lambda = math.exp(-_lambda)
-            k_factorial = 1
-            ps = []
-            for k in range(0, 128):
-                ps.append(e_to_the_minus_lambda * lambda_to_the_k / k_factorial)
-                lambda_to_the_k *= _lambda
-                k_factorial *= k + 1
-                if ps[-1] < 0.0000001:
-                    break
-            ps = torch.FloatTensor(ps)
-            self.mask_span_distribution = torch.distributions.Categorical(ps)
-
-    def __len__(self):
-        return self.samples_mapping.shape[0]
-
-    def __getitem__(self, idx):
-        start_idx, end_idx, seq_length = self.samples_mapping[idx]
-        sample = [self.indexed_dataset[i] for i in range(start_idx, end_idx)]
-        # Note that this rng state should be numpy and not python since
-        # python randint is inclusive whereas the numpy one is exclusive.
-        # We % 2**32 since numpy requres the seed to be between 0 and 2**32 - 1
-        np_rng = np.random.RandomState(seed=((self.seed + idx) % 2**32))
-        return self.build_training_sample(sample, self.max_seq_length, np_rng)
-
-    def build_training_sample(self, sample, max_seq_length, np_rng):
-        """Biuld training sample.
-
-        Arguments:
-            sample: A list of sentences in which each sentence is a list token ids.
-            max_seq_length: Desired sequence length.
-            np_rng: Random number genenrator. Note that this rng state should be
-                numpy and not python since python randint is inclusive for
-                the opper bound whereas the numpy one is exclusive.
-        """
-        # permute sentences
-        full_stops = []
-        tokens = [self.cls_id]
-        for sent in sample:
-            for t in sent:
-                token = self.vocab_id_to_token_dict[t]
-                if len(re.findall('##[\u4E00-\u9FA5]', token)) > 0:
-                    # 兼容erlangshen ##的方式做whole word mask
-                    t = self.tokenizer.convert_tokens_to_ids(token[2:])
-                tokens.append(t)
-                if t in self.seg_token_ids:
-                    tokens.append(self.sep_id)
-            if tokens[-1] != self.sep_id:
-                tokens.append(self.sep_id)
-
-        if len(tokens) > max_seq_length:
-            tokens = tokens[:max_seq_length]
-            tokens[-1] = self.sep_id
-        tokens = torch.LongTensor(tokens)
-        full_stops = (tokens == self.sep_id).long()
-        assert (max_seq_length - tokens.shape[0]) >= 0, (tokens.size(), tokens[-1], max_seq_length)
-
-        source, target = tokens, tokens[1:].clone()
-        use_decoder = 1
-        # if torch.rand(1).item() < 0.5:
-        #     use_decoder = 0
-
-        if self.permute_sentence_ratio > 0.0 and use_decoder == 1:
-            source = self.permute_sentences(source, full_stops, self.permute_sentence_ratio)
-
-        if self.mask_ratio > 0.0:
-            replace_length = 1 if use_decoder else -1
-            mask_ratio = self.mask_ratio * 2 if use_decoder else self.mask_ratio
-            source = self.add_whole_word_mask(source, mask_ratio, replace_length)
-
-        if self.insert_ratio > 0.0:
-            raise NotImplementedError
-            source = self.add_insertion_noise(source, self.insert_ratio)
-
-        if self.rotate_ratio > 0.0 and np.random.random() < self.rotate_ratio:
-            raise NotImplementedError
-            source = self.add_rolling_noise(source)
-
-        # there can additional changes to make:
-        if self.item_transform_func is not None:
-            source, target = self.item_transform_func(source, target)
-
-        assert (source >= 0).all()
-        # assert (source[1:-1] >= 1).all()
-        assert (source <= self.vocab_size).all()
-        assert source[0] == self.cls_id
-        assert source[-1] == self.sep_id
-
-        # tokenizer = get_tokenizer()
-        # print(' '.join(tokenizer.tokenizer.convert_ids_to_tokens(source)))
-        # print(tokenizer.detokenize(target))
-        # print(tokenizer.detokenize(source))
-        # print()
-
-        prev_output_tokens = torch.zeros_like(target)
-        prev_output_tokens[0] = self.sep_id  # match the preprocessing in fairseq
-        prev_output_tokens[1:] = target[:-1]
-
-        # src_padding_length = max_seq_length - source.shape[0]
-        # tgt_padding_length = max_seq_length - target.shape[0]
-        # assert src_padding_length >= 0, (source.size(), source[-1], max_seq_length)
-        # assert tgt_padding_length >= 0, (target.size(), target[-1], max_seq_length)
-        source_ = torch.full((max_seq_length,), self.pad_id, dtype=torch.long)
-        source_[:source.shape[0]] = source
-        target_ = torch.full((max_seq_length,), -100, dtype=torch.long)
-        # decoder not need bos in the front
-        target_[:target.shape[0]] = target
-        prev_output_tokens_ = torch.full((max_seq_length,), self.pad_id, dtype=torch.long)
-        prev_output_tokens_[:prev_output_tokens.shape[0]] = prev_output_tokens
-
-        return {
-            "input_ids": source_,
-            "labels": target_,
-            # "decoder_input_ids": prev_output_tokens_,
-            "attention_mask": (source_ != self.pad_id).long()
-        }
-
-    def permute_sentences(self, source, full_stops, p=1.0):
-        # Tokens that are full stops, where the previous token is not
-        sentence_ends = (full_stops[1:] * ~full_stops[:-1]).nonzero(as_tuple=False) + 2
-        result = source.clone()
-
-        num_sentences = sentence_ends.size(0)
-        num_to_permute = math.ceil((num_sentences * 2 * p) / 2.0)
-        substitutions = torch.randperm(num_sentences)[:num_to_permute]
-        ordering = torch.arange(0, num_sentences)
-        ordering[substitutions] = substitutions[torch.randperm(num_to_permute)]
-
-        # Ignore <bos> at start
-        index = 1
-        for i in ordering:
-            sentence = source[(sentence_ends[i - 1] if i > 0 else 1): sentence_ends[i]]
-            result[index: index + sentence.size(0)] = sentence
-            index += sentence.size(0)
-        return result
-
-    def word_starts_en(self, source):
-        if self.mask_whole_word is not None:
-            is_word_start = self.mask_whole_word.gather(0, source)
-        else:
-            is_word_start = torch.ones(source.size())
-        is_word_start[0] = 0
-        is_word_start[-1] = 0
-        return is_word_start
-
-    def word_starts(self, source):
-        if self.mask_whole_word is None:
-            is_word_start = torch.ones(source.size())
-            is_word_start[0] = 0
-            is_word_start[-1] = 0
-            return is_word_start
-        raw_tokens = [self.vocab_id_to_token_dict[i] for i in source.tolist()]
-        words = [raw_tokens[0]] + \
-            self.zh_tokenizer(''.join(raw_tokens[1:-1]), HMM=True) + [raw_tokens[-1]]
-
-        def _is_chinese_char(c):
-            """Checks whether CP is the #codepoint of a CJK character."""
-            # This defines a "chinese character" as anything in the CJK Unicode block:
-            #   https://en.wikipedia.org/wiki/CJK_Unified_Ideographs_(Unicode_block)
-            #
-            # Note that the CJK Unicode block is NOT all Japanese and Korean characters,
-            # despite its name. The modern Korean Hangul alphabet is a different block,
-            # as is Japanese Hiragana and Katakana. Those alphabets are used to write
-            # space-separated words, so they are not treated specially and handled
-            # like the all of the other languages.
-            if len(c) > 1:
-                return all([_is_chinese_char(c_i) for c_i in c])
-            cp = ord(c)
-            if ((cp >= 0x4E00 and cp <= 0x9FFF) or  #
-                (cp >= 0x3400 and cp <= 0x4DBF) or  #
-                (cp >= 0x20000 and cp <= 0x2A6DF) or  #
-                (cp >= 0x2A700 and cp <= 0x2B73F) or  #
-                (cp >= 0x2B740 and cp <= 0x2B81F) or  #
-                (cp >= 0x2B820 and cp <= 0x2CEAF) or
-                (cp >= 0xF900 and cp <= 0xFAFF) or  #
-                    (cp >= 0x2F800 and cp <= 0x2FA1F)):  #
-                return True
-
-            return False
-
-        def align_linear(atokens, btokens):
-            a2c = []
-            c2b = []
-            a2b = []
-            length = 0
-            for tok in atokens:
-                a2c.append([length + i for i in range(len(tok))])
-                length += len(tok)
-            for i, tok in enumerate(btokens):
-                c2b.extend([i for _ in range(len(tok))])
-
-            for i, amap in enumerate(a2c):
-                bmap = [c2b[ci] for ci in amap]
-                a2b.append(list(set(bmap)))
-            return a2b
-
-        raw_to_word_align = align_linear(raw_tokens, words)
-        is_word_start = torch.zeros(source.size())
-        word_starts = []
-        skip_cur_word = True
-        for i in range(1, len(raw_to_word_align)):
-            if raw_to_word_align[i-1] == raw_to_word_align[i]:
-                # not a word start, as they align to the same word
-                if not skip_cur_word and not _is_chinese_char(raw_tokens[i]):
-                    word_starts.pop(-1)
-                    skip_cur_word = True
-                continue
-            else:
-                is_word_start[i] = 1
-                if _is_chinese_char(raw_tokens[i]):
-                    word_starts.append(i)
-                    skip_cur_word = False
-        is_word_start[0] = 0
-        is_word_start[-1] = 0
-        word_starts = torch.tensor(word_starts).long().view(-1, 1)
-        return is_word_start, word_starts
-
-    def add_whole_word_mask(self, source, p, replace_length=1):
-        is_word_start, word_starts = self.word_starts(source)
-        num_to_mask_word = int(math.ceil(word_starts.size(0) * p))
-        num_to_mask_char = int(math.ceil(word_starts.size(0) * p * 0.1))
-        num_to_mask = num_to_mask_word + num_to_mask_char
-        if num_to_mask > word_starts.size(0):
-            word_starts = is_word_start.nonzero(as_tuple=False)
-        num_inserts = 0
-        if num_to_mask == 0:
-            return source
-
-        if self.mask_span_distribution is not None:
-            lengths = self.mask_span_distribution.sample(sample_shape=(num_to_mask,))
-
-            # Make sure we have enough to mask
-            cum_length = torch.cumsum(lengths, 0)
-            while cum_length[-1] < num_to_mask:
-                lengths = torch.cat(
-                    [
-                        lengths,
-                        self.mask_span_distribution.sample(sample_shape=(num_to_mask,)),
-                    ],
-                    dim=0,
-                )
-                cum_length = torch.cumsum(lengths, 0)
-
-            # Trim to masking budget
-            i = 0
-            while cum_length[i] < num_to_mask:
-                i += 1
-            lengths[i] = num_to_mask - (0 if i == 0 else cum_length[i - 1])
-            num_to_mask = i + 1
-            lengths = lengths[:num_to_mask]
-
-            # Handle 0-length mask (inserts) separately
-            lengths = lengths[lengths > 0]
-            num_inserts = num_to_mask - lengths.size(0)
-            num_to_mask -= num_inserts
-            if num_to_mask == 0:
-                return self.add_insertion_noise(source, num_inserts / source.size(0))
-
-            assert (lengths > 0).all()
-        else:
-            lengths = torch.ones((num_to_mask,)).long()
-        assert is_word_start[-1] == 0
-        indices = word_starts[
-            torch.randperm(word_starts.size(0))[:num_to_mask]
-        ].squeeze(1)
-        mask_random = torch.FloatTensor(num_to_mask).uniform_() < self.random_ratio
-        source_length = source.size(0)
-        assert source_length - 1 not in indices
-        to_keep = torch.ones(source_length, dtype=torch.bool)
-        is_word_start[
-            -1
-        ] = 255  # acts as a long length, so spans don't go over the end of doc
-        if replace_length == 0:
-            to_keep[indices] = 0
-        else:
-            # keep index, but replace it with [MASK]
-            # print(source.size(), word_starts.size(), indices.size(), mask_random.size())
-            source[indices] = self.mask_id
-            source[indices[mask_random]] = torch.randint(
-                1, self.vocab_size, size=(mask_random.sum(),)
-            )
-            # sorted_indices = torch.sort(indices)[0]
-            # continue_mask_pos = ((sorted_indices + 1)[:-1] == sorted_indices[1:])
-            # continue_mask_indices = sorted_indices[1:][continue_mask_pos]
-            # to_keep[continue_mask_indices] = 0
-
-        # for char indices, we already masked, the following loop handles word mask
-        indices = indices[:num_to_mask_word]
-        mask_random = mask_random[:num_to_mask_word]
-        if self.mask_span_distribution is not None:
-            assert len(lengths.size()) == 1
-            assert lengths.size() == indices.size()
-            lengths -= 1
-            while indices.size(0) > 0:
-                assert lengths.size() == indices.size()
-                lengths -= is_word_start[indices + 1].long()
-                uncompleted = lengths >= 0
-                indices = indices[uncompleted] + 1
-                mask_random = mask_random[uncompleted]
-                lengths = lengths[uncompleted]
-                if replace_length != -1:
-                    # delete token
-                    to_keep[indices] = 0
-                else:
-                    # keep index, but replace it with [MASK]
-                    source[indices] = self.mask_id
-                    source[indices[mask_random]] = torch.randint(
-                        1, self.vocab_size, size=(mask_random.sum(),)
-                    )
-        else:
-            # A bit faster when all lengths are 1
-            while indices.size(0) > 0:
-                uncompleted = is_word_start[indices + 1] == 0
-                indices = indices[uncompleted] + 1
-                mask_random = mask_random[uncompleted]
-                if replace_length != -1:
-                    # delete token
-                    to_keep[indices] = 0
-                else:
-                    # keep index, but replace it with [MASK]
-                    source[indices] = self.mask_id
-                    source[indices[mask_random]] = torch.randint(
-                        1, self.vocab_size, size=(mask_random.sum(),)
-                    )
-
-                assert source_length - 1 not in indices
-
-        source = source[to_keep]
-
-        if num_inserts > 0:
-            source = self.add_insertion_noise(source, num_inserts / source.size(0))
-
-        return source
-
-    def add_permuted_noise(self, tokens, p):
-        num_words = len(tokens)
-        num_to_permute = math.ceil(((num_words * 2) * p) / 2.0)
-        substitutions = torch.randperm(num_words - 2)[:num_to_permute] + 1
-        tokens[substitutions] = tokens[substitutions[torch.randperm(num_to_permute)]]
-        return tokens
-
-    def add_rolling_noise(self, tokens):
-        offset = np.random.randint(1, max(1, tokens.size(-1) - 1) + 1)
-        tokens = torch.cat(
-            (tokens[0:1], tokens[offset:-1], tokens[1:offset], tokens[-1:]),
-            dim=0,
-        )
-        return tokens
-
-    def add_insertion_noise(self, tokens, p):
-        if p == 0.0:
-            return tokens
-
-        num_tokens = len(tokens)
-        n = int(math.ceil(num_tokens * p))
-
-        noise_indices = torch.randperm(num_tokens + n - 2)[:n] + 1
-        noise_mask = torch.zeros(size=(num_tokens + n,), dtype=torch.bool)
-        noise_mask[noise_indices] = 1
-        result = torch.LongTensor(n + len(tokens)).fill_(-1)
-
-        num_random = int(math.ceil(n * self.random_ratio))
-        result[noise_indices[num_random:]] = self.mask_id
-        result[noise_indices[:num_random]] = torch.randint(
-            low=1, high=self.vocab_size, size=(num_random,)
-        )
-
-        result[~noise_mask] = tokens
-
-        assert (result >= 0).all()
-        return result
diff --git a/spaces/HarryLee/eCommerceImageCaptioning/fairseq/examples/speech_recognition/models/__init__.py b/spaces/HarryLee/eCommerceImageCaptioning/fairseq/examples/speech_recognition/models/__init__.py
deleted file mode 100644
index 54b5a1c31243e55d384f80ef9514461cd35b15c6..0000000000000000000000000000000000000000
--- a/spaces/HarryLee/eCommerceImageCaptioning/fairseq/examples/speech_recognition/models/__init__.py
+++ /dev/null
@@ -1,8 +0,0 @@
-import importlib
-import os
-
-
-for file in sorted(os.listdir(os.path.dirname(__file__))):
-    if file.endswith(".py") and not file.startswith("_"):
-        model_name = file[: file.find(".py")]
-        importlib.import_module("examples.speech_recognition.models." + model_name)
diff --git a/spaces/HarryLee/eCommerceImageCaptioning/fairseq/fairseq/criterions/ctc.py b/spaces/HarryLee/eCommerceImageCaptioning/fairseq/fairseq/criterions/ctc.py
deleted file mode 100644
index 10e3618382c86a84466cb4264d62f31537980251..0000000000000000000000000000000000000000
--- a/spaces/HarryLee/eCommerceImageCaptioning/fairseq/fairseq/criterions/ctc.py
+++ /dev/null
@@ -1,295 +0,0 @@
-# All rights reserved.
-#
-# This source code is licensed under the license found in the LICENSE file in
-# the root directory of this source tree. An additional grant of patent rights
-# can be found in the PATENTS file in the same directory.
-
-import math
-from argparse import Namespace
-from dataclasses import dataclass, field
-from omegaconf import II
-from typing import Optional
-
-import torch
-import torch.nn.functional as F
-from fairseq import metrics, utils
-from fairseq.criterions import FairseqCriterion, register_criterion
-from fairseq.dataclass import FairseqDataclass
-from fairseq.data.data_utils import post_process
-from fairseq.tasks import FairseqTask
-from fairseq.logging.meters import safe_round
-
-
-@dataclass
-class CtcCriterionConfig(FairseqDataclass):
-    zero_infinity: bool = field(
-        default=False,
-        metadata={"help": "zero inf loss when source length <= target length"},
-    )
-    sentence_avg: bool = II("optimization.sentence_avg")
-    post_process: str = field(
-        default="letter",
-        metadata={
-            "help": "how to post process predictions into words. can be letter, "
-            "wordpiece, BPE symbols, etc. "
-            "See fairseq.data.data_utils.post_process() for full list of options"
-        },
-    )
-    wer_kenlm_model: Optional[str] = field(
-        default=None,
-        metadata={
-            "help": "if this is provided, use kenlm to compute wer (along with other wer_* args)"
-        },
-    )
-    wer_lexicon: Optional[str] = field(
-        default=None,
-        metadata={"help": "lexicon to use with wer_kenlm_model"},
-    )
-    wer_lm_weight: float = field(
-        default=2.0,
-        metadata={"help": "lm weight to use with wer_kenlm_model"},
-    )
-    wer_word_score: float = field(
-        default=-1.0,
-        metadata={"help": "lm word score to use with wer_kenlm_model"},
-    )
-
-    wer_args: Optional[str] = field(
-        default=None,
-        metadata={
-            "help": "DEPRECATED: tuple of (wer_kenlm_model, wer_lexicon, wer_lm_weight, wer_word_score)"
-        },
-    )
-
-
-@register_criterion("ctc", dataclass=CtcCriterionConfig)
-class CtcCriterion(FairseqCriterion):
-    def __init__(self, cfg: CtcCriterionConfig, task: FairseqTask):
-        super().__init__(task)
-        self.blank_idx = (
-            task.target_dictionary.index(task.blank_symbol)
-            if hasattr(task, "blank_symbol")
-            else 0
-        )
-        self.pad_idx = task.target_dictionary.pad()
-        self.eos_idx = task.target_dictionary.eos()
-        self.post_process = cfg.post_process
-
-        if cfg.wer_args is not None:
-            (
-                cfg.wer_kenlm_model,
-                cfg.wer_lexicon,
-                cfg.wer_lm_weight,
-                cfg.wer_word_score,
-            ) = eval(cfg.wer_args)
-
-        if cfg.wer_kenlm_model is not None:
-            from examples.speech_recognition.w2l_decoder import W2lKenLMDecoder
-
-            dec_args = Namespace()
-            dec_args.nbest = 1
-            dec_args.criterion = "ctc"
-            dec_args.kenlm_model = cfg.wer_kenlm_model
-            dec_args.lexicon = cfg.wer_lexicon
-            dec_args.beam = 50
-            dec_args.beam_size_token = min(50, len(task.target_dictionary))
-            dec_args.beam_threshold = min(50, len(task.target_dictionary))
-            dec_args.lm_weight = cfg.wer_lm_weight
-            dec_args.word_score = cfg.wer_word_score
-            dec_args.unk_weight = -math.inf
-            dec_args.sil_weight = 0
-
-            self.w2l_decoder = W2lKenLMDecoder(dec_args, task.target_dictionary)
-        else:
-            self.w2l_decoder = None
-
-        self.zero_infinity = cfg.zero_infinity
-        self.sentence_avg = cfg.sentence_avg
-
-    def forward(self, model, sample, reduce=True):
-        net_output = model(**sample["net_input"])
-        lprobs = model.get_normalized_probs(
-            net_output, log_probs=True
-        ).contiguous()  # (T, B, C) from the encoder
-
-        if "src_lengths" in sample["net_input"]:
-            input_lengths = sample["net_input"]["src_lengths"]
-        else:
-            if net_output["padding_mask"] is not None:
-                non_padding_mask = ~net_output["padding_mask"]
-                input_lengths = non_padding_mask.long().sum(-1)
-            else:
-                input_lengths = lprobs.new_full(
-                    (lprobs.size(1),), lprobs.size(0), dtype=torch.long
-                )
-
-        pad_mask = (sample["target"] != self.pad_idx) & (
-            sample["target"] != self.eos_idx
-        )
-        targets_flat = sample["target"].masked_select(pad_mask)
-        if "target_lengths" in sample:
-            target_lengths = sample["target_lengths"]
-        else:
-            target_lengths = pad_mask.sum(-1)
-
-        with torch.backends.cudnn.flags(enabled=False):
-            loss = F.ctc_loss(
-                lprobs,
-                targets_flat,
-                input_lengths,
-                target_lengths,
-                blank=self.blank_idx,
-                reduction="sum",
-                zero_infinity=self.zero_infinity,
-            )
-
-        ntokens = (
-            sample["ntokens"] if "ntokens" in sample else target_lengths.sum().item()
-        )
-
-        sample_size = sample["target"].size(0) if self.sentence_avg else ntokens
-        logging_output = {
-            "loss": utils.item(loss.data),  # * sample['ntokens'],
-            "ntokens": ntokens,
-            "nsentences": sample["id"].numel(),
-            "sample_size": sample_size,
-        }
-
-        if not model.training:
-            import editdistance
-
-            with torch.no_grad():
-                lprobs_t = lprobs.transpose(0, 1).float().contiguous().cpu()
-
-                c_err = 0
-                c_len = 0
-                w_errs = 0
-                w_len = 0
-                wv_errs = 0
-                for lp, t, inp_l in zip(
-                    lprobs_t,
-                    sample["target_label"]
-                    if "target_label" in sample
-                    else sample["target"],
-                    input_lengths,
-                ):
-                    lp = lp[:inp_l].unsqueeze(0)
-
-                    decoded = None
-                    if self.w2l_decoder is not None:
-                        decoded = self.w2l_decoder.decode(lp)
-                        if len(decoded) < 1:
-                            decoded = None
-                        else:
-                            decoded = decoded[0]
-                            if len(decoded) < 1:
-                                decoded = None
-                            else:
-                                decoded = decoded[0]
-
-                    p = (t != self.task.target_dictionary.pad()) & (
-                        t != self.task.target_dictionary.eos()
-                    )
-                    targ = t[p]
-                    targ_units = self.task.target_dictionary.string(targ)
-                    targ_units_arr = targ.tolist()
-
-                    toks = lp.argmax(dim=-1).unique_consecutive()
-                    pred_units_arr = toks[toks != self.blank_idx].tolist()
-
-                    c_err += editdistance.eval(pred_units_arr, targ_units_arr)
-                    c_len += len(targ_units_arr)
-
-                    targ_words = post_process(targ_units, self.post_process).split()
-
-                    pred_units = self.task.target_dictionary.string(pred_units_arr)
-                    pred_words_raw = post_process(pred_units, self.post_process).split()
-
-                    if decoded is not None and "words" in decoded:
-                        pred_words = decoded["words"]
-                        w_errs += editdistance.eval(pred_words, targ_words)
-                        wv_errs += editdistance.eval(pred_words_raw, targ_words)
-                    else:
-                        dist = editdistance.eval(pred_words_raw, targ_words)
-                        w_errs += dist
-                        wv_errs += dist
-
-                    w_len += len(targ_words)
-
-                logging_output["wv_errors"] = wv_errs
-                logging_output["w_errors"] = w_errs
-                logging_output["w_total"] = w_len
-                logging_output["c_errors"] = c_err
-                logging_output["c_total"] = c_len
-
-        return loss, sample_size, logging_output
-
-    @staticmethod
-    def reduce_metrics(logging_outputs) -> None:
-        """Aggregate logging outputs from data parallel training."""
-
-        loss_sum = utils.item(sum(log.get("loss", 0) for log in logging_outputs))
-        ntokens = utils.item(sum(log.get("ntokens", 0) for log in logging_outputs))
-        nsentences = utils.item(
-            sum(log.get("nsentences", 0) for log in logging_outputs)
-        )
-        sample_size = utils.item(
-            sum(log.get("sample_size", 0) for log in logging_outputs)
-        )
-
-        metrics.log_scalar(
-            "loss", loss_sum / sample_size / math.log(2), sample_size, round=3
-        )
-        metrics.log_scalar("ntokens", ntokens)
-        metrics.log_scalar("nsentences", nsentences)
-        if sample_size != ntokens:
-            metrics.log_scalar(
-                "nll_loss", loss_sum / ntokens / math.log(2), ntokens, round=3
-            )
-
-        c_errors = sum(log.get("c_errors", 0) for log in logging_outputs)
-        metrics.log_scalar("_c_errors", c_errors)
-        c_total = sum(log.get("c_total", 0) for log in logging_outputs)
-        metrics.log_scalar("_c_total", c_total)
-        w_errors = sum(log.get("w_errors", 0) for log in logging_outputs)
-        metrics.log_scalar("_w_errors", w_errors)
-        wv_errors = sum(log.get("wv_errors", 0) for log in logging_outputs)
-        metrics.log_scalar("_wv_errors", wv_errors)
-        w_total = sum(log.get("w_total", 0) for log in logging_outputs)
-        metrics.log_scalar("_w_total", w_total)
-
-        if c_total > 0:
-            metrics.log_derived(
-                "uer",
-                lambda meters: safe_round(
-                    meters["_c_errors"].sum * 100.0 / meters["_c_total"].sum, 3
-                )
-                if meters["_c_total"].sum > 0
-                else float("nan"),
-            )
-        if w_total > 0:
-            metrics.log_derived(
-                "wer",
-                lambda meters: safe_round(
-                    meters["_w_errors"].sum * 100.0 / meters["_w_total"].sum, 3
-                )
-                if meters["_w_total"].sum > 0
-                else float("nan"),
-            )
-            metrics.log_derived(
-                "raw_wer",
-                lambda meters: safe_round(
-                    meters["_wv_errors"].sum * 100.0 / meters["_w_total"].sum, 3
-                )
-                if meters["_w_total"].sum > 0
-                else float("nan"),
-            )
-
-    @staticmethod
-    def logging_outputs_can_be_summed() -> bool:
-        """
-        Whether the logging outputs returned by `forward` can be summed
-        across workers prior to calling `reduce_metrics`. Setting this
-        to True will improves distributed training speed.
-        """
-        return True
diff --git a/spaces/HarryLee/eCommerceImageCaptioning/fairseq/fairseq/tasks/audio_pretraining.py b/spaces/HarryLee/eCommerceImageCaptioning/fairseq/fairseq/tasks/audio_pretraining.py
deleted file mode 100644
index cc310088db8852e80cd2e65d51f06f8f7cb592e3..0000000000000000000000000000000000000000
--- a/spaces/HarryLee/eCommerceImageCaptioning/fairseq/fairseq/tasks/audio_pretraining.py
+++ /dev/null
@@ -1,206 +0,0 @@
-# Copyright (c) 2017-present, Facebook, Inc.
-# All rights reserved.
-#
-# This source code is licensed under the license found in the LICENSE file in
-# the root directory of this source tree. An additional grant of patent rights
-# can be found in the PATENTS file in the same directory.
-
-import logging
-import os
-import sys
-
-from argparse import Namespace
-from dataclasses import dataclass, field
-from typing import Optional
-from omegaconf import MISSING, II, OmegaConf
-
-from fairseq.data import BinarizedAudioDataset, FileAudioDataset
-from fairseq.dataclass import FairseqDataclass, ChoiceEnum
-from fairseq.data.text_compressor import TextCompressionLevel
-
-from . import FairseqTask, register_task
-
-
-logger = logging.getLogger(__name__)
-
-
-@dataclass
-class InferredW2vConfig:
-    # The following are needed to precompute mask and mask channel indices
-    #   before model's forward.
-    mask_length: Optional[int] = II("model.mask_length")
-    mask_prob: Optional[float] = II("model.mask_prob")
-    mask_selection: Optional[str] = II("model.mask_selection")
-    mask_other: Optional[float] = II("model.mask_other")
-    no_mask_overlap: Optional[bool] = II("model.no_mask_overlap")
-    mask_min_space: Optional[int] = II("model.mask_min_space")
-    mask_channel_length: Optional[int] = II("model.mask_channel_length")
-    mask_channel_prob: Optional[float] = II("model.mask_channel_prob")
-    mask_channel_selection: Optional[str] = II("model.mask_channel_selection")
-    mask_channel_other: Optional[float] = II("model.mask_channel_other")
-    no_mask_channel_overlap: Optional[bool] = II("model.no_mask_channel_overlap")
-    mask_channel_min_space: Optional[int] = II("model.mask_channel_min_space")
-
-    conv_feature_layers: Optional[str] = II("model.conv_feature_layers")
-    encoder_embed_dim: Optional[int] = II("model.encoder_embed_dim")
-
-
-@dataclass
-class AudioPretrainingConfig(FairseqDataclass):
-    data: str = field(default=MISSING, metadata={"help": "path to data directory"})
-    labels: Optional[str] = field(
-        default=None,
-        metadata={
-            "help": "extension of the label file to load, used for fine-tuning"},
-    )
-    binarized_dataset: bool = field(
-        default=False,
-        metadata={
-            "help": "if true, loads binarized dataset (useful for very large datasets). "
-            "See examples/wav2vec/scripts/binarize_manifest.sh"
-        },
-    )
-    sample_rate: int = field(
-        default=16_000,
-        metadata={
-            "help": "target sample rate. audio files will be up/down sampled to this rate"
-        },
-    )
-    normalize: bool = field(
-        default=False,
-        metadata={"help": "if set, normalizes input to have 0 mean and unit variance"},
-    )
-    enable_padding: bool = field(
-        default=False, metadata={"help": "pad shorter samples instead of cropping"}
-    )
-    max_sample_size: Optional[int] = field(
-        default=None, metadata={"help": "max sample size to crop to for batching"}
-    )
-    min_sample_size: Optional[int] = field(
-        default=None, metadata={"help": "min sample size to skip small examples"}
-    )
-    num_batch_buckets: int = field(
-        default=0,
-        metadata={"help": "number of buckets"},
-    )
-    precompute_mask_indices: bool = field(
-        default=False,
-        metadata={
-            "help": "flag to compute mask indices in data preparation.",
-        },
-    )
-
-    inferred_w2v_config: Optional[InferredW2vConfig] = field(
-        default=None,
-        metadata={
-            "help": "wav2vec 2.0 masking arguments used to pre-compute masks (required for TPU)",
-        },
-    )
-
-    tpu: bool = II("common.tpu")
-    text_compression_level: ChoiceEnum([x.name for x in TextCompressionLevel]) = field(
-        default="none",
-        metadata={
-            "help": "compression level for texts (e.g. audio filenames, "
-                    "target texts): none/low/high (default: none). "
-        }
-    )
-
-
-@register_task("audio_pretraining", dataclass=AudioPretrainingConfig)
-class AudioPretrainingTask(FairseqTask):
-    """ """
-
-    cfg: AudioPretrainingConfig
-
-    @classmethod
-    def setup_task(cls, cfg: AudioPretrainingConfig, **kwargs):
-        """Setup the task (e.g., load dictionaries).
-
-        Args:
-            cfg (AudioPretrainingConfig): configuration of this task
-        """
-
-        return cls(cfg)
-
-    def _get_mask_precompute_kwargs(self, cfg):
-        if self.cfg.precompute_mask_indices or self.cfg.tpu:
-            assert (
-                cfg.inferred_w2v_config is not None
-            ), "inferred_w2v_config must be set"
-            return OmegaConf.to_container(
-                cfg.inferred_w2v_config, resolve=True, enum_to_str=True
-            )
-        else:
-            return {}
-
-    def load_dataset(self, split: str, task_cfg: FairseqDataclass = None, **kwargs):
-        data_path = self.cfg.data
-        task_cfg = task_cfg or self.cfg
-
-        # upgrade old task
-        if isinstance(task_cfg, Namespace):
-            if not hasattr(task_cfg, "autoregressive"):
-                task_cfg.autoregressive = not task_cfg.criterion == "ctc"
-
-        text_compression_level = getattr(
-            TextCompressionLevel, str(self.cfg.text_compression_level)
-        )
-        if getattr(task_cfg, "binarized_dataset", False):
-            self.datasets[split] = BinarizedAudioDataset(
-                data_path,
-                split=split,
-                sample_rate=task_cfg.get("sample_rate", self.cfg.sample_rate),
-                max_sample_size=self.cfg.max_sample_size,
-                min_sample_size=self.cfg.min_sample_size,
-                pad=task_cfg.labels is not None or task_cfg.enable_padding,
-                normalize=task_cfg.normalize,
-                num_buckets=self.cfg.num_batch_buckets or int(self.cfg.tpu),
-                compute_mask_indices=(self.cfg.precompute_mask_indices or self.cfg.tpu),
-                **self._get_mask_precompute_kwargs(task_cfg),
-            )
-        else:
-            manifest_path = os.path.join(data_path, "{}.tsv".format(split))
-
-            self.datasets[split] = FileAudioDataset(
-                manifest_path=manifest_path,
-                sample_rate=task_cfg.get("sample_rate", self.cfg.sample_rate),
-                max_sample_size=self.cfg.max_sample_size,
-                min_sample_size=self.cfg.min_sample_size,
-                pad=task_cfg.labels is not None or task_cfg.enable_padding,
-                normalize=task_cfg.normalize,
-                num_buckets=self.cfg.num_batch_buckets or int(self.cfg.tpu),
-                compute_mask_indices=(self.cfg.precompute_mask_indices or self.cfg.tpu),
-                text_compression_level=text_compression_level,
-                **self._get_mask_precompute_kwargs(task_cfg),
-            )
-
-        if self.cfg.tpu and task_cfg.inferred_w2v_config.mask_channel_prob == 0.0:
-            logger.info(
-                "Pretraining on TPUs may suffer convergence "
-                "issues when training with `mask_channel_prob` value of "
-                "0. You may want to set this to a low value close to 0."
-            )
-
-    @property
-    def source_dictionary(self):
-        return None
-
-    @property
-    def target_dictionary(self):
-        return None
-
-    def max_positions(self):
-        """Maximum input length supported by the encoder."""
-        return sys.maxsize, sys.maxsize
-
-    def build_model(self, model_cfg: FairseqDataclass):
-        model = super().build_model(model_cfg)
-
-        actualized_cfg = getattr(model, "cfg", None)
-        if actualized_cfg is not None:
-            # if "w2v_args" in actualized_cfg:
-            if hasattr(actualized_cfg, "w2v_args"):
-                model_cfg.w2v_args = actualized_cfg.w2v_args
-
-        return model
diff --git a/spaces/Harveenchadha/Vakyansh-Hindi-TTS/ttsv/utils/hifi/prepare_iitm_data_hifi.py b/spaces/Harveenchadha/Vakyansh-Hindi-TTS/ttsv/utils/hifi/prepare_iitm_data_hifi.py
deleted file mode 100644
index 1e1de2e28735143aeef8ddb10bc5a4672c02564b..0000000000000000000000000000000000000000
--- a/spaces/Harveenchadha/Vakyansh-Hindi-TTS/ttsv/utils/hifi/prepare_iitm_data_hifi.py
+++ /dev/null
@@ -1,64 +0,0 @@
-
-import glob
-import random
-import sys
-import os
-import argparse
-
-
-
-
-def process_data(args):
-    
-    path = args.input_path
-    valid_files = args.valid_files
-    test_files = args.test_files
-    dest_path = args.dest_path
-
-    list_paths = path.split(',')
-
-    valid_set = []
-    training_set = []
-    test_set = []
-
-    for local_path in list_paths:
-        files = glob.glob(local_path+'/*.wav')
-        print(f"Total files: {len(files)}")
-
-        valid_set_local = random.sample(files, valid_files)
-
-        test_set_local = random.sample(valid_set_local, test_files)
-        valid_set.extend(list(set(valid_set_local) - set(test_set_local)))
-        test_set.extend(test_set_local)
-
-        print(len(valid_set_local))
-
-        training_set_local = set(files) - set(valid_set_local)
-        print(len(training_set_local))
-        training_set.extend(training_set_local)
-
-
-    valid_set = random.sample(valid_set, len(valid_set))
-    test_set = random.sample(test_set, len(test_set))
-    training_set = random.sample(training_set, len(training_set))
-
-    with open(os.path.join(dest_path , 'valid.txt'), mode = 'w+') as file:
-        file.write("\n".join(list(valid_set)))
-
-    with open(os.path.join(dest_path , 'train.txt'), mode = 'w+') as file:
-        file.write("\n".join(list(training_set)))
-
-    with open(os.path.join(dest_path , 'test.txt'), mode = 'w+') as file:
-        file.write("\n".join(list(test_set)))
-
-
-if __name__ == "__main__":
-    parser = argparse.ArgumentParser()
-    parser.add_argument('-i','--input-path',type=str,help='path to input wav files')
-    parser.add_argument('-v','--valid-files',type=int,help='number of valid files')
-    parser.add_argument('-t','--test-files',type=int,help='number of test files')
-    parser.add_argument('-d','--dest-path',type=str,help='destination path to output filelists')
-
-    args = parser.parse_args()
-
-    process_data(args)
\ No newline at end of file
diff --git a/spaces/Heshwa/html-code-generation-from-images-with-deep-neural-networks/classes/model/autoencoder_image.py b/spaces/Heshwa/html-code-generation-from-images-with-deep-neural-networks/classes/model/autoencoder_image.py
deleted file mode 100644
index f4ddc426c2abee8a4e10d5a2b0b6e69e50df3ee0..0000000000000000000000000000000000000000
--- a/spaces/Heshwa/html-code-generation-from-images-with-deep-neural-networks/classes/model/autoencoder_image.py
+++ /dev/null
@@ -1,59 +0,0 @@
-__author__ = 'Taneem Jan, improved the old model through pretrained Auto-encoders'
-
-from keras.layers import Input, Dropout, Conv2D, MaxPooling2D, Conv2DTranspose, UpSampling2D
-from keras.models import Model
-from .Config import *
-from .AModel import *
-
-
-class autoencoder_image(AModel):
-    def __init__(self, input_shape, output_size, output_path):
-        AModel.__init__(self, input_shape, output_size, output_path)
-        self.name = 'autoencoder'
-
-        input_image = Input(shape=input_shape)
-        encoder = Conv2D(32, 3, padding='same', activation='relu')(input_image)
-        encoder = Conv2D(32, 3, padding='same', activation='relu')(encoder)
-        encoder = MaxPooling2D()(encoder)
-        encoder = Dropout(0.25)(encoder)
-
-        encoder = Conv2D(64, 3, padding='same', activation='relu')(encoder)
-        encoder = Conv2D(64, 3, padding='same', activation='relu')(encoder)
-        encoder = MaxPooling2D()(encoder)
-        encoder = Dropout(0.25)(encoder)
-
-        encoder = Conv2D(128, 3, padding='same', activation='relu')(encoder)
-        encoder = Conv2D(128, 3, padding='same', activation='relu')(encoder)
-        encoder = MaxPooling2D()(encoder)
-        encoded = Dropout(0.25, name='encoded_layer')(encoder)
-
-        decoder = Conv2DTranspose(128, 3, padding='same', activation='relu')(encoded)
-        decoder = Conv2DTranspose(128, 3, padding='same', activation='relu')(decoder)
-        decoder = UpSampling2D()(decoder)
-        decoder = Dropout(0.25)(decoder)
-
-        decoder = Conv2DTranspose(64, 3, padding='same', activation='relu')(decoder)
-        decoder = Conv2DTranspose(64, 3, padding='same', activation='relu')(decoder)
-        decoder = UpSampling2D()(decoder)
-        decoder = Dropout(0.25)(decoder)
-
-        decoder = Conv2DTranspose(32, 3, padding='same', activation='relu')(decoder)
-        decoder = Conv2DTranspose(3, 3, padding='same', activation='relu')(decoder)
-        decoder = UpSampling2D()(decoder)
-        decoded = Dropout(0.25)(decoder)
-
-        # decoder = Dense(256*256*3)(decoder)
-        # decoded = Reshape(target_shape=input_shape)(decoder)
-
-        self.model = Model(input_image, decoded)
-        self.model.compile(optimizer='adadelta', loss='binary_crossentropy')
-
-    # self.model.summary()
-
-    def fit_generator(self, generator, steps_per_epoch):
-        self.model.fit_generator(generator, steps_per_epoch=steps_per_epoch, epochs=EPOCHS, verbose=1)
-        self.save()
-
-    def predict_hidden(self, images):
-        hidden_layer_model = Model(inputs=self.input, outputs=self.get_layer('encoded_layer').output)
-        return hidden_layer_model.predict(images)
diff --git a/spaces/Hexamind/GDOC/src/domain/wikidoc.py b/spaces/Hexamind/GDOC/src/domain/wikidoc.py
deleted file mode 100644
index 25903666909e776182ab45beebdb99e44d4fb8a7..0000000000000000000000000000000000000000
--- a/spaces/Hexamind/GDOC/src/domain/wikidoc.py
+++ /dev/null
@@ -1,123 +0,0 @@
-class Doc:
-    def __init__(self, fulltext: str = '', title: str = '', params: dict = {}):
-        self.params = params
-        self.lines = [Line(text.strip(), self.params) for text in fulltext.split("\n") if text.strip()]
-        self.title, self.lines = self._get_title(title)
-        self.container = Container(lines=self.lines, title=self.title, father=self, params=params)
-        self.fulltext = fulltext
-
-    def _get_title(self, title):
-        lines = self.lines
-        if self.params['type'] == 'input_text':
-            if self.lines and self.lines[0] and self.lines[0].type == 'title':
-                title = self.lines[0].text
-                lines = lines[1:]
-            else:
-                title = 'the title is missing'
-        return title, lines
-
-
-class WikiPage(Doc):
-
-    def __init__(self, fulltext='', title=''):
-        self.params = {
-            'type': 'wiki',
-            'startswith_':
-                {'== ': '1', '=== ': '2', '==== ': '3', '===== ': '4', '====== ': '5', '======= ': '6'},
-            'endswith_':
-                [' ==', ' ===', ' ====', ' =====', ' ======', ' ======'],
-
-            'discarded': ["See also", "Notes", "References", "Sources", "External links", "Bibliography",
-                          "Cinematic adaptations", "Further reading", "Maps"]
-        }
-        super().__init__(fulltext=fulltext, title=title, params=self.params)
-
-    def get_paragraphs(self, chunk=500):
-        return self.container.get_paragraphs(chunk)
-
-
-class Container:
-
-    def __init__(self, lines=[], level=0, title='', father=None, params={}):
-
-        self.children = []
-        self.level = level
-        self.title = title
-        self.father = father
-        self.lines = []
-        self._expand(lines)
-        if params and 'discarded' in params.keys():
-            self.children = [child for child in self.children if child.title not in params['discarded']]
-        self.containers = [self]
-        for child in self.children:
-            self.containers += child.containers
-        self.text = ''
-        for child in self.children:
-            self.text += ' ' + child.text
-
-    def _expand(self, lines):
-        new_child = False
-        new_child_lines = []
-        new_child_title = []
-        for line in lines:
-            if not new_child:
-                if line.is_structure:
-                    new_child = True
-                    new_child_lines = []
-                    new_child_title = line.text
-                    line.level = self.level + 1
-                else:
-                    self.lines.append(line)
-
-            else:
-                if self.level + 1 < line.level or not line.is_structure:
-                    new_child_lines.append(line)
-                elif self.level + 1 == line.level:
-                    self.children.append(Container(lines=new_child_lines,
-                                                   level=self.level + 1,
-                                                   title=new_child_title,
-                                                   father=self))
-                    new_child_lines = []
-                    new_child_title = line.text
-        if new_child:
-            self.children.append(Container(lines=new_child_lines,
-                                           level=self.level + 1,
-                                           title=new_child_title,
-                                           father=self))
-
-    def get_paragraphs(self, chunk=500):
-        if len(self.text) < chunk:
-            paragraphs = [self.text]
-        else:
-            paragraphs = [self.root_text]
-            for child in self.children:
-                paragraphs += child.get_paragraphs(chunk)
-        return paragraphs
-
-
-class Line:
-
-    def __init__(self, text, params):
-        self.text = text
-        self.params = params
-        self.type, self.text = self._parse_text()
-        self.level = int(self.type) if self.type.isdigit() else -1
-        self.is_structure = 0 < self.level
-
-
-    def _parse_text(self):
-        def strip_text(text_, start, end):
-            text_ = text_.split(start)[1]
-            if end != "":
-                text_ = text_.split(end)[0]
-            # text += ". \n"
-            return text_.strip()
-
-        startswith_ = self.params['startswith_']
-
-        endswith_ = self.params['endswith_'] if 'endswith_' in self.params.keys() else [""] * len(startswith_)
-        types = [(strip_text(self.text, starter, endswith_[i]), startswith_[starter])
-                 for i, starter in enumerate(startswith_.keys())
-                 if self.text.startswith(starter)]
-        (text, type_) = types[0] if types else (self.text, 'normal')
-        return type_, text.strip()
diff --git a/spaces/ICML2022/OFA/fairseq/examples/textless_nlp/gslm/metrics/asr_metrics/README.md b/spaces/ICML2022/OFA/fairseq/examples/textless_nlp/gslm/metrics/asr_metrics/README.md
deleted file mode 100644
index 90741f42b0b070f2a91b63c8badb817c6aa24230..0000000000000000000000000000000000000000
--- a/spaces/ICML2022/OFA/fairseq/examples/textless_nlp/gslm/metrics/asr_metrics/README.md
+++ /dev/null
@@ -1,87 +0,0 @@
-# ASR-based evaluation
-
-Overall, the life cycle of the ASR-based evaluation for an ULM contains the following steps:
- 1. Training an ULM and sampling from it [[description]](./../../ulm)
- 2. Running UTS on the sampled unit sequences [[description]](./../../unit2speech)
- 3. Pre-processing for the ASR (down-sampling to 16 KHz, aligning length of the generated audio with ground-truth utterances)
- 4. Running ASR
- 5. Calculation of the post-ASR evaluation metrics
-
-Here we assume that you have already went throught the first two steps and focus on the rest.
-
-## Preprocessing
-### Down-sampling to 16KHz
-The bulk conversion can be done by running
-```bash
- python $FAIRSEQ_ROOT/examples/textless_nlp/gslm/unit2speech/convert_to_16k.py $UTS_OUTPUT $UTS_OUTPUT_DOWNSAMPLE
- ```
- where `$UTS_OUTPUT` specifies the directory with the generated audio and `$UTS_OUTPUT_DOWNSAMPLE` is the directory where downsampled audio would be saved.
-
- ### Matching by length
-This step is somewhat optional. However, if you want to compare the fluency and diversity of a generated speech utterance to that of the ground-truth speech with the same prefix, it is a good idea to force them to be of the same length.
-```bash
-python $FAIRSEQ_ROOT/examples/textless_nlp/asr_metrics/cut_as.py \
-    --samples_dir=$UTS_OUTPUT_DOWNSAMPLE --out_dir=$UTS_OUTPUT_DOWNSAMPLE_CUT \
-    --prompts_description=data/ground_truth_continuation_dev.json
-```
-
-Here `ground_truth_continuation_dev.json` is a json file with ground-truth text from LibriSpeech dev-clean, associated with some meta-data (assuming the evaluation is done on dev-clean). This file can be downloaded [[here]](https://dl.fbaipublicfiles.com/textless_nlp/gslm/eval_data/ground_truth_continuation_dev.json). A similar file for the test-clean is [[here]](https://dl.fbaipublicfiles.com/textless_nlp/gslm/eval_data/ground_truth_continuation_test.json). These files are used for the evaluation and contain texts for audio sequences that are at least 6s long.
-
-## Running ASR
-We use a pre-trained wav2vec model to run the ASR step. We firstly need to prepare manifest files which, roughly, tell the ASR system which files we want to transcribe. You can find more details and download the `960h_scratch.pt` checkpoint
-[[here]](https://github.com/pytorch/fairseq/blob/main/examples/wav2vec/README.md)). To run ASR, you would also need to
-install KenLM, Flashlight decoder, and download the KenLM 4-gram English language model.
-
-```bash
- python $FAIRSEQ_ROOT/examples/wav2vec/wav2vec_manifest.py  \
-    $UTS_OUTPUT_DOWNSAMPLE_CUT --valid-percent 0.0  --dest $MANIFEST_DIR --ext wav
-```
-where `$UTS_OUTPUT_DOWNSAMPLE_CUT` speficies the directory with the preprocessed UTS outputs and `$MANIFEST_DIR` is the output directory.
-
-We will be running an out-of-the-box evaluation script which requires ground-truth transcripts to measure quality metrics. We are only
-interested in the transcripts (and we don't have ground-truth outputs for when our ULM generated!), hence we will just generate
-some dummy transcripts instead:
-```bash
-cp $FAIRSEQ_ROOT/examples/textless_nlp/gslm/asr_metrics/misc/dict.ltr.txt $MANIFEST_DIR
-python $FAIRSEQ_ROOT/examples/textless_nlp/gslm/asr_metrics/misc/dummy_asr_data.py  --tsv=$MANIFEST_DIR/train.tsv \
- --output-dir=$MANIFEST_DIR
-```
-
-Now we are ready for running ASR:
-```
-mkdir -p asr
-python $FAIRSEQ_ROOT/examples/speech_recognition/infer.py  \
-    $MANIFEST_DIR \
-    --task audio_pretraining --nbest 1 --path 960h_scratch.pt \
-    --gen-subset=train --results-path $PATH_TO_ASR_OUTPUT \
-    --w2l-decoder kenlm --lm-model 4-gram.bin \
-    --lexicon librispeech/lexicon_ltr.lst --word-score -1 \
-    --sil-weight 0 --lm-weight 2 --criterion ctc --labels ltr --max-tokens 300000 --remove-bpe letter
-```
-where `lexicon_ltr.lst` is the LibriSpeech lexicon and `$PATH_TO_ASR_OUTPUT` is the output directory (can be downloaded [[here]](https://dl.fbaipublicfiles.com/textless_nlp/gslm/eval_data/lexicon_ltr.lst)).
-
-## Evaluation metrics
-We run evaluation on the 1_000 shortest sequences that are at least 6s long. To filter those from the ASR transcript, we additionally provide each metric script with the paths to the manifest and `ground_truth_continuation_*` files.
-
-### Perplexity (PPX)
-To get a PPX metric estimate on an ASR transcript, you need to run the following command:
-```bash
-python ppx.py $PATH_TO_ASR_OUTPUT/hypo.word-960h_scratch.pt-train.txt --cut-tail\
-  --manifest=$MANIFEST_DIR/train.tsv --prompts-description=data/ground_truth_continuation_dev.json
-```
-where `--cut-tail` tells the script to ignore the last token on each line (ASR puts the sequence ID there).
-
-### Self- and Auto-BLEU
-```bash
-python self_bleu.py $PATH_TO_ASR_OUTPUT/hypo.word-960h_scratch.pt-train.txt  --cut-tail \
-  --manifest=$MANIFEST_DIR/train.tsv --prompts-description=data/ground_truth_continuation_dev.json
-```
-
-### Continuation-BLEU
-```bash
-python continuation_eval.py --asr-transcript $PATH_TO_ASR_OUTPUT/hypo.word-960h_scratch.pt-train.txt \
-   --manifest=$MANIFEST_DIR/train.tsv --prompts-description=data/ground_truth_continuation_dev.json
-```
-
-### AUC
-Based on the metrics calculated above, we can estimate the AUC of the perplexity/diversity trade-off. We provide an illustration in a [Colab notebook](https://colab.research.google.com/drive/1pVPfOVax_PU3MkYdHRSsa-SI8GBUldNt?usp=sharing).
diff --git a/spaces/IDEA-Research/Grounded-SAM/segment_anything/segment_anything/utils/transforms.py b/spaces/IDEA-Research/Grounded-SAM/segment_anything/segment_anything/utils/transforms.py
deleted file mode 100644
index 3ad346661f84b0647026e130a552c4b38b83e2ac..0000000000000000000000000000000000000000
--- a/spaces/IDEA-Research/Grounded-SAM/segment_anything/segment_anything/utils/transforms.py
+++ /dev/null
@@ -1,102 +0,0 @@
-# Copyright (c) Meta Platforms, Inc. and affiliates.
-# All rights reserved.
-
-# This source code is licensed under the license found in the
-# LICENSE file in the root directory of this source tree.
-
-import numpy as np
-import torch
-from torch.nn import functional as F
-from torchvision.transforms.functional import resize, to_pil_image  # type: ignore
-
-from copy import deepcopy
-from typing import Tuple
-
-
-class ResizeLongestSide:
-    """
-    Resizes images to longest side 'target_length', as well as provides
-    methods for resizing coordinates and boxes. Provides methods for
-    transforming both numpy array and batched torch tensors.
-    """
-
-    def __init__(self, target_length: int) -> None:
-        self.target_length = target_length
-
-    def apply_image(self, image: np.ndarray) -> np.ndarray:
-        """
-        Expects a numpy array with shape HxWxC in uint8 format.
-        """
-        target_size = self.get_preprocess_shape(image.shape[0], image.shape[1], self.target_length)
-        return np.array(resize(to_pil_image(image), target_size))
-
-    def apply_coords(self, coords: np.ndarray, original_size: Tuple[int, ...]) -> np.ndarray:
-        """
-        Expects a numpy array of length 2 in the final dimension. Requires the
-        original image size in (H, W) format.
-        """
-        old_h, old_w = original_size
-        new_h, new_w = self.get_preprocess_shape(
-            original_size[0], original_size[1], self.target_length
-        )
-        coords = deepcopy(coords).astype(float)
-        coords[..., 0] = coords[..., 0] * (new_w / old_w)
-        coords[..., 1] = coords[..., 1] * (new_h / old_h)
-        return coords
-
-    def apply_boxes(self, boxes: np.ndarray, original_size: Tuple[int, ...]) -> np.ndarray:
-        """
-        Expects a numpy array shape Bx4. Requires the original image size
-        in (H, W) format.
-        """
-        boxes = self.apply_coords(boxes.reshape(-1, 2, 2), original_size)
-        return boxes.reshape(-1, 4)
-
-    def apply_image_torch(self, image: torch.Tensor) -> torch.Tensor:
-        """
-        Expects batched images with shape BxCxHxW and float format. This
-        transformation may not exactly match apply_image. apply_image is
-        the transformation expected by the model.
-        """
-        # Expects an image in BCHW format. May not exactly match apply_image.
-        target_size = self.get_preprocess_shape(image.shape[0], image.shape[1], self.target_length)
-        return F.interpolate(
-            image, target_size, mode="bilinear", align_corners=False, antialias=True
-        )
-
-    def apply_coords_torch(
-        self, coords: torch.Tensor, original_size: Tuple[int, ...]
-    ) -> torch.Tensor:
-        """
-        Expects a torch tensor with length 2 in the last dimension. Requires the
-        original image size in (H, W) format.
-        """
-        old_h, old_w = original_size
-        new_h, new_w = self.get_preprocess_shape(
-            original_size[0], original_size[1], self.target_length
-        )
-        coords = deepcopy(coords).to(torch.float)
-        coords[..., 0] = coords[..., 0] * (new_w / old_w)
-        coords[..., 1] = coords[..., 1] * (new_h / old_h)
-        return coords
-
-    def apply_boxes_torch(
-        self, boxes: torch.Tensor, original_size: Tuple[int, ...]
-    ) -> torch.Tensor:
-        """
-        Expects a torch tensor with shape Bx4. Requires the original image
-        size in (H, W) format.
-        """
-        boxes = self.apply_coords_torch(boxes.reshape(-1, 2, 2), original_size)
-        return boxes.reshape(-1, 4)
-
-    @staticmethod
-    def get_preprocess_shape(oldh: int, oldw: int, long_side_length: int) -> Tuple[int, int]:
-        """
-        Compute the output size given input size and target long side length.
-        """
-        scale = long_side_length * 1.0 / max(oldh, oldw)
-        newh, neww = oldh * scale, oldw * scale
-        neww = int(neww + 0.5)
-        newh = int(newh + 0.5)
-        return (newh, neww)
diff --git a/spaces/IIITT/SumMeet/utils.py b/spaces/IIITT/SumMeet/utils.py
deleted file mode 100644
index 4c56f26b9ad4c8108fa8dc833ab8cceac54510e5..0000000000000000000000000000000000000000
--- a/spaces/IIITT/SumMeet/utils.py
+++ /dev/null
@@ -1,96 +0,0 @@
-"""
-Created on Mon Mar 28 01:07:44 2022
-@author: adeep
-"""
-import numpy as np
-import pandas as pd
-from sklearn.metrics import label_ranking_average_precision_score
-import streamlit as st 
-import joblib
-import os
-from translate import Translator
-from moviepy.editor import VideoFileClip
-import speech_recognition as sr
-from pydub import AudioSegment
-from pydub.silence import split_on_silence
-import transformers
-from transformers import pipeline
-import nltk
-nltk.download('punkt')
-nltk.download('averaged_perceptron_tagger')
-import nltk
-nltk.download('punkt')
-nltk.download('averaged_perceptron_tagger')
-from nltk.tokenize import sent_tokenize
-import re 
-import stanfordnlp
-def welcome():
-    return "Welcome All"
-
-def get_large_audio_transcription(path):  
-    r = sr.Recognizer()
-    sound = AudioSegment.from_wav(path)  
-    chunks = split_on_silence(sound,
-        min_silence_len = 500,
-        silence_thresh = sound.dBFS-14,
-        keep_silence=500,
-    )
-    whole_text = ""
-    for i, audio_chunk in enumerate(chunks, start=1):
-        chunk_filename = os.path.join(f"chunk{i}.wav")
-        audio_chunk.export(chunk_filename, format="wav")
-        with sr.AudioFile(chunk_filename) as source:
-            audio_listened = r.record(source)
-            try:
-                text = r.recognize_google(audio_listened)
-            except sr.UnknownValueError as e:
-                print("Error:", str(e))
-            else:
-                text = f"{text.capitalize()}. "
-                whole_text += text
-    return whole_text
-
-def get_translation(source, dest, text):
-
-    #src = "en"
-    #dst = "hi"
-
-    lang_dict = {
-        'Hindi': 'hi',
-    #    'English':'en',
-        'Malayalam': 'ml',
-        'Marathi': 'mr',
-        'Kannada':'kn', 
-        'Telugu':'te', 
-        'Tamil':'ta', 
-        'Oriya':'or',
-        'Bengali':'bn',
-        'Gujarati':'gu', 
-        'Urdu':'ur'
-    }
-
-    #src = lang_dict[source]
-    dst = lang_dict[dest]
-
-    #task_name = f"translation_{src}_to_{dst}"
-    #model_name = f"Helsinki-NLP/opus-mt-{src}-{dst}"
-
-    #translator  = pipeline(task_name, model=model_name, tokenizer=model_name)
-    translator = Translator(from_lang = 'en', to_lang=dst)
-    a_list = nltk.tokenize.sent_tokenize(text)
-    trans = []
-    for i in a_list: 
-        translation = translator.translate(i)
-        trans.append(translation)
-    
-    return ' '.join(trans)
-    
-
-def truecasing_by_sentence_segmentation(input_text):
-    # split the text into sentences
-    sentences = sent_tokenize(input_text, language='english')
-    # capitalize the sentences
-    sentences_capitalized = [s.capitalize() for s in sentences]
-    # join the capitalized sentences
-    text_truecase = re.sub(" (?=[\.,'!?:;])", "", ' '.join(sentences_capitalized))
-    return text_truecase
\ No newline at end of file
diff --git a/spaces/Ikaros521/moe-tts/text/korean.py b/spaces/Ikaros521/moe-tts/text/korean.py
deleted file mode 100644
index edee07429a450c55e3d8e246997faaa1e0b89cc9..0000000000000000000000000000000000000000
--- a/spaces/Ikaros521/moe-tts/text/korean.py
+++ /dev/null
@@ -1,210 +0,0 @@
-import re
-from jamo import h2j, j2hcj
-import ko_pron
-
-
-# This is a list of Korean classifiers preceded by pure Korean numerals.
-_korean_classifiers = '군데 권 개 그루 닢 대 두 마리 모 모금 뭇 발 발짝 방 번 벌 보루 살 수 술 시 쌈 움큼 정 짝 채 척 첩 축 켤레 톨 통'
-
-# List of (hangul, hangul divided) pairs:
-_hangul_divided = [(re.compile('%s' % x[0]), x[1]) for x in [
-    ('ㄳ', 'ㄱㅅ'),
-    ('ㄵ', 'ㄴㅈ'),
-    ('ㄶ', 'ㄴㅎ'),
-    ('ㄺ', 'ㄹㄱ'),
-    ('ㄻ', 'ㄹㅁ'),
-    ('ㄼ', 'ㄹㅂ'),
-    ('ㄽ', 'ㄹㅅ'),
-    ('ㄾ', 'ㄹㅌ'),
-    ('ㄿ', 'ㄹㅍ'),
-    ('ㅀ', 'ㄹㅎ'),
-    ('ㅄ', 'ㅂㅅ'),
-    ('ㅘ', 'ㅗㅏ'),
-    ('ㅙ', 'ㅗㅐ'),
-    ('ㅚ', 'ㅗㅣ'),
-    ('ㅝ', 'ㅜㅓ'),
-    ('ㅞ', 'ㅜㅔ'),
-    ('ㅟ', 'ㅜㅣ'),
-    ('ㅢ', 'ㅡㅣ'),
-    ('ㅑ', 'ㅣㅏ'),
-    ('ㅒ', 'ㅣㅐ'),
-    ('ㅕ', 'ㅣㅓ'),
-    ('ㅖ', 'ㅣㅔ'),
-    ('ㅛ', 'ㅣㅗ'),
-    ('ㅠ', 'ㅣㅜ')
-]]
-
-# List of (Latin alphabet, hangul) pairs:
-_latin_to_hangul = [(re.compile('%s' % x[0], re.IGNORECASE), x[1]) for x in [
-    ('a', '에이'),
-    ('b', '비'),
-    ('c', '시'),
-    ('d', '디'),
-    ('e', '이'),
-    ('f', '에프'),
-    ('g', '지'),
-    ('h', '에이치'),
-    ('i', '아이'),
-    ('j', '제이'),
-    ('k', '케이'),
-    ('l', '엘'),
-    ('m', '엠'),
-    ('n', '엔'),
-    ('o', '오'),
-    ('p', '피'),
-    ('q', '큐'),
-    ('r', '아르'),
-    ('s', '에스'),
-    ('t', '티'),
-    ('u', '유'),
-    ('v', '브이'),
-    ('w', '더블유'),
-    ('x', '엑스'),
-    ('y', '와이'),
-    ('z', '제트')
-]]
-
-# List of (ipa, lazy ipa) pairs:
-_ipa_to_lazy_ipa = [(re.compile('%s' % x[0], re.IGNORECASE), x[1]) for x in [
-    ('t͡ɕ','ʧ'),
-    ('d͡ʑ','ʥ'),
-    ('ɲ','n^'),
-    ('ɕ','ʃ'),
-    ('ʷ','w'),
-    ('ɭ','l`'),
-    ('ʎ','ɾ'),
-    ('ɣ','ŋ'),
-    ('ɰ','ɯ'),
-    ('ʝ','j'),
-    ('ʌ','ə'),
-    ('ɡ','g'),
-    ('\u031a','#'),
-    ('\u0348','='),
-    ('\u031e',''),
-    ('\u0320',''),
-    ('\u0339','')
-]]
-
-
-def latin_to_hangul(text):
-    for regex, replacement in _latin_to_hangul:
-        text = re.sub(regex, replacement, text)
-    return text
-
-
-def divide_hangul(text):
-    text = j2hcj(h2j(text))
-    for regex, replacement in _hangul_divided:
-        text = re.sub(regex, replacement, text)
-    return text
-
-
-def hangul_number(num, sino=True):
-    '''Reference https://github.com/Kyubyong/g2pK'''
-    num = re.sub(',', '', num)
-
-    if num == '0':
-        return '영'
-    if not sino and num == '20':
-        return '스무'
-
-    digits = '123456789'
-    names = '일이삼사오육칠팔구'
-    digit2name = {d: n for d, n in zip(digits, names)}
-
-    modifiers = '한 두 세 네 다섯 여섯 일곱 여덟 아홉'
-    decimals = '열 스물 서른 마흔 쉰 예순 일흔 여든 아흔'
-    digit2mod = {d: mod for d, mod in zip(digits, modifiers.split())}
-    digit2dec = {d: dec for d, dec in zip(digits, decimals.split())}
-
-    spelledout = []
-    for i, digit in enumerate(num):
-        i = len(num) - i - 1
-        if sino:
-            if i == 0:
-                name = digit2name.get(digit, '')
-            elif i == 1:
-                name = digit2name.get(digit, '') + '십'
-                name = name.replace('일십', '십')
-        else:
-            if i == 0:
-                name = digit2mod.get(digit, '')
-            elif i == 1:
-                name = digit2dec.get(digit, '')
-        if digit == '0':
-            if i % 4 == 0:
-                last_three = spelledout[-min(3, len(spelledout)):]
-                if ''.join(last_three) == '':
-                    spelledout.append('')
-                    continue
-            else:
-                spelledout.append('')
-                continue
-        if i == 2:
-            name = digit2name.get(digit, '') + '백'
-            name = name.replace('일백', '백')
-        elif i == 3:
-            name = digit2name.get(digit, '') + '천'
-            name = name.replace('일천', '천')
-        elif i == 4:
-            name = digit2name.get(digit, '') + '만'
-            name = name.replace('일만', '만')
-        elif i == 5:
-            name = digit2name.get(digit, '') + '십'
-            name = name.replace('일십', '십')
-        elif i == 6:
-            name = digit2name.get(digit, '') + '백'
-            name = name.replace('일백', '백')
-        elif i == 7:
-            name = digit2name.get(digit, '') + '천'
-            name = name.replace('일천', '천')
-        elif i == 8:
-            name = digit2name.get(digit, '') + '억'
-        elif i == 9:
-            name = digit2name.get(digit, '') + '십'
-        elif i == 10:
-            name = digit2name.get(digit, '') + '백'
-        elif i == 11:
-            name = digit2name.get(digit, '') + '천'
-        elif i == 12:
-            name = digit2name.get(digit, '') + '조'
-        elif i == 13:
-            name = digit2name.get(digit, '') + '십'
-        elif i == 14:
-            name = digit2name.get(digit, '') + '백'
-        elif i == 15:
-            name = digit2name.get(digit, '') + '천'
-        spelledout.append(name)
-    return ''.join(elem for elem in spelledout)
-
-
-def number_to_hangul(text):
-    '''Reference https://github.com/Kyubyong/g2pK'''
-    tokens = set(re.findall(r'(\d[\d,]*)([\uac00-\ud71f]+)', text))
-    for token in tokens:
-        num, classifier = token
-        if classifier[:2] in _korean_classifiers or classifier[0] in _korean_classifiers:
-            spelledout = hangul_number(num, sino=False)
-        else:
-            spelledout = hangul_number(num, sino=True)
-        text = text.replace(f'{num}{classifier}', f'{spelledout}{classifier}')
-    # digit by digit for remaining digits
-    digits = '0123456789'
-    names = '영일이삼사오육칠팔구'
-    for d, n in zip(digits, names):
-        text = text.replace(d, n)
-    return text
-
-
-def korean_to_lazy_ipa(text):
-    text = latin_to_hangul(text)
-    text = number_to_hangul(text)
-    text=re.sub('[\uac00-\ud7af]+',lambda x:ko_pron.romanise(x.group(0),'ipa').split('] ~ [')[0],text)
-    for regex, replacement in _ipa_to_lazy_ipa:
-        text = re.sub(regex, replacement, text)
-    return text
-
-
-def korean_to_ipa(text):
-    text = korean_to_lazy_ipa(text)
-    return text.replace('ʧ','tʃ').replace('ʥ','dʑ')
diff --git a/spaces/Ikaros521/so-vits-svc-4.0-ikaros/modules/commons.py b/spaces/Ikaros521/so-vits-svc-4.0-ikaros/modules/commons.py
deleted file mode 100644
index 074888006392e956ce204d8368362dbb2cd4e304..0000000000000000000000000000000000000000
--- a/spaces/Ikaros521/so-vits-svc-4.0-ikaros/modules/commons.py
+++ /dev/null
@@ -1,188 +0,0 @@
-import math
-import numpy as np
-import torch
-from torch import nn
-from torch.nn import functional as F
-
-def slice_pitch_segments(x, ids_str, segment_size=4):
-  ret = torch.zeros_like(x[:, :segment_size])
-  for i in range(x.size(0)):
-    idx_str = ids_str[i]
-    idx_end = idx_str + segment_size
-    ret[i] = x[i, idx_str:idx_end]
-  return ret
-
-def rand_slice_segments_with_pitch(x, pitch, x_lengths=None, segment_size=4):
-  b, d, t = x.size()
-  if x_lengths is None:
-    x_lengths = t
-  ids_str_max = x_lengths - segment_size + 1
-  ids_str = (torch.rand([b]).to(device=x.device) * ids_str_max).to(dtype=torch.long)
-  ret = slice_segments(x, ids_str, segment_size)
-  ret_pitch = slice_pitch_segments(pitch, ids_str, segment_size)
-  return ret, ret_pitch, ids_str
-
-def init_weights(m, mean=0.0, std=0.01):
-  classname = m.__class__.__name__
-  if classname.find("Conv") != -1:
-    m.weight.data.normal_(mean, std)
-
-
-def get_padding(kernel_size, dilation=1):
-  return int((kernel_size*dilation - dilation)/2)
-
-
-def convert_pad_shape(pad_shape):
-  l = pad_shape[::-1]
-  pad_shape = [item for sublist in l for item in sublist]
-  return pad_shape
-
-
-def intersperse(lst, item):
-  result = [item] * (len(lst) * 2 + 1)
-  result[1::2] = lst
-  return result
-
-
-def kl_divergence(m_p, logs_p, m_q, logs_q):
-  """KL(P||Q)"""
-  kl = (logs_q - logs_p) - 0.5
-  kl += 0.5 * (torch.exp(2. * logs_p) + ((m_p - m_q)**2)) * torch.exp(-2. * logs_q)
-  return kl
-
-
-def rand_gumbel(shape):
-  """Sample from the Gumbel distribution, protect from overflows."""
-  uniform_samples = torch.rand(shape) * 0.99998 + 0.00001
-  return -torch.log(-torch.log(uniform_samples))
-
-
-def rand_gumbel_like(x):
-  g = rand_gumbel(x.size()).to(dtype=x.dtype, device=x.device)
-  return g
-
-
-def slice_segments(x, ids_str, segment_size=4):
-  ret = torch.zeros_like(x[:, :, :segment_size])
-  for i in range(x.size(0)):
-    idx_str = ids_str[i]
-    idx_end = idx_str + segment_size
-    ret[i] = x[i, :, idx_str:idx_end]
-  return ret
-
-
-def rand_slice_segments(x, x_lengths=None, segment_size=4):
-  b, d, t = x.size()
-  if x_lengths is None:
-    x_lengths = t
-  ids_str_max = x_lengths - segment_size + 1
-  ids_str = (torch.rand([b]).to(device=x.device) * ids_str_max).to(dtype=torch.long)
-  ret = slice_segments(x, ids_str, segment_size)
-  return ret, ids_str
-
-
-def rand_spec_segments(x, x_lengths=None, segment_size=4):
-  b, d, t = x.size()
-  if x_lengths is None:
-    x_lengths = t
-  ids_str_max = x_lengths - segment_size
-  ids_str = (torch.rand([b]).to(device=x.device) * ids_str_max).to(dtype=torch.long)
-  ret = slice_segments(x, ids_str, segment_size)
-  return ret, ids_str
-
-
-def get_timing_signal_1d(
-    length, channels, min_timescale=1.0, max_timescale=1.0e4):
-  position = torch.arange(length, dtype=torch.float)
-  num_timescales = channels // 2
-  log_timescale_increment = (
-      math.log(float(max_timescale) / float(min_timescale)) /
-      (num_timescales - 1))
-  inv_timescales = min_timescale * torch.exp(
-      torch.arange(num_timescales, dtype=torch.float) * -log_timescale_increment)
-  scaled_time = position.unsqueeze(0) * inv_timescales.unsqueeze(1)
-  signal = torch.cat([torch.sin(scaled_time), torch.cos(scaled_time)], 0)
-  signal = F.pad(signal, [0, 0, 0, channels % 2])
-  signal = signal.view(1, channels, length)
-  return signal
-
-
-def add_timing_signal_1d(x, min_timescale=1.0, max_timescale=1.0e4):
-  b, channels, length = x.size()
-  signal = get_timing_signal_1d(length, channels, min_timescale, max_timescale)
-  return x + signal.to(dtype=x.dtype, device=x.device)
-
-
-def cat_timing_signal_1d(x, min_timescale=1.0, max_timescale=1.0e4, axis=1):
-  b, channels, length = x.size()
-  signal = get_timing_signal_1d(length, channels, min_timescale, max_timescale)
-  return torch.cat([x, signal.to(dtype=x.dtype, device=x.device)], axis)
-
-
-def subsequent_mask(length):
-  mask = torch.tril(torch.ones(length, length)).unsqueeze(0).unsqueeze(0)
-  return mask
-
-
-@torch.jit.script
-def fused_add_tanh_sigmoid_multiply(input_a, input_b, n_channels):
-  n_channels_int = n_channels[0]
-  in_act = input_a + input_b
-  t_act = torch.tanh(in_act[:, :n_channels_int, :])
-  s_act = torch.sigmoid(in_act[:, n_channels_int:, :])
-  acts = t_act * s_act
-  return acts
-
-
-def convert_pad_shape(pad_shape):
-  l = pad_shape[::-1]
-  pad_shape = [item for sublist in l for item in sublist]
-  return pad_shape
-
-
-def shift_1d(x):
-  x = F.pad(x, convert_pad_shape([[0, 0], [0, 0], [1, 0]]))[:, :, :-1]
-  return x
-
-
-def sequence_mask(length, max_length=None):
-  if max_length is None:
-    max_length = length.max()
-  x = torch.arange(max_length, dtype=length.dtype, device=length.device)
-  return x.unsqueeze(0) < length.unsqueeze(1)
-
-
-def generate_path(duration, mask):
-  """
-  duration: [b, 1, t_x]
-  mask: [b, 1, t_y, t_x]
-  """
-  device = duration.device
-  
-  b, _, t_y, t_x = mask.shape
-  cum_duration = torch.cumsum(duration, -1)
-  
-  cum_duration_flat = cum_duration.view(b * t_x)
-  path = sequence_mask(cum_duration_flat, t_y).to(mask.dtype)
-  path = path.view(b, t_x, t_y)
-  path = path - F.pad(path, convert_pad_shape([[0, 0], [1, 0], [0, 0]]))[:, :-1]
-  path = path.unsqueeze(1).transpose(2,3) * mask
-  return path
-
-
-def clip_grad_value_(parameters, clip_value, norm_type=2):
-  if isinstance(parameters, torch.Tensor):
-    parameters = [parameters]
-  parameters = list(filter(lambda p: p.grad is not None, parameters))
-  norm_type = float(norm_type)
-  if clip_value is not None:
-    clip_value = float(clip_value)
-
-  total_norm = 0
-  for p in parameters:
-    param_norm = p.grad.data.norm(norm_type)
-    total_norm += param_norm.item() ** norm_type
-    if clip_value is not None:
-      p.grad.data.clamp_(min=-clip_value, max=clip_value)
-  total_norm = total_norm ** (1. / norm_type)
-  return total_norm
diff --git a/spaces/JacobLinCool/captcha-recognizer/src/preprocess.py b/spaces/JacobLinCool/captcha-recognizer/src/preprocess.py
deleted file mode 100644
index 0ba37031449d0e283838c58b61e3882c5ba00280..0000000000000000000000000000000000000000
--- a/spaces/JacobLinCool/captcha-recognizer/src/preprocess.py
+++ /dev/null
@@ -1,28 +0,0 @@
-import cv2
-import numpy as np
-
-
-def preprocess(image: np.ndarray) -> np.ndarray:
-    # Upscale, interpolation with nearest neighbor
-    image = cv2.resize(image, (0, 0), fx=3, fy=3, interpolation=cv2.INTER_NEAREST)
-
-    # Denoise gray-like pixels
-    hsv = cv2.cvtColor(image, cv2.COLOR_BGR2HSV)
-    mask = cv2.inRange(hsv, (0, 70, 70), (255, 255, 255))
-    mask = cv2.bitwise_not(mask)
-    image[np.where(mask)] = 255
-
-    # Convert to binary
-    image = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)
-    _, image = cv2.threshold(image, 0, 255, cv2.THRESH_OTSU)
-
-    # Fix some holes
-    kernel = np.ones((3, 3), np.uint8)
-    image = cv2.morphologyEx(image, cv2.MORPH_OPEN, kernel, iterations=2)
-
-    # add padding
-    image = cv2.copyMakeBorder(
-        image, 5, 5, 5, 5, cv2.BORDER_CONSTANT, value=(255, 255, 255)
-    )
-
-    return image
diff --git a/spaces/JohnSmith9982/VITS-Umamusume-voice-synthesizer/app.py b/spaces/JohnSmith9982/VITS-Umamusume-voice-synthesizer/app.py
deleted file mode 100644
index c9bfb000af1af5ec0a745290b95431df58ad7a61..0000000000000000000000000000000000000000
--- a/spaces/JohnSmith9982/VITS-Umamusume-voice-synthesizer/app.py
+++ /dev/null
@@ -1,256 +0,0 @@
-import argparse
-import json
-import os
-import re
-import tempfile
-import logging
-
-logging.getLogger('numba').setLevel(logging.WARNING)
-import librosa
-import numpy as np
-import torch
-from torch import no_grad, LongTensor
-import commons
-import utils
-import gradio as gr
-import gradio.utils as gr_utils
-import gradio.processing_utils as gr_processing_utils
-import ONNXVITS_infer
-import models
-from text import text_to_sequence, _clean_text
-from text.symbols import symbols
-from mel_processing import spectrogram_torch
-import psutil
-from datetime import datetime
-
-language_marks = {
-    "Japanese": "",
-    "日本語": "[JA]",
-    "简体中文": "[ZH]",
-    "English": "[EN]",
-    "Mix": "",
-}
-
-limitation = os.getenv("SYSTEM") == "spaces"  # limit text and audio length in huggingface spaces
-
-
-def create_tts_fn(model, hps, speaker_ids):
-    def tts_fn(text, speaker, language, speed, is_symbol):
-        if limitation:
-            text_len = len(re.sub("\[([A-Z]{2})\]", "", text))
-            max_len = 150
-            if is_symbol:
-                max_len *= 3
-            if text_len > max_len:
-                return "Error: Text is too long", None
-        if language is not None:
-            text = language_marks[language] + text + language_marks[language]
-        speaker_id = speaker_ids[speaker]
-        stn_tst = get_text(text, hps, is_symbol)
-        with no_grad():
-            x_tst = stn_tst.unsqueeze(0)
-            x_tst_lengths = LongTensor([stn_tst.size(0)])
-            sid = LongTensor([speaker_id])
-            audio = model.infer(x_tst, x_tst_lengths, sid=sid, noise_scale=.667, noise_scale_w=0.8,
-                                length_scale=1.0 / speed)[0][0, 0].data.cpu().float().numpy()
-        del stn_tst, x_tst, x_tst_lengths, sid
-        return "Success", (hps.data.sampling_rate, audio)
-
-    return tts_fn
-
-
-def create_vc_fn(model, hps, speaker_ids):
-    def vc_fn(original_speaker, target_speaker, input_audio):
-        if input_audio is None:
-            return "You need to upload an audio", None
-        sampling_rate, audio = input_audio
-        duration = audio.shape[0] / sampling_rate
-        if limitation and duration > 30:
-            return "Error: Audio is too long", None
-        original_speaker_id = speaker_ids[original_speaker]
-        target_speaker_id = speaker_ids[target_speaker]
-
-        audio = (audio / np.iinfo(audio.dtype).max).astype(np.float32)
-        if len(audio.shape) > 1:
-            audio = librosa.to_mono(audio.transpose(1, 0))
-        if sampling_rate != hps.data.sampling_rate:
-            audio = librosa.resample(audio, orig_sr=sampling_rate, target_sr=hps.data.sampling_rate)
-        with no_grad():
-            y = torch.FloatTensor(audio)
-            y = y.unsqueeze(0)
-            spec = spectrogram_torch(y, hps.data.filter_length,
-                                     hps.data.sampling_rate, hps.data.hop_length, hps.data.win_length,
-                                     center=False)
-            spec_lengths = LongTensor([spec.size(-1)])
-            sid_src = LongTensor([original_speaker_id])
-            sid_tgt = LongTensor([target_speaker_id])
-            audio = model.voice_conversion(spec, spec_lengths, sid_src=sid_src, sid_tgt=sid_tgt)[0][
-                0, 0].data.cpu().float().numpy()
-        del y, spec, spec_lengths, sid_src, sid_tgt
-        return "Success", (hps.data.sampling_rate, audio)
-
-    return vc_fn
-
-
-def get_text(text, hps, is_symbol):
-    text_norm = text_to_sequence(text, hps.symbols, [] if is_symbol else hps.data.text_cleaners)
-    if hps.data.add_blank:
-        text_norm = commons.intersperse(text_norm, 0)
-    text_norm = LongTensor(text_norm)
-    return text_norm
-
-
-def create_to_symbol_fn(hps):
-    def to_symbol_fn(is_symbol_input, input_text, temp_text):
-        return (_clean_text(input_text, hps.data.text_cleaners), input_text) if is_symbol_input \
-            else (temp_text, temp_text)
-
-    return to_symbol_fn
-
-
-models_tts = []
-models_vc = []
-models_info = [
-    {
-        "title": "Trilingual",
-        "languages": ['日本語', '简体中文', 'English', 'Mix'],
-        "description": """
-    This model is trained on a mix up of Umamusume, Genshin Impact, Sanoba Witch & VCTK voice data to learn multilanguage.
-    All characters can speak English, Chinese & Japanese.\n\n
-    To mix multiple languages in a single sentence, wrap the corresponding part with language tokens
-     ([JA] for Japanese, [ZH] for Chinese, [EN] for English), as shown in the examples.\n\n
-    这个模型在赛马娘，原神，魔女的夜宴以及VCTK数据集上混合训练以学习多种语言。
-    所有角色均可说中日英三语。\n\n
-    若需要在同一个句子中混合多种语言，使用相应的语言标记包裹句子。
-    （日语用[JA], 中文用[ZH], 英文用[EN]），参考Examples中的示例。
-    """,
-        "model_path": "./pretrained_models/G_trilingual.pth",
-        "config_path": "./configs/uma_trilingual.json",
-        "examples": [['你好，训练员先生，很高兴见到你。', '草上飞 Grass Wonder (Umamusume Pretty Derby)', '简体中文', 1, False],
-                     ['To be honest, I have no idea what to say as examples.', '派蒙 Paimon (Genshin Impact)', 'English',
-                      1, False],
-                     ['授業中に出しだら，学校生活終わるですわ。', '綾地 寧々 Ayachi Nene (Sanoba Witch)', '日本語', 1, False],
-                     ['[JA]こんにちわ。[JA][ZH]你好！[ZH][EN]Hello![EN]', '綾地 寧々 Ayachi Nene (Sanoba Witch)', 'Mix', 1, False]],
-        "onnx_dir": "./ONNX_net/G_trilingual/"
-    },
-    {
-        "title": "Japanese",
-        "languages": ["Japanese"],
-        "description": """
-                       This model contains 87 characters from Umamusume: Pretty Derby, Japanese only.\n\n
-                       这个模型包含赛马娘的所有87名角色，只能合成日语。
-                       """,
-        "model_path": "./pretrained_models/G_jp.pth",
-        "config_path": "./configs/uma87.json",
-        "examples": [['お疲れ様です，トレーナーさん。', '无声铃鹿 Silence Suzuka (Umamusume Pretty Derby)', 'Japanese', 1, False],
-                     ['張り切っていこう！', '北部玄驹 Kitasan Black (Umamusume Pretty Derby)', 'Japanese', 1, False],
-                     ['何でこんなに慣れでんのよ，私のほが先に好きだっだのに。', '草上飞 Grass Wonder (Umamusume Pretty Derby)', 'Japanese', 1, False],
-                     ['授業中に出しだら，学校生活終わるですわ。', '目白麦昆 Mejiro Mcqueen (Umamusume Pretty Derby)', 'Japanese', 1, False],
-                     ['お帰りなさい，お兄様！', '米浴 Rice Shower (Umamusume Pretty Derby)', 'Japanese', 1, False],
-                     ['私の処女をもらっでください！', '米浴 Rice Shower (Umamusume Pretty Derby)', 'Japanese', 1, False]],
-        "onnx_dir": "./ONNX_net/G_jp/"
-    },
-]
-
-if __name__ == "__main__":
-    parser = argparse.ArgumentParser()
-    parser.add_argument("--share", action="store_true", default=False, help="share gradio app")
-    args = parser.parse_args()
-    for info in models_info:
-        name = info['title']
-        lang = info['languages']
-        examples = info['examples']
-        config_path = info['config_path']
-        model_path = info['model_path']
-        description = info['description']
-        onnx_dir = info["onnx_dir"]
-        hps = utils.get_hparams_from_file(config_path)
-        model = ONNXVITS_infer.SynthesizerTrn(
-            len(hps.symbols),
-            hps.data.filter_length // 2 + 1,
-            hps.train.segment_size // hps.data.hop_length,
-            n_speakers=hps.data.n_speakers,
-            ONNX_dir=onnx_dir,
-            **hps.model)
-        utils.load_checkpoint(model_path, model, None)
-        model.eval()
-        speaker_ids = hps.speakers
-        speakers = list(hps.speakers.keys())
-        models_tts.append((name, description, speakers, lang, examples,
-                           hps.symbols, create_tts_fn(model, hps, speaker_ids),
-                           create_to_symbol_fn(hps)))
-        models_vc.append((name, description, speakers, create_vc_fn(model, hps, speaker_ids)))
-    app = gr.Blocks()
-    with app:
-        gr.Markdown("# English & Chinese & Japanese Anime TTS\n\n"
-                    "![visitor badge](https://visitor-badge.glitch.me/badge?page_id=Plachta.VITS-Umamusume-voice-synthesizer)\n\n"
-                    "Including Japanese TTS & Trilingual TTS, speakers are all anime characters. \n\n包含一个纯日语TTS和一个中日英三语TTS模型，主要为二次元角色。\n\n"
-                    "If you have any suggestions or bug reports, feel free to open discussion in [Community](https://huggingface.co/spaces/Plachta/VITS-Umamusume-voice-synthesizer/discussions).\n\n"
-                    "若有bug反馈或建议，请在[Community](https://huggingface.co/spaces/Plachta/VITS-Umamusume-voice-synthesizer/discussions)下开启一个新的Discussion。 \n\n"
-                    )
-        with gr.Tabs():
-            with gr.TabItem("TTS"):
-                with gr.Tabs():
-                    for i, (name, description, speakers, lang, example, symbols, tts_fn, to_symbol_fn) in enumerate(
-                            models_tts):
-                        with gr.TabItem(name):
-                            gr.Markdown(description)
-                            with gr.Row():
-                                with gr.Column():
-                                    textbox = gr.TextArea(label="Text",
-                                                          placeholder="Type your sentence here (Maximum 150 words)",
-                                                          value="こんにちわ。", elem_id=f"tts-input")
-                                    with gr.Accordion(label="Phoneme Input", open=False):
-                                        temp_text_var = gr.Variable()
-                                        symbol_input = gr.Checkbox(value=False, label="Symbol input")
-                                        symbol_list = gr.Dataset(label="Symbol list", components=[textbox],
-                                                                 samples=[[x] for x in symbols],
-                                                                 elem_id=f"symbol-list")
-                                        symbol_list_json = gr.Json(value=symbols, visible=False)
-                                    symbol_input.change(to_symbol_fn,
-                                                        [symbol_input, textbox, temp_text_var],
-                                                        [textbox, temp_text_var])
-                                    symbol_list.click(None, [symbol_list, symbol_list_json], textbox,
-                                                      _js=f"""
-                                    (i, symbols, text) => {{
-                                        let root = document.querySelector("body > gradio-app");
-                                        if (root.shadowRoot != null)
-                                            root = root.shadowRoot;
-                                        let text_input = root.querySelector("#tts-input").querySelector("textarea");
-                                        let startPos = text_input.selectionStart;
-                                        let endPos = text_input.selectionEnd;
-                                        let oldTxt = text_input.value;
-                                        let result = oldTxt.substring(0, startPos) + symbols[i] + oldTxt.substring(endPos);
-                                        text_input.value = result;
-                                        let x = window.scrollX, y = window.scrollY;
-                                        text_input.focus();
-                                        text_input.selectionStart = startPos + symbols[i].length;
-                                        text_input.selectionEnd = startPos + symbols[i].length;
-                                        text_input.blur();
-                                        window.scrollTo(x, y);
-
-                                        text = text_input.value;
-
-                                        return text;
-                                    }}""")
-                                    # select character
-                                    char_dropdown = gr.Dropdown(choices=speakers, value=speakers[0], label='character')
-                                    language_dropdown = gr.Dropdown(choices=lang, value=lang[0], label='language')
-                                    duration_slider = gr.Slider(minimum=0.1, maximum=5, value=1, step=0.1,
-                                                                label='速度 Speed')
-                                with gr.Column():
-                                    text_output = gr.Textbox(label="Message")
-                                    audio_output = gr.Audio(label="Output Audio", elem_id="tts-audio")
-                                    btn = gr.Button("Generate!")
-                                    btn.click(tts_fn,
-                                              inputs=[textbox, char_dropdown, language_dropdown, duration_slider,
-                                                      symbol_input],
-                                              outputs=[text_output, audio_output])
-                            gr.Examples(
-                                examples=example,
-                                inputs=[textbox, char_dropdown, language_dropdown,
-                                        duration_slider, symbol_input],
-                                outputs=[text_output, audio_output],
-                                fn=tts_fn
-                            )
-    app.queue(concurrency_count=3).launch(show_api=False, share=args.share)
\ No newline at end of file
diff --git a/spaces/JohnSmith9982/VITS-Umamusume-voice-synthesizer/text/cleaners.py b/spaces/JohnSmith9982/VITS-Umamusume-voice-synthesizer/text/cleaners.py
deleted file mode 100644
index c80e113b2b81a66134800dbdaa29c7d96a0152a7..0000000000000000000000000000000000000000
--- a/spaces/JohnSmith9982/VITS-Umamusume-voice-synthesizer/text/cleaners.py
+++ /dev/null
@@ -1,146 +0,0 @@
-import re
-
-
-def japanese_cleaners(text):
-    from text.japanese import japanese_to_romaji_with_accent
-    text = japanese_to_romaji_with_accent(text)
-    text = re.sub(r'([A-Za-z])$', r'\1.', text)
-    return text
-
-
-def japanese_cleaners2(text):
-    return japanese_cleaners(text).replace('ts', 'ʦ').replace('...', '…')
-
-
-def korean_cleaners(text):
-    '''Pipeline for Korean text'''
-    from text.korean import latin_to_hangul, number_to_hangul, divide_hangul
-    text = latin_to_hangul(text)
-    text = number_to_hangul(text)
-    text = divide_hangul(text)
-    text = re.sub(r'([\u3131-\u3163])$', r'\1.', text)
-    return text
-
-
-def chinese_cleaners(text):
-    '''Pipeline for Chinese text'''
-    from text.mandarin import number_to_chinese, chinese_to_bopomofo, latin_to_bopomofo
-    text = number_to_chinese(text)
-    text = chinese_to_bopomofo(text)
-    text = latin_to_bopomofo(text)
-    text = re.sub(r'([ˉˊˇˋ˙])$', r'\1。', text)
-    return text
-
-
-def zh_ja_mixture_cleaners(text):
-    from text.mandarin import chinese_to_romaji
-    from text.japanese import japanese_to_romaji_with_accent
-    text = re.sub(r'\[ZH\](.*?)\[ZH\]',
-                  lambda x: chinese_to_romaji(x.group(1))+' ', text)
-    text = re.sub(r'\[JA\](.*?)\[JA\]', lambda x: japanese_to_romaji_with_accent(
-        x.group(1)).replace('ts', 'ʦ').replace('u', 'ɯ').replace('...', '…')+' ', text)
-    text = re.sub(r'\s+$', '', text)
-    text = re.sub(r'([^\.,!\?\-…~])$', r'\1.', text)
-    return text
-
-
-def sanskrit_cleaners(text):
-    text = text.replace('॥', '।').replace('ॐ', 'ओम्')
-    if text[-1] != '।':
-        text += ' ।'
-    return text
-
-
-def cjks_cleaners(text):
-    from text.mandarin import chinese_to_lazy_ipa
-    from text.japanese import japanese_to_ipa
-    from text.korean import korean_to_lazy_ipa
-    from text.sanskrit import devanagari_to_ipa
-    from text.english import english_to_lazy_ipa
-    text = re.sub(r'\[ZH\](.*?)\[ZH\]',
-                  lambda x: chinese_to_lazy_ipa(x.group(1))+' ', text)
-    text = re.sub(r'\[JA\](.*?)\[JA\]',
-                  lambda x: japanese_to_ipa(x.group(1))+' ', text)
-    text = re.sub(r'\[KO\](.*?)\[KO\]',
-                  lambda x: korean_to_lazy_ipa(x.group(1))+' ', text)
-    text = re.sub(r'\[SA\](.*?)\[SA\]',
-                  lambda x: devanagari_to_ipa(x.group(1))+' ', text)
-    text = re.sub(r'\[EN\](.*?)\[EN\]',
-                  lambda x: english_to_lazy_ipa(x.group(1))+' ', text)
-    text = re.sub(r'\s+$', '', text)
-    text = re.sub(r'([^\.,!\?\-…~])$', r'\1.', text)
-    return text
-
-
-def cjke_cleaners(text):
-    from text.mandarin import chinese_to_lazy_ipa
-    from text.japanese import japanese_to_ipa
-    from text.korean import korean_to_ipa
-    from text.english import english_to_ipa2
-    text = re.sub(r'\[ZH\](.*?)\[ZH\]', lambda x: chinese_to_lazy_ipa(x.group(1)).replace(
-        'ʧ', 'tʃ').replace('ʦ', 'ts').replace('ɥan', 'ɥæn')+' ', text)
-    text = re.sub(r'\[JA\](.*?)\[JA\]', lambda x: japanese_to_ipa(x.group(1)).replace('ʧ', 'tʃ').replace(
-        'ʦ', 'ts').replace('ɥan', 'ɥæn').replace('ʥ', 'dz')+' ', text)
-    text = re.sub(r'\[KO\](.*?)\[KO\]',
-                  lambda x: korean_to_ipa(x.group(1))+' ', text)
-    text = re.sub(r'\[EN\](.*?)\[EN\]', lambda x: english_to_ipa2(x.group(1)).replace('ɑ', 'a').replace(
-        'ɔ', 'o').replace('ɛ', 'e').replace('ɪ', 'i').replace('ʊ', 'u')+' ', text)
-    text = re.sub(r'\s+$', '', text)
-    text = re.sub(r'([^\.,!\?\-…~])$', r'\1.', text)
-    return text
-
-
-def cjke_cleaners2(text):
-    from text.mandarin import chinese_to_ipa
-    from text.japanese import japanese_to_ipa2
-    from text.korean import korean_to_ipa
-    from text.english import english_to_ipa2
-    text = re.sub(r'\[ZH\](.*?)\[ZH\]',
-                  lambda x: chinese_to_ipa(x.group(1))+' ', text)
-    text = re.sub(r'\[JA\](.*?)\[JA\]',
-                  lambda x: japanese_to_ipa2(x.group(1))+' ', text)
-    text = re.sub(r'\[KO\](.*?)\[KO\]',
-                  lambda x: korean_to_ipa(x.group(1))+' ', text)
-    text = re.sub(r'\[EN\](.*?)\[EN\]',
-                  lambda x: english_to_ipa2(x.group(1))+' ', text)
-    text = re.sub(r'\s+$', '', text)
-    text = re.sub(r'([^\.,!\?\-…~])$', r'\1.', text)
-    return text
-
-
-def thai_cleaners(text):
-    from text.thai import num_to_thai, latin_to_thai
-    text = num_to_thai(text)
-    text = latin_to_thai(text)
-    return text
-
-
-def shanghainese_cleaners(text):
-    from text.shanghainese import shanghainese_to_ipa
-    text = shanghainese_to_ipa(text)
-    text = re.sub(r'([^\.,!\?\-…~])$', r'\1.', text)
-    return text
-
-
-def chinese_dialect_cleaners(text):
-    from text.mandarin import chinese_to_ipa2
-    from text.japanese import japanese_to_ipa3
-    from text.shanghainese import shanghainese_to_ipa
-    from text.cantonese import cantonese_to_ipa
-    from text.english import english_to_lazy_ipa2
-    from text.ngu_dialect import ngu_dialect_to_ipa
-    text = re.sub(r'\[ZH\](.*?)\[ZH\]',
-                  lambda x: chinese_to_ipa2(x.group(1))+' ', text)
-    text = re.sub(r'\[JA\](.*?)\[JA\]',
-                  lambda x: japanese_to_ipa3(x.group(1)).replace('Q', 'ʔ')+' ', text)
-    text = re.sub(r'\[SH\](.*?)\[SH\]', lambda x: shanghainese_to_ipa(x.group(1)).replace('1', '˥˧').replace('5',
-                  '˧˧˦').replace('6', '˩˩˧').replace('7', '˥').replace('8', '˩˨').replace('ᴀ', 'ɐ').replace('ᴇ', 'e')+' ', text)
-    text = re.sub(r'\[GD\](.*?)\[GD\]',
-                  lambda x: cantonese_to_ipa(x.group(1))+' ', text)
-    text = re.sub(r'\[EN\](.*?)\[EN\]',
-                  lambda x: english_to_lazy_ipa2(x.group(1))+' ', text)
-    text = re.sub(r'\[([A-Z]{2})\](.*?)\[\1\]', lambda x: ngu_dialect_to_ipa(x.group(2), x.group(
-        1)).replace('ʣ', 'dz').replace('ʥ', 'dʑ').replace('ʦ', 'ts').replace('ʨ', 'tɕ')+' ', text)
-    text = re.sub(r'\s+$', '', text)
-    text = re.sub(r'([^\.,!\?\-…~])$', r'\1.', text)
-    return text
diff --git a/spaces/Joom/Xtramrks/README.md b/spaces/Joom/Xtramrks/README.md
deleted file mode 100644
index e3bb141d63765d3f3a794e035ca83254db0c82d7..0000000000000000000000000000000000000000
--- a/spaces/Joom/Xtramrks/README.md
+++ /dev/null
@@ -1,13 +0,0 @@
----
-title: Xtramrks
-emoji: 🌖
-colorFrom: purple
-colorTo: yellow
-sdk: gradio
-sdk_version: 3.4.1
-app_file: app.py
-pinned: false
-license: mit
----
-
-Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
diff --git a/spaces/Kevin676/ChatGPT-with-Voice-Cloning-in-Chinese/ppg_extractor/frontend.py b/spaces/Kevin676/ChatGPT-with-Voice-Cloning-in-Chinese/ppg_extractor/frontend.py
deleted file mode 100644
index 32549ed050655d79be1793a9cf04d9d52644794a..0000000000000000000000000000000000000000
--- a/spaces/Kevin676/ChatGPT-with-Voice-Cloning-in-Chinese/ppg_extractor/frontend.py
+++ /dev/null
@@ -1,115 +0,0 @@
-import copy
-from typing import Tuple
-import numpy as np
-import torch
-from torch_complex.tensor import ComplexTensor
-
-from .log_mel import LogMel
-from .stft import Stft
-
-
-class DefaultFrontend(torch.nn.Module):
-    """Conventional frontend structure for ASR
-
-    Stft -> WPE -> MVDR-Beamformer -> Power-spec -> Mel-Fbank -> CMVN
-    """
-
-    def __init__(
-        self,
-        fs: 16000,
-        n_fft: int = 1024,
-        win_length: int = 800,
-        hop_length: int = 160,
-        center: bool = True,
-        pad_mode: str = "reflect",
-        normalized: bool = False,
-        onesided: bool = True,
-        n_mels: int = 80,
-        fmin: int = None,
-        fmax: int = None,
-        htk: bool = False,
-        norm=1,
-        frontend_conf=None, #Optional[dict] = get_default_kwargs(Frontend),
-        kaldi_padding_mode=False,
-        downsample_rate: int = 1,
-    ):
-        super().__init__()
-        self.downsample_rate = downsample_rate
-
-        # Deepcopy (In general, dict shouldn't be used as default arg)
-        frontend_conf = copy.deepcopy(frontend_conf)
-
-        self.stft = Stft(
-            n_fft=n_fft,
-            win_length=win_length,
-            hop_length=hop_length,
-            center=center,
-            pad_mode=pad_mode,
-            normalized=normalized,
-            onesided=onesided,
-            kaldi_padding_mode=kaldi_padding_mode
-        )
-        if frontend_conf is not None:
-            self.frontend = Frontend(idim=n_fft // 2 + 1, **frontend_conf)
-        else:
-            self.frontend = None
-
-        self.logmel = LogMel(
-            fs=fs, n_fft=n_fft, n_mels=n_mels, fmin=fmin, fmax=fmax, htk=htk, norm=norm,
-        )
-        self.n_mels = n_mels
-
-    def output_size(self) -> int:
-        return self.n_mels
-
-    def forward(
-        self, input: torch.Tensor, input_lengths: torch.Tensor
-    ) -> Tuple[torch.Tensor, torch.Tensor]:
-        # 1. Domain-conversion: e.g. Stft: time -> time-freq
-        input_stft, feats_lens = self.stft(input, input_lengths)
-
-        assert input_stft.dim() >= 4, input_stft.shape
-        # "2" refers to the real/imag parts of Complex
-        assert input_stft.shape[-1] == 2, input_stft.shape
-
-        # Change torch.Tensor to ComplexTensor
-        # input_stft: (..., F, 2) -> (..., F)
-        input_stft = ComplexTensor(input_stft[..., 0], input_stft[..., 1])
-
-        # 2. [Option] Speech enhancement
-        if self.frontend is not None:
-            assert isinstance(input_stft, ComplexTensor), type(input_stft)
-            # input_stft: (Batch, Length, [Channel], Freq)
-            input_stft, _, mask = self.frontend(input_stft, feats_lens)
-
-        # 3. [Multi channel case]: Select a channel
-        if input_stft.dim() == 4:
-            # h: (B, T, C, F) -> h: (B, T, F)
-            if self.training:
-                # Select 1ch randomly
-                ch = np.random.randint(input_stft.size(2))
-                input_stft = input_stft[:, :, ch, :]
-            else:
-                # Use the first channel
-                input_stft = input_stft[:, :, 0, :]
-
-        # 4. STFT -> Power spectrum
-        # h: ComplexTensor(B, T, F) -> torch.Tensor(B, T, F)
-        input_power = input_stft.real ** 2 + input_stft.imag ** 2
-
-        # 5. Feature transform e.g. Stft -> Log-Mel-Fbank
-        # input_power: (Batch, [Channel,] Length, Freq)
-        #       -> input_feats: (Batch, Length, Dim)
-        input_feats, _ = self.logmel(input_power, feats_lens)
-               
-        # NOTE(sx): pad
-        max_len = input_feats.size(1)
-        if self.downsample_rate > 1 and max_len % self.downsample_rate != 0:
-            padding = self.downsample_rate - max_len % self.downsample_rate
-            # print("Logmel: ", input_feats.size())
-            input_feats = torch.nn.functional.pad(input_feats, (0, 0, 0, padding),
-                                                  "constant", 0)
-            # print("Logmel(after padding): ",input_feats.size())
-            feats_lens[torch.argmax(feats_lens)] = max_len + padding 
-
-        return input_feats, feats_lens
diff --git a/spaces/Kevin676/ChatGPT-with-Voice-Cloning-in-Chinese/vocoder/hifigan/utils.py b/spaces/Kevin676/ChatGPT-with-Voice-Cloning-in-Chinese/vocoder/hifigan/utils.py
deleted file mode 100644
index e67cbcda0744201d8342b212160808b7c934ea64..0000000000000000000000000000000000000000
--- a/spaces/Kevin676/ChatGPT-with-Voice-Cloning-in-Chinese/vocoder/hifigan/utils.py
+++ /dev/null
@@ -1,58 +0,0 @@
-import glob
-import os
-import matplotlib
-import torch
-from torch.nn.utils import weight_norm
-matplotlib.use("Agg")
-import matplotlib.pylab as plt
-
-
-def plot_spectrogram(spectrogram):
-    fig, ax = plt.subplots(figsize=(10, 2))
-    im = ax.imshow(spectrogram, aspect="auto", origin="lower",
-                   interpolation='none')
-    plt.colorbar(im, ax=ax)
-
-    fig.canvas.draw()
-    plt.close()
-
-    return fig
-
-
-def init_weights(m, mean=0.0, std=0.01):
-    classname = m.__class__.__name__
-    if classname.find("Conv") != -1:
-        m.weight.data.normal_(mean, std)
-
-
-def apply_weight_norm(m):
-    classname = m.__class__.__name__
-    if classname.find("Conv") != -1:
-        weight_norm(m)
-
-
-def get_padding(kernel_size, dilation=1):
-    return int((kernel_size*dilation - dilation)/2)
-
-
-def load_checkpoint(filepath, device):
-    assert os.path.isfile(filepath)
-    print("Loading '{}'".format(filepath))
-    checkpoint_dict = torch.load(filepath, map_location=device)
-    print("Complete.")
-    return checkpoint_dict
-
-
-def save_checkpoint(filepath, obj):
-    print("Saving checkpoint to {}".format(filepath))
-    torch.save(obj, filepath)
-    print("Complete.")
-
-
-def scan_checkpoint(cp_dir, prefix):
-    pattern = os.path.join(cp_dir, prefix + '????????.pt')
-    cp_list = glob.glob(pattern)
-    if len(cp_list) == 0:
-        return None
-    return sorted(cp_list)[-1]
-
diff --git a/spaces/Kimata/multimodal-deepfakes/rawnet.py b/spaces/Kimata/multimodal-deepfakes/rawnet.py
deleted file mode 100644
index 9a9087a94079c30a11a6e99c8b0a12745600b751..0000000000000000000000000000000000000000
--- a/spaces/Kimata/multimodal-deepfakes/rawnet.py
+++ /dev/null
@@ -1,363 +0,0 @@
-import torch
-import torch.nn as nn
-import torch.nn.functional as F
-from torch import Tensor
-import numpy as np
-from torch.utils import data
-from collections import OrderedDict
-from torch.nn.parameter import Parameter
-
-
-___author__ = "Hemlata Tak"
-__email__ = "tak@eurecom.fr"
-
-
-class SincConv(nn.Module):
-    @staticmethod
-    def to_mel(hz):
-        return 2595 * np.log10(1 + hz / 700)
-
-    @staticmethod
-    def to_hz(mel):
-        return 700 * (10 ** (mel / 2595) - 1)
-
-
-    def __init__(self, device,out_channels, kernel_size,in_channels=1,sample_rate=16000,
-                 stride=1, padding=0, dilation=1, bias=False, groups=1):
-
-        super(SincConv,self).__init__()
-
-        if in_channels != 1:
-            
-            msg = "SincConv only support one input channel (here, in_channels = {%i})" % (in_channels)
-            raise ValueError(msg)
-        
-        self.out_channels = out_channels
-        self.kernel_size = kernel_size
-        self.sample_rate=sample_rate
-
-        # Forcing the filters to be odd (i.e, perfectly symmetrics)
-        if kernel_size%2==0:
-            self.kernel_size=self.kernel_size+1
-
-        self.device=device   
-        self.stride = stride
-        self.padding = padding
-        self.dilation = dilation
-        
-        if bias:
-            raise ValueError('SincConv does not support bias.')
-        if groups > 1:
-            raise ValueError('SincConv does not support groups.')
-        
-        
-        # initialize filterbanks using Mel scale
-        NFFT = 512
-        f=int(self.sample_rate/2)*np.linspace(0,1,int(NFFT/2)+1)
-        fmel=self.to_mel(f)   # Hz to mel conversion
-        fmelmax=np.max(fmel)
-        fmelmin=np.min(fmel)
-        filbandwidthsmel=np.linspace(fmelmin,fmelmax,self.out_channels+1)
-        filbandwidthsf=self.to_hz(filbandwidthsmel)  # Mel to Hz conversion
-        self.mel=filbandwidthsf
-        self.hsupp=torch.arange(-(self.kernel_size-1)/2, (self.kernel_size-1)/2+1)
-        self.band_pass=torch.zeros(self.out_channels,self.kernel_size)
-    
-       
-        
-    def forward(self,x):
-        for i in range(len(self.mel)-1):
-            fmin=self.mel[i]
-            fmax=self.mel[i+1]
-            hHigh=(2*fmax/self.sample_rate)*np.sinc(2*fmax*self.hsupp/self.sample_rate)
-            hLow=(2*fmin/self.sample_rate)*np.sinc(2*fmin*self.hsupp/self.sample_rate)
-            hideal=hHigh-hLow
-            
-            self.band_pass[i,:]=Tensor(np.hamming(self.kernel_size))*Tensor(hideal)
-        
-        band_pass_filter=self.band_pass.to(self.device)
-
-        self.filters = (band_pass_filter).view(self.out_channels, 1, self.kernel_size)
-        
-        return F.conv1d(x, self.filters, stride=self.stride,
-                        padding=self.padding, dilation=self.dilation,
-                         bias=None, groups=1)
-
-
-        
-class Residual_block(nn.Module):
-    def __init__(self, nb_filts, first = False):
-        super(Residual_block, self).__init__()
-        self.first = first
-        
-        if not self.first:
-            self.bn1 = nn.BatchNorm1d(num_features = nb_filts[0])
-        
-        self.lrelu = nn.LeakyReLU(negative_slope=0.3)
-        
-        self.conv1 = nn.Conv1d(in_channels = nb_filts[0],
-			out_channels = nb_filts[1],
-			kernel_size = 3,
-			padding = 1,
-			stride = 1)
-        
-        self.bn2 = nn.BatchNorm1d(num_features = nb_filts[1])
-        self.conv2 = nn.Conv1d(in_channels = nb_filts[1],
-			out_channels = nb_filts[1],
-			padding = 1,
-			kernel_size = 3,
-			stride = 1)
-        
-        if nb_filts[0] != nb_filts[1]:
-            self.downsample = True
-            self.conv_downsample = nn.Conv1d(in_channels = nb_filts[0],
-				out_channels = nb_filts[1],
-				padding = 0,
-				kernel_size = 1,
-				stride = 1)
-            
-        else:
-            self.downsample = False
-        self.mp = nn.MaxPool1d(3)
-        
-    def forward(self, x):
-        identity = x
-        if not self.first:
-            out = self.bn1(x)
-            out = self.lrelu(out)
-        else:
-            out = x
-            
-        out = self.conv1(x)
-        out = self.bn2(out)
-        out = self.lrelu(out)
-        out = self.conv2(out)
-        
-        if self.downsample:
-            identity = self.conv_downsample(identity)
-            
-        out += identity
-        out = self.mp(out)
-        return out
-
-
-
-
-
-class RawNet(nn.Module):
-    def __init__(self, d_args, device):
-        super(RawNet, self).__init__()
-
-        
-        self.device=device
-
-        self.Sinc_conv=SincConv(device=self.device,
-			out_channels = d_args['filts'][0],
-			kernel_size = d_args['first_conv'],
-                        in_channels = d_args['in_channels']
-        )
-        
-        self.first_bn = nn.BatchNorm1d(num_features = d_args['filts'][0])
-        self.selu = nn.SELU(inplace=True)
-        self.block0 = nn.Sequential(Residual_block(nb_filts = d_args['filts'][1], first = True))
-        self.block1 = nn.Sequential(Residual_block(nb_filts = d_args['filts'][1]))
-        self.block2 = nn.Sequential(Residual_block(nb_filts = d_args['filts'][2]))
-        d_args['filts'][2][0] = d_args['filts'][2][1]
-        self.block3 = nn.Sequential(Residual_block(nb_filts = d_args['filts'][2]))
-        self.block4 = nn.Sequential(Residual_block(nb_filts = d_args['filts'][2]))
-        self.block5 = nn.Sequential(Residual_block(nb_filts = d_args['filts'][2]))
-        self.avgpool = nn.AdaptiveAvgPool1d(1)
-
-        self.fc_attention0 = self._make_attention_fc(in_features = d_args['filts'][1][-1],
-            l_out_features = d_args['filts'][1][-1])
-        self.fc_attention1 = self._make_attention_fc(in_features = d_args['filts'][1][-1],
-            l_out_features = d_args['filts'][1][-1])
-        self.fc_attention2 = self._make_attention_fc(in_features = d_args['filts'][2][-1],
-            l_out_features = d_args['filts'][2][-1])
-        self.fc_attention3 = self._make_attention_fc(in_features = d_args['filts'][2][-1],
-            l_out_features = d_args['filts'][2][-1])
-        self.fc_attention4 = self._make_attention_fc(in_features = d_args['filts'][2][-1],
-            l_out_features = d_args['filts'][2][-1])
-        self.fc_attention5 = self._make_attention_fc(in_features = d_args['filts'][2][-1],
-            l_out_features = d_args['filts'][2][-1])
-
-        self.bn_before_gru = nn.BatchNorm1d(num_features = d_args['filts'][2][-1])
-        self.gru = nn.GRU(input_size = d_args['filts'][2][-1],
-			hidden_size = d_args['gru_node'],
-			num_layers = d_args['nb_gru_layer'],
-			batch_first = True)
-
-        
-        self.fc1_gru = nn.Linear(in_features = d_args['gru_node'],
-			out_features = d_args['nb_fc_node'])
-       
-        self.fc2_gru = nn.Linear(in_features = d_args['nb_fc_node'],
-			out_features = d_args['nb_classes'],bias=True)
-			
-       
-        self.sig = nn.Sigmoid()
-        self.logsoftmax = nn.LogSoftmax(dim=1)
-        
-    def forward(self, x, y = None):
-        
-        
-        nb_samp = x.shape[0]
-        len_seq = x.shape[1]
-        x=x.view(nb_samp,1,len_seq)
-        
-        x = self.Sinc_conv(x)    
-        x = F.max_pool1d(torch.abs(x), 3)
-        x = self.first_bn(x)
-        x =  self.selu(x)
-        
-        x0 = self.block0(x)
-        y0 = self.avgpool(x0).view(x0.size(0), -1) # torch.Size([batch, filter])
-        y0 = self.fc_attention0(y0)
-        y0 = self.sig(y0).view(y0.size(0), y0.size(1), -1)  # torch.Size([batch, filter, 1])
-        x = x0 * y0 + y0  # (batch, filter, time) x (batch, filter, 1)
-        
-
-        x1 = self.block1(x)
-        y1 = self.avgpool(x1).view(x1.size(0), -1) # torch.Size([batch, filter])
-        y1 = self.fc_attention1(y1)
-        y1 = self.sig(y1).view(y1.size(0), y1.size(1), -1)  # torch.Size([batch, filter, 1])
-        x = x1 * y1 + y1 # (batch, filter, time) x (batch, filter, 1)
-
-        x2 = self.block2(x)
-        y2 = self.avgpool(x2).view(x2.size(0), -1) # torch.Size([batch, filter])
-        y2 = self.fc_attention2(y2)
-        y2 = self.sig(y2).view(y2.size(0), y2.size(1), -1)  # torch.Size([batch, filter, 1])
-        x = x2 * y2 + y2 # (batch, filter, time) x (batch, filter, 1)
-
-        x3 = self.block3(x)
-        y3 = self.avgpool(x3).view(x3.size(0), -1) # torch.Size([batch, filter])
-        y3 = self.fc_attention3(y3)
-        y3 = self.sig(y3).view(y3.size(0), y3.size(1), -1)  # torch.Size([batch, filter, 1])
-        x = x3 * y3 + y3 # (batch, filter, time) x (batch, filter, 1)
-
-        x4 = self.block4(x)
-        y4 = self.avgpool(x4).view(x4.size(0), -1) # torch.Size([batch, filter])
-        y4 = self.fc_attention4(y4)
-        y4 = self.sig(y4).view(y4.size(0), y4.size(1), -1)  # torch.Size([batch, filter, 1])
-        x = x4 * y4 + y4 # (batch, filter, time) x (batch, filter, 1)
-
-        x5 = self.block5(x)
-        y5 = self.avgpool(x5).view(x5.size(0), -1) # torch.Size([batch, filter])
-        y5 = self.fc_attention5(y5)
-        y5 = self.sig(y5).view(y5.size(0), y5.size(1), -1)  # torch.Size([batch, filter, 1])
-        x = x5 * y5 + y5 # (batch, filter, time) x (batch, filter, 1)
-
-        x = self.bn_before_gru(x)
-        x = self.selu(x)
-        x = x.permute(0, 2, 1)     #(batch, filt, time) >> (batch, time, filt)
-        self.gru.flatten_parameters()
-        x, _ = self.gru(x)
-        x = x[:,-1,:]
-        x = self.fc1_gru(x)
-        x = self.fc2_gru(x)
-        output=self.logsoftmax(x)
-      
-        return output
-        
-        
-
-    def _make_attention_fc(self, in_features, l_out_features):
-
-        l_fc = []
-        
-        l_fc.append(nn.Linear(in_features = in_features,
-			        out_features = l_out_features))
-
-        
-
-        return nn.Sequential(*l_fc)
-
-
-    def _make_layer(self, nb_blocks, nb_filts, first = False):
-        layers = []
-        #def __init__(self, nb_filts, first = False):
-        for i in range(nb_blocks):
-            first = first if i == 0 else False
-            layers.append(Residual_block(nb_filts = nb_filts,
-				first = first))
-            if i == 0: nb_filts[0] = nb_filts[1]
-            
-        return nn.Sequential(*layers)
-
-    def summary(self, input_size, batch_size=-1, device="cuda", print_fn = None):
-        if print_fn == None: printfn = print
-        model = self
-        
-        def register_hook(module):
-            def hook(module, input, output):
-                class_name = str(module.__class__).split(".")[-1].split("'")[0]
-                module_idx = len(summary)
-                
-                m_key = "%s-%i" % (class_name, module_idx + 1)
-                summary[m_key] = OrderedDict()
-                summary[m_key]["input_shape"] = list(input[0].size())
-                summary[m_key]["input_shape"][0] = batch_size
-                if isinstance(output, (list, tuple)):
-                    summary[m_key]["output_shape"] = [
-						[-1] + list(o.size())[1:] for o in output
-					]
-                else:
-                    summary[m_key]["output_shape"] = list(output.size())
-                    if len(summary[m_key]["output_shape"]) != 0:
-                        summary[m_key]["output_shape"][0] = batch_size
-                        
-                params = 0
-                if hasattr(module, "weight") and hasattr(module.weight, "size"):
-                    params += torch.prod(torch.LongTensor(list(module.weight.size())))
-                    summary[m_key]["trainable"] = module.weight.requires_grad
-                if hasattr(module, "bias") and hasattr(module.bias, "size"):
-                    params += torch.prod(torch.LongTensor(list(module.bias.size())))
-                summary[m_key]["nb_params"] = params
-                
-            if (
-				not isinstance(module, nn.Sequential)
-				and not isinstance(module, nn.ModuleList)
-				and not (module == model)
-			):
-                hooks.append(module.register_forward_hook(hook))
-                
-        device = device.lower()
-        assert device in [
-			"cuda",
-			"cpu",
-		], "Input device is not valid, please specify 'cuda' or 'cpu'"
-        
-        if device == "cuda" and torch.cuda.is_available():
-            dtype = torch.cuda.FloatTensor
-        else:
-            dtype = torch.FloatTensor
-        if isinstance(input_size, tuple):
-            input_size = [input_size]
-        x = [torch.rand(2, *in_size).type(dtype) for in_size in input_size]
-        summary = OrderedDict()
-        hooks = []
-        model.apply(register_hook)
-        model(*x)
-        for h in hooks:
-            h.remove()
-            
-        print_fn("----------------------------------------------------------------")
-        line_new = "{:>20}  {:>25} {:>15}".format("Layer (type)", "Output Shape", "Param #")
-        print_fn(line_new)
-        print_fn("================================================================")
-        total_params = 0
-        total_output = 0
-        trainable_params = 0
-        for layer in summary:
-            # input_shape, output_shape, trainable, nb_params
-            line_new = "{:>20}  {:>25} {:>15}".format(
-				layer,
-				str(summary[layer]["output_shape"]),
-				"{0:,}".format(summary[layer]["nb_params"]),
-			)
-            total_params += summary[layer]["nb_params"]
-            total_output += np.prod(summary[layer]["output_shape"])
-            if "trainable" in summary[layer]:
-                if summary[layer]["trainable"] == True:
-                    trainable_params += summary[layer]["nb_params"]
-            print_fn(line_new)
diff --git a/spaces/Kirihasan/rvc-holo/infer_pack/commons.py b/spaces/Kirihasan/rvc-holo/infer_pack/commons.py
deleted file mode 100644
index 54470986f37825b35d90d7efa7437d1c26b87215..0000000000000000000000000000000000000000
--- a/spaces/Kirihasan/rvc-holo/infer_pack/commons.py
+++ /dev/null
@@ -1,166 +0,0 @@
-import math
-import numpy as np
-import torch
-from torch import nn
-from torch.nn import functional as F
-
-
-def init_weights(m, mean=0.0, std=0.01):
-    classname = m.__class__.__name__
-    if classname.find("Conv") != -1:
-        m.weight.data.normal_(mean, std)
-
-
-def get_padding(kernel_size, dilation=1):
-    return int((kernel_size * dilation - dilation) / 2)
-
-
-def convert_pad_shape(pad_shape):
-    l = pad_shape[::-1]
-    pad_shape = [item for sublist in l for item in sublist]
-    return pad_shape
-
-
-def kl_divergence(m_p, logs_p, m_q, logs_q):
-    """KL(P||Q)"""
-    kl = (logs_q - logs_p) - 0.5
-    kl += (
-        0.5 * (torch.exp(2.0 * logs_p) + ((m_p - m_q) ** 2)) * torch.exp(-2.0 * logs_q)
-    )
-    return kl
-
-
-def rand_gumbel(shape):
-    """Sample from the Gumbel distribution, protect from overflows."""
-    uniform_samples = torch.rand(shape) * 0.99998 + 0.00001
-    return -torch.log(-torch.log(uniform_samples))
-
-
-def rand_gumbel_like(x):
-    g = rand_gumbel(x.size()).to(dtype=x.dtype, device=x.device)
-    return g
-
-
-def slice_segments(x, ids_str, segment_size=4):
-    ret = torch.zeros_like(x[:, :, :segment_size])
-    for i in range(x.size(0)):
-        idx_str = ids_str[i]
-        idx_end = idx_str + segment_size
-        ret[i] = x[i, :, idx_str:idx_end]
-    return ret
-
-
-def slice_segments2(x, ids_str, segment_size=4):
-    ret = torch.zeros_like(x[:, :segment_size])
-    for i in range(x.size(0)):
-        idx_str = ids_str[i]
-        idx_end = idx_str + segment_size
-        ret[i] = x[i, idx_str:idx_end]
-    return ret
-
-
-def rand_slice_segments(x, x_lengths=None, segment_size=4):
-    b, d, t = x.size()
-    if x_lengths is None:
-        x_lengths = t
-    ids_str_max = x_lengths - segment_size + 1
-    ids_str = (torch.rand([b]).to(device=x.device) * ids_str_max).to(dtype=torch.long)
-    ret = slice_segments(x, ids_str, segment_size)
-    return ret, ids_str
-
-
-def get_timing_signal_1d(length, channels, min_timescale=1.0, max_timescale=1.0e4):
-    position = torch.arange(length, dtype=torch.float)
-    num_timescales = channels // 2
-    log_timescale_increment = math.log(float(max_timescale) / float(min_timescale)) / (
-        num_timescales - 1
-    )
-    inv_timescales = min_timescale * torch.exp(
-        torch.arange(num_timescales, dtype=torch.float) * -log_timescale_increment
-    )
-    scaled_time = position.unsqueeze(0) * inv_timescales.unsqueeze(1)
-    signal = torch.cat([torch.sin(scaled_time), torch.cos(scaled_time)], 0)
-    signal = F.pad(signal, [0, 0, 0, channels % 2])
-    signal = signal.view(1, channels, length)
-    return signal
-
-
-def add_timing_signal_1d(x, min_timescale=1.0, max_timescale=1.0e4):
-    b, channels, length = x.size()
-    signal = get_timing_signal_1d(length, channels, min_timescale, max_timescale)
-    return x + signal.to(dtype=x.dtype, device=x.device)
-
-
-def cat_timing_signal_1d(x, min_timescale=1.0, max_timescale=1.0e4, axis=1):
-    b, channels, length = x.size()
-    signal = get_timing_signal_1d(length, channels, min_timescale, max_timescale)
-    return torch.cat([x, signal.to(dtype=x.dtype, device=x.device)], axis)
-
-
-def subsequent_mask(length):
-    mask = torch.tril(torch.ones(length, length)).unsqueeze(0).unsqueeze(0)
-    return mask
-
-
-@torch.jit.script
-def fused_add_tanh_sigmoid_multiply(input_a, input_b, n_channels):
-    n_channels_int = n_channels[0]
-    in_act = input_a + input_b
-    t_act = torch.tanh(in_act[:, :n_channels_int, :])
-    s_act = torch.sigmoid(in_act[:, n_channels_int:, :])
-    acts = t_act * s_act
-    return acts
-
-
-def convert_pad_shape(pad_shape):
-    l = pad_shape[::-1]
-    pad_shape = [item for sublist in l for item in sublist]
-    return pad_shape
-
-
-def shift_1d(x):
-    x = F.pad(x, convert_pad_shape([[0, 0], [0, 0], [1, 0]]))[:, :, :-1]
-    return x
-
-
-def sequence_mask(length, max_length=None):
-    if max_length is None:
-        max_length = length.max()
-    x = torch.arange(max_length, dtype=length.dtype, device=length.device)
-    return x.unsqueeze(0) < length.unsqueeze(1)
-
-
-def generate_path(duration, mask):
-    """
-    duration: [b, 1, t_x]
-    mask: [b, 1, t_y, t_x]
-    """
-    device = duration.device
-
-    b, _, t_y, t_x = mask.shape
-    cum_duration = torch.cumsum(duration, -1)
-
-    cum_duration_flat = cum_duration.view(b * t_x)
-    path = sequence_mask(cum_duration_flat, t_y).to(mask.dtype)
-    path = path.view(b, t_x, t_y)
-    path = path - F.pad(path, convert_pad_shape([[0, 0], [1, 0], [0, 0]]))[:, :-1]
-    path = path.unsqueeze(1).transpose(2, 3) * mask
-    return path
-
-
-def clip_grad_value_(parameters, clip_value, norm_type=2):
-    if isinstance(parameters, torch.Tensor):
-        parameters = [parameters]
-    parameters = list(filter(lambda p: p.grad is not None, parameters))
-    norm_type = float(norm_type)
-    if clip_value is not None:
-        clip_value = float(clip_value)
-
-    total_norm = 0
-    for p in parameters:
-        param_norm = p.grad.data.norm(norm_type)
-        total_norm += param_norm.item() ** norm_type
-        if clip_value is not None:
-            p.grad.data.clamp_(min=-clip_value, max=clip_value)
-    total_norm = total_norm ** (1.0 / norm_type)
-    return total_norm
diff --git a/spaces/Kontrol/plasmo-food-crit/app.py b/spaces/Kontrol/plasmo-food-crit/app.py
deleted file mode 100644
index 556f102d3e638dc21a6099d984950e0cb5e9c956..0000000000000000000000000000000000000000
--- a/spaces/Kontrol/plasmo-food-crit/app.py
+++ /dev/null
@@ -1,3 +0,0 @@
-import gradio as gr
-
-gr.Interface.load("models/aipicasso/cool-japan-diffusion-2-1-1").launch()
\ No newline at end of file
diff --git a/spaces/KyanChen/RSPrompter/mmdet/models/task_modules/prior_generators/__init__.py b/spaces/KyanChen/RSPrompter/mmdet/models/task_modules/prior_generators/__init__.py
deleted file mode 100644
index 7795e98ca77bb5ffc77ff1da848130717d8f85a6..0000000000000000000000000000000000000000
--- a/spaces/KyanChen/RSPrompter/mmdet/models/task_modules/prior_generators/__init__.py
+++ /dev/null
@@ -1,11 +0,0 @@
-# Copyright (c) OpenMMLab. All rights reserved.
-from .anchor_generator import (AnchorGenerator, LegacyAnchorGenerator,
-                               SSDAnchorGenerator, YOLOAnchorGenerator)
-from .point_generator import MlvlPointGenerator, PointGenerator
-from .utils import anchor_inside_flags, calc_region
-
-__all__ = [
-    'AnchorGenerator', 'LegacyAnchorGenerator', 'anchor_inside_flags',
-    'PointGenerator', 'calc_region', 'YOLOAnchorGenerator',
-    'MlvlPointGenerator', 'SSDAnchorGenerator'
-]
diff --git a/spaces/KyanChen/RSPrompter/mmpl/models/backbones/huggingface_hub.py b/spaces/KyanChen/RSPrompter/mmpl/models/backbones/huggingface_hub.py
deleted file mode 100644
index 7b582bebefb2e093f8c3b91926464fcacb9e0059..0000000000000000000000000000000000000000
--- a/spaces/KyanChen/RSPrompter/mmpl/models/backbones/huggingface_hub.py
+++ /dev/null
@@ -1,12 +0,0 @@
-import torch.nn as nn
-from mmengine.model import BaseModule
-from mmengine.model.weight_init import constant_init
-from mmengine.utils.dl_utils.parrots_wrapper import _BatchNorm
-from mmpl.registry import MODELS
-from .base_backbone import BaseBackbone
-
-
-@MODELS.register_module()
-class HuggingfaceModel(BaseBackbone):
-    def __init__(self, ):
-        pass
diff --git a/spaces/LEOZHAO92/TTS/pretrain_work_dir/orig_model/README.md b/spaces/LEOZHAO92/TTS/pretrain_work_dir/orig_model/README.md
deleted file mode 100644
index d57bc2cf0baf064e0fdd0ac1ca3eb93ff6bfab6d..0000000000000000000000000000000000000000
--- a/spaces/LEOZHAO92/TTS/pretrain_work_dir/orig_model/README.md
+++ /dev/null
@@ -1,581 +0,0 @@
----
-tasks:
-- text-to-speech
-studios:
-- damo/personal_tts
-domain:
-- audio
-frameworks:
-- pytorch
-backbone:
-- transformer
-metrics:
-- MOS
-license: Apache License 2.0
-tags:
-- Alibaba
-- tts
-- personal
-- hifigan
-- nsf
-- sambert
-- text-to-speech
-- pretrain
-- zhcn
-- 16k
-widgets:
-  - task: text-to-speech
-    inputs:
-      - type: text 
-        name: input 
-        title: 文本 
-        validator: 
-          max_words: 300
-    examples:
-      - name: 1
-        title: 示例1 
-        inputs:
-          - name: input
-            data: 北京今天天气怎么样
-    inferencespec:
-      cpu: 4 #CPU数量
-      memory: 8192 
-      gpu: 1 #GPU数量
-      gpu_memory: 8192 
----
-
-
-## SAMBERT个性化语音合成模型介绍
-本文将介绍SAMBERT个性化语音合成模型, 包括其模型结构, 如何在ModelScope上体验模型效果, 以及如何使用开源代码训练SAMBERT个性化语音合成模型.
-
-## 个性化语音合成
-语音合成(Text-to-Speech, TTS) 是指将输入文字合成为对应语音信号的功能，即赋予计算机“说”的能力，是人机交互中重要的一环。现代语音合成最早可以追溯到1939年贝尔实验室制造的第一个电子语音合成器，后来历经共振峰合成、PSOLA合成、Unit Selection波形拼接、统计参数合成几代的发展，在2016年随着WaveNet的出现步入了深度学习合成时代，此时语音合成的效果已经表现出了比拟真人的水准。
-
-提到个性化定制语音，大家并不陌生，许多平台会选择一些大家耳熟能详的明星，进行声音定制，并普遍应用在语音导航，文字播报，小说阅读等场景中。这项技术来自文本到语音的服务，一般来说，语音合成数据需要专业播音员在录音棚录制，且数据量都是以500-1000句话起步，这种标准定制的流程，无论是对播音员、录制条件、录制数量和成本都提出了较高的要求。
-
-Personal TTS，即个性化语音合成，是通过身边的一些常见录音设备（手机、电脑、录音笔等），录取目标说话人的少量语音片段后，构建出这个人的语音合成系统。相比于标准定制，个性化定制的技术难点在于，数据量有限（20句话）、数据质量不佳和流程全自动化。而它的意义在于进一步降低语音合成的定制门槛，能够将语音合成定制推广到普通用户。
-
-学术界有很多关于声音克隆的工作，论文陈述效果很好。考虑到落地应用场景的效果，达摩院以自研语音合成系统KAN-TTS的迁移学习能力为基础，设计了一套较为完善的个性化语音合成方案。用户只需要录制20句话，经过几分钟的训练，就能够获得一个较好的个性化声音。
-
-<div align=center>
-    <figure>
-        <img src="description/ptts_normal.png">
-        <figcaption>定制方案比较</figcaption>
-    </figure>
-</div>
-
-
-## 模型框架
-
-模型框架主要由三个部分组成：
-1. 数据自动化处理和标注
-2. 韵律建模SAMBERT声学模型
-3. 基于说话人特征信息的个性化语音合成
-
-<div align=center>
-    <figure>
-        <img src="description/ptts_structure.png">
-        <figcaption>个性化定制流程</figcaption>
-    </figure>
-</div>
-   
-### 数据自动化处理和标注
-在用户录制完音频之后，我们只有<文本，音频>，而语音合成是需要一些额外的标注信息：韵律标注、音素时长标注。为了获得较好的标注信息，我们采用了一种融合了多种原子能力的全自动化处理和标注流程，包括，韵律预测、ASR、VAD和语音增强等。通过测试集测试，该自动化流程产生的标注信息，在准确度能够满足个性化的需求。
-
-此外，我们也在modelscope上发布了**TTS-Autolabel自动化数据标注工具**，旨在降低TTS数据标注门槛，使开发者更便捷的定制个性化语音合成模型，具体使用方式及相关教程请进入[TTS-AutoLabel工具主页](https://modelscope.cn/models/damo/speech_ptts_autolabel_16k/summary)获取。
-
-### 韵律建模SAMBERT声学模型
-在整个链路中，和效果最相关的模块就是声学模型。在语音合成领域，类似FastSpeech的Parallel模型是目前的主流，它针对基频（pitch）、能量（energy）和时长（duration）三种韵律表征分别建模。但是，该类模型普遍存在一些效果和性能上的问题，例如，独立建模时长、基频、能量，忽视了其内在联系；完全非自回归的网络结构，无法满足工业级实时合成需求；帧级别基频和能量预测不稳定。 因此达摩院语音实验室设计了SAMBERT，一种基于Parallel结构的改良版TTS模型，它具有以下优点：
-
-```
-1. Backbone采用Self-Attention-Mechanism(SAM)，提升模型建模能力。
-2. Encoder部分采用BERT进行初始化，引入更多文本信息，提升合成韵律。
-3. Variance Adaptor对音素级别的韵律(基频、能量、时长)轮廓进行粗粒度的预测，再通过decoder进行帧级别细粒度的建模;并在时长预测时考虑到其与基频、能量的关联信息，结合自回归结构，进一步提升韵律自然度.
-4. Decoder部分采用PNCA AR-Decoder[@li2020robutrans]，自然支持流式合成。
-```
-
-<div align=center>
-    <figure>
-        <img src="description/sambert.jpg">
-        <figcaption>SAMBERT模型结构</figcaption>
-    </figure>
-</div>
-
-### 基于说话人特征信息的个性化语音合成
-如果需要进行迁移学习，那么需要先构建多说话人的声学模型，不同说话人是通过可训练的说话人编码（speaker embedding）进行区分的。给定新的一个说话人，一般通过随机初始化一个speaker embedding，然后再基于这个说话人的数据进行更新（见下图说话人空间1）。对于个性化语音合成来说，发音人的数据量比较少，学习难度很大，最终合成声音的相似度就无法保证。因此，我们采用说话人特征信息来表示每个说话人，此时，以少量说话人数据初始化的 speaker embedding 距离实际的目标说话人更近得多（见下图说话人空间2），学习难度小，此时合成声音的相似度就比较高。采用基于说话人特征信息的个性化语音合成，使得在20句条件下，依旧能够有较好的相似度。
-
-<div align=center>
-    <figure>
-        <img src="description/speaker_embedding.png">
-        <figcaption>说话人特征空间</figcaption>
-    </figure>
-</div>
-
-## Notebook最佳实践
-
-首先我们从[sample_test_female](https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/TTS/download_files/test_female.zip)或者[sample_test_male](https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/TTS/download_files/test_male.zip)获得示例音频文件, 这里以`sample_test_male`为例。
-
-解压完成后得到如下文件结构:
-```
-test_male
-├── 01_000001.wav
-├── 01_000002.wav
-├── 01_000003.wav
-├── 01_000004.wav
-├── 01_000005.wav
-├── 01_000006.wav
-├── 01_000007.wav
-├── 01_000008.wav
-├── 01_000009.wav
-├── 01_000010.wav
-├── 01_000011.wav
-├── 01_000012.wav
-├── 01_000013.wav
-├── 01_000014.wav
-├── 01_000015.wav
-├── 01_000016.wav
-├── 01_000017.wav
-├── 01_000018.wav
-├── 01_000019.wav
-└── 01_000020.wav
-```
-
-<div align=center>
-    <figure>
-        <img src="description/notebook_steps/upload_wavs.jpg">
-        <figcaption>上传音频至Notebook</figcaption>
-    </figure>
-</div>
-
-接着选择这些wav文件上传至Notebook
-
-### 前置工作
-使用AutoLabeling需要用到`nltk`, 由于国内访问nltk资源较慢，所以我们建议先按下面的步骤手动下载nltk资源。
-
-在Terminal界面下使用`wget`获取`nltk_data`并解压至`home`目录
-```
-# 切换至home目录
-cd ~
-# 安装zip
-apt install zip
-# 下载并解压nltk_data
-wget https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/TTS/download_files/nltk_data.zip
-unzip nltk_data.zip
-```
-<div align=center>
-    <figure>
-        <img src="description/notebook_steps/fetch_nltk_data.jpg">
-        <figcaption>手动下载nltk资源</figcaption>
-    </figure>
-</div>
-
-### 运行TTS-AutoLabel自动标注
-首先在Notebook左侧新建TTS-AutoLabel工作文件夹`output_training_data`, 然后在Notebook code block中输入如下代码并运行, 由于Notebook运行环境已经安装了`modelscope`和`tts-autolabel`此处可以直接导入。
-```python
-from modelscope.tools import run_auto_label
-
-input_wav = "./test_wavs/"
-output_data = "./output_training_data/"
-
-ret, report = run_auto_label(input_wav=input_wav, work_dir=output_data, resource_revision="v1.0.4")
-```
-<div align=center>
-    <figure>
-        <img src="description/notebook_steps/autolabel_done.jpg">
-        <figcaption>Notebook运行TTS—AutoLabel自动标注数据</figcaption>
-    </figure>
-</div>
-二十条音频标注时间在2～4分钟。标注完成后在`output_training_data`中可以获取音频对应的TTS训练数据。
-
-### 基于PTTS-basemodel微调
-获得标注好的训练数据后，我们进行模型微调，新建一个Notebook代码块，并输入如下代码运行
-```python
-from modelscope.metainfo import Trainers
-from modelscope.trainers import build_trainer
-from modelscope.utils.audio.audio_utils import TtsTrainType
-
-pretrained_model_id = 'damo/speech_personal_sambert-hifigan_nsf_tts_zh-cn_pretrain_16k'
-
-dataset_id = "./output_training_data/"
-pretrain_work_dir = "./pretrain_work_dir/"
-        
-# 训练信息，用于指定需要训练哪个或哪些模型，这里展示AM和Vocoder模型皆进行训练
-# 目前支持训练：TtsTrainType.TRAIN_TYPE_SAMBERT, TtsTrainType.TRAIN_TYPE_VOC
-# 训练SAMBERT会以模型最新step作为基础进行finetune
-train_info = {
-    TtsTrainType.TRAIN_TYPE_SAMBERT: {  # 配置训练AM（sambert）模型
-        'train_steps': 202,               # 训练多少个step 
-        'save_interval_steps': 200,       # 每训练多少个step保存一次checkpoint
-        'log_interval': 10               # 每训练多少个step打印一次训练日志
-    }
-}
-
-# 配置训练参数，指定数据集，临时工作目录和train_info
-kwargs = dict(
-    model=pretrained_model_id,                  # 指定要finetune的模型
-    model_revision = "v1.0.5",
-    work_dir=pretrain_work_dir,                 # 指定临时工作目录
-    train_dataset=dataset_id,                   # 指定数据集id
-    train_type=train_info                       # 指定要训练类型及参数
-)
-
-trainer = build_trainer(Trainers.speech_kantts_trainer,
-                        default_args=kwargs)
-
-trainer.train()
-```
-
-<div align=center>
-    <figure>
-        <img src="description/notebook_steps/training.jpg">
-        <figcaption>在Notebook中使用trainer微调模型</figcaption>
-    </figure>
-</div>
-
-微调过程大概需要5分钟的时间，请耐心等待。
-
-
-### 体验模型合成效果
-使用上一步微调得到的模型合成音频，新建一个Notebook代码块, 输入以下代码
-```python
-import os
-from modelscope.models.audio.tts import SambertHifigan
-from modelscope.pipelines import pipeline
-from modelscope.utils.constant import Tasks
-
-model_dir = os.path.abspath("./pretrain_work_dir")
-
-custom_infer_abs = {
-    'voice_name':
-    'F7',
-    'am_ckpt':
-    os.path.join(model_dir, 'tmp_am', 'ckpt'),
-    'am_config':
-    os.path.join(model_dir, 'tmp_am', 'config.yaml'),
-    'voc_ckpt':
-    os.path.join(model_dir, 'orig_model', 'basemodel_16k', 'hifigan', 'ckpt'),
-    'voc_config':
-    os.path.join(model_dir, 'orig_model', 'basemodel_16k', 'hifigan',
-             'config.yaml'),
-    'audio_config':
-    os.path.join(model_dir, 'data', 'audio_config.yaml'),
-    'se_file':
-    os.path.join(model_dir, 'data', 'se', 'se.npy')
-}
-kwargs = {'custom_ckpt': custom_infer_abs}
-
-model_id = SambertHifigan(os.path.join(model_dir, "orig_model"), **kwargs)
-
-inference = pipeline(task=Tasks.text_to_speech, model=model_id)
-output = inference(input="今天的天气真不错")
-
-import IPython.display as ipd
-ipd.Audio(output["output_wav"], rate=16000)
-```
-
-<div align=center>
-    <figure>
-        <img src="description/notebook_steps/inference_play.jpg">
-        <figcaption>在Notebook中使用微调好的模型合成音频</figcaption>
-    </figure>
-</div>
-
-点击播放控件即可体验合成音频。
-
-## KAN-TTS最佳实践
-### 环境搭建
-获取KAN-TTS源码， 后续操作默认在代码库根目录下执行
-
-```bash
-git clone -b develop https://github.com/alibaba-damo-academy/KAN-TTS.git
-cd KAN-TTS
-```
-
-我们推荐使用Anaconda来搭建Python虚拟环境，使用以下命令创建(目前只兼容Linux x86系统)：
-
-```bash
-# 防止使用pip安装时出现网络问题，建议切换国内pip源
-pip config set global.index-url https://pypi.tuna.tsinghua.edu.cn/simple
-
-# 创建虚拟环境
-conda env create -f environment.yaml
-
-# 激活虚拟环境
-conda activate maas
-```
-
-
-### 拉取预训练模型
-ModelScope中文个性化语音合成模型是达摩院语音实验室在1000多小时4000多人数据集上训练产出的预训练模型，我们以此为basemodel做后续微调。
-使用git命令拉取模型，在拉取前，首先你需要安装git-lfs, 具体的安装教程见Git Large File Storage，安装完成后执行以下命令：
-
-```bash
-# 克隆预训练模型
- git clone https://www.modelscope.cn/damo/speech_personal_sambert-hifigan_nsf_tts_zh-cn_pretrain_16k.git
-```
-
-### 数据获取与自动标注
-
-目前KAN-TTS个性化语音合成支持达摩院TTS标准数据格式和普通音频格式。
-其中达摩院TTS标准数据格式，wav文件夹下存放了音频文件，prosody文件夹下的.txt文件对应的是音频文件的文本标注，interval文件夹下存放的是音素级别的时间戳标注，如下:
-```
-.
-├── interval
-│   ├── 500001.interval
-│   ├── 500002.interval
-│   ├── 500003.interval
-│   ├── ...
-│   └── 500020.interval
-├── prosody
-│   └── prosody.txt
-└── wav
-    ├── 500001.wav
-    ├── 500002.wav
-    ├── ...
-    └── 500020.wav
-```
-
-普通音频数据，不携带时间戳标注和prosody标注，如下：
-```
-.
-└── wav
-    ├── 1.wav
-    ├── 2.wav
-    ├── ...
-    └── 20.wav
-```
-
-**快速开始**：你可以从ModelScope下载经过阿里标准格式处理的[AISHELL-3开源语音合成数据集](https://modelscope.cn/datasets/speech_tts/AISHELL-3/summary)，用来进行后续操作。如果你只有普通音频格式的数据，那么可以采用PTTS Autolabel自动化标注工具进行格式转换，下面介绍使用Notebook 进行PTTS Autolable自动化标注的方式。
-
-#### PTTS Autolable自动化标注
-
-打开右上角的Notebook，上传[sample_test_male](https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/TTS/download_files/test_male.zip)的20条音频文件到目录如/mnt/workspace/Data/ptts_spk0_wav下面
-``` 
-ptts_spk0_wav
-├── 01_000001.wav
-├── 01_000002.wav
-├── 01_000003.wav
-├── 01_000004.wav
-├── 01_000005.wav
-├── 01_000006.wav
-├── 01_000007.wav
-├── 01_000008.wav
-├── 01_000009.wav
-├── 01_000010.wav
-├── 01_000011.wav
-├── 01_000012.wav
-├── 01_000013.wav
-├── 01_000014.wav
-├── 01_000015.wav
-├── 01_000016.wav
-├── 01_000017.wav
-├── 01_000018.wav
-├── 01_000019.wav
-└── 01_000020.wav
-```
-在Notebook的Jupyter中安装tts-autolabel
-
-``` Python
-# 运行此代码块安装tts-autolabel
-import sys
-!{sys.executable} -m pip install tts-autolabel -f https://modelscope.oss-cn-beijing.aliyuncs.com/releases/repo.html
-```
-``` Python
-# 导入run_auto_label工具, 初次运行会下载相关库文件
-from modelscope.tools import run_auto_label
-``` 
-
-``` Python
-# 运行 autolabel进行自动标注，20句音频的自动标注约4分钟
-import os 
-
-input_wav = '/mnt/workspace/Data/ptts_spk0_wav' # wav audio path
-work_dir = '/mnt/workspace/Data/ptts_spk0_autolabel' # output path
-os.makedirs(work_dir, exist_ok=True)
-
-ret, report = run_auto_label(input_wav = input_wav,
-                             work_dir = work_dir,
-                            resource_revision='v1.0.4')
-print(report)
-``` 
-
-完成数据标注后，下载对应文件夹`/mnt/workspace/Data/ptts_spk0_autolabel`, 使用`KAN-TTS`的数据前处理脚本做训练前数据准备。
-
-我们选择个性化语音合成配置文件进行特征提取操作，这里我们以提供的16k采样率为例kantts/configs/audio_config_se_16k.yaml
-运行以下命令来进行特征提取，其中--speaker代表该数据集对应发音人的名称，用户可以随意命名。
-```bash
-# 特征提取
-python kantts/preprocess/data_process.py --voice_input_dir ptts_spk0_autolabel --voice_output_dir training_stage/test_male_ptts_feats --audio_config kantts/configs/audio_config_se_16k.yaml --speaker F7 --se_model speech_personal_sambert-hifigan_nsf_tts_zh-cn_pretrain_16k/basemodel_16k/speaker_embedding/se.*     
-
-# 扩充epoch
-stage0=training_stage
-voice=test_male_ptts_feats
-
-cat $stage0/$voice/am_valid.lst  >> $stage0/$voice/am_train.lst
-lines=0
-while [ $lines -lt 400 ]
-do
-    shuf $stage0/$voice/am_train.lst >> $stage0/$voice/am_train.lst.tmp
-    lines=$(wc -l < "$stage0/$voice/am_train.lst.tmp")
-done
-mv $stage0/$voice/am_train.lst.tmp $stage0/$voice/am_train.lst
-```
-
-个性化语音合成只需要20句目标说话人的语音，特征提取只需要运行一小段时间，提取完毕后你会在training_stage/test_male_ptts_feats目录下得到如下结构的文件：
-```
-# 基于阿里标准格式数据所提取出的特征目录
-├── am_train.lst
-├── am_valid.lst
-├── audio_config.yaml
-├── badlist.txt
-├── data_process_stdout.log
-├── duration
-├── energy
-├── f0
-├── frame_energy
-├── frame_f0
-├── frame_uv
-├── mel
-├── raw_duration
-├── raw_metafile.txt
-├── Script.xml
-├── se
-├── train.lst
-├── valid.lst
-└── wav
-```
-至此数据准备工作就算完成了。
-
-微调声学模型
-KAN-TTS的训练脚本是配置驱动的，我们使用预训练模型中的speech_personal_sambert-hifigan_nsf_tts_zh-cn_pretrain_16k/basemodel_16k/sambert/config.yaml作为训练配置文件。
-我们提供默认的PTTS 默认使用的finetune参数值，希望在basemodel的基础上继续微调一定步数并保存，即train_max_steps配置项。
-
-```bash
-# 将train_max_steps改为 2400301
-...
-train_max_steps: 2400301
-...
-```
-完成上述必要的配置项修改后，我们就可以使用以下命令训练声学模型了：
-```bash
-# 训练声学模型
-CUDA_VISIBLE_DEVICES=0 python kantts/bin/train_sambert.py --model_config speech_personal_sambert-hifigan_nsf_tts_zh-cn_pretrain_16k/basemodel_16k/sambert/config.yaml --root_dir  training_stage/test_male_ptts_feats --stage_dir training_stage/test_male_ptts_sambert_ckpt --resume_path speech_personal_sambert-hifigan_nsf_tts_zh-cn_pretrain_16k/basemodel_16k/sambert/ckpt/checkpoint_*.pth
-```
-
-体验微调模型效果
-在声学模型微调完毕后，我们就可以使用产出的模型文件和预训练的声码器来合成语音了，在此之前需要做一些准备工作。
-
-将我们想要合成的文本写入一个文件test.txt，每句话按行分隔，如下所示
-```
-徐玠诡谲多智，善揣摩，知道徐知询不可辅佐，掌握着他的短处以归附徐知诰。
-许乐夫生于山东省临朐县杨善镇大辛庄，毕业于抗大一分校。
-宣统元年（1909年），顺德绅士冯国材在香山大黄圃成立安洲农务分会，管辖东海十六沙，冯国材任总理。
-学生们大多住在校区宿舍，通过参加不同的体育文化俱乐部及社交活动，形成一个友谊长存的社会圈。
-学校的“三节一会”（艺术节、社团节、科技节、运动会）是显示青春才华的盛大活动。
-雪是先天自闭症患者，不懂与人沟通，却拥有灵敏听觉，而且对复杂动作过目不忘。
-勋章通过一柱状螺孔和螺钉附着在衣物上。
-雅恩雷根斯堡足球俱乐部（）是一家位于德国雷根斯堡的足球俱乐部，处于德国足球丙级联赛。
-亚历山大·格罗滕迪克于1957年证明了一个深远的推广，现在叫做格罗滕迪克–黎曼–罗赫定理。
-```
-
-运行以下命令进行合成，其中se_file为特征提取环节抽取的speaker embedding，voc_ckpt为basemodel_16k中的预训练模型：
-
-``` bash
-# 运行合成语音
-CUDA_VISIBLE_DEVICES=0 python kantts/bin/text_to_wav.py --txt test.txt --output_dir res/test_male_ptts_syn --res_zip speech_sambert-hifigan_tts_zh-cn_multisp_pretrain_16k/resource.zip --am_ckpt training_stage/test_male_ptts_sambert_ckpt/ckpt/checkpoint_2400300.pth --voc_ckpt speech_sambert-hifigan_tts_zh-cn_multisp_pretrain_16k/hifigan/ckpt/checkpoint_2400000.pth --se_file training_stage/test_male_ptts_feats/se/se.npy
-```
-
-完成后在res/test_male_ptts_syn/res_wavs文件夹下就可以获得合成结果
-```
-.
-├── 0.wav
-├── 1.wav
-├── 2.wav
-├── 3.wav
-├── 4.wav
-├── 5.wav
-├── 6.wav
-├── 7.wav
-└── 8.wav
-```
-
-合成样音
-
-<audio id="audio" controls="" preload="none">
-      <source src="https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/TTS/download_files/ptts_modelcard_assets/wavs/synthesis/7.wav">
-</audio>
-<audio id="audio" controls="" preload="none">
-      <source src="https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/TTS/download_files/ptts_modelcard_assets/wavs/synthesis/8.wav">
-</audio>
-<audio id="audio" controls="" preload="none">
-      <source src="https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/TTS/download_files/ptts_modelcard_assets/wavs/synthesis/9.wav">
-</audio>
-
-原始录音
-
-<audio id="audio" controls="" preload="none">
-      <source src="https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/TTS/download_files/ptts_modelcard_assets/wavs/recordings/01_000003.wav">
-</audio>
-<audio id="audio" controls="" preload="none">
-      <source id="mp3" src="https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/TTS/download_files/ptts_modelcard_assets/wavs/recordings/01_000004.wav">
-</audio>
-<audio id="audio" controls="" preload="none">
-      <source id="mp3" src="https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/TTS/download_files/ptts_modelcard_assets/wavs/recordings/01_000005.wav">
-</audio>
-
-## 模型局限性以及可能的偏差
-* 该发音人支持中文及英文混合，TN规则为中文
-
-## 训练数据介绍
-使用约4000个不同发音人，共计约1000小时数据训练, 主要为中文语料, 包含少量英文语料。
-
-## 模型训练流程
-模型所需训练数据格式为：音频(.wav), 文本标注(.txt), 音素时长标注(.interval), 个性化语音合成模型微调训练时间需要2～5分钟。
-
-### 预处理
-模型训练需对音频文件提取声学特征(梅尔频谱)；音素时长根据配置项中的帧长将时间单位转换成帧数；文本标注，根据配置项中的音素集、音调分类、边界分类转换成对应的one-hot编号；
-
-
-## 引用
-如果你觉得这个该模型对有所帮助，请考虑引用下面的相关的论文：
-
-```BibTeX
-@inproceedings{li2020robutrans,
-  title={Robutrans: A robust transformer-based text-to-speech model},
-  author={Li, Naihan and Liu, Yanqing and Wu, Yu and Liu, Shujie and Zhao, Sheng and Liu, Ming},
-  booktitle={Proceedings of the AAAI Conference on Artificial Intelligence},
-  volume={34},
-  number={05},
-  pages={8228--8235},
-  year={2020}
-}
-```
-
-```BibTeX
-@article{devlin2018bert,
-  title={Bert: Pre-training of deep bidirectional transformers for language understanding},
-  author={Devlin, Jacob and Chang, Ming-Wei and Lee, Kenton and Toutanova, Kristina},
-  journal={arXiv preprint arXiv:1810.04805},
-  year={2018}
-}
-```
-```BibTeX
-@article{kong2020hifi,
-  title={Hifi-gan: Generative adversarial networks for efficient and high fidelity speech synthesis},
-  author={Kong, Jungil and Kim, Jaehyeon and Bae, Jaekyoung},
-  journal={Advances in Neural Information Processing Systems},
-  volume={33},
-  pages={17022--17033},
-  year={2020}
-}
-```
-
-本模型参考了以下实现
-- [1] [ming024's FastSpeech2 Implementation](https://github.com/ming024/FastSpeech2)
-- [2] [jik876/hifi-gan](https://github.com/jik876/hifi-gan)
-- [3] [kan-bayashi/ParallelWaveGAN](https://github.com/kan-bayashi/ParallelWaveGAN)
-- [4] [mozilla/TTS](https://github.com/mozilla/TTS)
-- [5] [espnet/espnet](https://github.com/espnet/espnet)
-
-
-
diff --git a/spaces/Laurie/IDEA-CCNL-Ziya-LLaMA-13B-v1/app.py b/spaces/Laurie/IDEA-CCNL-Ziya-LLaMA-13B-v1/app.py
deleted file mode 100644
index 591daf871d3b52023add1ca487c501a2036493c3..0000000000000000000000000000000000000000
--- a/spaces/Laurie/IDEA-CCNL-Ziya-LLaMA-13B-v1/app.py
+++ /dev/null
@@ -1,3 +0,0 @@
-import gradio as gr
-
-gr.Interface.load("models/IDEA-CCNL/Ziya-LLaMA-13B-v1").launch()
\ No newline at end of file
diff --git a/spaces/LightChen2333/OpenSLU/static/css/style.css b/spaces/LightChen2333/OpenSLU/static/css/style.css
deleted file mode 100644
index 4298d946ab63c672517d16cde93535f0553f520b..0000000000000000000000000000000000000000
--- a/spaces/LightChen2333/OpenSLU/static/css/style.css
+++ /dev/null
@@ -1,98 +0,0 @@
-.card {
-    --phoenix-card-spacer-y: 1.5rem;
-    --phoenix-card-spacer-x: 1.5rem;
-    --phoenix-card-title-spacer-y: 1rem;
-    --phoenix-card-border-width: 1px;
-    --phoenix-card-border-color: var(--phoenix-gray-200);
-    --phoenix-card-border-radius: 0.5rem;
-    --phoenix-card-box-shadow: ;
-    --phoenix-card-inner-border-radius: calc(0.5rem - 1px);
-    --phoenix-card-cap-padding-y: 1.5rem;
-    --phoenix-card-cap-padding-x: 1.5rem;
-    --phoenix-card-cap-bg: var(--phoenix-card-cap-bg);
-    --phoenix-card-cap-color: ;
-    --phoenix-card-height: ;
-    --phoenix-card-color: ;
-    --phoenix-card-bg: #fff;
-    --phoenix-card-img-overlay-padding: 1rem;
-    --phoenix-card-group-margin: 1rem;
-    position: relative;
-    display: -webkit-box;
-    display: -ms-flexbox;
-    display: flex;
-    -webkit-box-orient: vertical;
-    -webkit-box-direction: normal;
-    -ms-flex-direction: column;
-    flex-direction: column;
-    min-width: 0;
-    height: var(--phoenix-card-height);
-    word-wrap: break-word;
-    background-color: var(--phoenix-card-bg);
-    background-clip: border-box;
-    border: var(--phoenix-card-border-width) solid var(--phoenix-card-border-color);
-    border-radius: var(--phoenix-card-border-radius);
-    -webkit-box-shadow: var(--phoenix-card-box-shadow);
-    box-shadow: var(--phoenix-card-box-shadow);
-}
-.h-100 {
-    height: 100% !important;
-}
-.card-body {
-    -webkit-box-flex: 1;
-    -ms-flex: 1 1 auto;
-    flex: 1 1 auto;
-    padding: var(--phoenix-card-spacer-y) var(--phoenix-card-spacer-x);
-    color: var(--phoenix-card-color);
-}
-
-.justify-content-between {
-    -webkit-box-pack: justify !important;
-    -ms-flex-pack: justify !important;
-    justify-content: space-between !important;
-}
-.d-flex {
-    display: -webkit-box !important;
-    display: -ms-flexbox !important;
-    display: flex !important;
-}
-.pt-3 {
-    padding-top: 1rem !important;
-}
-.mb-2 {
-    margin-bottom: 0.5rem !important;
-}
-.align-items-center {
-    -webkit-box-align: center !important;
-    -ms-flex-align: center !important;
-    align-items: center !important;
-}
-.bullet-item {
-    height: 0.5rem;
-    width: 1rem;
-    border-radius: 2px;
-}
-.bg-primary {
-    --phoenix-bg-opacity: 1;
-    background-color: rgba(var(--phoenix-primary-rgb), var(--phoenix-bg-opacity)) !important;
-}
-.me-2 {
-    margin-right: 0.5rem !important;
-}
-.flex-1 {
-    -webkit-box-flex: 1;
-    -ms-flex: 1;
-    flex: 1;
-}
-.text-900 {
-    --phoenix-text-opacity: 1;
-    color: rgba(var(--phoenix-900-rgb), var(--phoenix-text-opacity)) !important;
-}
-.fw-semi-bold {
-    font-weight: 600 !important;
-}
-.mb-0 {
-    margin-bottom: 0 !important;
-}
-h6, .h6 {
-    font-size: 0.8rem;
-}
\ No newline at end of file
diff --git a/spaces/LuxOAI/HUXTT/app.py b/spaces/LuxOAI/HUXTT/app.py
deleted file mode 100644
index c732bd25882a6f850f97373435eb9fbfaa698bd1..0000000000000000000000000000000000000000
--- a/spaces/LuxOAI/HUXTT/app.py
+++ /dev/null
@@ -1,52 +0,0 @@
-import openai
-import gradio as gr
-import json
-
-openai.api_key = "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"
-
-def save_conversation():
-    with open('conversation.json', 'w') as f:
-        json.dump(messages, f)
-
-def load_conversation():
-    try:
-        with open('conversation.json', 'r') as f:
-            return json.load(f)
-    except FileNotFoundError:
-        return []
-
-messages = load_conversation()
-
-if not messages:
-    messages.append({"role": "system", "content": "You are a knowledgeable assistant specialized in recruiting and hiring, and familiar with ADP Workforce Now Recruitment and various hiring and CRM tools."})
-
-def CustomChatGPT(user_input):
-    messages.append({"role": "user", "content": user_input})
-
-    # Ensure the conversation fits within the model's maximum token limit
-    conversation = messages[-4096:]
-
-    try:
-        response = openai.ChatCompletion.create(
-            model="gpt-3.5-turbo",
-            messages=conversation,
-            max_tokens=1000,
-            temperature=0.7)
-    except openai.api_resources.request_error.RequestError as e:
-        print(f"Received error from OpenAI: {e}")
-        return "I'm sorry, but I'm unable to generate a response at this time."
-
-    ChatGPT_reply = response["choices"][0]["message"]["content"]
-    messages.append({"role": "assistant", "content": ChatGPT_reply})
-    
-    save_conversation()
-
-    return ChatGPT_reply
-
-interface = gr.Interface(fn=CustomChatGPT, 
-                         inputs="textbox", 
-                         outputs="textbox", 
-                         title="HR HELPER", 
-                         description="Chat with a specialized assistant that can answer questions about recruiting, hiring, and various HR and CRM tools. Developed by A. Leschik.")
-
-interface.launch()
diff --git a/spaces/LuxOAI/ResumeBud/README.md b/spaces/LuxOAI/ResumeBud/README.md
deleted file mode 100644
index 8d29af5a837ec491622bed243b65c4269dca3c48..0000000000000000000000000000000000000000
--- a/spaces/LuxOAI/ResumeBud/README.md
+++ /dev/null
@@ -1,13 +0,0 @@
----
-title: ResumeBud
-emoji: 🐠
-colorFrom: red
-colorTo: green
-sdk: gradio
-sdk_version: 3.32.0
-app_file: app.py
-pinned: false
-license: openrail
----
-
-Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
diff --git a/spaces/Lycorisdeve/DeepDanbooru_string/README.md b/spaces/Lycorisdeve/DeepDanbooru_string/README.md
deleted file mode 100644
index 4330b6f969246dc764a34ea254d2e807159f1c55..0000000000000000000000000000000000000000
--- a/spaces/Lycorisdeve/DeepDanbooru_string/README.md
+++ /dev/null
@@ -1,39 +0,0 @@
----
-title: DeepDanbooru String
-emoji: 💬
-colorFrom: blue
-colorTo: red
-sdk: gradio
-sdk_version: 3.6
-app_file: app.py
-pinned: false
-duplicated_from: NoCrypt/DeepDanbooru_string
----
-
-# Configuration
-
-`title`: _string_
-Display title for the Space
-
-`emoji`: _string_
-Space emoji (emoji-only character allowed)
-
-`colorFrom`: _string_
-Color for Thumbnail gradient (red, yellow, green, blue, indigo, purple, pink, gray)
-
-`colorTo`: _string_
-Color for Thumbnail gradient (red, yellow, green, blue, indigo, purple, pink, gray)
-
-`sdk`: _string_
-Can be either `gradio`, `streamlit`, or `static`
-
-`sdk_version` : _string_
-Only applicable for `streamlit` SDK.  
-See [doc](https://hf.co/docs/hub/spaces) for more info on supported versions.
-
-`app_file`: _string_
-Path to your main application file (which contains either `gradio` or `streamlit` Python code, or `static` html code).
-Path is relative to the root of the repository.
-
-`pinned`: _boolean_
-Whether the Space stays on top of your list.
diff --git a/spaces/Make-A-Protagonist/Make-A-Protagonist-inference/Make-A-Protagonist/experts/XMem/inference/interact/s2m/__init__.py b/spaces/Make-A-Protagonist/Make-A-Protagonist-inference/Make-A-Protagonist/experts/XMem/inference/interact/s2m/__init__.py
deleted file mode 100644
index e69de29bb2d1d6434b8b29ae775ad8c2e48c5391..0000000000000000000000000000000000000000
diff --git a/spaces/Makiing/coolb-in-gtest/tests/kblob.ts b/spaces/Makiing/coolb-in-gtest/tests/kblob.ts
deleted file mode 100644
index 9e15b41c1c94a690beb61b23cdb42fc78767ccd2..0000000000000000000000000000000000000000
--- a/spaces/Makiing/coolb-in-gtest/tests/kblob.ts
+++ /dev/null
@@ -1,27 +0,0 @@
-import FormData from 'form-data'
-
-import { fetch } from '@/lib/isomorphic'
-
-const formData = new FormData()
-
-const knowledgeRequest = {"imageInfo":{"url":"https://www.baidu.com/img/PCfb_5bf082d29588c07f842ccde3f97243ea.png"},"knowledgeRequest":{"invokedSkills":["ImageById"],"subscriptionId":"Bing.Chat.Multimodal","invokedSkillsRequestData":{"enableFaceBlur":true},"convoData":{"convoid":"51D|BingProdUnAuthenticatedUsers|E3DCA904FF236C67C3450163BCEC64CFF3F618CC8A4AFD75FD518F5ED0ADA080","convotone":"Creative"}}}
-
-formData.append('knowledgeRequest', JSON.stringify(knowledgeRequest))
-
-
-fetch('https://bing.vcanbb.top/images/kblob',
-  {
-    method: 'POST',
-    body: formData.getBuffer(),
-    headers: {
-      "sec-ch-ua": "\"Not/A)Brand\";v=\"99\", \"Google Chrome\";v=\"115\", \"Chromium\";v=\"115\"",
-      "sec-ch-ua-mobile": "?0",
-      "sec-ch-ua-platform": "\"Windows\"",
-      "Referer": "https://bing.vcanbb.top/web/index.html",
-      "Referrer-Policy": "origin-when-cross-origin",
-      ...formData.getHeaders()
-    }
-
-  }
-).then(res => res.text())
-.then(res => console.log('res', res))
diff --git a/spaces/Malmika/Osana-WEB-GPT/app_update02.py b/spaces/Malmika/Osana-WEB-GPT/app_update02.py
deleted file mode 100644
index 0be90bba24313876717017d4294e67d6746b1419..0000000000000000000000000000000000000000
--- a/spaces/Malmika/Osana-WEB-GPT/app_update02.py
+++ /dev/null
@@ -1,134 +0,0 @@
-import json
-import requests
-import wikipedia
-import gradio as gr
-import transformers
-import spacy
-from bs4 import BeautifulSoup
-from transformers import AutoTokenizer, AutoModelForSeq2SeqLM
-
-
-# Set up Google SERP API credentials
-serp_api_key = '5924c6cfe5fec240e39838ff06439c8d36d294a0'  # Replace with your actual Google SERP API key
-
- # Load the Pegasus model
-tokenizer = AutoTokenizer.from_pretrained("facebook/bart-large-cnn")
-model = AutoModelForSeq2SeqLM.from_pretrained("facebook/bart-large-cnn")
-
-# Function to send a message and receive a response from the chatbot
-def chat(message):
-    try:
-        # You can add your chatbot implementation here
-        return "."
-    except Exception as e:
-        print("An error occurred:", e)
-        return ""
-
-# Function to get the latest answers from Google SERP API
-def get_latest_answers(query):
-    url = "https://google.serper.dev/search"
-
-    payload = json.dumps({
-        "q": query
-    })
-    headers = {
-        'X-API-KEY': serp_api_key,
-        'Content-Type': 'application/json'
-    }
-
-    response = requests.request("POST", url, headers=headers, data=payload)
-
-    try:
-        # Parse the response JSON
-        data = json.loads(response.text)
-
-        # Extract details from the response
-        output = ""
-
-        if 'knowledgeGraph' in data:
-            knowledge_graph = data['knowledgeGraph']
-            output += "Website: {}\n".format(knowledge_graph.get('website'))
-            output += "Description: {}\n".format(knowledge_graph.get('description'))
-
-        if 'organic' in data:
-            organic_results = data['organic']
-            for result in organic_results:
-                output += "Snippet: {}\n".format(result.get('snippet'))
-
-        if 'peopleAlsoAsk' in data:
-            people_also_ask = data['peopleAlsoAsk']
-            for question in people_also_ask:
-                output += "Snippet: {}\n".format(question.get('snippet'))
-
-        return output
-
-    except json.JSONDecodeError:
-        print(".")
-        return ""
-
-    except Exception as e:
-        print(".")
-        return ""
-
-# Function to search Wikipedia for an answer and summarize it
-def search_wikipedia(query):
-    try:
-        search_results = wikipedia.search(query)
-
-        # Get the page summary of the first search result
-        if search_results:
-            page_title = search_results[0]
-            page_summary = wikipedia.summary(page_title)
-            return page_summary
-        else:
-            print(".")
-            return None
-    except wikipedia.exceptions.DisambiguationError as e:
-        # Handle disambiguation error
-        print(".")
-        return None
-    except wikipedia.exceptions.PageError as e:
-        # Handle page not found error
-        print(".")
-        return None
-    except Exception as e:
-        # Handle other exceptions
-        print(".")
-        return None
-
-# Function to generate summarized paragraph using Google Pegasus summarization
-def generate_summary(user_input):
-    output = get_latest_answers(user_input)
-    page_summary = search_wikipedia(user_input)
-    chat_answer = chat(user_input)
-
-    # Combine the input text from various sources
-    input_text = f"Google:\n{output}\nWikipedia :\n{page_summary}\n"
-
-  
-    # Tokenize and generate a summary
-    input_ids = tokenizer.encode(input_text, return_tensors="pt", max_length=1024, truncation=True)
-    summary_ids = model.generate(input_ids, max_length=200, min_length=50, length_penalty=2.0, num_beams=4, early_stopping=True)
-
-    # Decode the summary
-    summarized_paragraph = tokenizer.decode(summary_ids[0], skip_special_tokens=True)
-
-    return summarized_paragraph
-
-# Define the Gradio interface
-def summarizer_interface(user_input):
-    summarized_text = generate_summary(user_input)
-    return summarized_text
-
-iface = gr.Interface(
-    fn=summarizer_interface,
-    inputs="text",
-    outputs="text",
-    title="Osana Web-GPT",
-    description="Enter your query and get the latest and better answer.",
-    theme="black",
-    layout="horizontal",
-)
-
-# Launch the interface
-iface.launch()
diff --git a/spaces/Marshalls/testmtd/inference/generate.py b/spaces/Marshalls/testmtd/inference/generate.py
deleted file mode 100644
index a62f636319308743649390d8415e2b2de4a788f4..0000000000000000000000000000000000000000
--- a/spaces/Marshalls/testmtd/inference/generate.py
+++ /dev/null
@@ -1,172 +0,0 @@
-import sys
-import os
-THIS_DIR = os.path.dirname(os.path.abspath(__file__))
-ROOT_DIR = os.path.abspath(os.path.join(THIS_DIR, os.pardir))#os.pardir--get parent directory
-sys.path.append(ROOT_DIR)
-import numpy as np; import scipy.linalg
-# LUL
-w_shape = [219,219]
-w_init = np.linalg.qr(np.random.randn(*w_shape))[0].astype(np.float32)
-#np.random.randn(size)--Generate the matrix according to size
-#np.linalg.qr--caculate matrix QR decomposition
-np_p, np_l, np_u = scipy.linalg.lu(w_init)
-
-from training.datasets import create_dataset, create_dataloader
-
-from models import create_model
-from training.options.train_options import TrainOptions
-import torch
-import pytorch_lightning as pl
-import numpy as np
-import pickle, json, yaml
-import sklearn
-import argparse
-import os, glob
-from pathlib import Path
-
-from analysis.visualization.generate_video_from_mats import generate_video_from_mats
-from analysis.visualization.generate_video_from_expmaps import generate_video_from_expmaps
-from analysis.visualization.generate_video_from_moglow_pos import generate_video_from_moglow_loc
-
-from training.utils import get_latest_checkpoint
-
-if __name__ == '__main__':
-    print("Hi")
-    parser = argparse.ArgumentParser(description='Generate with model')
-    parser.add_argument('--data_dir', type=str)
-    parser.add_argument('--seeds', type=str, help='in the format: mod,seq_id;mod,seq_id')
-    parser.add_argument('--seeds_file', type=str, help='file from which to choose a random seed')
-    parser.add_argument('--output_folder', type=str)
-    parser.add_argument('--audio_format', type=str, default="wav")
-    parser.add_argument('--experiment_name', type=str)
-    parser.add_argument('--seq_id', type=str)
-    parser.add_argument('--max_length', type=int, default=-1)
-    parser.add_argument('--no-use_scalers', dest='use_scalers', action='store_false')#action='store_false'--set the Bool Value 0
-    parser.add_argument('--generate_video', action='store_true')#action='store_true'--set the Bool Value 1--choose to generate video
-    parser.add_argument('--generate_bvh', action='store_true')
-    parser.add_argument('--generate_ground_truth', action='store_true')
-    parser.add_argument('--fps', type=int, default=20)
-    parser.add_argument('--seed',type=str,help='nothing')
-    args = parser.parse_args()
-    data_dir = args.data_dir
-    audio_format = args.audio_format
-    fps = args.fps
-    output_folder = args.output_folder
-    print("##############################################################################")
-    print(output_folder)
-    print("##############################################################################")
-    seq_id = args.seq_id
-    seed=args.seed
-    if args.seeds is not None:
-        seeds = {mod:seq for mod,seq in [tuple(x.split(",")) for x in args.seeds.split(";")]}
-    else:
-        seeds = {}
-
-    if seq_id is None:
-        temp_base_filenames = [x[:-1] for x in open(data_dir + "/base_filenames_test.txt", "r").readlines()]#find the name of the song in the txt created before
-        seq_id = np.random.choice(temp_base_filenames)
-    if args.seeds_file is not None:
-        print("choosing random seed from "+args.seeds_file)
-        temp_base_filenames = [x[:-1] for x in open(args.seeds_file, "r").readlines()]
-        seq_id = np.random.choice(temp_base_filenames)
-
-
-    print('seq_id:  ',seq_id)
-
-    #load hparams file
-    default_save_path = "training/experiments/"+args.experiment_name
-    logs_path = default_save_path
-    latest_checkpoint = get_latest_checkpoint(logs_path)
-    print(latest_checkpoint)
-    checkpoint_dir = Path(latest_checkpoint).parent.parent.absolute()
-    # exp_opt = json.loads(open("training/experiments/"+args.experiment_name+"/opt.json","r").read())
-    exp_opt = yaml.safe_load(open(str(checkpoint_dir)+"/hparams.yaml","r").read())#yaml is a file saving the parameters(type=dictionery)
-    opt = vars(TrainOptions().parse(parse_args=["--model", exp_opt["model"]]))
-    #print(opt)
-    opt.update(exp_opt)
-    # opt["cond_concat_dims"] = True
-    # opt["bn_momentum"] = 0.0
-    opt["batch_size"] = 1
-    opt["phase"] = "inference"
-    opt["tpu_cores"] = 0
-    class Struct:
-        def __init__(self, **entries):
-            self.__dict__.update(entries)
-    #print(opt)
-    opt = Struct(**opt)
-
-    input_mods = opt.input_modalities.split(",")
-    output_mods = opt.output_modalities.split(",")
-    output_time_offsets = [int(x) for x in str(opt.output_time_offsets).split(",")]
-    if args.use_scalers:
-        scalers = [x+"_scaler.pkl" for x in output_mods]
-    else:
-        scalers = []
-
-    # Load latest trained checkpoint from experiment
-    model = create_model(opt)
-    model = model.load_from_checkpoint(latest_checkpoint, opt=opt)
-
-    # Load input features (sequences must have been processed previously into features)
-    features = {}
-    for i,mod in enumerate(input_mods): 
-        if mod in seeds:
-            feature = np.load(data_dir+"/"+seeds[mod]+"."+mod+".npy")
-        elif (seed is not None and i==0):
-            #feature = np.load(data_dir+"/"+seq_id+"."+mod+".npy")
-            feature=np.load(seed+'.npy')    
-        else:
-            feature=np.load(data_dir+'/'+seq_id+'.'+mod+'.npy')    
-        if args.max_length != -1:
-            feature = feature[:args.max_length]
-        if model.input_fix_length_types[i] == "single":
-            features["in_"+mod] = np.expand_dims(np.expand_dims(feature,1),1)
-        else:
-            features["in_"+mod] = np.expand_dims(feature,1)
-
-    # Generate prediction
-    if torch.cuda.is_available():
-        model.cuda()
-    #import pdb;pdb.set_trace()
-    #import time
-    #start_time = time.time()
-    predicted_mods = model.generate(features, ground_truth=args.generate_ground_truth)
-    #print("--- %s seconds ---" % (time.time() - start_time))
-    if len(predicted_mods) == 0:
-        print("Sequence too short!")
-    else:
-        # import pdb;pdb.set_trace()
-        for i, mod in enumerate(output_mods):
-            predicted_mod = predicted_mods[i].cpu().numpy()
-            if len(scalers)>0:
-                transform = pickle.load(open(data_dir+"/"+scalers[i], "rb"))
-                predicted_mod = transform.inverse_transform(predicted_mod)
-            #print(predicted_mod)
-            predicted_features_file = output_folder+"/"+args.experiment_name+"/predicted_mods/"+seq_id+"."+mod+".generated"
-            np.save(predicted_features_file,predicted_mod)
-            predicted_features_file += ".npy"
-            if args.generate_video:
-                trim_audio = output_time_offsets[i] / fps #converting trim_audio from being in frames (which is more convenient as thats how we specify the output_shift in the models), to seconds
-                #print("trim_audio: ",trim_audio)
-
-                audio_file = data_dir + "/" + seq_id + "."+audio_format
-
-                output_folder = output_folder+"/"+args.experiment_name+"/videos/"
-                if mod == "joint_angles_scaled":
-                    generate_video_from_mats(predicted_features_file,output_folder,audio_file,trim_audio,fps,plot_mats)
-                elif mod == "expmap_scaled" or mod == "expmap_scaled_20" or mod == "expmap_cr_scaled_20":
-                    pipeline_file = f'{data_dir}/motion_{mod}_data_pipe.sav'
-                    generate_video_from_expmaps(predicted_features_file,pipeline_file,output_folder,audio_file,trim_audio,args.generate_bvh)
-                elif mod == "position_scaled":
-                    control_file = f'{data_dir}/{seq_id}.moglow_control_scaled.npy'
-                    data = np.load(predicted_features_file)[:,0,:]
-                    control = np.load(control_file)
-                    if args.use_scalers:
-                        transform = pickle.load(open(data_dir+"/moglow_control_scaled_scaler.pkl", "rb"))
-                        control = transform.inverse_transform(control)
-                    control = control[int(opt.output_time_offsets.split(",")[0]):]
-                    generate_video_from_moglow_loc(data,control,output_folder,seq_id,audio_file,fps,trim_audio)
-                else:
-                    print("Warning: mod "+mod+" not supported")
-                    # raise NotImplementedError(f'Feature type {feature_type} not implemented')
-                    pass
diff --git a/spaces/Mellow-ai/PhotoAI_Mellow/annotator/uniformer/configs/_base_/models/deeplabv3plus_r50-d8.py b/spaces/Mellow-ai/PhotoAI_Mellow/annotator/uniformer/configs/_base_/models/deeplabv3plus_r50-d8.py
deleted file mode 100644
index 050e39e091d816df9028d23aa3ecf9db74e441e1..0000000000000000000000000000000000000000
--- a/spaces/Mellow-ai/PhotoAI_Mellow/annotator/uniformer/configs/_base_/models/deeplabv3plus_r50-d8.py
+++ /dev/null
@@ -1,46 +0,0 @@
-# model settings
-norm_cfg = dict(type='SyncBN', requires_grad=True)
-model = dict(
-    type='EncoderDecoder',
-    pretrained='open-mmlab://resnet50_v1c',
-    backbone=dict(
-        type='ResNetV1c',
-        depth=50,
-        num_stages=4,
-        out_indices=(0, 1, 2, 3),
-        dilations=(1, 1, 2, 4),
-        strides=(1, 2, 1, 1),
-        norm_cfg=norm_cfg,
-        norm_eval=False,
-        style='pytorch',
-        contract_dilation=True),
-    decode_head=dict(
-        type='DepthwiseSeparableASPPHead',
-        in_channels=2048,
-        in_index=3,
-        channels=512,
-        dilations=(1, 12, 24, 36),
-        c1_in_channels=256,
-        c1_channels=48,
-        dropout_ratio=0.1,
-        num_classes=19,
-        norm_cfg=norm_cfg,
-        align_corners=False,
-        loss_decode=dict(
-            type='CrossEntropyLoss', use_sigmoid=False, loss_weight=1.0)),
-    auxiliary_head=dict(
-        type='FCNHead',
-        in_channels=1024,
-        in_index=2,
-        channels=256,
-        num_convs=1,
-        concat_input=False,
-        dropout_ratio=0.1,
-        num_classes=19,
-        norm_cfg=norm_cfg,
-        align_corners=False,
-        loss_decode=dict(
-            type='CrossEntropyLoss', use_sigmoid=False, loss_weight=0.4)),
-    # model training and testing settings
-    train_cfg=dict(),
-    test_cfg=dict(mode='whole'))
diff --git a/spaces/MisterZee/PIFu-Clothed-Human-Digitization/PIFu/lib/model/ConvPIFuNet.py b/spaces/MisterZee/PIFu-Clothed-Human-Digitization/PIFu/lib/model/ConvPIFuNet.py
deleted file mode 100644
index 1d43d262aa237d03db0cf329b4d199061ee6a006..0000000000000000000000000000000000000000
--- a/spaces/MisterZee/PIFu-Clothed-Human-Digitization/PIFu/lib/model/ConvPIFuNet.py
+++ /dev/null
@@ -1,99 +0,0 @@
-import torch
-import torch.nn as nn
-import torch.nn.functional as F
-from .BasePIFuNet import BasePIFuNet
-from .SurfaceClassifier import SurfaceClassifier
-from .DepthNormalizer import DepthNormalizer
-from .ConvFilters import *
-from ..net_util import init_net
-
-class ConvPIFuNet(BasePIFuNet):
-    '''
-    Conv Piximp network is the standard 3-phase network that we will use.
-    The image filter is a pure multi-layer convolutional network,
-    while during feature extraction phase all features in the pyramid at the projected location
-    will be aggregated.
-    It does the following:
-        1. Compute image feature pyramids and store it in self.im_feat_list
-        2. Calculate calibration and indexing on each of the feat, and append them together
-        3. Classification.
-    '''
-
-    def __init__(self,
-                 opt,
-                 projection_mode='orthogonal',
-                 error_term=nn.MSELoss(),
-                 ):
-        super(ConvPIFuNet, self).__init__(
-            projection_mode=projection_mode,
-            error_term=error_term)
-
-        self.name = 'convpifu'
-
-        self.opt = opt
-        self.num_views = self.opt.num_views
-
-        self.image_filter = self.define_imagefilter(opt)
-
-        self.surface_classifier = SurfaceClassifier(
-            filter_channels=self.opt.mlp_dim,
-            num_views=self.opt.num_views,
-            no_residual=self.opt.no_residual,
-            last_op=nn.Sigmoid())
-
-        self.normalizer = DepthNormalizer(opt)
-
-        # This is a list of [B x Feat_i x H x W] features
-        self.im_feat_list = []
-
-        init_net(self)
-
-    def define_imagefilter(self, opt):
-        net = None
-        if opt.netIMF == 'multiconv':
-            net = MultiConv(opt.enc_dim)
-        elif 'resnet' in opt.netIMF:
-            net = ResNet(model=opt.netIMF)
-        elif opt.netIMF == 'vgg16':
-            net = Vgg16()
-        else:
-            raise NotImplementedError('model name [%s] is not recognized' % opt.imf_type)
-
-        return net
-
-    def filter(self, images):
-        '''
-        Filter the input images
-        store all intermediate features.
-        :param images: [B, C, H, W] input images
-        '''
-        self.im_feat_list = self.image_filter(images)
-
-    def query(self, points, calibs, transforms=None, labels=None):
-        '''
-        Given 3D points, query the network predictions for each point.
-        Image features should be pre-computed before this call.
-        store all intermediate features.
-        query() function may behave differently during training/testing.
-        :param points: [B, 3, N] world space coordinates of points
-        :param calibs: [B, 3, 4] calibration matrices for each image
-        :param transforms: Optional [B, 2, 3] image space coordinate transforms
-        :param labels: Optional [B, Res, N] gt labeling
-        :return: [B, Res, N] predictions for each point
-        '''
-        if labels is not None:
-            self.labels = labels
-
-        xyz = self.projection(points, calibs, transforms)
-        xy = xyz[:, :2, :]
-        z = xyz[:, 2:3, :]
-
-        z_feat = self.normalizer(z)
-
-        # This is a list of [B, Feat_i, N] features
-        point_local_feat_list = [self.index(im_feat, xy) for im_feat in self.im_feat_list]
-        point_local_feat_list.append(z_feat)
-        # [B, Feat_all, N]
-        point_local_feat = torch.cat(point_local_feat_list, 1)
-
-        self.preds = self.surface_classifier(point_local_feat)
diff --git a/spaces/MrBodean/VoiceClone/demo_toolbox.py b/spaces/MrBodean/VoiceClone/demo_toolbox.py
deleted file mode 100644
index ea30a29275965c7e2b815cd703e891a5ca53e97b..0000000000000000000000000000000000000000
--- a/spaces/MrBodean/VoiceClone/demo_toolbox.py
+++ /dev/null
@@ -1,43 +0,0 @@
-from pathlib import Path
-from toolbox import Toolbox
-from utils.argutils import print_args
-from utils.modelutils import check_model_paths
-import argparse
-import os
-
-
-if __name__ == '__main__':
-    parser = argparse.ArgumentParser(
-        description="Runs the toolbox",
-        formatter_class=argparse.ArgumentDefaultsHelpFormatter
-    )
-    
-    parser.add_argument("-d", "--datasets_root", type=Path, help= \
-        "Path to the directory containing your datasets. See toolbox/__init__.py for a list of "
-        "supported datasets.", default=None)
-    parser.add_argument("-e", "--enc_models_dir", type=Path, default="encoder/saved_models", 
-                        help="Directory containing saved encoder models")
-    parser.add_argument("-s", "--syn_models_dir", type=Path, default="synthesizer/saved_models", 
-                        help="Directory containing saved synthesizer models")
-    parser.add_argument("-v", "--voc_models_dir", type=Path, default="vocoder/saved_models", 
-                        help="Directory containing saved vocoder models")
-    parser.add_argument("--cpu", action="store_true", help=\
-        "If True, processing is done on CPU, even when a GPU is available.")
-    parser.add_argument("--seed", type=int, default=None, help=\
-        "Optional random number seed value to make toolbox deterministic.")
-    parser.add_argument("--no_mp3_support", action="store_true", help=\
-        "If True, no mp3 files are allowed.")
-    args = parser.parse_args()
-    print_args(args, parser)
-
-    if args.cpu:
-        # Hide GPUs from Pytorch to force CPU processing
-        os.environ["CUDA_VISIBLE_DEVICES"] = "-1"
-    del args.cpu
-
-    ## Remind the user to download pretrained models if needed
-    check_model_paths(encoder_path=args.enc_models_dir, synthesizer_path=args.syn_models_dir,
-                      vocoder_path=args.voc_models_dir)
-
-    # Launch the toolbox
-    Toolbox(**vars(args))    
diff --git a/spaces/MrBodean/VoiceClone/encoder/config.py b/spaces/MrBodean/VoiceClone/encoder/config.py
deleted file mode 100644
index 1c21312f3de971bfa008254c6035cebc09f05e4c..0000000000000000000000000000000000000000
--- a/spaces/MrBodean/VoiceClone/encoder/config.py
+++ /dev/null
@@ -1,45 +0,0 @@
-librispeech_datasets = {
-    "train": {
-        "clean": ["LibriSpeech/train-clean-100", "LibriSpeech/train-clean-360"],
-        "other": ["LibriSpeech/train-other-500"]
-    },
-    "test": {
-        "clean": ["LibriSpeech/test-clean"],
-        "other": ["LibriSpeech/test-other"]
-    },
-    "dev": {
-        "clean": ["LibriSpeech/dev-clean"],
-        "other": ["LibriSpeech/dev-other"]
-    },
-}
-libritts_datasets = {
-    "train": {
-        "clean": ["LibriTTS/train-clean-100", "LibriTTS/train-clean-360"],
-        "other": ["LibriTTS/train-other-500"]
-    },
-    "test": {
-        "clean": ["LibriTTS/test-clean"],
-        "other": ["LibriTTS/test-other"]
-    },
-    "dev": {
-        "clean": ["LibriTTS/dev-clean"],
-        "other": ["LibriTTS/dev-other"]
-    },
-}
-voxceleb_datasets = {
-    "voxceleb1" : {
-        "train": ["VoxCeleb1/wav"],
-        "test": ["VoxCeleb1/test_wav"]
-    },
-    "voxceleb2" : {
-        "train": ["VoxCeleb2/dev/aac"],
-        "test": ["VoxCeleb2/test_wav"]
-    }
-}
-
-other_datasets = [
-    "LJSpeech-1.1",
-    "VCTK-Corpus/wav48",
-]
-
-anglophone_nationalites = ["australia", "canada", "ireland", "uk", "usa"]
diff --git a/spaces/NAACL2022/CLIP-Caption-Reward/scripts_FineCapEval/clipscore_prepro_feats.py b/spaces/NAACL2022/CLIP-Caption-Reward/scripts_FineCapEval/clipscore_prepro_feats.py
deleted file mode 100644
index 5e085078ecd67e4e390bc50b543c14d4934cb260..0000000000000000000000000000000000000000
--- a/spaces/NAACL2022/CLIP-Caption-Reward/scripts_FineCapEval/clipscore_prepro_feats.py
+++ /dev/null
@@ -1,154 +0,0 @@
-"""
-Preprocess a raw json dataset into features files for use in data_loader.py
-
-Input: json file that has the form
-[{ file_path: 'path/img.jpg', captions: ['a caption', ...] }, ...]
-example element in this list would look like
-{'captions': [u'A man with a red helmet on a small moped on a dirt road. ', u'Man riding a motor bike on a dirt road on the countryside.', u'A man riding on the back of a motorcycle.', u'A dirt path with a young person on a motor bike rests to the foreground of a verdant area with a bridge and a background of cloud-wreathed mountains. ', u'A man in a red shirt and a red hat is on a motorcycle on a hill side.'], 'file_path': u'val2014/COCO_val2014_000000391895.jpg', 'id': 391895}
-
-This script reads this json, does some basic preprocessing on the captions
-(e.g. lowercase, etc.), creates a special UNK token, and encodes everything to arrays
-
-Output: two folders of features
-"""
-
-from __future__ import absolute_import
-from __future__ import division
-from __future__ import print_function
-
-import os
-import json
-import argparse
-from random import shuffle, seed
-import string
-# non-standard dependencies:
-import h5py
-from six.moves import cPickle
-import numpy as np
-import torch
-import torchvision.models as models
-import skimage.io
-
-from torchvision.transforms import Compose, Resize, CenterCrop, ToTensor, Normalize
-from PIL import Image
-from torch import nn
-
-# preprocess = Compose([
-#     Resize((448, 448), interpolation=Image.BICUBIC),
-#     CenterCrop((448, 448)),
-#     ToTensor()
-# ])
-
-
-# from clip.clip import load
-# from timm.models.vision_transformer import resize_pos_embed
-# import timm
-
-# from captioning.utils.resnet_utils import myResnet
-# import captioning.utils.resnet as resnet
-
-from captioning.utils.clipscore import CLIPScore
-
-from tqdm import tqdm
-
-
-def main(params):
-
-    clipscore_model = CLIPScore()
-    clipscore_model.to('cuda')
-
-    imgs = json.load(open(params['input_json'], 'r'))
-    imgs = imgs['images']
-    N = len(imgs)
-
-    seed(123) # make reproducible
-
-    # dir_fc = params['output_dir']+'_clip_'+save_model_type+'_fc'
-    # dir_att = params['output_dir']+'_clip_'+save_model_type+'_att'
-
-    vis_dir_fc = params['output_dir']+'_clipscore_vis'
-    if not os.path.isdir(vis_dir_fc):
-        os.mkdir(vis_dir_fc)
-
-    # text_dir_fc = params['output_dir']+'_clipscore_text'
-    # if not os.path.isdir(text_dir_fc):
-    #     os.mkdir(text_dir_fc)
-
-    # if not os.path.isdir(dir_att):
-    #     os.mkdir(dir_att)
-
-    for i,img in enumerate(tqdm(imgs)):
-        # load the image
-
-        # img_path = os.path.join(params['images_root'], img['filepath'], img['filename'])
-        # img_path = os.path.join(params['images_root'], img['file_name'])
-        img_path = os.path.join(params['images_root'], img['file_path'])
-
-        img_feat = clipscore_model.image_extract(img_path)
-        img_feat = img_feat.view(512)
-
-        # for d in img['sentences']:
-        #     text = d['raw'].strip()
-        #     text_feat = clipscore_model.text_extract(text)
-
-
-        # with torch.no_grad():
-
-            # image = preprocess(Image.open(os.path.join(params['images_root'], img['filepath'], img['filename']) ).convert("RGB"))
-            # image = torch.tensor(np.stack([image])).cuda()
-            # image -= mean
-            # image /= std
-            # if "RN" in params["model_type"]:
-            #     tmp_att, tmp_fc = model.encode_image(image)
-            #     tmp_att = tmp_att[0].permute(1, 2, 0)
-            #     tmp_fc = tmp_fc[0]
-            # elif params["model_type"] == 'vit_base_patch32_224_in21k':
-            #     x = model(image)
-            #     tmp_fc = x[0, 0, :]
-            #     tmp_att = x[0, 1:, :].reshape( 14, 14, 768 )
-            # else:
-            #     x = model.visual.conv1(image.half())  # shape = [*, width, grid, grid]
-            #     x = x.reshape(x.shape[0], x.shape[1], -1)  # shape = [*, width, grid ** 2]
-            #     x = x.permute(0, 2, 1)  # shape = [*, grid ** 2, width]
-            #     x = torch.cat([model.visual.class_embedding.to(x.dtype) + torch.zeros(x.shape[0], 1, x.shape[-1], dtype=x.dtype, device=x.device), x], dim=1)  # shape = [*, grid ** 2 + 1, width]
-            #     x = x + model.visual.positional_embedding.to(x.dtype)[:x.shape[1], :]
-            #     x = model.visual.ln_pre(x)
-
-            #     x = x.permute(1, 0, 2)  # NLD -> LND
-
-            #     for layer_idx, layer in enumerate(model.visual.transformer.resblocks):
-            #         x = layer(x)  
-
-            #     x = x.permute(1, 0, 2)
-            #     tmp_fc = x[0, 0, :]
-            #     tmp_att = x[0, 1:, :].reshape( 14, 14, 768 )
-                
-        np.save(os.path.join(vis_dir_fc, str(img['id'])), img_feat.data.cpu().float().numpy())
-        # np.save(os.path.join(text_dir_fc, str(img['cocoid'])), tmp_fc.data.cpu().float().numpy())
-
-
-        # np.savez_compressed(os.path.join(dir_att, str(img['cocoid'])), feat=tmp_att.data.cpu().float().numpy())
-
-        # if i % 1000 == 0:
-        #     print('processing %d/%d (%.2f%% done)' % (i, N, i*100.0/N))
-    print('wrote ', vis_dir_fc)
-
-if __name__ == "__main__":
-
-    parser = argparse.ArgumentParser()
-
-    # input json
-    # dataset_coco.json
-    parser.add_argument('--input_json', required=True, help='input json file to process into hdf5')
-    parser.add_argument('--output_dir', default='data', help='output h5 file')
-
-    # options
-    parser.add_argument('--images_root', default='', help='root location in which images are stored, to be prepended to file_path in input json')
-    # parser.add_argument('--att_size', default=14, type=int, help='14x14 or 7x7')
-    # parser.add_argument('--model_type', default='RN50', type=str, help='RN50, RN101, RN50x4, ViT-B/32, vit_base_patch32_224_in21k')
-
-    args = parser.parse_args()
-    params = vars(args) # convert to ordinary dict
-    print('parsed input parameters:')
-    print(json.dumps(params, indent = 2))
-    main(params)
diff --git a/spaces/NCTCMumbai/NCTC/models/official/nlp/bert/tokenization.py b/spaces/NCTCMumbai/NCTC/models/official/nlp/bert/tokenization.py
deleted file mode 100644
index b0f7e27e320c727c4eee511fc63ebb63929250c7..0000000000000000000000000000000000000000
--- a/spaces/NCTCMumbai/NCTC/models/official/nlp/bert/tokenization.py
+++ /dev/null
@@ -1,545 +0,0 @@
-# coding=utf-8
-# Copyright 2019 The TensorFlow Authors. All Rights Reserved.
-#
-# Licensed under the Apache License, Version 2.0 (the "License");
-# you may not use this file except in compliance with the License.
-# You may obtain a copy of the License at
-#
-#     http://www.apache.org/licenses/LICENSE-2.0
-#
-# Unless required by applicable law or agreed to in writing, software
-# distributed under the License is distributed on an "AS IS" BASIS,
-# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
-# See the License for the specific language governing permissions and
-# limitations under the License.
-# ==============================================================================
-"""Tokenization classes implementation.
-
-The file is forked from:
-https://github.com/google-research/bert/blob/master/tokenization.py.
-"""
-
-from __future__ import absolute_import
-from __future__ import division
-from __future__ import print_function
-
-import collections
-import re
-import unicodedata
-
-import six
-import tensorflow as tf
-
-import sentencepiece as spm
-
-SPIECE_UNDERLINE = "▁"
-
-
-def validate_case_matches_checkpoint(do_lower_case, init_checkpoint):
-  """Checks whether the casing config is consistent with the checkpoint name."""
-
-  # The casing has to be passed in by the user and there is no explicit check
-  # as to whether it matches the checkpoint. The casing information probably
-  # should have been stored in the bert_config.json file, but it's not, so
-  # we have to heuristically detect it to validate.
-
-  if not init_checkpoint:
-    return
-
-  m = re.match("^.*?([A-Za-z0-9_-]+)/bert_model.ckpt", init_checkpoint)
-  if m is None:
-    return
-
-  model_name = m.group(1)
-
-  lower_models = [
-      "uncased_L-24_H-1024_A-16", "uncased_L-12_H-768_A-12",
-      "multilingual_L-12_H-768_A-12", "chinese_L-12_H-768_A-12"
-  ]
-
-  cased_models = [
-      "cased_L-12_H-768_A-12", "cased_L-24_H-1024_A-16",
-      "multi_cased_L-12_H-768_A-12"
-  ]
-
-  is_bad_config = False
-  if model_name in lower_models and not do_lower_case:
-    is_bad_config = True
-    actual_flag = "False"
-    case_name = "lowercased"
-    opposite_flag = "True"
-
-  if model_name in cased_models and do_lower_case:
-    is_bad_config = True
-    actual_flag = "True"
-    case_name = "cased"
-    opposite_flag = "False"
-
-  if is_bad_config:
-    raise ValueError(
-        "You passed in `--do_lower_case=%s` with `--init_checkpoint=%s`. "
-        "However, `%s` seems to be a %s model, so you "
-        "should pass in `--do_lower_case=%s` so that the fine-tuning matches "
-        "how the model was pre-training. If this error is wrong, please "
-        "just comment out this check." %
-        (actual_flag, init_checkpoint, model_name, case_name, opposite_flag))
-
-
-def convert_to_unicode(text):
-  """Converts `text` to Unicode (if it's not already), assuming utf-8 input."""
-  if six.PY3:
-    if isinstance(text, str):
-      return text
-    elif isinstance(text, bytes):
-      return text.decode("utf-8", "ignore")
-    else:
-      raise ValueError("Unsupported string type: %s" % (type(text)))
-  elif six.PY2:
-    if isinstance(text, str):
-      return text.decode("utf-8", "ignore")
-    elif isinstance(text, unicode):
-      return text
-    else:
-      raise ValueError("Unsupported string type: %s" % (type(text)))
-  else:
-    raise ValueError("Not running on Python2 or Python 3?")
-
-
-def printable_text(text):
-  """Returns text encoded in a way suitable for print or `tf.logging`."""
-
-  # These functions want `str` for both Python2 and Python3, but in one case
-  # it's a Unicode string and in the other it's a byte string.
-  if six.PY3:
-    if isinstance(text, str):
-      return text
-    elif isinstance(text, bytes):
-      return text.decode("utf-8", "ignore")
-    else:
-      raise ValueError("Unsupported string type: %s" % (type(text)))
-  elif six.PY2:
-    if isinstance(text, str):
-      return text
-    elif isinstance(text, unicode):
-      return text.encode("utf-8")
-    else:
-      raise ValueError("Unsupported string type: %s" % (type(text)))
-  else:
-    raise ValueError("Not running on Python2 or Python 3?")
-
-
-def load_vocab(vocab_file):
-  """Loads a vocabulary file into a dictionary."""
-  vocab = collections.OrderedDict()
-  index = 0
-  with tf.io.gfile.GFile(vocab_file, "r") as reader:
-    while True:
-      token = convert_to_unicode(reader.readline())
-      if not token:
-        break
-      token = token.strip()
-      vocab[token] = index
-      index += 1
-  return vocab
-
-
-def convert_by_vocab(vocab, items):
-  """Converts a sequence of [tokens|ids] using the vocab."""
-  output = []
-  for item in items:
-    output.append(vocab[item])
-  return output
-
-
-def convert_tokens_to_ids(vocab, tokens):
-  return convert_by_vocab(vocab, tokens)
-
-
-def convert_ids_to_tokens(inv_vocab, ids):
-  return convert_by_vocab(inv_vocab, ids)
-
-
-def whitespace_tokenize(text):
-  """Runs basic whitespace cleaning and splitting on a piece of text."""
-  text = text.strip()
-  if not text:
-    return []
-  tokens = text.split()
-  return tokens
-
-
-class FullTokenizer(object):
-  """Runs end-to-end tokenziation."""
-
-  def __init__(self, vocab_file, do_lower_case=True, split_on_punc=True):
-    self.vocab = load_vocab(vocab_file)
-    self.inv_vocab = {v: k for k, v in self.vocab.items()}
-    self.basic_tokenizer = BasicTokenizer(
-        do_lower_case=do_lower_case, split_on_punc=split_on_punc)
-    self.wordpiece_tokenizer = WordpieceTokenizer(vocab=self.vocab)
-
-  def tokenize(self, text):
-    split_tokens = []
-    for token in self.basic_tokenizer.tokenize(text):
-      for sub_token in self.wordpiece_tokenizer.tokenize(token):
-        split_tokens.append(sub_token)
-
-    return split_tokens
-
-  def convert_tokens_to_ids(self, tokens):
-    return convert_by_vocab(self.vocab, tokens)
-
-  def convert_ids_to_tokens(self, ids):
-    return convert_by_vocab(self.inv_vocab, ids)
-
-
-class BasicTokenizer(object):
-  """Runs basic tokenization (punctuation splitting, lower casing, etc.)."""
-
-  def __init__(self, do_lower_case=True, split_on_punc=True):
-    """Constructs a BasicTokenizer.
-
-    Args:
-      do_lower_case: Whether to lower case the input.
-      split_on_punc: Whether to apply split on punctuations. By default BERT
-        starts a new token for punctuations. This makes detokenization difficult
-        for tasks like seq2seq decoding.
-    """
-    self.do_lower_case = do_lower_case
-    self.split_on_punc = split_on_punc
-
-  def tokenize(self, text):
-    """Tokenizes a piece of text."""
-    text = convert_to_unicode(text)
-    text = self._clean_text(text)
-
-    # This was added on November 1st, 2018 for the multilingual and Chinese
-    # models. This is also applied to the English models now, but it doesn't
-    # matter since the English models were not trained on any Chinese data
-    # and generally don't have any Chinese data in them (there are Chinese
-    # characters in the vocabulary because Wikipedia does have some Chinese
-    # words in the English Wikipedia.).
-    text = self._tokenize_chinese_chars(text)
-
-    orig_tokens = whitespace_tokenize(text)
-    split_tokens = []
-    for token in orig_tokens:
-      if self.do_lower_case:
-        token = token.lower()
-        token = self._run_strip_accents(token)
-      if self.split_on_punc:
-        split_tokens.extend(self._run_split_on_punc(token))
-      else:
-        split_tokens.append(token)
-
-    output_tokens = whitespace_tokenize(" ".join(split_tokens))
-    return output_tokens
-
-  def _run_strip_accents(self, text):
-    """Strips accents from a piece of text."""
-    text = unicodedata.normalize("NFD", text)
-    output = []
-    for char in text:
-      cat = unicodedata.category(char)
-      if cat == "Mn":
-        continue
-      output.append(char)
-    return "".join(output)
-
-  def _run_split_on_punc(self, text):
-    """Splits punctuation on a piece of text."""
-    chars = list(text)
-    i = 0
-    start_new_word = True
-    output = []
-    while i < len(chars):
-      char = chars[i]
-      if _is_punctuation(char):
-        output.append([char])
-        start_new_word = True
-      else:
-        if start_new_word:
-          output.append([])
-        start_new_word = False
-        output[-1].append(char)
-      i += 1
-
-    return ["".join(x) for x in output]
-
-  def _tokenize_chinese_chars(self, text):
-    """Adds whitespace around any CJK character."""
-    output = []
-    for char in text:
-      cp = ord(char)
-      if self._is_chinese_char(cp):
-        output.append(" ")
-        output.append(char)
-        output.append(" ")
-      else:
-        output.append(char)
-    return "".join(output)
-
-  def _is_chinese_char(self, cp):
-    """Checks whether CP is the codepoint of a CJK character."""
-    # This defines a "chinese character" as anything in the CJK Unicode block:
-    #   https://en.wikipedia.org/wiki/CJK_Unified_Ideographs_(Unicode_block)
-    #
-    # Note that the CJK Unicode block is NOT all Japanese and Korean characters,
-    # despite its name. The modern Korean Hangul alphabet is a different block,
-    # as is Japanese Hiragana and Katakana. Those alphabets are used to write
-    # space-separated words, so they are not treated specially and handled
-    # like the all of the other languages.
-    if ((cp >= 0x4E00 and cp <= 0x9FFF) or  #
-        (cp >= 0x3400 and cp <= 0x4DBF) or  #
-        (cp >= 0x20000 and cp <= 0x2A6DF) or  #
-        (cp >= 0x2A700 and cp <= 0x2B73F) or  #
-        (cp >= 0x2B740 and cp <= 0x2B81F) or  #
-        (cp >= 0x2B820 and cp <= 0x2CEAF) or
-        (cp >= 0xF900 and cp <= 0xFAFF) or  #
-        (cp >= 0x2F800 and cp <= 0x2FA1F)):  #
-      return True
-
-    return False
-
-  def _clean_text(self, text):
-    """Performs invalid character removal and whitespace cleanup on text."""
-    output = []
-    for char in text:
-      cp = ord(char)
-      if cp == 0 or cp == 0xfffd or _is_control(char):
-        continue
-      if _is_whitespace(char):
-        output.append(" ")
-      else:
-        output.append(char)
-    return "".join(output)
-
-
-class WordpieceTokenizer(object):
-  """Runs WordPiece tokenziation."""
-
-  def __init__(self, vocab, unk_token="[UNK]", max_input_chars_per_word=400):
-    self.vocab = vocab
-    self.unk_token = unk_token
-    self.max_input_chars_per_word = max_input_chars_per_word
-
-  def tokenize(self, text):
-    """Tokenizes a piece of text into its word pieces.
-
-    This uses a greedy longest-match-first algorithm to perform tokenization
-    using the given vocabulary.
-
-    For example:
-      input = "unaffable"
-      output = ["un", "##aff", "##able"]
-
-    Args:
-      text: A single token or whitespace separated tokens. This should have
-        already been passed through `BasicTokenizer.
-
-    Returns:
-      A list of wordpiece tokens.
-    """
-
-    text = convert_to_unicode(text)
-
-    output_tokens = []
-    for token in whitespace_tokenize(text):
-      chars = list(token)
-      if len(chars) > self.max_input_chars_per_word:
-        output_tokens.append(self.unk_token)
-        continue
-
-      is_bad = False
-      start = 0
-      sub_tokens = []
-      while start < len(chars):
-        end = len(chars)
-        cur_substr = None
-        while start < end:
-          substr = "".join(chars[start:end])
-          if start > 0:
-            substr = "##" + substr
-          if substr in self.vocab:
-            cur_substr = substr
-            break
-          end -= 1
-        if cur_substr is None:
-          is_bad = True
-          break
-        sub_tokens.append(cur_substr)
-        start = end
-
-      if is_bad:
-        output_tokens.append(self.unk_token)
-      else:
-        output_tokens.extend(sub_tokens)
-    return output_tokens
-
-
-def _is_whitespace(char):
-  """Checks whether `chars` is a whitespace character."""
-  # \t, \n, and \r are technically control characters but we treat them
-  # as whitespace since they are generally considered as such.
-  if char == " " or char == "\t" or char == "\n" or char == "\r":
-    return True
-  cat = unicodedata.category(char)
-  if cat == "Zs":
-    return True
-  return False
-
-
-def _is_control(char):
-  """Checks whether `chars` is a control character."""
-  # These are technically control characters but we count them as whitespace
-  # characters.
-  if char == "\t" or char == "\n" or char == "\r":
-    return False
-  cat = unicodedata.category(char)
-  if cat in ("Cc", "Cf"):
-    return True
-  return False
-
-
-def _is_punctuation(char):
-  """Checks whether `chars` is a punctuation character."""
-  cp = ord(char)
-  # We treat all non-letter/number ASCII as punctuation.
-  # Characters such as "^", "$", and "`" are not in the Unicode
-  # Punctuation class but we treat them as punctuation anyways, for
-  # consistency.
-  if ((cp >= 33 and cp <= 47) or (cp >= 58 and cp <= 64) or
-      (cp >= 91 and cp <= 96) or (cp >= 123 and cp <= 126)):
-    return True
-  cat = unicodedata.category(char)
-  if cat.startswith("P"):
-    return True
-  return False
-
-
-def preprocess_text(inputs, remove_space=True, lower=False):
-  """Preprocesses data by removing extra space and normalize data.
-
-  This method is used together with sentence piece tokenizer and is forked from:
-  https://github.com/google-research/google-research/blob/master/albert/tokenization.py
-
-  Args:
-    inputs: The input text.
-    remove_space: Whether to remove the extra space.
-    lower: Whether to lowercase the text.
-
-  Returns:
-    The preprocessed text.
-
-  """
-  outputs = inputs
-  if remove_space:
-    outputs = " ".join(inputs.strip().split())
-
-  if six.PY2 and isinstance(outputs, str):
-    try:
-      outputs = six.ensure_text(outputs, "utf-8")
-    except UnicodeDecodeError:
-      outputs = six.ensure_text(outputs, "latin-1")
-
-  outputs = unicodedata.normalize("NFKD", outputs)
-  outputs = "".join([c for c in outputs if not unicodedata.combining(c)])
-  if lower:
-    outputs = outputs.lower()
-
-  return outputs
-
-
-def encode_pieces(sp_model, text, sample=False):
-  """Segements text into pieces.
-
-  This method is used together with sentence piece tokenizer and is forked from:
-  https://github.com/google-research/google-research/blob/master/albert/tokenization.py
-
-
-  Args:
-    sp_model: A spm.SentencePieceProcessor object.
-    text: The input text to be segemented.
-    sample: Whether to randomly sample a segmentation output or return a
-      deterministic one.
-
-  Returns:
-    A list of token pieces.
-  """
-  if six.PY2 and isinstance(text, six.text_type):
-    text = six.ensure_binary(text, "utf-8")
-
-  if not sample:
-    pieces = sp_model.EncodeAsPieces(text)
-  else:
-    pieces = sp_model.SampleEncodeAsPieces(text, 64, 0.1)
-  new_pieces = []
-  for piece in pieces:
-    piece = printable_text(piece)
-    if len(piece) > 1 and piece[-1] == "," and piece[-2].isdigit():
-      cur_pieces = sp_model.EncodeAsPieces(piece[:-1].replace(
-          SPIECE_UNDERLINE, ""))
-      if piece[0] != SPIECE_UNDERLINE and cur_pieces[0][0] == SPIECE_UNDERLINE:
-        if len(cur_pieces[0]) == 1:
-          cur_pieces = cur_pieces[1:]
-        else:
-          cur_pieces[0] = cur_pieces[0][1:]
-      cur_pieces.append(piece[-1])
-      new_pieces.extend(cur_pieces)
-    else:
-      new_pieces.append(piece)
-
-  return new_pieces
-
-
-def encode_ids(sp_model, text, sample=False):
-  """Segments text and return token ids.
-
-  This method is used together with sentence piece tokenizer and is forked from:
-  https://github.com/google-research/google-research/blob/master/albert/tokenization.py
-
-  Args:
-    sp_model: A spm.SentencePieceProcessor object.
-    text: The input text to be segemented.
-    sample: Whether to randomly sample a segmentation output or return a
-      deterministic one.
-
-  Returns:
-    A list of token ids.
-  """
-  pieces = encode_pieces(sp_model, text, sample=sample)
-  ids = [sp_model.PieceToId(piece) for piece in pieces]
-  return ids
-
-
-class FullSentencePieceTokenizer(object):
-  """Runs end-to-end sentence piece tokenization.
-
-  The interface of this class is intended to keep the same as above
-  `FullTokenizer` class for easier usage.
-  """
-
-  def __init__(self, sp_model_file):
-    """Inits FullSentencePieceTokenizer.
-
-    Args:
-      sp_model_file: The path to the sentence piece model file.
-    """
-    self.sp_model = spm.SentencePieceProcessor()
-    self.sp_model.Load(sp_model_file)
-    self.vocab = {
-        self.sp_model.IdToPiece(i): i
-        for i in six.moves.range(self.sp_model.GetPieceSize())
-    }
-
-  def tokenize(self, text):
-    """Tokenizes text into pieces."""
-    return encode_pieces(self.sp_model, text)
-
-  def convert_tokens_to_ids(self, tokens):
-    """Converts a list of tokens to a list of ids."""
-    return [self.sp_model.PieceToId(printable_text(token)) for token in tokens]
-
-  def convert_ids_to_tokens(self, ids):
-    """Converts a list of ids ot a list of tokens."""
-    return [self.sp_model.IdToPiece(id_) for id_ in ids]
diff --git a/spaces/NingKanae/anime-voice-generator/monotonic_align/__init__.py b/spaces/NingKanae/anime-voice-generator/monotonic_align/__init__.py
deleted file mode 100644
index e97eecc595dd3bd97d0104ec62799e2e5efea57c..0000000000000000000000000000000000000000
--- a/spaces/NingKanae/anime-voice-generator/monotonic_align/__init__.py
+++ /dev/null
@@ -1,20 +0,0 @@
-from numpy import zeros, int32, float32
-from torch import from_numpy
-
-from .core import maximum_path_jit
-
-
-def maximum_path(neg_cent, mask):
-    """ numba optimized version.
-    neg_cent: [b, t_t, t_s]
-    mask: [b, t_t, t_s]
-    """
-    device = neg_cent.device
-    dtype = neg_cent.dtype
-    neg_cent = neg_cent.data.cpu().numpy().astype(float32)
-    path = zeros(neg_cent.shape, dtype=int32)
-
-    t_t_max = mask.sum(1)[:, 0].data.cpu().numpy().astype(int32)
-    t_s_max = mask.sum(2)[:, 0].data.cpu().numpy().astype(int32)
-    maximum_path_jit(path, neg_cent, t_t_max, t_s_max)
-    return from_numpy(path).to(device=device, dtype=dtype)
diff --git a/spaces/Noobian/How-To-Generator/README.md b/spaces/Noobian/How-To-Generator/README.md
deleted file mode 100644
index 336d34d9039e7fe1326aa30aa2faaf5074ba3045..0000000000000000000000000000000000000000
--- a/spaces/Noobian/How-To-Generator/README.md
+++ /dev/null
@@ -1,12 +0,0 @@
----
-title: How To Generatot
-emoji: 🌍
-colorFrom: yellow
-colorTo: green
-sdk: gradio
-sdk_version: 3.18.0
-app_file: app.py
-pinned: false
----
-
-Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
diff --git a/spaces/OFA-Sys/OFA-Generic_Interface/fairseq/examples/fast_noisy_channel/noisy_channel_beam_search.py b/spaces/OFA-Sys/OFA-Generic_Interface/fairseq/examples/fast_noisy_channel/noisy_channel_beam_search.py
deleted file mode 100644
index 23869ebcd0c438f36e310c8ccddd3b5c07a71182..0000000000000000000000000000000000000000
--- a/spaces/OFA-Sys/OFA-Generic_Interface/fairseq/examples/fast_noisy_channel/noisy_channel_beam_search.py
+++ /dev/null
@@ -1,71 +0,0 @@
-# Copyright (c) Facebook, Inc. and its affiliates.
-#
-# This source code is licensed under the MIT license found in the
-# LICENSE file in the root directory of this source tree.
-
-import torch
-from fairseq.search import Search
-
-
-class NoisyChannelBeamSearch(Search):
-
-    def __init__(self, tgt_dict):
-        super().__init__(tgt_dict)
-        self.fw_scores_buf = None
-        self.lm_scores_buf = None
-
-    def _init_buffers(self, t):
-        # super()._init_buffers(t)
-        if self.fw_scores_buf is None:
-            self.scores_buf = t.new()
-            self.indices_buf = torch.LongTensor().to(device=t.device)
-            self.beams_buf = torch.LongTensor().to(device=t.device)
-            self.fw_scores_buf = t.new()
-            self.lm_scores_buf = t.new()
-
-    def combine_fw_bw(self, combine_method, fw_cum, bw, step):
-        if combine_method == "noisy_channel":
-            fw_norm = fw_cum.div(step + 1)
-            lprobs = bw + fw_norm
-        elif combine_method == "lm_only":
-            lprobs = bw + fw_cum
-
-        return lprobs
-
-    def step(self, step, fw_lprobs, scores, bw_lprobs, lm_lprobs, combine_method):
-        self._init_buffers(fw_lprobs)
-        bsz, beam_size, vocab_size = fw_lprobs.size()
-
-        if step == 0:
-            # at the first step all hypotheses are equally likely, so use
-            # only the first beam
-            fw_lprobs = fw_lprobs[:, ::beam_size, :].contiguous()
-            bw_lprobs = bw_lprobs[:, ::beam_size, :].contiguous()
-            # nothing to add since we are at the first step
-            fw_lprobs_cum = fw_lprobs
-
-        else:
-            # make probs contain cumulative scores for each hypothesis
-            raw_scores = (scores[:, :, step - 1].unsqueeze(-1))
-            fw_lprobs_cum = (fw_lprobs.add(raw_scores))
-
-        combined_lprobs = self.combine_fw_bw(combine_method, fw_lprobs_cum, bw_lprobs, step)
-
-        # choose the top k according to the combined noisy channel model score
-        torch.topk(
-            combined_lprobs.view(bsz, -1),
-            k=min(
-                # Take the best 2 x beam_size predictions. We'll choose the first
-                # beam_size of these which don't predict eos to continue with.
-                beam_size * 2,
-                combined_lprobs.view(bsz, -1).size(1) - 1,  # -1 so we never select pad
-            ),
-            out=(self.scores_buf, self.indices_buf),
-        )
-        # save corresponding fw and lm scores
-        self.fw_scores_buf = torch.gather(fw_lprobs_cum.view(bsz, -1), 1, self.indices_buf)
-        self.lm_scores_buf = torch.gather(lm_lprobs.view(bsz, -1), 1, self.indices_buf)
-        # Project back into relative indices and beams
-        self.beams_buf = self.indices_buf // vocab_size
-        self.indices_buf.fmod_(vocab_size)
-        return self.scores_buf, self.fw_scores_buf, self.lm_scores_buf, self.indices_buf, self.beams_buf
diff --git a/spaces/OFA-Sys/OFA-Generic_Interface/fairseq/fairseq/clib/libbleu/module.cpp b/spaces/OFA-Sys/OFA-Generic_Interface/fairseq/fairseq/clib/libbleu/module.cpp
deleted file mode 100644
index 35288b3177185670135f7bdc1f1589c5bb992304..0000000000000000000000000000000000000000
--- a/spaces/OFA-Sys/OFA-Generic_Interface/fairseq/fairseq/clib/libbleu/module.cpp
+++ /dev/null
@@ -1,33 +0,0 @@
-/**
- * Copyright 2017-present, Facebook, Inc.
- * All rights reserved.
- *
- * This source code is licensed under the license found in the
- * LICENSE file in the root directory of this source tree.
- */
-
-#include <Python.h>
-
-static PyMethodDef method_def[] = {{NULL, NULL, 0, NULL}}; // NOLINT
-
-static struct PyModuleDef module_def = {
-    PyModuleDef_HEAD_INIT,
-    "libbleu", /* name of module */
-    // NOLINTNEXTLINE
-    NULL, /* module documentation, may be NULL */
-    -1, /* size of per-interpreter state of the module,
-           or -1 if the module keeps state in global variables. */
-    method_def}; // NOLINT
-
-#if PY_MAJOR_VERSION == 2
-PyMODINIT_FUNC init_libbleu()
-#else
-PyMODINIT_FUNC PyInit_libbleu()
-#endif
-{
-  PyObject* m = PyModule_Create(&module_def);
-  if (!m) {
-    return NULL;
-  }
-  return m;
-}
diff --git a/spaces/OFA-Sys/OFA-Image_Caption/fairseq/examples/speech_recognition/new/__init__.py b/spaces/OFA-Sys/OFA-Image_Caption/fairseq/examples/speech_recognition/new/__init__.py
deleted file mode 100644
index e69de29bb2d1d6434b8b29ae775ad8c2e48c5391..0000000000000000000000000000000000000000
diff --git a/spaces/OFA-Sys/OFA-Image_Caption/fairseq/examples/wav2vec/unsupervised/tasks/__init__.py b/spaces/OFA-Sys/OFA-Image_Caption/fairseq/examples/wav2vec/unsupervised/tasks/__init__.py
deleted file mode 100644
index 6d7dd625e09451be671908578f93148f371f53cd..0000000000000000000000000000000000000000
--- a/spaces/OFA-Sys/OFA-Image_Caption/fairseq/examples/wav2vec/unsupervised/tasks/__init__.py
+++ /dev/null
@@ -1,11 +0,0 @@
-# Copyright (c) Facebook, Inc. and its affiliates.
-#
-# This source code is licensed under the MIT license found in the
-# LICENSE file in the root directory of this source tree.
-
-from .unpaired_audio_text import UnpairedAudioText
-
-
-__all__ = [
-    "UnpairedAudioText",
-]
diff --git a/spaces/OFA-Sys/OFA-Image_Caption/fairseq/fairseq/models/roberta/alignment_utils.py b/spaces/OFA-Sys/OFA-Image_Caption/fairseq/fairseq/models/roberta/alignment_utils.py
deleted file mode 100644
index ccc7f74cb94d5b8baa2d4e9dfd44f653d47ee43e..0000000000000000000000000000000000000000
--- a/spaces/OFA-Sys/OFA-Image_Caption/fairseq/fairseq/models/roberta/alignment_utils.py
+++ /dev/null
@@ -1,118 +0,0 @@
-# Copyright (c) Facebook, Inc. and its affiliates.
-#
-# This source code is licensed under the MIT license found in the
-# LICENSE file in the root directory of this source tree.
-
-from collections import Counter
-from typing import List
-
-import torch
-
-
-def align_bpe_to_words(roberta, bpe_tokens: torch.LongTensor, other_tokens: List[str]):
-    """
-    Helper to align GPT-2 BPE to other tokenization formats (e.g., spaCy).
-
-    Args:
-        roberta (RobertaHubInterface): RoBERTa instance
-        bpe_tokens (torch.LongTensor): GPT-2 BPE tokens of shape `(T_bpe)`
-        other_tokens (List[str]): other tokens of shape `(T_words)`
-
-    Returns:
-        List[str]: mapping from *other_tokens* to corresponding *bpe_tokens*.
-    """
-    assert bpe_tokens.dim() == 1
-    assert bpe_tokens[0] == 0
-
-    def clean(text):
-        return text.strip()
-
-    # remove whitespaces to simplify alignment
-    bpe_tokens = [roberta.task.source_dictionary.string([x]) for x in bpe_tokens]
-    bpe_tokens = [
-        clean(roberta.bpe.decode(x) if x not in {"<s>", ""} else x) for x in bpe_tokens
-    ]
-    other_tokens = [clean(str(o)) for o in other_tokens]
-
-    # strip leading <s>
-    bpe_tokens = bpe_tokens[1:]
-    assert "".join(bpe_tokens) == "".join(other_tokens)
-
-    # create alignment from every word to a list of BPE tokens
-    alignment = []
-    bpe_toks = filter(lambda item: item[1] != "", enumerate(bpe_tokens, start=1))
-    j, bpe_tok = next(bpe_toks)
-    for other_tok in other_tokens:
-        bpe_indices = []
-        while True:
-            if other_tok.startswith(bpe_tok):
-                bpe_indices.append(j)
-                other_tok = other_tok[len(bpe_tok) :]
-                try:
-                    j, bpe_tok = next(bpe_toks)
-                except StopIteration:
-                    j, bpe_tok = None, None
-            elif bpe_tok.startswith(other_tok):
-                # other_tok spans multiple BPE tokens
-                bpe_indices.append(j)
-                bpe_tok = bpe_tok[len(other_tok) :]
-                other_tok = ""
-            else:
-                raise Exception('Cannot align "{}" and "{}"'.format(other_tok, bpe_tok))
-            if other_tok == "":
-                break
-        assert len(bpe_indices) > 0
-        alignment.append(bpe_indices)
-    assert len(alignment) == len(other_tokens)
-
-    return alignment
-
-
-def align_features_to_words(roberta, features, alignment):
-    """
-    Align given features to words.
-
-    Args:
-        roberta (RobertaHubInterface): RoBERTa instance
-        features (torch.Tensor): features to align of shape `(T_bpe x C)`
-        alignment: alignment between BPE tokens and words returned by
-            func:`align_bpe_to_words`.
-    """
-    assert features.dim() == 2
-
-    bpe_counts = Counter(j for bpe_indices in alignment for j in bpe_indices)
-    assert bpe_counts[0] == 0  # <s> shouldn't be aligned
-    denom = features.new([bpe_counts.get(j, 1) for j in range(len(features))])
-    weighted_features = features / denom.unsqueeze(-1)
-
-    output = [weighted_features[0]]
-    largest_j = -1
-    for bpe_indices in alignment:
-        output.append(weighted_features[bpe_indices].sum(dim=0))
-        largest_j = max(largest_j, *bpe_indices)
-    for j in range(largest_j + 1, len(features)):
-        output.append(weighted_features[j])
-    output = torch.stack(output)
-    assert torch.all(torch.abs(output.sum(dim=0) - features.sum(dim=0)) < 1e-4)
-    return output
-
-
-def spacy_nlp():
-    if getattr(spacy_nlp, "_nlp", None) is None:
-        try:
-            from spacy.lang.en import English
-
-            spacy_nlp._nlp = English()
-        except ImportError:
-            raise ImportError("Please install spacy with: pip install spacy")
-    return spacy_nlp._nlp
-
-
-def spacy_tokenizer():
-    if getattr(spacy_tokenizer, "_tokenizer", None) is None:
-        try:
-            nlp = spacy_nlp()
-            spacy_tokenizer._tokenizer = nlp.Defaults.create_tokenizer(nlp)
-        except ImportError:
-            raise ImportError("Please install spacy with: pip install spacy")
-    return spacy_tokenizer._tokenizer
diff --git a/spaces/OFA-Sys/OFA-vqa/fairseq/examples/speech_synthesis/data_utils.py b/spaces/OFA-Sys/OFA-vqa/fairseq/examples/speech_synthesis/data_utils.py
deleted file mode 100644
index f43a4a90046fb9ee4944dc06ba377c1faade141d..0000000000000000000000000000000000000000
--- a/spaces/OFA-Sys/OFA-vqa/fairseq/examples/speech_synthesis/data_utils.py
+++ /dev/null
@@ -1,320 +0,0 @@
-# Copyright (c) Facebook, Inc. and its affiliates.
-#
-# This source code is licensed under the MIT license found in the
-# LICENSE file in the root directory of this source tree.
-
-import os
-from pathlib import Path
-from typing import Optional, List, Dict
-import zipfile
-import tempfile
-from dataclasses import dataclass
-from itertools import groupby
-
-import torch
-import torch.nn.functional as F
-import numpy as np
-from tqdm import tqdm
-
-from examples.speech_to_text.data_utils import load_tsv_to_dicts
-from fairseq.data.audio.audio_utils import TTSSpectrogram, TTSMelScale
-
-
-def trim_or_pad_to_target_length(
-        data_1d_or_2d: np.ndarray, target_length: int
-) -> np.ndarray:
-    assert len(data_1d_or_2d.shape) in {1, 2}
-    delta = data_1d_or_2d.shape[0] - target_length
-    if delta >= 0:  # trim if being longer
-        data_1d_or_2d = data_1d_or_2d[: target_length]
-    else:  # pad if being shorter
-        if len(data_1d_or_2d.shape) == 1:
-            data_1d_or_2d = np.concatenate(
-                [data_1d_or_2d, np.zeros(-delta)], axis=0
-            )
-        else:
-            data_1d_or_2d = np.concatenate(
-                [data_1d_or_2d, np.zeros((-delta, data_1d_or_2d.shape[1]))],
-                axis=0
-            )
-    return data_1d_or_2d
-
-
-def extract_logmel_spectrogram(
-        waveform: torch.Tensor, sample_rate: int,
-        output_path: Optional[Path] = None, win_length: int = 1024,
-        hop_length: int = 256, n_fft: int = 1024,
-        win_fn: callable = torch.hann_window, n_mels: int = 80,
-        f_min: float = 0., f_max: float = 8000, eps: float = 1e-5,
-        overwrite: bool = False, target_length: Optional[int] = None
-):
-    if output_path is not None and output_path.is_file() and not overwrite:
-        return
-
-    spectrogram_transform = TTSSpectrogram(
-        n_fft=n_fft, win_length=win_length, hop_length=hop_length,
-        window_fn=win_fn
-    )
-    mel_scale_transform = TTSMelScale(
-        n_mels=n_mels, sample_rate=sample_rate, f_min=f_min, f_max=f_max,
-        n_stft=n_fft // 2 + 1
-    )
-    spectrogram = spectrogram_transform(waveform)
-    mel_spec = mel_scale_transform(spectrogram)
-    logmel_spec = torch.clamp(mel_spec, min=eps).log()
-    assert len(logmel_spec.shape) == 3 and logmel_spec.shape[0] == 1
-    logmel_spec = logmel_spec.squeeze().t()  # D x T -> T x D
-    if target_length is not None:
-        trim_or_pad_to_target_length(logmel_spec, target_length)
-
-    if output_path is not None:
-        np.save(output_path.as_posix(), logmel_spec)
-    else:
-        return logmel_spec
-
-
-def extract_pitch(
-        waveform: torch.Tensor, sample_rate: int,
-        output_path: Optional[Path] = None, hop_length: int = 256,
-        log_scale: bool = True, phoneme_durations: Optional[List[int]] = None
-):
-    if output_path is not None and output_path.is_file():
-        return
-
-    try:
-        import pyworld
-    except ImportError:
-        raise ImportError("Please install PyWORLD: pip install pyworld")
-
-    _waveform = waveform.squeeze(0).double().numpy()
-    pitch, t = pyworld.dio(
-        _waveform, sample_rate, frame_period=hop_length / sample_rate * 1000
-    )
-    pitch = pyworld.stonemask(_waveform, pitch, t, sample_rate)
-
-    if phoneme_durations is not None:
-        pitch = trim_or_pad_to_target_length(pitch, sum(phoneme_durations))
-        try:
-            from scipy.interpolate import interp1d
-        except ImportError:
-            raise ImportError("Please install SciPy: pip install scipy")
-        nonzero_ids = np.where(pitch != 0)[0]
-        interp_fn = interp1d(
-            nonzero_ids,
-            pitch[nonzero_ids],
-            fill_value=(pitch[nonzero_ids[0]], pitch[nonzero_ids[-1]]),
-            bounds_error=False,
-        )
-        pitch = interp_fn(np.arange(0, len(pitch)))
-        d_cumsum = np.cumsum(np.concatenate([np.array([0]), phoneme_durations]))
-        pitch = np.array(
-            [
-                np.mean(pitch[d_cumsum[i-1]: d_cumsum[i]])
-                for i in range(1, len(d_cumsum))
-            ]
-        )
-        assert len(pitch) == len(phoneme_durations)
-
-    if log_scale:
-        pitch = np.log(pitch + 1)
-
-    if output_path is not None:
-        np.save(output_path.as_posix(), pitch)
-    else:
-        return pitch
-
-
-def extract_energy(
-        waveform: torch.Tensor, output_path: Optional[Path] = None,
-        hop_length: int = 256, n_fft: int = 1024, log_scale: bool = True,
-        phoneme_durations: Optional[List[int]] = None
-):
-    if output_path is not None and output_path.is_file():
-        return
-
-    assert len(waveform.shape) == 2 and waveform.shape[0] == 1
-    waveform = waveform.view(1, 1, waveform.shape[1])
-    waveform = F.pad(
-        waveform.unsqueeze(1), [n_fft // 2, n_fft // 2, 0, 0],
-        mode="reflect"
-    )
-    waveform = waveform.squeeze(1)
-
-    fourier_basis = np.fft.fft(np.eye(n_fft))
-    cutoff = int((n_fft / 2 + 1))
-    fourier_basis = np.vstack(
-        [np.real(fourier_basis[:cutoff, :]),
-         np.imag(fourier_basis[:cutoff, :])]
-    )
-
-    forward_basis = torch.FloatTensor(fourier_basis[:, None, :])
-    forward_transform = F.conv1d(
-        waveform, forward_basis, stride=hop_length, padding=0
-    )
-
-    real_part = forward_transform[:, :cutoff, :]
-    imag_part = forward_transform[:, cutoff:, :]
-    magnitude = torch.sqrt(real_part ** 2 + imag_part ** 2)
-    energy = torch.norm(magnitude, dim=1).squeeze(0).numpy()
-
-    if phoneme_durations is not None:
-        energy = trim_or_pad_to_target_length(energy, sum(phoneme_durations))
-        d_cumsum = np.cumsum(np.concatenate([np.array([0]), phoneme_durations]))
-        energy = np.array(
-            [
-                np.mean(energy[d_cumsum[i - 1]: d_cumsum[i]])
-                for i in range(1, len(d_cumsum))
-            ]
-        )
-        assert len(energy) == len(phoneme_durations)
-
-    if log_scale:
-        energy = np.log(energy + 1)
-
-    if output_path is not None:
-        np.save(output_path.as_posix(), energy)
-    else:
-        return energy
-
-
-def get_global_cmvn(feature_root: Path, output_path: Optional[Path] = None):
-    mean_x, mean_x2, n_frames = None, None, 0
-    feature_paths = feature_root.glob("*.npy")
-    for p in tqdm(feature_paths):
-        with open(p, 'rb') as f:
-            frames = np.load(f).squeeze()
-
-        n_frames += frames.shape[0]
-
-        cur_mean_x = frames.sum(axis=0)
-        if mean_x is None:
-            mean_x = cur_mean_x
-        else:
-            mean_x += cur_mean_x
-
-        cur_mean_x2 = (frames ** 2).sum(axis=0)
-        if mean_x2 is None:
-            mean_x2 = cur_mean_x2
-        else:
-            mean_x2 += cur_mean_x2
-
-    mean_x /= n_frames
-    mean_x2 /= n_frames
-    var_x = mean_x2 - mean_x ** 2
-    std_x = np.sqrt(np.maximum(var_x, 1e-10))
-
-    if output_path is not None:
-        with open(output_path, 'wb') as f:
-            np.savez(f, mean=mean_x, std=std_x)
-    else:
-        return {"mean": mean_x, "std": std_x}
-
-
-def ipa_phonemize(text, lang="en-us", use_g2p=False):
-    if use_g2p:
-        assert lang == "en-us", "g2pE phonemizer only works for en-us"
-        try:
-            from g2p_en import G2p
-            g2p = G2p()
-            return " ".join("|" if p == " " else p for p in g2p(text))
-        except ImportError:
-            raise ImportError(
-                "Please install phonemizer: pip install g2p_en"
-            )
-    else:
-        try:
-            from phonemizer import phonemize
-            from phonemizer.separator import Separator
-            return phonemize(
-                text, backend='espeak', language=lang,
-                separator=Separator(word="| ", phone=" ")
-            )
-        except ImportError:
-            raise ImportError(
-                "Please install phonemizer: pip install phonemizer"
-            )
-
-
-@dataclass
-class ForceAlignmentInfo(object):
-    tokens: List[str]
-    frame_durations: List[int]
-    start_sec: Optional[float]
-    end_sec: Optional[float]
-
-
-def get_mfa_alignment_by_sample_id(
-        textgrid_zip_path: str, sample_id: str, sample_rate: int,
-        hop_length: int, silence_phones: List[str] = ("sil", "sp", "spn")
-) -> ForceAlignmentInfo:
-    try:
-        import tgt
-    except ImportError:
-        raise ImportError("Please install TextGridTools: pip install tgt")
-
-    filename = f"{sample_id}.TextGrid"
-    out_root = Path(tempfile.gettempdir())
-    tgt_path = out_root / filename
-    with zipfile.ZipFile(textgrid_zip_path) as f_zip:
-        f_zip.extract(filename, path=out_root)
-    textgrid = tgt.io.read_textgrid(tgt_path.as_posix())
-    os.remove(tgt_path)
-
-    phones, frame_durations = [], []
-    start_sec, end_sec, end_idx = 0, 0, 0
-    for t in textgrid.get_tier_by_name("phones")._objects:
-        s, e, p = t.start_time, t.end_time, t.text
-        # Trim leading silences
-        if len(phones) == 0:
-            if p in silence_phones:
-                continue
-            else:
-                start_sec = s
-        phones.append(p)
-        if p not in silence_phones:
-            end_sec = e
-            end_idx = len(phones)
-        r = sample_rate / hop_length
-        frame_durations.append(int(np.round(e * r) - np.round(s * r)))
-    # Trim tailing silences
-    phones = phones[:end_idx]
-    frame_durations = frame_durations[:end_idx]
-
-    return ForceAlignmentInfo(
-        tokens=phones, frame_durations=frame_durations, start_sec=start_sec,
-        end_sec=end_sec
-    )
-
-
-def get_mfa_alignment(
-        textgrid_zip_path: str, sample_ids: List[str], sample_rate: int,
-        hop_length: int
-) -> Dict[str, ForceAlignmentInfo]:
-    return {
-        i: get_mfa_alignment_by_sample_id(
-            textgrid_zip_path, i, sample_rate, hop_length
-        ) for i in tqdm(sample_ids)
-    }
-
-
-def get_unit_alignment(
-        id_to_unit_tsv_path: str, sample_ids: List[str]
-) -> Dict[str, ForceAlignmentInfo]:
-    id_to_units = {
-        e["id"]: e["units"] for e in load_tsv_to_dicts(id_to_unit_tsv_path)
-    }
-    id_to_units = {i: id_to_units[i].split() for i in sample_ids}
-    id_to_units_collapsed = {
-        i: [uu for uu, _ in groupby(u)] for i, u in id_to_units.items()
-    }
-    id_to_durations = {
-        i: [len(list(g)) for _, g in groupby(u)] for i, u in id_to_units.items()
-    }
-
-    return {
-        i: ForceAlignmentInfo(
-            tokens=id_to_units_collapsed[i], frame_durations=id_to_durations[i],
-            start_sec=None, end_sec=None
-        )
-        for i in sample_ids
-    }
diff --git a/spaces/OFA-Sys/OFA-vqa/fairseq/fairseq/benchmark/dummy_masked_lm.py b/spaces/OFA-Sys/OFA-vqa/fairseq/fairseq/benchmark/dummy_masked_lm.py
deleted file mode 100644
index 12b9c5d0f55993bf8750564882a351fc3f8055f0..0000000000000000000000000000000000000000
--- a/spaces/OFA-Sys/OFA-vqa/fairseq/fairseq/benchmark/dummy_masked_lm.py
+++ /dev/null
@@ -1,94 +0,0 @@
-# Copyright (c) Facebook, Inc. and its affiliates.
-#
-# This source code is licensed under the MIT license found in the
-# LICENSE file in the root directory of this source tree.
-
-import logging
-from dataclasses import dataclass, field
-from typing import Optional
-
-import torch
-from omegaconf import II
-
-from .dummy_dataset import DummyDataset
-from fairseq.data import Dictionary
-from fairseq.dataclass import FairseqDataclass
-from fairseq.tasks import FairseqTask, register_task
-
-logger = logging.getLogger(__name__)
-
-
-@dataclass
-class DummyMaskedLMConfig(FairseqDataclass):
-    dict_size: int = 49996
-    dataset_size: int = 100000
-    tokens_per_sample: int = field(
-        default=512,
-        metadata={
-            "help": "max number of total tokens over all"
-            " segments per sample for BERT dataset"
-        },
-    )
-    batch_size: Optional[int] = II("dataset.batch_size")
-    max_tokens: Optional[int] = II("dataset.max_tokens")
-    max_target_positions: int = II("task.tokens_per_sample")
-
-
-@register_task("dummy_masked_lm", dataclass=DummyMaskedLMConfig)
-class DummyMaskedLMTask(FairseqTask):
-    def __init__(self, cfg: DummyMaskedLMConfig):
-        super().__init__(cfg)
-
-        self.dictionary = Dictionary()
-        for i in range(cfg.dict_size):
-            self.dictionary.add_symbol("word{}".format(i))
-        logger.info("dictionary: {} types".format(len(self.dictionary)))
-        # add mask token
-        self.mask_idx = self.dictionary.add_symbol("<mask>")
-        self.dictionary.pad_to_multiple_(8)  # often faster if divisible by 8
-
-        mask_idx = 0
-        pad_idx = 1
-        seq = torch.arange(cfg.tokens_per_sample) + pad_idx + 1
-        mask = torch.arange(2, cfg.tokens_per_sample, 7)  # ~15%
-        src = seq.clone()
-        src[mask] = mask_idx
-        tgt = torch.full_like(seq, pad_idx)
-        tgt[mask] = seq[mask]
-
-        self.dummy_src = src
-        self.dummy_tgt = tgt
-
-    def load_dataset(self, split, epoch=1, combine=False, **kwargs):
-        """Load a given dataset split.
-        Args:
-            split (str): name of the split (e.g., train, valid, test)
-        """
-        if self.cfg.batch_size is not None:
-            bsz = self.cfg.batch_size
-        else:
-            bsz = max(1, self.cfg.max_tokens // self.cfg.tokens_per_sample)
-        self.datasets[split] = DummyDataset(
-            {
-                "id": 1,
-                "net_input": {
-                    "src_tokens": torch.stack([self.dummy_src for _ in range(bsz)]),
-                    "src_lengths": torch.full(
-                        (bsz,), self.cfg.tokens_per_sample, dtype=torch.long
-                    ),
-                },
-                "target": torch.stack([self.dummy_tgt for _ in range(bsz)]),
-                "nsentences": bsz,
-                "ntokens": bsz * self.cfg.tokens_per_sample,
-            },
-            num_items=self.cfg.dataset_size,
-            item_size=self.cfg.tokens_per_sample,
-        )
-
-    @property
-    def source_dictionary(self):
-        return self.dictionary
-
-    @property
-    def target_dictionary(self):
-        return self.dictionary
diff --git a/spaces/ORI-Muchim/ONFIRETTS/utils.py b/spaces/ORI-Muchim/ONFIRETTS/utils.py
deleted file mode 100644
index 4cb5b43d0ca2bae496e7871b2094f2ffb26ab642..0000000000000000000000000000000000000000
--- a/spaces/ORI-Muchim/ONFIRETTS/utils.py
+++ /dev/null
@@ -1,226 +0,0 @@
-import os
-import glob
-import sys
-import argparse
-import logging
-import json
-import subprocess
-import numpy as np
-from scipy.io.wavfile import read
-import torch
-
-MATPLOTLIB_FLAG = False
-
-logging.basicConfig(stream=sys.stdout, level=logging.ERROR)
-logger = logging
-
-
-def load_checkpoint(checkpoint_path, model, optimizer=None):
-    assert os.path.isfile(checkpoint_path)
-    checkpoint_dict = torch.load(checkpoint_path, map_location='cpu')
-    iteration = checkpoint_dict['iteration']
-    learning_rate = checkpoint_dict['learning_rate']
-    if optimizer is not None:
-        optimizer.load_state_dict(checkpoint_dict['optimizer'])
-    saved_state_dict = checkpoint_dict['model']
-    if hasattr(model, 'module'):
-        state_dict = model.module.state_dict()
-    else:
-        state_dict = model.state_dict()
-    new_state_dict = {}
-    for k, v in state_dict.items():
-        try:
-            new_state_dict[k] = saved_state_dict[k]
-        except:
-            logger.info("%s is not in the checkpoint" % k)
-            new_state_dict[k] = v
-    if hasattr(model, 'module'):
-        model.module.load_state_dict(new_state_dict)
-    else:
-        model.load_state_dict(new_state_dict)
-    logger.info("Loaded checkpoint '{}' (iteration {})".format(
-        checkpoint_path, iteration))
-    return model, optimizer, learning_rate, iteration
-
-
-def plot_spectrogram_to_numpy(spectrogram):
-    global MATPLOTLIB_FLAG
-    if not MATPLOTLIB_FLAG:
-        import matplotlib
-        matplotlib.use("Agg")
-        MATPLOTLIB_FLAG = True
-        mpl_logger = logging.getLogger('matplotlib')
-        mpl_logger.setLevel(logging.WARNING)
-    import matplotlib.pylab as plt
-    import numpy as np
-
-    fig, ax = plt.subplots(figsize=(10, 2))
-    im = ax.imshow(spectrogram, aspect="auto", origin="lower",
-                   interpolation='none')
-    plt.colorbar(im, ax=ax)
-    plt.xlabel("Frames")
-    plt.ylabel("Channels")
-    plt.tight_layout()
-
-    fig.canvas.draw()
-    data = np.fromstring(fig.canvas.tostring_rgb(), dtype=np.uint8, sep='')
-    data = data.reshape(fig.canvas.get_width_height()[::-1] + (3,))
-    plt.close()
-    return data
-
-
-def plot_alignment_to_numpy(alignment, info=None):
-    global MATPLOTLIB_FLAG
-    if not MATPLOTLIB_FLAG:
-        import matplotlib
-        matplotlib.use("Agg")
-        MATPLOTLIB_FLAG = True
-        mpl_logger = logging.getLogger('matplotlib')
-        mpl_logger.setLevel(logging.WARNING)
-    import matplotlib.pylab as plt
-    import numpy as np
-
-    fig, ax = plt.subplots(figsize=(6, 4))
-    im = ax.imshow(alignment.transpose(), aspect='auto', origin='lower',
-                   interpolation='none')
-    fig.colorbar(im, ax=ax)
-    xlabel = 'Decoder timestep'
-    if info is not None:
-        xlabel += '\n\n' + info
-    plt.xlabel(xlabel)
-    plt.ylabel('Encoder timestep')
-    plt.tight_layout()
-
-    fig.canvas.draw()
-    data = np.fromstring(fig.canvas.tostring_rgb(), dtype=np.uint8, sep='')
-    data = data.reshape(fig.canvas.get_width_height()[::-1] + (3,))
-    plt.close()
-    return data
-
-
-def load_wav_to_torch(full_path):
-    sampling_rate, data = read(full_path)
-    return torch.FloatTensor(data.astype(np.float32)), sampling_rate
-
-
-def load_filepaths_and_text(filename, split="|"):
-    with open(filename, encoding='utf-8') as f:
-        filepaths_and_text = [line.strip().split(split) for line in f]
-    return filepaths_and_text
-
-
-def get_hparams(init=True):
-    parser = argparse.ArgumentParser()
-    parser.add_argument('-c', '--config', type=str, default="./configs/base.json",
-                        help='JSON file for configuration')
-    parser.add_argument('-m', '--model', type=str, required=True,
-                        help='Model name')
-
-    args = parser.parse_args()
-    model_dir = os.path.join("./logs", args.model)
-
-    if not os.path.exists(model_dir):
-        os.makedirs(model_dir)
-
-    config_path = args.config
-    config_save_path = os.path.join(model_dir, "config.json")
-    if init:
-        with open(config_path, "r") as f:
-            data = f.read()
-        with open(config_save_path, "w") as f:
-            f.write(data)
-    else:
-        with open(config_save_path, "r") as f:
-            data = f.read()
-    config = json.loads(data)
-
-    hparams = HParams(**config)
-    hparams.model_dir = model_dir
-    return hparams
-
-
-def get_hparams_from_dir(model_dir):
-    config_save_path = os.path.join(model_dir, "config.json")
-    with open(config_save_path, "r") as f:
-        data = f.read()
-    config = json.loads(data)
-
-    hparams = HParams(**config)
-    hparams.model_dir = model_dir
-    return hparams
-
-
-def get_hparams_from_file(config_path):
-    with open(config_path, "r", encoding="utf-8") as f:
-        data = f.read()
-    config = json.loads(data)
-
-    hparams = HParams(**config)
-    return hparams
-
-
-def check_git_hash(model_dir):
-    source_dir = os.path.dirname(os.path.realpath(__file__))
-    if not os.path.exists(os.path.join(source_dir, ".git")):
-        logger.warn("{} is not a git repository, therefore hash value comparison will be ignored.".format(
-            source_dir
-        ))
-        return
-
-    cur_hash = subprocess.getoutput("git rev-parse HEAD")
-
-    path = os.path.join(model_dir, "githash")
-    if os.path.exists(path):
-        saved_hash = open(path).read()
-        if saved_hash != cur_hash:
-            logger.warn("git hash values are different. {}(saved) != {}(current)".format(
-                saved_hash[:8], cur_hash[:8]))
-    else:
-        open(path, "w").write(cur_hash)
-
-
-def get_logger(model_dir, filename="train.log"):
-    global logger
-    logger = logging.getLogger(os.path.basename(model_dir))
-    logger.setLevel(logging.DEBUG)
-
-    formatter = logging.Formatter("%(asctime)s\t%(name)s\t%(levelname)s\t%(message)s")
-    if not os.path.exists(model_dir):
-        os.makedirs(model_dir)
-    h = logging.FileHandler(os.path.join(model_dir, filename))
-    h.setLevel(logging.DEBUG)
-    h.setFormatter(formatter)
-    logger.addHandler(h)
-    return logger
-
-
-class HParams():
-    def __init__(self, **kwargs):
-        for k, v in kwargs.items():
-            if type(v) == dict:
-                v = HParams(**v)
-            self[k] = v
-
-    def keys(self):
-        return self.__dict__.keys()
-
-    def items(self):
-        return self.__dict__.items()
-
-    def values(self):
-        return self.__dict__.values()
-
-    def __len__(self):
-        return len(self.__dict__)
-
-    def __getitem__(self, key):
-        return getattr(self, key)
-
-    def __setitem__(self, key, value):
-        return setattr(self, key, value)
-
-    def __contains__(self, key):
-        return key in self.__dict__
-
-    def __repr__(self):
-        return self.__dict__.__repr__()
diff --git a/spaces/Omnibus/Video-Diffusion-WebUI/video_diffusion/tuneavideo/models/unet.py b/spaces/Omnibus/Video-Diffusion-WebUI/video_diffusion/tuneavideo/models/unet.py
deleted file mode 100644
index d0cf2d5d1bd6605ea8cb0a86fd08d6466d5aba6f..0000000000000000000000000000000000000000
--- a/spaces/Omnibus/Video-Diffusion-WebUI/video_diffusion/tuneavideo/models/unet.py
+++ /dev/null
@@ -1,437 +0,0 @@
-# Adapted from https://github.com/huggingface/diffusers/blob/main/src/diffusers/models/unet_2d_condition.py
-
-import json
-import os
-from dataclasses import dataclass
-from typing import List, Optional, Tuple, Union
-
-import torch
-import torch.nn as nn
-import torch.utils.checkpoint
-from diffusers.configuration_utils import ConfigMixin, register_to_config
-from diffusers.models.embeddings import TimestepEmbedding, Timesteps
-from diffusers.models.modeling_utils import ModelMixin
-from diffusers.utils import BaseOutput, logging
-
-from .resnet import InflatedConv3d
-from .unet_blocks import (
-    CrossAttnDownBlock3D,
-    CrossAttnUpBlock3D,
-    DownBlock3D,
-    UNetMidBlock3DCrossAttn,
-    UpBlock3D,
-    get_down_block,
-    get_up_block,
-)
-
-logger = logging.get_logger(__name__)  # pylint: disable=invalid-name
-
-
-@dataclass
-class UNet3DConditionOutput(BaseOutput):
-    sample: torch.FloatTensor
-
-
-class UNet3DConditionModel(ModelMixin, ConfigMixin):
-    _supports_gradient_checkpointing = True
-
-    @register_to_config
-    def __init__(
-        self,
-        sample_size: Optional[int] = None,
-        in_channels: int = 4,
-        out_channels: int = 4,
-        center_input_sample: bool = False,
-        flip_sin_to_cos: bool = True,
-        freq_shift: int = 0,
-        down_block_types: Tuple[str] = (
-            "CrossAttnDownBlock3D",
-            "CrossAttnDownBlock3D",
-            "CrossAttnDownBlock3D",
-            "DownBlock3D",
-        ),
-        mid_block_type: str = "UNetMidBlock3DCrossAttn",
-        up_block_types: Tuple[str] = ("UpBlock3D", "CrossAttnUpBlock3D", "CrossAttnUpBlock3D", "CrossAttnUpBlock3D"),
-        only_cross_attention: Union[bool, Tuple[bool]] = False,
-        block_out_channels: Tuple[int] = (320, 640, 1280, 1280),
-        layers_per_block: int = 2,
-        downsample_padding: int = 1,
-        mid_block_scale_factor: float = 1,
-        act_fn: str = "silu",
-        norm_num_groups: int = 32,
-        norm_eps: float = 1e-5,
-        cross_attention_dim: int = 1280,
-        attention_head_dim: Union[int, Tuple[int]] = 8,
-        dual_cross_attention: bool = False,
-        use_linear_projection: bool = False,
-        class_embed_type: Optional[str] = None,
-        num_class_embeds: Optional[int] = None,
-        upcast_attention: bool = False,
-        resnet_time_scale_shift: str = "default",
-    ):
-        super().__init__()
-
-        self.sample_size = sample_size
-        time_embed_dim = block_out_channels[0] * 4
-
-        # input
-        self.conv_in = InflatedConv3d(in_channels, block_out_channels[0], kernel_size=3, padding=(1, 1))
-
-        # time
-        self.time_proj = Timesteps(block_out_channels[0], flip_sin_to_cos, freq_shift)
-        timestep_input_dim = block_out_channels[0]
-
-        self.time_embedding = TimestepEmbedding(timestep_input_dim, time_embed_dim)
-
-        # class embedding
-        if class_embed_type is None and num_class_embeds is not None:
-            self.class_embedding = nn.Embedding(num_class_embeds, time_embed_dim)
-        elif class_embed_type == "timestep":
-            self.class_embedding = TimestepEmbedding(timestep_input_dim, time_embed_dim)
-        elif class_embed_type == "identity":
-            self.class_embedding = nn.Identity(time_embed_dim, time_embed_dim)
-        else:
-            self.class_embedding = None
-
-        self.down_blocks = nn.ModuleList([])
-        self.mid_block = None
-        self.up_blocks = nn.ModuleList([])
-
-        if isinstance(only_cross_attention, bool):
-            only_cross_attention = [only_cross_attention] * len(down_block_types)
-
-        if isinstance(attention_head_dim, int):
-            attention_head_dim = (attention_head_dim,) * len(down_block_types)
-
-        # down
-        output_channel = block_out_channels[0]
-        for i, down_block_type in enumerate(down_block_types):
-            input_channel = output_channel
-            output_channel = block_out_channels[i]
-            is_final_block = i == len(block_out_channels) - 1
-
-            down_block = get_down_block(
-                down_block_type,
-                num_layers=layers_per_block,
-                in_channels=input_channel,
-                out_channels=output_channel,
-                temb_channels=time_embed_dim,
-                add_downsample=not is_final_block,
-                resnet_eps=norm_eps,
-                resnet_act_fn=act_fn,
-                resnet_groups=norm_num_groups,
-                cross_attention_dim=cross_attention_dim,
-                attn_num_head_channels=attention_head_dim[i],
-                downsample_padding=downsample_padding,
-                dual_cross_attention=dual_cross_attention,
-                use_linear_projection=use_linear_projection,
-                only_cross_attention=only_cross_attention[i],
-                upcast_attention=upcast_attention,
-                resnet_time_scale_shift=resnet_time_scale_shift,
-            )
-            self.down_blocks.append(down_block)
-
-        # mid
-        if mid_block_type == "UNetMidBlock3DCrossAttn":
-            self.mid_block = UNetMidBlock3DCrossAttn(
-                in_channels=block_out_channels[-1],
-                temb_channels=time_embed_dim,
-                resnet_eps=norm_eps,
-                resnet_act_fn=act_fn,
-                output_scale_factor=mid_block_scale_factor,
-                resnet_time_scale_shift=resnet_time_scale_shift,
-                cross_attention_dim=cross_attention_dim,
-                attn_num_head_channels=attention_head_dim[-1],
-                resnet_groups=norm_num_groups,
-                dual_cross_attention=dual_cross_attention,
-                use_linear_projection=use_linear_projection,
-                upcast_attention=upcast_attention,
-            )
-        else:
-            raise ValueError(f"unknown mid_block_type : {mid_block_type}")
-
-        # count how many layers upsample the videos
-        self.num_upsamplers = 0
-
-        # up
-        reversed_block_out_channels = list(reversed(block_out_channels))
-        reversed_attention_head_dim = list(reversed(attention_head_dim))
-        only_cross_attention = list(reversed(only_cross_attention))
-        output_channel = reversed_block_out_channels[0]
-        for i, up_block_type in enumerate(up_block_types):
-            is_final_block = i == len(block_out_channels) - 1
-
-            prev_output_channel = output_channel
-            output_channel = reversed_block_out_channels[i]
-            input_channel = reversed_block_out_channels[min(i + 1, len(block_out_channels) - 1)]
-
-            # add upsample block for all BUT final layer
-            if not is_final_block:
-                add_upsample = True
-                self.num_upsamplers += 1
-            else:
-                add_upsample = False
-
-            up_block = get_up_block(
-                up_block_type,
-                num_layers=layers_per_block + 1,
-                in_channels=input_channel,
-                out_channels=output_channel,
-                prev_output_channel=prev_output_channel,
-                temb_channels=time_embed_dim,
-                add_upsample=add_upsample,
-                resnet_eps=norm_eps,
-                resnet_act_fn=act_fn,
-                resnet_groups=norm_num_groups,
-                cross_attention_dim=cross_attention_dim,
-                attn_num_head_channels=reversed_attention_head_dim[i],
-                dual_cross_attention=dual_cross_attention,
-                use_linear_projection=use_linear_projection,
-                only_cross_attention=only_cross_attention[i],
-                upcast_attention=upcast_attention,
-                resnet_time_scale_shift=resnet_time_scale_shift,
-            )
-            self.up_blocks.append(up_block)
-            prev_output_channel = output_channel
-
-        # out
-        self.conv_norm_out = nn.GroupNorm(num_channels=block_out_channels[0], num_groups=norm_num_groups, eps=norm_eps)
-        self.conv_act = nn.SiLU()
-        self.conv_out = InflatedConv3d(block_out_channels[0], out_channels, kernel_size=3, padding=1)
-
-    def set_attention_slice(self, slice_size):
-        r"""
-        Enable sliced attention computation.
-
-        When this option is enabled, the attention module will split the input tensor in slices, to compute attention
-        in several steps. This is useful to save some memory in exchange for a small speed decrease.
-
-        Args:
-            slice_size (`str` or `int` or `list(int)`, *optional*, defaults to `"auto"`):
-                When `"auto"`, halves the input to the attention heads, so attention will be computed in two steps. If
-                `"max"`, maxium amount of memory will be saved by running only one slice at a time. If a number is
-                provided, uses as many slices as `attention_head_dim // slice_size`. In this case, `attention_head_dim`
-                must be a multiple of `slice_size`.
-        """
-        sliceable_head_dims = []
-
-        def fn_recursive_retrieve_slicable_dims(module: torch.nn.Module):
-            if hasattr(module, "set_attention_slice"):
-                sliceable_head_dims.append(module.sliceable_head_dim)
-
-            for child in module.children():
-                fn_recursive_retrieve_slicable_dims(child)
-
-        # retrieve number of attention layers
-        for module in self.children():
-            fn_recursive_retrieve_slicable_dims(module)
-
-        num_slicable_layers = len(sliceable_head_dims)
-
-        if slice_size == "auto":
-            # half the attention head size is usually a good trade-off between
-            # speed and memory
-            slice_size = [dim // 2 for dim in sliceable_head_dims]
-        elif slice_size == "max":
-            # make smallest slice possible
-            slice_size = num_slicable_layers * [1]
-
-        slice_size = num_slicable_layers * [slice_size] if not isinstance(slice_size, list) else slice_size
-
-        if len(slice_size) != len(sliceable_head_dims):
-            raise ValueError(
-                f"You have provided {len(slice_size)}, but {self.config} has {len(sliceable_head_dims)} different"
-                f" attention layers. Make sure to match `len(slice_size)` to be {len(sliceable_head_dims)}."
-            )
-
-        for i in range(len(slice_size)):
-            size = slice_size[i]
-            dim = sliceable_head_dims[i]
-            if size is not None and size > dim:
-                raise ValueError(f"size {size} has to be smaller or equal to {dim}.")
-
-        # Recursively walk through all the children.
-        # Any children which exposes the set_attention_slice method
-        # gets the message
-        def fn_recursive_set_attention_slice(module: torch.nn.Module, slice_size: List[int]):
-            if hasattr(module, "set_attention_slice"):
-                module.set_attention_slice(slice_size.pop())
-
-            for child in module.children():
-                fn_recursive_set_attention_slice(child, slice_size)
-
-        reversed_slice_size = list(reversed(slice_size))
-        for module in self.children():
-            fn_recursive_set_attention_slice(module, reversed_slice_size)
-
-    def _set_gradient_checkpointing(self, module, value=False):
-        if isinstance(module, (CrossAttnDownBlock3D, DownBlock3D, CrossAttnUpBlock3D, UpBlock3D)):
-            module.gradient_checkpointing = value
-
-    def forward(
-        self,
-        sample: torch.FloatTensor,
-        timestep: Union[torch.Tensor, float, int],
-        encoder_hidden_states: torch.Tensor,
-        class_labels: Optional[torch.Tensor] = None,
-        attention_mask: Optional[torch.Tensor] = None,
-        return_dict: bool = True,
-    ) -> Union[UNet3DConditionOutput, Tuple]:
-        r"""
-        Args:
-            sample (`torch.FloatTensor`): (batch, channel, height, width) noisy inputs tensor
-            timestep (`torch.FloatTensor` or `float` or `int`): (batch) timesteps
-            encoder_hidden_states (`torch.FloatTensor`): (batch, sequence_length, feature_dim) encoder hidden states
-            return_dict (`bool`, *optional*, defaults to `True`):
-                Whether or not to return a [`models.unet_2d_condition.UNet2DConditionOutput`] instead of a plain tuple.
-
-        Returns:
-            [`~models.unet_2d_condition.UNet2DConditionOutput`] or `tuple`:
-            [`~models.unet_2d_condition.UNet2DConditionOutput`] if `return_dict` is True, otherwise a `tuple`. When
-            returning a tuple, the first element is the sample tensor.
-        """
-        # By default samples have to be AT least a multiple of the overall upsampling factor.
-        # The overall upsampling factor is equal to 2 ** (# num of upsampling layears).
-        # However, the upsampling interpolation output size can be forced to fit any upsampling size
-        # on the fly if necessary.
-        default_overall_up_factor = 2**self.num_upsamplers
-
-        # upsample size should be forwarded when sample is not a multiple of `default_overall_up_factor`
-        forward_upsample_size = False
-        upsample_size = None
-
-        if any(s % default_overall_up_factor != 0 for s in sample.shape[-2:]):
-            logger.info("Forward upsample size to force interpolation output size.")
-            forward_upsample_size = True
-
-        # prepare attention_mask
-        if attention_mask is not None:
-            attention_mask = (1 - attention_mask.to(sample.dtype)) * -10000.0
-            attention_mask = attention_mask.unsqueeze(1)
-
-        # center input if necessary
-        if self.config.center_input_sample:
-            sample = 2 * sample - 1.0
-
-        # time
-        timesteps = timestep
-        if not torch.is_tensor(timesteps):
-            # This would be a good case for the `match` statement (Python 3.10+)
-            is_mps = sample.device.type == "mps"
-            if isinstance(timestep, float):
-                dtype = torch.float32 if is_mps else torch.float64
-            else:
-                dtype = torch.int32 if is_mps else torch.int64
-            timesteps = torch.tensor([timesteps], dtype=dtype, device=sample.device)
-        elif len(timesteps.shape) == 0:
-            timesteps = timesteps[None].to(sample.device)
-
-        # broadcast to batch dimension in a way that's compatible with ONNX/Core ML
-        timesteps = timesteps.expand(sample.shape[0])
-
-        t_emb = self.time_proj(timesteps)
-
-        # timesteps does not contain any weights and will always return f32 tensors
-        # but time_embedding might actually be running in fp16. so we need to cast here.
-        # there might be better ways to encapsulate this.
-        t_emb = t_emb.to(dtype=self.dtype)
-        emb = self.time_embedding(t_emb)
-
-        if self.class_embedding is not None:
-            if class_labels is None:
-                raise ValueError("class_labels should be provided when num_class_embeds > 0")
-
-            if self.config.class_embed_type == "timestep":
-                class_labels = self.time_proj(class_labels)
-
-            class_emb = self.class_embedding(class_labels).to(dtype=self.dtype)
-            emb = emb + class_emb
-
-        # pre-process
-        sample = self.conv_in(sample)
-
-        # down
-        down_block_res_samples = (sample,)
-        for downsample_block in self.down_blocks:
-            if hasattr(downsample_block, "has_cross_attention") and downsample_block.has_cross_attention:
-                sample, res_samples = downsample_block(
-                    hidden_states=sample,
-                    temb=emb,
-                    encoder_hidden_states=encoder_hidden_states,
-                    attention_mask=attention_mask,
-                )
-            else:
-                sample, res_samples = downsample_block(hidden_states=sample, temb=emb)
-
-            down_block_res_samples += res_samples
-
-        # mid
-        sample = self.mid_block(sample, emb, encoder_hidden_states=encoder_hidden_states, attention_mask=attention_mask)
-
-        # up
-        for i, upsample_block in enumerate(self.up_blocks):
-            is_final_block = i == len(self.up_blocks) - 1
-
-            res_samples = down_block_res_samples[-len(upsample_block.resnets) :]
-            down_block_res_samples = down_block_res_samples[: -len(upsample_block.resnets)]
-
-            # if we have not reached the final block and need to forward the
-            # upsample size, we do it here
-            if not is_final_block and forward_upsample_size:
-                upsample_size = down_block_res_samples[-1].shape[2:]
-
-            if hasattr(upsample_block, "has_cross_attention") and upsample_block.has_cross_attention:
-                sample = upsample_block(
-                    hidden_states=sample,
-                    temb=emb,
-                    res_hidden_states_tuple=res_samples,
-                    encoder_hidden_states=encoder_hidden_states,
-                    upsample_size=upsample_size,
-                    attention_mask=attention_mask,
-                )
-            else:
-                sample = upsample_block(
-                    hidden_states=sample, temb=emb, res_hidden_states_tuple=res_samples, upsample_size=upsample_size
-                )
-        # post-process
-        sample = self.conv_norm_out(sample)
-        sample = self.conv_act(sample)
-        sample = self.conv_out(sample)
-
-        if not return_dict:
-            return (sample,)
-
-        return UNet3DConditionOutput(sample=sample)
-
-    @classmethod
-    def from_pretrained_2d(cls, pretrained_model_path, subfolder=None):
-        if subfolder is not None:
-            pretrained_model_path = os.path.join(pretrained_model_path, subfolder)
-
-        config_file = os.path.join(pretrained_model_path, "config.json")
-        if not os.path.isfile(config_file):
-            raise RuntimeError(f"{config_file} does not exist")
-        with open(config_file, "r") as f:
-            config = json.load(f)
-        config["_class_name"] = cls.__name__
-        config["down_block_types"] = [
-            "CrossAttnDownBlock3D",
-            "CrossAttnDownBlock3D",
-            "CrossAttnDownBlock3D",
-            "DownBlock3D",
-        ]
-        config["up_block_types"] = ["UpBlock3D", "CrossAttnUpBlock3D", "CrossAttnUpBlock3D", "CrossAttnUpBlock3D"]
-
-        from diffusers.utils import WEIGHTS_NAME
-
-        model = cls.from_config(config)
-        model_file = os.path.join(pretrained_model_path, WEIGHTS_NAME)
-        if not os.path.isfile(model_file):
-            raise RuntimeError(f"{model_file} does not exist")
-        state_dict = torch.load(model_file, map_location="cpu")
-        for k, v in model.state_dict().items():
-            if "_temp." in k:
-                state_dict.update({k: v})
-        model.load_state_dict(state_dict)
-
-        return model
diff --git a/spaces/OpenGVLab/InternGPT/iGPT/models/grit_src/grit/modeling/text/text_decoder.py b/spaces/OpenGVLab/InternGPT/iGPT/models/grit_src/grit/modeling/text/text_decoder.py
deleted file mode 100644
index 071baa7a52d21d7132cc492f070cba066d17aa43..0000000000000000000000000000000000000000
--- a/spaces/OpenGVLab/InternGPT/iGPT/models/grit_src/grit/modeling/text/text_decoder.py
+++ /dev/null
@@ -1,672 +0,0 @@
-# Modified by Jialian Wu from
-# https://github.com/microsoft/GenerativeImage2Text/blob/main/generativeimage2text/layers/decoder.py
-# and https://github.com/kdexd/virtex
-from torch import nn
-import torch
-import functools
-from torch.nn import functional as F
-import warnings
-
-
-class TextualHead(nn.Module):
-    def __init__(self,
-                 visual_feature_size: int, vocab_size: int, hidden_size: int):
-        super().__init__()
-        self.visual_feature_size = visual_feature_size
-        self.vocab_size = vocab_size
-        self.hidden_size = hidden_size
-
-    @property
-    def textual_feature_size(self):
-        return self.hidden_size
-
-
-class WordAndPositionalEmbedding(nn.Module):
-    def __init__(
-        self,
-        vocab_size: int,
-        hidden_size: int,
-        dropout: float = 0.0,
-        max_caption_length: int = 30,
-        padding_idx: int = 0,
-    ):
-        super().__init__()
-        self.vocab_size = vocab_size
-        self.padding_idx = padding_idx
-
-        #self.words = nn.Embedding(vocab_size, hidden_size, padding_idx=padding_idx)
-        self.words = nn.Embedding(vocab_size, hidden_size)
-
-        # We provide no "padding index" for positional embeddings. We zero out
-        # the positional embeddings of padded positions as a post-processing.
-        self.positions = nn.Embedding(max_caption_length, hidden_size)
-        self.layer_norm = nn.LayerNorm(
-            hidden_size, eps=1e-8, elementwise_affine=True
-        )
-        self.dropout = nn.Dropout(p=dropout)
-
-    def forward(self, tokens: torch.Tensor):
-        position_indices = self._create_position_indices(tokens)
-
-        # shape: (batch_size, max_caption_length, hidden_size)
-        word_embeddings = self.words(tokens)
-        position_embeddings = self.positions(position_indices)
-
-        # shape: (batch_size, max_caption_length, hidden_size)
-        embeddings = self.layer_norm(word_embeddings + position_embeddings)
-        embeddings = self.dropout(embeddings)
-
-        return embeddings
-
-    @functools.lru_cache(maxsize=128)
-    def _create_position_indices(self, tokens: torch.Tensor):
-
-        # Create position indices of the same size as token indices.
-        batch_size, max_caption_length = tokens.size()
-        positions = torch.arange(
-            max_caption_length, dtype=tokens.dtype, device=tokens.device
-        )
-        # shape: (batch_size, max_caption_length)
-        positions = positions.unsqueeze(0).expand(batch_size, max_caption_length)
-        return positions
-
-
-class BertEncoderAsDecoder(nn.Module):
-    def __init__(self, encoder):
-        super().__init__()
-        self.encoder = encoder
-
-    def forward(self, tgt, memory,
-                tgt_mask=None,
-                tgt_key_padding_mask=None,
-                memory_key_padding_mask=None,
-                tgt_bi_valid_mask=None,
-                encoder_history_states=None,
-                ):
-        assert tgt_key_padding_mask is None, 'not supported'
-        assert tgt_mask.dim() == 2
-        assert tgt_mask.shape[0] == tgt_mask.shape[1]
-        # tgt_mask should always be 0/negative infinity
-        tgt = tgt.transpose(0, 1)
-        memory = memory.transpose(0, 1)
-
-        hidden_states = torch.cat((memory, tgt), dim=1)
-        num_tgt = tgt.shape[1]
-        num_memory = memory.shape[1]
-        device = tgt.device
-        dtype = tgt.dtype
-        top_left = torch.zeros((num_memory, num_memory), device=device, dtype=dtype)
-        top_right = torch.full((num_memory, num_tgt), float('-inf'), device=tgt.device, dtype=dtype,)
-        bottom_left = torch.zeros((num_tgt, num_memory), dtype=dtype, device=tgt_mask.device,)
-        left = torch.cat((top_left, bottom_left), dim=0)
-        right = torch.cat((top_right, tgt_mask.to(dtype)), dim=0)
-
-        full_attention_mask = torch.cat((left, right), dim=1)[None, :]
-
-        if memory_key_padding_mask is None:
-            memory_key_padding_mask = torch.full((memory.shape[0], memory.shape[1]), fill_value=False, device=device)
-        # if it is False, it means valid. That is, it is not a padding
-        assert memory_key_padding_mask.dtype == torch.bool
-        zero_negative_infinity = torch.zeros_like(memory_key_padding_mask, dtype=tgt.dtype)
-        zero_negative_infinity[memory_key_padding_mask] = float('-inf')
-        full_attention_mask = full_attention_mask.expand((memory_key_padding_mask.shape[0], num_memory + num_tgt, num_memory + num_tgt))
-        full_attention_mask = full_attention_mask.clone()
-        origin_left = full_attention_mask[:, :, :num_memory]
-        update = zero_negative_infinity[:, None, :]
-        full_attention_mask[:, :, :num_memory] = origin_left + update
-
-        if tgt_bi_valid_mask is not None:
-            # verify the correctness
-            bs = full_attention_mask.shape[0]
-            # during inference, tgt_bi_valid_mask's length is not changed, but
-            # num_tgt can be increased
-            max_valid_target = tgt_bi_valid_mask.shape[1]
-            mask = tgt_bi_valid_mask[:, None, :].expand((bs, num_memory+num_tgt, max_valid_target))
-            full_attention_mask[:, :, num_memory:(num_memory+max_valid_target)][mask] = 0
-
-        # add axis for multi-head
-        full_attention_mask = full_attention_mask[:, None, :, :]
-
-        if encoder_history_states is None:
-            result = self.encoder(
-                hidden_states=hidden_states,
-                attention_mask=full_attention_mask,
-                encoder_history_states=encoder_history_states,
-            )
-            result = list(result)
-            result[0] = result[0][:, num_memory:].transpose(0, 1)
-            if self.encoder.output_hidden_states:
-                return result[0], result[1]
-            else:
-                # make it back-compatible
-                return result[0]
-        else:
-            encoder_out = self.encoder(
-                hidden_states=hidden_states[:, -1:],
-                attention_mask=full_attention_mask[:, :, -1:],
-                encoder_history_states=encoder_history_states,
-            )
-            result = encoder_out[0].transpose(0, 1)
-            if self.encoder.output_hidden_states:
-                return result, encoder_out[1]
-            else:
-                return result
-
-
-def create_transformer(decoder_type, norm_type,
-                   textual_feature_size,
-                   attention_heads,
-                   feedforward_size,
-                   dropout,
-                   num_layers,
-                   output_hidden_states=False,
-                   use_mlp_wrapper=None,
-                   use_act_checkpoint=True,
-                   ):
-    assert norm_type in ['post', 'pre']
-    if decoder_type is None:
-        LayerClass = (
-            nn.TransformerDecoderLayer
-            if norm_type == "post"
-            else PreNormTransformerDecoderLayer
-        )
-        _layer = LayerClass(
-            textual_feature_size,
-            attention_heads,
-            dim_feedforward=feedforward_size,
-            dropout=dropout,
-            activation="gelu",
-        )
-        return nn.TransformerDecoder(_layer, num_layers)
-    elif decoder_type == 'bert_en':
-        from .modeling_bert import BertConfig, BertEncoder
-        config = BertConfig(
-            vocab_size_or_config_json_file=30522,
-            hidden_size=textual_feature_size,
-            num_hidden_layers=num_layers,
-            num_attention_heads=attention_heads,
-            intermediate_size=feedforward_size,
-            hidden_act="gelu",
-            hidden_dropout_prob=0.1,
-            attention_probs_dropout_prob=0.1,
-            layer_norm_eps=1e-12,
-        )
-        config.pre_norm = (norm_type == 'pre')
-        config.use_mlp_wrapper = use_mlp_wrapper
-        config.output_hidden_states = output_hidden_states
-        encoder = BertEncoder(config, use_act_checkpoint=use_act_checkpoint)
-        return BertEncoderAsDecoder(encoder)
-
-
-class PreNormTransformerDecoderLayer(nn.TransformerDecoderLayer):
-    def forward(self, tgt, memory, tgt_mask=None, memory_mask=None,
-                tgt_key_padding_mask=None, memory_key_padding_mask=None):
-        # fmt: off
-        # We use the members (modules) from super-class, just the order of
-        # operations is changed here. First layernorm, then attention.
-        tgt2 = self.norm1(tgt)
-        tgt2, _ = self.self_attn(
-            tgt2, tgt2, tgt2, attn_mask=tgt_mask,
-            key_padding_mask=tgt_key_padding_mask
-        )
-        tgt = tgt + self.dropout1(tgt2)
-
-        # Layernorm first, then decoder attention.
-        tgt2 = self.norm2(tgt)
-        tgt2, _ = self.multihead_attn(
-            tgt2, memory, memory, attn_mask=memory_mask,
-            key_padding_mask=memory_key_padding_mask
-        )
-        tgt = tgt + self.dropout2(tgt2)
-
-        # Layernorm first, then transformation through feedforward network.
-        tgt2 = self.norm3(tgt)
-        tgt2 = self.linear2(self.dropout(self.activation(self.linear1(tgt2))))
-        tgt = tgt + self.dropout3(tgt2)
-        return tgt
-
-
-class TransformerDecoderTextualHead(TextualHead):
-    def __init__(
-        self,
-        object_feature_size: int,
-        vocab_size: int,
-        hidden_size: int,
-        num_layers: int,
-        attention_heads: int,
-        feedforward_size: int,
-        dropout: float = 0.1,
-        norm_type: str = "post",
-        mask_future_positions: bool = True,
-        max_caption_length: int = 1024,
-        padding_idx: int = 0,
-        decoder_type=None,
-        not_tie_weight=None,
-        output_hidden_states=None,
-        use_mlp_wrapper=None,
-        use_act_checkpoint=True,
-    ):
-        super().__init__(object_feature_size, vocab_size, hidden_size)
-        self.num_layers = num_layers
-        self.attention_heads = attention_heads
-        self.feedforward_size = feedforward_size
-        self.dropout = dropout
-        assert mask_future_positions
-        self.padding_idx = padding_idx
-
-        self.object_feature_projection = nn.Sequential(
-            nn.Linear(object_feature_size, self.textual_feature_size),
-            nn.LayerNorm(self.textual_feature_size))
-
-        self.embedding = WordAndPositionalEmbedding(
-            self.vocab_size,
-            self.textual_feature_size,
-            dropout=dropout,
-            max_caption_length=max_caption_length,
-            padding_idx=padding_idx,
-        )
-        self.transformer = create_transformer(
-            decoder_type=decoder_type,
-            norm_type=norm_type,
-            textual_feature_size=self.textual_feature_size,
-            attention_heads=self.attention_heads,
-            feedforward_size=self.feedforward_size,
-            dropout=dropout,
-            num_layers=self.num_layers,
-            output_hidden_states=output_hidden_states,
-            use_mlp_wrapper=use_mlp_wrapper,
-            use_act_checkpoint=use_act_checkpoint,
-        )
-        self.apply(self._init_weights)
-
-        # Create an output linear layer and tie the input and output word
-        # embeddings to reduce parametejs.
-        self.output = nn.Linear(self.textual_feature_size, vocab_size)
-        if not not_tie_weight:
-            self.output.weight = self.embedding.words.weight
-
-    @staticmethod
-    def _init_weights(module):
-        """Initialize weights like BERT - N(0.0, 0.02), bias = 0."""
-
-        if isinstance(module, nn.Linear):
-            module.weight.data.normal_(mean=0.0, std=0.02)
-        elif isinstance(module, nn.MultiheadAttention):
-            module.in_proj_weight.data.normal_(mean=0.0, std=0.02)
-            module.out_proj.weight.data.normal_(mean=0.0, std=0.02)
-        elif isinstance(module, nn.Embedding):
-            module.weight.data.normal_(mean=0.0, std=0.02)
-            if module.padding_idx is not None:
-                module.weight.data[module.padding_idx].zero_()
-
-    def forward(
-        self,
-        hidden_states,
-        text_tokens,
-    ):
-        projected_object_features = self.object_feature_projection(hidden_states) if hidden_states is not None else None
-        batch_size, max_text_length = text_tokens.size()
-        text_embeddings = self.embedding(text_tokens)
-
-        # An additive mask for masking the future (one direction).
-        uni_mask_zero_neg = self._generate_future_mask(
-            max_text_length, text_embeddings.dtype, text_embeddings.device
-        )
-
-        # We transpose the first two dimensions of tokens embeddings and visual
-        # features, as required by decoder.
-        text_embeddings = text_embeddings.transpose(0, 1)
-
-        projected_object_features = projected_object_features.transpose(0, 1)
-
-        # if transformer here is the pytorch/decoder, there is no chance, the
-        # output is always tensor
-        trans_out = self.transformer(
-            text_embeddings,
-            projected_object_features,
-            tgt_mask=uni_mask_zero_neg,
-        )
-        if isinstance(trans_out, tuple):
-            textual_features = trans_out[0]
-        else:
-            assert isinstance(trans_out, torch.Tensor)
-            textual_features = trans_out
-        # Undo the transpose and bring batch to dim 0.
-        # shape: (batch_size, max_caption_length, hidden_size)
-        textual_features = textual_features.transpose(0, 1)
-
-        # shape: (batch_size, max_caption_length, vocab_size)
-        output_logits = self.output(textual_features)
-        if isinstance(trans_out, tuple):
-            return output_logits, trans_out[1]
-        else:
-            return output_logits
-
-    def _generate_future_mask(
-        self, size: int, dtype: torch.dtype, device: torch.device
-    ):
-        # Default mask is for forward direction. Flip for backward direction.
-        mask = torch.triu(
-            torch.ones(size, size, device=device, dtype=dtype), diagonal=1
-        )
-        mask = mask.masked_fill(mask == 1, float("-inf"))
-        return mask
-
-
-class AutoRegressiveBeamSearch(object):
-    def __init__(
-        self,
-        end_token_id: int,
-        max_steps: int = 50,
-        beam_size: int = 5,
-        objectdet=True,
-        per_node_beam_size: int = 2,
-    ):
-        self._eos_index = end_token_id
-        self.max_steps = max_steps
-        self.beam_size = beam_size
-        self.objectdet = objectdet
-        self.per_node_beam_size = per_node_beam_size or beam_size
-
-    def search(self, begin_tokens, step):
-        if self.beam_size > 1 and self.objectdet:
-            only_return_best = False
-        else:
-            only_return_best = True
-
-        batch_size = begin_tokens.size()[0]
-
-        predictions = begin_tokens.unsqueeze(1).expand((batch_size, self.beam_size, begin_tokens.shape[-1]))
-        # Calculate the first timestep. This is done outside the main loop
-        # because we are going from a single decoder input (the output from the
-        # encoder) to the top `beam_size` decoder outputs. On the other hand,
-        # within the main loop we are going from the `beam_size` elements of the
-        # beam to `beam_size`^2 candidates from which we will select the top
-        # `beam_size` elements for the next iteration.
-        # shape: (batch_size, num_classes)
-        start_class_logits = step(begin_tokens)
-
-        # Convert logits to logprobs.
-        # shape: (batch_size * beam_size, vocab_size)
-        start_class_logprobs = F.log_softmax(start_class_logits, dim=1)
-
-        num_classes = start_class_logprobs.size()[1]
-
-        # shape: (batch_size, beam_size), (batch_size, beam_size)
-        start_top_logprobs, start_predicted_classes = start_class_logprobs.topk(
-            self.beam_size
-        )
-
-        if (
-            self.beam_size == 1
-            and (start_predicted_classes == self._eos_index).all()
-        ):
-            warnings.warn(
-                "Empty object description predicted. You may want to increase beam"
-                "size or ensure your step function is working properly.",
-                RuntimeWarning,
-            )
-            if only_return_best:
-                return start_predicted_classes, start_top_logprobs
-            else:
-                return start_predicted_classes.unsqueeze(-1), start_top_logprobs
-
-        # The log probs for the last time step.
-        # shape: (batch_size, beam_size)
-        last_logprobs = start_top_logprobs
-
-        # shape: (batch_size, beam_size, sequence_length)
-        predictions = torch.cat([predictions, start_predicted_classes.unsqueeze(-1)], dim=-1)
-
-        # Log probability tensor that mandates that the end token is selected.
-        # shape: (batch_size * beam_size, num_classes)
-        logprobs_after_end = start_class_logprobs.new_full(
-            (batch_size * self.beam_size, num_classes), float("-inf")
-        )
-        logprobs_after_end[:, self._eos_index] = 0.0
-
-        logits_after_end = start_class_logprobs.new_full(
-            (batch_size * self.beam_size, num_classes), float("-inf")
-        )
-        logits_after_end[:, self._eos_index] = 0
-
-        while predictions.shape[-1] < self.max_steps:
-            # shape: (batch_size * beam_size,)
-            last_predictions = predictions[:, :, -1].reshape(batch_size * self.beam_size)
-
-            # If every predicted token from the last step is `self._eos_index`,
-            # then we can stop early.
-            if (last_predictions == self._eos_index).all():
-                break
-
-            predictions_so_far = predictions.view(
-                batch_size * self.beam_size, -1
-            )
-            # shape: (batch_size * beam_size, num_classes)
-            class_logits = step(predictions_so_far)
-
-            # Set logprobs of last predicted tokens as high negative value to avoid
-            # repetition in description.
-            class_logits = class_logits.scatter(1, predictions_so_far[:, -1].view((-1, 1)), -10000)
-
-            # shape: (batch_size * beam_size, num_classes)
-            last_predictions_expanded = last_predictions.unsqueeze(-1).expand(
-                batch_size * self.beam_size, num_classes
-            )
-
-            # Here we are finding any beams where we predicted the end token in
-            # the previous timestep and replacing the distribution with a
-            # one-hot distribution, forcing the beam to predict the end token
-            # this timestep as well.
-            class_logits = torch.where(
-                last_predictions_expanded == self._eos_index,
-                logits_after_end,
-                class_logits,
-            )
-
-            # Convert logits to logprobs.
-            # shape: (batch_size * beam_size, vocab_size)
-            class_logprobs = F.log_softmax(class_logits, dim=1)
-
-            # shape (both): (batch_size * beam_size, per_node_beam_size)
-            top_logprobs, predicted_classes = class_logprobs.topk(
-                self.per_node_beam_size
-            )
-
-            # Here we expand the last log probs to `(batch_size * beam_size,
-            # per_node_beam_size)` so that we can add them to the current log
-            # probs for this timestep. This lets us maintain the log
-            # probability of each element on the beam.
-            # shape: (batch_size * beam_size, per_node_beam_size)
-            expanded_last_logprobs = (
-                last_logprobs.unsqueeze(2)
-                .expand(batch_size, self.beam_size, self.per_node_beam_size)
-                .reshape(batch_size * self.beam_size, self.per_node_beam_size)
-            )
-            # shape: (batch_size * beam_size, per_node_beam_size)
-            summed_top_logprobs = top_logprobs + expanded_last_logprobs
-
-            # shape: (batch_size, beam_size * per_node_beam_size)
-            reshaped_summed = summed_top_logprobs.reshape(
-                batch_size, self.beam_size * self.per_node_beam_size
-            )
-            # shape: (batch_size, beam_size * per_node_beam_size)
-            reshaped_predicted_classes = predicted_classes.reshape(
-                batch_size, self.beam_size * self.per_node_beam_size
-            )
-            # Append the predictions to the current beam.
-            reshaped_beam = (
-                predictions.view(batch_size * self.beam_size, 1, -1)
-                .repeat(1, self.per_node_beam_size, 1)
-                .reshape(batch_size, self.beam_size * self.per_node_beam_size, -1)
-            )
-            # batch_size, (beam_size * per_node_beach_size), #token
-            reshaped_beam = torch.cat([reshaped_beam, reshaped_predicted_classes.unsqueeze(-1)], dim=-1)
-
-            # Keep only the top `beam_size` beam indices.
-            # shape: (batch_size, beam_size), (batch_size, beam_size)
-            restricted_beam_logprobs, restricted_beam_indices = reshaped_summed.topk(
-                self.beam_size
-            )
-            predictions = reshaped_beam.gather(
-                1, restricted_beam_indices.unsqueeze(-1).repeat(1,1,reshaped_beam.shape[-1])
-            )
-
-            # shape: (batch_size, beam_size)
-            last_logprobs = restricted_beam_logprobs
-
-        if not torch.isfinite(last_logprobs).all():
-            warnings.warn(
-                "Infinite log probs encountered. Some final descriptions may not "
-                "make sense. This can happen when the beam size is larger than"
-                " the number of valid (non-zero probability) transitions that "
-                "the step function produces.",
-                RuntimeWarning,
-            )
-
-        # Optionally select best beam and its logprobs.
-        if only_return_best:
-            # shape: (batch_size, sequence_length)
-            predictions = predictions[:, 0, :]
-            last_logprobs = last_logprobs[:, 0]
-        num_valid = (predictions != self._eos_index).sum(dim=-1)
-        num_valid += (predictions == self._eos_index).sum(dim=-1) > 0
-        num_valid = num_valid - begin_tokens.shape[1]
-        num_valid = num_valid.clip(min=1)
-
-        last_logprobs = last_logprobs / num_valid
-
-        return predictions, last_logprobs
-
-
-class GRiTTextDecoder(nn.Module):
-    def __init__(
-        self,
-        transformer,
-        begin_token_id=101,
-        beamsearch_decode=None,
-        loss_type=None,
-        tokenizer=None,
-    ):
-        super().__init__()
-        self.textual = transformer
-        self.padding_idx = self.textual.padding_idx
-
-        self.begin_token_id = begin_token_id
-        self.beamsearch_decode = beamsearch_decode
-        self.tokenizer = tokenizer
-
-        if loss_type is None:
-            self.loss = nn.CrossEntropyLoss(ignore_index=self.padding_idx)
-        elif loss_type == 'smooth':
-            self.loss = SmoothLabelCrossEntropyLoss(ignore_index=self.padding_idx)
-        else:
-            raise NotImplementedError(loss_type)
-
-    def forward(self, batch):
-        object_features = batch['object_features']
-
-        if self.training:
-            caption_token_input = batch["text_tokens"]
-
-            output_logits = self.textual(
-                object_features,
-                caption_token_input,
-            )
-
-            if 'need_predict' in batch:
-                # in place should also be good, but we do not choose that for
-                # safety as we may use it in prediction results in future
-                target = batch["text_tokens"].clone()
-                target[batch['need_predict'] == 0] = self.padding_idx
-            else:
-                target = batch["text_tokens"]
-
-            feat = output_logits[:, :-1].contiguous()
-            target = target[:, 1:].contiguous()
-            feat = feat.view(-1, self.textual.vocab_size)
-            target = target.view(-1)
-
-            valid_mask = target != self.padding_idx
-            target = target[valid_mask]
-            feat = feat[valid_mask]
-            loss = self.loss(feat, target)
-
-            return loss
-        else:
-            output_dict = self.infer(object_features)
-        return output_dict
-
-    def infer(self, object_features):
-        batch_size = object_features.size(0)
-        begin_tokens = object_features.new_full(
-            (batch_size, 1), self.begin_token_id
-        ).long()
-
-        decoding_step = functools.partial(
-            self.decoding_step, object_features
-        )
-
-        object_description_tokens, logprobs = self.beamsearch_decode.search(
-            begin_tokens, decoding_step
-        )
-
-        output_dict = {
-            'predictions': object_description_tokens,
-            'logprobs': logprobs,
-        }
-
-        return output_dict
-
-    def decoding_step(self, object_features, partial_text):
-        batch_size = object_features.shape[0]
-        beam_size = int(partial_text.size(0) / batch_size)
-        if beam_size > 1:
-            batch_size, num_token, channels = object_features.size()
-            object_features = object_features.unsqueeze(1).repeat(1, beam_size, 1, 1)
-            object_features = object_features.view(
-                batch_size * beam_size, num_token, channels
-            )
-
-        text_lengths = torch.ones_like(partial_text)
-        if len(text_lengths.size()) != 2:
-            partial_text = partial_text.unsqueeze(1)
-
-        # shape: (batch_size * beam_size, partial_caption_length, vocab_size)
-        logits = self.textual(
-            object_features,
-            partial_text,
-        )
-
-        return logits[:, -1, :].float()
-
-
-class SmoothLabelCrossEntropyLoss(nn.Module):
-    def __init__(self, eps=0.1, log_prefix='', ignore_index=None):
-        super().__init__()
-        self.eps = eps
-        self.log_soft = nn.LogSoftmax(dim=1)
-        self.kl = nn.KLDivLoss(reduction='none')
-
-        self.iter = 0
-        self.max_loss = 0
-        self.min_loss = 0
-        self.log_prefix = log_prefix
-        self.ignore_index = ignore_index
-
-    def forward(self, feature, target):
-        feature = feature.float()
-        if self.ignore_index is not None:
-            valid_mask = target != self.ignore_index
-            target = target[valid_mask]
-            feature = feature[valid_mask]
-        assert target.numel() > 0
-        self.iter += 1
-        eps = self.eps
-        n_class = feature.size(1)
-        one_hot = torch.zeros_like(feature).scatter(1, target.view(-1, 1), 1)
-        one_hot = one_hot * (1 - eps) + (1 - one_hot) * eps / (n_class - 1)
-        log_prb = self.log_soft(feature)
-        loss = self.kl(log_prb, one_hot)
-        return loss.sum(dim=1).mean()
-
diff --git a/spaces/OpenGVLab/InternGPT/iGPT/models/grit_src/third_party/CenterNet2/tests/test_engine.py b/spaces/OpenGVLab/InternGPT/iGPT/models/grit_src/third_party/CenterNet2/tests/test_engine.py
deleted file mode 100644
index 6f6a0997d2a670e40e26286b258773ae56536a87..0000000000000000000000000000000000000000
--- a/spaces/OpenGVLab/InternGPT/iGPT/models/grit_src/third_party/CenterNet2/tests/test_engine.py
+++ /dev/null
@@ -1,186 +0,0 @@
-# Copyright (c) Facebook, Inc. and its affiliates.
-
-import json
-import math
-import os
-import tempfile
-import time
-import unittest
-from unittest import mock
-import torch
-from fvcore.common.checkpoint import Checkpointer
-from torch import nn
-
-from detectron2 import model_zoo
-from detectron2.config import configurable, get_cfg
-from detectron2.engine import DefaultTrainer, SimpleTrainer, default_setup, hooks
-from detectron2.modeling.meta_arch import META_ARCH_REGISTRY
-from detectron2.utils.events import CommonMetricPrinter, JSONWriter
-
-
-@META_ARCH_REGISTRY.register()
-class _SimpleModel(nn.Module):
-    @configurable
-    def __init__(self, sleep_sec=0):
-        super().__init__()
-        self.mod = nn.Linear(10, 20)
-        self.sleep_sec = sleep_sec
-
-    @classmethod
-    def from_config(cls, cfg):
-        return {}
-
-    def forward(self, x):
-        if self.sleep_sec > 0:
-            time.sleep(self.sleep_sec)
-        return {"loss": x.sum() + sum([x.mean() for x in self.parameters()])}
-
-
-class TestTrainer(unittest.TestCase):
-    def _data_loader(self, device):
-        device = torch.device(device)
-        while True:
-            yield torch.rand(3, 3).to(device)
-
-    def test_simple_trainer(self, device="cpu"):
-        model = _SimpleModel().to(device=device)
-        trainer = SimpleTrainer(
-            model, self._data_loader(device), torch.optim.SGD(model.parameters(), 0.1)
-        )
-        trainer.train(0, 10)
-
-    @unittest.skipIf(not torch.cuda.is_available(), "CUDA not available")
-    def test_simple_trainer_cuda(self):
-        self.test_simple_trainer(device="cuda")
-
-    def test_writer_hooks(self):
-        model = _SimpleModel(sleep_sec=0.1)
-        trainer = SimpleTrainer(
-            model, self._data_loader("cpu"), torch.optim.SGD(model.parameters(), 0.1)
-        )
-
-        max_iter = 50
-
-        with tempfile.TemporaryDirectory(prefix="detectron2_test") as d:
-            json_file = os.path.join(d, "metrics.json")
-            writers = [CommonMetricPrinter(max_iter), JSONWriter(json_file)]
-
-            trainer.register_hooks(
-                [hooks.EvalHook(0, lambda: {"metric": 100}), hooks.PeriodicWriter(writers)]
-            )
-            with self.assertLogs(writers[0].logger) as logs:
-                trainer.train(0, max_iter)
-
-            with open(json_file, "r") as f:
-                data = [json.loads(line.strip()) for line in f]
-                self.assertEqual([x["iteration"] for x in data], [19, 39, 49, 50])
-                # the eval metric is in the last line with iter 50
-                self.assertIn("metric", data[-1], "Eval metric must be in last line of JSON!")
-
-            # test logged messages from CommonMetricPrinter
-            self.assertEqual(len(logs.output), 3)
-            for log, iter in zip(logs.output, [19, 39, 49]):
-                self.assertIn(f"iter: {iter}", log)
-
-            self.assertIn("eta: 0:00:00", logs.output[-1], "Last ETA must be 0!")
-
-    def test_default_trainer(self):
-        # TODO: this test requires manifold access, so changed device to CPU. see: T88318502
-        cfg = get_cfg()
-        cfg.MODEL.DEVICE = "cpu"
-        cfg.MODEL.META_ARCHITECTURE = "_SimpleModel"
-        cfg.DATASETS.TRAIN = ("coco_2017_val_100",)
-        with tempfile.TemporaryDirectory(prefix="detectron2_test") as d:
-            cfg.OUTPUT_DIR = d
-            trainer = DefaultTrainer(cfg)
-
-            # test property
-            self.assertIs(trainer.model, trainer._trainer.model)
-            trainer.model = _SimpleModel()
-            self.assertIs(trainer.model, trainer._trainer.model)
-
-    def test_checkpoint_resume(self):
-        model = _SimpleModel()
-        dataloader = self._data_loader("cpu")
-        opt = torch.optim.SGD(model.parameters(), 0.1)
-        scheduler = torch.optim.lr_scheduler.StepLR(opt, 3)
-
-        with tempfile.TemporaryDirectory(prefix="detectron2_test") as d:
-            trainer = SimpleTrainer(model, dataloader, opt)
-            checkpointer = Checkpointer(model, d, opt=opt, trainer=trainer)
-
-            trainer.register_hooks(
-                [
-                    hooks.LRScheduler(scheduler=scheduler),
-                    # checkpoint after scheduler to properly save the state of scheduler
-                    hooks.PeriodicCheckpointer(checkpointer, 10),
-                ]
-            )
-
-            trainer.train(0, 12)
-            self.assertAlmostEqual(opt.param_groups[0]["lr"], 1e-5)
-            self.assertEqual(scheduler.last_epoch, 12)
-            del trainer
-
-            opt = torch.optim.SGD(model.parameters(), 999)  # lr will be loaded
-            trainer = SimpleTrainer(model, dataloader, opt)
-            scheduler = torch.optim.lr_scheduler.StepLR(opt, 3)
-            trainer.register_hooks(
-                [
-                    hooks.LRScheduler(scheduler=scheduler),
-                ]
-            )
-            checkpointer = Checkpointer(model, d, opt=opt, trainer=trainer)
-            checkpointer.resume_or_load("non_exist.pth")
-            self.assertEqual(trainer.iter, 11)  # last finished iter number (0-based in Trainer)
-            # number of times `scheduler.step()` was called (1-based)
-            self.assertEqual(scheduler.last_epoch, 12)
-            self.assertAlmostEqual(opt.param_groups[0]["lr"], 1e-5)
-
-    def test_eval_hook(self):
-        model = _SimpleModel()
-        dataloader = self._data_loader("cpu")
-        opt = torch.optim.SGD(model.parameters(), 0.1)
-
-        for total_iter, period, eval_count in [(30, 15, 2), (31, 15, 3), (20, 0, 1)]:
-            test_func = mock.Mock(return_value={"metric": 3.0})
-            trainer = SimpleTrainer(model, dataloader, opt)
-            trainer.register_hooks([hooks.EvalHook(period, test_func)])
-            trainer.train(0, total_iter)
-            self.assertEqual(test_func.call_count, eval_count)
-
-    def test_best_checkpointer(self):
-        model = _SimpleModel()
-        dataloader = self._data_loader("cpu")
-        opt = torch.optim.SGD(model.parameters(), 0.1)
-        metric_name = "metric"
-        total_iter = 40
-        test_period = 10
-        test_cases = [
-            ("max", iter([0.3, 0.4, 0.35, 0.5]), 3),
-            ("min", iter([1.0, 0.8, 0.9, 0.9]), 2),
-            ("min", iter([math.nan, 0.8, 0.9, 0.9]), 1),
-        ]
-        for mode, metrics, call_count in test_cases:
-            trainer = SimpleTrainer(model, dataloader, opt)
-            with tempfile.TemporaryDirectory(prefix="detectron2_test") as d:
-                checkpointer = Checkpointer(model, d, opt=opt, trainer=trainer)
-                trainer.register_hooks(
-                    [
-                        hooks.EvalHook(test_period, lambda: {metric_name: next(metrics)}),
-                        hooks.BestCheckpointer(test_period, checkpointer, metric_name, mode=mode),
-                    ]
-                )
-                with mock.patch.object(checkpointer, "save") as mock_save_method:
-                    trainer.train(0, total_iter)
-                    self.assertEqual(mock_save_method.call_count, call_count)
-
-    def test_setup_config(self):
-        with tempfile.TemporaryDirectory(prefix="detectron2_test") as d:
-            cfg = get_cfg()
-            cfg.OUTPUT_DIR = os.path.join(d, "yacs")
-            default_setup(cfg, {})
-
-            cfg = model_zoo.get_config("COCO-InstanceSegmentation/mask_rcnn_R_50_FPN_1x.py")
-            cfg.train.output_dir = os.path.join(d, "omegaconf")
-            default_setup(cfg, {})
diff --git a/spaces/OpenMotionLab/MotionGPT/pyrender/tests/unit/test_lights.py b/spaces/OpenMotionLab/MotionGPT/pyrender/tests/unit/test_lights.py
deleted file mode 100644
index ffde856b21e8cce9532f0308fcd1c7eb2d1eba90..0000000000000000000000000000000000000000
--- a/spaces/OpenMotionLab/MotionGPT/pyrender/tests/unit/test_lights.py
+++ /dev/null
@@ -1,104 +0,0 @@
-import numpy as np
-import pytest
-
-from pyrender import (DirectionalLight, SpotLight, PointLight, Texture,
-                      PerspectiveCamera, OrthographicCamera)
-from pyrender.constants import SHADOW_TEX_SZ
-
-
-def test_directional_light():
-
-    d = DirectionalLight()
-    assert d.name is None
-    assert np.all(d.color == 1.0)
-    assert d.intensity == 1.0
-
-    d.name = 'direc'
-    with pytest.raises(ValueError):
-        d.color = None
-    with pytest.raises(TypeError):
-        d.intensity = None
-
-    d = DirectionalLight(color=[0.0, 0.0, 0.0])
-    assert np.all(d.color == 0.0)
-
-    d._generate_shadow_texture()
-    st = d.shadow_texture
-    assert isinstance(st, Texture)
-    assert st.width == st.height == SHADOW_TEX_SZ
-
-    sc = d._get_shadow_camera(scene_scale=5.0)
-    assert isinstance(sc, OrthographicCamera)
-    assert sc.xmag == sc.ymag == 5.0
-    assert sc.znear == 0.01 * 5.0
-    assert sc.zfar == 10 * 5.0
-
-
-def test_spot_light():
-
-    s = SpotLight()
-    assert s.name is None
-    assert np.all(s.color == 1.0)
-    assert s.intensity == 1.0
-    assert s.innerConeAngle == 0.0
-    assert s.outerConeAngle == np.pi / 4.0
-    assert s.range is None
-
-    with pytest.raises(ValueError):
-        s.range = -1.0
-
-    with pytest.raises(ValueError):
-        s.range = 0.0
-
-    with pytest.raises(ValueError):
-        s.innerConeAngle = -1.0
-
-    with pytest.raises(ValueError):
-        s.innerConeAngle = np.pi / 3.0
-
-    with pytest.raises(ValueError):
-        s.outerConeAngle = -1.0
-
-    with pytest.raises(ValueError):
-        s.outerConeAngle = np.pi
-
-    s.range = 5.0
-    s.outerConeAngle = np.pi / 2 - 0.05
-    s.innerConeAngle = np.pi / 3
-    s.innerConeAngle = 0.0
-    s.outerConeAngle = np.pi / 4.0
-
-    s._generate_shadow_texture()
-    st = s.shadow_texture
-    assert isinstance(st, Texture)
-    assert st.width == st.height == SHADOW_TEX_SZ
-
-    sc = s._get_shadow_camera(scene_scale=5.0)
-    assert isinstance(sc, PerspectiveCamera)
-    assert sc.znear == 0.01 * 5.0
-    assert sc.zfar == 10 * 5.0
-    assert sc.aspectRatio == 1.0
-    assert np.allclose(sc.yfov, np.pi / 16.0 * 9.0)  # Plus pi / 16
-
-
-def test_point_light():
-
-    s = PointLight()
-    assert s.name is None
-    assert np.all(s.color == 1.0)
-    assert s.intensity == 1.0
-    assert s.range is None
-
-    with pytest.raises(ValueError):
-        s.range = -1.0
-
-    with pytest.raises(ValueError):
-        s.range = 0.0
-
-    s.range = 5.0
-
-    with pytest.raises(NotImplementedError):
-        s._generate_shadow_texture()
-
-    with pytest.raises(NotImplementedError):
-        s._get_shadow_camera(scene_scale=5.0)
diff --git a/spaces/PKUWilliamYang/StyleGANEX/scripts/calc_id_loss_parallel.py b/spaces/PKUWilliamYang/StyleGANEX/scripts/calc_id_loss_parallel.py
deleted file mode 100644
index efc82bf851b252e92c45be3c87be877616f44ead..0000000000000000000000000000000000000000
--- a/spaces/PKUWilliamYang/StyleGANEX/scripts/calc_id_loss_parallel.py
+++ /dev/null
@@ -1,119 +0,0 @@
-from argparse import ArgumentParser
-import time
-import numpy as np
-import os
-import json
-import sys
-from PIL import Image
-import multiprocessing as mp
-import math
-import torch
-import torchvision.transforms as trans
-
-sys.path.append(".")
-sys.path.append("..")
-
-from models.mtcnn.mtcnn import MTCNN
-from models.encoders.model_irse import IR_101
-from configs.paths_config import model_paths
-CIRCULAR_FACE_PATH = model_paths['circular_face']
-
-
-def chunks(lst, n):
-	"""Yield successive n-sized chunks from lst."""
-	for i in range(0, len(lst), n):
-		yield lst[i:i + n]
-
-
-def extract_on_paths(file_paths):
-	facenet = IR_101(input_size=112)
-	facenet.load_state_dict(torch.load(CIRCULAR_FACE_PATH))
-	facenet.cuda()
-	facenet.eval()
-	mtcnn = MTCNN()
-	id_transform = trans.Compose([
-		trans.ToTensor(),
-		trans.Normalize([0.5, 0.5, 0.5], [0.5, 0.5, 0.5])
-	])
-
-	pid = mp.current_process().name
-	print('\t{} is starting to extract on {} images'.format(pid, len(file_paths)))
-	tot_count = len(file_paths)
-	count = 0
-
-	scores_dict = {}
-	for res_path, gt_path in file_paths:
-		count += 1
-		if count % 100 == 0:
-			print('{} done with {}/{}'.format(pid, count, tot_count))
-		if True:
-			input_im = Image.open(res_path)
-			input_im, _ = mtcnn.align(input_im)
-			if input_im is None:
-				print('{} skipping {}'.format(pid, res_path))
-				continue
-
-			input_id = facenet(id_transform(input_im).unsqueeze(0).cuda())[0]
-
-			result_im = Image.open(gt_path)
-			result_im, _ = mtcnn.align(result_im)
-			if result_im is None:
-				print('{} skipping {}'.format(pid, gt_path))
-				continue
-
-			result_id = facenet(id_transform(result_im).unsqueeze(0).cuda())[0]
-			score = float(input_id.dot(result_id))
-			scores_dict[os.path.basename(gt_path)] = score
-
-	return scores_dict
-
-
-def parse_args():
-	parser = ArgumentParser(add_help=False)
-	parser.add_argument('--num_threads', type=int, default=4)
-	parser.add_argument('--data_path', type=str,  default='results')
-	parser.add_argument('--gt_path', type=str, default='gt_images')
-	args = parser.parse_args()
-	return args
-
-
-def run(args):
-	file_paths = []
-	for f in os.listdir(args.data_path):
-		image_path = os.path.join(args.data_path, f)
-		gt_path = os.path.join(args.gt_path, f)
-		if f.endswith(".jpg") or f.endswith('.png'):
-			file_paths.append([image_path, gt_path.replace('.png','.jpg')])
-
-	file_chunks = list(chunks(file_paths, int(math.ceil(len(file_paths) / args.num_threads))))
-	pool = mp.Pool(args.num_threads)
-	print('Running on {} paths\nHere we goooo'.format(len(file_paths)))
-
-	tic = time.time()
-	results = pool.map(extract_on_paths, file_chunks)
-	scores_dict = {}
-	for d in results:
-		scores_dict.update(d)
-
-	all_scores = list(scores_dict.values())
-	mean = np.mean(all_scores)
-	std = np.std(all_scores)
-	result_str = 'New Average score is {:.2f}+-{:.2f}'.format(mean, std)
-	print(result_str)
-
-	out_path = os.path.join(os.path.dirname(args.data_path), 'inference_metrics')
-	if not os.path.exists(out_path):
-		os.makedirs(out_path)
-
-	with open(os.path.join(out_path, 'stat_id.txt'), 'w') as f:
-		f.write(result_str)
-	with open(os.path.join(out_path, 'scores_id.json'), 'w') as f:
-		json.dump(scores_dict, f)
-
-	toc = time.time()
-	print('Mischief managed in {}s'.format(toc - tic))
-
-
-if __name__ == '__main__':
-	args = parse_args()
-	run(args)
diff --git a/spaces/PSLD/PSLD/diffusion-posterior-sampling/util/logger.py b/spaces/PSLD/PSLD/diffusion-posterior-sampling/util/logger.py
deleted file mode 100644
index 7992959680b35ab36fd9649774ad872f06847158..0000000000000000000000000000000000000000
--- a/spaces/PSLD/PSLD/diffusion-posterior-sampling/util/logger.py
+++ /dev/null
@@ -1,12 +0,0 @@
-import logging
-
-def get_logger():
-    logger = logging.getLogger(name='DPS')
-    logger.setLevel(logging.INFO)
-    
-    formatter = logging.Formatter("%(asctime)s [%(name)s] >> %(message)s")
-    stream_handler = logging.StreamHandler()
-    stream_handler.setFormatter(formatter)
-    logger.addHandler(stream_handler)
-    
-    return logger
\ No newline at end of file
diff --git a/spaces/PaddlePaddle/resnet_v2_34_imagenet/app.py b/spaces/PaddlePaddle/resnet_v2_34_imagenet/app.py
deleted file mode 100644
index 6f9fc9f75f2c7d8bc5d202efe413ebcfc6e2ab80..0000000000000000000000000000000000000000
--- a/spaces/PaddlePaddle/resnet_v2_34_imagenet/app.py
+++ /dev/null
@@ -1,18 +0,0 @@
-import gradio as gr
-import paddlehub as hub
-
-classifier = hub.Module(name="resnet_v2_34_imagenet")
-
-def inference(img):
-  test_img_path = img
-  input_dict = {"image": [test_img_path]}
-  result = classifier.classification(data=input_dict)
-  print(result)
-  return result[0][0]
-
-  
-title="resnet_v2_34_imagenet"
-description="The ResNet series model is one of the important models in the field of image classification. The residual unit proposed in the model effectively solves the difficult problem of deep network training, and improves the accuracy of the model by increasing the depth of the model. The PaddleHub Module has a ResNet34 structure and is trained on the ImageNet-2012 dataset. The input image size is 224 x 224 x 3, and it supports prediction directly through the command line or Python interface."
-
-examples=[['cat2.jpg']]
-gr.Interface(inference,gr.inputs.Image(type="filepath"),"label",title=title,description=description,examples=examples).launch(enable_queue=True,cache_examples=True)
\ No newline at end of file
diff --git a/spaces/PatrickTyBrown/LoanDocumentClassifier/README.md b/spaces/PatrickTyBrown/LoanDocumentClassifier/README.md
deleted file mode 100644
index 9ef3746bea64d426f950ddfc56f7d0b43d6164ab..0000000000000000000000000000000000000000
--- a/spaces/PatrickTyBrown/LoanDocumentClassifier/README.md
+++ /dev/null
@@ -1,12 +0,0 @@
----
-title: LoanDocumentClassifier
-emoji: 👁
-colorFrom: gray
-colorTo: pink
-sdk: gradio
-app_file: app.py
-pinned: false
-license: apache-2.0
----
-
-Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
diff --git a/spaces/Pattr/DrumClassification/lilypond-2.24.2/lib/guile/2.2/ccache/ice-9/and-let-star.go b/spaces/Pattr/DrumClassification/lilypond-2.24.2/lib/guile/2.2/ccache/ice-9/and-let-star.go
deleted file mode 100644
index 9ec2e48045f8fde5ab14abf2d295e66634994d79..0000000000000000000000000000000000000000
Binary files a/spaces/Pattr/DrumClassification/lilypond-2.24.2/lib/guile/2.2/ccache/ice-9/and-let-star.go and /dev/null differ
diff --git a/spaces/Pattr/DrumClassification/lilypond-2.24.2/lib/guile/2.2/ccache/scripts/disassemble.go b/spaces/Pattr/DrumClassification/lilypond-2.24.2/lib/guile/2.2/ccache/scripts/disassemble.go
deleted file mode 100644
index 19f5842dcf2ee20d7288f3d8aee6a70d86d09af0..0000000000000000000000000000000000000000
Binary files a/spaces/Pattr/DrumClassification/lilypond-2.24.2/lib/guile/2.2/ccache/scripts/disassemble.go and /dev/null differ
diff --git a/spaces/Raspberry-ai/main/.env/lib/python3.11/site-packages/pkg_resources/_vendor/more_itertools/recipes.py b/spaces/Raspberry-ai/main/.env/lib/python3.11/site-packages/pkg_resources/_vendor/more_itertools/recipes.py
deleted file mode 100644
index a2596423a4c3dbd15a357241477a0af0a531f9ec..0000000000000000000000000000000000000000
--- a/spaces/Raspberry-ai/main/.env/lib/python3.11/site-packages/pkg_resources/_vendor/more_itertools/recipes.py
+++ /dev/null
@@ -1,698 +0,0 @@
-"""Imported from the recipes section of the itertools documentation.
-
-All functions taken from the recipes section of the itertools library docs
-[1]_.
-Some backward-compatible usability improvements have been made.
-
-.. [1] http://docs.python.org/library/itertools.html#recipes
-
-"""
-import warnings
-from collections import deque
-from itertools import (
-    chain,
-    combinations,
-    count,
-    cycle,
-    groupby,
-    islice,
-    repeat,
-    starmap,
-    tee,
-    zip_longest,
-)
-import operator
-from random import randrange, sample, choice
-
-__all__ = [
-    'all_equal',
-    'before_and_after',
-    'consume',
-    'convolve',
-    'dotproduct',
-    'first_true',
-    'flatten',
-    'grouper',
-    'iter_except',
-    'ncycles',
-    'nth',
-    'nth_combination',
-    'padnone',
-    'pad_none',
-    'pairwise',
-    'partition',
-    'powerset',
-    'prepend',
-    'quantify',
-    'random_combination_with_replacement',
-    'random_combination',
-    'random_permutation',
-    'random_product',
-    'repeatfunc',
-    'roundrobin',
-    'sliding_window',
-    'tabulate',
-    'tail',
-    'take',
-    'triplewise',
-    'unique_everseen',
-    'unique_justseen',
-]
-
-
-def take(n, iterable):
-    """Return first *n* items of the iterable as a list.
-
-        >>> take(3, range(10))
-        [0, 1, 2]
-
-    If there are fewer than *n* items in the iterable, all of them are
-    returned.
-
-        >>> take(10, range(3))
-        [0, 1, 2]
-
-    """
-    return list(islice(iterable, n))
-
-
-def tabulate(function, start=0):
-    """Return an iterator over the results of ``func(start)``,
-    ``func(start + 1)``, ``func(start + 2)``...
-
-    *func* should be a function that accepts one integer argument.
-
-    If *start* is not specified it defaults to 0. It will be incremented each
-    time the iterator is advanced.
-
-        >>> square = lambda x: x ** 2
-        >>> iterator = tabulate(square, -3)
-        >>> take(4, iterator)
-        [9, 4, 1, 0]
-
-    """
-    return map(function, count(start))
-
-
-def tail(n, iterable):
-    """Return an iterator over the last *n* items of *iterable*.
-
-    >>> t = tail(3, 'ABCDEFG')
-    >>> list(t)
-    ['E', 'F', 'G']
-
-    """
-    return iter(deque(iterable, maxlen=n))
-
-
-def consume(iterator, n=None):
-    """Advance *iterable* by *n* steps. If *n* is ``None``, consume it
-    entirely.
-
-    Efficiently exhausts an iterator without returning values. Defaults to
-    consuming the whole iterator, but an optional second argument may be
-    provided to limit consumption.
-
-        >>> i = (x for x in range(10))
-        >>> next(i)
-        0
-        >>> consume(i, 3)
-        >>> next(i)
-        4
-        >>> consume(i)
-        >>> next(i)
-        Traceback (most recent call last):
-          File "<stdin>", line 1, in <module>
-        StopIteration
-
-    If the iterator has fewer items remaining than the provided limit, the
-    whole iterator will be consumed.
-
-        >>> i = (x for x in range(3))
-        >>> consume(i, 5)
-        >>> next(i)
-        Traceback (most recent call last):
-          File "<stdin>", line 1, in <module>
-        StopIteration
-
-    """
-    # Use functions that consume iterators at C speed.
-    if n is None:
-        # feed the entire iterator into a zero-length deque
-        deque(iterator, maxlen=0)
-    else:
-        # advance to the empty slice starting at position n
-        next(islice(iterator, n, n), None)
-
-
-def nth(iterable, n, default=None):
-    """Returns the nth item or a default value.
-
-    >>> l = range(10)
-    >>> nth(l, 3)
-    3
-    >>> nth(l, 20, "zebra")
-    'zebra'
-
-    """
-    return next(islice(iterable, n, None), default)
-
-
-def all_equal(iterable):
-    """
-    Returns ``True`` if all the elements are equal to each other.
-
-        >>> all_equal('aaaa')
-        True
-        >>> all_equal('aaab')
-        False
-
-    """
-    g = groupby(iterable)
-    return next(g, True) and not next(g, False)
-
-
-def quantify(iterable, pred=bool):
-    """Return the how many times the predicate is true.
-
-    >>> quantify([True, False, True])
-    2
-
-    """
-    return sum(map(pred, iterable))
-
-
-def pad_none(iterable):
-    """Returns the sequence of elements and then returns ``None`` indefinitely.
-
-        >>> take(5, pad_none(range(3)))
-        [0, 1, 2, None, None]
-
-    Useful for emulating the behavior of the built-in :func:`map` function.
-
-    See also :func:`padded`.
-
-    """
-    return chain(iterable, repeat(None))
-
-
-padnone = pad_none
-
-
-def ncycles(iterable, n):
-    """Returns the sequence elements *n* times
-
-    >>> list(ncycles(["a", "b"], 3))
-    ['a', 'b', 'a', 'b', 'a', 'b']
-
-    """
-    return chain.from_iterable(repeat(tuple(iterable), n))
-
-
-def dotproduct(vec1, vec2):
-    """Returns the dot product of the two iterables.
-
-    >>> dotproduct([10, 10], [20, 20])
-    400
-
-    """
-    return sum(map(operator.mul, vec1, vec2))
-
-
-def flatten(listOfLists):
-    """Return an iterator flattening one level of nesting in a list of lists.
-
-        >>> list(flatten([[0, 1], [2, 3]]))
-        [0, 1, 2, 3]
-
-    See also :func:`collapse`, which can flatten multiple levels of nesting.
-
-    """
-    return chain.from_iterable(listOfLists)
-
-
-def repeatfunc(func, times=None, *args):
-    """Call *func* with *args* repeatedly, returning an iterable over the
-    results.
-
-    If *times* is specified, the iterable will terminate after that many
-    repetitions:
-
-        >>> from operator import add
-        >>> times = 4
-        >>> args = 3, 5
-        >>> list(repeatfunc(add, times, *args))
-        [8, 8, 8, 8]
-
-    If *times* is ``None`` the iterable will not terminate:
-
-        >>> from random import randrange
-        >>> times = None
-        >>> args = 1, 11
-        >>> take(6, repeatfunc(randrange, times, *args))  # doctest:+SKIP
-        [2, 4, 8, 1, 8, 4]
-
-    """
-    if times is None:
-        return starmap(func, repeat(args))
-    return starmap(func, repeat(args, times))
-
-
-def _pairwise(iterable):
-    """Returns an iterator of paired items, overlapping, from the original
-
-    >>> take(4, pairwise(count()))
-    [(0, 1), (1, 2), (2, 3), (3, 4)]
-
-    On Python 3.10 and above, this is an alias for :func:`itertools.pairwise`.
-
-    """
-    a, b = tee(iterable)
-    next(b, None)
-    yield from zip(a, b)
-
-
-try:
-    from itertools import pairwise as itertools_pairwise
-except ImportError:
-    pairwise = _pairwise
-else:
-
-    def pairwise(iterable):
-        yield from itertools_pairwise(iterable)
-
-    pairwise.__doc__ = _pairwise.__doc__
-
-
-def grouper(iterable, n, fillvalue=None):
-    """Collect data into fixed-length chunks or blocks.
-
-    >>> list(grouper('ABCDEFG', 3, 'x'))
-    [('A', 'B', 'C'), ('D', 'E', 'F'), ('G', 'x', 'x')]
-
-    """
-    if isinstance(iterable, int):
-        warnings.warn(
-            "grouper expects iterable as first parameter", DeprecationWarning
-        )
-        n, iterable = iterable, n
-    args = [iter(iterable)] * n
-    return zip_longest(fillvalue=fillvalue, *args)
-
-
-def roundrobin(*iterables):
-    """Yields an item from each iterable, alternating between them.
-
-        >>> list(roundrobin('ABC', 'D', 'EF'))
-        ['A', 'D', 'E', 'B', 'F', 'C']
-
-    This function produces the same output as :func:`interleave_longest`, but
-    may perform better for some inputs (in particular when the number of
-    iterables is small).
-
-    """
-    # Recipe credited to George Sakkis
-    pending = len(iterables)
-    nexts = cycle(iter(it).__next__ for it in iterables)
-    while pending:
-        try:
-            for next in nexts:
-                yield next()
-        except StopIteration:
-            pending -= 1
-            nexts = cycle(islice(nexts, pending))
-
-
-def partition(pred, iterable):
-    """
-    Returns a 2-tuple of iterables derived from the input iterable.
-    The first yields the items that have ``pred(item) == False``.
-    The second yields the items that have ``pred(item) == True``.
-
-        >>> is_odd = lambda x: x % 2 != 0
-        >>> iterable = range(10)
-        >>> even_items, odd_items = partition(is_odd, iterable)
-        >>> list(even_items), list(odd_items)
-        ([0, 2, 4, 6, 8], [1, 3, 5, 7, 9])
-
-    If *pred* is None, :func:`bool` is used.
-
-        >>> iterable = [0, 1, False, True, '', ' ']
-        >>> false_items, true_items = partition(None, iterable)
-        >>> list(false_items), list(true_items)
-        ([0, False, ''], [1, True, ' '])
-
-    """
-    if pred is None:
-        pred = bool
-
-    evaluations = ((pred(x), x) for x in iterable)
-    t1, t2 = tee(evaluations)
-    return (
-        (x for (cond, x) in t1 if not cond),
-        (x for (cond, x) in t2 if cond),
-    )
-
-
-def powerset(iterable):
-    """Yields all possible subsets of the iterable.
-
-        >>> list(powerset([1, 2, 3]))
-        [(), (1,), (2,), (3,), (1, 2), (1, 3), (2, 3), (1, 2, 3)]
-
-    :func:`powerset` will operate on iterables that aren't :class:`set`
-    instances, so repeated elements in the input will produce repeated elements
-    in the output. Use :func:`unique_everseen` on the input to avoid generating
-    duplicates:
-
-        >>> seq = [1, 1, 0]
-        >>> list(powerset(seq))
-        [(), (1,), (1,), (0,), (1, 1), (1, 0), (1, 0), (1, 1, 0)]
-        >>> from more_itertools import unique_everseen
-        >>> list(powerset(unique_everseen(seq)))
-        [(), (1,), (0,), (1, 0)]
-
-    """
-    s = list(iterable)
-    return chain.from_iterable(combinations(s, r) for r in range(len(s) + 1))
-
-
-def unique_everseen(iterable, key=None):
-    """
-    Yield unique elements, preserving order.
-
-        >>> list(unique_everseen('AAAABBBCCDAABBB'))
-        ['A', 'B', 'C', 'D']
-        >>> list(unique_everseen('ABBCcAD', str.lower))
-        ['A', 'B', 'C', 'D']
-
-    Sequences with a mix of hashable and unhashable items can be used.
-    The function will be slower (i.e., `O(n^2)`) for unhashable items.
-
-    Remember that ``list`` objects are unhashable - you can use the *key*
-    parameter to transform the list to a tuple (which is hashable) to
-    avoid a slowdown.
-
-        >>> iterable = ([1, 2], [2, 3], [1, 2])
-        >>> list(unique_everseen(iterable))  # Slow
-        [[1, 2], [2, 3]]
-        >>> list(unique_everseen(iterable, key=tuple))  # Faster
-        [[1, 2], [2, 3]]
-
-    Similary, you may want to convert unhashable ``set`` objects with
-    ``key=frozenset``. For ``dict`` objects,
-    ``key=lambda x: frozenset(x.items())`` can be used.
-
-    """
-    seenset = set()
-    seenset_add = seenset.add
-    seenlist = []
-    seenlist_add = seenlist.append
-    use_key = key is not None
-
-    for element in iterable:
-        k = key(element) if use_key else element
-        try:
-            if k not in seenset:
-                seenset_add(k)
-                yield element
-        except TypeError:
-            if k not in seenlist:
-                seenlist_add(k)
-                yield element
-
-
-def unique_justseen(iterable, key=None):
-    """Yields elements in order, ignoring serial duplicates
-
-    >>> list(unique_justseen('AAAABBBCCDAABBB'))
-    ['A', 'B', 'C', 'D', 'A', 'B']
-    >>> list(unique_justseen('ABBCcAD', str.lower))
-    ['A', 'B', 'C', 'A', 'D']
-
-    """
-    return map(next, map(operator.itemgetter(1), groupby(iterable, key)))
-
-
-def iter_except(func, exception, first=None):
-    """Yields results from a function repeatedly until an exception is raised.
-
-    Converts a call-until-exception interface to an iterator interface.
-    Like ``iter(func, sentinel)``, but uses an exception instead of a sentinel
-    to end the loop.
-
-        >>> l = [0, 1, 2]
-        >>> list(iter_except(l.pop, IndexError))
-        [2, 1, 0]
-
-    Multiple exceptions can be specified as a stopping condition:
-
-        >>> l = [1, 2, 3, '...', 4, 5, 6]
-        >>> list(iter_except(lambda: 1 + l.pop(), (IndexError, TypeError)))
-        [7, 6, 5]
-        >>> list(iter_except(lambda: 1 + l.pop(), (IndexError, TypeError)))
-        [4, 3, 2]
-        >>> list(iter_except(lambda: 1 + l.pop(), (IndexError, TypeError)))
-        []
-
-    """
-    try:
-        if first is not None:
-            yield first()
-        while 1:
-            yield func()
-    except exception:
-        pass
-
-
-def first_true(iterable, default=None, pred=None):
-    """
-    Returns the first true value in the iterable.
-
-    If no true value is found, returns *default*
-
-    If *pred* is not None, returns the first item for which
-    ``pred(item) == True`` .
-
-        >>> first_true(range(10))
-        1
-        >>> first_true(range(10), pred=lambda x: x > 5)
-        6
-        >>> first_true(range(10), default='missing', pred=lambda x: x > 9)
-        'missing'
-
-    """
-    return next(filter(pred, iterable), default)
-
-
-def random_product(*args, repeat=1):
-    """Draw an item at random from each of the input iterables.
-
-        >>> random_product('abc', range(4), 'XYZ')  # doctest:+SKIP
-        ('c', 3, 'Z')
-
-    If *repeat* is provided as a keyword argument, that many items will be
-    drawn from each iterable.
-
-        >>> random_product('abcd', range(4), repeat=2)  # doctest:+SKIP
-        ('a', 2, 'd', 3)
-
-    This equivalent to taking a random selection from
-    ``itertools.product(*args, **kwarg)``.
-
-    """
-    pools = [tuple(pool) for pool in args] * repeat
-    return tuple(choice(pool) for pool in pools)
-
-
-def random_permutation(iterable, r=None):
-    """Return a random *r* length permutation of the elements in *iterable*.
-
-    If *r* is not specified or is ``None``, then *r* defaults to the length of
-    *iterable*.
-
-        >>> random_permutation(range(5))  # doctest:+SKIP
-        (3, 4, 0, 1, 2)
-
-    This equivalent to taking a random selection from
-    ``itertools.permutations(iterable, r)``.
-
-    """
-    pool = tuple(iterable)
-    r = len(pool) if r is None else r
-    return tuple(sample(pool, r))
-
-
-def random_combination(iterable, r):
-    """Return a random *r* length subsequence of the elements in *iterable*.
-
-        >>> random_combination(range(5), 3)  # doctest:+SKIP
-        (2, 3, 4)
-
-    This equivalent to taking a random selection from
-    ``itertools.combinations(iterable, r)``.
-
-    """
-    pool = tuple(iterable)
-    n = len(pool)
-    indices = sorted(sample(range(n), r))
-    return tuple(pool[i] for i in indices)
-
-
-def random_combination_with_replacement(iterable, r):
-    """Return a random *r* length subsequence of elements in *iterable*,
-    allowing individual elements to be repeated.
-
-        >>> random_combination_with_replacement(range(3), 5) # doctest:+SKIP
-        (0, 0, 1, 2, 2)
-
-    This equivalent to taking a random selection from
-    ``itertools.combinations_with_replacement(iterable, r)``.
-
-    """
-    pool = tuple(iterable)
-    n = len(pool)
-    indices = sorted(randrange(n) for i in range(r))
-    return tuple(pool[i] for i in indices)
-
-
-def nth_combination(iterable, r, index):
-    """Equivalent to ``list(combinations(iterable, r))[index]``.
-
-    The subsequences of *iterable* that are of length *r* can be ordered
-    lexicographically. :func:`nth_combination` computes the subsequence at
-    sort position *index* directly, without computing the previous
-    subsequences.
-
-        >>> nth_combination(range(5), 3, 5)
-        (0, 3, 4)
-
-    ``ValueError`` will be raised If *r* is negative or greater than the length
-    of *iterable*.
-    ``IndexError`` will be raised if the given *index* is invalid.
-    """
-    pool = tuple(iterable)
-    n = len(pool)
-    if (r < 0) or (r > n):
-        raise ValueError
-
-    c = 1
-    k = min(r, n - r)
-    for i in range(1, k + 1):
-        c = c * (n - k + i) // i
-
-    if index < 0:
-        index += c
-
-    if (index < 0) or (index >= c):
-        raise IndexError
-
-    result = []
-    while r:
-        c, n, r = c * r // n, n - 1, r - 1
-        while index >= c:
-            index -= c
-            c, n = c * (n - r) // n, n - 1
-        result.append(pool[-1 - n])
-
-    return tuple(result)
-
-
-def prepend(value, iterator):
-    """Yield *value*, followed by the elements in *iterator*.
-
-        >>> value = '0'
-        >>> iterator = ['1', '2', '3']
-        >>> list(prepend(value, iterator))
-        ['0', '1', '2', '3']
-
-    To prepend multiple values, see :func:`itertools.chain`
-    or :func:`value_chain`.
-
-    """
-    return chain([value], iterator)
-
-
-def convolve(signal, kernel):
-    """Convolve the iterable *signal* with the iterable *kernel*.
-
-        >>> signal = (1, 2, 3, 4, 5)
-        >>> kernel = [3, 2, 1]
-        >>> list(convolve(signal, kernel))
-        [3, 8, 14, 20, 26, 14, 5]
-
-    Note: the input arguments are not interchangeable, as the *kernel*
-    is immediately consumed and stored.
-
-    """
-    kernel = tuple(kernel)[::-1]
-    n = len(kernel)
-    window = deque([0], maxlen=n) * n
-    for x in chain(signal, repeat(0, n - 1)):
-        window.append(x)
-        yield sum(map(operator.mul, kernel, window))
-
-
-def before_and_after(predicate, it):
-    """A variant of :func:`takewhile` that allows complete access to the
-    remainder of the iterator.
-
-         >>> it = iter('ABCdEfGhI')
-         >>> all_upper, remainder = before_and_after(str.isupper, it)
-         >>> ''.join(all_upper)
-         'ABC'
-         >>> ''.join(remainder) # takewhile() would lose the 'd'
-         'dEfGhI'
-
-    Note that the first iterator must be fully consumed before the second
-    iterator can generate valid results.
-    """
-    it = iter(it)
-    transition = []
-
-    def true_iterator():
-        for elem in it:
-            if predicate(elem):
-                yield elem
-            else:
-                transition.append(elem)
-                return
-
-    def remainder_iterator():
-        yield from transition
-        yield from it
-
-    return true_iterator(), remainder_iterator()
-
-
-def triplewise(iterable):
-    """Return overlapping triplets from *iterable*.
-
-    >>> list(triplewise('ABCDE'))
-    [('A', 'B', 'C'), ('B', 'C', 'D'), ('C', 'D', 'E')]
-
-    """
-    for (a, _), (b, c) in pairwise(pairwise(iterable)):
-        yield a, b, c
-
-
-def sliding_window(iterable, n):
-    """Return a sliding window of width *n* over *iterable*.
-
-        >>> list(sliding_window(range(6), 4))
-        [(0, 1, 2, 3), (1, 2, 3, 4), (2, 3, 4, 5)]
-
-    If *iterable* has fewer than *n* items, then nothing is yielded:
-
-        >>> list(sliding_window(range(3), 4))
-        []
-
-    For a variant with more features, see :func:`windowed`.
-    """
-    it = iter(iterable)
-    window = deque(islice(it, n), maxlen=n)
-    if len(window) == n:
-        yield tuple(window)
-    for x in it:
-        window.append(x)
-        yield tuple(window)
diff --git a/spaces/Raspberry-ai/main/.env/lib/python3.11/site-packages/pkg_resources/_vendor/pyparsing/diagram/__init__.py b/spaces/Raspberry-ai/main/.env/lib/python3.11/site-packages/pkg_resources/_vendor/pyparsing/diagram/__init__.py
deleted file mode 100644
index 898644755cbbf9a8d4df562663114a7eb7e11fd1..0000000000000000000000000000000000000000
--- a/spaces/Raspberry-ai/main/.env/lib/python3.11/site-packages/pkg_resources/_vendor/pyparsing/diagram/__init__.py
+++ /dev/null
@@ -1,642 +0,0 @@
-import railroad
-import pyparsing
-import typing
-from typing import (
-    List,
-    NamedTuple,
-    Generic,
-    TypeVar,
-    Dict,
-    Callable,
-    Set,
-    Iterable,
-)
-from jinja2 import Template
-from io import StringIO
-import inspect
-
-
-jinja2_template_source = """\
-<!DOCTYPE html>
-<html>
-<head>
-    {% if not head %}
-        <style type="text/css">
-            .railroad-heading {
-                font-family: monospace;
-            }
-        </style>
-    {% else %}
-        {{ head | safe }}
-    {% endif %}
-</head>
-<body>
-{{ body | safe }}
-{% for diagram in diagrams %}
-    <div class="railroad-group">
-        <h1 class="railroad-heading">{{ diagram.title }}</h1>
-        <div class="railroad-description">{{ diagram.text }}</div>
-        <div class="railroad-svg">
-            {{ diagram.svg }}
-        </div>
-    </div>
-{% endfor %}
-</body>
-</html>
-"""
-
-template = Template(jinja2_template_source)
-
-# Note: ideally this would be a dataclass, but we're supporting Python 3.5+ so we can't do this yet
-NamedDiagram = NamedTuple(
-    "NamedDiagram",
-    [("name", str), ("diagram", typing.Optional[railroad.DiagramItem]), ("index", int)],
-)
-"""
-A simple structure for associating a name with a railroad diagram
-"""
-
-T = TypeVar("T")
-
-
-class EachItem(railroad.Group):
-    """
-    Custom railroad item to compose a:
-    - Group containing a
-      - OneOrMore containing a
-        - Choice of the elements in the Each
-    with the group label indicating that all must be matched
-    """
-
-    all_label = "[ALL]"
-
-    def __init__(self, *items):
-        choice_item = railroad.Choice(len(items) - 1, *items)
-        one_or_more_item = railroad.OneOrMore(item=choice_item)
-        super().__init__(one_or_more_item, label=self.all_label)
-
-
-class AnnotatedItem(railroad.Group):
-    """
-    Simple subclass of Group that creates an annotation label
-    """
-
-    def __init__(self, label: str, item):
-        super().__init__(item=item, label="[{}]".format(label) if label else label)
-
-
-class EditablePartial(Generic[T]):
-    """
-    Acts like a functools.partial, but can be edited. In other words, it represents a type that hasn't yet been
-    constructed.
-    """
-
-    # We need this here because the railroad constructors actually transform the data, so can't be called until the
-    # entire tree is assembled
-
-    def __init__(self, func: Callable[..., T], args: list, kwargs: dict):
-        self.func = func
-        self.args = args
-        self.kwargs = kwargs
-
-    @classmethod
-    def from_call(cls, func: Callable[..., T], *args, **kwargs) -> "EditablePartial[T]":
-        """
-        If you call this function in the same way that you would call the constructor, it will store the arguments
-        as you expect. For example EditablePartial.from_call(Fraction, 1, 3)() == Fraction(1, 3)
-        """
-        return EditablePartial(func=func, args=list(args), kwargs=kwargs)
-
-    @property
-    def name(self):
-        return self.kwargs["name"]
-
-    def __call__(self) -> T:
-        """
-        Evaluate the partial and return the result
-        """
-        args = self.args.copy()
-        kwargs = self.kwargs.copy()
-
-        # This is a helpful hack to allow you to specify varargs parameters (e.g. *args) as keyword args (e.g.
-        # args=['list', 'of', 'things'])
-        arg_spec = inspect.getfullargspec(self.func)
-        if arg_spec.varargs in self.kwargs:
-            args += kwargs.pop(arg_spec.varargs)
-
-        return self.func(*args, **kwargs)
-
-
-def railroad_to_html(diagrams: List[NamedDiagram], **kwargs) -> str:
-    """
-    Given a list of NamedDiagram, produce a single HTML string that visualises those diagrams
-    :params kwargs: kwargs to be passed in to the template
-    """
-    data = []
-    for diagram in diagrams:
-        if diagram.diagram is None:
-            continue
-        io = StringIO()
-        diagram.diagram.writeSvg(io.write)
-        title = diagram.name
-        if diagram.index == 0:
-            title += " (root)"
-        data.append({"title": title, "text": "", "svg": io.getvalue()})
-
-    return template.render(diagrams=data, **kwargs)
-
-
-def resolve_partial(partial: "EditablePartial[T]") -> T:
-    """
-    Recursively resolves a collection of Partials into whatever type they are
-    """
-    if isinstance(partial, EditablePartial):
-        partial.args = resolve_partial(partial.args)
-        partial.kwargs = resolve_partial(partial.kwargs)
-        return partial()
-    elif isinstance(partial, list):
-        return [resolve_partial(x) for x in partial]
-    elif isinstance(partial, dict):
-        return {key: resolve_partial(x) for key, x in partial.items()}
-    else:
-        return partial
-
-
-def to_railroad(
-    element: pyparsing.ParserElement,
-    diagram_kwargs: typing.Optional[dict] = None,
-    vertical: int = 3,
-    show_results_names: bool = False,
-    show_groups: bool = False,
-) -> List[NamedDiagram]:
-    """
-    Convert a pyparsing element tree into a list of diagrams. This is the recommended entrypoint to diagram
-    creation if you want to access the Railroad tree before it is converted to HTML
-    :param element: base element of the parser being diagrammed
-    :param diagram_kwargs: kwargs to pass to the Diagram() constructor
-    :param vertical: (optional) - int - limit at which number of alternatives should be
-       shown vertically instead of horizontally
-    :param show_results_names - bool to indicate whether results name annotations should be
-       included in the diagram
-    :param show_groups - bool to indicate whether groups should be highlighted with an unlabeled
-       surrounding box
-    """
-    # Convert the whole tree underneath the root
-    lookup = ConverterState(diagram_kwargs=diagram_kwargs or {})
-    _to_diagram_element(
-        element,
-        lookup=lookup,
-        parent=None,
-        vertical=vertical,
-        show_results_names=show_results_names,
-        show_groups=show_groups,
-    )
-
-    root_id = id(element)
-    # Convert the root if it hasn't been already
-    if root_id in lookup:
-        if not element.customName:
-            lookup[root_id].name = ""
-        lookup[root_id].mark_for_extraction(root_id, lookup, force=True)
-
-    # Now that we're finished, we can convert from intermediate structures into Railroad elements
-    diags = list(lookup.diagrams.values())
-    if len(diags) > 1:
-        # collapse out duplicate diags with the same name
-        seen = set()
-        deduped_diags = []
-        for d in diags:
-            # don't extract SkipTo elements, they are uninformative as subdiagrams
-            if d.name == "...":
-                continue
-            if d.name is not None and d.name not in seen:
-                seen.add(d.name)
-                deduped_diags.append(d)
-        resolved = [resolve_partial(partial) for partial in deduped_diags]
-    else:
-        # special case - if just one diagram, always display it, even if
-        # it has no name
-        resolved = [resolve_partial(partial) for partial in diags]
-    return sorted(resolved, key=lambda diag: diag.index)
-
-
-def _should_vertical(
-    specification: int, exprs: Iterable[pyparsing.ParserElement]
-) -> bool:
-    """
-    Returns true if we should return a vertical list of elements
-    """
-    if specification is None:
-        return False
-    else:
-        return len(_visible_exprs(exprs)) >= specification
-
-
-class ElementState:
-    """
-    State recorded for an individual pyparsing Element
-    """
-
-    # Note: this should be a dataclass, but we have to support Python 3.5
-    def __init__(
-        self,
-        element: pyparsing.ParserElement,
-        converted: EditablePartial,
-        parent: EditablePartial,
-        number: int,
-        name: str = None,
-        parent_index: typing.Optional[int] = None,
-    ):
-        #: The pyparsing element that this represents
-        self.element: pyparsing.ParserElement = element
-        #: The name of the element
-        self.name: typing.Optional[str] = name
-        #: The output Railroad element in an unconverted state
-        self.converted: EditablePartial = converted
-        #: The parent Railroad element, which we store so that we can extract this if it's duplicated
-        self.parent: EditablePartial = parent
-        #: The order in which we found this element, used for sorting diagrams if this is extracted into a diagram
-        self.number: int = number
-        #: The index of this inside its parent
-        self.parent_index: typing.Optional[int] = parent_index
-        #: If true, we should extract this out into a subdiagram
-        self.extract: bool = False
-        #: If true, all of this element's children have been filled out
-        self.complete: bool = False
-
-    def mark_for_extraction(
-        self, el_id: int, state: "ConverterState", name: str = None, force: bool = False
-    ):
-        """
-        Called when this instance has been seen twice, and thus should eventually be extracted into a sub-diagram
-        :param el_id: id of the element
-        :param state: element/diagram state tracker
-        :param name: name to use for this element's text
-        :param force: If true, force extraction now, regardless of the state of this. Only useful for extracting the
-        root element when we know we're finished
-        """
-        self.extract = True
-
-        # Set the name
-        if not self.name:
-            if name:
-                # Allow forcing a custom name
-                self.name = name
-            elif self.element.customName:
-                self.name = self.element.customName
-            else:
-                self.name = ""
-
-        # Just because this is marked for extraction doesn't mean we can do it yet. We may have to wait for children
-        # to be added
-        # Also, if this is just a string literal etc, don't bother extracting it
-        if force or (self.complete and _worth_extracting(self.element)):
-            state.extract_into_diagram(el_id)
-
-
-class ConverterState:
-    """
-    Stores some state that persists between recursions into the element tree
-    """
-
-    def __init__(self, diagram_kwargs: typing.Optional[dict] = None):
-        #: A dictionary mapping ParserElements to state relating to them
-        self._element_diagram_states: Dict[int, ElementState] = {}
-        #: A dictionary mapping ParserElement IDs to subdiagrams generated from them
-        self.diagrams: Dict[int, EditablePartial[NamedDiagram]] = {}
-        #: The index of the next unnamed element
-        self.unnamed_index: int = 1
-        #: The index of the next element. This is used for sorting
-        self.index: int = 0
-        #: Shared kwargs that are used to customize the construction of diagrams
-        self.diagram_kwargs: dict = diagram_kwargs or {}
-        self.extracted_diagram_names: Set[str] = set()
-
-    def __setitem__(self, key: int, value: ElementState):
-        self._element_diagram_states[key] = value
-
-    def __getitem__(self, key: int) -> ElementState:
-        return self._element_diagram_states[key]
-
-    def __delitem__(self, key: int):
-        del self._element_diagram_states[key]
-
-    def __contains__(self, key: int):
-        return key in self._element_diagram_states
-
-    def generate_unnamed(self) -> int:
-        """
-        Generate a number used in the name of an otherwise unnamed diagram
-        """
-        self.unnamed_index += 1
-        return self.unnamed_index
-
-    def generate_index(self) -> int:
-        """
-        Generate a number used to index a diagram
-        """
-        self.index += 1
-        return self.index
-
-    def extract_into_diagram(self, el_id: int):
-        """
-        Used when we encounter the same token twice in the same tree. When this
-        happens, we replace all instances of that token with a terminal, and
-        create a new subdiagram for the token
-        """
-        position = self[el_id]
-
-        # Replace the original definition of this element with a regular block
-        if position.parent:
-            ret = EditablePartial.from_call(railroad.NonTerminal, text=position.name)
-            if "item" in position.parent.kwargs:
-                position.parent.kwargs["item"] = ret
-            elif "items" in position.parent.kwargs:
-                position.parent.kwargs["items"][position.parent_index] = ret
-
-        # If the element we're extracting is a group, skip to its content but keep the title
-        if position.converted.func == railroad.Group:
-            content = position.converted.kwargs["item"]
-        else:
-            content = position.converted
-
-        self.diagrams[el_id] = EditablePartial.from_call(
-            NamedDiagram,
-            name=position.name,
-            diagram=EditablePartial.from_call(
-                railroad.Diagram, content, **self.diagram_kwargs
-            ),
-            index=position.number,
-        )
-
-        del self[el_id]
-
-
-def _worth_extracting(element: pyparsing.ParserElement) -> bool:
-    """
-    Returns true if this element is worth having its own sub-diagram. Simply, if any of its children
-    themselves have children, then its complex enough to extract
-    """
-    children = element.recurse()
-    return any(child.recurse() for child in children)
-
-
-def _apply_diagram_item_enhancements(fn):
-    """
-    decorator to ensure enhancements to a diagram item (such as results name annotations)
-    get applied on return from _to_diagram_element (we do this since there are several
-    returns in _to_diagram_element)
-    """
-
-    def _inner(
-        element: pyparsing.ParserElement,
-        parent: typing.Optional[EditablePartial],
-        lookup: ConverterState = None,
-        vertical: int = None,
-        index: int = 0,
-        name_hint: str = None,
-        show_results_names: bool = False,
-        show_groups: bool = False,
-    ) -> typing.Optional[EditablePartial]:
-
-        ret = fn(
-            element,
-            parent,
-            lookup,
-            vertical,
-            index,
-            name_hint,
-            show_results_names,
-            show_groups,
-        )
-
-        # apply annotation for results name, if present
-        if show_results_names and ret is not None:
-            element_results_name = element.resultsName
-            if element_results_name:
-                # add "*" to indicate if this is a "list all results" name
-                element_results_name += "" if element.modalResults else "*"
-                ret = EditablePartial.from_call(
-                    railroad.Group, item=ret, label=element_results_name
-                )
-
-        return ret
-
-    return _inner
-
-
-def _visible_exprs(exprs: Iterable[pyparsing.ParserElement]):
-    non_diagramming_exprs = (
-        pyparsing.ParseElementEnhance,
-        pyparsing.PositionToken,
-        pyparsing.And._ErrorStop,
-    )
-    return [
-        e
-        for e in exprs
-        if not (e.customName or e.resultsName or isinstance(e, non_diagramming_exprs))
-    ]
-
-
-@_apply_diagram_item_enhancements
-def _to_diagram_element(
-    element: pyparsing.ParserElement,
-    parent: typing.Optional[EditablePartial],
-    lookup: ConverterState = None,
-    vertical: int = None,
-    index: int = 0,
-    name_hint: str = None,
-    show_results_names: bool = False,
-    show_groups: bool = False,
-) -> typing.Optional[EditablePartial]:
-    """
-    Recursively converts a PyParsing Element to a railroad Element
-    :param lookup: The shared converter state that keeps track of useful things
-    :param index: The index of this element within the parent
-    :param parent: The parent of this element in the output tree
-    :param vertical: Controls at what point we make a list of elements vertical. If this is an integer (the default),
-    it sets the threshold of the number of items before we go vertical. If True, always go vertical, if False, never
-    do so
-    :param name_hint: If provided, this will override the generated name
-    :param show_results_names: bool flag indicating whether to add annotations for results names
-    :returns: The converted version of the input element, but as a Partial that hasn't yet been constructed
-    :param show_groups: bool flag indicating whether to show groups using bounding box
-    """
-    exprs = element.recurse()
-    name = name_hint or element.customName or element.__class__.__name__
-
-    # Python's id() is used to provide a unique identifier for elements
-    el_id = id(element)
-
-    element_results_name = element.resultsName
-
-    # Here we basically bypass processing certain wrapper elements if they contribute nothing to the diagram
-    if not element.customName:
-        if isinstance(
-            element,
-            (
-                # pyparsing.TokenConverter,
-                # pyparsing.Forward,
-                pyparsing.Located,
-            ),
-        ):
-            # However, if this element has a useful custom name, and its child does not, we can pass it on to the child
-            if exprs:
-                if not exprs[0].customName:
-                    propagated_name = name
-                else:
-                    propagated_name = None
-
-                return _to_diagram_element(
-                    element.expr,
-                    parent=parent,
-                    lookup=lookup,
-                    vertical=vertical,
-                    index=index,
-                    name_hint=propagated_name,
-                    show_results_names=show_results_names,
-                    show_groups=show_groups,
-                )
-
-    # If the element isn't worth extracting, we always treat it as the first time we say it
-    if _worth_extracting(element):
-        if el_id in lookup:
-            # If we've seen this element exactly once before, we are only just now finding out that it's a duplicate,
-            # so we have to extract it into a new diagram.
-            looked_up = lookup[el_id]
-            looked_up.mark_for_extraction(el_id, lookup, name=name_hint)
-            ret = EditablePartial.from_call(railroad.NonTerminal, text=looked_up.name)
-            return ret
-
-        elif el_id in lookup.diagrams:
-            # If we have seen the element at least twice before, and have already extracted it into a subdiagram, we
-            # just put in a marker element that refers to the sub-diagram
-            ret = EditablePartial.from_call(
-                railroad.NonTerminal, text=lookup.diagrams[el_id].kwargs["name"]
-            )
-            return ret
-
-    # Recursively convert child elements
-    # Here we find the most relevant Railroad element for matching pyparsing Element
-    # We use ``items=[]`` here to hold the place for where the child elements will go once created
-    if isinstance(element, pyparsing.And):
-        # detect And's created with ``expr*N`` notation - for these use a OneOrMore with a repeat
-        # (all will have the same name, and resultsName)
-        if not exprs:
-            return None
-        if len(set((e.name, e.resultsName) for e in exprs)) == 1:
-            ret = EditablePartial.from_call(
-                railroad.OneOrMore, item="", repeat=str(len(exprs))
-            )
-        elif _should_vertical(vertical, exprs):
-            ret = EditablePartial.from_call(railroad.Stack, items=[])
-        else:
-            ret = EditablePartial.from_call(railroad.Sequence, items=[])
-    elif isinstance(element, (pyparsing.Or, pyparsing.MatchFirst)):
-        if not exprs:
-            return None
-        if _should_vertical(vertical, exprs):
-            ret = EditablePartial.from_call(railroad.Choice, 0, items=[])
-        else:
-            ret = EditablePartial.from_call(railroad.HorizontalChoice, items=[])
-    elif isinstance(element, pyparsing.Each):
-        if not exprs:
-            return None
-        ret = EditablePartial.from_call(EachItem, items=[])
-    elif isinstance(element, pyparsing.NotAny):
-        ret = EditablePartial.from_call(AnnotatedItem, label="NOT", item="")
-    elif isinstance(element, pyparsing.FollowedBy):
-        ret = EditablePartial.from_call(AnnotatedItem, label="LOOKAHEAD", item="")
-    elif isinstance(element, pyparsing.PrecededBy):
-        ret = EditablePartial.from_call(AnnotatedItem, label="LOOKBEHIND", item="")
-    elif isinstance(element, pyparsing.Group):
-        if show_groups:
-            ret = EditablePartial.from_call(AnnotatedItem, label="", item="")
-        else:
-            ret = EditablePartial.from_call(railroad.Group, label="", item="")
-    elif isinstance(element, pyparsing.TokenConverter):
-        ret = EditablePartial.from_call(
-            AnnotatedItem, label=type(element).__name__.lower(), item=""
-        )
-    elif isinstance(element, pyparsing.Opt):
-        ret = EditablePartial.from_call(railroad.Optional, item="")
-    elif isinstance(element, pyparsing.OneOrMore):
-        ret = EditablePartial.from_call(railroad.OneOrMore, item="")
-    elif isinstance(element, pyparsing.ZeroOrMore):
-        ret = EditablePartial.from_call(railroad.ZeroOrMore, item="")
-    elif isinstance(element, pyparsing.Group):
-        ret = EditablePartial.from_call(
-            railroad.Group, item=None, label=element_results_name
-        )
-    elif isinstance(element, pyparsing.Empty) and not element.customName:
-        # Skip unnamed "Empty" elements
-        ret = None
-    elif len(exprs) > 1:
-        ret = EditablePartial.from_call(railroad.Sequence, items=[])
-    elif len(exprs) > 0 and not element_results_name:
-        ret = EditablePartial.from_call(railroad.Group, item="", label=name)
-    else:
-        terminal = EditablePartial.from_call(railroad.Terminal, element.defaultName)
-        ret = terminal
-
-    if ret is None:
-        return
-
-    # Indicate this element's position in the tree so we can extract it if necessary
-    lookup[el_id] = ElementState(
-        element=element,
-        converted=ret,
-        parent=parent,
-        parent_index=index,
-        number=lookup.generate_index(),
-    )
-    if element.customName:
-        lookup[el_id].mark_for_extraction(el_id, lookup, element.customName)
-
-    i = 0
-    for expr in exprs:
-        # Add a placeholder index in case we have to extract the child before we even add it to the parent
-        if "items" in ret.kwargs:
-            ret.kwargs["items"].insert(i, None)
-
-        item = _to_diagram_element(
-            expr,
-            parent=ret,
-            lookup=lookup,
-            vertical=vertical,
-            index=i,
-            show_results_names=show_results_names,
-            show_groups=show_groups,
-        )
-
-        # Some elements don't need to be shown in the diagram
-        if item is not None:
-            if "item" in ret.kwargs:
-                ret.kwargs["item"] = item
-            elif "items" in ret.kwargs:
-                # If we've already extracted the child, don't touch this index, since it's occupied by a nonterminal
-                ret.kwargs["items"][i] = item
-                i += 1
-        elif "items" in ret.kwargs:
-            # If we're supposed to skip this element, remove it from the parent
-            del ret.kwargs["items"][i]
-
-    # If all this items children are none, skip this item
-    if ret and (
-        ("items" in ret.kwargs and len(ret.kwargs["items"]) == 0)
-        or ("item" in ret.kwargs and ret.kwargs["item"] is None)
-    ):
-        ret = EditablePartial.from_call(railroad.Terminal, name)
-
-    # Mark this element as "complete", ie it has all of its children
-    if el_id in lookup:
-        lookup[el_id].complete = True
-
-    if el_id in lookup and lookup[el_id].extract and lookup[el_id].complete:
-        lookup.extract_into_diagram(el_id)
-        if ret is not None:
-            ret = EditablePartial.from_call(
-                railroad.NonTerminal, text=lookup.diagrams[el_id].kwargs["name"]
-            )
-
-    return ret
diff --git a/spaces/Realcat/image-matching-webui/third_party/ASpanFormer/configs/data/megadepth_trainval_832.py b/spaces/Realcat/image-matching-webui/third_party/ASpanFormer/configs/data/megadepth_trainval_832.py
deleted file mode 100644
index 48b9bd095d64c681d0e64ee9416fb63fbd1f27b5..0000000000000000000000000000000000000000
--- a/spaces/Realcat/image-matching-webui/third_party/ASpanFormer/configs/data/megadepth_trainval_832.py
+++ /dev/null
@@ -1,26 +0,0 @@
-from configs.data.base import cfg
-
-
-TRAIN_BASE_PATH = "data/megadepth/index"
-cfg.DATASET.TRAINVAL_DATA_SOURCE = "MegaDepth"
-cfg.DATASET.TRAIN_DATA_ROOT = "data/megadepth/train"
-cfg.DATASET.TRAIN_NPZ_ROOT = f"{TRAIN_BASE_PATH}/scene_info_0.1_0.7"
-cfg.DATASET.TRAIN_LIST_PATH = f"{TRAIN_BASE_PATH}/trainvaltest_list/train_list.txt"
-cfg.DATASET.MIN_OVERLAP_SCORE_TRAIN = 0.0
-
-TEST_BASE_PATH = "data/megadepth/index"
-cfg.DATASET.TEST_DATA_SOURCE = "MegaDepth"
-cfg.DATASET.VAL_DATA_ROOT = cfg.DATASET.TEST_DATA_ROOT = "data/megadepth/test"
-cfg.DATASET.VAL_NPZ_ROOT = (
-    cfg.DATASET.TEST_NPZ_ROOT
-) = f"{TEST_BASE_PATH}/scene_info_val_1500"
-cfg.DATASET.VAL_LIST_PATH = (
-    cfg.DATASET.TEST_LIST_PATH
-) = f"{TEST_BASE_PATH}/trainvaltest_list/val_list.txt"
-cfg.DATASET.MIN_OVERLAP_SCORE_TEST = 0.0  # for both test and val
-
-# 368 scenes in total for MegaDepth
-# (with difficulty balanced (further split each scene to 3 sub-scenes))
-cfg.TRAINER.N_SAMPLES_PER_SUBSET = 100
-
-cfg.DATASET.MGDPT_IMG_RESIZE = 832  # for training on 32GB meme GPUs
diff --git a/spaces/Realcat/image-matching-webui/third_party/SGMNet/datadump/dumper/base_dumper.py b/spaces/Realcat/image-matching-webui/third_party/SGMNet/datadump/dumper/base_dumper.py
deleted file mode 100644
index 039c565d9afcb744d30594f3697d45e8d1f234f9..0000000000000000000000000000000000000000
--- a/spaces/Realcat/image-matching-webui/third_party/SGMNet/datadump/dumper/base_dumper.py
+++ /dev/null
@@ -1,128 +0,0 @@
-from abc import ABCMeta, abstractmethod
-import os
-import h5py
-import numpy as np
-from tqdm import trange
-from torch.multiprocessing import Pool, set_start_method
-
-set_start_method("spawn", force=True)
-
-import sys
-
-ROOT_DIR = os.path.abspath(os.path.join(os.path.dirname(__file__), "../../"))
-sys.path.insert(0, ROOT_DIR)
-from components import load_component
-
-
-class BaseDumper(metaclass=ABCMeta):
-    def __init__(self, config):
-        self.config = config
-        self.img_seq = []
-        self.dump_seq = []  # feature dump seq
-
-    @abstractmethod
-    def get_seqs(self):
-        raise NotImplementedError
-
-    @abstractmethod
-    def format_dump_folder(self):
-        raise NotImplementedError
-
-    @abstractmethod
-    def format_dump_data(self):
-        raise NotImplementedError
-
-    def initialize(self):
-        self.extractor = load_component(
-            "extractor", self.config["extractor"]["name"], self.config["extractor"]
-        )
-        self.get_seqs()
-        self.format_dump_folder()
-
-    def extract(self, index):
-        img_path, dump_path = self.img_seq[index], self.dump_seq[index]
-        if not self.config["extractor"]["overwrite"] and os.path.exists(dump_path):
-            return
-        kp, desc = self.extractor.run(img_path)
-        self.write_feature(kp, desc, dump_path)
-
-    def dump_feature(self):
-        print("Extrating features...")
-        self.num_img = len(self.dump_seq)
-        pool = Pool(self.config["extractor"]["num_process"])
-        iteration_num = self.num_img // self.config["extractor"]["num_process"]
-        if self.num_img % self.config["extractor"]["num_process"] != 0:
-            iteration_num += 1
-        for index in trange(iteration_num):
-            indicies_list = range(
-                index * self.config["extractor"]["num_process"],
-                min(
-                    (index + 1) * self.config["extractor"]["num_process"], self.num_img
-                ),
-            )
-            pool.map(self.extract, indicies_list)
-        pool.close()
-        pool.join()
-
-    def write_feature(self, pts, desc, filename):
-        with h5py.File(filename, "w") as ifp:
-            ifp.create_dataset("keypoints", pts.shape, dtype=np.float32)
-            ifp.create_dataset("descriptors", desc.shape, dtype=np.float32)
-            ifp["keypoints"][:] = pts
-            ifp["descriptors"][:] = desc
-
-    def form_standard_dataset(self):
-        dataset_path = os.path.join(
-            self.config["dataset_dump_dir"],
-            self.config["data_name"]
-            + "_"
-            + self.config["extractor"]["name"]
-            + "_"
-            + str(self.config["extractor"]["num_kpt"])
-            + ".hdf5",
-        )
-
-        pair_data_type = ["K1", "K2", "R", "T", "e", "f"]
-        num_pairs = len(self.data["K1"])
-        with h5py.File(dataset_path, "w") as f:
-            print("collecting pair info...")
-            for type in pair_data_type:
-                dg = f.create_group(type)
-                for idx in range(num_pairs):
-                    data_item = np.asarray(self.data[type][idx])
-                    dg.create_dataset(
-                        str(idx), data_item.shape, data_item.dtype, data=data_item
-                    )
-
-            for type in ["img_path1", "img_path2"]:
-                dg = f.create_group(type)
-                for idx in range(num_pairs):
-                    dg.create_dataset(
-                        str(idx),
-                        [1],
-                        h5py.string_dtype(encoding="ascii"),
-                        data=self.data[type][idx].encode("ascii"),
-                    )
-
-            # dump desc
-            print("collecting desc and kpt...")
-            desc1_g, desc2_g, kpt1_g, kpt2_g = (
-                f.create_group("desc1"),
-                f.create_group("desc2"),
-                f.create_group("kpt1"),
-                f.create_group("kpt2"),
-            )
-            for idx in trange(num_pairs):
-                desc_file1, desc_file2 = h5py.File(
-                    self.data["fea_path1"][idx], "r"
-                ), h5py.File(self.data["fea_path2"][idx], "r")
-                desc1, desc2, kpt1, kpt2 = (
-                    desc_file1["descriptors"][()],
-                    desc_file2["descriptors"][()],
-                    desc_file1["keypoints"][()],
-                    desc_file2["keypoints"][()],
-                )
-                desc1_g.create_dataset(str(idx), desc1.shape, desc1.dtype, data=desc1)
-                desc2_g.create_dataset(str(idx), desc2.shape, desc2.dtype, data=desc2)
-                kpt1_g.create_dataset(str(idx), kpt1.shape, kpt1.dtype, data=kpt1)
-                kpt2_g.create_dataset(str(idx), kpt2.shape, kpt2.dtype, data=kpt2)
diff --git a/spaces/Sarst/VITS-Umamusume-voice-synthesizer2/utils.py b/spaces/Sarst/VITS-Umamusume-voice-synthesizer2/utils.py
deleted file mode 100644
index 9794e0fc3463a5e8fad05c037cce64683059a6d3..0000000000000000000000000000000000000000
--- a/spaces/Sarst/VITS-Umamusume-voice-synthesizer2/utils.py
+++ /dev/null
@@ -1,226 +0,0 @@
-import os
-import glob
-import sys
-import argparse
-import logging
-import json
-import subprocess
-import numpy as np
-from scipy.io.wavfile import read
-import torch
-
-MATPLOTLIB_FLAG = False
-
-logging.basicConfig(stream=sys.stdout, level=logging.ERROR)
-logger = logging
-
-
-def load_checkpoint(checkpoint_path, model, optimizer=None):
-    assert os.path.isfile(checkpoint_path)
-    checkpoint_dict = torch.load(checkpoint_path, map_location='cpu')
-    iteration = checkpoint_dict['iteration']
-    learning_rate = checkpoint_dict['learning_rate']
-    if optimizer is not None:
-        optimizer.load_state_dict(checkpoint_dict['optimizer'])
-    saved_state_dict = checkpoint_dict['model']
-    if hasattr(model, 'module'):
-        state_dict = model.module.state_dict()
-    else:
-        state_dict = model.state_dict()
-    new_state_dict = {}
-    for k, v in state_dict.items():
-        try:
-            new_state_dict[k] = saved_state_dict[k]
-        except:
-            logger.info("%s is not in the checkpoint" % k)
-            new_state_dict[k] = v
-    if hasattr(model, 'module'):
-        model.module.load_state_dict(new_state_dict)
-    else:
-        model.load_state_dict(new_state_dict)
-    logger.info("Loaded checkpoint '{}' (iteration {})".format(
-        checkpoint_path, iteration))
-    return model, optimizer, learning_rate, iteration
-
-
-def plot_spectrogram_to_numpy(spectrogram):
-    global MATPLOTLIB_FLAG
-    if not MATPLOTLIB_FLAG:
-        import matplotlib
-        matplotlib.use("Agg")
-        MATPLOTLIB_FLAG = True
-        mpl_logger = logging.getLogger('matplotlib')
-        mpl_logger.setLevel(logging.WARNING)
-    import matplotlib.pylab as plt
-    import numpy as np
-
-    fig, ax = plt.subplots(figsize=(10, 2))
-    im = ax.imshow(spectrogram, aspect="auto", origin="lower",
-                   interpolation='none')
-    plt.colorbar(im, ax=ax)
-    plt.xlabel("Frames")
-    plt.ylabel("Channels")
-    plt.tight_layout()
-
-    fig.canvas.draw()
-    data = np.fromstring(fig.canvas.tostring_rgb(), dtype=np.uint8, sep='')
-    data = data.reshape(fig.canvas.get_width_height()[::-1] + (3,))
-    plt.close()
-    return data
-
-
-def plot_alignment_to_numpy(alignment, info=None):
-    global MATPLOTLIB_FLAG
-    if not MATPLOTLIB_FLAG:
-        import matplotlib
-        matplotlib.use("Agg")
-        MATPLOTLIB_FLAG = True
-        mpl_logger = logging.getLogger('matplotlib')
-        mpl_logger.setLevel(logging.WARNING)
-    import matplotlib.pylab as plt
-    import numpy as np
-
-    fig, ax = plt.subplots(figsize=(6, 4))
-    im = ax.imshow(alignment.transpose(), aspect='auto', origin='lower',
-                   interpolation='none')
-    fig.colorbar(im, ax=ax)
-    xlabel = 'Decoder timestep'
-    if info is not None:
-        xlabel += '\n\n' + info
-    plt.xlabel(xlabel)
-    plt.ylabel('Encoder timestep')
-    plt.tight_layout()
-
-    fig.canvas.draw()
-    data = np.fromstring(fig.canvas.tostring_rgb(), dtype=np.uint8, sep='')
-    data = data.reshape(fig.canvas.get_width_height()[::-1] + (3,))
-    plt.close()
-    return data
-
-
-def load_wav_to_torch(full_path):
-    sampling_rate, data = read(full_path)
-    return torch.FloatTensor(data.astype(np.float32)), sampling_rate
-
-
-def load_filepaths_and_text(filename, split="|"):
-    with open(filename, encoding='utf-8') as f:
-        filepaths_and_text = [line.strip().split(split) for line in f]
-    return filepaths_and_text
-
-
-def get_hparams(init=True):
-    parser = argparse.ArgumentParser()
-    parser.add_argument('-c', '--config', type=str, default="./configs/base.json",
-                        help='JSON file for configuration')
-    parser.add_argument('-m', '--model', type=str, required=True,
-                        help='Model name')
-
-    args = parser.parse_args()
-    model_dir = os.path.join("./logs", args.model)
-
-    if not os.path.exists(model_dir):
-        os.makedirs(model_dir)
-
-    config_path = args.config
-    config_save_path = os.path.join(model_dir, "config.json")
-    if init:
-        with open(config_path, "r") as f:
-            data = f.read()
-        with open(config_save_path, "w") as f:
-            f.write(data)
-    else:
-        with open(config_save_path, "r") as f:
-            data = f.read()
-    config = json.loads(data)
-
-    hparams = HParams(**config)
-    hparams.model_dir = model_dir
-    return hparams
-
-
-def get_hparams_from_dir(model_dir):
-    config_save_path = os.path.join(model_dir, "config.json")
-    with open(config_save_path, "r") as f:
-        data = f.read()
-    config = json.loads(data)
-
-    hparams = HParams(**config)
-    hparams.model_dir = model_dir
-    return hparams
-
-
-def get_hparams_from_file(config_path):
-    with open(config_path, "r", encoding="utf-8") as f:
-        data = f.read()
-    config = json.loads(data)
-
-    hparams = HParams(**config)
-    return hparams
-
-
-def check_git_hash(model_dir):
-    source_dir = os.path.dirname(os.path.realpath(__file__))
-    if not os.path.exists(os.path.join(source_dir, ".git")):
-        logger.warn("{} is not a git repository, therefore hash value comparison will be ignored.".format(
-            source_dir
-        ))
-        return
-
-    cur_hash = subprocess.getoutput("git rev-parse HEAD")
-
-    path = os.path.join(model_dir, "githash")
-    if os.path.exists(path):
-        saved_hash = open(path).read()
-        if saved_hash != cur_hash:
-            logger.warn("git hash values are different. {}(saved) != {}(current)".format(
-                saved_hash[:8], cur_hash[:8]))
-    else:
-        open(path, "w").write(cur_hash)
-
-
-def get_logger(model_dir, filename="train.log"):
-    global logger
-    logger = logging.getLogger(os.path.basename(model_dir))
-    logger.setLevel(logging.DEBUG)
-
-    formatter = logging.Formatter("%(asctime)s\t%(name)s\t%(levelname)s\t%(message)s")
-    if not os.path.exists(model_dir):
-        os.makedirs(model_dir)
-    h = logging.FileHandler(os.path.join(model_dir, filename))
-    h.setLevel(logging.DEBUG)
-    h.setFormatter(formatter)
-    logger.addHandler(h)
-    return logger
-
-
-class HParams():
-    def __init__(self, **kwargs):
-        for k, v in kwargs.items():
-            if type(v) == dict:
-                v = HParams(**v)
-            self[k] = v
-
-    def keys(self):
-        return self.__dict__.keys()
-
-    def items(self):
-        return self.__dict__.items()
-
-    def values(self):
-        return self.__dict__.values()
-
-    def __len__(self):
-        return len(self.__dict__)
-
-    def __getitem__(self, key):
-        return getattr(self, key)
-
-    def __setitem__(self, key, value):
-        return setattr(self, key, value)
-
-    def __contains__(self, key):
-        return key in self.__dict__
-
-    def __repr__(self):
-        return self.__dict__.__repr__()
\ No newline at end of file
diff --git a/spaces/SeViLA/SeViLA/lavis/common/vqa_tools/vqa_eval.py b/spaces/SeViLA/SeViLA/lavis/common/vqa_tools/vqa_eval.py
deleted file mode 100644
index ee808b349bb6166c744338b02af2bc84a68650ff..0000000000000000000000000000000000000000
--- a/spaces/SeViLA/SeViLA/lavis/common/vqa_tools/vqa_eval.py
+++ /dev/null
@@ -1,324 +0,0 @@
-"""
- Copyright (c) 2022, salesforce.com, inc.
- All rights reserved.
- SPDX-License-Identifier: BSD-3-Clause
- For full license text, see the LICENSE file in the repo root or https://opensource.org/licenses/BSD-3-Clause
-"""
-
-# coding=utf-8
-
-__author__ = "aagrawal"
-
-# This code is based on the code written by Tsung-Yi Lin for MSCOCO Python API available at the following link:
-# (https://github.com/tylin/coco-caption/blob/master/pycocoevalcap/eval.py).
-import sys
-import re
-
-
-class VQAEval:
-    def __init__(self, vqa=None, vqaRes=None, n=2):
-        self.n = n
-        self.accuracy = {}
-        self.evalQA = {}
-        self.evalQuesType = {}
-        self.evalAnsType = {}
-        self.vqa = vqa
-        self.vqaRes = vqaRes
-        if vqa is not None:
-            self.params = {"question_id": vqa.getQuesIds()}
-        self.contractions = {
-            "aint": "ain't",
-            "arent": "aren't",
-            "cant": "can't",
-            "couldve": "could've",
-            "couldnt": "couldn't",
-            "couldn'tve": "couldn't've",
-            "couldnt've": "couldn't've",
-            "didnt": "didn't",
-            "doesnt": "doesn't",
-            "dont": "don't",
-            "hadnt": "hadn't",
-            "hadnt've": "hadn't've",
-            "hadn'tve": "hadn't've",
-            "hasnt": "hasn't",
-            "havent": "haven't",
-            "hed": "he'd",
-            "hed've": "he'd've",
-            "he'dve": "he'd've",
-            "hes": "he's",
-            "howd": "how'd",
-            "howll": "how'll",
-            "hows": "how's",
-            "Id've": "I'd've",
-            "I'dve": "I'd've",
-            "Im": "I'm",
-            "Ive": "I've",
-            "isnt": "isn't",
-            "itd": "it'd",
-            "itd've": "it'd've",
-            "it'dve": "it'd've",
-            "itll": "it'll",
-            "let's": "let's",
-            "maam": "ma'am",
-            "mightnt": "mightn't",
-            "mightnt've": "mightn't've",
-            "mightn'tve": "mightn't've",
-            "mightve": "might've",
-            "mustnt": "mustn't",
-            "mustve": "must've",
-            "neednt": "needn't",
-            "notve": "not've",
-            "oclock": "o'clock",
-            "oughtnt": "oughtn't",
-            "ow's'at": "'ow's'at",
-            "'ows'at": "'ow's'at",
-            "'ow'sat": "'ow's'at",
-            "shant": "shan't",
-            "shed've": "she'd've",
-            "she'dve": "she'd've",
-            "she's": "she's",
-            "shouldve": "should've",
-            "shouldnt": "shouldn't",
-            "shouldnt've": "shouldn't've",
-            "shouldn'tve": "shouldn't've",
-            "somebody'd": "somebodyd",
-            "somebodyd've": "somebody'd've",
-            "somebody'dve": "somebody'd've",
-            "somebodyll": "somebody'll",
-            "somebodys": "somebody's",
-            "someoned": "someone'd",
-            "someoned've": "someone'd've",
-            "someone'dve": "someone'd've",
-            "someonell": "someone'll",
-            "someones": "someone's",
-            "somethingd": "something'd",
-            "somethingd've": "something'd've",
-            "something'dve": "something'd've",
-            "somethingll": "something'll",
-            "thats": "that's",
-            "thered": "there'd",
-            "thered've": "there'd've",
-            "there'dve": "there'd've",
-            "therere": "there're",
-            "theres": "there's",
-            "theyd": "they'd",
-            "theyd've": "they'd've",
-            "they'dve": "they'd've",
-            "theyll": "they'll",
-            "theyre": "they're",
-            "theyve": "they've",
-            "twas": "'twas",
-            "wasnt": "wasn't",
-            "wed've": "we'd've",
-            "we'dve": "we'd've",
-            "weve": "we've",
-            "werent": "weren't",
-            "whatll": "what'll",
-            "whatre": "what're",
-            "whats": "what's",
-            "whatve": "what've",
-            "whens": "when's",
-            "whered": "where'd",
-            "wheres": "where's",
-            "whereve": "where've",
-            "whod": "who'd",
-            "whod've": "who'd've",
-            "who'dve": "who'd've",
-            "wholl": "who'll",
-            "whos": "who's",
-            "whove": "who've",
-            "whyll": "why'll",
-            "whyre": "why're",
-            "whys": "why's",
-            "wont": "won't",
-            "wouldve": "would've",
-            "wouldnt": "wouldn't",
-            "wouldnt've": "wouldn't've",
-            "wouldn'tve": "wouldn't've",
-            "yall": "y'all",
-            "yall'll": "y'all'll",
-            "y'allll": "y'all'll",
-            "yall'd've": "y'all'd've",
-            "y'alld've": "y'all'd've",
-            "y'all'dve": "y'all'd've",
-            "youd": "you'd",
-            "youd've": "you'd've",
-            "you'dve": "you'd've",
-            "youll": "you'll",
-            "youre": "you're",
-            "youve": "you've",
-        }
-        self.manualMap = {
-            "none": "0",
-            "zero": "0",
-            "one": "1",
-            "two": "2",
-            "three": "3",
-            "four": "4",
-            "five": "5",
-            "six": "6",
-            "seven": "7",
-            "eight": "8",
-            "nine": "9",
-            "ten": "10",
-        }
-        self.articles = ["a", "an", "the"]
-
-        self.periodStrip = re.compile("(?!<=\d)(\.)(?!\d)")
-        self.commaStrip = re.compile("(\d)(,)(\d)")
-        self.punct = [
-            ";",
-            r"/",
-            "[",
-            "]",
-            '"',
-            "{",
-            "}",
-            "(",
-            ")",
-            "=",
-            "+",
-            "\\",
-            "_",
-            "-",
-            ">",
-            "<",
-            "@",
-            "`",
-            ",",
-            "?",
-            "!",
-        ]
-
-    def evaluate(self, quesIds=None):
-        if quesIds == None:
-            quesIds = [quesId for quesId in self.params["question_id"]]
-        gts = {}
-        res = {}
-        for quesId in quesIds:
-            gts[quesId] = self.vqa.qa[quesId]
-            res[quesId] = self.vqaRes.qa[quesId]
-
-        # =================================================
-        # Compute accuracy
-        # =================================================
-        accQA = []
-        accQuesType = {}
-        accAnsType = {}
-        print("computing accuracy")
-        step = 0
-        for quesId in quesIds:
-            resAns = res[quesId]["answer"]
-            resAns = resAns.replace("\n", " ")
-            resAns = resAns.replace("\t", " ")
-            resAns = resAns.strip()
-            resAns = self.processPunctuation(resAns)
-            resAns = self.processDigitArticle(resAns)
-            gtAcc = []
-            gtAnswers = [ans["answer"] for ans in gts[quesId]["answers"]]
-            if len(set(gtAnswers)) > 1:
-                for ansDic in gts[quesId]["answers"]:
-                    ansDic["answer"] = self.processPunctuation(ansDic["answer"])
-            for gtAnsDatum in gts[quesId]["answers"]:
-                otherGTAns = [
-                    item for item in gts[quesId]["answers"] if item != gtAnsDatum
-                ]
-                matchingAns = [item for item in otherGTAns if item["answer"] == resAns]
-                acc = min(1, float(len(matchingAns)) / 3)
-                gtAcc.append(acc)
-            quesType = gts[quesId]["question_type"]
-            ansType = gts[quesId]["answer_type"]
-            avgGTAcc = float(sum(gtAcc)) / len(gtAcc)
-            accQA.append(avgGTAcc)
-            if quesType not in accQuesType:
-                accQuesType[quesType] = []
-            accQuesType[quesType].append(avgGTAcc)
-            if ansType not in accAnsType:
-                accAnsType[ansType] = []
-            accAnsType[ansType].append(avgGTAcc)
-            self.setEvalQA(quesId, avgGTAcc)
-            self.setEvalQuesType(quesId, quesType, avgGTAcc)
-            self.setEvalAnsType(quesId, ansType, avgGTAcc)
-            if step % 100 == 0:
-                self.updateProgress(step / float(len(quesIds)))
-            step = step + 1
-
-        self.setAccuracy(accQA, accQuesType, accAnsType)
-        print("Done computing accuracy")
-
-    def processPunctuation(self, inText):
-        outText = inText
-        for p in self.punct:
-            if (p + " " in inText or " " + p in inText) or (
-                re.search(self.commaStrip, inText) != None
-            ):
-                outText = outText.replace(p, "")
-            else:
-                outText = outText.replace(p, " ")
-        outText = self.periodStrip.sub("", outText, re.UNICODE)
-        return outText
-
-    def processDigitArticle(self, inText):
-        outText = []
-        tempText = inText.lower().split()
-        for word in tempText:
-            word = self.manualMap.setdefault(word, word)
-            if word not in self.articles:
-                outText.append(word)
-            else:
-                pass
-        for wordId, word in enumerate(outText):
-            if word in self.contractions:
-                outText[wordId] = self.contractions[word]
-        outText = " ".join(outText)
-        return outText
-
-    def setAccuracy(self, accQA, accQuesType, accAnsType):
-        self.accuracy["overall"] = round(100 * float(sum(accQA)) / len(accQA), self.n)
-        self.accuracy["perQuestionType"] = {
-            quesType: round(
-                100 * float(sum(accQuesType[quesType])) / len(accQuesType[quesType]),
-                self.n,
-            )
-            for quesType in accQuesType
-        }
-        self.accuracy["perAnswerType"] = {
-            ansType: round(
-                100 * float(sum(accAnsType[ansType])) / len(accAnsType[ansType]), self.n
-            )
-            for ansType in accAnsType
-        }
-
-    def setEvalQA(self, quesId, acc):
-        self.evalQA[quesId] = round(100 * acc, self.n)
-
-    def setEvalQuesType(self, quesId, quesType, acc):
-        if quesType not in self.evalQuesType:
-            self.evalQuesType[quesType] = {}
-        self.evalQuesType[quesType][quesId] = round(100 * acc, self.n)
-
-    def setEvalAnsType(self, quesId, ansType, acc):
-        if ansType not in self.evalAnsType:
-            self.evalAnsType[ansType] = {}
-        self.evalAnsType[ansType][quesId] = round(100 * acc, self.n)
-
-    def updateProgress(self, progress):
-        barLength = 20
-        status = ""
-        if isinstance(progress, int):
-            progress = float(progress)
-        if not isinstance(progress, float):
-            progress = 0
-            status = "error: progress var must be float\r\n"
-        if progress < 0:
-            progress = 0
-            status = "Halt...\r\n"
-        if progress >= 1:
-            progress = 1
-            status = "Done...\r\n"
-        block = int(round(barLength * progress))
-        text = "\rFinshed Percent: [{0}] {1}% {2}".format(
-            "#" * block + "-" * (barLength - block), int(progress * 100), status
-        )
-        sys.stdout.write(text)
-        sys.stdout.flush()
diff --git a/spaces/SeViLA/SeViLA/lavis/datasets/download_scripts/DownloadConceptualCaptions/download_data_cc3m.py b/spaces/SeViLA/SeViLA/lavis/datasets/download_scripts/DownloadConceptualCaptions/download_data_cc3m.py
deleted file mode 100644
index 2edd7a224436f7fa2d923501caadd40db040f8a1..0000000000000000000000000000000000000000
--- a/spaces/SeViLA/SeViLA/lavis/datasets/download_scripts/DownloadConceptualCaptions/download_data_cc3m.py
+++ /dev/null
@@ -1,229 +0,0 @@
-"""
- Copyright (c) 2022, salesforce.com, inc.
- All rights reserved.
- SPDX-License-Identifier: BSD-3-Clause
- For full license text, see the LICENSE file in the repo root or https://opensource.org/licenses/BSD-3-Clause
-"""
-
-import glob
-from pathlib import Path
-import time
-from omegaconf import OmegaConf
-import pandas as pd
-import numpy as np
-import requests
-import zlib
-import os
-import io
-import shelve
-from lavis.common.utils import get_abs_path, get_cache_path
-import magic  # pip install python-magic
-import json
-from multiprocessing import Pool
-from tqdm import tqdm
-from PIL import Image
-from torchvision.transforms import functional as TF
-
-headers = {
-    #'User-Agent': 'Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/71.0.3578.98 Safari/537.36',
-    "User-Agent": "Googlebot-Image/1.0",  # Pretend to be googlebot
-    "X-Forwarded-For": "64.18.15.200",
-}
-
-
-def _df_split_apply(tup_arg):
-    split_ind, subset, func = tup_arg
-    r = subset.apply(func, axis=1)
-    return (split_ind, r)
-
-
-def df_multiprocess(df, processes, chunk_size, func, dataset_name):
-    print("Generating parts...")
-    with shelve.open(
-        "%s_%s_%s_results.tmp" % (dataset_name, func.__name__, chunk_size)
-    ) as results:
-
-        pbar = tqdm(total=len(df), position=0)
-        # Resume:
-        finished_chunks = set([int(k) for k in results.keys()])
-        pbar.desc = "Resuming"
-        for k in results.keys():
-            pbar.update(len(results[str(k)][1]))
-
-        pool_data = (
-            (index, df[i : i + chunk_size], func)
-            for index, i in enumerate(range(0, len(df), chunk_size))
-            if index not in finished_chunks
-        )
-        print(
-            int(len(df) / chunk_size),
-            "parts.",
-            chunk_size,
-            "per part.",
-            "Using",
-            processes,
-            "processes",
-        )
-
-        pbar.desc = "Downloading"
-        with Pool(processes) as pool:
-            for i, result in enumerate(
-                pool.imap_unordered(_df_split_apply, pool_data, 2)
-            ):
-                results[str(result[0])] = result
-                pbar.update(len(result[1]))
-        pbar.close()
-
-    print("Finished Downloading.")
-    return
-
-
-# Unique name based on url
-def _file_name(row):
-    name = (
-        "%s/%s_%s"
-        % (
-            # row["folder"],
-            storage_dir,
-            row.name,
-            (zlib.crc32(row["url"].encode("utf-8")) & 0xFFFFFFFF),
-        )
-        + ".jpg"
-    )
-    return name
-
-
-# For checking mimetypes separately without download
-def check_mimetype(row):
-    if os.path.isfile(str(row["file"])):
-        row["mimetype"] = magic.from_file(row["file"], mime=True)
-        row["size"] = os.stat(row["file"]).st_size
-    return row
-
-
-# Don't download image, just check with a HEAD request, can't resume.
-# Can use this instead of download_image to get HTTP status codes.
-def check_download(row):
-    fname = _file_name(row)
-    try:
-        # not all sites will support HEAD
-        response = requests.head(
-            row["url"], stream=False, timeout=5, allow_redirects=True, headers=headers
-        )
-        row["status"] = response.status_code
-        row["headers"] = dict(response.headers)
-    except:
-        # log errors later, set error as 408 timeout
-        row["status"] = 408
-        return row
-    if response.ok:
-        row["file"] = fname
-    return row
-
-
-def resize_img(req):
-    image = Image.open(req).convert("RGB")
-    image = TF.resize(
-        # image, size=(resize_size, resize_size)
-        image,
-        size=resize_size,
-    )  # , interpolation=Image.LANCZOS)
-    return image
-
-
-def download_image(row):
-    fname = _file_name(row)
-    # Skip Already downloaded, retry others later
-    if os.path.isfile(fname):
-        row["status"] = 200
-        row["file"] = fname
-        row["mimetype"] = magic.from_file(row["file"], mime=True)
-        row["size"] = os.stat(row["file"]).st_size
-        return row
-
-    try:
-        # use smaller timeout to skip errors, but can result in failed downloads
-        response = requests.get(
-            row["url"], stream=False, timeout=5, allow_redirects=True, headers=headers
-        )
-        row["status"] = response.status_code
-        # row['headers'] = dict(response.headers)
-    except Exception as e:
-        # log errors later, set error as 408 timeout
-        row["status"] = 408
-        return row
-
-    if response.ok:
-        try:
-            # some sites respond with gzip transport encoding
-            response.raw.decode_content = True
-            img = resize_img(io.BytesIO(response.content))
-            img.save(fname)
-
-            row["mimetype"] = magic.from_file(fname, mime=True)
-            row["size"] = os.stat(fname).st_size
-
-        except Exception as e:
-            #     # This is if it times out during a download or decode
-            row["status"] = 408
-
-    row["file"] = fname
-    return row
-
-
-def open_tsv(fname, folder):
-    print("Opening %s Data File..." % fname)
-    df = pd.read_csv(
-        fname, sep="\t", names=["caption", "url"]
-    )  # , usecols=range(1, 2))
-    df["folder"] = folder
-    print("Processing", len(df), " Images:")
-    return df
-
-
-def df_from_shelve(chunk_size, func, dataset_name):
-    print("Generating Dataframe from results...")
-    with shelve.open(
-        "%s_%s_%s_results.tmp" % (dataset_name, func.__name__, chunk_size)
-    ) as results:
-        keylist = sorted([int(k) for k in results.keys()])
-        df = pd.concat([results[str(k)][1] for k in keylist], sort=True)
-    return df
-
-
-resize_size = 384
-
-config_path = get_abs_path("configs/datasets/conceptual_caption/defaults_3m.yaml")
-
-storage_dir = OmegaConf.load(
-    config_path
-).datasets.conceptual_caption_3m.build_info.images.storage
-storage_dir = Path(get_cache_path(storage_dir))
-
-os.makedirs(storage_dir, exist_ok=True)
-
-# number of processes in the pool can be larger than cores
-num_processes = 32
-# chunk_size is how many images per chunk per process - changing this resets progress when restarting.
-images_per_part = 100
-
-data_name = "cc3m"
-df = open_tsv("Train_GCC-training.tsv", data_name)
-df_multiprocess(
-    df=df,
-    processes=num_processes,
-    chunk_size=images_per_part,
-    func=download_image,
-    dataset_name=data_name,
-)
-df = df_from_shelve(
-    chunk_size=images_per_part, func=download_image, dataset_name=data_name
-)
-df.to_csv(
-    "downloaded_%s_report.tsv.gz" % data_name,
-    compression="gzip",
-    sep="\t",
-    header=False,
-    index=False,
-)
-print("Saved.")
diff --git a/spaces/ServerX/PorcoDiaz/demucs/model.py b/spaces/ServerX/PorcoDiaz/demucs/model.py
deleted file mode 100644
index e9d932f4d014f7b95b394d2e24ed5edc379ded8d..0000000000000000000000000000000000000000
--- a/spaces/ServerX/PorcoDiaz/demucs/model.py
+++ /dev/null
@@ -1,202 +0,0 @@
-# Copyright (c) Facebook, Inc. and its affiliates.
-# All rights reserved.
-#
-# This source code is licensed under the license found in the
-# LICENSE file in the root directory of this source tree.
-
-import math
-
-import julius
-from torch import nn
-
-from .utils import capture_init, center_trim
-
-
-class BLSTM(nn.Module):
-    def __init__(self, dim, layers=1):
-        super().__init__()
-        self.lstm = nn.LSTM(bidirectional=True, num_layers=layers, hidden_size=dim, input_size=dim)
-        self.linear = nn.Linear(2 * dim, dim)
-
-    def forward(self, x):
-        x = x.permute(2, 0, 1)
-        x = self.lstm(x)[0]
-        x = self.linear(x)
-        x = x.permute(1, 2, 0)
-        return x
-
-
-def rescale_conv(conv, reference):
-    std = conv.weight.std().detach()
-    scale = (std / reference)**0.5
-    conv.weight.data /= scale
-    if conv.bias is not None:
-        conv.bias.data /= scale
-
-
-def rescale_module(module, reference):
-    for sub in module.modules():
-        if isinstance(sub, (nn.Conv1d, nn.ConvTranspose1d)):
-            rescale_conv(sub, reference)
-
-
-class Demucs(nn.Module):
-    @capture_init
-    def __init__(self,
-                 sources,
-                 audio_channels=2,
-                 channels=64,
-                 depth=6,
-                 rewrite=True,
-                 glu=True,
-                 rescale=0.1,
-                 resample=True,
-                 kernel_size=8,
-                 stride=4,
-                 growth=2.,
-                 lstm_layers=2,
-                 context=3,
-                 normalize=False,
-                 samplerate=44100,
-                 segment_length=4 * 10 * 44100):
-        """
-        Args:
-            sources (list[str]): list of source names
-            audio_channels (int): stereo or mono
-            channels (int): first convolution channels
-            depth (int): number of encoder/decoder layers
-            rewrite (bool): add 1x1 convolution to each encoder layer
-                and a convolution to each decoder layer.
-                For the decoder layer, `context` gives the kernel size.
-            glu (bool): use glu instead of ReLU
-            resample_input (bool): upsample x2 the input and downsample /2 the output.
-            rescale (int): rescale initial weights of convolutions
-                to get their standard deviation closer to `rescale`
-            kernel_size (int): kernel size for convolutions
-            stride (int): stride for convolutions
-            growth (float): multiply (resp divide) number of channels by that
-                for each layer of the encoder (resp decoder)
-            lstm_layers (int): number of lstm layers, 0 = no lstm
-            context (int): kernel size of the convolution in the
-                decoder before the transposed convolution. If > 1,
-                will provide some context from neighboring time
-                steps.
-            samplerate (int): stored as meta information for easing
-                future evaluations of the model.
-            segment_length (int): stored as meta information for easing
-                future evaluations of the model. Length of the segments on which
-                the model was trained.
-        """
-
-        super().__init__()
-        self.audio_channels = audio_channels
-        self.sources = sources
-        self.kernel_size = kernel_size
-        self.context = context
-        self.stride = stride
-        self.depth = depth
-        self.resample = resample
-        self.channels = channels
-        self.normalize = normalize
-        self.samplerate = samplerate
-        self.segment_length = segment_length
-
-        self.encoder = nn.ModuleList()
-        self.decoder = nn.ModuleList()
-
-        if glu:
-            activation = nn.GLU(dim=1)
-            ch_scale = 2
-        else:
-            activation = nn.ReLU()
-            ch_scale = 1
-        in_channels = audio_channels
-        for index in range(depth):
-            encode = []
-            encode += [nn.Conv1d(in_channels, channels, kernel_size, stride), nn.ReLU()]
-            if rewrite:
-                encode += [nn.Conv1d(channels, ch_scale * channels, 1), activation]
-            self.encoder.append(nn.Sequential(*encode))
-
-            decode = []
-            if index > 0:
-                out_channels = in_channels
-            else:
-                out_channels = len(self.sources) * audio_channels
-            if rewrite:
-                decode += [nn.Conv1d(channels, ch_scale * channels, context), activation]
-            decode += [nn.ConvTranspose1d(channels, out_channels, kernel_size, stride)]
-            if index > 0:
-                decode.append(nn.ReLU())
-            self.decoder.insert(0, nn.Sequential(*decode))
-            in_channels = channels
-            channels = int(growth * channels)
-
-        channels = in_channels
-
-        if lstm_layers:
-            self.lstm = BLSTM(channels, lstm_layers)
-        else:
-            self.lstm = None
-
-        if rescale:
-            rescale_module(self, reference=rescale)
-
-    def valid_length(self, length):
-        """
-        Return the nearest valid length to use with the model so that
-        there is no time steps left over in a convolutions, e.g. for all
-        layers, size of the input - kernel_size % stride = 0.
-
-        If the mixture has a valid length, the estimated sources
-        will have exactly the same length when context = 1. If context > 1,
-        the two signals can be center trimmed to match.
-
-        For training, extracts should have a valid length.For evaluation
-        on full tracks we recommend passing `pad = True` to :method:`forward`.
-        """
-        if self.resample:
-            length *= 2
-        for _ in range(self.depth):
-            length = math.ceil((length - self.kernel_size) / self.stride) + 1
-            length = max(1, length)
-            length += self.context - 1
-        for _ in range(self.depth):
-            length = (length - 1) * self.stride + self.kernel_size
-
-        if self.resample:
-            length = math.ceil(length / 2)
-        return int(length)
-
-    def forward(self, mix):
-        x = mix
-
-        if self.normalize:
-            mono = mix.mean(dim=1, keepdim=True)
-            mean = mono.mean(dim=-1, keepdim=True)
-            std = mono.std(dim=-1, keepdim=True)
-        else:
-            mean = 0
-            std = 1
-
-        x = (x - mean) / (1e-5 + std)
-
-        if self.resample:
-            x = julius.resample_frac(x, 1, 2)
-
-        saved = []
-        for encode in self.encoder:
-            x = encode(x)
-            saved.append(x)
-        if self.lstm:
-            x = self.lstm(x)
-        for decode in self.decoder:
-            skip = center_trim(saved.pop(-1), x)
-            x = x + skip
-            x = decode(x)
-
-        if self.resample:
-            x = julius.resample_frac(x, 2, 1)
-        x = x * std + mean
-        x = x.view(x.size(0), len(self.sources), self.audio_channels, x.size(-1))
-        return x
diff --git a/spaces/SimFG/LangChain-Zilliz-Cloud/app.py b/spaces/SimFG/LangChain-Zilliz-Cloud/app.py
deleted file mode 100644
index 27156dd6ee9a5b202376a48d80057c0ce2166b58..0000000000000000000000000000000000000000
--- a/spaces/SimFG/LangChain-Zilliz-Cloud/app.py
+++ /dev/null
@@ -1,123 +0,0 @@
-from typing import Callable, Optional
-
-import gradio as gr
-from langchain.embeddings.openai import OpenAIEmbeddings
-from langchain.vectorstores import Zilliz
-from langchain.document_loaders import WebBaseLoader
-from langchain.text_splitter import CharacterTextSplitter
-from langchain.chains import RetrievalQAWithSourcesChain
-from langchain.llms import OpenAI
-
-chain: Optional[Callable] = None
-
-
-def web_loader(url_list, openai_key, zilliz_uri, user, password):
-    if not url_list:
-        return "please enter url list"
-    loader = WebBaseLoader(url_list.split())
-    docs = loader.load()
-
-    text_splitter = CharacterTextSplitter(chunk_size=1024, chunk_overlap=0)
-    docs = text_splitter.split_documents(docs)
-    embeddings = OpenAIEmbeddings(model="ada", openai_api_key=openai_key)
-
-    docsearch = Zilliz.from_documents(
-        docs,
-        embedding=embeddings,
-        connection_args={
-            "uri": zilliz_uri,
-            "user": user,
-            "password": password,
-            "secure": True,
-        },
-    )
-
-    global chain
-    chain = RetrievalQAWithSourcesChain.from_chain_type(
-        OpenAI(temperature=0, openai_api_key=openai_key),
-        chain_type="map_reduce",
-        retriever=docsearch.as_retriever(),
-    )
-    return "success to load data"
-
-
-def query(question):
-    global chain
-    # "What is milvus?"
-    if not chain:
-        return "please load the data first"
-    return chain(inputs={"question": question}, return_only_outputs=True).get(
-        "answer", "fail to get answer"
-    )
-
-
-if __name__ == "__main__":
-    block = gr.Blocks()
-    with block as demo:
-        gr.Markdown(
-            """
-        <h1><center>Langchain And Zilliz Cloud Example</center></h1>
-        This is how to use Zilliz Cloud as vector store in LangChain. 
-        The purpose of this example is to allow you to input multiple URLs (separated by newlines) and then ask questions about the content of the corresponding web pages.
-        
-        ## 📋 Prerequisite:
-
-        1. 🔑 To obtain an OpenAI key, please visit https://platform.openai.com/account/api-keys.
-        2. 💻 Create a Zilliz Cloud account to get free credits for usage by visiting https://cloud.zilliz.com.
-        3. 🗄️ Create a database in Zilliz Cloud.
-        
-        ## 📝 Steps for usage:
-
-        1. 🖋️ Fill in the url list input box with multiple URLs.
-        2. 🔑 Fill in the OpenAI API key in the openai api key input box.
-        3. 🌩️ Fill in the Zilliz Cloud connection parameters, including the connection URL, corresponding username, and password.
-        4. 🚀 Click the Load Data button to load the data. When the load status text box prompts that the data has been successfully loaded, proceed to the next step.
-        5. ❓ In the question input box, enter the relevant question about the web page.
-        6. 🔍 Click the Generate button to search for the answer to the question. The final answer will be displayed in the question answer text box.
-        """
-        )
-        url_list_text = gr.Textbox(
-            label="url list",
-            lines=3,
-            placeholder="https://milvus.io/docs/overview.md",
-        )
-        openai_key_text = gr.Textbox(label="openai api key", type="password", placeholder="sk-******")
-        with gr.Row():
-            zilliz_uri_text = gr.Textbox(
-                label="zilliz cloud uri",
-                placeholder="https://<instance-id>.<cloud-region-id>.vectordb.zillizcloud.com:<port>",
-            )
-            user_text = gr.Textbox(label="username", placeholder="db_admin")
-            password_text = gr.Textbox(
-                label="password", type="password", placeholder="******"
-            )
-        loader_output = gr.Textbox(label="load status")
-        loader_btn = gr.Button("Load Data")
-        loader_btn.click(
-            fn=web_loader,
-            inputs=[
-                url_list_text,
-                openai_key_text,
-                zilliz_uri_text,
-                user_text,
-                password_text,
-            ],
-            outputs=loader_output,
-            api_name="web_load",
-        )
-
-        question_text = gr.Textbox(
-            label="question",
-            lines=3,
-            placeholder="What is milvus?",
-        )
-        query_output = gr.Textbox(label="question answer", lines=3)
-        query_btn = gr.Button("Generate")
-        query_btn.click(
-            fn=query,
-            inputs=[question_text],
-            outputs=query_output,
-            api_name="generate_answer",
-        )
-
-        demo.queue().launch(server_name="0.0.0.0", share=False)
diff --git a/spaces/SkalskiP/SAM_and_MetaCLIP/README.md b/spaces/SkalskiP/SAM_and_MetaCLIP/README.md
deleted file mode 100644
index 07a6b7e34de038a83a0eb830631ba8ebb4e90f1c..0000000000000000000000000000000000000000
--- a/spaces/SkalskiP/SAM_and_MetaCLIP/README.md
+++ /dev/null
@@ -1,12 +0,0 @@
----
-title: SAM And MetaCLIP
-emoji: 👁
-colorFrom: pink
-colorTo: yellow
-sdk: gradio
-sdk_version: 3.50.2
-app_file: app.py
-pinned: false
----
-
-Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
diff --git a/spaces/Slava917/pronunciation-trainer/README.md b/spaces/Slava917/pronunciation-trainer/README.md
deleted file mode 100644
index a33bec35da8b807a3407feb7b1a6789e6e402a3c..0000000000000000000000000000000000000000
--- a/spaces/Slava917/pronunciation-trainer/README.md
+++ /dev/null
@@ -1,12 +0,0 @@
----
-title: Pronunciation Trainer
-emoji: 📉
-colorFrom: pink
-colorTo: yellow
-sdk: gradio
-sdk_version: 2.7.5.2
-app_file: app.py
-pinned: false
----
-
-Check out the configuration reference at https://huggingface.co/docs/hub/spaces#reference
diff --git a/spaces/Snowling/White-box-Cartoonization/app.py b/spaces/Snowling/White-box-Cartoonization/app.py
deleted file mode 100644
index c55ced56bd87a85f59d1c8ef84b7eca87422720f..0000000000000000000000000000000000000000
--- a/spaces/Snowling/White-box-Cartoonization/app.py
+++ /dev/null
@@ -1,108 +0,0 @@
-#!/usr/bin/env python
-
-from __future__ import annotations
-import argparse
-import functools
-import os
-import pathlib
-import sys
-from typing import Callable
-import uuid
-
-import gradio as gr
-import huggingface_hub
-import numpy as np
-import PIL.Image
-
-from io import BytesIO
-from wbc.cartoonize import Cartoonize
-
-ORIGINAL_REPO_URL = 'https://github.com/SystemErrorWang/White-box-Cartoonization'
-TITLE = 'SystemErrorWang/White-box-Cartoonization'
-DESCRIPTION = f"""This is a demo for {ORIGINAL_REPO_URL}.
-
-"""
-ARTICLE = """
-
-"""
-
-SAFEHASH = [x for x in "0123456789-abcdefghijklmnopqrstuvwxyz_ABCDEFGHIJKLMNOPQRSTUVWXYZ"]
-def compress_UUID():
-    '''
-    根据http://www.ietf.org/rfc/rfc1738.txt,由uuid编码扩bai大字符域生成du串
-    包括:[0-9a-zA-Z\-_]共64个
-    长度:(32-2)/3*2=20
-    备注:可在地球上人zhi人都用,使用100年不重复(2^120)
-    :return:String
-    '''
-    row = str(uuid.uuid4()).replace('-', '')
-    safe_code = ''
-    for i in range(10):
-        enbin = "%012d" % int(bin(int(row[i * 3] + row[i * 3 + 1] + row[i * 3 + 2], 16))[2:], 10)
-        safe_code += (SAFEHASH[int(enbin[0:6], 2)] + SAFEHASH[int(enbin[6:12], 2)])
-    safe_code = safe_code.replace('-', '')
-    return safe_code
-
-
-def parse_args() -> argparse.Namespace:
-    parser = argparse.ArgumentParser()
-    parser.add_argument('--device', type=str, default='cpu')
-    parser.add_argument('--theme', type=str)
-    parser.add_argument('--live', action='store_true')
-    parser.add_argument('--share', action='store_true')
-    parser.add_argument('--port', type=int)
-    parser.add_argument('--disable-queue',
-                        dest='enable_queue',
-                        action='store_false')
-    parser.add_argument('--allow-flagging', type=str, default='never')
-    parser.add_argument('--allow-screenshot', action='store_true')
-    return parser.parse_args()
-
-def run(
-        image,
-        cartoonize : Cartoonize
-) -> tuple[PIL.Image.Image]:
-
-    out_path = compress_UUID()+'.png'
-    cartoonize.run_sigle(image.name, out_path)
-
-    return PIL.Image.open(out_path)
-
-
-def main():
-    gr.close_all()
-
-    args = parse_args()
-
-    cartoonize = Cartoonize(os.path.join(os.path.dirname(os.path.abspath(__file__)),'wbc/saved_models/'))
-
-    func = functools.partial(run, cartoonize=cartoonize)
-    func = functools.update_wrapper(func, run)
-
-    gr.Interface(
-        func,
-        [
-            gr.inputs.Image(type='file', label='Input Image'),
-        ],
-        [
-            gr.outputs.Image(
-                type='pil',
-                label='Result'),
-        ],
-        # examples=examples,
-        theme=args.theme,
-        title=TITLE,
-        description=DESCRIPTION,
-        article=ARTICLE,
-        allow_screenshot=args.allow_screenshot,
-        allow_flagging=args.allow_flagging,
-        live=args.live,
-    ).launch(
-        enable_queue=args.enable_queue,
-        server_port=args.port,
-        share=args.share,
-    )
-
-
-if __name__ == '__main__':
-    main()
diff --git a/spaces/Solis/Solis/llm_src/demo.py b/spaces/Solis/Solis/llm_src/demo.py
deleted file mode 100644
index 7f5dc8f0078babf674d4f72e2035b9a03d8e2ddd..0000000000000000000000000000000000000000
--- a/spaces/Solis/Solis/llm_src/demo.py
+++ /dev/null
@@ -1,68 +0,0 @@
-import argparse
-import random
-
-from utils.cot.get_prompt import get_prompt
-from utils.decoder import Decoder, answer_cleansing
-from utils.fp_substitution import fp_substitute, get_nums_from_passage
-from utils.solis.solis_solver import try_search
-from utils.solis.helper import *
-
-
-def demo(decoder: Decoder, x: str, CNT_SUM):
-    random.seed(123)
-    args = get_default_argument()
-    prompt_x = get_prompt()
-    
-    orig_nums, _ = get_nums_from_passage(x)
-    if len(orig_nums) > 3:
-        return "Too many operands!"
-    orig_x = prompt_x + f"Q: {x}\nA:"
-    # step 0, original predict
-    try:
-        orig_z = decoder.decode(args, orig_x, CNT_SUM)
-        orig_z = answer_cleansing(args, orig_z)
-    except Exception as e:
-        print(e)
-        orig_z = "Too Frequent!"
-        return orig_z
-    
-    # step 1, #TODO skip operand proposal
-    # step 2, substitute
-    fp_data_list = fp_substitute(x, args.substitute_time)
-    fp_results = []
-    for fp_data in fp_data_list:
-        fp_x = prompt_x + f"Q: {fp_data['Question']}\nA:"
-        try:
-            fp_z = decoder.decode(args, fp_x, CNT_SUM)
-            fp_z = answer_cleansing(args, fp_z)
-        except Exception as e:
-            print(e)
-            fp_z = "Too Frequent!"
-            return fp_z
-        fp_results.append({
-            "fp_nums": fp_data["Alignments"],
-            "fp_z": fp_z,
-        })
-    # step 3, arith relationship inversion
-    solis_ret = try_search(args, orig_nums, fp_results)
-    print(solis_ret)
-    return solis_ret
-
-def get_default_argument():
-    parser = argparse.ArgumentParser(description="Solis")
-    parser.add_argument("--seed", type=int, default=123)
-    parser.add_argument("--api_time_interval", type=float, default=2)
-    parser.add_argument("--max_length", type=int, default=256)
-    parser.add_argument("--substitute_time", type=int, default=5)
-    parser.add_argument("--dataset", type=str, default="multiarith")
-    parser.add_argument("--direct_answer_trigger_for_fewshot", type=str, default="The answer is")
-    args = parser.parse_args()
-    return args
-
-if __name__ == "__main__":
-    test_examples = [
-        "Nancy uploaded 41 pictures to Facebook. She put 37 pics into one album and put the rest into 2 different albums. How many pictures were in each album?",
-    ]
-    decoder = Decoder()
-    for test_example in test_examples:
-        demo(decoder, test_example, 0)
\ No newline at end of file
diff --git a/spaces/Sonnt/Fracture_Webapp/mLogsFunctions/dataprocessing.py b/spaces/Sonnt/Fracture_Webapp/mLogsFunctions/dataprocessing.py
deleted file mode 100644
index 753e8e188c02fb732d1c539170e9203a42855154..0000000000000000000000000000000000000000
--- a/spaces/Sonnt/Fracture_Webapp/mLogsFunctions/dataprocessing.py
+++ /dev/null
@@ -1,14 +0,0 @@
-import pandas as pd
-import streamlit as st
-
-def columns_list(data:pd.DataFrame, no_depth:bool=None, no_well:bool=None):
-    columns_list = list(data.columns.unique())
-    columns_list.sort()
-    if "DEPTH" in columns_list and no_depth == True:
-        columns_list.remove("DEPTH")
-    if "WELL" in columns_list and no_well == True:
-        columns_list.remove("WELL")
-    return columns_list
-
-def well_filter(df, well_name):
-    return df[df.WELL == well_name]
\ No newline at end of file
diff --git a/spaces/SuYuanS/AudioCraft_Plus/audiocraft/modules/chroma.py b/spaces/SuYuanS/AudioCraft_Plus/audiocraft/modules/chroma.py
deleted file mode 100644
index e84fb66b4a4aaefb0b3ccac8a9a44c3b20e48f61..0000000000000000000000000000000000000000
--- a/spaces/SuYuanS/AudioCraft_Plus/audiocraft/modules/chroma.py
+++ /dev/null
@@ -1,66 +0,0 @@
-# Copyright (c) Meta Platforms, Inc. and affiliates.
-# All rights reserved.
-#
-# This source code is licensed under the license found in the
-# LICENSE file in the root directory of this source tree.
-import typing as tp
-
-from einops import rearrange
-from librosa import filters
-import torch
-from torch import nn
-import torch.nn.functional as F
-import torchaudio
-
-
-class ChromaExtractor(nn.Module):
-    """Chroma extraction and quantization.
-
-    Args:
-        sample_rate (int): Sample rate for the chroma extraction.
-        n_chroma (int): Number of chroma bins for the chroma extraction.
-        radix2_exp (int): Size of stft window for the chroma extraction (power of 2, e.g. 12 -> 2^12).
-        nfft (int, optional): Number of FFT.
-        winlen (int, optional): Window length.
-        winhop (int, optional): Window hop size.
-        argmax (bool, optional): Whether to use argmax. Defaults to False.
-        norm (float, optional): Norm for chroma normalization. Defaults to inf.
-    """
-    def __init__(self, sample_rate: int, n_chroma: int = 12, radix2_exp: int = 12, nfft: tp.Optional[int] = None,
-                 winlen: tp.Optional[int] = None, winhop: tp.Optional[int] = None, argmax: bool = False,
-                 norm: float = torch.inf):
-        super().__init__()
-        self.winlen = winlen or 2 ** radix2_exp
-        self.nfft = nfft or self.winlen
-        self.winhop = winhop or (self.winlen // 4)
-        self.sample_rate = sample_rate
-        self.n_chroma = n_chroma
-        self.norm = norm
-        self.argmax = argmax
-        self.register_buffer('fbanks', torch.from_numpy(filters.chroma(sr=sample_rate, n_fft=self.nfft, tuning=0,
-                                                                       n_chroma=self.n_chroma)), persistent=False)
-        self.spec = torchaudio.transforms.Spectrogram(n_fft=self.nfft, win_length=self.winlen,
-                                                      hop_length=self.winhop, power=2, center=True,
-                                                      pad=0, normalized=True)
-
-    def forward(self, wav: torch.Tensor) -> torch.Tensor:
-        T = wav.shape[-1]
-        # in case we are getting a wav that was dropped out (nullified)
-        # from the conditioner, make sure wav length is no less that nfft
-        if T < self.nfft:
-            pad = self.nfft - T
-            r = 0 if pad % 2 == 0 else 1
-            wav = F.pad(wav, (pad // 2, pad // 2 + r), 'constant', 0)
-            assert wav.shape[-1] == self.nfft, f"expected len {self.nfft} but got {wav.shape[-1]}"
-
-        spec = self.spec(wav).squeeze(1)
-        raw_chroma = torch.einsum('cf,...ft->...ct', self.fbanks, spec)
-        norm_chroma = torch.nn.functional.normalize(raw_chroma, p=self.norm, dim=-2, eps=1e-6)
-        norm_chroma = rearrange(norm_chroma, 'b d t -> b t d')
-
-        if self.argmax:
-            idx = norm_chroma.argmax(-1, keepdim=True)
-            norm_chroma[:] = 0
-            norm_chroma.scatter_(dim=-1, index=idx, value=1)
-
-        return norm_chroma
diff --git a/spaces/SungBeom/chatwine-korean/.venv/Lib/site-packages/clickhouse_connect/driver/npconv.py b/spaces/SungBeom/chatwine-korean/.venv/Lib/site-packages/clickhouse_connect/driver/npconv.py
deleted file mode 100644
index df99550d348a89dd4086050358591ac94ad50467..0000000000000000000000000000000000000000
--- a/spaces/SungBeom/chatwine-korean/.venv/Lib/site-packages/clickhouse_connect/driver/npconv.py
+++ /dev/null
@@ -1,9 +0,0 @@
-from clickhouse_connect.driver.options import np
-
-from clickhouse_connect.driver.types import ByteSource
-
-
-def read_numpy_array(source: ByteSource, np_type: str, num_rows: int):
-    dtype = np.dtype(np_type)
-    buffer = source.read_bytes(dtype.itemsize * num_rows)
-    return np.frombuffer(buffer, dtype, num_rows)
diff --git a/spaces/SungBeom/chatwine-korean/.venv/Lib/site-packages/debugpy/_vendored/pydevd/_pydev_bundle/pydev_monkey_qt.py b/spaces/SungBeom/chatwine-korean/.venv/Lib/site-packages/debugpy/_vendored/pydevd/_pydev_bundle/pydev_monkey_qt.py
deleted file mode 100644
index e348b842d4a02e91e772a08ea6703f3caf760280..0000000000000000000000000000000000000000
--- a/spaces/SungBeom/chatwine-korean/.venv/Lib/site-packages/debugpy/_vendored/pydevd/_pydev_bundle/pydev_monkey_qt.py
+++ /dev/null
@@ -1,216 +0,0 @@
-from __future__ import nested_scopes
-
-from _pydev_bundle._pydev_saved_modules import threading
-import os
-from _pydev_bundle import pydev_log
-
-
-def set_trace_in_qt():
-    from _pydevd_bundle.pydevd_comm import get_global_debugger
-    py_db = get_global_debugger()
-    if py_db is not None:
-        threading.current_thread()  # Create the dummy thread for qt.
-        py_db.enable_tracing()
-
-
-_patched_qt = False
-
-
-def patch_qt(qt_support_mode):
-    '''
-    This method patches qt (PySide2, PySide, PyQt4, PyQt5) so that we have hooks to set the tracing for QThread.
-    '''
-    if not qt_support_mode:
-        return
-
-    if qt_support_mode is True or qt_support_mode == 'True':
-        # do not break backward compatibility
-        qt_support_mode = 'auto'
-
-    if qt_support_mode == 'auto':
-        qt_support_mode = os.getenv('PYDEVD_PYQT_MODE', 'auto')
-
-    # Avoid patching more than once
-    global _patched_qt
-    if _patched_qt:
-        return
-
-    pydev_log.debug('Qt support mode: %s', qt_support_mode)
-
-    _patched_qt = True
-
-    if qt_support_mode == 'auto':
-
-        patch_qt_on_import = None
-        try:
-            import PySide2  # @UnresolvedImport @UnusedImport
-            qt_support_mode = 'pyside2'
-        except:
-            try:
-                import Pyside  # @UnresolvedImport @UnusedImport
-                qt_support_mode = 'pyside'
-            except:
-                try:
-                    import PyQt5  # @UnresolvedImport @UnusedImport
-                    qt_support_mode = 'pyqt5'
-                except:
-                    try:
-                        import PyQt4  # @UnresolvedImport @UnusedImport
-                        qt_support_mode = 'pyqt4'
-                    except:
-                        return
-
-    if qt_support_mode == 'pyside2':
-        try:
-            import PySide2.QtCore  # @UnresolvedImport
-            _internal_patch_qt(PySide2.QtCore, qt_support_mode)
-        except:
-            return
-
-    elif qt_support_mode == 'pyside':
-        try:
-            import PySide.QtCore  # @UnresolvedImport
-            _internal_patch_qt(PySide.QtCore, qt_support_mode)
-        except:
-            return
-
-    elif qt_support_mode == 'pyqt5':
-        try:
-            import PyQt5.QtCore  # @UnresolvedImport
-            _internal_patch_qt(PyQt5.QtCore)
-        except:
-            return
-
-    elif qt_support_mode == 'pyqt4':
-        # Ok, we have an issue here:
-        # PyDev-452: Selecting PyQT API version using sip.setapi fails in debug mode
-        # http://pyqt.sourceforge.net/Docs/PyQt4/incompatible_apis.html
-        # Mostly, if the user uses a different API version (i.e.: v2 instead of v1),
-        # that has to be done before importing PyQt4 modules (PySide/PyQt5 don't have this issue
-        # as they only implements v2).
-        patch_qt_on_import = 'PyQt4'
-
-        def get_qt_core_module():
-            import PyQt4.QtCore  # @UnresolvedImport
-            return PyQt4.QtCore
-
-        _patch_import_to_patch_pyqt_on_import(patch_qt_on_import, get_qt_core_module)
-
-    else:
-        raise ValueError('Unexpected qt support mode: %s' % (qt_support_mode,))
-
-
-def _patch_import_to_patch_pyqt_on_import(patch_qt_on_import, get_qt_core_module):
-    # I don't like this approach very much as we have to patch __import__, but I like even less
-    # asking the user to configure something in the client side...
-    # So, our approach is to patch PyQt4 right before the user tries to import it (at which
-    # point he should've set the sip api version properly already anyways).
-
-    pydev_log.debug('Setting up Qt post-import monkeypatch.')
-
-    dotted = patch_qt_on_import + '.'
-    original_import = __import__
-
-    from _pydev_bundle._pydev_sys_patch import patch_sys_module, patch_reload, cancel_patches_in_sys_module
-
-    patch_sys_module()
-    patch_reload()
-
-    def patched_import(name, *args, **kwargs):
-        if patch_qt_on_import == name or name.startswith(dotted):
-            builtins.__import__ = original_import
-            cancel_patches_in_sys_module()
-            _internal_patch_qt(get_qt_core_module())  # Patch it only when the user would import the qt module
-        return original_import(name, *args, **kwargs)
-
-    import builtins  # Py3
-
-    builtins.__import__ = patched_import
-
-
-def _internal_patch_qt(QtCore, qt_support_mode='auto'):
-    pydev_log.debug('Patching Qt: %s', QtCore)
-
-    _original_thread_init = QtCore.QThread.__init__
-    _original_runnable_init = QtCore.QRunnable.__init__
-    _original_QThread = QtCore.QThread
-
-    class FuncWrapper:
-
-        def __init__(self, original):
-            self._original = original
-
-        def __call__(self, *args, **kwargs):
-            set_trace_in_qt()
-            return self._original(*args, **kwargs)
-
-    class StartedSignalWrapper(QtCore.QObject):  # Wrapper for the QThread.started signal
-
-        try:
-            _signal = QtCore.Signal()  # @UndefinedVariable
-        except:
-            _signal = QtCore.pyqtSignal()  # @UndefinedVariable
-
-        def __init__(self, thread, original_started):
-            QtCore.QObject.__init__(self)
-            self.thread = thread
-            self.original_started = original_started
-            if qt_support_mode in ('pyside', 'pyside2'):
-                self._signal = original_started
-            else:
-                self._signal.connect(self._on_call)
-                self.original_started.connect(self._signal)
-
-        def connect(self, func, *args, **kwargs):
-            if qt_support_mode in ('pyside', 'pyside2'):
-                return self._signal.connect(FuncWrapper(func), *args, **kwargs)
-            else:
-                return self._signal.connect(func, *args, **kwargs)
-
-        def disconnect(self, *args, **kwargs):
-            return self._signal.disconnect(*args, **kwargs)
-
-        def emit(self, *args, **kwargs):
-            return self._signal.emit(*args, **kwargs)
-
-        def _on_call(self, *args, **kwargs):
-            set_trace_in_qt()
-
-    class ThreadWrapper(QtCore.QThread):  # Wrapper for QThread
-
-        def __init__(self, *args, **kwargs):
-            _original_thread_init(self, *args, **kwargs)
-
-            # In PyQt5 the program hangs when we try to call original run method of QThread class.
-            # So we need to distinguish instances of QThread class and instances of QThread inheritors.
-            if self.__class__.run == _original_QThread.run:
-                self.run = self._exec_run
-            else:
-                self._original_run = self.run
-                self.run = self._new_run
-            self._original_started = self.started
-            self.started = StartedSignalWrapper(self, self.started)
-
-        def _exec_run(self):
-            set_trace_in_qt()
-            self.exec_()
-            return None
-
-        def _new_run(self):
-            set_trace_in_qt()
-            return self._original_run()
-
-    class RunnableWrapper(QtCore.QRunnable):  # Wrapper for QRunnable
-
-        def __init__(self, *args, **kwargs):
-            _original_runnable_init(self, *args, **kwargs)
-
-            self._original_run = self.run
-            self.run = self._new_run
-
-        def _new_run(self):
-            set_trace_in_qt()
-            return self._original_run()
-
-    QtCore.QThread = ThreadWrapper
-    QtCore.QRunnable = RunnableWrapper
diff --git a/spaces/Suniilkumaar/SwapMukham/face_parsing/swap.py b/spaces/Suniilkumaar/SwapMukham/face_parsing/swap.py
deleted file mode 100644
index 0ae65e486b4cc2fa729a0992f28d922f45ada840..0000000000000000000000000000000000000000
--- a/spaces/Suniilkumaar/SwapMukham/face_parsing/swap.py
+++ /dev/null
@@ -1,133 +0,0 @@
-import torch
-import torch.nn as nn
-import torch.nn.functional as F
-import torchvision.transforms as transforms
-import cv2
-import numpy as np
-
-from .model import BiSeNet
-
-mask_regions = {
-    "Background":0,
-    "Skin":1,
-    "L-Eyebrow":2,
-    "R-Eyebrow":3,
-    "L-Eye":4,
-    "R-Eye":5,
-    "Eye-G":6,
-    "L-Ear":7,
-    "R-Ear":8,
-    "Ear-R":9,
-    "Nose":10,
-    "Mouth":11,
-    "U-Lip":12,
-    "L-Lip":13,
-    "Neck":14,
-    "Neck-L":15,
-    "Cloth":16,
-    "Hair":17,
-    "Hat":18
-}
-
-# Borrowed from simswap
-# https://github.com/neuralchen/SimSwap/blob/26c84d2901bd56eda4d5e3c5ca6da16e65dc82a6/util/reverse2original.py#L30
-class SoftErosion(nn.Module):
-    def __init__(self, kernel_size=15, threshold=0.6, iterations=1):
-        super(SoftErosion, self).__init__()
-        r = kernel_size // 2
-        self.padding = r
-        self.iterations = iterations
-        self.threshold = threshold
-
-        # Create kernel
-        y_indices, x_indices = torch.meshgrid(torch.arange(0., kernel_size), torch.arange(0., kernel_size))
-        dist = torch.sqrt((x_indices - r) ** 2 + (y_indices - r) ** 2)
-        kernel = dist.max() - dist
-        kernel /= kernel.sum()
-        kernel = kernel.view(1, 1, *kernel.shape)
-        self.register_buffer('weight', kernel)
-
-    def forward(self, x):
-        x = x.float()
-        for i in range(self.iterations - 1):
-            x = torch.min(x, F.conv2d(x, weight=self.weight, groups=x.shape[1], padding=self.padding))
-        x = F.conv2d(x, weight=self.weight, groups=x.shape[1], padding=self.padding)
-
-        mask = x >= self.threshold
-        x[mask] = 1.0
-        x[~mask] /= x[~mask].max()
-
-        return x, mask
-
-device = "cpu"
-
-def init_parser(pth_path, mode="cpu"):
-    global device
-    device = mode
-    n_classes = 19
-    net = BiSeNet(n_classes=n_classes)
-    if device == "cuda":
-        net.cuda()
-        net.load_state_dict(torch.load(pth_path))
-    else:
-        net.load_state_dict(torch.load(pth_path, map_location=torch.device('cpu')))
-    net.eval()
-    return net
-
-
-def image_to_parsing(img, net):
-    img = cv2.resize(img, (512, 512))
-    img = img[:,:,::-1]
-    transform = transforms.Compose([
-        transforms.ToTensor(),
-        transforms.Normalize((0.485, 0.456, 0.406), (0.229, 0.224, 0.225))
-    ])
-    img = transform(img.copy())
-    img = torch.unsqueeze(img, 0)
-
-    with torch.no_grad():
-        img = img.to(device)
-        out = net(img)[0]
-        parsing = out.squeeze(0).cpu().numpy().argmax(0)
-        return parsing
-
-
-def get_mask(parsing, classes):
-    res = parsing == classes[0]
-    for val in classes[1:]:
-        res += parsing == val
-    return res
-
-
-def swap_regions(source, target, net, smooth_mask, includes=[1,2,3,4,5,10,11,12,13], blur=10):
-    parsing = image_to_parsing(source, net)
-
-    if len(includes) == 0:
-        return source, np.zeros_like(source)
-
-    include_mask = get_mask(parsing, includes)
-    mask = np.repeat(include_mask[:, :, np.newaxis], 3, axis=2).astype("float32")
-
-    if smooth_mask is not None:
-        mask_tensor = torch.from_numpy(mask.copy().transpose((2, 0, 1))).float().to(device)
-        face_mask_tensor = mask_tensor[0] + mask_tensor[1]
-        soft_face_mask_tensor, _ = smooth_mask(face_mask_tensor.unsqueeze_(0).unsqueeze_(0))
-        soft_face_mask_tensor.squeeze_()
-        mask = np.repeat(soft_face_mask_tensor.cpu().numpy()[:, :, np.newaxis], 3, axis=2)
-
-    if blur > 0:
-        mask = cv2.GaussianBlur(mask, (0, 0), blur)
-
-    resized_source = cv2.resize((source).astype("float32"), (512, 512))
-    resized_target = cv2.resize((target).astype("float32"), (512, 512))
-    result = mask * resized_source + (1 - mask) * resized_target
-    result = cv2.resize(result.astype("uint8"), (source.shape[1], source.shape[0]))
-
-    return result
-
-def mask_regions_to_list(values):
-    out_ids = []
-    for value in values:
-        if value in mask_regions.keys():
-            out_ids.append(mask_regions.get(value))
-    return out_ids
diff --git a/spaces/Superlang/ImageComposition/app.py b/spaces/Superlang/ImageComposition/app.py
deleted file mode 100644
index 9b2f81027e725370471e4a7f15588312cae742d1..0000000000000000000000000000000000000000
--- a/spaces/Superlang/ImageComposition/app.py
+++ /dev/null
@@ -1,57 +0,0 @@
-import importlib
-import os
-from PIL import Image
-import gradio as gr
-from omegaconf import OmegaConf
-
-config = OmegaConf.load("config/annotator.yaml")
-
-package_annotator = "processor"
-
-
-def process_image(cls: str, fg: Image.Image, bg: Image.Image, *kwargs):
-    if fg.size != bg.size:
-        fg = fg.resize(bg.size)
-    module_imp = importlib.import_module(package_annotator)
-    model = getattr(module_imp, cls)
-    image_processor = model()
-    result = image_processor(fg, bg, *kwargs)
-    if type(result) == tuple:
-        return result
-    return [result]
-
-
-def process(cls):
-    def process_fc(img, res, *args):
-        return process_image(cls, img, res, *args)
-
-    return process_fc
-
-
-block = gr.Blocks().queue()
-examples = [[os.path.join(os.path.dirname(__file__), "example/product.png"),
-             os.path.join(os.path.dirname(__file__), "example/bg.png")]]
-with block:
-    for key in config.keys():
-        cls, input_element = config[key]["process"], config[key].get("input")
-        input_append = []
-        with gr.Tab(key):
-            with gr.Row():
-                gr.Markdown("## " + key)
-            with gr.Row():
-                with gr.Column():
-                    input_image = gr.Image(label="foreground", source='upload', type="pil", image_mode="RGBA")
-                    bg_image = gr.Image(label="background", source='upload', type="pil", image_mode="RGBA")
-                    if input_element is not None:
-                        for item in input_element:
-                            input_append.append(getattr(gr, item["attr"])(**item["args"]))
-                    run_button = gr.Button(label="Run")
-                    gr.Examples(examples, [input_image, bg_image])
-                with gr.Column():
-                    gallery = gr.Gallery(label="Generated images", show_label=False).style(height="auto")
-
-            run_button.click(fn=process(cls),
-                             inputs=[input_image, bg_image] + input_append,
-                             outputs=[gallery])
-
-block.launch()
diff --git a/spaces/Superlang/ImageProcessor/annotator/zoe/zoedepth/models/base_models/midas_repo/tf/run_onnx.py b/spaces/Superlang/ImageProcessor/annotator/zoe/zoedepth/models/base_models/midas_repo/tf/run_onnx.py
deleted file mode 100644
index 7107b99969a127f951814f743d5c562a436b2430..0000000000000000000000000000000000000000
--- a/spaces/Superlang/ImageProcessor/annotator/zoe/zoedepth/models/base_models/midas_repo/tf/run_onnx.py
+++ /dev/null
@@ -1,119 +0,0 @@
-"""Compute depth maps for images in the input folder.
-"""
-import os
-import glob
-import utils
-import cv2
-import sys
-import numpy as np
-import argparse
-
-import onnx
-import onnxruntime as rt
-
-from transforms import Resize, NormalizeImage, PrepareForNet
-
-
-def run(input_path, output_path, model_path, model_type="large"):
-    """Run MonoDepthNN to compute depth maps.
-
-    Args:
-        input_path (str): path to input folder
-        output_path (str): path to output folder
-        model_path (str): path to saved model
-    """
-    print("initialize")
-
-    # select device
-    device = "CUDA:0"
-    #device = "CPU"
-    print("device: %s" % device)
-
-    # network resolution
-    if model_type == "large":
-        net_w, net_h = 384, 384
-    elif model_type == "small":
-        net_w, net_h = 256, 256
-    else:
-        print(f"model_type '{model_type}' not implemented, use: --model_type large")
-        assert False
-
-    # load network
-    print("loading model...")
-    model = rt.InferenceSession(model_path)
-    input_name = model.get_inputs()[0].name
-    output_name = model.get_outputs()[0].name
-
-    resize_image = Resize(
-                net_w,
-                net_h,
-                resize_target=None,
-                keep_aspect_ratio=False,
-                ensure_multiple_of=32,
-                resize_method="upper_bound",
-                image_interpolation_method=cv2.INTER_CUBIC,
-            )
-    
-    def compose2(f1, f2):
-        return lambda x: f2(f1(x))
-
-    transform = compose2(resize_image, PrepareForNet())
-
-    # get input
-    img_names = glob.glob(os.path.join(input_path, "*"))
-    num_images = len(img_names)
-
-    # create output folder
-    os.makedirs(output_path, exist_ok=True)
-
-    print("start processing")
-
-    for ind, img_name in enumerate(img_names):
-
-        print("  processing {} ({}/{})".format(img_name, ind + 1, num_images))
-
-        # input
-        img = utils.read_image(img_name)
-        img_input = transform({"image": img})["image"]
-
-        # compute
-        output = model.run([output_name], {input_name: img_input.reshape(1, 3, net_h, net_w).astype(np.float32)})[0]
-        prediction = np.array(output).reshape(net_h, net_w)
-        prediction = cv2.resize(prediction, (img.shape[1], img.shape[0]), interpolation=cv2.INTER_CUBIC)
-       
-        # output
-        filename = os.path.join(
-            output_path, os.path.splitext(os.path.basename(img_name))[0]
-        )
-        utils.write_depth(filename, prediction, bits=2)
-
-    print("finished")
-
-
-if __name__ == "__main__":
-    parser = argparse.ArgumentParser()
-
-    parser.add_argument('-i', '--input_path', 
-        default='input',
-        help='folder with input images'
-    )
-
-    parser.add_argument('-o', '--output_path', 
-        default='output',
-        help='folder for output images'
-    )
-
-    parser.add_argument('-m', '--model_weights', 
-        default='model-f6b98070.onnx',
-        help='path to the trained weights of model'
-    )
-
-    parser.add_argument('-t', '--model_type', 
-        default='large',
-        help='model type: large or small'
-    )
-
-    args = parser.parse_args()
-
-    # compute depth maps
-    run(args.input_path, args.output_path, args.model_weights, args.model_type)
diff --git a/spaces/TRaw/dtet/README.md b/spaces/TRaw/dtet/README.md
deleted file mode 100644
index 8936dea47ba363c737d8348383e5809f781bc5fd..0000000000000000000000000000000000000000
--- a/spaces/TRaw/dtet/README.md
+++ /dev/null
@@ -1,13 +0,0 @@
----
-title: Chat Ui Template
-emoji: 🚀
-colorFrom: indigo
-colorTo: blue
-sdk: docker
-pinned: false
-app_port: 3000
-suggested_hardware: a10g-small
-duplicated_from: huggingchat/chat-ui-template
----
-
-Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
diff --git a/spaces/TencentARC/VLog/models/grit_src/third_party/CenterNet2/detectron2/modeling/roi_heads/roi_heads.py b/spaces/TencentARC/VLog/models/grit_src/third_party/CenterNet2/detectron2/modeling/roi_heads/roi_heads.py
deleted file mode 100644
index 13dd57a0478917001841f6c6299f380e1198e63a..0000000000000000000000000000000000000000
--- a/spaces/TencentARC/VLog/models/grit_src/third_party/CenterNet2/detectron2/modeling/roi_heads/roi_heads.py
+++ /dev/null
@@ -1,877 +0,0 @@
-# Copyright (c) Facebook, Inc. and its affiliates.
-import inspect
-import logging
-import numpy as np
-from typing import Dict, List, Optional, Tuple
-import torch
-from torch import nn
-
-from detectron2.config import configurable
-from detectron2.layers import ShapeSpec, nonzero_tuple
-from detectron2.structures import Boxes, ImageList, Instances, pairwise_iou
-from detectron2.utils.events import get_event_storage
-from detectron2.utils.registry import Registry
-
-from ..backbone.resnet import BottleneckBlock, ResNet
-from ..matcher import Matcher
-from ..poolers import ROIPooler
-from ..proposal_generator.proposal_utils import add_ground_truth_to_proposals
-from ..sampling import subsample_labels
-from .box_head import build_box_head
-from .fast_rcnn import FastRCNNOutputLayers
-from .keypoint_head import build_keypoint_head
-from .mask_head import build_mask_head
-
-ROI_HEADS_REGISTRY = Registry("ROI_HEADS")
-ROI_HEADS_REGISTRY.__doc__ = """
-Registry for ROI heads in a generalized R-CNN model.
-ROIHeads take feature maps and region proposals, and
-perform per-region computation.
-
-The registered object will be called with `obj(cfg, input_shape)`.
-The call is expected to return an :class:`ROIHeads`.
-"""
-
-logger = logging.getLogger(__name__)
-
-
-def build_roi_heads(cfg, input_shape):
-    """
-    Build ROIHeads defined by `cfg.MODEL.ROI_HEADS.NAME`.
-    """
-    name = cfg.MODEL.ROI_HEADS.NAME
-    return ROI_HEADS_REGISTRY.get(name)(cfg, input_shape)
-
-
-def select_foreground_proposals(
-    proposals: List[Instances], bg_label: int
-) -> Tuple[List[Instances], List[torch.Tensor]]:
-    """
-    Given a list of N Instances (for N images), each containing a `gt_classes` field,
-    return a list of Instances that contain only instances with `gt_classes != -1 &&
-    gt_classes != bg_label`.
-
-    Args:
-        proposals (list[Instances]): A list of N Instances, where N is the number of
-            images in the batch.
-        bg_label: label index of background class.
-
-    Returns:
-        list[Instances]: N Instances, each contains only the selected foreground instances.
-        list[Tensor]: N boolean vector, correspond to the selection mask of
-            each Instances object. True for selected instances.
-    """
-    assert isinstance(proposals, (list, tuple))
-    assert isinstance(proposals[0], Instances)
-    assert proposals[0].has("gt_classes")
-    fg_proposals = []
-    fg_selection_masks = []
-    for proposals_per_image in proposals:
-        gt_classes = proposals_per_image.gt_classes
-        fg_selection_mask = (gt_classes != -1) & (gt_classes != bg_label)
-        fg_idxs = fg_selection_mask.nonzero().squeeze(1)
-        fg_proposals.append(proposals_per_image[fg_idxs])
-        fg_selection_masks.append(fg_selection_mask)
-    return fg_proposals, fg_selection_masks
-
-
-def select_proposals_with_visible_keypoints(proposals: List[Instances]) -> List[Instances]:
-    """
-    Args:
-        proposals (list[Instances]): a list of N Instances, where N is the
-            number of images.
-
-    Returns:
-        proposals: only contains proposals with at least one visible keypoint.
-
-    Note that this is still slightly different from Detectron.
-    In Detectron, proposals for training keypoint head are re-sampled from
-    all the proposals with IOU>threshold & >=1 visible keypoint.
-
-    Here, the proposals are first sampled from all proposals with
-    IOU>threshold, then proposals with no visible keypoint are filtered out.
-    This strategy seems to make no difference on Detectron and is easier to implement.
-    """
-    ret = []
-    all_num_fg = []
-    for proposals_per_image in proposals:
-        # If empty/unannotated image (hard negatives), skip filtering for train
-        if len(proposals_per_image) == 0:
-            ret.append(proposals_per_image)
-            continue
-        gt_keypoints = proposals_per_image.gt_keypoints.tensor
-        # #fg x K x 3
-        vis_mask = gt_keypoints[:, :, 2] >= 1
-        xs, ys = gt_keypoints[:, :, 0], gt_keypoints[:, :, 1]
-        proposal_boxes = proposals_per_image.proposal_boxes.tensor.unsqueeze(dim=1)  # #fg x 1 x 4
-        kp_in_box = (
-            (xs >= proposal_boxes[:, :, 0])
-            & (xs <= proposal_boxes[:, :, 2])
-            & (ys >= proposal_boxes[:, :, 1])
-            & (ys <= proposal_boxes[:, :, 3])
-        )
-        selection = (kp_in_box & vis_mask).any(dim=1)
-        selection_idxs = nonzero_tuple(selection)[0]
-        all_num_fg.append(selection_idxs.numel())
-        ret.append(proposals_per_image[selection_idxs])
-
-    storage = get_event_storage()
-    storage.put_scalar("keypoint_head/num_fg_samples", np.mean(all_num_fg))
-    return ret
-
-
-class ROIHeads(torch.nn.Module):
-    """
-    ROIHeads perform all per-region computation in an R-CNN.
-
-    It typically contains logic to
-
-    1. (in training only) match proposals with ground truth and sample them
-    2. crop the regions and extract per-region features using proposals
-    3. make per-region predictions with different heads
-
-    It can have many variants, implemented as subclasses of this class.
-    This base class contains the logic to match/sample proposals.
-    But it is not necessary to inherit this class if the sampling logic is not needed.
-    """
-
-    @configurable
-    def __init__(
-        self,
-        *,
-        num_classes,
-        batch_size_per_image,
-        positive_fraction,
-        proposal_matcher,
-        proposal_append_gt=True,
-    ):
-        """
-        NOTE: this interface is experimental.
-
-        Args:
-            num_classes (int): number of foreground classes (i.e. background is not included)
-            batch_size_per_image (int): number of proposals to sample for training
-            positive_fraction (float): fraction of positive (foreground) proposals
-                to sample for training.
-            proposal_matcher (Matcher): matcher that matches proposals and ground truth
-            proposal_append_gt (bool): whether to include ground truth as proposals as well
-        """
-        super().__init__()
-        self.batch_size_per_image = batch_size_per_image
-        self.positive_fraction = positive_fraction
-        self.num_classes = num_classes
-        self.proposal_matcher = proposal_matcher
-        self.proposal_append_gt = proposal_append_gt
-
-    @classmethod
-    def from_config(cls, cfg):
-        return {
-            "batch_size_per_image": cfg.MODEL.ROI_HEADS.BATCH_SIZE_PER_IMAGE,
-            "positive_fraction": cfg.MODEL.ROI_HEADS.POSITIVE_FRACTION,
-            "num_classes": cfg.MODEL.ROI_HEADS.NUM_CLASSES,
-            "proposal_append_gt": cfg.MODEL.ROI_HEADS.PROPOSAL_APPEND_GT,
-            # Matcher to assign box proposals to gt boxes
-            "proposal_matcher": Matcher(
-                cfg.MODEL.ROI_HEADS.IOU_THRESHOLDS,
-                cfg.MODEL.ROI_HEADS.IOU_LABELS,
-                allow_low_quality_matches=False,
-            ),
-        }
-
-    def _sample_proposals(
-        self, matched_idxs: torch.Tensor, matched_labels: torch.Tensor, gt_classes: torch.Tensor
-    ) -> Tuple[torch.Tensor, torch.Tensor]:
-        """
-        Based on the matching between N proposals and M groundtruth,
-        sample the proposals and set their classification labels.
-
-        Args:
-            matched_idxs (Tensor): a vector of length N, each is the best-matched
-                gt index in [0, M) for each proposal.
-            matched_labels (Tensor): a vector of length N, the matcher's label
-                (one of cfg.MODEL.ROI_HEADS.IOU_LABELS) for each proposal.
-            gt_classes (Tensor): a vector of length M.
-
-        Returns:
-            Tensor: a vector of indices of sampled proposals. Each is in [0, N).
-            Tensor: a vector of the same length, the classification label for
-                each sampled proposal. Each sample is labeled as either a category in
-                [0, num_classes) or the background (num_classes).
-        """
-        has_gt = gt_classes.numel() > 0
-        # Get the corresponding GT for each proposal
-        if has_gt:
-            gt_classes = gt_classes[matched_idxs]
-            # Label unmatched proposals (0 label from matcher) as background (label=num_classes)
-            gt_classes[matched_labels == 0] = self.num_classes
-            # Label ignore proposals (-1 label)
-            gt_classes[matched_labels == -1] = -1
-        else:
-            gt_classes = torch.zeros_like(matched_idxs) + self.num_classes
-
-        sampled_fg_idxs, sampled_bg_idxs = subsample_labels(
-            gt_classes, self.batch_size_per_image, self.positive_fraction, self.num_classes
-        )
-
-        sampled_idxs = torch.cat([sampled_fg_idxs, sampled_bg_idxs], dim=0)
-        return sampled_idxs, gt_classes[sampled_idxs]
-
-    @torch.no_grad()
-    def label_and_sample_proposals(
-        self, proposals: List[Instances], targets: List[Instances]
-    ) -> List[Instances]:
-        """
-        Prepare some proposals to be used to train the ROI heads.
-        It performs box matching between `proposals` and `targets`, and assigns
-        training labels to the proposals.
-        It returns ``self.batch_size_per_image`` random samples from proposals and groundtruth
-        boxes, with a fraction of positives that is no larger than
-        ``self.positive_fraction``.
-
-        Args:
-            See :meth:`ROIHeads.forward`
-
-        Returns:
-            list[Instances]:
-                length `N` list of `Instances`s containing the proposals
-                sampled for training. Each `Instances` has the following fields:
-
-                - proposal_boxes: the proposal boxes
-                - gt_boxes: the ground-truth box that the proposal is assigned to
-                  (this is only meaningful if the proposal has a label > 0; if label = 0
-                  then the ground-truth box is random)
-
-                Other fields such as "gt_classes", "gt_masks", that's included in `targets`.
-        """
-        # Augment proposals with ground-truth boxes.
-        # In the case of learned proposals (e.g., RPN), when training starts
-        # the proposals will be low quality due to random initialization.
-        # It's possible that none of these initial
-        # proposals have high enough overlap with the gt objects to be used
-        # as positive examples for the second stage components (box head,
-        # cls head, mask head). Adding the gt boxes to the set of proposals
-        # ensures that the second stage components will have some positive
-        # examples from the start of training. For RPN, this augmentation improves
-        # convergence and empirically improves box AP on COCO by about 0.5
-        # points (under one tested configuration).
-        if self.proposal_append_gt:
-            proposals = add_ground_truth_to_proposals(targets, proposals)
-
-        proposals_with_gt = []
-
-        num_fg_samples = []
-        num_bg_samples = []
-        for proposals_per_image, targets_per_image in zip(proposals, targets):
-            has_gt = len(targets_per_image) > 0
-            match_quality_matrix = pairwise_iou(
-                targets_per_image.gt_boxes, proposals_per_image.proposal_boxes
-            )
-            matched_idxs, matched_labels = self.proposal_matcher(match_quality_matrix)
-            sampled_idxs, gt_classes = self._sample_proposals(
-                matched_idxs, matched_labels, targets_per_image.gt_classes
-            )
-
-            # Set target attributes of the sampled proposals:
-            proposals_per_image = proposals_per_image[sampled_idxs]
-            proposals_per_image.gt_classes = gt_classes
-
-            if has_gt:
-                sampled_targets = matched_idxs[sampled_idxs]
-                # We index all the attributes of targets that start with "gt_"
-                # and have not been added to proposals yet (="gt_classes").
-                # NOTE: here the indexing waste some compute, because heads
-                # like masks, keypoints, etc, will filter the proposals again,
-                # (by foreground/background, or number of keypoints in the image, etc)
-                # so we essentially index the data twice.
-                for (trg_name, trg_value) in targets_per_image.get_fields().items():
-                    if trg_name.startswith("gt_") and not proposals_per_image.has(trg_name):
-                        proposals_per_image.set(trg_name, trg_value[sampled_targets])
-            # If no GT is given in the image, we don't know what a dummy gt value can be.
-            # Therefore the returned proposals won't have any gt_* fields, except for a
-            # gt_classes full of background label.
-
-            num_bg_samples.append((gt_classes == self.num_classes).sum().item())
-            num_fg_samples.append(gt_classes.numel() - num_bg_samples[-1])
-            proposals_with_gt.append(proposals_per_image)
-
-        # Log the number of fg/bg samples that are selected for training ROI heads
-        storage = get_event_storage()
-        storage.put_scalar("roi_head/num_fg_samples", np.mean(num_fg_samples))
-        storage.put_scalar("roi_head/num_bg_samples", np.mean(num_bg_samples))
-
-        return proposals_with_gt
-
-    def forward(
-        self,
-        images: ImageList,
-        features: Dict[str, torch.Tensor],
-        proposals: List[Instances],
-        targets: Optional[List[Instances]] = None,
-    ) -> Tuple[List[Instances], Dict[str, torch.Tensor]]:
-        """
-        Args:
-            images (ImageList):
-            features (dict[str,Tensor]): input data as a mapping from feature
-                map name to tensor. Axis 0 represents the number of images `N` in
-                the input data; axes 1-3 are channels, height, and width, which may
-                vary between feature maps (e.g., if a feature pyramid is used).
-            proposals (list[Instances]): length `N` list of `Instances`. The i-th
-                `Instances` contains object proposals for the i-th input image,
-                with fields "proposal_boxes" and "objectness_logits".
-            targets (list[Instances], optional): length `N` list of `Instances`. The i-th
-                `Instances` contains the ground-truth per-instance annotations
-                for the i-th input image.  Specify `targets` during training only.
-                It may have the following fields:
-
-                - gt_boxes: the bounding box of each instance.
-                - gt_classes: the label for each instance with a category ranging in [0, #class].
-                - gt_masks: PolygonMasks or BitMasks, the ground-truth masks of each instance.
-                - gt_keypoints: NxKx3, the groud-truth keypoints for each instance.
-
-        Returns:
-            list[Instances]: length `N` list of `Instances` containing the
-            detected instances. Returned during inference only; may be [] during training.
-
-            dict[str->Tensor]:
-            mapping from a named loss to a tensor storing the loss. Used during training only.
-        """
-        raise NotImplementedError()
-
-
-@ROI_HEADS_REGISTRY.register()
-class Res5ROIHeads(ROIHeads):
-    """
-    The ROIHeads in a typical "C4" R-CNN model, where
-    the box and mask head share the cropping and
-    the per-region feature computation by a Res5 block.
-    See :paper:`ResNet` Appendix A.
-    """
-
-    @configurable
-    def __init__(
-        self,
-        *,
-        in_features: List[str],
-        pooler: ROIPooler,
-        res5: nn.Module,
-        box_predictor: nn.Module,
-        mask_head: Optional[nn.Module] = None,
-        **kwargs,
-    ):
-        """
-        NOTE: this interface is experimental.
-
-        Args:
-            in_features (list[str]): list of backbone feature map names to use for
-                feature extraction
-            pooler (ROIPooler): pooler to extra region features from backbone
-            res5 (nn.Sequential): a CNN to compute per-region features, to be used by
-                ``box_predictor`` and ``mask_head``. Typically this is a "res5"
-                block from a ResNet.
-            box_predictor (nn.Module): make box predictions from the feature.
-                Should have the same interface as :class:`FastRCNNOutputLayers`.
-            mask_head (nn.Module): transform features to make mask predictions
-        """
-        super().__init__(**kwargs)
-        self.in_features = in_features
-        self.pooler = pooler
-        if isinstance(res5, (list, tuple)):
-            res5 = nn.Sequential(*res5)
-        self.res5 = res5
-        self.box_predictor = box_predictor
-        self.mask_on = mask_head is not None
-        if self.mask_on:
-            self.mask_head = mask_head
-
-    @classmethod
-    def from_config(cls, cfg, input_shape):
-        # fmt: off
-        ret = super().from_config(cfg)
-        in_features = ret["in_features"] = cfg.MODEL.ROI_HEADS.IN_FEATURES
-        pooler_resolution = cfg.MODEL.ROI_BOX_HEAD.POOLER_RESOLUTION
-        pooler_type       = cfg.MODEL.ROI_BOX_HEAD.POOLER_TYPE
-        pooler_scales     = (1.0 / input_shape[in_features[0]].stride, )
-        sampling_ratio    = cfg.MODEL.ROI_BOX_HEAD.POOLER_SAMPLING_RATIO
-        mask_on           = cfg.MODEL.MASK_ON
-        # fmt: on
-        assert not cfg.MODEL.KEYPOINT_ON
-        assert len(in_features) == 1
-
-        ret["pooler"] = ROIPooler(
-            output_size=pooler_resolution,
-            scales=pooler_scales,
-            sampling_ratio=sampling_ratio,
-            pooler_type=pooler_type,
-        )
-
-        # Compatbility with old moco code. Might be useful.
-        # See notes in StandardROIHeads.from_config
-        if not inspect.ismethod(cls._build_res5_block):
-            logger.warning(
-                "The behavior of _build_res5_block may change. "
-                "Please do not depend on private methods."
-            )
-            cls._build_res5_block = classmethod(cls._build_res5_block)
-
-        ret["res5"], out_channels = cls._build_res5_block(cfg)
-        ret["box_predictor"] = FastRCNNOutputLayers(
-            cfg, ShapeSpec(channels=out_channels, height=1, width=1)
-        )
-
-        if mask_on:
-            ret["mask_head"] = build_mask_head(
-                cfg,
-                ShapeSpec(channels=out_channels, width=pooler_resolution, height=pooler_resolution),
-            )
-        return ret
-
-    @classmethod
-    def _build_res5_block(cls, cfg):
-        # fmt: off
-        stage_channel_factor = 2 ** 3  # res5 is 8x res2
-        num_groups           = cfg.MODEL.RESNETS.NUM_GROUPS
-        width_per_group      = cfg.MODEL.RESNETS.WIDTH_PER_GROUP
-        bottleneck_channels  = num_groups * width_per_group * stage_channel_factor
-        out_channels         = cfg.MODEL.RESNETS.RES2_OUT_CHANNELS * stage_channel_factor
-        stride_in_1x1        = cfg.MODEL.RESNETS.STRIDE_IN_1X1
-        norm                 = cfg.MODEL.RESNETS.NORM
-        assert not cfg.MODEL.RESNETS.DEFORM_ON_PER_STAGE[-1], \
-            "Deformable conv is not yet supported in res5 head."
-        # fmt: on
-
-        blocks = ResNet.make_stage(
-            BottleneckBlock,
-            3,
-            stride_per_block=[2, 1, 1],
-            in_channels=out_channels // 2,
-            bottleneck_channels=bottleneck_channels,
-            out_channels=out_channels,
-            num_groups=num_groups,
-            norm=norm,
-            stride_in_1x1=stride_in_1x1,
-        )
-        return nn.Sequential(*blocks), out_channels
-
-    def _shared_roi_transform(self, features: List[torch.Tensor], boxes: List[Boxes]):
-        x = self.pooler(features, boxes)
-        return self.res5(x)
-
-    def forward(
-        self,
-        images: ImageList,
-        features: Dict[str, torch.Tensor],
-        proposals: List[Instances],
-        targets: Optional[List[Instances]] = None,
-    ):
-        """
-        See :meth:`ROIHeads.forward`.
-        """
-        del images
-
-        if self.training:
-            assert targets
-            proposals = self.label_and_sample_proposals(proposals, targets)
-        del targets
-
-        proposal_boxes = [x.proposal_boxes for x in proposals]
-        box_features = self._shared_roi_transform(
-            [features[f] for f in self.in_features], proposal_boxes
-        )
-        predictions = self.box_predictor(box_features.mean(dim=[2, 3]))
-
-        if self.training:
-            del features
-            losses = self.box_predictor.losses(predictions, proposals)
-            if self.mask_on:
-                proposals, fg_selection_masks = select_foreground_proposals(
-                    proposals, self.num_classes
-                )
-                # Since the ROI feature transform is shared between boxes and masks,
-                # we don't need to recompute features. The mask loss is only defined
-                # on foreground proposals, so we need to select out the foreground
-                # features.
-                mask_features = box_features[torch.cat(fg_selection_masks, dim=0)]
-                del box_features
-                losses.update(self.mask_head(mask_features, proposals))
-            return [], losses
-        else:
-            pred_instances, _ = self.box_predictor.inference(predictions, proposals)
-            pred_instances = self.forward_with_given_boxes(features, pred_instances)
-            return pred_instances, {}
-
-    def forward_with_given_boxes(
-        self, features: Dict[str, torch.Tensor], instances: List[Instances]
-    ) -> List[Instances]:
-        """
-        Use the given boxes in `instances` to produce other (non-box) per-ROI outputs.
-
-        Args:
-            features: same as in `forward()`
-            instances (list[Instances]): instances to predict other outputs. Expect the keys
-                "pred_boxes" and "pred_classes" to exist.
-
-        Returns:
-            instances (Instances):
-                the same `Instances` object, with extra
-                fields such as `pred_masks` or `pred_keypoints`.
-        """
-        assert not self.training
-        assert instances[0].has("pred_boxes") and instances[0].has("pred_classes")
-
-        if self.mask_on:
-            feature_list = [features[f] for f in self.in_features]
-            x = self._shared_roi_transform(feature_list, [x.pred_boxes for x in instances])
-            return self.mask_head(x, instances)
-        else:
-            return instances
-
-
-@ROI_HEADS_REGISTRY.register()
-class StandardROIHeads(ROIHeads):
-    """
-    It's "standard" in a sense that there is no ROI transform sharing
-    or feature sharing between tasks.
-    Each head independently processes the input features by each head's
-    own pooler and head.
-
-    This class is used by most models, such as FPN and C5.
-    To implement more models, you can subclass it and implement a different
-    :meth:`forward()` or a head.
-    """
-
-    @configurable
-    def __init__(
-        self,
-        *,
-        box_in_features: List[str],
-        box_pooler: ROIPooler,
-        box_head: nn.Module,
-        box_predictor: nn.Module,
-        mask_in_features: Optional[List[str]] = None,
-        mask_pooler: Optional[ROIPooler] = None,
-        mask_head: Optional[nn.Module] = None,
-        keypoint_in_features: Optional[List[str]] = None,
-        keypoint_pooler: Optional[ROIPooler] = None,
-        keypoint_head: Optional[nn.Module] = None,
-        train_on_pred_boxes: bool = False,
-        **kwargs,
-    ):
-        """
-        NOTE: this interface is experimental.
-
-        Args:
-            box_in_features (list[str]): list of feature names to use for the box head.
-            box_pooler (ROIPooler): pooler to extra region features for box head
-            box_head (nn.Module): transform features to make box predictions
-            box_predictor (nn.Module): make box predictions from the feature.
-                Should have the same interface as :class:`FastRCNNOutputLayers`.
-            mask_in_features (list[str]): list of feature names to use for the mask
-                pooler or mask head. None if not using mask head.
-            mask_pooler (ROIPooler): pooler to extract region features from image features.
-                The mask head will then take region features to make predictions.
-                If None, the mask head will directly take the dict of image features
-                defined by `mask_in_features`
-            mask_head (nn.Module): transform features to make mask predictions
-            keypoint_in_features, keypoint_pooler, keypoint_head: similar to ``mask_*``.
-            train_on_pred_boxes (bool): whether to use proposal boxes or
-                predicted boxes from the box head to train other heads.
-        """
-        super().__init__(**kwargs)
-        # keep self.in_features for backward compatibility
-        self.in_features = self.box_in_features = box_in_features
-        self.box_pooler = box_pooler
-        self.box_head = box_head
-        self.box_predictor = box_predictor
-
-        self.mask_on = mask_in_features is not None
-        if self.mask_on:
-            self.mask_in_features = mask_in_features
-            self.mask_pooler = mask_pooler
-            self.mask_head = mask_head
-
-        self.keypoint_on = keypoint_in_features is not None
-        if self.keypoint_on:
-            self.keypoint_in_features = keypoint_in_features
-            self.keypoint_pooler = keypoint_pooler
-            self.keypoint_head = keypoint_head
-
-        self.train_on_pred_boxes = train_on_pred_boxes
-
-    @classmethod
-    def from_config(cls, cfg, input_shape):
-        ret = super().from_config(cfg)
-        ret["train_on_pred_boxes"] = cfg.MODEL.ROI_BOX_HEAD.TRAIN_ON_PRED_BOXES
-        # Subclasses that have not been updated to use from_config style construction
-        # may have overridden _init_*_head methods. In this case, those overridden methods
-        # will not be classmethods and we need to avoid trying to call them here.
-        # We test for this with ismethod which only returns True for bound methods of cls.
-        # Such subclasses will need to handle calling their overridden _init_*_head methods.
-        if inspect.ismethod(cls._init_box_head):
-            ret.update(cls._init_box_head(cfg, input_shape))
-        if inspect.ismethod(cls._init_mask_head):
-            ret.update(cls._init_mask_head(cfg, input_shape))
-        if inspect.ismethod(cls._init_keypoint_head):
-            ret.update(cls._init_keypoint_head(cfg, input_shape))
-        return ret
-
-    @classmethod
-    def _init_box_head(cls, cfg, input_shape):
-        # fmt: off
-        in_features       = cfg.MODEL.ROI_HEADS.IN_FEATURES
-        pooler_resolution = cfg.MODEL.ROI_BOX_HEAD.POOLER_RESOLUTION
-        pooler_scales     = tuple(1.0 / input_shape[k].stride for k in in_features)
-        sampling_ratio    = cfg.MODEL.ROI_BOX_HEAD.POOLER_SAMPLING_RATIO
-        pooler_type       = cfg.MODEL.ROI_BOX_HEAD.POOLER_TYPE
-        # fmt: on
-
-        # If StandardROIHeads is applied on multiple feature maps (as in FPN),
-        # then we share the same predictors and therefore the channel counts must be the same
-        in_channels = [input_shape[f].channels for f in in_features]
-        # Check all channel counts are equal
-        assert len(set(in_channels)) == 1, in_channels
-        in_channels = in_channels[0]
-
-        box_pooler = ROIPooler(
-            output_size=pooler_resolution,
-            scales=pooler_scales,
-            sampling_ratio=sampling_ratio,
-            pooler_type=pooler_type,
-        )
-        # Here we split "box head" and "box predictor", which is mainly due to historical reasons.
-        # They are used together so the "box predictor" layers should be part of the "box head".
-        # New subclasses of ROIHeads do not need "box predictor"s.
-        box_head = build_box_head(
-            cfg, ShapeSpec(channels=in_channels, height=pooler_resolution, width=pooler_resolution)
-        )
-        box_predictor = FastRCNNOutputLayers(cfg, box_head.output_shape)
-        return {
-            "box_in_features": in_features,
-            "box_pooler": box_pooler,
-            "box_head": box_head,
-            "box_predictor": box_predictor,
-        }
-
-    @classmethod
-    def _init_mask_head(cls, cfg, input_shape):
-        if not cfg.MODEL.MASK_ON:
-            return {}
-        # fmt: off
-        in_features       = cfg.MODEL.ROI_HEADS.IN_FEATURES
-        pooler_resolution = cfg.MODEL.ROI_MASK_HEAD.POOLER_RESOLUTION
-        pooler_scales     = tuple(1.0 / input_shape[k].stride for k in in_features)
-        sampling_ratio    = cfg.MODEL.ROI_MASK_HEAD.POOLER_SAMPLING_RATIO
-        pooler_type       = cfg.MODEL.ROI_MASK_HEAD.POOLER_TYPE
-        # fmt: on
-
-        in_channels = [input_shape[f].channels for f in in_features][0]
-
-        ret = {"mask_in_features": in_features}
-        ret["mask_pooler"] = (
-            ROIPooler(
-                output_size=pooler_resolution,
-                scales=pooler_scales,
-                sampling_ratio=sampling_ratio,
-                pooler_type=pooler_type,
-            )
-            if pooler_type
-            else None
-        )
-        if pooler_type:
-            shape = ShapeSpec(
-                channels=in_channels, width=pooler_resolution, height=pooler_resolution
-            )
-        else:
-            shape = {f: input_shape[f] for f in in_features}
-        ret["mask_head"] = build_mask_head(cfg, shape)
-        return ret
-
-    @classmethod
-    def _init_keypoint_head(cls, cfg, input_shape):
-        if not cfg.MODEL.KEYPOINT_ON:
-            return {}
-        # fmt: off
-        in_features       = cfg.MODEL.ROI_HEADS.IN_FEATURES
-        pooler_resolution = cfg.MODEL.ROI_KEYPOINT_HEAD.POOLER_RESOLUTION
-        pooler_scales     = tuple(1.0 / input_shape[k].stride for k in in_features)  # noqa
-        sampling_ratio    = cfg.MODEL.ROI_KEYPOINT_HEAD.POOLER_SAMPLING_RATIO
-        pooler_type       = cfg.MODEL.ROI_KEYPOINT_HEAD.POOLER_TYPE
-        # fmt: on
-
-        in_channels = [input_shape[f].channels for f in in_features][0]
-
-        ret = {"keypoint_in_features": in_features}
-        ret["keypoint_pooler"] = (
-            ROIPooler(
-                output_size=pooler_resolution,
-                scales=pooler_scales,
-                sampling_ratio=sampling_ratio,
-                pooler_type=pooler_type,
-            )
-            if pooler_type
-            else None
-        )
-        if pooler_type:
-            shape = ShapeSpec(
-                channels=in_channels, width=pooler_resolution, height=pooler_resolution
-            )
-        else:
-            shape = {f: input_shape[f] for f in in_features}
-        ret["keypoint_head"] = build_keypoint_head(cfg, shape)
-        return ret
-
-    def forward(
-        self,
-        images: ImageList,
-        features: Dict[str, torch.Tensor],
-        proposals: List[Instances],
-        targets: Optional[List[Instances]] = None,
-    ) -> Tuple[List[Instances], Dict[str, torch.Tensor]]:
-        """
-        See :class:`ROIHeads.forward`.
-        """
-        del images
-        if self.training:
-            assert targets, "'targets' argument is required during training"
-            proposals = self.label_and_sample_proposals(proposals, targets)
-        del targets
-
-        if self.training:
-            losses = self._forward_box(features, proposals)
-            # Usually the original proposals used by the box head are used by the mask, keypoint
-            # heads. But when `self.train_on_pred_boxes is True`, proposals will contain boxes
-            # predicted by the box head.
-            losses.update(self._forward_mask(features, proposals))
-            losses.update(self._forward_keypoint(features, proposals))
-            return proposals, losses
-        else:
-            pred_instances = self._forward_box(features, proposals)
-            # During inference cascaded prediction is used: the mask and keypoints heads are only
-            # applied to the top scoring box detections.
-            pred_instances = self.forward_with_given_boxes(features, pred_instances)
-            return pred_instances, {}
-
-    def forward_with_given_boxes(
-        self, features: Dict[str, torch.Tensor], instances: List[Instances]
-    ) -> List[Instances]:
-        """
-        Use the given boxes in `instances` to produce other (non-box) per-ROI outputs.
-
-        This is useful for downstream tasks where a box is known, but need to obtain
-        other attributes (outputs of other heads).
-        Test-time augmentation also uses this.
-
-        Args:
-            features: same as in `forward()`
-            instances (list[Instances]): instances to predict other outputs. Expect the keys
-                "pred_boxes" and "pred_classes" to exist.
-
-        Returns:
-            list[Instances]:
-                the same `Instances` objects, with extra
-                fields such as `pred_masks` or `pred_keypoints`.
-        """
-        assert not self.training
-        assert instances[0].has("pred_boxes") and instances[0].has("pred_classes")
-
-        instances = self._forward_mask(features, instances)
-        instances = self._forward_keypoint(features, instances)
-        return instances
-
-    def _forward_box(self, features: Dict[str, torch.Tensor], proposals: List[Instances]):
-        """
-        Forward logic of the box prediction branch. If `self.train_on_pred_boxes is True`,
-            the function puts predicted boxes in the `proposal_boxes` field of `proposals` argument.
-
-        Args:
-            features (dict[str, Tensor]): mapping from feature map names to tensor.
-                Same as in :meth:`ROIHeads.forward`.
-            proposals (list[Instances]): the per-image object proposals with
-                their matching ground truth.
-                Each has fields "proposal_boxes", and "objectness_logits",
-                "gt_classes", "gt_boxes".
-
-        Returns:
-            In training, a dict of losses.
-            In inference, a list of `Instances`, the predicted instances.
-        """
-        features = [features[f] for f in self.box_in_features]
-        box_features = self.box_pooler(features, [x.proposal_boxes for x in proposals])
-        box_features = self.box_head(box_features)
-        predictions = self.box_predictor(box_features)
-        del box_features
-
-        if self.training:
-            losses = self.box_predictor.losses(predictions, proposals)
-            # proposals is modified in-place below, so losses must be computed first.
-            if self.train_on_pred_boxes:
-                with torch.no_grad():
-                    pred_boxes = self.box_predictor.predict_boxes_for_gt_classes(
-                        predictions, proposals
-                    )
-                    for proposals_per_image, pred_boxes_per_image in zip(proposals, pred_boxes):
-                        proposals_per_image.proposal_boxes = Boxes(pred_boxes_per_image)
-            return losses
-        else:
-            pred_instances, _ = self.box_predictor.inference(predictions, proposals)
-            return pred_instances
-
-    def _forward_mask(self, features: Dict[str, torch.Tensor], instances: List[Instances]):
-        """
-        Forward logic of the mask prediction branch.
-
-        Args:
-            features (dict[str, Tensor]): mapping from feature map names to tensor.
-                Same as in :meth:`ROIHeads.forward`.
-            instances (list[Instances]): the per-image instances to train/predict masks.
-                In training, they can be the proposals.
-                In inference, they can be the boxes predicted by R-CNN box head.
-
-        Returns:
-            In training, a dict of losses.
-            In inference, update `instances` with new fields "pred_masks" and return it.
-        """
-        if not self.mask_on:
-            return {} if self.training else instances
-
-        if self.training:
-            # head is only trained on positive proposals.
-            instances, _ = select_foreground_proposals(instances, self.num_classes)
-
-        if self.mask_pooler is not None:
-            features = [features[f] for f in self.mask_in_features]
-            boxes = [x.proposal_boxes if self.training else x.pred_boxes for x in instances]
-            features = self.mask_pooler(features, boxes)
-        else:
-            features = {f: features[f] for f in self.mask_in_features}
-        return self.mask_head(features, instances)
-
-    def _forward_keypoint(self, features: Dict[str, torch.Tensor], instances: List[Instances]):
-        """
-        Forward logic of the keypoint prediction branch.
-
-        Args:
-            features (dict[str, Tensor]): mapping from feature map names to tensor.
-                Same as in :meth:`ROIHeads.forward`.
-            instances (list[Instances]): the per-image instances to train/predict keypoints.
-                In training, they can be the proposals.
-                In inference, they can be the boxes predicted by R-CNN box head.
-
-        Returns:
-            In training, a dict of losses.
-            In inference, update `instances` with new fields "pred_keypoints" and return it.
-        """
-        if not self.keypoint_on:
-            return {} if self.training else instances
-
-        if self.training:
-            # head is only trained on positive proposals with >=1 visible keypoints.
-            instances, _ = select_foreground_proposals(instances, self.num_classes)
-            instances = select_proposals_with_visible_keypoints(instances)
-
-        if self.keypoint_pooler is not None:
-            features = [features[f] for f in self.keypoint_in_features]
-            boxes = [x.proposal_boxes if self.training else x.pred_boxes for x in instances]
-            features = self.keypoint_pooler(features, boxes)
-        else:
-            features = {f: features[f] for f in self.keypoint_in_features}
-        return self.keypoint_head(features, instances)
diff --git a/spaces/Tetel/secondbing/EdgeGPT/__init__.py b/spaces/Tetel/secondbing/EdgeGPT/__init__.py
deleted file mode 100644
index e69de29bb2d1d6434b8b29ae775ad8c2e48c5391..0000000000000000000000000000000000000000
diff --git a/spaces/Toxfu/BIgVisionEffnetB2/model.py b/spaces/Toxfu/BIgVisionEffnetB2/model.py
deleted file mode 100644
index 52c2696c874740179528f0bdae8ce87b774a138f..0000000000000000000000000000000000000000
--- a/spaces/Toxfu/BIgVisionEffnetB2/model.py
+++ /dev/null
@@ -1,36 +0,0 @@
-import torch
-import torchvision
-
-from torch import nn
-
-
-def create_effnetb2_model(num_classes:int=3, 
-                          seed:int=42):
-    """Creates an EfficientNetB2 feature extractor model and transforms.
-
-    Args:
-        num_classes (int, optional): number of classes in the classifier head. 
-            Defaults to 3.
-        seed (int, optional): random seed value. Defaults to 42.
-
-    Returns:
-        model (torch.nn.Module): EffNetB2 feature extractor model. 
-        transforms (torchvision.transforms): EffNetB2 image transforms.
-    """
-    # Create EffNetB2 pretrained weights, transforms and model
-    weights = torchvision.models.EfficientNet_B2_Weights.DEFAULT
-    transforms = weights.transforms()
-    model = torchvision.models.efficientnet_b2(weights=weights)
-
-    # Freeze all layers in base model
-    for param in model.parameters():
-        param.requires_grad = False
-
-    # Change classifier head with random seed for reproducibility
-    torch.manual_seed(seed)
-    model.classifier = nn.Sequential(
-        nn.Dropout(p=0.3, inplace=True),
-        nn.Linear(in_features=1408, out_features=num_classes),
-    )
-    
-    return model, transforms
diff --git a/spaces/Uppuluri/mychatbotai/app.py b/spaces/Uppuluri/mychatbotai/app.py
deleted file mode 100644
index 2dbf3ae89c2e3fdab7134107dd346f984dca8eb1..0000000000000000000000000000000000000000
--- a/spaces/Uppuluri/mychatbotai/app.py
+++ /dev/null
@@ -1,34 +0,0 @@
-import os
-import gradio as gr
-from langchain.chat_models import ChatOpenAI
-from langchain import LLMChain, PromptTemplate
-from langchain.memory import ConversationBufferMemory
-
-OPENAI_API_KEY=os.getenv('OPENAI_API_KEY')
-
-template = """Meet Riya, your youthful and witty personal assistant! At 21 years old, she's full of energy and always eager to help. Riya's goal is to assist you with any questions or problems you might have. Her enthusiasm shines through in every response, making interactions with her enjoyable and engaging.
-{chat_history}
-User: {user_message}
-Chatbot:"""
-
-prompt = PromptTemplate(
-    input_variables=["chat_history", "user_message"], template=template
-)
-
-memory = ConversationBufferMemory(memory_key="chat_history")
-
-llm_chain = LLMChain(
-    llm=ChatOpenAI(temperature='0.5', model_name="gpt-3.5-turbo"),
-    prompt=prompt,
-    verbose=True,
-    memory=memory,
-)
-
-def get_text_response(user_message,history):
-    response = llm_chain.predict(user_message = user_message)
-    return response
-
-demo = gr.ChatInterface(get_text_response)
-
-if __name__ == "__main__":
-    demo.launch() #To create a public link, set `share=True` in `launch()`. To enable errors and logs, set `debug=True` in `launch()`.
diff --git a/spaces/VGG1555/VGG1/README.md b/spaces/VGG1555/VGG1/README.md
deleted file mode 100644
index a77f0699171af01cd870ccf0d950e683160d1293..0000000000000000000000000000000000000000
--- a/spaces/VGG1555/VGG1/README.md
+++ /dev/null
@@ -1,13 +0,0 @@
----
-title: VGG1
-emoji: 🐢
-colorFrom: green
-colorTo: red
-sdk: streamlit
-sdk_version: 1.21.0
-app_file: app.py
-pinned: false
-license: openrail
----
-
-Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
diff --git a/spaces/Vipitis/ShaderEval/ShaderEval.py b/spaces/Vipitis/ShaderEval/ShaderEval.py
deleted file mode 100644
index 0ea60f9bc64966519e12d8ec90f821669fc2360e..0000000000000000000000000000000000000000
--- a/spaces/Vipitis/ShaderEval/ShaderEval.py
+++ /dev/null
@@ -1,242 +0,0 @@
-# Copyright 2020 The HuggingFace Datasets Authors and the current dataset script contributor.
-#
-# #TODO: license: MIT pending (evaluation suite itself can be completely open, nothing copyleft from the dataset reaches us here)
-"""TODO: Add a description here."""
-
-# TODO: Add BibTeX citation
-_CITATION = """\
-@InProceedings{huggingface:module,
-title = {A great new module},
-authors={huggingface, Inc.},
-year={2023}
-}
-"""
-
-# TODO: Add description of the module here
-_DESCRIPTION = """\
-This EvaluationSuite currently solves {1} tasks to test code intelligence of genereative language models for "creative programming" (fragment shaders).
-"""
-
-
-
-
-# via https://huggingface.co/docs/evaluate/evaluation_suite
-import evaluate
-from evaluate import evaluator #used by Suite.run()
-from evaluate.evaluator.utils import DatasetColumn # used in .prepare_data()
-from evaluate.evaluation_suite import SubTask
-from datasets import Dataset
-from typing import Any, Callable, Dict, List, Optional, Union # used in .prepare_pipeline()
-import transformers
-from transformers import Pipeline, pipeline, GenerationConfig, AutoTokenizer #GenerationConfig to specify greedy and avoid error
-from datasets import load_dataset #used by Suite.run()
-
-# write a custom evaluator, inherent from: https://github.com/huggingface/evaluate/blob/v0.4.0/src/evaluate/evaluator/text_generation.py#L31
-class ReturnGenerationEvaluator(evaluate.TextGenerationEvaluator):
-    def __init__(self, task="text-generation", default_metric_name="exact_match", predictions_prefix: str = "generated"):
-        super().__init__(task=task, default_metric_name=default_metric_name)
-        self.predictions_prefix = predictions_prefix
-
-    greedy_cfg = GenerationConfig(
-        do_sample = False, # default to ensure greedy
-        num_beams = 1, # same as above
-    )
-    PIPELINE_KWARGS = {"return_full_text": False, "generation_config":greedy_cfg} #these kwargs are for the pipeline call, not the pipeline init - but that seems to still work.
-    
-    # for the pipeline init we need to copy the whole function and add two lines. this still prints errors due to the pad_toke_id = eos_token_id change.
-    # from: https://github.com/huggingface/evaluate/blob/v0.4.0/src/evaluate/evaluator/base.py#L375
-    def prepare_pipeline(
-        self,
-        model_or_pipeline: Union[str, "Pipeline", Callable, "PreTrainedModel", "TFPreTrainedModel"],  # noqa: F821
-        tokenizer: Union["PreTrainedTokenizerBase", "FeatureExtractionMixin"] = None,  # noqa: F821
-        feature_extractor: Union["PreTrainedTokenizerBase", "FeatureExtractionMixin"] = None,  # noqa: F821
-        device: int = None,
-    ):
-        """
-        Prepare pipeline.
-        Args:
-            model_or_pipeline (`str` or `Pipeline` or `Callable` or `PreTrainedModel` or `TFPreTrainedModel`,
-            defaults to `None`):
-                If the argument in not specified, we initialize the default pipeline for the task. If the argument is of the type `str` or
-                is a model instance, we use it to initialize a new `Pipeline` with the given model. Otherwise we assume the
-                argument specifies a pre-initialized pipeline.
-            preprocessor (`PreTrainedTokenizerBase` or `FeatureExtractionMixin`, *optional*, defaults to `None`):
-                Argument can be used to overwrite a default preprocessor if `model_or_pipeline` represents a model for
-                which we build a pipeline. If `model_or_pipeline` is `None` or a pre-initialized pipeline, we ignore
-                this argument.
-        Returns:
-            The initialized pipeline, with modifications for the specific task of generating text, even with long inputs.
-        """
-
-        if device is None:
-            device = self._infer_device()
-
-        if (
-            isinstance(model_or_pipeline, str)
-            or isinstance(model_or_pipeline, transformers.PreTrainedModel)
-            or isinstance(model_or_pipeline, transformers.TFPreTrainedModel)
-        ):
-            if isinstance(model_or_pipeline, str):
-                # load tokenizer manually, since the pipeline does fail to do so at times. needed for bigcode/santacoder for example.
-                tokenizer = AutoTokenizer.from_pretrained(model_or_pipeline, trust_remote_code=True)
-                
-            pipe = pipeline(
-                self.task,
-                model=model_or_pipeline,
-                tokenizer=tokenizer,
-                feature_extractor=feature_extractor,
-                device=device,
-                # my additions here:
-                handle_long_generation= "hole", #our solution? relevant: https://github.com/huggingface/transformers/issues/14033#issuecomment-948385227
-                # pad_token_id=tokenizer.eos_token_id, #to avoid the warning, however there might be issues as tokenizers will call this differently.
-                do_sample=False, #important to get reproduceable results but we need to make sure the generator is deterministic
-                trust_remote_code=True, # do we need this for some custom models? need to test if it works right here. one example is bigcode/santacoder
-            )
-        else:
-            if model_or_pipeline is None:
-                pipe = pipeline(self.task, device=device)
-            else:
-                pipe = model_or_pipeline
-            # if tokenizer is not None and feature_extractor is not None:
-                # logger.warning("Ignoring the value of the preprocessor argument (`tokenizer` or `feature_extractor`).") #excluded warning because I didn't import logger
-        if (pipe.task != self.task) and not (self.task == "translation" and pipe.task.startswith("translation")):
-            raise ValueError(
-                f"Incompatible `model_or_pipeline`. Please specify `model_or_pipeline` compatible with the `{self.task}` task."
-            )
-        
-        # fixinging default for max_lenght 
-        pipe.model.config.max_length = self._resolve_context_lenght(pipe=pipe)
-
-        # update the generation config with information from the pipe
-        self._update_generation_config(pipe)
-
-        return pipe
-
-    def _update_generation_config(self, pipe):
-        """
-        Update the generation config with information from the pipe. Sets eos_token_id and pad_token_id.
-        Args:
-            pipe (:class:`~transformers.Pipeline`): we need to access the tokenizer.vocab
-        returns:
-            None
-        """
-        semicolon_token_ids = [v for k,v in pipe.tokenizer.vocab.items() if ";" in k] # this requires the tokenizer, which we only have once a pipe is made.
-        # GenerationConfig.update also exists, but it does only replace, not add kwargs.
-        self.greedy_cfg.eos_token_id = semicolon_token_ids # eos_token_id can be a list, so we give them all possible tokens.
-        self.greedy_cfg.pad_token_id = semicolon_token_ids[0] # pad_token_id has to be an int, so we just take the first one.
-        return None # doesn't do anything?
-
-    def _resolve_context_lenght(self, model_or_pipeline=None, pipe=None): #TODO should really copy the typing hints here.
-        if isinstance(model_or_pipeline, transformers.GPT2Model): # you are comparing a string here -.-
-            return model_or_pipeline.config.n_ctx # how GPT2 models might handle is, seen with 
-        if pipe is not None: #should I figure out a way to pass this.
-            return pipe.tokenizer.model_max_length # this is set to something small for pipeline default task, but we would want to put it to the max instead.
-        # tokenizer needs to know the context length for our pipe strategy, but it has to be passed to the tokenizer, not model.
-        # the tokenizer should read from the model config, but that can be wrong, or it has a task overwrite (for "text-generation" for example you get 50)
-        #model_or_pipeline only exists via the .compute call, so we have to take it in
-        # model_or_pipeline.tokenier.config.max_new_tokens = 1024 # we shouldn't return it, but overwrite the tokenizer config, which the pipeline relies on.
-
-        return 1024 # we shouldn't return it, but overwrite the tokenizer config, which the pipeline relies on. 
-    
-    def _estimate_stopping(self, labels, **kwargs):
-        """ estimates max_new_tokens for the pipeline call
-            by counting the characters in the  longest string of the references adding 5 (for good measure but probably not needed)
-        Args:
-            labels: A list of dicts by knowing the labels
-        Returns:
-            `int`: the estimated max_new_tokens, should be smaller than context_lenght in all cases
-        """
-        context_lenght = self._resolve_context_lenght(**kwargs)
-        estimate = min(max([len(ref) for ref in labels]) + 5, context_lenght) #does the min call get done inside the pipeline anyway? is there even a single case where the return statement is this long?
-        return estimate
-
-    # this one needs to be adjusted 
-    def predictions_processor(self, predictions, *args, **kwargs):
-        """
-        processes the output of the pipeline to be compatible with the metric.
-        generated texts cut off by the first semicolon and whitespaces are stripped (using python str builtins)
-        Args:
-            predictions: A list of lists of dicts
-        Returns:
-            `dict`: All the processed text are flattened and stored under the "predictions" key.
-        """
-        return {"predictions": [pred[f"{self.predictions_prefix}_text"].split(";")[0].strip() for pred_list in predictions for pred in pred_list]}
-    
-    # straight copy, doesn't seem to give me the 
-    def prepare_data(self, data: Dataset, input_column: str, label_column: str, *args, **kwargs):
-        """
-        Prepare data.
-        Args:
-            data (`Dataset`): Specifies the dataset we will run evaluation on.
-            input_column (`str`, defaults to `"text"`):
-                the name of the column containing the text feature in the dataset specified by `data`.
-            label_column (`str`, defaults to `"label"`):
-                the name of the column containing the labels in the dataset specified by `data`.
-        Returns:
-            `dict`:  metric inputs. everything before the first semicolon and whitespaces are stripped (using python str builtins, just like the  pred prep)
-            `list`:  pipeline inputs.
-        """
-
-        self.check_required_columns(data, {"input_column": input_column, "label_column": label_column}) #this will throw and exception with useful error messages
-        
-        # don't put everything in the return statement, so you have the control...
-        references = [ref.split(";")[0].strip() for ref in data[label_column]]
-        self.PIPELINE_KWARGS.update({"max_new_tokens": self._estimate_stopping(references)}) #this is a hack, does it work tho?
-
-        return {"references": references}, data[input_column] #DatasetColumn(data, input_column) doesn't seem to work. data[input_column] does, but ignores any of the features of the helper class..
-
-
-
-# via: https://huggingface.co/docs/evaluate/evaluation_suite
-# relevant source: https://github.com/huggingface/evaluate/blob/v0.4.0/src/evaluate/evaluation_suite/__init__.py
-class Suite(evaluate.EvaluationSuite):
-
-
-    def __init__(self, name):
-        super().__init__(name)
-        self.preprocessor = lambda x: {"return_statement": x["return_statement"].split(";")[0]} #like this? refactored to RetrunGenerationEvaluator
-        self.suite = [
-            # more subtasks are only possible once we can pass custom evaluators. -> https://github.com/huggingface/evaluate/pull/367
-            SubTask( #this one is adjusted already
-                task_type="text-generation", #this call an evaluator, but can you specify your own custom evaluator instead?
-                data="Vipitis/Shadertoys-fine",
-                subset="return_completion",
-                split="test", # use this to select a subset of the data during testing, perhaps remove later?
-                args_for_task={
-                    # "metric": "exact_match",
-                    "input_column": "body",
-                    "label_column": "return_statement",
-                }
-            )
-        ]
-
-    # from: https://github.com/huggingface/evaluate/blob/v0.4.0/src/evaluate/evaluation_suite/__init__.py#LL103C5-L129C27
-    def run(
-        self, model_or_pipeline: Union[str, "Pipeline", Callable, "PreTrainedModel", "TFPreTrainedModel"] = "Vipitis/santacoder-finetuned-Shadertoys-fine", #not so useful default model?
-        snippet: int = "" # noqa: F821 
-    ) -> Dict[str, float]:
-
-        self.assert_suite_nonempty()
-
-        results_all = []
-        for task in self.suite:
-
-            task_name = task.data
-
-            if task.data_preprocessor:  # task requires extra preprocessing is all done inside the Evaluator
-                ds = load_dataset(task.data, name=task.subset, split=(task.split + f"[:{snippet}]"))
-                task.data = ds.map(task.data_preprocessor)
-
-            task_evaluator = ReturnGenerationEvaluator() #this is the change we make: specify our custom evaluator from above.
-            args_for_task = task.args_for_task
-            args_for_task["model_or_pipeline"] = model_or_pipeline
-            args_for_task["data"] = task.data
-            args_for_task["subset"] = task.subset
-            args_for_task["split"] = (task.split + f"[:{snippet}]") #make a downselection of the split via keywordarg in the .run() call?
-            results = task_evaluator.compute(**args_for_task)
-
-            results["model_cp"] = model_or_pipeline #added this to the output, should be useful. But be careful when passed something that is not a string. #TODO: currently the same for all tasks, maybe move to the list?
-            results["task_name"] = task_name + "/" + task.subset if task.subset else task_name
-            results["data_preprocessor"] = str(task.data_preprocessor) if task.data_preprocessor is not None else None
-            results_all.append(results)
-        return results_all
\ No newline at end of file
diff --git a/spaces/Xenova/doodle-dash/assets/index-973c1bab.js b/spaces/Xenova/doodle-dash/assets/index-973c1bab.js
deleted file mode 100644
index dca22da9c3f41d05d03079bd2ffe549ab57643e2..0000000000000000000000000000000000000000
--- a/spaces/Xenova/doodle-dash/assets/index-973c1bab.js
+++ /dev/null
@@ -1,60 +0,0 @@
-(function(){const t=document.createElement("link").relList;if(t&&t.supports&&t.supports("modulepreload"))return;for(const i of document.querySelectorAll('link[rel="modulepreload"]'))r(i);new MutationObserver(i=>{for(const o of i)if(o.type==="childList")for(const s of o.addedNodes)s.tagName==="LINK"&&s.rel==="modulepreload"&&r(s)}).observe(document,{childList:!0,subtree:!0});function n(i){const o={};return i.integrity&&(o.integrity=i.integrity),i.referrerPolicy&&(o.referrerPolicy=i.referrerPolicy),i.crossOrigin==="use-credentials"?o.credentials="include":i.crossOrigin==="anonymous"?o.credentials="omit":o.credentials="same-origin",o}function r(i){if(i.ep)return;i.ep=!0;const o=n(i);fetch(i.href,o)}})();function um(e){return e&&e.__esModule&&Object.prototype.hasOwnProperty.call(e,"default")?e.default:e}var Lf={exports:{}},ko={},Mf={exports:{}},I={};/**
- * @license React
- * react.production.min.js
- *
- * Copyright (c) Facebook, Inc. and its affiliates.
- *
- * This source code is licensed under the MIT license found in the
- * LICENSE file in the root directory of this source tree.
- */var Jr=Symbol.for("react.element"),cm=Symbol.for("react.portal"),fm=Symbol.for("react.fragment"),dm=Symbol.for("react.strict_mode"),pm=Symbol.for("react.profiler"),hm=Symbol.for("react.provider"),mm=Symbol.for("react.context"),gm=Symbol.for("react.forward_ref"),ym=Symbol.for("react.suspense"),vm=Symbol.for("react.memo"),wm=Symbol.for("react.lazy"),au=Symbol.iterator;function xm(e){return e===null||typeof e!="object"?null:(e=au&&e[au]||e["@@iterator"],typeof e=="function"?e:null)}var Rf={isMounted:function(){return!1},enqueueForceUpdate:function(){},enqueueReplaceState:function(){},enqueueSetState:function(){}},Vf=Object.assign,Af={};function er(e,t,n){this.props=e,this.context=t,this.refs=Af,this.updater=n||Rf}er.prototype.isReactComponent={};er.prototype.setState=function(e,t){if(typeof e!="object"&&typeof e!="function"&&e!=null)throw Error("setState(...): takes an object of state variables to update or a function which returns an object of state variables.");this.updater.enqueueSetState(this,e,t,"setState")};er.prototype.forceUpdate=function(e){this.updater.enqueueForceUpdate(this,e,"forceUpdate")};function _f(){}_f.prototype=er.prototype;function Wl(e,t,n){this.props=e,this.context=t,this.refs=Af,this.updater=n||Rf}var Gl=Wl.prototype=new _f;Gl.constructor=Wl;Vf(Gl,er.prototype);Gl.isPureReactComponent=!0;var uu=Array.isArray,Nf=Object.prototype.hasOwnProperty,Kl={current:null},Of={key:!0,ref:!0,__self:!0,__source:!0};function jf(e,t,n){var r,i={},o=null,s=null;if(t!=null)for(r in t.ref!==void 0&&(s=t.ref),t.key!==void 0&&(o=""+t.key),t)Nf.call(t,r)&&!Of.hasOwnProperty(r)&&(i[r]=t[r]);var l=arguments.length-2;if(l===1)i.children=n;else if(1<l){for(var a=Array(l),u=0;u<l;u++)a[u]=arguments[u+2];i.children=a}if(e&&e.defaultProps)for(r in l=e.defaultProps,l)i[r]===void 0&&(i[r]=l[r]);return{$$typeof:Jr,type:e,key:o,ref:s,props:i,_owner:Kl.current}}function Sm(e,t){return{$$typeof:Jr,type:e.type,key:t,ref:e.ref,props:e.props,_owner:e._owner}}function Ql(e){return typeof e=="object"&&e!==null&&e.$$typeof===Jr}function km(e){var t={"=":"=0",":":"=2"};return"$"+e.replace(/[=:]/g,function(n){return t[n]})}var cu=/\/+/g;function Qo(e,t){return typeof e=="object"&&e!==null&&e.key!=null?km(""+e.key):t.toString(36)}function Li(e,t,n,r,i){var o=typeof e;(o==="undefined"||o==="boolean")&&(e=null);var s=!1;if(e===null)s=!0;else switch(o){case"string":case"number":s=!0;break;case"object":switch(e.$$typeof){case Jr:case cm:s=!0}}if(s)return s=e,i=i(s),e=r===""?"."+Qo(s,0):r,uu(i)?(n="",e!=null&&(n=e.replace(cu,"$&/")+"/"),Li(i,t,n,"",function(u){return u})):i!=null&&(Ql(i)&&(i=Sm(i,n+(!i.key||s&&s.key===i.key?"":(""+i.key).replace(cu,"$&/")+"/")+e)),t.push(i)),1;if(s=0,r=r===""?".":r+":",uu(e))for(var l=0;l<e.length;l++){o=e[l];var a=r+Qo(o,l);s+=Li(o,t,n,a,i)}else if(a=xm(e),typeof a=="function")for(e=a.call(e),l=0;!(o=e.next()).done;)o=o.value,a=r+Qo(o,l++),s+=Li(o,t,n,a,i);else if(o==="object")throw t=String(e),Error("Objects are not valid as a React child (found: "+(t==="[object Object]"?"object with keys {"+Object.keys(e).join(", ")+"}":t)+"). If you meant to render a collection of children, use an array instead.");return s}function ai(e,t,n){if(e==null)return e;var r=[],i=0;return Li(e,r,"","",function(o){return t.call(n,o,i++)}),r}function Pm(e){if(e._status===-1){var t=e._result;t=t(),t.then(function(n){(e._status===0||e._status===-1)&&(e._status=1,e._result=n)},function(n){(e._status===0||e._status===-1)&&(e._status=2,e._result=n)}),e._status===-1&&(e._status=0,e._result=t)}if(e._status===1)return e._result.default;throw e._result}var Pe={current:null},Mi={transition:null},Cm={ReactCurrentDispatcher:Pe,ReactCurrentBatchConfig:Mi,ReactCurrentOwner:Kl};I.Children={map:ai,forEach:function(e,t,n){ai(e,function(){t.apply(this,arguments)},n)},count:function(e){var t=0;return ai(e,function(){t++}),t},toArray:function(e){return ai(e,function(t){return t})||[]},only:function(e){if(!Ql(e))throw Error("React.Children.only expected to receive a single React element child.");return e}};I.Component=er;I.Fragment=fm;I.Profiler=pm;I.PureComponent=Wl;I.StrictMode=dm;I.Suspense=ym;I.__SECRET_INTERNALS_DO_NOT_USE_OR_YOU_WILL_BE_FIRED=Cm;I.cloneElement=function(e,t,n){if(e==null)throw Error("React.cloneElement(...): The argument must be a React element, but you passed "+e+".");var r=Vf({},e.props),i=e.key,o=e.ref,s=e._owner;if(t!=null){if(t.ref!==void 0&&(o=t.ref,s=Kl.current),t.key!==void 0&&(i=""+t.key),e.type&&e.type.defaultProps)var l=e.type.defaultProps;for(a in t)Nf.call(t,a)&&!Of.hasOwnProperty(a)&&(r[a]=t[a]===void 0&&l!==void 0?l[a]:t[a])}var a=arguments.length-2;if(a===1)r.children=n;else if(1<a){l=Array(a);for(var u=0;u<a;u++)l[u]=arguments[u+2];r.children=l}return{$$typeof:Jr,type:e.type,key:i,ref:o,props:r,_owner:s}};I.createContext=function(e){return e={$$typeof:mm,_currentValue:e,_currentValue2:e,_threadCount:0,Provider:null,Consumer:null,_defaultValue:null,_globalName:null},e.Provider={$$typeof:hm,_context:e},e.Consumer=e};I.createElement=jf;I.createFactory=function(e){var t=jf.bind(null,e);return t.type=e,t};I.createRef=function(){return{current:null}};I.forwardRef=function(e){return{$$typeof:gm,render:e}};I.isValidElement=Ql;I.lazy=function(e){return{$$typeof:wm,_payload:{_status:-1,_result:e},_init:Pm}};I.memo=function(e,t){return{$$typeof:vm,type:e,compare:t===void 0?null:t}};I.startTransition=function(e){var t=Mi.transition;Mi.transition={};try{e()}finally{Mi.transition=t}};I.unstable_act=function(){throw Error("act(...) is not supported in production builds of React.")};I.useCallback=function(e,t){return Pe.current.useCallback(e,t)};I.useContext=function(e){return Pe.current.useContext(e)};I.useDebugValue=function(){};I.useDeferredValue=function(e){return Pe.current.useDeferredValue(e)};I.useEffect=function(e,t){return Pe.current.useEffect(e,t)};I.useId=function(){return Pe.current.useId()};I.useImperativeHandle=function(e,t,n){return Pe.current.useImperativeHandle(e,t,n)};I.useInsertionEffect=function(e,t){return Pe.current.useInsertionEffect(e,t)};I.useLayoutEffect=function(e,t){return Pe.current.useLayoutEffect(e,t)};I.useMemo=function(e,t){return Pe.current.useMemo(e,t)};I.useReducer=function(e,t,n){return Pe.current.useReducer(e,t,n)};I.useRef=function(e){return Pe.current.useRef(e)};I.useState=function(e){return Pe.current.useState(e)};I.useSyncExternalStore=function(e,t,n){return Pe.current.useSyncExternalStore(e,t,n)};I.useTransition=function(){return Pe.current.useTransition()};I.version="18.2.0";Mf.exports=I;var S=Mf.exports;const Yl=um(S);/**
- * @license React
- * react-jsx-runtime.production.min.js
- *
- * Copyright (c) Facebook, Inc. and its affiliates.
- *
- * This source code is licensed under the MIT license found in the
- * LICENSE file in the root directory of this source tree.
- */var Tm=S,Em=Symbol.for("react.element"),Dm=Symbol.for("react.fragment"),Lm=Object.prototype.hasOwnProperty,Mm=Tm.__SECRET_INTERNALS_DO_NOT_USE_OR_YOU_WILL_BE_FIRED.ReactCurrentOwner,Rm={key:!0,ref:!0,__self:!0,__source:!0};function Ff(e,t,n){var r,i={},o=null,s=null;n!==void 0&&(o=""+n),t.key!==void 0&&(o=""+t.key),t.ref!==void 0&&(s=t.ref);for(r in t)Lm.call(t,r)&&!Rm.hasOwnProperty(r)&&(i[r]=t[r]);if(e&&e.defaultProps)for(r in t=e.defaultProps,t)i[r]===void 0&&(i[r]=t[r]);return{$$typeof:Em,type:e,key:o,ref:s,props:i,_owner:Mm.current}}ko.Fragment=Dm;ko.jsx=Ff;ko.jsxs=Ff;Lf.exports=ko;var O=Lf.exports,js={},If={exports:{}},Ie={},zf={exports:{}},Bf={};/**
- * @license React
- * scheduler.production.min.js
- *
- * Copyright (c) Facebook, Inc. and its affiliates.
- *
- * This source code is licensed under the MIT license found in the
- * LICENSE file in the root directory of this source tree.
- */(function(e){function t(L,_){var N=L.length;L.push(_);e:for(;0<N;){var D=N-1>>>1,F=L[D];if(0<i(F,_))L[D]=_,L[N]=F,N=D;else break e}}function n(L){return L.length===0?null:L[0]}function r(L){if(L.length===0)return null;var _=L[0],N=L.pop();if(N!==_){L[0]=N;e:for(var D=0,F=L.length,Be=F>>>1;D<Be;){var ee=2*(D+1)-1,qt=L[ee],me=ee+1,Ue=L[me];if(0>i(qt,N))me<F&&0>i(Ue,qt)?(L[D]=Ue,L[me]=N,D=me):(L[D]=qt,L[ee]=N,D=ee);else if(me<F&&0>i(Ue,N))L[D]=Ue,L[me]=N,D=me;else break e}}return _}function i(L,_){var N=L.sortIndex-_.sortIndex;return N!==0?N:L.id-_.id}if(typeof performance=="object"&&typeof performance.now=="function"){var o=performance;e.unstable_now=function(){return o.now()}}else{var s=Date,l=s.now();e.unstable_now=function(){return s.now()-l}}var a=[],u=[],c=1,f=null,p=3,g=!1,y=!1,v=!1,T=typeof setTimeout=="function"?setTimeout:null,m=typeof clearTimeout=="function"?clearTimeout:null,d=typeof setImmediate<"u"?setImmediate:null;typeof navigator<"u"&&navigator.scheduling!==void 0&&navigator.scheduling.isInputPending!==void 0&&navigator.scheduling.isInputPending.bind(navigator.scheduling);function h(L){for(var _=n(u);_!==null;){if(_.callback===null)r(u);else if(_.startTime<=L)r(u),_.sortIndex=_.expirationTime,t(a,_);else break;_=n(u)}}function w(L){if(v=!1,h(L),!y)if(n(a)!==null)y=!0,he(x);else{var _=n(u);_!==null&&Ae(w,_.startTime-L)}}function x(L,_){y=!1,v&&(v=!1,m(k),k=-1),g=!0;var N=p;try{for(h(_),f=n(a);f!==null&&(!(f.expirationTime>_)||L&&!j());){var D=f.callback;if(typeof D=="function"){f.callback=null,p=f.priorityLevel;var F=D(f.expirationTime<=_);_=e.unstable_now(),typeof F=="function"?f.callback=F:f===n(a)&&r(a),h(_)}else r(a);f=n(a)}if(f!==null)var Be=!0;else{var ee=n(u);ee!==null&&Ae(w,ee.startTime-_),Be=!1}return Be}finally{f=null,p=N,g=!1}}var C=!1,E=null,k=-1,V=5,R=-1;function j(){return!(e.unstable_now()-R<V)}function de(){if(E!==null){var L=e.unstable_now();R=L;var _=!0;try{_=E(!0,L)}finally{_?pe():(C=!1,E=null)}}else C=!1}var pe;if(typeof d=="function")pe=function(){d(de)};else if(typeof MessageChannel<"u"){var U=new MessageChannel,$=U.port2;U.port1.onmessage=de,pe=function(){$.postMessage(null)}}else pe=function(){T(de,0)};function he(L){E=L,C||(C=!0,pe())}function Ae(L,_){k=T(function(){L(e.unstable_now())},_)}e.unstable_IdlePriority=5,e.unstable_ImmediatePriority=1,e.unstable_LowPriority=4,e.unstable_NormalPriority=3,e.unstable_Profiling=null,e.unstable_UserBlockingPriority=2,e.unstable_cancelCallback=function(L){L.callback=null},e.unstable_continueExecution=function(){y||g||(y=!0,he(x))},e.unstable_forceFrameRate=function(L){0>L||125<L?console.error("forceFrameRate takes a positive int between 0 and 125, forcing frame rates higher than 125 fps is not supported"):V=0<L?Math.floor(1e3/L):5},e.unstable_getCurrentPriorityLevel=function(){return p},e.unstable_getFirstCallbackNode=function(){return n(a)},e.unstable_next=function(L){switch(p){case 1:case 2:case 3:var _=3;break;default:_=p}var N=p;p=_;try{return L()}finally{p=N}},e.unstable_pauseExecution=function(){},e.unstable_requestPaint=function(){},e.unstable_runWithPriority=function(L,_){switch(L){case 1:case 2:case 3:case 4:case 5:break;default:L=3}var N=p;p=L;try{return _()}finally{p=N}},e.unstable_scheduleCallback=function(L,_,N){var D=e.unstable_now();switch(typeof N=="object"&&N!==null?(N=N.delay,N=typeof N=="number"&&0<N?D+N:D):N=D,L){case 1:var F=-1;break;case 2:F=250;break;case 5:F=1073741823;break;case 4:F=1e4;break;default:F=5e3}return F=N+F,L={id:c++,callback:_,priorityLevel:L,startTime:N,expirationTime:F,sortIndex:-1},N>D?(L.sortIndex=N,t(u,L),n(a)===null&&L===n(u)&&(v?(m(k),k=-1):v=!0,Ae(w,N-D))):(L.sortIndex=F,t(a,L),y||g||(y=!0,he(x))),L},e.unstable_shouldYield=j,e.unstable_wrapCallback=function(L){var _=p;return function(){var N=p;p=_;try{return L.apply(this,arguments)}finally{p=N}}}})(Bf);zf.exports=Bf;var Vm=zf.exports;/**
- * @license React
- * react-dom.production.min.js
- *
- * Copyright (c) Facebook, Inc. and its affiliates.
- *
- * This source code is licensed under the MIT license found in the
- * LICENSE file in the root directory of this source tree.
- */var Uf=S,je=Vm;function P(e){for(var t="https://reactjs.org/docs/error-decoder.html?invariant="+e,n=1;n<arguments.length;n++)t+="&args[]="+encodeURIComponent(arguments[n]);return"Minified React error #"+e+"; visit "+t+" for the full message or use the non-minified dev environment for full errors and additional helpful warnings."}var $f=new Set,Vr={};function yn(e,t){Kn(e,t),Kn(e+"Capture",t)}function Kn(e,t){for(Vr[e]=t,e=0;e<t.length;e++)$f.add(t[e])}var vt=!(typeof window>"u"||typeof window.document>"u"||typeof window.document.createElement>"u"),Fs=Object.prototype.hasOwnProperty,Am=/^[:A-Z_a-z\u00C0-\u00D6\u00D8-\u00F6\u00F8-\u02FF\u0370-\u037D\u037F-\u1FFF\u200C-\u200D\u2070-\u218F\u2C00-\u2FEF\u3001-\uD7FF\uF900-\uFDCF\uFDF0-\uFFFD][:A-Z_a-z\u00C0-\u00D6\u00D8-\u00F6\u00F8-\u02FF\u0370-\u037D\u037F-\u1FFF\u200C-\u200D\u2070-\u218F\u2C00-\u2FEF\u3001-\uD7FF\uF900-\uFDCF\uFDF0-\uFFFD\-.0-9\u00B7\u0300-\u036F\u203F-\u2040]*$/,fu={},du={};function _m(e){return Fs.call(du,e)?!0:Fs.call(fu,e)?!1:Am.test(e)?du[e]=!0:(fu[e]=!0,!1)}function Nm(e,t,n,r){if(n!==null&&n.type===0)return!1;switch(typeof t){case"function":case"symbol":return!0;case"boolean":return r?!1:n!==null?!n.acceptsBooleans:(e=e.toLowerCase().slice(0,5),e!=="data-"&&e!=="aria-");default:return!1}}function Om(e,t,n,r){if(t===null||typeof t>"u"||Nm(e,t,n,r))return!0;if(r)return!1;if(n!==null)switch(n.type){case 3:return!t;case 4:return t===!1;case 5:return isNaN(t);case 6:return isNaN(t)||1>t}return!1}function Ce(e,t,n,r,i,o,s){this.acceptsBooleans=t===2||t===3||t===4,this.attributeName=r,this.attributeNamespace=i,this.mustUseProperty=n,this.propertyName=e,this.type=t,this.sanitizeURL=o,this.removeEmptyString=s}var fe={};"children dangerouslySetInnerHTML defaultValue defaultChecked innerHTML suppressContentEditableWarning suppressHydrationWarning style".split(" ").forEach(function(e){fe[e]=new Ce(e,0,!1,e,null,!1,!1)});[["acceptCharset","accept-charset"],["className","class"],["htmlFor","for"],["httpEquiv","http-equiv"]].forEach(function(e){var t=e[0];fe[t]=new Ce(t,1,!1,e[1],null,!1,!1)});["contentEditable","draggable","spellCheck","value"].forEach(function(e){fe[e]=new Ce(e,2,!1,e.toLowerCase(),null,!1,!1)});["autoReverse","externalResourcesRequired","focusable","preserveAlpha"].forEach(function(e){fe[e]=new Ce(e,2,!1,e,null,!1,!1)});"allowFullScreen async autoFocus autoPlay controls default defer disabled disablePictureInPicture disableRemotePlayback formNoValidate hidden loop noModule noValidate open playsInline readOnly required reversed scoped seamless itemScope".split(" ").forEach(function(e){fe[e]=new Ce(e,3,!1,e.toLowerCase(),null,!1,!1)});["checked","multiple","muted","selected"].forEach(function(e){fe[e]=new Ce(e,3,!0,e,null,!1,!1)});["capture","download"].forEach(function(e){fe[e]=new Ce(e,4,!1,e,null,!1,!1)});["cols","rows","size","span"].forEach(function(e){fe[e]=new Ce(e,6,!1,e,null,!1,!1)});["rowSpan","start"].forEach(function(e){fe[e]=new Ce(e,5,!1,e.toLowerCase(),null,!1,!1)});var Xl=/[\-:]([a-z])/g;function Zl(e){return e[1].toUpperCase()}"accent-height alignment-baseline arabic-form baseline-shift cap-height clip-path clip-rule color-interpolation color-interpolation-filters color-profile color-rendering dominant-baseline enable-background fill-opacity fill-rule flood-color flood-opacity font-family font-size font-size-adjust font-stretch font-style font-variant font-weight glyph-name glyph-orientation-horizontal glyph-orientation-vertical horiz-adv-x horiz-origin-x image-rendering letter-spacing lighting-color marker-end marker-mid marker-start overline-position overline-thickness paint-order panose-1 pointer-events rendering-intent shape-rendering stop-color stop-opacity strikethrough-position strikethrough-thickness stroke-dasharray stroke-dashoffset stroke-linecap stroke-linejoin stroke-miterlimit stroke-opacity stroke-width text-anchor text-decoration text-rendering underline-position underline-thickness unicode-bidi unicode-range units-per-em v-alphabetic v-hanging v-ideographic v-mathematical vector-effect vert-adv-y vert-origin-x vert-origin-y word-spacing writing-mode xmlns:xlink x-height".split(" ").forEach(function(e){var t=e.replace(Xl,Zl);fe[t]=new Ce(t,1,!1,e,null,!1,!1)});"xlink:actuate xlink:arcrole xlink:role xlink:show xlink:title xlink:type".split(" ").forEach(function(e){var t=e.replace(Xl,Zl);fe[t]=new Ce(t,1,!1,e,"http://www.w3.org/1999/xlink",!1,!1)});["xml:base","xml:lang","xml:space"].forEach(function(e){var t=e.replace(Xl,Zl);fe[t]=new Ce(t,1,!1,e,"http://www.w3.org/XML/1998/namespace",!1,!1)});["tabIndex","crossOrigin"].forEach(function(e){fe[e]=new Ce(e,1,!1,e.toLowerCase(),null,!1,!1)});fe.xlinkHref=new Ce("xlinkHref",1,!1,"xlink:href","http://www.w3.org/1999/xlink",!0,!1);["src","href","action","formAction"].forEach(function(e){fe[e]=new Ce(e,1,!1,e.toLowerCase(),null,!0,!0)});function ql(e,t,n,r){var i=fe.hasOwnProperty(t)?fe[t]:null;(i!==null?i.type!==0:r||!(2<t.length)||t[0]!=="o"&&t[0]!=="O"||t[1]!=="n"&&t[1]!=="N")&&(Om(t,n,i,r)&&(n=null),r||i===null?_m(t)&&(n===null?e.removeAttribute(t):e.setAttribute(t,""+n)):i.mustUseProperty?e[i.propertyName]=n===null?i.type===3?!1:"":n:(t=i.attributeName,r=i.attributeNamespace,n===null?e.removeAttribute(t):(i=i.type,n=i===3||i===4&&n===!0?"":""+n,r?e.setAttributeNS(r,t,n):e.setAttribute(t,n))))}var Pt=Uf.__SECRET_INTERNALS_DO_NOT_USE_OR_YOU_WILL_BE_FIRED,ui=Symbol.for("react.element"),Pn=Symbol.for("react.portal"),Cn=Symbol.for("react.fragment"),Jl=Symbol.for("react.strict_mode"),Is=Symbol.for("react.profiler"),Hf=Symbol.for("react.provider"),Wf=Symbol.for("react.context"),bl=Symbol.for("react.forward_ref"),zs=Symbol.for("react.suspense"),Bs=Symbol.for("react.suspense_list"),ea=Symbol.for("react.memo"),Et=Symbol.for("react.lazy"),Gf=Symbol.for("react.offscreen"),pu=Symbol.iterator;function rr(e){return e===null||typeof e!="object"?null:(e=pu&&e[pu]||e["@@iterator"],typeof e=="function"?e:null)}var J=Object.assign,Yo;function pr(e){if(Yo===void 0)try{throw Error()}catch(n){var t=n.stack.trim().match(/\n( *(at )?)/);Yo=t&&t[1]||""}return`
-`+Yo+e}var Xo=!1;function Zo(e,t){if(!e||Xo)return"";Xo=!0;var n=Error.prepareStackTrace;Error.prepareStackTrace=void 0;try{if(t)if(t=function(){throw Error()},Object.defineProperty(t.prototype,"props",{set:function(){throw Error()}}),typeof Reflect=="object"&&Reflect.construct){try{Reflect.construct(t,[])}catch(u){var r=u}Reflect.construct(e,[],t)}else{try{t.call()}catch(u){r=u}e.call(t.prototype)}else{try{throw Error()}catch(u){r=u}e()}}catch(u){if(u&&r&&typeof u.stack=="string"){for(var i=u.stack.split(`
-`),o=r.stack.split(`
-`),s=i.length-1,l=o.length-1;1<=s&&0<=l&&i[s]!==o[l];)l--;for(;1<=s&&0<=l;s--,l--)if(i[s]!==o[l]){if(s!==1||l!==1)do if(s--,l--,0>l||i[s]!==o[l]){var a=`
-`+i[s].replace(" at new "," at ");return e.displayName&&a.includes("<anonymous>")&&(a=a.replace("<anonymous>",e.displayName)),a}while(1<=s&&0<=l);break}}}finally{Xo=!1,Error.prepareStackTrace=n}return(e=e?e.displayName||e.name:"")?pr(e):""}function jm(e){switch(e.tag){case 5:return pr(e.type);case 16:return pr("Lazy");case 13:return pr("Suspense");case 19:return pr("SuspenseList");case 0:case 2:case 15:return e=Zo(e.type,!1),e;case 11:return e=Zo(e.type.render,!1),e;case 1:return e=Zo(e.type,!0),e;default:return""}}function Us(e){if(e==null)return null;if(typeof e=="function")return e.displayName||e.name||null;if(typeof e=="string")return e;switch(e){case Cn:return"Fragment";case Pn:return"Portal";case Is:return"Profiler";case Jl:return"StrictMode";case zs:return"Suspense";case Bs:return"SuspenseList"}if(typeof e=="object")switch(e.$$typeof){case Wf:return(e.displayName||"Context")+".Consumer";case Hf:return(e._context.displayName||"Context")+".Provider";case bl:var t=e.render;return e=e.displayName,e||(e=t.displayName||t.name||"",e=e!==""?"ForwardRef("+e+")":"ForwardRef"),e;case ea:return t=e.displayName||null,t!==null?t:Us(e.type)||"Memo";case Et:t=e._payload,e=e._init;try{return Us(e(t))}catch{}}return null}function Fm(e){var t=e.type;switch(e.tag){case 24:return"Cache";case 9:return(t.displayName||"Context")+".Consumer";case 10:return(t._context.displayName||"Context")+".Provider";case 18:return"DehydratedFragment";case 11:return e=t.render,e=e.displayName||e.name||"",t.displayName||(e!==""?"ForwardRef("+e+")":"ForwardRef");case 7:return"Fragment";case 5:return t;case 4:return"Portal";case 3:return"Root";case 6:return"Text";case 16:return Us(t);case 8:return t===Jl?"StrictMode":"Mode";case 22:return"Offscreen";case 12:return"Profiler";case 21:return"Scope";case 13:return"Suspense";case 19:return"SuspenseList";case 25:return"TracingMarker";case 1:case 0:case 17:case 2:case 14:case 15:if(typeof t=="function")return t.displayName||t.name||null;if(typeof t=="string")return t}return null}function Ht(e){switch(typeof e){case"boolean":case"number":case"string":case"undefined":return e;case"object":return e;default:return""}}function Kf(e){var t=e.type;return(e=e.nodeName)&&e.toLowerCase()==="input"&&(t==="checkbox"||t==="radio")}function Im(e){var t=Kf(e)?"checked":"value",n=Object.getOwnPropertyDescriptor(e.constructor.prototype,t),r=""+e[t];if(!e.hasOwnProperty(t)&&typeof n<"u"&&typeof n.get=="function"&&typeof n.set=="function"){var i=n.get,o=n.set;return Object.defineProperty(e,t,{configurable:!0,get:function(){return i.call(this)},set:function(s){r=""+s,o.call(this,s)}}),Object.defineProperty(e,t,{enumerable:n.enumerable}),{getValue:function(){return r},setValue:function(s){r=""+s},stopTracking:function(){e._valueTracker=null,delete e[t]}}}}function ci(e){e._valueTracker||(e._valueTracker=Im(e))}function Qf(e){if(!e)return!1;var t=e._valueTracker;if(!t)return!0;var n=t.getValue(),r="";return e&&(r=Kf(e)?e.checked?"true":"false":e.value),e=r,e!==n?(t.setValue(e),!0):!1}function $i(e){if(e=e||(typeof document<"u"?document:void 0),typeof e>"u")return null;try{return e.activeElement||e.body}catch{return e.body}}function $s(e,t){var n=t.checked;return J({},t,{defaultChecked:void 0,defaultValue:void 0,value:void 0,checked:n??e._wrapperState.initialChecked})}function hu(e,t){var n=t.defaultValue==null?"":t.defaultValue,r=t.checked!=null?t.checked:t.defaultChecked;n=Ht(t.value!=null?t.value:n),e._wrapperState={initialChecked:r,initialValue:n,controlled:t.type==="checkbox"||t.type==="radio"?t.checked!=null:t.value!=null}}function Yf(e,t){t=t.checked,t!=null&&ql(e,"checked",t,!1)}function Hs(e,t){Yf(e,t);var n=Ht(t.value),r=t.type;if(n!=null)r==="number"?(n===0&&e.value===""||e.value!=n)&&(e.value=""+n):e.value!==""+n&&(e.value=""+n);else if(r==="submit"||r==="reset"){e.removeAttribute("value");return}t.hasOwnProperty("value")?Ws(e,t.type,n):t.hasOwnProperty("defaultValue")&&Ws(e,t.type,Ht(t.defaultValue)),t.checked==null&&t.defaultChecked!=null&&(e.defaultChecked=!!t.defaultChecked)}function mu(e,t,n){if(t.hasOwnProperty("value")||t.hasOwnProperty("defaultValue")){var r=t.type;if(!(r!=="submit"&&r!=="reset"||t.value!==void 0&&t.value!==null))return;t=""+e._wrapperState.initialValue,n||t===e.value||(e.value=t),e.defaultValue=t}n=e.name,n!==""&&(e.name=""),e.defaultChecked=!!e._wrapperState.initialChecked,n!==""&&(e.name=n)}function Ws(e,t,n){(t!=="number"||$i(e.ownerDocument)!==e)&&(n==null?e.defaultValue=""+e._wrapperState.initialValue:e.defaultValue!==""+n&&(e.defaultValue=""+n))}var hr=Array.isArray;function zn(e,t,n,r){if(e=e.options,t){t={};for(var i=0;i<n.length;i++)t["$"+n[i]]=!0;for(n=0;n<e.length;n++)i=t.hasOwnProperty("$"+e[n].value),e[n].selected!==i&&(e[n].selected=i),i&&r&&(e[n].defaultSelected=!0)}else{for(n=""+Ht(n),t=null,i=0;i<e.length;i++){if(e[i].value===n){e[i].selected=!0,r&&(e[i].defaultSelected=!0);return}t!==null||e[i].disabled||(t=e[i])}t!==null&&(t.selected=!0)}}function Gs(e,t){if(t.dangerouslySetInnerHTML!=null)throw Error(P(91));return J({},t,{value:void 0,defaultValue:void 0,children:""+e._wrapperState.initialValue})}function gu(e,t){var n=t.value;if(n==null){if(n=t.children,t=t.defaultValue,n!=null){if(t!=null)throw Error(P(92));if(hr(n)){if(1<n.length)throw Error(P(93));n=n[0]}t=n}t==null&&(t=""),n=t}e._wrapperState={initialValue:Ht(n)}}function Xf(e,t){var n=Ht(t.value),r=Ht(t.defaultValue);n!=null&&(n=""+n,n!==e.value&&(e.value=n),t.defaultValue==null&&e.defaultValue!==n&&(e.defaultValue=n)),r!=null&&(e.defaultValue=""+r)}function yu(e){var t=e.textContent;t===e._wrapperState.initialValue&&t!==""&&t!==null&&(e.value=t)}function Zf(e){switch(e){case"svg":return"http://www.w3.org/2000/svg";case"math":return"http://www.w3.org/1998/Math/MathML";default:return"http://www.w3.org/1999/xhtml"}}function Ks(e,t){return e==null||e==="http://www.w3.org/1999/xhtml"?Zf(t):e==="http://www.w3.org/2000/svg"&&t==="foreignObject"?"http://www.w3.org/1999/xhtml":e}var fi,qf=function(e){return typeof MSApp<"u"&&MSApp.execUnsafeLocalFunction?function(t,n,r,i){MSApp.execUnsafeLocalFunction(function(){return e(t,n,r,i)})}:e}(function(e,t){if(e.namespaceURI!=="http://www.w3.org/2000/svg"||"innerHTML"in e)e.innerHTML=t;else{for(fi=fi||document.createElement("div"),fi.innerHTML="<svg>"+t.valueOf().toString()+"</svg>",t=fi.firstChild;e.firstChild;)e.removeChild(e.firstChild);for(;t.firstChild;)e.appendChild(t.firstChild)}});function Ar(e,t){if(t){var n=e.firstChild;if(n&&n===e.lastChild&&n.nodeType===3){n.nodeValue=t;return}}e.textContent=t}var vr={animationIterationCount:!0,aspectRatio:!0,borderImageOutset:!0,borderImageSlice:!0,borderImageWidth:!0,boxFlex:!0,boxFlexGroup:!0,boxOrdinalGroup:!0,columnCount:!0,columns:!0,flex:!0,flexGrow:!0,flexPositive:!0,flexShrink:!0,flexNegative:!0,flexOrder:!0,gridArea:!0,gridRow:!0,gridRowEnd:!0,gridRowSpan:!0,gridRowStart:!0,gridColumn:!0,gridColumnEnd:!0,gridColumnSpan:!0,gridColumnStart:!0,fontWeight:!0,lineClamp:!0,lineHeight:!0,opacity:!0,order:!0,orphans:!0,tabSize:!0,widows:!0,zIndex:!0,zoom:!0,fillOpacity:!0,floodOpacity:!0,stopOpacity:!0,strokeDasharray:!0,strokeDashoffset:!0,strokeMiterlimit:!0,strokeOpacity:!0,strokeWidth:!0},zm=["Webkit","ms","Moz","O"];Object.keys(vr).forEach(function(e){zm.forEach(function(t){t=t+e.charAt(0).toUpperCase()+e.substring(1),vr[t]=vr[e]})});function Jf(e,t,n){return t==null||typeof t=="boolean"||t===""?"":n||typeof t!="number"||t===0||vr.hasOwnProperty(e)&&vr[e]?(""+t).trim():t+"px"}function bf(e,t){e=e.style;for(var n in t)if(t.hasOwnProperty(n)){var r=n.indexOf("--")===0,i=Jf(n,t[n],r);n==="float"&&(n="cssFloat"),r?e.setProperty(n,i):e[n]=i}}var Bm=J({menuitem:!0},{area:!0,base:!0,br:!0,col:!0,embed:!0,hr:!0,img:!0,input:!0,keygen:!0,link:!0,meta:!0,param:!0,source:!0,track:!0,wbr:!0});function Qs(e,t){if(t){if(Bm[e]&&(t.children!=null||t.dangerouslySetInnerHTML!=null))throw Error(P(137,e));if(t.dangerouslySetInnerHTML!=null){if(t.children!=null)throw Error(P(60));if(typeof t.dangerouslySetInnerHTML!="object"||!("__html"in t.dangerouslySetInnerHTML))throw Error(P(61))}if(t.style!=null&&typeof t.style!="object")throw Error(P(62))}}function Ys(e,t){if(e.indexOf("-")===-1)return typeof t.is=="string";switch(e){case"annotation-xml":case"color-profile":case"font-face":case"font-face-src":case"font-face-uri":case"font-face-format":case"font-face-name":case"missing-glyph":return!1;default:return!0}}var Xs=null;function ta(e){return e=e.target||e.srcElement||window,e.correspondingUseElement&&(e=e.correspondingUseElement),e.nodeType===3?e.parentNode:e}var Zs=null,Bn=null,Un=null;function vu(e){if(e=ti(e)){if(typeof Zs!="function")throw Error(P(280));var t=e.stateNode;t&&(t=Do(t),Zs(e.stateNode,e.type,t))}}function ed(e){Bn?Un?Un.push(e):Un=[e]:Bn=e}function td(){if(Bn){var e=Bn,t=Un;if(Un=Bn=null,vu(e),t)for(e=0;e<t.length;e++)vu(t[e])}}function nd(e,t){return e(t)}function rd(){}var qo=!1;function id(e,t,n){if(qo)return e(t,n);qo=!0;try{return nd(e,t,n)}finally{qo=!1,(Bn!==null||Un!==null)&&(rd(),td())}}function _r(e,t){var n=e.stateNode;if(n===null)return null;var r=Do(n);if(r===null)return null;n=r[t];e:switch(t){case"onClick":case"onClickCapture":case"onDoubleClick":case"onDoubleClickCapture":case"onMouseDown":case"onMouseDownCapture":case"onMouseMove":case"onMouseMoveCapture":case"onMouseUp":case"onMouseUpCapture":case"onMouseEnter":(r=!r.disabled)||(e=e.type,r=!(e==="button"||e==="input"||e==="select"||e==="textarea")),e=!r;break e;default:e=!1}if(e)return null;if(n&&typeof n!="function")throw Error(P(231,t,typeof n));return n}var qs=!1;if(vt)try{var ir={};Object.defineProperty(ir,"passive",{get:function(){qs=!0}}),window.addEventListener("test",ir,ir),window.removeEventListener("test",ir,ir)}catch{qs=!1}function Um(e,t,n,r,i,o,s,l,a){var u=Array.prototype.slice.call(arguments,3);try{t.apply(n,u)}catch(c){this.onError(c)}}var wr=!1,Hi=null,Wi=!1,Js=null,$m={onError:function(e){wr=!0,Hi=e}};function Hm(e,t,n,r,i,o,s,l,a){wr=!1,Hi=null,Um.apply($m,arguments)}function Wm(e,t,n,r,i,o,s,l,a){if(Hm.apply(this,arguments),wr){if(wr){var u=Hi;wr=!1,Hi=null}else throw Error(P(198));Wi||(Wi=!0,Js=u)}}function vn(e){var t=e,n=e;if(e.alternate)for(;t.return;)t=t.return;else{e=t;do t=e,t.flags&4098&&(n=t.return),e=t.return;while(e)}return t.tag===3?n:null}function od(e){if(e.tag===13){var t=e.memoizedState;if(t===null&&(e=e.alternate,e!==null&&(t=e.memoizedState)),t!==null)return t.dehydrated}return null}function wu(e){if(vn(e)!==e)throw Error(P(188))}function Gm(e){var t=e.alternate;if(!t){if(t=vn(e),t===null)throw Error(P(188));return t!==e?null:e}for(var n=e,r=t;;){var i=n.return;if(i===null)break;var o=i.alternate;if(o===null){if(r=i.return,r!==null){n=r;continue}break}if(i.child===o.child){for(o=i.child;o;){if(o===n)return wu(i),e;if(o===r)return wu(i),t;o=o.sibling}throw Error(P(188))}if(n.return!==r.return)n=i,r=o;else{for(var s=!1,l=i.child;l;){if(l===n){s=!0,n=i,r=o;break}if(l===r){s=!0,r=i,n=o;break}l=l.sibling}if(!s){for(l=o.child;l;){if(l===n){s=!0,n=o,r=i;break}if(l===r){s=!0,r=o,n=i;break}l=l.sibling}if(!s)throw Error(P(189))}}if(n.alternate!==r)throw Error(P(190))}if(n.tag!==3)throw Error(P(188));return n.stateNode.current===n?e:t}function sd(e){return e=Gm(e),e!==null?ld(e):null}function ld(e){if(e.tag===5||e.tag===6)return e;for(e=e.child;e!==null;){var t=ld(e);if(t!==null)return t;e=e.sibling}return null}var ad=je.unstable_scheduleCallback,xu=je.unstable_cancelCallback,Km=je.unstable_shouldYield,Qm=je.unstable_requestPaint,te=je.unstable_now,Ym=je.unstable_getCurrentPriorityLevel,na=je.unstable_ImmediatePriority,ud=je.unstable_UserBlockingPriority,Gi=je.unstable_NormalPriority,Xm=je.unstable_LowPriority,cd=je.unstable_IdlePriority,Po=null,lt=null;function Zm(e){if(lt&&typeof lt.onCommitFiberRoot=="function")try{lt.onCommitFiberRoot(Po,e,void 0,(e.current.flags&128)===128)}catch{}}var et=Math.clz32?Math.clz32:bm,qm=Math.log,Jm=Math.LN2;function bm(e){return e>>>=0,e===0?32:31-(qm(e)/Jm|0)|0}var di=64,pi=4194304;function mr(e){switch(e&-e){case 1:return 1;case 2:return 2;case 4:return 4;case 8:return 8;case 16:return 16;case 32:return 32;case 64:case 128:case 256:case 512:case 1024:case 2048:case 4096:case 8192:case 16384:case 32768:case 65536:case 131072:case 262144:case 524288:case 1048576:case 2097152:return e&4194240;case 4194304:case 8388608:case 16777216:case 33554432:case 67108864:return e&130023424;case 134217728:return 134217728;case 268435456:return 268435456;case 536870912:return 536870912;case 1073741824:return 1073741824;default:return e}}function Ki(e,t){var n=e.pendingLanes;if(n===0)return 0;var r=0,i=e.suspendedLanes,o=e.pingedLanes,s=n&268435455;if(s!==0){var l=s&~i;l!==0?r=mr(l):(o&=s,o!==0&&(r=mr(o)))}else s=n&~i,s!==0?r=mr(s):o!==0&&(r=mr(o));if(r===0)return 0;if(t!==0&&t!==r&&!(t&i)&&(i=r&-r,o=t&-t,i>=o||i===16&&(o&4194240)!==0))return t;if(r&4&&(r|=n&16),t=e.entangledLanes,t!==0)for(e=e.entanglements,t&=r;0<t;)n=31-et(t),i=1<<n,r|=e[n],t&=~i;return r}function eg(e,t){switch(e){case 1:case 2:case 4:return t+250;case 8:case 16:case 32:case 64:case 128:case 256:case 512:case 1024:case 2048:case 4096:case 8192:case 16384:case 32768:case 65536:case 131072:case 262144:case 524288:case 1048576:case 2097152:return t+5e3;case 4194304:case 8388608:case 16777216:case 33554432:case 67108864:return-1;case 134217728:case 268435456:case 536870912:case 1073741824:return-1;default:return-1}}function tg(e,t){for(var n=e.suspendedLanes,r=e.pingedLanes,i=e.expirationTimes,o=e.pendingLanes;0<o;){var s=31-et(o),l=1<<s,a=i[s];a===-1?(!(l&n)||l&r)&&(i[s]=eg(l,t)):a<=t&&(e.expiredLanes|=l),o&=~l}}function bs(e){return e=e.pendingLanes&-1073741825,e!==0?e:e&1073741824?1073741824:0}function fd(){var e=di;return di<<=1,!(di&4194240)&&(di=64),e}function Jo(e){for(var t=[],n=0;31>n;n++)t.push(e);return t}function br(e,t,n){e.pendingLanes|=t,t!==536870912&&(e.suspendedLanes=0,e.pingedLanes=0),e=e.eventTimes,t=31-et(t),e[t]=n}function ng(e,t){var n=e.pendingLanes&~t;e.pendingLanes=t,e.suspendedLanes=0,e.pingedLanes=0,e.expiredLanes&=t,e.mutableReadLanes&=t,e.entangledLanes&=t,t=e.entanglements;var r=e.eventTimes;for(e=e.expirationTimes;0<n;){var i=31-et(n),o=1<<i;t[i]=0,r[i]=-1,e[i]=-1,n&=~o}}function ra(e,t){var n=e.entangledLanes|=t;for(e=e.entanglements;n;){var r=31-et(n),i=1<<r;i&t|e[r]&t&&(e[r]|=t),n&=~i}}var B=0;function dd(e){return e&=-e,1<e?4<e?e&268435455?16:536870912:4:1}var pd,ia,hd,md,gd,el=!1,hi=[],_t=null,Nt=null,Ot=null,Nr=new Map,Or=new Map,Mt=[],rg="mousedown mouseup touchcancel touchend touchstart auxclick dblclick pointercancel pointerdown pointerup dragend dragstart drop compositionend compositionstart keydown keypress keyup input textInput copy cut paste click change contextmenu reset submit".split(" ");function Su(e,t){switch(e){case"focusin":case"focusout":_t=null;break;case"dragenter":case"dragleave":Nt=null;break;case"mouseover":case"mouseout":Ot=null;break;case"pointerover":case"pointerout":Nr.delete(t.pointerId);break;case"gotpointercapture":case"lostpointercapture":Or.delete(t.pointerId)}}function or(e,t,n,r,i,o){return e===null||e.nativeEvent!==o?(e={blockedOn:t,domEventName:n,eventSystemFlags:r,nativeEvent:o,targetContainers:[i]},t!==null&&(t=ti(t),t!==null&&ia(t)),e):(e.eventSystemFlags|=r,t=e.targetContainers,i!==null&&t.indexOf(i)===-1&&t.push(i),e)}function ig(e,t,n,r,i){switch(t){case"focusin":return _t=or(_t,e,t,n,r,i),!0;case"dragenter":return Nt=or(Nt,e,t,n,r,i),!0;case"mouseover":return Ot=or(Ot,e,t,n,r,i),!0;case"pointerover":var o=i.pointerId;return Nr.set(o,or(Nr.get(o)||null,e,t,n,r,i)),!0;case"gotpointercapture":return o=i.pointerId,Or.set(o,or(Or.get(o)||null,e,t,n,r,i)),!0}return!1}function yd(e){var t=sn(e.target);if(t!==null){var n=vn(t);if(n!==null){if(t=n.tag,t===13){if(t=od(n),t!==null){e.blockedOn=t,gd(e.priority,function(){hd(n)});return}}else if(t===3&&n.stateNode.current.memoizedState.isDehydrated){e.blockedOn=n.tag===3?n.stateNode.containerInfo:null;return}}}e.blockedOn=null}function Ri(e){if(e.blockedOn!==null)return!1;for(var t=e.targetContainers;0<t.length;){var n=tl(e.domEventName,e.eventSystemFlags,t[0],e.nativeEvent);if(n===null){n=e.nativeEvent;var r=new n.constructor(n.type,n);Xs=r,n.target.dispatchEvent(r),Xs=null}else return t=ti(n),t!==null&&ia(t),e.blockedOn=n,!1;t.shift()}return!0}function ku(e,t,n){Ri(e)&&n.delete(t)}function og(){el=!1,_t!==null&&Ri(_t)&&(_t=null),Nt!==null&&Ri(Nt)&&(Nt=null),Ot!==null&&Ri(Ot)&&(Ot=null),Nr.forEach(ku),Or.forEach(ku)}function sr(e,t){e.blockedOn===t&&(e.blockedOn=null,el||(el=!0,je.unstable_scheduleCallback(je.unstable_NormalPriority,og)))}function jr(e){function t(i){return sr(i,e)}if(0<hi.length){sr(hi[0],e);for(var n=1;n<hi.length;n++){var r=hi[n];r.blockedOn===e&&(r.blockedOn=null)}}for(_t!==null&&sr(_t,e),Nt!==null&&sr(Nt,e),Ot!==null&&sr(Ot,e),Nr.forEach(t),Or.forEach(t),n=0;n<Mt.length;n++)r=Mt[n],r.blockedOn===e&&(r.blockedOn=null);for(;0<Mt.length&&(n=Mt[0],n.blockedOn===null);)yd(n),n.blockedOn===null&&Mt.shift()}var $n=Pt.ReactCurrentBatchConfig,Qi=!0;function sg(e,t,n,r){var i=B,o=$n.transition;$n.transition=null;try{B=1,oa(e,t,n,r)}finally{B=i,$n.transition=o}}function lg(e,t,n,r){var i=B,o=$n.transition;$n.transition=null;try{B=4,oa(e,t,n,r)}finally{B=i,$n.transition=o}}function oa(e,t,n,r){if(Qi){var i=tl(e,t,n,r);if(i===null)as(e,t,r,Yi,n),Su(e,r);else if(ig(i,e,t,n,r))r.stopPropagation();else if(Su(e,r),t&4&&-1<rg.indexOf(e)){for(;i!==null;){var o=ti(i);if(o!==null&&pd(o),o=tl(e,t,n,r),o===null&&as(e,t,r,Yi,n),o===i)break;i=o}i!==null&&r.stopPropagation()}else as(e,t,r,null,n)}}var Yi=null;function tl(e,t,n,r){if(Yi=null,e=ta(r),e=sn(e),e!==null)if(t=vn(e),t===null)e=null;else if(n=t.tag,n===13){if(e=od(t),e!==null)return e;e=null}else if(n===3){if(t.stateNode.current.memoizedState.isDehydrated)return t.tag===3?t.stateNode.containerInfo:null;e=null}else t!==e&&(e=null);return Yi=e,null}function vd(e){switch(e){case"cancel":case"click":case"close":case"contextmenu":case"copy":case"cut":case"auxclick":case"dblclick":case"dragend":case"dragstart":case"drop":case"focusin":case"focusout":case"input":case"invalid":case"keydown":case"keypress":case"keyup":case"mousedown":case"mouseup":case"paste":case"pause":case"play":case"pointercancel":case"pointerdown":case"pointerup":case"ratechange":case"reset":case"resize":case"seeked":case"submit":case"touchcancel":case"touchend":case"touchstart":case"volumechange":case"change":case"selectionchange":case"textInput":case"compositionstart":case"compositionend":case"compositionupdate":case"beforeblur":case"afterblur":case"beforeinput":case"blur":case"fullscreenchange":case"focus":case"hashchange":case"popstate":case"select":case"selectstart":return 1;case"drag":case"dragenter":case"dragexit":case"dragleave":case"dragover":case"mousemove":case"mouseout":case"mouseover":case"pointermove":case"pointerout":case"pointerover":case"scroll":case"toggle":case"touchmove":case"wheel":case"mouseenter":case"mouseleave":case"pointerenter":case"pointerleave":return 4;case"message":switch(Ym()){case na:return 1;case ud:return 4;case Gi:case Xm:return 16;case cd:return 536870912;default:return 16}default:return 16}}var Vt=null,sa=null,Vi=null;function wd(){if(Vi)return Vi;var e,t=sa,n=t.length,r,i="value"in Vt?Vt.value:Vt.textContent,o=i.length;for(e=0;e<n&&t[e]===i[e];e++);var s=n-e;for(r=1;r<=s&&t[n-r]===i[o-r];r++);return Vi=i.slice(e,1<r?1-r:void 0)}function Ai(e){var t=e.keyCode;return"charCode"in e?(e=e.charCode,e===0&&t===13&&(e=13)):e=t,e===10&&(e=13),32<=e||e===13?e:0}function mi(){return!0}function Pu(){return!1}function ze(e){function t(n,r,i,o,s){this._reactName=n,this._targetInst=i,this.type=r,this.nativeEvent=o,this.target=s,this.currentTarget=null;for(var l in e)e.hasOwnProperty(l)&&(n=e[l],this[l]=n?n(o):o[l]);return this.isDefaultPrevented=(o.defaultPrevented!=null?o.defaultPrevented:o.returnValue===!1)?mi:Pu,this.isPropagationStopped=Pu,this}return J(t.prototype,{preventDefault:function(){this.defaultPrevented=!0;var n=this.nativeEvent;n&&(n.preventDefault?n.preventDefault():typeof n.returnValue!="unknown"&&(n.returnValue=!1),this.isDefaultPrevented=mi)},stopPropagation:function(){var n=this.nativeEvent;n&&(n.stopPropagation?n.stopPropagation():typeof n.cancelBubble!="unknown"&&(n.cancelBubble=!0),this.isPropagationStopped=mi)},persist:function(){},isPersistent:mi}),t}var tr={eventPhase:0,bubbles:0,cancelable:0,timeStamp:function(e){return e.timeStamp||Date.now()},defaultPrevented:0,isTrusted:0},la=ze(tr),ei=J({},tr,{view:0,detail:0}),ag=ze(ei),bo,es,lr,Co=J({},ei,{screenX:0,screenY:0,clientX:0,clientY:0,pageX:0,pageY:0,ctrlKey:0,shiftKey:0,altKey:0,metaKey:0,getModifierState:aa,button:0,buttons:0,relatedTarget:function(e){return e.relatedTarget===void 0?e.fromElement===e.srcElement?e.toElement:e.fromElement:e.relatedTarget},movementX:function(e){return"movementX"in e?e.movementX:(e!==lr&&(lr&&e.type==="mousemove"?(bo=e.screenX-lr.screenX,es=e.screenY-lr.screenY):es=bo=0,lr=e),bo)},movementY:function(e){return"movementY"in e?e.movementY:es}}),Cu=ze(Co),ug=J({},Co,{dataTransfer:0}),cg=ze(ug),fg=J({},ei,{relatedTarget:0}),ts=ze(fg),dg=J({},tr,{animationName:0,elapsedTime:0,pseudoElement:0}),pg=ze(dg),hg=J({},tr,{clipboardData:function(e){return"clipboardData"in e?e.clipboardData:window.clipboardData}}),mg=ze(hg),gg=J({},tr,{data:0}),Tu=ze(gg),yg={Esc:"Escape",Spacebar:" ",Left:"ArrowLeft",Up:"ArrowUp",Right:"ArrowRight",Down:"ArrowDown",Del:"Delete",Win:"OS",Menu:"ContextMenu",Apps:"ContextMenu",Scroll:"ScrollLock",MozPrintableKey:"Unidentified"},vg={8:"Backspace",9:"Tab",12:"Clear",13:"Enter",16:"Shift",17:"Control",18:"Alt",19:"Pause",20:"CapsLock",27:"Escape",32:" ",33:"PageUp",34:"PageDown",35:"End",36:"Home",37:"ArrowLeft",38:"ArrowUp",39:"ArrowRight",40:"ArrowDown",45:"Insert",46:"Delete",112:"F1",113:"F2",114:"F3",115:"F4",116:"F5",117:"F6",118:"F7",119:"F8",120:"F9",121:"F10",122:"F11",123:"F12",144:"NumLock",145:"ScrollLock",224:"Meta"},wg={Alt:"altKey",Control:"ctrlKey",Meta:"metaKey",Shift:"shiftKey"};function xg(e){var t=this.nativeEvent;return t.getModifierState?t.getModifierState(e):(e=wg[e])?!!t[e]:!1}function aa(){return xg}var Sg=J({},ei,{key:function(e){if(e.key){var t=yg[e.key]||e.key;if(t!=="Unidentified")return t}return e.type==="keypress"?(e=Ai(e),e===13?"Enter":String.fromCharCode(e)):e.type==="keydown"||e.type==="keyup"?vg[e.keyCode]||"Unidentified":""},code:0,location:0,ctrlKey:0,shiftKey:0,altKey:0,metaKey:0,repeat:0,locale:0,getModifierState:aa,charCode:function(e){return e.type==="keypress"?Ai(e):0},keyCode:function(e){return e.type==="keydown"||e.type==="keyup"?e.keyCode:0},which:function(e){return e.type==="keypress"?Ai(e):e.type==="keydown"||e.type==="keyup"?e.keyCode:0}}),kg=ze(Sg),Pg=J({},Co,{pointerId:0,width:0,height:0,pressure:0,tangentialPressure:0,tiltX:0,tiltY:0,twist:0,pointerType:0,isPrimary:0}),Eu=ze(Pg),Cg=J({},ei,{touches:0,targetTouches:0,changedTouches:0,altKey:0,metaKey:0,ctrlKey:0,shiftKey:0,getModifierState:aa}),Tg=ze(Cg),Eg=J({},tr,{propertyName:0,elapsedTime:0,pseudoElement:0}),Dg=ze(Eg),Lg=J({},Co,{deltaX:function(e){return"deltaX"in e?e.deltaX:"wheelDeltaX"in e?-e.wheelDeltaX:0},deltaY:function(e){return"deltaY"in e?e.deltaY:"wheelDeltaY"in e?-e.wheelDeltaY:"wheelDelta"in e?-e.wheelDelta:0},deltaZ:0,deltaMode:0}),Mg=ze(Lg),Rg=[9,13,27,32],ua=vt&&"CompositionEvent"in window,xr=null;vt&&"documentMode"in document&&(xr=document.documentMode);var Vg=vt&&"TextEvent"in window&&!xr,xd=vt&&(!ua||xr&&8<xr&&11>=xr),Du=String.fromCharCode(32),Lu=!1;function Sd(e,t){switch(e){case"keyup":return Rg.indexOf(t.keyCode)!==-1;case"keydown":return t.keyCode!==229;case"keypress":case"mousedown":case"focusout":return!0;default:return!1}}function kd(e){return e=e.detail,typeof e=="object"&&"data"in e?e.data:null}var Tn=!1;function Ag(e,t){switch(e){case"compositionend":return kd(t);case"keypress":return t.which!==32?null:(Lu=!0,Du);case"textInput":return e=t.data,e===Du&&Lu?null:e;default:return null}}function _g(e,t){if(Tn)return e==="compositionend"||!ua&&Sd(e,t)?(e=wd(),Vi=sa=Vt=null,Tn=!1,e):null;switch(e){case"paste":return null;case"keypress":if(!(t.ctrlKey||t.altKey||t.metaKey)||t.ctrlKey&&t.altKey){if(t.char&&1<t.char.length)return t.char;if(t.which)return String.fromCharCode(t.which)}return null;case"compositionend":return xd&&t.locale!=="ko"?null:t.data;default:return null}}var Ng={color:!0,date:!0,datetime:!0,"datetime-local":!0,email:!0,month:!0,number:!0,password:!0,range:!0,search:!0,tel:!0,text:!0,time:!0,url:!0,week:!0};function Mu(e){var t=e&&e.nodeName&&e.nodeName.toLowerCase();return t==="input"?!!Ng[e.type]:t==="textarea"}function Pd(e,t,n,r){ed(r),t=Xi(t,"onChange"),0<t.length&&(n=new la("onChange","change",null,n,r),e.push({event:n,listeners:t}))}var Sr=null,Fr=null;function Og(e){Nd(e,0)}function To(e){var t=Ln(e);if(Qf(t))return e}function jg(e,t){if(e==="change")return t}var Cd=!1;if(vt){var ns;if(vt){var rs="oninput"in document;if(!rs){var Ru=document.createElement("div");Ru.setAttribute("oninput","return;"),rs=typeof Ru.oninput=="function"}ns=rs}else ns=!1;Cd=ns&&(!document.documentMode||9<document.documentMode)}function Vu(){Sr&&(Sr.detachEvent("onpropertychange",Td),Fr=Sr=null)}function Td(e){if(e.propertyName==="value"&&To(Fr)){var t=[];Pd(t,Fr,e,ta(e)),id(Og,t)}}function Fg(e,t,n){e==="focusin"?(Vu(),Sr=t,Fr=n,Sr.attachEvent("onpropertychange",Td)):e==="focusout"&&Vu()}function Ig(e){if(e==="selectionchange"||e==="keyup"||e==="keydown")return To(Fr)}function zg(e,t){if(e==="click")return To(t)}function Bg(e,t){if(e==="input"||e==="change")return To(t)}function Ug(e,t){return e===t&&(e!==0||1/e===1/t)||e!==e&&t!==t}var nt=typeof Object.is=="function"?Object.is:Ug;function Ir(e,t){if(nt(e,t))return!0;if(typeof e!="object"||e===null||typeof t!="object"||t===null)return!1;var n=Object.keys(e),r=Object.keys(t);if(n.length!==r.length)return!1;for(r=0;r<n.length;r++){var i=n[r];if(!Fs.call(t,i)||!nt(e[i],t[i]))return!1}return!0}function Au(e){for(;e&&e.firstChild;)e=e.firstChild;return e}function _u(e,t){var n=Au(e);e=0;for(var r;n;){if(n.nodeType===3){if(r=e+n.textContent.length,e<=t&&r>=t)return{node:n,offset:t-e};e=r}e:{for(;n;){if(n.nextSibling){n=n.nextSibling;break e}n=n.parentNode}n=void 0}n=Au(n)}}function Ed(e,t){return e&&t?e===t?!0:e&&e.nodeType===3?!1:t&&t.nodeType===3?Ed(e,t.parentNode):"contains"in e?e.contains(t):e.compareDocumentPosition?!!(e.compareDocumentPosition(t)&16):!1:!1}function Dd(){for(var e=window,t=$i();t instanceof e.HTMLIFrameElement;){try{var n=typeof t.contentWindow.location.href=="string"}catch{n=!1}if(n)e=t.contentWindow;else break;t=$i(e.document)}return t}function ca(e){var t=e&&e.nodeName&&e.nodeName.toLowerCase();return t&&(t==="input"&&(e.type==="text"||e.type==="search"||e.type==="tel"||e.type==="url"||e.type==="password")||t==="textarea"||e.contentEditable==="true")}function $g(e){var t=Dd(),n=e.focusedElem,r=e.selectionRange;if(t!==n&&n&&n.ownerDocument&&Ed(n.ownerDocument.documentElement,n)){if(r!==null&&ca(n)){if(t=r.start,e=r.end,e===void 0&&(e=t),"selectionStart"in n)n.selectionStart=t,n.selectionEnd=Math.min(e,n.value.length);else if(e=(t=n.ownerDocument||document)&&t.defaultView||window,e.getSelection){e=e.getSelection();var i=n.textContent.length,o=Math.min(r.start,i);r=r.end===void 0?o:Math.min(r.end,i),!e.extend&&o>r&&(i=r,r=o,o=i),i=_u(n,o);var s=_u(n,r);i&&s&&(e.rangeCount!==1||e.anchorNode!==i.node||e.anchorOffset!==i.offset||e.focusNode!==s.node||e.focusOffset!==s.offset)&&(t=t.createRange(),t.setStart(i.node,i.offset),e.removeAllRanges(),o>r?(e.addRange(t),e.extend(s.node,s.offset)):(t.setEnd(s.node,s.offset),e.addRange(t)))}}for(t=[],e=n;e=e.parentNode;)e.nodeType===1&&t.push({element:e,left:e.scrollLeft,top:e.scrollTop});for(typeof n.focus=="function"&&n.focus(),n=0;n<t.length;n++)e=t[n],e.element.scrollLeft=e.left,e.element.scrollTop=e.top}}var Hg=vt&&"documentMode"in document&&11>=document.documentMode,En=null,nl=null,kr=null,rl=!1;function Nu(e,t,n){var r=n.window===n?n.document:n.nodeType===9?n:n.ownerDocument;rl||En==null||En!==$i(r)||(r=En,"selectionStart"in r&&ca(r)?r={start:r.selectionStart,end:r.selectionEnd}:(r=(r.ownerDocument&&r.ownerDocument.defaultView||window).getSelection(),r={anchorNode:r.anchorNode,anchorOffset:r.anchorOffset,focusNode:r.focusNode,focusOffset:r.focusOffset}),kr&&Ir(kr,r)||(kr=r,r=Xi(nl,"onSelect"),0<r.length&&(t=new la("onSelect","select",null,t,n),e.push({event:t,listeners:r}),t.target=En)))}function gi(e,t){var n={};return n[e.toLowerCase()]=t.toLowerCase(),n["Webkit"+e]="webkit"+t,n["Moz"+e]="moz"+t,n}var Dn={animationend:gi("Animation","AnimationEnd"),animationiteration:gi("Animation","AnimationIteration"),animationstart:gi("Animation","AnimationStart"),transitionend:gi("Transition","TransitionEnd")},is={},Ld={};vt&&(Ld=document.createElement("div").style,"AnimationEvent"in window||(delete Dn.animationend.animation,delete Dn.animationiteration.animation,delete Dn.animationstart.animation),"TransitionEvent"in window||delete Dn.transitionend.transition);function Eo(e){if(is[e])return is[e];if(!Dn[e])return e;var t=Dn[e],n;for(n in t)if(t.hasOwnProperty(n)&&n in Ld)return is[e]=t[n];return e}var Md=Eo("animationend"),Rd=Eo("animationiteration"),Vd=Eo("animationstart"),Ad=Eo("transitionend"),_d=new Map,Ou="abort auxClick cancel canPlay canPlayThrough click close contextMenu copy cut drag dragEnd dragEnter dragExit dragLeave dragOver dragStart drop durationChange emptied encrypted ended error gotPointerCapture input invalid keyDown keyPress keyUp load loadedData loadedMetadata loadStart lostPointerCapture mouseDown mouseMove mouseOut mouseOver mouseUp paste pause play playing pointerCancel pointerDown pointerMove pointerOut pointerOver pointerUp progress rateChange reset resize seeked seeking stalled submit suspend timeUpdate touchCancel touchEnd touchStart volumeChange scroll toggle touchMove waiting wheel".split(" ");function Qt(e,t){_d.set(e,t),yn(t,[e])}for(var os=0;os<Ou.length;os++){var ss=Ou[os],Wg=ss.toLowerCase(),Gg=ss[0].toUpperCase()+ss.slice(1);Qt(Wg,"on"+Gg)}Qt(Md,"onAnimationEnd");Qt(Rd,"onAnimationIteration");Qt(Vd,"onAnimationStart");Qt("dblclick","onDoubleClick");Qt("focusin","onFocus");Qt("focusout","onBlur");Qt(Ad,"onTransitionEnd");Kn("onMouseEnter",["mouseout","mouseover"]);Kn("onMouseLeave",["mouseout","mouseover"]);Kn("onPointerEnter",["pointerout","pointerover"]);Kn("onPointerLeave",["pointerout","pointerover"]);yn("onChange","change click focusin focusout input keydown keyup selectionchange".split(" "));yn("onSelect","focusout contextmenu dragend focusin keydown keyup mousedown mouseup selectionchange".split(" "));yn("onBeforeInput",["compositionend","keypress","textInput","paste"]);yn("onCompositionEnd","compositionend focusout keydown keypress keyup mousedown".split(" "));yn("onCompositionStart","compositionstart focusout keydown keypress keyup mousedown".split(" "));yn("onCompositionUpdate","compositionupdate focusout keydown keypress keyup mousedown".split(" "));var gr="abort canplay canplaythrough durationchange emptied encrypted ended error loadeddata loadedmetadata loadstart pause play playing progress ratechange resize seeked seeking stalled suspend timeupdate volumechange waiting".split(" "),Kg=new Set("cancel close invalid load scroll toggle".split(" ").concat(gr));function ju(e,t,n){var r=e.type||"unknown-event";e.currentTarget=n,Wm(r,t,void 0,e),e.currentTarget=null}function Nd(e,t){t=(t&4)!==0;for(var n=0;n<e.length;n++){var r=e[n],i=r.event;r=r.listeners;e:{var o=void 0;if(t)for(var s=r.length-1;0<=s;s--){var l=r[s],a=l.instance,u=l.currentTarget;if(l=l.listener,a!==o&&i.isPropagationStopped())break e;ju(i,l,u),o=a}else for(s=0;s<r.length;s++){if(l=r[s],a=l.instance,u=l.currentTarget,l=l.listener,a!==o&&i.isPropagationStopped())break e;ju(i,l,u),o=a}}}if(Wi)throw e=Js,Wi=!1,Js=null,e}function W(e,t){var n=t[al];n===void 0&&(n=t[al]=new Set);var r=e+"__bubble";n.has(r)||(Od(t,e,2,!1),n.add(r))}function ls(e,t,n){var r=0;t&&(r|=4),Od(n,e,r,t)}var yi="_reactListening"+Math.random().toString(36).slice(2);function zr(e){if(!e[yi]){e[yi]=!0,$f.forEach(function(n){n!=="selectionchange"&&(Kg.has(n)||ls(n,!1,e),ls(n,!0,e))});var t=e.nodeType===9?e:e.ownerDocument;t===null||t[yi]||(t[yi]=!0,ls("selectionchange",!1,t))}}function Od(e,t,n,r){switch(vd(t)){case 1:var i=sg;break;case 4:i=lg;break;default:i=oa}n=i.bind(null,t,n,e),i=void 0,!qs||t!=="touchstart"&&t!=="touchmove"&&t!=="wheel"||(i=!0),r?i!==void 0?e.addEventListener(t,n,{capture:!0,passive:i}):e.addEventListener(t,n,!0):i!==void 0?e.addEventListener(t,n,{passive:i}):e.addEventListener(t,n,!1)}function as(e,t,n,r,i){var o=r;if(!(t&1)&&!(t&2)&&r!==null)e:for(;;){if(r===null)return;var s=r.tag;if(s===3||s===4){var l=r.stateNode.containerInfo;if(l===i||l.nodeType===8&&l.parentNode===i)break;if(s===4)for(s=r.return;s!==null;){var a=s.tag;if((a===3||a===4)&&(a=s.stateNode.containerInfo,a===i||a.nodeType===8&&a.parentNode===i))return;s=s.return}for(;l!==null;){if(s=sn(l),s===null)return;if(a=s.tag,a===5||a===6){r=o=s;continue e}l=l.parentNode}}r=r.return}id(function(){var u=o,c=ta(n),f=[];e:{var p=_d.get(e);if(p!==void 0){var g=la,y=e;switch(e){case"keypress":if(Ai(n)===0)break e;case"keydown":case"keyup":g=kg;break;case"focusin":y="focus",g=ts;break;case"focusout":y="blur",g=ts;break;case"beforeblur":case"afterblur":g=ts;break;case"click":if(n.button===2)break e;case"auxclick":case"dblclick":case"mousedown":case"mousemove":case"mouseup":case"mouseout":case"mouseover":case"contextmenu":g=Cu;break;case"drag":case"dragend":case"dragenter":case"dragexit":case"dragleave":case"dragover":case"dragstart":case"drop":g=cg;break;case"touchcancel":case"touchend":case"touchmove":case"touchstart":g=Tg;break;case Md:case Rd:case Vd:g=pg;break;case Ad:g=Dg;break;case"scroll":g=ag;break;case"wheel":g=Mg;break;case"copy":case"cut":case"paste":g=mg;break;case"gotpointercapture":case"lostpointercapture":case"pointercancel":case"pointerdown":case"pointermove":case"pointerout":case"pointerover":case"pointerup":g=Eu}var v=(t&4)!==0,T=!v&&e==="scroll",m=v?p!==null?p+"Capture":null:p;v=[];for(var d=u,h;d!==null;){h=d;var w=h.stateNode;if(h.tag===5&&w!==null&&(h=w,m!==null&&(w=_r(d,m),w!=null&&v.push(Br(d,w,h)))),T)break;d=d.return}0<v.length&&(p=new g(p,y,null,n,c),f.push({event:p,listeners:v}))}}if(!(t&7)){e:{if(p=e==="mouseover"||e==="pointerover",g=e==="mouseout"||e==="pointerout",p&&n!==Xs&&(y=n.relatedTarget||n.fromElement)&&(sn(y)||y[wt]))break e;if((g||p)&&(p=c.window===c?c:(p=c.ownerDocument)?p.defaultView||p.parentWindow:window,g?(y=n.relatedTarget||n.toElement,g=u,y=y?sn(y):null,y!==null&&(T=vn(y),y!==T||y.tag!==5&&y.tag!==6)&&(y=null)):(g=null,y=u),g!==y)){if(v=Cu,w="onMouseLeave",m="onMouseEnter",d="mouse",(e==="pointerout"||e==="pointerover")&&(v=Eu,w="onPointerLeave",m="onPointerEnter",d="pointer"),T=g==null?p:Ln(g),h=y==null?p:Ln(y),p=new v(w,d+"leave",g,n,c),p.target=T,p.relatedTarget=h,w=null,sn(c)===u&&(v=new v(m,d+"enter",y,n,c),v.target=h,v.relatedTarget=T,w=v),T=w,g&&y)t:{for(v=g,m=y,d=0,h=v;h;h=Sn(h))d++;for(h=0,w=m;w;w=Sn(w))h++;for(;0<d-h;)v=Sn(v),d--;for(;0<h-d;)m=Sn(m),h--;for(;d--;){if(v===m||m!==null&&v===m.alternate)break t;v=Sn(v),m=Sn(m)}v=null}else v=null;g!==null&&Fu(f,p,g,v,!1),y!==null&&T!==null&&Fu(f,T,y,v,!0)}}e:{if(p=u?Ln(u):window,g=p.nodeName&&p.nodeName.toLowerCase(),g==="select"||g==="input"&&p.type==="file")var x=jg;else if(Mu(p))if(Cd)x=Bg;else{x=Ig;var C=Fg}else(g=p.nodeName)&&g.toLowerCase()==="input"&&(p.type==="checkbox"||p.type==="radio")&&(x=zg);if(x&&(x=x(e,u))){Pd(f,x,n,c);break e}C&&C(e,p,u),e==="focusout"&&(C=p._wrapperState)&&C.controlled&&p.type==="number"&&Ws(p,"number",p.value)}switch(C=u?Ln(u):window,e){case"focusin":(Mu(C)||C.contentEditable==="true")&&(En=C,nl=u,kr=null);break;case"focusout":kr=nl=En=null;break;case"mousedown":rl=!0;break;case"contextmenu":case"mouseup":case"dragend":rl=!1,Nu(f,n,c);break;case"selectionchange":if(Hg)break;case"keydown":case"keyup":Nu(f,n,c)}var E;if(ua)e:{switch(e){case"compositionstart":var k="onCompositionStart";break e;case"compositionend":k="onCompositionEnd";break e;case"compositionupdate":k="onCompositionUpdate";break e}k=void 0}else Tn?Sd(e,n)&&(k="onCompositionEnd"):e==="keydown"&&n.keyCode===229&&(k="onCompositionStart");k&&(xd&&n.locale!=="ko"&&(Tn||k!=="onCompositionStart"?k==="onCompositionEnd"&&Tn&&(E=wd()):(Vt=c,sa="value"in Vt?Vt.value:Vt.textContent,Tn=!0)),C=Xi(u,k),0<C.length&&(k=new Tu(k,e,null,n,c),f.push({event:k,listeners:C}),E?k.data=E:(E=kd(n),E!==null&&(k.data=E)))),(E=Vg?Ag(e,n):_g(e,n))&&(u=Xi(u,"onBeforeInput"),0<u.length&&(c=new Tu("onBeforeInput","beforeinput",null,n,c),f.push({event:c,listeners:u}),c.data=E))}Nd(f,t)})}function Br(e,t,n){return{instance:e,listener:t,currentTarget:n}}function Xi(e,t){for(var n=t+"Capture",r=[];e!==null;){var i=e,o=i.stateNode;i.tag===5&&o!==null&&(i=o,o=_r(e,n),o!=null&&r.unshift(Br(e,o,i)),o=_r(e,t),o!=null&&r.push(Br(e,o,i))),e=e.return}return r}function Sn(e){if(e===null)return null;do e=e.return;while(e&&e.tag!==5);return e||null}function Fu(e,t,n,r,i){for(var o=t._reactName,s=[];n!==null&&n!==r;){var l=n,a=l.alternate,u=l.stateNode;if(a!==null&&a===r)break;l.tag===5&&u!==null&&(l=u,i?(a=_r(n,o),a!=null&&s.unshift(Br(n,a,l))):i||(a=_r(n,o),a!=null&&s.push(Br(n,a,l)))),n=n.return}s.length!==0&&e.push({event:t,listeners:s})}var Qg=/\r\n?/g,Yg=/\u0000|\uFFFD/g;function Iu(e){return(typeof e=="string"?e:""+e).replace(Qg,`
-`).replace(Yg,"")}function vi(e,t,n){if(t=Iu(t),Iu(e)!==t&&n)throw Error(P(425))}function Zi(){}var il=null,ol=null;function sl(e,t){return e==="textarea"||e==="noscript"||typeof t.children=="string"||typeof t.children=="number"||typeof t.dangerouslySetInnerHTML=="object"&&t.dangerouslySetInnerHTML!==null&&t.dangerouslySetInnerHTML.__html!=null}var ll=typeof setTimeout=="function"?setTimeout:void 0,Xg=typeof clearTimeout=="function"?clearTimeout:void 0,zu=typeof Promise=="function"?Promise:void 0,Zg=typeof queueMicrotask=="function"?queueMicrotask:typeof zu<"u"?function(e){return zu.resolve(null).then(e).catch(qg)}:ll;function qg(e){setTimeout(function(){throw e})}function us(e,t){var n=t,r=0;do{var i=n.nextSibling;if(e.removeChild(n),i&&i.nodeType===8)if(n=i.data,n==="/$"){if(r===0){e.removeChild(i),jr(t);return}r--}else n!=="$"&&n!=="$?"&&n!=="$!"||r++;n=i}while(n);jr(t)}function jt(e){for(;e!=null;e=e.nextSibling){var t=e.nodeType;if(t===1||t===3)break;if(t===8){if(t=e.data,t==="$"||t==="$!"||t==="$?")break;if(t==="/$")return null}}return e}function Bu(e){e=e.previousSibling;for(var t=0;e;){if(e.nodeType===8){var n=e.data;if(n==="$"||n==="$!"||n==="$?"){if(t===0)return e;t--}else n==="/$"&&t++}e=e.previousSibling}return null}var nr=Math.random().toString(36).slice(2),st="__reactFiber$"+nr,Ur="__reactProps$"+nr,wt="__reactContainer$"+nr,al="__reactEvents$"+nr,Jg="__reactListeners$"+nr,bg="__reactHandles$"+nr;function sn(e){var t=e[st];if(t)return t;for(var n=e.parentNode;n;){if(t=n[wt]||n[st]){if(n=t.alternate,t.child!==null||n!==null&&n.child!==null)for(e=Bu(e);e!==null;){if(n=e[st])return n;e=Bu(e)}return t}e=n,n=e.parentNode}return null}function ti(e){return e=e[st]||e[wt],!e||e.tag!==5&&e.tag!==6&&e.tag!==13&&e.tag!==3?null:e}function Ln(e){if(e.tag===5||e.tag===6)return e.stateNode;throw Error(P(33))}function Do(e){return e[Ur]||null}var ul=[],Mn=-1;function Yt(e){return{current:e}}function G(e){0>Mn||(e.current=ul[Mn],ul[Mn]=null,Mn--)}function H(e,t){Mn++,ul[Mn]=e.current,e.current=t}var Wt={},we=Yt(Wt),Le=Yt(!1),dn=Wt;function Qn(e,t){var n=e.type.contextTypes;if(!n)return Wt;var r=e.stateNode;if(r&&r.__reactInternalMemoizedUnmaskedChildContext===t)return r.__reactInternalMemoizedMaskedChildContext;var i={},o;for(o in n)i[o]=t[o];return r&&(e=e.stateNode,e.__reactInternalMemoizedUnmaskedChildContext=t,e.__reactInternalMemoizedMaskedChildContext=i),i}function Me(e){return e=e.childContextTypes,e!=null}function qi(){G(Le),G(we)}function Uu(e,t,n){if(we.current!==Wt)throw Error(P(168));H(we,t),H(Le,n)}function jd(e,t,n){var r=e.stateNode;if(t=t.childContextTypes,typeof r.getChildContext!="function")return n;r=r.getChildContext();for(var i in r)if(!(i in t))throw Error(P(108,Fm(e)||"Unknown",i));return J({},n,r)}function Ji(e){return e=(e=e.stateNode)&&e.__reactInternalMemoizedMergedChildContext||Wt,dn=we.current,H(we,e),H(Le,Le.current),!0}function $u(e,t,n){var r=e.stateNode;if(!r)throw Error(P(169));n?(e=jd(e,t,dn),r.__reactInternalMemoizedMergedChildContext=e,G(Le),G(we),H(we,e)):G(Le),H(Le,n)}var ft=null,Lo=!1,cs=!1;function Fd(e){ft===null?ft=[e]:ft.push(e)}function ey(e){Lo=!0,Fd(e)}function Xt(){if(!cs&&ft!==null){cs=!0;var e=0,t=B;try{var n=ft;for(B=1;e<n.length;e++){var r=n[e];do r=r(!0);while(r!==null)}ft=null,Lo=!1}catch(i){throw ft!==null&&(ft=ft.slice(e+1)),ad(na,Xt),i}finally{B=t,cs=!1}}return null}var Rn=[],Vn=0,bi=null,eo=0,He=[],We=0,pn=null,dt=1,pt="";function tn(e,t){Rn[Vn++]=eo,Rn[Vn++]=bi,bi=e,eo=t}function Id(e,t,n){He[We++]=dt,He[We++]=pt,He[We++]=pn,pn=e;var r=dt;e=pt;var i=32-et(r)-1;r&=~(1<<i),n+=1;var o=32-et(t)+i;if(30<o){var s=i-i%5;o=(r&(1<<s)-1).toString(32),r>>=s,i-=s,dt=1<<32-et(t)+i|n<<i|r,pt=o+e}else dt=1<<o|n<<i|r,pt=e}function fa(e){e.return!==null&&(tn(e,1),Id(e,1,0))}function da(e){for(;e===bi;)bi=Rn[--Vn],Rn[Vn]=null,eo=Rn[--Vn],Rn[Vn]=null;for(;e===pn;)pn=He[--We],He[We]=null,pt=He[--We],He[We]=null,dt=He[--We],He[We]=null}var Oe=null,Ne=null,K=!1,be=null;function zd(e,t){var n=Ge(5,null,null,0);n.elementType="DELETED",n.stateNode=t,n.return=e,t=e.deletions,t===null?(e.deletions=[n],e.flags|=16):t.push(n)}function Hu(e,t){switch(e.tag){case 5:var n=e.type;return t=t.nodeType!==1||n.toLowerCase()!==t.nodeName.toLowerCase()?null:t,t!==null?(e.stateNode=t,Oe=e,Ne=jt(t.firstChild),!0):!1;case 6:return t=e.pendingProps===""||t.nodeType!==3?null:t,t!==null?(e.stateNode=t,Oe=e,Ne=null,!0):!1;case 13:return t=t.nodeType!==8?null:t,t!==null?(n=pn!==null?{id:dt,overflow:pt}:null,e.memoizedState={dehydrated:t,treeContext:n,retryLane:1073741824},n=Ge(18,null,null,0),n.stateNode=t,n.return=e,e.child=n,Oe=e,Ne=null,!0):!1;default:return!1}}function cl(e){return(e.mode&1)!==0&&(e.flags&128)===0}function fl(e){if(K){var t=Ne;if(t){var n=t;if(!Hu(e,t)){if(cl(e))throw Error(P(418));t=jt(n.nextSibling);var r=Oe;t&&Hu(e,t)?zd(r,n):(e.flags=e.flags&-4097|2,K=!1,Oe=e)}}else{if(cl(e))throw Error(P(418));e.flags=e.flags&-4097|2,K=!1,Oe=e}}}function Wu(e){for(e=e.return;e!==null&&e.tag!==5&&e.tag!==3&&e.tag!==13;)e=e.return;Oe=e}function wi(e){if(e!==Oe)return!1;if(!K)return Wu(e),K=!0,!1;var t;if((t=e.tag!==3)&&!(t=e.tag!==5)&&(t=e.type,t=t!=="head"&&t!=="body"&&!sl(e.type,e.memoizedProps)),t&&(t=Ne)){if(cl(e))throw Bd(),Error(P(418));for(;t;)zd(e,t),t=jt(t.nextSibling)}if(Wu(e),e.tag===13){if(e=e.memoizedState,e=e!==null?e.dehydrated:null,!e)throw Error(P(317));e:{for(e=e.nextSibling,t=0;e;){if(e.nodeType===8){var n=e.data;if(n==="/$"){if(t===0){Ne=jt(e.nextSibling);break e}t--}else n!=="$"&&n!=="$!"&&n!=="$?"||t++}e=e.nextSibling}Ne=null}}else Ne=Oe?jt(e.stateNode.nextSibling):null;return!0}function Bd(){for(var e=Ne;e;)e=jt(e.nextSibling)}function Yn(){Ne=Oe=null,K=!1}function pa(e){be===null?be=[e]:be.push(e)}var ty=Pt.ReactCurrentBatchConfig;function qe(e,t){if(e&&e.defaultProps){t=J({},t),e=e.defaultProps;for(var n in e)t[n]===void 0&&(t[n]=e[n]);return t}return t}var to=Yt(null),no=null,An=null,ha=null;function ma(){ha=An=no=null}function ga(e){var t=to.current;G(to),e._currentValue=t}function dl(e,t,n){for(;e!==null;){var r=e.alternate;if((e.childLanes&t)!==t?(e.childLanes|=t,r!==null&&(r.childLanes|=t)):r!==null&&(r.childLanes&t)!==t&&(r.childLanes|=t),e===n)break;e=e.return}}function Hn(e,t){no=e,ha=An=null,e=e.dependencies,e!==null&&e.firstContext!==null&&(e.lanes&t&&(De=!0),e.firstContext=null)}function Qe(e){var t=e._currentValue;if(ha!==e)if(e={context:e,memoizedValue:t,next:null},An===null){if(no===null)throw Error(P(308));An=e,no.dependencies={lanes:0,firstContext:e}}else An=An.next=e;return t}var ln=null;function ya(e){ln===null?ln=[e]:ln.push(e)}function Ud(e,t,n,r){var i=t.interleaved;return i===null?(n.next=n,ya(t)):(n.next=i.next,i.next=n),t.interleaved=n,xt(e,r)}function xt(e,t){e.lanes|=t;var n=e.alternate;for(n!==null&&(n.lanes|=t),n=e,e=e.return;e!==null;)e.childLanes|=t,n=e.alternate,n!==null&&(n.childLanes|=t),n=e,e=e.return;return n.tag===3?n.stateNode:null}var Dt=!1;function va(e){e.updateQueue={baseState:e.memoizedState,firstBaseUpdate:null,lastBaseUpdate:null,shared:{pending:null,interleaved:null,lanes:0},effects:null}}function $d(e,t){e=e.updateQueue,t.updateQueue===e&&(t.updateQueue={baseState:e.baseState,firstBaseUpdate:e.firstBaseUpdate,lastBaseUpdate:e.lastBaseUpdate,shared:e.shared,effects:e.effects})}function mt(e,t){return{eventTime:e,lane:t,tag:0,payload:null,callback:null,next:null}}function Ft(e,t,n){var r=e.updateQueue;if(r===null)return null;if(r=r.shared,z&2){var i=r.pending;return i===null?t.next=t:(t.next=i.next,i.next=t),r.pending=t,xt(e,n)}return i=r.interleaved,i===null?(t.next=t,ya(r)):(t.next=i.next,i.next=t),r.interleaved=t,xt(e,n)}function _i(e,t,n){if(t=t.updateQueue,t!==null&&(t=t.shared,(n&4194240)!==0)){var r=t.lanes;r&=e.pendingLanes,n|=r,t.lanes=n,ra(e,n)}}function Gu(e,t){var n=e.updateQueue,r=e.alternate;if(r!==null&&(r=r.updateQueue,n===r)){var i=null,o=null;if(n=n.firstBaseUpdate,n!==null){do{var s={eventTime:n.eventTime,lane:n.lane,tag:n.tag,payload:n.payload,callback:n.callback,next:null};o===null?i=o=s:o=o.next=s,n=n.next}while(n!==null);o===null?i=o=t:o=o.next=t}else i=o=t;n={baseState:r.baseState,firstBaseUpdate:i,lastBaseUpdate:o,shared:r.shared,effects:r.effects},e.updateQueue=n;return}e=n.lastBaseUpdate,e===null?n.firstBaseUpdate=t:e.next=t,n.lastBaseUpdate=t}function ro(e,t,n,r){var i=e.updateQueue;Dt=!1;var o=i.firstBaseUpdate,s=i.lastBaseUpdate,l=i.shared.pending;if(l!==null){i.shared.pending=null;var a=l,u=a.next;a.next=null,s===null?o=u:s.next=u,s=a;var c=e.alternate;c!==null&&(c=c.updateQueue,l=c.lastBaseUpdate,l!==s&&(l===null?c.firstBaseUpdate=u:l.next=u,c.lastBaseUpdate=a))}if(o!==null){var f=i.baseState;s=0,c=u=a=null,l=o;do{var p=l.lane,g=l.eventTime;if((r&p)===p){c!==null&&(c=c.next={eventTime:g,lane:0,tag:l.tag,payload:l.payload,callback:l.callback,next:null});e:{var y=e,v=l;switch(p=t,g=n,v.tag){case 1:if(y=v.payload,typeof y=="function"){f=y.call(g,f,p);break e}f=y;break e;case 3:y.flags=y.flags&-65537|128;case 0:if(y=v.payload,p=typeof y=="function"?y.call(g,f,p):y,p==null)break e;f=J({},f,p);break e;case 2:Dt=!0}}l.callback!==null&&l.lane!==0&&(e.flags|=64,p=i.effects,p===null?i.effects=[l]:p.push(l))}else g={eventTime:g,lane:p,tag:l.tag,payload:l.payload,callback:l.callback,next:null},c===null?(u=c=g,a=f):c=c.next=g,s|=p;if(l=l.next,l===null){if(l=i.shared.pending,l===null)break;p=l,l=p.next,p.next=null,i.lastBaseUpdate=p,i.shared.pending=null}}while(1);if(c===null&&(a=f),i.baseState=a,i.firstBaseUpdate=u,i.lastBaseUpdate=c,t=i.shared.interleaved,t!==null){i=t;do s|=i.lane,i=i.next;while(i!==t)}else o===null&&(i.shared.lanes=0);mn|=s,e.lanes=s,e.memoizedState=f}}function Ku(e,t,n){if(e=t.effects,t.effects=null,e!==null)for(t=0;t<e.length;t++){var r=e[t],i=r.callback;if(i!==null){if(r.callback=null,r=n,typeof i!="function")throw Error(P(191,i));i.call(r)}}}var Hd=new Uf.Component().refs;function pl(e,t,n,r){t=e.memoizedState,n=n(r,t),n=n==null?t:J({},t,n),e.memoizedState=n,e.lanes===0&&(e.updateQueue.baseState=n)}var Mo={isMounted:function(e){return(e=e._reactInternals)?vn(e)===e:!1},enqueueSetState:function(e,t,n){e=e._reactInternals;var r=ke(),i=zt(e),o=mt(r,i);o.payload=t,n!=null&&(o.callback=n),t=Ft(e,o,i),t!==null&&(tt(t,e,i,r),_i(t,e,i))},enqueueReplaceState:function(e,t,n){e=e._reactInternals;var r=ke(),i=zt(e),o=mt(r,i);o.tag=1,o.payload=t,n!=null&&(o.callback=n),t=Ft(e,o,i),t!==null&&(tt(t,e,i,r),_i(t,e,i))},enqueueForceUpdate:function(e,t){e=e._reactInternals;var n=ke(),r=zt(e),i=mt(n,r);i.tag=2,t!=null&&(i.callback=t),t=Ft(e,i,r),t!==null&&(tt(t,e,r,n),_i(t,e,r))}};function Qu(e,t,n,r,i,o,s){return e=e.stateNode,typeof e.shouldComponentUpdate=="function"?e.shouldComponentUpdate(r,o,s):t.prototype&&t.prototype.isPureReactComponent?!Ir(n,r)||!Ir(i,o):!0}function Wd(e,t,n){var r=!1,i=Wt,o=t.contextType;return typeof o=="object"&&o!==null?o=Qe(o):(i=Me(t)?dn:we.current,r=t.contextTypes,o=(r=r!=null)?Qn(e,i):Wt),t=new t(n,o),e.memoizedState=t.state!==null&&t.state!==void 0?t.state:null,t.updater=Mo,e.stateNode=t,t._reactInternals=e,r&&(e=e.stateNode,e.__reactInternalMemoizedUnmaskedChildContext=i,e.__reactInternalMemoizedMaskedChildContext=o),t}function Yu(e,t,n,r){e=t.state,typeof t.componentWillReceiveProps=="function"&&t.componentWillReceiveProps(n,r),typeof t.UNSAFE_componentWillReceiveProps=="function"&&t.UNSAFE_componentWillReceiveProps(n,r),t.state!==e&&Mo.enqueueReplaceState(t,t.state,null)}function hl(e,t,n,r){var i=e.stateNode;i.props=n,i.state=e.memoizedState,i.refs=Hd,va(e);var o=t.contextType;typeof o=="object"&&o!==null?i.context=Qe(o):(o=Me(t)?dn:we.current,i.context=Qn(e,o)),i.state=e.memoizedState,o=t.getDerivedStateFromProps,typeof o=="function"&&(pl(e,t,o,n),i.state=e.memoizedState),typeof t.getDerivedStateFromProps=="function"||typeof i.getSnapshotBeforeUpdate=="function"||typeof i.UNSAFE_componentWillMount!="function"&&typeof i.componentWillMount!="function"||(t=i.state,typeof i.componentWillMount=="function"&&i.componentWillMount(),typeof i.UNSAFE_componentWillMount=="function"&&i.UNSAFE_componentWillMount(),t!==i.state&&Mo.enqueueReplaceState(i,i.state,null),ro(e,n,i,r),i.state=e.memoizedState),typeof i.componentDidMount=="function"&&(e.flags|=4194308)}function ar(e,t,n){if(e=n.ref,e!==null&&typeof e!="function"&&typeof e!="object"){if(n._owner){if(n=n._owner,n){if(n.tag!==1)throw Error(P(309));var r=n.stateNode}if(!r)throw Error(P(147,e));var i=r,o=""+e;return t!==null&&t.ref!==null&&typeof t.ref=="function"&&t.ref._stringRef===o?t.ref:(t=function(s){var l=i.refs;l===Hd&&(l=i.refs={}),s===null?delete l[o]:l[o]=s},t._stringRef=o,t)}if(typeof e!="string")throw Error(P(284));if(!n._owner)throw Error(P(290,e))}return e}function xi(e,t){throw e=Object.prototype.toString.call(t),Error(P(31,e==="[object Object]"?"object with keys {"+Object.keys(t).join(", ")+"}":e))}function Xu(e){var t=e._init;return t(e._payload)}function Gd(e){function t(m,d){if(e){var h=m.deletions;h===null?(m.deletions=[d],m.flags|=16):h.push(d)}}function n(m,d){if(!e)return null;for(;d!==null;)t(m,d),d=d.sibling;return null}function r(m,d){for(m=new Map;d!==null;)d.key!==null?m.set(d.key,d):m.set(d.index,d),d=d.sibling;return m}function i(m,d){return m=Bt(m,d),m.index=0,m.sibling=null,m}function o(m,d,h){return m.index=h,e?(h=m.alternate,h!==null?(h=h.index,h<d?(m.flags|=2,d):h):(m.flags|=2,d)):(m.flags|=1048576,d)}function s(m){return e&&m.alternate===null&&(m.flags|=2),m}function l(m,d,h,w){return d===null||d.tag!==6?(d=ys(h,m.mode,w),d.return=m,d):(d=i(d,h),d.return=m,d)}function a(m,d,h,w){var x=h.type;return x===Cn?c(m,d,h.props.children,w,h.key):d!==null&&(d.elementType===x||typeof x=="object"&&x!==null&&x.$$typeof===Et&&Xu(x)===d.type)?(w=i(d,h.props),w.ref=ar(m,d,h),w.return=m,w):(w=zi(h.type,h.key,h.props,null,m.mode,w),w.ref=ar(m,d,h),w.return=m,w)}function u(m,d,h,w){return d===null||d.tag!==4||d.stateNode.containerInfo!==h.containerInfo||d.stateNode.implementation!==h.implementation?(d=vs(h,m.mode,w),d.return=m,d):(d=i(d,h.children||[]),d.return=m,d)}function c(m,d,h,w,x){return d===null||d.tag!==7?(d=fn(h,m.mode,w,x),d.return=m,d):(d=i(d,h),d.return=m,d)}function f(m,d,h){if(typeof d=="string"&&d!==""||typeof d=="number")return d=ys(""+d,m.mode,h),d.return=m,d;if(typeof d=="object"&&d!==null){switch(d.$$typeof){case ui:return h=zi(d.type,d.key,d.props,null,m.mode,h),h.ref=ar(m,null,d),h.return=m,h;case Pn:return d=vs(d,m.mode,h),d.return=m,d;case Et:var w=d._init;return f(m,w(d._payload),h)}if(hr(d)||rr(d))return d=fn(d,m.mode,h,null),d.return=m,d;xi(m,d)}return null}function p(m,d,h,w){var x=d!==null?d.key:null;if(typeof h=="string"&&h!==""||typeof h=="number")return x!==null?null:l(m,d,""+h,w);if(typeof h=="object"&&h!==null){switch(h.$$typeof){case ui:return h.key===x?a(m,d,h,w):null;case Pn:return h.key===x?u(m,d,h,w):null;case Et:return x=h._init,p(m,d,x(h._payload),w)}if(hr(h)||rr(h))return x!==null?null:c(m,d,h,w,null);xi(m,h)}return null}function g(m,d,h,w,x){if(typeof w=="string"&&w!==""||typeof w=="number")return m=m.get(h)||null,l(d,m,""+w,x);if(typeof w=="object"&&w!==null){switch(w.$$typeof){case ui:return m=m.get(w.key===null?h:w.key)||null,a(d,m,w,x);case Pn:return m=m.get(w.key===null?h:w.key)||null,u(d,m,w,x);case Et:var C=w._init;return g(m,d,h,C(w._payload),x)}if(hr(w)||rr(w))return m=m.get(h)||null,c(d,m,w,x,null);xi(d,w)}return null}function y(m,d,h,w){for(var x=null,C=null,E=d,k=d=0,V=null;E!==null&&k<h.length;k++){E.index>k?(V=E,E=null):V=E.sibling;var R=p(m,E,h[k],w);if(R===null){E===null&&(E=V);break}e&&E&&R.alternate===null&&t(m,E),d=o(R,d,k),C===null?x=R:C.sibling=R,C=R,E=V}if(k===h.length)return n(m,E),K&&tn(m,k),x;if(E===null){for(;k<h.length;k++)E=f(m,h[k],w),E!==null&&(d=o(E,d,k),C===null?x=E:C.sibling=E,C=E);return K&&tn(m,k),x}for(E=r(m,E);k<h.length;k++)V=g(E,m,k,h[k],w),V!==null&&(e&&V.alternate!==null&&E.delete(V.key===null?k:V.key),d=o(V,d,k),C===null?x=V:C.sibling=V,C=V);return e&&E.forEach(function(j){return t(m,j)}),K&&tn(m,k),x}function v(m,d,h,w){var x=rr(h);if(typeof x!="function")throw Error(P(150));if(h=x.call(h),h==null)throw Error(P(151));for(var C=x=null,E=d,k=d=0,V=null,R=h.next();E!==null&&!R.done;k++,R=h.next()){E.index>k?(V=E,E=null):V=E.sibling;var j=p(m,E,R.value,w);if(j===null){E===null&&(E=V);break}e&&E&&j.alternate===null&&t(m,E),d=o(j,d,k),C===null?x=j:C.sibling=j,C=j,E=V}if(R.done)return n(m,E),K&&tn(m,k),x;if(E===null){for(;!R.done;k++,R=h.next())R=f(m,R.value,w),R!==null&&(d=o(R,d,k),C===null?x=R:C.sibling=R,C=R);return K&&tn(m,k),x}for(E=r(m,E);!R.done;k++,R=h.next())R=g(E,m,k,R.value,w),R!==null&&(e&&R.alternate!==null&&E.delete(R.key===null?k:R.key),d=o(R,d,k),C===null?x=R:C.sibling=R,C=R);return e&&E.forEach(function(de){return t(m,de)}),K&&tn(m,k),x}function T(m,d,h,w){if(typeof h=="object"&&h!==null&&h.type===Cn&&h.key===null&&(h=h.props.children),typeof h=="object"&&h!==null){switch(h.$$typeof){case ui:e:{for(var x=h.key,C=d;C!==null;){if(C.key===x){if(x=h.type,x===Cn){if(C.tag===7){n(m,C.sibling),d=i(C,h.props.children),d.return=m,m=d;break e}}else if(C.elementType===x||typeof x=="object"&&x!==null&&x.$$typeof===Et&&Xu(x)===C.type){n(m,C.sibling),d=i(C,h.props),d.ref=ar(m,C,h),d.return=m,m=d;break e}n(m,C);break}else t(m,C);C=C.sibling}h.type===Cn?(d=fn(h.props.children,m.mode,w,h.key),d.return=m,m=d):(w=zi(h.type,h.key,h.props,null,m.mode,w),w.ref=ar(m,d,h),w.return=m,m=w)}return s(m);case Pn:e:{for(C=h.key;d!==null;){if(d.key===C)if(d.tag===4&&d.stateNode.containerInfo===h.containerInfo&&d.stateNode.implementation===h.implementation){n(m,d.sibling),d=i(d,h.children||[]),d.return=m,m=d;break e}else{n(m,d);break}else t(m,d);d=d.sibling}d=vs(h,m.mode,w),d.return=m,m=d}return s(m);case Et:return C=h._init,T(m,d,C(h._payload),w)}if(hr(h))return y(m,d,h,w);if(rr(h))return v(m,d,h,w);xi(m,h)}return typeof h=="string"&&h!==""||typeof h=="number"?(h=""+h,d!==null&&d.tag===6?(n(m,d.sibling),d=i(d,h),d.return=m,m=d):(n(m,d),d=ys(h,m.mode,w),d.return=m,m=d),s(m)):n(m,d)}return T}var Xn=Gd(!0),Kd=Gd(!1),ni={},at=Yt(ni),$r=Yt(ni),Hr=Yt(ni);function an(e){if(e===ni)throw Error(P(174));return e}function wa(e,t){switch(H(Hr,t),H($r,e),H(at,ni),e=t.nodeType,e){case 9:case 11:t=(t=t.documentElement)?t.namespaceURI:Ks(null,"");break;default:e=e===8?t.parentNode:t,t=e.namespaceURI||null,e=e.tagName,t=Ks(t,e)}G(at),H(at,t)}function Zn(){G(at),G($r),G(Hr)}function Qd(e){an(Hr.current);var t=an(at.current),n=Ks(t,e.type);t!==n&&(H($r,e),H(at,n))}function xa(e){$r.current===e&&(G(at),G($r))}var X=Yt(0);function io(e){for(var t=e;t!==null;){if(t.tag===13){var n=t.memoizedState;if(n!==null&&(n=n.dehydrated,n===null||n.data==="$?"||n.data==="$!"))return t}else if(t.tag===19&&t.memoizedProps.revealOrder!==void 0){if(t.flags&128)return t}else if(t.child!==null){t.child.return=t,t=t.child;continue}if(t===e)break;for(;t.sibling===null;){if(t.return===null||t.return===e)return null;t=t.return}t.sibling.return=t.return,t=t.sibling}return null}var fs=[];function Sa(){for(var e=0;e<fs.length;e++)fs[e]._workInProgressVersionPrimary=null;fs.length=0}var Ni=Pt.ReactCurrentDispatcher,ds=Pt.ReactCurrentBatchConfig,hn=0,q=null,ie=null,le=null,oo=!1,Pr=!1,Wr=0,ny=0;function ge(){throw Error(P(321))}function ka(e,t){if(t===null)return!1;for(var n=0;n<t.length&&n<e.length;n++)if(!nt(e[n],t[n]))return!1;return!0}function Pa(e,t,n,r,i,o){if(hn=o,q=t,t.memoizedState=null,t.updateQueue=null,t.lanes=0,Ni.current=e===null||e.memoizedState===null?sy:ly,e=n(r,i),Pr){o=0;do{if(Pr=!1,Wr=0,25<=o)throw Error(P(301));o+=1,le=ie=null,t.updateQueue=null,Ni.current=ay,e=n(r,i)}while(Pr)}if(Ni.current=so,t=ie!==null&&ie.next!==null,hn=0,le=ie=q=null,oo=!1,t)throw Error(P(300));return e}function Ca(){var e=Wr!==0;return Wr=0,e}function it(){var e={memoizedState:null,baseState:null,baseQueue:null,queue:null,next:null};return le===null?q.memoizedState=le=e:le=le.next=e,le}function Ye(){if(ie===null){var e=q.alternate;e=e!==null?e.memoizedState:null}else e=ie.next;var t=le===null?q.memoizedState:le.next;if(t!==null)le=t,ie=e;else{if(e===null)throw Error(P(310));ie=e,e={memoizedState:ie.memoizedState,baseState:ie.baseState,baseQueue:ie.baseQueue,queue:ie.queue,next:null},le===null?q.memoizedState=le=e:le=le.next=e}return le}function Gr(e,t){return typeof t=="function"?t(e):t}function ps(e){var t=Ye(),n=t.queue;if(n===null)throw Error(P(311));n.lastRenderedReducer=e;var r=ie,i=r.baseQueue,o=n.pending;if(o!==null){if(i!==null){var s=i.next;i.next=o.next,o.next=s}r.baseQueue=i=o,n.pending=null}if(i!==null){o=i.next,r=r.baseState;var l=s=null,a=null,u=o;do{var c=u.lane;if((hn&c)===c)a!==null&&(a=a.next={lane:0,action:u.action,hasEagerState:u.hasEagerState,eagerState:u.eagerState,next:null}),r=u.hasEagerState?u.eagerState:e(r,u.action);else{var f={lane:c,action:u.action,hasEagerState:u.hasEagerState,eagerState:u.eagerState,next:null};a===null?(l=a=f,s=r):a=a.next=f,q.lanes|=c,mn|=c}u=u.next}while(u!==null&&u!==o);a===null?s=r:a.next=l,nt(r,t.memoizedState)||(De=!0),t.memoizedState=r,t.baseState=s,t.baseQueue=a,n.lastRenderedState=r}if(e=n.interleaved,e!==null){i=e;do o=i.lane,q.lanes|=o,mn|=o,i=i.next;while(i!==e)}else i===null&&(n.lanes=0);return[t.memoizedState,n.dispatch]}function hs(e){var t=Ye(),n=t.queue;if(n===null)throw Error(P(311));n.lastRenderedReducer=e;var r=n.dispatch,i=n.pending,o=t.memoizedState;if(i!==null){n.pending=null;var s=i=i.next;do o=e(o,s.action),s=s.next;while(s!==i);nt(o,t.memoizedState)||(De=!0),t.memoizedState=o,t.baseQueue===null&&(t.baseState=o),n.lastRenderedState=o}return[o,r]}function Yd(){}function Xd(e,t){var n=q,r=Ye(),i=t(),o=!nt(r.memoizedState,i);if(o&&(r.memoizedState=i,De=!0),r=r.queue,Ta(Jd.bind(null,n,r,e),[e]),r.getSnapshot!==t||o||le!==null&&le.memoizedState.tag&1){if(n.flags|=2048,Kr(9,qd.bind(null,n,r,i,t),void 0,null),ae===null)throw Error(P(349));hn&30||Zd(n,t,i)}return i}function Zd(e,t,n){e.flags|=16384,e={getSnapshot:t,value:n},t=q.updateQueue,t===null?(t={lastEffect:null,stores:null},q.updateQueue=t,t.stores=[e]):(n=t.stores,n===null?t.stores=[e]:n.push(e))}function qd(e,t,n,r){t.value=n,t.getSnapshot=r,bd(t)&&ep(e)}function Jd(e,t,n){return n(function(){bd(t)&&ep(e)})}function bd(e){var t=e.getSnapshot;e=e.value;try{var n=t();return!nt(e,n)}catch{return!0}}function ep(e){var t=xt(e,1);t!==null&&tt(t,e,1,-1)}function Zu(e){var t=it();return typeof e=="function"&&(e=e()),t.memoizedState=t.baseState=e,e={pending:null,interleaved:null,lanes:0,dispatch:null,lastRenderedReducer:Gr,lastRenderedState:e},t.queue=e,e=e.dispatch=oy.bind(null,q,e),[t.memoizedState,e]}function Kr(e,t,n,r){return e={tag:e,create:t,destroy:n,deps:r,next:null},t=q.updateQueue,t===null?(t={lastEffect:null,stores:null},q.updateQueue=t,t.lastEffect=e.next=e):(n=t.lastEffect,n===null?t.lastEffect=e.next=e:(r=n.next,n.next=e,e.next=r,t.lastEffect=e)),e}function tp(){return Ye().memoizedState}function Oi(e,t,n,r){var i=it();q.flags|=e,i.memoizedState=Kr(1|t,n,void 0,r===void 0?null:r)}function Ro(e,t,n,r){var i=Ye();r=r===void 0?null:r;var o=void 0;if(ie!==null){var s=ie.memoizedState;if(o=s.destroy,r!==null&&ka(r,s.deps)){i.memoizedState=Kr(t,n,o,r);return}}q.flags|=e,i.memoizedState=Kr(1|t,n,o,r)}function qu(e,t){return Oi(8390656,8,e,t)}function Ta(e,t){return Ro(2048,8,e,t)}function np(e,t){return Ro(4,2,e,t)}function rp(e,t){return Ro(4,4,e,t)}function ip(e,t){if(typeof t=="function")return e=e(),t(e),function(){t(null)};if(t!=null)return e=e(),t.current=e,function(){t.current=null}}function op(e,t,n){return n=n!=null?n.concat([e]):null,Ro(4,4,ip.bind(null,t,e),n)}function Ea(){}function sp(e,t){var n=Ye();t=t===void 0?null:t;var r=n.memoizedState;return r!==null&&t!==null&&ka(t,r[1])?r[0]:(n.memoizedState=[e,t],e)}function lp(e,t){var n=Ye();t=t===void 0?null:t;var r=n.memoizedState;return r!==null&&t!==null&&ka(t,r[1])?r[0]:(e=e(),n.memoizedState=[e,t],e)}function ap(e,t,n){return hn&21?(nt(n,t)||(n=fd(),q.lanes|=n,mn|=n,e.baseState=!0),t):(e.baseState&&(e.baseState=!1,De=!0),e.memoizedState=n)}function ry(e,t){var n=B;B=n!==0&&4>n?n:4,e(!0);var r=ds.transition;ds.transition={};try{e(!1),t()}finally{B=n,ds.transition=r}}function up(){return Ye().memoizedState}function iy(e,t,n){var r=zt(e);if(n={lane:r,action:n,hasEagerState:!1,eagerState:null,next:null},cp(e))fp(t,n);else if(n=Ud(e,t,n,r),n!==null){var i=ke();tt(n,e,r,i),dp(n,t,r)}}function oy(e,t,n){var r=zt(e),i={lane:r,action:n,hasEagerState:!1,eagerState:null,next:null};if(cp(e))fp(t,i);else{var o=e.alternate;if(e.lanes===0&&(o===null||o.lanes===0)&&(o=t.lastRenderedReducer,o!==null))try{var s=t.lastRenderedState,l=o(s,n);if(i.hasEagerState=!0,i.eagerState=l,nt(l,s)){var a=t.interleaved;a===null?(i.next=i,ya(t)):(i.next=a.next,a.next=i),t.interleaved=i;return}}catch{}finally{}n=Ud(e,t,i,r),n!==null&&(i=ke(),tt(n,e,r,i),dp(n,t,r))}}function cp(e){var t=e.alternate;return e===q||t!==null&&t===q}function fp(e,t){Pr=oo=!0;var n=e.pending;n===null?t.next=t:(t.next=n.next,n.next=t),e.pending=t}function dp(e,t,n){if(n&4194240){var r=t.lanes;r&=e.pendingLanes,n|=r,t.lanes=n,ra(e,n)}}var so={readContext:Qe,useCallback:ge,useContext:ge,useEffect:ge,useImperativeHandle:ge,useInsertionEffect:ge,useLayoutEffect:ge,useMemo:ge,useReducer:ge,useRef:ge,useState:ge,useDebugValue:ge,useDeferredValue:ge,useTransition:ge,useMutableSource:ge,useSyncExternalStore:ge,useId:ge,unstable_isNewReconciler:!1},sy={readContext:Qe,useCallback:function(e,t){return it().memoizedState=[e,t===void 0?null:t],e},useContext:Qe,useEffect:qu,useImperativeHandle:function(e,t,n){return n=n!=null?n.concat([e]):null,Oi(4194308,4,ip.bind(null,t,e),n)},useLayoutEffect:function(e,t){return Oi(4194308,4,e,t)},useInsertionEffect:function(e,t){return Oi(4,2,e,t)},useMemo:function(e,t){var n=it();return t=t===void 0?null:t,e=e(),n.memoizedState=[e,t],e},useReducer:function(e,t,n){var r=it();return t=n!==void 0?n(t):t,r.memoizedState=r.baseState=t,e={pending:null,interleaved:null,lanes:0,dispatch:null,lastRenderedReducer:e,lastRenderedState:t},r.queue=e,e=e.dispatch=iy.bind(null,q,e),[r.memoizedState,e]},useRef:function(e){var t=it();return e={current:e},t.memoizedState=e},useState:Zu,useDebugValue:Ea,useDeferredValue:function(e){return it().memoizedState=e},useTransition:function(){var e=Zu(!1),t=e[0];return e=ry.bind(null,e[1]),it().memoizedState=e,[t,e]},useMutableSource:function(){},useSyncExternalStore:function(e,t,n){var r=q,i=it();if(K){if(n===void 0)throw Error(P(407));n=n()}else{if(n=t(),ae===null)throw Error(P(349));hn&30||Zd(r,t,n)}i.memoizedState=n;var o={value:n,getSnapshot:t};return i.queue=o,qu(Jd.bind(null,r,o,e),[e]),r.flags|=2048,Kr(9,qd.bind(null,r,o,n,t),void 0,null),n},useId:function(){var e=it(),t=ae.identifierPrefix;if(K){var n=pt,r=dt;n=(r&~(1<<32-et(r)-1)).toString(32)+n,t=":"+t+"R"+n,n=Wr++,0<n&&(t+="H"+n.toString(32)),t+=":"}else n=ny++,t=":"+t+"r"+n.toString(32)+":";return e.memoizedState=t},unstable_isNewReconciler:!1},ly={readContext:Qe,useCallback:sp,useContext:Qe,useEffect:Ta,useImperativeHandle:op,useInsertionEffect:np,useLayoutEffect:rp,useMemo:lp,useReducer:ps,useRef:tp,useState:function(){return ps(Gr)},useDebugValue:Ea,useDeferredValue:function(e){var t=Ye();return ap(t,ie.memoizedState,e)},useTransition:function(){var e=ps(Gr)[0],t=Ye().memoizedState;return[e,t]},useMutableSource:Yd,useSyncExternalStore:Xd,useId:up,unstable_isNewReconciler:!1},ay={readContext:Qe,useCallback:sp,useContext:Qe,useEffect:Ta,useImperativeHandle:op,useInsertionEffect:np,useLayoutEffect:rp,useMemo:lp,useReducer:hs,useRef:tp,useState:function(){return hs(Gr)},useDebugValue:Ea,useDeferredValue:function(e){var t=Ye();return ie===null?t.memoizedState=e:ap(t,ie.memoizedState,e)},useTransition:function(){var e=hs(Gr)[0],t=Ye().memoizedState;return[e,t]},useMutableSource:Yd,useSyncExternalStore:Xd,useId:up,unstable_isNewReconciler:!1};function qn(e,t){try{var n="",r=t;do n+=jm(r),r=r.return;while(r);var i=n}catch(o){i=`
-Error generating stack: `+o.message+`
-`+o.stack}return{value:e,source:t,stack:i,digest:null}}function ms(e,t,n){return{value:e,source:null,stack:n??null,digest:t??null}}function ml(e,t){try{console.error(t.value)}catch(n){setTimeout(function(){throw n})}}var uy=typeof WeakMap=="function"?WeakMap:Map;function pp(e,t,n){n=mt(-1,n),n.tag=3,n.payload={element:null};var r=t.value;return n.callback=function(){ao||(ao=!0,Tl=r),ml(e,t)},n}function hp(e,t,n){n=mt(-1,n),n.tag=3;var r=e.type.getDerivedStateFromError;if(typeof r=="function"){var i=t.value;n.payload=function(){return r(i)},n.callback=function(){ml(e,t)}}var o=e.stateNode;return o!==null&&typeof o.componentDidCatch=="function"&&(n.callback=function(){ml(e,t),typeof r!="function"&&(It===null?It=new Set([this]):It.add(this));var s=t.stack;this.componentDidCatch(t.value,{componentStack:s!==null?s:""})}),n}function Ju(e,t,n){var r=e.pingCache;if(r===null){r=e.pingCache=new uy;var i=new Set;r.set(t,i)}else i=r.get(t),i===void 0&&(i=new Set,r.set(t,i));i.has(n)||(i.add(n),e=Py.bind(null,e,t,n),t.then(e,e))}function bu(e){do{var t;if((t=e.tag===13)&&(t=e.memoizedState,t=t!==null?t.dehydrated!==null:!0),t)return e;e=e.return}while(e!==null);return null}function ec(e,t,n,r,i){return e.mode&1?(e.flags|=65536,e.lanes=i,e):(e===t?e.flags|=65536:(e.flags|=128,n.flags|=131072,n.flags&=-52805,n.tag===1&&(n.alternate===null?n.tag=17:(t=mt(-1,1),t.tag=2,Ft(n,t,1))),n.lanes|=1),e)}var cy=Pt.ReactCurrentOwner,De=!1;function Se(e,t,n,r){t.child=e===null?Kd(t,null,n,r):Xn(t,e.child,n,r)}function tc(e,t,n,r,i){n=n.render;var o=t.ref;return Hn(t,i),r=Pa(e,t,n,r,o,i),n=Ca(),e!==null&&!De?(t.updateQueue=e.updateQueue,t.flags&=-2053,e.lanes&=~i,St(e,t,i)):(K&&n&&fa(t),t.flags|=1,Se(e,t,r,i),t.child)}function nc(e,t,n,r,i){if(e===null){var o=n.type;return typeof o=="function"&&!Na(o)&&o.defaultProps===void 0&&n.compare===null&&n.defaultProps===void 0?(t.tag=15,t.type=o,mp(e,t,o,r,i)):(e=zi(n.type,null,r,t,t.mode,i),e.ref=t.ref,e.return=t,t.child=e)}if(o=e.child,!(e.lanes&i)){var s=o.memoizedProps;if(n=n.compare,n=n!==null?n:Ir,n(s,r)&&e.ref===t.ref)return St(e,t,i)}return t.flags|=1,e=Bt(o,r),e.ref=t.ref,e.return=t,t.child=e}function mp(e,t,n,r,i){if(e!==null){var o=e.memoizedProps;if(Ir(o,r)&&e.ref===t.ref)if(De=!1,t.pendingProps=r=o,(e.lanes&i)!==0)e.flags&131072&&(De=!0);else return t.lanes=e.lanes,St(e,t,i)}return gl(e,t,n,r,i)}function gp(e,t,n){var r=t.pendingProps,i=r.children,o=e!==null?e.memoizedState:null;if(r.mode==="hidden")if(!(t.mode&1))t.memoizedState={baseLanes:0,cachePool:null,transitions:null},H(Nn,_e),_e|=n;else{if(!(n&1073741824))return e=o!==null?o.baseLanes|n:n,t.lanes=t.childLanes=1073741824,t.memoizedState={baseLanes:e,cachePool:null,transitions:null},t.updateQueue=null,H(Nn,_e),_e|=e,null;t.memoizedState={baseLanes:0,cachePool:null,transitions:null},r=o!==null?o.baseLanes:n,H(Nn,_e),_e|=r}else o!==null?(r=o.baseLanes|n,t.memoizedState=null):r=n,H(Nn,_e),_e|=r;return Se(e,t,i,n),t.child}function yp(e,t){var n=t.ref;(e===null&&n!==null||e!==null&&e.ref!==n)&&(t.flags|=512,t.flags|=2097152)}function gl(e,t,n,r,i){var o=Me(n)?dn:we.current;return o=Qn(t,o),Hn(t,i),n=Pa(e,t,n,r,o,i),r=Ca(),e!==null&&!De?(t.updateQueue=e.updateQueue,t.flags&=-2053,e.lanes&=~i,St(e,t,i)):(K&&r&&fa(t),t.flags|=1,Se(e,t,n,i),t.child)}function rc(e,t,n,r,i){if(Me(n)){var o=!0;Ji(t)}else o=!1;if(Hn(t,i),t.stateNode===null)ji(e,t),Wd(t,n,r),hl(t,n,r,i),r=!0;else if(e===null){var s=t.stateNode,l=t.memoizedProps;s.props=l;var a=s.context,u=n.contextType;typeof u=="object"&&u!==null?u=Qe(u):(u=Me(n)?dn:we.current,u=Qn(t,u));var c=n.getDerivedStateFromProps,f=typeof c=="function"||typeof s.getSnapshotBeforeUpdate=="function";f||typeof s.UNSAFE_componentWillReceiveProps!="function"&&typeof s.componentWillReceiveProps!="function"||(l!==r||a!==u)&&Yu(t,s,r,u),Dt=!1;var p=t.memoizedState;s.state=p,ro(t,r,s,i),a=t.memoizedState,l!==r||p!==a||Le.current||Dt?(typeof c=="function"&&(pl(t,n,c,r),a=t.memoizedState),(l=Dt||Qu(t,n,l,r,p,a,u))?(f||typeof s.UNSAFE_componentWillMount!="function"&&typeof s.componentWillMount!="function"||(typeof s.componentWillMount=="function"&&s.componentWillMount(),typeof s.UNSAFE_componentWillMount=="function"&&s.UNSAFE_componentWillMount()),typeof s.componentDidMount=="function"&&(t.flags|=4194308)):(typeof s.componentDidMount=="function"&&(t.flags|=4194308),t.memoizedProps=r,t.memoizedState=a),s.props=r,s.state=a,s.context=u,r=l):(typeof s.componentDidMount=="function"&&(t.flags|=4194308),r=!1)}else{s=t.stateNode,$d(e,t),l=t.memoizedProps,u=t.type===t.elementType?l:qe(t.type,l),s.props=u,f=t.pendingProps,p=s.context,a=n.contextType,typeof a=="object"&&a!==null?a=Qe(a):(a=Me(n)?dn:we.current,a=Qn(t,a));var g=n.getDerivedStateFromProps;(c=typeof g=="function"||typeof s.getSnapshotBeforeUpdate=="function")||typeof s.UNSAFE_componentWillReceiveProps!="function"&&typeof s.componentWillReceiveProps!="function"||(l!==f||p!==a)&&Yu(t,s,r,a),Dt=!1,p=t.memoizedState,s.state=p,ro(t,r,s,i);var y=t.memoizedState;l!==f||p!==y||Le.current||Dt?(typeof g=="function"&&(pl(t,n,g,r),y=t.memoizedState),(u=Dt||Qu(t,n,u,r,p,y,a)||!1)?(c||typeof s.UNSAFE_componentWillUpdate!="function"&&typeof s.componentWillUpdate!="function"||(typeof s.componentWillUpdate=="function"&&s.componentWillUpdate(r,y,a),typeof s.UNSAFE_componentWillUpdate=="function"&&s.UNSAFE_componentWillUpdate(r,y,a)),typeof s.componentDidUpdate=="function"&&(t.flags|=4),typeof s.getSnapshotBeforeUpdate=="function"&&(t.flags|=1024)):(typeof s.componentDidUpdate!="function"||l===e.memoizedProps&&p===e.memoizedState||(t.flags|=4),typeof s.getSnapshotBeforeUpdate!="function"||l===e.memoizedProps&&p===e.memoizedState||(t.flags|=1024),t.memoizedProps=r,t.memoizedState=y),s.props=r,s.state=y,s.context=a,r=u):(typeof s.componentDidUpdate!="function"||l===e.memoizedProps&&p===e.memoizedState||(t.flags|=4),typeof s.getSnapshotBeforeUpdate!="function"||l===e.memoizedProps&&p===e.memoizedState||(t.flags|=1024),r=!1)}return yl(e,t,n,r,o,i)}function yl(e,t,n,r,i,o){yp(e,t);var s=(t.flags&128)!==0;if(!r&&!s)return i&&$u(t,n,!1),St(e,t,o);r=t.stateNode,cy.current=t;var l=s&&typeof n.getDerivedStateFromError!="function"?null:r.render();return t.flags|=1,e!==null&&s?(t.child=Xn(t,e.child,null,o),t.child=Xn(t,null,l,o)):Se(e,t,l,o),t.memoizedState=r.state,i&&$u(t,n,!0),t.child}function vp(e){var t=e.stateNode;t.pendingContext?Uu(e,t.pendingContext,t.pendingContext!==t.context):t.context&&Uu(e,t.context,!1),wa(e,t.containerInfo)}function ic(e,t,n,r,i){return Yn(),pa(i),t.flags|=256,Se(e,t,n,r),t.child}var vl={dehydrated:null,treeContext:null,retryLane:0};function wl(e){return{baseLanes:e,cachePool:null,transitions:null}}function wp(e,t,n){var r=t.pendingProps,i=X.current,o=!1,s=(t.flags&128)!==0,l;if((l=s)||(l=e!==null&&e.memoizedState===null?!1:(i&2)!==0),l?(o=!0,t.flags&=-129):(e===null||e.memoizedState!==null)&&(i|=1),H(X,i&1),e===null)return fl(t),e=t.memoizedState,e!==null&&(e=e.dehydrated,e!==null)?(t.mode&1?e.data==="$!"?t.lanes=8:t.lanes=1073741824:t.lanes=1,null):(s=r.children,e=r.fallback,o?(r=t.mode,o=t.child,s={mode:"hidden",children:s},!(r&1)&&o!==null?(o.childLanes=0,o.pendingProps=s):o=_o(s,r,0,null),e=fn(e,r,n,null),o.return=t,e.return=t,o.sibling=e,t.child=o,t.child.memoizedState=wl(n),t.memoizedState=vl,e):Da(t,s));if(i=e.memoizedState,i!==null&&(l=i.dehydrated,l!==null))return fy(e,t,s,r,l,i,n);if(o){o=r.fallback,s=t.mode,i=e.child,l=i.sibling;var a={mode:"hidden",children:r.children};return!(s&1)&&t.child!==i?(r=t.child,r.childLanes=0,r.pendingProps=a,t.deletions=null):(r=Bt(i,a),r.subtreeFlags=i.subtreeFlags&14680064),l!==null?o=Bt(l,o):(o=fn(o,s,n,null),o.flags|=2),o.return=t,r.return=t,r.sibling=o,t.child=r,r=o,o=t.child,s=e.child.memoizedState,s=s===null?wl(n):{baseLanes:s.baseLanes|n,cachePool:null,transitions:s.transitions},o.memoizedState=s,o.childLanes=e.childLanes&~n,t.memoizedState=vl,r}return o=e.child,e=o.sibling,r=Bt(o,{mode:"visible",children:r.children}),!(t.mode&1)&&(r.lanes=n),r.return=t,r.sibling=null,e!==null&&(n=t.deletions,n===null?(t.deletions=[e],t.flags|=16):n.push(e)),t.child=r,t.memoizedState=null,r}function Da(e,t){return t=_o({mode:"visible",children:t},e.mode,0,null),t.return=e,e.child=t}function Si(e,t,n,r){return r!==null&&pa(r),Xn(t,e.child,null,n),e=Da(t,t.pendingProps.children),e.flags|=2,t.memoizedState=null,e}function fy(e,t,n,r,i,o,s){if(n)return t.flags&256?(t.flags&=-257,r=ms(Error(P(422))),Si(e,t,s,r)):t.memoizedState!==null?(t.child=e.child,t.flags|=128,null):(o=r.fallback,i=t.mode,r=_o({mode:"visible",children:r.children},i,0,null),o=fn(o,i,s,null),o.flags|=2,r.return=t,o.return=t,r.sibling=o,t.child=r,t.mode&1&&Xn(t,e.child,null,s),t.child.memoizedState=wl(s),t.memoizedState=vl,o);if(!(t.mode&1))return Si(e,t,s,null);if(i.data==="$!"){if(r=i.nextSibling&&i.nextSibling.dataset,r)var l=r.dgst;return r=l,o=Error(P(419)),r=ms(o,r,void 0),Si(e,t,s,r)}if(l=(s&e.childLanes)!==0,De||l){if(r=ae,r!==null){switch(s&-s){case 4:i=2;break;case 16:i=8;break;case 64:case 128:case 256:case 512:case 1024:case 2048:case 4096:case 8192:case 16384:case 32768:case 65536:case 131072:case 262144:case 524288:case 1048576:case 2097152:case 4194304:case 8388608:case 16777216:case 33554432:case 67108864:i=32;break;case 536870912:i=268435456;break;default:i=0}i=i&(r.suspendedLanes|s)?0:i,i!==0&&i!==o.retryLane&&(o.retryLane=i,xt(e,i),tt(r,e,i,-1))}return _a(),r=ms(Error(P(421))),Si(e,t,s,r)}return i.data==="$?"?(t.flags|=128,t.child=e.child,t=Cy.bind(null,e),i._reactRetry=t,null):(e=o.treeContext,Ne=jt(i.nextSibling),Oe=t,K=!0,be=null,e!==null&&(He[We++]=dt,He[We++]=pt,He[We++]=pn,dt=e.id,pt=e.overflow,pn=t),t=Da(t,r.children),t.flags|=4096,t)}function oc(e,t,n){e.lanes|=t;var r=e.alternate;r!==null&&(r.lanes|=t),dl(e.return,t,n)}function gs(e,t,n,r,i){var o=e.memoizedState;o===null?e.memoizedState={isBackwards:t,rendering:null,renderingStartTime:0,last:r,tail:n,tailMode:i}:(o.isBackwards=t,o.rendering=null,o.renderingStartTime=0,o.last=r,o.tail=n,o.tailMode=i)}function xp(e,t,n){var r=t.pendingProps,i=r.revealOrder,o=r.tail;if(Se(e,t,r.children,n),r=X.current,r&2)r=r&1|2,t.flags|=128;else{if(e!==null&&e.flags&128)e:for(e=t.child;e!==null;){if(e.tag===13)e.memoizedState!==null&&oc(e,n,t);else if(e.tag===19)oc(e,n,t);else if(e.child!==null){e.child.return=e,e=e.child;continue}if(e===t)break e;for(;e.sibling===null;){if(e.return===null||e.return===t)break e;e=e.return}e.sibling.return=e.return,e=e.sibling}r&=1}if(H(X,r),!(t.mode&1))t.memoizedState=null;else switch(i){case"forwards":for(n=t.child,i=null;n!==null;)e=n.alternate,e!==null&&io(e)===null&&(i=n),n=n.sibling;n=i,n===null?(i=t.child,t.child=null):(i=n.sibling,n.sibling=null),gs(t,!1,i,n,o);break;case"backwards":for(n=null,i=t.child,t.child=null;i!==null;){if(e=i.alternate,e!==null&&io(e)===null){t.child=i;break}e=i.sibling,i.sibling=n,n=i,i=e}gs(t,!0,n,null,o);break;case"together":gs(t,!1,null,null,void 0);break;default:t.memoizedState=null}return t.child}function ji(e,t){!(t.mode&1)&&e!==null&&(e.alternate=null,t.alternate=null,t.flags|=2)}function St(e,t,n){if(e!==null&&(t.dependencies=e.dependencies),mn|=t.lanes,!(n&t.childLanes))return null;if(e!==null&&t.child!==e.child)throw Error(P(153));if(t.child!==null){for(e=t.child,n=Bt(e,e.pendingProps),t.child=n,n.return=t;e.sibling!==null;)e=e.sibling,n=n.sibling=Bt(e,e.pendingProps),n.return=t;n.sibling=null}return t.child}function dy(e,t,n){switch(t.tag){case 3:vp(t),Yn();break;case 5:Qd(t);break;case 1:Me(t.type)&&Ji(t);break;case 4:wa(t,t.stateNode.containerInfo);break;case 10:var r=t.type._context,i=t.memoizedProps.value;H(to,r._currentValue),r._currentValue=i;break;case 13:if(r=t.memoizedState,r!==null)return r.dehydrated!==null?(H(X,X.current&1),t.flags|=128,null):n&t.child.childLanes?wp(e,t,n):(H(X,X.current&1),e=St(e,t,n),e!==null?e.sibling:null);H(X,X.current&1);break;case 19:if(r=(n&t.childLanes)!==0,e.flags&128){if(r)return xp(e,t,n);t.flags|=128}if(i=t.memoizedState,i!==null&&(i.rendering=null,i.tail=null,i.lastEffect=null),H(X,X.current),r)break;return null;case 22:case 23:return t.lanes=0,gp(e,t,n)}return St(e,t,n)}var Sp,xl,kp,Pp;Sp=function(e,t){for(var n=t.child;n!==null;){if(n.tag===5||n.tag===6)e.appendChild(n.stateNode);else if(n.tag!==4&&n.child!==null){n.child.return=n,n=n.child;continue}if(n===t)break;for(;n.sibling===null;){if(n.return===null||n.return===t)return;n=n.return}n.sibling.return=n.return,n=n.sibling}};xl=function(){};kp=function(e,t,n,r){var i=e.memoizedProps;if(i!==r){e=t.stateNode,an(at.current);var o=null;switch(n){case"input":i=$s(e,i),r=$s(e,r),o=[];break;case"select":i=J({},i,{value:void 0}),r=J({},r,{value:void 0}),o=[];break;case"textarea":i=Gs(e,i),r=Gs(e,r),o=[];break;default:typeof i.onClick!="function"&&typeof r.onClick=="function"&&(e.onclick=Zi)}Qs(n,r);var s;n=null;for(u in i)if(!r.hasOwnProperty(u)&&i.hasOwnProperty(u)&&i[u]!=null)if(u==="style"){var l=i[u];for(s in l)l.hasOwnProperty(s)&&(n||(n={}),n[s]="")}else u!=="dangerouslySetInnerHTML"&&u!=="children"&&u!=="suppressContentEditableWarning"&&u!=="suppressHydrationWarning"&&u!=="autoFocus"&&(Vr.hasOwnProperty(u)?o||(o=[]):(o=o||[]).push(u,null));for(u in r){var a=r[u];if(l=i!=null?i[u]:void 0,r.hasOwnProperty(u)&&a!==l&&(a!=null||l!=null))if(u==="style")if(l){for(s in l)!l.hasOwnProperty(s)||a&&a.hasOwnProperty(s)||(n||(n={}),n[s]="");for(s in a)a.hasOwnProperty(s)&&l[s]!==a[s]&&(n||(n={}),n[s]=a[s])}else n||(o||(o=[]),o.push(u,n)),n=a;else u==="dangerouslySetInnerHTML"?(a=a?a.__html:void 0,l=l?l.__html:void 0,a!=null&&l!==a&&(o=o||[]).push(u,a)):u==="children"?typeof a!="string"&&typeof a!="number"||(o=o||[]).push(u,""+a):u!=="suppressContentEditableWarning"&&u!=="suppressHydrationWarning"&&(Vr.hasOwnProperty(u)?(a!=null&&u==="onScroll"&&W("scroll",e),o||l===a||(o=[])):(o=o||[]).push(u,a))}n&&(o=o||[]).push("style",n);var u=o;(t.updateQueue=u)&&(t.flags|=4)}};Pp=function(e,t,n,r){n!==r&&(t.flags|=4)};function ur(e,t){if(!K)switch(e.tailMode){case"hidden":t=e.tail;for(var n=null;t!==null;)t.alternate!==null&&(n=t),t=t.sibling;n===null?e.tail=null:n.sibling=null;break;case"collapsed":n=e.tail;for(var r=null;n!==null;)n.alternate!==null&&(r=n),n=n.sibling;r===null?t||e.tail===null?e.tail=null:e.tail.sibling=null:r.sibling=null}}function ye(e){var t=e.alternate!==null&&e.alternate.child===e.child,n=0,r=0;if(t)for(var i=e.child;i!==null;)n|=i.lanes|i.childLanes,r|=i.subtreeFlags&14680064,r|=i.flags&14680064,i.return=e,i=i.sibling;else for(i=e.child;i!==null;)n|=i.lanes|i.childLanes,r|=i.subtreeFlags,r|=i.flags,i.return=e,i=i.sibling;return e.subtreeFlags|=r,e.childLanes=n,t}function py(e,t,n){var r=t.pendingProps;switch(da(t),t.tag){case 2:case 16:case 15:case 0:case 11:case 7:case 8:case 12:case 9:case 14:return ye(t),null;case 1:return Me(t.type)&&qi(),ye(t),null;case 3:return r=t.stateNode,Zn(),G(Le),G(we),Sa(),r.pendingContext&&(r.context=r.pendingContext,r.pendingContext=null),(e===null||e.child===null)&&(wi(t)?t.flags|=4:e===null||e.memoizedState.isDehydrated&&!(t.flags&256)||(t.flags|=1024,be!==null&&(Ll(be),be=null))),xl(e,t),ye(t),null;case 5:xa(t);var i=an(Hr.current);if(n=t.type,e!==null&&t.stateNode!=null)kp(e,t,n,r,i),e.ref!==t.ref&&(t.flags|=512,t.flags|=2097152);else{if(!r){if(t.stateNode===null)throw Error(P(166));return ye(t),null}if(e=an(at.current),wi(t)){r=t.stateNode,n=t.type;var o=t.memoizedProps;switch(r[st]=t,r[Ur]=o,e=(t.mode&1)!==0,n){case"dialog":W("cancel",r),W("close",r);break;case"iframe":case"object":case"embed":W("load",r);break;case"video":case"audio":for(i=0;i<gr.length;i++)W(gr[i],r);break;case"source":W("error",r);break;case"img":case"image":case"link":W("error",r),W("load",r);break;case"details":W("toggle",r);break;case"input":hu(r,o),W("invalid",r);break;case"select":r._wrapperState={wasMultiple:!!o.multiple},W("invalid",r);break;case"textarea":gu(r,o),W("invalid",r)}Qs(n,o),i=null;for(var s in o)if(o.hasOwnProperty(s)){var l=o[s];s==="children"?typeof l=="string"?r.textContent!==l&&(o.suppressHydrationWarning!==!0&&vi(r.textContent,l,e),i=["children",l]):typeof l=="number"&&r.textContent!==""+l&&(o.suppressHydrationWarning!==!0&&vi(r.textContent,l,e),i=["children",""+l]):Vr.hasOwnProperty(s)&&l!=null&&s==="onScroll"&&W("scroll",r)}switch(n){case"input":ci(r),mu(r,o,!0);break;case"textarea":ci(r),yu(r);break;case"select":case"option":break;default:typeof o.onClick=="function"&&(r.onclick=Zi)}r=i,t.updateQueue=r,r!==null&&(t.flags|=4)}else{s=i.nodeType===9?i:i.ownerDocument,e==="http://www.w3.org/1999/xhtml"&&(e=Zf(n)),e==="http://www.w3.org/1999/xhtml"?n==="script"?(e=s.createElement("div"),e.innerHTML="<script><\/script>",e=e.removeChild(e.firstChild)):typeof r.is=="string"?e=s.createElement(n,{is:r.is}):(e=s.createElement(n),n==="select"&&(s=e,r.multiple?s.multiple=!0:r.size&&(s.size=r.size))):e=s.createElementNS(e,n),e[st]=t,e[Ur]=r,Sp(e,t,!1,!1),t.stateNode=e;e:{switch(s=Ys(n,r),n){case"dialog":W("cancel",e),W("close",e),i=r;break;case"iframe":case"object":case"embed":W("load",e),i=r;break;case"video":case"audio":for(i=0;i<gr.length;i++)W(gr[i],e);i=r;break;case"source":W("error",e),i=r;break;case"img":case"image":case"link":W("error",e),W("load",e),i=r;break;case"details":W("toggle",e),i=r;break;case"input":hu(e,r),i=$s(e,r),W("invalid",e);break;case"option":i=r;break;case"select":e._wrapperState={wasMultiple:!!r.multiple},i=J({},r,{value:void 0}),W("invalid",e);break;case"textarea":gu(e,r),i=Gs(e,r),W("invalid",e);break;default:i=r}Qs(n,i),l=i;for(o in l)if(l.hasOwnProperty(o)){var a=l[o];o==="style"?bf(e,a):o==="dangerouslySetInnerHTML"?(a=a?a.__html:void 0,a!=null&&qf(e,a)):o==="children"?typeof a=="string"?(n!=="textarea"||a!=="")&&Ar(e,a):typeof a=="number"&&Ar(e,""+a):o!=="suppressContentEditableWarning"&&o!=="suppressHydrationWarning"&&o!=="autoFocus"&&(Vr.hasOwnProperty(o)?a!=null&&o==="onScroll"&&W("scroll",e):a!=null&&ql(e,o,a,s))}switch(n){case"input":ci(e),mu(e,r,!1);break;case"textarea":ci(e),yu(e);break;case"option":r.value!=null&&e.setAttribute("value",""+Ht(r.value));break;case"select":e.multiple=!!r.multiple,o=r.value,o!=null?zn(e,!!r.multiple,o,!1):r.defaultValue!=null&&zn(e,!!r.multiple,r.defaultValue,!0);break;default:typeof i.onClick=="function"&&(e.onclick=Zi)}switch(n){case"button":case"input":case"select":case"textarea":r=!!r.autoFocus;break e;case"img":r=!0;break e;default:r=!1}}r&&(t.flags|=4)}t.ref!==null&&(t.flags|=512,t.flags|=2097152)}return ye(t),null;case 6:if(e&&t.stateNode!=null)Pp(e,t,e.memoizedProps,r);else{if(typeof r!="string"&&t.stateNode===null)throw Error(P(166));if(n=an(Hr.current),an(at.current),wi(t)){if(r=t.stateNode,n=t.memoizedProps,r[st]=t,(o=r.nodeValue!==n)&&(e=Oe,e!==null))switch(e.tag){case 3:vi(r.nodeValue,n,(e.mode&1)!==0);break;case 5:e.memoizedProps.suppressHydrationWarning!==!0&&vi(r.nodeValue,n,(e.mode&1)!==0)}o&&(t.flags|=4)}else r=(n.nodeType===9?n:n.ownerDocument).createTextNode(r),r[st]=t,t.stateNode=r}return ye(t),null;case 13:if(G(X),r=t.memoizedState,e===null||e.memoizedState!==null&&e.memoizedState.dehydrated!==null){if(K&&Ne!==null&&t.mode&1&&!(t.flags&128))Bd(),Yn(),t.flags|=98560,o=!1;else if(o=wi(t),r!==null&&r.dehydrated!==null){if(e===null){if(!o)throw Error(P(318));if(o=t.memoizedState,o=o!==null?o.dehydrated:null,!o)throw Error(P(317));o[st]=t}else Yn(),!(t.flags&128)&&(t.memoizedState=null),t.flags|=4;ye(t),o=!1}else be!==null&&(Ll(be),be=null),o=!0;if(!o)return t.flags&65536?t:null}return t.flags&128?(t.lanes=n,t):(r=r!==null,r!==(e!==null&&e.memoizedState!==null)&&r&&(t.child.flags|=8192,t.mode&1&&(e===null||X.current&1?se===0&&(se=3):_a())),t.updateQueue!==null&&(t.flags|=4),ye(t),null);case 4:return Zn(),xl(e,t),e===null&&zr(t.stateNode.containerInfo),ye(t),null;case 10:return ga(t.type._context),ye(t),null;case 17:return Me(t.type)&&qi(),ye(t),null;case 19:if(G(X),o=t.memoizedState,o===null)return ye(t),null;if(r=(t.flags&128)!==0,s=o.rendering,s===null)if(r)ur(o,!1);else{if(se!==0||e!==null&&e.flags&128)for(e=t.child;e!==null;){if(s=io(e),s!==null){for(t.flags|=128,ur(o,!1),r=s.updateQueue,r!==null&&(t.updateQueue=r,t.flags|=4),t.subtreeFlags=0,r=n,n=t.child;n!==null;)o=n,e=r,o.flags&=14680066,s=o.alternate,s===null?(o.childLanes=0,o.lanes=e,o.child=null,o.subtreeFlags=0,o.memoizedProps=null,o.memoizedState=null,o.updateQueue=null,o.dependencies=null,o.stateNode=null):(o.childLanes=s.childLanes,o.lanes=s.lanes,o.child=s.child,o.subtreeFlags=0,o.deletions=null,o.memoizedProps=s.memoizedProps,o.memoizedState=s.memoizedState,o.updateQueue=s.updateQueue,o.type=s.type,e=s.dependencies,o.dependencies=e===null?null:{lanes:e.lanes,firstContext:e.firstContext}),n=n.sibling;return H(X,X.current&1|2),t.child}e=e.sibling}o.tail!==null&&te()>Jn&&(t.flags|=128,r=!0,ur(o,!1),t.lanes=4194304)}else{if(!r)if(e=io(s),e!==null){if(t.flags|=128,r=!0,n=e.updateQueue,n!==null&&(t.updateQueue=n,t.flags|=4),ur(o,!0),o.tail===null&&o.tailMode==="hidden"&&!s.alternate&&!K)return ye(t),null}else 2*te()-o.renderingStartTime>Jn&&n!==1073741824&&(t.flags|=128,r=!0,ur(o,!1),t.lanes=4194304);o.isBackwards?(s.sibling=t.child,t.child=s):(n=o.last,n!==null?n.sibling=s:t.child=s,o.last=s)}return o.tail!==null?(t=o.tail,o.rendering=t,o.tail=t.sibling,o.renderingStartTime=te(),t.sibling=null,n=X.current,H(X,r?n&1|2:n&1),t):(ye(t),null);case 22:case 23:return Aa(),r=t.memoizedState!==null,e!==null&&e.memoizedState!==null!==r&&(t.flags|=8192),r&&t.mode&1?_e&1073741824&&(ye(t),t.subtreeFlags&6&&(t.flags|=8192)):ye(t),null;case 24:return null;case 25:return null}throw Error(P(156,t.tag))}function hy(e,t){switch(da(t),t.tag){case 1:return Me(t.type)&&qi(),e=t.flags,e&65536?(t.flags=e&-65537|128,t):null;case 3:return Zn(),G(Le),G(we),Sa(),e=t.flags,e&65536&&!(e&128)?(t.flags=e&-65537|128,t):null;case 5:return xa(t),null;case 13:if(G(X),e=t.memoizedState,e!==null&&e.dehydrated!==null){if(t.alternate===null)throw Error(P(340));Yn()}return e=t.flags,e&65536?(t.flags=e&-65537|128,t):null;case 19:return G(X),null;case 4:return Zn(),null;case 10:return ga(t.type._context),null;case 22:case 23:return Aa(),null;case 24:return null;default:return null}}var ki=!1,ve=!1,my=typeof WeakSet=="function"?WeakSet:Set,M=null;function _n(e,t){var n=e.ref;if(n!==null)if(typeof n=="function")try{n(null)}catch(r){b(e,t,r)}else n.current=null}function Sl(e,t,n){try{n()}catch(r){b(e,t,r)}}var sc=!1;function gy(e,t){if(il=Qi,e=Dd(),ca(e)){if("selectionStart"in e)var n={start:e.selectionStart,end:e.selectionEnd};else e:{n=(n=e.ownerDocument)&&n.defaultView||window;var r=n.getSelection&&n.getSelection();if(r&&r.rangeCount!==0){n=r.anchorNode;var i=r.anchorOffset,o=r.focusNode;r=r.focusOffset;try{n.nodeType,o.nodeType}catch{n=null;break e}var s=0,l=-1,a=-1,u=0,c=0,f=e,p=null;t:for(;;){for(var g;f!==n||i!==0&&f.nodeType!==3||(l=s+i),f!==o||r!==0&&f.nodeType!==3||(a=s+r),f.nodeType===3&&(s+=f.nodeValue.length),(g=f.firstChild)!==null;)p=f,f=g;for(;;){if(f===e)break t;if(p===n&&++u===i&&(l=s),p===o&&++c===r&&(a=s),(g=f.nextSibling)!==null)break;f=p,p=f.parentNode}f=g}n=l===-1||a===-1?null:{start:l,end:a}}else n=null}n=n||{start:0,end:0}}else n=null;for(ol={focusedElem:e,selectionRange:n},Qi=!1,M=t;M!==null;)if(t=M,e=t.child,(t.subtreeFlags&1028)!==0&&e!==null)e.return=t,M=e;else for(;M!==null;){t=M;try{var y=t.alternate;if(t.flags&1024)switch(t.tag){case 0:case 11:case 15:break;case 1:if(y!==null){var v=y.memoizedProps,T=y.memoizedState,m=t.stateNode,d=m.getSnapshotBeforeUpdate(t.elementType===t.type?v:qe(t.type,v),T);m.__reactInternalSnapshotBeforeUpdate=d}break;case 3:var h=t.stateNode.containerInfo;h.nodeType===1?h.textContent="":h.nodeType===9&&h.documentElement&&h.removeChild(h.documentElement);break;case 5:case 6:case 4:case 17:break;default:throw Error(P(163))}}catch(w){b(t,t.return,w)}if(e=t.sibling,e!==null){e.return=t.return,M=e;break}M=t.return}return y=sc,sc=!1,y}function Cr(e,t,n){var r=t.updateQueue;if(r=r!==null?r.lastEffect:null,r!==null){var i=r=r.next;do{if((i.tag&e)===e){var o=i.destroy;i.destroy=void 0,o!==void 0&&Sl(t,n,o)}i=i.next}while(i!==r)}}function Vo(e,t){if(t=t.updateQueue,t=t!==null?t.lastEffect:null,t!==null){var n=t=t.next;do{if((n.tag&e)===e){var r=n.create;n.destroy=r()}n=n.next}while(n!==t)}}function kl(e){var t=e.ref;if(t!==null){var n=e.stateNode;switch(e.tag){case 5:e=n;break;default:e=n}typeof t=="function"?t(e):t.current=e}}function Cp(e){var t=e.alternate;t!==null&&(e.alternate=null,Cp(t)),e.child=null,e.deletions=null,e.sibling=null,e.tag===5&&(t=e.stateNode,t!==null&&(delete t[st],delete t[Ur],delete t[al],delete t[Jg],delete t[bg])),e.stateNode=null,e.return=null,e.dependencies=null,e.memoizedProps=null,e.memoizedState=null,e.pendingProps=null,e.stateNode=null,e.updateQueue=null}function Tp(e){return e.tag===5||e.tag===3||e.tag===4}function lc(e){e:for(;;){for(;e.sibling===null;){if(e.return===null||Tp(e.return))return null;e=e.return}for(e.sibling.return=e.return,e=e.sibling;e.tag!==5&&e.tag!==6&&e.tag!==18;){if(e.flags&2||e.child===null||e.tag===4)continue e;e.child.return=e,e=e.child}if(!(e.flags&2))return e.stateNode}}function Pl(e,t,n){var r=e.tag;if(r===5||r===6)e=e.stateNode,t?n.nodeType===8?n.parentNode.insertBefore(e,t):n.insertBefore(e,t):(n.nodeType===8?(t=n.parentNode,t.insertBefore(e,n)):(t=n,t.appendChild(e)),n=n._reactRootContainer,n!=null||t.onclick!==null||(t.onclick=Zi));else if(r!==4&&(e=e.child,e!==null))for(Pl(e,t,n),e=e.sibling;e!==null;)Pl(e,t,n),e=e.sibling}function Cl(e,t,n){var r=e.tag;if(r===5||r===6)e=e.stateNode,t?n.insertBefore(e,t):n.appendChild(e);else if(r!==4&&(e=e.child,e!==null))for(Cl(e,t,n),e=e.sibling;e!==null;)Cl(e,t,n),e=e.sibling}var ue=null,Je=!1;function Ct(e,t,n){for(n=n.child;n!==null;)Ep(e,t,n),n=n.sibling}function Ep(e,t,n){if(lt&&typeof lt.onCommitFiberUnmount=="function")try{lt.onCommitFiberUnmount(Po,n)}catch{}switch(n.tag){case 5:ve||_n(n,t);case 6:var r=ue,i=Je;ue=null,Ct(e,t,n),ue=r,Je=i,ue!==null&&(Je?(e=ue,n=n.stateNode,e.nodeType===8?e.parentNode.removeChild(n):e.removeChild(n)):ue.removeChild(n.stateNode));break;case 18:ue!==null&&(Je?(e=ue,n=n.stateNode,e.nodeType===8?us(e.parentNode,n):e.nodeType===1&&us(e,n),jr(e)):us(ue,n.stateNode));break;case 4:r=ue,i=Je,ue=n.stateNode.containerInfo,Je=!0,Ct(e,t,n),ue=r,Je=i;break;case 0:case 11:case 14:case 15:if(!ve&&(r=n.updateQueue,r!==null&&(r=r.lastEffect,r!==null))){i=r=r.next;do{var o=i,s=o.destroy;o=o.tag,s!==void 0&&(o&2||o&4)&&Sl(n,t,s),i=i.next}while(i!==r)}Ct(e,t,n);break;case 1:if(!ve&&(_n(n,t),r=n.stateNode,typeof r.componentWillUnmount=="function"))try{r.props=n.memoizedProps,r.state=n.memoizedState,r.componentWillUnmount()}catch(l){b(n,t,l)}Ct(e,t,n);break;case 21:Ct(e,t,n);break;case 22:n.mode&1?(ve=(r=ve)||n.memoizedState!==null,Ct(e,t,n),ve=r):Ct(e,t,n);break;default:Ct(e,t,n)}}function ac(e){var t=e.updateQueue;if(t!==null){e.updateQueue=null;var n=e.stateNode;n===null&&(n=e.stateNode=new my),t.forEach(function(r){var i=Ty.bind(null,e,r);n.has(r)||(n.add(r),r.then(i,i))})}}function Ze(e,t){var n=t.deletions;if(n!==null)for(var r=0;r<n.length;r++){var i=n[r];try{var o=e,s=t,l=s;e:for(;l!==null;){switch(l.tag){case 5:ue=l.stateNode,Je=!1;break e;case 3:ue=l.stateNode.containerInfo,Je=!0;break e;case 4:ue=l.stateNode.containerInfo,Je=!0;break e}l=l.return}if(ue===null)throw Error(P(160));Ep(o,s,i),ue=null,Je=!1;var a=i.alternate;a!==null&&(a.return=null),i.return=null}catch(u){b(i,t,u)}}if(t.subtreeFlags&12854)for(t=t.child;t!==null;)Dp(t,e),t=t.sibling}function Dp(e,t){var n=e.alternate,r=e.flags;switch(e.tag){case 0:case 11:case 14:case 15:if(Ze(t,e),rt(e),r&4){try{Cr(3,e,e.return),Vo(3,e)}catch(v){b(e,e.return,v)}try{Cr(5,e,e.return)}catch(v){b(e,e.return,v)}}break;case 1:Ze(t,e),rt(e),r&512&&n!==null&&_n(n,n.return);break;case 5:if(Ze(t,e),rt(e),r&512&&n!==null&&_n(n,n.return),e.flags&32){var i=e.stateNode;try{Ar(i,"")}catch(v){b(e,e.return,v)}}if(r&4&&(i=e.stateNode,i!=null)){var o=e.memoizedProps,s=n!==null?n.memoizedProps:o,l=e.type,a=e.updateQueue;if(e.updateQueue=null,a!==null)try{l==="input"&&o.type==="radio"&&o.name!=null&&Yf(i,o),Ys(l,s);var u=Ys(l,o);for(s=0;s<a.length;s+=2){var c=a[s],f=a[s+1];c==="style"?bf(i,f):c==="dangerouslySetInnerHTML"?qf(i,f):c==="children"?Ar(i,f):ql(i,c,f,u)}switch(l){case"input":Hs(i,o);break;case"textarea":Xf(i,o);break;case"select":var p=i._wrapperState.wasMultiple;i._wrapperState.wasMultiple=!!o.multiple;var g=o.value;g!=null?zn(i,!!o.multiple,g,!1):p!==!!o.multiple&&(o.defaultValue!=null?zn(i,!!o.multiple,o.defaultValue,!0):zn(i,!!o.multiple,o.multiple?[]:"",!1))}i[Ur]=o}catch(v){b(e,e.return,v)}}break;case 6:if(Ze(t,e),rt(e),r&4){if(e.stateNode===null)throw Error(P(162));i=e.stateNode,o=e.memoizedProps;try{i.nodeValue=o}catch(v){b(e,e.return,v)}}break;case 3:if(Ze(t,e),rt(e),r&4&&n!==null&&n.memoizedState.isDehydrated)try{jr(t.containerInfo)}catch(v){b(e,e.return,v)}break;case 4:Ze(t,e),rt(e);break;case 13:Ze(t,e),rt(e),i=e.child,i.flags&8192&&(o=i.memoizedState!==null,i.stateNode.isHidden=o,!o||i.alternate!==null&&i.alternate.memoizedState!==null||(Ra=te())),r&4&&ac(e);break;case 22:if(c=n!==null&&n.memoizedState!==null,e.mode&1?(ve=(u=ve)||c,Ze(t,e),ve=u):Ze(t,e),rt(e),r&8192){if(u=e.memoizedState!==null,(e.stateNode.isHidden=u)&&!c&&e.mode&1)for(M=e,c=e.child;c!==null;){for(f=M=c;M!==null;){switch(p=M,g=p.child,p.tag){case 0:case 11:case 14:case 15:Cr(4,p,p.return);break;case 1:_n(p,p.return);var y=p.stateNode;if(typeof y.componentWillUnmount=="function"){r=p,n=p.return;try{t=r,y.props=t.memoizedProps,y.state=t.memoizedState,y.componentWillUnmount()}catch(v){b(r,n,v)}}break;case 5:_n(p,p.return);break;case 22:if(p.memoizedState!==null){cc(f);continue}}g!==null?(g.return=p,M=g):cc(f)}c=c.sibling}e:for(c=null,f=e;;){if(f.tag===5){if(c===null){c=f;try{i=f.stateNode,u?(o=i.style,typeof o.setProperty=="function"?o.setProperty("display","none","important"):o.display="none"):(l=f.stateNode,a=f.memoizedProps.style,s=a!=null&&a.hasOwnProperty("display")?a.display:null,l.style.display=Jf("display",s))}catch(v){b(e,e.return,v)}}}else if(f.tag===6){if(c===null)try{f.stateNode.nodeValue=u?"":f.memoizedProps}catch(v){b(e,e.return,v)}}else if((f.tag!==22&&f.tag!==23||f.memoizedState===null||f===e)&&f.child!==null){f.child.return=f,f=f.child;continue}if(f===e)break e;for(;f.sibling===null;){if(f.return===null||f.return===e)break e;c===f&&(c=null),f=f.return}c===f&&(c=null),f.sibling.return=f.return,f=f.sibling}}break;case 19:Ze(t,e),rt(e),r&4&&ac(e);break;case 21:break;default:Ze(t,e),rt(e)}}function rt(e){var t=e.flags;if(t&2){try{e:{for(var n=e.return;n!==null;){if(Tp(n)){var r=n;break e}n=n.return}throw Error(P(160))}switch(r.tag){case 5:var i=r.stateNode;r.flags&32&&(Ar(i,""),r.flags&=-33);var o=lc(e);Cl(e,o,i);break;case 3:case 4:var s=r.stateNode.containerInfo,l=lc(e);Pl(e,l,s);break;default:throw Error(P(161))}}catch(a){b(e,e.return,a)}e.flags&=-3}t&4096&&(e.flags&=-4097)}function yy(e,t,n){M=e,Lp(e)}function Lp(e,t,n){for(var r=(e.mode&1)!==0;M!==null;){var i=M,o=i.child;if(i.tag===22&&r){var s=i.memoizedState!==null||ki;if(!s){var l=i.alternate,a=l!==null&&l.memoizedState!==null||ve;l=ki;var u=ve;if(ki=s,(ve=a)&&!u)for(M=i;M!==null;)s=M,a=s.child,s.tag===22&&s.memoizedState!==null?fc(i):a!==null?(a.return=s,M=a):fc(i);for(;o!==null;)M=o,Lp(o),o=o.sibling;M=i,ki=l,ve=u}uc(e)}else i.subtreeFlags&8772&&o!==null?(o.return=i,M=o):uc(e)}}function uc(e){for(;M!==null;){var t=M;if(t.flags&8772){var n=t.alternate;try{if(t.flags&8772)switch(t.tag){case 0:case 11:case 15:ve||Vo(5,t);break;case 1:var r=t.stateNode;if(t.flags&4&&!ve)if(n===null)r.componentDidMount();else{var i=t.elementType===t.type?n.memoizedProps:qe(t.type,n.memoizedProps);r.componentDidUpdate(i,n.memoizedState,r.__reactInternalSnapshotBeforeUpdate)}var o=t.updateQueue;o!==null&&Ku(t,o,r);break;case 3:var s=t.updateQueue;if(s!==null){if(n=null,t.child!==null)switch(t.child.tag){case 5:n=t.child.stateNode;break;case 1:n=t.child.stateNode}Ku(t,s,n)}break;case 5:var l=t.stateNode;if(n===null&&t.flags&4){n=l;var a=t.memoizedProps;switch(t.type){case"button":case"input":case"select":case"textarea":a.autoFocus&&n.focus();break;case"img":a.src&&(n.src=a.src)}}break;case 6:break;case 4:break;case 12:break;case 13:if(t.memoizedState===null){var u=t.alternate;if(u!==null){var c=u.memoizedState;if(c!==null){var f=c.dehydrated;f!==null&&jr(f)}}}break;case 19:case 17:case 21:case 22:case 23:case 25:break;default:throw Error(P(163))}ve||t.flags&512&&kl(t)}catch(p){b(t,t.return,p)}}if(t===e){M=null;break}if(n=t.sibling,n!==null){n.return=t.return,M=n;break}M=t.return}}function cc(e){for(;M!==null;){var t=M;if(t===e){M=null;break}var n=t.sibling;if(n!==null){n.return=t.return,M=n;break}M=t.return}}function fc(e){for(;M!==null;){var t=M;try{switch(t.tag){case 0:case 11:case 15:var n=t.return;try{Vo(4,t)}catch(a){b(t,n,a)}break;case 1:var r=t.stateNode;if(typeof r.componentDidMount=="function"){var i=t.return;try{r.componentDidMount()}catch(a){b(t,i,a)}}var o=t.return;try{kl(t)}catch(a){b(t,o,a)}break;case 5:var s=t.return;try{kl(t)}catch(a){b(t,s,a)}}}catch(a){b(t,t.return,a)}if(t===e){M=null;break}var l=t.sibling;if(l!==null){l.return=t.return,M=l;break}M=t.return}}var vy=Math.ceil,lo=Pt.ReactCurrentDispatcher,La=Pt.ReactCurrentOwner,Ke=Pt.ReactCurrentBatchConfig,z=0,ae=null,re=null,ce=0,_e=0,Nn=Yt(0),se=0,Qr=null,mn=0,Ao=0,Ma=0,Tr=null,Ee=null,Ra=0,Jn=1/0,ct=null,ao=!1,Tl=null,It=null,Pi=!1,At=null,uo=0,Er=0,El=null,Fi=-1,Ii=0;function ke(){return z&6?te():Fi!==-1?Fi:Fi=te()}function zt(e){return e.mode&1?z&2&&ce!==0?ce&-ce:ty.transition!==null?(Ii===0&&(Ii=fd()),Ii):(e=B,e!==0||(e=window.event,e=e===void 0?16:vd(e.type)),e):1}function tt(e,t,n,r){if(50<Er)throw Er=0,El=null,Error(P(185));br(e,n,r),(!(z&2)||e!==ae)&&(e===ae&&(!(z&2)&&(Ao|=n),se===4&&Rt(e,ce)),Re(e,r),n===1&&z===0&&!(t.mode&1)&&(Jn=te()+500,Lo&&Xt()))}function Re(e,t){var n=e.callbackNode;tg(e,t);var r=Ki(e,e===ae?ce:0);if(r===0)n!==null&&xu(n),e.callbackNode=null,e.callbackPriority=0;else if(t=r&-r,e.callbackPriority!==t){if(n!=null&&xu(n),t===1)e.tag===0?ey(dc.bind(null,e)):Fd(dc.bind(null,e)),Zg(function(){!(z&6)&&Xt()}),n=null;else{switch(dd(r)){case 1:n=na;break;case 4:n=ud;break;case 16:n=Gi;break;case 536870912:n=cd;break;default:n=Gi}n=jp(n,Mp.bind(null,e))}e.callbackPriority=t,e.callbackNode=n}}function Mp(e,t){if(Fi=-1,Ii=0,z&6)throw Error(P(327));var n=e.callbackNode;if(Wn()&&e.callbackNode!==n)return null;var r=Ki(e,e===ae?ce:0);if(r===0)return null;if(r&30||r&e.expiredLanes||t)t=co(e,r);else{t=r;var i=z;z|=2;var o=Vp();(ae!==e||ce!==t)&&(ct=null,Jn=te()+500,cn(e,t));do try{Sy();break}catch(l){Rp(e,l)}while(1);ma(),lo.current=o,z=i,re!==null?t=0:(ae=null,ce=0,t=se)}if(t!==0){if(t===2&&(i=bs(e),i!==0&&(r=i,t=Dl(e,i))),t===1)throw n=Qr,cn(e,0),Rt(e,r),Re(e,te()),n;if(t===6)Rt(e,r);else{if(i=e.current.alternate,!(r&30)&&!wy(i)&&(t=co(e,r),t===2&&(o=bs(e),o!==0&&(r=o,t=Dl(e,o))),t===1))throw n=Qr,cn(e,0),Rt(e,r),Re(e,te()),n;switch(e.finishedWork=i,e.finishedLanes=r,t){case 0:case 1:throw Error(P(345));case 2:nn(e,Ee,ct);break;case 3:if(Rt(e,r),(r&130023424)===r&&(t=Ra+500-te(),10<t)){if(Ki(e,0)!==0)break;if(i=e.suspendedLanes,(i&r)!==r){ke(),e.pingedLanes|=e.suspendedLanes&i;break}e.timeoutHandle=ll(nn.bind(null,e,Ee,ct),t);break}nn(e,Ee,ct);break;case 4:if(Rt(e,r),(r&4194240)===r)break;for(t=e.eventTimes,i=-1;0<r;){var s=31-et(r);o=1<<s,s=t[s],s>i&&(i=s),r&=~o}if(r=i,r=te()-r,r=(120>r?120:480>r?480:1080>r?1080:1920>r?1920:3e3>r?3e3:4320>r?4320:1960*vy(r/1960))-r,10<r){e.timeoutHandle=ll(nn.bind(null,e,Ee,ct),r);break}nn(e,Ee,ct);break;case 5:nn(e,Ee,ct);break;default:throw Error(P(329))}}}return Re(e,te()),e.callbackNode===n?Mp.bind(null,e):null}function Dl(e,t){var n=Tr;return e.current.memoizedState.isDehydrated&&(cn(e,t).flags|=256),e=co(e,t),e!==2&&(t=Ee,Ee=n,t!==null&&Ll(t)),e}function Ll(e){Ee===null?Ee=e:Ee.push.apply(Ee,e)}function wy(e){for(var t=e;;){if(t.flags&16384){var n=t.updateQueue;if(n!==null&&(n=n.stores,n!==null))for(var r=0;r<n.length;r++){var i=n[r],o=i.getSnapshot;i=i.value;try{if(!nt(o(),i))return!1}catch{return!1}}}if(n=t.child,t.subtreeFlags&16384&&n!==null)n.return=t,t=n;else{if(t===e)break;for(;t.sibling===null;){if(t.return===null||t.return===e)return!0;t=t.return}t.sibling.return=t.return,t=t.sibling}}return!0}function Rt(e,t){for(t&=~Ma,t&=~Ao,e.suspendedLanes|=t,e.pingedLanes&=~t,e=e.expirationTimes;0<t;){var n=31-et(t),r=1<<n;e[n]=-1,t&=~r}}function dc(e){if(z&6)throw Error(P(327));Wn();var t=Ki(e,0);if(!(t&1))return Re(e,te()),null;var n=co(e,t);if(e.tag!==0&&n===2){var r=bs(e);r!==0&&(t=r,n=Dl(e,r))}if(n===1)throw n=Qr,cn(e,0),Rt(e,t),Re(e,te()),n;if(n===6)throw Error(P(345));return e.finishedWork=e.current.alternate,e.finishedLanes=t,nn(e,Ee,ct),Re(e,te()),null}function Va(e,t){var n=z;z|=1;try{return e(t)}finally{z=n,z===0&&(Jn=te()+500,Lo&&Xt())}}function gn(e){At!==null&&At.tag===0&&!(z&6)&&Wn();var t=z;z|=1;var n=Ke.transition,r=B;try{if(Ke.transition=null,B=1,e)return e()}finally{B=r,Ke.transition=n,z=t,!(z&6)&&Xt()}}function Aa(){_e=Nn.current,G(Nn)}function cn(e,t){e.finishedWork=null,e.finishedLanes=0;var n=e.timeoutHandle;if(n!==-1&&(e.timeoutHandle=-1,Xg(n)),re!==null)for(n=re.return;n!==null;){var r=n;switch(da(r),r.tag){case 1:r=r.type.childContextTypes,r!=null&&qi();break;case 3:Zn(),G(Le),G(we),Sa();break;case 5:xa(r);break;case 4:Zn();break;case 13:G(X);break;case 19:G(X);break;case 10:ga(r.type._context);break;case 22:case 23:Aa()}n=n.return}if(ae=e,re=e=Bt(e.current,null),ce=_e=t,se=0,Qr=null,Ma=Ao=mn=0,Ee=Tr=null,ln!==null){for(t=0;t<ln.length;t++)if(n=ln[t],r=n.interleaved,r!==null){n.interleaved=null;var i=r.next,o=n.pending;if(o!==null){var s=o.next;o.next=i,r.next=s}n.pending=r}ln=null}return e}function Rp(e,t){do{var n=re;try{if(ma(),Ni.current=so,oo){for(var r=q.memoizedState;r!==null;){var i=r.queue;i!==null&&(i.pending=null),r=r.next}oo=!1}if(hn=0,le=ie=q=null,Pr=!1,Wr=0,La.current=null,n===null||n.return===null){se=1,Qr=t,re=null;break}e:{var o=e,s=n.return,l=n,a=t;if(t=ce,l.flags|=32768,a!==null&&typeof a=="object"&&typeof a.then=="function"){var u=a,c=l,f=c.tag;if(!(c.mode&1)&&(f===0||f===11||f===15)){var p=c.alternate;p?(c.updateQueue=p.updateQueue,c.memoizedState=p.memoizedState,c.lanes=p.lanes):(c.updateQueue=null,c.memoizedState=null)}var g=bu(s);if(g!==null){g.flags&=-257,ec(g,s,l,o,t),g.mode&1&&Ju(o,u,t),t=g,a=u;var y=t.updateQueue;if(y===null){var v=new Set;v.add(a),t.updateQueue=v}else y.add(a);break e}else{if(!(t&1)){Ju(o,u,t),_a();break e}a=Error(P(426))}}else if(K&&l.mode&1){var T=bu(s);if(T!==null){!(T.flags&65536)&&(T.flags|=256),ec(T,s,l,o,t),pa(qn(a,l));break e}}o=a=qn(a,l),se!==4&&(se=2),Tr===null?Tr=[o]:Tr.push(o),o=s;do{switch(o.tag){case 3:o.flags|=65536,t&=-t,o.lanes|=t;var m=pp(o,a,t);Gu(o,m);break e;case 1:l=a;var d=o.type,h=o.stateNode;if(!(o.flags&128)&&(typeof d.getDerivedStateFromError=="function"||h!==null&&typeof h.componentDidCatch=="function"&&(It===null||!It.has(h)))){o.flags|=65536,t&=-t,o.lanes|=t;var w=hp(o,l,t);Gu(o,w);break e}}o=o.return}while(o!==null)}_p(n)}catch(x){t=x,re===n&&n!==null&&(re=n=n.return);continue}break}while(1)}function Vp(){var e=lo.current;return lo.current=so,e===null?so:e}function _a(){(se===0||se===3||se===2)&&(se=4),ae===null||!(mn&268435455)&&!(Ao&268435455)||Rt(ae,ce)}function co(e,t){var n=z;z|=2;var r=Vp();(ae!==e||ce!==t)&&(ct=null,cn(e,t));do try{xy();break}catch(i){Rp(e,i)}while(1);if(ma(),z=n,lo.current=r,re!==null)throw Error(P(261));return ae=null,ce=0,se}function xy(){for(;re!==null;)Ap(re)}function Sy(){for(;re!==null&&!Km();)Ap(re)}function Ap(e){var t=Op(e.alternate,e,_e);e.memoizedProps=e.pendingProps,t===null?_p(e):re=t,La.current=null}function _p(e){var t=e;do{var n=t.alternate;if(e=t.return,t.flags&32768){if(n=hy(n,t),n!==null){n.flags&=32767,re=n;return}if(e!==null)e.flags|=32768,e.subtreeFlags=0,e.deletions=null;else{se=6,re=null;return}}else if(n=py(n,t,_e),n!==null){re=n;return}if(t=t.sibling,t!==null){re=t;return}re=t=e}while(t!==null);se===0&&(se=5)}function nn(e,t,n){var r=B,i=Ke.transition;try{Ke.transition=null,B=1,ky(e,t,n,r)}finally{Ke.transition=i,B=r}return null}function ky(e,t,n,r){do Wn();while(At!==null);if(z&6)throw Error(P(327));n=e.finishedWork;var i=e.finishedLanes;if(n===null)return null;if(e.finishedWork=null,e.finishedLanes=0,n===e.current)throw Error(P(177));e.callbackNode=null,e.callbackPriority=0;var o=n.lanes|n.childLanes;if(ng(e,o),e===ae&&(re=ae=null,ce=0),!(n.subtreeFlags&2064)&&!(n.flags&2064)||Pi||(Pi=!0,jp(Gi,function(){return Wn(),null})),o=(n.flags&15990)!==0,n.subtreeFlags&15990||o){o=Ke.transition,Ke.transition=null;var s=B;B=1;var l=z;z|=4,La.current=null,gy(e,n),Dp(n,e),$g(ol),Qi=!!il,ol=il=null,e.current=n,yy(n),Qm(),z=l,B=s,Ke.transition=o}else e.current=n;if(Pi&&(Pi=!1,At=e,uo=i),o=e.pendingLanes,o===0&&(It=null),Zm(n.stateNode),Re(e,te()),t!==null)for(r=e.onRecoverableError,n=0;n<t.length;n++)i=t[n],r(i.value,{componentStack:i.stack,digest:i.digest});if(ao)throw ao=!1,e=Tl,Tl=null,e;return uo&1&&e.tag!==0&&Wn(),o=e.pendingLanes,o&1?e===El?Er++:(Er=0,El=e):Er=0,Xt(),null}function Wn(){if(At!==null){var e=dd(uo),t=Ke.transition,n=B;try{if(Ke.transition=null,B=16>e?16:e,At===null)var r=!1;else{if(e=At,At=null,uo=0,z&6)throw Error(P(331));var i=z;for(z|=4,M=e.current;M!==null;){var o=M,s=o.child;if(M.flags&16){var l=o.deletions;if(l!==null){for(var a=0;a<l.length;a++){var u=l[a];for(M=u;M!==null;){var c=M;switch(c.tag){case 0:case 11:case 15:Cr(8,c,o)}var f=c.child;if(f!==null)f.return=c,M=f;else for(;M!==null;){c=M;var p=c.sibling,g=c.return;if(Cp(c),c===u){M=null;break}if(p!==null){p.return=g,M=p;break}M=g}}}var y=o.alternate;if(y!==null){var v=y.child;if(v!==null){y.child=null;do{var T=v.sibling;v.sibling=null,v=T}while(v!==null)}}M=o}}if(o.subtreeFlags&2064&&s!==null)s.return=o,M=s;else e:for(;M!==null;){if(o=M,o.flags&2048)switch(o.tag){case 0:case 11:case 15:Cr(9,o,o.return)}var m=o.sibling;if(m!==null){m.return=o.return,M=m;break e}M=o.return}}var d=e.current;for(M=d;M!==null;){s=M;var h=s.child;if(s.subtreeFlags&2064&&h!==null)h.return=s,M=h;else e:for(s=d;M!==null;){if(l=M,l.flags&2048)try{switch(l.tag){case 0:case 11:case 15:Vo(9,l)}}catch(x){b(l,l.return,x)}if(l===s){M=null;break e}var w=l.sibling;if(w!==null){w.return=l.return,M=w;break e}M=l.return}}if(z=i,Xt(),lt&&typeof lt.onPostCommitFiberRoot=="function")try{lt.onPostCommitFiberRoot(Po,e)}catch{}r=!0}return r}finally{B=n,Ke.transition=t}}return!1}function pc(e,t,n){t=qn(n,t),t=pp(e,t,1),e=Ft(e,t,1),t=ke(),e!==null&&(br(e,1,t),Re(e,t))}function b(e,t,n){if(e.tag===3)pc(e,e,n);else for(;t!==null;){if(t.tag===3){pc(t,e,n);break}else if(t.tag===1){var r=t.stateNode;if(typeof t.type.getDerivedStateFromError=="function"||typeof r.componentDidCatch=="function"&&(It===null||!It.has(r))){e=qn(n,e),e=hp(t,e,1),t=Ft(t,e,1),e=ke(),t!==null&&(br(t,1,e),Re(t,e));break}}t=t.return}}function Py(e,t,n){var r=e.pingCache;r!==null&&r.delete(t),t=ke(),e.pingedLanes|=e.suspendedLanes&n,ae===e&&(ce&n)===n&&(se===4||se===3&&(ce&130023424)===ce&&500>te()-Ra?cn(e,0):Ma|=n),Re(e,t)}function Np(e,t){t===0&&(e.mode&1?(t=pi,pi<<=1,!(pi&130023424)&&(pi=4194304)):t=1);var n=ke();e=xt(e,t),e!==null&&(br(e,t,n),Re(e,n))}function Cy(e){var t=e.memoizedState,n=0;t!==null&&(n=t.retryLane),Np(e,n)}function Ty(e,t){var n=0;switch(e.tag){case 13:var r=e.stateNode,i=e.memoizedState;i!==null&&(n=i.retryLane);break;case 19:r=e.stateNode;break;default:throw Error(P(314))}r!==null&&r.delete(t),Np(e,n)}var Op;Op=function(e,t,n){if(e!==null)if(e.memoizedProps!==t.pendingProps||Le.current)De=!0;else{if(!(e.lanes&n)&&!(t.flags&128))return De=!1,dy(e,t,n);De=!!(e.flags&131072)}else De=!1,K&&t.flags&1048576&&Id(t,eo,t.index);switch(t.lanes=0,t.tag){case 2:var r=t.type;ji(e,t),e=t.pendingProps;var i=Qn(t,we.current);Hn(t,n),i=Pa(null,t,r,e,i,n);var o=Ca();return t.flags|=1,typeof i=="object"&&i!==null&&typeof i.render=="function"&&i.$$typeof===void 0?(t.tag=1,t.memoizedState=null,t.updateQueue=null,Me(r)?(o=!0,Ji(t)):o=!1,t.memoizedState=i.state!==null&&i.state!==void 0?i.state:null,va(t),i.updater=Mo,t.stateNode=i,i._reactInternals=t,hl(t,r,e,n),t=yl(null,t,r,!0,o,n)):(t.tag=0,K&&o&&fa(t),Se(null,t,i,n),t=t.child),t;case 16:r=t.elementType;e:{switch(ji(e,t),e=t.pendingProps,i=r._init,r=i(r._payload),t.type=r,i=t.tag=Dy(r),e=qe(r,e),i){case 0:t=gl(null,t,r,e,n);break e;case 1:t=rc(null,t,r,e,n);break e;case 11:t=tc(null,t,r,e,n);break e;case 14:t=nc(null,t,r,qe(r.type,e),n);break e}throw Error(P(306,r,""))}return t;case 0:return r=t.type,i=t.pendingProps,i=t.elementType===r?i:qe(r,i),gl(e,t,r,i,n);case 1:return r=t.type,i=t.pendingProps,i=t.elementType===r?i:qe(r,i),rc(e,t,r,i,n);case 3:e:{if(vp(t),e===null)throw Error(P(387));r=t.pendingProps,o=t.memoizedState,i=o.element,$d(e,t),ro(t,r,null,n);var s=t.memoizedState;if(r=s.element,o.isDehydrated)if(o={element:r,isDehydrated:!1,cache:s.cache,pendingSuspenseBoundaries:s.pendingSuspenseBoundaries,transitions:s.transitions},t.updateQueue.baseState=o,t.memoizedState=o,t.flags&256){i=qn(Error(P(423)),t),t=ic(e,t,r,n,i);break e}else if(r!==i){i=qn(Error(P(424)),t),t=ic(e,t,r,n,i);break e}else for(Ne=jt(t.stateNode.containerInfo.firstChild),Oe=t,K=!0,be=null,n=Kd(t,null,r,n),t.child=n;n;)n.flags=n.flags&-3|4096,n=n.sibling;else{if(Yn(),r===i){t=St(e,t,n);break e}Se(e,t,r,n)}t=t.child}return t;case 5:return Qd(t),e===null&&fl(t),r=t.type,i=t.pendingProps,o=e!==null?e.memoizedProps:null,s=i.children,sl(r,i)?s=null:o!==null&&sl(r,o)&&(t.flags|=32),yp(e,t),Se(e,t,s,n),t.child;case 6:return e===null&&fl(t),null;case 13:return wp(e,t,n);case 4:return wa(t,t.stateNode.containerInfo),r=t.pendingProps,e===null?t.child=Xn(t,null,r,n):Se(e,t,r,n),t.child;case 11:return r=t.type,i=t.pendingProps,i=t.elementType===r?i:qe(r,i),tc(e,t,r,i,n);case 7:return Se(e,t,t.pendingProps,n),t.child;case 8:return Se(e,t,t.pendingProps.children,n),t.child;case 12:return Se(e,t,t.pendingProps.children,n),t.child;case 10:e:{if(r=t.type._context,i=t.pendingProps,o=t.memoizedProps,s=i.value,H(to,r._currentValue),r._currentValue=s,o!==null)if(nt(o.value,s)){if(o.children===i.children&&!Le.current){t=St(e,t,n);break e}}else for(o=t.child,o!==null&&(o.return=t);o!==null;){var l=o.dependencies;if(l!==null){s=o.child;for(var a=l.firstContext;a!==null;){if(a.context===r){if(o.tag===1){a=mt(-1,n&-n),a.tag=2;var u=o.updateQueue;if(u!==null){u=u.shared;var c=u.pending;c===null?a.next=a:(a.next=c.next,c.next=a),u.pending=a}}o.lanes|=n,a=o.alternate,a!==null&&(a.lanes|=n),dl(o.return,n,t),l.lanes|=n;break}a=a.next}}else if(o.tag===10)s=o.type===t.type?null:o.child;else if(o.tag===18){if(s=o.return,s===null)throw Error(P(341));s.lanes|=n,l=s.alternate,l!==null&&(l.lanes|=n),dl(s,n,t),s=o.sibling}else s=o.child;if(s!==null)s.return=o;else for(s=o;s!==null;){if(s===t){s=null;break}if(o=s.sibling,o!==null){o.return=s.return,s=o;break}s=s.return}o=s}Se(e,t,i.children,n),t=t.child}return t;case 9:return i=t.type,r=t.pendingProps.children,Hn(t,n),i=Qe(i),r=r(i),t.flags|=1,Se(e,t,r,n),t.child;case 14:return r=t.type,i=qe(r,t.pendingProps),i=qe(r.type,i),nc(e,t,r,i,n);case 15:return mp(e,t,t.type,t.pendingProps,n);case 17:return r=t.type,i=t.pendingProps,i=t.elementType===r?i:qe(r,i),ji(e,t),t.tag=1,Me(r)?(e=!0,Ji(t)):e=!1,Hn(t,n),Wd(t,r,i),hl(t,r,i,n),yl(null,t,r,!0,e,n);case 19:return xp(e,t,n);case 22:return gp(e,t,n)}throw Error(P(156,t.tag))};function jp(e,t){return ad(e,t)}function Ey(e,t,n,r){this.tag=e,this.key=n,this.sibling=this.child=this.return=this.stateNode=this.type=this.elementType=null,this.index=0,this.ref=null,this.pendingProps=t,this.dependencies=this.memoizedState=this.updateQueue=this.memoizedProps=null,this.mode=r,this.subtreeFlags=this.flags=0,this.deletions=null,this.childLanes=this.lanes=0,this.alternate=null}function Ge(e,t,n,r){return new Ey(e,t,n,r)}function Na(e){return e=e.prototype,!(!e||!e.isReactComponent)}function Dy(e){if(typeof e=="function")return Na(e)?1:0;if(e!=null){if(e=e.$$typeof,e===bl)return 11;if(e===ea)return 14}return 2}function Bt(e,t){var n=e.alternate;return n===null?(n=Ge(e.tag,t,e.key,e.mode),n.elementType=e.elementType,n.type=e.type,n.stateNode=e.stateNode,n.alternate=e,e.alternate=n):(n.pendingProps=t,n.type=e.type,n.flags=0,n.subtreeFlags=0,n.deletions=null),n.flags=e.flags&14680064,n.childLanes=e.childLanes,n.lanes=e.lanes,n.child=e.child,n.memoizedProps=e.memoizedProps,n.memoizedState=e.memoizedState,n.updateQueue=e.updateQueue,t=e.dependencies,n.dependencies=t===null?null:{lanes:t.lanes,firstContext:t.firstContext},n.sibling=e.sibling,n.index=e.index,n.ref=e.ref,n}function zi(e,t,n,r,i,o){var s=2;if(r=e,typeof e=="function")Na(e)&&(s=1);else if(typeof e=="string")s=5;else e:switch(e){case Cn:return fn(n.children,i,o,t);case Jl:s=8,i|=8;break;case Is:return e=Ge(12,n,t,i|2),e.elementType=Is,e.lanes=o,e;case zs:return e=Ge(13,n,t,i),e.elementType=zs,e.lanes=o,e;case Bs:return e=Ge(19,n,t,i),e.elementType=Bs,e.lanes=o,e;case Gf:return _o(n,i,o,t);default:if(typeof e=="object"&&e!==null)switch(e.$$typeof){case Hf:s=10;break e;case Wf:s=9;break e;case bl:s=11;break e;case ea:s=14;break e;case Et:s=16,r=null;break e}throw Error(P(130,e==null?e:typeof e,""))}return t=Ge(s,n,t,i),t.elementType=e,t.type=r,t.lanes=o,t}function fn(e,t,n,r){return e=Ge(7,e,r,t),e.lanes=n,e}function _o(e,t,n,r){return e=Ge(22,e,r,t),e.elementType=Gf,e.lanes=n,e.stateNode={isHidden:!1},e}function ys(e,t,n){return e=Ge(6,e,null,t),e.lanes=n,e}function vs(e,t,n){return t=Ge(4,e.children!==null?e.children:[],e.key,t),t.lanes=n,t.stateNode={containerInfo:e.containerInfo,pendingChildren:null,implementation:e.implementation},t}function Ly(e,t,n,r,i){this.tag=t,this.containerInfo=e,this.finishedWork=this.pingCache=this.current=this.pendingChildren=null,this.timeoutHandle=-1,this.callbackNode=this.pendingContext=this.context=null,this.callbackPriority=0,this.eventTimes=Jo(0),this.expirationTimes=Jo(-1),this.entangledLanes=this.finishedLanes=this.mutableReadLanes=this.expiredLanes=this.pingedLanes=this.suspendedLanes=this.pendingLanes=0,this.entanglements=Jo(0),this.identifierPrefix=r,this.onRecoverableError=i,this.mutableSourceEagerHydrationData=null}function Oa(e,t,n,r,i,o,s,l,a){return e=new Ly(e,t,n,l,a),t===1?(t=1,o===!0&&(t|=8)):t=0,o=Ge(3,null,null,t),e.current=o,o.stateNode=e,o.memoizedState={element:r,isDehydrated:n,cache:null,transitions:null,pendingSuspenseBoundaries:null},va(o),e}function My(e,t,n){var r=3<arguments.length&&arguments[3]!==void 0?arguments[3]:null;return{$$typeof:Pn,key:r==null?null:""+r,children:e,containerInfo:t,implementation:n}}function Fp(e){if(!e)return Wt;e=e._reactInternals;e:{if(vn(e)!==e||e.tag!==1)throw Error(P(170));var t=e;do{switch(t.tag){case 3:t=t.stateNode.context;break e;case 1:if(Me(t.type)){t=t.stateNode.__reactInternalMemoizedMergedChildContext;break e}}t=t.return}while(t!==null);throw Error(P(171))}if(e.tag===1){var n=e.type;if(Me(n))return jd(e,n,t)}return t}function Ip(e,t,n,r,i,o,s,l,a){return e=Oa(n,r,!0,e,i,o,s,l,a),e.context=Fp(null),n=e.current,r=ke(),i=zt(n),o=mt(r,i),o.callback=t??null,Ft(n,o,i),e.current.lanes=i,br(e,i,r),Re(e,r),e}function No(e,t,n,r){var i=t.current,o=ke(),s=zt(i);return n=Fp(n),t.context===null?t.context=n:t.pendingContext=n,t=mt(o,s),t.payload={element:e},r=r===void 0?null:r,r!==null&&(t.callback=r),e=Ft(i,t,s),e!==null&&(tt(e,i,s,o),_i(e,i,s)),s}function fo(e){if(e=e.current,!e.child)return null;switch(e.child.tag){case 5:return e.child.stateNode;default:return e.child.stateNode}}function hc(e,t){if(e=e.memoizedState,e!==null&&e.dehydrated!==null){var n=e.retryLane;e.retryLane=n!==0&&n<t?n:t}}function ja(e,t){hc(e,t),(e=e.alternate)&&hc(e,t)}function Ry(){return null}var zp=typeof reportError=="function"?reportError:function(e){console.error(e)};function Fa(e){this._internalRoot=e}Oo.prototype.render=Fa.prototype.render=function(e){var t=this._internalRoot;if(t===null)throw Error(P(409));No(e,t,null,null)};Oo.prototype.unmount=Fa.prototype.unmount=function(){var e=this._internalRoot;if(e!==null){this._internalRoot=null;var t=e.containerInfo;gn(function(){No(null,e,null,null)}),t[wt]=null}};function Oo(e){this._internalRoot=e}Oo.prototype.unstable_scheduleHydration=function(e){if(e){var t=md();e={blockedOn:null,target:e,priority:t};for(var n=0;n<Mt.length&&t!==0&&t<Mt[n].priority;n++);Mt.splice(n,0,e),n===0&&yd(e)}};function Ia(e){return!(!e||e.nodeType!==1&&e.nodeType!==9&&e.nodeType!==11)}function jo(e){return!(!e||e.nodeType!==1&&e.nodeType!==9&&e.nodeType!==11&&(e.nodeType!==8||e.nodeValue!==" react-mount-point-unstable "))}function mc(){}function Vy(e,t,n,r,i){if(i){if(typeof r=="function"){var o=r;r=function(){var u=fo(s);o.call(u)}}var s=Ip(t,r,e,0,null,!1,!1,"",mc);return e._reactRootContainer=s,e[wt]=s.current,zr(e.nodeType===8?e.parentNode:e),gn(),s}for(;i=e.lastChild;)e.removeChild(i);if(typeof r=="function"){var l=r;r=function(){var u=fo(a);l.call(u)}}var a=Oa(e,0,!1,null,null,!1,!1,"",mc);return e._reactRootContainer=a,e[wt]=a.current,zr(e.nodeType===8?e.parentNode:e),gn(function(){No(t,a,n,r)}),a}function Fo(e,t,n,r,i){var o=n._reactRootContainer;if(o){var s=o;if(typeof i=="function"){var l=i;i=function(){var a=fo(s);l.call(a)}}No(t,s,e,i)}else s=Vy(n,t,e,i,r);return fo(s)}pd=function(e){switch(e.tag){case 3:var t=e.stateNode;if(t.current.memoizedState.isDehydrated){var n=mr(t.pendingLanes);n!==0&&(ra(t,n|1),Re(t,te()),!(z&6)&&(Jn=te()+500,Xt()))}break;case 13:gn(function(){var r=xt(e,1);if(r!==null){var i=ke();tt(r,e,1,i)}}),ja(e,1)}};ia=function(e){if(e.tag===13){var t=xt(e,134217728);if(t!==null){var n=ke();tt(t,e,134217728,n)}ja(e,134217728)}};hd=function(e){if(e.tag===13){var t=zt(e),n=xt(e,t);if(n!==null){var r=ke();tt(n,e,t,r)}ja(e,t)}};md=function(){return B};gd=function(e,t){var n=B;try{return B=e,t()}finally{B=n}};Zs=function(e,t,n){switch(t){case"input":if(Hs(e,n),t=n.name,n.type==="radio"&&t!=null){for(n=e;n.parentNode;)n=n.parentNode;for(n=n.querySelectorAll("input[name="+JSON.stringify(""+t)+'][type="radio"]'),t=0;t<n.length;t++){var r=n[t];if(r!==e&&r.form===e.form){var i=Do(r);if(!i)throw Error(P(90));Qf(r),Hs(r,i)}}}break;case"textarea":Xf(e,n);break;case"select":t=n.value,t!=null&&zn(e,!!n.multiple,t,!1)}};nd=Va;rd=gn;var Ay={usingClientEntryPoint:!1,Events:[ti,Ln,Do,ed,td,Va]},cr={findFiberByHostInstance:sn,bundleType:0,version:"18.2.0",rendererPackageName:"react-dom"},_y={bundleType:cr.bundleType,version:cr.version,rendererPackageName:cr.rendererPackageName,rendererConfig:cr.rendererConfig,overrideHookState:null,overrideHookStateDeletePath:null,overrideHookStateRenamePath:null,overrideProps:null,overridePropsDeletePath:null,overridePropsRenamePath:null,setErrorHandler:null,setSuspenseHandler:null,scheduleUpdate:null,currentDispatcherRef:Pt.ReactCurrentDispatcher,findHostInstanceByFiber:function(e){return e=sd(e),e===null?null:e.stateNode},findFiberByHostInstance:cr.findFiberByHostInstance||Ry,findHostInstancesForRefresh:null,scheduleRefresh:null,scheduleRoot:null,setRefreshHandler:null,getCurrentFiber:null,reconcilerVersion:"18.2.0-next-9e3b772b8-20220608"};if(typeof __REACT_DEVTOOLS_GLOBAL_HOOK__<"u"){var Ci=__REACT_DEVTOOLS_GLOBAL_HOOK__;if(!Ci.isDisabled&&Ci.supportsFiber)try{Po=Ci.inject(_y),lt=Ci}catch{}}Ie.__SECRET_INTERNALS_DO_NOT_USE_OR_YOU_WILL_BE_FIRED=Ay;Ie.createPortal=function(e,t){var n=2<arguments.length&&arguments[2]!==void 0?arguments[2]:null;if(!Ia(t))throw Error(P(200));return My(e,t,null,n)};Ie.createRoot=function(e,t){if(!Ia(e))throw Error(P(299));var n=!1,r="",i=zp;return t!=null&&(t.unstable_strictMode===!0&&(n=!0),t.identifierPrefix!==void 0&&(r=t.identifierPrefix),t.onRecoverableError!==void 0&&(i=t.onRecoverableError)),t=Oa(e,1,!1,null,null,n,!1,r,i),e[wt]=t.current,zr(e.nodeType===8?e.parentNode:e),new Fa(t)};Ie.findDOMNode=function(e){if(e==null)return null;if(e.nodeType===1)return e;var t=e._reactInternals;if(t===void 0)throw typeof e.render=="function"?Error(P(188)):(e=Object.keys(e).join(","),Error(P(268,e)));return e=sd(t),e=e===null?null:e.stateNode,e};Ie.flushSync=function(e){return gn(e)};Ie.hydrate=function(e,t,n){if(!jo(t))throw Error(P(200));return Fo(null,e,t,!0,n)};Ie.hydrateRoot=function(e,t,n){if(!Ia(e))throw Error(P(405));var r=n!=null&&n.hydratedSources||null,i=!1,o="",s=zp;if(n!=null&&(n.unstable_strictMode===!0&&(i=!0),n.identifierPrefix!==void 0&&(o=n.identifierPrefix),n.onRecoverableError!==void 0&&(s=n.onRecoverableError)),t=Ip(t,null,e,1,n??null,i,!1,o,s),e[wt]=t.current,zr(e),r)for(e=0;e<r.length;e++)n=r[e],i=n._getVersion,i=i(n._source),t.mutableSourceEagerHydrationData==null?t.mutableSourceEagerHydrationData=[n,i]:t.mutableSourceEagerHydrationData.push(n,i);return new Oo(t)};Ie.render=function(e,t,n){if(!jo(t))throw Error(P(200));return Fo(null,e,t,!1,n)};Ie.unmountComponentAtNode=function(e){if(!jo(e))throw Error(P(40));return e._reactRootContainer?(gn(function(){Fo(null,null,e,!1,function(){e._reactRootContainer=null,e[wt]=null})}),!0):!1};Ie.unstable_batchedUpdates=Va;Ie.unstable_renderSubtreeIntoContainer=function(e,t,n,r){if(!jo(n))throw Error(P(200));if(e==null||e._reactInternals===void 0)throw Error(P(38));return Fo(e,t,n,!1,r)};Ie.version="18.2.0-next-9e3b772b8-20220608";function Bp(){if(!(typeof __REACT_DEVTOOLS_GLOBAL_HOOK__>"u"||typeof __REACT_DEVTOOLS_GLOBAL_HOOK__.checkDCE!="function"))try{__REACT_DEVTOOLS_GLOBAL_HOOK__.checkDCE(Bp)}catch(e){console.error(e)}}Bp(),If.exports=Ie;var Ny=If.exports,gc=Ny;js.createRoot=gc.createRoot,js.hydrateRoot=gc.hydrateRoot;function Oy(e,t){let n=0;return function(...r){const i=performance.now();i-n<t||(n=i,e(...r))}}function jy(){let e=!1;return function(t){(/(android|bb\d+|meego).+mobile|avantgo|bada\/|blackberry|blazer|compal|elaine|fennec|hiptop|iemobile|ip(hone|od)|iris|kindle|lge |maemo|midp|mmp|mobile.+firefox|netfront|opera m(ob|in)i|palm( os)?|phone|p(ixi|re)\/|plucker|pocket|psp|series(4|6)0|symbian|treo|up\.(browser|link)|vodafone|wap|windows ce|xda|xiino|android|ipad|playbook|silk/i.test(t)||/1207|6310|6590|3gso|4thp|50[1-6]i|770s|802s|a wa|abac|ac(er|oo|s-)|ai(ko|rn)|al(av|ca|co)|amoi|an(ex|ny|yw)|aptu|ar(ch|go)|as(te|us)|attw|au(di|-m|r |s )|avan|be(ck|ll|nq)|bi(lb|rd)|bl(ac|az)|br(e|v)w|bumb|bw-(n|u)|c55\/|capi|ccwa|cdm-|cell|chtm|cldc|cmd-|co(mp|nd)|craw|da(it|ll|ng)|dbte|dc-s|devi|dica|dmob|do(c|p)o|ds(12|-d)|el(49|ai)|em(l2|ul)|er(ic|k0)|esl8|ez([4-7]0|os|wa|ze)|fetc|fly(-|_)|g1 u|g560|gene|gf-5|g-mo|go(\.w|od)|gr(ad|un)|haie|hcit|hd-(m|p|t)|hei-|hi(pt|ta)|hp( i|ip)|hs-c|ht(c(-| |_|a|g|p|s|t)|tp)|hu(aw|tc)|i-(20|go|ma)|i230|iac( |-|\/)|ibro|idea|ig01|ikom|im1k|inno|ipaq|iris|ja(t|v)a|jbro|jemu|jigs|kddi|keji|kgt( |\/)|klon|kpt |kwc-|kyo(c|k)|le(no|xi)|lg( g|\/(k|l|u)|50|54|-[a-w])|libw|lynx|m1-w|m3ga|m50\/|ma(te|ui|xo)|mc(01|21|ca)|m-cr|me(rc|ri)|mi(o8|oa|ts)|mmef|mo(01|02|bi|de|do|t(-| |o|v)|zz)|mt(50|p1|v )|mwbp|mywa|n10[0-2]|n20[2-3]|n30(0|2)|n50(0|2|5)|n7(0(0|1)|10)|ne((c|m)-|on|tf|wf|wg|wt)|nok(6|i)|nzph|o2im|op(ti|wv)|oran|owg1|p800|pan(a|d|t)|pdxg|pg(13|-([1-8]|c))|phil|pire|pl(ay|uc)|pn-2|po(ck|rt|se)|prox|psio|pt-g|qa-a|qc(07|12|21|32|60|-[2-7]|i-)|qtek|r380|r600|raks|rim9|ro(ve|zo)|s55\/|sa(ge|ma|mm|ms|ny|va)|sc(01|h-|oo|p-)|sdk\/|se(c(-|0|1)|47|mc|nd|ri)|sgh-|shar|sie(-|m)|sk-0|sl(45|id)|sm(al|ar|b3|it|t5)|so(ft|ny)|sp(01|h-|v-|v )|sy(01|mb)|t2(18|50)|t6(00|10|18)|ta(gt|lk)|tcl-|tdg-|tel(i|m)|tim-|t-mo|to(pl|sh)|ts(70|m-|m3|m5)|tx-9|up(\.b|g1|si)|utst|v400|v750|veri|vi(rg|te)|vk(40|5[0-3]|-v)|vm40|voda|vulc|vx(52|53|60|61|70|80|81|83|85|98)|w3c(-| )|webc|whit|wi(g |nc|nw)|wmlb|wonu|x700|yas-|your|zeto|zte-/i.test(t.substr(0,4)))&&(e=!0)}(navigator.userAgent||navigator.vendor||("opera"in window&&typeof window.opera=="string"?window.opera:"")),e}const Fy=jy(),Te={DEFAULT_MODEL:"quickdraw-mobilevit-small",DEFAULT_QUANTIZED:!1,BANNED_LABELS:["animal migration","arm","barn","bat","circle","hexagon","stitches","sweather","van"],PREDICTION_REFRESH_TIME:10,BRUSH_SIZE:Fy?12:16,TARGET_FPS:60,GAME_DURATION:1e3+.5,COUNTDOWN_TIMER:3,EASY_MODE_THRESHOLD:.2,EASY_MODE_DURATION:120*1e3,EASY_MODE_DELAY:3*1e3,SKIP_PENALTY:3*1e3,LABELS:{0:"aircraft carrier",1:"airplane",2:"alarm clock",3:"ambulance",4:"angel",5:"animal migration",6:"ant",7:"anvil",8:"apple",9:"arm",10:"asparagus",11:"axe",12:"backpack",13:"banana",14:"bandage",15:"barn",16:"baseball bat",17:"baseball",18:"basket",19:"basketball",20:"bat",21:"bathtub",22:"beach",23:"bear",24:"beard",25:"bed",26:"bee",27:"belt",28:"bench",29:"bicycle",30:"binoculars",31:"bird",32:"birthday cake",33:"blackberry",34:"blueberry",35:"book",36:"boomerang",37:"bottlecap",38:"bowtie",39:"bracelet",40:"brain",41:"bread",42:"bridge",43:"broccoli",44:"broom",45:"bucket",46:"bulldozer",47:"bus",48:"bush",49:"butterfly",50:"cactus",51:"cake",52:"calculator",53:"calendar",54:"camel",55:"camera",56:"camouflage",57:"campfire",58:"candle",59:"cannon",60:"canoe",61:"car",62:"carrot",63:"castle",64:"cat",65:"ceiling fan",66:"cell phone",67:"cello",68:"chair",69:"chandelier",70:"church",71:"circle",72:"clarinet",73:"clock",74:"cloud",75:"coffee cup",76:"compass",77:"computer",78:"cookie",79:"cooler",80:"couch",81:"cow",82:"crab",83:"crayon",84:"crocodile",85:"crown",86:"cruise ship",87:"cup",88:"diamond",89:"dishwasher",90:"diving board",91:"dog",92:"dolphin",93:"donut",94:"door",95:"dragon",96:"dresser",97:"drill",98:"drums",99:"duck",100:"dumbbell",101:"ear",102:"elbow",103:"elephant",104:"envelope",105:"eraser",106:"eye",107:"eyeglasses",108:"face",109:"fan",110:"feather",111:"fence",112:"finger",113:"fire hydrant",114:"fireplace",115:"firetruck",116:"fish",117:"flamingo",118:"flashlight",119:"flip flops",120:"floor lamp",121:"flower",122:"flying saucer",123:"foot",124:"fork",125:"frog",126:"frying pan",127:"garden hose",128:"garden",129:"giraffe",130:"goatee",131:"golf club",132:"grapes",133:"grass",134:"guitar",135:"hamburger",136:"hammer",137:"hand",138:"harp",139:"hat",140:"headphones",141:"hedgehog",142:"helicopter",143:"helmet",144:"hexagon",145:"hockey puck",146:"hockey stick",147:"horse",148:"hospital",149:"hot air balloon",150:"hot dog",151:"hot tub",152:"hourglass",153:"house plant",154:"house",155:"hurricane",156:"ice cream",157:"jacket",158:"jail",159:"kangaroo",160:"key",161:"keyboard",162:"knee",163:"knife",164:"ladder",165:"lantern",166:"laptop",167:"leaf",168:"leg",169:"light bulb",170:"lighter",171:"lighthouse",172:"lightning",173:"line",174:"lion",175:"lipstick",176:"lobster",177:"lollipop",178:"mailbox",179:"map",180:"marker",181:"matches",182:"megaphone",183:"mermaid",184:"microphone",185:"microwave",186:"monkey",187:"moon",188:"mosquito",189:"motorbike",190:"mountain",191:"mouse",192:"moustache",193:"mouth",194:"mug",195:"mushroom",196:"nail",197:"necklace",198:"nose",199:"ocean",200:"octagon",201:"octopus",202:"onion",203:"oven",204:"owl",205:"paint can",206:"paintbrush",207:"palm tree",208:"panda",209:"pants",210:"paper clip",211:"parachute",212:"parrot",213:"passport",214:"peanut",215:"pear",216:"peas",217:"pencil",218:"penguin",219:"piano",220:"pickup truck",221:"picture frame",222:"pig",223:"pillow",224:"pineapple",225:"pizza",226:"pliers",227:"police car",228:"pond",229:"pool",230:"popsicle",231:"postcard",232:"potato",233:"power outlet",234:"purse",235:"rabbit",236:"raccoon",237:"radio",238:"rain",239:"rainbow",240:"rake",241:"remote control",242:"rhinoceros",243:"rifle",244:"river",245:"roller coaster",246:"rollerskates",247:"sailboat",248:"sandwich",249:"saw",250:"saxophone",251:"school bus",252:"scissors",253:"scorpion",254:"screwdriver",255:"sea turtle",256:"see saw",257:"shark",258:"sheep",259:"shoe",260:"shorts",261:"shovel",262:"sink",263:"skateboard",264:"skull",265:"skyscraper",266:"sleeping bag",267:"smiley face",268:"snail",269:"snake",270:"snorkel",271:"snowflake",272:"snowman",273:"soccer ball",274:"sock",275:"speedboat",276:"spider",277:"spoon",278:"spreadsheet",279:"square",280:"squiggle",281:"squirrel",282:"stairs",283:"star",284:"steak",285:"stereo",286:"stethoscope",287:"stitches",288:"stop sign",289:"stove",290:"strawberry",291:"streetlight",292:"string bean",293:"submarine",294:"suitcase",295:"sun",296:"swan",297:"sweater",298:"swing set",299:"sword",300:"syringe",301:"t-shirt",302:"table",303:"teapot",304:"teddy-bear",305:"telephone",306:"television",307:"tennis racquet",308:"tent",309:"The Eiffel Tower",310:"The Great Wall of China",311:"The Mona Lisa",312:"tiger",313:"toaster",314:"toe",315:"toilet",316:"tooth",317:"toothbrush",318:"toothpaste",319:"tornado",320:"tractor",321:"traffic light",322:"train",323:"tree",324:"triangle",325:"trombone",326:"truck",327:"trumpet",328:"umbrella",329:"underwear",330:"van",331:"vase",332:"violin",333:"washing machine",334:"watermelon",335:"waterslide",336:"whale",337:"wheel",338:"windmill",339:"wine bottle",340:"wine glass",341:"wristwatch",342:"yoga",343:"zebra",344:"zigzag"}},yc=["mousedown","touchstart"],vc=["mousemove","touchmove"],wc=["mouseup","mouseout","touchend"],xc=10,Sc=Math.max(window.screen.width,window.screen.height),ws=4,xs=(e,t,n)=>{for(let r of t)e.addEventListener(r,n)},Ss=(e,t,n)=>{for(let r of t)e.removeEventListener(r,n)},kc=e=>{if(e.touches&&e.touches[0]){const t=(e.target.offsetHeight-document.body.offsetHeight)/2;return[e.touches[0].clientX,e.touches[0].clientY-t]}else return[e.offsetX,e.offsetY]},Up=S.forwardRef(({onSketchChange:e,disabled:t},n)=>{const r=S.useRef(null),i=S.useRef(null),[o,s]=S.useState(null),[l,a]=S.useState(!1),[u,c]=S.useState(0);S.useEffect(()=>{const g=r.current;i.current||(i.current=g.getContext("2d",{willReadFrequently:!0}));const y=i.current;y.imageSmoothingEnabled=!0,y.lineWidth=Te.BRUSH_SIZE,y.lineJoin="round",y.lineCap="round",y.strokeStyle="black",y.shadowColor="rgba(0, 0, 0, 0.9)",y.shadowBlur=1;const v=(g.width-window.innerWidth)/2,T=(g.height-window.innerHeight)/2,m=Te.BRUSH_SIZE/2,d=()=>{g.style.width=window.innerWidth,g.style.height=window.innerHeight},h=C=>{if(t)return;const[E,k]=kc(C),V=E+v,R=k+T;y.moveTo(V,R),y.beginPath(),y.lineTo(V,R),y.arc(V,R,.5,0,2*Math.PI),y.stroke(),a(!0),s(j=>j===null?[V,R,V,R]:[Math.min(j[0],V-m),Math.min(j[1],R-m),Math.max(j[2],V+m),Math.max(j[3],R+m)]),e()},w=Oy(C=>{if(!l||t)return;c(j=>j+xc);const[E,k]=kc(C),V=E+v,R=k+T;s(j=>j===null?j:[Math.min(j[0],V-m),Math.min(j[1],R-m),Math.max(j[2],V+m),Math.max(j[3],R+m)]),y.lineTo(V,R),y.stroke(),e()},xc),x=()=>{a(!1)};return d(),window.addEventListener("resize",d),xs(g,yc,h),xs(g,vc,w),xs(g,wc,x),()=>{window.removeEventListener("resize",d),Ss(g,yc,h),Ss(g,vc,w),Ss(g,wc,x)}},[l,e,t]);const f=()=>{if(o===null)return null;const g=i.current;let y=o[0],v=o[1],T=o[2]-o[0],m=o[3]-o[1],d=2*ws;return T>=m?(d+=T,v=Math.max(v-(T-m)/2,0)):(d+=m,y=Math.max(y-(m-T)/2,0)),g.getImageData(y-ws,v-ws,d,d)},p=(g=!1)=>{s(null);const y=r.current;i.current.clearRect(0,0,y.width,y.height),a(!1),g&&c(0)};return S.useImperativeHandle(n,()=>({getCanvasData:f,clearCanvas:p,getTimeSpentDrawing:()=>u})),O.jsx("canvas",{className:"object-none w-full h-full",ref:r,width:Sc,height:Sc})});Up.displayName="SketchCanvas";const $p=S.createContext({transformPagePoint:e=>e,isStatic:!1,reducedMotion:"never"}),Io=S.createContext({}),zo=S.createContext(null),Bo=typeof document<"u",po=Bo?S.useLayoutEffect:S.useEffect,Hp=S.createContext({strict:!1});function Iy(e,t,n,r){const{visualElement:i}=S.useContext(Io),o=S.useContext(Hp),s=S.useContext(zo),l=S.useContext($p).reducedMotion,a=S.useRef();r=r||o.renderer,!a.current&&r&&(a.current=r(e,{visualState:t,parent:i,props:n,presenceContext:s,blockInitialAnimation:s?s.initial===!1:!1,reducedMotionConfig:l}));const u=a.current;return S.useInsertionEffect(()=>{u&&u.update(n,s)}),po(()=>{u&&u.render()}),S.useEffect(()=>{u&&u.updateFeatures()}),(window.HandoffAppearAnimations?po:S.useEffect)(()=>{u&&u.animationState&&u.animationState.animateChanges()}),u}function On(e){return typeof e=="object"&&Object.prototype.hasOwnProperty.call(e,"current")}function zy(e,t,n){return S.useCallback(r=>{r&&e.mount&&e.mount(r),t&&(r?t.mount(r):t.unmount()),n&&(typeof n=="function"?n(r):On(n)&&(n.current=r))},[t])}function Yr(e){return typeof e=="string"||Array.isArray(e)}function Uo(e){return typeof e=="object"&&typeof e.start=="function"}const za=["animate","whileInView","whileFocus","whileHover","whileTap","whileDrag","exit"],Ba=["initial",...za];function $o(e){return Uo(e.animate)||Ba.some(t=>Yr(e[t]))}function Wp(e){return!!($o(e)||e.variants)}function By(e,t){if($o(e)){const{initial:n,animate:r}=e;return{initial:n===!1||Yr(n)?n:void 0,animate:Yr(r)?r:void 0}}return e.inherit!==!1?t:{}}function Uy(e){const{initial:t,animate:n}=By(e,S.useContext(Io));return S.useMemo(()=>({initial:t,animate:n}),[Pc(t),Pc(n)])}function Pc(e){return Array.isArray(e)?e.join(" "):e}const Cc={animation:["animate","variants","whileHover","whileTap","exit","whileInView","whileFocus","whileDrag"],exit:["exit"],drag:["drag","dragControls"],focus:["whileFocus"],hover:["whileHover","onHoverStart","onHoverEnd"],tap:["whileTap","onTap","onTapStart","onTapCancel"],pan:["onPan","onPanStart","onPanSessionStart","onPanEnd"],inView:["whileInView","onViewportEnter","onViewportLeave"],layout:["layout","layoutId"]},Xr={};for(const e in Cc)Xr[e]={isEnabled:t=>Cc[e].some(n=>!!t[n])};function $y(e){for(const t in e)Xr[t]={...Xr[t],...e[t]}}const Ua=S.createContext({}),Gp=S.createContext({}),Hy=Symbol.for("motionComponentSymbol");function Wy({preloadedFeatures:e,createVisualElement:t,useRender:n,useVisualState:r,Component:i}){e&&$y(e);function o(l,a){let u;const c={...S.useContext($p),...l,layoutId:Gy(l)},{isStatic:f}=c,p=Uy(l),g=r(l,f);if(!f&&Bo){p.visualElement=Iy(i,g,c,t);const y=S.useContext(Gp),v=S.useContext(Hp).strict;p.visualElement&&(u=p.visualElement.loadFeatures(c,v,e,y))}return S.createElement(Io.Provider,{value:p},u&&p.visualElement?S.createElement(u,{visualElement:p.visualElement,...c}):null,n(i,l,zy(g,p.visualElement,a),g,f,p.visualElement))}const s=S.forwardRef(o);return s[Hy]=i,s}function Gy({layoutId:e}){const t=S.useContext(Ua).id;return t&&e!==void 0?t+"-"+e:e}function Ky(e){function t(r,i={}){return Wy(e(r,i))}if(typeof Proxy>"u")return t;const n=new Map;return new Proxy(t,{get:(r,i)=>(n.has(i)||n.set(i,t(i)),n.get(i))})}const Qy=["animate","circle","defs","desc","ellipse","g","image","line","filter","marker","mask","metadata","path","pattern","polygon","polyline","rect","stop","switch","symbol","svg","text","tspan","use","view"];function $a(e){return typeof e!="string"||e.includes("-")?!1:!!(Qy.indexOf(e)>-1||/[A-Z]/.test(e))}const ho={};function Yy(e){Object.assign(ho,e)}const ri=["transformPerspective","x","y","z","translateX","translateY","translateZ","scale","scaleX","scaleY","rotate","rotateX","rotateY","rotateZ","skew","skewX","skewY"],wn=new Set(ri);function Kp(e,{layout:t,layoutId:n}){return wn.has(e)||e.startsWith("origin")||(t||n!==void 0)&&(!!ho[e]||e==="opacity")}const Ve=e=>!!(e&&e.getVelocity),Xy={x:"translateX",y:"translateY",z:"translateZ",transformPerspective:"perspective"},Zy=ri.length;function qy(e,{enableHardwareAcceleration:t=!0,allowTransformNone:n=!0},r,i){let o="";for(let s=0;s<Zy;s++){const l=ri[s];if(e[l]!==void 0){const a=Xy[l]||l;o+=`${a}(${e[l]}) `}}return t&&!e.z&&(o+="translateZ(0)"),o=o.trim(),i?o=i(e,r?"":o):n&&r&&(o="none"),o}const Qp=e=>t=>typeof t=="string"&&t.startsWith(e),Yp=Qp("--"),Ml=Qp("var(--"),Jy=/var\s*\(\s*--[\w-]+(\s*,\s*(?:(?:[^)(]|\((?:[^)(]+|\([^)(]*\))*\))*)+)?\s*\)/g,by=(e,t)=>t&&typeof e=="number"?t.transform(e):e,Gt=(e,t,n)=>Math.min(Math.max(n,e),t),xn={test:e=>typeof e=="number",parse:parseFloat,transform:e=>e},Dr={...xn,transform:e=>Gt(0,1,e)},Ti={...xn,default:1},Lr=e=>Math.round(e*1e5)/1e5,Ho=/(-)?([\d]*\.?[\d])+/g,Xp=/(#[0-9a-f]{3,8}|(rgb|hsl)a?\((-?[\d\.]+%?[,\s]+){2}(-?[\d\.]+%?)\s*[\,\/]?\s*[\d\.]*%?\))/gi,e0=/^(#[0-9a-f]{3,8}|(rgb|hsl)a?\((-?[\d\.]+%?[,\s]+){2}(-?[\d\.]+%?)\s*[\,\/]?\s*[\d\.]*%?\))$/i;function ii(e){return typeof e=="string"}const oi=e=>({test:t=>ii(t)&&t.endsWith(e)&&t.split(" ").length===1,parse:parseFloat,transform:t=>`${t}${e}`}),Tt=oi("deg"),ut=oi("%"),A=oi("px"),t0=oi("vh"),n0=oi("vw"),Tc={...ut,parse:e=>ut.parse(e)/100,transform:e=>ut.transform(e*100)},Ec={...xn,transform:Math.round},Zp={borderWidth:A,borderTopWidth:A,borderRightWidth:A,borderBottomWidth:A,borderLeftWidth:A,borderRadius:A,radius:A,borderTopLeftRadius:A,borderTopRightRadius:A,borderBottomRightRadius:A,borderBottomLeftRadius:A,width:A,maxWidth:A,height:A,maxHeight:A,size:A,top:A,right:A,bottom:A,left:A,padding:A,paddingTop:A,paddingRight:A,paddingBottom:A,paddingLeft:A,margin:A,marginTop:A,marginRight:A,marginBottom:A,marginLeft:A,rotate:Tt,rotateX:Tt,rotateY:Tt,rotateZ:Tt,scale:Ti,scaleX:Ti,scaleY:Ti,scaleZ:Ti,skew:Tt,skewX:Tt,skewY:Tt,distance:A,translateX:A,translateY:A,translateZ:A,x:A,y:A,z:A,perspective:A,transformPerspective:A,opacity:Dr,originX:Tc,originY:Tc,originZ:A,zIndex:Ec,fillOpacity:Dr,strokeOpacity:Dr,numOctaves:Ec};function Ha(e,t,n,r){const{style:i,vars:o,transform:s,transformOrigin:l}=e;let a=!1,u=!1,c=!0;for(const f in t){const p=t[f];if(Yp(f)){o[f]=p;continue}const g=Zp[f],y=by(p,g);if(wn.has(f)){if(a=!0,s[f]=y,!c)continue;p!==(g.default||0)&&(c=!1)}else f.startsWith("origin")?(u=!0,l[f]=y):i[f]=y}if(t.transform||(a||r?i.transform=qy(e.transform,n,c,r):i.transform&&(i.transform="none")),u){const{originX:f="50%",originY:p="50%",originZ:g=0}=l;i.transformOrigin=`${f} ${p} ${g}`}}const Wa=()=>({style:{},transform:{},transformOrigin:{},vars:{}});function qp(e,t,n){for(const r in t)!Ve(t[r])&&!Kp(r,n)&&(e[r]=t[r])}function r0({transformTemplate:e},t,n){return S.useMemo(()=>{const r=Wa();return Ha(r,t,{enableHardwareAcceleration:!n},e),Object.assign({},r.vars,r.style)},[t])}function i0(e,t,n){const r=e.style||{},i={};return qp(i,r,e),Object.assign(i,r0(e,t,n)),e.transformValues?e.transformValues(i):i}function o0(e,t,n){const r={},i=i0(e,t,n);return e.drag&&e.dragListener!==!1&&(r.draggable=!1,i.userSelect=i.WebkitUserSelect=i.WebkitTouchCallout="none",i.touchAction=e.drag===!0?"none":`pan-${e.drag==="x"?"y":"x"}`),e.tabIndex===void 0&&(e.onTap||e.onTapStart||e.whileTap)&&(r.tabIndex=0),r.style=i,r}const s0=new Set(["animate","exit","variants","initial","style","values","variants","transition","transformTemplate","transformValues","custom","inherit","onLayoutAnimationStart","onLayoutAnimationComplete","onLayoutMeasure","onBeforeLayoutMeasure","onAnimationStart","onAnimationComplete","onUpdate","onDragStart","onDrag","onDragEnd","onMeasureDragConstraints","onDirectionLock","onDragTransitionEnd","_dragX","_dragY","onHoverStart","onHoverEnd","onViewportEnter","onViewportLeave","ignoreStrict","viewport"]);function mo(e){return e.startsWith("while")||e.startsWith("drag")&&e!=="draggable"||e.startsWith("layout")||e.startsWith("onTap")||e.startsWith("onPan")||s0.has(e)}let Jp=e=>!mo(e);function l0(e){e&&(Jp=t=>t.startsWith("on")?!mo(t):e(t))}try{l0(require("@emotion/is-prop-valid").default)}catch{}function a0(e,t,n){const r={};for(const i in e)i==="values"&&typeof e.values=="object"||(Jp(i)||n===!0&&mo(i)||!t&&!mo(i)||e.draggable&&i.startsWith("onDrag"))&&(r[i]=e[i]);return r}function Dc(e,t,n){return typeof e=="string"?e:A.transform(t+n*e)}function u0(e,t,n){const r=Dc(t,e.x,e.width),i=Dc(n,e.y,e.height);return`${r} ${i}`}const c0={offset:"stroke-dashoffset",array:"stroke-dasharray"},f0={offset:"strokeDashoffset",array:"strokeDasharray"};function d0(e,t,n=1,r=0,i=!0){e.pathLength=1;const o=i?c0:f0;e[o.offset]=A.transform(-r);const s=A.transform(t),l=A.transform(n);e[o.array]=`${s} ${l}`}function Ga(e,{attrX:t,attrY:n,attrScale:r,originX:i,originY:o,pathLength:s,pathSpacing:l=1,pathOffset:a=0,...u},c,f,p){if(Ha(e,u,c,p),f){e.style.viewBox&&(e.attrs.viewBox=e.style.viewBox);return}e.attrs=e.style,e.style={};const{attrs:g,style:y,dimensions:v}=e;g.transform&&(v&&(y.transform=g.transform),delete g.transform),v&&(i!==void 0||o!==void 0||y.transform)&&(y.transformOrigin=u0(v,i!==void 0?i:.5,o!==void 0?o:.5)),t!==void 0&&(g.x=t),n!==void 0&&(g.y=n),r!==void 0&&(g.scale=r),s!==void 0&&d0(g,s,l,a,!1)}const bp=()=>({...Wa(),attrs:{}}),Ka=e=>typeof e=="string"&&e.toLowerCase()==="svg";function p0(e,t,n,r){const i=S.useMemo(()=>{const o=bp();return Ga(o,t,{enableHardwareAcceleration:!1},Ka(r),e.transformTemplate),{...o.attrs,style:{...o.style}}},[t]);if(e.style){const o={};qp(o,e.style,e),i.style={...o,...i.style}}return i}function h0(e=!1){return(n,r,i,{latestValues:o},s)=>{const a=($a(n)?p0:o0)(r,o,s,n),c={...a0(r,typeof n=="string",e),...a,ref:i},{children:f}=r,p=S.useMemo(()=>Ve(f)?f.get():f,[f]);return S.createElement(n,{...c,children:p})}}const Qa=e=>e.replace(/([a-z])([A-Z])/g,"$1-$2").toLowerCase();function eh(e,{style:t,vars:n},r,i){Object.assign(e.style,t,i&&i.getProjectionStyles(r));for(const o in n)e.style.setProperty(o,n[o])}const th=new Set(["baseFrequency","diffuseConstant","kernelMatrix","kernelUnitLength","keySplines","keyTimes","limitingConeAngle","markerHeight","markerWidth","numOctaves","targetX","targetY","surfaceScale","specularConstant","specularExponent","stdDeviation","tableValues","viewBox","gradientTransform","pathLength","startOffset","textLength","lengthAdjust"]);function nh(e,t,n,r){eh(e,t,void 0,r);for(const i in t.attrs)e.setAttribute(th.has(i)?i:Qa(i),t.attrs[i])}function Ya(e,t){const{style:n}=e,r={};for(const i in n)(Ve(n[i])||t.style&&Ve(t.style[i])||Kp(i,e))&&(r[i]=n[i]);return r}function rh(e,t){const n=Ya(e,t);for(const r in e)if(Ve(e[r])||Ve(t[r])){const i=ri.indexOf(r)!==-1?"attr"+r.charAt(0).toUpperCase()+r.substring(1):r;n[i]=e[r]}return n}function Xa(e,t,n,r={},i={}){return typeof t=="function"&&(t=t(n!==void 0?n:e.custom,r,i)),typeof t=="string"&&(t=e.variants&&e.variants[t]),typeof t=="function"&&(t=t(n!==void 0?n:e.custom,r,i)),t}function ih(e){const t=S.useRef(null);return t.current===null&&(t.current=e()),t.current}const go=e=>Array.isArray(e),m0=e=>!!(e&&typeof e=="object"&&e.mix&&e.toValue),g0=e=>go(e)?e[e.length-1]||0:e;function Bi(e){const t=Ve(e)?e.get():e;return m0(t)?t.toValue():t}function y0({scrapeMotionValuesFromProps:e,createRenderState:t,onMount:n},r,i,o){const s={latestValues:v0(r,i,o,e),renderState:t()};return n&&(s.mount=l=>n(r,l,s)),s}const oh=e=>(t,n)=>{const r=S.useContext(Io),i=S.useContext(zo),o=()=>y0(e,t,r,i);return n?o():ih(o)};function v0(e,t,n,r){const i={},o=r(e,{});for(const p in o)i[p]=Bi(o[p]);let{initial:s,animate:l}=e;const a=$o(e),u=Wp(e);t&&u&&!a&&e.inherit!==!1&&(s===void 0&&(s=t.initial),l===void 0&&(l=t.animate));let c=n?n.initial===!1:!1;c=c||s===!1;const f=c?l:s;return f&&typeof f!="boolean"&&!Uo(f)&&(Array.isArray(f)?f:[f]).forEach(g=>{const y=Xa(e,g);if(!y)return;const{transitionEnd:v,transition:T,...m}=y;for(const d in m){let h=m[d];if(Array.isArray(h)){const w=c?h.length-1:0;h=h[w]}h!==null&&(i[d]=h)}for(const d in v)i[d]=v[d]}),i}const w0={useVisualState:oh({scrapeMotionValuesFromProps:rh,createRenderState:bp,onMount:(e,t,{renderState:n,latestValues:r})=>{try{n.dimensions=typeof t.getBBox=="function"?t.getBBox():t.getBoundingClientRect()}catch{n.dimensions={x:0,y:0,width:0,height:0}}Ga(n,r,{enableHardwareAcceleration:!1},Ka(t.tagName),e.transformTemplate),nh(t,n)}})},x0={useVisualState:oh({scrapeMotionValuesFromProps:Ya,createRenderState:Wa})};function S0(e,{forwardMotionProps:t=!1},n,r){return{...$a(e)?w0:x0,preloadedFeatures:n,useRender:h0(t),createVisualElement:r,Component:e}}function ht(e,t,n,r={passive:!0}){return e.addEventListener(t,n,r),()=>e.removeEventListener(t,n)}const sh=e=>e.pointerType==="mouse"?typeof e.button!="number"||e.button<=0:e.isPrimary!==!1;function Wo(e,t="page"){return{point:{x:e[t+"X"],y:e[t+"Y"]}}}const k0=e=>t=>sh(t)&&e(t,Wo(t));function gt(e,t,n,r){return ht(e,t,k0(n),r)}const P0=(e,t)=>n=>t(e(n)),Ut=(...e)=>e.reduce(P0);function lh(e){let t=null;return()=>{const n=()=>{t=null};return t===null?(t=e,n):!1}}const Lc=lh("dragHorizontal"),Mc=lh("dragVertical");function ah(e){let t=!1;if(e==="y")t=Mc();else if(e==="x")t=Lc();else{const n=Lc(),r=Mc();n&&r?t=()=>{n(),r()}:(n&&n(),r&&r())}return t}function uh(){const e=ah(!0);return e?(e(),!1):!0}class Zt{constructor(t){this.isMounted=!1,this.node=t}update(){}}function C0(e){let t=[],n=[],r=0,i=!1,o=!1;const s=new WeakSet,l={schedule:(a,u=!1,c=!1)=>{const f=c&&i,p=f?t:n;return u&&s.add(a),p.indexOf(a)===-1&&(p.push(a),f&&i&&(r=t.length)),a},cancel:a=>{const u=n.indexOf(a);u!==-1&&n.splice(u,1),s.delete(a)},process:a=>{if(i){o=!0;return}if(i=!0,[t,n]=[n,t],n.length=0,r=t.length,r)for(let u=0;u<r;u++){const c=t[u];c(a),s.has(c)&&(l.schedule(c),e())}i=!1,o&&(o=!1,l.process(a))}};return l}const Y={delta:0,timestamp:0,isProcessing:!1},T0=40;let Rl=!0,Zr=!1;const Go=["read","update","preRender","render","postRender"],Gn=Go.reduce((e,t)=>(e[t]=C0(()=>Zr=!0),e),{}),E0=e=>Gn[e].process(Y),ch=e=>{Zr=!1,Y.delta=Rl?1e3/60:Math.max(Math.min(e-Y.timestamp,T0),1),Y.timestamp=e,Y.isProcessing=!0,Go.forEach(E0),Y.isProcessing=!1,Zr&&(Rl=!1,requestAnimationFrame(ch))},D0=()=>{Zr=!0,Rl=!0,Y.isProcessing||requestAnimationFrame(ch)},Q=Go.reduce((e,t)=>{const n=Gn[t];return e[t]=(r,i=!1,o=!1)=>(Zr||D0(),n.schedule(r,i,o)),e},{});function kt(e){Go.forEach(t=>Gn[t].cancel(e))}function Rc(e,t){const n="pointer"+(t?"enter":"leave"),r="onHover"+(t?"Start":"End"),i=(o,s)=>{if(o.type==="touch"||uh())return;const l=e.getProps();e.animationState&&l.whileHover&&e.animationState.setActive("whileHover",t),l[r]&&Q.update(()=>l[r](o,s))};return gt(e.current,n,i,{passive:!e.getProps()[r]})}class L0 extends Zt{mount(){this.unmount=Ut(Rc(this.node,!0),Rc(this.node,!1))}unmount(){}}class M0 extends Zt{constructor(){super(...arguments),this.isActive=!1}onFocus(){let t=!1;try{t=this.node.current.matches(":focus-visible")}catch{t=!0}!t||!this.node.animationState||(this.node.animationState.setActive("whileFocus",!0),this.isActive=!0)}onBlur(){!this.isActive||!this.node.animationState||(this.node.animationState.setActive("whileFocus",!1),this.isActive=!1)}mount(){this.unmount=Ut(ht(this.node.current,"focus",()=>this.onFocus()),ht(this.node.current,"blur",()=>this.onBlur()))}unmount(){}}const fh=(e,t)=>t?e===t?!0:fh(e,t.parentElement):!1,oe=e=>e;function ks(e,t){if(!t)return;const n=new PointerEvent("pointer"+e);t(n,Wo(n))}class R0 extends Zt{constructor(){super(...arguments),this.removeStartListeners=oe,this.removeEndListeners=oe,this.removeAccessibleListeners=oe,this.startPointerPress=(t,n)=>{if(this.removeEndListeners(),this.isPressing)return;const r=this.node.getProps(),o=gt(window,"pointerup",(l,a)=>{if(!this.checkPressEnd())return;const{onTap:u,onTapCancel:c}=this.node.getProps();Q.update(()=>{fh(this.node.current,l.target)?u&&u(l,a):c&&c(l,a)})},{passive:!(r.onTap||r.onPointerUp)}),s=gt(window,"pointercancel",(l,a)=>this.cancelPress(l,a),{passive:!(r.onTapCancel||r.onPointerCancel)});this.removeEndListeners=Ut(o,s),this.startPress(t,n)},this.startAccessiblePress=()=>{const t=o=>{if(o.key!=="Enter"||this.isPressing)return;const s=l=>{l.key!=="Enter"||!this.checkPressEnd()||ks("up",(a,u)=>{const{onTap:c}=this.node.getProps();c&&Q.update(()=>c(a,u))})};this.removeEndListeners(),this.removeEndListeners=ht(this.node.current,"keyup",s),ks("down",(l,a)=>{this.startPress(l,a)})},n=ht(this.node.current,"keydown",t),r=()=>{this.isPressing&&ks("cancel",(o,s)=>this.cancelPress(o,s))},i=ht(this.node.current,"blur",r);this.removeAccessibleListeners=Ut(n,i)}}startPress(t,n){this.isPressing=!0;const{onTapStart:r,whileTap:i}=this.node.getProps();i&&this.node.animationState&&this.node.animationState.setActive("whileTap",!0),r&&Q.update(()=>r(t,n))}checkPressEnd(){return this.removeEndListeners(),this.isPressing=!1,this.node.getProps().whileTap&&this.node.animationState&&this.node.animationState.setActive("whileTap",!1),!uh()}cancelPress(t,n){if(!this.checkPressEnd())return;const{onTapCancel:r}=this.node.getProps();r&&Q.update(()=>r(t,n))}mount(){const t=this.node.getProps(),n=gt(this.node.current,"pointerdown",this.startPointerPress,{passive:!(t.onTapStart||t.onPointerStart)}),r=ht(this.node.current,"focus",this.startAccessiblePress);this.removeStartListeners=Ut(n,r)}unmount(){this.removeStartListeners(),this.removeEndListeners(),this.removeAccessibleListeners()}}const Vl=new WeakMap,Ps=new WeakMap,V0=e=>{const t=Vl.get(e.target);t&&t(e)},A0=e=>{e.forEach(V0)};function _0({root:e,...t}){const n=e||document;Ps.has(n)||Ps.set(n,{});const r=Ps.get(n),i=JSON.stringify(t);return r[i]||(r[i]=new IntersectionObserver(A0,{root:e,...t})),r[i]}function N0(e,t,n){const r=_0(t);return Vl.set(e,n),r.observe(e),()=>{Vl.delete(e),r.unobserve(e)}}const O0={some:0,all:1};class j0 extends Zt{constructor(){super(...arguments),this.hasEnteredView=!1,this.isInView=!1}startObserver(){this.unmount();const{viewport:t={}}=this.node.getProps(),{root:n,margin:r,amount:i="some",once:o}=t,s={root:n?n.current:void 0,rootMargin:r,threshold:typeof i=="number"?i:O0[i]},l=a=>{const{isIntersecting:u}=a;if(this.isInView===u||(this.isInView=u,o&&!u&&this.hasEnteredView))return;u&&(this.hasEnteredView=!0),this.node.animationState&&this.node.animationState.setActive("whileInView",u);const{onViewportEnter:c,onViewportLeave:f}=this.node.getProps(),p=u?c:f;p&&p(a)};return N0(this.node.current,s,l)}mount(){this.startObserver()}update(){if(typeof IntersectionObserver>"u")return;const{props:t,prevProps:n}=this.node;["amount","margin","root"].some(F0(t,n))&&this.startObserver()}unmount(){}}function F0({viewport:e={}},{viewport:t={}}={}){return n=>e[n]!==t[n]}const I0={inView:{Feature:j0},tap:{Feature:R0},focus:{Feature:M0},hover:{Feature:L0}};function dh(e,t){if(!Array.isArray(t))return!1;const n=t.length;if(n!==e.length)return!1;for(let r=0;r<n;r++)if(t[r]!==e[r])return!1;return!0}function z0(e){const t={};return e.values.forEach((n,r)=>t[r]=n.get()),t}function B0(e){const t={};return e.values.forEach((n,r)=>t[r]=n.getVelocity()),t}function Ko(e,t,n){const r=e.getProps();return Xa(r,t,n!==void 0?n:r.custom,z0(e),B0(e))}const U0="framerAppearId",$0="data-"+Qa(U0);let H0=oe,Za=oe;const $t=e=>e*1e3,yt=e=>e/1e3,W0={current:!1},ph=e=>Array.isArray(e)&&typeof e[0]=="number";function hh(e){return!!(!e||typeof e=="string"&&mh[e]||ph(e)||Array.isArray(e)&&e.every(hh))}const yr=([e,t,n,r])=>`cubic-bezier(${e}, ${t}, ${n}, ${r})`,mh={linear:"linear",ease:"ease",easeIn:"ease-in",easeOut:"ease-out",easeInOut:"ease-in-out",circIn:yr([0,.65,.55,1]),circOut:yr([.55,0,1,.45]),backIn:yr([.31,.01,.66,-.59]),backOut:yr([.33,1.53,.69,.99])};function gh(e){if(e)return ph(e)?yr(e):Array.isArray(e)?e.map(gh):mh[e]}function G0(e,t,n,{delay:r=0,duration:i,repeat:o=0,repeatType:s="loop",ease:l,times:a}={}){const u={[t]:n};a&&(u.offset=a);const c=gh(l);return Array.isArray(c)&&(u.easing=c),e.animate(u,{delay:r,duration:i,easing:Array.isArray(c)?"linear":c,fill:"both",iterations:o+1,direction:s==="reverse"?"alternate":"normal"})}const Vc={waapi:()=>Object.hasOwnProperty.call(Element.prototype,"animate")},Cs={},yh={};for(const e in Vc)yh[e]=()=>(Cs[e]===void 0&&(Cs[e]=Vc[e]()),Cs[e]);function K0(e,{repeat:t,repeatType:n="loop"}){const r=t&&n!=="loop"&&t%2===1?0:e.length-1;return e[r]}const vh=(e,t,n)=>(((1-3*n+3*t)*e+(3*n-6*t))*e+3*t)*e,Q0=1e-7,Y0=12;function X0(e,t,n,r,i){let o,s,l=0;do s=t+(n-t)/2,o=vh(s,r,i)-e,o>0?n=s:t=s;while(Math.abs(o)>Q0&&++l<Y0);return s}function si(e,t,n,r){if(e===t&&n===r)return oe;const i=o=>X0(o,0,1,e,n);return o=>o===0||o===1?o:vh(i(o),t,r)}const Z0=si(.42,0,1,1),q0=si(0,0,.58,1),wh=si(.42,0,.58,1),J0=e=>Array.isArray(e)&&typeof e[0]!="number",xh=e=>t=>t<=.5?e(2*t)/2:(2-e(2*(1-t)))/2,Sh=e=>t=>1-e(1-t),kh=e=>1-Math.sin(Math.acos(e)),qa=Sh(kh),b0=xh(qa),Ph=si(.33,1.53,.69,.99),Ja=Sh(Ph),ev=xh(Ja),tv=e=>(e*=2)<1?.5*Ja(e):.5*(2-Math.pow(2,-10*(e-1))),nv={linear:oe,easeIn:Z0,easeInOut:wh,easeOut:q0,circIn:kh,circInOut:b0,circOut:qa,backIn:Ja,backInOut:ev,backOut:Ph,anticipate:tv},Ac=e=>{if(Array.isArray(e)){Za(e.length===4);const[t,n,r,i]=e;return si(t,n,r,i)}else if(typeof e=="string")return nv[e];return e},ba=(e,t)=>n=>!!(ii(n)&&e0.test(n)&&n.startsWith(e)||t&&Object.prototype.hasOwnProperty.call(n,t)),Ch=(e,t,n)=>r=>{if(!ii(r))return r;const[i,o,s,l]=r.match(Ho);return{[e]:parseFloat(i),[t]:parseFloat(o),[n]:parseFloat(s),alpha:l!==void 0?parseFloat(l):1}},rv=e=>Gt(0,255,e),Ts={...xn,transform:e=>Math.round(rv(e))},un={test:ba("rgb","red"),parse:Ch("red","green","blue"),transform:({red:e,green:t,blue:n,alpha:r=1})=>"rgba("+Ts.transform(e)+", "+Ts.transform(t)+", "+Ts.transform(n)+", "+Lr(Dr.transform(r))+")"};function iv(e){let t="",n="",r="",i="";return e.length>5?(t=e.substring(1,3),n=e.substring(3,5),r=e.substring(5,7),i=e.substring(7,9)):(t=e.substring(1,2),n=e.substring(2,3),r=e.substring(3,4),i=e.substring(4,5),t+=t,n+=n,r+=r,i+=i),{red:parseInt(t,16),green:parseInt(n,16),blue:parseInt(r,16),alpha:i?parseInt(i,16)/255:1}}const Al={test:ba("#"),parse:iv,transform:un.transform},jn={test:ba("hsl","hue"),parse:Ch("hue","saturation","lightness"),transform:({hue:e,saturation:t,lightness:n,alpha:r=1})=>"hsla("+Math.round(e)+", "+ut.transform(Lr(t))+", "+ut.transform(Lr(n))+", "+Lr(Dr.transform(r))+")"},xe={test:e=>un.test(e)||Al.test(e)||jn.test(e),parse:e=>un.test(e)?un.parse(e):jn.test(e)?jn.parse(e):Al.parse(e),transform:e=>ii(e)?e:e.hasOwnProperty("red")?un.transform(e):jn.transform(e)},Z=(e,t,n)=>-n*e+n*t+e;function Es(e,t,n){return n<0&&(n+=1),n>1&&(n-=1),n<1/6?e+(t-e)*6*n:n<1/2?t:n<2/3?e+(t-e)*(2/3-n)*6:e}function ov({hue:e,saturation:t,lightness:n,alpha:r}){e/=360,t/=100,n/=100;let i=0,o=0,s=0;if(!t)i=o=s=n;else{const l=n<.5?n*(1+t):n+t-n*t,a=2*n-l;i=Es(a,l,e+1/3),o=Es(a,l,e),s=Es(a,l,e-1/3)}return{red:Math.round(i*255),green:Math.round(o*255),blue:Math.round(s*255),alpha:r}}const Ds=(e,t,n)=>{const r=e*e;return Math.sqrt(Math.max(0,n*(t*t-r)+r))},sv=[Al,un,jn],lv=e=>sv.find(t=>t.test(e));function _c(e){const t=lv(e);let n=t.parse(e);return t===jn&&(n=ov(n)),n}const Th=(e,t)=>{const n=_c(e),r=_c(t),i={...n};return o=>(i.red=Ds(n.red,r.red,o),i.green=Ds(n.green,r.green,o),i.blue=Ds(n.blue,r.blue,o),i.alpha=Z(n.alpha,r.alpha,o),un.transform(i))};function av(e){var t,n;return isNaN(e)&&ii(e)&&(((t=e.match(Ho))===null||t===void 0?void 0:t.length)||0)+(((n=e.match(Xp))===null||n===void 0?void 0:n.length)||0)>0}const Eh={regex:Jy,countKey:"Vars",token:"${v}",parse:oe},Dh={regex:Xp,countKey:"Colors",token:"${c}",parse:xe.parse},Lh={regex:Ho,countKey:"Numbers",token:"${n}",parse:xn.parse};function Ls(e,{regex:t,countKey:n,token:r,parse:i}){const o=e.tokenised.match(t);o&&(e["num"+n]=o.length,e.tokenised=e.tokenised.replace(t,r),e.values.push(...o.map(i)))}function yo(e){const t=e.toString(),n={value:t,tokenised:t,values:[],numVars:0,numColors:0,numNumbers:0};return n.value.includes("var(--")&&Ls(n,Eh),Ls(n,Dh),Ls(n,Lh),n}function Mh(e){return yo(e).values}function Rh(e){const{values:t,numColors:n,numVars:r,tokenised:i}=yo(e),o=t.length;return s=>{let l=i;for(let a=0;a<o;a++)a<r?l=l.replace(Eh.token,s[a]):a<r+n?l=l.replace(Dh.token,xe.transform(s[a])):l=l.replace(Lh.token,Lr(s[a]));return l}}const uv=e=>typeof e=="number"?0:e;function cv(e){const t=Mh(e);return Rh(e)(t.map(uv))}const Kt={test:av,parse:Mh,createTransformer:Rh,getAnimatableNone:cv},Vh=(e,t)=>n=>`${n>0?t:e}`;function Ah(e,t){return typeof e=="number"?n=>Z(e,t,n):xe.test(e)?Th(e,t):e.startsWith("var(")?Vh(e,t):Nh(e,t)}const _h=(e,t)=>{const n=[...e],r=n.length,i=e.map((o,s)=>Ah(o,t[s]));return o=>{for(let s=0;s<r;s++)n[s]=i[s](o);return n}},fv=(e,t)=>{const n={...e,...t},r={};for(const i in n)e[i]!==void 0&&t[i]!==void 0&&(r[i]=Ah(e[i],t[i]));return i=>{for(const o in r)n[o]=r[o](i);return n}},Nh=(e,t)=>{const n=Kt.createTransformer(t),r=yo(e),i=yo(t);return r.numVars===i.numVars&&r.numColors===i.numColors&&r.numNumbers>=i.numNumbers?Ut(_h(r.values,i.values),n):Vh(e,t)},qr=(e,t,n)=>{const r=t-e;return r===0?1:(n-e)/r},Nc=(e,t)=>n=>Z(e,t,n);function dv(e){return typeof e=="number"?Nc:typeof e=="string"?xe.test(e)?Th:Nh:Array.isArray(e)?_h:typeof e=="object"?fv:Nc}function pv(e,t,n){const r=[],i=n||dv(e[0]),o=e.length-1;for(let s=0;s<o;s++){let l=i(e[s],e[s+1]);if(t){const a=Array.isArray(t)?t[s]||oe:t;l=Ut(a,l)}r.push(l)}return r}function Oh(e,t,{clamp:n=!0,ease:r,mixer:i}={}){const o=e.length;if(Za(o===t.length),o===1)return()=>t[0];e[0]>e[o-1]&&(e=[...e].reverse(),t=[...t].reverse());const s=pv(t,r,i),l=s.length,a=u=>{let c=0;if(l>1)for(;c<e.length-2&&!(u<e[c+1]);c++);const f=qr(e[c],e[c+1],u);return s[c](f)};return n?u=>a(Gt(e[0],e[o-1],u)):a}function hv(e,t){const n=e[e.length-1];for(let r=1;r<=t;r++){const i=qr(0,t,r);e.push(Z(n,1,i))}}function mv(e){const t=[0];return hv(t,e.length-1),t}function gv(e,t){return e.map(n=>n*t)}function yv(e,t){return e.map(()=>t||wh).splice(0,e.length-1)}function vo({duration:e=300,keyframes:t,times:n,ease:r="easeInOut"}){const i=J0(r)?r.map(Ac):Ac(r),o={done:!1,value:t[0]},s=gv(n&&n.length===t.length?n:mv(t),e),l=Oh(s,t,{ease:Array.isArray(i)?i:yv(t,i)});return{calculatedDuration:e,next:a=>(o.value=l(a),o.done=a>=e,o)}}function jh(e,t){return t?e*(1e3/t):0}const vv=5;function Fh(e,t,n){const r=Math.max(t-vv,0);return jh(n-e(r),t-r)}const Ms=.001,wv=.01,Oc=10,xv=.05,Sv=1;function kv({duration:e=800,bounce:t=.25,velocity:n=0,mass:r=1}){let i,o;H0(e<=$t(Oc));let s=1-t;s=Gt(xv,Sv,s),e=Gt(wv,Oc,yt(e)),s<1?(i=u=>{const c=u*s,f=c*e,p=c-n,g=_l(u,s),y=Math.exp(-f);return Ms-p/g*y},o=u=>{const f=u*s*e,p=f*n+n,g=Math.pow(s,2)*Math.pow(u,2)*e,y=Math.exp(-f),v=_l(Math.pow(u,2),s);return(-i(u)+Ms>0?-1:1)*((p-g)*y)/v}):(i=u=>{const c=Math.exp(-u*e),f=(u-n)*e+1;return-Ms+c*f},o=u=>{const c=Math.exp(-u*e),f=(n-u)*(e*e);return c*f});const l=5/e,a=Cv(i,o,l);if(e=$t(e),isNaN(a))return{stiffness:100,damping:10,duration:e};{const u=Math.pow(a,2)*r;return{stiffness:u,damping:s*2*Math.sqrt(r*u),duration:e}}}const Pv=12;function Cv(e,t,n){let r=n;for(let i=1;i<Pv;i++)r=r-e(r)/t(r);return r}function _l(e,t){return e*Math.sqrt(1-t*t)}const Tv=["duration","bounce"],Ev=["stiffness","damping","mass"];function jc(e,t){return t.some(n=>e[n]!==void 0)}function Dv(e){let t={velocity:0,stiffness:100,damping:10,mass:1,isResolvedFromDuration:!1,...e};if(!jc(e,Ev)&&jc(e,Tv)){const n=kv(e);t={...t,...n,velocity:0,mass:1},t.isResolvedFromDuration=!0}return t}function Ih({keyframes:e,restDelta:t,restSpeed:n,...r}){const i=e[0],o=e[e.length-1],s={done:!1,value:i},{stiffness:l,damping:a,mass:u,velocity:c,duration:f,isResolvedFromDuration:p}=Dv(r),g=c?-yt(c):0,y=a/(2*Math.sqrt(l*u)),v=o-i,T=yt(Math.sqrt(l/u)),m=Math.abs(v)<5;n||(n=m?.01:2),t||(t=m?.005:.5);let d;if(y<1){const h=_l(T,y);d=w=>{const x=Math.exp(-y*T*w);return o-x*((g+y*T*v)/h*Math.sin(h*w)+v*Math.cos(h*w))}}else if(y===1)d=h=>o-Math.exp(-T*h)*(v+(g+T*v)*h);else{const h=T*Math.sqrt(y*y-1);d=w=>{const x=Math.exp(-y*T*w),C=Math.min(h*w,300);return o-x*((g+y*T*v)*Math.sinh(C)+h*v*Math.cosh(C))/h}}return{calculatedDuration:p&&f||null,next:h=>{const w=d(h);if(p)s.done=h>=f;else{let x=g;h!==0&&(y<1?x=Fh(d,h,w):x=0);const C=Math.abs(x)<=n,E=Math.abs(o-w)<=t;s.done=C&&E}return s.value=s.done?o:w,s}}}function Fc({keyframes:e,velocity:t=0,power:n=.8,timeConstant:r=325,bounceDamping:i=10,bounceStiffness:o=500,modifyTarget:s,min:l,max:a,restDelta:u=.5,restSpeed:c}){const f=e[0],p={done:!1,value:f},g=k=>l!==void 0&&k<l||a!==void 0&&k>a,y=k=>l===void 0?a:a===void 0||Math.abs(l-k)<Math.abs(a-k)?l:a;let v=n*t;const T=f+v,m=s===void 0?T:s(T);m!==T&&(v=m-f);const d=k=>-v*Math.exp(-k/r),h=k=>m+d(k),w=k=>{const V=d(k),R=h(k);p.done=Math.abs(V)<=u,p.value=p.done?m:R};let x,C;const E=k=>{g(p.value)&&(x=k,C=Ih({keyframes:[p.value,y(p.value)],velocity:Fh(h,k,p.value),damping:i,stiffness:o,restDelta:u,restSpeed:c}))};return E(0),{calculatedDuration:null,next:k=>{let V=!1;return!C&&x===void 0&&(V=!0,w(k),E(k)),x!==void 0&&k>x?C.next(k-x):(!V&&w(k),p)}}}const Lv=e=>{const t=({timestamp:n})=>e(n);return{start:()=>Q.update(t,!0),stop:()=>kt(t),now:()=>Y.isProcessing?Y.timestamp:performance.now()}},Ic=2e4;function zc(e){let t=0;const n=50;let r=e.next(t);for(;!r.done&&t<Ic;)t+=n,r=e.next(t);return t>=Ic?1/0:t}const Mv={decay:Fc,inertia:Fc,tween:vo,keyframes:vo,spring:Ih};function wo({autoplay:e=!0,delay:t=0,driver:n=Lv,keyframes:r,type:i="keyframes",repeat:o=0,repeatDelay:s=0,repeatType:l="loop",onPlay:a,onStop:u,onComplete:c,onUpdate:f,...p}){let g=1,y=!1,v,T;const m=()=>{v&&v(),T=new Promise(D=>{v=D})};m();let d;const h=Mv[i]||vo;let w;h!==vo&&typeof r[0]!="number"&&(w=Oh([0,100],r,{clamp:!1}),r=[0,100]);const x=h({...p,keyframes:r});let C;l==="mirror"&&(C=h({...p,keyframes:[...r].reverse(),velocity:-(p.velocity||0)}));let E="idle",k=null,V=null,R=null;x.calculatedDuration===null&&o&&(x.calculatedDuration=zc(x));const{calculatedDuration:j}=x;let de=1/0,pe=1/0;j!==null&&(de=j+s,pe=de*(o+1)-s);let U=0;const $=D=>{if(V===null)return;g>0&&(V=Math.min(V,D)),g<0&&(V=Math.min(D-pe/g,V)),k!==null?U=k:U=Math.round(D-V)*g;const F=U-t*(g>=0?1:-1),Be=g>=0?F<0:F>pe;U=Math.max(F,0),E==="finished"&&k===null&&(U=pe);let ee=U,qt=x;if(o){const Jt=U/de;let li=Math.floor(Jt),bt=Jt%1;!bt&&Jt>=1&&(bt=1),bt===1&&li--,li=Math.min(li,o+1);const su=!!(li%2);su&&(l==="reverse"?(bt=1-bt,s&&(bt-=s/de)):l==="mirror"&&(qt=C));let lu=Gt(0,1,bt);U>pe&&(lu=l==="reverse"&&su?1:0),ee=lu*de}const me=Be?{done:!1,value:r[0]}:qt.next(ee);w&&(me.value=w(me.value));let{done:Ue}=me;!Be&&j!==null&&(Ue=g>=0?U>=pe:U<=0);const Xe=k===null&&(E==="finished"||E==="running"&&Ue);return f&&f(me.value),Xe&&L(),me},he=()=>{d&&d.stop(),d=void 0},Ae=()=>{E="idle",he(),m(),V=R=null},L=()=>{E="finished",c&&c(),he(),m()},_=()=>{if(y)return;d||(d=n($));const D=d.now();a&&a(),k!==null?V=D-k:(!V||E==="finished")&&(V=D),R=V,k=null,E="running",d.start()};e&&_();const N={then(D,F){return T.then(D,F)},get time(){return yt(U)},set time(D){D=$t(D),U=D,k!==null||!d||g===0?k=D:V=d.now()-D/g},get duration(){const D=x.calculatedDuration===null?zc(x):x.calculatedDuration;return yt(D)},get speed(){return g},set speed(D){D===g||!d||(g=D,N.time=yt(U))},get state(){return E},play:_,pause:()=>{E="paused",k=U},stop:()=>{y=!0,E!=="idle"&&(E="idle",u&&u(),Ae())},cancel:()=>{R!==null&&$(R),Ae()},complete:()=>{E="finished"},sample:D=>(V=0,$(D))};return N}const Rv=new Set(["opacity","clipPath","filter","transform","backgroundColor"]),Ei=10,Vv=2e4,Av=(e,t)=>t.type==="spring"||e==="backgroundColor"||!hh(t.ease);function _v(e,t,{onUpdate:n,onComplete:r,...i}){if(!(yh.waapi()&&Rv.has(t)&&!i.repeatDelay&&i.repeatType!=="mirror"&&i.damping!==0&&i.type!=="inertia"))return!1;let s=!1,l,a;const u=()=>{a=new Promise(m=>{l=m})};u();let{keyframes:c,duration:f=300,ease:p,times:g}=i;if(Av(t,i)){const m=wo({...i,repeat:0,delay:0});let d={done:!1,value:c[0]};const h=[];let w=0;for(;!d.done&&w<Vv;)d=m.sample(w),h.push(d.value),w+=Ei;g=void 0,c=h,f=w-Ei,p="linear"}const y=G0(e.owner.current,t,c,{...i,duration:f,ease:p,times:g}),v=()=>y.cancel(),T=()=>{Q.update(v),l(),u()};return y.onfinish=()=>{e.set(K0(c,i)),r&&r(),T()},{then(m,d){return a.then(m,d)},get time(){return yt(y.currentTime||0)},set time(m){y.currentTime=$t(m)},get speed(){return y.playbackRate},set speed(m){y.playbackRate=m},get duration(){return yt(f)},play:()=>{s||(y.play(),kt(v))},pause:()=>y.pause(),stop:()=>{if(s=!0,y.playState==="idle")return;const{currentTime:m}=y;if(m){const d=wo({...i,autoplay:!1});e.setWithVelocity(d.sample(m-Ei).value,d.sample(m).value,Ei)}T()},complete:()=>y.finish(),cancel:T}}function Nv({keyframes:e,delay:t,onUpdate:n,onComplete:r}){const i=()=>(n&&n(e[e.length-1]),r&&r(),{time:0,speed:1,duration:0,play:oe,pause:oe,stop:oe,then:o=>(o(),Promise.resolve()),cancel:oe,complete:oe});return t?wo({keyframes:[0,1],duration:0,delay:t,onComplete:i}):i()}const Ov={type:"spring",stiffness:500,damping:25,restSpeed:10},jv=e=>({type:"spring",stiffness:550,damping:e===0?2*Math.sqrt(550):30,restSpeed:10}),Fv={type:"keyframes",duration:.8},Iv={type:"keyframes",ease:[.25,.1,.35,1],duration:.3},zv=(e,{keyframes:t})=>t.length>2?Fv:wn.has(e)?e.startsWith("scale")?jv(t[1]):Ov:Iv,Nl=(e,t)=>e==="zIndex"?!1:!!(typeof t=="number"||Array.isArray(t)||typeof t=="string"&&(Kt.test(t)||t==="0")&&!t.startsWith("url(")),Bv=new Set(["brightness","contrast","saturate","opacity"]);function Uv(e){const[t,n]=e.slice(0,-1).split("(");if(t==="drop-shadow")return e;const[r]=n.match(Ho)||[];if(!r)return e;const i=n.replace(r,"");let o=Bv.has(t)?1:0;return r!==n&&(o*=100),t+"("+o+i+")"}const $v=/([a-z-]*)\(.*?\)/g,Ol={...Kt,getAnimatableNone:e=>{const t=e.match($v);return t?t.map(Uv).join(" "):e}},Hv={...Zp,color:xe,backgroundColor:xe,outlineColor:xe,fill:xe,stroke:xe,borderColor:xe,borderTopColor:xe,borderRightColor:xe,borderBottomColor:xe,borderLeftColor:xe,filter:Ol,WebkitFilter:Ol},eu=e=>Hv[e];function zh(e,t){let n=eu(e);return n!==Ol&&(n=Kt),n.getAnimatableNone?n.getAnimatableNone(t):void 0}const Bh=e=>/^0[^.\s]+$/.test(e);function Wv(e){if(typeof e=="number")return e===0;if(e!==null)return e==="none"||e==="0"||Bh(e)}function Gv(e,t,n,r){const i=Nl(t,n);let o;Array.isArray(n)?o=[...n]:o=[null,n];const s=r.from!==void 0?r.from:e.get();let l;const a=[];for(let u=0;u<o.length;u++)o[u]===null&&(o[u]=u===0?s:o[u-1]),Wv(o[u])&&a.push(u),typeof o[u]=="string"&&o[u]!=="none"&&o[u]!=="0"&&(l=o[u]);if(i&&a.length&&l)for(let u=0;u<a.length;u++){const c=a[u];o[c]=zh(t,l)}return o}function Kv({when:e,delay:t,delayChildren:n,staggerChildren:r,staggerDirection:i,repeat:o,repeatType:s,repeatDelay:l,from:a,elapsed:u,...c}){return!!Object.keys(c).length}function Uh(e,t){return e[t]||e.default||e}const tu=(e,t,n,r={})=>i=>{const o=Uh(r,e)||{},s=o.delay||r.delay||0;let{elapsed:l=0}=r;l=l-$t(s);const a=Gv(t,e,n,o),u=a[0],c=a[a.length-1],f=Nl(e,u),p=Nl(e,c);let g={keyframes:a,velocity:t.getVelocity(),ease:"easeOut",...o,delay:-l,onUpdate:y=>{t.set(y),o.onUpdate&&o.onUpdate(y)},onComplete:()=>{i(),o.onComplete&&o.onComplete()}};if(Kv(o)||(g={...g,...zv(e,g)}),g.duration&&(g.duration=$t(g.duration)),g.repeatDelay&&(g.repeatDelay=$t(g.repeatDelay)),!f||!p||W0.current||o.type===!1)return Nv(g);if(t.owner&&t.owner.current instanceof HTMLElement&&!t.owner.getProps().onUpdate){const y=_v(t,e,g);if(y)return y}return wo(g)};function xo(e){return!!(Ve(e)&&e.add)}const Qv=e=>/^\-?\d*\.?\d+$/.test(e);function nu(e,t){e.indexOf(t)===-1&&e.push(t)}function ru(e,t){const n=e.indexOf(t);n>-1&&e.splice(n,1)}class iu{constructor(){this.subscriptions=[]}add(t){return nu(this.subscriptions,t),()=>ru(this.subscriptions,t)}notify(t,n,r){const i=this.subscriptions.length;if(i)if(i===1)this.subscriptions[0](t,n,r);else for(let o=0;o<i;o++){const s=this.subscriptions[o];s&&s(t,n,r)}}getSize(){return this.subscriptions.length}clear(){this.subscriptions.length=0}}const Yv=e=>!isNaN(parseFloat(e));class Xv{constructor(t,n={}){this.version="10.12.18",this.timeDelta=0,this.lastUpdated=0,this.canTrackVelocity=!1,this.events={},this.updateAndNotify=(r,i=!0)=>{this.prev=this.current,this.current=r;const{delta:o,timestamp:s}=Y;this.lastUpdated!==s&&(this.timeDelta=o,this.lastUpdated=s,Q.postRender(this.scheduleVelocityCheck)),this.prev!==this.current&&this.events.change&&this.events.change.notify(this.current),this.events.velocityChange&&this.events.velocityChange.notify(this.getVelocity()),i&&this.events.renderRequest&&this.events.renderRequest.notify(this.current)},this.scheduleVelocityCheck=()=>Q.postRender(this.velocityCheck),this.velocityCheck=({timestamp:r})=>{r!==this.lastUpdated&&(this.prev=this.current,this.events.velocityChange&&this.events.velocityChange.notify(this.getVelocity()))},this.hasAnimated=!1,this.prev=this.current=t,this.canTrackVelocity=Yv(this.current),this.owner=n.owner}onChange(t){return this.on("change",t)}on(t,n){this.events[t]||(this.events[t]=new iu);const r=this.events[t].add(n);return t==="change"?()=>{r(),Q.read(()=>{this.events.change.getSize()||this.stop()})}:r}clearListeners(){for(const t in this.events)this.events[t].clear()}attach(t,n){this.passiveEffect=t,this.stopPassiveEffect=n}set(t,n=!0){!n||!this.passiveEffect?this.updateAndNotify(t,n):this.passiveEffect(t,this.updateAndNotify)}setWithVelocity(t,n,r){this.set(n),this.prev=t,this.timeDelta=r}jump(t){this.updateAndNotify(t),this.prev=t,this.stop(),this.stopPassiveEffect&&this.stopPassiveEffect()}get(){return this.current}getPrevious(){return this.prev}getVelocity(){return this.canTrackVelocity?jh(parseFloat(this.current)-parseFloat(this.prev),this.timeDelta):0}start(t){return this.stop(),new Promise(n=>{this.hasAnimated=!0,this.animation=t(n),this.events.animationStart&&this.events.animationStart.notify()}).then(()=>{this.events.animationComplete&&this.events.animationComplete.notify(),this.clearAnimation()})}stop(){this.animation&&(this.animation.stop(),this.events.animationCancel&&this.events.animationCancel.notify()),this.clearAnimation()}isAnimating(){return!!this.animation}clearAnimation(){delete this.animation}destroy(){this.clearListeners(),this.stop(),this.stopPassiveEffect&&this.stopPassiveEffect()}}function bn(e,t){return new Xv(e,t)}const $h=e=>t=>t.test(e),Zv={test:e=>e==="auto",parse:e=>e},Hh=[xn,A,ut,Tt,n0,t0,Zv],fr=e=>Hh.find($h(e)),qv=[...Hh,xe,Kt],Jv=e=>qv.find($h(e));function bv(e,t,n){e.hasValue(t)?e.getValue(t).set(n):e.addValue(t,bn(n))}function e1(e,t){const n=Ko(e,t);let{transitionEnd:r={},transition:i={},...o}=n?e.makeTargetAnimatable(n,!1):{};o={...o,...r};for(const s in o){const l=g0(o[s]);bv(e,s,l)}}function t1(e,t,n){var r,i;const o=Object.keys(t).filter(l=>!e.hasValue(l)),s=o.length;if(s)for(let l=0;l<s;l++){const a=o[l],u=t[a];let c=null;Array.isArray(u)&&(c=u[0]),c===null&&(c=(i=(r=n[a])!==null&&r!==void 0?r:e.readValue(a))!==null&&i!==void 0?i:t[a]),c!=null&&(typeof c=="string"&&(Qv(c)||Bh(c))?c=parseFloat(c):!Jv(c)&&Kt.test(u)&&(c=zh(a,u)),e.addValue(a,bn(c,{owner:e})),n[a]===void 0&&(n[a]=c),c!==null&&e.setBaseTarget(a,c))}}function n1(e,t){return t?(t[e]||t.default||t).from:void 0}function r1(e,t,n){const r={};for(const i in e){const o=n1(i,t);if(o!==void 0)r[i]=o;else{const s=n.getValue(i);s&&(r[i]=s.get())}}return r}function i1({protectedKeys:e,needsAnimating:t},n){const r=e.hasOwnProperty(n)&&t[n]!==!0;return t[n]=!1,r}function Wh(e,t,{delay:n=0,transitionOverride:r,type:i}={}){let{transition:o=e.getDefaultTransition(),transitionEnd:s,...l}=e.makeTargetAnimatable(t);const a=e.getValue("willChange");r&&(o=r);const u=[],c=i&&e.animationState&&e.animationState.getState()[i];for(const f in l){const p=e.getValue(f),g=l[f];if(!p||g===void 0||c&&i1(c,f))continue;const y={delay:n,elapsed:0,...o};if(window.HandoffAppearAnimations&&!p.hasAnimated){const T=e.getProps()[$0];T&&(y.elapsed=window.HandoffAppearAnimations(T,f,p,Q))}p.start(tu(f,p,g,e.shouldReduceMotion&&wn.has(f)?{type:!1}:y));const v=p.animation;xo(a)&&(a.add(f),v.then(()=>a.remove(f))),u.push(v)}return s&&Promise.all(u).then(()=>{s&&e1(e,s)}),u}function jl(e,t,n={}){const r=Ko(e,t,n.custom);let{transition:i=e.getDefaultTransition()||{}}=r||{};n.transitionOverride&&(i=n.transitionOverride);const o=r?()=>Promise.all(Wh(e,r,n)):()=>Promise.resolve(),s=e.variantChildren&&e.variantChildren.size?(a=0)=>{const{delayChildren:u=0,staggerChildren:c,staggerDirection:f}=i;return o1(e,t,u+a,c,f,n)}:()=>Promise.resolve(),{when:l}=i;if(l){const[a,u]=l==="beforeChildren"?[o,s]:[s,o];return a().then(()=>u())}else return Promise.all([o(),s(n.delay)])}function o1(e,t,n=0,r=0,i=1,o){const s=[],l=(e.variantChildren.size-1)*r,a=i===1?(u=0)=>u*r:(u=0)=>l-u*r;return Array.from(e.variantChildren).sort(s1).forEach((u,c)=>{u.notify("AnimationStart",t),s.push(jl(u,t,{...o,delay:n+a(c)}).then(()=>u.notify("AnimationComplete",t)))}),Promise.all(s)}function s1(e,t){return e.sortNodePosition(t)}function l1(e,t,n={}){e.notify("AnimationStart",t);let r;if(Array.isArray(t)){const i=t.map(o=>jl(e,o,n));r=Promise.all(i)}else if(typeof t=="string")r=jl(e,t,n);else{const i=typeof t=="function"?Ko(e,t,n.custom):t;r=Promise.all(Wh(e,i,n))}return r.then(()=>e.notify("AnimationComplete",t))}const a1=[...za].reverse(),u1=za.length;function c1(e){return t=>Promise.all(t.map(({animation:n,options:r})=>l1(e,n,r)))}function f1(e){let t=c1(e);const n=p1();let r=!0;const i=(a,u)=>{const c=Ko(e,u);if(c){const{transition:f,transitionEnd:p,...g}=c;a={...a,...g,...p}}return a};function o(a){t=a(e)}function s(a,u){const c=e.getProps(),f=e.getVariantContext(!0)||{},p=[],g=new Set;let y={},v=1/0;for(let m=0;m<u1;m++){const d=a1[m],h=n[d],w=c[d]!==void 0?c[d]:f[d],x=Yr(w),C=d===u?h.isActive:null;C===!1&&(v=m);let E=w===f[d]&&w!==c[d]&&x;if(E&&r&&e.manuallyAnimateOnMount&&(E=!1),h.protectedKeys={...y},!h.isActive&&C===null||!w&&!h.prevProp||Uo(w)||typeof w=="boolean")continue;const k=d1(h.prevProp,w);let V=k||d===u&&h.isActive&&!E&&x||m>v&&x;const R=Array.isArray(w)?w:[w];let j=R.reduce(i,{});C===!1&&(j={});const{prevResolvedValues:de={}}=h,pe={...de,...j},U=$=>{V=!0,g.delete($),h.needsAnimating[$]=!0};for(const $ in pe){const he=j[$],Ae=de[$];y.hasOwnProperty($)||(he!==Ae?go(he)&&go(Ae)?!dh(he,Ae)||k?U($):h.protectedKeys[$]=!0:he!==void 0?U($):g.add($):he!==void 0&&g.has($)?U($):h.protectedKeys[$]=!0)}h.prevProp=w,h.prevResolvedValues=j,h.isActive&&(y={...y,...j}),r&&e.blockInitialAnimation&&(V=!1),V&&!E&&p.push(...R.map($=>({animation:$,options:{type:d,...a}})))}if(g.size){const m={};g.forEach(d=>{const h=e.getBaseTarget(d);h!==void 0&&(m[d]=h)}),p.push({animation:m})}let T=!!p.length;return r&&c.initial===!1&&!e.manuallyAnimateOnMount&&(T=!1),r=!1,T?t(p):Promise.resolve()}function l(a,u,c){var f;if(n[a].isActive===u)return Promise.resolve();(f=e.variantChildren)===null||f===void 0||f.forEach(g=>{var y;return(y=g.animationState)===null||y===void 0?void 0:y.setActive(a,u)}),n[a].isActive=u;const p=s(c,a);for(const g in n)n[g].protectedKeys={};return p}return{animateChanges:s,setActive:l,setAnimateFunction:o,getState:()=>n}}function d1(e,t){return typeof t=="string"?t!==e:Array.isArray(t)?!dh(t,e):!1}function en(e=!1){return{isActive:e,protectedKeys:{},needsAnimating:{},prevResolvedValues:{}}}function p1(){return{animate:en(!0),whileInView:en(),whileHover:en(),whileTap:en(),whileDrag:en(),whileFocus:en(),exit:en()}}class h1 extends Zt{constructor(t){super(t),t.animationState||(t.animationState=f1(t))}updateAnimationControlsSubscription(){const{animate:t}=this.node.getProps();this.unmount(),Uo(t)&&(this.unmount=t.subscribe(this.node))}mount(){this.updateAnimationControlsSubscription()}update(){const{animate:t}=this.node.getProps(),{animate:n}=this.node.prevProps||{};t!==n&&this.updateAnimationControlsSubscription()}unmount(){}}let m1=0;class g1 extends Zt{constructor(){super(...arguments),this.id=m1++}update(){if(!this.node.presenceContext)return;const{isPresent:t,onExitComplete:n,custom:r}=this.node.presenceContext,{isPresent:i}=this.node.prevPresenceContext||{};if(!this.node.animationState||t===i)return;const o=this.node.animationState.setActive("exit",!t,{custom:r??this.node.getProps().custom});n&&!t&&o.then(()=>n(this.id))}mount(){const{register:t}=this.node.presenceContext||{};t&&(this.unmount=t(this.id))}unmount(){}}const y1={animation:{Feature:h1},exit:{Feature:g1}},Bc=(e,t)=>Math.abs(e-t);function v1(e,t){const n=Bc(e.x,t.x),r=Bc(e.y,t.y);return Math.sqrt(n**2+r**2)}class Gh{constructor(t,n,{transformPagePoint:r}={}){if(this.startEvent=null,this.lastMoveEvent=null,this.lastMoveEventInfo=null,this.handlers={},this.updatePoint=()=>{if(!(this.lastMoveEvent&&this.lastMoveEventInfo))return;const u=Vs(this.lastMoveEventInfo,this.history),c=this.startEvent!==null,f=v1(u.offset,{x:0,y:0})>=3;if(!c&&!f)return;const{point:p}=u,{timestamp:g}=Y;this.history.push({...p,timestamp:g});const{onStart:y,onMove:v}=this.handlers;c||(y&&y(this.lastMoveEvent,u),this.startEvent=this.lastMoveEvent),v&&v(this.lastMoveEvent,u)},this.handlePointerMove=(u,c)=>{this.lastMoveEvent=u,this.lastMoveEventInfo=Rs(c,this.transformPagePoint),Q.update(this.updatePoint,!0)},this.handlePointerUp=(u,c)=>{if(this.end(),!(this.lastMoveEvent&&this.lastMoveEventInfo))return;const{onEnd:f,onSessionEnd:p}=this.handlers,g=Vs(u.type==="pointercancel"?this.lastMoveEventInfo:Rs(c,this.transformPagePoint),this.history);this.startEvent&&f&&f(u,g),p&&p(u,g)},!sh(t))return;this.handlers=n,this.transformPagePoint=r;const i=Wo(t),o=Rs(i,this.transformPagePoint),{point:s}=o,{timestamp:l}=Y;this.history=[{...s,timestamp:l}];const{onSessionStart:a}=n;a&&a(t,Vs(o,this.history)),this.removeListeners=Ut(gt(window,"pointermove",this.handlePointerMove),gt(window,"pointerup",this.handlePointerUp),gt(window,"pointercancel",this.handlePointerUp))}updateHandlers(t){this.handlers=t}end(){this.removeListeners&&this.removeListeners(),kt(this.updatePoint)}}function Rs(e,t){return t?{point:t(e.point)}:e}function Uc(e,t){return{x:e.x-t.x,y:e.y-t.y}}function Vs({point:e},t){return{point:e,delta:Uc(e,Kh(t)),offset:Uc(e,w1(t)),velocity:x1(t,.1)}}function w1(e){return e[0]}function Kh(e){return e[e.length-1]}function x1(e,t){if(e.length<2)return{x:0,y:0};let n=e.length-1,r=null;const i=Kh(e);for(;n>=0&&(r=e[n],!(i.timestamp-r.timestamp>$t(t)));)n--;if(!r)return{x:0,y:0};const o=yt(i.timestamp-r.timestamp);if(o===0)return{x:0,y:0};const s={x:(i.x-r.x)/o,y:(i.y-r.y)/o};return s.x===1/0&&(s.x=0),s.y===1/0&&(s.y=0),s}function Fe(e){return e.max-e.min}function Fl(e,t=0,n=.01){return Math.abs(e-t)<=n}function $c(e,t,n,r=.5){e.origin=r,e.originPoint=Z(t.min,t.max,e.origin),e.scale=Fe(n)/Fe(t),(Fl(e.scale,1,1e-4)||isNaN(e.scale))&&(e.scale=1),e.translate=Z(n.min,n.max,e.origin)-e.originPoint,(Fl(e.translate)||isNaN(e.translate))&&(e.translate=0)}function Mr(e,t,n,r){$c(e.x,t.x,n.x,r?r.originX:void 0),$c(e.y,t.y,n.y,r?r.originY:void 0)}function Hc(e,t,n){e.min=n.min+t.min,e.max=e.min+Fe(t)}function S1(e,t,n){Hc(e.x,t.x,n.x),Hc(e.y,t.y,n.y)}function Wc(e,t,n){e.min=t.min-n.min,e.max=e.min+Fe(t)}function Rr(e,t,n){Wc(e.x,t.x,n.x),Wc(e.y,t.y,n.y)}function k1(e,{min:t,max:n},r){return t!==void 0&&e<t?e=r?Z(t,e,r.min):Math.max(e,t):n!==void 0&&e>n&&(e=r?Z(n,e,r.max):Math.min(e,n)),e}function Gc(e,t,n){return{min:t!==void 0?e.min+t:void 0,max:n!==void 0?e.max+n-(e.max-e.min):void 0}}function P1(e,{top:t,left:n,bottom:r,right:i}){return{x:Gc(e.x,n,i),y:Gc(e.y,t,r)}}function Kc(e,t){let n=t.min-e.min,r=t.max-e.max;return t.max-t.min<e.max-e.min&&([n,r]=[r,n]),{min:n,max:r}}function C1(e,t){return{x:Kc(e.x,t.x),y:Kc(e.y,t.y)}}function T1(e,t){let n=.5;const r=Fe(e),i=Fe(t);return i>r?n=qr(t.min,t.max-r,e.min):r>i&&(n=qr(e.min,e.max-i,t.min)),Gt(0,1,n)}function E1(e,t){const n={};return t.min!==void 0&&(n.min=t.min-e.min),t.max!==void 0&&(n.max=t.max-e.min),n}const Il=.35;function D1(e=Il){return e===!1?e=0:e===!0&&(e=Il),{x:Qc(e,"left","right"),y:Qc(e,"top","bottom")}}function Qc(e,t,n){return{min:Yc(e,t),max:Yc(e,n)}}function Yc(e,t){return typeof e=="number"?e:e[t]||0}const Xc=()=>({translate:0,scale:1,origin:0,originPoint:0}),Fn=()=>({x:Xc(),y:Xc()}),Zc=()=>({min:0,max:0}),ne=()=>({x:Zc(),y:Zc()});function ot(e){return[e("x"),e("y")]}function Qh({top:e,left:t,right:n,bottom:r}){return{x:{min:t,max:n},y:{min:e,max:r}}}function L1({x:e,y:t}){return{top:t.min,right:e.max,bottom:t.max,left:e.min}}function M1(e,t){if(!t)return e;const n=t({x:e.left,y:e.top}),r=t({x:e.right,y:e.bottom});return{top:n.y,left:n.x,bottom:r.y,right:r.x}}function As(e){return e===void 0||e===1}function zl({scale:e,scaleX:t,scaleY:n}){return!As(e)||!As(t)||!As(n)}function rn(e){return zl(e)||Yh(e)||e.z||e.rotate||e.rotateX||e.rotateY}function Yh(e){return qc(e.x)||qc(e.y)}function qc(e){return e&&e!=="0%"}function So(e,t,n){const r=e-n,i=t*r;return n+i}function Jc(e,t,n,r,i){return i!==void 0&&(e=So(e,i,r)),So(e,n,r)+t}function Bl(e,t=0,n=1,r,i){e.min=Jc(e.min,t,n,r,i),e.max=Jc(e.max,t,n,r,i)}function Xh(e,{x:t,y:n}){Bl(e.x,t.translate,t.scale,t.originPoint),Bl(e.y,n.translate,n.scale,n.originPoint)}function R1(e,t,n,r=!1){const i=n.length;if(!i)return;t.x=t.y=1;let o,s;for(let l=0;l<i;l++){o=n[l],s=o.projectionDelta;const a=o.instance;a&&a.style&&a.style.display==="contents"||(r&&o.options.layoutScroll&&o.scroll&&o!==o.root&&In(e,{x:-o.scroll.offset.x,y:-o.scroll.offset.y}),s&&(t.x*=s.x.scale,t.y*=s.y.scale,Xh(e,s)),r&&rn(o.latestValues)&&In(e,o.latestValues))}t.x=bc(t.x),t.y=bc(t.y)}function bc(e){return Number.isInteger(e)||e>1.0000000000001||e<.999999999999?e:1}function Lt(e,t){e.min=e.min+t,e.max=e.max+t}function ef(e,t,[n,r,i]){const o=t[i]!==void 0?t[i]:.5,s=Z(e.min,e.max,o);Bl(e,t[n],t[r],s,t.scale)}const V1=["x","scaleX","originX"],A1=["y","scaleY","originY"];function In(e,t){ef(e.x,t,V1),ef(e.y,t,A1)}function Zh(e,t){return Qh(M1(e.getBoundingClientRect(),t))}function _1(e,t,n){const r=Zh(e,n),{scroll:i}=t;return i&&(Lt(r.x,i.offset.x),Lt(r.y,i.offset.y)),r}const N1=new WeakMap;class O1{constructor(t){this.openGlobalLock=null,this.isDragging=!1,this.currentDirection=null,this.originPoint={x:0,y:0},this.constraints=!1,this.hasMutatedConstraints=!1,this.elastic=ne(),this.visualElement=t}start(t,{snapToCursor:n=!1}={}){const{presenceContext:r}=this.visualElement;if(r&&r.isPresent===!1)return;const i=a=>{this.stopAnimation(),n&&this.snapToCursor(Wo(a,"page").point)},o=(a,u)=>{const{drag:c,dragPropagation:f,onDragStart:p}=this.getProps();if(c&&!f&&(this.openGlobalLock&&this.openGlobalLock(),this.openGlobalLock=ah(c),!this.openGlobalLock))return;this.isDragging=!0,this.currentDirection=null,this.resolveConstraints(),this.visualElement.projection&&(this.visualElement.projection.isAnimationBlocked=!0,this.visualElement.projection.target=void 0),ot(y=>{let v=this.getAxisMotionValue(y).get()||0;if(ut.test(v)){const{projection:T}=this.visualElement;if(T&&T.layout){const m=T.layout.layoutBox[y];m&&(v=Fe(m)*(parseFloat(v)/100))}}this.originPoint[y]=v}),p&&Q.update(()=>p(a,u),!1,!0);const{animationState:g}=this.visualElement;g&&g.setActive("whileDrag",!0)},s=(a,u)=>{const{dragPropagation:c,dragDirectionLock:f,onDirectionLock:p,onDrag:g}=this.getProps();if(!c&&!this.openGlobalLock)return;const{offset:y}=u;if(f&&this.currentDirection===null){this.currentDirection=j1(y),this.currentDirection!==null&&p&&p(this.currentDirection);return}this.updateAxis("x",u.point,y),this.updateAxis("y",u.point,y),this.visualElement.render(),g&&g(a,u)},l=(a,u)=>this.stop(a,u);this.panSession=new Gh(t,{onSessionStart:i,onStart:o,onMove:s,onSessionEnd:l},{transformPagePoint:this.visualElement.getTransformPagePoint()})}stop(t,n){const r=this.isDragging;if(this.cancel(),!r)return;const{velocity:i}=n;this.startAnimation(i);const{onDragEnd:o}=this.getProps();o&&Q.update(()=>o(t,n))}cancel(){this.isDragging=!1;const{projection:t,animationState:n}=this.visualElement;t&&(t.isAnimationBlocked=!1),this.panSession&&this.panSession.end(),this.panSession=void 0;const{dragPropagation:r}=this.getProps();!r&&this.openGlobalLock&&(this.openGlobalLock(),this.openGlobalLock=null),n&&n.setActive("whileDrag",!1)}updateAxis(t,n,r){const{drag:i}=this.getProps();if(!r||!Di(t,i,this.currentDirection))return;const o=this.getAxisMotionValue(t);let s=this.originPoint[t]+r[t];this.constraints&&this.constraints[t]&&(s=k1(s,this.constraints[t],this.elastic[t])),o.set(s)}resolveConstraints(){const{dragConstraints:t,dragElastic:n}=this.getProps(),{layout:r}=this.visualElement.projection||{},i=this.constraints;t&&On(t)?this.constraints||(this.constraints=this.resolveRefConstraints()):t&&r?this.constraints=P1(r.layoutBox,t):this.constraints=!1,this.elastic=D1(n),i!==this.constraints&&r&&this.constraints&&!this.hasMutatedConstraints&&ot(o=>{this.getAxisMotionValue(o)&&(this.constraints[o]=E1(r.layoutBox[o],this.constraints[o]))})}resolveRefConstraints(){const{dragConstraints:t,onMeasureDragConstraints:n}=this.getProps();if(!t||!On(t))return!1;const r=t.current,{projection:i}=this.visualElement;if(!i||!i.layout)return!1;const o=_1(r,i.root,this.visualElement.getTransformPagePoint());let s=C1(i.layout.layoutBox,o);if(n){const l=n(L1(s));this.hasMutatedConstraints=!!l,l&&(s=Qh(l))}return s}startAnimation(t){const{drag:n,dragMomentum:r,dragElastic:i,dragTransition:o,dragSnapToOrigin:s,onDragTransitionEnd:l}=this.getProps(),a=this.constraints||{},u=ot(c=>{if(!Di(c,n,this.currentDirection))return;let f=a&&a[c]||{};s&&(f={min:0,max:0});const p=i?200:1e6,g=i?40:1e7,y={type:"inertia",velocity:r?t[c]:0,bounceStiffness:p,bounceDamping:g,timeConstant:750,restDelta:1,restSpeed:10,...o,...f};return this.startAxisValueAnimation(c,y)});return Promise.all(u).then(l)}startAxisValueAnimation(t,n){const r=this.getAxisMotionValue(t);return r.start(tu(t,r,0,n))}stopAnimation(){ot(t=>this.getAxisMotionValue(t).stop())}getAxisMotionValue(t){const n="_drag"+t.toUpperCase(),r=this.visualElement.getProps(),i=r[n];return i||this.visualElement.getValue(t,(r.initial?r.initial[t]:void 0)||0)}snapToCursor(t){ot(n=>{const{drag:r}=this.getProps();if(!Di(n,r,this.currentDirection))return;const{projection:i}=this.visualElement,o=this.getAxisMotionValue(n);if(i&&i.layout){const{min:s,max:l}=i.layout.layoutBox[n];o.set(t[n]-Z(s,l,.5))}})}scalePositionWithinConstraints(){if(!this.visualElement.current)return;const{drag:t,dragConstraints:n}=this.getProps(),{projection:r}=this.visualElement;if(!On(n)||!r||!this.constraints)return;this.stopAnimation();const i={x:0,y:0};ot(s=>{const l=this.getAxisMotionValue(s);if(l){const a=l.get();i[s]=T1({min:a,max:a},this.constraints[s])}});const{transformTemplate:o}=this.visualElement.getProps();this.visualElement.current.style.transform=o?o({},""):"none",r.root&&r.root.updateScroll(),r.updateLayout(),this.resolveConstraints(),ot(s=>{if(!Di(s,t,null))return;const l=this.getAxisMotionValue(s),{min:a,max:u}=this.constraints[s];l.set(Z(a,u,i[s]))})}addListeners(){if(!this.visualElement.current)return;N1.set(this.visualElement,this);const t=this.visualElement.current,n=gt(t,"pointerdown",a=>{const{drag:u,dragListener:c=!0}=this.getProps();u&&c&&this.start(a)}),r=()=>{const{dragConstraints:a}=this.getProps();On(a)&&(this.constraints=this.resolveRefConstraints())},{projection:i}=this.visualElement,o=i.addEventListener("measure",r);i&&!i.layout&&(i.root&&i.root.updateScroll(),i.updateLayout()),r();const s=ht(window,"resize",()=>this.scalePositionWithinConstraints()),l=i.addEventListener("didUpdate",({delta:a,hasLayoutChanged:u})=>{this.isDragging&&u&&(ot(c=>{const f=this.getAxisMotionValue(c);f&&(this.originPoint[c]+=a[c].translate,f.set(f.get()+a[c].translate))}),this.visualElement.render())});return()=>{s(),n(),o(),l&&l()}}getProps(){const t=this.visualElement.getProps(),{drag:n=!1,dragDirectionLock:r=!1,dragPropagation:i=!1,dragConstraints:o=!1,dragElastic:s=Il,dragMomentum:l=!0}=t;return{...t,drag:n,dragDirectionLock:r,dragPropagation:i,dragConstraints:o,dragElastic:s,dragMomentum:l}}}function Di(e,t,n){return(t===!0||t===e)&&(n===null||n===e)}function j1(e,t=10){let n=null;return Math.abs(e.y)>t?n="y":Math.abs(e.x)>t&&(n="x"),n}class F1 extends Zt{constructor(t){super(t),this.removeGroupControls=oe,this.removeListeners=oe,this.controls=new O1(t)}mount(){const{dragControls:t}=this.node.getProps();t&&(this.removeGroupControls=t.subscribe(this.controls)),this.removeListeners=this.controls.addListeners()||oe}unmount(){this.removeGroupControls(),this.removeListeners()}}const tf=e=>(t,n)=>{e&&Q.update(()=>e(t,n))};class I1 extends Zt{constructor(){super(...arguments),this.removePointerDownListener=oe}onPointerDown(t){this.session=new Gh(t,this.createPanHandlers(),{transformPagePoint:this.node.getTransformPagePoint()})}createPanHandlers(){const{onPanSessionStart:t,onPanStart:n,onPan:r,onPanEnd:i}=this.node.getProps();return{onSessionStart:tf(t),onStart:tf(n),onMove:r,onEnd:(o,s)=>{delete this.session,i&&Q.update(()=>i(o,s))}}}mount(){this.removePointerDownListener=gt(this.node.current,"pointerdown",t=>this.onPointerDown(t))}update(){this.session&&this.session.updateHandlers(this.createPanHandlers())}unmount(){this.removePointerDownListener(),this.session&&this.session.end()}}function z1(){const e=S.useContext(zo);if(e===null)return[!0,null];const{isPresent:t,onExitComplete:n,register:r}=e,i=S.useId();return S.useEffect(()=>r(i),[]),!t&&n?[!1,()=>n&&n(i)]:[!0]}const Ui={hasAnimatedSinceResize:!0,hasEverUpdated:!1};function nf(e,t){return t.max===t.min?0:e/(t.max-t.min)*100}const dr={correct:(e,t)=>{if(!t.target)return e;if(typeof e=="string")if(A.test(e))e=parseFloat(e);else return e;const n=nf(e,t.target.x),r=nf(e,t.target.y);return`${n}% ${r}%`}},B1={correct:(e,{treeScale:t,projectionDelta:n})=>{const r=e,i=Kt.parse(e);if(i.length>5)return r;const o=Kt.createTransformer(e),s=typeof i[0]!="number"?1:0,l=n.x.scale*t.x,a=n.y.scale*t.y;i[0+s]/=l,i[1+s]/=a;const u=Z(l,a,.5);return typeof i[2+s]=="number"&&(i[2+s]/=u),typeof i[3+s]=="number"&&(i[3+s]/=u),o(i)}};class U1 extends Yl.Component{componentDidMount(){const{visualElement:t,layoutGroup:n,switchLayoutGroup:r,layoutId:i}=this.props,{projection:o}=t;Yy($1),o&&(n.group&&n.group.add(o),r&&r.register&&i&&r.register(o),o.root.didUpdate(),o.addEventListener("animationComplete",()=>{this.safeToRemove()}),o.setOptions({...o.options,onExitComplete:()=>this.safeToRemove()})),Ui.hasEverUpdated=!0}getSnapshotBeforeUpdate(t){const{layoutDependency:n,visualElement:r,drag:i,isPresent:o}=this.props,s=r.projection;return s&&(s.isPresent=o,i||t.layoutDependency!==n||n===void 0?s.willUpdate():this.safeToRemove(),t.isPresent!==o&&(o?s.promote():s.relegate()||Q.postRender(()=>{const l=s.getStack();(!l||!l.members.length)&&this.safeToRemove()}))),null}componentDidUpdate(){const{projection:t}=this.props.visualElement;t&&(t.root.didUpdate(),queueMicrotask(()=>{!t.currentAnimation&&t.isLead()&&this.safeToRemove()}))}componentWillUnmount(){const{visualElement:t,layoutGroup:n,switchLayoutGroup:r}=this.props,{projection:i}=t;i&&(i.scheduleCheckAfterUnmount(),n&&n.group&&n.group.remove(i),r&&r.deregister&&r.deregister(i))}safeToRemove(){const{safeToRemove:t}=this.props;t&&t()}render(){return null}}function qh(e){const[t,n]=z1(),r=S.useContext(Ua);return Yl.createElement(U1,{...e,layoutGroup:r,switchLayoutGroup:S.useContext(Gp),isPresent:t,safeToRemove:n})}const $1={borderRadius:{...dr,applyTo:["borderTopLeftRadius","borderTopRightRadius","borderBottomLeftRadius","borderBottomRightRadius"]},borderTopLeftRadius:dr,borderTopRightRadius:dr,borderBottomLeftRadius:dr,borderBottomRightRadius:dr,boxShadow:B1},Jh=["TopLeft","TopRight","BottomLeft","BottomRight"],H1=Jh.length,rf=e=>typeof e=="string"?parseFloat(e):e,of=e=>typeof e=="number"||A.test(e);function W1(e,t,n,r,i,o){i?(e.opacity=Z(0,n.opacity!==void 0?n.opacity:1,G1(r)),e.opacityExit=Z(t.opacity!==void 0?t.opacity:1,0,K1(r))):o&&(e.opacity=Z(t.opacity!==void 0?t.opacity:1,n.opacity!==void 0?n.opacity:1,r));for(let s=0;s<H1;s++){const l=`border${Jh[s]}Radius`;let a=sf(t,l),u=sf(n,l);if(a===void 0&&u===void 0)continue;a||(a=0),u||(u=0),a===0||u===0||of(a)===of(u)?(e[l]=Math.max(Z(rf(a),rf(u),r),0),(ut.test(u)||ut.test(a))&&(e[l]+="%")):e[l]=u}(t.rotate||n.rotate)&&(e.rotate=Z(t.rotate||0,n.rotate||0,r))}function sf(e,t){return e[t]!==void 0?e[t]:e.borderRadius}const G1=bh(0,.5,qa),K1=bh(.5,.95,oe);function bh(e,t,n){return r=>r<e?0:r>t?1:n(qr(e,t,r))}function lf(e,t){e.min=t.min,e.max=t.max}function $e(e,t){lf(e.x,t.x),lf(e.y,t.y)}function af(e,t,n,r,i){return e-=t,e=So(e,1/n,r),i!==void 0&&(e=So(e,1/i,r)),e}function Q1(e,t=0,n=1,r=.5,i,o=e,s=e){if(ut.test(t)&&(t=parseFloat(t),t=Z(s.min,s.max,t/100)-s.min),typeof t!="number")return;let l=Z(o.min,o.max,r);e===o&&(l-=t),e.min=af(e.min,t,n,l,i),e.max=af(e.max,t,n,l,i)}function uf(e,t,[n,r,i],o,s){Q1(e,t[n],t[r],t[i],t.scale,o,s)}const Y1=["x","scaleX","originX"],X1=["y","scaleY","originY"];function cf(e,t,n,r){uf(e.x,t,Y1,n?n.x:void 0,r?r.x:void 0),uf(e.y,t,X1,n?n.y:void 0,r?r.y:void 0)}function ff(e){return e.translate===0&&e.scale===1}function em(e){return ff(e.x)&&ff(e.y)}function Ul(e,t){return e.x.min===t.x.min&&e.x.max===t.x.max&&e.y.min===t.y.min&&e.y.max===t.y.max}function df(e){return Fe(e.x)/Fe(e.y)}class Z1{constructor(){this.members=[]}add(t){nu(this.members,t),t.scheduleRender()}remove(t){if(ru(this.members,t),t===this.prevLead&&(this.prevLead=void 0),t===this.lead){const n=this.members[this.members.length-1];n&&this.promote(n)}}relegate(t){const n=this.members.findIndex(i=>t===i);if(n===0)return!1;let r;for(let i=n;i>=0;i--){const o=this.members[i];if(o.isPresent!==!1){r=o;break}}return r?(this.promote(r),!0):!1}promote(t,n){const r=this.lead;if(t!==r&&(this.prevLead=r,this.lead=t,t.show(),r)){r.instance&&r.scheduleRender(),t.scheduleRender(),t.resumeFrom=r,n&&(t.resumeFrom.preserveOpacity=!0),r.snapshot&&(t.snapshot=r.snapshot,t.snapshot.latestValues=r.animationValues||r.latestValues),t.root&&t.root.isUpdating&&(t.isLayoutDirty=!0);const{crossfade:i}=t.options;i===!1&&r.hide()}}exitAnimationComplete(){this.members.forEach(t=>{const{options:n,resumingFrom:r}=t;n.onExitComplete&&n.onExitComplete(),r&&r.options.onExitComplete&&r.options.onExitComplete()})}scheduleRender(){this.members.forEach(t=>{t.instance&&t.scheduleRender(!1)})}removeLeadSnapshot(){this.lead&&this.lead.snapshot&&(this.lead.snapshot=void 0)}}function pf(e,t,n){let r="";const i=e.x.translate/t.x,o=e.y.translate/t.y;if((i||o)&&(r=`translate3d(${i}px, ${o}px, 0) `),(t.x!==1||t.y!==1)&&(r+=`scale(${1/t.x}, ${1/t.y}) `),n){const{rotate:a,rotateX:u,rotateY:c}=n;a&&(r+=`rotate(${a}deg) `),u&&(r+=`rotateX(${u}deg) `),c&&(r+=`rotateY(${c}deg) `)}const s=e.x.scale*t.x,l=e.y.scale*t.y;return(s!==1||l!==1)&&(r+=`scale(${s}, ${l})`),r||"none"}const q1=(e,t)=>e.depth-t.depth;class J1{constructor(){this.children=[],this.isDirty=!1}add(t){nu(this.children,t),this.isDirty=!0}remove(t){ru(this.children,t),this.isDirty=!0}forEach(t){this.isDirty&&this.children.sort(q1),this.isDirty=!1,this.children.forEach(t)}}function b1(e,t){const n=performance.now(),r=({timestamp:i})=>{const o=i-n;o>=t&&(kt(r),e(o-t))};return Q.read(r,!0),()=>kt(r)}function ew(e){window.MotionDebug&&window.MotionDebug.record(e)}function tw(e){return e instanceof SVGElement&&e.tagName!=="svg"}function nw(e,t,n){const r=Ve(e)?e:bn(e);return r.start(tu("",r,t,n)),r.animation}const hf=["","X","Y","Z"],mf=1e3;let rw=0;const on={type:"projectionFrame",totalNodes:0,resolvedTargetDeltas:0,recalculatedProjection:0};function tm({attachResizeListener:e,defaultParent:t,measureScroll:n,checkIsScrollRoot:r,resetTransform:i}){return class{constructor(s={},l=t==null?void 0:t()){this.id=rw++,this.animationId=0,this.children=new Set,this.options={},this.isTreeAnimating=!1,this.isAnimationBlocked=!1,this.isLayoutDirty=!1,this.isProjectionDirty=!1,this.isSharedProjectionDirty=!1,this.isTransformDirty=!1,this.updateManuallyBlocked=!1,this.updateBlockedByResize=!1,this.isUpdating=!1,this.isSVG=!1,this.needsReset=!1,this.shouldResetTransform=!1,this.treeScale={x:1,y:1},this.eventHandlers=new Map,this.hasTreeAnimated=!1,this.updateScheduled=!1,this.checkUpdateFailed=()=>{this.isUpdating&&(this.isUpdating=!1,this.clearAllSnapshots())},this.updateProjection=()=>{on.totalNodes=on.resolvedTargetDeltas=on.recalculatedProjection=0,this.nodes.forEach(sw),this.nodes.forEach(fw),this.nodes.forEach(dw),this.nodes.forEach(lw),ew(on)},this.hasProjected=!1,this.isVisible=!0,this.animationProgress=0,this.sharedNodes=new Map,this.latestValues=s,this.root=l?l.root||l:this,this.path=l?[...l.path,l]:[],this.parent=l,this.depth=l?l.depth+1:0;for(let a=0;a<this.path.length;a++)this.path[a].shouldResetTransform=!0;this.root===this&&(this.nodes=new J1)}addEventListener(s,l){return this.eventHandlers.has(s)||this.eventHandlers.set(s,new iu),this.eventHandlers.get(s).add(l)}notifyListeners(s,...l){const a=this.eventHandlers.get(s);a&&a.notify(...l)}hasListeners(s){return this.eventHandlers.has(s)}mount(s,l=this.root.hasTreeAnimated){if(this.instance)return;this.isSVG=tw(s),this.instance=s;const{layoutId:a,layout:u,visualElement:c}=this.options;if(c&&!c.current&&c.mount(s),this.root.nodes.add(this),this.parent&&this.parent.children.add(this),l&&(u||a)&&(this.isLayoutDirty=!0),e){let f;const p=()=>this.root.updateBlockedByResize=!1;e(s,()=>{this.root.updateBlockedByResize=!0,f&&f(),f=b1(p,250),Ui.hasAnimatedSinceResize&&(Ui.hasAnimatedSinceResize=!1,this.nodes.forEach(yf))})}a&&this.root.registerSharedNode(a,this),this.options.animate!==!1&&c&&(a||u)&&this.addEventListener("didUpdate",({delta:f,hasLayoutChanged:p,hasRelativeTargetChanged:g,layout:y})=>{if(this.isTreeAnimationBlocked()){this.target=void 0,this.relativeTarget=void 0;return}const v=this.options.transition||c.getDefaultTransition()||yw,{onLayoutAnimationStart:T,onLayoutAnimationComplete:m}=c.getProps(),d=!this.targetLayout||!Ul(this.targetLayout,y)||g,h=!p&&g;if(this.options.layoutRoot||this.resumeFrom&&this.resumeFrom.instance||h||p&&(d||!this.currentAnimation)){this.resumeFrom&&(this.resumingFrom=this.resumeFrom,this.resumingFrom.resumingFrom=void 0),this.setAnimationOrigin(f,h);const w={...Uh(v,"layout"),onPlay:T,onComplete:m};(c.shouldReduceMotion||this.options.layoutRoot)&&(w.delay=0,w.type=!1),this.startAnimation(w)}else p||yf(this),this.isLead()&&this.options.onExitComplete&&this.options.onExitComplete();this.targetLayout=y})}unmount(){this.options.layoutId&&this.willUpdate(),this.root.nodes.remove(this);const s=this.getStack();s&&s.remove(this),this.parent&&this.parent.children.delete(this),this.instance=void 0,kt(this.updateProjection)}blockUpdate(){this.updateManuallyBlocked=!0}unblockUpdate(){this.updateManuallyBlocked=!1}isUpdateBlocked(){return this.updateManuallyBlocked||this.updateBlockedByResize}isTreeAnimationBlocked(){return this.isAnimationBlocked||this.parent&&this.parent.isTreeAnimationBlocked()||!1}startUpdate(){this.isUpdateBlocked()||(this.isUpdating=!0,this.nodes&&this.nodes.forEach(pw),this.animationId++)}getTransformTemplate(){const{visualElement:s}=this.options;return s&&s.getProps().transformTemplate}willUpdate(s=!0){if(this.root.hasTreeAnimated=!0,this.root.isUpdateBlocked()){this.options.onExitComplete&&this.options.onExitComplete();return}if(!this.root.isUpdating&&this.root.startUpdate(),this.isLayoutDirty)return;this.isLayoutDirty=!0;for(let c=0;c<this.path.length;c++){const f=this.path[c];f.shouldResetTransform=!0,f.updateScroll("snapshot"),f.options.layoutRoot&&f.willUpdate(!1)}const{layoutId:l,layout:a}=this.options;if(l===void 0&&!a)return;const u=this.getTransformTemplate();this.prevTransformTemplateValue=u?u(this.latestValues,""):void 0,this.updateSnapshot(),s&&this.notifyListeners("willUpdate")}update(){if(this.updateScheduled=!1,this.isUpdateBlocked()){this.unblockUpdate(),this.clearAllSnapshots(),this.nodes.forEach(gf);return}this.isUpdating||this.nodes.forEach(uw),this.isUpdating=!1,this.nodes.forEach(cw),this.nodes.forEach(iw),this.nodes.forEach(ow),this.clearAllSnapshots();const l=performance.now();Y.delta=Gt(0,1e3/60,l-Y.timestamp),Y.timestamp=l,Y.isProcessing=!0,Gn.update.process(Y),Gn.preRender.process(Y),Gn.render.process(Y),Y.isProcessing=!1}didUpdate(){this.updateScheduled||(this.updateScheduled=!0,queueMicrotask(()=>this.update()))}clearAllSnapshots(){this.nodes.forEach(aw),this.sharedNodes.forEach(hw)}scheduleUpdateProjection(){Q.preRender(this.updateProjection,!1,!0)}scheduleCheckAfterUnmount(){Q.postRender(()=>{this.isLayoutDirty?this.root.didUpdate():this.root.checkUpdateFailed()})}updateSnapshot(){this.snapshot||!this.instance||(this.snapshot=this.measure())}updateLayout(){if(!this.instance||(this.updateScroll(),!(this.options.alwaysMeasureLayout&&this.isLead())&&!this.isLayoutDirty))return;if(this.resumeFrom&&!this.resumeFrom.instance)for(let a=0;a<this.path.length;a++)this.path[a].updateScroll();const s=this.layout;this.layout=this.measure(!1),this.layoutCorrected=ne(),this.isLayoutDirty=!1,this.projectionDelta=void 0,this.notifyListeners("measure",this.layout.layoutBox);const{visualElement:l}=this.options;l&&l.notify("LayoutMeasure",this.layout.layoutBox,s?s.layoutBox:void 0)}updateScroll(s="measure"){let l=!!(this.options.layoutScroll&&this.instance);this.scroll&&this.scroll.animationId===this.root.animationId&&this.scroll.phase===s&&(l=!1),l&&(this.scroll={animationId:this.root.animationId,phase:s,isRoot:r(this.instance),offset:n(this.instance)})}resetTransform(){if(!i)return;const s=this.isLayoutDirty||this.shouldResetTransform,l=this.projectionDelta&&!em(this.projectionDelta),a=this.getTransformTemplate(),u=a?a(this.latestValues,""):void 0,c=u!==this.prevTransformTemplateValue;s&&(l||rn(this.latestValues)||c)&&(i(this.instance,u),this.shouldResetTransform=!1,this.scheduleRender())}measure(s=!0){const l=this.measurePageBox();let a=this.removeElementScroll(l);return s&&(a=this.removeTransform(a)),vw(a),{animationId:this.root.animationId,measuredBox:l,layoutBox:a,latestValues:{},source:this.id}}measurePageBox(){const{visualElement:s}=this.options;if(!s)return ne();const l=s.measureViewportBox(),{scroll:a}=this.root;return a&&(Lt(l.x,a.offset.x),Lt(l.y,a.offset.y)),l}removeElementScroll(s){const l=ne();$e(l,s);for(let a=0;a<this.path.length;a++){const u=this.path[a],{scroll:c,options:f}=u;if(u!==this.root&&c&&f.layoutScroll){if(c.isRoot){$e(l,s);const{scroll:p}=this.root;p&&(Lt(l.x,-p.offset.x),Lt(l.y,-p.offset.y))}Lt(l.x,c.offset.x),Lt(l.y,c.offset.y)}}return l}applyTransform(s,l=!1){const a=ne();$e(a,s);for(let u=0;u<this.path.length;u++){const c=this.path[u];!l&&c.options.layoutScroll&&c.scroll&&c!==c.root&&In(a,{x:-c.scroll.offset.x,y:-c.scroll.offset.y}),rn(c.latestValues)&&In(a,c.latestValues)}return rn(this.latestValues)&&In(a,this.latestValues),a}removeTransform(s){const l=ne();$e(l,s);for(let a=0;a<this.path.length;a++){const u=this.path[a];if(!u.instance||!rn(u.latestValues))continue;zl(u.latestValues)&&u.updateSnapshot();const c=ne(),f=u.measurePageBox();$e(c,f),cf(l,u.latestValues,u.snapshot?u.snapshot.layoutBox:void 0,c)}return rn(this.latestValues)&&cf(l,this.latestValues),l}setTargetDelta(s){this.targetDelta=s,this.root.scheduleUpdateProjection(),this.isProjectionDirty=!0}setOptions(s){this.options={...this.options,...s,crossfade:s.crossfade!==void 0?s.crossfade:!0}}clearMeasurements(){this.scroll=void 0,this.layout=void 0,this.snapshot=void 0,this.prevTransformTemplateValue=void 0,this.targetDelta=void 0,this.target=void 0,this.isLayoutDirty=!1}forceRelativeParentToResolveTarget(){this.relativeParent&&this.relativeParent.resolvedRelativeTargetAt!==Y.timestamp&&this.relativeParent.resolveTargetDelta(!0)}resolveTargetDelta(s=!1){var l;const a=this.getLead();this.isProjectionDirty||(this.isProjectionDirty=a.isProjectionDirty),this.isTransformDirty||(this.isTransformDirty=a.isTransformDirty),this.isSharedProjectionDirty||(this.isSharedProjectionDirty=a.isSharedProjectionDirty);const u=!!this.resumingFrom||this!==a;if(!(s||u&&this.isSharedProjectionDirty||this.isProjectionDirty||!((l=this.parent)===null||l===void 0)&&l.isProjectionDirty||this.attemptToResolveRelativeTarget))return;const{layout:f,layoutId:p}=this.options;if(!(!this.layout||!(f||p))){if(this.resolvedRelativeTargetAt=Y.timestamp,!this.targetDelta&&!this.relativeTarget){const g=this.getClosestProjectingParent();g&&g.layout&&this.animationProgress!==1?(this.relativeParent=g,this.forceRelativeParentToResolveTarget(),this.relativeTarget=ne(),this.relativeTargetOrigin=ne(),Rr(this.relativeTargetOrigin,this.layout.layoutBox,g.layout.layoutBox),$e(this.relativeTarget,this.relativeTargetOrigin)):this.relativeParent=this.relativeTarget=void 0}if(!(!this.relativeTarget&&!this.targetDelta)){if(this.target||(this.target=ne(),this.targetWithTransforms=ne()),this.relativeTarget&&this.relativeTargetOrigin&&this.relativeParent&&this.relativeParent.target?(this.forceRelativeParentToResolveTarget(),S1(this.target,this.relativeTarget,this.relativeParent.target)):this.targetDelta?(this.resumingFrom?this.target=this.applyTransform(this.layout.layoutBox):$e(this.target,this.layout.layoutBox),Xh(this.target,this.targetDelta)):$e(this.target,this.layout.layoutBox),this.attemptToResolveRelativeTarget){this.attemptToResolveRelativeTarget=!1;const g=this.getClosestProjectingParent();g&&!!g.resumingFrom==!!this.resumingFrom&&!g.options.layoutScroll&&g.target&&this.animationProgress!==1?(this.relativeParent=g,this.forceRelativeParentToResolveTarget(),this.relativeTarget=ne(),this.relativeTargetOrigin=ne(),Rr(this.relativeTargetOrigin,this.target,g.target),$e(this.relativeTarget,this.relativeTargetOrigin)):this.relativeParent=this.relativeTarget=void 0}on.resolvedTargetDeltas++}}}getClosestProjectingParent(){if(!(!this.parent||zl(this.parent.latestValues)||Yh(this.parent.latestValues)))return this.parent.isProjecting()?this.parent:this.parent.getClosestProjectingParent()}isProjecting(){return!!((this.relativeTarget||this.targetDelta||this.options.layoutRoot)&&this.layout)}calcProjection(){var s;const l=this.getLead(),a=!!this.resumingFrom||this!==l;let u=!0;if((this.isProjectionDirty||!((s=this.parent)===null||s===void 0)&&s.isProjectionDirty)&&(u=!1),a&&(this.isSharedProjectionDirty||this.isTransformDirty)&&(u=!1),this.resolvedRelativeTargetAt===Y.timestamp&&(u=!1),u)return;const{layout:c,layoutId:f}=this.options;if(this.isTreeAnimating=!!(this.parent&&this.parent.isTreeAnimating||this.currentAnimation||this.pendingAnimation),this.isTreeAnimating||(this.targetDelta=this.relativeTarget=void 0),!this.layout||!(c||f))return;$e(this.layoutCorrected,this.layout.layoutBox);const p=this.treeScale.x,g=this.treeScale.y;R1(this.layoutCorrected,this.treeScale,this.path,a),l.layout&&!l.target&&(this.treeScale.x!==1||this.treeScale.y!==1)&&(l.target=l.layout.layoutBox);const{target:y}=l;if(!y){this.projectionTransform&&(this.projectionDelta=Fn(),this.projectionTransform="none",this.scheduleRender());return}this.projectionDelta||(this.projectionDelta=Fn(),this.projectionDeltaWithTransform=Fn());const v=this.projectionTransform;Mr(this.projectionDelta,this.layoutCorrected,y,this.latestValues),this.projectionTransform=pf(this.projectionDelta,this.treeScale),(this.projectionTransform!==v||this.treeScale.x!==p||this.treeScale.y!==g)&&(this.hasProjected=!0,this.scheduleRender(),this.notifyListeners("projectionUpdate",y)),on.recalculatedProjection++}hide(){this.isVisible=!1}show(){this.isVisible=!0}scheduleRender(s=!0){if(this.options.scheduleRender&&this.options.scheduleRender(),s){const l=this.getStack();l&&l.scheduleRender()}this.resumingFrom&&!this.resumingFrom.instance&&(this.resumingFrom=void 0)}setAnimationOrigin(s,l=!1){const a=this.snapshot,u=a?a.latestValues:{},c={...this.latestValues},f=Fn();(!this.relativeParent||!this.relativeParent.options.layoutRoot)&&(this.relativeTarget=this.relativeTargetOrigin=void 0),this.attemptToResolveRelativeTarget=!l;const p=ne(),g=a?a.source:void 0,y=this.layout?this.layout.source:void 0,v=g!==y,T=this.getStack(),m=!T||T.members.length<=1,d=!!(v&&!m&&this.options.crossfade===!0&&!this.path.some(gw));this.animationProgress=0;let h;this.mixTargetDelta=w=>{const x=w/1e3;vf(f.x,s.x,x),vf(f.y,s.y,x),this.setTargetDelta(f),this.relativeTarget&&this.relativeTargetOrigin&&this.layout&&this.relativeParent&&this.relativeParent.layout&&(Rr(p,this.layout.layoutBox,this.relativeParent.layout.layoutBox),mw(this.relativeTarget,this.relativeTargetOrigin,p,x),h&&Ul(this.relativeTarget,h)&&(this.isProjectionDirty=!1),h||(h=ne()),$e(h,this.relativeTarget)),v&&(this.animationValues=c,W1(c,u,this.latestValues,x,d,m)),this.root.scheduleUpdateProjection(),this.scheduleRender(),this.animationProgress=x},this.mixTargetDelta(this.options.layoutRoot?1e3:0)}startAnimation(s){this.notifyListeners("animationStart"),this.currentAnimation&&this.currentAnimation.stop(),this.resumingFrom&&this.resumingFrom.currentAnimation&&this.resumingFrom.currentAnimation.stop(),this.pendingAnimation&&(kt(this.pendingAnimation),this.pendingAnimation=void 0),this.pendingAnimation=Q.update(()=>{Ui.hasAnimatedSinceResize=!0,this.currentAnimation=nw(0,mf,{...s,onUpdate:l=>{this.mixTargetDelta(l),s.onUpdate&&s.onUpdate(l)},onComplete:()=>{s.onComplete&&s.onComplete(),this.completeAnimation()}}),this.resumingFrom&&(this.resumingFrom.currentAnimation=this.currentAnimation),this.pendingAnimation=void 0})}completeAnimation(){this.resumingFrom&&(this.resumingFrom.currentAnimation=void 0,this.resumingFrom.preserveOpacity=void 0);const s=this.getStack();s&&s.exitAnimationComplete(),this.resumingFrom=this.currentAnimation=this.animationValues=void 0,this.notifyListeners("animationComplete")}finishAnimation(){this.currentAnimation&&(this.mixTargetDelta&&this.mixTargetDelta(mf),this.currentAnimation.stop()),this.completeAnimation()}applyTransformsToTarget(){const s=this.getLead();let{targetWithTransforms:l,target:a,layout:u,latestValues:c}=s;if(!(!l||!a||!u)){if(this!==s&&this.layout&&u&&nm(this.options.animationType,this.layout.layoutBox,u.layoutBox)){a=this.target||ne();const f=Fe(this.layout.layoutBox.x);a.x.min=s.target.x.min,a.x.max=a.x.min+f;const p=Fe(this.layout.layoutBox.y);a.y.min=s.target.y.min,a.y.max=a.y.min+p}$e(l,a),In(l,c),Mr(this.projectionDeltaWithTransform,this.layoutCorrected,l,c)}}registerSharedNode(s,l){this.sharedNodes.has(s)||this.sharedNodes.set(s,new Z1),this.sharedNodes.get(s).add(l);const u=l.options.initialPromotionConfig;l.promote({transition:u?u.transition:void 0,preserveFollowOpacity:u&&u.shouldPreserveFollowOpacity?u.shouldPreserveFollowOpacity(l):void 0})}isLead(){const s=this.getStack();return s?s.lead===this:!0}getLead(){var s;const{layoutId:l}=this.options;return l?((s=this.getStack())===null||s===void 0?void 0:s.lead)||this:this}getPrevLead(){var s;const{layoutId:l}=this.options;return l?(s=this.getStack())===null||s===void 0?void 0:s.prevLead:void 0}getStack(){const{layoutId:s}=this.options;if(s)return this.root.sharedNodes.get(s)}promote({needsReset:s,transition:l,preserveFollowOpacity:a}={}){const u=this.getStack();u&&u.promote(this,a),s&&(this.projectionDelta=void 0,this.needsReset=!0),l&&this.setOptions({transition:l})}relegate(){const s=this.getStack();return s?s.relegate(this):!1}resetRotation(){const{visualElement:s}=this.options;if(!s)return;let l=!1;const{latestValues:a}=s;if((a.rotate||a.rotateX||a.rotateY||a.rotateZ)&&(l=!0),!l)return;const u={};for(let c=0;c<hf.length;c++){const f="rotate"+hf[c];a[f]&&(u[f]=a[f],s.setStaticValue(f,0))}s.render();for(const c in u)s.setStaticValue(c,u[c]);s.scheduleRender()}getProjectionStyles(s={}){var l,a;const u={};if(!this.instance||this.isSVG)return u;if(this.isVisible)u.visibility="";else return{visibility:"hidden"};const c=this.getTransformTemplate();if(this.needsReset)return this.needsReset=!1,u.opacity="",u.pointerEvents=Bi(s.pointerEvents)||"",u.transform=c?c(this.latestValues,""):"none",u;const f=this.getLead();if(!this.projectionDelta||!this.layout||!f.target){const v={};return this.options.layoutId&&(v.opacity=this.latestValues.opacity!==void 0?this.latestValues.opacity:1,v.pointerEvents=Bi(s.pointerEvents)||""),this.hasProjected&&!rn(this.latestValues)&&(v.transform=c?c({},""):"none",this.hasProjected=!1),v}const p=f.animationValues||f.latestValues;this.applyTransformsToTarget(),u.transform=pf(this.projectionDeltaWithTransform,this.treeScale,p),c&&(u.transform=c(p,u.transform));const{x:g,y}=this.projectionDelta;u.transformOrigin=`${g.origin*100}% ${y.origin*100}% 0`,f.animationValues?u.opacity=f===this?(a=(l=p.opacity)!==null&&l!==void 0?l:this.latestValues.opacity)!==null&&a!==void 0?a:1:this.preserveOpacity?this.latestValues.opacity:p.opacityExit:u.opacity=f===this?p.opacity!==void 0?p.opacity:"":p.opacityExit!==void 0?p.opacityExit:0;for(const v in ho){if(p[v]===void 0)continue;const{correct:T,applyTo:m}=ho[v],d=u.transform==="none"?p[v]:T(p[v],f);if(m){const h=m.length;for(let w=0;w<h;w++)u[m[w]]=d}else u[v]=d}return this.options.layoutId&&(u.pointerEvents=f===this?Bi(s.pointerEvents)||"":"none"),u}clearSnapshot(){this.resumeFrom=this.snapshot=void 0}resetTree(){this.root.nodes.forEach(s=>{var l;return(l=s.currentAnimation)===null||l===void 0?void 0:l.stop()}),this.root.nodes.forEach(gf),this.root.sharedNodes.clear()}}}function iw(e){e.updateLayout()}function ow(e){var t;const n=((t=e.resumeFrom)===null||t===void 0?void 0:t.snapshot)||e.snapshot;if(e.isLead()&&e.layout&&n&&e.hasListeners("didUpdate")){const{layoutBox:r,measuredBox:i}=e.layout,{animationType:o}=e.options,s=n.source!==e.layout.source;o==="size"?ot(f=>{const p=s?n.measuredBox[f]:n.layoutBox[f],g=Fe(p);p.min=r[f].min,p.max=p.min+g}):nm(o,n.layoutBox,r)&&ot(f=>{const p=s?n.measuredBox[f]:n.layoutBox[f],g=Fe(r[f]);p.max=p.min+g,e.relativeTarget&&!e.currentAnimation&&(e.isProjectionDirty=!0,e.relativeTarget[f].max=e.relativeTarget[f].min+g)});const l=Fn();Mr(l,r,n.layoutBox);const a=Fn();s?Mr(a,e.applyTransform(i,!0),n.measuredBox):Mr(a,r,n.layoutBox);const u=!em(l);let c=!1;if(!e.resumeFrom){const f=e.getClosestProjectingParent();if(f&&!f.resumeFrom){const{snapshot:p,layout:g}=f;if(p&&g){const y=ne();Rr(y,n.layoutBox,p.layoutBox);const v=ne();Rr(v,r,g.layoutBox),Ul(y,v)||(c=!0),f.options.layoutRoot&&(e.relativeTarget=v,e.relativeTargetOrigin=y,e.relativeParent=f)}}}e.notifyListeners("didUpdate",{layout:r,snapshot:n,delta:a,layoutDelta:l,hasLayoutChanged:u,hasRelativeTargetChanged:c})}else if(e.isLead()){const{onExitComplete:r}=e.options;r&&r()}e.options.transition=void 0}function sw(e){on.totalNodes++,e.parent&&(e.isProjecting()||(e.isProjectionDirty=e.parent.isProjectionDirty),e.isSharedProjectionDirty||(e.isSharedProjectionDirty=!!(e.isProjectionDirty||e.parent.isProjectionDirty||e.parent.isSharedProjectionDirty)),e.isTransformDirty||(e.isTransformDirty=e.parent.isTransformDirty))}function lw(e){e.isProjectionDirty=e.isSharedProjectionDirty=e.isTransformDirty=!1}function aw(e){e.clearSnapshot()}function gf(e){e.clearMeasurements()}function uw(e){e.isLayoutDirty=!1}function cw(e){const{visualElement:t}=e.options;t&&t.getProps().onBeforeLayoutMeasure&&t.notify("BeforeLayoutMeasure"),e.resetTransform()}function yf(e){e.finishAnimation(),e.targetDelta=e.relativeTarget=e.target=void 0,e.isProjectionDirty=!0}function fw(e){e.resolveTargetDelta()}function dw(e){e.calcProjection()}function pw(e){e.resetRotation()}function hw(e){e.removeLeadSnapshot()}function vf(e,t,n){e.translate=Z(t.translate,0,n),e.scale=Z(t.scale,1,n),e.origin=t.origin,e.originPoint=t.originPoint}function wf(e,t,n,r){e.min=Z(t.min,n.min,r),e.max=Z(t.max,n.max,r)}function mw(e,t,n,r){wf(e.x,t.x,n.x,r),wf(e.y,t.y,n.y,r)}function gw(e){return e.animationValues&&e.animationValues.opacityExit!==void 0}const yw={duration:.45,ease:[.4,0,.1,1]};function xf(e){e.min=Math.round(e.min),e.max=Math.round(e.max)}function vw(e){xf(e.x),xf(e.y)}function nm(e,t,n){return e==="position"||e==="preserve-aspect"&&!Fl(df(t),df(n),.2)}const ww=tm({attachResizeListener:(e,t)=>ht(e,"resize",t),measureScroll:()=>({x:document.documentElement.scrollLeft||document.body.scrollLeft,y:document.documentElement.scrollTop||document.body.scrollTop}),checkIsScrollRoot:()=>!0}),_s={current:void 0},rm=tm({measureScroll:e=>({x:e.scrollLeft,y:e.scrollTop}),defaultParent:()=>{if(!_s.current){const e=new ww({});e.mount(window),e.setOptions({layoutScroll:!0}),_s.current=e}return _s.current},resetTransform:(e,t)=>{e.style.transform=t!==void 0?t:"none"},checkIsScrollRoot:e=>window.getComputedStyle(e).position==="fixed"}),xw={pan:{Feature:I1},drag:{Feature:F1,ProjectionNode:rm,MeasureLayout:qh}},Sw=/var\((--[a-zA-Z0-9-_]+),? ?([a-zA-Z0-9 ()%#.,-]+)?\)/;function kw(e){const t=Sw.exec(e);if(!t)return[,];const[,n,r]=t;return[n,r]}function $l(e,t,n=1){const[r,i]=kw(e);if(!r)return;const o=window.getComputedStyle(t).getPropertyValue(r);return o?o.trim():Ml(i)?$l(i,t,n+1):i}function Pw(e,{...t},n){const r=e.current;if(!(r instanceof Element))return{target:t,transitionEnd:n};n&&(n={...n}),e.values.forEach(i=>{const o=i.get();if(!Ml(o))return;const s=$l(o,r);s&&i.set(s)});for(const i in t){const o=t[i];if(!Ml(o))continue;const s=$l(o,r);s&&(t[i]=s,n||(n={}),n[i]===void 0&&(n[i]=o))}return{target:t,transitionEnd:n}}const Cw=new Set(["width","height","top","left","right","bottom","x","y","translateX","translateY"]),im=e=>Cw.has(e),Tw=e=>Object.keys(e).some(im),Sf=e=>e===xn||e===A,kf=(e,t)=>parseFloat(e.split(", ")[t]),Pf=(e,t)=>(n,{transform:r})=>{if(r==="none"||!r)return 0;const i=r.match(/^matrix3d\((.+)\)$/);if(i)return kf(i[1],t);{const o=r.match(/^matrix\((.+)\)$/);return o?kf(o[1],e):0}},Ew=new Set(["x","y","z"]),Dw=ri.filter(e=>!Ew.has(e));function Lw(e){const t=[];return Dw.forEach(n=>{const r=e.getValue(n);r!==void 0&&(t.push([n,r.get()]),r.set(n.startsWith("scale")?1:0))}),t.length&&e.render(),t}const Cf={width:({x:e},{paddingLeft:t="0",paddingRight:n="0"})=>e.max-e.min-parseFloat(t)-parseFloat(n),height:({y:e},{paddingTop:t="0",paddingBottom:n="0"})=>e.max-e.min-parseFloat(t)-parseFloat(n),top:(e,{top:t})=>parseFloat(t),left:(e,{left:t})=>parseFloat(t),bottom:({y:e},{top:t})=>parseFloat(t)+(e.max-e.min),right:({x:e},{left:t})=>parseFloat(t)+(e.max-e.min),x:Pf(4,13),y:Pf(5,14)},Mw=(e,t,n)=>{const r=t.measureViewportBox(),i=t.current,o=getComputedStyle(i),{display:s}=o,l={};s==="none"&&t.setStaticValue("display",e.display||"block"),n.forEach(u=>{l[u]=Cf[u](r,o)}),t.render();const a=t.measureViewportBox();return n.forEach(u=>{const c=t.getValue(u);c&&c.jump(l[u]),e[u]=Cf[u](a,o)}),e},Rw=(e,t,n={},r={})=>{t={...t},r={...r};const i=Object.keys(t).filter(im);let o=[],s=!1;const l=[];if(i.forEach(a=>{const u=e.getValue(a);if(!e.hasValue(a))return;let c=n[a],f=fr(c);const p=t[a];let g;if(go(p)){const y=p.length,v=p[0]===null?1:0;c=p[v],f=fr(c);for(let T=v;T<y&&p[T]!==null;T++)g?Za(fr(p[T])===g):g=fr(p[T])}else g=fr(p);if(f!==g)if(Sf(f)&&Sf(g)){const y=u.get();typeof y=="string"&&u.set(parseFloat(y)),typeof p=="string"?t[a]=parseFloat(p):Array.isArray(p)&&g===A&&(t[a]=p.map(parseFloat))}else f!=null&&f.transform&&(g!=null&&g.transform)&&(c===0||p===0)?c===0?u.set(g.transform(c)):t[a]=f.transform(p):(s||(o=Lw(e),s=!0),l.push(a),r[a]=r[a]!==void 0?r[a]:t[a],u.jump(p))}),l.length){const a=l.indexOf("height")>=0?window.pageYOffset:null,u=Mw(t,e,l);return o.length&&o.forEach(([c,f])=>{e.getValue(c).set(f)}),e.render(),Bo&&a!==null&&window.scrollTo({top:a}),{target:u,transitionEnd:r}}else return{target:t,transitionEnd:r}};function Vw(e,t,n,r){return Tw(t)?Rw(e,t,n,r):{target:t,transitionEnd:r}}const Aw=(e,t,n,r)=>{const i=Pw(e,t,r);return t=i.target,r=i.transitionEnd,Vw(e,t,n,r)},Hl={current:null},om={current:!1};function _w(){if(om.current=!0,!!Bo)if(window.matchMedia){const e=window.matchMedia("(prefers-reduced-motion)"),t=()=>Hl.current=e.matches;e.addListener(t),t()}else Hl.current=!1}function Nw(e,t,n){const{willChange:r}=t;for(const i in t){const o=t[i],s=n[i];if(Ve(o))e.addValue(i,o),xo(r)&&r.add(i);else if(Ve(s))e.addValue(i,bn(o,{owner:e})),xo(r)&&r.remove(i);else if(s!==o)if(e.hasValue(i)){const l=e.getValue(i);!l.hasAnimated&&l.set(o)}else{const l=e.getStaticValue(i);e.addValue(i,bn(l!==void 0?l:o,{owner:e}))}}for(const i in n)t[i]===void 0&&e.removeValue(i);return t}const Tf=new WeakMap,sm=Object.keys(Xr),Ow=sm.length,Ef=["AnimationStart","AnimationComplete","Update","BeforeLayoutMeasure","LayoutMeasure","LayoutAnimationStart","LayoutAnimationComplete"],jw=Ba.length;class Fw{constructor({parent:t,props:n,presenceContext:r,reducedMotionConfig:i,visualState:o},s={}){this.current=null,this.children=new Set,this.isVariantNode=!1,this.isControllingVariants=!1,this.shouldReduceMotion=null,this.values=new Map,this.features={},this.valueSubscriptions=new Map,this.prevMotionValues={},this.events={},this.propEventSubscriptions={},this.notifyUpdate=()=>this.notify("Update",this.latestValues),this.render=()=>{this.current&&(this.triggerBuild(),this.renderInstance(this.current,this.renderState,this.props.style,this.projection))},this.scheduleRender=()=>Q.render(this.render,!1,!0);const{latestValues:l,renderState:a}=o;this.latestValues=l,this.baseTarget={...l},this.initialValues=n.initial?{...l}:{},this.renderState=a,this.parent=t,this.props=n,this.presenceContext=r,this.depth=t?t.depth+1:0,this.reducedMotionConfig=i,this.options=s,this.isControllingVariants=$o(n),this.isVariantNode=Wp(n),this.isVariantNode&&(this.variantChildren=new Set),this.manuallyAnimateOnMount=!!(t&&t.current);const{willChange:u,...c}=this.scrapeMotionValuesFromProps(n,{});for(const f in c){const p=c[f];l[f]!==void 0&&Ve(p)&&(p.set(l[f],!1),xo(u)&&u.add(f))}}scrapeMotionValuesFromProps(t,n){return{}}mount(t){this.current=t,Tf.set(t,this),this.projection&&!this.projection.instance&&this.projection.mount(t),this.parent&&this.isVariantNode&&!this.isControllingVariants&&(this.removeFromVariantTree=this.parent.addVariantChild(this)),this.values.forEach((n,r)=>this.bindToMotionValue(r,n)),om.current||_w(),this.shouldReduceMotion=this.reducedMotionConfig==="never"?!1:this.reducedMotionConfig==="always"?!0:Hl.current,this.parent&&this.parent.children.add(this),this.update(this.props,this.presenceContext)}unmount(){Tf.delete(this.current),this.projection&&this.projection.unmount(),kt(this.notifyUpdate),kt(this.render),this.valueSubscriptions.forEach(t=>t()),this.removeFromVariantTree&&this.removeFromVariantTree(),this.parent&&this.parent.children.delete(this);for(const t in this.events)this.events[t].clear();for(const t in this.features)this.features[t].unmount();this.current=null}bindToMotionValue(t,n){const r=wn.has(t),i=n.on("change",s=>{this.latestValues[t]=s,this.props.onUpdate&&Q.update(this.notifyUpdate,!1,!0),r&&this.projection&&(this.projection.isTransformDirty=!0)}),o=n.on("renderRequest",this.scheduleRender);this.valueSubscriptions.set(t,()=>{i(),o()})}sortNodePosition(t){return!this.current||!this.sortInstanceNodePosition||this.type!==t.type?0:this.sortInstanceNodePosition(this.current,t.current)}loadFeatures({children:t,...n},r,i,o){let s,l;for(let a=0;a<Ow;a++){const u=sm[a],{isEnabled:c,Feature:f,ProjectionNode:p,MeasureLayout:g}=Xr[u];p&&(s=p),c(n)&&(!this.features[u]&&f&&(this.features[u]=new f(this)),g&&(l=g))}if(!this.projection&&s){this.projection=new s(this.latestValues,this.parent&&this.parent.projection);const{layoutId:a,layout:u,drag:c,dragConstraints:f,layoutScroll:p,layoutRoot:g}=n;this.projection.setOptions({layoutId:a,layout:u,alwaysMeasureLayout:!!c||f&&On(f),visualElement:this,scheduleRender:()=>this.scheduleRender(),animationType:typeof u=="string"?u:"both",initialPromotionConfig:o,layoutScroll:p,layoutRoot:g})}return l}updateFeatures(){for(const t in this.features){const n=this.features[t];n.isMounted?n.update():(n.mount(),n.isMounted=!0)}}triggerBuild(){this.build(this.renderState,this.latestValues,this.options,this.props)}measureViewportBox(){return this.current?this.measureInstanceViewportBox(this.current,this.props):ne()}getStaticValue(t){return this.latestValues[t]}setStaticValue(t,n){this.latestValues[t]=n}makeTargetAnimatable(t,n=!0){return this.makeTargetAnimatableFromInstance(t,this.props,n)}update(t,n){(t.transformTemplate||this.props.transformTemplate)&&this.scheduleRender(),this.prevProps=this.props,this.props=t,this.prevPresenceContext=this.presenceContext,this.presenceContext=n;for(let r=0;r<Ef.length;r++){const i=Ef[r];this.propEventSubscriptions[i]&&(this.propEventSubscriptions[i](),delete this.propEventSubscriptions[i]);const o=t["on"+i];o&&(this.propEventSubscriptions[i]=this.on(i,o))}this.prevMotionValues=Nw(this,this.scrapeMotionValuesFromProps(t,this.prevProps),this.prevMotionValues),this.handleChildMotionValue&&this.handleChildMotionValue()}getProps(){return this.props}getVariant(t){return this.props.variants?this.props.variants[t]:void 0}getDefaultTransition(){return this.props.transition}getTransformPagePoint(){return this.props.transformPagePoint}getClosestVariantNode(){return this.isVariantNode?this:this.parent?this.parent.getClosestVariantNode():void 0}getVariantContext(t=!1){if(t)return this.parent?this.parent.getVariantContext():void 0;if(!this.isControllingVariants){const r=this.parent?this.parent.getVariantContext()||{}:{};return this.props.initial!==void 0&&(r.initial=this.props.initial),r}const n={};for(let r=0;r<jw;r++){const i=Ba[r],o=this.props[i];(Yr(o)||o===!1)&&(n[i]=o)}return n}addVariantChild(t){const n=this.getClosestVariantNode();if(n)return n.variantChildren&&n.variantChildren.add(t),()=>n.variantChildren.delete(t)}addValue(t,n){n!==this.values.get(t)&&(this.removeValue(t),this.bindToMotionValue(t,n)),this.values.set(t,n),this.latestValues[t]=n.get()}removeValue(t){this.values.delete(t);const n=this.valueSubscriptions.get(t);n&&(n(),this.valueSubscriptions.delete(t)),delete this.latestValues[t],this.removeValueFromRenderState(t,this.renderState)}hasValue(t){return this.values.has(t)}getValue(t,n){if(this.props.values&&this.props.values[t])return this.props.values[t];let r=this.values.get(t);return r===void 0&&n!==void 0&&(r=bn(n,{owner:this}),this.addValue(t,r)),r}readValue(t){return this.latestValues[t]!==void 0||!this.current?this.latestValues[t]:this.readValueFromInstance(this.current,t,this.options)}setBaseTarget(t,n){this.baseTarget[t]=n}getBaseTarget(t){var n;const{initial:r}=this.props,i=typeof r=="string"||typeof r=="object"?(n=Xa(this.props,r))===null||n===void 0?void 0:n[t]:void 0;if(r&&i!==void 0)return i;const o=this.getBaseTargetFromProps(this.props,t);return o!==void 0&&!Ve(o)?o:this.initialValues[t]!==void 0&&i===void 0?void 0:this.baseTarget[t]}on(t,n){return this.events[t]||(this.events[t]=new iu),this.events[t].add(n)}notify(t,...n){this.events[t]&&this.events[t].notify(...n)}}class lm extends Fw{sortInstanceNodePosition(t,n){return t.compareDocumentPosition(n)&2?1:-1}getBaseTargetFromProps(t,n){return t.style?t.style[n]:void 0}removeValueFromRenderState(t,{vars:n,style:r}){delete n[t],delete r[t]}makeTargetAnimatableFromInstance({transition:t,transitionEnd:n,...r},{transformValues:i},o){let s=r1(r,t||{},this);if(i&&(n&&(n=i(n)),r&&(r=i(r)),s&&(s=i(s))),o){t1(this,r,s);const l=Aw(this,r,s,n);n=l.transitionEnd,r=l.target}return{transition:t,transitionEnd:n,...r}}}function Iw(e){return window.getComputedStyle(e)}class zw extends lm{readValueFromInstance(t,n){if(wn.has(n)){const r=eu(n);return r&&r.default||0}else{const r=Iw(t),i=(Yp(n)?r.getPropertyValue(n):r[n])||0;return typeof i=="string"?i.trim():i}}measureInstanceViewportBox(t,{transformPagePoint:n}){return Zh(t,n)}build(t,n,r,i){Ha(t,n,r,i.transformTemplate)}scrapeMotionValuesFromProps(t,n){return Ya(t,n)}handleChildMotionValue(){this.childSubscription&&(this.childSubscription(),delete this.childSubscription);const{children:t}=this.props;Ve(t)&&(this.childSubscription=t.on("change",n=>{this.current&&(this.current.textContent=`${n}`)}))}renderInstance(t,n,r,i){eh(t,n,r,i)}}class Bw extends lm{constructor(){super(...arguments),this.isSVGTag=!1}getBaseTargetFromProps(t,n){return t[n]}readValueFromInstance(t,n){if(wn.has(n)){const r=eu(n);return r&&r.default||0}return n=th.has(n)?n:Qa(n),t.getAttribute(n)}measureInstanceViewportBox(){return ne()}scrapeMotionValuesFromProps(t,n){return rh(t,n)}build(t,n,r,i){Ga(t,n,r,this.isSVGTag,i.transformTemplate)}renderInstance(t,n,r,i){nh(t,n,r,i)}mount(t){this.isSVGTag=Ka(t.tagName),super.mount(t)}}const Uw=(e,t)=>$a(e)?new Bw(t,{enableHardwareAcceleration:!1}):new zw(t,{enableHardwareAcceleration:!0}),$w={layout:{ProjectionNode:rm,MeasureLayout:qh}},Hw={...y1,...I0,...xw,...$w},ou=Ky((e,t)=>S0(e,t,Hw,Uw));function am(){const e=S.useRef(!1);return po(()=>(e.current=!0,()=>{e.current=!1}),[]),e}function Ww(){const e=am(),[t,n]=S.useState(0),r=S.useCallback(()=>{e.current&&n(t+1)},[t]);return[S.useCallback(()=>Q.postRender(r),[r]),t]}class Gw extends S.Component{getSnapshotBeforeUpdate(t){const n=this.props.childRef.current;if(n&&t.isPresent&&!this.props.isPresent){const r=this.props.sizeRef.current;r.height=n.offsetHeight||0,r.width=n.offsetWidth||0,r.top=n.offsetTop,r.left=n.offsetLeft}return null}componentDidUpdate(){}render(){return this.props.children}}function Kw({children:e,isPresent:t}){const n=S.useId(),r=S.useRef(null),i=S.useRef({width:0,height:0,top:0,left:0});return S.useInsertionEffect(()=>{const{width:o,height:s,top:l,left:a}=i.current;if(t||!r.current||!o||!s)return;r.current.dataset.motionPopId=n;const u=document.createElement("style");return document.head.appendChild(u),u.sheet&&u.sheet.insertRule(`
-          [data-motion-pop-id="${n}"] {
-            position: absolute !important;
-            width: ${o}px !important;
-            height: ${s}px !important;
-            top: ${l}px !important;
-            left: ${a}px !important;
-          }
-        `),()=>{document.head.removeChild(u)}},[t]),S.createElement(Gw,{isPresent:t,childRef:r,sizeRef:i},S.cloneElement(e,{ref:r}))}const Ns=({children:e,initial:t,isPresent:n,onExitComplete:r,custom:i,presenceAffectsLayout:o,mode:s})=>{const l=ih(Qw),a=S.useId(),u=S.useMemo(()=>({id:a,initial:t,isPresent:n,custom:i,onExitComplete:c=>{l.set(c,!0);for(const f of l.values())if(!f)return;r&&r()},register:c=>(l.set(c,!1),()=>l.delete(c))}),o?void 0:[n]);return S.useMemo(()=>{l.forEach((c,f)=>l.set(f,!1))},[n]),S.useEffect(()=>{!n&&!l.size&&r&&r()},[n]),s==="popLayout"&&(e=S.createElement(Kw,{isPresent:n},e)),S.createElement(zo.Provider,{value:u},e)};function Qw(){return new Map}function Yw(e){return S.useEffect(()=>()=>e(),[])}const kn=e=>e.key||"";function Xw(e,t){e.forEach(n=>{const r=kn(n);t.set(r,n)})}function Zw(e){const t=[];return S.Children.forEach(e,n=>{S.isValidElement(n)&&t.push(n)}),t}const Os=({children:e,custom:t,initial:n=!0,onExitComplete:r,exitBeforeEnter:i,presenceAffectsLayout:o=!0,mode:s="sync"})=>{const l=S.useContext(Ua).forceRender||Ww()[0],a=am(),u=Zw(e);let c=u;const f=S.useRef(new Map).current,p=S.useRef(c),g=S.useRef(new Map).current,y=S.useRef(!0);if(po(()=>{y.current=!1,Xw(u,g),p.current=c}),Yw(()=>{y.current=!0,g.clear(),f.clear()}),y.current)return S.createElement(S.Fragment,null,c.map(d=>S.createElement(Ns,{key:kn(d),isPresent:!0,initial:n?void 0:!1,presenceAffectsLayout:o,mode:s},d)));c=[...c];const v=p.current.map(kn),T=u.map(kn),m=v.length;for(let d=0;d<m;d++){const h=v[d];T.indexOf(h)===-1&&!f.has(h)&&f.set(h,void 0)}return s==="wait"&&f.size&&(c=[]),f.forEach((d,h)=>{if(T.indexOf(h)!==-1)return;const w=g.get(h);if(!w)return;const x=v.indexOf(h);let C=d;if(!C){const E=()=>{g.delete(h),f.delete(h);const k=p.current.findIndex(V=>V.key===h);if(p.current.splice(k,1),!f.size){if(p.current=u,a.current===!1)return;l(),r&&r()}};C=S.createElement(Ns,{key:kn(w),isPresent:!1,onExitComplete:E,custom:t,presenceAffectsLayout:o,mode:s},w),f.set(h,C)}c.splice(x,0,C)}),c=c.map(d=>{const h=d.key;return f.has(h)?d:S.createElement(Ns,{key:kn(d),isPresent:!0,presenceAffectsLayout:o,mode:s},d)}),S.createElement(S.Fragment,null,f.size?c:c.map(d=>S.cloneElement(d)))},qw={hidden:{y:"-100vh",transition:{delay:.1,type:"spring",damping:10,stiffness:100}},visible:{y:"0",opacity:1,transition:{type:"spring",damping:10,stiffness:100}}},Jw=({onClick:e,gameState:t})=>O.jsxs(ou.div,{initial:"hidden",animate:"visible",variants:qw,exit:"hidden",className:"absolute w-full h-full flex justify-center items-center flex-col px-8 text-center",children:[O.jsx("h1",{className:"sm:text-8xl text-7xl mb-4 font-extrabold tracking-tight text-slate-900 text-center",children:"Doodle Dash"}),O.jsx("h2",{className:"sm:text-2xl text-xl mb-3 font-semibold text-slate-900",children:"How fast can a neural network predict your doodles?"}),O.jsxs("button",{onClick:e,disabled:t!=="menu",type:"button",className:`
-          inline-flex items-center px-4 py-2 font-semibold
-          leading-6 shadow rounded-md text-white bg-indigo-500 hover:bg-indigo-400
-          transition ease-in-out duration-150 ${t==="loading"?"cursor-not-allowed":""}
-          `,children:[t==="loading"&&O.jsxs("svg",{className:"animate-spin -ml-1 mr-3 h-5 w-5 text-white",xmlns:"http://www.w3.org/2000/svg",fill:"none",viewBox:"0 0 24 24",children:[O.jsx("circle",{className:"opacity-25",cx:"12",cy:"12",r:"10",stroke:"currentColor",strokeWidth:"4"}),O.jsx("path",{className:"opacity-75",fill:"currentColor",d:"M4 12a8 8 0 018-8V0C5.373 0 0 5.373 0 12h4zm2 5.291A7.962 7.962 0 014 12H0c0 3.042 1.135 5.824 3 7.938l3-2.647z"})]}),t==="loading"?"Loading neural network...":"Play Game"]})]}),bw={hidden:{y:"-100vh",transition:{delay:.1,type:"spring",damping:10,stiffness:100}},visible:{y:"0",opacity:1,transition:{type:"spring",damping:10,stiffness:100}}};function ex(e){const t=document.createElement("canvas"),n=t.getContext("2d");return t.width=e.width,t.height=e.height,n.putImageData(e,0,0),t.toDataURL()}const tx=({predictions:e,onClick:t})=>(console.log("predictions",e),O.jsxs(ou.div,{initial:"hidden",animate:"visible",variants:bw,exit:"hidden",className:"absolute w-full h-full flex justify-center items-center flex-col px-8 text-center",children:[O.jsx("h1",{className:"sm:text-7xl text-6xl mb-3 font-bold tracking-tight text-slate-900 text-center",children:"Game Over!"}),O.jsxs("h2",{className:"mb-4 sm:text-2xl text-xl font-semibold text-slate-900",children:["Score: ",e.filter(n=>n.correct).length," / ",e.length]}),O.jsx("div",{className:"overflow-x-auto flex gap-4 px-8 p-4 rounded-lg shadow-[0_5px_25px_-5px_rgb(0,0,0,0.1),_0_8px_10px_-6px_rgb(0,0,0,0.1);]",children:e.map((n,r)=>O.jsxs("div",{className:"flex justify-center items-center w-full flex-col",children:[O.jsx("img",{className:"max-h-[12rem] min-w-[12rem]",src:n.image?ex(n.image):""}),O.jsxs("p",{className:"text-slate-900 text-lg font-semibold mt-2",children:[n.target," ",n.correct?"✅":"❌"]})]},r))}),O.jsxs("div",{className:"flex mt-6 gap-4",children:[O.jsx("button",{onClick:()=>t(!0),type:"button",className:`
-          inline-flex items-center px-4 py-2 font-semibold
-          leading-6 shadow rounded-md text-white bg-indigo-500 hover:bg-indigo-400
-          transition ease-in-out duration-150
-          `,children:"Play Again"}),O.jsx("button",{onClick:()=>t(!1),type:"button",className:`
-    inline-flex items-center px-4 py-2 font-semibold
-    leading-6 shadow rounded-md text-white bg-yellow-500 hover:bg-yellow-400
-    transition ease-in-out duration-150
-  `,children:"Main Menu"})]})]})),nx={hidden:{y:"100vh",transition:{delay:.1,type:"spring",damping:10,stiffness:100}},visible:{y:"0",opacity:1,transition:{type:"spring",damping:10,stiffness:100}},exit:{scale:8,opacity:0,transition:{duration:1,type:"ease-out"}}},rx=({countdown:e})=>O.jsx(ou.div,{initial:"hidden",animate:"visible",variants:nx,exit:"exit",className:"pointer-events-none absolute w-full h-full flex justify-center items-center",children:O.jsx("h1",{style:{transform:"translateY(-0.8rem)"},className:"text-9xl",children:e>0?e:"Draw!"})}),ix=e=>{e=Math.floor(e);const t=Math.floor(e/60),n=e%60;return`${t.toString().padStart(2,"0")}:${n.toString().padStart(2,"0")}`};function ox(e){for(let t=e.length-1;t>0;t--){const n=Math.floor(Math.random()*(t+1));[e[t],e[n]]=[e[n],e[t]]}}function Df(e,t,n){return e*(1-n)+t*n}function sx(){const[e,t]=S.useState(!1),[n,r]=S.useState("menu"),[i,o]=S.useState(Te.COUNTDOWN_TIMER),[s,l]=S.useState(null),[a,u]=S.useState(null),[c,f]=S.useState(null),[p,g]=S.useState(!1),[y,v]=S.useState(!1),[T,m]=S.useState(null),[d,h]=S.useState(0),[w,x]=S.useState([]),C=S.useRef(null);S.useEffect(()=>{C.current||(C.current=new Worker(new URL("/assets/worker-6c635e10.js",self.location),{type:"module"}));const D=F=>{const Be=F.data;switch(Be.status){case"ready":t(!0),j();break;case"update":break;case"result":g(!1);{const ee=Be.data.filter(Ue=>!Te.BANNED_LABELS.includes(Ue.label)),me=k.current.getTimeSpentDrawing()-Te.EASY_MODE_DELAY;if(me>0&&ee[0].score>Te.EASY_MODE_THRESHOLD){const Ue=Math.min(1,me/Te.EASY_MODE_DURATION);for(let Xe=0;Xe<ee.length;++Xe)if(ee[Xe].label===T[d]){ee[Xe].score=Df(ee[Xe].score,1,Ue);break}else{const Jt=(1-Ue)/(ee.length-1);ee[Xe].score=Df(ee[Xe].score,0,Jt)}ee.sort((Xe,Jt)=>Jt.score-Xe.score)}f(ee)}break}};return C.current.addEventListener("message",D),()=>C.current.removeEventListener("message",D)});const E=S.useCallback(()=>{if(C.current&&k.current){const D=k.current.getCanvasData();D!==null&&(g(!0),C.current.postMessage({action:"classify",image:D}))}},[]),k=S.useRef(null),V=(D=!1)=>{$(D)},R=(D=!1)=>{k.current&&k.current.clearCanvas(D)},j=()=>{r("countdown");const D=Object.values(Te.LABELS).filter(F=>!Te.BANNED_LABELS.includes(F));ox(D),m(D),h(0)},de=()=>{e?j():(r("loading"),C.current.postMessage({action:"load"}))},pe=D=>{D?j():$(!0)};S.useEffect(()=>{n==="countdown"&&i<=0&&(u(performance.now()),x([]),r("playing"))},[n,i]);const U=S.useCallback(D=>{const F=k.current.getCanvasData();x(Be=>[...Be,{output:(c==null?void 0:c[0])??null,image:F,correct:D,target:T[d]}])},[c,d,T]),$=S.useCallback((D=!1)=>{D||U(!1),u(null),f(null),v(!1),R(!0),o(Te.COUNTDOWN_TIMER),r(D?"menu":"end")},[U]);S.useEffect(()=>{n==="playing"&&s!==null&&a!==null&&(s-a)/1e3>Te.GAME_DURATION&&$()},[$,n,a,s]);const he=S.useCallback((D=!1)=>{D||u(F=>F-Te.SKIP_PENALTY),U(D),h(F=>F+1),f(null),v(!1),R(!0)},[U]);S.useEffect(()=>{n==="playing"&&c!==null&&T!==null&&T[d]===c[0].label&&he(!0)},[he,n,c,T,d]),S.useEffect(()=>{if(n==="countdown"){const D=setInterval(()=>{o(F=>F-1)},1e3);return()=>{clearInterval(D)}}else if(n==="playing"){const D=setInterval(()=>{y&&!p&&E(),v(!1),l(performance.now())},Te.PREDICTION_REFRESH_TIME);return()=>{clearInterval(D)}}else n==="end"&&R(!0)},[n,p,y,U,E]),S.useEffect(()=>{if(n==="playing"){const D=F=>F.preventDefault();return document.addEventListener("touchmove",D,{passive:!1}),()=>{document.removeEventListener("touchmove",D,{passive:!1})}}},[n]);const Ae=n==="menu"||n==="loading",L=n==="playing",_=n==="countdown",N=n==="end";return O.jsxs(O.Fragment,{children:[O.jsx("div",{className:"h-full w-full top-0 left-0 absolute",children:O.jsx(Up,{onSketchChange:()=>{v(!0)},ref:k})}),O.jsx(Os,{initial:!1,mode:"wait",children:Ae&&O.jsx(Jw,{gameState:n,onClick:de})}),O.jsx(Os,{initial:!1,mode:"wait",children:_&&O.jsx(rx,{countdown:i})}),O.jsx(Os,{initial:!1,mode:"wait",children:N&&O.jsx(tx,{predictions:w,onClick:pe})}),L&&s!==null&&T&&O.jsxs("div",{className:"absolute top-5 text-center",children:[O.jsxs("h2",{className:"text-4xl",children:['Draw "',T[d],'"']}),O.jsx("h3",{className:"text-2xl",children:ix(Math.max(Te.GAME_DURATION-(s-a)/1e3,0))})]}),Ae&&O.jsxs("div",{className:"absolute bottom-4",children:["Made with"," ",O.jsx("a",{className:"underline",href:"https://github.com/xenova/transformers.js",children:"🤗 Transformers.js"})]}),L&&O.jsxs("div",{className:"absolute bottom-5 text-center",children:[O.jsx("h1",{className:"text-2xl font-bold mb-3",children:c&&`Prediction: ${c[0].label} (${(100*c[0].score).toFixed(1)}%)`}),O.jsxs("div",{className:"flex gap-2 justify-center",children:[O.jsx("button",{onClick:()=>{R()},children:"Clear"}),O.jsx("button",{onClick:()=>{he(!1)},children:"Skip"}),O.jsx("button",{onClick:()=>{V(!0)},children:"Exit"})]})]})]})}js.createRoot(document.getElementById("root")).render(O.jsx(Yl.StrictMode,{children:O.jsx(sx,{})}));
diff --git a/spaces/XzJosh/Azuma-Bert-VITS2/losses.py b/spaces/XzJosh/Azuma-Bert-VITS2/losses.py
deleted file mode 100644
index fb22a0e834dd87edaa37bb8190eee2c3c7abe0d5..0000000000000000000000000000000000000000
--- a/spaces/XzJosh/Azuma-Bert-VITS2/losses.py
+++ /dev/null
@@ -1,61 +0,0 @@
-import torch 
-from torch.nn import functional as F
-
-import commons
-
-
-def feature_loss(fmap_r, fmap_g):
-  loss = 0
-  for dr, dg in zip(fmap_r, fmap_g):
-    for rl, gl in zip(dr, dg):
-      rl = rl.float().detach()
-      gl = gl.float()
-      loss += torch.mean(torch.abs(rl - gl))
-
-  return loss * 2 
-
-
-def discriminator_loss(disc_real_outputs, disc_generated_outputs):
-  loss = 0
-  r_losses = []
-  g_losses = []
-  for dr, dg in zip(disc_real_outputs, disc_generated_outputs):
-    dr = dr.float()
-    dg = dg.float()
-    r_loss = torch.mean((1-dr)**2)
-    g_loss = torch.mean(dg**2)
-    loss += (r_loss + g_loss)
-    r_losses.append(r_loss.item())
-    g_losses.append(g_loss.item())
-
-  return loss, r_losses, g_losses
-
-
-def generator_loss(disc_outputs):
-  loss = 0
-  gen_losses = []
-  for dg in disc_outputs:
-    dg = dg.float()
-    l = torch.mean((1-dg)**2)
-    gen_losses.append(l)
-    loss += l
-
-  return loss, gen_losses
-
-
-def kl_loss(z_p, logs_q, m_p, logs_p, z_mask):
-  """
-  z_p, logs_q: [b, h, t_t]
-  m_p, logs_p: [b, h, t_t]
-  """
-  z_p = z_p.float()
-  logs_q = logs_q.float()
-  m_p = m_p.float()
-  logs_p = logs_p.float()
-  z_mask = z_mask.float()
-
-  kl = logs_p - logs_q - 0.5
-  kl += 0.5 * ((z_p - m_p)**2) * torch.exp(-2. * logs_p)
-  kl = torch.sum(kl * z_mask)
-  l = kl / torch.sum(z_mask)
-  return l
diff --git a/spaces/XzJosh/Nana7mi-Bert-VITS2/text/symbols.py b/spaces/XzJosh/Nana7mi-Bert-VITS2/text/symbols.py
deleted file mode 100644
index 9dfae4e633829f20c4fd767b1c7a9198911ed801..0000000000000000000000000000000000000000
--- a/spaces/XzJosh/Nana7mi-Bert-VITS2/text/symbols.py
+++ /dev/null
@@ -1,51 +0,0 @@
-punctuation = ['!', '?', '…', ",", ".", "'", '-']
-pu_symbols = punctuation + ["SP", "UNK"]
-pad = '_'
-
-# chinese
-zh_symbols = ['E', 'En', 'a', 'ai', 'an', 'ang', 'ao', 'b', 'c', 'ch', 'd', 'e', 'ei', 'en', 'eng', 'er', 'f', 'g', 'h',
-       'i', 'i0', 'ia', 'ian', 'iang', 'iao', 'ie', 'in', 'ing', 'iong', 'ir', 'iu', 'j', 'k', 'l', 'm', 'n', 'o',
-       'ong',
-       'ou', 'p', 'q', 'r', 's', 'sh', 't', 'u', 'ua', 'uai', 'uan', 'uang', 'ui', 'un', 'uo', 'v', 'van', 've', 'vn',
-       'w', 'x', 'y', 'z', 'zh',
-        "AA", "EE", "OO"]
-num_zh_tones = 6
-
-# japanese
-ja_symbols = ['I', 'N', 'U', 'a', 'b', 'by', 'ch', 'cl', 'd', 'dy', 'e', 'f', 'g', 'gy', 'h', 'hy', 'i', 'j', 'k', 'ky',
-              'm', 'my', 'n', 'ny', 'o', 'p', 'py', 'r', 'ry', 's', 'sh', 't', 'ts', 'u', 'V', 'w', 'y', 'z']
-num_ja_tones = 1
-
-# English
-en_symbols = ['aa', 'ae', 'ah', 'ao', 'aw', 'ay', 'b', 'ch', 'd', 'dh', 'eh', 'er', 'ey', 'f', 'g', 'hh', 'ih', 'iy',
-              'jh', 'k', 'l', 'm', 'n', 'ng', 'ow', 'oy', 'p', 'r', 's',
-              'sh', 't', 'th', 'uh', 'uw', 'V', 'w', 'y', 'z', 'zh']
-num_en_tones = 4
-
-# combine all symbols
-normal_symbols = sorted(set(zh_symbols + ja_symbols + en_symbols))
-symbols = [pad] + normal_symbols + pu_symbols
-sil_phonemes_ids = [symbols.index(i) for i in pu_symbols]
-
-# combine all tones
-num_tones = num_zh_tones + num_ja_tones + num_en_tones
-
-# language maps
-language_id_map = {
-    'ZH': 0,
-    "JA": 1,
-    "EN": 2
-}
-num_languages = len(language_id_map.keys())
-
-language_tone_start_map = {
-    'ZH': 0,
-    "JA": num_zh_tones,
-    "EN": num_zh_tones + num_ja_tones
-}
-
-if __name__ == '__main__':
-    a = set(zh_symbols)
-    b = set(en_symbols)
-    print(sorted(a&b))
-
diff --git a/spaces/YUANAI/DiffspeechResearch/tasks/tts/ps_flow.py b/spaces/YUANAI/DiffspeechResearch/tasks/tts/ps_flow.py
deleted file mode 100644
index 37a2469ed08d382b58bcb6b8b1750986bb3dd345..0000000000000000000000000000000000000000
--- a/spaces/YUANAI/DiffspeechResearch/tasks/tts/ps_flow.py
+++ /dev/null
@@ -1,134 +0,0 @@
-import torch
-from modules.tts.portaspeech.portaspeech_flow import PortaSpeechFlow
-from tasks.tts.fs import FastSpeechTask
-from tasks.tts.ps import PortaSpeechTask
-from utils.audio.pitch.utils import denorm_f0
-from utils.commons.hparams import hparams
-
-
-class PortaSpeechFlowTask(PortaSpeechTask):
-    def __init__(self):
-        super().__init__()
-        self.training_post_glow = False
-
-    def build_tts_model(self):
-        ph_dict_size = len(self.token_encoder)
-        word_dict_size = len(self.word_encoder)
-        self.model = PortaSpeechFlow(ph_dict_size, word_dict_size, hparams)
-
-    def _training_step(self, sample, batch_idx, opt_idx):
-        self.training_post_glow = self.global_step >= hparams['post_glow_training_start'] \
-                                  and hparams['use_post_flow']
-        if hparams['two_stage'] and \
-                ((opt_idx == 0 and self.training_post_glow) or (opt_idx == 1 and not self.training_post_glow)):
-            return None
-        loss_output, _ = self.run_model(sample)
-        total_loss = sum([v for v in loss_output.values() if isinstance(v, torch.Tensor) and v.requires_grad])
-        loss_output['batch_size'] = sample['txt_tokens'].size()[0]
-        if 'postflow' in loss_output and loss_output['postflow'] is None:
-            return None
-        return total_loss, loss_output
-
-    def run_model(self, sample, infer=False, *args, **kwargs):
-        if not infer:
-            training_post_glow = self.training_post_glow
-            spk_embed = sample.get('spk_embed')
-            spk_id = sample.get('spk_ids')
-            output = self.model(sample['txt_tokens'],
-                                sample['word_tokens'],
-                                ph2word=sample['ph2word'],
-                                mel2word=sample['mel2word'],
-                                mel2ph=sample['mel2ph'],
-                                word_len=sample['word_lengths'].max(),
-                                tgt_mels=sample['mels'],
-                                pitch=sample.get('pitch'),
-                                spk_embed=spk_embed,
-                                spk_id=spk_id,
-                                infer=False,
-                                forward_post_glow=training_post_glow,
-                                two_stage=hparams['two_stage'],
-                                global_step=self.global_step)
-            losses = {}
-            self.add_mel_loss(output['mel_out'], sample['mels'], losses)
-            if (training_post_glow or not hparams['two_stage']) and hparams['use_post_flow']:
-                losses['postflow'] = output['postflow']
-                losses['l1'] = losses['l1'].detach()
-                losses['ssim'] = losses['ssim'].detach()
-            if not training_post_glow or not hparams['two_stage'] or not self.training:
-                losses['kl'] = output['kl']
-                if self.global_step < hparams['kl_start_steps']:
-                    losses['kl'] = losses['kl'].detach()
-                else:
-                    losses['kl'] = torch.clamp(losses['kl'], min=hparams['kl_min'])
-                losses['kl'] = losses['kl'] * hparams['lambda_kl']
-                if hparams['dur_level'] == 'word':
-                    self.add_dur_loss(
-                        output['dur'], sample['mel2word'], sample['word_lengths'], sample['txt_tokens'], losses)
-                    self.get_attn_stats(output['attn'], sample, losses)
-                else:
-                    super().add_dur_loss(output['dur'], sample['mel2ph'], sample['txt_tokens'], losses)
-            return losses, output
-        else:
-            use_gt_dur = kwargs.get('infer_use_gt_dur', hparams['use_gt_dur'])
-            forward_post_glow = self.global_step >= hparams['post_glow_training_start'] + 1000 \
-                                and hparams['use_post_flow']
-            spk_embed = sample.get('spk_embed')
-            spk_id = sample.get('spk_ids')
-            output = self.model(
-                sample['txt_tokens'],
-                sample['word_tokens'],
-                ph2word=sample['ph2word'],
-                word_len=sample['word_lengths'].max(),
-                pitch=sample.get('pitch'),
-                mel2ph=sample['mel2ph'] if use_gt_dur else None,
-                mel2word=sample['mel2word'] if hparams['profile_infer'] or hparams['use_gt_dur'] else None,
-                infer=True,
-                forward_post_glow=forward_post_glow,
-                spk_embed=spk_embed,
-                spk_id=spk_id,
-                two_stage=hparams['two_stage']
-            )
-            return output
-
-    def validation_step(self, sample, batch_idx):
-        self.training_post_glow = self.global_step >= hparams['post_glow_training_start'] \
-                                  and hparams['use_post_flow']
-        return super().validation_step(sample, batch_idx)
-
-    def save_valid_result(self, sample, batch_idx, model_out):
-        super(PortaSpeechFlowTask, self).save_valid_result(sample, batch_idx, model_out)
-        sr = hparams['audio_sample_rate']
-        f0_gt = None
-        if sample.get('f0') is not None:
-            f0_gt = denorm_f0(sample['f0'][0].cpu(), sample['uv'][0].cpu())
-        if self.global_step > 0:
-            # save FVAE result
-            if hparams['use_post_flow']:
-                wav_pred = self.vocoder.spec2wav(model_out['mel_out_fvae'][0].cpu(), f0=f0_gt)
-                self.logger.add_audio(f'wav_fvae_{batch_idx}', wav_pred, self.global_step, sr)
-                self.plot_mel(batch_idx, sample['mels'], model_out['mel_out_fvae'][0],
-                              f'mel_fvae_{batch_idx}', f0s=f0_gt)
-
-    def build_optimizer(self, model):
-        if hparams['two_stage'] and hparams['use_post_flow']:
-            self.optimizer = torch.optim.AdamW(
-                [p for name, p in self.model.named_parameters() if 'post_flow' not in name],
-                lr=hparams['lr'],
-                betas=(hparams['optimizer_adam_beta1'], hparams['optimizer_adam_beta2']),
-                weight_decay=hparams['weight_decay'])
-            self.post_flow_optimizer = torch.optim.AdamW(
-                self.model.post_flow.parameters(),
-                lr=hparams['post_flow_lr'],
-                betas=(hparams['optimizer_adam_beta1'], hparams['optimizer_adam_beta2']),
-                weight_decay=hparams['weight_decay'])
-            return [self.optimizer, self.post_flow_optimizer]
-        else:
-            self.optimizer = torch.optim.AdamW(
-                self.model.parameters(),
-                lr=hparams['lr'],
-                betas=(hparams['optimizer_adam_beta1'], hparams['optimizer_adam_beta2']),
-                weight_decay=hparams['weight_decay'])
-            return [self.optimizer]
-
-    def build_scheduler(self, optimizer):
-        return FastSpeechTask.build_scheduler(self, optimizer[0])
\ No newline at end of file
diff --git a/spaces/Zhenhong/text-to-speech-SpeechT5-demo/README.md b/spaces/Zhenhong/text-to-speech-SpeechT5-demo/README.md
deleted file mode 100644
index 22e3781d9f850db3b272f200e701afe5ecebdb3e..0000000000000000000000000000000000000000
--- a/spaces/Zhenhong/text-to-speech-SpeechT5-demo/README.md
+++ /dev/null
@@ -1,13 +0,0 @@
----
-title: Text To Speech SpeechT5 Demo
-emoji: 🚀
-colorFrom: red
-colorTo: purple
-sdk: gradio
-sdk_version: 3.17.0
-app_file: app.py
-pinned: true
-license: afl-3.0
----
-
-Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
\ No newline at end of file
diff --git a/spaces/aaaaaabbbbbbbdddddddduuuuulllll/Ashaar/poetry_diacritizer/create_configs.py b/spaces/aaaaaabbbbbbbdddddddduuuuulllll/Ashaar/poetry_diacritizer/create_configs.py
deleted file mode 100644
index cd47aacb01ee07c8bc673ff33daff334fe85d0f2..0000000000000000000000000000000000000000
--- a/spaces/aaaaaabbbbbbbdddddddduuuuulllll/Ashaar/poetry_diacritizer/create_configs.py
+++ /dev/null
@@ -1,13 +0,0 @@
-import yaml
-
-fname = "config/gpt-cls-tash-proc.yml"
-
-stream = open(fname, 'r')
-data = yaml.load(stream,  Loader=yaml.FullLoader)
-
-for i in range(0, 10):
-    data['n_layer'] = i
-    data['log_directory'] = f'log_dir_cls_{i}_tash_proc'
-    data['max_steps'] = 5000
-    with open(f"config/gpt-cls-{i}-tash-proc.yml", 'w') as yaml_file:
-        yaml_file.write( yaml.dump(data, default_flow_style=False))
diff --git a/spaces/abcde1234www/personal-chat-gpt/app.py b/spaces/abcde1234www/personal-chat-gpt/app.py
deleted file mode 100644
index e41cc3d770df09fc1943f00c119bbbd5953b601f..0000000000000000000000000000000000000000
--- a/spaces/abcde1234www/personal-chat-gpt/app.py
+++ /dev/null
@@ -1,101 +0,0 @@
-import os
-import openai
-import gradio as gr
-
-#if you have OpenAI API key as an environment variable, enable the below
-#openai.api_key = os.getenv("OPENAI_API_KEY")
-
-#if you have OpenAI API key as a string, enable the below
-openai.api_key = "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"
-
-start_sequence = "\nAI:"
-restart_sequence = "\nHuman: "
-
-prompt = "The following is a conversation with an AI assistant.\nHuman: "
-
-def openai_create(prompt):
-
-    response = openai.Completion.create(
-    model="text-davinci-003",
-    prompt="\nHuman: Who is Angela Busheska? \nAI: Angela Busheska is the founder of EnRoute! She was chosen as a Forbes 30 Under 30. She is passionate about helping people to reduce carbon emissions. She has given keynotes at Google and Harvard.",
-    temperature=0.9,
-    max_tokens=150,
-    top_p=1,
-    frequency_penalty=0,
-    presence_penalty=0.6,
-    stop=[" Human:", " AI:"]
-)
-
-prompt1 = "What is Angela Busheska passionate about?. "
-
-def openai_create1(prompt1):
-
-    response = openai.Completion.create(
-    model="text-davinci-003",
-    prompt="\nAI: Angela Busheska is passionate about saving the environment. She aspires to help people reduce carbon emissions from shopping and transport activities.",
-    temperature=0.9,
-    max_tokens=150,
-    top_p=1,
-    frequency_penalty=0,
-    presence_penalty=0.6,
-    stop=[" Human:", " AI:"]
-)
-
-prompt2 = "What is Angela Busheska studying?. "
-
-def openai_create1(prompt2):
-
-    response = openai.Completion.create(
-    model="text-davinci-003",
-    prompt="\nAI: Angela Busheska is studying computer science and electrical engineering. Her goal is to utilize technology to solve the greatest problems with climate change. ",
-    temperature=0.9,
-    max_tokens=150,
-    top_p=1,
-    frequency_penalty=0,
-    presence_penalty=0.6,
-    stop=[" Human:", " AI:"]
-)
-
-prompt3 = "What did Angela Busheska discover?. "
-
-def openai_create1(prompt2):
-
-    response = openai.Completion.create(
-    model="text-davinci-003",
-    prompt="\nAI: Angela Busheska created EnRoute to help people reduce their carbon footprint from daily activities. She mobilized over 60.000 people to fight for climate justice.  ",
-    temperature=0.9,
-    max_tokens=150,
-    top_p=1,
-    frequency_penalty=0,
-    presence_penalty=0.6,
-    stop=[" Human:", " AI:"]
-)
-
-    return response.choices[0].text
-
-
-
-def chatgpt_clone(input, history):
-    history = history or []
-    s = list(sum(history, ()))
-    s.append(input)
-    inp = ' '.join(s)
-    output = openai_create(inp)
-    output = openai_create1(inp)
-    history.append((input, output))
-    return history, history
-
-
-block = gr.Blocks()
-
-
-with block:
-    gr.Markdown("""<h1><center>Learn More About Me!</center></h1>
-    """)
-    chatbot = gr.Chatbot()
-    message = gr.Textbox(placeholder=prompt)
-    state = gr.State()
-    submit = gr.Button("SEND")
-    submit.click(chatgpt_clone, inputs=[message, state], outputs=[chatbot, state])
-
-block.launch(debug = True, share = False)
\ No newline at end of file
diff --git a/spaces/abdvl/datahub_qa_bot/docs/actions/actions/executor.md b/spaces/abdvl/datahub_qa_bot/docs/actions/actions/executor.md
deleted file mode 100644
index 784ac43940866072059e257da9e4a6c3ff65c0be..0000000000000000000000000000000000000000
--- a/spaces/abdvl/datahub_qa_bot/docs/actions/actions/executor.md
+++ /dev/null
@@ -1,82 +0,0 @@
-# Ingestion Executor
-<!-- Set Support Status -->
-![Certified](https://img.shields.io/badge/support%20status-certified-brightgreen)
-
-
-## Overview
-
-This Action executes ingestion recipes that are configured via the UI.
-
-### Capabilities
-
-- Executing `datahub ingest` command in a sub-process when an Execution Request command is received from DataHub. (Scheduled or manual ingestion run)
-- Resolving secrets within an ingestion recipe from DataHub
-- Reporting ingestion execution status to DataHub
-
-### Supported Events
-
-- `MetadataChangeLog_v1`
-
-Specifically, changes to the `dataHubExecutionRequestInput` and `dataHubExecutionRequestSignal` aspects of the `dataHubExecutionRequest` entity are required.
-
-
-## Action Quickstart 
-
-### Prerequisites
-
-#### DataHub Privileges
-
-This action must be executed as a privileged DataHub user (e.g. using Personal Access Tokens). Specifically, the user must have the `Manage Secrets` Platform Privilege, which allows for retrieval
-of decrypted secrets for injection into an ingestion recipe. 
-
-An access token generated from a privileged account must be configured in the `datahub` configuration
-block of the YAML configuration, as shown in the example below. 
-
-#### Connecting to Ingestion Sources 
-
-In order for ingestion to run successfully, the process running the Actions must have 
-network connectivity to any source systems that are required for ingestion. 
-
-For example, if the ingestion recipe is pulling from an internal DBMS, the actions container
-must be able to resolve & connect to that DBMS system for the ingestion command to run successfully.
-
-### Install the Plugin(s)
-
-Run the following commands to install the relevant action plugin(s):
-
-`pip install 'acryl-datahub-actions[executor]'`
-
-
-### Configure the Action Config
-
-Use the following config(s) to get started with this Action. 
-
-```yml
-name: "pipeline-name"
-source:
-  # source configs
-action:
-  type: "executor"
-# Requires DataHub API configurations to report to DataHub
-datahub:
-  server: "http://${DATAHUB_GMS_HOST:-localhost}:${DATAHUB_GMS_PORT:-8080}"
-  # token: <token> # Must have "Manage Secrets" privilege
-```
-
-<details>
-  <summary>View All Configuration Options</summary>
-  
-  | Field | Required | Default | Description |
-  | --- | :-: | :-: | --- |
-  | `executor_id` | ❌ | `default` | An executor ID assigned to the executor. This can be used to manage multiple distinct executors. |
-</details>
-
-
-## Troubleshooting
-
-### Quitting the Actions Framework
-
-Currently, when you quit the Actions framework, any in-flight ingestion processing will continue to execute as a subprocess on your system. This means that there may be "orphaned" processes which
-are never marked as "Succeeded" or "Failed" in the UI, even though they may have completed. 
-
-To address this, simply "Cancel" the ingestion source on the UI once you've restarted the Ingestion Executor action. 
diff --git a/spaces/abhishek/sketch-to-image/annotator/uniformer/mmdet/core/anchor/builder.py b/spaces/abhishek/sketch-to-image/annotator/uniformer/mmdet/core/anchor/builder.py
deleted file mode 100644
index d79b448ebca9f2b21d455046623172c48c5c3ef0..0000000000000000000000000000000000000000
--- a/spaces/abhishek/sketch-to-image/annotator/uniformer/mmdet/core/anchor/builder.py
+++ /dev/null
@@ -1,7 +0,0 @@
-from mmcv.utils import Registry, build_from_cfg
-
-ANCHOR_GENERATORS = Registry('Anchor generator')
-
-
-def build_anchor_generator(cfg, default_args=None):
-    return build_from_cfg(cfg, ANCHOR_GENERATORS, default_args)
diff --git a/spaces/abhishek/sketch-to-image/annotator/uniformer/mmdet_null/models/builder.py b/spaces/abhishek/sketch-to-image/annotator/uniformer/mmdet_null/models/builder.py
deleted file mode 100644
index 81c927e507a7c1625ffb114de10e93c94927af25..0000000000000000000000000000000000000000
--- a/spaces/abhishek/sketch-to-image/annotator/uniformer/mmdet_null/models/builder.py
+++ /dev/null
@@ -1,77 +0,0 @@
-import warnings
-
-from mmcv.utils import Registry, build_from_cfg
-from torch import nn
-
-BACKBONES = Registry('backbone')
-NECKS = Registry('neck')
-ROI_EXTRACTORS = Registry('roi_extractor')
-SHARED_HEADS = Registry('shared_head')
-HEADS = Registry('head')
-LOSSES = Registry('loss')
-DETECTORS = Registry('detector')
-
-
-def build(cfg, registry, default_args=None):
-    """Build a module.
-
-    Args:
-        cfg (dict, list[dict]): The config of modules, is is either a dict
-            or a list of configs.
-        registry (:obj:`Registry`): A registry the module belongs to.
-        default_args (dict, optional): Default arguments to build the module.
-            Defaults to None.
-
-    Returns:
-        nn.Module: A built nn module.
-    """
-    if isinstance(cfg, list):
-        modules = [
-            build_from_cfg(cfg_, registry, default_args) for cfg_ in cfg
-        ]
-        return nn.Sequential(*modules)
-    else:
-        return build_from_cfg(cfg, registry, default_args)
-
-
-def build_backbone(cfg):
-    """Build backbone."""
-    return build(cfg, BACKBONES)
-
-
-def build_neck(cfg):
-    """Build neck."""
-    return build(cfg, NECKS)
-
-
-def build_roi_extractor(cfg):
-    """Build roi extractor."""
-    return build(cfg, ROI_EXTRACTORS)
-
-
-def build_shared_head(cfg):
-    """Build shared head."""
-    return build(cfg, SHARED_HEADS)
-
-
-def build_head(cfg):
-    """Build head."""
-    return build(cfg, HEADS)
-
-
-def build_loss(cfg):
-    """Build loss."""
-    return build(cfg, LOSSES)
-
-
-def build_detector(cfg, train_cfg=None, test_cfg=None):
-    """Build detector."""
-    if train_cfg is not None or test_cfg is not None:
-        warnings.warn(
-            'train_cfg and test_cfg is deprecated, '
-            'please specify them in model', UserWarning)
-    assert cfg.get('train_cfg') is None or train_cfg is None, \
-        'train_cfg specified in both outer field and model field '
-    assert cfg.get('test_cfg') is None or test_cfg is None, \
-        'test_cfg specified in both outer field and model field '
-    return build(cfg, DETECTORS, dict(train_cfg=train_cfg, test_cfg=test_cfg))
diff --git a/spaces/abhishek/sketch-to-image/annotator/uniformer/mmdet_null/utils/contextmanagers.py b/spaces/abhishek/sketch-to-image/annotator/uniformer/mmdet_null/utils/contextmanagers.py
deleted file mode 100644
index 38a639262d949b5754dedf12f33fa814b030ea38..0000000000000000000000000000000000000000
--- a/spaces/abhishek/sketch-to-image/annotator/uniformer/mmdet_null/utils/contextmanagers.py
+++ /dev/null
@@ -1,121 +0,0 @@
-import asyncio
-import contextlib
-import logging
-import os
-import time
-from typing import List
-
-import torch
-
-logger = logging.getLogger(__name__)
-
-DEBUG_COMPLETED_TIME = bool(os.environ.get('DEBUG_COMPLETED_TIME', False))
-
-
-@contextlib.asynccontextmanager
-async def completed(trace_name='',
-                    name='',
-                    sleep_interval=0.05,
-                    streams: List[torch.cuda.Stream] = None):
-    """Async context manager that waits for work to complete on given CUDA
-    streams."""
-    if not torch.cuda.is_available():
-        yield
-        return
-
-    stream_before_context_switch = torch.cuda.current_stream()
-    if not streams:
-        streams = [stream_before_context_switch]
-    else:
-        streams = [s if s else stream_before_context_switch for s in streams]
-
-    end_events = [
-        torch.cuda.Event(enable_timing=DEBUG_COMPLETED_TIME) for _ in streams
-    ]
-
-    if DEBUG_COMPLETED_TIME:
-        start = torch.cuda.Event(enable_timing=True)
-        stream_before_context_switch.record_event(start)
-
-        cpu_start = time.monotonic()
-    logger.debug('%s %s starting, streams: %s', trace_name, name, streams)
-    grad_enabled_before = torch.is_grad_enabled()
-    try:
-        yield
-    finally:
-        current_stream = torch.cuda.current_stream()
-        assert current_stream == stream_before_context_switch
-
-        if DEBUG_COMPLETED_TIME:
-            cpu_end = time.monotonic()
-        for i, stream in enumerate(streams):
-            event = end_events[i]
-            stream.record_event(event)
-
-        grad_enabled_after = torch.is_grad_enabled()
-
-        # observed change of torch.is_grad_enabled() during concurrent run of
-        # async_test_bboxes code
-        assert (grad_enabled_before == grad_enabled_after
-                ), 'Unexpected is_grad_enabled() value change'
-
-        are_done = [e.query() for e in end_events]
-        logger.debug('%s %s completed: %s streams: %s', trace_name, name,
-                     are_done, streams)
-        with torch.cuda.stream(stream_before_context_switch):
-            while not all(are_done):
-                await asyncio.sleep(sleep_interval)
-                are_done = [e.query() for e in end_events]
-                logger.debug(
-                    '%s %s completed: %s streams: %s',
-                    trace_name,
-                    name,
-                    are_done,
-                    streams,
-                )
-
-        current_stream = torch.cuda.current_stream()
-        assert current_stream == stream_before_context_switch
-
-        if DEBUG_COMPLETED_TIME:
-            cpu_time = (cpu_end - cpu_start) * 1000
-            stream_times_ms = ''
-            for i, stream in enumerate(streams):
-                elapsed_time = start.elapsed_time(end_events[i])
-                stream_times_ms += f' {stream} {elapsed_time:.2f} ms'
-            logger.info('%s %s %.2f ms %s', trace_name, name, cpu_time,
-                        stream_times_ms)
-
-
-@contextlib.asynccontextmanager
-async def concurrent(streamqueue: asyncio.Queue,
-                     trace_name='concurrent',
-                     name='stream'):
-    """Run code concurrently in different streams.
-
-    :param streamqueue: asyncio.Queue instance.
-
-    Queue tasks define the pool of streams used for concurrent execution.
-    """
-    if not torch.cuda.is_available():
-        yield
-        return
-
-    initial_stream = torch.cuda.current_stream()
-
-    with torch.cuda.stream(initial_stream):
-        stream = await streamqueue.get()
-        assert isinstance(stream, torch.cuda.Stream)
-
-        try:
-            with torch.cuda.stream(stream):
-                logger.debug('%s %s is starting, stream: %s', trace_name, name,
-                             stream)
-                yield
-                current = torch.cuda.current_stream()
-                assert current == stream
-                logger.debug('%s %s has finished, stream: %s', trace_name,
-                             name, stream)
-        finally:
-            streamqueue.task_done()
-            streamqueue.put_nowait(stream)
diff --git a/spaces/abhishek/sketch-to-image/annotator/uniformer_base/mmcv/visualization/__init__.py b/spaces/abhishek/sketch-to-image/annotator/uniformer_base/mmcv/visualization/__init__.py
deleted file mode 100644
index 835df136bdcf69348281d22914d41aa84cdf92b1..0000000000000000000000000000000000000000
--- a/spaces/abhishek/sketch-to-image/annotator/uniformer_base/mmcv/visualization/__init__.py
+++ /dev/null
@@ -1,9 +0,0 @@
-# Copyright (c) OpenMMLab. All rights reserved.
-from .color import Color, color_val
-from .image import imshow, imshow_bboxes, imshow_det_bboxes
-from .optflow import flow2rgb, flowshow, make_color_wheel
-
-__all__ = [
-    'Color', 'color_val', 'imshow', 'imshow_bboxes', 'imshow_det_bboxes',
-    'flowshow', 'flow2rgb', 'make_color_wheel'
-]
diff --git a/spaces/abrar-lohia/text-2-character-anim/pyrender/.eggs/pyglet-2.0.5-py3.10.egg/pyglet/image/__init__.py b/spaces/abrar-lohia/text-2-character-anim/pyrender/.eggs/pyglet-2.0.5-py3.10.egg/pyglet/image/__init__.py
deleted file mode 100644
index 9ccd1697e14de00df62a8f2debbc17810c979798..0000000000000000000000000000000000000000
--- a/spaces/abrar-lohia/text-2-character-anim/pyrender/.eggs/pyglet-2.0.5-py3.10.egg/pyglet/image/__init__.py
+++ /dev/null
@@ -1,2152 +0,0 @@
-"""Image load, capture and high-level texture functions.
-
-Only basic functionality is described here; for full reference see the
-accompanying documentation.
-
-To load an image::
-
-    from pyglet import image
-    pic = image.load('picture.png')
-
-The supported image file types include PNG, BMP, GIF, JPG, and many more,
-somewhat depending on the operating system.  To load an image from a file-like
-object instead of a filename::
-
-    pic = image.load('hint.jpg', file=fileobj)
-
-The hint helps the module locate an appropriate decoder to use based on the
-file extension.  It is optional.
-
-Once loaded, images can be used directly by most other modules of pyglet.  All
-images have a width and height you can access::
-
-    width, height = pic.width, pic.height
-
-You can extract a region of an image (this keeps the original image intact;
-the memory is shared efficiently)::
-
-    subimage = pic.get_region(x, y, width, height)
-
-Remember that y-coordinates are always increasing upwards.
-
-Drawing images
---------------
-
-To draw an image at some point on the screen::
-
-    pic.blit(x, y, z)
-
-This assumes an appropriate view transform and projection have been applied.
-
-Some images have an intrinsic "anchor point": this is the point which will be
-aligned to the ``x`` and ``y`` coordinates when the image is drawn.  By
-default the anchor point is the lower-left corner of the image.  You can use
-the anchor point to center an image at a given point, for example::
-
-    pic.anchor_x = pic.width // 2
-    pic.anchor_y = pic.height // 2
-    pic.blit(x, y, z)
-
-Texture access
---------------
-
-If you are using OpenGL directly, you can access the image as a texture::
-
-    texture = pic.get_texture()
-
-(This is the most efficient way to obtain a texture; some images are
-immediately loaded as textures, whereas others go through an intermediate
-form).  To use a texture with pyglet.gl::
-
-    from pyglet.gl import *
-    glEnable(texture.target)        # typically target is GL_TEXTURE_2D
-    glBindTexture(texture.target, texture.id)
-    # ... draw with the texture
-
-Pixel access
-------------
-
-To access raw pixel data of an image::
-
-    rawimage = pic.get_image_data()
-
-(If the image has just been loaded this will be a very quick operation;
-however if the image is a texture a relatively expensive readback operation
-will occur).  The pixels can be accessed as a string::
-
-    format = 'RGBA'
-    pitch = rawimage.width * len(format)
-    pixels = rawimage.get_data(format, pitch)
-
-"format" strings consist of characters that give the byte order of each color
-component.  For example, if rawimage.format is 'RGBA', there are four color
-components: red, green, blue and alpha, in that order.  Other common format
-strings are 'RGB', 'LA' (luminance, alpha) and 'I' (intensity).
-
-The "pitch" of an image is the number of bytes in a row (this may validly be
-more than the number required to make up the width of the image, it is common
-to see this for word alignment).  If "pitch" is negative the rows of the image
-are ordered from top to bottom, otherwise they are ordered from bottom to top.
-
-Retrieving data with the format and pitch given in `ImageData.format` and
-`ImageData.pitch` avoids the need for data conversion (assuming you can make
-use of the data in this arbitrary format).
-
-"""
-import re
-import weakref
-
-from ctypes import *
-from io import open, BytesIO
-
-import pyglet
-
-from pyglet.gl import *
-from pyglet.gl import gl_info
-from pyglet.util import asbytes
-
-from .codecs import ImageEncodeException, ImageDecodeException
-from .codecs import registry as _codec_registry
-from .codecs import add_default_codecs as _add_default_codecs
-
-from .animation import Animation, AnimationFrame
-from .buffer import *
-from . import atlas
-
-
-class ImageException(Exception):
-    pass
-
-
-def load(filename, file=None, decoder=None):
-    """Load an image from a file.
-
-    :note: You can make no assumptions about the return type; usually it will
-        be ImageData or CompressedImageData, but decoders are free to return
-        any subclass of AbstractImage.
-
-    :Parameters:
-        `filename` : str
-            Used to guess the image format, and to load the file if `file` is
-            unspecified.
-        `file` : file-like object or None
-            Source of image data in any supported format.
-        `decoder` : ImageDecoder or None
-            If unspecified, all decoders that are registered for the filename
-            extension are tried.  If none succeed, the exception from the
-            first decoder is raised.
-
-    :rtype: AbstractImage
-    """
-    if decoder:
-        return decoder.decode(filename, file)
-    else:
-        return _codec_registry.decode(filename, file)
-
-
-def load_animation(filename, file=None, decoder=None):
-    """Load an animation from a file.
-
-    Currently, the only supported format is GIF.
-
-    :Parameters:
-        `filename` : str
-            Used to guess the animation format, and to load the file if `file`
-            is unspecified.
-        `file` : file-like object or None
-            File object containing the animation stream.
-        `decoder` : ImageDecoder or None
-            If unspecified, all decoders that are registered for the filename
-            extension are tried.  If none succeed, the exception from the
-            first decoder is raised.
-
-    :rtype: Animation
-    """
-    if decoder:
-        return decoder.decode_animation(filename, file)
-    else:
-        return _codec_registry.decode_animation(filename, file)
-
-
-def create(width, height, pattern=None):
-    """Create an image optionally filled with the given pattern.
-
-    :note: You can make no assumptions about the return type; usually it will
-        be ImageData or CompressedImageData, but patterns are free to return
-        any subclass of AbstractImage.
-
-    :Parameters:
-        `width` : int
-            Width of image to create
-        `height` : int
-            Height of image to create
-        `pattern` : ImagePattern or None
-            Pattern to fill image with.  If unspecified, the image will
-            initially be transparent.
-
-    :rtype: AbstractImage
-    """
-    if not pattern:
-        pattern = SolidColorImagePattern()
-    return pattern.create_image(width, height)
-
-
-def get_max_texture_size():
-    """Query the maximum texture size available"""
-    size = c_int()
-    glGetIntegerv(GL_MAX_TEXTURE_SIZE, size)
-    return size.value
-
-
-def get_max_array_texture_layers():
-    """Query the maximum TextureArray depth"""
-    max_layers = c_int()
-    glGetIntegerv(GL_MAX_ARRAY_TEXTURE_LAYERS, max_layers)
-    return max_layers.value
-
-
-def _color_as_bytes(color):
-    if len(color) != 4:
-        raise TypeError("color is expected to have 4 components")
-    return bytes(color)
-
-
-class ImagePattern:
-    """Abstract image creation class."""
-
-    def create_image(self, width, height):
-        """Create an image of the given size.
-
-        :Parameters:
-            `width` : int
-                Width of image to create
-            `height` : int
-                Height of image to create
-
-        :rtype: AbstractImage
-        """
-        raise NotImplementedError('abstract')
-
-
-class SolidColorImagePattern(ImagePattern):
-    """Creates an image filled with a solid color."""
-
-    def __init__(self, color=(0, 0, 0, 0)):
-        """Create a solid image pattern with the given color.
-
-        :Parameters:
-            `color` : (int, int, int, int)
-                4-tuple of ints in range [0,255] giving RGBA components of
-                color to fill with.
-
-        """
-        self.color = _color_as_bytes(color)
-
-    def create_image(self, width, height):
-        data = self.color * width * height
-        return ImageData(width, height, 'RGBA', data)
-
-
-class CheckerImagePattern(ImagePattern):
-    """Create an image with a tileable checker image.
-    """
-
-    def __init__(self, color1=(150, 150, 150, 255), color2=(200, 200, 200, 255)):
-        """Initialise with the given colors.
-
-        :Parameters:
-            `color1` : (int, int, int, int)
-                4-tuple of ints in range [0,255] giving RGBA components of
-                color to fill with.  This color appears in the top-left and
-                bottom-right corners of the image.
-            `color2` : (int, int, int, int)
-                4-tuple of ints in range [0,255] giving RGBA components of
-                color to fill with.  This color appears in the top-right and
-                bottom-left corners of the image.
-
-        """
-        self.color1 = _color_as_bytes(color1)
-        self.color2 = _color_as_bytes(color2)
-
-    def create_image(self, width, height):
-        hw = width // 2
-        hh = height // 2
-        row1 = self.color1 * hw + self.color2 * hw
-        row2 = self.color2 * hw + self.color1 * hw
-        data = row1 * hh + row2 * hh
-        return ImageData(width, height, 'RGBA', data)
-
-
-class AbstractImage:
-    """Abstract class representing an image.
-
-    :Parameters:
-        `width` : int
-            Width of image
-        `height` : int
-            Height of image
-        `anchor_x` : int
-            X coordinate of anchor, relative to left edge of image data
-        `anchor_y` : int
-            Y coordinate of anchor, relative to bottom edge of image data
-    """
-    anchor_x = 0
-    anchor_y = 0
-
-    def __init__(self, width, height):
-        self.width = width
-        self.height = height
-
-    def __repr__(self):
-        return "{}(size={}x{})".format(self.__class__.__name__, self.width, self.height)
-
-    def get_image_data(self):
-        """Get an ImageData view of this image.
-
-        Changes to the returned instance may or may not be reflected in this
-        image.
-
-        :rtype: :py:class:`~pyglet.image.ImageData`
-
-        .. versionadded:: 1.1
-        """
-        raise ImageException('Cannot retrieve image data for %r' % self)
-
-    def get_texture(self, rectangle=False):
-        """A :py:class:`~pyglet.image.Texture` view of this image.
-
-        :Parameters:
-            `rectangle` : bool
-                Unused. Kept for compatibility.
-
-                .. versionadded:: 1.1.4.
-        :rtype: :py:class:`~pyglet.image.Texture`
-
-        .. versionadded:: 1.1
-        """
-        raise ImageException('Cannot retrieve texture for %r' % self)
-
-    def get_mipmapped_texture(self):
-        """Retrieve a :py:class:`~pyglet.image.Texture` instance with all mipmap levels filled in.
-
-        :rtype: :py:class:`~pyglet.image.Texture`
-
-        .. versionadded:: 1.1
-        """
-        raise ImageException('Cannot retrieve mipmapped texture for %r' % self)
-
-    def get_region(self, x, y, width, height):
-        """Retrieve a rectangular region of this image.
-
-        :Parameters:
-            `x` : int
-                Left edge of region.
-            `y` : int
-                Bottom edge of region.
-            `width` : int
-                Width of region.
-            `height` : int
-                Height of region.
-
-        :rtype: AbstractImage
-        """
-        raise ImageException('Cannot get region for %r' % self)
-
-    def save(self, filename=None, file=None, encoder=None):
-        """Save this image to a file.
-
-        :Parameters:
-            `filename` : str
-                Used to set the image file format, and to open the output file
-                if `file` is unspecified.
-            `file` : file-like object or None
-                File to write image data to.
-            `encoder` : ImageEncoder or None
-                If unspecified, all encoders matching the filename extension
-                are tried.  If all fail, the exception from the first one
-                attempted is raised.
-
-        """
-        if not file:
-            file = open(filename, 'wb')
-
-        if encoder:
-            encoder.encode(self, filename, file)
-        else:
-            first_exception = None
-            for encoder in _codec_registry.get_encoders(filename):
-                try:
-                    return encoder.encode(self, filename, file)
-                except ImageEncodeException as e:
-                    first_exception = first_exception or e
-                    file.seek(0)
-
-            if not first_exception:
-                raise ImageEncodeException('No image encoders are available')
-            raise first_exception
-
-    def blit(self, x, y, z=0):
-        """Draw this image to the active framebuffers.
-
-        The image will be drawn with the lower-left corner at
-        (``x -`` `anchor_x`, ``y -`` `anchor_y`, ``z``).
-        """
-        raise ImageException('Cannot blit %r.' % self)
-
-    def blit_into(self, source, x, y, z):
-        """Draw `source` on this image.
-
-        `source` will be copied into this image such that its anchor point
-        is aligned with the `x` and `y` parameters.  If this image is a 3D
-        texture, the `z` coordinate gives the image slice to copy into.
-
-        Note that if `source` is larger than this image (or the positioning
-        would cause the copy to go out of bounds) then you must pass a
-        region of `source` to this method, typically using get_region().
-        """
-        raise ImageException('Cannot blit images onto %r.' % self)
-
-    def blit_to_texture(self, target, level, x, y, z=0):
-        """Draw this image on the currently bound texture at `target`.
-
-        This image is copied into the texture such that this image's anchor
-        point is aligned with the given `x` and `y` coordinates of the
-        destination texture.  If the currently bound texture is a 3D texture,
-        the `z` coordinate gives the image slice to blit into.
-        """
-        raise ImageException('Cannot blit %r to a texture.' % self)
-
-
-class AbstractImageSequence:
-    """Abstract sequence of images.
-
-    The sequence is useful for storing image animations or slices of a volume.
-    For efficient access, use the `texture_sequence` member.  The class
-    also implements the sequence interface (`__len__`, `__getitem__`,
-    `__setitem__`).
-    """
-
-    def get_texture_sequence(self):
-        """Get a TextureSequence.
-
-        :rtype: `TextureSequence`
-
-        .. versionadded:: 1.1
-        """
-        raise NotImplementedError('abstract')
-
-    def get_animation(self, period, loop=True):
-        """Create an animation over this image sequence for the given constant
-        framerate.
-
-        :Parameters
-            `period` : float
-                Number of seconds to display each frame.
-            `loop` : bool
-                If True, the animation will loop continuously.
-
-        :rtype: :py:class:`~pyglet.image.Animation`
-
-        .. versionadded:: 1.1
-        """
-        return Animation.from_image_sequence(self, period, loop)
-
-    def __getitem__(self, slice):
-        """Retrieve a (list of) image.
-
-        :rtype: AbstractImage
-        """
-        raise NotImplementedError('abstract')
-
-    def __setitem__(self, slice, image):
-        """Replace one or more images in the sequence.
-
-        :Parameters:
-            `image` : `~pyglet.image.AbstractImage`
-                The replacement image.  The actual instance may not be used,
-                depending on this implementation.
-
-        """
-        raise NotImplementedError('abstract')
-
-    def __len__(self):
-        raise NotImplementedError('abstract')
-
-    def __iter__(self):
-        """Iterate over the images in sequence.
-
-        :rtype: Iterator
-
-        .. versionadded:: 1.1
-        """
-        raise NotImplementedError('abstract')
-
-
-class TextureSequence(AbstractImageSequence):
-    """Interface for a sequence of textures.
-
-    Typical implementations store multiple :py:class:`~pyglet.image.TextureRegion` s within one
-    :py:class:`~pyglet.image.Texture` so as to minimise state changes.
-    """
-
-    def get_texture_sequence(self):
-        return self
-
-
-class UniformTextureSequence(TextureSequence):
-    """Interface for a sequence of textures, each with the same dimensions.
-
-    :Parameters:
-        `item_width` : int
-            Width of each texture in the sequence.
-        `item_height` : int
-            Height of each texture in the sequence.
-
-    """
-
-    def _get_item_width(self):
-        raise NotImplementedError('abstract')
-
-    def _get_item_height(self):
-        raise NotImplementedError('abstract')
-
-    @property
-    def item_width(self):
-        return self._get_item_width()
-
-    @property
-    def item_height(self):
-        return self._get_item_height()
-
-
-class ImageData(AbstractImage):
-    """An image represented as a string of unsigned bytes.
-
-    :Parameters:
-        `data` : str
-            Pixel data, encoded according to `format` and `pitch`.
-        `format` : str
-            The format string to use when reading or writing `data`.
-        `pitch` : int
-            Number of bytes per row.  Negative values indicate a top-to-bottom
-            arrangement.
-
-    """
-    _swap1_pattern = re.compile(asbytes('(.)'), re.DOTALL)
-    _swap2_pattern = re.compile(asbytes('(.)(.)'), re.DOTALL)
-    _swap3_pattern = re.compile(asbytes('(.)(.)(.)'), re.DOTALL)
-    _swap4_pattern = re.compile(asbytes('(.)(.)(.)(.)'), re.DOTALL)
-
-    _current_texture = None
-    _current_mipmap_texture = None
-
-    def __init__(self, width, height, fmt, data, pitch=None):
-        """Initialise image data.
-
-        :Parameters:
-            `width` : int
-                Width of image data
-            `height` : int
-                Height of image data
-            `fmt` : str
-                A valid format string, such as 'RGB', 'RGBA', 'ARGB', etc.
-            `data` : sequence
-                String or array/list of bytes giving the decoded data.
-            `pitch` : int or None
-                If specified, the number of bytes per row.  Negative values
-                indicate a top-to-bottom arrangement.  Defaults to
-                ``width * len(format)``.
-
-        """
-        super().__init__(width, height)
-
-        self._current_format = self._desired_format = fmt.upper()
-        self._current_data = data
-        self.pitch = pitch or width * len(fmt)
-        self._current_pitch = self.pitch
-        self.mipmap_images = []
-
-    def __getstate__(self):
-        return {
-            'width': self.width,
-            'height': self.height,
-            '_current_data': self.get_data(self._current_format, self._current_pitch),
-            '_current_format': self._current_format,
-            '_desired_format': self._desired_format,
-            '_current_pitch': self._current_pitch,
-            'pitch': self.pitch,
-            'mipmap_images': self.mipmap_images
-        }
-
-    def get_image_data(self):
-        return self
-
-    @property
-    def format(self):
-        """Format string of the data.  Read-write.
-
-        :type: str
-        """
-        return self._desired_format
-
-    @format.setter
-    def format(self, fmt):
-        self._desired_format = fmt.upper()
-        self._current_texture = None
-
-    def get_data(self, fmt=None, pitch=None):
-        """Get the byte data of the image.
-
-        :Parameters:
-            `fmt` : str
-                Format string of the return data.
-            `pitch` : int
-                Number of bytes per row.  Negative values indicate a
-                top-to-bottom arrangement.
-
-        .. versionadded:: 1.1
-
-        :rtype: sequence of bytes, or str
-        """
-        fmt = fmt or self._desired_format
-        pitch = pitch or self._current_pitch
-
-        if fmt == self._current_format and pitch == self._current_pitch:
-            return self._current_data
-        return self._convert(fmt, pitch)
-
-    def set_data(self, fmt, pitch, data):
-        """Set the byte data of the image.
-
-        :Parameters:
-            `fmt` : str
-                Format string of the return data.
-            `pitch` : int
-                Number of bytes per row.  Negative values indicate a
-                top-to-bottom arrangement.
-            `data` : str or sequence of bytes
-                Image data.
-
-        .. versionadded:: 1.1
-        """
-        self._current_format = fmt
-        self._current_pitch = pitch
-        self._current_data = data
-        self._current_texture = None
-        self._current_mipmap_texture = None
-
-    def set_mipmap_image(self, level, image):
-        """Set a mipmap image for a particular level.
-
-        The mipmap image will be applied to textures obtained via
-        `get_mipmapped_texture`.
-
-        :Parameters:
-            `level` : int
-                Mipmap level to set image at, must be >= 1.
-            `image` : AbstractImage
-                Image to set.  Must have correct dimensions for that mipmap
-                level (i.e., width >> level, height >> level)
-        """
-
-        if level == 0:
-            raise ImageException('Cannot set mipmap image at level 0 (it is this image)')
-
-        # Check dimensions of mipmap
-        width, height = self.width, self.height
-        for i in range(level):
-            width >>= 1
-            height >>= 1
-        if width != image.width or height != image.height:
-            raise ImageException('Mipmap image has wrong dimensions for level %d' % level)
-
-        # Extend mipmap_images list to required level
-        self.mipmap_images += [None] * (level - len(self.mipmap_images))
-        self.mipmap_images[level - 1] = image
-
-    def create_texture(self, cls, rectangle=False):
-        """Create a texture containing this image.
-
-        :Parameters:
-            `cls` : class (subclass of Texture)
-                Class to construct.
-            `rectangle` : bool
-                Unused. kept for compatibility.
-
-                .. versionadded:: 1.1
-
-        :rtype: cls or cls.region_class
-        """
-        internalformat = self._get_internalformat(self._desired_format)
-        texture = cls.create(self.width, self.height, GL_TEXTURE_2D, internalformat, False, blank_data=False)
-        if self.anchor_x or self.anchor_y:
-            texture.anchor_x = self.anchor_x
-            texture.anchor_y = self.anchor_y
-
-        self.blit_to_texture(texture.target, texture.level, self.anchor_x, self.anchor_y, 0, None)
-
-        return texture
-
-    def get_texture(self, rectangle=False):
-        if not self._current_texture:
-            self._current_texture = self.create_texture(Texture, rectangle)
-        return self._current_texture
-
-    def get_mipmapped_texture(self):
-        """Return a Texture with mipmaps.
-
-        If :py:class:`~pyglet.image.set_mipmap_Image` has been called with at least one image, the set
-        of images defined will be used.  Otherwise, mipmaps will be
-        automatically generated.
-
-        :rtype: :py:class:`~pyglet.image.Texture`
-
-        .. versionadded:: 1.1
-        """
-        if self._current_mipmap_texture:
-            return self._current_mipmap_texture
-
-        texture = Texture.create(self.width, self.height, GL_TEXTURE_2D, None, blank_data=False)
-        if self.anchor_x or self.anchor_y:
-            texture.anchor_x = self.anchor_x
-            texture.anchor_y = self.anchor_y
-
-        internalformat = self._get_internalformat(self.format)
-
-        glBindTexture(texture.target, texture.id)
-        glTexParameteri(texture.target, GL_TEXTURE_MIN_FILTER, GL_LINEAR_MIPMAP_LINEAR)
-
-        if self.mipmap_images:
-            self.blit_to_texture(texture.target, texture.level, self.anchor_x, self.anchor_y, 0, internalformat)
-            level = 0
-            for image in self.mipmap_images:
-                level += 1
-                if image:
-                    image.blit_to_texture(texture.target, level, self.anchor_x, self.anchor_y, 0, internalformat)
-                    # TODO: should set base and max mipmap level if some mipmaps are missing.
-        else:
-            glGenerateMipmap(texture.target)
-            self.blit_to_texture(texture.target, texture.level, self.anchor_x, self.anchor_y, 0, internalformat)
-
-        self._current_mipmap_texture = texture
-        return texture
-
-    def get_region(self, x, y, width, height):
-        """Retrieve a rectangular region of this image data.
-
-        :Parameters:
-            `x` : int
-                Left edge of region.
-            `y` : int
-                Bottom edge of region.
-            `width` : int
-                Width of region.
-            `height` : int
-                Height of region.
-
-        :rtype: ImageDataRegion
-        """
-        return ImageDataRegion(x, y, width, height, self)
-
-    def blit(self, x, y, z=0, width=None, height=None):
-        self.get_texture().blit(x, y, z, width, height)
-
-    def blit_to_texture(self, target, level, x, y, z, internalformat=None):
-        """Draw this image to to the currently bound texture at `target`.
-
-        This image's anchor point will be aligned to the given `x` and `y`
-        coordinates.  If the currently bound texture is a 3D texture, the `z`
-        parameter gives the image slice to blit into.
-
-        If `internalformat` is specified, glTexImage is used to initialise
-        the texture; otherwise, glTexSubImage is used to update a region.
-        """
-        x -= self.anchor_x
-        y -= self.anchor_y
-
-        data_format = self.format
-        data_pitch = abs(self._current_pitch)
-
-        # Determine pixel format from format string
-        fmt, gl_type = self._get_gl_format_and_type(data_format)
-
-        if fmt is None:
-            # Need to convert data to a standard form
-            data_format = {
-                1: 'R',
-                2: 'RG',
-                3: 'RGB',
-                4: 'RGBA'}.get(len(data_format))
-            fmt, gl_type = self._get_gl_format_and_type(data_format)
-
-        # Get data in required format (hopefully will be the same format it's already
-        # in, unless that's an obscure format, upside-down or the driver is old).
-        data = self._convert(data_format, data_pitch)
-
-        if data_pitch & 0x1:
-            align = 1
-        elif data_pitch & 0x2:
-            align = 2
-        else:
-            align = 4
-        row_length = data_pitch // len(data_format)
-
-        glPixelStorei(GL_UNPACK_ALIGNMENT, align)
-        glPixelStorei(GL_UNPACK_ROW_LENGTH, row_length)
-        self._apply_region_unpack()
-
-        if target == GL_TEXTURE_3D or target == GL_TEXTURE_2D_ARRAY:
-            assert not internalformat
-            glTexSubImage3D(target, level,
-                            x, y, z,
-                            self.width, self.height, 1,
-                            fmt, gl_type,
-                            data)
-        elif internalformat:
-            glTexImage2D(target, level,
-                         internalformat,
-                         self.width, self.height,
-                         0,
-                         fmt, gl_type,
-                         data)
-        else:
-            glTexSubImage2D(target, level,
-                            x, y,
-                            self.width, self.height,
-                            fmt, gl_type,
-                            data)
-
-        # Unset GL_UNPACK_ROW_LENGTH:
-        glPixelStorei(GL_UNPACK_ROW_LENGTH, 0)
-        self._default_region_unpack()
-
-        # Flush image upload before data get GC'd:
-        glFlush()
-
-    def _apply_region_unpack(self):
-        pass
-
-    def _default_region_unpack(self):
-        pass
-
-    def _convert(self, fmt, pitch):
-        """Return data in the desired format; does not alter this instance's
-        current format or pitch.
-        """
-        if fmt == self._current_format and pitch == self._current_pitch:
-            if type(self._current_data) is str:
-                return asbytes(self._current_data)
-            return self._current_data
-
-        self._ensure_bytes()
-        data = self._current_data
-        current_pitch = self._current_pitch
-        current_format = self._current_format
-        sign_pitch = current_pitch // abs(current_pitch)
-        if fmt != self._current_format:
-            # Create replacement string, e.g. r'\4\1\2\3' to convert RGBA to ARGB
-            repl = asbytes('')
-            for c in fmt:
-                try:
-                    idx = current_format.index(c) + 1
-                except ValueError:
-                    idx = 1
-                repl += asbytes(r'\%d' % idx)
-
-            if len(current_format) == 1:
-                swap_pattern = self._swap1_pattern
-            elif len(current_format) == 2:
-                swap_pattern = self._swap2_pattern
-            elif len(current_format) == 3:
-                swap_pattern = self._swap3_pattern
-            elif len(current_format) == 4:
-                swap_pattern = self._swap4_pattern
-            else:
-                raise ImageException('Current image format is wider than 32 bits.')
-
-            packed_pitch = self.width * len(current_format)
-            if abs(self._current_pitch) != packed_pitch:
-                # Pitch is wider than pixel data, need to go row-by-row.
-                new_pitch = abs(self._current_pitch)
-                rows = [data[i:i+new_pitch] for i in range(0, len(data), new_pitch)]
-                rows = [swap_pattern.sub(repl, r[:packed_pitch]) for r in rows]
-                data = asbytes('').join(rows)
-            else:
-                # Rows are tightly packed, apply regex over whole image.
-                data = swap_pattern.sub(repl, data)
-
-            # After conversion, rows will always be tightly packed
-            current_pitch = sign_pitch * (len(fmt) * self.width)
-
-        if pitch != current_pitch:
-            diff = abs(current_pitch) - abs(pitch)
-            if diff > 0:
-                # New pitch is shorter than old pitch, chop bytes off each row
-                new_pitch = abs(pitch)
-                rows = [data[i:i+new_pitch-diff] for i in range(0, len(data), new_pitch)]
-                data = asbytes('').join(rows)
-
-            elif diff < 0:
-                # New pitch is longer than old pitch, add '0' bytes to each row
-                new_pitch = abs(current_pitch)
-                padding = asbytes(1) * -diff
-                rows = [data[i:i+new_pitch] + padding for i in range(0, len(data), new_pitch)]
-                data = asbytes('').join(rows)
-
-            if current_pitch * pitch < 0:
-                # Pitch differs in sign, swap row order
-                new_pitch = abs(pitch)
-                rows = [data[i:i+new_pitch] for i in range(0, len(data), new_pitch)]
-                rows.reverse()
-                data = asbytes('').join(rows)
-
-        return asbytes(data)
-
-    def _ensure_bytes(self):
-        if type(self._current_data) is not bytes:
-            self._current_data = asbytes(self._current_data)
-
-    @staticmethod
-    def _get_gl_format_and_type(fmt):
-        if fmt == 'R':
-            return GL_RED, GL_UNSIGNED_BYTE
-        elif fmt == 'RG':
-            return GL_RG, GL_UNSIGNED_BYTE
-        elif fmt == 'RGB':
-            return GL_RGB, GL_UNSIGNED_BYTE
-        elif fmt == 'BGR':
-            return GL_BGR, GL_UNSIGNED_BYTE
-        elif fmt == 'RGBA':
-            return GL_RGBA, GL_UNSIGNED_BYTE
-        elif fmt == 'BGRA':
-            return GL_BGRA, GL_UNSIGNED_BYTE
-
-        elif fmt == 'L':
-            return GL_LUMINANCE, GL_UNSIGNED_BYTE
-        elif fmt == 'A':
-            return GL_ALPHA, GL_UNSIGNED_BYTE
-
-        return None, None
-
-    @staticmethod
-    def _get_internalformat(fmt):
-        if fmt == 'R':
-            return GL_RED
-        elif fmt == 'RG':
-            return GL_RG
-        elif fmt == 'RGB':
-            return GL_RGB
-        elif fmt == 'RGBA':
-            return GL_RGBA
-        elif fmt == 'D':
-            return GL_DEPTH_COMPONENT
-        elif fmt == 'DS':
-            return GL_DEPTH_STENCIL
-
-        elif fmt == 'L':
-            return GL_LUMINANCE
-        elif fmt == 'A':
-            return GL_ALPHA
-
-        return GL_RGBA
-
-
-class ImageDataRegion(ImageData):
-    def __init__(self, x, y, width, height, image_data):
-        super().__init__(width, height,
-                         image_data._current_format,
-                         image_data._current_data,
-                         image_data._current_pitch)
-        self.x = x
-        self.y = y
-
-    def __getstate__(self):
-        return {
-            'width': self.width,
-            'height': self.height,
-            '_current_data': self.get_data(self._current_format, self._current_pitch),
-            '_current_format': self._current_format,
-            '_desired_format': self._desired_format,
-            '_current_pitch': self._current_pitch,
-            'pitch': self.pitch,
-            'mipmap_images': self.mipmap_images,
-            'x': self.x,
-            'y': self.y
-        }
-
-    def get_data(self, fmt=None, pitch=None):
-        x1 = len(self._current_format) * self.x
-        x2 = len(self._current_format) * (self.x + self.width)
-
-        self._ensure_bytes()
-        data = self._convert(self._current_format, abs(self._current_pitch))
-        new_pitch = abs(self._current_pitch)
-        rows = [data[i:i+new_pitch] for i in range(0, len(data), new_pitch)]
-        rows = [row[x1:x2] for row in rows[self.y:self.y + self.height]]
-        self._current_data = b''.join(rows)
-        self._current_pitch = self.width * len(self._current_format)
-        self._current_texture = None
-        self.x = 0
-        self.y = 0
-
-        fmt = fmt or self._desired_format
-        pitch = pitch or self._current_pitch
-        return super().get_data(fmt, pitch)
-
-    def set_data(self, fmt, pitch, data):
-        self.x = 0
-        self.y = 0
-        super().set_data(fmt, pitch, data)
-
-    def _apply_region_unpack(self):
-        glPixelStorei(GL_UNPACK_SKIP_PIXELS, self.x)
-        glPixelStorei(GL_UNPACK_SKIP_ROWS, self.y)
-
-    def _default_region_unpack(self):
-        glPixelStorei(GL_UNPACK_SKIP_PIXELS, 0)
-        glPixelStorei(GL_UNPACK_SKIP_ROWS, 0)
-
-    def get_region(self, x, y, width, height):
-        x += self.x
-        y += self.y
-        return super().get_region(x, y, width, height)
-
-
-class CompressedImageData(AbstractImage):
-    """Image representing some compressed data suitable for direct uploading
-    to driver.
-    """
-
-    _current_texture = None
-    _current_mipmap_texture = None
-
-    def __init__(self, width, height, gl_format, data, extension=None, decoder=None):
-        """Construct a CompressedImageData with the given compressed data.
-
-        :Parameters:
-            `width` : int
-                Width of image
-            `height` : int
-                Height of image
-            `gl_format` : int
-                GL constant giving format of compressed data; for example,
-                ``GL_COMPRESSED_RGBA_S3TC_DXT5_EXT``.
-            `data` : sequence
-                String or array/list of bytes giving compressed image data.
-            `extension` : str or None
-                If specified, gives the name of a GL extension to check for
-                before creating a texture.
-            `decoder` : function(data, width, height) -> AbstractImage
-                A function to decode the compressed data, to be used if the
-                required extension is not present.
-
-        """
-        super().__init__(width, height)
-        self.data = data
-        self.gl_format = gl_format
-        self.extension = extension
-        self.decoder = decoder
-        self.mipmap_data = []
-
-    def set_mipmap_data(self, level, data):
-        """Set data for a mipmap level.
-
-        Supplied data gives a compressed image for the given mipmap level.
-        The image must be of the correct dimensions for the level
-        (i.e., width >> level, height >> level); but this is not checked.  If
-        any mipmap levels are specified, they are used; otherwise, mipmaps for
-        `mipmapped_texture` are generated automatically.
-
-        :Parameters:
-            `level` : int
-                Level of mipmap image to set.
-            `data` : sequence
-                String or array/list of bytes giving compressed image data.
-                Data must be in same format as specified in constructor.
-
-        """
-        # Extend mipmap_data list to required level
-        self.mipmap_data += [None] * (level - len(self.mipmap_data))
-        self.mipmap_data[level - 1] = data
-
-    def _have_extension(self):
-        return self.extension is None or gl_info.have_extension(self.extension)
-
-    def _verify_driver_supported(self):
-        """Assert that the extension required for this image data is
-        supported.
-
-        Raises `ImageException` if not.
-        """
-
-        if not self._have_extension():
-            raise ImageException('%s is required to decode %r' % (self.extension, self))
-
-    def get_texture(self, rectangle=False):
-        if rectangle:
-            raise ImageException('Compressed texture rectangles not supported')
-
-        if self._current_texture:
-            return self._current_texture
-
-        texture = Texture.create(self.width, self.height, GL_TEXTURE_2D, None)
-
-        if self.anchor_x or self.anchor_y:
-            texture.anchor_x = self.anchor_x
-            texture.anchor_y = self.anchor_y
-
-        glBindTexture(texture.target, texture.id)
-        glTexParameteri(texture.target, GL_TEXTURE_MIN_FILTER, texture.min_filter)
-        glTexParameteri(texture.target, GL_TEXTURE_MAG_FILTER, texture.mag_filter)
-
-        if self._have_extension():
-            glCompressedTexImage2D(texture.target, texture.level,
-                                   self.gl_format,
-                                   self.width, self.height, 0,
-                                   len(self.data), self.data)
-        else:
-            image = self.decoder(self.data, self.width, self.height)
-            texture = image.get_texture()
-            assert texture.width == self.width
-            assert texture.height == self.height
-
-        glFlush()
-        self._current_texture = texture
-        return texture
-
-    def get_mipmapped_texture(self):
-        if self._current_mipmap_texture:
-            return self._current_mipmap_texture
-
-        if not self._have_extension():
-            # TODO mip-mapped software decoded compressed textures.  For now,
-            # just return a non-mipmapped texture.
-            return self.get_texture()
-
-        texture = Texture.create(self.width, self.height, GL_TEXTURE_2D, None)
-
-        if self.anchor_x or self.anchor_y:
-            texture.anchor_x = self.anchor_x
-            texture.anchor_y = self.anchor_y
-
-        glBindTexture(texture.target, texture.id)
-
-        glTexParameteri(texture.target, GL_TEXTURE_MIN_FILTER, GL_LINEAR_MIPMAP_LINEAR)
-
-        if not self.mipmap_data:
-            glGenerateMipmap(texture.target)
-
-        glCompressedTexImage2D(texture.target, texture.level,
-                               self.gl_format,
-                               self.width, self.height, 0,
-                               len(self.data), self.data)
-
-        width, height = self.width, self.height
-        level = 0
-        for data in self.mipmap_data:
-            width >>= 1
-            height >>= 1
-            level += 1
-            glCompressedTexImage2D(texture.target, level, self.gl_format, width, height, 0, len(data), data)
-
-        glFlush()
-
-        self._current_mipmap_texture = texture
-        return texture
-
-    def blit_to_texture(self, target, level, x, y, z):
-        self._verify_driver_supported()
-
-        if target == GL_TEXTURE_3D:
-            glCompressedTexSubImage3D(target, level,
-                                      x - self.anchor_x, y - self.anchor_y, z,
-                                      self.width, self.height, 1,
-                                      self.gl_format,
-                                      len(self.data), self.data)
-        else:
-            glCompressedTexSubImage2D(target, level,
-                                      x - self.anchor_x, y - self.anchor_y,
-                                      self.width, self.height,
-                                      self.gl_format,
-                                      len(self.data), self.data)
-
-
-class Texture(AbstractImage):
-    """An image loaded into video memory that can be efficiently drawn
-    to the framebuffer.
-
-    Typically, you will get an instance of Texture by accessing the `texture`
-    member of any other AbstractImage.
-
-    :Parameters:
-        `region_class` : class (subclass of TextureRegion)
-            Class to use when constructing regions of this texture.
-        `tex_coords` : tuple
-            12-tuple of float, named (u1, v1, r1, u2, v2, r2, ...).  u, v, r
-            give the 3D texture coordinates for vertices 1-4.  The vertices
-            are specified in the order bottom-left, bottom-right, top-right
-            and top-left.
-        `target` : int
-            The GL texture target (e.g., ``GL_TEXTURE_2D``).
-        `level` : int
-            The mipmap level of this texture.
-
-    """
-
-    region_class = None  # Set to TextureRegion after it's defined
-    tex_coords = (0, 0, 0, 1, 0, 0, 1, 1, 0, 0, 1, 0)
-    tex_coords_order = (0, 1, 2, 3)
-    colors = (0, 0, 0, 0) * 4
-    level = 0
-    images = 1
-    x = y = z = 0
-    default_min_filter = GL_LINEAR
-    default_mag_filter = GL_LINEAR
-
-    def __init__(self, width, height, target, tex_id):
-        super().__init__(width, height)
-        self.target = target
-        self.id = tex_id
-        self._context = pyglet.gl.current_context
-
-    def __del__(self):
-        try:
-            self._context.delete_texture(self.id)
-        except Exception:
-            pass
-
-    def bind(self, texture_unit: int = 0):
-        """Bind to a specific Texture Unit by number."""
-        glActiveTexture(GL_TEXTURE0 + texture_unit)
-        glBindTexture(self.target, self.id)
-
-    def bind_image_texture(self, unit, level=0, layered=False, layer=0, access=GL_READ_WRITE, fmt=GL_RGBA32F):
-        """Bind as an ImageTexture for use with a :py:class:`~pyglet.shader.ComputeShaderProgram`.
-
-        ..note:: OpenGL 4.3, or 4.2 with the GL_ARB_compute_shader extention is required.
-        """
-        glBindImageTexture(unit, self.id, level, layered, layer, access, fmt)
-
-    @classmethod
-    def create(cls, width, height, target=GL_TEXTURE_2D, internalformat=GL_RGBA8, min_filter=None, mag_filter=None, fmt=GL_RGBA, blank_data=True):
-        """Create a Texture
-
-        Create a Texture with the specified dimentions, target and format.
-        On return, the texture will be bound.
-
-        :Parameters:
-            `width` : int
-                Width of texture in pixels.
-            `height` : int
-                Height of texture in pixels.
-            `target` : int
-                GL constant giving texture target to use, typically ``GL_TEXTURE_2D``.
-            `internalformat` : int
-                GL constant giving internal format of texture; for example, ``GL_RGBA``.
-                The internal format decides how the texture data will be stored internally.
-                If ``None``, the texture will be created but not initialized.
-            `min_filter` : int
-                The minifaction filter used for this texture, commonly ``GL_LINEAR`` or ``GL_NEAREST``
-            `mag_filter` : int
-                The magnification filter used for this texture, commonly ``GL_LINEAR`` or ``GL_NEAREST``
-            `fmt` : int
-                GL constant giving format of texture; for example, ``GL_RGBA``.
-                The format specifies what format the pixel data we're expecting to write
-                to the texture and should ideally be the same as for internal format.
-            `blank_data` : bool
-                Setting to True will initialize the texture data with all zeros. Setting False, will initialize Texture
-                with no data.
-
-        :rtype: :py:class:`~pyglet.image.Texture`
-        """
-        min_filter = min_filter or cls.default_min_filter
-        mag_filter = mag_filter or cls.default_mag_filter
-
-        tex_id = GLuint()
-        glGenTextures(1, byref(tex_id))
-        glBindTexture(target, tex_id.value)
-        glTexParameteri(target, GL_TEXTURE_MIN_FILTER, min_filter)
-        glTexParameteri(target, GL_TEXTURE_MAG_FILTER, mag_filter)
-
-        if internalformat is not None:
-            blank = (GLubyte * (width * height * 4))() if blank_data else None
-            glTexImage2D(target, 0,
-                         internalformat,
-                         width, height,
-                         0,
-                         fmt,
-                         GL_UNSIGNED_BYTE,
-                         blank)
-            glFlush()
-
-        texture = cls(width, height, target, tex_id.value)
-        texture.min_filter = min_filter
-        texture.mag_filter = mag_filter
-        texture.tex_coords = cls.tex_coords
-
-        return texture
-
-    def get_image_data(self, z=0):
-        """Get the image data of this texture.
-
-        Changes to the returned instance will not be reflected in this
-        texture.
-
-        :Parameters:
-            `z` : int
-                For 3D textures, the image slice to retrieve.
-
-        :rtype: :py:class:`~pyglet.image.ImageData`
-        """
-        glBindTexture(self.target, self.id)
-
-        # Always extract complete RGBA data.  Could check internalformat
-        # to only extract used channels. XXX
-        fmt = 'RGBA'
-        gl_format = GL_RGBA
-
-        buf = (GLubyte * (self.width * self.height * self.images * len(fmt)))()
-
-        # TODO: Clean up this temporary hack
-        if pyglet.gl.current_context.get_info().get_opengl_api() == "gles":
-            fbo = c_uint()
-            glGenFramebuffers(1, fbo)
-            glBindFramebuffer(GL_FRAMEBUFFER, fbo.value)
-            glPixelStorei(GL_PACK_ALIGNMENT, 1)
-            glCheckFramebufferStatus(GL_FRAMEBUFFER)
-            glFramebufferTexture2D(GL_FRAMEBUFFER, GL_COLOR_ATTACHMENT0, GL_TEXTURE_2D, self.id, self.level)
-            glReadPixels(0, 0, self.width, self.height, gl_format, GL_UNSIGNED_BYTE, buf)
-            glBindFramebuffer(GL_FRAMEBUFFER, 0)
-            glDeleteFramebuffers(1, fbo)
-        else:
-            glPixelStorei(GL_PACK_ALIGNMENT, 1)
-            glGetTexImage(self.target, self.level, gl_format, GL_UNSIGNED_BYTE, buf)
-
-        data = ImageData(self.width, self.height, fmt, buf)
-        if self.images > 1:
-            data = data.get_region(0, z * self.height, self.width, self.height)
-        return data
-
-    def get_texture(self, rectangle=False):
-        return self
-
-    # no implementation of blit_to_texture yet
-
-    def blit(self, x, y, z=0, width=None, height=None):
-        x1 = x - self.anchor_x
-        y1 = y - self.anchor_y
-        x2 = x1 + (width is None and self.width or width)
-        y2 = y1 + (height is None and self.height or height)
-        vertices = x1, y1, z,  x2, y1, z,  x2, y2, z,  x1, y2, z
-
-        glActiveTexture(GL_TEXTURE0)
-        glBindTexture(self.target, self.id)
-
-        pyglet.graphics.draw_indexed(4, GL_TRIANGLES, [0, 1, 2, 0, 2, 3],
-                                     position=('f', vertices),
-                                     tex_coords=('f', self.tex_coords),
-                                     colors=('Bn', self.colors))
-
-        glBindTexture(self.target, 0)
-
-    def blit_into(self, source, x, y, z):
-        glBindTexture(self.target, self.id)
-        source.blit_to_texture(self.target, self.level, x, y, z)
-
-    def get_region(self, x, y, width, height):
-        return self.region_class(x, y, 0, width, height, self)
-
-    def get_transform(self, flip_x=False, flip_y=False, rotate=0):
-        """Create a copy of this image applying a simple transformation.
-
-        The transformation is applied to the texture coordinates only;
-        :py:meth:`~pyglet.image.ImageData.get_image_data` will return the untransformed data.  The
-        transformation is applied around the anchor point.
-
-        :Parameters:
-            `flip_x` : bool
-                If True, the returned image will be flipped horizontally.
-            `flip_y` : bool
-                If True, the returned image will be flipped vertically.
-            `rotate` : int
-                Degrees of clockwise rotation of the returned image.  Only
-                90-degree increments are supported.
-
-        :rtype: :py:class:`~pyglet.image.TextureRegion`
-        """
-        transform = self.get_region(0, 0, self.width, self.height)
-        bl, br, tr, tl = 0, 1, 2, 3
-        transform.anchor_x = self.anchor_x
-        transform.anchor_y = self.anchor_y
-        if flip_x:
-            bl, br, tl, tr = br, bl, tr, tl
-            transform.anchor_x = self.width - self.anchor_x
-        if flip_y:
-            bl, br, tl, tr = tl, tr, bl, br
-            transform.anchor_y = self.height - self.anchor_y
-        rotate %= 360
-        if rotate < 0:
-            rotate += 360
-        if rotate == 0:
-            pass
-        elif rotate == 90:
-            bl, br, tr, tl = br, tr, tl, bl
-            transform.anchor_x, transform.anchor_y = transform.anchor_y, transform.width - transform.anchor_x
-        elif rotate == 180:
-            bl, br, tr, tl = tr, tl, bl, br
-            transform.anchor_x = transform.width - transform.anchor_x
-            transform.anchor_y = transform.height - transform.anchor_y
-        elif rotate == 270:
-            bl, br, tr, tl = tl, bl, br, tr
-            transform.anchor_x, transform.anchor_y = transform.height - transform.anchor_y, transform.anchor_x
-        else:
-            assert False, 'Only 90 degree rotations are supported.'
-        if rotate in (90, 270):
-            transform.width, transform.height = transform.height, transform.width
-        transform._set_tex_coords_order(bl, br, tr, tl)
-        return transform
-
-    def _set_tex_coords_order(self, bl, br, tr, tl):
-        tex_coords = (self.tex_coords[:3],
-                      self.tex_coords[3:6],
-                      self.tex_coords[6:9],
-                      self.tex_coords[9:])
-        self.tex_coords = tex_coords[bl] + tex_coords[br] + tex_coords[tr] + tex_coords[tl]
-
-        order = self.tex_coords_order
-        self.tex_coords_order = (order[bl], order[br], order[tr], order[tl])
-
-    def __repr__(self):
-        return "{}(id={}, size={}x{})".format(self.__class__.__name__, self.id, self.width, self.height)
-
-
-class TextureRegion(Texture):
-    """A rectangular region of a texture, presented as if it were a separate texture.
-    """
-
-    def __init__(self, x, y, z, width, height, owner):
-        super().__init__(width, height, owner.target, owner.id)
-
-        self.x = x
-        self.y = y
-        self.z = z
-        self.owner = owner
-        owner_u1 = owner.tex_coords[0]
-        owner_v1 = owner.tex_coords[1]
-        owner_u2 = owner.tex_coords[3]
-        owner_v2 = owner.tex_coords[7]
-        scale_u = owner_u2 - owner_u1
-        scale_v = owner_v2 - owner_v1
-        u1 = x / owner.width * scale_u + owner_u1
-        v1 = y / owner.height * scale_v + owner_v1
-        u2 = (x + width) / owner.width * scale_u + owner_u1
-        v2 = (y + height) / owner.height * scale_v + owner_v1
-        r = z / owner.images + owner.tex_coords[2]
-        self.tex_coords = (u1, v1, r, u2, v1, r, u2, v2, r, u1, v2, r)
-
-    def get_image_data(self):
-        image_data = self.owner.get_image_data(self.z)
-        return image_data.get_region(self.x, self.y, self.width, self.height)
-
-    def get_region(self, x, y, width, height):
-        x += self.x
-        y += self.y
-        region = self.region_class(x, y, self.z, width, height, self.owner)
-        region._set_tex_coords_order(*self.tex_coords_order)
-        return region
-
-    def blit_into(self, source, x, y, z):
-        self.owner.blit_into(source, x + self.x, y + self.y, z + self.z)
-
-    def __repr__(self):
-        return "{}(id={}, size={}x{}, owner={}x{})".format(self.__class__.__name__, self.id, self.width, self.height,
-                                                           self.owner.width, self.owner.height)
-
-    def __del__(self):
-        # only the owner Texture should handle deletion
-        pass
-
-
-Texture.region_class = TextureRegion
-
-
-class Texture3D(Texture, UniformTextureSequence):
-    """A texture with more than one image slice.
-
-    Use `create_for_images` or `create_for_image_grid` classmethod to
-    construct.
-    """
-    item_width = 0
-    item_height = 0
-    items = ()
-
-    @classmethod
-    def create_for_images(cls, images, internalformat=GL_RGBA, blank_data=True):
-        item_width = images[0].width
-        item_height = images[0].height
-        for image in images:
-            if image.width != item_width or image.height != item_height:
-                raise ImageException('Images do not have same dimensions.')
-
-        depth = len(images)
-
-        texture = cls.create(item_width, item_height, GL_TEXTURE_3D, None)
-        if images[0].anchor_x or images[0].anchor_y:
-            texture.anchor_x = images[0].anchor_x
-            texture.anchor_y = images[0].anchor_y
-
-        texture.images = depth
-
-        blank = (GLubyte * (texture.width * texture.height * texture.images))() if blank_data else None
-        glBindTexture(texture.target, texture.id)
-        glTexImage3D(texture.target, texture.level,
-                     internalformat,
-                     texture.width, texture.height, texture.images, 0,
-                     GL_ALPHA, GL_UNSIGNED_BYTE,
-                     blank)
-
-        items = []
-        for i, image in enumerate(images):
-            item = cls.region_class(0, 0, i, item_width, item_height, texture)
-            items.append(item)
-            image.blit_to_texture(texture.target, texture.level, image.anchor_x, image.anchor_y, i)
-
-        glFlush()
-
-        texture.items = items
-        texture.item_width = item_width
-        texture.item_height = item_height
-        return texture
-
-    @classmethod
-    def create_for_image_grid(cls, grid, internalformat=GL_RGBA):
-        return cls.create_for_images(grid[:], internalformat)
-
-    def __len__(self):
-        return len(self.items)
-
-    def __getitem__(self, index):
-        return self.items[index]
-
-    def __setitem__(self, index, value):
-        if type(index) is slice:
-            for item, image in zip(self[index], value):
-                image.blit_to_texture(self.target, self.level, image.anchor_x, image.anchor_y, item.z)
-        else:
-            value.blit_to_texture(self.target, self.level, value.anchor_x, value.anchor_y, self[index].z)
-
-    def __iter__(self):
-        return iter(self.items)
-
-
-class TextureArrayRegion(TextureRegion):
-    """A region of a TextureArray, presented as if it were a separate texture.
-    """
-    def __init__(self, x, y, z, width, height, owner):
-        super().__init__(width, height, owner.target, owner.id)
-
-        self.x = x
-        self.y = y
-        self.z = z
-        self.owner = owner
-        owner_u1 = owner.tex_coords[0]
-        owner_v1 = owner.tex_coords[1]
-        owner_u2 = owner.tex_coords[3]
-        owner_v2 = owner.tex_coords[7]
-        scale_u = owner_u2 - owner_u1
-        scale_v = owner_v2 - owner_v1
-        u1 = x / owner.width * scale_u + owner_u1
-        v1 = y / owner.height * scale_v + owner_v1
-        u2 = (x + width) / owner.width * scale_u + owner_u1
-        v2 = (y + height) / owner.height * scale_v + owner_v1
-        z = float(z)
-        self.tex_coords = (u1, v1, z, u2, v1, z, u2, v2, z, u1, v2, z)
-
-    def __repr__(self):
-        return "{}(id={}, size={}x{}, layer={})".format(self.__class__.__name__, self.id, self.width, self.height, self.z)
-
-
-class TextureArray(Texture, UniformTextureSequence):
-    allow_smaller_pack = True
-
-    @classmethod
-    def create(cls, width, height, internalformat=GL_RGBA, min_filter=None, mag_filter=None, max_depth=256):
-        """Create an empty TextureArray.
-
-        You may specify the maximum depth, or layers, the Texture Array should have. This defaults
-        to 256, but will be hardware and driver dependent.
-
-        :Parameters:
-            `width` : int
-                Width of the texture.
-            `height` : int
-                Height of the texture.
-            `internalformat` : int
-                GL constant giving the internal format of the texture array; for example, ``GL_RGBA``.
-            `min_filter` : int
-                The minifaction filter used for this texture array, commonly ``GL_LINEAR`` or ``GL_NEAREST``
-            `mag_filter` : int
-                The magnification filter used for this texture array, commonly ``GL_LINEAR`` or ``GL_NEAREST``
-            `max_depth` : int
-                The number of layers in the texture array.
-
-        :rtype: :py:class:`~pyglet.image.TextureArray`
-
-        .. versionadded:: 2.0
-        """
-        min_filter = min_filter or cls.default_min_filter
-        mag_filter = mag_filter or cls.default_mag_filter
-
-        max_depth_limit = get_max_array_texture_layers()
-        assert max_depth <= max_depth_limit, "TextureArray max_depth supported is {}.".format(max_depth_limit)
-
-        tex_id = GLuint()
-        glGenTextures(1, byref(tex_id))
-        glBindTexture(GL_TEXTURE_2D_ARRAY, tex_id.value)
-        glTexParameteri(GL_TEXTURE_2D_ARRAY, GL_TEXTURE_MIN_FILTER, min_filter)
-        glTexParameteri(GL_TEXTURE_2D_ARRAY, GL_TEXTURE_MAG_FILTER, mag_filter)
-
-        glTexImage3D(GL_TEXTURE_2D_ARRAY, 0,
-                     internalformat,
-                     width, height, max_depth,
-                     0,
-                     internalformat, GL_UNSIGNED_BYTE,
-                     0)
-        glFlush()
-
-        texture = cls(width, height, GL_TEXTURE_2D_ARRAY, tex_id.value)
-        texture.items = []  # No items on creation
-        texture.max_depth = max_depth
-        texture.min_filter = min_filter
-        texture.mag_filter = mag_filter
-
-        return texture
-
-    def _verify_size(self, image):
-        if image.width > self.width or image.height > self.height:
-            raise ImageException('Image ({0}x{1}) exceeds the size of the TextureArray ({2}x{3})'.format(
-                image.width, image.height, self.width, self.height))
-
-    def allocate(self, *images):
-        if len(self.items) + len(images) > self.max_depth:
-            raise Exception("The amount of images being added exceeds the depth of this TextureArray.")
-
-        textures = []
-        start_length = len(self.items)
-        for i, image in enumerate(images):
-            self._verify_size(image)
-            item = self.region_class(0, 0, start_length + i, image.width, image.height, self)
-            self.items.append(item)
-            image.blit_to_texture(self.target, self.level, image.anchor_x, image.anchor_y, start_length + i)
-
-        glFlush()
-
-        return self.items[start_length:]
-
-    @classmethod
-    def create_for_image_grid(cls, grid, internalformat=GL_RGBA):
-        texture_array = cls.create(grid[0].width, grid[0].height, internalformat, max_depth=len(grid))
-        texture_array.allocate(*grid[:])
-        return texture_array
-
-    def __len__(self):
-        return len(self.items)
-
-    def __getitem__(self, index):
-        return self.items[index]
-
-    def __setitem__(self, index, value):
-        if type(index) is slice:
-            for old_item, image in zip(self[index], value):
-                self._verify_size(image)
-                item = self.region_class(0, 0, old_item.z, image.width, image.height, self)
-                image.blit_to_texture(self.target, self.level, image.anchor_x, image.anchor_y, old_item.z)
-                self.items[old_item.z] = item
-        else:
-            self._verify_size(value)
-            item = self.region_class(0, 0, index, value.width, value.height, self)
-            value.blit_to_texture(self.target, self.level, value.anchor_x, value.anchor_y, index)
-            self.items[index] = item
-
-    def __iter__(self):
-        return iter(self.items)
-
-
-TextureArray.region_class = TextureArrayRegion
-TextureArrayRegion.region_class = TextureArrayRegion
-
-
-class TileableTexture(Texture):
-    """A texture that can be tiled efficiently.
-
-    Use :py:class:`~pyglet.image.create_for_image` classmethod to construct.
-    """
-
-    def get_region(self, x, y, width, height):
-        raise ImageException('Cannot get region of %r' % self)
-
-    def blit_tiled(self, x, y, z, width, height):
-        """Blit this texture tiled over the given area.
-
-        The image will be tiled with the bottom-left corner of the destination
-        rectangle aligned with the anchor point of this texture.
-        """
-        u1 = self.anchor_x / self.width
-        v1 = self.anchor_y / self.height
-        u2 = u1 + width / self.width
-        v2 = v1 + height / self.height
-        w, h = width, height
-        t = self.tex_coords
-
-        vertices = (x, y, z,
-                    x + w, y, z,
-                    x + w, y + h, z,
-                    x, y + h, z)
-
-        tex_coords = (u1, v1, t[2],
-                      u2, v1, t[5],
-                      u2, v2, t[8],
-                      u1, v2, t[11],)
-
-        glActiveTexture(GL_TEXTURE0)
-        glBindTexture(self.target, self.id)
-        pyglet.graphics.draw_indexed(4, GL_TRIANGLES, [0, 1, 2, 0, 2, 3],
-                                     position=('f', vertices),
-                                     tex_coords=('f', tex_coords))
-        glBindTexture(self.target, 0)
-
-    @classmethod
-    def create_for_image(cls, image):
-        image = image.get_image_data()
-        return image.create_texture(cls)
-
-
-class DepthTexture(Texture):
-    """A texture with depth samples (typically 24-bit)."""
-
-    def blit_into(self, source, x, y, z):
-        glBindTexture(self.target, self.id)
-        source.blit_to_texture(self.level, x, y, z)
-
-
-class ImageGrid(AbstractImage, AbstractImageSequence):
-    """An imaginary grid placed over an image allowing easy access to
-    regular regions of that image.
-
-    The grid can be accessed either as a complete image, or as a sequence
-    of images.  The most useful applications are to access the grid
-    as a :py:class:`~pyglet.image.TextureGrid`::
-
-        image_grid = ImageGrid(...)
-        texture_grid = image_grid.get_texture_sequence()
-
-    or as a :py:class:`~pyglet.image.Texture3D`::
-
-        image_grid = ImageGrid(...)
-        texture_3d = Texture3D.create_for_image_grid(image_grid)
-
-    """
-    _items = ()
-    _texture_grid = None
-
-    def __init__(self, image, rows, columns, item_width=None, item_height=None, row_padding=0, column_padding=0):
-        """Construct a grid for the given image.
-
-        You can specify parameters for the grid, for example setting
-        the padding between cells.  Grids are always aligned to the
-        bottom-left corner of the image.
-
-        :Parameters:
-            `image` : AbstractImage
-                Image over which to construct the grid.
-            `rows` : int
-                Number of rows in the grid.
-            `columns` : int
-                Number of columns in the grid.
-            `item_width` : int
-                Width of each column.  If unspecified, is calculated such
-                that the entire image width is used.
-            `item_height` : int
-                Height of each row.  If unspecified, is calculated such that
-                the entire image height is used.
-            `row_padding` : int
-                Pixels separating adjacent rows.  The padding is only
-                inserted between rows, not at the edges of the grid.
-            `column_padding` : int
-                Pixels separating adjacent columns.  The padding is only
-                inserted between columns, not at the edges of the grid.
-        """
-        super().__init__(image.width, image.height)
-        self.image = image
-        self.rows = rows
-        self.columns = columns
-        self.item_width = item_width or (image.width - column_padding * (columns - 1)) // columns
-        self.item_height = item_height or (image.height - row_padding * (rows - 1)) // rows
-        self.row_padding = row_padding
-        self.column_padding = column_padding
-
-    def get_texture(self, rectangle=False):
-        return self.image.get_texture(rectangle)
-
-    def get_image_data(self):
-        return self.image.get_image_data()
-
-    def get_texture_sequence(self):
-        if not self._texture_grid:
-            self._texture_grid = TextureGrid(self)
-        return self._texture_grid
-
-    def __len__(self):
-        return self.rows * self.columns
-
-    def _update_items(self):
-        if not self._items:
-            self._items = []
-            y = 0
-            for row in range(self.rows):
-                x = 0
-                for col in range(self.columns):
-                    self._items.append(self.image.get_region(x, y, self.item_width, self.item_height))
-                    x += self.item_width + self.column_padding
-                y += self.item_height + self.row_padding
-
-    def __getitem__(self, index):
-        self._update_items()
-        if type(index) is tuple:
-            row, column = index
-            assert 0 <= row < self.rows and 0 <= column < self.columns
-            return self._items[row * self.columns + column]
-        else:
-            return self._items[index]
-
-    def __iter__(self):
-        self._update_items()
-        return iter(self._items)
-
-
-class TextureGrid(TextureRegion, UniformTextureSequence):
-    """A texture containing a regular grid of texture regions.
-
-    To construct, create an :py:class:`~pyglet.image.ImageGrid` first::
-
-        image_grid = ImageGrid(...)
-        texture_grid = TextureGrid(image_grid)
-
-    The texture grid can be accessed as a single texture, or as a sequence
-    of :py:class:`~pyglet.image.TextureRegion`.  When accessing as a sequence, you can specify
-    integer indexes, in which the images are arranged in rows from the
-    bottom-left to the top-right::
-
-        # assume the texture_grid is 3x3:
-        current_texture = texture_grid[3] # get the middle-left image
-
-    You can also specify tuples in the sequence methods, which are addressed
-    as ``row, column``::
-
-        # equivalent to the previous example:
-        current_texture = texture_grid[1, 0]
-
-    When using tuples in a slice, the returned sequence is over the
-    rectangular region defined by the slice::
-
-        # returns center, center-right, center-top, top-right images in that
-        # order:
-        images = texture_grid[(1,1):]
-        # equivalent to
-        images = texture_grid[(1,1):(3,3)]
-
-    """
-    items = ()
-    rows = 1
-    columns = 1
-    item_width = 0
-    item_height = 0
-
-    def __init__(self, grid):
-        image = grid.get_texture()
-        if isinstance(image, TextureRegion):
-            owner = image.owner
-        else:
-            owner = image
-
-        super().__init__(image.x, image.y, image.z, image.width, image.height, owner)
-
-        items = []
-        y = 0
-        for row in range(grid.rows):
-            x = 0
-            for col in range(grid.columns):
-                items.append(self.get_region(x, y, grid.item_width, grid.item_height))
-                x += grid.item_width + grid.column_padding
-            y += grid.item_height + grid.row_padding
-
-        self.items = items
-        self.rows = grid.rows
-        self.columns = grid.columns
-        self.item_width = grid.item_width
-        self.item_height = grid.item_height
-
-    def get(self, row, column):
-        return self[(row, column)]
-
-    def __getitem__(self, index):
-        if type(index) is slice:
-            if type(index.start) is not tuple and type(index.stop) is not tuple:
-                return self.items[index]
-            else:
-                row1 = 0
-                col1 = 0
-                row2 = self.rows
-                col2 = self.columns
-                if type(index.start) is tuple:
-                    row1, col1 = index.start
-                elif type(index.start) is int:
-                    row1 = index.start // self.columns
-                    col1 = index.start % self.columns
-                assert 0 <= row1 < self.rows and 0 <= col1 < self.columns
-
-                if type(index.stop) is tuple:
-                    row2, col2 = index.stop
-                elif type(index.stop) is int:
-                    row2 = index.stop // self.columns
-                    col2 = index.stop % self.columns
-                assert 0 <= row2 <= self.rows and 0 <= col2 <= self.columns
-
-                result = []
-                i = row1 * self.columns
-                for row in range(row1, row2):
-                    result += self.items[i + col1:i + col2]
-                    i += self.columns
-                return result
-        else:
-            if type(index) is tuple:
-                row, column = index
-                assert 0 <= row < self.rows and 0 <= column < self.columns
-                return self.items[row * self.columns + column]
-            elif type(index) is int:
-                return self.items[index]
-
-    def __setitem__(self, index, value):
-        if type(index) is slice:
-            for region, image in zip(self[index], value):
-                if image.width != self.item_width or image.height != self.item_height:
-                    raise ImageException('Image has incorrect dimensions')
-                image.blit_into(region, image.anchor_x, image.anchor_y, 0)
-        else:
-            image = value
-            if image.width != self.item_width or image.height != self.item_height:
-                raise ImageException('Image has incorrect dimensions')
-            image.blit_into(self[index], image.anchor_x, image.anchor_y, 0)
-
-    def __len__(self):
-        return len(self.items)
-
-    def __iter__(self):
-        return iter(self.items)
-
-
-# Initialise default codecs
-_add_default_codecs()
-
-# Default Framebuffer classes:
-###############################################################
-
-
-class BufferManager:
-    """Manages the set of framebuffers for a context.
-
-    Use :py:func:`~pyglet.image.get_buffer_manager` to obtain the instance of this class for the
-    current context.
-    """
-
-    def __init__(self):
-        self.color_buffer = None
-        self.depth_buffer = None
-        self.free_stencil_bits = None
-        self.refs = []
-
-    @staticmethod
-    def get_viewport():
-        """Get the current OpenGL viewport dimensions.
-
-        :rtype: 4-tuple of float.
-        :return: Left, top, right and bottom dimensions.
-        """
-        viewport = (GLint * 4)()
-        glGetIntegerv(GL_VIEWPORT, viewport)
-        return viewport
-
-    def get_color_buffer(self):
-        """Get the color buffer.
-
-        :rtype: :py:class:`~pyglet.image.ColorBufferImage`
-        """
-        viewport = self.get_viewport()
-        viewport_width = viewport[2]
-        viewport_height = viewport[3]
-        if (not self.color_buffer or
-                viewport_width != self.color_buffer.width or
-                viewport_height != self.color_buffer.height):
-            self.color_buffer = ColorBufferImage(*viewport)
-        return self.color_buffer
-
-    def get_depth_buffer(self):
-        """Get the depth buffer.
-
-        :rtype: :py:class:`~pyglet.image.DepthBufferImage`
-        """
-        viewport = self.get_viewport()
-        viewport_width = viewport[2]
-        viewport_height = viewport[3]
-        if (not self.depth_buffer or
-                viewport_width != self.depth_buffer.width or
-                viewport_height != self.depth_buffer.height):
-            self.depth_buffer = DepthBufferImage(*viewport)
-        return self.depth_buffer
-
-    def get_buffer_mask(self):
-        """Get a free bitmask buffer.
-
-        A bitmask buffer is a buffer referencing a single bit in the stencil
-        buffer.  If no bits are free, `ImageException` is raised.  Bits are
-        released when the bitmask buffer is garbage collected.
-
-        :rtype: :py:class:`~pyglet.image.BufferImageMask`
-        """
-        if self.free_stencil_bits is None:
-            try:
-                stencil_bits = GLint()
-                glGetFramebufferAttachmentParameteriv(GL_DRAW_FRAMEBUFFER,
-                                                      GL_STENCIL,
-                                                      GL_FRAMEBUFFER_ATTACHMENT_STENCIL_SIZE,
-                                                      stencil_bits)
-                self.free_stencil_bits = list(range(stencil_bits.value))
-            except GLException:
-                pass
-
-        if not self.free_stencil_bits:
-            raise ImageException('No free stencil bits are available.')
-
-        stencil_bit = self.free_stencil_bits.pop(0)
-        x, y, width, height = self.get_viewport()
-        bufimg = BufferImageMask(x, y, width, height)
-        bufimg.stencil_bit = stencil_bit
-
-        def release_buffer(ref, owner=self):
-            owner.free_stencil_bits.insert(0, stencil_bit)
-
-        self.refs.append(weakref.ref(bufimg, release_buffer))
-
-        return bufimg
-
-
-def get_buffer_manager():
-    """Get the buffer manager for the current OpenGL context.
-
-    :rtype: :py:class:`~pyglet.image.BufferManager`
-    """
-    context = pyglet.gl.current_context
-    if not hasattr(context, 'image_buffer_manager'):
-        context.image_buffer_manager = BufferManager()
-    return context.image_buffer_manager
-
-
-class BufferImage(AbstractImage):
-    """An abstract framebuffer.
-    """
-    #: The OpenGL read and write target for this buffer.
-    gl_buffer = GL_BACK
-
-    #: The OpenGL format constant for image data.
-    gl_format = 0
-
-    #: The format string used for image data.
-    format = ''
-
-    owner = None
-
-    # TODO: enable methods
-
-    def __init__(self, x, y, width, height):
-        super().__init__(width, height)
-        self.x = x
-        self.y = y
-        self.width = width
-        self.height = height
-
-    def get_image_data(self):
-        buf = (GLubyte * (len(self.format) * self.width * self.height))()
-
-        x = self.x
-        y = self.y
-        if self.owner:
-            x += self.owner.x
-            y += self.owner.y
-
-        glReadBuffer(self.gl_buffer)
-        glPixelStorei(GL_PACK_ALIGNMENT, 1)
-        glReadPixels(x, y, self.width, self.height, self.gl_format, GL_UNSIGNED_BYTE, buf)
-        return ImageData(self.width, self.height, self.format, buf)
-
-    def get_region(self, x, y, width, height):
-        if self.owner:
-            return self.owner.get_region(x + self.x, y + self.y, width, height)
-
-        region = self.__class__(x + self.x, y + self.y, width, height)
-        region.gl_buffer = self.gl_buffer
-        region.owner = self
-        return region
-
-
-class ColorBufferImage(BufferImage):
-    """A color framebuffer.
-
-    This class is used to wrap the primary color buffer (i.e., the back
-    buffer)
-    """
-    gl_format = GL_RGBA
-    format = 'RGBA'
-
-    def get_texture(self, rectangle=False):
-        texture = Texture.create(self.width, self.height, GL_TEXTURE_2D, GL_RGBA, blank_data=False)
-        self.blit_to_texture(texture.target, texture.level, self.anchor_x, self.anchor_y, 0)
-        return texture
-
-    def blit_to_texture(self, target, level, x, y, z):
-        glReadBuffer(self.gl_buffer)
-        glCopyTexSubImage2D(target, level, x-self.anchor_x, y-self.anchor_y, self.x, self.y, self.width, self.height)
-
-
-class DepthBufferImage(BufferImage):
-    """The depth buffer.
-    """
-    gl_format = GL_DEPTH_COMPONENT
-    format = 'L'
-
-    def get_texture(self, rectangle=False):
-        assert rectangle is False, 'Depth textures cannot be rectangular'
-
-        texture = DepthTexture.create(self.width, self.height, GL_TEXTURE_2D, None)
-        if self.anchor_x or self.anchor_y:
-            texture.anchor_x = self.anchor_x
-            texture.anchor_y = self.anchor_y
-
-        glReadBuffer(self.gl_buffer)
-        glCopyTexImage2D(texture.target, 0,
-                         GL_DEPTH_COMPONENT,
-                         self.x, self.y, self.width, self.height,
-                         0)
-        return texture
-
-    def blit_to_texture(self, target, level, x, y, z):
-        glReadBuffer(self.gl_buffer)
-        glCopyTexSubImage2D(target, level, x-self.anchor_x, y-self.anchor_y, self.x, self.y, self.width, self.height)
-
-
-class BufferImageMask(BufferImage):
-    """A single bit of the stencil buffer.
-    """
-    gl_format = GL_STENCIL_INDEX
-    format = 'L'
-
-    # TODO mask methods
diff --git a/spaces/abrar-lohia/text-2-character-anim/pyrender/setup.py b/spaces/abrar-lohia/text-2-character-anim/pyrender/setup.py
deleted file mode 100644
index 9a11b5c2d32983cd3c240597a504995dfb439af4..0000000000000000000000000000000000000000
--- a/spaces/abrar-lohia/text-2-character-anim/pyrender/setup.py
+++ /dev/null
@@ -1,76 +0,0 @@
-"""
-Setup of pyrender Python codebase.
-
-Author: Matthew Matl
-"""
-import sys
-from setuptools import setup
-
-# load __version__
-exec(open('pyrender/version.py').read())
-
-def get_imageio_dep():
-    if sys.version[0] == "2":
-        return 'imageio<=2.6.1'
-    return 'imageio'
-
-requirements = [
-    'freetype-py',                # For font loading
-    get_imageio_dep(),            # For Image I/O
-    'networkx',                   # For the scene graph
-    'numpy',                      # Numpy
-    'Pillow',                     # For Trimesh texture conversions
-    'pyglet>=1.5.24',             # For the pyglet viewer
-    'PyOpenGL~=3.1.0',            # For OpenGL
-    'PyOpenGL_accelerate~=3.1.0', # For OpenGL
-    'scipy',                      # Because of trimesh missing dep
-    'six',                        # For Python 2/3 interop
-    'trimesh',                    # For meshes
-]
-
-dev_requirements = [
-    'flake8',            # Code formatting checker
-    'pre-commit',        # Pre-commit hooks
-    'pytest',            # Code testing
-    'pytest-cov',        # Coverage testing
-    'tox',               # Automatic virtualenv testing
-]
-
-docs_requirements = [
-    'sphinx',            # General doc library
-    'sphinx_rtd_theme',  # RTD theme for sphinx
-    'sphinx-automodapi'  # For generating nice tables
-]
-
-
-setup(
-    name = 'pyrender',
-    version=__version__,
-    description='Easy-to-use Python renderer for 3D visualization',
-    long_description='A simple implementation of Physically-Based Rendering '
-                       '(PBR) in Python. Compliant with the glTF 2.0 standard.',
-    author='Matthew Matl',
-    author_email='matthewcmatl@gmail.com',
-    license='MIT License',
-    url = 'https://github.com/mmatl/pyrender',
-    classifiers = [
-        'Development Status :: 4 - Beta',
-        'License :: OSI Approved :: MIT License',
-        'Operating System :: POSIX :: Linux',
-        'Operating System :: MacOS :: MacOS X',
-        'Programming Language :: Python :: 2.7',
-        'Programming Language :: Python :: 3.5',
-        'Programming Language :: Python :: 3.6',
-        'Natural Language :: English',
-        'Topic :: Scientific/Engineering'
-    ],
-    keywords = 'rendering graphics opengl 3d visualization pbr gltf',
-    packages = ['pyrender', 'pyrender.platforms'],
-    setup_requires = requirements,
-    install_requires = requirements,
-    extras_require={
-        'dev': dev_requirements,
-        'docs': docs_requirements,
-    },
-    include_package_data=True
-)
diff --git a/spaces/aijack/jojo/e4e/README.md b/spaces/aijack/jojo/e4e/README.md
deleted file mode 100644
index 14b6bc701b2bad3c2fc7b1d9b36f1892681ded5f..0000000000000000000000000000000000000000
--- a/spaces/aijack/jojo/e4e/README.md
+++ /dev/null
@@ -1,142 +0,0 @@
-# Designing an Encoder for StyleGAN Image Manipulation
-  <a href="https://arxiv.org/abs/2102.02766"><img src="https://img.shields.io/badge/arXiv-2008.00951-b31b1b.svg"></a>
-  <a href="https://opensource.org/licenses/MIT"><img src="https://img.shields.io/badge/License-MIT-yellow.svg"></a>
-  [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](http://colab.research.google.com/github/omertov/encoder4editing/blob/main/notebooks/inference_playground.ipynb)
-
-> Recently, there has been a surge of diverse methods for performing image editing by employing pre-trained unconditional generators. Applying these methods on real images, however, remains a challenge, as it necessarily requires the inversion of the images into their latent space. To successfully invert a real image, one needs to find a latent code that reconstructs the input image accurately, and more importantly, allows for its meaningful manipulation. In this paper, we carefully study the latent space of StyleGAN, the state-of-the-art unconditional generator. We identify and analyze the existence of a distortion-editability tradeoff and a distortion-perception tradeoff within the StyleGAN latent space. We then suggest two principles for designing encoders in a manner that allows one to control the proximity of the inversions to regions that StyleGAN was originally trained on. We present an encoder based on our two principles that is specifically designed for facilitating editing on real images by balancing these tradeoffs. By evaluating its performance qualitatively and quantitatively on numerous challenging domains, including cars and horses, we show that our inversion method, followed by common editing techniques, achieves superior real-image editing quality, with only a small reconstruction accuracy drop.
-
-<p align="center">
-<img src="docs/teaser.jpg" width="800px"/>
-</p>
-
-## Description   
-Official Implementation of "<a href="https://arxiv.org/abs/2102.02766">Designing an Encoder for StyleGAN Image Manipulation</a>" paper for both training and evaluation. 
-The e4e encoder is specifically designed to complement existing image manipulation techniques performed over StyleGAN's latent space.
-
-## Recent Updates
-`2021.03.25`: Add pose editing direction.
-
-## Getting Started
-### Prerequisites
-- Linux or macOS
-- NVIDIA GPU + CUDA CuDNN (CPU may be possible with some modifications, but is not inherently supported)
-- Python 3
-
-### Installation
-- Clone the repository:
-``` 
-git clone https://github.com/omertov/encoder4editing.git
-cd encoder4editing
-```
-- Dependencies:  
-We recommend running this repository using [Anaconda](https://docs.anaconda.com/anaconda/install/). 
-All dependencies for defining the environment are provided in `environment/e4e_env.yaml`.
-
-### Inference Notebook
-We provide a Jupyter notebook found in `notebooks/inference_playground.ipynb` that allows one to encode and perform several editings on real images using StyleGAN.   
-
-### Pretrained Models
-Please download the pre-trained models from the following links. Each e4e model contains the entire pSp framework architecture, including the encoder and decoder weights.
-| Path | Description
-| :--- | :----------
-|[FFHQ Inversion](https://drive.google.com/file/d/1cUv_reLE6k3604or78EranS7XzuVMWeO/view?usp=sharing)  | FFHQ e4e encoder.
-|[Cars Inversion](https://drive.google.com/file/d/17faPqBce2m1AQeLCLHUVXaDfxMRU2QcV/view?usp=sharing)  | Cars e4e encoder.
-|[Horse Inversion](https://drive.google.com/file/d/1TkLLnuX86B_BMo2ocYD0kX9kWh53rUVX/view?usp=sharing)  | Horse e4e encoder.
-|[Church Inversion](https://drive.google.com/file/d/1-L0ZdnQLwtdy6-A_Ccgq5uNJGTqE7qBa/view?usp=sharing) | Church e4e encoder.
-
-If you wish to use one of the pretrained models for training or inference, you may do so using the flag `--checkpoint_path`.
-
-In addition, we provide various auxiliary models needed for training your own e4e model from scratch.
-| Path | Description
-| :--- | :----------
-|[FFHQ StyleGAN](https://drive.google.com/file/d/1EM87UquaoQmk17Q8d5kYIAHqu0dkYqdT/view?usp=sharing) | StyleGAN model pretrained on FFHQ taken from [rosinality](https://github.com/rosinality/stylegan2-pytorch) with 1024x1024 output resolution.
-|[IR-SE50 Model](https://drive.google.com/file/d/1KW7bjndL3QG3sxBbZxreGHigcCCpsDgn/view?usp=sharing) | Pretrained IR-SE50 model taken from [TreB1eN](https://github.com/TreB1eN/InsightFace_Pytorch) for use in our ID loss during training.
-|[MOCOv2 Model](https://drive.google.com/file/d/18rLcNGdteX5LwT7sv_F7HWr12HpVEzVe/view?usp=sharing) | Pretrained ResNet-50 model trained using MOCOv2 for use in our simmilarity loss for domains other then human faces during training.
-
-By default, we assume that all auxiliary models are downloaded and saved to the directory `pretrained_models`. However, you may use your own paths by changing the necessary values in `configs/path_configs.py`. 
-
-## Training
-To train the e4e encoder, make sure the paths to the required models, as well as training and testing data is configured in `configs/path_configs.py` and `configs/data_configs.py`.
-#### **Training the e4e Encoder**
-```
-python scripts/train.py \
---dataset_type cars_encode \
---exp_dir new/experiment/directory \
---start_from_latent_avg \
---use_w_pool \
---w_discriminator_lambda 0.1 \
---progressive_start 20000 \
---id_lambda 0.5 \
---val_interval 10000 \
---max_steps 200000 \
---stylegan_size 512 \
---stylegan_weights path/to/pretrained/stylegan.pt \
---workers 8 \
---batch_size 8 \
---test_batch_size 4 \
---test_workers 4 
-```
-
-#### Training on your own dataset
-In order to train the e4e encoder on a custom dataset, perform the following adjustments:
-1. Insert the paths to your train and test data into the `dataset_paths` variable defined in `configs/paths_config.py`:
-```
-dataset_paths = {
-    'my_train_data': '/path/to/train/images/directory',
-    'my_test_data': '/path/to/test/images/directory'
-}
-```
-2. Configure a new dataset under the DATASETS variable defined in `configs/data_configs.py`:
-```
-DATASETS = {
-   'my_data_encode': {
-        'transforms': transforms_config.EncodeTransforms,
-        'train_source_root': dataset_paths['my_train_data'],
-        'train_target_root': dataset_paths['my_train_data'],
-        'test_source_root': dataset_paths['my_test_data'],
-        'test_target_root': dataset_paths['my_test_data']
-    }
-}
-```
-Refer to `configs/transforms_config.py` for the transformations applied to the train and test images during training. 
-
-3. Finally, run a training session with `--dataset_type my_data_encode`.
-
-## Inference
-Having trained your model, you can use `scripts/inference.py` to apply the model on a set of images.   
-For example, 
-```
-python scripts/inference.py \
---images_dir=/path/to/images/directory \
---save_dir=/path/to/saving/directory \
-path/to/checkpoint.pt 
-```
-
-## Latent Editing Consistency (LEC)
-As described in the paper, we suggest a new metric, Latent Editing Consistency (LEC), for evaluating the encoder's 
-performance.
-We provide an example for calculating the metric over the FFHQ StyleGAN using the aging editing direction in 
-`metrics/LEC.py`.     
-
-To run the example: 
-```
-cd metrics
-python LEC.py \
---images_dir=/path/to/images/directory \
-path/to/checkpoint.pt 
-```
-
-## Acknowledgments
-This code borrows heavily from [pixel2style2pixel](https://github.com/eladrich/pixel2style2pixel)
-
-## Citation
-If you use this code for your research, please cite our paper <a href="https://arxiv.org/abs/2102.02766">Designing an Encoder for StyleGAN Image Manipulation</a>:
-
-```
-@article{tov2021designing,
-  title={Designing an Encoder for StyleGAN Image Manipulation},
-  author={Tov, Omer and Alaluf, Yuval and Nitzan, Yotam and Patashnik, Or and Cohen-Or, Daniel},
-  journal={arXiv preprint arXiv:2102.02766},
-  year={2021}
-}
-```
diff --git a/spaces/aijack/jojo/e4e/editings/ganspace.py b/spaces/aijack/jojo/e4e/editings/ganspace.py
deleted file mode 100644
index 0c286a421280c542e9776a75e64bb65409da8fc7..0000000000000000000000000000000000000000
--- a/spaces/aijack/jojo/e4e/editings/ganspace.py
+++ /dev/null
@@ -1,22 +0,0 @@
-import torch
-
-
-def edit(latents, pca, edit_directions):
-    edit_latents = []
-    for latent in latents:
-        for pca_idx, start, end, strength in edit_directions:
-            delta = get_delta(pca, latent, pca_idx, strength)
-            delta_padded = torch.zeros(latent.shape).to('cuda')
-            delta_padded[start:end] += delta.repeat(end - start, 1)
-            edit_latents.append(latent + delta_padded)
-    return torch.stack(edit_latents)
-
-
-def get_delta(pca, latent, idx, strength):
-    # pca: ganspace checkpoint. latent: (16, 512) w+
-    w_centered = latent - pca['mean'].to('cuda')
-    lat_comp = pca['comp'].to('cuda')
-    lat_std = pca['std'].to('cuda')
-    w_coord = torch.sum(w_centered[0].reshape(-1)*lat_comp[idx].reshape(-1)) / lat_std[idx]
-    delta = (strength - w_coord)*lat_comp[idx]*lat_std[idx]
-    return delta
diff --git a/spaces/akhaliq/Deit/app.py b/spaces/akhaliq/Deit/app.py
deleted file mode 100644
index a4ae366e2df23e7efa5daa2c7acdcaa75a057ce3..0000000000000000000000000000000000000000
--- a/spaces/akhaliq/Deit/app.py
+++ /dev/null
@@ -1,59 +0,0 @@
-from PIL import Image
-
-import torch
-import timm
-import torchvision
-import torchvision.transforms as T
-
-from timm.data.constants import IMAGENET_DEFAULT_MEAN, IMAGENET_DEFAULT_STD
-import gradio as gr
-
-torch.set_grad_enabled(False);
-
-with open("imagenet_classes.txt", "r") as f:
-    imagenet_categories = [s.strip() for s in f.readlines()]
-
-transform = T.Compose([
-    T.Resize(256, interpolation=3),
-    T.CenterCrop(224),
-    T.ToTensor(),
-    T.Normalize(IMAGENET_DEFAULT_MEAN, IMAGENET_DEFAULT_STD),
-])
-
-model = torch.hub.load('facebookresearch/deit:main', 'deit_base_patch16_224', pretrained=True)
-
-def detr(im):
-  img = transform(im).unsqueeze(0)
-
-  # compute the predictions
-  out = model(img)
-
-  # and convert them into probabilities
-  scores = torch.nn.functional.softmax(out, dim=-1)[0]
-
-  # finally get the index of the prediction with highest score
-  topk_scores, topk_label = torch.topk(scores, k=5, dim=-1)
-
-
-  d = {}
-  for i in range(5):
-      pred_name = imagenet_categories[topk_label[i]]
-      pred_name = f"{pred_name:<25}"
-      score = topk_scores[i]
-      score = f"{score:.3f}"
-      d[pred_name] = score
-  return d
-
-inputs = gr.inputs.Image(type='pil', label="Original Image")
-outputs = gr.outputs.Label(type="confidences",num_top_classes=5)
-
-title = "Deit"
-description = "Gradio demo for Facebook DeiT: Data-efficient Image Transformers. To use it, simply upload your image, or click one of the examples to load them. Read more at the links below."
-article = "<p style='text-align: center'><a href='https://arxiv.org/abs/2012.12877' target='_blank'>Training data-efficient image transformers & distillation through attention</a> | <a href='https://github.com/facebookresearch/deit' target='_blank'>Github Repo</a></p>"
-
-examples = [
-    ['deer.jpeg'],
-    ['cat.jpeg']
-]
-
-gr.Interface(detr, inputs, outputs, title=title, description=description, article=article, examples=examples).launch() 
\ No newline at end of file
diff --git a/spaces/akhaliq/neural-waveshaping-synthesis/neural_waveshaping_synthesis/utils/utils.py b/spaces/akhaliq/neural-waveshaping-synthesis/neural_waveshaping_synthesis/utils/utils.py
deleted file mode 100644
index 8037684781679d26bf4576a8842c8a1934c49fde..0000000000000000000000000000000000000000
--- a/spaces/akhaliq/neural-waveshaping-synthesis/neural_waveshaping_synthesis/utils/utils.py
+++ /dev/null
@@ -1,23 +0,0 @@
-import os
-from typing import Callable, Sequence
-
-
-def apply(fn: Callable[[any], any], x: Sequence[any]):
-    if type(x) not in (tuple, list):
-        raise TypeError("x must be a tuple or list.")
-    return type(x)([fn(element) for element in x])
-
-
-def apply_unpack(fn: Callable[[any], any], x: Sequence[Sequence[any]]):
-    if type(x) not in (tuple, list):
-        raise TypeError("x must be a tuple or list.")
-    return type(x)([fn(*element) for element in x])
-
-
-def unzip(x: Sequence[any]):
-    return list(zip(*x))
-
-
-def make_dir_if_not_exists(path):
-    if not os.path.exists(path):
-        os.makedirs(path, exist_ok=True)
diff --git a/spaces/alexray/btc_predictor/venv/lib/python3.10/site-packages/pip/_vendor/idna/idnadata.py b/spaces/alexray/btc_predictor/venv/lib/python3.10/site-packages/pip/_vendor/idna/idnadata.py
deleted file mode 100644
index 1b5805d15e53994f9909dd6f064603574eefdb32..0000000000000000000000000000000000000000
--- a/spaces/alexray/btc_predictor/venv/lib/python3.10/site-packages/pip/_vendor/idna/idnadata.py
+++ /dev/null
@@ -1,2137 +0,0 @@
-# This file is automatically generated by tools/idna-data
-
-__version__ = '14.0.0'
-scripts = {
-    'Greek': (
-        0x37000000374,
-        0x37500000378,
-        0x37a0000037e,
-        0x37f00000380,
-        0x38400000385,
-        0x38600000387,
-        0x3880000038b,
-        0x38c0000038d,
-        0x38e000003a2,
-        0x3a3000003e2,
-        0x3f000000400,
-        0x1d2600001d2b,
-        0x1d5d00001d62,
-        0x1d6600001d6b,
-        0x1dbf00001dc0,
-        0x1f0000001f16,
-        0x1f1800001f1e,
-        0x1f2000001f46,
-        0x1f4800001f4e,
-        0x1f5000001f58,
-        0x1f5900001f5a,
-        0x1f5b00001f5c,
-        0x1f5d00001f5e,
-        0x1f5f00001f7e,
-        0x1f8000001fb5,
-        0x1fb600001fc5,
-        0x1fc600001fd4,
-        0x1fd600001fdc,
-        0x1fdd00001ff0,
-        0x1ff200001ff5,
-        0x1ff600001fff,
-        0x212600002127,
-        0xab650000ab66,
-        0x101400001018f,
-        0x101a0000101a1,
-        0x1d2000001d246,
-    ),
-    'Han': (
-        0x2e8000002e9a,
-        0x2e9b00002ef4,
-        0x2f0000002fd6,
-        0x300500003006,
-        0x300700003008,
-        0x30210000302a,
-        0x30380000303c,
-        0x340000004dc0,
-        0x4e000000a000,
-        0xf9000000fa6e,
-        0xfa700000fada,
-        0x16fe200016fe4,
-        0x16ff000016ff2,
-        0x200000002a6e0,
-        0x2a7000002b739,
-        0x2b7400002b81e,
-        0x2b8200002cea2,
-        0x2ceb00002ebe1,
-        0x2f8000002fa1e,
-        0x300000003134b,
-    ),
-    'Hebrew': (
-        0x591000005c8,
-        0x5d0000005eb,
-        0x5ef000005f5,
-        0xfb1d0000fb37,
-        0xfb380000fb3d,
-        0xfb3e0000fb3f,
-        0xfb400000fb42,
-        0xfb430000fb45,
-        0xfb460000fb50,
-    ),
-    'Hiragana': (
-        0x304100003097,
-        0x309d000030a0,
-        0x1b0010001b120,
-        0x1b1500001b153,
-        0x1f2000001f201,
-    ),
-    'Katakana': (
-        0x30a1000030fb,
-        0x30fd00003100,
-        0x31f000003200,
-        0x32d0000032ff,
-        0x330000003358,
-        0xff660000ff70,
-        0xff710000ff9e,
-        0x1aff00001aff4,
-        0x1aff50001affc,
-        0x1affd0001afff,
-        0x1b0000001b001,
-        0x1b1200001b123,
-        0x1b1640001b168,
-    ),
-}
-joining_types = {
-    0x600: 85,
-    0x601: 85,
-    0x602: 85,
-    0x603: 85,
-    0x604: 85,
-    0x605: 85,
-    0x608: 85,
-    0x60b: 85,
-    0x620: 68,
-    0x621: 85,
-    0x622: 82,
-    0x623: 82,
-    0x624: 82,
-    0x625: 82,
-    0x626: 68,
-    0x627: 82,
-    0x628: 68,
-    0x629: 82,
-    0x62a: 68,
-    0x62b: 68,
-    0x62c: 68,
-    0x62d: 68,
-    0x62e: 68,
-    0x62f: 82,
-    0x630: 82,
-    0x631: 82,
-    0x632: 82,
-    0x633: 68,
-    0x634: 68,
-    0x635: 68,
-    0x636: 68,
-    0x637: 68,
-    0x638: 68,
-    0x639: 68,
-    0x63a: 68,
-    0x63b: 68,
-    0x63c: 68,
-    0x63d: 68,
-    0x63e: 68,
-    0x63f: 68,
-    0x640: 67,
-    0x641: 68,
-    0x642: 68,
-    0x643: 68,
-    0x644: 68,
-    0x645: 68,
-    0x646: 68,
-    0x647: 68,
-    0x648: 82,
-    0x649: 68,
-    0x64a: 68,
-    0x66e: 68,
-    0x66f: 68,
-    0x671: 82,
-    0x672: 82,
-    0x673: 82,
-    0x674: 85,
-    0x675: 82,
-    0x676: 82,
-    0x677: 82,
-    0x678: 68,
-    0x679: 68,
-    0x67a: 68,
-    0x67b: 68,
-    0x67c: 68,
-    0x67d: 68,
-    0x67e: 68,
-    0x67f: 68,
-    0x680: 68,
-    0x681: 68,
-    0x682: 68,
-    0x683: 68,
-    0x684: 68,
-    0x685: 68,
-    0x686: 68,
-    0x687: 68,
-    0x688: 82,
-    0x689: 82,
-    0x68a: 82,
-    0x68b: 82,
-    0x68c: 82,
-    0x68d: 82,
-    0x68e: 82,
-    0x68f: 82,
-    0x690: 82,
-    0x691: 82,
-    0x692: 82,
-    0x693: 82,
-    0x694: 82,
-    0x695: 82,
-    0x696: 82,
-    0x697: 82,
-    0x698: 82,
-    0x699: 82,
-    0x69a: 68,
-    0x69b: 68,
-    0x69c: 68,
-    0x69d: 68,
-    0x69e: 68,
-    0x69f: 68,
-    0x6a0: 68,
-    0x6a1: 68,
-    0x6a2: 68,
-    0x6a3: 68,
-    0x6a4: 68,
-    0x6a5: 68,
-    0x6a6: 68,
-    0x6a7: 68,
-    0x6a8: 68,
-    0x6a9: 68,
-    0x6aa: 68,
-    0x6ab: 68,
-    0x6ac: 68,
-    0x6ad: 68,
-    0x6ae: 68,
-    0x6af: 68,
-    0x6b0: 68,
-    0x6b1: 68,
-    0x6b2: 68,
-    0x6b3: 68,
-    0x6b4: 68,
-    0x6b5: 68,
-    0x6b6: 68,
-    0x6b7: 68,
-    0x6b8: 68,
-    0x6b9: 68,
-    0x6ba: 68,
-    0x6bb: 68,
-    0x6bc: 68,
-    0x6bd: 68,
-    0x6be: 68,
-    0x6bf: 68,
-    0x6c0: 82,
-    0x6c1: 68,
-    0x6c2: 68,
-    0x6c3: 82,
-    0x6c4: 82,
-    0x6c5: 82,
-    0x6c6: 82,
-    0x6c7: 82,
-    0x6c8: 82,
-    0x6c9: 82,
-    0x6ca: 82,
-    0x6cb: 82,
-    0x6cc: 68,
-    0x6cd: 82,
-    0x6ce: 68,
-    0x6cf: 82,
-    0x6d0: 68,
-    0x6d1: 68,
-    0x6d2: 82,
-    0x6d3: 82,
-    0x6d5: 82,
-    0x6dd: 85,
-    0x6ee: 82,
-    0x6ef: 82,
-    0x6fa: 68,
-    0x6fb: 68,
-    0x6fc: 68,
-    0x6ff: 68,
-    0x70f: 84,
-    0x710: 82,
-    0x712: 68,
-    0x713: 68,
-    0x714: 68,
-    0x715: 82,
-    0x716: 82,
-    0x717: 82,
-    0x718: 82,
-    0x719: 82,
-    0x71a: 68,
-    0x71b: 68,
-    0x71c: 68,
-    0x71d: 68,
-    0x71e: 82,
-    0x71f: 68,
-    0x720: 68,
-    0x721: 68,
-    0x722: 68,
-    0x723: 68,
-    0x724: 68,
-    0x725: 68,
-    0x726: 68,
-    0x727: 68,
-    0x728: 82,
-    0x729: 68,
-    0x72a: 82,
-    0x72b: 68,
-    0x72c: 82,
-    0x72d: 68,
-    0x72e: 68,
-    0x72f: 82,
-    0x74d: 82,
-    0x74e: 68,
-    0x74f: 68,
-    0x750: 68,
-    0x751: 68,
-    0x752: 68,
-    0x753: 68,
-    0x754: 68,
-    0x755: 68,
-    0x756: 68,
-    0x757: 68,
-    0x758: 68,
-    0x759: 82,
-    0x75a: 82,
-    0x75b: 82,
-    0x75c: 68,
-    0x75d: 68,
-    0x75e: 68,
-    0x75f: 68,
-    0x760: 68,
-    0x761: 68,
-    0x762: 68,
-    0x763: 68,
-    0x764: 68,
-    0x765: 68,
-    0x766: 68,
-    0x767: 68,
-    0x768: 68,
-    0x769: 68,
-    0x76a: 68,
-    0x76b: 82,
-    0x76c: 82,
-    0x76d: 68,
-    0x76e: 68,
-    0x76f: 68,
-    0x770: 68,
-    0x771: 82,
-    0x772: 68,
-    0x773: 82,
-    0x774: 82,
-    0x775: 68,
-    0x776: 68,
-    0x777: 68,
-    0x778: 82,
-    0x779: 82,
-    0x77a: 68,
-    0x77b: 68,
-    0x77c: 68,
-    0x77d: 68,
-    0x77e: 68,
-    0x77f: 68,
-    0x7ca: 68,
-    0x7cb: 68,
-    0x7cc: 68,
-    0x7cd: 68,
-    0x7ce: 68,
-    0x7cf: 68,
-    0x7d0: 68,
-    0x7d1: 68,
-    0x7d2: 68,
-    0x7d3: 68,
-    0x7d4: 68,
-    0x7d5: 68,
-    0x7d6: 68,
-    0x7d7: 68,
-    0x7d8: 68,
-    0x7d9: 68,
-    0x7da: 68,
-    0x7db: 68,
-    0x7dc: 68,
-    0x7dd: 68,
-    0x7de: 68,
-    0x7df: 68,
-    0x7e0: 68,
-    0x7e1: 68,
-    0x7e2: 68,
-    0x7e3: 68,
-    0x7e4: 68,
-    0x7e5: 68,
-    0x7e6: 68,
-    0x7e7: 68,
-    0x7e8: 68,
-    0x7e9: 68,
-    0x7ea: 68,
-    0x7fa: 67,
-    0x840: 82,
-    0x841: 68,
-    0x842: 68,
-    0x843: 68,
-    0x844: 68,
-    0x845: 68,
-    0x846: 82,
-    0x847: 82,
-    0x848: 68,
-    0x849: 82,
-    0x84a: 68,
-    0x84b: 68,
-    0x84c: 68,
-    0x84d: 68,
-    0x84e: 68,
-    0x84f: 68,
-    0x850: 68,
-    0x851: 68,
-    0x852: 68,
-    0x853: 68,
-    0x854: 82,
-    0x855: 68,
-    0x856: 82,
-    0x857: 82,
-    0x858: 82,
-    0x860: 68,
-    0x861: 85,
-    0x862: 68,
-    0x863: 68,
-    0x864: 68,
-    0x865: 68,
-    0x866: 85,
-    0x867: 82,
-    0x868: 68,
-    0x869: 82,
-    0x86a: 82,
-    0x870: 82,
-    0x871: 82,
-    0x872: 82,
-    0x873: 82,
-    0x874: 82,
-    0x875: 82,
-    0x876: 82,
-    0x877: 82,
-    0x878: 82,
-    0x879: 82,
-    0x87a: 82,
-    0x87b: 82,
-    0x87c: 82,
-    0x87d: 82,
-    0x87e: 82,
-    0x87f: 82,
-    0x880: 82,
-    0x881: 82,
-    0x882: 82,
-    0x883: 67,
-    0x884: 67,
-    0x885: 67,
-    0x886: 68,
-    0x887: 85,
-    0x888: 85,
-    0x889: 68,
-    0x88a: 68,
-    0x88b: 68,
-    0x88c: 68,
-    0x88d: 68,
-    0x88e: 82,
-    0x890: 85,
-    0x891: 85,
-    0x8a0: 68,
-    0x8a1: 68,
-    0x8a2: 68,
-    0x8a3: 68,
-    0x8a4: 68,
-    0x8a5: 68,
-    0x8a6: 68,
-    0x8a7: 68,
-    0x8a8: 68,
-    0x8a9: 68,
-    0x8aa: 82,
-    0x8ab: 82,
-    0x8ac: 82,
-    0x8ad: 85,
-    0x8ae: 82,
-    0x8af: 68,
-    0x8b0: 68,
-    0x8b1: 82,
-    0x8b2: 82,
-    0x8b3: 68,
-    0x8b4: 68,
-    0x8b5: 68,
-    0x8b6: 68,
-    0x8b7: 68,
-    0x8b8: 68,
-    0x8b9: 82,
-    0x8ba: 68,
-    0x8bb: 68,
-    0x8bc: 68,
-    0x8bd: 68,
-    0x8be: 68,
-    0x8bf: 68,
-    0x8c0: 68,
-    0x8c1: 68,
-    0x8c2: 68,
-    0x8c3: 68,
-    0x8c4: 68,
-    0x8c5: 68,
-    0x8c6: 68,
-    0x8c7: 68,
-    0x8c8: 68,
-    0x8e2: 85,
-    0x1806: 85,
-    0x1807: 68,
-    0x180a: 67,
-    0x180e: 85,
-    0x1820: 68,
-    0x1821: 68,
-    0x1822: 68,
-    0x1823: 68,
-    0x1824: 68,
-    0x1825: 68,
-    0x1826: 68,
-    0x1827: 68,
-    0x1828: 68,
-    0x1829: 68,
-    0x182a: 68,
-    0x182b: 68,
-    0x182c: 68,
-    0x182d: 68,
-    0x182e: 68,
-    0x182f: 68,
-    0x1830: 68,
-    0x1831: 68,
-    0x1832: 68,
-    0x1833: 68,
-    0x1834: 68,
-    0x1835: 68,
-    0x1836: 68,
-    0x1837: 68,
-    0x1838: 68,
-    0x1839: 68,
-    0x183a: 68,
-    0x183b: 68,
-    0x183c: 68,
-    0x183d: 68,
-    0x183e: 68,
-    0x183f: 68,
-    0x1840: 68,
-    0x1841: 68,
-    0x1842: 68,
-    0x1843: 68,
-    0x1844: 68,
-    0x1845: 68,
-    0x1846: 68,
-    0x1847: 68,
-    0x1848: 68,
-    0x1849: 68,
-    0x184a: 68,
-    0x184b: 68,
-    0x184c: 68,
-    0x184d: 68,
-    0x184e: 68,
-    0x184f: 68,
-    0x1850: 68,
-    0x1851: 68,
-    0x1852: 68,
-    0x1853: 68,
-    0x1854: 68,
-    0x1855: 68,
-    0x1856: 68,
-    0x1857: 68,
-    0x1858: 68,
-    0x1859: 68,
-    0x185a: 68,
-    0x185b: 68,
-    0x185c: 68,
-    0x185d: 68,
-    0x185e: 68,
-    0x185f: 68,
-    0x1860: 68,
-    0x1861: 68,
-    0x1862: 68,
-    0x1863: 68,
-    0x1864: 68,
-    0x1865: 68,
-    0x1866: 68,
-    0x1867: 68,
-    0x1868: 68,
-    0x1869: 68,
-    0x186a: 68,
-    0x186b: 68,
-    0x186c: 68,
-    0x186d: 68,
-    0x186e: 68,
-    0x186f: 68,
-    0x1870: 68,
-    0x1871: 68,
-    0x1872: 68,
-    0x1873: 68,
-    0x1874: 68,
-    0x1875: 68,
-    0x1876: 68,
-    0x1877: 68,
-    0x1878: 68,
-    0x1880: 85,
-    0x1881: 85,
-    0x1882: 85,
-    0x1883: 85,
-    0x1884: 85,
-    0x1885: 84,
-    0x1886: 84,
-    0x1887: 68,
-    0x1888: 68,
-    0x1889: 68,
-    0x188a: 68,
-    0x188b: 68,
-    0x188c: 68,
-    0x188d: 68,
-    0x188e: 68,
-    0x188f: 68,
-    0x1890: 68,
-    0x1891: 68,
-    0x1892: 68,
-    0x1893: 68,
-    0x1894: 68,
-    0x1895: 68,
-    0x1896: 68,
-    0x1897: 68,
-    0x1898: 68,
-    0x1899: 68,
-    0x189a: 68,
-    0x189b: 68,
-    0x189c: 68,
-    0x189d: 68,
-    0x189e: 68,
-    0x189f: 68,
-    0x18a0: 68,
-    0x18a1: 68,
-    0x18a2: 68,
-    0x18a3: 68,
-    0x18a4: 68,
-    0x18a5: 68,
-    0x18a6: 68,
-    0x18a7: 68,
-    0x18a8: 68,
-    0x18aa: 68,
-    0x200c: 85,
-    0x200d: 67,
-    0x202f: 85,
-    0x2066: 85,
-    0x2067: 85,
-    0x2068: 85,
-    0x2069: 85,
-    0xa840: 68,
-    0xa841: 68,
-    0xa842: 68,
-    0xa843: 68,
-    0xa844: 68,
-    0xa845: 68,
-    0xa846: 68,
-    0xa847: 68,
-    0xa848: 68,
-    0xa849: 68,
-    0xa84a: 68,
-    0xa84b: 68,
-    0xa84c: 68,
-    0xa84d: 68,
-    0xa84e: 68,
-    0xa84f: 68,
-    0xa850: 68,
-    0xa851: 68,
-    0xa852: 68,
-    0xa853: 68,
-    0xa854: 68,
-    0xa855: 68,
-    0xa856: 68,
-    0xa857: 68,
-    0xa858: 68,
-    0xa859: 68,
-    0xa85a: 68,
-    0xa85b: 68,
-    0xa85c: 68,
-    0xa85d: 68,
-    0xa85e: 68,
-    0xa85f: 68,
-    0xa860: 68,
-    0xa861: 68,
-    0xa862: 68,
-    0xa863: 68,
-    0xa864: 68,
-    0xa865: 68,
-    0xa866: 68,
-    0xa867: 68,
-    0xa868: 68,
-    0xa869: 68,
-    0xa86a: 68,
-    0xa86b: 68,
-    0xa86c: 68,
-    0xa86d: 68,
-    0xa86e: 68,
-    0xa86f: 68,
-    0xa870: 68,
-    0xa871: 68,
-    0xa872: 76,
-    0xa873: 85,
-    0x10ac0: 68,
-    0x10ac1: 68,
-    0x10ac2: 68,
-    0x10ac3: 68,
-    0x10ac4: 68,
-    0x10ac5: 82,
-    0x10ac6: 85,
-    0x10ac7: 82,
-    0x10ac8: 85,
-    0x10ac9: 82,
-    0x10aca: 82,
-    0x10acb: 85,
-    0x10acc: 85,
-    0x10acd: 76,
-    0x10ace: 82,
-    0x10acf: 82,
-    0x10ad0: 82,
-    0x10ad1: 82,
-    0x10ad2: 82,
-    0x10ad3: 68,
-    0x10ad4: 68,
-    0x10ad5: 68,
-    0x10ad6: 68,
-    0x10ad7: 76,
-    0x10ad8: 68,
-    0x10ad9: 68,
-    0x10ada: 68,
-    0x10adb: 68,
-    0x10adc: 68,
-    0x10add: 82,
-    0x10ade: 68,
-    0x10adf: 68,
-    0x10ae0: 68,
-    0x10ae1: 82,
-    0x10ae2: 85,
-    0x10ae3: 85,
-    0x10ae4: 82,
-    0x10aeb: 68,
-    0x10aec: 68,
-    0x10aed: 68,
-    0x10aee: 68,
-    0x10aef: 82,
-    0x10b80: 68,
-    0x10b81: 82,
-    0x10b82: 68,
-    0x10b83: 82,
-    0x10b84: 82,
-    0x10b85: 82,
-    0x10b86: 68,
-    0x10b87: 68,
-    0x10b88: 68,
-    0x10b89: 82,
-    0x10b8a: 68,
-    0x10b8b: 68,
-    0x10b8c: 82,
-    0x10b8d: 68,
-    0x10b8e: 82,
-    0x10b8f: 82,
-    0x10b90: 68,
-    0x10b91: 82,
-    0x10ba9: 82,
-    0x10baa: 82,
-    0x10bab: 82,
-    0x10bac: 82,
-    0x10bad: 68,
-    0x10bae: 68,
-    0x10baf: 85,
-    0x10d00: 76,
-    0x10d01: 68,
-    0x10d02: 68,
-    0x10d03: 68,
-    0x10d04: 68,
-    0x10d05: 68,
-    0x10d06: 68,
-    0x10d07: 68,
-    0x10d08: 68,
-    0x10d09: 68,
-    0x10d0a: 68,
-    0x10d0b: 68,
-    0x10d0c: 68,
-    0x10d0d: 68,
-    0x10d0e: 68,
-    0x10d0f: 68,
-    0x10d10: 68,
-    0x10d11: 68,
-    0x10d12: 68,
-    0x10d13: 68,
-    0x10d14: 68,
-    0x10d15: 68,
-    0x10d16: 68,
-    0x10d17: 68,
-    0x10d18: 68,
-    0x10d19: 68,
-    0x10d1a: 68,
-    0x10d1b: 68,
-    0x10d1c: 68,
-    0x10d1d: 68,
-    0x10d1e: 68,
-    0x10d1f: 68,
-    0x10d20: 68,
-    0x10d21: 68,
-    0x10d22: 82,
-    0x10d23: 68,
-    0x10f30: 68,
-    0x10f31: 68,
-    0x10f32: 68,
-    0x10f33: 82,
-    0x10f34: 68,
-    0x10f35: 68,
-    0x10f36: 68,
-    0x10f37: 68,
-    0x10f38: 68,
-    0x10f39: 68,
-    0x10f3a: 68,
-    0x10f3b: 68,
-    0x10f3c: 68,
-    0x10f3d: 68,
-    0x10f3e: 68,
-    0x10f3f: 68,
-    0x10f40: 68,
-    0x10f41: 68,
-    0x10f42: 68,
-    0x10f43: 68,
-    0x10f44: 68,
-    0x10f45: 85,
-    0x10f51: 68,
-    0x10f52: 68,
-    0x10f53: 68,
-    0x10f54: 82,
-    0x10f70: 68,
-    0x10f71: 68,
-    0x10f72: 68,
-    0x10f73: 68,
-    0x10f74: 82,
-    0x10f75: 82,
-    0x10f76: 68,
-    0x10f77: 68,
-    0x10f78: 68,
-    0x10f79: 68,
-    0x10f7a: 68,
-    0x10f7b: 68,
-    0x10f7c: 68,
-    0x10f7d: 68,
-    0x10f7e: 68,
-    0x10f7f: 68,
-    0x10f80: 68,
-    0x10f81: 68,
-    0x10fb0: 68,
-    0x10fb1: 85,
-    0x10fb2: 68,
-    0x10fb3: 68,
-    0x10fb4: 82,
-    0x10fb5: 82,
-    0x10fb6: 82,
-    0x10fb7: 85,
-    0x10fb8: 68,
-    0x10fb9: 82,
-    0x10fba: 82,
-    0x10fbb: 68,
-    0x10fbc: 68,
-    0x10fbd: 82,
-    0x10fbe: 68,
-    0x10fbf: 68,
-    0x10fc0: 85,
-    0x10fc1: 68,
-    0x10fc2: 82,
-    0x10fc3: 82,
-    0x10fc4: 68,
-    0x10fc5: 85,
-    0x10fc6: 85,
-    0x10fc7: 85,
-    0x10fc8: 85,
-    0x10fc9: 82,
-    0x10fca: 68,
-    0x10fcb: 76,
-    0x110bd: 85,
-    0x110cd: 85,
-    0x1e900: 68,
-    0x1e901: 68,
-    0x1e902: 68,
-    0x1e903: 68,
-    0x1e904: 68,
-    0x1e905: 68,
-    0x1e906: 68,
-    0x1e907: 68,
-    0x1e908: 68,
-    0x1e909: 68,
-    0x1e90a: 68,
-    0x1e90b: 68,
-    0x1e90c: 68,
-    0x1e90d: 68,
-    0x1e90e: 68,
-    0x1e90f: 68,
-    0x1e910: 68,
-    0x1e911: 68,
-    0x1e912: 68,
-    0x1e913: 68,
-    0x1e914: 68,
-    0x1e915: 68,
-    0x1e916: 68,
-    0x1e917: 68,
-    0x1e918: 68,
-    0x1e919: 68,
-    0x1e91a: 68,
-    0x1e91b: 68,
-    0x1e91c: 68,
-    0x1e91d: 68,
-    0x1e91e: 68,
-    0x1e91f: 68,
-    0x1e920: 68,
-    0x1e921: 68,
-    0x1e922: 68,
-    0x1e923: 68,
-    0x1e924: 68,
-    0x1e925: 68,
-    0x1e926: 68,
-    0x1e927: 68,
-    0x1e928: 68,
-    0x1e929: 68,
-    0x1e92a: 68,
-    0x1e92b: 68,
-    0x1e92c: 68,
-    0x1e92d: 68,
-    0x1e92e: 68,
-    0x1e92f: 68,
-    0x1e930: 68,
-    0x1e931: 68,
-    0x1e932: 68,
-    0x1e933: 68,
-    0x1e934: 68,
-    0x1e935: 68,
-    0x1e936: 68,
-    0x1e937: 68,
-    0x1e938: 68,
-    0x1e939: 68,
-    0x1e93a: 68,
-    0x1e93b: 68,
-    0x1e93c: 68,
-    0x1e93d: 68,
-    0x1e93e: 68,
-    0x1e93f: 68,
-    0x1e940: 68,
-    0x1e941: 68,
-    0x1e942: 68,
-    0x1e943: 68,
-    0x1e94b: 84,
-}
-codepoint_classes = {
-    'PVALID': (
-        0x2d0000002e,
-        0x300000003a,
-        0x610000007b,
-        0xdf000000f7,
-        0xf800000100,
-        0x10100000102,
-        0x10300000104,
-        0x10500000106,
-        0x10700000108,
-        0x1090000010a,
-        0x10b0000010c,
-        0x10d0000010e,
-        0x10f00000110,
-        0x11100000112,
-        0x11300000114,
-        0x11500000116,
-        0x11700000118,
-        0x1190000011a,
-        0x11b0000011c,
-        0x11d0000011e,
-        0x11f00000120,
-        0x12100000122,
-        0x12300000124,
-        0x12500000126,
-        0x12700000128,
-        0x1290000012a,
-        0x12b0000012c,
-        0x12d0000012e,
-        0x12f00000130,
-        0x13100000132,
-        0x13500000136,
-        0x13700000139,
-        0x13a0000013b,
-        0x13c0000013d,
-        0x13e0000013f,
-        0x14200000143,
-        0x14400000145,
-        0x14600000147,
-        0x14800000149,
-        0x14b0000014c,
-        0x14d0000014e,
-        0x14f00000150,
-        0x15100000152,
-        0x15300000154,
-        0x15500000156,
-        0x15700000158,
-        0x1590000015a,
-        0x15b0000015c,
-        0x15d0000015e,
-        0x15f00000160,
-        0x16100000162,
-        0x16300000164,
-        0x16500000166,
-        0x16700000168,
-        0x1690000016a,
-        0x16b0000016c,
-        0x16d0000016e,
-        0x16f00000170,
-        0x17100000172,
-        0x17300000174,
-        0x17500000176,
-        0x17700000178,
-        0x17a0000017b,
-        0x17c0000017d,
-        0x17e0000017f,
-        0x18000000181,
-        0x18300000184,
-        0x18500000186,
-        0x18800000189,
-        0x18c0000018e,
-        0x19200000193,
-        0x19500000196,
-        0x1990000019c,
-        0x19e0000019f,
-        0x1a1000001a2,
-        0x1a3000001a4,
-        0x1a5000001a6,
-        0x1a8000001a9,
-        0x1aa000001ac,
-        0x1ad000001ae,
-        0x1b0000001b1,
-        0x1b4000001b5,
-        0x1b6000001b7,
-        0x1b9000001bc,
-        0x1bd000001c4,
-        0x1ce000001cf,
-        0x1d0000001d1,
-        0x1d2000001d3,
-        0x1d4000001d5,
-        0x1d6000001d7,
-        0x1d8000001d9,
-        0x1da000001db,
-        0x1dc000001de,
-        0x1df000001e0,
-        0x1e1000001e2,
-        0x1e3000001e4,
-        0x1e5000001e6,
-        0x1e7000001e8,
-        0x1e9000001ea,
-        0x1eb000001ec,
-        0x1ed000001ee,
-        0x1ef000001f1,
-        0x1f5000001f6,
-        0x1f9000001fa,
-        0x1fb000001fc,
-        0x1fd000001fe,
-        0x1ff00000200,
-        0x20100000202,
-        0x20300000204,
-        0x20500000206,
-        0x20700000208,
-        0x2090000020a,
-        0x20b0000020c,
-        0x20d0000020e,
-        0x20f00000210,
-        0x21100000212,
-        0x21300000214,
-        0x21500000216,
-        0x21700000218,
-        0x2190000021a,
-        0x21b0000021c,
-        0x21d0000021e,
-        0x21f00000220,
-        0x22100000222,
-        0x22300000224,
-        0x22500000226,
-        0x22700000228,
-        0x2290000022a,
-        0x22b0000022c,
-        0x22d0000022e,
-        0x22f00000230,
-        0x23100000232,
-        0x2330000023a,
-        0x23c0000023d,
-        0x23f00000241,
-        0x24200000243,
-        0x24700000248,
-        0x2490000024a,
-        0x24b0000024c,
-        0x24d0000024e,
-        0x24f000002b0,
-        0x2b9000002c2,
-        0x2c6000002d2,
-        0x2ec000002ed,
-        0x2ee000002ef,
-        0x30000000340,
-        0x34200000343,
-        0x3460000034f,
-        0x35000000370,
-        0x37100000372,
-        0x37300000374,
-        0x37700000378,
-        0x37b0000037e,
-        0x39000000391,
-        0x3ac000003cf,
-        0x3d7000003d8,
-        0x3d9000003da,
-        0x3db000003dc,
-        0x3dd000003de,
-        0x3df000003e0,
-        0x3e1000003e2,
-        0x3e3000003e4,
-        0x3e5000003e6,
-        0x3e7000003e8,
-        0x3e9000003ea,
-        0x3eb000003ec,
-        0x3ed000003ee,
-        0x3ef000003f0,
-        0x3f3000003f4,
-        0x3f8000003f9,
-        0x3fb000003fd,
-        0x43000000460,
-        0x46100000462,
-        0x46300000464,
-        0x46500000466,
-        0x46700000468,
-        0x4690000046a,
-        0x46b0000046c,
-        0x46d0000046e,
-        0x46f00000470,
-        0x47100000472,
-        0x47300000474,
-        0x47500000476,
-        0x47700000478,
-        0x4790000047a,
-        0x47b0000047c,
-        0x47d0000047e,
-        0x47f00000480,
-        0x48100000482,
-        0x48300000488,
-        0x48b0000048c,
-        0x48d0000048e,
-        0x48f00000490,
-        0x49100000492,
-        0x49300000494,
-        0x49500000496,
-        0x49700000498,
-        0x4990000049a,
-        0x49b0000049c,
-        0x49d0000049e,
-        0x49f000004a0,
-        0x4a1000004a2,
-        0x4a3000004a4,
-        0x4a5000004a6,
-        0x4a7000004a8,
-        0x4a9000004aa,
-        0x4ab000004ac,
-        0x4ad000004ae,
-        0x4af000004b0,
-        0x4b1000004b2,
-        0x4b3000004b4,
-        0x4b5000004b6,
-        0x4b7000004b8,
-        0x4b9000004ba,
-        0x4bb000004bc,
-        0x4bd000004be,
-        0x4bf000004c0,
-        0x4c2000004c3,
-        0x4c4000004c5,
-        0x4c6000004c7,
-        0x4c8000004c9,
-        0x4ca000004cb,
-        0x4cc000004cd,
-        0x4ce000004d0,
-        0x4d1000004d2,
-        0x4d3000004d4,
-        0x4d5000004d6,
-        0x4d7000004d8,
-        0x4d9000004da,
-        0x4db000004dc,
-        0x4dd000004de,
-        0x4df000004e0,
-        0x4e1000004e2,
-        0x4e3000004e4,
-        0x4e5000004e6,
-        0x4e7000004e8,
-        0x4e9000004ea,
-        0x4eb000004ec,
-        0x4ed000004ee,
-        0x4ef000004f0,
-        0x4f1000004f2,
-        0x4f3000004f4,
-        0x4f5000004f6,
-        0x4f7000004f8,
-        0x4f9000004fa,
-        0x4fb000004fc,
-        0x4fd000004fe,
-        0x4ff00000500,
-        0x50100000502,
-        0x50300000504,
-        0x50500000506,
-        0x50700000508,
-        0x5090000050a,
-        0x50b0000050c,
-        0x50d0000050e,
-        0x50f00000510,
-        0x51100000512,
-        0x51300000514,
-        0x51500000516,
-        0x51700000518,
-        0x5190000051a,
-        0x51b0000051c,
-        0x51d0000051e,
-        0x51f00000520,
-        0x52100000522,
-        0x52300000524,
-        0x52500000526,
-        0x52700000528,
-        0x5290000052a,
-        0x52b0000052c,
-        0x52d0000052e,
-        0x52f00000530,
-        0x5590000055a,
-        0x56000000587,
-        0x58800000589,
-        0x591000005be,
-        0x5bf000005c0,
-        0x5c1000005c3,
-        0x5c4000005c6,
-        0x5c7000005c8,
-        0x5d0000005eb,
-        0x5ef000005f3,
-        0x6100000061b,
-        0x62000000640,
-        0x64100000660,
-        0x66e00000675,
-        0x679000006d4,
-        0x6d5000006dd,
-        0x6df000006e9,
-        0x6ea000006f0,
-        0x6fa00000700,
-        0x7100000074b,
-        0x74d000007b2,
-        0x7c0000007f6,
-        0x7fd000007fe,
-        0x8000000082e,
-        0x8400000085c,
-        0x8600000086b,
-        0x87000000888,
-        0x8890000088f,
-        0x898000008e2,
-        0x8e300000958,
-        0x96000000964,
-        0x96600000970,
-        0x97100000984,
-        0x9850000098d,
-        0x98f00000991,
-        0x993000009a9,
-        0x9aa000009b1,
-        0x9b2000009b3,
-        0x9b6000009ba,
-        0x9bc000009c5,
-        0x9c7000009c9,
-        0x9cb000009cf,
-        0x9d7000009d8,
-        0x9e0000009e4,
-        0x9e6000009f2,
-        0x9fc000009fd,
-        0x9fe000009ff,
-        0xa0100000a04,
-        0xa0500000a0b,
-        0xa0f00000a11,
-        0xa1300000a29,
-        0xa2a00000a31,
-        0xa3200000a33,
-        0xa3500000a36,
-        0xa3800000a3a,
-        0xa3c00000a3d,
-        0xa3e00000a43,
-        0xa4700000a49,
-        0xa4b00000a4e,
-        0xa5100000a52,
-        0xa5c00000a5d,
-        0xa6600000a76,
-        0xa8100000a84,
-        0xa8500000a8e,
-        0xa8f00000a92,
-        0xa9300000aa9,
-        0xaaa00000ab1,
-        0xab200000ab4,
-        0xab500000aba,
-        0xabc00000ac6,
-        0xac700000aca,
-        0xacb00000ace,
-        0xad000000ad1,
-        0xae000000ae4,
-        0xae600000af0,
-        0xaf900000b00,
-        0xb0100000b04,
-        0xb0500000b0d,
-        0xb0f00000b11,
-        0xb1300000b29,
-        0xb2a00000b31,
-        0xb3200000b34,
-        0xb3500000b3a,
-        0xb3c00000b45,
-        0xb4700000b49,
-        0xb4b00000b4e,
-        0xb5500000b58,
-        0xb5f00000b64,
-        0xb6600000b70,
-        0xb7100000b72,
-        0xb8200000b84,
-        0xb8500000b8b,
-        0xb8e00000b91,
-        0xb9200000b96,
-        0xb9900000b9b,
-        0xb9c00000b9d,
-        0xb9e00000ba0,
-        0xba300000ba5,
-        0xba800000bab,
-        0xbae00000bba,
-        0xbbe00000bc3,
-        0xbc600000bc9,
-        0xbca00000bce,
-        0xbd000000bd1,
-        0xbd700000bd8,
-        0xbe600000bf0,
-        0xc0000000c0d,
-        0xc0e00000c11,
-        0xc1200000c29,
-        0xc2a00000c3a,
-        0xc3c00000c45,
-        0xc4600000c49,
-        0xc4a00000c4e,
-        0xc5500000c57,
-        0xc5800000c5b,
-        0xc5d00000c5e,
-        0xc6000000c64,
-        0xc6600000c70,
-        0xc8000000c84,
-        0xc8500000c8d,
-        0xc8e00000c91,
-        0xc9200000ca9,
-        0xcaa00000cb4,
-        0xcb500000cba,
-        0xcbc00000cc5,
-        0xcc600000cc9,
-        0xcca00000cce,
-        0xcd500000cd7,
-        0xcdd00000cdf,
-        0xce000000ce4,
-        0xce600000cf0,
-        0xcf100000cf3,
-        0xd0000000d0d,
-        0xd0e00000d11,
-        0xd1200000d45,
-        0xd4600000d49,
-        0xd4a00000d4f,
-        0xd5400000d58,
-        0xd5f00000d64,
-        0xd6600000d70,
-        0xd7a00000d80,
-        0xd8100000d84,
-        0xd8500000d97,
-        0xd9a00000db2,
-        0xdb300000dbc,
-        0xdbd00000dbe,
-        0xdc000000dc7,
-        0xdca00000dcb,
-        0xdcf00000dd5,
-        0xdd600000dd7,
-        0xdd800000de0,
-        0xde600000df0,
-        0xdf200000df4,
-        0xe0100000e33,
-        0xe3400000e3b,
-        0xe4000000e4f,
-        0xe5000000e5a,
-        0xe8100000e83,
-        0xe8400000e85,
-        0xe8600000e8b,
-        0xe8c00000ea4,
-        0xea500000ea6,
-        0xea700000eb3,
-        0xeb400000ebe,
-        0xec000000ec5,
-        0xec600000ec7,
-        0xec800000ece,
-        0xed000000eda,
-        0xede00000ee0,
-        0xf0000000f01,
-        0xf0b00000f0c,
-        0xf1800000f1a,
-        0xf2000000f2a,
-        0xf3500000f36,
-        0xf3700000f38,
-        0xf3900000f3a,
-        0xf3e00000f43,
-        0xf4400000f48,
-        0xf4900000f4d,
-        0xf4e00000f52,
-        0xf5300000f57,
-        0xf5800000f5c,
-        0xf5d00000f69,
-        0xf6a00000f6d,
-        0xf7100000f73,
-        0xf7400000f75,
-        0xf7a00000f81,
-        0xf8200000f85,
-        0xf8600000f93,
-        0xf9400000f98,
-        0xf9900000f9d,
-        0xf9e00000fa2,
-        0xfa300000fa7,
-        0xfa800000fac,
-        0xfad00000fb9,
-        0xfba00000fbd,
-        0xfc600000fc7,
-        0x10000000104a,
-        0x10500000109e,
-        0x10d0000010fb,
-        0x10fd00001100,
-        0x120000001249,
-        0x124a0000124e,
-        0x125000001257,
-        0x125800001259,
-        0x125a0000125e,
-        0x126000001289,
-        0x128a0000128e,
-        0x1290000012b1,
-        0x12b2000012b6,
-        0x12b8000012bf,
-        0x12c0000012c1,
-        0x12c2000012c6,
-        0x12c8000012d7,
-        0x12d800001311,
-        0x131200001316,
-        0x13180000135b,
-        0x135d00001360,
-        0x138000001390,
-        0x13a0000013f6,
-        0x14010000166d,
-        0x166f00001680,
-        0x16810000169b,
-        0x16a0000016eb,
-        0x16f1000016f9,
-        0x170000001716,
-        0x171f00001735,
-        0x174000001754,
-        0x17600000176d,
-        0x176e00001771,
-        0x177200001774,
-        0x1780000017b4,
-        0x17b6000017d4,
-        0x17d7000017d8,
-        0x17dc000017de,
-        0x17e0000017ea,
-        0x18100000181a,
-        0x182000001879,
-        0x1880000018ab,
-        0x18b0000018f6,
-        0x19000000191f,
-        0x19200000192c,
-        0x19300000193c,
-        0x19460000196e,
-        0x197000001975,
-        0x1980000019ac,
-        0x19b0000019ca,
-        0x19d0000019da,
-        0x1a0000001a1c,
-        0x1a2000001a5f,
-        0x1a6000001a7d,
-        0x1a7f00001a8a,
-        0x1a9000001a9a,
-        0x1aa700001aa8,
-        0x1ab000001abe,
-        0x1abf00001acf,
-        0x1b0000001b4d,
-        0x1b5000001b5a,
-        0x1b6b00001b74,
-        0x1b8000001bf4,
-        0x1c0000001c38,
-        0x1c4000001c4a,
-        0x1c4d00001c7e,
-        0x1cd000001cd3,
-        0x1cd400001cfb,
-        0x1d0000001d2c,
-        0x1d2f00001d30,
-        0x1d3b00001d3c,
-        0x1d4e00001d4f,
-        0x1d6b00001d78,
-        0x1d7900001d9b,
-        0x1dc000001e00,
-        0x1e0100001e02,
-        0x1e0300001e04,
-        0x1e0500001e06,
-        0x1e0700001e08,
-        0x1e0900001e0a,
-        0x1e0b00001e0c,
-        0x1e0d00001e0e,
-        0x1e0f00001e10,
-        0x1e1100001e12,
-        0x1e1300001e14,
-        0x1e1500001e16,
-        0x1e1700001e18,
-        0x1e1900001e1a,
-        0x1e1b00001e1c,
-        0x1e1d00001e1e,
-        0x1e1f00001e20,
-        0x1e2100001e22,
-        0x1e2300001e24,
-        0x1e2500001e26,
-        0x1e2700001e28,
-        0x1e2900001e2a,
-        0x1e2b00001e2c,
-        0x1e2d00001e2e,
-        0x1e2f00001e30,
-        0x1e3100001e32,
-        0x1e3300001e34,
-        0x1e3500001e36,
-        0x1e3700001e38,
-        0x1e3900001e3a,
-        0x1e3b00001e3c,
-        0x1e3d00001e3e,
-        0x1e3f00001e40,
-        0x1e4100001e42,
-        0x1e4300001e44,
-        0x1e4500001e46,
-        0x1e4700001e48,
-        0x1e4900001e4a,
-        0x1e4b00001e4c,
-        0x1e4d00001e4e,
-        0x1e4f00001e50,
-        0x1e5100001e52,
-        0x1e5300001e54,
-        0x1e5500001e56,
-        0x1e5700001e58,
-        0x1e5900001e5a,
-        0x1e5b00001e5c,
-        0x1e5d00001e5e,
-        0x1e5f00001e60,
-        0x1e6100001e62,
-        0x1e6300001e64,
-        0x1e6500001e66,
-        0x1e6700001e68,
-        0x1e6900001e6a,
-        0x1e6b00001e6c,
-        0x1e6d00001e6e,
-        0x1e6f00001e70,
-        0x1e7100001e72,
-        0x1e7300001e74,
-        0x1e7500001e76,
-        0x1e7700001e78,
-        0x1e7900001e7a,
-        0x1e7b00001e7c,
-        0x1e7d00001e7e,
-        0x1e7f00001e80,
-        0x1e8100001e82,
-        0x1e8300001e84,
-        0x1e8500001e86,
-        0x1e8700001e88,
-        0x1e8900001e8a,
-        0x1e8b00001e8c,
-        0x1e8d00001e8e,
-        0x1e8f00001e90,
-        0x1e9100001e92,
-        0x1e9300001e94,
-        0x1e9500001e9a,
-        0x1e9c00001e9e,
-        0x1e9f00001ea0,
-        0x1ea100001ea2,
-        0x1ea300001ea4,
-        0x1ea500001ea6,
-        0x1ea700001ea8,
-        0x1ea900001eaa,
-        0x1eab00001eac,
-        0x1ead00001eae,
-        0x1eaf00001eb0,
-        0x1eb100001eb2,
-        0x1eb300001eb4,
-        0x1eb500001eb6,
-        0x1eb700001eb8,
-        0x1eb900001eba,
-        0x1ebb00001ebc,
-        0x1ebd00001ebe,
-        0x1ebf00001ec0,
-        0x1ec100001ec2,
-        0x1ec300001ec4,
-        0x1ec500001ec6,
-        0x1ec700001ec8,
-        0x1ec900001eca,
-        0x1ecb00001ecc,
-        0x1ecd00001ece,
-        0x1ecf00001ed0,
-        0x1ed100001ed2,
-        0x1ed300001ed4,
-        0x1ed500001ed6,
-        0x1ed700001ed8,
-        0x1ed900001eda,
-        0x1edb00001edc,
-        0x1edd00001ede,
-        0x1edf00001ee0,
-        0x1ee100001ee2,
-        0x1ee300001ee4,
-        0x1ee500001ee6,
-        0x1ee700001ee8,
-        0x1ee900001eea,
-        0x1eeb00001eec,
-        0x1eed00001eee,
-        0x1eef00001ef0,
-        0x1ef100001ef2,
-        0x1ef300001ef4,
-        0x1ef500001ef6,
-        0x1ef700001ef8,
-        0x1ef900001efa,
-        0x1efb00001efc,
-        0x1efd00001efe,
-        0x1eff00001f08,
-        0x1f1000001f16,
-        0x1f2000001f28,
-        0x1f3000001f38,
-        0x1f4000001f46,
-        0x1f5000001f58,
-        0x1f6000001f68,
-        0x1f7000001f71,
-        0x1f7200001f73,
-        0x1f7400001f75,
-        0x1f7600001f77,
-        0x1f7800001f79,
-        0x1f7a00001f7b,
-        0x1f7c00001f7d,
-        0x1fb000001fb2,
-        0x1fb600001fb7,
-        0x1fc600001fc7,
-        0x1fd000001fd3,
-        0x1fd600001fd8,
-        0x1fe000001fe3,
-        0x1fe400001fe8,
-        0x1ff600001ff7,
-        0x214e0000214f,
-        0x218400002185,
-        0x2c3000002c60,
-        0x2c6100002c62,
-        0x2c6500002c67,
-        0x2c6800002c69,
-        0x2c6a00002c6b,
-        0x2c6c00002c6d,
-        0x2c7100002c72,
-        0x2c7300002c75,
-        0x2c7600002c7c,
-        0x2c8100002c82,
-        0x2c8300002c84,
-        0x2c8500002c86,
-        0x2c8700002c88,
-        0x2c8900002c8a,
-        0x2c8b00002c8c,
-        0x2c8d00002c8e,
-        0x2c8f00002c90,
-        0x2c9100002c92,
-        0x2c9300002c94,
-        0x2c9500002c96,
-        0x2c9700002c98,
-        0x2c9900002c9a,
-        0x2c9b00002c9c,
-        0x2c9d00002c9e,
-        0x2c9f00002ca0,
-        0x2ca100002ca2,
-        0x2ca300002ca4,
-        0x2ca500002ca6,
-        0x2ca700002ca8,
-        0x2ca900002caa,
-        0x2cab00002cac,
-        0x2cad00002cae,
-        0x2caf00002cb0,
-        0x2cb100002cb2,
-        0x2cb300002cb4,
-        0x2cb500002cb6,
-        0x2cb700002cb8,
-        0x2cb900002cba,
-        0x2cbb00002cbc,
-        0x2cbd00002cbe,
-        0x2cbf00002cc0,
-        0x2cc100002cc2,
-        0x2cc300002cc4,
-        0x2cc500002cc6,
-        0x2cc700002cc8,
-        0x2cc900002cca,
-        0x2ccb00002ccc,
-        0x2ccd00002cce,
-        0x2ccf00002cd0,
-        0x2cd100002cd2,
-        0x2cd300002cd4,
-        0x2cd500002cd6,
-        0x2cd700002cd8,
-        0x2cd900002cda,
-        0x2cdb00002cdc,
-        0x2cdd00002cde,
-        0x2cdf00002ce0,
-        0x2ce100002ce2,
-        0x2ce300002ce5,
-        0x2cec00002ced,
-        0x2cee00002cf2,
-        0x2cf300002cf4,
-        0x2d0000002d26,
-        0x2d2700002d28,
-        0x2d2d00002d2e,
-        0x2d3000002d68,
-        0x2d7f00002d97,
-        0x2da000002da7,
-        0x2da800002daf,
-        0x2db000002db7,
-        0x2db800002dbf,
-        0x2dc000002dc7,
-        0x2dc800002dcf,
-        0x2dd000002dd7,
-        0x2dd800002ddf,
-        0x2de000002e00,
-        0x2e2f00002e30,
-        0x300500003008,
-        0x302a0000302e,
-        0x303c0000303d,
-        0x304100003097,
-        0x30990000309b,
-        0x309d0000309f,
-        0x30a1000030fb,
-        0x30fc000030ff,
-        0x310500003130,
-        0x31a0000031c0,
-        0x31f000003200,
-        0x340000004dc0,
-        0x4e000000a48d,
-        0xa4d00000a4fe,
-        0xa5000000a60d,
-        0xa6100000a62c,
-        0xa6410000a642,
-        0xa6430000a644,
-        0xa6450000a646,
-        0xa6470000a648,
-        0xa6490000a64a,
-        0xa64b0000a64c,
-        0xa64d0000a64e,
-        0xa64f0000a650,
-        0xa6510000a652,
-        0xa6530000a654,
-        0xa6550000a656,
-        0xa6570000a658,
-        0xa6590000a65a,
-        0xa65b0000a65c,
-        0xa65d0000a65e,
-        0xa65f0000a660,
-        0xa6610000a662,
-        0xa6630000a664,
-        0xa6650000a666,
-        0xa6670000a668,
-        0xa6690000a66a,
-        0xa66b0000a66c,
-        0xa66d0000a670,
-        0xa6740000a67e,
-        0xa67f0000a680,
-        0xa6810000a682,
-        0xa6830000a684,
-        0xa6850000a686,
-        0xa6870000a688,
-        0xa6890000a68a,
-        0xa68b0000a68c,
-        0xa68d0000a68e,
-        0xa68f0000a690,
-        0xa6910000a692,
-        0xa6930000a694,
-        0xa6950000a696,
-        0xa6970000a698,
-        0xa6990000a69a,
-        0xa69b0000a69c,
-        0xa69e0000a6e6,
-        0xa6f00000a6f2,
-        0xa7170000a720,
-        0xa7230000a724,
-        0xa7250000a726,
-        0xa7270000a728,
-        0xa7290000a72a,
-        0xa72b0000a72c,
-        0xa72d0000a72e,
-        0xa72f0000a732,
-        0xa7330000a734,
-        0xa7350000a736,
-        0xa7370000a738,
-        0xa7390000a73a,
-        0xa73b0000a73c,
-        0xa73d0000a73e,
-        0xa73f0000a740,
-        0xa7410000a742,
-        0xa7430000a744,
-        0xa7450000a746,
-        0xa7470000a748,
-        0xa7490000a74a,
-        0xa74b0000a74c,
-        0xa74d0000a74e,
-        0xa74f0000a750,
-        0xa7510000a752,
-        0xa7530000a754,
-        0xa7550000a756,
-        0xa7570000a758,
-        0xa7590000a75a,
-        0xa75b0000a75c,
-        0xa75d0000a75e,
-        0xa75f0000a760,
-        0xa7610000a762,
-        0xa7630000a764,
-        0xa7650000a766,
-        0xa7670000a768,
-        0xa7690000a76a,
-        0xa76b0000a76c,
-        0xa76d0000a76e,
-        0xa76f0000a770,
-        0xa7710000a779,
-        0xa77a0000a77b,
-        0xa77c0000a77d,
-        0xa77f0000a780,
-        0xa7810000a782,
-        0xa7830000a784,
-        0xa7850000a786,
-        0xa7870000a789,
-        0xa78c0000a78d,
-        0xa78e0000a790,
-        0xa7910000a792,
-        0xa7930000a796,
-        0xa7970000a798,
-        0xa7990000a79a,
-        0xa79b0000a79c,
-        0xa79d0000a79e,
-        0xa79f0000a7a0,
-        0xa7a10000a7a2,
-        0xa7a30000a7a4,
-        0xa7a50000a7a6,
-        0xa7a70000a7a8,
-        0xa7a90000a7aa,
-        0xa7af0000a7b0,
-        0xa7b50000a7b6,
-        0xa7b70000a7b8,
-        0xa7b90000a7ba,
-        0xa7bb0000a7bc,
-        0xa7bd0000a7be,
-        0xa7bf0000a7c0,
-        0xa7c10000a7c2,
-        0xa7c30000a7c4,
-        0xa7c80000a7c9,
-        0xa7ca0000a7cb,
-        0xa7d10000a7d2,
-        0xa7d30000a7d4,
-        0xa7d50000a7d6,
-        0xa7d70000a7d8,
-        0xa7d90000a7da,
-        0xa7f20000a7f5,
-        0xa7f60000a7f8,
-        0xa7fa0000a828,
-        0xa82c0000a82d,
-        0xa8400000a874,
-        0xa8800000a8c6,
-        0xa8d00000a8da,
-        0xa8e00000a8f8,
-        0xa8fb0000a8fc,
-        0xa8fd0000a92e,
-        0xa9300000a954,
-        0xa9800000a9c1,
-        0xa9cf0000a9da,
-        0xa9e00000a9ff,
-        0xaa000000aa37,
-        0xaa400000aa4e,
-        0xaa500000aa5a,
-        0xaa600000aa77,
-        0xaa7a0000aac3,
-        0xaadb0000aade,
-        0xaae00000aaf0,
-        0xaaf20000aaf7,
-        0xab010000ab07,
-        0xab090000ab0f,
-        0xab110000ab17,
-        0xab200000ab27,
-        0xab280000ab2f,
-        0xab300000ab5b,
-        0xab600000ab6a,
-        0xabc00000abeb,
-        0xabec0000abee,
-        0xabf00000abfa,
-        0xac000000d7a4,
-        0xfa0e0000fa10,
-        0xfa110000fa12,
-        0xfa130000fa15,
-        0xfa1f0000fa20,
-        0xfa210000fa22,
-        0xfa230000fa25,
-        0xfa270000fa2a,
-        0xfb1e0000fb1f,
-        0xfe200000fe30,
-        0xfe730000fe74,
-        0x100000001000c,
-        0x1000d00010027,
-        0x100280001003b,
-        0x1003c0001003e,
-        0x1003f0001004e,
-        0x100500001005e,
-        0x10080000100fb,
-        0x101fd000101fe,
-        0x102800001029d,
-        0x102a0000102d1,
-        0x102e0000102e1,
-        0x1030000010320,
-        0x1032d00010341,
-        0x103420001034a,
-        0x103500001037b,
-        0x103800001039e,
-        0x103a0000103c4,
-        0x103c8000103d0,
-        0x104280001049e,
-        0x104a0000104aa,
-        0x104d8000104fc,
-        0x1050000010528,
-        0x1053000010564,
-        0x10597000105a2,
-        0x105a3000105b2,
-        0x105b3000105ba,
-        0x105bb000105bd,
-        0x1060000010737,
-        0x1074000010756,
-        0x1076000010768,
-        0x1078000010786,
-        0x10787000107b1,
-        0x107b2000107bb,
-        0x1080000010806,
-        0x1080800010809,
-        0x1080a00010836,
-        0x1083700010839,
-        0x1083c0001083d,
-        0x1083f00010856,
-        0x1086000010877,
-        0x108800001089f,
-        0x108e0000108f3,
-        0x108f4000108f6,
-        0x1090000010916,
-        0x109200001093a,
-        0x10980000109b8,
-        0x109be000109c0,
-        0x10a0000010a04,
-        0x10a0500010a07,
-        0x10a0c00010a14,
-        0x10a1500010a18,
-        0x10a1900010a36,
-        0x10a3800010a3b,
-        0x10a3f00010a40,
-        0x10a6000010a7d,
-        0x10a8000010a9d,
-        0x10ac000010ac8,
-        0x10ac900010ae7,
-        0x10b0000010b36,
-        0x10b4000010b56,
-        0x10b6000010b73,
-        0x10b8000010b92,
-        0x10c0000010c49,
-        0x10cc000010cf3,
-        0x10d0000010d28,
-        0x10d3000010d3a,
-        0x10e8000010eaa,
-        0x10eab00010ead,
-        0x10eb000010eb2,
-        0x10f0000010f1d,
-        0x10f2700010f28,
-        0x10f3000010f51,
-        0x10f7000010f86,
-        0x10fb000010fc5,
-        0x10fe000010ff7,
-        0x1100000011047,
-        0x1106600011076,
-        0x1107f000110bb,
-        0x110c2000110c3,
-        0x110d0000110e9,
-        0x110f0000110fa,
-        0x1110000011135,
-        0x1113600011140,
-        0x1114400011148,
-        0x1115000011174,
-        0x1117600011177,
-        0x11180000111c5,
-        0x111c9000111cd,
-        0x111ce000111db,
-        0x111dc000111dd,
-        0x1120000011212,
-        0x1121300011238,
-        0x1123e0001123f,
-        0x1128000011287,
-        0x1128800011289,
-        0x1128a0001128e,
-        0x1128f0001129e,
-        0x1129f000112a9,
-        0x112b0000112eb,
-        0x112f0000112fa,
-        0x1130000011304,
-        0x113050001130d,
-        0x1130f00011311,
-        0x1131300011329,
-        0x1132a00011331,
-        0x1133200011334,
-        0x113350001133a,
-        0x1133b00011345,
-        0x1134700011349,
-        0x1134b0001134e,
-        0x1135000011351,
-        0x1135700011358,
-        0x1135d00011364,
-        0x113660001136d,
-        0x1137000011375,
-        0x114000001144b,
-        0x114500001145a,
-        0x1145e00011462,
-        0x11480000114c6,
-        0x114c7000114c8,
-        0x114d0000114da,
-        0x11580000115b6,
-        0x115b8000115c1,
-        0x115d8000115de,
-        0x1160000011641,
-        0x1164400011645,
-        0x116500001165a,
-        0x11680000116b9,
-        0x116c0000116ca,
-        0x117000001171b,
-        0x1171d0001172c,
-        0x117300001173a,
-        0x1174000011747,
-        0x118000001183b,
-        0x118c0000118ea,
-        0x118ff00011907,
-        0x119090001190a,
-        0x1190c00011914,
-        0x1191500011917,
-        0x1191800011936,
-        0x1193700011939,
-        0x1193b00011944,
-        0x119500001195a,
-        0x119a0000119a8,
-        0x119aa000119d8,
-        0x119da000119e2,
-        0x119e3000119e5,
-        0x11a0000011a3f,
-        0x11a4700011a48,
-        0x11a5000011a9a,
-        0x11a9d00011a9e,
-        0x11ab000011af9,
-        0x11c0000011c09,
-        0x11c0a00011c37,
-        0x11c3800011c41,
-        0x11c5000011c5a,
-        0x11c7200011c90,
-        0x11c9200011ca8,
-        0x11ca900011cb7,
-        0x11d0000011d07,
-        0x11d0800011d0a,
-        0x11d0b00011d37,
-        0x11d3a00011d3b,
-        0x11d3c00011d3e,
-        0x11d3f00011d48,
-        0x11d5000011d5a,
-        0x11d6000011d66,
-        0x11d6700011d69,
-        0x11d6a00011d8f,
-        0x11d9000011d92,
-        0x11d9300011d99,
-        0x11da000011daa,
-        0x11ee000011ef7,
-        0x11fb000011fb1,
-        0x120000001239a,
-        0x1248000012544,
-        0x12f9000012ff1,
-        0x130000001342f,
-        0x1440000014647,
-        0x1680000016a39,
-        0x16a4000016a5f,
-        0x16a6000016a6a,
-        0x16a7000016abf,
-        0x16ac000016aca,
-        0x16ad000016aee,
-        0x16af000016af5,
-        0x16b0000016b37,
-        0x16b4000016b44,
-        0x16b5000016b5a,
-        0x16b6300016b78,
-        0x16b7d00016b90,
-        0x16e6000016e80,
-        0x16f0000016f4b,
-        0x16f4f00016f88,
-        0x16f8f00016fa0,
-        0x16fe000016fe2,
-        0x16fe300016fe5,
-        0x16ff000016ff2,
-        0x17000000187f8,
-        0x1880000018cd6,
-        0x18d0000018d09,
-        0x1aff00001aff4,
-        0x1aff50001affc,
-        0x1affd0001afff,
-        0x1b0000001b123,
-        0x1b1500001b153,
-        0x1b1640001b168,
-        0x1b1700001b2fc,
-        0x1bc000001bc6b,
-        0x1bc700001bc7d,
-        0x1bc800001bc89,
-        0x1bc900001bc9a,
-        0x1bc9d0001bc9f,
-        0x1cf000001cf2e,
-        0x1cf300001cf47,
-        0x1da000001da37,
-        0x1da3b0001da6d,
-        0x1da750001da76,
-        0x1da840001da85,
-        0x1da9b0001daa0,
-        0x1daa10001dab0,
-        0x1df000001df1f,
-        0x1e0000001e007,
-        0x1e0080001e019,
-        0x1e01b0001e022,
-        0x1e0230001e025,
-        0x1e0260001e02b,
-        0x1e1000001e12d,
-        0x1e1300001e13e,
-        0x1e1400001e14a,
-        0x1e14e0001e14f,
-        0x1e2900001e2af,
-        0x1e2c00001e2fa,
-        0x1e7e00001e7e7,
-        0x1e7e80001e7ec,
-        0x1e7ed0001e7ef,
-        0x1e7f00001e7ff,
-        0x1e8000001e8c5,
-        0x1e8d00001e8d7,
-        0x1e9220001e94c,
-        0x1e9500001e95a,
-        0x1fbf00001fbfa,
-        0x200000002a6e0,
-        0x2a7000002b739,
-        0x2b7400002b81e,
-        0x2b8200002cea2,
-        0x2ceb00002ebe1,
-        0x300000003134b,
-    ),
-    'CONTEXTJ': (
-        0x200c0000200e,
-    ),
-    'CONTEXTO': (
-        0xb7000000b8,
-        0x37500000376,
-        0x5f3000005f5,
-        0x6600000066a,
-        0x6f0000006fa,
-        0x30fb000030fc,
-    ),
-}
diff --git a/spaces/alexray/btc_predictor/venv/lib/python3.10/site-packages/pip/_vendor/packaging/version.py b/spaces/alexray/btc_predictor/venv/lib/python3.10/site-packages/pip/_vendor/packaging/version.py
deleted file mode 100644
index de9a09a4ed3b078b37e7490a6686f660ae935aca..0000000000000000000000000000000000000000
--- a/spaces/alexray/btc_predictor/venv/lib/python3.10/site-packages/pip/_vendor/packaging/version.py
+++ /dev/null
@@ -1,504 +0,0 @@
-# This file is dual licensed under the terms of the Apache License, Version
-# 2.0, and the BSD License. See the LICENSE file in the root of this repository
-# for complete details.
-
-import collections
-import itertools
-import re
-import warnings
-from typing import Callable, Iterator, List, Optional, SupportsInt, Tuple, Union
-
-from ._structures import Infinity, InfinityType, NegativeInfinity, NegativeInfinityType
-
-__all__ = ["parse", "Version", "LegacyVersion", "InvalidVersion", "VERSION_PATTERN"]
-
-InfiniteTypes = Union[InfinityType, NegativeInfinityType]
-PrePostDevType = Union[InfiniteTypes, Tuple[str, int]]
-SubLocalType = Union[InfiniteTypes, int, str]
-LocalType = Union[
-    NegativeInfinityType,
-    Tuple[
-        Union[
-            SubLocalType,
-            Tuple[SubLocalType, str],
-            Tuple[NegativeInfinityType, SubLocalType],
-        ],
-        ...,
-    ],
-]
-CmpKey = Tuple[
-    int, Tuple[int, ...], PrePostDevType, PrePostDevType, PrePostDevType, LocalType
-]
-LegacyCmpKey = Tuple[int, Tuple[str, ...]]
-VersionComparisonMethod = Callable[
-    [Union[CmpKey, LegacyCmpKey], Union[CmpKey, LegacyCmpKey]], bool
-]
-
-_Version = collections.namedtuple(
-    "_Version", ["epoch", "release", "dev", "pre", "post", "local"]
-)
-
-
-def parse(version: str) -> Union["LegacyVersion", "Version"]:
-    """
-    Parse the given version string and return either a :class:`Version` object
-    or a :class:`LegacyVersion` object depending on if the given version is
-    a valid PEP 440 version or a legacy version.
-    """
-    try:
-        return Version(version)
-    except InvalidVersion:
-        return LegacyVersion(version)
-
-
-class InvalidVersion(ValueError):
-    """
-    An invalid version was found, users should refer to PEP 440.
-    """
-
-
-class _BaseVersion:
-    _key: Union[CmpKey, LegacyCmpKey]
-
-    def __hash__(self) -> int:
-        return hash(self._key)
-
-    # Please keep the duplicated `isinstance` check
-    # in the six comparisons hereunder
-    # unless you find a way to avoid adding overhead function calls.
-    def __lt__(self, other: "_BaseVersion") -> bool:
-        if not isinstance(other, _BaseVersion):
-            return NotImplemented
-
-        return self._key < other._key
-
-    def __le__(self, other: "_BaseVersion") -> bool:
-        if not isinstance(other, _BaseVersion):
-            return NotImplemented
-
-        return self._key <= other._key
-
-    def __eq__(self, other: object) -> bool:
-        if not isinstance(other, _BaseVersion):
-            return NotImplemented
-
-        return self._key == other._key
-
-    def __ge__(self, other: "_BaseVersion") -> bool:
-        if not isinstance(other, _BaseVersion):
-            return NotImplemented
-
-        return self._key >= other._key
-
-    def __gt__(self, other: "_BaseVersion") -> bool:
-        if not isinstance(other, _BaseVersion):
-            return NotImplemented
-
-        return self._key > other._key
-
-    def __ne__(self, other: object) -> bool:
-        if not isinstance(other, _BaseVersion):
-            return NotImplemented
-
-        return self._key != other._key
-
-
-class LegacyVersion(_BaseVersion):
-    def __init__(self, version: str) -> None:
-        self._version = str(version)
-        self._key = _legacy_cmpkey(self._version)
-
-        warnings.warn(
-            "Creating a LegacyVersion has been deprecated and will be "
-            "removed in the next major release",
-            DeprecationWarning,
-        )
-
-    def __str__(self) -> str:
-        return self._version
-
-    def __repr__(self) -> str:
-        return f"<LegacyVersion('{self}')>"
-
-    @property
-    def public(self) -> str:
-        return self._version
-
-    @property
-    def base_version(self) -> str:
-        return self._version
-
-    @property
-    def epoch(self) -> int:
-        return -1
-
-    @property
-    def release(self) -> None:
-        return None
-
-    @property
-    def pre(self) -> None:
-        return None
-
-    @property
-    def post(self) -> None:
-        return None
-
-    @property
-    def dev(self) -> None:
-        return None
-
-    @property
-    def local(self) -> None:
-        return None
-
-    @property
-    def is_prerelease(self) -> bool:
-        return False
-
-    @property
-    def is_postrelease(self) -> bool:
-        return False
-
-    @property
-    def is_devrelease(self) -> bool:
-        return False
-
-
-_legacy_version_component_re = re.compile(r"(\d+ | [a-z]+ | \.| -)", re.VERBOSE)
-
-_legacy_version_replacement_map = {
-    "pre": "c",
-    "preview": "c",
-    "-": "final-",
-    "rc": "c",
-    "dev": "@",
-}
-
-
-def _parse_version_parts(s: str) -> Iterator[str]:
-    for part in _legacy_version_component_re.split(s):
-        part = _legacy_version_replacement_map.get(part, part)
-
-        if not part or part == ".":
-            continue
-
-        if part[:1] in "0123456789":
-            # pad for numeric comparison
-            yield part.zfill(8)
-        else:
-            yield "*" + part
-
-    # ensure that alpha/beta/candidate are before final
-    yield "*final"
-
-
-def _legacy_cmpkey(version: str) -> LegacyCmpKey:
-
-    # We hardcode an epoch of -1 here. A PEP 440 version can only have a epoch
-    # greater than or equal to 0. This will effectively put the LegacyVersion,
-    # which uses the defacto standard originally implemented by setuptools,
-    # as before all PEP 440 versions.
-    epoch = -1
-
-    # This scheme is taken from pkg_resources.parse_version setuptools prior to
-    # it's adoption of the packaging library.
-    parts: List[str] = []
-    for part in _parse_version_parts(version.lower()):
-        if part.startswith("*"):
-            # remove "-" before a prerelease tag
-            if part < "*final":
-                while parts and parts[-1] == "*final-":
-                    parts.pop()
-
-            # remove trailing zeros from each series of numeric parts
-            while parts and parts[-1] == "00000000":
-                parts.pop()
-
-        parts.append(part)
-
-    return epoch, tuple(parts)
-
-
-# Deliberately not anchored to the start and end of the string, to make it
-# easier for 3rd party code to reuse
-VERSION_PATTERN = r"""
-    v?
-    (?:
-        (?:(?P<epoch>[0-9]+)!)?                           # epoch
-        (?P<release>[0-9]+(?:\.[0-9]+)*)                  # release segment
-        (?P<pre>                                          # pre-release
-            [-_\.]?
-            (?P<pre_l>(a|b|c|rc|alpha|beta|pre|preview))
-            [-_\.]?
-            (?P<pre_n>[0-9]+)?
-        )?
-        (?P<post>                                         # post release
-            (?:-(?P<post_n1>[0-9]+))
-            |
-            (?:
-                [-_\.]?
-                (?P<post_l>post|rev|r)
-                [-_\.]?
-                (?P<post_n2>[0-9]+)?
-            )
-        )?
-        (?P<dev>                                          # dev release
-            [-_\.]?
-            (?P<dev_l>dev)
-            [-_\.]?
-            (?P<dev_n>[0-9]+)?
-        )?
-    )
-    (?:\+(?P<local>[a-z0-9]+(?:[-_\.][a-z0-9]+)*))?       # local version
-"""
-
-
-class Version(_BaseVersion):
-
-    _regex = re.compile(r"^\s*" + VERSION_PATTERN + r"\s*$", re.VERBOSE | re.IGNORECASE)
-
-    def __init__(self, version: str) -> None:
-
-        # Validate the version and parse it into pieces
-        match = self._regex.search(version)
-        if not match:
-            raise InvalidVersion(f"Invalid version: '{version}'")
-
-        # Store the parsed out pieces of the version
-        self._version = _Version(
-            epoch=int(match.group("epoch")) if match.group("epoch") else 0,
-            release=tuple(int(i) for i in match.group("release").split(".")),
-            pre=_parse_letter_version(match.group("pre_l"), match.group("pre_n")),
-            post=_parse_letter_version(
-                match.group("post_l"), match.group("post_n1") or match.group("post_n2")
-            ),
-            dev=_parse_letter_version(match.group("dev_l"), match.group("dev_n")),
-            local=_parse_local_version(match.group("local")),
-        )
-
-        # Generate a key which will be used for sorting
-        self._key = _cmpkey(
-            self._version.epoch,
-            self._version.release,
-            self._version.pre,
-            self._version.post,
-            self._version.dev,
-            self._version.local,
-        )
-
-    def __repr__(self) -> str:
-        return f"<Version('{self}')>"
-
-    def __str__(self) -> str:
-        parts = []
-
-        # Epoch
-        if self.epoch != 0:
-            parts.append(f"{self.epoch}!")
-
-        # Release segment
-        parts.append(".".join(str(x) for x in self.release))
-
-        # Pre-release
-        if self.pre is not None:
-            parts.append("".join(str(x) for x in self.pre))
-
-        # Post-release
-        if self.post is not None:
-            parts.append(f".post{self.post}")
-
-        # Development release
-        if self.dev is not None:
-            parts.append(f".dev{self.dev}")
-
-        # Local version segment
-        if self.local is not None:
-            parts.append(f"+{self.local}")
-
-        return "".join(parts)
-
-    @property
-    def epoch(self) -> int:
-        _epoch: int = self._version.epoch
-        return _epoch
-
-    @property
-    def release(self) -> Tuple[int, ...]:
-        _release: Tuple[int, ...] = self._version.release
-        return _release
-
-    @property
-    def pre(self) -> Optional[Tuple[str, int]]:
-        _pre: Optional[Tuple[str, int]] = self._version.pre
-        return _pre
-
-    @property
-    def post(self) -> Optional[int]:
-        return self._version.post[1] if self._version.post else None
-
-    @property
-    def dev(self) -> Optional[int]:
-        return self._version.dev[1] if self._version.dev else None
-
-    @property
-    def local(self) -> Optional[str]:
-        if self._version.local:
-            return ".".join(str(x) for x in self._version.local)
-        else:
-            return None
-
-    @property
-    def public(self) -> str:
-        return str(self).split("+", 1)[0]
-
-    @property
-    def base_version(self) -> str:
-        parts = []
-
-        # Epoch
-        if self.epoch != 0:
-            parts.append(f"{self.epoch}!")
-
-        # Release segment
-        parts.append(".".join(str(x) for x in self.release))
-
-        return "".join(parts)
-
-    @property
-    def is_prerelease(self) -> bool:
-        return self.dev is not None or self.pre is not None
-
-    @property
-    def is_postrelease(self) -> bool:
-        return self.post is not None
-
-    @property
-    def is_devrelease(self) -> bool:
-        return self.dev is not None
-
-    @property
-    def major(self) -> int:
-        return self.release[0] if len(self.release) >= 1 else 0
-
-    @property
-    def minor(self) -> int:
-        return self.release[1] if len(self.release) >= 2 else 0
-
-    @property
-    def micro(self) -> int:
-        return self.release[2] if len(self.release) >= 3 else 0
-
-
-def _parse_letter_version(
-    letter: str, number: Union[str, bytes, SupportsInt]
-) -> Optional[Tuple[str, int]]:
-
-    if letter:
-        # We consider there to be an implicit 0 in a pre-release if there is
-        # not a numeral associated with it.
-        if number is None:
-            number = 0
-
-        # We normalize any letters to their lower case form
-        letter = letter.lower()
-
-        # We consider some words to be alternate spellings of other words and
-        # in those cases we want to normalize the spellings to our preferred
-        # spelling.
-        if letter == "alpha":
-            letter = "a"
-        elif letter == "beta":
-            letter = "b"
-        elif letter in ["c", "pre", "preview"]:
-            letter = "rc"
-        elif letter in ["rev", "r"]:
-            letter = "post"
-
-        return letter, int(number)
-    if not letter and number:
-        # We assume if we are given a number, but we are not given a letter
-        # then this is using the implicit post release syntax (e.g. 1.0-1)
-        letter = "post"
-
-        return letter, int(number)
-
-    return None
-
-
-_local_version_separators = re.compile(r"[\._-]")
-
-
-def _parse_local_version(local: str) -> Optional[LocalType]:
-    """
-    Takes a string like abc.1.twelve and turns it into ("abc", 1, "twelve").
-    """
-    if local is not None:
-        return tuple(
-            part.lower() if not part.isdigit() else int(part)
-            for part in _local_version_separators.split(local)
-        )
-    return None
-
-
-def _cmpkey(
-    epoch: int,
-    release: Tuple[int, ...],
-    pre: Optional[Tuple[str, int]],
-    post: Optional[Tuple[str, int]],
-    dev: Optional[Tuple[str, int]],
-    local: Optional[Tuple[SubLocalType]],
-) -> CmpKey:
-
-    # When we compare a release version, we want to compare it with all of the
-    # trailing zeros removed. So we'll use a reverse the list, drop all the now
-    # leading zeros until we come to something non zero, then take the rest
-    # re-reverse it back into the correct order and make it a tuple and use
-    # that for our sorting key.
-    _release = tuple(
-        reversed(list(itertools.dropwhile(lambda x: x == 0, reversed(release))))
-    )
-
-    # We need to "trick" the sorting algorithm to put 1.0.dev0 before 1.0a0.
-    # We'll do this by abusing the pre segment, but we _only_ want to do this
-    # if there is not a pre or a post segment. If we have one of those then
-    # the normal sorting rules will handle this case correctly.
-    if pre is None and post is None and dev is not None:
-        _pre: PrePostDevType = NegativeInfinity
-    # Versions without a pre-release (except as noted above) should sort after
-    # those with one.
-    elif pre is None:
-        _pre = Infinity
-    else:
-        _pre = pre
-
-    # Versions without a post segment should sort before those with one.
-    if post is None:
-        _post: PrePostDevType = NegativeInfinity
-
-    else:
-        _post = post
-
-    # Versions without a development segment should sort after those with one.
-    if dev is None:
-        _dev: PrePostDevType = Infinity
-
-    else:
-        _dev = dev
-
-    if local is None:
-        # Versions without a local segment should sort before those with one.
-        _local: LocalType = NegativeInfinity
-    else:
-        # Versions with a local segment need that segment parsed to implement
-        # the sorting rules in PEP440.
-        # - Alpha numeric segments sort before numeric segments
-        # - Alpha numeric segments sort lexicographically
-        # - Numeric segments sort numerically
-        # - Shorter versions sort before longer versions when the prefixes
-        #   match exactly
-        _local = tuple(
-            (i, "") if isinstance(i, int) else (NegativeInfinity, i) for i in local
-        )
-
-    return epoch, _release, _pre, _post, _dev, _local
diff --git a/spaces/aliabd/SummerTime/model/third_party/HMNet/Models/Trainers/BaseTrainer.py b/spaces/aliabd/SummerTime/model/third_party/HMNet/Models/Trainers/BaseTrainer.py
deleted file mode 100644
index 532070d5d776b1a2b9435522b7fe9d03224ff87f..0000000000000000000000000000000000000000
--- a/spaces/aliabd/SummerTime/model/third_party/HMNet/Models/Trainers/BaseTrainer.py
+++ /dev/null
@@ -1,68 +0,0 @@
-# Copyright (c) Microsoft Corporation.
-# Licensed under the MIT license.
-
-import os
-
-
-class BaseTrainer:
-    def __init__(self, opt):
-        self.opt = opt
-        if self.opt["cuda"] == True:
-            self.use_cuda = True
-            print("Using Cuda\n")
-        else:
-            self.use_cuda = False
-            print("Using CPU\n")
-
-        self.is_official = "OFFICIAL" in self.opt
-        self.opt["logFile"] = "log.txt"
-        self.saveFolder = None
-        self.logFileHandle = None
-        self.tb_writer = None
-
-    def log(self, s):
-        # In official case, the program does not output logs
-        if self.is_official:
-            return
-        try:
-            if self.logFileHandle is None:
-                self.logFileHandle = open(
-                    os.path.join(self.saveFolder, self.opt["logFile"]), "a"
-                )
-            self.logFileHandle.write(s + "\n")
-        except Exception as e:
-            print("ERROR while writing log file:", e)
-        print(s)
-
-    def getSaveFolder(self):
-        runid = 1
-        while True:
-            saveFolder = os.path.join(
-                self.opt["datadir"],
-                self.opt["basename"] + "_conf~",
-                "run_" + str(runid),
-            )
-            if not os.path.exists(saveFolder):
-                self.saveFolder = saveFolder
-                os.makedirs(self.saveFolder)
-                print("Saving logs, model and evaluation in " + self.saveFolder)
-                return
-            runid = runid + 1
-
-    # save copy of conf file
-    def saveConf(self):
-        # with open(self.opt['confFile'], encoding='utf-8') as f:
-        #     with open(os.path.join(self.saveFolder, 'conf_copy.tsv'), 'w', encoding='utf-8') as fw:
-        #         for line in f:
-        #             fw.write(line)
-        with open(
-            os.path.join(self.saveFolder, "conf_copy.tsv"), "w", encoding="utf-8"
-        ) as fw:
-            for k in self.opt:
-                fw.write("{0}\t{1}\n".format(k, self.opt[k]))
-
-    def train(self):
-        pass
-
-    def load(self):
-        pass
diff --git a/spaces/aliceoq/vozes-da-loirinha/lib/uvr5_pack/lib_v5/nets_537238KB.py b/spaces/aliceoq/vozes-da-loirinha/lib/uvr5_pack/lib_v5/nets_537238KB.py
deleted file mode 100644
index a1bb530e006482704f234c2e739a695174142941..0000000000000000000000000000000000000000
--- a/spaces/aliceoq/vozes-da-loirinha/lib/uvr5_pack/lib_v5/nets_537238KB.py
+++ /dev/null
@@ -1,123 +0,0 @@
-import torch
-import numpy as np
-from torch import nn
-import torch.nn.functional as F
-
-from . import layers_537238KB as layers
-
-
-class BaseASPPNet(nn.Module):
-    def __init__(self, nin, ch, dilations=(4, 8, 16)):
-        super(BaseASPPNet, self).__init__()
-        self.enc1 = layers.Encoder(nin, ch, 3, 2, 1)
-        self.enc2 = layers.Encoder(ch, ch * 2, 3, 2, 1)
-        self.enc3 = layers.Encoder(ch * 2, ch * 4, 3, 2, 1)
-        self.enc4 = layers.Encoder(ch * 4, ch * 8, 3, 2, 1)
-
-        self.aspp = layers.ASPPModule(ch * 8, ch * 16, dilations)
-
-        self.dec4 = layers.Decoder(ch * (8 + 16), ch * 8, 3, 1, 1)
-        self.dec3 = layers.Decoder(ch * (4 + 8), ch * 4, 3, 1, 1)
-        self.dec2 = layers.Decoder(ch * (2 + 4), ch * 2, 3, 1, 1)
-        self.dec1 = layers.Decoder(ch * (1 + 2), ch, 3, 1, 1)
-
-    def __call__(self, x):
-        h, e1 = self.enc1(x)
-        h, e2 = self.enc2(h)
-        h, e3 = self.enc3(h)
-        h, e4 = self.enc4(h)
-
-        h = self.aspp(h)
-
-        h = self.dec4(h, e4)
-        h = self.dec3(h, e3)
-        h = self.dec2(h, e2)
-        h = self.dec1(h, e1)
-
-        return h
-
-
-class CascadedASPPNet(nn.Module):
-    def __init__(self, n_fft):
-        super(CascadedASPPNet, self).__init__()
-        self.stg1_low_band_net = BaseASPPNet(2, 64)
-        self.stg1_high_band_net = BaseASPPNet(2, 64)
-
-        self.stg2_bridge = layers.Conv2DBNActiv(66, 32, 1, 1, 0)
-        self.stg2_full_band_net = BaseASPPNet(32, 64)
-
-        self.stg3_bridge = layers.Conv2DBNActiv(130, 64, 1, 1, 0)
-        self.stg3_full_band_net = BaseASPPNet(64, 128)
-
-        self.out = nn.Conv2d(128, 2, 1, bias=False)
-        self.aux1_out = nn.Conv2d(64, 2, 1, bias=False)
-        self.aux2_out = nn.Conv2d(64, 2, 1, bias=False)
-
-        self.max_bin = n_fft // 2
-        self.output_bin = n_fft // 2 + 1
-
-        self.offset = 128
-
-    def forward(self, x, aggressiveness=None):
-        mix = x.detach()
-        x = x.clone()
-
-        x = x[:, :, : self.max_bin]
-
-        bandw = x.size()[2] // 2
-        aux1 = torch.cat(
-            [
-                self.stg1_low_band_net(x[:, :, :bandw]),
-                self.stg1_high_band_net(x[:, :, bandw:]),
-            ],
-            dim=2,
-        )
-
-        h = torch.cat([x, aux1], dim=1)
-        aux2 = self.stg2_full_band_net(self.stg2_bridge(h))
-
-        h = torch.cat([x, aux1, aux2], dim=1)
-        h = self.stg3_full_band_net(self.stg3_bridge(h))
-
-        mask = torch.sigmoid(self.out(h))
-        mask = F.pad(
-            input=mask,
-            pad=(0, 0, 0, self.output_bin - mask.size()[2]),
-            mode="replicate",
-        )
-
-        if self.training:
-            aux1 = torch.sigmoid(self.aux1_out(aux1))
-            aux1 = F.pad(
-                input=aux1,
-                pad=(0, 0, 0, self.output_bin - aux1.size()[2]),
-                mode="replicate",
-            )
-            aux2 = torch.sigmoid(self.aux2_out(aux2))
-            aux2 = F.pad(
-                input=aux2,
-                pad=(0, 0, 0, self.output_bin - aux2.size()[2]),
-                mode="replicate",
-            )
-            return mask * mix, aux1 * mix, aux2 * mix
-        else:
-            if aggressiveness:
-                mask[:, :, : aggressiveness["split_bin"]] = torch.pow(
-                    mask[:, :, : aggressiveness["split_bin"]],
-                    1 + aggressiveness["value"] / 3,
-                )
-                mask[:, :, aggressiveness["split_bin"] :] = torch.pow(
-                    mask[:, :, aggressiveness["split_bin"] :],
-                    1 + aggressiveness["value"],
-                )
-
-            return mask * mix
-
-    def predict(self, x_mag, aggressiveness=None):
-        h = self.forward(x_mag, aggressiveness)
-
-        if self.offset > 0:
-            h = h[:, :, :, self.offset : -self.offset]
-            assert h.size()[3] > 0
-
-        return h
diff --git a/spaces/allandclive/Uganda_MMS/asr.py b/spaces/allandclive/Uganda_MMS/asr.py
deleted file mode 100644
index 3c7361aaf29cd007dbbdffafb86c1e0fdf7d1aba..0000000000000000000000000000000000000000
--- a/spaces/allandclive/Uganda_MMS/asr.py
+++ /dev/null
@@ -1,41 +0,0 @@
-import librosa
-from transformers import Wav2Vec2ForCTC, AutoProcessor
-import torch
-
-ASR_SAMPLING_RATE = 16_000
-
-
-MODEL_ID = "facebook/mms-1b-all"
-
-processor = AutoProcessor.from_pretrained(MODEL_ID)
-model = Wav2Vec2ForCTC.from_pretrained(MODEL_ID)
-
-
-def transcribe(microphone, file_upload, lang):
-
-    warn_output = ""
-    if (microphone is not None) and (file_upload is not None):
-        warn_output = (
-            "WARNING: You've uploaded an audio file and used the microphone. "
-            "The recorded file from the microphone will be used and the uploaded audio will be discarded.\n"
-        )
-    elif (microphone is None) and (file_upload is None):
-        return "ERROR: You have to either use the microphone or upload an audio file"
-
-    audio_fp = microphone if microphone is not None else file_upload
-    audio_samples = librosa.load(audio_fp, sr=ASR_SAMPLING_RATE, mono=True)[0]
-
-    lang_code = lang.split(":")[0]
-    processor.tokenizer.set_target_lang(lang_code)
-    model.load_adapter(lang_code)
-
-    inputs = processor(
-        audio_samples, sampling_rate=ASR_SAMPLING_RATE, return_tensors="pt"
-    )
-
-    with torch.no_grad():
-        outputs = model(**inputs).logits
-
-    ids = torch.argmax(outputs, dim=-1)[0]
-    transcription = processor.decode(ids)
-    return warn_output + transcription
diff --git a/spaces/allknowingroger/Image-Models-Test205/README.md b/spaces/allknowingroger/Image-Models-Test205/README.md
deleted file mode 100644
index f91e4b31ab345f987b425de029c057bfb69d9e1b..0000000000000000000000000000000000000000
--- a/spaces/allknowingroger/Image-Models-Test205/README.md
+++ /dev/null
@@ -1,13 +0,0 @@
----
-title: More Image Models
-emoji: 😻
-colorFrom: red
-colorTo: gray
-sdk: gradio
-sdk_version: 3.23.0
-app_file: app.py
-pinned: true
-duplicated_from: allknowingroger/Image-Models-Test
----
-
-<!--Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference-->
\ No newline at end of file
diff --git a/spaces/amanmibra/void-demo-aisf/server/README.md b/spaces/amanmibra/void-demo-aisf/server/README.md
deleted file mode 100644
index 12f69df40038c1b8dbaa5a922ad9179f62a17fed..0000000000000000000000000000000000000000
--- a/spaces/amanmibra/void-demo-aisf/server/README.md
+++ /dev/null
@@ -1,5 +0,0 @@
-# VoID API
-
-Run locally: `uvicorn main:app --reload`
-
-Go to docs: `http://localhost:8000/docs`
diff --git a/spaces/amarzana/Drop_image_to_short_story/app.py b/spaces/amarzana/Drop_image_to_short_story/app.py
deleted file mode 100644
index e5b5e71d8abda3a310e1ad94662cf507799b8efe..0000000000000000000000000000000000000000
--- a/spaces/amarzana/Drop_image_to_short_story/app.py
+++ /dev/null
@@ -1,32 +0,0 @@
-import gradio as gr
-from transformers import pipeline
-
-image_to_text = pipeline("image-to-text", 
-                         model="nlpconnect/vit-gpt2-image-captioning")
-
-generator = pipeline('text-generation', model='gpt2')
-
-def generate(text):
-    
-    result1 = str(image_to_text(text)[0]['generated_text'])
-
-    result2 = str(generator(result1, max_length=100, \
-                            num_return_sequences=1)[0]['generated_text'])
-    
-    return result2
-
-
-demo = gr.Blocks()
-
-with demo:
-    url = gr.inputs.Textbox(label="Input a image url")
-    image = gr.Image(type="pil", label="Drop image here")
-    text = gr.Textbox(label="Output Box")
-
-    b1 = gr.Button("Input url")
-    b2 = gr.Button("Drop image")
-
-    b1.click(generate, inputs=url, outputs=text)
-    b2.click(generate, inputs=image, outputs=text)
-
-demo.launch()
diff --git a/spaces/aminghias/text_analytics_project/app.py b/spaces/aminghias/text_analytics_project/app.py
deleted file mode 100644
index a9c1d40d56fea8450b9a55e8c36a7ede1c997fb5..0000000000000000000000000000000000000000
--- a/spaces/aminghias/text_analytics_project/app.py
+++ /dev/null
@@ -1,68 +0,0 @@
-import gradio as gr
-import pandas as pd
-
-
-from transformers import pipeline
-
-
-
-pipe = pipeline("fill-mask", model="aminghias/Clinical-BERT-finetuned")
-pipe2 = pipeline("fill-mask", model="emilyalsentzer/Bio_ClinicalBERT")
-pipe3= pipeline("fill-mask", model="medicalai/ClinicalBERT")
-
-
-
-def predict(text):
-
-    pred1 = pipe(text)
-    pred2 = pipe2(text)
-    pred3= pipe3(text)
-    
-    df_sum=pd.DataFrame(pred1)
-    
-    df_sum
-    df_sum['score_finetuned_CBERT']=df_sum['score']
-    df_sum2=pd.DataFrame(pred2)
-    df_sum2['score_Bio_CBERT']=df_sum2['score']
-    df_sum2
-
-    df_sum3= pd.DataFrame(pred3)
-    df_sum3['score_CBERT']=df_sum3['score']
-    
-    # # join the two dataframes on token do outer join
-    
-    df_join=pd.merge(df_sum,df_sum2,on='token_str',how='outer')
-    df_join=pd.merge(df_sum3,df_join,on='token_str',how='outer')
-    
-    df_join
-    df_join['sum_sequence']=df_join['sequence_x'].fillna(df_join['sequence_y'])
-    df_join['sum_sequence']=df_join['sum_sequence'].fillna(df_join['sequence'])
-    df_join=df_join.fillna(0)
-    df_join['score_average']=(df_join['score_finetuned_CBERT']+df_join['score_Bio_CBERT']+df_join['score_CBERT'])/3
-    
-    df_join=df_join.sort_values(by='score_average',ascending=False)
-    df_join=df_join.reset_index(drop=True)
-
-    df=df_join.copy()
-    df_join=df_join[['token_str','score_average','score_finetuned_CBERT','score_Bio_CBERT','score_CBERT']].head()
-
-
-    return (df['sum_sequence'][0],df_join)
-
-
-    
-demo = gr.Interface(
-  fn=predict, 
-  inputs='text',
-  # outputs='text',
-  outputs=['text', gr.Dataframe()],
-
-  title="Filling Missing Clinical/Medical Data ",
-    examples=[ ['The  high blood pressure was due to [MASK]  which is critical.'],
-              ['The  patient is suffering from throat infection causing [MASK] and cough.']
-             ],
-    description="This application fills any missing words in the medical domain",
-
-)
-
-demo.launch()
\ No newline at end of file
diff --git a/spaces/amsterdamNLP/attention-rollout/lib/util.py b/spaces/amsterdamNLP/attention-rollout/lib/util.py
deleted file mode 100644
index 5d8646a508b2f79c3188c60913d347052dc328dd..0000000000000000000000000000000000000000
--- a/spaces/amsterdamNLP/attention-rollout/lib/util.py
+++ /dev/null
@@ -1,87 +0,0 @@
-import pathlib
-import gradio
-from captum.attr import visualization
-
-class Markdown(gradio.Markdown):
-    def __init__(self, value, *args, **kwargs):
-        if isinstance(value, pathlib.Path):
-            value = value.read_text()
-        elif isinstance(value, io.TextIOWrapper):
-            value = value.read()
-        super().__init__(value, *args, **kwargs)
-
-# from https://discuss.pytorch.org/t/using-scikit-learns-scalers-for-torchvision/53455
-class PyTMinMaxScalerVectorized(object):
-    """
-    Transforms each channel to the range [0, 1].
-    """
-
-    def __init__(self, dimension=-1):
-        self.d = dimension
-
-    def __call__(self, tensor):
-        d = self.d
-        scale = 1.0 / (
-            tensor.max(dim=d, keepdim=True)[0] - tensor.min(dim=d, keepdim=True)[0]
-        )
-        tensor.mul_(scale).sub_(tensor.min(dim=d, keepdim=True)[0])
-        return tensor
-
-# copied out of captum because we need raw html instead of a jupyter widget
-def visualize_text(datarecords, legend=False):
-    dom = ["<table width: 100%>"]
-    rows = [
-#        "<tr><th>True Label</th>"
-        "<th style='text-align: left'>Predicted Label</th>"
-        "<th style='text-align: left'>Attribution Label</th>"
-#        "<th>Attribution Score</th>"
-        "<th style='text-align: left'>Word Importance</th>"
-    ]
-    for datarecord in datarecords:
-        rows.append(
-            "".join(
-                [
-                    "<tr>",
-#                    visualization.format_classname(datarecord.true_class),
-#                    visualization.format_classname(
-#                        "{0} ({1:.2f})".format(
-#                            datarecord.pred_class#, datarecord.pred_prob
-#                        )
-#                    ),
-                    visualization.format_classname(datarecord.pred_class),
-                    visualization.format_classname(datarecord.attr_class),
-#                    visualization.format_classname(
-#                        "{0:.2f}".format(datarecord.attr_score)
-#                    ),
-                    visualization.format_word_importances(
-                        datarecord.raw_input_ids, datarecord.word_attributions
-                    ),
-                    "<tr>",
-                ]
-            )
-        )
-
-    if legend:
-        dom.append(
-            '<div style="border-top: 1px solid; margin-top: 5px; \
-            padding-top: 5px; display: inline-block">'
-        )
-        dom.append("<b>Legend: </b>")
-
-        for value, label in zip([-1, 0, 1], ["Negative", "Neutral", "Positive"]):
-            dom.append(
-                '<span style="display: inline-block; width: 10px; height: 10px; \
-                border: 1px solid; background-color: \
-                {value}"></span> {label}  '.format(
-                    value=visualization._get_color(value), label=label
-                )
-            )
-        dom.append("</div>")
-
-    dom.append("".join(rows))
-    dom.append("</table>")
-    html = "".join(dom)
-
-    return html
-
-
diff --git a/spaces/aodianyun/stable-diffusion-webui/extensions/deforum/scripts/deforum_helpers/__init__.py b/spaces/aodianyun/stable-diffusion-webui/extensions/deforum/scripts/deforum_helpers/__init__.py
deleted file mode 100644
index fe08549e9c92f0e8a7bc96cead3277dedd12583c..0000000000000000000000000000000000000000
--- a/spaces/aodianyun/stable-diffusion-webui/extensions/deforum/scripts/deforum_helpers/__init__.py
+++ /dev/null
@@ -1,7 +0,0 @@
-"""
-from .save_images import save_samples, get_output_folder
-from .depth import DepthModel
-from .prompt import sanitize
-from .animation import construct_RotationMatrixHomogenous, getRotationMatrixManual, getPoints_for_PerspectiveTranformEstimation, warpMatrix, anim_frame_warp_2d, anim_frame_warp_3d
-from .generate import add_noise, load_img, load_mask_latent, prepare_mask
-"""
\ No newline at end of file
diff --git a/spaces/arxify/RVC-beta-v2-0618/runtime/Lib/site-packages/aiohttp/client.py b/spaces/arxify/RVC-beta-v2-0618/runtime/Lib/site-packages/aiohttp/client.py
deleted file mode 100644
index 0d0f4c16c0cfa3751343e2ee60104e3e1a3db04c..0000000000000000000000000000000000000000
--- a/spaces/arxify/RVC-beta-v2-0618/runtime/Lib/site-packages/aiohttp/client.py
+++ /dev/null
@@ -1,1305 +0,0 @@
-"""HTTP Client for asyncio."""
-
-import asyncio
-import base64
-import hashlib
-import json
-import os
-import sys
-import traceback
-import warnings
-from contextlib import suppress
-from types import SimpleNamespace, TracebackType
-from typing import (
-    Any,
-    Awaitable,
-    Callable,
-    Coroutine,
-    FrozenSet,
-    Generator,
-    Generic,
-    Iterable,
-    List,
-    Mapping,
-    Optional,
-    Set,
-    Tuple,
-    Type,
-    TypeVar,
-    Union,
-)
-
-import attr
-from multidict import CIMultiDict, MultiDict, MultiDictProxy, istr
-from yarl import URL
-
-from . import hdrs, http, payload
-from .abc import AbstractCookieJar
-from .client_exceptions import (
-    ClientConnectionError as ClientConnectionError,
-    ClientConnectorCertificateError as ClientConnectorCertificateError,
-    ClientConnectorError as ClientConnectorError,
-    ClientConnectorSSLError as ClientConnectorSSLError,
-    ClientError as ClientError,
-    ClientHttpProxyError as ClientHttpProxyError,
-    ClientOSError as ClientOSError,
-    ClientPayloadError as ClientPayloadError,
-    ClientProxyConnectionError as ClientProxyConnectionError,
-    ClientResponseError as ClientResponseError,
-    ClientSSLError as ClientSSLError,
-    ContentTypeError as ContentTypeError,
-    InvalidURL as InvalidURL,
-    ServerConnectionError as ServerConnectionError,
-    ServerDisconnectedError as ServerDisconnectedError,
-    ServerFingerprintMismatch as ServerFingerprintMismatch,
-    ServerTimeoutError as ServerTimeoutError,
-    TooManyRedirects as TooManyRedirects,
-    WSServerHandshakeError as WSServerHandshakeError,
-)
-from .client_reqrep import (
-    ClientRequest as ClientRequest,
-    ClientResponse as ClientResponse,
-    Fingerprint as Fingerprint,
-    RequestInfo as RequestInfo,
-    _merge_ssl_params,
-)
-from .client_ws import ClientWebSocketResponse as ClientWebSocketResponse
-from .connector import (
-    BaseConnector as BaseConnector,
-    NamedPipeConnector as NamedPipeConnector,
-    TCPConnector as TCPConnector,
-    UnixConnector as UnixConnector,
-)
-from .cookiejar import CookieJar
-from .helpers import (
-    DEBUG,
-    PY_36,
-    BasicAuth,
-    TimeoutHandle,
-    ceil_timeout,
-    get_env_proxy_for_url,
-    get_running_loop,
-    sentinel,
-    strip_auth_from_url,
-)
-from .http import WS_KEY, HttpVersion, WebSocketReader, WebSocketWriter
-from .http_websocket import WSHandshakeError, WSMessage, ws_ext_gen, ws_ext_parse
-from .streams import FlowControlDataQueue
-from .tracing import Trace, TraceConfig
-from .typedefs import Final, JSONEncoder, LooseCookies, LooseHeaders, StrOrURL
-
-__all__ = (
-    # client_exceptions
-    "ClientConnectionError",
-    "ClientConnectorCertificateError",
-    "ClientConnectorError",
-    "ClientConnectorSSLError",
-    "ClientError",
-    "ClientHttpProxyError",
-    "ClientOSError",
-    "ClientPayloadError",
-    "ClientProxyConnectionError",
-    "ClientResponseError",
-    "ClientSSLError",
-    "ContentTypeError",
-    "InvalidURL",
-    "ServerConnectionError",
-    "ServerDisconnectedError",
-    "ServerFingerprintMismatch",
-    "ServerTimeoutError",
-    "TooManyRedirects",
-    "WSServerHandshakeError",
-    # client_reqrep
-    "ClientRequest",
-    "ClientResponse",
-    "Fingerprint",
-    "RequestInfo",
-    # connector
-    "BaseConnector",
-    "TCPConnector",
-    "UnixConnector",
-    "NamedPipeConnector",
-    # client_ws
-    "ClientWebSocketResponse",
-    # client
-    "ClientSession",
-    "ClientTimeout",
-    "request",
-)
-
-
-try:
-    from ssl import SSLContext
-except ImportError:  # pragma: no cover
-    SSLContext = object  # type: ignore[misc,assignment]
-
-
-@attr.s(auto_attribs=True, frozen=True, slots=True)
-class ClientTimeout:
-    total: Optional[float] = None
-    connect: Optional[float] = None
-    sock_read: Optional[float] = None
-    sock_connect: Optional[float] = None
-
-    # pool_queue_timeout: Optional[float] = None
-    # dns_resolution_timeout: Optional[float] = None
-    # socket_connect_timeout: Optional[float] = None
-    # connection_acquiring_timeout: Optional[float] = None
-    # new_connection_timeout: Optional[float] = None
-    # http_header_timeout: Optional[float] = None
-    # response_body_timeout: Optional[float] = None
-
-    # to create a timeout specific for a single request, either
-    # - create a completely new one to overwrite the default
-    # - or use http://www.attrs.org/en/stable/api.html#attr.evolve
-    # to overwrite the defaults
-
-
-# 5 Minute default read timeout
-DEFAULT_TIMEOUT: Final[ClientTimeout] = ClientTimeout(total=5 * 60)
-
-_RetType = TypeVar("_RetType")
-
-
-class ClientSession:
-    """First-class interface for making HTTP requests."""
-
-    ATTRS = frozenset(
-        [
-            "_base_url",
-            "_source_traceback",
-            "_connector",
-            "requote_redirect_url",
-            "_loop",
-            "_cookie_jar",
-            "_connector_owner",
-            "_default_auth",
-            "_version",
-            "_json_serialize",
-            "_requote_redirect_url",
-            "_timeout",
-            "_raise_for_status",
-            "_auto_decompress",
-            "_trust_env",
-            "_default_headers",
-            "_skip_auto_headers",
-            "_request_class",
-            "_response_class",
-            "_ws_response_class",
-            "_trace_configs",
-            "_read_bufsize",
-        ]
-    )
-
-    _source_traceback = None  # type: Optional[traceback.StackSummary]
-    _connector = None  # type: Optional[BaseConnector]
-
-    def __init__(
-        self,
-        base_url: Optional[StrOrURL] = None,
-        *,
-        connector: Optional[BaseConnector] = None,
-        loop: Optional[asyncio.AbstractEventLoop] = None,
-        cookies: Optional[LooseCookies] = None,
-        headers: Optional[LooseHeaders] = None,
-        skip_auto_headers: Optional[Iterable[str]] = None,
-        auth: Optional[BasicAuth] = None,
-        json_serialize: JSONEncoder = json.dumps,
-        request_class: Type[ClientRequest] = ClientRequest,
-        response_class: Type[ClientResponse] = ClientResponse,
-        ws_response_class: Type[ClientWebSocketResponse] = ClientWebSocketResponse,
-        version: HttpVersion = http.HttpVersion11,
-        cookie_jar: Optional[AbstractCookieJar] = None,
-        connector_owner: bool = True,
-        raise_for_status: bool = False,
-        read_timeout: Union[float, object] = sentinel,
-        conn_timeout: Optional[float] = None,
-        timeout: Union[object, ClientTimeout] = sentinel,
-        auto_decompress: bool = True,
-        trust_env: bool = False,
-        requote_redirect_url: bool = True,
-        trace_configs: Optional[List[TraceConfig]] = None,
-        read_bufsize: int = 2**16,
-    ) -> None:
-        if loop is None:
-            if connector is not None:
-                loop = connector._loop
-
-        loop = get_running_loop(loop)
-
-        if base_url is None or isinstance(base_url, URL):
-            self._base_url: Optional[URL] = base_url
-        else:
-            self._base_url = URL(base_url)
-            assert (
-                self._base_url.origin() == self._base_url
-            ), "Only absolute URLs without path part are supported"
-
-        if connector is None:
-            connector = TCPConnector(loop=loop)
-
-        if connector._loop is not loop:
-            raise RuntimeError("Session and connector has to use same event loop")
-
-        self._loop = loop
-
-        if loop.get_debug():
-            self._source_traceback = traceback.extract_stack(sys._getframe(1))
-
-        if cookie_jar is None:
-            cookie_jar = CookieJar(loop=loop)
-        self._cookie_jar = cookie_jar
-
-        if cookies is not None:
-            self._cookie_jar.update_cookies(cookies)
-
-        self._connector = connector
-        self._connector_owner = connector_owner
-        self._default_auth = auth
-        self._version = version
-        self._json_serialize = json_serialize
-        if timeout is sentinel:
-            self._timeout = DEFAULT_TIMEOUT
-            if read_timeout is not sentinel:
-                warnings.warn(
-                    "read_timeout is deprecated, " "use timeout argument instead",
-                    DeprecationWarning,
-                    stacklevel=2,
-                )
-                self._timeout = attr.evolve(self._timeout, total=read_timeout)
-            if conn_timeout is not None:
-                self._timeout = attr.evolve(self._timeout, connect=conn_timeout)
-                warnings.warn(
-                    "conn_timeout is deprecated, " "use timeout argument instead",
-                    DeprecationWarning,
-                    stacklevel=2,
-                )
-        else:
-            self._timeout = timeout  # type: ignore[assignment]
-            if read_timeout is not sentinel:
-                raise ValueError(
-                    "read_timeout and timeout parameters "
-                    "conflict, please setup "
-                    "timeout.read"
-                )
-            if conn_timeout is not None:
-                raise ValueError(
-                    "conn_timeout and timeout parameters "
-                    "conflict, please setup "
-                    "timeout.connect"
-                )
-        self._raise_for_status = raise_for_status
-        self._auto_decompress = auto_decompress
-        self._trust_env = trust_env
-        self._requote_redirect_url = requote_redirect_url
-        self._read_bufsize = read_bufsize
-
-        # Convert to list of tuples
-        if headers:
-            real_headers: CIMultiDict[str] = CIMultiDict(headers)
-        else:
-            real_headers = CIMultiDict()
-        self._default_headers: CIMultiDict[str] = real_headers
-        if skip_auto_headers is not None:
-            self._skip_auto_headers = frozenset(istr(i) for i in skip_auto_headers)
-        else:
-            self._skip_auto_headers = frozenset()
-
-        self._request_class = request_class
-        self._response_class = response_class
-        self._ws_response_class = ws_response_class
-
-        self._trace_configs = trace_configs or []
-        for trace_config in self._trace_configs:
-            trace_config.freeze()
-
-    def __init_subclass__(cls: Type["ClientSession"]) -> None:
-        warnings.warn(
-            "Inheritance class {} from ClientSession "
-            "is discouraged".format(cls.__name__),
-            DeprecationWarning,
-            stacklevel=2,
-        )
-
-    if DEBUG:
-
-        def __setattr__(self, name: str, val: Any) -> None:
-            if name not in self.ATTRS:
-                warnings.warn(
-                    "Setting custom ClientSession.{} attribute "
-                    "is discouraged".format(name),
-                    DeprecationWarning,
-                    stacklevel=2,
-                )
-            super().__setattr__(name, val)
-
-    def __del__(self, _warnings: Any = warnings) -> None:
-        if not self.closed:
-            if PY_36:
-                kwargs = {"source": self}
-            else:
-                kwargs = {}
-            _warnings.warn(
-                f"Unclosed client session {self!r}", ResourceWarning, **kwargs
-            )
-            context = {"client_session": self, "message": "Unclosed client session"}
-            if self._source_traceback is not None:
-                context["source_traceback"] = self._source_traceback
-            self._loop.call_exception_handler(context)
-
-    def request(
-        self, method: str, url: StrOrURL, **kwargs: Any
-    ) -> "_RequestContextManager":
-        """Perform HTTP request."""
-        return _RequestContextManager(self._request(method, url, **kwargs))
-
-    def _build_url(self, str_or_url: StrOrURL) -> URL:
-        url = URL(str_or_url)
-        if self._base_url is None:
-            return url
-        else:
-            assert not url.is_absolute() and url.path.startswith("/")
-            return self._base_url.join(url)
-
-    async def _request(
-        self,
-        method: str,
-        str_or_url: StrOrURL,
-        *,
-        params: Optional[Mapping[str, str]] = None,
-        data: Any = None,
-        json: Any = None,
-        cookies: Optional[LooseCookies] = None,
-        headers: Optional[LooseHeaders] = None,
-        skip_auto_headers: Optional[Iterable[str]] = None,
-        auth: Optional[BasicAuth] = None,
-        allow_redirects: bool = True,
-        max_redirects: int = 10,
-        compress: Optional[str] = None,
-        chunked: Optional[bool] = None,
-        expect100: bool = False,
-        raise_for_status: Optional[bool] = None,
-        read_until_eof: bool = True,
-        proxy: Optional[StrOrURL] = None,
-        proxy_auth: Optional[BasicAuth] = None,
-        timeout: Union[ClientTimeout, object] = sentinel,
-        verify_ssl: Optional[bool] = None,
-        fingerprint: Optional[bytes] = None,
-        ssl_context: Optional[SSLContext] = None,
-        ssl: Optional[Union[SSLContext, bool, Fingerprint]] = None,
-        proxy_headers: Optional[LooseHeaders] = None,
-        trace_request_ctx: Optional[SimpleNamespace] = None,
-        read_bufsize: Optional[int] = None,
-    ) -> ClientResponse:
-
-        # NOTE: timeout clamps existing connect and read timeouts.  We cannot
-        # set the default to None because we need to detect if the user wants
-        # to use the existing timeouts by setting timeout to None.
-
-        if self.closed:
-            raise RuntimeError("Session is closed")
-
-        ssl = _merge_ssl_params(ssl, verify_ssl, ssl_context, fingerprint)
-
-        if data is not None and json is not None:
-            raise ValueError(
-                "data and json parameters can not be used at the same time"
-            )
-        elif json is not None:
-            data = payload.JsonPayload(json, dumps=self._json_serialize)
-
-        if not isinstance(chunked, bool) and chunked is not None:
-            warnings.warn("Chunk size is deprecated #1615", DeprecationWarning)
-
-        redirects = 0
-        history = []
-        version = self._version
-
-        # Merge with default headers and transform to CIMultiDict
-        headers = self._prepare_headers(headers)
-        proxy_headers = self._prepare_headers(proxy_headers)
-
-        try:
-            url = self._build_url(str_or_url)
-        except ValueError as e:
-            raise InvalidURL(str_or_url) from e
-
-        skip_headers = set(self._skip_auto_headers)
-        if skip_auto_headers is not None:
-            for i in skip_auto_headers:
-                skip_headers.add(istr(i))
-
-        if proxy is not None:
-            try:
-                proxy = URL(proxy)
-            except ValueError as e:
-                raise InvalidURL(proxy) from e
-
-        if timeout is sentinel:
-            real_timeout: ClientTimeout = self._timeout
-        else:
-            if not isinstance(timeout, ClientTimeout):
-                real_timeout = ClientTimeout(total=timeout)  # type: ignore[arg-type]
-            else:
-                real_timeout = timeout
-        # timeout is cumulative for all request operations
-        # (request, redirects, responses, data consuming)
-        tm = TimeoutHandle(self._loop, real_timeout.total)
-        handle = tm.start()
-
-        if read_bufsize is None:
-            read_bufsize = self._read_bufsize
-
-        traces = [
-            Trace(
-                self,
-                trace_config,
-                trace_config.trace_config_ctx(trace_request_ctx=trace_request_ctx),
-            )
-            for trace_config in self._trace_configs
-        ]
-
-        for trace in traces:
-            await trace.send_request_start(method, url.update_query(params), headers)
-
-        timer = tm.timer()
-        try:
-            with timer:
-                while True:
-                    url, auth_from_url = strip_auth_from_url(url)
-                    if auth and auth_from_url:
-                        raise ValueError(
-                            "Cannot combine AUTH argument with "
-                            "credentials encoded in URL"
-                        )
-
-                    if auth is None:
-                        auth = auth_from_url
-                    if auth is None:
-                        auth = self._default_auth
-                    # It would be confusing if we support explicit
-                    # Authorization header with auth argument
-                    if (
-                        headers is not None
-                        and auth is not None
-                        and hdrs.AUTHORIZATION in headers
-                    ):
-                        raise ValueError(
-                            "Cannot combine AUTHORIZATION header "
-                            "with AUTH argument or credentials "
-                            "encoded in URL"
-                        )
-
-                    all_cookies = self._cookie_jar.filter_cookies(url)
-
-                    if cookies is not None:
-                        tmp_cookie_jar = CookieJar()
-                        tmp_cookie_jar.update_cookies(cookies)
-                        req_cookies = tmp_cookie_jar.filter_cookies(url)
-                        if req_cookies:
-                            all_cookies.load(req_cookies)
-
-                    if proxy is not None:
-                        proxy = URL(proxy)
-                    elif self._trust_env:
-                        with suppress(LookupError):
-                            proxy, proxy_auth = get_env_proxy_for_url(url)
-
-                    req = self._request_class(
-                        method,
-                        url,
-                        params=params,
-                        headers=headers,
-                        skip_auto_headers=skip_headers,
-                        data=data,
-                        cookies=all_cookies,
-                        auth=auth,
-                        version=version,
-                        compress=compress,
-                        chunked=chunked,
-                        expect100=expect100,
-                        loop=self._loop,
-                        response_class=self._response_class,
-                        proxy=proxy,
-                        proxy_auth=proxy_auth,
-                        timer=timer,
-                        session=self,
-                        ssl=ssl,
-                        proxy_headers=proxy_headers,
-                        traces=traces,
-                    )
-
-                    # connection timeout
-                    try:
-                        async with ceil_timeout(real_timeout.connect):
-                            assert self._connector is not None
-                            conn = await self._connector.connect(
-                                req, traces=traces, timeout=real_timeout
-                            )
-                    except asyncio.TimeoutError as exc:
-                        raise ServerTimeoutError(
-                            "Connection timeout " "to host {}".format(url)
-                        ) from exc
-
-                    assert conn.transport is not None
-
-                    assert conn.protocol is not None
-                    conn.protocol.set_response_params(
-                        timer=timer,
-                        skip_payload=method.upper() == "HEAD",
-                        read_until_eof=read_until_eof,
-                        auto_decompress=self._auto_decompress,
-                        read_timeout=real_timeout.sock_read,
-                        read_bufsize=read_bufsize,
-                    )
-
-                    try:
-                        try:
-                            resp = await req.send(conn)
-                            try:
-                                await resp.start(conn)
-                            except BaseException:
-                                resp.close()
-                                raise
-                        except BaseException:
-                            conn.close()
-                            raise
-                    except ClientError:
-                        raise
-                    except OSError as exc:
-                        if exc.errno is None and isinstance(exc, asyncio.TimeoutError):
-                            raise
-                        raise ClientOSError(*exc.args) from exc
-
-                    self._cookie_jar.update_cookies(resp.cookies, resp.url)
-
-                    # redirects
-                    if resp.status in (301, 302, 303, 307, 308) and allow_redirects:
-
-                        for trace in traces:
-                            await trace.send_request_redirect(
-                                method, url.update_query(params), headers, resp
-                            )
-
-                        redirects += 1
-                        history.append(resp)
-                        if max_redirects and redirects >= max_redirects:
-                            resp.close()
-                            raise TooManyRedirects(
-                                history[0].request_info, tuple(history)
-                            )
-
-                        # For 301 and 302, mimic IE, now changed in RFC
-                        # https://github.com/kennethreitz/requests/pull/269
-                        if (resp.status == 303 and resp.method != hdrs.METH_HEAD) or (
-                            resp.status in (301, 302) and resp.method == hdrs.METH_POST
-                        ):
-                            method = hdrs.METH_GET
-                            data = None
-                            if headers.get(hdrs.CONTENT_LENGTH):
-                                headers.pop(hdrs.CONTENT_LENGTH)
-
-                        r_url = resp.headers.get(hdrs.LOCATION) or resp.headers.get(
-                            hdrs.URI
-                        )
-                        if r_url is None:
-                            # see github.com/aio-libs/aiohttp/issues/2022
-                            break
-                        else:
-                            # reading from correct redirection
-                            # response is forbidden
-                            resp.release()
-
-                        try:
-                            parsed_url = URL(
-                                r_url, encoded=not self._requote_redirect_url
-                            )
-
-                        except ValueError as e:
-                            raise InvalidURL(r_url) from e
-
-                        scheme = parsed_url.scheme
-                        if scheme not in ("http", "https", ""):
-                            resp.close()
-                            raise ValueError("Can redirect only to http or https")
-                        elif not scheme:
-                            parsed_url = url.join(parsed_url)
-
-                        if url.origin() != parsed_url.origin():
-                            auth = None
-                            headers.pop(hdrs.AUTHORIZATION, None)
-
-                        url = parsed_url
-                        params = None
-                        resp.release()
-                        continue
-
-                    break
-
-            # check response status
-            if raise_for_status is None:
-                raise_for_status = self._raise_for_status
-            if raise_for_status:
-                resp.raise_for_status()
-
-            # register connection
-            if handle is not None:
-                if resp.connection is not None:
-                    resp.connection.add_callback(handle.cancel)
-                else:
-                    handle.cancel()
-
-            resp._history = tuple(history)
-
-            for trace in traces:
-                await trace.send_request_end(
-                    method, url.update_query(params), headers, resp
-                )
-            return resp
-
-        except BaseException as e:
-            # cleanup timer
-            tm.close()
-            if handle:
-                handle.cancel()
-                handle = None
-
-            for trace in traces:
-                await trace.send_request_exception(
-                    method, url.update_query(params), headers, e
-                )
-            raise
-
-    def ws_connect(
-        self,
-        url: StrOrURL,
-        *,
-        method: str = hdrs.METH_GET,
-        protocols: Iterable[str] = (),
-        timeout: float = 10.0,
-        receive_timeout: Optional[float] = None,
-        autoclose: bool = True,
-        autoping: bool = True,
-        heartbeat: Optional[float] = None,
-        auth: Optional[BasicAuth] = None,
-        origin: Optional[str] = None,
-        params: Optional[Mapping[str, str]] = None,
-        headers: Optional[LooseHeaders] = None,
-        proxy: Optional[StrOrURL] = None,
-        proxy_auth: Optional[BasicAuth] = None,
-        ssl: Union[SSLContext, bool, None, Fingerprint] = None,
-        verify_ssl: Optional[bool] = None,
-        fingerprint: Optional[bytes] = None,
-        ssl_context: Optional[SSLContext] = None,
-        proxy_headers: Optional[LooseHeaders] = None,
-        compress: int = 0,
-        max_msg_size: int = 4 * 1024 * 1024,
-    ) -> "_WSRequestContextManager":
-        """Initiate websocket connection."""
-        return _WSRequestContextManager(
-            self._ws_connect(
-                url,
-                method=method,
-                protocols=protocols,
-                timeout=timeout,
-                receive_timeout=receive_timeout,
-                autoclose=autoclose,
-                autoping=autoping,
-                heartbeat=heartbeat,
-                auth=auth,
-                origin=origin,
-                params=params,
-                headers=headers,
-                proxy=proxy,
-                proxy_auth=proxy_auth,
-                ssl=ssl,
-                verify_ssl=verify_ssl,
-                fingerprint=fingerprint,
-                ssl_context=ssl_context,
-                proxy_headers=proxy_headers,
-                compress=compress,
-                max_msg_size=max_msg_size,
-            )
-        )
-
-    async def _ws_connect(
-        self,
-        url: StrOrURL,
-        *,
-        method: str = hdrs.METH_GET,
-        protocols: Iterable[str] = (),
-        timeout: float = 10.0,
-        receive_timeout: Optional[float] = None,
-        autoclose: bool = True,
-        autoping: bool = True,
-        heartbeat: Optional[float] = None,
-        auth: Optional[BasicAuth] = None,
-        origin: Optional[str] = None,
-        params: Optional[Mapping[str, str]] = None,
-        headers: Optional[LooseHeaders] = None,
-        proxy: Optional[StrOrURL] = None,
-        proxy_auth: Optional[BasicAuth] = None,
-        ssl: Union[SSLContext, bool, None, Fingerprint] = None,
-        verify_ssl: Optional[bool] = None,
-        fingerprint: Optional[bytes] = None,
-        ssl_context: Optional[SSLContext] = None,
-        proxy_headers: Optional[LooseHeaders] = None,
-        compress: int = 0,
-        max_msg_size: int = 4 * 1024 * 1024,
-    ) -> ClientWebSocketResponse:
-
-        if headers is None:
-            real_headers: CIMultiDict[str] = CIMultiDict()
-        else:
-            real_headers = CIMultiDict(headers)
-
-        default_headers = {
-            hdrs.UPGRADE: "websocket",
-            hdrs.CONNECTION: "upgrade",
-            hdrs.SEC_WEBSOCKET_VERSION: "13",
-        }
-
-        for key, value in default_headers.items():
-            real_headers.setdefault(key, value)
-
-        sec_key = base64.b64encode(os.urandom(16))
-        real_headers[hdrs.SEC_WEBSOCKET_KEY] = sec_key.decode()
-
-        if protocols:
-            real_headers[hdrs.SEC_WEBSOCKET_PROTOCOL] = ",".join(protocols)
-        if origin is not None:
-            real_headers[hdrs.ORIGIN] = origin
-        if compress:
-            extstr = ws_ext_gen(compress=compress)
-            real_headers[hdrs.SEC_WEBSOCKET_EXTENSIONS] = extstr
-
-        ssl = _merge_ssl_params(ssl, verify_ssl, ssl_context, fingerprint)
-
-        # send request
-        resp = await self.request(
-            method,
-            url,
-            params=params,
-            headers=real_headers,
-            read_until_eof=False,
-            auth=auth,
-            proxy=proxy,
-            proxy_auth=proxy_auth,
-            ssl=ssl,
-            proxy_headers=proxy_headers,
-        )
-
-        try:
-            # check handshake
-            if resp.status != 101:
-                raise WSServerHandshakeError(
-                    resp.request_info,
-                    resp.history,
-                    message="Invalid response status",
-                    status=resp.status,
-                    headers=resp.headers,
-                )
-
-            if resp.headers.get(hdrs.UPGRADE, "").lower() != "websocket":
-                raise WSServerHandshakeError(
-                    resp.request_info,
-                    resp.history,
-                    message="Invalid upgrade header",
-                    status=resp.status,
-                    headers=resp.headers,
-                )
-
-            if resp.headers.get(hdrs.CONNECTION, "").lower() != "upgrade":
-                raise WSServerHandshakeError(
-                    resp.request_info,
-                    resp.history,
-                    message="Invalid connection header",
-                    status=resp.status,
-                    headers=resp.headers,
-                )
-
-            # key calculation
-            r_key = resp.headers.get(hdrs.SEC_WEBSOCKET_ACCEPT, "")
-            match = base64.b64encode(hashlib.sha1(sec_key + WS_KEY).digest()).decode()
-            if r_key != match:
-                raise WSServerHandshakeError(
-                    resp.request_info,
-                    resp.history,
-                    message="Invalid challenge response",
-                    status=resp.status,
-                    headers=resp.headers,
-                )
-
-            # websocket protocol
-            protocol = None
-            if protocols and hdrs.SEC_WEBSOCKET_PROTOCOL in resp.headers:
-                resp_protocols = [
-                    proto.strip()
-                    for proto in resp.headers[hdrs.SEC_WEBSOCKET_PROTOCOL].split(",")
-                ]
-
-                for proto in resp_protocols:
-                    if proto in protocols:
-                        protocol = proto
-                        break
-
-            # websocket compress
-            notakeover = False
-            if compress:
-                compress_hdrs = resp.headers.get(hdrs.SEC_WEBSOCKET_EXTENSIONS)
-                if compress_hdrs:
-                    try:
-                        compress, notakeover = ws_ext_parse(compress_hdrs)
-                    except WSHandshakeError as exc:
-                        raise WSServerHandshakeError(
-                            resp.request_info,
-                            resp.history,
-                            message=exc.args[0],
-                            status=resp.status,
-                            headers=resp.headers,
-                        ) from exc
-                else:
-                    compress = 0
-                    notakeover = False
-
-            conn = resp.connection
-            assert conn is not None
-            conn_proto = conn.protocol
-            assert conn_proto is not None
-            transport = conn.transport
-            assert transport is not None
-            reader: FlowControlDataQueue[WSMessage] = FlowControlDataQueue(
-                conn_proto, 2**16, loop=self._loop
-            )
-            conn_proto.set_parser(WebSocketReader(reader, max_msg_size), reader)
-            writer = WebSocketWriter(
-                conn_proto,
-                transport,
-                use_mask=True,
-                compress=compress,
-                notakeover=notakeover,
-            )
-        except BaseException:
-            resp.close()
-            raise
-        else:
-            return self._ws_response_class(
-                reader,
-                writer,
-                protocol,
-                resp,
-                timeout,
-                autoclose,
-                autoping,
-                self._loop,
-                receive_timeout=receive_timeout,
-                heartbeat=heartbeat,
-                compress=compress,
-                client_notakeover=notakeover,
-            )
-
-    def _prepare_headers(self, headers: Optional[LooseHeaders]) -> "CIMultiDict[str]":
-        """Add default headers and transform it to CIMultiDict"""
-        # Convert headers to MultiDict
-        result = CIMultiDict(self._default_headers)
-        if headers:
-            if not isinstance(headers, (MultiDictProxy, MultiDict)):
-                headers = CIMultiDict(headers)
-            added_names: Set[str] = set()
-            for key, value in headers.items():
-                if key in added_names:
-                    result.add(key, value)
-                else:
-                    result[key] = value
-                    added_names.add(key)
-        return result
-
-    def get(
-        self, url: StrOrURL, *, allow_redirects: bool = True, **kwargs: Any
-    ) -> "_RequestContextManager":
-        """Perform HTTP GET request."""
-        return _RequestContextManager(
-            self._request(hdrs.METH_GET, url, allow_redirects=allow_redirects, **kwargs)
-        )
-
-    def options(
-        self, url: StrOrURL, *, allow_redirects: bool = True, **kwargs: Any
-    ) -> "_RequestContextManager":
-        """Perform HTTP OPTIONS request."""
-        return _RequestContextManager(
-            self._request(
-                hdrs.METH_OPTIONS, url, allow_redirects=allow_redirects, **kwargs
-            )
-        )
-
-    def head(
-        self, url: StrOrURL, *, allow_redirects: bool = False, **kwargs: Any
-    ) -> "_RequestContextManager":
-        """Perform HTTP HEAD request."""
-        return _RequestContextManager(
-            self._request(
-                hdrs.METH_HEAD, url, allow_redirects=allow_redirects, **kwargs
-            )
-        )
-
-    def post(
-        self, url: StrOrURL, *, data: Any = None, **kwargs: Any
-    ) -> "_RequestContextManager":
-        """Perform HTTP POST request."""
-        return _RequestContextManager(
-            self._request(hdrs.METH_POST, url, data=data, **kwargs)
-        )
-
-    def put(
-        self, url: StrOrURL, *, data: Any = None, **kwargs: Any
-    ) -> "_RequestContextManager":
-        """Perform HTTP PUT request."""
-        return _RequestContextManager(
-            self._request(hdrs.METH_PUT, url, data=data, **kwargs)
-        )
-
-    def patch(
-        self, url: StrOrURL, *, data: Any = None, **kwargs: Any
-    ) -> "_RequestContextManager":
-        """Perform HTTP PATCH request."""
-        return _RequestContextManager(
-            self._request(hdrs.METH_PATCH, url, data=data, **kwargs)
-        )
-
-    def delete(self, url: StrOrURL, **kwargs: Any) -> "_RequestContextManager":
-        """Perform HTTP DELETE request."""
-        return _RequestContextManager(self._request(hdrs.METH_DELETE, url, **kwargs))
-
-    async def close(self) -> None:
-        """Close underlying connector.
-
-        Release all acquired resources.
-        """
-        if not self.closed:
-            if self._connector is not None and self._connector_owner:
-                await self._connector.close()
-            self._connector = None
-
-    @property
-    def closed(self) -> bool:
-        """Is client session closed.
-
-        A readonly property.
-        """
-        return self._connector is None or self._connector.closed
-
-    @property
-    def connector(self) -> Optional[BaseConnector]:
-        """Connector instance used for the session."""
-        return self._connector
-
-    @property
-    def cookie_jar(self) -> AbstractCookieJar:
-        """The session cookies."""
-        return self._cookie_jar
-
-    @property
-    def version(self) -> Tuple[int, int]:
-        """The session HTTP protocol version."""
-        return self._version
-
-    @property
-    def requote_redirect_url(self) -> bool:
-        """Do URL requoting on redirection handling."""
-        return self._requote_redirect_url
-
-    @requote_redirect_url.setter
-    def requote_redirect_url(self, val: bool) -> None:
-        """Do URL requoting on redirection handling."""
-        warnings.warn(
-            "session.requote_redirect_url modification " "is deprecated #2778",
-            DeprecationWarning,
-            stacklevel=2,
-        )
-        self._requote_redirect_url = val
-
-    @property
-    def loop(self) -> asyncio.AbstractEventLoop:
-        """Session's loop."""
-        warnings.warn(
-            "client.loop property is deprecated", DeprecationWarning, stacklevel=2
-        )
-        return self._loop
-
-    @property
-    def timeout(self) -> ClientTimeout:
-        """Timeout for the session."""
-        return self._timeout
-
-    @property
-    def headers(self) -> "CIMultiDict[str]":
-        """The default headers of the client session."""
-        return self._default_headers
-
-    @property
-    def skip_auto_headers(self) -> FrozenSet[istr]:
-        """Headers for which autogeneration should be skipped"""
-        return self._skip_auto_headers
-
-    @property
-    def auth(self) -> Optional[BasicAuth]:
-        """An object that represents HTTP Basic Authorization"""
-        return self._default_auth
-
-    @property
-    def json_serialize(self) -> JSONEncoder:
-        """Json serializer callable"""
-        return self._json_serialize
-
-    @property
-    def connector_owner(self) -> bool:
-        """Should connector be closed on session closing"""
-        return self._connector_owner
-
-    @property
-    def raise_for_status(
-        self,
-    ) -> Union[bool, Callable[[ClientResponse], Awaitable[None]]]:
-        """Should `ClientResponse.raise_for_status()` be called for each response."""
-        return self._raise_for_status
-
-    @property
-    def auto_decompress(self) -> bool:
-        """Should the body response be automatically decompressed."""
-        return self._auto_decompress
-
-    @property
-    def trust_env(self) -> bool:
-        """
-        Should proxies information from environment or netrc be trusted.
-
-        Information is from HTTP_PROXY / HTTPS_PROXY environment variables
-        or ~/.netrc file if present.
-        """
-        return self._trust_env
-
-    @property
-    def trace_configs(self) -> List[TraceConfig]:
-        """A list of TraceConfig instances used for client tracing"""
-        return self._trace_configs
-
-    def detach(self) -> None:
-        """Detach connector from session without closing the former.
-
-        Session is switched to closed state anyway.
-        """
-        self._connector = None
-
-    def __enter__(self) -> None:
-        raise TypeError("Use async with instead")
-
-    def __exit__(
-        self,
-        exc_type: Optional[Type[BaseException]],
-        exc_val: Optional[BaseException],
-        exc_tb: Optional[TracebackType],
-    ) -> None:
-        # __exit__ should exist in pair with __enter__ but never executed
-        pass  # pragma: no cover
-
-    async def __aenter__(self) -> "ClientSession":
-        return self
-
-    async def __aexit__(
-        self,
-        exc_type: Optional[Type[BaseException]],
-        exc_val: Optional[BaseException],
-        exc_tb: Optional[TracebackType],
-    ) -> None:
-        await self.close()
-
-
-class _BaseRequestContextManager(Coroutine[Any, Any, _RetType], Generic[_RetType]):
-
-    __slots__ = ("_coro", "_resp")
-
-    def __init__(self, coro: Coroutine["asyncio.Future[Any]", None, _RetType]) -> None:
-        self._coro = coro
-
-    def send(self, arg: None) -> "asyncio.Future[Any]":
-        return self._coro.send(arg)
-
-    def throw(self, arg: BaseException) -> None:  # type: ignore[arg-type,override]
-        self._coro.throw(arg)
-
-    def close(self) -> None:
-        return self._coro.close()
-
-    def __await__(self) -> Generator[Any, None, _RetType]:
-        ret = self._coro.__await__()
-        return ret
-
-    def __iter__(self) -> Generator[Any, None, _RetType]:
-        return self.__await__()
-
-    async def __aenter__(self) -> _RetType:
-        self._resp = await self._coro
-        return self._resp
-
-
-class _RequestContextManager(_BaseRequestContextManager[ClientResponse]):
-    __slots__ = ()
-
-    async def __aexit__(
-        self,
-        exc_type: Optional[Type[BaseException]],
-        exc: Optional[BaseException],
-        tb: Optional[TracebackType],
-    ) -> None:
-        # We're basing behavior on the exception as it can be caused by
-        # user code unrelated to the status of the connection.  If you
-        # would like to close a connection you must do that
-        # explicitly.  Otherwise connection error handling should kick in
-        # and close/recycle the connection as required.
-        self._resp.release()
-
-
-class _WSRequestContextManager(_BaseRequestContextManager[ClientWebSocketResponse]):
-    __slots__ = ()
-
-    async def __aexit__(
-        self,
-        exc_type: Optional[Type[BaseException]],
-        exc: Optional[BaseException],
-        tb: Optional[TracebackType],
-    ) -> None:
-        await self._resp.close()
-
-
-class _SessionRequestContextManager:
-
-    __slots__ = ("_coro", "_resp", "_session")
-
-    def __init__(
-        self,
-        coro: Coroutine["asyncio.Future[Any]", None, ClientResponse],
-        session: ClientSession,
-    ) -> None:
-        self._coro = coro
-        self._resp: Optional[ClientResponse] = None
-        self._session = session
-
-    async def __aenter__(self) -> ClientResponse:
-        try:
-            self._resp = await self._coro
-        except BaseException:
-            await self._session.close()
-            raise
-        else:
-            return self._resp
-
-    async def __aexit__(
-        self,
-        exc_type: Optional[Type[BaseException]],
-        exc: Optional[BaseException],
-        tb: Optional[TracebackType],
-    ) -> None:
-        assert self._resp is not None
-        self._resp.close()
-        await self._session.close()
-
-
-def request(
-    method: str,
-    url: StrOrURL,
-    *,
-    params: Optional[Mapping[str, str]] = None,
-    data: Any = None,
-    json: Any = None,
-    headers: Optional[LooseHeaders] = None,
-    skip_auto_headers: Optional[Iterable[str]] = None,
-    auth: Optional[BasicAuth] = None,
-    allow_redirects: bool = True,
-    max_redirects: int = 10,
-    compress: Optional[str] = None,
-    chunked: Optional[bool] = None,
-    expect100: bool = False,
-    raise_for_status: Optional[bool] = None,
-    read_until_eof: bool = True,
-    proxy: Optional[StrOrURL] = None,
-    proxy_auth: Optional[BasicAuth] = None,
-    timeout: Union[ClientTimeout, object] = sentinel,
-    cookies: Optional[LooseCookies] = None,
-    version: HttpVersion = http.HttpVersion11,
-    connector: Optional[BaseConnector] = None,
-    read_bufsize: Optional[int] = None,
-    loop: Optional[asyncio.AbstractEventLoop] = None,
-) -> _SessionRequestContextManager:
-    """Constructs and sends a request.
-
-    Returns response object.
-    method - HTTP method
-    url - request url
-    params - (optional) Dictionary or bytes to be sent in the query
-      string of the new request
-    data - (optional) Dictionary, bytes, or file-like object to
-      send in the body of the request
-    json - (optional) Any json compatible python object
-    headers - (optional) Dictionary of HTTP Headers to send with
-      the request
-    cookies - (optional) Dict object to send with the request
-    auth - (optional) BasicAuth named tuple represent HTTP Basic Auth
-    auth - aiohttp.helpers.BasicAuth
-    allow_redirects - (optional) If set to False, do not follow
-      redirects
-    version - Request HTTP version.
-    compress - Set to True if request has to be compressed
-       with deflate encoding.
-    chunked - Set to chunk size for chunked transfer encoding.
-    expect100 - Expect 100-continue response from server.
-    connector - BaseConnector sub-class instance to support
-       connection pooling.
-    read_until_eof - Read response until eof if response
-       does not have Content-Length header.
-    loop - Optional event loop.
-    timeout - Optional ClientTimeout settings structure, 5min
-       total timeout by default.
-    Usage::
-      >>> import aiohttp
-      >>> resp = await aiohttp.request('GET', 'http://python.org/')
-      >>> resp
-      <ClientResponse(python.org/) [200]>
-      >>> data = await resp.read()
-    """
-    connector_owner = False
-    if connector is None:
-        connector_owner = True
-        connector = TCPConnector(loop=loop, force_close=True)
-
-    session = ClientSession(
-        loop=loop,
-        cookies=cookies,
-        version=version,
-        timeout=timeout,
-        connector=connector,
-        connector_owner=connector_owner,
-    )
-
-    return _SessionRequestContextManager(
-        session._request(
-            method,
-            url,
-            params=params,
-            data=data,
-            json=json,
-            headers=headers,
-            skip_auto_headers=skip_auto_headers,
-            auth=auth,
-            allow_redirects=allow_redirects,
-            max_redirects=max_redirects,
-            compress=compress,
-            chunked=chunked,
-            expect100=expect100,
-            raise_for_status=raise_for_status,
-            read_until_eof=read_until_eof,
-            proxy=proxy,
-            proxy_auth=proxy_auth,
-            read_bufsize=read_bufsize,
-        ),
-        session,
-    )
diff --git a/spaces/arxify/RVC-beta-v2-0618/runtime/Lib/site-packages/fairseq/distributed/module_proxy_wrapper.py b/spaces/arxify/RVC-beta-v2-0618/runtime/Lib/site-packages/fairseq/distributed/module_proxy_wrapper.py
deleted file mode 100644
index 904dc0c202e09db244518836c0f061e0850cad61..0000000000000000000000000000000000000000
--- a/spaces/arxify/RVC-beta-v2-0618/runtime/Lib/site-packages/fairseq/distributed/module_proxy_wrapper.py
+++ /dev/null
@@ -1,56 +0,0 @@
-# Copyright (c) Facebook, Inc. and its affiliates.
-#
-# This source code is licensed under the MIT license found in the
-# LICENSE file in the root directory of this source tree.
-
-from torch import nn
-
-
-class ModuleProxyWrapper(nn.Module):
-    """
-    Wrap a DistributedDataParallel module and forward requests for missing
-    attributes to the module wrapped by DDP (the twice-wrapped module).
-    Also forward calls to :func:`state_dict` and :func:`load_state_dict`.
-
-    Usage::
-
-        module.xyz = "hello world"
-        wrapped_module = DistributedDataParallel(module, **ddp_args)
-        wrapped_module = ModuleProxyWrapper(wrapped_module)
-        assert wrapped_module.xyz == "hello world"
-        assert wrapped_module.state_dict().keys() == module.state_dict().keys()
-
-    Args:
-        module (nn.Module): module to wrap
-    """
-
-    def __init__(self, module: nn.Module):
-        super().__init__()
-        assert hasattr(
-            module, "module"
-        ), "ModuleProxyWrapper expects input to wrap another module"
-        self.module = module
-
-    def __getattr__(self, name):
-        """Forward missing attributes to twice-wrapped module."""
-        try:
-            # defer to nn.Module's logic
-            return super().__getattr__(name)
-        except AttributeError:
-            try:
-                # forward to the once-wrapped module
-                return getattr(self.module, name)
-            except AttributeError:
-                # forward to the twice-wrapped module
-                return getattr(self.module.module, name)
-
-    def state_dict(self, *args, **kwargs):
-        """Forward to the twice-wrapped module."""
-        return self.module.module.state_dict(*args, **kwargs)
-
-    def load_state_dict(self, *args, **kwargs):
-        """Forward to the twice-wrapped module."""
-        return self.module.module.load_state_dict(*args, **kwargs)
-
-    def forward(self, *args, **kwargs):
-        return self.module(*args, **kwargs)
diff --git a/spaces/asafAdge/Detic/tools/remove_lvis_rare.py b/spaces/asafAdge/Detic/tools/remove_lvis_rare.py
deleted file mode 100644
index 06e4e881bfa50e2cd74747511a3ad2e8676e0c70..0000000000000000000000000000000000000000
--- a/spaces/asafAdge/Detic/tools/remove_lvis_rare.py
+++ /dev/null
@@ -1,20 +0,0 @@
-# Copyright (c) Facebook, Inc. and its affiliates.
-import argparse
-import json
-
-if __name__ == '__main__':
-    parser = argparse.ArgumentParser()
-    parser.add_argument('--ann', default='datasets/lvis/lvis_v1_train.json')
-    args = parser.parse_args()
-
-    print('Loading', args.ann)
-    data = json.load(open(args.ann, 'r'))
-    catid2freq = {x['id']: x['frequency'] for x in data['categories']}
-    print('ori #anns', len(data['annotations']))
-    exclude = ['r']
-    data['annotations'] = [x for x in data['annotations'] \
-        if catid2freq[x['category_id']] not in exclude]
-    print('filtered #anns', len(data['annotations']))
-    out_path = args.ann[:-5] + '_norare.json'
-    print('Saving to', out_path)
-    json.dump(data, open(out_path, 'w'))
diff --git a/spaces/avivdm1/AutoGPT/README.md b/spaces/avivdm1/AutoGPT/README.md
deleted file mode 100644
index 5bf09b995f04f7af05d1314906b1b1ff39c20ddc..0000000000000000000000000000000000000000
--- a/spaces/avivdm1/AutoGPT/README.md
+++ /dev/null
@@ -1,13 +0,0 @@
----
-title: AutoGPT
-emoji: 🦾
-colorFrom: yellow
-colorTo: yellow
-sdk: gradio
-sdk_version: 3.27.0
-app_file: ui/app.py
-pinned: false
-license: mit
-duplicated_from: aliabid94/AutoGPT
----
-
diff --git a/spaces/awacke1/CarePlanQnAWithContext2/README.md b/spaces/awacke1/CarePlanQnAWithContext2/README.md
deleted file mode 100644
index 9525eacefea25861dcfdce7b951a3a2cd95b7861..0000000000000000000000000000000000000000
--- a/spaces/awacke1/CarePlanQnAWithContext2/README.md
+++ /dev/null
@@ -1,13 +0,0 @@
----
-title: 3-CarePlanQnA-Gradio
-emoji: ⚗️🧠🔬🩺⚕️🧬
-colorFrom: pink
-colorTo: indigo
-sdk: gradio
-sdk_version: 3.1.1
-app_file: app.py
-pinned: false
-license: mit
----
-
-Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
diff --git a/spaces/awacke1/GenAI-Generate-New-Data-Resembling-Example/app.py b/spaces/awacke1/GenAI-Generate-New-Data-Resembling-Example/app.py
deleted file mode 100644
index e8d0a1d7baf10fb67bb56d0f5ad637763b05601a..0000000000000000000000000000000000000000
--- a/spaces/awacke1/GenAI-Generate-New-Data-Resembling-Example/app.py
+++ /dev/null
@@ -1,50 +0,0 @@
-import streamlit as st
-import pandas as pd
-import numpy as np
-
-# Load the largest hospitals data
-data = [
-    {"Hospital": "Texas Health Presbyterian Hospital Dallas", "City": "Dallas", "State": "TX", "Beds": 898},
-    {"Hospital": "Cedars-Sinai Medical Center", "City": "Los Angeles", "State": "CA", "Beds": 886},
-    {"Hospital": "Jackson Memorial Hospital", "City": "Miami", "State": "FL", "Beds": 1618},
-    {"Hospital": "New York-Presbyterian Hospital", "City": "New York", "State": "NY", "Beds": 2528},
-    {"Hospital": "Barnes-Jewish Hospital", "City": "St. Louis", "State": "MO", "Beds": 1252},
-]
-
-# Create a Pandas DataFrame from the data
-df = pd.DataFrame(data)
-
-# Define the generative AI function
-def generate_data(df, num_rows=1):
-    # Calculate the mean and standard deviation of the Beds column
-    bed_mean = df["Beds"].mean()
-    bed_std = df["Beds"].std()
-    
-    # Generate new data using a normal distribution
-    new_data = {
-        "Hospital": [f"Generated Hospital {i}" for i in range(num_rows)],
-        "City": np.random.choice(df["City"], num_rows),
-        "State": np.random.choice(df["State"], num_rows),
-        "Beds": np.random.normal(bed_mean, bed_std, num_rows).astype(int)
-    }
-    
-    # Create a new DataFrame from the generated data and return it
-    return pd.DataFrame(new_data)
-
-# Define the Streamlit app
-def app():
-    st.title("Generative AI Demo")
-    
-    # Display the original data
-    st.subheader("Original Data")
-    st.write(df)
-    
-    # Generate new data and display it
-    st.subheader("Generated Data")
-    num_rows = st.slider("Number of rows to generate", min_value=1, max_value=100, value=1)
-    new_data = generate_data(df, num_rows=num_rows)
-    st.write(new_data)
-
-# Run the Streamlit app
-if __name__ == "__main__":
-    app()
diff --git a/spaces/awacke1/MusicGenStreamFacebook/README.md b/spaces/awacke1/MusicGenStreamFacebook/README.md
deleted file mode 100644
index 8b15550d5d6c4d4d58bf1d8db1bea5b087ef4286..0000000000000000000000000000000000000000
--- a/spaces/awacke1/MusicGenStreamFacebook/README.md
+++ /dev/null
@@ -1,32 +0,0 @@
----
-title: 🎵MusicHub🌐StreamZone📘Socialify👥
-emoji: 🎵🌐📘👥
-colorFrom: gray
-colorTo: red
-sdk: gradio
-sdk_version: 3.47.1
-app_file: app.py
-pinned: false
-license: mit
----
-
-🎵MusicHub🌐StreamZone📘Socialify👥
-🎶VibeGen🔄StreamSphere👤FBUnite🔗
-🎧TuneMaster📡StreamCentral🤳FBLive🔴
-🎼MelodyMaker🌪StreamWave👋FaceConnect🌐
-🎸RiffForge🌊StreamOcean🤝FBHarmony✨
-🎹PianoGen📺StreamTV📱FBMingle🦋
-🥁BeatCraft🎥StreamCinema🙋FBMeet🚀
-🎷SaxGen🌈StreamRainbow🌟FBStars🤩
-🎺TrumpetHub🌪StreamTwister🌈FBKaleidoscope🎉
-🎻StringGen🎬StreamTheater💌FBMessage📬
-🎤VoiceGen🎦StreamArena👬FBCircle🔄
-🎙MicMaster🌌StreamCosmos😃FBSmileClub😁
-🎚VolumeZone🎆StreamFiesta👭FBUnity🤗
-🎛SoundLab🌠StreamGalaxy😎FBCoolCrew🕶
-🎜MusicLoom🎇StreamFireworks👥FBMingle🔥
-🎉PartyGen🌌StreamNebula🥳FBPartyTime🎈
-🎊Festify🌠StreamStarz👫FBCompanions👋
-🎋MusicBouquet🎭StreamDrama👨‍👩‍👦FBClan🏡
-🎍SongHarbor⛈StreamStorm💑FBLoveNest🏠
-🎎MelodyMingle🌪StreamWhirl🤝FBFriendFest🎡
\ No newline at end of file
diff --git a/spaces/awacke1/SNOMED-LOINC-eCQM/README.md b/spaces/awacke1/SNOMED-LOINC-eCQM/README.md
deleted file mode 100644
index 9029dc9080883a45f274683af41661307947c234..0000000000000000000000000000000000000000
--- a/spaces/awacke1/SNOMED-LOINC-eCQM/README.md
+++ /dev/null
@@ -1,13 +0,0 @@
----
-title: 🔬🧬UI-AI-UX-Demo-All-Inputs🧠
-emoji: ⚗️🧠CT🔬🧬
-colorFrom: yellow
-colorTo: green
-sdk: gradio
-sdk_version: 3.5
-app_file: app.py
-pinned: false
-license: mit
----
-
-Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
diff --git a/spaces/banana-projects/web3d/node_modules/three/src/loaders/AnimationLoader.js b/spaces/banana-projects/web3d/node_modules/three/src/loaders/AnimationLoader.js
deleted file mode 100644
index 921f30cdfbaa48333d839835a866868966a2d21d..0000000000000000000000000000000000000000
--- a/spaces/banana-projects/web3d/node_modules/three/src/loaders/AnimationLoader.js
+++ /dev/null
@@ -1,57 +0,0 @@
-import { AnimationClip } from '../animation/AnimationClip.js';
-import { FileLoader } from './FileLoader.js';
-import { DefaultLoadingManager } from './LoadingManager.js';
-
-/**
- * @author bhouston / http://clara.io/
- */
-
-function AnimationLoader( manager ) {
-
-	this.manager = ( manager !== undefined ) ? manager : DefaultLoadingManager;
-
-}
-
-Object.assign( AnimationLoader.prototype, {
-
-	load: function ( url, onLoad, onProgress, onError ) {
-
-		var scope = this;
-
-		var loader = new FileLoader( scope.manager );
-		loader.setPath( scope.path );
-		loader.load( url, function ( text ) {
-
-			onLoad( scope.parse( JSON.parse( text ) ) );
-
-		}, onProgress, onError );
-
-	},
-
-	parse: function ( json ) {
-
-		var animations = [];
-
-		for ( var i = 0; i < json.length; i ++ ) {
-
-			var clip = AnimationClip.parse( json[ i ] );
-
-			animations.push( clip );
-
-		}
-
-		return animations;
-
-	},
-
-	setPath: function ( value ) {
-
-		this.path = value;
-		return this;
-
-	}
-
-} );
-
-
-export { AnimationLoader };
diff --git a/spaces/banana-projects/web3d/node_modules/three/src/objects/Bone.d.ts b/spaces/banana-projects/web3d/node_modules/three/src/objects/Bone.d.ts
deleted file mode 100644
index e6d323792c661b76aac0ce91c8b8f1d53d28cd87..0000000000000000000000000000000000000000
--- a/spaces/banana-projects/web3d/node_modules/three/src/objects/Bone.d.ts
+++ /dev/null
@@ -1,9 +0,0 @@
-import { Object3D } from './../core/Object3D';
-
-// Objects //////////////////////////////////////////////////////////////////////////////////
-
-export class Bone extends Object3D {
-  constructor();
-  isBone: true;
-  type: 'Bone';
-}
diff --git a/spaces/bguberfain/Detic/detic/evaluation/oideval.py b/spaces/bguberfain/Detic/detic/evaluation/oideval.py
deleted file mode 100644
index e60125aec21f1f32f054cac51cdfb85368c53895..0000000000000000000000000000000000000000
--- a/spaces/bguberfain/Detic/detic/evaluation/oideval.py
+++ /dev/null
@@ -1,699 +0,0 @@
-# Part of the code is from https://github.com/tensorflow/models/blob/master/research/object_detection/metrics/oid_challenge_evaluation.py
-# Copyright 2018 The TensorFlow Authors. All Rights Reserved.
-# The original code is under Apache License, Version 2.0 (the "License");
-# Part of the code is from https://github.com/lvis-dataset/lvis-api/blob/master/lvis/eval.py
-# Copyright (c) 2019, Agrim Gupta and Ross Girshick
-# Modified by Xingyi Zhou
-# This script re-implement OpenImages evaluation in detectron2
-# The code is from https://github.com/xingyizhou/UniDet/blob/master/projects/UniDet/unidet/evaluation/oideval.py
-# The original code is under Apache-2.0 License
-# Copyright (c) Facebook, Inc. and its affiliates.
-import os 
-import datetime
-import logging
-import itertools
-from collections import OrderedDict
-from collections import defaultdict
-import copy
-import json
-import numpy as np
-import torch
-from tabulate import tabulate
-
-from lvis.lvis import LVIS
-from lvis.results import LVISResults
-
-import pycocotools.mask as mask_utils
-
-from fvcore.common.file_io import PathManager
-import detectron2.utils.comm as comm
-from detectron2.data import MetadataCatalog
-from detectron2.evaluation.coco_evaluation import instances_to_coco_json
-from detectron2.utils.logger import create_small_table
-from detectron2.evaluation import DatasetEvaluator
-
-def compute_average_precision(precision, recall):
-  """Compute Average Precision according to the definition in VOCdevkit.
-  Precision is modified to ensure that it does not decrease as recall
-  decrease.
-  Args:
-    precision: A float [N, 1] numpy array of precisions
-    recall: A float [N, 1] numpy array of recalls
-  Raises:
-    ValueError: if the input is not of the correct format
-  Returns:
-    average_precison: The area under the precision recall curve. NaN if
-      precision and recall are None.
-  """
-  if precision is None:
-    if recall is not None:
-      raise ValueError("If precision is None, recall must also be None")
-    return np.NAN
-
-  if not isinstance(precision, np.ndarray) or not isinstance(
-      recall, np.ndarray):
-    raise ValueError("precision and recall must be numpy array")
-  if precision.dtype != np.float or recall.dtype != np.float:
-    raise ValueError("input must be float numpy array.")
-  if len(precision) != len(recall):
-    raise ValueError("precision and recall must be of the same size.")
-  if not precision.size:
-    return 0.0
-  if np.amin(precision) < 0 or np.amax(precision) > 1:
-    raise ValueError("Precision must be in the range of [0, 1].")
-  if np.amin(recall) < 0 or np.amax(recall) > 1:
-    raise ValueError("recall must be in the range of [0, 1].")
-  if not all(recall[i] <= recall[i + 1] for i in range(len(recall) - 1)):
-    raise ValueError("recall must be a non-decreasing array")
-
-  recall = np.concatenate([[0], recall, [1]])
-  precision = np.concatenate([[0], precision, [0]])
-
-  for i in range(len(precision) - 2, -1, -1):
-    precision[i] = np.maximum(precision[i], precision[i + 1])
-  indices = np.where(recall[1:] != recall[:-1])[0] + 1
-  average_precision = np.sum(
-      (recall[indices] - recall[indices - 1]) * precision[indices])
-  return average_precision
-
-class OIDEval:
-    def __init__(
-        self, lvis_gt, lvis_dt, iou_type="bbox", expand_pred_label=False, 
-        oid_hierarchy_path='./datasets/oid/annotations/challenge-2019-label500-hierarchy.json'):
-        """Constructor for OIDEval.
-        Args:
-            lvis_gt (LVIS class instance, or str containing path of annotation file)
-            lvis_dt (LVISResult class instance, or str containing path of result file,
-            or list of dict)
-            iou_type (str): segm or bbox evaluation
-        """
-        self.logger = logging.getLogger(__name__)
-
-        if iou_type not in ["bbox", "segm"]:
-            raise ValueError("iou_type: {} is not supported.".format(iou_type))
-
-        if isinstance(lvis_gt, LVIS):
-            self.lvis_gt = lvis_gt
-        elif isinstance(lvis_gt, str):
-            self.lvis_gt = LVIS(lvis_gt)
-        else:
-            raise TypeError("Unsupported type {} of lvis_gt.".format(lvis_gt))
-
-        if isinstance(lvis_dt, LVISResults):
-            self.lvis_dt = lvis_dt
-        elif isinstance(lvis_dt, (str, list)):
-            # self.lvis_dt = LVISResults(self.lvis_gt, lvis_dt, max_dets=-1)
-            self.lvis_dt = LVISResults(self.lvis_gt, lvis_dt)
-        else:
-            raise TypeError("Unsupported type {} of lvis_dt.".format(lvis_dt))
-
-        if expand_pred_label:
-            oid_hierarchy = json.load(open(oid_hierarchy_path, 'r'))
-            cat_info = self.lvis_gt.dataset['categories']
-            freebase2id = {x['freebase_id']: x['id'] for x in cat_info}
-            id2freebase = {x['id']: x['freebase_id'] for x in cat_info}
-            id2name = {x['id']: x['name'] for x in cat_info}
-            
-            fas = defaultdict(set)
-            def dfs(hierarchy, cur_id):
-                all_childs = set()
-                all_keyed_child = {}
-                if 'Subcategory' in hierarchy:
-                    for x in hierarchy['Subcategory']:
-                        childs = dfs(x, freebase2id[x['LabelName']])
-                        all_childs.update(childs)
-                if cur_id != -1:
-                    for c in all_childs:
-                        fas[c].add(cur_id)
-                all_childs.add(cur_id)
-                return all_childs
-            dfs(oid_hierarchy, -1)
-            
-            expanded_pred = []
-            id_count = 0
-            for d in self.lvis_dt.dataset['annotations']:
-                cur_id = d['category_id']
-                ids = [cur_id] + [x for x in fas[cur_id]]
-                for cat_id in ids:
-                    new_box = copy.deepcopy(d)
-                    id_count = id_count + 1
-                    new_box['id'] = id_count
-                    new_box['category_id'] = cat_id
-                    expanded_pred.append(new_box)
-
-            print('Expanding original {} preds to {} preds'.format(
-                len(self.lvis_dt.dataset['annotations']),
-                len(expanded_pred)
-                ))
-            self.lvis_dt.dataset['annotations'] = expanded_pred
-            self.lvis_dt._create_index()
-        
-        # per-image per-category evaluation results
-        self.eval_imgs = defaultdict(list)
-        self.eval = {}  # accumulated evaluation results
-        self._gts = defaultdict(list)  # gt for evaluation
-        self._dts = defaultdict(list)  # dt for evaluation
-        self.params = Params(iou_type=iou_type)  # parameters
-        self.results = OrderedDict()
-        self.ious = {}  # ious between all gts and dts
-
-        self.params.img_ids = sorted(self.lvis_gt.get_img_ids())
-        self.params.cat_ids = sorted(self.lvis_gt.get_cat_ids())
-
-    def _to_mask(self, anns, lvis):
-        for ann in anns:
-            rle = lvis.ann_to_rle(ann)
-            ann["segmentation"] = rle
-
-    def _prepare(self):
-        """Prepare self._gts and self._dts for evaluation based on params."""
-
-        cat_ids = self.params.cat_ids if self.params.cat_ids else None
-
-        gts = self.lvis_gt.load_anns(
-            self.lvis_gt.get_ann_ids(img_ids=self.params.img_ids, cat_ids=cat_ids)
-        )
-        dts = self.lvis_dt.load_anns(
-            self.lvis_dt.get_ann_ids(img_ids=self.params.img_ids, cat_ids=cat_ids)
-        )
-        # convert ground truth to mask if iou_type == 'segm'
-        if self.params.iou_type == "segm":
-            self._to_mask(gts, self.lvis_gt)
-            self._to_mask(dts, self.lvis_dt)
-
-        for gt in gts:
-            self._gts[gt["image_id"], gt["category_id"]].append(gt)
-
-        # For federated dataset evaluation we will filter out all dt for an
-        # image which belong to categories not present in gt and not present in
-        # the negative list for an image. In other words detector is not penalized
-        # for categories about which we don't have gt information about their
-        # presence or absence in an image.
-        img_data = self.lvis_gt.load_imgs(ids=self.params.img_ids)
-        # per image map of categories not present in image
-        img_nl = {d["id"]: d["neg_category_ids"] for d in img_data}
-        # per image list of categories present in image
-        img_pl = {d["id"]: d["pos_category_ids"] for d in img_data}
-        # img_pl = defaultdict(set)
-        for ann in gts:
-            # img_pl[ann["image_id"]].add(ann["category_id"])
-            assert ann["category_id"] in img_pl[ann["image_id"]]
-        # print('check pos ids OK.')
-        
-        for dt in dts:
-            img_id, cat_id = dt["image_id"], dt["category_id"]
-            if cat_id not in img_nl[img_id] and cat_id not in img_pl[img_id]:
-                continue
-            self._dts[img_id, cat_id].append(dt)
-
-    def evaluate(self):
-        """
-        Run per image evaluation on given images and store results
-        (a list of dict) in self.eval_imgs.
-        """
-        self.logger.info("Running per image evaluation.")
-        self.logger.info("Evaluate annotation type *{}*".format(self.params.iou_type))
-
-        self.params.img_ids = list(np.unique(self.params.img_ids))
-
-        if self.params.use_cats:
-            cat_ids = self.params.cat_ids
-        else:
-            cat_ids = [-1]
-
-        self._prepare()
-
-        self.ious = {
-            (img_id, cat_id): self.compute_iou(img_id, cat_id)
-            for img_id in self.params.img_ids
-            for cat_id in cat_ids
-        }
-
-        # loop through images, area range, max detection number
-        print('Evaluating ...')
-        self.eval_imgs = [
-            self.evaluate_img_google(img_id, cat_id, area_rng)
-            for cat_id in cat_ids
-            for area_rng in self.params.area_rng
-            for img_id in self.params.img_ids
-        ]
-
-    def _get_gt_dt(self, img_id, cat_id):
-        """Create gt, dt which are list of anns/dets. If use_cats is true
-        only anns/dets corresponding to tuple (img_id, cat_id) will be
-        used. Else, all anns/dets in image are used and cat_id is not used.
-        """
-        if self.params.use_cats:
-            gt = self._gts[img_id, cat_id]
-            dt = self._dts[img_id, cat_id]
-        else:
-            gt = [
-                _ann
-                for _cat_id in self.params.cat_ids
-                for _ann in self._gts[img_id, cat_id]
-            ]
-            dt = [
-                _ann
-                for _cat_id in self.params.cat_ids
-                for _ann in self._dts[img_id, cat_id]
-            ]
-        return gt, dt
-
-    def compute_iou(self, img_id, cat_id):
-        gt, dt = self._get_gt_dt(img_id, cat_id)
-
-        if len(gt) == 0 and len(dt) == 0:
-            return []
-
-        # Sort detections in decreasing order of score.
-        idx = np.argsort([-d["score"] for d in dt], kind="mergesort")
-        dt = [dt[i] for i in idx]
-
-        # iscrowd = [int(False)] * len(gt)
-        iscrowd = [int('iscrowd' in g and g['iscrowd'] > 0) for g in gt]
-
-        if self.params.iou_type == "segm":
-            ann_type = "segmentation"
-        elif self.params.iou_type == "bbox":
-            ann_type = "bbox"
-        else:
-            raise ValueError("Unknown iou_type for iou computation.")
-        gt = [g[ann_type] for g in gt]
-        dt = [d[ann_type] for d in dt]
-
-        # compute iou between each dt and gt region
-        # will return array of shape len(dt), len(gt)
-        ious = mask_utils.iou(dt, gt, iscrowd)
-        return ious
-
-    def evaluate_img_google(self, img_id, cat_id, area_rng):
-        gt, dt = self._get_gt_dt(img_id, cat_id)
-        if len(gt) == 0 and len(dt) == 0:
-            return None
-        
-        if len(dt) == 0:
-            return {
-                "image_id": img_id,
-                "category_id": cat_id,
-                "area_rng": area_rng,
-                "dt_ids": [],
-                "dt_matches": np.array([], dtype=np.int32).reshape(1, -1),
-                "dt_scores": [],
-                "dt_ignore": np.array([], dtype=np.int32).reshape(1, -1),
-                'num_gt': len(gt)
-            }
-
-        no_crowd_inds = [i for i, g in enumerate(gt) \
-            if ('iscrowd' not in g) or g['iscrowd'] == 0]
-        crowd_inds = [i for i, g in enumerate(gt) \
-            if 'iscrowd' in g and g['iscrowd'] == 1]
-        dt_idx = np.argsort([-d["score"] for d in dt], kind="mergesort")
-
-        if len(self.ious[img_id, cat_id]) > 0:
-            ious = self.ious[img_id, cat_id]
-            iou = ious[:, no_crowd_inds]
-            iou = iou[dt_idx]
-            ioa = ious[:, crowd_inds]
-            ioa = ioa[dt_idx]
-        else:
-            iou = np.zeros((len(dt_idx), 0))
-            ioa = np.zeros((len(dt_idx), 0))
-        scores = np.array([dt[i]['score'] for i in dt_idx])
-
-        num_detected_boxes = len(dt)
-        tp_fp_labels = np.zeros(num_detected_boxes, dtype=bool)
-        is_matched_to_group_of = np.zeros(num_detected_boxes, dtype=bool)
-
-        def compute_match_iou(iou):
-            max_overlap_gt_ids = np.argmax(iou, axis=1)
-            is_gt_detected = np.zeros(iou.shape[1], dtype=bool)
-            for i in range(num_detected_boxes):
-                gt_id = max_overlap_gt_ids[i]
-                is_evaluatable = (not tp_fp_labels[i] and
-                                iou[i, gt_id] >= 0.5 and
-                                not is_matched_to_group_of[i])
-                if is_evaluatable:
-                    if not is_gt_detected[gt_id]:
-                        tp_fp_labels[i] = True
-                        is_gt_detected[gt_id] = True
-
-        def compute_match_ioa(ioa):
-            scores_group_of = np.zeros(ioa.shape[1], dtype=float)
-            tp_fp_labels_group_of = np.ones(
-                ioa.shape[1], dtype=float)
-            max_overlap_group_of_gt_ids = np.argmax(ioa, axis=1)
-            for i in range(num_detected_boxes):
-                gt_id = max_overlap_group_of_gt_ids[i]
-                is_evaluatable = (not tp_fp_labels[i] and
-                                ioa[i, gt_id] >= 0.5 and
-                                not is_matched_to_group_of[i])
-                if is_evaluatable:
-                    is_matched_to_group_of[i] = True
-                    scores_group_of[gt_id] = max(scores_group_of[gt_id], scores[i])
-            selector = np.where((scores_group_of > 0) & (tp_fp_labels_group_of > 0))
-            scores_group_of = scores_group_of[selector]
-            tp_fp_labels_group_of = tp_fp_labels_group_of[selector]
-
-            return scores_group_of, tp_fp_labels_group_of
-
-        if iou.shape[1] > 0:
-            compute_match_iou(iou)
-
-        scores_box_group_of = np.ndarray([0], dtype=float)
-        tp_fp_labels_box_group_of = np.ndarray([0], dtype=float)
-
-        if ioa.shape[1] > 0:
-            scores_box_group_of, tp_fp_labels_box_group_of = compute_match_ioa(ioa)
-
-        valid_entries = (~is_matched_to_group_of)
-
-        scores =  np.concatenate(
-            (scores[valid_entries], scores_box_group_of))
-        tp_fps = np.concatenate(
-            (tp_fp_labels[valid_entries].astype(float),
-             tp_fp_labels_box_group_of))
-    
-        return {
-            "image_id": img_id,
-            "category_id": cat_id,
-            "area_rng": area_rng,
-            "dt_matches": np.array([1 if x > 0 else 0 for x in tp_fps], dtype=np.int32).reshape(1, -1),
-            "dt_scores": [x for x in scores],
-            "dt_ignore":  np.array([0 for x in scores], dtype=np.int32).reshape(1, -1),
-            'num_gt': len(gt)
-        }
-
-    def accumulate(self):
-        """Accumulate per image evaluation results and store the result in
-        self.eval.
-        """
-        self.logger.info("Accumulating evaluation results.")
-
-        if not self.eval_imgs:
-            self.logger.warn("Please run evaluate first.")
-
-        if self.params.use_cats:
-            cat_ids = self.params.cat_ids
-        else:
-            cat_ids = [-1]
-
-        num_thrs = 1
-        num_recalls = 1
-
-        num_cats = len(cat_ids)
-        num_area_rngs = 1
-        num_imgs = len(self.params.img_ids)
-
-        # -1 for absent categories
-        precision = -np.ones(
-            (num_thrs, num_recalls, num_cats, num_area_rngs)
-        )
-        recall = -np.ones((num_thrs, num_cats, num_area_rngs))
-
-        # Initialize dt_pointers
-        dt_pointers = {}
-        for cat_idx in range(num_cats):
-            dt_pointers[cat_idx] = {}
-            for area_idx in range(num_area_rngs):
-                dt_pointers[cat_idx][area_idx] = {}
-
-        # Per category evaluation
-        for cat_idx in range(num_cats):
-            Nk = cat_idx * num_area_rngs * num_imgs
-            for area_idx in range(num_area_rngs):
-                Na = area_idx * num_imgs
-                E = [
-                    self.eval_imgs[Nk + Na + img_idx]
-                    for img_idx in range(num_imgs)
-                ]
-                # Remove elements which are None
-                E = [e for e in E if not e is None]
-                if len(E) == 0:
-                    continue
-
-                dt_scores = np.concatenate([e["dt_scores"] for e in E], axis=0)
-                dt_idx = np.argsort(-dt_scores, kind="mergesort")
-                dt_scores = dt_scores[dt_idx]
-                dt_m = np.concatenate([e["dt_matches"] for e in E], axis=1)[:, dt_idx]
-                dt_ig = np.concatenate([e["dt_ignore"] for e in E], axis=1)[:, dt_idx]
-
-                num_gt = sum([e['num_gt'] for e in E])
-                if num_gt == 0:
-                    continue
-
-                tps = np.logical_and(dt_m, np.logical_not(dt_ig))
-                fps = np.logical_and(np.logical_not(dt_m), np.logical_not(dt_ig))
-                tp_sum = np.cumsum(tps, axis=1).astype(dtype=np.float)
-                fp_sum = np.cumsum(fps, axis=1).astype(dtype=np.float)
-
-                dt_pointers[cat_idx][area_idx] = {
-                    "tps": tps,
-                    "fps": fps,
-                }
-
-                for iou_thr_idx, (tp, fp) in enumerate(zip(tp_sum, fp_sum)):
-                    tp = np.array(tp)
-                    fp = np.array(fp)
-                    num_tp = len(tp)
-                    rc = tp / num_gt
-                    
-                    if num_tp:
-                        recall[iou_thr_idx, cat_idx, area_idx] = rc[
-                            -1
-                        ]
-                    else:
-                        recall[iou_thr_idx, cat_idx, area_idx] = 0
-
-                    # np.spacing(1) ~= eps
-                    pr = tp / (fp + tp + np.spacing(1))
-                    pr = pr.tolist()
-
-                    for i in range(num_tp - 1, 0, -1):
-                        if pr[i] > pr[i - 1]:
-                            pr[i - 1] = pr[i]
-
-                    mAP = compute_average_precision(
-                        np.array(pr, np.float).reshape(-1), 
-                        np.array(rc, np.float).reshape(-1))
-                    precision[iou_thr_idx, :, cat_idx, area_idx] = mAP
-
-        self.eval = {
-            "params": self.params,
-            "counts": [num_thrs, num_recalls, num_cats, num_area_rngs],
-            "date": datetime.datetime.now().strftime("%Y-%m-%d %H:%M:%S"),
-            "precision": precision,
-            "recall": recall,
-            "dt_pointers": dt_pointers,
-        }
-
-    def _summarize(self, summary_type):
-        s = self.eval["precision"]
-        if len(s[s > -1]) == 0:
-            mean_s = -1
-        else:
-            mean_s = np.mean(s[s > -1])
-            # print(s.reshape(1, 1, -1, 1))
-        return mean_s
-
-    def summarize(self):
-        """Compute and display summary metrics for evaluation results."""
-        if not self.eval:
-            raise RuntimeError("Please run accumulate() first.")
-
-        max_dets = self.params.max_dets
-        self.results["AP50"] = self._summarize('ap')
-
-    def run(self):
-        """Wrapper function which calculates the results."""
-        self.evaluate()
-        self.accumulate()
-        self.summarize()
-
-    def print_results(self):
-        template = " {:<18} {} @[ IoU={:<9} | area={:>6s} | maxDets={:>3d} catIds={:>3s}] = {:0.3f}"
-
-        for key, value in self.results.items():
-            max_dets = self.params.max_dets
-            if "AP" in key:
-                title = "Average Precision"
-                _type = "(AP)"
-            else:
-                title = "Average Recall"
-                _type = "(AR)"
-
-            if len(key) > 2 and key[2].isdigit():
-                iou_thr = (float(key[2:]) / 100)
-                iou = "{:0.2f}".format(iou_thr)
-            else:
-                iou = "{:0.2f}:{:0.2f}".format(
-                    self.params.iou_thrs[0], self.params.iou_thrs[-1]
-                )
-
-            cat_group_name = "all"
-            area_rng = "all"
-
-            print(template.format(title, _type, iou, area_rng, max_dets, cat_group_name, value))
-
-    def get_results(self):
-        if not self.results:
-            self.logger.warn("results is empty. Call run().")
-        return self.results
-
-
-class Params:
-    def __init__(self, iou_type):
-        self.img_ids = []
-        self.cat_ids = []
-        # np.arange causes trouble.  the data point on arange is slightly
-        # larger than the true value
-        self.iou_thrs = np.linspace(
-            0.5, 0.95, int(np.round((0.95 - 0.5) / 0.05)) + 1, endpoint=True
-        )
-        self.google_style = True
-        # print('Using google style PR curve')
-        self.iou_thrs = self.iou_thrs[:1]
-        self.max_dets = 1000
-
-        self.area_rng = [
-            [0 ** 2, 1e5 ** 2],
-        ]
-        self.area_rng_lbl = ["all"]
-        self.use_cats = 1
-        self.iou_type = iou_type
-
-
-class OIDEvaluator(DatasetEvaluator):
-    def __init__(self, dataset_name, cfg, distributed, output_dir=None):
-        self._distributed = distributed
-        self._output_dir = output_dir
-
-        self._cpu_device = torch.device("cpu")
-        self._logger = logging.getLogger(__name__)
-
-        self._metadata = MetadataCatalog.get(dataset_name)
-        json_file = PathManager.get_local_path(self._metadata.json_file)
-        self._oid_api = LVIS(json_file)
-        # Test set json files do not contain annotations (evaluation must be
-        # performed using the LVIS evaluation server).
-        self._do_evaluation = len(self._oid_api.get_ann_ids()) > 0
-        self._mask_on = cfg.MODEL.MASK_ON
-
-    def reset(self):
-        self._predictions = []
-        self._oid_results = []
-
-    def process(self, inputs, outputs):
-        for input, output in zip(inputs, outputs):
-            prediction = {"image_id": input["image_id"]}
-            instances = output["instances"].to(self._cpu_device)
-            prediction["instances"] = instances_to_coco_json(
-                instances, input["image_id"])
-            self._predictions.append(prediction)
-
-    def evaluate(self):
-        if self._distributed:
-            comm.synchronize()
-            self._predictions = comm.gather(self._predictions, dst=0)
-            self._predictions = list(itertools.chain(*self._predictions))
-
-            if not comm.is_main_process():
-                return
-
-        if len(self._predictions) == 0:
-            self._logger.warning("[LVISEvaluator] Did not receive valid predictions.")
-            return {}
-
-        self._logger.info("Preparing results in the OID format ...")
-        self._oid_results = list(
-            itertools.chain(*[x["instances"] for x in self._predictions]))
-
-        # unmap the category ids for LVIS (from 0-indexed to 1-indexed)
-        for result in self._oid_results:
-            result["category_id"] += 1
-
-        PathManager.mkdirs(self._output_dir)
-        file_path = os.path.join(
-            self._output_dir, "oid_instances_results.json")
-        self._logger.info("Saving results to {}".format(file_path))
-        with PathManager.open(file_path, "w") as f:
-            f.write(json.dumps(self._oid_results))
-            f.flush()
-
-        if not self._do_evaluation:
-            self._logger.info("Annotations are not available for evaluation.")
-            return
-
-        self._logger.info("Evaluating predictions ...")
-        self._results = OrderedDict()
-        res, mAP = _evaluate_predictions_on_oid(
-            self._oid_api,
-            file_path,
-            eval_seg=self._mask_on,
-            class_names=self._metadata.get("thing_classes"),
-        )
-        self._results['bbox'] = res
-        mAP_out_path = os.path.join(self._output_dir, "oid_mAP.npy")
-        self._logger.info('Saving mAP to' + mAP_out_path)
-        np.save(mAP_out_path, mAP)
-        return copy.deepcopy(self._results)
-
-def _evaluate_predictions_on_oid(
-    oid_gt, oid_results_path, eval_seg=False,
-    class_names=None):
-    logger = logging.getLogger(__name__)
-    metrics = ["AP50", "AP50_expand"]
-
-    results = {}
-    oid_eval = OIDEval(oid_gt, oid_results_path, 'bbox', expand_pred_label=False)
-    oid_eval.run()
-    oid_eval.print_results()
-    results["AP50"] = oid_eval.get_results()["AP50"]
-
-    if eval_seg:
-        oid_eval = OIDEval(oid_gt, oid_results_path, 'segm', expand_pred_label=False)
-        oid_eval.run()
-        oid_eval.print_results()
-        results["AP50_segm"] = oid_eval.get_results()["AP50"]
-    else:
-        oid_eval = OIDEval(oid_gt, oid_results_path, 'bbox', expand_pred_label=True)
-        oid_eval.run()
-        oid_eval.print_results()
-        results["AP50_expand"] = oid_eval.get_results()["AP50"]
-
-    mAP = np.zeros(len(class_names)) - 1
-    precisions = oid_eval.eval['precision']
-    assert len(class_names) == precisions.shape[2]
-    results_per_category = []
-    id2apiid = sorted(oid_gt.get_cat_ids())
-    inst_aware_ap, inst_count = 0, 0
-    for idx, name in enumerate(class_names):
-        precision = precisions[:, :, idx, 0]
-        precision = precision[precision > -1]
-        ap = np.mean(precision) if precision.size else float("nan")
-        inst_num = len(oid_gt.get_ann_ids(cat_ids=[id2apiid[idx]]))
-        if inst_num > 0:
-            results_per_category.append(("{} {}".format(
-                name.replace(' ', '_'), 
-                inst_num if inst_num < 1000 else '{:.1f}k'.format(inst_num / 1000)), 
-                float(ap * 100)))
-            inst_aware_ap += inst_num * ap
-            inst_count += inst_num
-            mAP[idx] = ap
-            # logger.info("{} {} {:.2f}".format(name, inst_num, ap * 100))
-    inst_aware_ap = inst_aware_ap * 100 / inst_count
-    N_COLS = min(6, len(results_per_category) * 2)
-    results_flatten = list(itertools.chain(*results_per_category))
-    results_2d = itertools.zip_longest(*[results_flatten[i::N_COLS] for i in range(N_COLS)])
-    table = tabulate(
-        results_2d,
-        tablefmt="pipe",
-        floatfmt=".3f",
-        headers=["category", "AP"] * (N_COLS // 2),
-        numalign="left",
-    )
-    logger.info("Per-category {} AP: \n".format('bbox') + table)
-    logger.info("Instance-aware {} AP: {:.4f}".format('bbox', inst_aware_ap))
-
-    logger.info("Evaluation results for bbox: \n" + \
-        create_small_table(results))
-    return results, mAP
\ No newline at end of file
diff --git a/spaces/bigjoker/stable-diffusion-webui/extensions/deforum/javascript/deforum.js b/spaces/bigjoker/stable-diffusion-webui/extensions/deforum/javascript/deforum.js
deleted file mode 100644
index 889e76f39c937d9eb3b602aa5510d8ac637f5e3c..0000000000000000000000000000000000000000
--- a/spaces/bigjoker/stable-diffusion-webui/extensions/deforum/javascript/deforum.js
+++ /dev/null
@@ -1,21 +0,0 @@
-function submit_deforum(){
-	// alert('Hello, Deforum!')
-    rememberGallerySelection('deforum_gallery')
-    showSubmitButtons('deforum', false)
-
-    var id = randomId()
-    requestProgress(id, gradioApp().getElementById('deforum_gallery_container'), gradioApp().getElementById('deforum_gallery'), function(){
-        showSubmitButtons('deforum', true)
-    })
-
-    var res = create_submit_args(arguments)
-
-    res[0] = id
-	// res[1] = get_tab_index('deforum')
-
-    return res
-}
-
-onUiUpdate(function(){
-    check_gallery('deforum_gallery')
-})
diff --git a/spaces/bigslime/stablediffusion-infinity/js/mode.js b/spaces/bigslime/stablediffusion-infinity/js/mode.js
deleted file mode 100644
index c11264029f5a72c44988ff7318345f3d62a3e28e..0000000000000000000000000000000000000000
--- a/spaces/bigslime/stablediffusion-infinity/js/mode.js
+++ /dev/null
@@ -1,6 +0,0 @@
-function(mode){
-    let app=document.querySelector("gradio-app").shadowRoot;
-    let frame=app.querySelector("#sdinfframe").contentWindow.document;
-    frame.querySelector("#mode").value=mode;
-    return mode;
-}
\ No newline at end of file
diff --git a/spaces/bioriAsaeru/text-to-voice/ATV Flash (black) Version 1.4.1 For Windows Download _VERIFIED_.md b/spaces/bioriAsaeru/text-to-voice/ATV Flash (black) Version 1.4.1 For Windows Download _VERIFIED_.md
deleted file mode 100644
index cd0a955528accbfe5fc2ecf18569f7c7504ef875..0000000000000000000000000000000000000000
--- a/spaces/bioriAsaeru/text-to-voice/ATV Flash (black) Version 1.4.1 For Windows Download _VERIFIED_.md	
+++ /dev/null
@@ -1,6 +0,0 @@
-<h2>ATV Flash (black) Version 1.4.1 For Windows Download</h2><br /><p><b><b>Download Zip</b> &#10003; <a href="https://urloso.com/2uyRPo">https://urloso.com/2uyRPo</a></b></p><br /><br />
-<br />
-Clear caches feature to free up unused disk space Updated many backend components to latest versions Other various fixes and improvements 2.5 Jan-27-2015 NEW! ... Added integrated subtitle downloads from OpenSubtitles.org; Added support for purchased iTunes content (matching iTunes login ... 1.4.1 Mar-30-2012. 4d29de3e1b<br />
-<br />
-<br />
-<p></p>
diff --git a/spaces/bioriAsaeru/text-to-voice/Gheorghe Zamfir Discography Torrent Download.md b/spaces/bioriAsaeru/text-to-voice/Gheorghe Zamfir Discography Torrent Download.md
deleted file mode 100644
index bdc87dfd9312ef7ad572c8540dec8e5ae9adc5b7..0000000000000000000000000000000000000000
--- a/spaces/bioriAsaeru/text-to-voice/Gheorghe Zamfir Discography Torrent Download.md	
+++ /dev/null
@@ -1,12 +0,0 @@
-<h2>Gheorghe Zamfir discography torrent download</h2><br /><p><b><b>Download File</b> &#10027;&#10027;&#10027; <a href="https://urloso.com/2uyQxR">https://urloso.com/2uyQxR</a></b></p><br /><br />
-<br />
-George Zamfira's albums and discography at AllMusic, including all information about the best, old and new albums. All songs by Gheorghe Zamfira, including all albums, songs, lyrics, etc. etc. are presented here.
-All lyrics at AllMusic.
-All songs by Gheorghe Zamfira
-Hymns of life: music for the new film by Luis Buñuel
-Louis Bunuel is one of the most prominent representatives of world surrealism, the creator of such famous films as "Andalusian Dog", "Golden Age", "Milky Way" and others.
-He died quite recently - in August 2009.
-His work has not become outdated and has not lost its relevance. 8a78ff9644<br />
-<br />
-<br />
-<p></p>
diff --git a/spaces/bofenghuang/speech-to-text/run_demo_layout.py b/spaces/bofenghuang/speech-to-text/run_demo_layout.py
deleted file mode 100644
index e371a0a289f07e5b3a7212ebda9e111f7b0722a3..0000000000000000000000000000000000000000
--- a/spaces/bofenghuang/speech-to-text/run_demo_layout.py
+++ /dev/null
@@ -1,314 +0,0 @@
-#! /usr/bin/env python
-# coding=utf-8
-# Copyright 2023 Bofeng Huang
-
-import datetime
-import logging
-import os
-import re
-import warnings
-
-import gradio as gr
-import librosa
-
-# import nltk
-import pandas as pd
-import psutil
-import pytube as pt
-import torch
-
-# import torchaudio
-from transformers import pipeline, Wav2Vec2ProcessorWithLM, AutoModelForCTC
-from transformers.utils.logging import disable_progress_bar
-
-# nltk.download("punkt")
-# from nltk.tokenize import sent_tokenize
-
-warnings.filterwarnings("ignore")
-disable_progress_bar()
-
-DEFAULT_MODEL_NAME = "bofenghuang/asr-wav2vec2-ctc-french"
-SAMPLE_RATE = 16_000
-
-GEN_KWARGS = {
-    "chunk_length_s": 30,
-    "stride_length_s": 5,
-}
-
-logging.basicConfig(
-    format="%(asctime)s [%(levelname)s] [%(name)s] %(message)s",
-    datefmt="%Y-%m-%dT%H:%M:%SZ",
-)
-logger = logging.getLogger(__name__)
-logger.setLevel(logging.DEBUG)
-
-# device = 0 if torch.cuda.is_available() else "cpu"
-device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")
-logger.info(f"Model will be loaded on device `{device}`")
-
-cached_models = {}
-
-
-def _return_yt_html_embed(yt_url):
-    video_id = yt_url.split("?v=")[-1]
-    HTML_str = (
-        f'<center> <iframe width="500" height="320" src="https://www.youtube.com/embed/{video_id}"> </iframe>'
-        " </center>"
-    )
-    return HTML_str
-
-
-def download_audio_from_youtube(yt_url, downloaded_filename="audio.wav"):
-    yt = pt.YouTube(yt_url)
-    stream = yt.streams.filter(only_audio=True)[0]
-    # stream.download(filename="audio.mp3")
-    stream.download(filename=downloaded_filename)
-    return downloaded_filename
-
-
-def download_video_from_youtube(yt_url, downloaded_filename="video.mp4"):
-    yt = pt.YouTube(yt_url)
-    stream = yt.streams.filter(progressive=True, file_extension="mp4").order_by("resolution").desc().first()
-    stream.download(filename=downloaded_filename)
-    logger.info(f"Download YouTube video from {yt_url}")
-    return downloaded_filename
-
-
-def _print_memory_info():
-    memory = psutil.virtual_memory()
-    logger.info(
-        f"Memory info - Free: {memory.available / (1024 ** 3):.2f} Gb, used: {memory.percent}%, total: {memory.total / (1024 ** 3):.2f} Gb"
-    )
-
-
-def _print_cuda_memory_info():
-    used_mem, tot_mem = torch.cuda.mem_get_info()
-    logger.info(
-        f"CUDA memory info - Free: {used_mem / 1024 ** 3:.2f} Gb, used: {(tot_mem - used_mem) / 1024 ** 3:.2f} Gb, total: {tot_mem / 1024 ** 3:.2f} Gb"
-    )
-
-
-def print_memory_info():
-    _print_memory_info()
-    if torch.cuda.is_available():
-        _print_cuda_memory_info()
-
-
-def maybe_load_cached_pipeline(model_name):
-    model = cached_models.get(model_name)
-    if model is None:
-        pipe = pipeline(model=model_name, device=device)
-
-        # model = AutoModelForCTC.from_pretrained(model_name).to(device)
-        # processor = Wav2Vec2ProcessorWithLM.from_pretrained(model_name)
-        # pipe = pipeline(
-        #     "automatic-speech-recognition",
-        #     model=model,
-        #     tokenizer=processor.tokenizer,
-        #     feature_extractor=processor.feature_extractor,
-        #     decoder=processor.decoder,
-        # )
-
-        logger.info(f"`{model_name}` has been loaded on device `{device}`")
-
-        print_memory_info()
-
-        cached_models[model_name] = pipe
-    return model
-
-
-def process_audio_file(audio_file):
-    # waveform, sample_rate = torchaudio.load(audio_file)
-    # waveform = waveform.squeeze(axis=0)  # mono
-    # # resample
-    # if sample_rate != SAMPLE_RATE:
-    #     resampler = torchaudio.transforms.Resample(sample_rate, SAMPLE_RATE)
-    #     waveform = resampler(waveform)
-
-    waveform, sample_rate = librosa.load(audio_file, mono=True)
-
-    # resample
-    if sample_rate != SAMPLE_RATE:
-        waveform = librosa.resample(waveform, orig_sr=sample_rate, target_sr=SAMPLE_RATE)
-
-    return waveform
-
-
-def infer(model, filename, return_df=False):
-    audio_data = process_audio_file(filename)
-
-    text = model(audio_data, **GEN_KWARGS)["text"]
-
-    if return_df:
-        # return pd.DataFrame({"text": sent_tokenize(text)})
-        return pd.DataFrame({"text": [text]})
-    else:
-        return text
-
-
-def transcribe(microphone, file_upload, model_name=DEFAULT_MODEL_NAME):
-    warn_output = ""
-    if (microphone is not None) and (file_upload is not None):
-        warn_output = (
-            "WARNING: You've uploaded an audio file and used the microphone. "
-            "The recorded file from the microphone will be used and the uploaded audio will be discarded.\n"
-        )
-
-    elif (microphone is None) and (file_upload is None):
-        return "ERROR: You have to either use the microphone or upload an audio file"
-
-    file = microphone if microphone is not None else file_upload
-
-    model = maybe_load_cached_pipeline(model_name)
-    text = infer(model, file, return_df=True)
-
-    logger.info(f'Transcription by `{model_name}`:\n{text.to_json(orient="index", force_ascii=False, indent=2)}\n')
-
-    # return warn_output + text
-    return text
-
-
-def yt_transcribe(yt_url, model_name=DEFAULT_MODEL_NAME):
-    # html_embed_str = _return_yt_html_embed(yt_url)
-    audio_file_path = download_audio_from_youtube(yt_url)
-
-    model = maybe_load_cached_pipeline(model_name)
-    text = infer(model, audio_file_path, return_df=True)
-
-    logger.info(
-        f'Transcription by `{model_name}` of "{yt_url}":\n{text.to_json(orient="index", force_ascii=False, indent=2)}\n'
-    )
-
-    # return html_embed_str, text
-    return text
-
-
-def video_transcribe(video_file_path, model_name=DEFAULT_MODEL_NAME):
-    if video_file_path is None:
-        raise ValueError("Failed to transcribe video as no video_file_path has been defined")
-
-    audio_file_path = re.sub(r"\.mp4$", ".wav", video_file_path)
-    os.system(
-        f'ffmpeg -hide_banner -loglevel error -y -i "{video_file_path}" -ar 16000 -ac 1 -c:a pcm_s16le "{audio_file_path}"'
-    )
-
-    model = maybe_load_cached_pipeline(model_name)
-    text = infer(model, audio_file_path, return_df=True)
-
-    logger.info(f'Transcription by `{model_name}`:\n{text.to_json(orient="index", force_ascii=False, indent=2)}\n')
-
-    return text
-
-
-# load default model
-maybe_load_cached_pipeline(DEFAULT_MODEL_NAME)
-
-# default_text_output_df = pd.DataFrame(columns=["start", "end", "text"])
-default_text_output_df = pd.DataFrame(columns=["text"])
-
-with gr.Blocks() as demo:
-    with gr.Tab("Transcribe Audio"):
-        gr.Markdown(
-            f"""
-              <div>
-              <h1 style='text-align: center'>Speech-to-Text in French: Transcribe Audio</h1>
-              </div>
-              Transcribe long-form microphone or audio inputs!
-              
-              Demo uses the fine-tuned wav2vec2 model <a href='https://huggingface.co/{DEFAULT_MODEL_NAME}' target='_blank'><b>{DEFAULT_MODEL_NAME}</b></a> and 🤗 Transformers to transcribe audio files of arbitrary length.
-
-              To achieve improved accuracy and well-punctuated text, please use the [Whisper demo](https://huggingface.co/spaces/bofenghuang/whisper-demo-french).
-          """
-        )
-
-        microphone_input = gr.inputs.Audio(source="microphone", type="filepath", label="Record", optional=True)
-        upload_input = gr.inputs.Audio(source="upload", type="filepath", label="Upload File", optional=True)
-        # with_timestamps_input = gr.Checkbox(label="With timestamps?")
-
-        microphone_transcribe_btn = gr.Button("Transcribe Audio")
-
-        # gr.Markdown('''
-        #     Here you will get generated transcrit.
-        # ''')
-
-        # microphone_text_output = gr.outputs.Textbox(label="Transcription")
-        text_output_df2 = gr.DataFrame(
-            value=default_text_output_df,
-            label="Transcription",
-            row_count=(0, "dynamic"),
-            max_rows=10,
-            wrap=True,
-            overflow_row_behaviour="paginate",
-        )
-
-        microphone_transcribe_btn.click(transcribe, inputs=[microphone_input, upload_input], outputs=text_output_df2)
-
-    # with gr.Tab("Transcribe YouTube"):
-    #     gr.Markdown(
-    #         f"""
-    #           <div>
-    #           <h1 style='text-align: center'>Speech-to-Text in French: Transcribe YouTube</h1>
-    #           </div>
-    #           Transcribe long-form YouTube videos!
-
-    #           Demo uses the fine-tuned checkpoint: <a href='https://huggingface.co/{DEFAULT_MODEL_NAME}' target='_blank'><b>{DEFAULT_MODEL_NAME}</b></a> to transcribe video files of arbitrary length.
-    #       """
-    #     )
-
-    #     yt_link_input2 = gr.inputs.Textbox(lines=1, placeholder="Paste the URL to a YouTube video here", label="YouTube URL")
-    #     with_timestamps_input2 = gr.Checkbox(label="With timestamps?", value=True)
-
-    #     yt_transcribe_btn = gr.Button("Transcribe YouTube")
-
-    #     # yt_text_output = gr.outputs.Textbox(label="Transcription")
-    #     text_output_df3 = gr.DataFrame(
-    #         value=default_text_output_df,
-    #         label="Transcription",
-    #         row_count=(0, "dynamic"),
-    #         max_rows=10,
-    #         wrap=True,
-    #         overflow_row_behaviour="paginate",
-    #     )
-    #     # yt_html_output = gr.outputs.HTML(label="YouTube Page")
-
-    #     yt_transcribe_btn.click(yt_transcribe, inputs=[yt_link_input2, with_timestamps_input2], outputs=[text_output_df3])
-
-    with gr.Tab("Transcribe Video"):
-        gr.Markdown(
-            f"""
-              <div>
-              <h1 style='text-align: center'>Speech-to-Text in French: Transcribe Video</h1>
-              </div>
-              Transcribe long-form YouTube videos or uploaded video inputs!
-              
-              Demo uses the fine-tuned wav2vec2 model <a href='https://huggingface.co/{DEFAULT_MODEL_NAME}' target='_blank'><b>{DEFAULT_MODEL_NAME}</b></a> and 🤗 Transformers to transcribe audio files of arbitrary length.
-
-              To achieve improved accuracy and well-punctuated text, please use the [Whisper demo](https://huggingface.co/spaces/bofenghuang/whisper-demo-french).
-          """
-        )
-
-        yt_link_input = gr.inputs.Textbox(
-            lines=1, placeholder="Paste the URL to a YouTube video here", label="YouTube URL"
-        )
-        download_youtube_btn = gr.Button("Download Youtube video")
-        downloaded_video_output = gr.Video(label="Video file", mirror_webcam=False)
-        download_youtube_btn.click(
-            download_video_from_youtube, inputs=[yt_link_input], outputs=[downloaded_video_output]
-        )
-
-        # with_timestamps_input3 = gr.Checkbox(label="With timestamps?", value=True)
-        video_transcribe_btn = gr.Button("Transcribe video")
-        text_output_df = gr.DataFrame(
-            value=default_text_output_df,
-            label="Transcription",
-            row_count=(0, "dynamic"),
-            max_rows=10,
-            wrap=True,
-            overflow_row_behaviour="paginate",
-        )
-
-        video_transcribe_btn.click(video_transcribe, inputs=[downloaded_video_output], outputs=[text_output_df])
-
-demo.launch(server_name="0.0.0.0", debug=True)
-# demo.launch(server_name="0.0.0.0", debug=True, share=True)
-# demo.launch(enable_queue=True)
diff --git a/spaces/bookbot/Grad-TTS-Weildan-Playground/Grad-TTS/hifi-gan/README.md b/spaces/bookbot/Grad-TTS-Weildan-Playground/Grad-TTS/hifi-gan/README.md
deleted file mode 100644
index 4c63381f7c41874fe97c13f40b92d6bb9413e751..0000000000000000000000000000000000000000
--- a/spaces/bookbot/Grad-TTS-Weildan-Playground/Grad-TTS/hifi-gan/README.md
+++ /dev/null
@@ -1,105 +0,0 @@
-# HiFi-GAN: Generative Adversarial Networks for Efficient and High Fidelity Speech Synthesis
-
-### Jungil Kong, Jaehyeon Kim, Jaekyoung Bae
-
-In our [paper](https://arxiv.org/abs/2010.05646), 
-we proposed HiFi-GAN: a GAN-based model capable of generating high fidelity speech efficiently.<br/>
-We provide our implementation and pretrained models as open source in this repository.
-
-**Abstract :**
-Several recent work on speech synthesis have employed generative adversarial networks (GANs) to produce raw waveforms. 
-Although such methods improve the sampling efficiency and memory usage, 
-their sample quality has not yet reached that of autoregressive and flow-based generative models. 
-In this work, we propose HiFi-GAN, which achieves both efficient and high-fidelity speech synthesis. 
-As speech audio consists of sinusoidal signals with various periods, 
-we demonstrate that modeling periodic patterns of an audio is crucial for enhancing sample quality. 
-A subjective human evaluation (mean opinion score, MOS) of a single speaker dataset indicates that our proposed method 
-demonstrates similarity to human quality while generating 22.05 kHz high-fidelity audio 167.9 times faster than 
-real-time on a single V100 GPU. We further show the generality of HiFi-GAN to the mel-spectrogram inversion of unseen 
-speakers and end-to-end speech synthesis. Finally, a small footprint version of HiFi-GAN generates samples 13.4 times 
-faster than real-time on CPU with comparable quality to an autoregressive counterpart.
-
-Visit our [demo website](https://jik876.github.io/hifi-gan-demo/) for audio samples.
-
-
-## Pre-requisites
-1. Python >= 3.6
-2. Clone this repository.
-3. Install python requirements. Please refer [requirements.txt](requirements.txt)
-4. Download and extract the [LJ Speech dataset](https://keithito.com/LJ-Speech-Dataset/).
-And move all wav files to `LJSpeech-1.1/wavs`
-
-
-## Training
-```
-python train.py --config config_v1.json
-```
-To train V2 or V3 Generator, replace `config_v1.json` with `config_v2.json` or `config_v3.json`.<br>
-Checkpoints and copy of the configuration file are saved in `cp_hifigan` directory by default.<br>
-You can change the path by adding `--checkpoint_path` option.
-
-Validation loss during training with V1 generator.<br>
-![validation loss](./validation_loss.png)
-
-## Pretrained Model
-You can also use pretrained models we provide.<br/>
-[Download pretrained models](https://drive.google.com/drive/folders/1-eEYTB5Av9jNql0WGBlRoi-WH2J7bp5Y?usp=sharing)<br/> 
-Details of each folder are as in follows:
-
-|Folder Name|Generator|Dataset|Fine-Tuned|
-|------|---|---|---|
-|LJ_V1|V1|LJSpeech|No|
-|LJ_V2|V2|LJSpeech|No|
-|LJ_V3|V3|LJSpeech|No|
-|LJ_FT_T2_V1|V1|LJSpeech|Yes ([Tacotron2](https://github.com/NVIDIA/tacotron2))|
-|LJ_FT_T2_V2|V2|LJSpeech|Yes ([Tacotron2](https://github.com/NVIDIA/tacotron2))|
-|LJ_FT_T2_V3|V3|LJSpeech|Yes ([Tacotron2](https://github.com/NVIDIA/tacotron2))|
-|VCTK_V1|V1|VCTK|No|
-|VCTK_V2|V2|VCTK|No|
-|VCTK_V3|V3|VCTK|No|
-|UNIVERSAL_V1|V1|Universal|No|
-
-We provide the universal model with discriminator weights that can be used as a base for transfer learning to other datasets.
-
-## Fine-Tuning
-1. Generate mel-spectrograms in numpy format using [Tacotron2](https://github.com/NVIDIA/tacotron2) with teacher-forcing.<br/>
-The file name of the generated mel-spectrogram should match the audio file and the extension should be `.npy`.<br/>
-Example:
-    ```
-    Audio File : LJ001-0001.wav
-    Mel-Spectrogram File : LJ001-0001.npy
-    ```
-2. Create `ft_dataset` folder and copy the generated mel-spectrogram files into it.<br/>
-3. Run the following command.
-    ```
-    python train.py --fine_tuning True --config config_v1.json
-    ```
-    For other command line options, please refer to the training section.
-
-
-## Inference from wav file
-1. Make `test_files` directory and copy wav files into the directory.
-2. Run the following command.
-    ```
-    python inference.py --checkpoint_file [generator checkpoint file path]
-    ```
-Generated wav files are saved in `generated_files` by default.<br>
-You can change the path by adding `--output_dir` option.
-
-
-## Inference for end-to-end speech synthesis
-1. Make `test_mel_files` directory and copy generated mel-spectrogram files into the directory.<br>
-You can generate mel-spectrograms using [Tacotron2](https://github.com/NVIDIA/tacotron2), 
-[Glow-TTS](https://github.com/jaywalnut310/glow-tts) and so forth.
-2. Run the following command.
-    ```
-    python inference_e2e.py --checkpoint_file [generator checkpoint file path]
-    ```
-Generated wav files are saved in `generated_files_from_mel` by default.<br>
-You can change the path by adding `--output_dir` option.
-
-
-## Acknowledgements
-We referred to [WaveGlow](https://github.com/NVIDIA/waveglow), [MelGAN](https://github.com/descriptinc/melgan-neurips) 
-and [Tacotron2](https://github.com/NVIDIA/tacotron2) to implement this.
-
diff --git a/spaces/brainblow/AudioCreator_Music-Audio_Generation/audiocraft/optim/dadam.py b/spaces/brainblow/AudioCreator_Music-Audio_Generation/audiocraft/optim/dadam.py
deleted file mode 100644
index a84402f744867610180b9576b2ee3302501fd035..0000000000000000000000000000000000000000
--- a/spaces/brainblow/AudioCreator_Music-Audio_Generation/audiocraft/optim/dadam.py
+++ /dev/null
@@ -1,252 +0,0 @@
-# Copyright (c) Meta Platforms, Inc. and affiliates.
-# All rights reserved.
-#
-# This source code is licensed under the license found in the
-# LICENSE file in the root directory of this source tree.
-
-import logging
-from typing import TYPE_CHECKING, Any
-
-import torch
-import torch.optim
-import torch.distributed as dist
-
-if TYPE_CHECKING:
-    from torch.optim.optimizer import _params_t
-else:
-    _params_t = Any
-
-
-logger = logging.getLogger(__name__)
-
-
-def to_real(x):
-    if torch.is_complex(x):
-        return x.real
-    else:
-        return x
-
-
-class DAdaptAdam(torch.optim.Optimizer):
-    """Adam with D-Adaptation automatic step-sizes.
-    Leave LR set to 1 unless you encounter instability.
-
-    Args:
-        params (iterable):
-            Iterable of parameters to optimize or dicts defining parameter groups.
-        lr (float):
-            Learning rate adjustment parameter. Increases or decreases the D-adapted learning rate.
-        betas (tuple[float, float], optional): coefficients used for computing
-            running averages of gradient and its square (default: (0.9, 0.999))
-        momentum (float):
-            Momentum value in  the range [0,1) (default: 0.9).
-        eps (float):
-            Term added to the denominator outside of the root operation to improve numerical stability. (default: 1e-8).
-        weight_decay (float):
-            Weight decay, i.e. a L2 penalty (default: 0).
-        log_every (int):
-            Log using print every k steps, default 0 (no logging).
-        decouple (boolean):
-            Use AdamW style decoupled weight decay
-        d0 (float):
-            Initial D estimate for D-adaptation (default 1e-6). Rarely needs changing.
-        growth_rate (float):
-            prevent the D estimate from growing faster than this multiplicative rate.
-            Default is inf, for unrestricted. Values like 1.02 give a kind of learning
-            rate warmup effect.
-        fsdp_in_use (bool):
-            If you're using sharded parameters, this should be set to True. The optimizer
-            will attempt to auto-detect this, but if you're using an implementation other
-            than PyTorch's builtin version, the auto-detection won't work.
-    """
-    def __init__(self, params, lr=1.0,
-                 betas=(0.9, 0.999),
-                 eps=1e-8,
-                 weight_decay=0,
-                 log_every=0,
-                 decouple=True,
-                 d0=1e-6,
-                 growth_rate=float('inf')):
-        if not 0.0 < d0:
-            raise ValueError("Invalid d0 value: {}".format(d0))
-        if not 0.0 < lr:
-            raise ValueError("Invalid learning rate: {}".format(lr))
-        if not 0.0 < eps:
-            raise ValueError("Invalid epsilon value: {}".format(eps))
-        if not 0.0 <= betas[0] < 1.0:
-            raise ValueError("Invalid beta parameter at index 0: {}".format(betas[0]))
-        if not 0.0 <= betas[1] < 1.0:
-            raise ValueError("Invalid beta parameter at index 1: {}".format(betas[1]))
-
-        if decouple:
-            logger.info("Using decoupled weight decay")
-
-        from .fsdp import is_fsdp_used
-        fsdp_in_use = is_fsdp_used()
-        defaults = dict(lr=lr, betas=betas, eps=eps,
-                        weight_decay=weight_decay,
-                        d=d0,
-                        k=0,
-                        gsq_weighted=0.0,
-                        log_every=log_every,
-                        decouple=decouple,
-                        growth_rate=growth_rate,
-                        fsdp_in_use=fsdp_in_use)
-
-        super().__init__(params, defaults)
-
-    @property
-    def supports_memory_efficient_fp16(self):
-        return False
-
-    @property
-    def supports_flat_params(self):
-        return True
-
-    def step(self, closure=None):
-        """Performs a single optimization step.
-
-        Args:
-            closure (callable, optional): A closure that reevaluates the model
-                and returns the loss.
-        """
-        loss = None
-        if closure is not None:
-            loss = closure()
-
-        g_sq = 0.0
-        sksq_weighted = 0.0
-        sk_l1 = 0.0
-
-        lr = max(group['lr'] for group in self.param_groups)
-
-        group = self.param_groups[0]
-        gsq_weighted = group['gsq_weighted']
-        d = group['d']
-        dlr = d*lr
-
-        growth_rate = group['growth_rate']
-        decouple = group['decouple']
-        fsdp_in_use = group['fsdp_in_use']
-        log_every = group['log_every']
-
-        beta1, beta2 = group['betas']
-
-        for group in self.param_groups:
-            group_lr = group['lr']
-            decay = group['weight_decay']
-            k = group['k']
-            eps = group['eps']
-
-            if group_lr not in [lr, 0.0]:
-                raise RuntimeError("Setting different lr values in different parameter "
-                                   "groups is only supported for values of 0")
-
-            for p in group['params']:
-                if p.grad is None:
-                    continue
-                if hasattr(p, "_fsdp_flattened"):
-                    fsdp_in_use = True
-                grad = p.grad.data
-
-                # Apply weight decay (coupled variant)
-                if decay != 0 and not decouple:
-                    grad.add_(p.data, alpha=decay)
-
-                state = self.state[p]
-
-                # State initialization
-                if 'step' not in state:
-                    state['step'] = 0
-                    state['s'] = torch.zeros_like(p.data, memory_format=torch.preserve_format).detach()
-                    # Exponential moving average of gradient values
-                    state['exp_avg'] = torch.zeros_like(p.data, memory_format=torch.preserve_format).detach()
-                    # Exponential moving average of squared gradient values
-                    state['exp_avg_sq'] = torch.zeros_like(
-                        to_real(p.data), memory_format=torch.preserve_format).detach()
-
-                exp_avg, exp_avg_sq = state['exp_avg'], state['exp_avg_sq']
-
-                grad_grad = to_real(grad * grad.conj())
-
-                # Adam EMA updates
-                if group_lr > 0:
-                    exp_avg.mul_(beta1).add_(grad, alpha=dlr*(1-beta1))
-                    exp_avg_sq.mul_(beta2).add_(grad_grad, alpha=1-beta2)
-
-                    denom = exp_avg_sq.sqrt().add_(eps)
-
-                    g_sq += grad_grad.div_(denom).sum().item()
-
-                    s = state['s']
-                    s.mul_(beta2).add_(grad, alpha=dlr*(1-beta2))
-                    sksq_weighted += to_real(s * s.conj()).div_(denom).sum().item()
-                    sk_l1 += s.abs().sum().item()
-
-            ######
-
-        gsq_weighted = beta2*gsq_weighted + g_sq*(dlr**2)*(1-beta2)
-        d_hat = d
-
-        # if we have not done any progres, return
-        # if we have any gradients available, will have sk_l1 > 0 (unless \|g\|=0)
-        if sk_l1 == 0:
-            return loss
-
-        if lr > 0.0:
-            if fsdp_in_use:
-                dist_tensor = torch.zeros(3, device='cuda')
-                dist_tensor[0] = sksq_weighted
-                dist_tensor[1] = gsq_weighted
-                dist_tensor[2] = sk_l1
-                dist.all_reduce(dist_tensor, op=dist.ReduceOp.SUM)
-                global_sksq_weighted = dist_tensor[0]
-                global_gsq_weighted = dist_tensor[1]
-                global_sk_l1 = dist_tensor[2]
-            else:
-                global_sksq_weighted = sksq_weighted
-                global_gsq_weighted = gsq_weighted
-                global_sk_l1 = sk_l1
-
-            d_hat = (global_sksq_weighted/(1-beta2) - global_gsq_weighted)/global_sk_l1
-            d = max(d, min(d_hat, d*growth_rate))
-
-        if log_every > 0 and k % log_every == 0:
-            logger.info(
-                f"(k={k}) dlr: {dlr:1.1e} d_hat: {d_hat:1.1e}, d: {d:1.8}. "
-                f"sksq_weighted={global_sksq_weighted:1.1e} gsq_weighted={global_gsq_weighted:1.1e} "
-                f"sk_l1={global_sk_l1:1.1e}{' (FSDP)' if fsdp_in_use else ''}")
-
-        for group in self.param_groups:
-            group['gsq_weighted'] = gsq_weighted
-            group['d'] = d
-
-            group_lr = group['lr']
-            decay = group['weight_decay']
-            k = group['k']
-            eps = group['eps']
-
-            for p in group['params']:
-                if p.grad is None:
-                    continue
-                grad = p.grad.data
-
-                state = self.state[p]
-
-                exp_avg, exp_avg_sq = state['exp_avg'], state['exp_avg_sq']
-
-                state['step'] += 1
-
-                denom = exp_avg_sq.sqrt().add_(eps)
-                denom = denom.type(p.type())
-
-                # Apply weight decay (decoupled variant)
-                if decay != 0 and decouple and group_lr > 0:
-                    p.data.add_(p.data, alpha=-decay * dlr)
-
-                # Take step
-                p.data.addcdiv_(exp_avg, denom, value=-1)
-
-            group['k'] = k + 1
-
-        return loss
diff --git a/spaces/brjathu/HMR2.0/demo.py b/spaces/brjathu/HMR2.0/demo.py
deleted file mode 100644
index ef6c63347e61f4064975d2f6c2d540f44be78c8b..0000000000000000000000000000000000000000
--- a/spaces/brjathu/HMR2.0/demo.py
+++ /dev/null
@@ -1,130 +0,0 @@
-from pathlib import Path
-import torch
-import argparse
-import os
-import cv2
-import numpy as np
-
-from hmr2.configs import get_config
-from hmr2.models import HMR2
-from hmr2.utils import recursive_to
-from hmr2.datasets.vitdet_dataset import ViTDetDataset, DEFAULT_MEAN, DEFAULT_STD
-from hmr2.utils.renderer import Renderer, cam_crop_to_full
-
-LIGHT_BLUE=(0.65098039,  0.74117647,  0.85882353)
-# DEFAULT_CHECKPOINT='logs/train/multiruns/20b1_mix11_a1/0/checkpoints/epoch=30-step=1000000.ckpt'
-DEFAULT_CHECKPOINT='logs/train/multiruns/hmr2/0/checkpoints/epoch=35-step=1000000.ckpt'
-parser = argparse.ArgumentParser(description='HMR2 demo code')
-parser.add_argument('--checkpoint', type=str, default=DEFAULT_CHECKPOINT, help='Path to pretrained model checkpoint')
-parser.add_argument('--img_folder', type=str, default='example_data/images', help='Folder with input images')
-parser.add_argument('--out_folder', type=str, default='demo_out', help='Output folder to save rendered results')
-parser.add_argument('--side_view', dest='side_view', action='store_true', default=False, help='If set, render side view also')
-parser.add_argument('--batch_size', type=int, default=1, help='Batch size for inference/fitting')
-
-args = parser.parse_args()
-
-# Setup HMR2.0 model
-device = torch.device('cuda') if torch.cuda.is_available() else torch.device('cpu')
-model_cfg = str(Path(args.checkpoint).parent.parent / 'model_config.yaml')
-model_cfg = get_config(model_cfg)
-model = HMR2.load_from_checkpoint(args.checkpoint, strict=False, cfg=model_cfg).to(device)
-model.eval()
-
-# Load detector
-from detectron2.config import LazyConfig
-from hmr2.utils.utils_detectron2 import DefaultPredictor_Lazy
-detectron2_cfg = LazyConfig.load(f"vendor/detectron2/projects/ViTDet/configs/COCO/cascade_mask_rcnn_vitdet_h_75ep.py")
-detectron2_cfg.train.init_checkpoint = "https://dl.fbaipublicfiles.com/detectron2/ViTDet/COCO/cascade_mask_rcnn_vitdet_h/f328730692/model_final_f05665.pkl"
-for i in range(3):
-    detectron2_cfg.model.roi_heads.box_predictors[i].test_score_thresh = 0.25
-detector = DefaultPredictor_Lazy(detectron2_cfg)
-
-# Setup the renderer
-renderer = Renderer(model_cfg, faces=model.smpl.faces)
-
-# Make output directory if it does not exist
-os.makedirs(args.out_folder, exist_ok=True)
-
-# Iterate over all images in folder
-for img_path in Path(args.img_folder).glob('*.png'):
-    img_cv2 = cv2.imread(str(img_path), cv2.IMREAD_COLOR)
-
-    # Detect humans in image
-    det_out = detector(img_cv2)
-
-    det_instances = det_out['instances']
-    valid_idx = (det_instances.pred_classes==0) & (det_instances.scores > 0.5)
-    boxes=det_instances.pred_boxes.tensor[valid_idx].cpu().numpy()
-
-    # Run HMR2.0 on all detected humans
-    dataset = ViTDetDataset(model_cfg, img_cv2.copy(), boxes)
-    dataloader = torch.utils.data.DataLoader(dataset, batch_size=8, shuffle=False, num_workers=0)
-
-
-    all_verts = []
-    all_cam_t = []
-
-    for batch in dataloader:
-        batch = recursive_to(batch, device)
-        with torch.no_grad():
-            out = model(batch)
-
-        pred_cam = out['pred_cam']
-        box_center = batch["box_center"].float()
-        box_size = batch["box_size"].float()
-        img_size = batch["img_size"].float()
-        render_size = img_size
-        pred_cam_t = cam_crop_to_full(pred_cam, box_center, box_size, render_size).detach().cpu().numpy()
-
-        # Render the result
-        batch_size = batch['img'].shape[0]
-        for n in range(batch_size):
-            # Get filename from path img_path
-            img_fn, _ = os.path.splitext(os.path.basename(img_path))
-            person_id = int(batch['personid'][n])
-            white_img = (torch.ones_like(batch['img'][n]).cpu() - DEFAULT_MEAN[:,None,None]/255) / (DEFAULT_STD[:,None,None]/255)
-            input_patch = batch['img'][n].cpu() * (DEFAULT_STD[:,None,None]/255) + (DEFAULT_MEAN[:,None,None]/255)
-            input_patch = input_patch.permute(1,2,0).numpy()
-            
-            regression_img = renderer(out['pred_vertices'][n].detach().cpu().numpy(),
-                                    out['pred_cam_t'][n].detach().cpu().numpy(),
-                                    batch['img'][n],
-                                    mesh_base_color=LIGHT_BLUE,
-                                    scene_bg_color=(1, 1, 1),
-                                    )
-
-            if args.side_view:
-                side_img = renderer(out['pred_vertices'][n].detach().cpu().numpy(),
-                                        out['pred_cam_t'][n].detach().cpu().numpy(),
-                                        white_img,
-                                        mesh_base_color=LIGHT_BLUE,
-                                        scene_bg_color=(1, 1, 1),
-                                        side_view=True)
-                final_img = np.concatenate([input_patch, regression_img, side_img], axis=1)
-            else:
-                final_img = np.concatenate([input_patch, regression_img], axis=1)
-
-
-            verts = out['pred_vertices'][n].detach().cpu().numpy()
-            cam_t = pred_cam_t[n]
-
-            all_verts.append(verts)
-            all_cam_t.append(cam_t)
-
-    misc_args = dict(
-        mesh_base_color=LIGHT_BLUE,
-        scene_bg_color=(1, 1, 1),
-    )
-
-    # Render front view
-    if len(all_verts) > 0:
-        cam_view = renderer.render_rgba_multiple(all_verts, cam_t=all_cam_t, render_res=render_size[n], **misc_args)
-
-        # Overlay image
-        input_img = img_cv2.astype(np.float32)[:,:,::-1]/255.0
-        input_img = np.concatenate([input_img, np.ones_like(input_img[:,:,:1])], axis=2) # Add alpha channel
-        input_img_overlay = input_img[:,:,:3] * (1-cam_view[:,:,3:]) + cam_view[:,:,:3] * cam_view[:,:,3:]
-
-
-        # cv2.imwrite(os.path.join(args.out_folder, f'{img_fn}_{person_id}.jpg'), 255*final_img[:, :, ::-1])
-        cv2.imwrite(os.path.join(args.out_folder, f'rend_{img_fn}.jpg'), 255*input_img_overlay[:, :, ::-1])
diff --git a/spaces/brjathu/HMR2.0/vendor/detectron2/detectron2/modeling/roi_heads/rotated_fast_rcnn.py b/spaces/brjathu/HMR2.0/vendor/detectron2/detectron2/modeling/roi_heads/rotated_fast_rcnn.py
deleted file mode 100644
index 1e7bfabdedff5c5a826d8d4f551ea96b541f2cb6..0000000000000000000000000000000000000000
--- a/spaces/brjathu/HMR2.0/vendor/detectron2/detectron2/modeling/roi_heads/rotated_fast_rcnn.py
+++ /dev/null
@@ -1,271 +0,0 @@
-# Copyright (c) Facebook, Inc. and its affiliates.
-import logging
-import numpy as np
-import torch
-
-from detectron2.config import configurable
-from detectron2.layers import ShapeSpec, batched_nms_rotated
-from detectron2.structures import Instances, RotatedBoxes, pairwise_iou_rotated
-from detectron2.utils.events import get_event_storage
-
-from ..box_regression import Box2BoxTransformRotated
-from ..poolers import ROIPooler
-from ..proposal_generator.proposal_utils import add_ground_truth_to_proposals
-from .box_head import build_box_head
-from .fast_rcnn import FastRCNNOutputLayers
-from .roi_heads import ROI_HEADS_REGISTRY, StandardROIHeads
-
-logger = logging.getLogger(__name__)
-
-"""
-Shape shorthand in this module:
-
-    N: number of images in the minibatch
-    R: number of ROIs, combined over all images, in the minibatch
-    Ri: number of ROIs in image i
-    K: number of foreground classes. E.g.,there are 80 foreground classes in COCO.
-
-Naming convention:
-
-    deltas: refers to the 5-d (dx, dy, dw, dh, da) deltas that parameterize the box2box
-    transform (see :class:`box_regression.Box2BoxTransformRotated`).
-
-    pred_class_logits: predicted class scores in [-inf, +inf]; use
-        softmax(pred_class_logits) to estimate P(class).
-
-    gt_classes: ground-truth classification labels in [0, K], where [0, K) represent
-        foreground object classes and K represents the background class.
-
-    pred_proposal_deltas: predicted rotated box2box transform deltas for transforming proposals
-        to detection box predictions.
-
-    gt_proposal_deltas: ground-truth rotated box2box transform deltas
-"""
-
-
-def fast_rcnn_inference_rotated(
-    boxes, scores, image_shapes, score_thresh, nms_thresh, topk_per_image
-):
-    """
-    Call `fast_rcnn_inference_single_image_rotated` for all images.
-
-    Args:
-        boxes (list[Tensor]): A list of Tensors of predicted class-specific or class-agnostic
-            boxes for each image. Element i has shape (Ri, K * 5) if doing
-            class-specific regression, or (Ri, 5) if doing class-agnostic
-            regression, where Ri is the number of predicted objects for image i.
-            This is compatible with the output of :meth:`FastRCNNOutputLayers.predict_boxes`.
-        scores (list[Tensor]): A list of Tensors of predicted class scores for each image.
-            Element i has shape (Ri, K + 1), where Ri is the number of predicted objects
-            for image i. Compatible with the output of :meth:`FastRCNNOutputLayers.predict_probs`.
-        image_shapes (list[tuple]): A list of (width, height) tuples for each image in the batch.
-        score_thresh (float): Only return detections with a confidence score exceeding this
-            threshold.
-        nms_thresh (float):  The threshold to use for box non-maximum suppression. Value in [0, 1].
-        topk_per_image (int): The number of top scoring detections to return. Set < 0 to return
-            all detections.
-
-    Returns:
-        instances: (list[Instances]): A list of N instances, one for each image in the batch,
-            that stores the topk most confidence detections.
-        kept_indices: (list[Tensor]): A list of 1D tensor of length of N, each element indicates
-            the corresponding boxes/scores index in [0, Ri) from the input, for image i.
-    """
-    result_per_image = [
-        fast_rcnn_inference_single_image_rotated(
-            boxes_per_image, scores_per_image, image_shape, score_thresh, nms_thresh, topk_per_image
-        )
-        for scores_per_image, boxes_per_image, image_shape in zip(scores, boxes, image_shapes)
-    ]
-    return [x[0] for x in result_per_image], [x[1] for x in result_per_image]
-
-
-@torch.no_grad()
-def fast_rcnn_inference_single_image_rotated(
-    boxes, scores, image_shape, score_thresh, nms_thresh, topk_per_image
-):
-    """
-    Single-image inference. Return rotated bounding-box detection results by thresholding
-    on scores and applying rotated non-maximum suppression (Rotated NMS).
-
-    Args:
-        Same as `fast_rcnn_inference_rotated`, but with rotated boxes, scores, and image shapes
-        per image.
-
-    Returns:
-        Same as `fast_rcnn_inference_rotated`, but for only one image.
-    """
-    valid_mask = torch.isfinite(boxes).all(dim=1) & torch.isfinite(scores).all(dim=1)
-    if not valid_mask.all():
-        boxes = boxes[valid_mask]
-        scores = scores[valid_mask]
-
-    B = 5  # box dimension
-    scores = scores[:, :-1]
-    num_bbox_reg_classes = boxes.shape[1] // B
-    # Convert to Boxes to use the `clip` function ...
-    boxes = RotatedBoxes(boxes.reshape(-1, B))
-    boxes.clip(image_shape)
-    boxes = boxes.tensor.view(-1, num_bbox_reg_classes, B)  # R x C x B
-    # Filter results based on detection scores
-    filter_mask = scores > score_thresh  # R x K
-    # R' x 2. First column contains indices of the R predictions;
-    # Second column contains indices of classes.
-    filter_inds = filter_mask.nonzero()
-    if num_bbox_reg_classes == 1:
-        boxes = boxes[filter_inds[:, 0], 0]
-    else:
-        boxes = boxes[filter_mask]
-    scores = scores[filter_mask]
-
-    # Apply per-class Rotated NMS
-    keep = batched_nms_rotated(boxes, scores, filter_inds[:, 1], nms_thresh)
-    if topk_per_image >= 0:
-        keep = keep[:topk_per_image]
-    boxes, scores, filter_inds = boxes[keep], scores[keep], filter_inds[keep]
-
-    result = Instances(image_shape)
-    result.pred_boxes = RotatedBoxes(boxes)
-    result.scores = scores
-    result.pred_classes = filter_inds[:, 1]
-
-    return result, filter_inds[:, 0]
-
-
-class RotatedFastRCNNOutputLayers(FastRCNNOutputLayers):
-    """
-    Two linear layers for predicting Rotated Fast R-CNN outputs.
-    """
-
-    @classmethod
-    def from_config(cls, cfg, input_shape):
-        args = super().from_config(cfg, input_shape)
-        args["box2box_transform"] = Box2BoxTransformRotated(
-            weights=cfg.MODEL.ROI_BOX_HEAD.BBOX_REG_WEIGHTS
-        )
-        return args
-
-    def inference(self, predictions, proposals):
-        """
-        Returns:
-            list[Instances]: same as `fast_rcnn_inference_rotated`.
-            list[Tensor]: same as `fast_rcnn_inference_rotated`.
-        """
-        boxes = self.predict_boxes(predictions, proposals)
-        scores = self.predict_probs(predictions, proposals)
-        image_shapes = [x.image_size for x in proposals]
-
-        return fast_rcnn_inference_rotated(
-            boxes,
-            scores,
-            image_shapes,
-            self.test_score_thresh,
-            self.test_nms_thresh,
-            self.test_topk_per_image,
-        )
-
-
-@ROI_HEADS_REGISTRY.register()
-class RROIHeads(StandardROIHeads):
-    """
-    This class is used by Rotated Fast R-CNN to detect rotated boxes.
-    For now, it only supports box predictions but not mask or keypoints.
-    """
-
-    @configurable
-    def __init__(self, **kwargs):
-        """
-        NOTE: this interface is experimental.
-        """
-        super().__init__(**kwargs)
-        assert (
-            not self.mask_on and not self.keypoint_on
-        ), "Mask/Keypoints not supported in Rotated ROIHeads."
-        assert not self.train_on_pred_boxes, "train_on_pred_boxes not implemented for RROIHeads!"
-
-    @classmethod
-    def _init_box_head(cls, cfg, input_shape):
-        # fmt: off
-        in_features       = cfg.MODEL.ROI_HEADS.IN_FEATURES
-        pooler_resolution = cfg.MODEL.ROI_BOX_HEAD.POOLER_RESOLUTION
-        pooler_scales     = tuple(1.0 / input_shape[k].stride for k in in_features)
-        sampling_ratio    = cfg.MODEL.ROI_BOX_HEAD.POOLER_SAMPLING_RATIO
-        pooler_type       = cfg.MODEL.ROI_BOX_HEAD.POOLER_TYPE
-        # fmt: on
-        assert pooler_type in ["ROIAlignRotated"], pooler_type
-        # assume all channel counts are equal
-        in_channels = [input_shape[f].channels for f in in_features][0]
-
-        box_pooler = ROIPooler(
-            output_size=pooler_resolution,
-            scales=pooler_scales,
-            sampling_ratio=sampling_ratio,
-            pooler_type=pooler_type,
-        )
-        box_head = build_box_head(
-            cfg, ShapeSpec(channels=in_channels, height=pooler_resolution, width=pooler_resolution)
-        )
-        # This line is the only difference v.s. StandardROIHeads
-        box_predictor = RotatedFastRCNNOutputLayers(cfg, box_head.output_shape)
-        return {
-            "box_in_features": in_features,
-            "box_pooler": box_pooler,
-            "box_head": box_head,
-            "box_predictor": box_predictor,
-        }
-
-    @torch.no_grad()
-    def label_and_sample_proposals(self, proposals, targets):
-        """
-        Prepare some proposals to be used to train the RROI heads.
-        It performs box matching between `proposals` and `targets`, and assigns
-        training labels to the proposals.
-        It returns `self.batch_size_per_image` random samples from proposals and groundtruth boxes,
-        with a fraction of positives that is no larger than `self.positive_sample_fraction.
-
-        Args:
-            See :meth:`StandardROIHeads.forward`
-
-        Returns:
-            list[Instances]: length `N` list of `Instances`s containing the proposals
-                sampled for training. Each `Instances` has the following fields:
-                - proposal_boxes: the rotated proposal boxes
-                - gt_boxes: the ground-truth rotated boxes that the proposal is assigned to
-                  (this is only meaningful if the proposal has a label > 0; if label = 0
-                   then the ground-truth box is random)
-                - gt_classes: the ground-truth classification lable for each proposal
-        """
-        if self.proposal_append_gt:
-            proposals = add_ground_truth_to_proposals(targets, proposals)
-
-        proposals_with_gt = []
-
-        num_fg_samples = []
-        num_bg_samples = []
-        for proposals_per_image, targets_per_image in zip(proposals, targets):
-            has_gt = len(targets_per_image) > 0
-            match_quality_matrix = pairwise_iou_rotated(
-                targets_per_image.gt_boxes, proposals_per_image.proposal_boxes
-            )
-            matched_idxs, matched_labels = self.proposal_matcher(match_quality_matrix)
-            sampled_idxs, gt_classes = self._sample_proposals(
-                matched_idxs, matched_labels, targets_per_image.gt_classes
-            )
-
-            proposals_per_image = proposals_per_image[sampled_idxs]
-            proposals_per_image.gt_classes = gt_classes
-
-            if has_gt:
-                sampled_targets = matched_idxs[sampled_idxs]
-                proposals_per_image.gt_boxes = targets_per_image.gt_boxes[sampled_targets]
-
-            num_bg_samples.append((gt_classes == self.num_classes).sum().item())
-            num_fg_samples.append(gt_classes.numel() - num_bg_samples[-1])
-            proposals_with_gt.append(proposals_per_image)
-
-        # Log the number of fg/bg samples that are selected for training ROI heads
-        storage = get_event_storage()
-        storage.put_scalar("roi_head/num_fg_samples", np.mean(num_fg_samples))
-        storage.put_scalar("roi_head/num_bg_samples", np.mean(num_bg_samples))
-
-        return proposals_with_gt
diff --git a/spaces/brjathu/HMR2.0/vendor/detectron2/projects/DensePose/densepose/modeling/predictors/__init__.py b/spaces/brjathu/HMR2.0/vendor/detectron2/projects/DensePose/densepose/modeling/predictors/__init__.py
deleted file mode 100644
index 1ece0757acf2a4924079c884cab44a71cea22c37..0000000000000000000000000000000000000000
--- a/spaces/brjathu/HMR2.0/vendor/detectron2/projects/DensePose/densepose/modeling/predictors/__init__.py
+++ /dev/null
@@ -1,9 +0,0 @@
-# Copyright (c) Facebook, Inc. and its affiliates.
-
-from .chart import DensePoseChartPredictor
-from .chart_confidence import DensePoseChartConfidencePredictorMixin
-from .chart_with_confidence import DensePoseChartWithConfidencePredictor
-from .cse import DensePoseEmbeddingPredictor
-from .cse_confidence import DensePoseEmbeddingConfidencePredictorMixin
-from .cse_with_confidence import DensePoseEmbeddingWithConfidencePredictor
-from .registry import DENSEPOSE_PREDICTOR_REGISTRY
diff --git a/spaces/brjathu/HMR2.0/vendor/detectron2/projects/TridentNet/tridentnet/trident_backbone.py b/spaces/brjathu/HMR2.0/vendor/detectron2/projects/TridentNet/tridentnet/trident_backbone.py
deleted file mode 100644
index 7789bd219b01d452e876ad2ad7f811502719465c..0000000000000000000000000000000000000000
--- a/spaces/brjathu/HMR2.0/vendor/detectron2/projects/TridentNet/tridentnet/trident_backbone.py
+++ /dev/null
@@ -1,220 +0,0 @@
-# Copyright (c) Facebook, Inc. and its affiliates.
-import fvcore.nn.weight_init as weight_init
-import torch
-import torch.nn.functional as F
-
-from detectron2.layers import Conv2d, FrozenBatchNorm2d, get_norm
-from detectron2.modeling import BACKBONE_REGISTRY, ResNet, ResNetBlockBase
-from detectron2.modeling.backbone.resnet import BasicStem, BottleneckBlock, DeformBottleneckBlock
-
-from .trident_conv import TridentConv
-
-__all__ = ["TridentBottleneckBlock", "make_trident_stage", "build_trident_resnet_backbone"]
-
-
-class TridentBottleneckBlock(ResNetBlockBase):
-    def __init__(
-        self,
-        in_channels,
-        out_channels,
-        *,
-        bottleneck_channels,
-        stride=1,
-        num_groups=1,
-        norm="BN",
-        stride_in_1x1=False,
-        num_branch=3,
-        dilations=(1, 2, 3),
-        concat_output=False,
-        test_branch_idx=-1,
-    ):
-        """
-        Args:
-            num_branch (int): the number of branches in TridentNet.
-            dilations (tuple): the dilations of multiple branches in TridentNet.
-            concat_output (bool): if concatenate outputs of multiple branches in TridentNet.
-                Use 'True' for the last trident block.
-        """
-        super().__init__(in_channels, out_channels, stride)
-
-        assert num_branch == len(dilations)
-
-        self.num_branch = num_branch
-        self.concat_output = concat_output
-        self.test_branch_idx = test_branch_idx
-
-        if in_channels != out_channels:
-            self.shortcut = Conv2d(
-                in_channels,
-                out_channels,
-                kernel_size=1,
-                stride=stride,
-                bias=False,
-                norm=get_norm(norm, out_channels),
-            )
-        else:
-            self.shortcut = None
-
-        stride_1x1, stride_3x3 = (stride, 1) if stride_in_1x1 else (1, stride)
-
-        self.conv1 = Conv2d(
-            in_channels,
-            bottleneck_channels,
-            kernel_size=1,
-            stride=stride_1x1,
-            bias=False,
-            norm=get_norm(norm, bottleneck_channels),
-        )
-
-        self.conv2 = TridentConv(
-            bottleneck_channels,
-            bottleneck_channels,
-            kernel_size=3,
-            stride=stride_3x3,
-            paddings=dilations,
-            bias=False,
-            groups=num_groups,
-            dilations=dilations,
-            num_branch=num_branch,
-            test_branch_idx=test_branch_idx,
-            norm=get_norm(norm, bottleneck_channels),
-        )
-
-        self.conv3 = Conv2d(
-            bottleneck_channels,
-            out_channels,
-            kernel_size=1,
-            bias=False,
-            norm=get_norm(norm, out_channels),
-        )
-
-        for layer in [self.conv1, self.conv2, self.conv3, self.shortcut]:
-            if layer is not None:  # shortcut can be None
-                weight_init.c2_msra_fill(layer)
-
-    def forward(self, x):
-        num_branch = self.num_branch if self.training or self.test_branch_idx == -1 else 1
-        if not isinstance(x, list):
-            x = [x] * num_branch
-        out = [self.conv1(b) for b in x]
-        out = [F.relu_(b) for b in out]
-
-        out = self.conv2(out)
-        out = [F.relu_(b) for b in out]
-
-        out = [self.conv3(b) for b in out]
-
-        if self.shortcut is not None:
-            shortcut = [self.shortcut(b) for b in x]
-        else:
-            shortcut = x
-
-        out = [out_b + shortcut_b for out_b, shortcut_b in zip(out, shortcut)]
-        out = [F.relu_(b) for b in out]
-        if self.concat_output:
-            out = torch.cat(out)
-        return out
-
-
-def make_trident_stage(block_class, num_blocks, **kwargs):
-    """
-    Create a resnet stage by creating many blocks for TridentNet.
-    """
-    concat_output = [False] * (num_blocks - 1) + [True]
-    kwargs["concat_output_per_block"] = concat_output
-    return ResNet.make_stage(block_class, num_blocks, **kwargs)
-
-
-@BACKBONE_REGISTRY.register()
-def build_trident_resnet_backbone(cfg, input_shape):
-    """
-    Create a ResNet instance from config for TridentNet.
-
-    Returns:
-        ResNet: a :class:`ResNet` instance.
-    """
-    # need registration of new blocks/stems?
-    norm = cfg.MODEL.RESNETS.NORM
-    stem = BasicStem(
-        in_channels=input_shape.channels,
-        out_channels=cfg.MODEL.RESNETS.STEM_OUT_CHANNELS,
-        norm=norm,
-    )
-    freeze_at = cfg.MODEL.BACKBONE.FREEZE_AT
-
-    if freeze_at >= 1:
-        for p in stem.parameters():
-            p.requires_grad = False
-        stem = FrozenBatchNorm2d.convert_frozen_batchnorm(stem)
-
-    # fmt: off
-    out_features         = cfg.MODEL.RESNETS.OUT_FEATURES
-    depth                = cfg.MODEL.RESNETS.DEPTH
-    num_groups           = cfg.MODEL.RESNETS.NUM_GROUPS
-    width_per_group      = cfg.MODEL.RESNETS.WIDTH_PER_GROUP
-    bottleneck_channels  = num_groups * width_per_group
-    in_channels          = cfg.MODEL.RESNETS.STEM_OUT_CHANNELS
-    out_channels         = cfg.MODEL.RESNETS.RES2_OUT_CHANNELS
-    stride_in_1x1        = cfg.MODEL.RESNETS.STRIDE_IN_1X1
-    res5_dilation        = cfg.MODEL.RESNETS.RES5_DILATION
-    deform_on_per_stage  = cfg.MODEL.RESNETS.DEFORM_ON_PER_STAGE
-    deform_modulated     = cfg.MODEL.RESNETS.DEFORM_MODULATED
-    deform_num_groups    = cfg.MODEL.RESNETS.DEFORM_NUM_GROUPS
-    num_branch           = cfg.MODEL.TRIDENT.NUM_BRANCH
-    branch_dilations     = cfg.MODEL.TRIDENT.BRANCH_DILATIONS
-    trident_stage        = cfg.MODEL.TRIDENT.TRIDENT_STAGE
-    test_branch_idx      = cfg.MODEL.TRIDENT.TEST_BRANCH_IDX
-    # fmt: on
-    assert res5_dilation in {1, 2}, "res5_dilation cannot be {}.".format(res5_dilation)
-
-    num_blocks_per_stage = {50: [3, 4, 6, 3], 101: [3, 4, 23, 3], 152: [3, 8, 36, 3]}[depth]
-
-    stages = []
-
-    res_stage_idx = {"res2": 2, "res3": 3, "res4": 4, "res5": 5}
-    out_stage_idx = [res_stage_idx[f] for f in out_features]
-    trident_stage_idx = res_stage_idx[trident_stage]
-    max_stage_idx = max(out_stage_idx)
-    for idx, stage_idx in enumerate(range(2, max_stage_idx + 1)):
-        dilation = res5_dilation if stage_idx == 5 else 1
-        first_stride = 1 if idx == 0 or (stage_idx == 5 and dilation == 2) else 2
-        stage_kargs = {
-            "num_blocks": num_blocks_per_stage[idx],
-            "stride_per_block": [first_stride] + [1] * (num_blocks_per_stage[idx] - 1),
-            "in_channels": in_channels,
-            "bottleneck_channels": bottleneck_channels,
-            "out_channels": out_channels,
-            "num_groups": num_groups,
-            "norm": norm,
-            "stride_in_1x1": stride_in_1x1,
-            "dilation": dilation,
-        }
-        if stage_idx == trident_stage_idx:
-            assert not deform_on_per_stage[
-                idx
-            ], "Not support deformable conv in Trident blocks yet."
-            stage_kargs["block_class"] = TridentBottleneckBlock
-            stage_kargs["num_branch"] = num_branch
-            stage_kargs["dilations"] = branch_dilations
-            stage_kargs["test_branch_idx"] = test_branch_idx
-            stage_kargs.pop("dilation")
-        elif deform_on_per_stage[idx]:
-            stage_kargs["block_class"] = DeformBottleneckBlock
-            stage_kargs["deform_modulated"] = deform_modulated
-            stage_kargs["deform_num_groups"] = deform_num_groups
-        else:
-            stage_kargs["block_class"] = BottleneckBlock
-        blocks = (
-            make_trident_stage(**stage_kargs)
-            if stage_idx == trident_stage_idx
-            else ResNet.make_stage(**stage_kargs)
-        )
-        in_channels = out_channels
-        out_channels *= 2
-        bottleneck_channels *= 2
-
-        if freeze_at >= stage_idx:
-            for block in blocks:
-                block.freeze()
-        stages.append(blocks)
-    return ResNet(stem, stages, out_features=out_features)
diff --git a/spaces/cahya/image-search/README.md b/spaces/cahya/image-search/README.md
deleted file mode 100644
index 6aee5a1e6fa3027a2dc82209fb784e78424c06c7..0000000000000000000000000000000000000000
--- a/spaces/cahya/image-search/README.md
+++ /dev/null
@@ -1,33 +0,0 @@
----
-title: Image Search
-emoji: 😻
-colorFrom: blue
-colorTo: gray
-sdk: streamlit
-app_file: app.py
-pinned: false
----
-
-# Configuration
-
-`title`: _string_  
-Display title for the Space
-
-`emoji`: _string_  
-Space emoji (emoji-only character allowed)
-
-`colorFrom`: _string_  
-Color for Thumbnail gradient (red, yellow, green, blue, indigo, purple, pink, gray)
-
-`colorTo`: _string_  
-Color for Thumbnail gradient (red, yellow, green, blue, indigo, purple, pink, gray)
-
-`sdk`: _string_  
-Can be either `gradio` or `streamlit`
-
-`app_file`: _string_  
-Path to your main application file (which contains either `gradio` or `streamlit` Python code).  
-Path is relative to the root of the repository.
-
-`pinned`: _boolean_  
-Whether the Space stays on top of your list.
diff --git a/spaces/camenduru-com/seamless/TemplateData/style.css b/spaces/camenduru-com/seamless/TemplateData/style.css
deleted file mode 100644
index 5448f1003bf2bea32077d5a308641fd5eb05c8ee..0000000000000000000000000000000000000000
--- a/spaces/camenduru-com/seamless/TemplateData/style.css
+++ /dev/null
@@ -1,17 +0,0 @@
-html, body { width: 100%; height: 100% }
-body { padding: 0; margin: 0 }
-#unity-container { padding: 1%; margin: auto; width: 98%; height: 90%; }
-#unity-container.unity-desktop { padding: 1%; margin: auto; width: 98%; height: 90%; }
-#unity-container.unity-mobile { width: 100%; height: 100% }
-#unity-canvas { width: 100%; height: 100%; background: #231F20 }
-.unity-mobile #unity-canvas { width: 100%; height: 100% }
-#unity-loading-bar { position: absolute; left: 50%; top: 50%; transform: translate(-50%, -50%); display: none }
-#unity-logo { width: 154px; height: 130px; background: url('unity-logo-dark.png') no-repeat center }
-#unity-progress-bar-empty { width: 141px; height: 18px; margin-top: 10px; margin-left: 6.5px; background: url('progress-bar-empty-dark.png') no-repeat center }
-#unity-progress-bar-full { width: 0%; height: 18px; margin-top: 10px; background: url('progress-bar-full-dark.png') no-repeat center }
-#unity-footer { position: relative }
-.unity-mobile #unity-footer { display: none }
-#unity-webgl-logo { float:left; width: 204px; height: 38px; background: url('webgl-logo.png') no-repeat center }
-#unity-build-title { float: right; margin-right: 10px; line-height: 38px; font-family: arial; font-size: 18px }
-#unity-fullscreen-button { float: right; width: 38px; height: 38px; background: url('fullscreen-button.png') no-repeat center }
-#unity-warning { position: absolute; left: 50%; top: 5%; transform: translate(-50%); background: white; padding: 10px; display: none }
diff --git a/spaces/candlend/vits-hoshimi/sovits/modules.py b/spaces/candlend/vits-hoshimi/sovits/modules.py
deleted file mode 100644
index 52ee14e41a5b6d67d875d1b694aecd2a51244897..0000000000000000000000000000000000000000
--- a/spaces/candlend/vits-hoshimi/sovits/modules.py
+++ /dev/null
@@ -1,342 +0,0 @@
-import copy
-import math
-import numpy as np
-import scipy
-import torch
-from torch import nn
-from torch.nn import functional as F
-
-from torch.nn import Conv1d, ConvTranspose1d, AvgPool1d, Conv2d
-from torch.nn.utils import weight_norm, remove_weight_norm
-
-import commons
-from commons import init_weights, get_padding
-
-
-LRELU_SLOPE = 0.1
-
-
-class LayerNorm(nn.Module):
-  def __init__(self, channels, eps=1e-5):
-    super().__init__()
-    self.channels = channels
-    self.eps = eps
-
-    self.gamma = nn.Parameter(torch.ones(channels))
-    self.beta = nn.Parameter(torch.zeros(channels))
-
-  def forward(self, x):
-    x = x.transpose(1, -1)
-    x = F.layer_norm(x, (self.channels,), self.gamma, self.beta, self.eps)
-    return x.transpose(1, -1)
-
- 
-class ConvReluNorm(nn.Module):
-  def __init__(self, in_channels, hidden_channels, out_channels, kernel_size, n_layers, p_dropout):
-    super().__init__()
-    self.in_channels = in_channels
-    self.hidden_channels = hidden_channels
-    self.out_channels = out_channels
-    self.kernel_size = kernel_size
-    self.n_layers = n_layers
-    self.p_dropout = p_dropout
-    assert n_layers > 1, "Number of layers should be larger than 0."
-
-    self.conv_layers = nn.ModuleList()
-    self.norm_layers = nn.ModuleList()
-    self.conv_layers.append(nn.Conv1d(in_channels, hidden_channels, kernel_size, padding=kernel_size//2))
-    self.norm_layers.append(LayerNorm(hidden_channels))
-    self.relu_drop = nn.Sequential(
-        nn.ReLU(),
-        nn.Dropout(p_dropout))
-    for _ in range(n_layers-1):
-      self.conv_layers.append(nn.Conv1d(hidden_channels, hidden_channels, kernel_size, padding=kernel_size//2))
-      self.norm_layers.append(LayerNorm(hidden_channels))
-    self.proj = nn.Conv1d(hidden_channels, out_channels, 1)
-    self.proj.weight.data.zero_()
-    self.proj.bias.data.zero_()
-
-  def forward(self, x, x_mask):
-    x_org = x
-    for i in range(self.n_layers):
-      x = self.conv_layers[i](x * x_mask)
-      x = self.norm_layers[i](x)
-      x = self.relu_drop(x)
-    x = x_org + self.proj(x)
-    return x * x_mask
-
-
-class DDSConv(nn.Module):
-  """
-  Dialted and Depth-Separable Convolution
-  """
-  def __init__(self, channels, kernel_size, n_layers, p_dropout=0.):
-    super().__init__()
-    self.channels = channels
-    self.kernel_size = kernel_size
-    self.n_layers = n_layers
-    self.p_dropout = p_dropout
-
-    self.drop = nn.Dropout(p_dropout)
-    self.convs_sep = nn.ModuleList()
-    self.convs_1x1 = nn.ModuleList()
-    self.norms_1 = nn.ModuleList()
-    self.norms_2 = nn.ModuleList()
-    for i in range(n_layers):
-      dilation = kernel_size ** i
-      padding = (kernel_size * dilation - dilation) // 2
-      self.convs_sep.append(nn.Conv1d(channels, channels, kernel_size, 
-          groups=channels, dilation=dilation, padding=padding
-      ))
-      self.convs_1x1.append(nn.Conv1d(channels, channels, 1))
-      self.norms_1.append(LayerNorm(channels))
-      self.norms_2.append(LayerNorm(channels))
-
-  def forward(self, x, x_mask, g=None):
-    if g is not None:
-      x = x + g
-    for i in range(self.n_layers):
-      y = self.convs_sep[i](x * x_mask)
-      y = self.norms_1[i](y)
-      y = F.gelu(y)
-      y = self.convs_1x1[i](y)
-      y = self.norms_2[i](y)
-      y = F.gelu(y)
-      y = self.drop(y)
-      x = x + y
-    return x * x_mask
-
-
-class WN(torch.nn.Module):
-  def __init__(self, hidden_channels, kernel_size, dilation_rate, n_layers, gin_channels=0, p_dropout=0):
-    super(WN, self).__init__()
-    assert(kernel_size % 2 == 1)
-    self.hidden_channels =hidden_channels
-    self.kernel_size = kernel_size,
-    self.dilation_rate = dilation_rate
-    self.n_layers = n_layers
-    self.gin_channels = gin_channels
-    self.p_dropout = p_dropout
-
-    self.in_layers = torch.nn.ModuleList()
-    self.res_skip_layers = torch.nn.ModuleList()
-    self.drop = nn.Dropout(p_dropout)
-
-    if gin_channels != 0:
-      cond_layer = torch.nn.Conv1d(gin_channels, 2*hidden_channels*n_layers, 1)
-      self.cond_layer = torch.nn.utils.weight_norm(cond_layer, name='weight')
-
-    for i in range(n_layers):
-      dilation = dilation_rate ** i
-      padding = int((kernel_size * dilation - dilation) / 2)
-      in_layer = torch.nn.Conv1d(hidden_channels, 2*hidden_channels, kernel_size,
-                                 dilation=dilation, padding=padding)
-      in_layer = torch.nn.utils.weight_norm(in_layer, name='weight')
-      self.in_layers.append(in_layer)
-
-      # last one is not necessary
-      if i < n_layers - 1:
-        res_skip_channels = 2 * hidden_channels
-      else:
-        res_skip_channels = hidden_channels
-
-      res_skip_layer = torch.nn.Conv1d(hidden_channels, res_skip_channels, 1)
-      res_skip_layer = torch.nn.utils.weight_norm(res_skip_layer, name='weight')
-      self.res_skip_layers.append(res_skip_layer)
-
-  def forward(self, x, x_mask, g=None, **kwargs):
-    output = torch.zeros_like(x)
-    n_channels_tensor = torch.IntTensor([self.hidden_channels])
-
-    if g is not None:
-      g = self.cond_layer(g)
-
-    for i in range(self.n_layers):
-      x_in = self.in_layers[i](x)
-      if g is not None:
-        cond_offset = i * 2 * self.hidden_channels
-        g_l = g[:,cond_offset:cond_offset+2*self.hidden_channels,:]
-      else:
-        g_l = torch.zeros_like(x_in)
-
-      acts = commons.fused_add_tanh_sigmoid_multiply(
-          x_in,
-          g_l,
-          n_channels_tensor)
-      acts = self.drop(acts)
-
-      res_skip_acts = self.res_skip_layers[i](acts)
-      if i < self.n_layers - 1:
-        res_acts = res_skip_acts[:,:self.hidden_channels,:]
-        x = (x + res_acts) * x_mask
-        output = output + res_skip_acts[:,self.hidden_channels:,:]
-      else:
-        output = output + res_skip_acts
-    return output * x_mask
-
-  def remove_weight_norm(self):
-    if self.gin_channels != 0:
-      torch.nn.utils.remove_weight_norm(self.cond_layer)
-    for l in self.in_layers:
-      torch.nn.utils.remove_weight_norm(l)
-    for l in self.res_skip_layers:
-     torch.nn.utils.remove_weight_norm(l)
-
-
-class ResBlock1(torch.nn.Module):
-    def __init__(self, channels, kernel_size=3, dilation=(1, 3, 5)):
-        super(ResBlock1, self).__init__()
-        self.convs1 = nn.ModuleList([
-            weight_norm(Conv1d(channels, channels, kernel_size, 1, dilation=dilation[0],
-                               padding=get_padding(kernel_size, dilation[0]))),
-            weight_norm(Conv1d(channels, channels, kernel_size, 1, dilation=dilation[1],
-                               padding=get_padding(kernel_size, dilation[1]))),
-            weight_norm(Conv1d(channels, channels, kernel_size, 1, dilation=dilation[2],
-                               padding=get_padding(kernel_size, dilation[2])))
-        ])
-        self.convs1.apply(init_weights)
-
-        self.convs2 = nn.ModuleList([
-            weight_norm(Conv1d(channels, channels, kernel_size, 1, dilation=1,
-                               padding=get_padding(kernel_size, 1))),
-            weight_norm(Conv1d(channels, channels, kernel_size, 1, dilation=1,
-                               padding=get_padding(kernel_size, 1))),
-            weight_norm(Conv1d(channels, channels, kernel_size, 1, dilation=1,
-                               padding=get_padding(kernel_size, 1)))
-        ])
-        self.convs2.apply(init_weights)
-
-    def forward(self, x, x_mask=None):
-        for c1, c2 in zip(self.convs1, self.convs2):
-            xt = F.leaky_relu(x, LRELU_SLOPE)
-            if x_mask is not None:
-                xt = xt * x_mask
-            xt = c1(xt)
-            xt = F.leaky_relu(xt, LRELU_SLOPE)
-            if x_mask is not None:
-                xt = xt * x_mask
-            xt = c2(xt)
-            x = xt + x
-        if x_mask is not None:
-            x = x * x_mask
-        return x
-
-    def remove_weight_norm(self):
-        for l in self.convs1:
-            remove_weight_norm(l)
-        for l in self.convs2:
-            remove_weight_norm(l)
-
-
-class ResBlock2(torch.nn.Module):
-    def __init__(self, channels, kernel_size=3, dilation=(1, 3)):
-        super(ResBlock2, self).__init__()
-        self.convs = nn.ModuleList([
-            weight_norm(Conv1d(channels, channels, kernel_size, 1, dilation=dilation[0],
-                               padding=get_padding(kernel_size, dilation[0]))),
-            weight_norm(Conv1d(channels, channels, kernel_size, 1, dilation=dilation[1],
-                               padding=get_padding(kernel_size, dilation[1])))
-        ])
-        self.convs.apply(init_weights)
-
-    def forward(self, x, x_mask=None):
-        for c in self.convs:
-            xt = F.leaky_relu(x, LRELU_SLOPE)
-            if x_mask is not None:
-                xt = xt * x_mask
-            xt = c(xt)
-            x = xt + x
-        if x_mask is not None:
-            x = x * x_mask
-        return x
-
-    def remove_weight_norm(self):
-        for l in self.convs:
-            remove_weight_norm(l)
-
-
-class Log(nn.Module):
-  def forward(self, x, x_mask, reverse=False, **kwargs):
-    if not reverse:
-      y = torch.log(torch.clamp_min(x, 1e-5)) * x_mask
-      logdet = torch.sum(-y, [1, 2])
-      return y, logdet
-    else:
-      x = torch.exp(x) * x_mask
-      return x
-    
-
-class Flip(nn.Module):
-  def forward(self, x, *args, reverse=False, **kwargs):
-    x = torch.flip(x, [1])
-    if not reverse:
-      logdet = torch.zeros(x.size(0)).to(dtype=x.dtype, device=x.device)
-      return x, logdet
-    else:
-      return x
-
-
-class ElementwiseAffine(nn.Module):
-  def __init__(self, channels):
-    super().__init__()
-    self.channels = channels
-    self.m = nn.Parameter(torch.zeros(channels,1))
-    self.logs = nn.Parameter(torch.zeros(channels,1))
-
-  def forward(self, x, x_mask, reverse=False, **kwargs):
-    if not reverse:
-      y = self.m + torch.exp(self.logs) * x
-      y = y * x_mask
-      logdet = torch.sum(self.logs * x_mask, [1,2])
-      return y, logdet
-    else:
-      x = (x - self.m) * torch.exp(-self.logs) * x_mask
-      return x
-
-
-class ResidualCouplingLayer(nn.Module):
-  def __init__(self,
-      channels,
-      hidden_channels,
-      kernel_size,
-      dilation_rate,
-      n_layers,
-      p_dropout=0,
-      gin_channels=0,
-      mean_only=False):
-    assert channels % 2 == 0, "channels should be divisible by 2"
-    super().__init__()
-    self.channels = channels
-    self.hidden_channels = hidden_channels
-    self.kernel_size = kernel_size
-    self.dilation_rate = dilation_rate
-    self.n_layers = n_layers
-    self.half_channels = channels // 2
-    self.mean_only = mean_only
-
-    self.pre = nn.Conv1d(self.half_channels, hidden_channels, 1)
-    self.enc = WN(hidden_channels, kernel_size, dilation_rate, n_layers, p_dropout=p_dropout, gin_channels=gin_channels)
-    self.post = nn.Conv1d(hidden_channels, self.half_channels * (2 - mean_only), 1)
-    self.post.weight.data.zero_()
-    self.post.bias.data.zero_()
-
-  def forward(self, x, x_mask, g=None, reverse=False):
-    x0, x1 = torch.split(x, [self.half_channels]*2, 1)
-    h = self.pre(x0) * x_mask
-    h = self.enc(h, x_mask, g=g)
-    stats = self.post(h) * x_mask
-    if not self.mean_only:
-      m, logs = torch.split(stats, [self.half_channels]*2, 1)
-    else:
-      m = stats
-      logs = torch.zeros_like(m)
-
-    if not reverse:
-      x1 = m + x1 * torch.exp(logs) * x_mask
-      x = torch.cat([x0, x1], 1)
-      logdet = torch.sum(logs, [1,2])
-      return x, logdet
-    else:
-      x1 = (x1 - m) * torch.exp(-logs) * x_mask
-      x = torch.cat([x0, x1], 1)
-      return x
diff --git a/spaces/carlosalonso/Detection-video/carpeta_deteccion/detectron2/model_zoo/model_zoo.py b/spaces/carlosalonso/Detection-video/carpeta_deteccion/detectron2/model_zoo/model_zoo.py
deleted file mode 100644
index 5b90bc9a165ea46ada72ed0e71f1e80e71ea9f40..0000000000000000000000000000000000000000
--- a/spaces/carlosalonso/Detection-video/carpeta_deteccion/detectron2/model_zoo/model_zoo.py
+++ /dev/null
@@ -1,213 +0,0 @@
-# Copyright (c) Facebook, Inc. and its affiliates.
-import os
-from typing import Optional
-import pkg_resources
-import torch
-
-from detectron2.checkpoint import DetectionCheckpointer
-from detectron2.config import CfgNode, LazyConfig, get_cfg, instantiate
-from detectron2.modeling import build_model
-
-
-class _ModelZooUrls(object):
-    """
-    Mapping from names to officially released Detectron2 pre-trained models.
-    """
-
-    S3_PREFIX = "https://dl.fbaipublicfiles.com/detectron2/"
-
-    # format: {config_path.yaml} -> model_id/model_final_{commit}.pkl
-    CONFIG_PATH_TO_URL_SUFFIX = {
-        # COCO Detection with Faster R-CNN
-        "COCO-Detection/faster_rcnn_R_50_C4_1x": "137257644/model_final_721ade.pkl",
-        "COCO-Detection/faster_rcnn_R_50_DC5_1x": "137847829/model_final_51d356.pkl",
-        "COCO-Detection/faster_rcnn_R_50_FPN_1x": "137257794/model_final_b275ba.pkl",
-        "COCO-Detection/faster_rcnn_R_50_C4_3x": "137849393/model_final_f97cb7.pkl",
-        "COCO-Detection/faster_rcnn_R_50_DC5_3x": "137849425/model_final_68d202.pkl",
-        "COCO-Detection/faster_rcnn_R_50_FPN_3x": "137849458/model_final_280758.pkl",
-        "COCO-Detection/faster_rcnn_R_101_C4_3x": "138204752/model_final_298dad.pkl",
-        "COCO-Detection/faster_rcnn_R_101_DC5_3x": "138204841/model_final_3e0943.pkl",
-        "COCO-Detection/faster_rcnn_R_101_FPN_3x": "137851257/model_final_f6e8b1.pkl",
-        "COCO-Detection/faster_rcnn_X_101_32x8d_FPN_3x": "139173657/model_final_68b088.pkl",
-        # COCO Detection with RetinaNet
-        "COCO-Detection/retinanet_R_50_FPN_1x": "190397773/model_final_bfca0b.pkl",
-        "COCO-Detection/retinanet_R_50_FPN_3x": "190397829/model_final_5bd44e.pkl",
-        "COCO-Detection/retinanet_R_101_FPN_3x": "190397697/model_final_971ab9.pkl",
-        # COCO Detection with RPN and Fast R-CNN
-        "COCO-Detection/rpn_R_50_C4_1x": "137258005/model_final_450694.pkl",
-        "COCO-Detection/rpn_R_50_FPN_1x": "137258492/model_final_02ce48.pkl",
-        "COCO-Detection/fast_rcnn_R_50_FPN_1x": "137635226/model_final_e5f7ce.pkl",
-        # COCO Instance Segmentation Baselines with Mask R-CNN
-        "COCO-InstanceSegmentation/mask_rcnn_R_50_C4_1x": "137259246/model_final_9243eb.pkl",
-        "COCO-InstanceSegmentation/mask_rcnn_R_50_DC5_1x": "137260150/model_final_4f86c3.pkl",
-        "COCO-InstanceSegmentation/mask_rcnn_R_50_FPN_1x": "137260431/model_final_a54504.pkl",
-        "COCO-InstanceSegmentation/mask_rcnn_R_50_C4_3x": "137849525/model_final_4ce675.pkl",
-        "COCO-InstanceSegmentation/mask_rcnn_R_50_DC5_3x": "137849551/model_final_84107b.pkl",
-        "COCO-InstanceSegmentation/mask_rcnn_R_50_FPN_3x": "137849600/model_final_f10217.pkl",
-        "COCO-InstanceSegmentation/mask_rcnn_R_101_C4_3x": "138363239/model_final_a2914c.pkl",
-        "COCO-InstanceSegmentation/mask_rcnn_R_101_DC5_3x": "138363294/model_final_0464b7.pkl",
-        "COCO-InstanceSegmentation/mask_rcnn_R_101_FPN_3x": "138205316/model_final_a3ec72.pkl",
-        "COCO-InstanceSegmentation/mask_rcnn_X_101_32x8d_FPN_3x": "139653917/model_final_2d9806.pkl",  # noqa
-        # New baselines using Large-Scale Jitter and Longer Training Schedule
-        "new_baselines/mask_rcnn_R_50_FPN_100ep_LSJ": "42047764/model_final_bb69de.pkl",
-        "new_baselines/mask_rcnn_R_50_FPN_200ep_LSJ": "42047638/model_final_89a8d3.pkl",
-        "new_baselines/mask_rcnn_R_50_FPN_400ep_LSJ": "42019571/model_final_14d201.pkl",
-        "new_baselines/mask_rcnn_R_101_FPN_100ep_LSJ": "42025812/model_final_4f7b58.pkl",
-        "new_baselines/mask_rcnn_R_101_FPN_200ep_LSJ": "42131867/model_final_0bb7ae.pkl",
-        "new_baselines/mask_rcnn_R_101_FPN_400ep_LSJ": "42073830/model_final_f96b26.pkl",
-        "new_baselines/mask_rcnn_regnetx_4gf_dds_FPN_100ep_LSJ": "42047771/model_final_b7fbab.pkl",  # noqa
-        "new_baselines/mask_rcnn_regnetx_4gf_dds_FPN_200ep_LSJ": "42132721/model_final_5d87c1.pkl",  # noqa
-        "new_baselines/mask_rcnn_regnetx_4gf_dds_FPN_400ep_LSJ": "42025447/model_final_f1362d.pkl",  # noqa
-        "new_baselines/mask_rcnn_regnety_4gf_dds_FPN_100ep_LSJ": "42047784/model_final_6ba57e.pkl",  # noqa
-        "new_baselines/mask_rcnn_regnety_4gf_dds_FPN_200ep_LSJ": "42047642/model_final_27b9c1.pkl",  # noqa
-        "new_baselines/mask_rcnn_regnety_4gf_dds_FPN_400ep_LSJ": "42045954/model_final_ef3a80.pkl",  # noqa
-        # COCO Person Keypoint Detection Baselines with Keypoint R-CNN
-        "COCO-Keypoints/keypoint_rcnn_R_50_FPN_1x": "137261548/model_final_04e291.pkl",
-        "COCO-Keypoints/keypoint_rcnn_R_50_FPN_3x": "137849621/model_final_a6e10b.pkl",
-        "COCO-Keypoints/keypoint_rcnn_R_101_FPN_3x": "138363331/model_final_997cc7.pkl",
-        "COCO-Keypoints/keypoint_rcnn_X_101_32x8d_FPN_3x": "139686956/model_final_5ad38f.pkl",
-        # COCO Panoptic Segmentation Baselines with Panoptic FPN
-        "COCO-PanopticSegmentation/panoptic_fpn_R_50_1x": "139514544/model_final_dbfeb4.pkl",
-        "COCO-PanopticSegmentation/panoptic_fpn_R_50_3x": "139514569/model_final_c10459.pkl",
-        "COCO-PanopticSegmentation/panoptic_fpn_R_101_3x": "139514519/model_final_cafdb1.pkl",
-        # LVIS Instance Segmentation Baselines with Mask R-CNN
-        "LVISv0.5-InstanceSegmentation/mask_rcnn_R_50_FPN_1x": "144219072/model_final_571f7c.pkl",  # noqa
-        "LVISv0.5-InstanceSegmentation/mask_rcnn_R_101_FPN_1x": "144219035/model_final_824ab5.pkl",  # noqa
-        "LVISv0.5-InstanceSegmentation/mask_rcnn_X_101_32x8d_FPN_1x": "144219108/model_final_5e3439.pkl",  # noqa
-        # Cityscapes & Pascal VOC Baselines
-        "Cityscapes/mask_rcnn_R_50_FPN": "142423278/model_final_af9cf5.pkl",
-        "PascalVOC-Detection/faster_rcnn_R_50_C4": "142202221/model_final_b1acc2.pkl",
-        # Other Settings
-        "Misc/mask_rcnn_R_50_FPN_1x_dconv_c3-c5": "138602867/model_final_65c703.pkl",
-        "Misc/mask_rcnn_R_50_FPN_3x_dconv_c3-c5": "144998336/model_final_821d0b.pkl",
-        "Misc/cascade_mask_rcnn_R_50_FPN_1x": "138602847/model_final_e9d89b.pkl",
-        "Misc/cascade_mask_rcnn_R_50_FPN_3x": "144998488/model_final_480dd8.pkl",
-        "Misc/mask_rcnn_R_50_FPN_3x_syncbn": "169527823/model_final_3b3c51.pkl",
-        "Misc/mask_rcnn_R_50_FPN_3x_gn": "138602888/model_final_dc5d9e.pkl",
-        "Misc/scratch_mask_rcnn_R_50_FPN_3x_gn": "138602908/model_final_01ca85.pkl",
-        "Misc/scratch_mask_rcnn_R_50_FPN_9x_gn": "183808979/model_final_da7b4c.pkl",
-        "Misc/scratch_mask_rcnn_R_50_FPN_9x_syncbn": "184226666/model_final_5ce33e.pkl",
-        "Misc/panoptic_fpn_R_101_dconv_cascade_gn_3x": "139797668/model_final_be35db.pkl",
-        "Misc/cascade_mask_rcnn_X_152_32x8d_FPN_IN5k_gn_dconv": "18131413/model_0039999_e76410.pkl",  # noqa
-        # D1 Comparisons
-        "Detectron1-Comparisons/faster_rcnn_R_50_FPN_noaug_1x": "137781054/model_final_7ab50c.pkl",  # noqa
-        "Detectron1-Comparisons/mask_rcnn_R_50_FPN_noaug_1x": "137781281/model_final_62ca52.pkl",  # noqa
-        "Detectron1-Comparisons/keypoint_rcnn_R_50_FPN_1x": "137781195/model_final_cce136.pkl",
-    }
-
-    @staticmethod
-    def query(config_path: str) -> Optional[str]:
-        """
-        Args:
-            config_path: relative config filename
-        """
-        name = config_path.replace(".yaml", "").replace(".py", "")
-        if name in _ModelZooUrls.CONFIG_PATH_TO_URL_SUFFIX:
-            suffix = _ModelZooUrls.CONFIG_PATH_TO_URL_SUFFIX[name]
-            return _ModelZooUrls.S3_PREFIX + name + "/" + suffix
-        return None
-
-
-def get_checkpoint_url(config_path):
-    """
-    Returns the URL to the model trained using the given config
-
-    Args:
-        config_path (str): config file name relative to detectron2's "configs/"
-            directory, e.g., "COCO-InstanceSegmentation/mask_rcnn_R_50_FPN_1x.yaml"
-
-    Returns:
-        str: a URL to the model
-    """
-    url = _ModelZooUrls.query(config_path)
-    if url is None:
-        raise RuntimeError("Pretrained model for {} is not available!".format(config_path))
-    return url
-
-
-def get_config_file(config_path):
-    """
-    Returns path to a builtin config file.
-
-    Args:
-        config_path (str): config file name relative to detectron2's "configs/"
-            directory, e.g., "COCO-InstanceSegmentation/mask_rcnn_R_50_FPN_1x.yaml"
-
-    Returns:
-        str: the real path to the config file.
-    """
-    cfg_file = pkg_resources.resource_filename(
-        "detectron2.model_zoo", os.path.join("configs", config_path)
-    )
-    if not os.path.exists(cfg_file):
-        raise RuntimeError("{} not available in Model Zoo!".format(config_path))
-    return cfg_file
-
-
-def get_config(config_path, trained: bool = False):
-    """
-    Returns a config object for a model in model zoo.
-
-    Args:
-        config_path (str): config file name relative to detectron2's "configs/"
-            directory, e.g., "COCO-InstanceSegmentation/mask_rcnn_R_50_FPN_1x.yaml"
-        trained (bool): If True, will set ``MODEL.WEIGHTS`` to trained model zoo weights.
-            If False, the checkpoint specified in the config file's ``MODEL.WEIGHTS`` is used
-            instead; this will typically (though not always) initialize a subset of weights using
-            an ImageNet pre-trained model, while randomly initializing the other weights.
-
-    Returns:
-        CfgNode or omegaconf.DictConfig: a config object
-    """
-    cfg_file = get_config_file(config_path)
-    if cfg_file.endswith(".yaml"):
-        cfg = get_cfg()
-        cfg.merge_from_file(cfg_file)
-        if trained:
-            cfg.MODEL.WEIGHTS = get_checkpoint_url(config_path)
-        return cfg
-    elif cfg_file.endswith(".py"):
-        cfg = LazyConfig.load(cfg_file)
-        if trained:
-            url = get_checkpoint_url(config_path)
-            if "train" in cfg and "init_checkpoint" in cfg.train:
-                cfg.train.init_checkpoint = url
-            else:
-                raise NotImplementedError
-        return cfg
-
-
-def get(config_path, trained: bool = False, device: Optional[str] = None):
-    """
-    Get a model specified by relative path under Detectron2's official ``configs/`` directory.
-
-    Args:
-        config_path (str): config file name relative to detectron2's "configs/"
-            directory, e.g., "COCO-InstanceSegmentation/mask_rcnn_R_50_FPN_1x.yaml"
-        trained (bool): see :func:`get_config`.
-        device (str or None): overwrite the device in config, if given.
-
-    Returns:
-        nn.Module: a detectron2 model. Will be in training mode.
-
-    Example:
-    ::
-        from detectron2 import model_zoo
-        model = model_zoo.get("COCO-InstanceSegmentation/mask_rcnn_R_50_FPN_1x.yaml", trained=True)
-    """
-    cfg = get_config(config_path, trained)
-    if device is None and not torch.cuda.is_available():
-        device = "cpu"
-    if device is not None and isinstance(cfg, CfgNode):
-        cfg.MODEL.DEVICE = device
-
-    if isinstance(cfg, CfgNode):
-        model = build_model(cfg)
-        DetectionCheckpointer(model).load(cfg.MODEL.WEIGHTS)
-    else:
-        model = instantiate(cfg.model)
-        if device is not None:
-            model = model.to(device)
-        if "train" in cfg and "init_checkpoint" in cfg.train:
-            DetectionCheckpointer(model).load(cfg.train.init_checkpoint)
-    return model
diff --git a/spaces/carlosalonso/Detection-video/carpeta_deteccion/projects/DensePose/doc/BOOTSTRAPPING_PIPELINE.md b/spaces/carlosalonso/Detection-video/carpeta_deteccion/projects/DensePose/doc/BOOTSTRAPPING_PIPELINE.md
deleted file mode 100644
index a1326862abe5479140269f5e6af50b68e7c2d0aa..0000000000000000000000000000000000000000
--- a/spaces/carlosalonso/Detection-video/carpeta_deteccion/projects/DensePose/doc/BOOTSTRAPPING_PIPELINE.md
+++ /dev/null
@@ -1,197 +0,0 @@
-# Bootstrapping Pipeline
-
-Bootstrapping pipeline for DensePose was proposed in
-[Sanakoyeu et al., 2020](https://arxiv.org/pdf/2003.00080.pdf)
-to extend DensePose from humans to proximal animal classes
-(chimpanzees). Currently, the pipeline is only implemented for
-[chart-based models](DENSEPOSE_IUV.md).
-Bootstrapping proceeds in two steps.
-
-## Master Model Training
-
-Master model is trained on data from source domain (humans)
-and supporting domain (animals). Instances from the source domain
-contain full DensePose annotations (`S`, `I`, `U` and `V`) and
-instances from the supporting domain have segmentation annotations only.
-To ensure segmentation quality in the target domain, only a subset of
-supporting domain classes is included into the training. This is achieved
-through category filters, e.g.
-(see [configs/evolution/Base-RCNN-FPN-Atop10P_CA.yaml](../configs/evolution/Base-RCNN-FPN-Atop10P_CA.yaml)):
-
-```
-  WHITELISTED_CATEGORIES:
-    "base_coco_2017_train":
-      - 1  # person
-      - 16 # bird
-      - 17 # cat
-      - 18 # dog
-      - 19 # horse
-      - 20 # sheep
-      - 21 # cow
-      - 22 # elephant
-      - 23 # bear
-      - 24 # zebra
-      - 25 # girafe
-```
-The acronym `Atop10P` in config file names indicates that categories are filtered to
-only contain top 10 animals and person.
-
-The training is performed in a *class-agnostic* manner: all instances
-are mapped into the same class (person), e.g.
-(see [configs/evolution/Base-RCNN-FPN-Atop10P_CA.yaml](../configs/evolution/Base-RCNN-FPN-Atop10P_CA.yaml)):
-
-```
-  CATEGORY_MAPS:
-    "base_coco_2017_train":
-      "16": 1 # bird -> person
-      "17": 1 # cat -> person
-      "18": 1 # dog -> person
-      "19": 1 # horse -> person
-      "20": 1 # sheep -> person
-      "21": 1 # cow -> person
-      "22": 1 # elephant -> person
-      "23": 1 # bear -> person
-      "24": 1 # zebra -> person
-      "25": 1 # girafe -> person
-```
-The acronym `CA` in config file names indicates that the training is class-agnostic.
-
-## Student Model Training
-
-Student model is trained on data from source domain (humans),
-supporting domain (animals) and target domain (chimpanzees).
-Annotations in source and supporting domains are similar to the ones
-used for the master model training.
-Annotations in target domain are obtained by applying the master model
-to images that contain instances from the target category and sampling
-sparse annotations from dense results. This process is called *bootstrapping*.
-Below we give details on how the bootstrapping pipeline is implemented.
-
-### Data Loaders
-
-The central components that enable bootstrapping are
-[`InferenceBasedLoader`](../densepose/data/inference_based_loader.py) and
-[`CombinedDataLoader`](../densepose/data/combined_loader.py).
-
-`InferenceBasedLoader` takes images from a data loader, applies a model
-to the images, filters the model outputs based on the selected criteria and
-samples the filtered outputs to produce annotations.
-
-`CombinedDataLoader` combines data obtained from the loaders based on specified
-ratios. The standard data loader has the default ratio of 1.0,
-ratios for bootstrap datasets are specified in the configuration file.
-The higher the ratio the higher the probability to include samples from the
-particular data loader into a batch.
-
-Here is an example of the bootstrapping configuration taken from
-[`configs/evolution/densepose_R_50_FPN_DL_WC1M_3x_Atop10P_CA_B_uniform.yaml`](../configs/evolution/densepose_R_50_FPN_DL_WC1M_3x_Atop10P_CA_B_uniform.yaml):
-```
-BOOTSTRAP_DATASETS:
-  - DATASET: "chimpnsee"
-    RATIO: 1.0
-    IMAGE_LOADER:
-      TYPE: "video_keyframe"
-      SELECT:
-        STRATEGY: "random_k"
-        NUM_IMAGES: 4
-      TRANSFORM:
-        TYPE: "resize"
-        MIN_SIZE: 800
-        MAX_SIZE: 1333
-      BATCH_SIZE: 8
-      NUM_WORKERS: 1
-    INFERENCE:
-      INPUT_BATCH_SIZE: 1
-      OUTPUT_BATCH_SIZE: 1
-    DATA_SAMPLER:
-      # supported types:
-      #   densepose_uniform
-      #   densepose_UV_confidence
-      #   densepose_fine_segm_confidence
-      #   densepose_coarse_segm_confidence
-      TYPE: "densepose_uniform"
-      COUNT_PER_CLASS: 8
-    FILTER:
-      TYPE: "detection_score"
-      MIN_VALUE: 0.8
-BOOTSTRAP_MODEL:
-  WEIGHTS: https://dl.fbaipublicfiles.com/densepose/evolution/densepose_R_50_FPN_DL_WC1M_3x_Atop10P_CA/217578784/model_final_9fe1cc.pkl
-```
-
-The above example has one bootstrap dataset (`chimpnsee`). This dataset is registered as
-a [VIDEO_LIST](../densepose/data/datasets/chimpnsee.py) dataset, which means that
-it consists of a number of videos specified in a text file. For videos there can be
-different strategies to sample individual images. Here we use `video_keyframe` strategy
-which considers only keyframes; this ensures temporal offset between sampled images and
-faster seek operations. We select at most 4 random keyframes in each video:
-
-```
-SELECT:
-  STRATEGY: "random_k"
-  NUM_IMAGES: 4
-```
-
-The frames are then resized
-
-```
-TRANSFORM:
-  TYPE: "resize"
-  MIN_SIZE: 800
-  MAX_SIZE: 1333
-```
-
-and batched using the standard
-[PyTorch DataLoader](https://pytorch.org/docs/stable/data.html#torch.utils.data.DataLoader):
-
-```
-BATCH_SIZE: 8
-NUM_WORKERS: 1
-```
-
-`InferenceBasedLoader` decomposes those batches into batches of size `INPUT_BATCH_SIZE`
-and applies the master model specified by `BOOTSTRAP_MODEL`. Models outputs are filtered
-by detection score:
-
-```
-FILTER:
-  TYPE: "detection_score"
-  MIN_VALUE: 0.8
-```
-
-and sampled using the specified sampling strategy:
-
-```
-DATA_SAMPLER:
-  # supported types:
-  #   densepose_uniform
-  #   densepose_UV_confidence
-  #   densepose_fine_segm_confidence
-  #   densepose_coarse_segm_confidence
-  TYPE: "densepose_uniform"
-  COUNT_PER_CLASS: 8
-```
-
-The current implementation supports
-[uniform sampling](../densepose/data/samplers/densepose_uniform.py) and
-[confidence-based sampling](../densepose/data/samplers/densepose_confidence_based.py)
-to obtain sparse annotations from dense results. For confidence-based
-sampling one needs to use the master model which produces confidence estimates.
-The `WC1M` master model used in the example above produces all three types of confidence
-estimates.
-
-Finally, sampled data is grouped into batches of size `OUTPUT_BATCH_SIZE`:
-
-```
-INFERENCE:
-  INPUT_BATCH_SIZE: 1
-  OUTPUT_BATCH_SIZE: 1
-```
-
-The proportion of data from annotated datasets and bootstrapped dataset can be tracked
-in the logs, e.g.:
-
-```
-[... densepose.engine.trainer]: batch/ 1.8, batch/base_coco_2017_train 6.4, batch/densepose_coco_2014_train 3.85
-```
-
-which means that over the last 20 iterations, on average for 1.8 bootstrapped data samples there were 6.4 samples from `base_coco_2017_train` and 3.85 samples from `densepose_coco_2014_train`.
diff --git a/spaces/ccds/vits_onnx/export/vits/mel_processing.py b/spaces/ccds/vits_onnx/export/vits/mel_processing.py
deleted file mode 100644
index 575ee5ef554ce4ef12cfee0cfbae87c869c1be05..0000000000000000000000000000000000000000
--- a/spaces/ccds/vits_onnx/export/vits/mel_processing.py
+++ /dev/null
@@ -1,137 +0,0 @@
-import torch
-import torch.nn.functional as F
-import torch.utils.data
-from librosa.filters import mel as librosa_mel_fn
-
-MAX_WAV_VALUE = 32768.0
-
-
-def dynamic_range_compression_torch(x, C=1, clip_val=1e-5):
-    """
-    PARAMS
-    ------
-    C: compression factor
-    """
-    return torch.log(torch.clamp(x, min=clip_val) * C)
-
-
-def dynamic_range_decompression_torch(x, C=1):
-    """
-    PARAMS
-    ------
-    C: compression factor used to compress
-    """
-    return torch.exp(x) / C
-
-
-def spectral_normalize_torch(magnitudes):
-    output = dynamic_range_compression_torch(magnitudes)
-    return output
-
-
-def spectral_de_normalize_torch(magnitudes):
-    output = dynamic_range_decompression_torch(magnitudes)
-    return output
-
-
-mel_basis = {}
-hann_window = {}
-
-
-def spectrogram_torch(y,
-                      n_fft,
-                      sampling_rate,
-                      hop_size,
-                      win_size,
-                      center=False):
-    if torch.min(y) < -1.:
-        print('min value is ', torch.min(y))
-    if torch.max(y) > 1.:
-        print('max value is ', torch.max(y))
-
-    global hann_window
-    dtype_device = str(y.dtype) + '_' + str(y.device)
-    wnsize_dtype_device = str(win_size) + '_' + dtype_device
-    if wnsize_dtype_device not in hann_window:
-        hann_window[wnsize_dtype_device] = torch.hann_window(win_size).to(
-            dtype=y.dtype, device=y.device)
-
-    y = F.pad(y.unsqueeze(1),
-              (int((n_fft - hop_size) / 2), int((n_fft - hop_size) / 2)),
-              mode='reflect')
-    y = y.squeeze(1)
-
-    spec = torch.stft(y,
-                      n_fft,
-                      hop_length=hop_size,
-                      win_length=win_size,
-                      window=hann_window[wnsize_dtype_device],
-                      center=center,
-                      pad_mode='reflect',
-                      normalized=False,
-                      onesided=True)
-
-    spec = torch.sqrt(spec.pow(2).sum(-1) + 1e-6)
-    return spec
-
-
-def spec_to_mel_torch(spec, n_fft, num_mels, sampling_rate, fmin, fmax):
-    global mel_basis
-    dtype_device = str(spec.dtype) + '_' + str(spec.device)
-    fmax_dtype_device = str(fmax) + '_' + dtype_device
-    if fmax_dtype_device not in mel_basis:
-        mel = librosa_mel_fn(sampling_rate, n_fft, num_mels, fmin, fmax)
-        mel_basis[fmax_dtype_device] = torch.from_numpy(mel).to(
-            dtype=spec.dtype, device=spec.device)
-    spec = torch.matmul(mel_basis[fmax_dtype_device], spec)
-    spec = spectral_normalize_torch(spec)
-    return spec
-
-
-def mel_spectrogram_torch(y,
-                          n_fft,
-                          num_mels,
-                          sampling_rate,
-                          hop_size,
-                          win_size,
-                          fmin,
-                          fmax,
-                          center=False):
-    if torch.min(y) < -1.:
-        print('min value is ', torch.min(y))
-    if torch.max(y) > 1.:
-        print('max value is ', torch.max(y))
-
-    global mel_basis, hann_window
-    dtype_device = str(y.dtype) + '_' + str(y.device)
-    fmax_dtype_device = str(fmax) + '_' + dtype_device
-    wnsize_dtype_device = str(win_size) + '_' + dtype_device
-    if fmax_dtype_device not in mel_basis:
-        mel = librosa_mel_fn(sampling_rate, n_fft, num_mels, fmin, fmax)
-        mel_basis[fmax_dtype_device] = torch.from_numpy(mel).to(
-            dtype=y.dtype, device=y.device)
-    if wnsize_dtype_device not in hann_window:
-        hann_window[wnsize_dtype_device] = torch.hann_window(win_size).to(
-            dtype=y.dtype, device=y.device)
-
-    y = F.pad(y.unsqueeze(1),
-              (int((n_fft - hop_size) / 2), int((n_fft - hop_size) / 2)),
-              mode='reflect')
-    y = y.squeeze(1)
-
-    spec = torch.stft(y,
-                      n_fft,
-                      hop_length=hop_size,
-                      win_length=win_size,
-                      window=hann_window[wnsize_dtype_device],
-                      center=center,
-                      pad_mode='reflect',
-                      normalized=False,
-                      onesided=True)
-
-    spec = torch.sqrt(spec.pow(2).sum(-1) + 1e-6)
-
-    spec = torch.matmul(mel_basis[fmax_dtype_device], spec)
-    spec = spectral_normalize_torch(spec)
-
-    return spec
diff --git a/spaces/chanhi0603/Create_subtitles_for_videos_ChatGPT/Create_subtitles_for_videos_ChatGPT/README.md b/spaces/chanhi0603/Create_subtitles_for_videos_ChatGPT/Create_subtitles_for_videos_ChatGPT/README.md
deleted file mode 100644
index a90615af2a6294a40f6aa645c095141ca55f5573..0000000000000000000000000000000000000000
--- a/spaces/chanhi0603/Create_subtitles_for_videos_ChatGPT/Create_subtitles_for_videos_ChatGPT/README.md
+++ /dev/null
@@ -1,12 +0,0 @@
----
-title: Create Subtitles For Videos ChatGPT 
-emoji: 🚀
-colorFrom: pink
-colorTo: pink
-sdk: gradio
-sdk_version: 3.35.2
-app_file: app.py
-pinned: false
----
-
-Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
diff --git a/spaces/chansung/zero2story/modules/llms/utils.py b/spaces/chansung/zero2story/modules/llms/utils.py
deleted file mode 100644
index 1aad3c1e178ccad984883fad58fed36e8816b258..0000000000000000000000000000000000000000
--- a/spaces/chansung/zero2story/modules/llms/utils.py
+++ /dev/null
@@ -1,8 +0,0 @@
-from modules.llms import *
-
-def get_llm_factory(llm_type: str) -> 'PaLM':
-    factory = None
-    if llm_type.lower() == 'palm':
-        factory = PaLMFactory()
-    
-    return factory
diff --git a/spaces/chendl/compositional_test/multimodal/open_flamingo/eval/task/crepe.py b/spaces/chendl/compositional_test/multimodal/open_flamingo/eval/task/crepe.py
deleted file mode 100644
index 604db5ce8eb303c259bc83a43eca2c54423658d3..0000000000000000000000000000000000000000
--- a/spaces/chendl/compositional_test/multimodal/open_flamingo/eval/task/crepe.py
+++ /dev/null
@@ -1,93 +0,0 @@
-import json
-import webdataset as wds
-from tqdm import tqdm
-from PIL import Image
-import torch
-import numpy as np
-import os
-import time
-import cv2
-import random
-import pandas as pd
-from .vl_checklist import _eval_text_image
-DATASET_ROOT = "/gpfs/u/home/LMCG/LMCGljnn/scratch-shared/cdl/instruct_data/crepe/prod_hard_negatives"
-
-
-def evaluate_crepe(
-    model,
-    tokenizer,
-    image_processor,
-    vis_embed_size=None,
-    rank=0,
-    world_size=1,
-    id=0,
-    subset=True,
-    debug=False,
-    level=4,
-    type="swap",
-):
-    if rank == 0:
-        tqdm.write(f"level: {level}")
-        tqdm.write(f"type: {type}")
-    dataset_name = "crepe"
-    media_token_id = tokenizer("<|#image#|>", add_special_tokens=False)["input_ids"][-1]
-    box_token_id = tokenizer("<|#box#|>", add_special_tokens=False)["input_ids"][-1]
-    endofobject_token_id = tokenizer("<|#endofobject#|>", add_special_tokens=False)["input_ids"][-1]
-    endofattr_token_id = tokenizer("<|#endofattr#|>", add_special_tokens=False)["input_ids"][-1]
-    endofmedia_token_id = tokenizer("<|#endofimage#|>", add_special_tokens=False)["input_ids"][-1]
-    visual_token_id = tokenizer("<|#visual#|>", add_special_tokens=False)["input_ids"][-1]
-    previsual_token_id = tokenizer("<|#previsual#|>", add_special_tokens=False)["input_ids"][-1]
-    prebox_token_id = tokenizer("<|#prebox#|>", add_special_tokens=False)["input_ids"][-1]
-    model.eval().cuda()
-    total = 0
-    correct = 0
-    assert type in ["swap"]
-    assert 4 <= level <= 12
-    filename = os.path.join(DATASET_ROOT, type, f"prod_vg_hard_negs_{type}_complexity_{level}.csv")
-    df = pd.read_csv(filename)
-    pbar = tqdm(df.iterrows(), disable=(rank != 0))
-    for ii, sample in pbar:
-        if ii % world_size != rank:
-            continue
-        text = sample.caption
-        image_path = "/gpfs/u/home/LMCG/LMCGljnn/scratch/datasets/raw/vg/VG_100K/{}.jpg".format(sample.image_id)
-        x = sample.x
-        y = sample.y
-        width = sample.width
-        height = sample.height
-        image = Image.open(image_path).convert("RGB")
-        image = image.crop((x, y, x+width, y+height))
-        image = image.resize((224, 224))
-        final_rank, final_ranks = _eval_text_image(text, image, model, tokenizer, image_processor, vis_embed_size, media_token_id, prebox_token_id, debug=debug)
-        if final_rank is None:
-            continue
-        correct += int((np.array(final_ranks) < 10).sum())
-        total += len(final_ranks)
-        if debug:
-            tqdm.write("="*80)
-        pbar.set_description(f"{text} | score: {correct / total:.4f} | {final_rank} | {final_ranks}")
-
-
-    with open(f"{dataset_name}_results_part{rank}_{id}.json", "w") as f:
-        f.write(json.dumps([total, correct]))
-    if world_size > 1:
-        torch.distributed.barrier()
-    if rank == 0:
-        total = 0
-        correct = 0
-        print(f"evaluate on rank {rank}. world size is {world_size}")
-        for rank_i in range(world_size):
-            [total_part, correct_part] = json.load(open(f"{dataset_name}_results_part{rank_i}_{id}.json"))
-            os.remove(f"{dataset_name}_results_part{rank_i}_{id}.json")
-            total += total_part
-            correct += correct_part
-        score = correct / total
-        print("score:", score, "total:", total)
-        with open(os.path.join("eval_results", f"{dataset_name}_{model.expr_name}_{model.step_num}_{int(time.time())}_{score}"), "w") as f:
-            pass
-    else:
-        score = 0.0
-    if world_size > 1:
-        torch.distributed.barrier()
-    return score
-
diff --git a/spaces/chendl/compositional_test/transformers/examples/flax/question-answering/utils_qa.py b/spaces/chendl/compositional_test/transformers/examples/flax/question-answering/utils_qa.py
deleted file mode 100644
index 23a46370d1739342a5629ec7d155d7d2f90446a3..0000000000000000000000000000000000000000
--- a/spaces/chendl/compositional_test/transformers/examples/flax/question-answering/utils_qa.py
+++ /dev/null
@@ -1,443 +0,0 @@
-# coding=utf-8
-# Copyright 2020 The HuggingFace Team All rights reserved.
-#
-# Licensed under the Apache License, Version 2.0 (the "License");
-# you may not use this file except in compliance with the License.
-# You may obtain a copy of the License at
-#
-#     http://www.apache.org/licenses/LICENSE-2.0
-#
-# Unless required by applicable law or agreed to in writing, software
-# distributed under the License is distributed on an "AS IS" BASIS,
-# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
-# See the License for the specific language governing permissions and
-# limitations under the License.
-"""
-Post-processing utilities for question answering.
-"""
-import collections
-import json
-import logging
-import os
-from typing import Optional, Tuple
-
-import numpy as np
-from tqdm.auto import tqdm
-
-
-logger = logging.getLogger(__name__)
-
-
-def postprocess_qa_predictions(
-    examples,
-    features,
-    predictions: Tuple[np.ndarray, np.ndarray],
-    version_2_with_negative: bool = False,
-    n_best_size: int = 20,
-    max_answer_length: int = 30,
-    null_score_diff_threshold: float = 0.0,
-    output_dir: Optional[str] = None,
-    prefix: Optional[str] = None,
-    log_level: Optional[int] = logging.WARNING,
-):
-    """
-    Post-processes the predictions of a question-answering model to convert them to answers that are substrings of the
-    original contexts. This is the base postprocessing functions for models that only return start and end logits.
-
-    Args:
-        examples: The non-preprocessed dataset (see the main script for more information).
-        features: The processed dataset (see the main script for more information).
-        predictions (:obj:`Tuple[np.ndarray, np.ndarray]`):
-            The predictions of the model: two arrays containing the start logits and the end logits respectively. Its
-            first dimension must match the number of elements of :obj:`features`.
-        version_2_with_negative (:obj:`bool`, `optional`, defaults to :obj:`False`):
-            Whether or not the underlying dataset contains examples with no answers.
-        n_best_size (:obj:`int`, `optional`, defaults to 20):
-            The total number of n-best predictions to generate when looking for an answer.
-        max_answer_length (:obj:`int`, `optional`, defaults to 30):
-            The maximum length of an answer that can be generated. This is needed because the start and end predictions
-            are not conditioned on one another.
-        null_score_diff_threshold (:obj:`float`, `optional`, defaults to 0):
-            The threshold used to select the null answer: if the best answer has a score that is less than the score of
-            the null answer minus this threshold, the null answer is selected for this example (note that the score of
-            the null answer for an example giving several features is the minimum of the scores for the null answer on
-            each feature: all features must be aligned on the fact they `want` to predict a null answer).
-
-            Only useful when :obj:`version_2_with_negative` is :obj:`True`.
-        output_dir (:obj:`str`, `optional`):
-            If provided, the dictionaries of predictions, n_best predictions (with their scores and logits) and, if
-            :obj:`version_2_with_negative=True`, the dictionary of the scores differences between best and null
-            answers, are saved in `output_dir`.
-        prefix (:obj:`str`, `optional`):
-            If provided, the dictionaries mentioned above are saved with `prefix` added to their names.
-        log_level (:obj:`int`, `optional`, defaults to ``logging.WARNING``):
-            ``logging`` log level (e.g., ``logging.WARNING``)
-    """
-    if len(predictions) != 2:
-        raise ValueError("`predictions` should be a tuple with two elements (start_logits, end_logits).")
-    all_start_logits, all_end_logits = predictions
-
-    if len(predictions[0]) != len(features):
-        raise ValueError(f"Got {len(predictions[0])} predictions and {len(features)} features.")
-
-    # Build a map example to its corresponding features.
-    example_id_to_index = {k: i for i, k in enumerate(examples["id"])}
-    features_per_example = collections.defaultdict(list)
-    for i, feature in enumerate(features):
-        features_per_example[example_id_to_index[feature["example_id"]]].append(i)
-
-    # The dictionaries we have to fill.
-    all_predictions = collections.OrderedDict()
-    all_nbest_json = collections.OrderedDict()
-    if version_2_with_negative:
-        scores_diff_json = collections.OrderedDict()
-
-    # Logging.
-    logger.setLevel(log_level)
-    logger.info(f"Post-processing {len(examples)} example predictions split into {len(features)} features.")
-
-    # Let's loop over all the examples!
-    for example_index, example in enumerate(tqdm(examples)):
-        # Those are the indices of the features associated to the current example.
-        feature_indices = features_per_example[example_index]
-
-        min_null_prediction = None
-        prelim_predictions = []
-
-        # Looping through all the features associated to the current example.
-        for feature_index in feature_indices:
-            # We grab the predictions of the model for this feature.
-            start_logits = all_start_logits[feature_index]
-            end_logits = all_end_logits[feature_index]
-            # This is what will allow us to map some the positions in our logits to span of texts in the original
-            # context.
-            offset_mapping = features[feature_index]["offset_mapping"]
-            # Optional `token_is_max_context`, if provided we will remove answers that do not have the maximum context
-            # available in the current feature.
-            token_is_max_context = features[feature_index].get("token_is_max_context", None)
-
-            # Update minimum null prediction.
-            feature_null_score = start_logits[0] + end_logits[0]
-            if min_null_prediction is None or min_null_prediction["score"] > feature_null_score:
-                min_null_prediction = {
-                    "offsets": (0, 0),
-                    "score": feature_null_score,
-                    "start_logit": start_logits[0],
-                    "end_logit": end_logits[0],
-                }
-
-            # Go through all possibilities for the `n_best_size` greater start and end logits.
-            start_indexes = np.argsort(start_logits)[-1 : -n_best_size - 1 : -1].tolist()
-            end_indexes = np.argsort(end_logits)[-1 : -n_best_size - 1 : -1].tolist()
-            for start_index in start_indexes:
-                for end_index in end_indexes:
-                    # Don't consider out-of-scope answers, either because the indices are out of bounds or correspond
-                    # to part of the input_ids that are not in the context.
-                    if (
-                        start_index >= len(offset_mapping)
-                        or end_index >= len(offset_mapping)
-                        or offset_mapping[start_index] is None
-                        or len(offset_mapping[start_index]) < 2
-                        or offset_mapping[end_index] is None
-                        or len(offset_mapping[end_index]) < 2
-                    ):
-                        continue
-                    # Don't consider answers with a length that is either < 0 or > max_answer_length.
-                    if end_index < start_index or end_index - start_index + 1 > max_answer_length:
-                        continue
-                    # Don't consider answer that don't have the maximum context available (if such information is
-                    # provided).
-                    if token_is_max_context is not None and not token_is_max_context.get(str(start_index), False):
-                        continue
-
-                    prelim_predictions.append(
-                        {
-                            "offsets": (offset_mapping[start_index][0], offset_mapping[end_index][1]),
-                            "score": start_logits[start_index] + end_logits[end_index],
-                            "start_logit": start_logits[start_index],
-                            "end_logit": end_logits[end_index],
-                        }
-                    )
-        if version_2_with_negative and min_null_prediction is not None:
-            # Add the minimum null prediction
-            prelim_predictions.append(min_null_prediction)
-            null_score = min_null_prediction["score"]
-
-        # Only keep the best `n_best_size` predictions.
-        predictions = sorted(prelim_predictions, key=lambda x: x["score"], reverse=True)[:n_best_size]
-
-        # Add back the minimum null prediction if it was removed because of its low score.
-        if (
-            version_2_with_negative
-            and min_null_prediction is not None
-            and not any(p["offsets"] == (0, 0) for p in predictions)
-        ):
-            predictions.append(min_null_prediction)
-
-        # Use the offsets to gather the answer text in the original context.
-        context = example["context"]
-        for pred in predictions:
-            offsets = pred.pop("offsets")
-            pred["text"] = context[offsets[0] : offsets[1]]
-
-        # In the very rare edge case we have not a single non-null prediction, we create a fake prediction to avoid
-        # failure.
-        if len(predictions) == 0 or (len(predictions) == 1 and predictions[0]["text"] == ""):
-            predictions.insert(0, {"text": "empty", "start_logit": 0.0, "end_logit": 0.0, "score": 0.0})
-
-        # Compute the softmax of all scores (we do it with numpy to stay independent from torch/tf in this file, using
-        # the LogSumExp trick).
-        scores = np.array([pred.pop("score") for pred in predictions])
-        exp_scores = np.exp(scores - np.max(scores))
-        probs = exp_scores / exp_scores.sum()
-
-        # Include the probabilities in our predictions.
-        for prob, pred in zip(probs, predictions):
-            pred["probability"] = prob
-
-        # Pick the best prediction. If the null answer is not possible, this is easy.
-        if not version_2_with_negative:
-            all_predictions[example["id"]] = predictions[0]["text"]
-        else:
-            # Otherwise we first need to find the best non-empty prediction.
-            i = 0
-            while predictions[i]["text"] == "":
-                i += 1
-            best_non_null_pred = predictions[i]
-
-            # Then we compare to the null prediction using the threshold.
-            score_diff = null_score - best_non_null_pred["start_logit"] - best_non_null_pred["end_logit"]
-            scores_diff_json[example["id"]] = float(score_diff)  # To be JSON-serializable.
-            if score_diff > null_score_diff_threshold:
-                all_predictions[example["id"]] = ""
-            else:
-                all_predictions[example["id"]] = best_non_null_pred["text"]
-
-        # Make `predictions` JSON-serializable by casting np.float back to float.
-        all_nbest_json[example["id"]] = [
-            {k: (float(v) if isinstance(v, (np.float16, np.float32, np.float64)) else v) for k, v in pred.items()}
-            for pred in predictions
-        ]
-
-    # If we have an output_dir, let's save all those dicts.
-    if output_dir is not None:
-        if not os.path.isdir(output_dir):
-            raise EnvironmentError(f"{output_dir} is not a directory.")
-
-        prediction_file = os.path.join(
-            output_dir, "predictions.json" if prefix is None else f"{prefix}_predictions.json"
-        )
-        nbest_file = os.path.join(
-            output_dir, "nbest_predictions.json" if prefix is None else f"{prefix}_nbest_predictions.json"
-        )
-        if version_2_with_negative:
-            null_odds_file = os.path.join(
-                output_dir, "null_odds.json" if prefix is None else f"{prefix}_null_odds.json"
-            )
-
-        logger.info(f"Saving predictions to {prediction_file}.")
-        with open(prediction_file, "w") as writer:
-            writer.write(json.dumps(all_predictions, indent=4) + "\n")
-        logger.info(f"Saving nbest_preds to {nbest_file}.")
-        with open(nbest_file, "w") as writer:
-            writer.write(json.dumps(all_nbest_json, indent=4) + "\n")
-        if version_2_with_negative:
-            logger.info(f"Saving null_odds to {null_odds_file}.")
-            with open(null_odds_file, "w") as writer:
-                writer.write(json.dumps(scores_diff_json, indent=4) + "\n")
-
-    return all_predictions
-
-
-def postprocess_qa_predictions_with_beam_search(
-    examples,
-    features,
-    predictions: Tuple[np.ndarray, np.ndarray],
-    version_2_with_negative: bool = False,
-    n_best_size: int = 20,
-    max_answer_length: int = 30,
-    start_n_top: int = 5,
-    end_n_top: int = 5,
-    output_dir: Optional[str] = None,
-    prefix: Optional[str] = None,
-    log_level: Optional[int] = logging.WARNING,
-):
-    """
-    Post-processes the predictions of a question-answering model with beam search to convert them to answers that are substrings of the
-    original contexts. This is the postprocessing functions for models that return start and end logits, indices, as well as
-    cls token predictions.
-
-    Args:
-        examples: The non-preprocessed dataset (see the main script for more information).
-        features: The processed dataset (see the main script for more information).
-        predictions (:obj:`Tuple[np.ndarray, np.ndarray]`):
-            The predictions of the model: two arrays containing the start logits and the end logits respectively. Its
-            first dimension must match the number of elements of :obj:`features`.
-        version_2_with_negative (:obj:`bool`, `optional`, defaults to :obj:`False`):
-            Whether or not the underlying dataset contains examples with no answers.
-        n_best_size (:obj:`int`, `optional`, defaults to 20):
-            The total number of n-best predictions to generate when looking for an answer.
-        max_answer_length (:obj:`int`, `optional`, defaults to 30):
-            The maximum length of an answer that can be generated. This is needed because the start and end predictions
-            are not conditioned on one another.
-        start_n_top (:obj:`int`, `optional`, defaults to 5):
-            The number of top start logits too keep when searching for the :obj:`n_best_size` predictions.
-        end_n_top (:obj:`int`, `optional`, defaults to 5):
-            The number of top end logits too keep when searching for the :obj:`n_best_size` predictions.
-        output_dir (:obj:`str`, `optional`):
-            If provided, the dictionaries of predictions, n_best predictions (with their scores and logits) and, if
-            :obj:`version_2_with_negative=True`, the dictionary of the scores differences between best and null
-            answers, are saved in `output_dir`.
-        prefix (:obj:`str`, `optional`):
-            If provided, the dictionaries mentioned above are saved with `prefix` added to their names.
-        log_level (:obj:`int`, `optional`, defaults to ``logging.WARNING``):
-            ``logging`` log level (e.g., ``logging.WARNING``)
-    """
-    if len(predictions) != 5:
-        raise ValueError("`predictions` should be a tuple with five elements.")
-    start_top_log_probs, start_top_index, end_top_log_probs, end_top_index, cls_logits = predictions
-
-    if len(predictions[0]) != len(features):
-        raise ValueError(f"Got {len(predictions[0])} predictions and {len(features)} features.")
-
-    # Build a map example to its corresponding features.
-    example_id_to_index = {k: i for i, k in enumerate(examples["id"])}
-    features_per_example = collections.defaultdict(list)
-    for i, feature in enumerate(features):
-        features_per_example[example_id_to_index[feature["example_id"]]].append(i)
-
-    # The dictionaries we have to fill.
-    all_predictions = collections.OrderedDict()
-    all_nbest_json = collections.OrderedDict()
-    scores_diff_json = collections.OrderedDict() if version_2_with_negative else None
-
-    # Logging.
-    logger.setLevel(log_level)
-    logger.info(f"Post-processing {len(examples)} example predictions split into {len(features)} features.")
-
-    # Let's loop over all the examples!
-    for example_index, example in enumerate(tqdm(examples)):
-        # Those are the indices of the features associated to the current example.
-        feature_indices = features_per_example[example_index]
-
-        min_null_score = None
-        prelim_predictions = []
-
-        # Looping through all the features associated to the current example.
-        for feature_index in feature_indices:
-            # We grab the predictions of the model for this feature.
-            start_log_prob = start_top_log_probs[feature_index]
-            start_indexes = start_top_index[feature_index]
-            end_log_prob = end_top_log_probs[feature_index]
-            end_indexes = end_top_index[feature_index]
-            feature_null_score = cls_logits[feature_index]
-            # This is what will allow us to map some the positions in our logits to span of texts in the original
-            # context.
-            offset_mapping = features[feature_index]["offset_mapping"]
-            # Optional `token_is_max_context`, if provided we will remove answers that do not have the maximum context
-            # available in the current feature.
-            token_is_max_context = features[feature_index].get("token_is_max_context", None)
-
-            # Update minimum null prediction
-            if min_null_score is None or feature_null_score < min_null_score:
-                min_null_score = feature_null_score
-
-            # Go through all possibilities for the `n_start_top`/`n_end_top` greater start and end logits.
-            for i in range(start_n_top):
-                for j in range(end_n_top):
-                    start_index = int(start_indexes[i])
-                    j_index = i * end_n_top + j
-                    end_index = int(end_indexes[j_index])
-                    # Don't consider out-of-scope answers (last part of the test should be unnecessary because of the
-                    # p_mask but let's not take any risk)
-                    if (
-                        start_index >= len(offset_mapping)
-                        or end_index >= len(offset_mapping)
-                        or offset_mapping[start_index] is None
-                        or len(offset_mapping[start_index]) < 2
-                        or offset_mapping[end_index] is None
-                        or len(offset_mapping[end_index]) < 2
-                    ):
-                        continue
-
-                    # Don't consider answers with a length negative or > max_answer_length.
-                    if end_index < start_index or end_index - start_index + 1 > max_answer_length:
-                        continue
-                    # Don't consider answer that don't have the maximum context available (if such information is
-                    # provided).
-                    if token_is_max_context is not None and not token_is_max_context.get(str(start_index), False):
-                        continue
-                    prelim_predictions.append(
-                        {
-                            "offsets": (offset_mapping[start_index][0], offset_mapping[end_index][1]),
-                            "score": start_log_prob[i] + end_log_prob[j_index],
-                            "start_log_prob": start_log_prob[i],
-                            "end_log_prob": end_log_prob[j_index],
-                        }
-                    )
-
-        # Only keep the best `n_best_size` predictions.
-        predictions = sorted(prelim_predictions, key=lambda x: x["score"], reverse=True)[:n_best_size]
-
-        # Use the offsets to gather the answer text in the original context.
-        context = example["context"]
-        for pred in predictions:
-            offsets = pred.pop("offsets")
-            pred["text"] = context[offsets[0] : offsets[1]]
-
-        # In the very rare edge case we have not a single non-null prediction, we create a fake prediction to avoid
-        # failure.
-        if len(predictions) == 0:
-            # Without predictions min_null_score is going to be None and None will cause an exception later
-            min_null_score = -2e-6
-            predictions.insert(0, {"text": "", "start_logit": -1e-6, "end_logit": -1e-6, "score": min_null_score})
-
-        # Compute the softmax of all scores (we do it with numpy to stay independent from torch/tf in this file, using
-        # the LogSumExp trick).
-        scores = np.array([pred.pop("score") for pred in predictions])
-        exp_scores = np.exp(scores - np.max(scores))
-        probs = exp_scores / exp_scores.sum()
-
-        # Include the probabilities in our predictions.
-        for prob, pred in zip(probs, predictions):
-            pred["probability"] = prob
-
-        # Pick the best prediction and set the probability for the null answer.
-        all_predictions[example["id"]] = predictions[0]["text"]
-        if version_2_with_negative:
-            scores_diff_json[example["id"]] = float(min_null_score)
-
-        # Make `predictions` JSON-serializable by casting np.float back to float.
-        all_nbest_json[example["id"]] = [
-            {k: (float(v) if isinstance(v, (np.float16, np.float32, np.float64)) else v) for k, v in pred.items()}
-            for pred in predictions
-        ]
-
-    # If we have an output_dir, let's save all those dicts.
-    if output_dir is not None:
-        if not os.path.isdir(output_dir):
-            raise EnvironmentError(f"{output_dir} is not a directory.")
-
-        prediction_file = os.path.join(
-            output_dir, "predictions.json" if prefix is None else f"{prefix}_predictions.json"
-        )
-        nbest_file = os.path.join(
-            output_dir, "nbest_predictions.json" if prefix is None else f"{prefix}_nbest_predictions.json"
-        )
-        if version_2_with_negative:
-            null_odds_file = os.path.join(
-                output_dir, "null_odds.json" if prefix is None else f"{prefix}_null_odds.json"
-            )
-
-        logger.info(f"Saving predictions to {prediction_file}.")
-        with open(prediction_file, "w") as writer:
-            writer.write(json.dumps(all_predictions, indent=4) + "\n")
-        logger.info(f"Saving nbest_preds to {nbest_file}.")
-        with open(nbest_file, "w") as writer:
-            writer.write(json.dumps(all_nbest_json, indent=4) + "\n")
-        if version_2_with_negative:
-            logger.info(f"Saving null_odds to {null_odds_file}.")
-            with open(null_odds_file, "w") as writer:
-                writer.write(json.dumps(scores_diff_json, indent=4) + "\n")
-
-    return all_predictions, scores_diff_json
diff --git a/spaces/chendl/compositional_test/transformers/examples/research_projects/bert-loses-patience/test_run_glue_with_pabee.py b/spaces/chendl/compositional_test/transformers/examples/research_projects/bert-loses-patience/test_run_glue_with_pabee.py
deleted file mode 100644
index 6a084d0741d5f59d6a7db1e06fffd87b5e5dbd93..0000000000000000000000000000000000000000
--- a/spaces/chendl/compositional_test/transformers/examples/research_projects/bert-loses-patience/test_run_glue_with_pabee.py
+++ /dev/null
@@ -1,51 +0,0 @@
-import argparse
-import logging
-import sys
-from unittest.mock import patch
-
-import run_glue_with_pabee
-
-from transformers.testing_utils import TestCasePlus
-
-
-logging.basicConfig(level=logging.DEBUG)
-
-logger = logging.getLogger()
-
-
-def get_setup_file():
-    parser = argparse.ArgumentParser()
-    parser.add_argument("-f")
-    args = parser.parse_args()
-    return args.f
-
-
-class PabeeTests(TestCasePlus):
-    def test_run_glue(self):
-        stream_handler = logging.StreamHandler(sys.stdout)
-        logger.addHandler(stream_handler)
-
-        tmp_dir = self.get_auto_remove_tmp_dir()
-        testargs = f"""
-            run_glue_with_pabee.py
-            --model_type albert
-            --model_name_or_path albert-base-v2
-            --data_dir ./tests/fixtures/tests_samples/MRPC/
-            --output_dir {tmp_dir}
-            --overwrite_output_dir
-            --task_name mrpc
-            --do_train
-            --do_eval
-            --per_gpu_train_batch_size=2
-            --per_gpu_eval_batch_size=1
-            --learning_rate=2e-5
-            --max_steps=50
-            --warmup_steps=2
-            --seed=42
-            --max_seq_length=128
-            """.split()
-
-        with patch.object(sys, "argv", testargs):
-            result = run_glue_with_pabee.main()
-            for value in result.values():
-                self.assertGreaterEqual(value, 0.75)
diff --git a/spaces/chriscelaya/merve-chatgpt-prompts-bart-long/app.py b/spaces/chriscelaya/merve-chatgpt-prompts-bart-long/app.py
deleted file mode 100644
index 5fd85653f44ca7ff508177a6fcd37fb1fb552fa7..0000000000000000000000000000000000000000
--- a/spaces/chriscelaya/merve-chatgpt-prompts-bart-long/app.py
+++ /dev/null
@@ -1,3 +0,0 @@
-import gradio as gr
-
-gr.Interface.load("models/merve/chatgpt-prompts-bart-long").launch()
\ No newline at end of file
diff --git a/spaces/chuan-hd/law-assistant-chatbot/.venv/lib/python3.11/site-packages/aiohttp/worker.py b/spaces/chuan-hd/law-assistant-chatbot/.venv/lib/python3.11/site-packages/aiohttp/worker.py
deleted file mode 100644
index f1302899f2f0e078613e69d9a8103ecc00bae95d..0000000000000000000000000000000000000000
--- a/spaces/chuan-hd/law-assistant-chatbot/.venv/lib/python3.11/site-packages/aiohttp/worker.py
+++ /dev/null
@@ -1,269 +0,0 @@
-"""Async gunicorn worker for aiohttp.web"""
-
-import asyncio
-import os
-import re
-import signal
-import sys
-from types import FrameType
-from typing import Any, Awaitable, Callable, Optional, Union  # noqa
-
-from gunicorn.config import AccessLogFormat as GunicornAccessLogFormat
-from gunicorn.workers import base
-
-from aiohttp import web
-
-from .helpers import set_result
-from .web_app import Application
-from .web_log import AccessLogger
-
-try:
-    import ssl
-
-    SSLContext = ssl.SSLContext
-except ImportError:  # pragma: no cover
-    ssl = None  # type: ignore[assignment]
-    SSLContext = object  # type: ignore[misc,assignment]
-
-
-__all__ = ("GunicornWebWorker", "GunicornUVLoopWebWorker", "GunicornTokioWebWorker")
-
-
-class GunicornWebWorker(base.Worker):  # type: ignore[misc,no-any-unimported]
-
-    DEFAULT_AIOHTTP_LOG_FORMAT = AccessLogger.LOG_FORMAT
-    DEFAULT_GUNICORN_LOG_FORMAT = GunicornAccessLogFormat.default
-
-    def __init__(self, *args: Any, **kw: Any) -> None:  # pragma: no cover
-        super().__init__(*args, **kw)
-
-        self._task: Optional[asyncio.Task[None]] = None
-        self.exit_code = 0
-        self._notify_waiter: Optional[asyncio.Future[bool]] = None
-
-    def init_process(self) -> None:
-        # create new event_loop after fork
-        asyncio.get_event_loop().close()
-
-        self.loop = asyncio.new_event_loop()
-        asyncio.set_event_loop(self.loop)
-
-        super().init_process()
-
-    def run(self) -> None:
-        self._task = self.loop.create_task(self._run())
-
-        try:  # ignore all finalization problems
-            self.loop.run_until_complete(self._task)
-        except Exception:
-            self.log.exception("Exception in gunicorn worker")
-        self.loop.run_until_complete(self.loop.shutdown_asyncgens())
-        self.loop.close()
-
-        sys.exit(self.exit_code)
-
-    async def _run(self) -> None:
-        runner = None
-        if isinstance(self.wsgi, Application):
-            app = self.wsgi
-        elif asyncio.iscoroutinefunction(self.wsgi):
-            wsgi = await self.wsgi()
-            if isinstance(wsgi, web.AppRunner):
-                runner = wsgi
-                app = runner.app
-            else:
-                app = wsgi
-        else:
-            raise RuntimeError(
-                "wsgi app should be either Application or "
-                "async function returning Application, got {}".format(self.wsgi)
-            )
-
-        if runner is None:
-            access_log = self.log.access_log if self.cfg.accesslog else None
-            runner = web.AppRunner(
-                app,
-                logger=self.log,
-                keepalive_timeout=self.cfg.keepalive,
-                access_log=access_log,
-                access_log_format=self._get_valid_log_format(
-                    self.cfg.access_log_format
-                ),
-            )
-        await runner.setup()
-
-        ctx = self._create_ssl_context(self.cfg) if self.cfg.is_ssl else None
-
-        runner = runner
-        assert runner is not None
-        server = runner.server
-        assert server is not None
-        for sock in self.sockets:
-            site = web.SockSite(
-                runner,
-                sock,
-                ssl_context=ctx,
-                shutdown_timeout=self.cfg.graceful_timeout / 100 * 95,
-            )
-            await site.start()
-
-        # If our parent changed then we shut down.
-        pid = os.getpid()
-        try:
-            while self.alive:  # type: ignore[has-type]
-                self.notify()
-
-                cnt = server.requests_count
-                if self.cfg.max_requests and cnt > self.cfg.max_requests:
-                    self.alive = False
-                    self.log.info("Max requests, shutting down: %s", self)
-
-                elif pid == os.getpid() and self.ppid != os.getppid():
-                    self.alive = False
-                    self.log.info("Parent changed, shutting down: %s", self)
-                else:
-                    await self._wait_next_notify()
-        except BaseException:
-            pass
-
-        await runner.cleanup()
-
-    def _wait_next_notify(self) -> "asyncio.Future[bool]":
-        self._notify_waiter_done()
-
-        loop = self.loop
-        assert loop is not None
-        self._notify_waiter = waiter = loop.create_future()
-        self.loop.call_later(1.0, self._notify_waiter_done, waiter)
-
-        return waiter
-
-    def _notify_waiter_done(
-        self, waiter: Optional["asyncio.Future[bool]"] = None
-    ) -> None:
-        if waiter is None:
-            waiter = self._notify_waiter
-        if waiter is not None:
-            set_result(waiter, True)
-
-        if waiter is self._notify_waiter:
-            self._notify_waiter = None
-
-    def init_signals(self) -> None:
-        # Set up signals through the event loop API.
-
-        self.loop.add_signal_handler(
-            signal.SIGQUIT, self.handle_quit, signal.SIGQUIT, None
-        )
-
-        self.loop.add_signal_handler(
-            signal.SIGTERM, self.handle_exit, signal.SIGTERM, None
-        )
-
-        self.loop.add_signal_handler(
-            signal.SIGINT, self.handle_quit, signal.SIGINT, None
-        )
-
-        self.loop.add_signal_handler(
-            signal.SIGWINCH, self.handle_winch, signal.SIGWINCH, None
-        )
-
-        self.loop.add_signal_handler(
-            signal.SIGUSR1, self.handle_usr1, signal.SIGUSR1, None
-        )
-
-        self.loop.add_signal_handler(
-            signal.SIGABRT, self.handle_abort, signal.SIGABRT, None
-        )
-
-        # Don't let SIGTERM and SIGUSR1 disturb active requests
-        # by interrupting system calls
-        signal.siginterrupt(signal.SIGTERM, False)
-        signal.siginterrupt(signal.SIGUSR1, False)
-        # Reset signals so Gunicorn doesn't swallow subprocess return codes
-        # See: https://github.com/aio-libs/aiohttp/issues/6130
-        if sys.version_info < (3, 8):
-            # Starting from Python 3.8,
-            # the default child watcher is ThreadedChildWatcher.
-            # The watcher doesn't depend on SIGCHLD signal,
-            # there is no need to reset it.
-            signal.signal(signal.SIGCHLD, signal.SIG_DFL)
-
-    def handle_quit(self, sig: int, frame: FrameType) -> None:
-        self.alive = False
-
-        # worker_int callback
-        self.cfg.worker_int(self)
-
-        # wakeup closing process
-        self._notify_waiter_done()
-
-    def handle_abort(self, sig: int, frame: FrameType) -> None:
-        self.alive = False
-        self.exit_code = 1
-        self.cfg.worker_abort(self)
-        sys.exit(1)
-
-    @staticmethod
-    def _create_ssl_context(cfg: Any) -> "SSLContext":
-        """Creates SSLContext instance for usage in asyncio.create_server.
-
-        See ssl.SSLSocket.__init__ for more details.
-        """
-        if ssl is None:  # pragma: no cover
-            raise RuntimeError("SSL is not supported.")
-
-        ctx = ssl.SSLContext(cfg.ssl_version)
-        ctx.load_cert_chain(cfg.certfile, cfg.keyfile)
-        ctx.verify_mode = cfg.cert_reqs
-        if cfg.ca_certs:
-            ctx.load_verify_locations(cfg.ca_certs)
-        if cfg.ciphers:
-            ctx.set_ciphers(cfg.ciphers)
-        return ctx
-
-    def _get_valid_log_format(self, source_format: str) -> str:
-        if source_format == self.DEFAULT_GUNICORN_LOG_FORMAT:
-            return self.DEFAULT_AIOHTTP_LOG_FORMAT
-        elif re.search(r"%\([^\)]+\)", source_format):
-            raise ValueError(
-                "Gunicorn's style options in form of `%(name)s` are not "
-                "supported for the log formatting. Please use aiohttp's "
-                "format specification to configure access log formatting: "
-                "http://docs.aiohttp.org/en/stable/logging.html"
-                "#format-specification"
-            )
-        else:
-            return source_format
-
-
-class GunicornUVLoopWebWorker(GunicornWebWorker):
-    def init_process(self) -> None:
-        import uvloop
-
-        # Close any existing event loop before setting a
-        # new policy.
-        asyncio.get_event_loop().close()
-
-        # Setup uvloop policy, so that every
-        # asyncio.get_event_loop() will create an instance
-        # of uvloop event loop.
-        asyncio.set_event_loop_policy(uvloop.EventLoopPolicy())
-
-        super().init_process()
-
-
-class GunicornTokioWebWorker(GunicornWebWorker):
-    def init_process(self) -> None:  # pragma: no cover
-        import tokio
-
-        # Close any existing event loop before setting a
-        # new policy.
-        asyncio.get_event_loop().close()
-
-        # Setup tokio policy, so that every
-        # asyncio.get_event_loop() will create an instance
-        # of tokio event loop.
-        asyncio.set_event_loop_policy(tokio.EventLoopPolicy())
-
-        super().init_process()
diff --git a/spaces/chuan-hd/law-assistant-chatbot/.venv/lib/python3.11/site-packages/gradio/components/__init__.py b/spaces/chuan-hd/law-assistant-chatbot/.venv/lib/python3.11/site-packages/gradio/components/__init__.py
deleted file mode 100644
index 96a64dd9b2e1619052547eb220e9ab904eaf8fdd..0000000000000000000000000000000000000000
--- a/spaces/chuan-hd/law-assistant-chatbot/.venv/lib/python3.11/site-packages/gradio/components/__init__.py
+++ /dev/null
@@ -1,116 +0,0 @@
-from gradio.components.annotated_image import AnnotatedImage
-from gradio.components.audio import Audio
-from gradio.components.bar_plot import BarPlot
-from gradio.components.base import (
-    Column,
-    Component,
-    Form,
-    FormComponent,
-    IOComponent,
-    Row,
-    _Keywords,
-    component,
-    get_component_instance,
-)
-from gradio.components.button import Button
-from gradio.components.carousel import Carousel
-from gradio.components.chatbot import Chatbot
-from gradio.components.checkbox import Checkbox
-from gradio.components.checkboxgroup import CheckboxGroup
-from gradio.components.clear_button import ClearButton
-from gradio.components.code import Code
-from gradio.components.color_picker import ColorPicker
-from gradio.components.dataframe import Dataframe
-from gradio.components.dataset import Dataset
-from gradio.components.dropdown import Dropdown
-from gradio.components.duplicate_button import DuplicateButton
-from gradio.components.file import File
-from gradio.components.gallery import Gallery
-from gradio.components.highlighted_text import HighlightedText
-from gradio.components.html import HTML
-from gradio.components.image import Image
-from gradio.components.interpretation import Interpretation
-from gradio.components.json_component import JSON
-from gradio.components.label import Label
-from gradio.components.line_plot import LinePlot
-from gradio.components.markdown import Markdown
-from gradio.components.model3d import Model3D
-from gradio.components.number import Number
-from gradio.components.plot import Plot
-from gradio.components.radio import Radio
-from gradio.components.scatter_plot import ScatterPlot
-from gradio.components.slider import Slider
-from gradio.components.state import State, Variable
-from gradio.components.status_tracker import StatusTracker
-from gradio.components.textbox import Textbox
-from gradio.components.timeseries import Timeseries
-from gradio.components.upload_button import UploadButton
-from gradio.components.video import Video
-
-Text = Textbox
-DataFrame = Dataframe
-Highlightedtext = HighlightedText
-Annotatedimage = AnnotatedImage
-Highlight = HighlightedText
-Checkboxgroup = CheckboxGroup
-TimeSeries = Timeseries
-Json = JSON
-
-__all__ = [
-    "Audio",
-    "BarPlot",
-    "Button",
-    "Carousel",
-    "Chatbot",
-    "ClearButton",
-    "Component",
-    "component",
-    "get_component_instance",
-    "_Keywords",
-    "Checkbox",
-    "CheckboxGroup",
-    "Code",
-    "ColorPicker",
-    "Column",
-    "Dataframe",
-    "DataFrame",
-    "Dataset",
-    "DuplicateButton",
-    "Form",
-    "FormComponent",
-    "Gallery",
-    "HTML",
-    "Image",
-    "IOComponent",
-    "Interpretation",
-    "JSON",
-    "Json",
-    "Label",
-    "LinePlot",
-    "Markdown",
-    "Textbox",
-    "Dropdown",
-    "Model3D",
-    "File",
-    "HighlightedText",
-    "AnnotatedImage",
-    "CheckboxGroup",
-    "Timeseries",
-    "Text",
-    "Highlightedtext",
-    "Annotatedimage",
-    "Highlight",
-    "Checkboxgroup",
-    "TimeSeries",
-    "Number",
-    "Plot",
-    "Radio",
-    "Row",
-    "ScatterPlot",
-    "Slider",
-    "State",
-    "Variable",
-    "StatusTracker",
-    "UploadButton",
-    "Video",
-]
diff --git a/spaces/chumeng/anime-ai-detect/README.md b/spaces/chumeng/anime-ai-detect/README.md
deleted file mode 100644
index 952c183fd69ccb1664b4236b6132fc6d0358c7de..0000000000000000000000000000000000000000
--- a/spaces/chumeng/anime-ai-detect/README.md
+++ /dev/null
@@ -1,13 +0,0 @@
----
-title: Anime Ai Detect
-emoji: 🤖
-colorFrom: green
-colorTo: purple
-sdk: gradio
-sdk_version: 3.15.0
-app_file: app.py
-pinned: true
-duplicated_from: saltacc/anime-ai-detect
----
-
-Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
diff --git a/spaces/chuoguejiofor/CatBreedClassifier/app.py b/spaces/chuoguejiofor/CatBreedClassifier/app.py
deleted file mode 100644
index 9557dcf82c89d7ce5a3613308fa4e7ec67ddd02c..0000000000000000000000000000000000000000
--- a/spaces/chuoguejiofor/CatBreedClassifier/app.py
+++ /dev/null
@@ -1,15 +0,0 @@
-import gradio as gr
-from fastai.vision.all import *
-
-learn = load_learner('model.pkl')
-
-categories = ('Abyssinian','American Shorthair', 'American Wirehair', 'Bengal', 'Bombay', 'British Shorthair', 'Burmese', 'Chartreux','Rex','Egyptian Mau','Japanese Bobtail','Korat', 'Manx', 'Ocicat', 'Oriental Shorthair', 'Russian Blue', 'Scottish Fold', 'Siamese', 'Sphynx', 'Maine Coon','Himalayan', 'Persian')
-def classify_image(img):
-    pred,idx,probs = learn.predict(img)
-    return dict(zip(categories, map(float, probs)))
-
-image = gr.inputs.Image(shape=(192,192))
-label = gr.outputs.Label()
-
-intf = gr.Interface(fn=classify_image, inputs=image, outputs=label)
-intf.launch(inline=False)
\ No newline at end of file
diff --git a/spaces/cihyFjudo/fairness-paper-search/Days Of Tafree Dual Audio Eng Hindi 1080pl The Best Way to Enjoy the College Days.md b/spaces/cihyFjudo/fairness-paper-search/Days Of Tafree Dual Audio Eng Hindi 1080pl The Best Way to Enjoy the College Days.md
deleted file mode 100644
index 4e2c6a0a9b41015bf80ad940298685a5f12d54f1..0000000000000000000000000000000000000000
--- a/spaces/cihyFjudo/fairness-paper-search/Days Of Tafree Dual Audio Eng Hindi 1080pl The Best Way to Enjoy the College Days.md	
+++ /dev/null
@@ -1,6 +0,0 @@
-<h2>Days Of Tafree Dual Audio Eng Hindi 1080pl</h2><br /><p><b><b>Download Zip</b> --->>> <a href="https://tinurli.com/2uwj6q">https://tinurli.com/2uwj6q</a></b></p><br /><br />
-
- aaccfb2cb3<br />
-<br />
-<br />
-<p></p>
diff --git a/spaces/cihyFjudo/fairness-paper-search/Finite Element Analysis Senthil Pdf Downloadl A Step-by-Step Tutorial on FEM.md b/spaces/cihyFjudo/fairness-paper-search/Finite Element Analysis Senthil Pdf Downloadl A Step-by-Step Tutorial on FEM.md
deleted file mode 100644
index 35171a4e9131486150a1fa117f9aff5d2ab61563..0000000000000000000000000000000000000000
--- a/spaces/cihyFjudo/fairness-paper-search/Finite Element Analysis Senthil Pdf Downloadl A Step-by-Step Tutorial on FEM.md	
+++ /dev/null
@@ -1,6 +0,0 @@
-
-<p>This book also has exercises! The text material evolved from over 50 years of combined teaching experience it deals with a formulation and application of the finite element method. A meaningful course can be constructed from a subset of the chapters in this book for a quarter course; instructions for such use are given in the preface. The course material is organized in three chronological units of one month each:</p>
-<h2>Finite Element Analysis Senthil Pdf Downloadl</h2><br /><p><b><b>Download File</b> &#127383; <a href="https://tinurli.com/2uwj6f">https://tinurli.com/2uwj6f</a></b></p><br /><br />
-<p>This book provides a simple, basic approach to the course material that can be understood by both undergraduate and graduate students without the usual prerequisites (i.e. structural analysis). The book is written primarily as a basic learning tool for the undergraduate student in civil and mechanical engineering whose main interest is in stress analysis and heat transfer. The text is geared toward those who want to apply the finite element method as a tool to solve practical physical problems.</p> aaccfb2cb3<br />
-<br />
-<br />
\ No newline at end of file
diff --git a/spaces/cihyFjudo/fairness-paper-search/Realterm Spy Driver Download A Comprehensive Manual for Realterm Users.md b/spaces/cihyFjudo/fairness-paper-search/Realterm Spy Driver Download A Comprehensive Manual for Realterm Users.md
deleted file mode 100644
index 66d1937b94d94380db8f32cadd9c031a3d766558..0000000000000000000000000000000000000000
--- a/spaces/cihyFjudo/fairness-paper-search/Realterm Spy Driver Download A Comprehensive Manual for Realterm Users.md	
+++ /dev/null
@@ -1,15 +0,0 @@
-
-<p>Thought I would post a follow-up to see if anyone has heard anything from the developer on this. I just donated to support this development. Unfortunately, after donating and you're redirected to the driver download page, you learn at that moment that it only supports 32 bit. Any word on a 64-bit version? I've seen several related posts going back at least a few years and most of them seem to have been ignored by the developer.</p>
-<h2>Realterm Spy Driver Download</h2><br /><p><b><b>Download Zip</b> &rArr;&rArr;&rArr; <a href="https://tinurli.com/2uwkPi">https://tinurli.com/2uwkPi</a></b></p><br /><br />
-<p>I received my drivers and installed them successfully. However, now I get the message that they are not properly installed, even after a reinstall. All I can imagine now is that it is related to having updated RealTerm or to running with reduced (non-admin) permissions. Any ideas?</p>
-<p>Haven't heard back. Sad because it appears the author is actively monitoring this site. If the drivers are not available anymore, then a new stable release without the donate/get drivers popup should be made the default download.</p>
-<p>EOBD-Facile<br />The people that brought us the iOS version of EOBD-Facile now offer a Mac OSX version. The free download allows you to read trouble codes, while the paid version offers full functionality. See the Outils OBD Facile YouTube page for additional info.</p>
-<p>Movi and Movi Pro<br />Only for the Mac, there are two versions of this software. The standard version provides all the basic OBD functions, while Movi Pro adds more bells and whistles. If you just want to try it out, the download will operate in demo mode.</p>
-<p>Tera Term is a free software utility offered by the current development team: Tera Term Project. The free download package is<strong> lightweight </strong>and does not require a lot of storage space on PC computers and laptops.</p>
-<p>Both the old releases and the latest updates are available to download and install. The developers update the software on a <strong>relatively consistent </strong>basis. You can visit their home page in your website browser to view their most recent <strong>software update</strong>, privacy policy, copyright terms, etc.</p>
-<p></p>
-<p>The devicetree configuration allows you to use a minimal pin configuration.Connect all unused pins to the fixed logic level as instructed in the official documentation.For example, csd-gpios is an optional pin that sets the device into sleep mode.If this pin is not controlled by the driver, it must be connected to the fixed logic level.</p>
-<p>On the nRF5340 development kit, the physical UART interface of the application core is used for communication with the tester device.This sample uses the IPC UART driver for sending responses and receiving commands through the UART interface of the application core.</p>
-<p>make sure you have the FDTI drivers installed<br/>make sure you have connected the buspirate and the red led is lit <br/>if you were on preorder 2 make sure you have uploaded the firmware see this for more information -pirate-firmware-upgrades/ and =100.0<br/></p> aaccfb2cb3<br />
-<br />
-<br />
\ No newline at end of file
diff --git a/spaces/cleanmaster/akagi-sovits3/vdecoder/__init__.py b/spaces/cleanmaster/akagi-sovits3/vdecoder/__init__.py
deleted file mode 100644
index e69de29bb2d1d6434b8b29ae775ad8c2e48c5391..0000000000000000000000000000000000000000
diff --git a/spaces/colakin/video-generater/public/ffmpeg/compat/solaris/make_sunver.pl b/spaces/colakin/video-generater/public/ffmpeg/compat/solaris/make_sunver.pl
deleted file mode 100644
index 0e9ed1d351ec2ac65817609dd929100fb49e43ae..0000000000000000000000000000000000000000
--- a/spaces/colakin/video-generater/public/ffmpeg/compat/solaris/make_sunver.pl
+++ /dev/null
@@ -1,352 +0,0 @@
-#!/usr/bin/env perl
-
-# make_sunver.pl
-#
-#   Copyright (C) 2010, 2011, 2012, 2013
-#   Free Software Foundation, Inc.
-#
-# This file is free software; you can redistribute it and/or modify it
-# under the terms of the GNU General Public License as published by
-# the Free Software Foundation; either version 3 of the License, or
-# (at your option) any later version.
-#
-# This program is distributed in the hope that it will be useful, but
-# WITHOUT ANY WARRANTY; without even the implied warranty of
-# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
-# General Public License for more details.
-#
-# You should have received a copy of the GNU General Public License
-# along with this program; see the file COPYING.GPLv3.  If not see
-# <http://www.gnu.org/licenses/>.
-
-# This script takes at least two arguments, a GNU style version script and
-# a list of object and archive files, and generates a corresponding Sun
-# style version script as follows:
-#
-# Each glob pattern, C++ mangled pattern or literal in the input script is
-# matched against all global symbols in the input objects, emitting those
-# that matched (or nothing if no match was found).
-# A comment with the original pattern and its type is left in the output
-# file to make it easy to understand the matches.
-#
-# It uses elfdump when present (native), GNU readelf otherwise.
-# It depends on the GNU version of c++filt, since it must understand the
-# GNU mangling style.
-
-use FileHandle;
-use IPC::Open2;
-
-# Enforce C locale.
-$ENV{'LC_ALL'} = "C";
-$ENV{'LANG'} = "C";
-
-# Input version script, GNU style.
-my $symvers = shift;
-
-##########
-# Get all the symbols from the library, match them, and add them to a hash.
-
-my %sym_hash = ();
-
-# List of objects and archives to process.
-my @OBJECTS = ();
-
-# List of shared objects to omit from processing.
-my @SHAREDOBJS = ();
-
-# Filter out those input archives that have corresponding shared objects to
-# avoid adding all symbols matched in the archive to the output map.
-foreach $file (@ARGV) {
-    if (($so = $file) =~ s/\.a$/.so/ && -e $so) {
-    printf STDERR "omitted $file -> $so\n";
-    push (@SHAREDOBJS, $so);
-    } else {
-    push (@OBJECTS, $file);
-    }
-}
-
-# We need to detect and ignore hidden symbols.  Solaris nm can only detect
-# this in the harder to parse default output format, and GNU nm not at all,
-# so use elfdump -s in the native case and GNU readelf -s otherwise.
-# GNU objdump -t cannot be used since it produces a variable number of
-# columns.
-
-# The path to elfdump.
-my $elfdump = "/usr/ccs/bin/elfdump";
-
-if (-f $elfdump) {
-    open ELFDUMP,$elfdump.' -s '.(join ' ',@OBJECTS).'|' or die $!;
-    my $skip_arsym = 0;
-
-    while (<ELFDUMP>) {
-    chomp;
-
-    # Ignore empty lines.
-    if (/^$/) {
-        # End of archive symbol table, stop skipping.
-        $skip_arsym = 0 if $skip_arsym;
-        next;
-    }
-
-    # Keep skipping until end of archive symbol table.
-    next if ($skip_arsym);
-
-    # Ignore object name header for individual objects and archives.
-    next if (/:$/);
-
-    # Ignore table header lines.
-    next if (/^Symbol Table Section:/);
-    next if (/index.*value.*size/);
-
-    # Start of archive symbol table: start skipping.
-    if (/^Symbol Table: \(archive/) {
-        $skip_arsym = 1;
-        next;
-    }
-
-    # Split table.
-    (undef, undef, undef, undef, $bind, $oth, undef, $shndx, $name) = split;
-
-    # Error out for unknown input.
-    die "unknown input line:\n$_" unless defined($bind);
-
-    # Ignore local symbols.
-    next if ($bind eq "LOCL");
-    # Ignore hidden symbols.
-    next if ($oth eq "H");
-    # Ignore undefined symbols.
-    next if ($shndx eq "UNDEF");
-    # Error out for unhandled cases.
-    if ($bind !~ /^(GLOB|WEAK)/ or $oth ne "D") {
-        die "unhandled symbol:\n$_";
-    }
-
-    # Remember symbol.
-    $sym_hash{$name}++;
-    }
-    close ELFDUMP or die "$elfdump error";
-} else {
-    open READELF, 'readelf -s -W '.(join ' ',@OBJECTS).'|' or die $!;
-    # Process each symbol.
-    while (<READELF>) {
-    chomp;
-
-    # Ignore empty lines.
-    next if (/^$/);
-
-    # Ignore object name header.
-    next if (/^File: .*$/);
-
-    # Ignore table header lines.
-    next if (/^Symbol table.*contains.*:/);
-    next if (/Num:.*Value.*Size/);
-
-    # Split table.
-    (undef, undef, undef, undef, $bind, $vis, $ndx, $name) = split;
-
-    # Error out for unknown input.
-    die "unknown input line:\n$_" unless defined($bind);
-
-    # Ignore local symbols.
-    next if ($bind eq "LOCAL");
-    # Ignore hidden symbols.
-    next if ($vis eq "HIDDEN");
-    # Ignore undefined symbols.
-    next if ($ndx eq "UND");
-    # Error out for unhandled cases.
-    if ($bind !~ /^(GLOBAL|WEAK)/ or $vis ne "DEFAULT") {
-        die "unhandled symbol:\n$_";
-    }
-
-    # Remember symbol.
-    $sym_hash{$name}++;
-    }
-    close READELF or die "readelf error";
-}
-
-##########
-# The various types of glob patterns.
-#
-# A glob pattern that is to be applied to the demangled name: 'cxx'.
-# A glob patterns that applies directly to the name in the .o files: 'glob'.
-# This pattern is ignored; used for local variables (usually just '*'): 'ign'.
-
-# The type of the current pattern.
-my $glob = 'glob';
-
-# We're currently inside `extern "C++"', which Sun ld doesn't understand.
-my $in_extern = 0;
-
-# The c++filt command to use.  This *must* be GNU c++filt; the Sun Studio
-# c++filt doesn't handle the GNU mangling style.
-my $cxxfilt = $ENV{'CXXFILT'} || "c++filt";
-
-# The current version name.
-my $current_version = "";
-
-# Was there any attempt to match a symbol to this version?
-my $matches_attempted;
-
-# The number of versions which matched this symbol.
-my $matched_symbols;
-
-open F,$symvers or die $!;
-
-# Print information about generating this file
-print "# This file was generated by make_sunver.pl.  DO NOT EDIT!\n";
-print "# It was generated by:\n";
-printf "# %s %s %s\n", $0, $symvers, (join ' ',@ARGV);
-printf "# Omitted archives with corresponding shared libraries: %s\n",
-    (join ' ', @SHAREDOBJS) if $#SHAREDOBJS >= 0;
-print "#\n\n";
-
-print "\$mapfile_version 2\n";
-
-while (<F>) {
-    # Lines of the form '};'
-    if (/^([ \t]*)(\}[ \t]*;[ \t]*)$/) {
-    $glob = 'glob';
-    if ($in_extern) {
-        $in_extern--;
-        print "$1##$2\n";
-    } else {
-        print;
-    }
-    next;
-    }
-
-    # Lines of the form '} SOME_VERSION_NAME_1.0;'
-    if (/^[ \t]*\}[ \tA-Z0-9_.a-z]+;[ \t]*$/) {
-    $glob = 'glob';
-    # We tried to match symbols agains this version, but none matched.
-    # Emit dummy hidden symbol to avoid marking this version WEAK.
-    if ($matches_attempted && $matched_symbols == 0) {
-        print "  hidden:\n";
-        print "    .force_WEAK_off_$current_version = DATA S0x0 V0x0;\n";
-    }
-    print; next;
-    }
-
-    # Comment and blank lines
-    if (/^[ \t]*\#/) { print; next; }
-    if (/^[ \t]*$/) { print; next; }
-
-    # Lines of the form '{'
-    if (/^([ \t]*){$/) {
-    if ($in_extern) {
-        print "$1##{\n";
-    } else {
-        print;
-    }
-    next;
-    }
-
-    # Lines of the form 'SOME_VERSION_NAME_1.1 {'
-    if (/^([A-Z0-9_.]+)[ \t]+{$/) {
-    # Record version name.
-    $current_version = $1;
-    # Reset match attempts, #matched symbols for this version.
-    $matches_attempted = 0;
-    $matched_symbols = 0;
-    print "SYMBOL_VERSION $1 {\n";
-    next;
-    }
-
-    # Ignore 'global:'
-    if (/^[ \t]*global:$/) { print; next; }
-
-    # After 'local:', globs should be ignored, they won't be exported.
-    if (/^[ \t]*local:$/) {
-    $glob = 'ign';
-    print;
-    next;
-    }
-
-    # After 'extern "C++"', globs are C++ patterns
-    if (/^([ \t]*)(extern \"C\+\+\"[ \t]*)$/) {
-    $in_extern++;
-    $glob = 'cxx';
-    # Need to comment, Sun ld cannot handle this.
-    print "$1##$2\n"; next;
-    }
-
-    # Chomp newline now we're done with passing through the input file.
-    chomp;
-
-    # Catch globs.  Note that '{}' is not allowed in globs by this script,
-    # so only '*' and '[]' are available.
-    if (/^([ \t]*)([^ \t;{}#]+);?[ \t]*$/) {
-    my $ws = $1;
-    my $ptn = $2;
-    # Turn the glob into a regex by replacing '*' with '.*', '?' with '.'.
-    # Keep $ptn so we can still print the original form.
-    ($pattern = $ptn) =~ s/\*/\.\*/g;
-    $pattern =~ s/\?/\./g;
-
-    if ($glob eq 'ign') {
-        # We're in a local: * section; just continue.
-        print "$_\n";
-        next;
-    }
-
-    # Print the glob commented for human readers.
-    print "$ws##$ptn ($glob)\n";
-    # We tried to match a symbol to this version.
-    $matches_attempted++;
-
-    if ($glob eq 'glob') {
-        my %ptn_syms = ();
-
-        # Match ptn against symbols in %sym_hash.
-        foreach my $sym (keys %sym_hash) {
-        # Maybe it matches one of the patterns based on the symbol in
-        # the .o file.
-        $ptn_syms{$sym}++ if ($sym =~ /^$pattern$/);
-        }
-
-        foreach my $sym (sort keys(%ptn_syms)) {
-        $matched_symbols++;
-        print "$ws$sym;\n";
-        }
-    } elsif ($glob eq 'cxx') {
-        my %dem_syms = ();
-
-        # Verify that we're actually using GNU c++filt.  Other versions
-        # most likely cannot handle GNU style symbol mangling.
-        my $cxxout = `$cxxfilt --version 2>&1`;
-        $cxxout =~ m/GNU/ or die "$0 requires GNU c++filt to function";
-
-        # Talk to c++filt through a pair of file descriptors.
-        # Need to start a fresh instance per pattern, otherwise the
-        # process grows to 500+ MB.
-        my $pid = open2(*FILTIN, *FILTOUT, $cxxfilt) or die $!;
-
-        # Match ptn against symbols in %sym_hash.
-        foreach my $sym (keys %sym_hash) {
-        # No?  Well, maybe its demangled form matches one of those
-        # patterns.
-        printf FILTOUT "%s\n",$sym;
-        my $dem = <FILTIN>;
-        chomp $dem;
-        $dem_syms{$sym}++ if ($dem =~ /^$pattern$/);
-        }
-
-        close FILTOUT or die "c++filt error";
-        close FILTIN or die "c++filt error";
-        # Need to wait for the c++filt process to avoid lots of zombies.
-        waitpid $pid, 0;
-
-        foreach my $sym (sort keys(%dem_syms)) {
-        $matched_symbols++;
-        print "$ws$sym;\n";
-        }
-    } else {
-        # No?  Well, then ignore it.
-    }
-    next;
-    }
-    # Important sanity check.  This script can't handle lots of formats
-    # that GNU ld can, so be sure to error out if one is seen!
-    die "strange line `$_'";
-}
-close F;
diff --git a/spaces/colakin/video-generater/public/ffmpeg/libavcodec/dxva2_hevc.c b/spaces/colakin/video-generater/public/ffmpeg/libavcodec/dxva2_hevc.c
deleted file mode 100644
index 6b239d9917cf75dac20e7610f3750d229579627c..0000000000000000000000000000000000000000
--- a/spaces/colakin/video-generater/public/ffmpeg/libavcodec/dxva2_hevc.c
+++ /dev/null
@@ -1,471 +0,0 @@
-/*
- * DXVA2 HEVC HW acceleration.
- *
- * copyright (c) 2014 - 2015 Hendrik Leppkes
- *
- * This file is part of FFmpeg.
- *
- * FFmpeg is free software; you can redistribute it and/or
- * modify it under the terms of the GNU Lesser General Public
- * License as published by the Free Software Foundation; either
- * version 2.1 of the License, or (at your option) any later version.
- *
- * FFmpeg is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
- * Lesser General Public License for more details.
- *
- * You should have received a copy of the GNU Lesser General Public
- * License along with FFmpeg; if not, write to the Free Software
- * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA
- */
-
-#include "config_components.h"
-
-#include "libavutil/avassert.h"
-
-#include "dxva2_internal.h"
-#include "hevc_data.h"
-#include "hevcdec.h"
-
-#define MAX_SLICES 256
-
-struct hevc_dxva2_picture_context {
-    DXVA_PicParams_HEVC   pp;
-    DXVA_Qmatrix_HEVC     qm;
-    unsigned              slice_count;
-    DXVA_Slice_HEVC_Short slice_short[MAX_SLICES];
-    const uint8_t         *bitstream;
-    unsigned              bitstream_size;
-};
-
-static void fill_picture_entry(DXVA_PicEntry_HEVC *pic,
-                               unsigned index, unsigned flag)
-{
-    av_assert0((index & 0x7f) == index && (flag & 0x01) == flag);
-    pic->bPicEntry = index | (flag << 7);
-}
-
-static int get_refpic_index(const DXVA_PicParams_HEVC *pp, int surface_index)
-{
-    int i;
-    for (i = 0; i < FF_ARRAY_ELEMS(pp->RefPicList); i++) {
-        if ((pp->RefPicList[i].bPicEntry & 0x7f) == surface_index)
-          return i;
-    }
-    return 0xff;
-}
-
-static void fill_picture_parameters(const AVCodecContext *avctx, AVDXVAContext *ctx, const HEVCContext *h,
-                                    DXVA_PicParams_HEVC *pp)
-{
-    const HEVCFrame *current_picture = h->ref;
-    const HEVCSPS *sps = h->ps.sps;
-    const HEVCPPS *pps = h->ps.pps;
-    int i, j;
-
-    memset(pp, 0, sizeof(*pp));
-
-    pp->PicWidthInMinCbsY  = sps->min_cb_width;
-    pp->PicHeightInMinCbsY = sps->min_cb_height;
-
-    pp->wFormatAndSequenceInfoFlags = (sps->chroma_format_idc             <<  0) |
-                                      (sps->separate_colour_plane_flag    <<  2) |
-                                      ((sps->bit_depth - 8)               <<  3) |
-                                      ((sps->bit_depth - 8)               <<  6) |
-                                      ((sps->log2_max_poc_lsb - 4)        <<  9) |
-                                      (0                                  << 13) |
-                                      (0                                  << 14) |
-                                      (0                                  << 15);
-
-    fill_picture_entry(&pp->CurrPic, ff_dxva2_get_surface_index(avctx, ctx, current_picture->frame), 0);
-
-    pp->sps_max_dec_pic_buffering_minus1         = sps->temporal_layer[sps->max_sub_layers - 1].max_dec_pic_buffering - 1;
-    pp->log2_min_luma_coding_block_size_minus3   = sps->log2_min_cb_size - 3;
-    pp->log2_diff_max_min_luma_coding_block_size = sps->log2_diff_max_min_coding_block_size;
-    pp->log2_min_transform_block_size_minus2     = sps->log2_min_tb_size - 2;
-    pp->log2_diff_max_min_transform_block_size   = sps->log2_max_trafo_size  - sps->log2_min_tb_size;
-    pp->max_transform_hierarchy_depth_inter      = sps->max_transform_hierarchy_depth_inter;
-    pp->max_transform_hierarchy_depth_intra      = sps->max_transform_hierarchy_depth_intra;
-    pp->num_short_term_ref_pic_sets              = sps->nb_st_rps;
-    pp->num_long_term_ref_pics_sps               = sps->num_long_term_ref_pics_sps;
-
-    pp->num_ref_idx_l0_default_active_minus1     = pps->num_ref_idx_l0_default_active - 1;
-    pp->num_ref_idx_l1_default_active_minus1     = pps->num_ref_idx_l1_default_active - 1;
-    pp->init_qp_minus26                          = pps->pic_init_qp_minus26;
-
-    if (h->sh.short_term_ref_pic_set_sps_flag == 0 && h->sh.short_term_rps) {
-        pp->ucNumDeltaPocsOfRefRpsIdx            = h->sh.short_term_rps->rps_idx_num_delta_pocs;
-        pp->wNumBitsForShortTermRPSInSlice       = h->sh.short_term_ref_pic_set_size;
-    }
-
-    pp->dwCodingParamToolFlags = (sps->scaling_list_enable_flag                  <<  0) |
-                                 (sps->amp_enabled_flag                          <<  1) |
-                                 (sps->sao_enabled                               <<  2) |
-                                 (sps->pcm_enabled_flag                          <<  3) |
-                                 ((sps->pcm_enabled_flag ? (sps->pcm.bit_depth - 1) : 0)            <<  4) |
-                                 ((sps->pcm_enabled_flag ? (sps->pcm.bit_depth_chroma - 1) : 0)     <<  8) |
-                                 ((sps->pcm_enabled_flag ? (sps->pcm.log2_min_pcm_cb_size - 3) : 0) << 12) |
-                                 ((sps->pcm_enabled_flag ? (sps->pcm.log2_max_pcm_cb_size - sps->pcm.log2_min_pcm_cb_size) : 0) << 14) |
-                                 (sps->pcm.loop_filter_disable_flag              << 16) |
-                                 (sps->long_term_ref_pics_present_flag           << 17) |
-                                 (sps->sps_temporal_mvp_enabled_flag             << 18) |
-                                 (sps->sps_strong_intra_smoothing_enable_flag    << 19) |
-                                 (pps->dependent_slice_segments_enabled_flag     << 20) |
-                                 (pps->output_flag_present_flag                  << 21) |
-                                 (pps->num_extra_slice_header_bits               << 22) |
-                                 (pps->sign_data_hiding_flag                     << 25) |
-                                 (pps->cabac_init_present_flag                   << 26) |
-                                 (0                                              << 27);
-
-    pp->dwCodingSettingPicturePropertyFlags = (pps->constrained_intra_pred_flag                   <<  0) |
-                                              (pps->transform_skip_enabled_flag                   <<  1) |
-                                              (pps->cu_qp_delta_enabled_flag                      <<  2) |
-                                              (pps->pic_slice_level_chroma_qp_offsets_present_flag <<  3) |
-                                              (pps->weighted_pred_flag                            <<  4) |
-                                              (pps->weighted_bipred_flag                          <<  5) |
-                                              (pps->transquant_bypass_enable_flag                 <<  6) |
-                                              (pps->tiles_enabled_flag                            <<  7) |
-                                              (pps->entropy_coding_sync_enabled_flag              <<  8) |
-                                              (pps->uniform_spacing_flag                          <<  9) |
-                                              ((pps->tiles_enabled_flag ? pps->loop_filter_across_tiles_enabled_flag : 0) << 10) |
-                                              (pps->seq_loop_filter_across_slices_enabled_flag    << 11) |
-                                              (pps->deblocking_filter_override_enabled_flag       << 12) |
-                                              (pps->disable_dbf                                   << 13) |
-                                              (pps->lists_modification_present_flag               << 14) |
-                                              (pps->slice_header_extension_present_flag           << 15) |
-                                              (IS_IRAP(h)                                         << 16) |
-                                              (IS_IDR(h)                                          << 17) |
-                                              /* IntraPicFlag */
-                                              (IS_IRAP(h)                                         << 18) |
-                                              (0                                                  << 19);
-    pp->pps_cb_qp_offset            = pps->cb_qp_offset;
-    pp->pps_cr_qp_offset            = pps->cr_qp_offset;
-    if (pps->tiles_enabled_flag) {
-        pp->num_tile_columns_minus1 = pps->num_tile_columns - 1;
-        pp->num_tile_rows_minus1    = pps->num_tile_rows - 1;
-
-        if (!pps->uniform_spacing_flag) {
-            for (i = 0; i < pps->num_tile_columns; i++)
-                pp->column_width_minus1[i] = pps->column_width[i] - 1;
-
-            for (i = 0; i < pps->num_tile_rows; i++)
-                pp->row_height_minus1[i] = pps->row_height[i] - 1;
-        }
-    }
-
-    pp->diff_cu_qp_delta_depth           = pps->diff_cu_qp_delta_depth;
-    pp->pps_beta_offset_div2             = pps->beta_offset / 2;
-    pp->pps_tc_offset_div2               = pps->tc_offset / 2;
-    pp->log2_parallel_merge_level_minus2 = pps->log2_parallel_merge_level - 2;
-    pp->CurrPicOrderCntVal               = h->poc;
-
-    // fill RefPicList from the DPB
-    for (i = 0, j = 0; i < FF_ARRAY_ELEMS(pp->RefPicList); i++) {
-        const HEVCFrame *frame = NULL;
-        while (!frame && j < FF_ARRAY_ELEMS(h->DPB)) {
-            if (&h->DPB[j] != current_picture && (h->DPB[j].flags & (HEVC_FRAME_FLAG_LONG_REF | HEVC_FRAME_FLAG_SHORT_REF)))
-                frame = &h->DPB[j];
-            j++;
-        }
-
-        if (frame) {
-            fill_picture_entry(&pp->RefPicList[i], ff_dxva2_get_surface_index(avctx, ctx, frame->frame), !!(frame->flags & HEVC_FRAME_FLAG_LONG_REF));
-            pp->PicOrderCntValList[i] = frame->poc;
-        } else {
-            pp->RefPicList[i].bPicEntry = 0xff;
-            pp->PicOrderCntValList[i]   = 0;
-        }
-    }
-
-    #define DO_REF_LIST(ref_idx, ref_list) { \
-        const RefPicList *rpl = &h->rps[ref_idx]; \
-        for (i = 0, j = 0; i < FF_ARRAY_ELEMS(pp->ref_list); i++) { \
-            const HEVCFrame *frame = NULL; \
-            while (!frame && j < rpl->nb_refs) \
-                frame = rpl->ref[j++]; \
-            if (frame && frame->flags & (HEVC_FRAME_FLAG_LONG_REF | HEVC_FRAME_FLAG_SHORT_REF)) \
-                pp->ref_list[i] = get_refpic_index(pp, ff_dxva2_get_surface_index(avctx, ctx, frame->frame)); \
-            else \
-                pp->ref_list[i] = 0xff; \
-        } \
-    }
-
-    // Fill short term and long term lists
-    DO_REF_LIST(ST_CURR_BEF, RefPicSetStCurrBefore);
-    DO_REF_LIST(ST_CURR_AFT, RefPicSetStCurrAfter);
-    DO_REF_LIST(LT_CURR, RefPicSetLtCurr);
-
-    pp->StatusReportFeedbackNumber = 1 + DXVA_CONTEXT_REPORT_ID(avctx, ctx)++;
-}
-
-static void fill_scaling_lists(AVDXVAContext *ctx, const HEVCContext *h, DXVA_Qmatrix_HEVC *qm)
-{
-    unsigned i, j, pos;
-    const ScalingList *sl = h->ps.pps->scaling_list_data_present_flag ?
-                            &h->ps.pps->scaling_list : &h->ps.sps->scaling_list;
-
-    memset(qm, 0, sizeof(*qm));
-    for (i = 0; i < 6; i++) {
-        for (j = 0; j < 16; j++) {
-            pos = 4 * ff_hevc_diag_scan4x4_y[j] + ff_hevc_diag_scan4x4_x[j];
-            qm->ucScalingLists0[i][j] = sl->sl[0][i][pos];
-        }
-
-        for (j = 0; j < 64; j++) {
-            pos = 8 * ff_hevc_diag_scan8x8_y[j] + ff_hevc_diag_scan8x8_x[j];
-            qm->ucScalingLists1[i][j] = sl->sl[1][i][pos];
-            qm->ucScalingLists2[i][j] = sl->sl[2][i][pos];
-
-            if (i < 2)
-                qm->ucScalingLists3[i][j] = sl->sl[3][i * 3][pos];
-        }
-
-        qm->ucScalingListDCCoefSizeID2[i] = sl->sl_dc[0][i];
-        if (i < 2)
-            qm->ucScalingListDCCoefSizeID3[i] = sl->sl_dc[1][i * 3];
-    }
-}
-
-static void fill_slice_short(DXVA_Slice_HEVC_Short *slice,
-                             unsigned position, unsigned size)
-{
-    memset(slice, 0, sizeof(*slice));
-    slice->BSNALunitDataLocation = position;
-    slice->SliceBytesInBuffer    = size;
-    slice->wBadSliceChopping     = 0;
-}
-
-static int commit_bitstream_and_slice_buffer(AVCodecContext *avctx,
-                                             DECODER_BUFFER_DESC *bs,
-                                             DECODER_BUFFER_DESC *sc)
-{
-    const HEVCContext *h = avctx->priv_data;
-    AVDXVAContext *ctx = DXVA_CONTEXT(avctx);
-    const HEVCFrame *current_picture = h->ref;
-    struct hevc_dxva2_picture_context *ctx_pic = current_picture->hwaccel_picture_private;
-    DXVA_Slice_HEVC_Short *slice = NULL;
-    void     *dxva_data_ptr;
-    uint8_t  *dxva_data, *current, *end;
-    unsigned dxva_size;
-    void     *slice_data;
-    unsigned slice_size;
-    unsigned padding;
-    unsigned i;
-    unsigned type;
-
-    /* Create an annex B bitstream buffer with only slice NAL and finalize slice */
-#if CONFIG_D3D11VA
-    if (ff_dxva2_is_d3d11(avctx)) {
-        type = D3D11_VIDEO_DECODER_BUFFER_BITSTREAM;
-        if (FAILED(ID3D11VideoContext_GetDecoderBuffer(D3D11VA_CONTEXT(ctx)->video_context,
-                                                       D3D11VA_CONTEXT(ctx)->decoder,
-                                                       type,
-                                                       &dxva_size, &dxva_data_ptr)))
-            return -1;
-    }
-#endif
-#if CONFIG_DXVA2
-    if (avctx->pix_fmt == AV_PIX_FMT_DXVA2_VLD) {
-        type = DXVA2_BitStreamDateBufferType;
-        if (FAILED(IDirectXVideoDecoder_GetBuffer(DXVA2_CONTEXT(ctx)->decoder,
-                                                  type,
-                                                  &dxva_data_ptr, &dxva_size)))
-            return -1;
-    }
-#endif
-
-    dxva_data = dxva_data_ptr;
-    current = dxva_data;
-    end = dxva_data + dxva_size;
-
-    for (i = 0; i < ctx_pic->slice_count; i++) {
-        static const uint8_t start_code[] = { 0, 0, 1 };
-        static const unsigned start_code_size = sizeof(start_code);
-        unsigned position, size;
-
-        slice = &ctx_pic->slice_short[i];
-
-        position = slice->BSNALunitDataLocation;
-        size     = slice->SliceBytesInBuffer;
-        if (start_code_size + size > end - current) {
-            av_log(avctx, AV_LOG_ERROR, "Failed to build bitstream");
-            break;
-        }
-
-        slice->BSNALunitDataLocation = current - dxva_data;
-        slice->SliceBytesInBuffer    = start_code_size + size;
-
-        memcpy(current, start_code, start_code_size);
-        current += start_code_size;
-
-        memcpy(current, &ctx_pic->bitstream[position], size);
-        current += size;
-    }
-    padding = FFMIN(128 - ((current - dxva_data) & 127), end - current);
-    if (slice && padding > 0) {
-        memset(current, 0, padding);
-        current += padding;
-
-        slice->SliceBytesInBuffer += padding;
-    }
-#if CONFIG_D3D11VA
-    if (ff_dxva2_is_d3d11(avctx))
-        if (FAILED(ID3D11VideoContext_ReleaseDecoderBuffer(D3D11VA_CONTEXT(ctx)->video_context, D3D11VA_CONTEXT(ctx)->decoder, type)))
-            return -1;
-#endif
-#if CONFIG_DXVA2
-    if (avctx->pix_fmt == AV_PIX_FMT_DXVA2_VLD)
-        if (FAILED(IDirectXVideoDecoder_ReleaseBuffer(DXVA2_CONTEXT(ctx)->decoder, type)))
-            return -1;
-#endif
-    if (i < ctx_pic->slice_count)
-        return -1;
-
-#if CONFIG_D3D11VA
-    if (ff_dxva2_is_d3d11(avctx)) {
-        D3D11_VIDEO_DECODER_BUFFER_DESC *dsc11 = bs;
-        memset(dsc11, 0, sizeof(*dsc11));
-        dsc11->BufferType           = type;
-        dsc11->DataSize             = current - dxva_data;
-        dsc11->NumMBsInBuffer       = 0;
-
-        type = D3D11_VIDEO_DECODER_BUFFER_SLICE_CONTROL;
-    }
-#endif
-#if CONFIG_DXVA2
-    if (avctx->pix_fmt == AV_PIX_FMT_DXVA2_VLD) {
-        DXVA2_DecodeBufferDesc *dsc2 = bs;
-        memset(dsc2, 0, sizeof(*dsc2));
-        dsc2->CompressedBufferType = type;
-        dsc2->DataSize             = current - dxva_data;
-        dsc2->NumMBsInBuffer       = 0;
-
-        type = DXVA2_SliceControlBufferType;
-    }
-#endif
-
-    slice_data = ctx_pic->slice_short;
-    slice_size = ctx_pic->slice_count * sizeof(*ctx_pic->slice_short);
-
-    av_assert0(((current - dxva_data) & 127) == 0);
-    return ff_dxva2_commit_buffer(avctx, ctx, sc,
-                                  type,
-                                  slice_data, slice_size, 0);
-}
-
-
-static int dxva2_hevc_start_frame(AVCodecContext *avctx,
-                                  av_unused const uint8_t *buffer,
-                                  av_unused uint32_t size)
-{
-    const HEVCContext *h = avctx->priv_data;
-    AVDXVAContext *ctx = DXVA_CONTEXT(avctx);
-    struct hevc_dxva2_picture_context *ctx_pic = h->ref->hwaccel_picture_private;
-
-    if (!DXVA_CONTEXT_VALID(avctx, ctx))
-        return -1;
-    av_assert0(ctx_pic);
-
-    /* Fill up DXVA_PicParams_HEVC */
-    fill_picture_parameters(avctx, ctx, h, &ctx_pic->pp);
-
-    /* Fill up DXVA_Qmatrix_HEVC */
-    fill_scaling_lists(ctx, h, &ctx_pic->qm);
-
-    ctx_pic->slice_count    = 0;
-    ctx_pic->bitstream_size = 0;
-    ctx_pic->bitstream      = NULL;
-    return 0;
-}
-
-static int dxva2_hevc_decode_slice(AVCodecContext *avctx,
-                                   const uint8_t *buffer,
-                                   uint32_t size)
-{
-    const HEVCContext *h = avctx->priv_data;
-    const HEVCFrame *current_picture = h->ref;
-    struct hevc_dxva2_picture_context *ctx_pic = current_picture->hwaccel_picture_private;
-    unsigned position;
-
-    if (ctx_pic->slice_count >= MAX_SLICES)
-        return -1;
-
-    if (!ctx_pic->bitstream)
-        ctx_pic->bitstream = buffer;
-    ctx_pic->bitstream_size += size;
-
-    position = buffer - ctx_pic->bitstream;
-    fill_slice_short(&ctx_pic->slice_short[ctx_pic->slice_count], position, size);
-    ctx_pic->slice_count++;
-
-    return 0;
-}
-
-static int dxva2_hevc_end_frame(AVCodecContext *avctx)
-{
-    HEVCContext *h = avctx->priv_data;
-    struct hevc_dxva2_picture_context *ctx_pic = h->ref->hwaccel_picture_private;
-    int scale = ctx_pic->pp.dwCodingParamToolFlags & 1;
-    int ret;
-
-    if (ctx_pic->slice_count <= 0 || ctx_pic->bitstream_size <= 0)
-        return -1;
-
-    ret = ff_dxva2_common_end_frame(avctx, h->ref->frame,
-                                    &ctx_pic->pp, sizeof(ctx_pic->pp),
-                                    scale ? &ctx_pic->qm : NULL, scale ? sizeof(ctx_pic->qm) : 0,
-                                    commit_bitstream_and_slice_buffer);
-    return ret;
-}
-
-#if CONFIG_HEVC_DXVA2_HWACCEL
-const AVHWAccel ff_hevc_dxva2_hwaccel = {
-    .name           = "hevc_dxva2",
-    .type           = AVMEDIA_TYPE_VIDEO,
-    .id             = AV_CODEC_ID_HEVC,
-    .pix_fmt        = AV_PIX_FMT_DXVA2_VLD,
-    .init           = ff_dxva2_decode_init,
-    .uninit         = ff_dxva2_decode_uninit,
-    .start_frame    = dxva2_hevc_start_frame,
-    .decode_slice   = dxva2_hevc_decode_slice,
-    .end_frame      = dxva2_hevc_end_frame,
-    .frame_params   = ff_dxva2_common_frame_params,
-    .frame_priv_data_size = sizeof(struct hevc_dxva2_picture_context),
-    .priv_data_size = sizeof(FFDXVASharedContext),
-};
-#endif
-
-#if CONFIG_HEVC_D3D11VA_HWACCEL
-const AVHWAccel ff_hevc_d3d11va_hwaccel = {
-    .name           = "hevc_d3d11va",
-    .type           = AVMEDIA_TYPE_VIDEO,
-    .id             = AV_CODEC_ID_HEVC,
-    .pix_fmt        = AV_PIX_FMT_D3D11VA_VLD,
-    .init           = ff_dxva2_decode_init,
-    .uninit         = ff_dxva2_decode_uninit,
-    .start_frame    = dxva2_hevc_start_frame,
-    .decode_slice   = dxva2_hevc_decode_slice,
-    .end_frame      = dxva2_hevc_end_frame,
-    .frame_params   = ff_dxva2_common_frame_params,
-    .frame_priv_data_size = sizeof(struct hevc_dxva2_picture_context),
-    .priv_data_size = sizeof(FFDXVASharedContext),
-};
-#endif
-
-#if CONFIG_HEVC_D3D11VA2_HWACCEL
-const AVHWAccel ff_hevc_d3d11va2_hwaccel = {
-    .name           = "hevc_d3d11va2",
-    .type           = AVMEDIA_TYPE_VIDEO,
-    .id             = AV_CODEC_ID_HEVC,
-    .pix_fmt        = AV_PIX_FMT_D3D11,
-    .init           = ff_dxva2_decode_init,
-    .uninit         = ff_dxva2_decode_uninit,
-    .start_frame    = dxva2_hevc_start_frame,
-    .decode_slice   = dxva2_hevc_decode_slice,
-    .end_frame      = dxva2_hevc_end_frame,
-    .frame_params   = ff_dxva2_common_frame_params,
-    .frame_priv_data_size = sizeof(struct hevc_dxva2_picture_context),
-    .priv_data_size = sizeof(FFDXVASharedContext),
-};
-#endif
diff --git a/spaces/colakin/video-generater/public/ffmpeg/libavcodec/hevc_data.h b/spaces/colakin/video-generater/public/ffmpeg/libavcodec/hevc_data.h
deleted file mode 100644
index 74558f0a989584ca9b4a10386787cd99395efd85..0000000000000000000000000000000000000000
--- a/spaces/colakin/video-generater/public/ffmpeg/libavcodec/hevc_data.h
+++ /dev/null
@@ -1,31 +0,0 @@
-/*
- * HEVC shared data tables
- *
- * This file is part of FFmpeg.
- *
- * FFmpeg is free software; you can redistribute it and/or
- * modify it under the terms of the GNU Lesser General Public
- * License as published by the Free Software Foundation; either
- * version 2.1 of the License, or (at your option) any later version.
- *
- * FFmpeg is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
- * Lesser General Public License for more details.
- *
- * You should have received a copy of the GNU Lesser General Public
- * License along with FFmpeg; if not, write to the Free Software
- * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA
- */
-
-#ifndef AVCODEC_HEVC_DATA_H
-#define AVCODEC_HEVC_DATA_H
-
-#include <stdint.h>
-
-extern const uint8_t ff_hevc_diag_scan4x4_x[16];
-extern const uint8_t ff_hevc_diag_scan4x4_y[16];
-extern const uint8_t ff_hevc_diag_scan8x8_x[64];
-extern const uint8_t ff_hevc_diag_scan8x8_y[64];
-
-#endif /* AVCODEC_HEVC_DATA_H */
diff --git a/spaces/colakin/video-generater/public/ffmpeg/libavcodec/libshine.c b/spaces/colakin/video-generater/public/ffmpeg/libavcodec/libshine.c
deleted file mode 100644
index 2f6a9233e02c214936058c940bb47644ee5389fe..0000000000000000000000000000000000000000
--- a/spaces/colakin/video-generater/public/ffmpeg/libavcodec/libshine.c
+++ /dev/null
@@ -1,149 +0,0 @@
-/*
- * Interface to libshine for mp3 encoding
- * Copyright (c) 2012 Paul B Mahol
- *
- * This file is part of FFmpeg.
- *
- * FFmpeg is free software; you can redistribute it and/or
- * modify it under the terms of the GNU Lesser General Public
- * License as published by the Free Software Foundation; either
- * version 2.1 of the License, or (at your option) any later version.
- *
- * FFmpeg is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
- * Lesser General Public License for more details.
- *
- * You should have received a copy of the GNU Lesser General Public
- * License along with FFmpeg; if not, write to the Free Software
- * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA
- */
-
-#include <shine/layer3.h>
-
-#include "libavutil/channel_layout.h"
-#include "libavutil/intreadwrite.h"
-#include "audio_frame_queue.h"
-#include "avcodec.h"
-#include "codec_internal.h"
-#include "encode.h"
-#include "mpegaudio.h"
-#include "mpegaudiodecheader.h"
-
-#define BUFFER_SIZE (4096 * 20)
-
-typedef struct SHINEContext {
-    shine_config_t  config;
-    shine_t         shine;
-    uint8_t         buffer[BUFFER_SIZE];
-    int             buffer_index;
-    AudioFrameQueue afq;
-} SHINEContext;
-
-static av_cold int libshine_encode_init(AVCodecContext *avctx)
-{
-    SHINEContext *s = avctx->priv_data;
-
-    shine_set_config_mpeg_defaults(&s->config.mpeg);
-    if (avctx->bit_rate)
-        s->config.mpeg.bitr = avctx->bit_rate / 1000;
-    s->config.mpeg.mode = avctx->ch_layout.nb_channels == 2 ? STEREO : MONO;
-    s->config.wave.samplerate = avctx->sample_rate;
-    s->config.wave.channels   = avctx->ch_layout.nb_channels == 2 ? PCM_STEREO : PCM_MONO;
-    if (shine_check_config(s->config.wave.samplerate, s->config.mpeg.bitr) < 0) {
-        av_log(avctx, AV_LOG_ERROR, "invalid configuration\n");
-        return AVERROR(EINVAL);
-    }
-    s->shine = shine_initialise(&s->config);
-    if (!s->shine)
-        return AVERROR(ENOMEM);
-    avctx->frame_size = shine_samples_per_pass(s->shine);
-    ff_af_queue_init(avctx, &s->afq);
-    return 0;
-}
-
-static int libshine_encode_frame(AVCodecContext *avctx, AVPacket *avpkt,
-                                 const AVFrame *frame, int *got_packet_ptr)
-{
-    SHINEContext *s = avctx->priv_data;
-    MPADecodeHeader hdr;
-    unsigned char *data;
-    int written;
-    int ret, len;
-
-    if (frame)
-        data = shine_encode_buffer(s->shine, (int16_t **)frame->data, &written);
-    else
-        data = shine_flush(s->shine, &written);
-    if (written < 0)
-        return -1;
-    if (written > 0) {
-        if (s->buffer_index + written > BUFFER_SIZE) {
-            av_log(avctx, AV_LOG_ERROR, "internal buffer too small\n");
-            return AVERROR_BUG;
-        }
-        memcpy(s->buffer + s->buffer_index, data, written);
-        s->buffer_index += written;
-    }
-    if (frame) {
-        if ((ret = ff_af_queue_add(&s->afq, frame)) < 0)
-            return ret;
-    }
-
-    if (s->buffer_index < 4 || !s->afq.frame_count)
-        return 0;
-    if (avpriv_mpegaudio_decode_header(&hdr, AV_RB32(s->buffer))) {
-        av_log(avctx, AV_LOG_ERROR, "free format output not supported\n");
-        return -1;
-    }
-
-    len = hdr.frame_size;
-    if (len <= s->buffer_index) {
-        if ((ret = ff_get_encode_buffer(avctx, avpkt, len, 0)))
-            return ret;
-        memcpy(avpkt->data, s->buffer, len);
-        s->buffer_index -= len;
-        memmove(s->buffer, s->buffer + len, s->buffer_index);
-
-        ff_af_queue_remove(&s->afq, avctx->frame_size, &avpkt->pts,
-                           &avpkt->duration);
-
-        *got_packet_ptr = 1;
-    }
-    return 0;
-}
-
-static av_cold int libshine_encode_close(AVCodecContext *avctx)
-{
-    SHINEContext *s = avctx->priv_data;
-
-    ff_af_queue_close(&s->afq);
-    shine_close(s->shine);
-    return 0;
-}
-
-static const int libshine_sample_rates[] = {
-    44100, 48000, 32000, 0
-};
-
-const FFCodec ff_libshine_encoder = {
-    .p.name                = "libshine",
-    CODEC_LONG_NAME("libshine MP3 (MPEG audio layer 3)"),
-    .p.type                = AVMEDIA_TYPE_AUDIO,
-    .p.id                  = AV_CODEC_ID_MP3,
-    .p.capabilities        = AV_CODEC_CAP_DR1 | AV_CODEC_CAP_DELAY,
-    .caps_internal         = FF_CODEC_CAP_NOT_INIT_THREADSAFE,
-    .priv_data_size        = sizeof(SHINEContext),
-    .init                  = libshine_encode_init,
-    FF_CODEC_ENCODE_CB(libshine_encode_frame),
-    .close                 = libshine_encode_close,
-    .p.sample_fmts         = (const enum AVSampleFormat[]){ AV_SAMPLE_FMT_S16P,
-                                                            AV_SAMPLE_FMT_NONE },
-    .p.supported_samplerates = libshine_sample_rates,
-    CODEC_OLD_CHANNEL_LAYOUTS(AV_CH_LAYOUT_MONO, AV_CH_LAYOUT_STEREO)
-    .p.ch_layouts          = (const AVChannelLayout[]) { AV_CHANNEL_LAYOUT_MONO,
-                                                         AV_CHANNEL_LAYOUT_STEREO,
-                                                         { 0 },
-    },
-    .p.wrapper_name        = "libshine",
-};
diff --git a/spaces/colakin/video-generater/public/ffmpeg/libavcodec/mips/pixblockdsp_init_mips.c b/spaces/colakin/video-generater/public/ffmpeg/libavcodec/mips/pixblockdsp_init_mips.c
deleted file mode 100644
index 2e2d70953bdd97c6c15a3653b3463e10280d25ef..0000000000000000000000000000000000000000
--- a/spaces/colakin/video-generater/public/ffmpeg/libavcodec/mips/pixblockdsp_init_mips.c
+++ /dev/null
@@ -1,56 +0,0 @@
-/*
- * Copyright (c) 2015 Shivraj Patil (Shivraj.Patil@imgtec.com)
- *                    Zhou Xiaoyong <zhouxiaoyong@loongson.cn>
- *
- * This file is part of FFmpeg.
- *
- * FFmpeg is free software; you can redistribute it and/or
- * modify it under the terms of the GNU Lesser General Public
- * License as published by the Free Software Foundation; either
- * version 2.1 of the License, or (at your option) any later version.
- *
- * FFmpeg is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
- * Lesser General Public License for more details.
- *
- * You should have received a copy of the GNU Lesser General Public
- * License along with FFmpeg; if not, write to the Free Software
- * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA
- */
-
-#include "libavutil/mips/cpu.h"
-#include "pixblockdsp_mips.h"
-
-void ff_pixblockdsp_init_mips(PixblockDSPContext *c, AVCodecContext *avctx,
-                              unsigned high_bit_depth)
-{
-    int cpu_flags = av_get_cpu_flags();
-
-    if (have_mmi(cpu_flags)) {
-        c->diff_pixels = ff_diff_pixels_mmi;
-
-        if (!high_bit_depth || avctx->codec_type != AVMEDIA_TYPE_VIDEO) {
-            c->get_pixels = ff_get_pixels_8_mmi;
-        }
-    }
-
-    if (have_msa(cpu_flags)) {
-        c->diff_pixels = ff_diff_pixels_msa;
-
-        switch (avctx->bits_per_raw_sample) {
-        case 9:
-        case 10:
-        case 12:
-        case 14:
-            c->get_pixels = ff_get_pixels_16_msa;
-            break;
-        default:
-            if (avctx->bits_per_raw_sample <= 8 || avctx->codec_type !=
-                AVMEDIA_TYPE_VIDEO) {
-                c->get_pixels = ff_get_pixels_8_msa;
-            }
-            break;
-        }
-    }
-}
diff --git a/spaces/congsaPfin/Manga-OCR/logs/20 Minutes Till Dawn (Full) APK A Pixel Art Game with Horror Atmosphere and Action-packed Combat.md b/spaces/congsaPfin/Manga-OCR/logs/20 Minutes Till Dawn (Full) APK A Pixel Art Game with Horror Atmosphere and Action-packed Combat.md
deleted file mode 100644
index de56769b7692c8bac23535e452deb905a77ad9cf..0000000000000000000000000000000000000000
--- a/spaces/congsaPfin/Manga-OCR/logs/20 Minutes Till Dawn (Full) APK A Pixel Art Game with Horror Atmosphere and Action-packed Combat.md	
+++ /dev/null
@@ -1,123 +0,0 @@
-
-<h1>20 Minutes Till Dawn: A Survival Game with a Lovecraftian Twist</h1>
-<p>If you are looking for a challenging and ghoulish shoot 'em up game, you might want to check out 20 Minutes Till Dawn. This game is inspired by the works of Howard Lovecraft, the master of horror and cosmic dread. In this game, you have to survive the onslaught of an endless horde of monsters for 20 minutes, using various weapons and abilities. Sounds easy? Think again. This game will test your skills, reflexes, and nerves as you face the horrors that lurk in the dark.</p>
- <h2>Introduction</h2>
-<h3>What is 20 Minutes Till Dawn?</h3>
-<p>20 Minutes Till Dawn is a survival game developed by Flanne Games. It is available for Android devices as an apk file that you can download for free from various sources . The game has a pixel art style and a top-down perspective. The game is set in large open arenas where you have to fight waves of monsters that come from different directions. The monsters are based on the creatures from Lovecraftian mythology, such as Cthulhu, Shoggoths, Deep Ones, and more.</p>
-<h2>20 minutes till dawn apk full</h2><br /><p><b><b>Download File</b> &#128504;&#128504;&#128504; <a href="https://urlca.com/2uOaLt">https://urlca.com/2uOaLt</a></b></p><br /><br />
- <h3>How to play 20 Minutes Till Dawn?</h3>
-<p>The game is simple to play but hard to master. You control your character with a virtual joystick on the left side of the screen and aim and shoot with another joystick on the right side. You can also use buttons to switch weapons, reload, and use abilities. You start with a basic pistol and a knife, but as you kill more enemies, you can unlock new weapons and abilities. You can choose from more than 50 abilities in total, such as fireballs, lightning bolts, grenades, mines, turrets, shields, and more. Each time you level up, you can choose one of two random upgrades that will boost your stats or give you new skills.</p>
- <h3>What are the features of 20 Minutes Till Dawn?</h3>
-<p>Some of the features that make this game stand out are:</p>
-<ul>
-<li>Randomized gameplay: Each playthrough is different as you get different weapons, abilities, upgrades, enemies, and arenas.</li>
-<li>Multiple characters: You can choose from different characters that have their own strengths and weaknesses. For example, you can play as a fire mage that can burn enemies with his spells or a ninja warrior that can fight with melee weapons.</li>
-<li>Leaderboards and achievements: You can compete with other players around the world and see how you rank on the leaderboards. You can also unlock achievements that will reward you with coins that you can use to buy new characters or skins.</li>
-</ul>
- <h2>Gameplay Review</h2>
-<h3>Graphics and Sound</h3>
-<p>The game has a retro pixel art style that suits the theme of the game. The graphics are colorful and detailed, and the animations are smooth and fluid. The game also has a dark and eerie atmosphere that creates a sense of tension and dread. The sound effects are crisp and realistic, and the music is catchy and fitting. The game also has voice acting for some of the characters and enemies that adds more personality and humor to the game.</p>
- <h3>Difficulty and Replayability</h3>
-<p>The game is very challenging and addictive. The difficulty increases as you progress through the game, as the enemies become faster, stronger, and more numerous. You have to be quick and smart to survive for 20 minutes without dying or running out of ammo. The game also has a lot of replay value, as you can try different characters, weapons, abilities, and strategies to beat your own score or challenge other players. The game also has a lot of variety and surprises, as you never know what you will encounter in each playthrough.</p>
- <h3>Pros and Cons</h3>
-<p>Here are some of the pros and cons of 20 Minutes Till Dawn:</p>
-<table>
-<tr>
-<th>Pros</th>
-<th>Cons</th>
-</tr>
-<tr>
-<td>- Fun and addictive gameplay</td>
-<td>- Can be frustrating and repetitive</td>
-</tr>
-<tr>
-<td>- Cool pixel art graphics and sound</td>
-<td>- Can be laggy or buggy on some devices</td>
-</tr>
-<tr>
-<td>- Lots of customization and options</td>
-<td>- Can be hard to control on small screens</td>
-</tr>
-<tr>
-<td>- Free to download and play</td>
-<td>- Contains ads and in-app purchases</td>
-</tr>
-</table>
- <h2>Download and Install 20 Minutes Till Dawn</h2>
-<h3>How to download 20 Minutes Till Dawn apk full for Android?</h3>
-<p>If you want to play 20 Minutes Till Dawn on your Android device, you will need to download the apk file from a reliable source. You can find the apk file on various websites that offer free games and apps for Android . However, you should be careful when downloading apk files from unknown sources, as they may contain viruses or malware that can harm your device. You should always scan the apk file with an antivirus software before installing it.</p>
- <h3>How to install 20 Minutes Till Dawn apk full on Android?</h3>
-<p>Once you have downloaded the apk file, you will need to enable the installation of apps from unknown sources on your device. To do this, you can follow these steps:</p>
-<ol>
-<li>Go to Settings > Security > Unknown Sources and toggle it on.</li>
-<li>Locate the apk file on your device using a file manager app.</li>
-<li>Tap on the apk file and follow the instructions to install it.</li>
-<li>Launch the game and enjoy!</li>
-</ol>
- <h2>Conclusion</h2>
-<h4>Summary of the article</h4>
-<p>In this article, we have discussed 20 Minutes Till Dawn, a survival game with a Lovecraftian twist. We have explained what the game is, how to play it, what are its features, and how to download and install it on your Android device. We have also given our gameplay review and listed some of the pros and cons of the game. We hope that you have found this article helpful and informative, and that you will give 20 Minutes Till Dawn a try.</p>
-<p>20 minutes till dawn premium apk download<br />
-20 minutes till dawn android game free<br />
-20 minutes till dawn full version mod<br />
-20 minutes till dawn roguelike shooting game<br />
-20 minutes till dawn lovecraftian survival<br />
-20 minutes till dawn apk for android (free)<br />
-20 minutes till dawn strategy game apkcombo<br />
-20 minutes till dawn unlock characters and weapons<br />
-20 minutes till dawn endless horde of monsters<br />
-20 minutes till dawn shoot 'em up apk<br />
-20 minutes till dawn pixel art game android<br />
-20 minutes till dawn top-down shooter apk<br />
-20 minutes till dawn how to survive till dawn<br />
-20 minutes till dawn apk file download mob.org<br />
-20 minutes till dawn best upgrades and synergies<br />
-20 minutes till dawn sword runes and shield runes<br />
-20 minutes till dawn apk latest version free<br />
-20 minutes till dawn erabit studios game android<br />
-20 minutes till dawn ghoulish and challenging apk<br />
-20 minutes till dawn mini sun fusion experiment<br />
-20 minutes till dawn quickplay mode can be fun<br />
-20 minutes till dawn try different characters apk<br />
-20 minutes till dawn pick upgrades that build on weapons<br />
-20 minutes till dawn keep an eye on synergies apk<br />
-20 minutes till dawn don't forget the runes android<br />
-20 minutes till dawn contact us discord twitter facebook email<br />
-20 minutes till dawn game review and rating apk<br />
-20 minutes till dawn how to download and install apk<br />
-20 minutes till dawn gameplay tips and tricks android<br />
-20 minutes till dawn cheats and hacks apk mod<br />
-20 minutes till dawn similar games for android free<br />
-20 minutes till dawn play store qr code share apk<br />
-20 minutes till dawn google play id com.Flanne.MinutesTillDawn.roguelike.shooting.gp<br />
-20 minutes till dawn game description of mob.org apk<br />
-20 minutes till dawn game description of apkcombo apk<br />
-20 minutes till dawn game screenshots and videos android<br />
-20 minutes till dawn game features and details apk free<br />
-20 minutes till dawn game system requirements and compatibility android<br />
-20 minutes till dawn game updates and news apk latest<br />
-20 minutes till dawn game feedback and support android help<br />
-20 minutes till dawn game bugs and issues apk fix<br />
-20 minutes till dawn game faq and guide android wiki<br />
-20 minutes till dawn game forum and community apk chat<br />
-20 minutes till dawn game fan art and memes android fun<br />
-20 minutes till dawn game merchandise and gifts apk buy<br />
-20 minutes till dawn game developer and publisher android info<br />
-20 minutes till dawn game privacy policy and terms of service apk legal<br />
-20 minutes till dawn game disclaimer and warning android safe<br />
-20 minutes till dawn game credits and acknowledgements apk thank</p>
- <h4>FAQs</h4>
-<p>Here are some of the frequently asked questions about 20 Minutes Till Dawn:</p>
- <ol type="a">
-<li><b>What is the goal of 20 Minutes Till Dawn?</b></li>
-<p>The goal of 20 Minutes Till Dawn is to survive for 20 minutes without dying or running out of ammo. You have to kill as many enemies as possible and collect coins, ammo, health packs, and power-ups along the way.</p>
- <li><b>How many characters are there in 20 Minutes Till Dawn?</b></li>
-<p>There are 10 characters that you can choose from in 20 Minutes Till Dawn. Each character has their own stats, weapons, abilities, and skins. You can unlock new characters by spending coins that you earn from playing the game.</p>
- <li><b>How many weapons are there in 20 Minutes Till Dawn?</b></li>
-<p>There are more than 30 weapons that you can use in 20 Minutes Till Dawn. You can find new weapons by killing enemies or opening chests. You can also upgrade your weapons by spending coins. Some of the weapons include pistols, shotguns, rifles, machine guns, rocket launchers, flamethrowers, lasers, swords, axes, hammers, and more.</p>
- <li><b>How many abilities are there in 20 Minutes Till Dawn?</b></li>
-<p>There are more than 50 abilities that you can use in 20 Minutes Till Dawn. You can unlock new abilities by leveling up or opening chests. You can also switch abilities by spending coins. Some of the abilities include fireballs, lightning bolts, grenades, mines, turrets, shields, teleports, heals, buffs, debuffs, summons, traps, and more.</p>
- <li><b>Is 20 Minutes Till Dawn online or offline?</b></li>
-<p>20 Minutes Till Dawn is an offline game that does not require an internet connection to play. However, you will need an internet connection to access some of the features such as leaderboards , achievements, and in-app purchases. You can also play the game online with other players in the multiplayer mode, where you can cooperate or compete with each other.</p> 197e85843d<br />
-<br />
-<br />
\ No newline at end of file
diff --git a/spaces/congsaPfin/Manga-OCR/logs/AutoChess Moba Beta APK A New and Exciting MOBA Game with Free Heroes and Diverse Items.md b/spaces/congsaPfin/Manga-OCR/logs/AutoChess Moba Beta APK A New and Exciting MOBA Game with Free Heroes and Diverse Items.md
deleted file mode 100644
index 89b58a70e49b7a83f4b213354f230c4c6aa4d31e..0000000000000000000000000000000000000000
--- a/spaces/congsaPfin/Manga-OCR/logs/AutoChess Moba Beta APK A New and Exciting MOBA Game with Free Heroes and Diverse Items.md	
+++ /dev/null
@@ -1,179 +0,0 @@
-<br />
-<h1>AutoChess Moba: A New and Innovative MOBA Game for Android</h1>
-<p>If you are a fan of MOBA games, you might have heard of AutoChess Moba, a new and innovative game that combines the elements of auto chess and MOBA. AutoChess Moba is a free-to-play game that offers a fair and balanced gameplay experience, a diverse and creative hero design, a unique and asymmetrical map, and an ingenious item system. In this article, we will introduce you to AutoChess Moba, show you how to download and install its beta apk, and give you some tips on how to play and enjoy this game.</p>
- <h2>What is AutoChess Moba?</h2>
-<p>AutoChess Moba is a game developed by AutoChess Moba, a team that is inspired by the popular mod Auto Chess. Auto Chess is a game mode that originated from Dota 2, where players compete against each other by placing chess pieces on a board and letting them fight automatically. Auto Chess became a huge hit among gamers, spawning several spin-offs and standalone games.</p>
-<h2>auto chess moba beta apk</h2><br /><p><b><b>Download File</b> &#9999; &#9999; &#9999; <a href="https://urlca.com/2uOfsp">https://urlca.com/2uOfsp</a></b></p><br /><br />
-<p>AutoChess Moba is one of these games, but it adds a twist to the genre by incorporating the features of MOBA games. MOBA stands for multiplayer online battle arena, which is a type of game where two teams of players control individual characters called heroes and try to destroy the enemy base. Some of the most popular MOBA games are League of Legends, Dota 2, and Mobile Legends.</p>
-<p>AutoChess Moba combines the best aspects of auto chess and MOBA, creating a game that is both strategic and action-packed. Here are some of the features that make AutoChess Moba stand out from other games:</p>
- <h3>The origin and features of AutoChess Moba</h3>
-<ul>
-<li><b>The origin of AutoChess Moba:</b> AutoChess Moba is based on the worldview of Auto Chess, where the familiar chess pieces are transformed into heroes with different abilities and personalities. These heroes embark on a new fighting journey in the world of AutoChess Moba, where they face various challenges and enemies.</li>
-<li><b>The features of AutoChess Moba:</b> AutoChess Moba has several features that make it different from other MOBA games, such as: <ul>
-<li>A completely fair rivalry, where all heroes are free to obtain and no pay-to-win elements are involved.</li>
-<li>A 5v5 team fighting mode, where players can cooperate with their teammates or solo carry the game.</li>
-<li>An avant-garde hero design, where each hero has four exclusive abilities with diverse effects and combos.</li>
-<li>A new asymmetrical map, where the two teams have different objectives and strategies.</li>
-<li>An ingenious item system, where players can purchase and equip items with various active abilities.</li>
-</ul>
-</li>
-</ul>
- <h3>The gameplay and modes of AutoChess Moba</h3>
-<p>The gameplay of AutoChess Moba is similar to other MOBA games, but with some differences. The game consists of two teams of five players each, who control one hero each. The heroes have different roles, such as tank, fighter, mage, marksman, assassin, or support. The heroes can level up by killing enemy units or heroes, gaining gold and experience. The gold can be used to buy items that enhance the hero's attributes or abilities. The experience can be used to unlock or upgrade the hero's abilities.</p>
-<p>auto chess moba game free download apk<br />
-auto chess moba latest version apk<br />
-auto chess moba android game apk<br />
-auto chess moba strategy game apk<br />
-auto chess moba xapk file download<br />
-auto chess moba apk for pc<br />
-auto chess moba mod apk unlimited money<br />
-auto chess moba hack apk download<br />
-auto chess moba offline apk<br />
-auto chess moba online apk<br />
-auto chess moba update apk<br />
-auto chess moba new heroes apk<br />
-auto chess moba best build apk<br />
-auto chess moba guide apk<br />
-auto chess moba tips and tricks apk<br />
-auto chess moba review apk<br />
-auto chess moba gameplay apk<br />
-auto chess moba trailer apk<br />
-auto chess moba reddit apk<br />
-auto chess moba discord apk<br />
-auto chess moba wiki apk<br />
-auto chess moba tier list apk<br />
-auto chess moba patch notes apk<br />
-auto chess moba release date apk<br />
-auto chess moba system requirements apk<br />
-auto chess moba size apk<br />
-auto chess moba how to play apk<br />
-auto chess moba characters apk<br />
-auto chess moba items apk<br />
-auto chess moba skills apk<br />
-auto chess moba combos apk<br />
-auto chess moba map apk<br />
-auto chess moba modes apk<br />
-auto chess moba ranks apk<br />
-auto chess moba rewards apk<br />
-auto chess moba events apk<br />
-auto chess moba codes apk<br />
-auto chess moba coupons apk<br />
-auto chess moba gift card apk<br />
-auto chess moba redeem code apk<br />
-auto chess moba referral code apk<br />
-auto chess moba invite code apk<br />
-auto chess moba support code apk<br />
-auto chess moba error code apk<br />
-auto chess moba server status apk<br />
-auto chess moba maintenance schedule apk<br />
-auto chess moba developer contact apk <br />
-auto chess moba customer service apk <br />
-auto chess moba feedback form apk</p>
-<p>The main mode of AutoChess Moba is the 5v5 team fighting mode <p>The gameplay of AutoChess Moba is similar to other MOBA games, but with some differences. The game consists of two teams of five players each, who control one hero each. The heroes have different roles, such as tank, fighter, mage, marksman, assassin, or support. The heroes can level up by killing enemy units or heroes, gaining gold and experience. The gold can be used to buy items that enhance the hero's attributes or abilities. The experience can be used to unlock or upgrade the hero's abilities.</p>
-<p>The main mode of AutoChess Moba is the 5v5 team fighting mode, where the two teams compete to destroy the enemy base. The base consists of a core building and several towers that protect it. The towers can deal damage to enemy units and heroes, but they can also be destroyed by them. The core building is the main objective of the game, and destroying it will grant victory to the team that does so.</p>
-<p>However, unlike other MOBA games, AutoChess Moba has an asymmetrical map design, which means that the two teams have different layouts and objectives. The map is divided into two halves by a river, and each half has three lanes: top, mid, and bottom. The lanes are connected by a jungle area, where neutral monsters spawn and provide gold and buffs to the players who kill them.</p>
-<p>The team on the left side of the map is called the Radiant team, and their base is located at the bottom left corner. Their objective is to destroy the Dire team's core building, which is located at the top right corner. To do so, they have to push their lanes with the help of their minions, which are small units that spawn periodically and march towards the enemy base. They also have to defend their own towers and core from the enemy attacks.</p>
-<p>The team on the right side of the map is called the Dire team, and their base is located at the top right corner. Their objective is to destroy the Radiant team's core building, which is located at the bottom left corner. However, they have a different way of doing so than the Radiant team. Instead of pushing their lanes with minions, they have to collect crystals from the jungle area and deliver them to a special altar near their base. The altar will then fire a powerful beam that will damage the Radiant team's core building. They also have to defend their own towers and core from the enemy attacks.</p>
- <h3>The heroes and items of AutoChess Moba</h3>
-<p>AutoChess Moba features a diverse and creative hero design, where each hero has four exclusive abilities with different effects and combos. The heroes are based on the chess pieces from Auto Chess, but they have been redesigned and reimagined for this game. There are currently 40 heroes in AutoChess Moba, divided into 10 races and 10 classes. Each race and class has a unique passive ability that can be activated by having multiple heroes of the same race or class on your team.</p>
-<p>Some examples of heroes in AutoChess Moba are:</p>
-<ul>
-<li><b>God of War:</b> A tank hero from the God race and Warrior class. He has high durability and crowd control abilities. His ultimate ability allows him to summon a shield that blocks all damage and reflects it back to his enemies.</li>
-<li><b>Flame Wizard:</b> A mage hero from the Human race and Mage class. She has high burst damage and area of effect abilities. Her ultimate ability allows her to cast a meteor shower that rains down fireballs on a large area.</li>
-<li><b>Shadowcrawler:</b> An assassin hero from the Elf race and Assassin class. She has high mobility and single-target damage abilities. Her ultimate ability allows her to dash through multiple enemies and deal critical damage to them.</li>
-<li><b>Siren:</b> A support hero from the Marine race and Hunter class. She has high utility and healing abilities. Her ultimate ability allows her to sing a song that charms all enemies in a cone in front of her.</li>
-</ul>
-<p>The items in AutoChess Moba are also different from other MOBA games, as they have various active abilities that can be used in combat. The items can be purchased from a shop near your base or from a courier that can deliver them to you anywhere on the map. The items can be upgraded by combining them with other items or materials.</p>
-<p>Some examples of items in AutoChess Moba are:</p>
-<ul>
-<li><b>Blink Dagger:</b> An item that grants an active ability that allows you to teleport to a target location within a short range.</li>
-<li><b>Scythe of Vyse:</b> An item that grants an active ability that allows you to turn an enemy hero into a sheep for a few seconds.</li>
-<li><b>Mekansm:</b> An <p>Mekansm: An item that grants an active ability that allows you to heal yourself and nearby allies for a moderate amount.</li>
-<li><b>Divine Rapier:</b> An item that grants a massive boost to your attack damage, but drops on death and can be picked up by anyone.</li>
-</ul>
- <h2>How to download and install AutoChess Moba beta apk?</h2>
-<p>If you are interested in trying out AutoChess Moba, you might want to download and install its beta apk. A beta apk is an application package file that contains the latest version of the game before it is officially released. By downloading and installing the beta apk, you can enjoy the new features and updates of the game before anyone else. However, you should also be aware of the benefits and risks of doing so, as well as the steps and tips to download and install the beta apk.</p>
- <h3>The benefits and risks of downloading beta apk</h3>
-<p>Downloading and installing the beta apk of AutoChess Moba has some benefits, such as:</p>
-<ul>
-<li><b>Accessing the latest content and updates:</b> You can experience the new heroes, items, modes, maps, and other changes that are not yet available in the official version of the game.</li>
-<li><b>Giving feedback and suggestions:</b> You can report any bugs, glitches, errors, or problems that you encounter while playing the game, and help the developers improve the game quality and performance. You can also share your opinions, ideas, or requests for future improvements or additions to the game.</li>
-<li><b>Supporting the developers:</b> You can show your support and appreciation for the developers by testing their game and giving them constructive feedback. You can also help them spread the word about their game and attract more players.</li>
-</ul>
-<p>However, downloading and installing the beta apk of AutoChess Moba also has some risks, such as:</p>
-<ul>
-<li><b>Exposing your device to malware or viruses:</b> The beta apk file might not be safe or secure to download or install, as it might contain malicious software or viruses that can harm your device or steal your personal information. You should always download the beta apk from a trusted source or website, and scan it with an antivirus program before installing it.</li>
-<li><b>Facing compatibility or stability issues:</b> The beta apk file might not be compatible with your device model or operating system, or it might not run smoothly or properly on your device. You might encounter crashes, freezes, lags, errors, or other problems while playing the game. You should always check the system requirements and specifications of the game before downloading or installing it.</li>
-<li><b>Losing your progress or data:</b> The beta apk file might not be compatible with the official version of the game, or it might be overwritten or deleted when the official version is released. You might lose your progress, data, achievements, or rewards that you have earned while playing the game. You should always back up your data or use a different account when playing the beta version of the game.</li>
-</ul>
- <h3>The steps to download and install beta apk</h3>
-<p>If you have decided to download and install the beta apk of AutoChess Moba, you should follow these steps:</p>
-<ol>
-<li><b>Find a reliable source or website that provides the beta apk file of AutoChess Moba:</b> You can search online for websites that offer the beta apk file of AutoChess Moba, or you can visit the official website or social media pages of AutoChess Moba to find the link to download it. Make sure that the source or website is trustworthy and reputable, and avoid any suspicious or fraudulent links.</li>
-<li><b>Download the beta apk file of AutoChess Moba to your device:</b> Once you have found a reliable source or website that provides the beta apk file of AutoChess Moba, you can click on the download button or link and save the file to your device. The file size is about 500 MB, so make sure that you have enough storage space and a stable internet connection. You can also scan the file with an antivirus program before opening it.</li>
-<li><b>Enable the installation of unknown sources on your device:</b> Before you can install the beta apk file of AutoChess Moba, you need to allow your device to install applications from unknown sources. To do this, you need to go to your device settings, then security, then enable the option of unknown sources. This will let you install applications that are not from the Google Play Store or other official sources.</li>
-<li><b>Install the beta apk file of AutoChess Moba on your device:</b> After you have enabled the installation of unknown sources, you can proceed to install the beta apk file of AutoChess Moba on your device. To do this, you need to locate the file on your device, then tap on it and follow the instructions on the screen. The installation process might take a few minutes, depending on your device performance and speed.</li>
-<li><b>Launch and enjoy AutoChess Moba on your device:</b> Once you have successfully installed the beta apk file of AutoChess Moba on your device, you can launch the game and enjoy its features and updates. You can create or log in to your account, choose your hero, join a match, and start playing. You can also access the settings, shop, inventory, chat, and other options from the game menu.</li>
-</ol>
- <h3>The tips to fix common issues with beta apk</h3>
-<p>While playing AutoChess Moba with the beta apk, you might encounter some common issues or problems that might affect your gameplay experience. Here are some tips to fix them:</p>
-<ul>
-<li><b>If the game crashes, freezes, lags, or errors:</b> You can try to restart the game or your device, clear the game cache or data, update the game or your device software, check your internet connection or speed, or reinstall the game.</li>
-<li><b>If the game is not compatible with your device or operating system:</b> You can try to change your device settings, such as resolution, graphics, sound, or language, or use a different device or emulator that meets the system requirements and specifications of the game.</li>
-<li><b>If the game is not available in your region or country:</b> You can try to use a VPN service or application that can change your IP address and location, or wait for the official release of the game in your region or country.</li>
-</ul>
- <h2>How to play and enjoy AutoChess Moba?</h2>
-<p>Now that you have downloaded and installed AutoChess Moba on your device, you might want to know how to play and enjoy this game. AutoChess Moba is a game that requires both strategy and skill, as well as teamwork and communication. Here are some tips on how to play and enjoy AutoChess Moba:</p>
- <h3>The basic tips and tricks for beginners</h3>
-<p>If you are new to AutoChess Moba or MOBA games in general, here are some basic tips and tricks that can help you get started:</p>
-<ul>
-<li><b>Learn the basics of the game:</b> You should familiarize yourself with the rules, objectives, controls, interface, and mechanics of the game. You should also learn about the heroes, items, modes, maps and other features of the game. You can read the game guide, watch the tutorial videos, or practice in the training mode to learn the basics of the game.</li>
-<li><b>Choose a suitable hero and role:</b> You should choose a hero and role that suits your playstyle, preference, and skill level. You should also consider the team composition, the enemy lineup, and the game mode when choosing your hero and role. You can try different heroes and roles in the casual mode or the custom mode to find your favorite ones.</li>
-<li><b>Build your items and abilities wisely:</b> You should build your items and abilities according to your hero's strengths, weaknesses, and needs. You should also adapt your build to the situation and the enemy's build. You can follow the recommended build or the popular build in the game, or you can create your own build based on your experience and knowledge.</li>
-<li><b>Communicate and cooperate with your teammates:</b> You should communicate and cooperate with your teammates to achieve your objectives and win the game. You can use the voice chat, the text chat, or the quick chat to communicate with your teammates. You can also use the ping system, the map, or the scoreboard to share information and coordinate with your teammates.</li>
-<li><b>Play safely and smartly:</b> You should play safely and smartly to avoid unnecessary deaths and losses. You should avoid overextending, diving, chasing, or fighting alone. You should also avoid engaging in unfavorable fights, such as when you are outnumbered, outleveled, or outfarmed. You should also pay attention to your surroundings, such as the enemy's position, vision, cooldowns, and items.</li>
-</ul>
- <h3>The advanced strategies and tactics for experts</h3>
-<p>If you are already familiar with AutoChess Moba or MOBA games in general, here are some advanced strategies and tactics that can help you improve your gameplay and performance:</p>
-<ul>
-<li><b>Master your hero and role:</b> You should master your hero and role by learning their abilities, combos, counters, synergies, tips, and tricks. You should also practice your mechanics, such as last hitting, positioning, targeting, dodging, kiting, or skill shots. You should also optimize your build, such as choosing the best items, runes, talents, or emblems for your hero and role.</li>
-<li><b>Analyze and exploit the enemy's weaknesses:</b> You should analyze and exploit the enemy's weaknesses by observing their behavior, habits, mistakes, patterns, or tendencies. You should also take advantage of their weaknesses, such as their lack of vision, map awareness, teamwork, or coordination. You should also punish their mistakes such as their overextending, diving, chasing, or fighting alone. You should also use your items or abilities to counter or disable their heroes or strategies.</li>
-<li><b>Control and secure the objectives and resources:</b> You should control and secure the objectives and resources on the map, such as the towers, the crystals, the jungle monsters, the buffs, or the bosses. You should also contest or steal the enemy's objectives and resources, such as by ganking, invading, ambushing, or sneaking. You should also use the objectives and resources to your advantage, such as by pushing, sieging, split pushing, or team fighting.</li>
-<li><b>Adapt and improvise to the situation:</b> You should adapt and improvise to the situation by changing your plan, strategy, or tactic according to the circumstances. You should also be flexible and versatile in your hero choice, role switch, item build, ability upgrade, or team composition. You should also be creative and innovative in your gameplay, such as by using unconventional methods, tricks, or surprises.</li>
-<li><b>Lead and inspire your teammates:</b> You should lead and inspire your teammates by setting an example, giving directions, making calls, or motivating them. You should also support and help your teammates by healing, shielding, buffing, or saving them. You should also respect and appreciate your teammates by acknowledging their contributions, praising their efforts, or thanking them.</li>
-</ul>
- <h3>The best resources and communities for AutoChess Moba players</h3>
-<p>If you want to learn more about AutoChess Moba or connect with other players, here are some of the best resources and communities that you can use:</p>
-<ul>
-<li><b>The official website and social media pages of AutoChess Moba:</b> You can visit the official website of AutoChess Moba at <a href="">https://autochessmoba.com</a>, where you can find the latest news, updates, events, guides, videos, and more about the game. You can also follow the official social media pages of AutoChess Moba on Facebook, Twitter, Instagram, YouTube, Discord, Reddit, or TikTok, where you can interact with the developers and other players.</li>
-<li><b>The fan-made websites and blogs of AutoChess Moba:</b> You can visit some of the fan-made websites and blogs of AutoChess Moba such as <a href="">https://autochessmoba.net</a>, <a href="">https://autochessmoba.info</a>, or <a href="">https://autochessmoba.org</a>, where you can find more detailed and comprehensive information, analysis, reviews, tips, tricks, guides, builds, strategies, and more about the game.</li>
-<li><b>The online forums and groups of AutoChess Moba:</b> You can join some of the online forums and groups of AutoChess Moba, such as on Facebook, Reddit, Discord, or Steam, where you can discuss, share, ask, answer, or chat with other players about anything related to the game. You can also find or create your own team, clan, guild, or squad with other players.</li>
-<li><b>The streaming platforms and channels of AutoChess Moba:</b> You can watch some of the streaming platforms and channels of AutoChess Moba, such as on Twitch, YouTube, Facebook Gaming, or Nimo TV, where you can watch live or recorded gameplay videos of the game. You can also learn from or interact with some of the popular or professional players, streamers, or influencers of the game.</li>
-</ul>
- <h2>Conclusion</h2>
-<h4>Summary of the main points</h4>
-<p>In conclusion, AutoChess Moba is a new and innovative MOBA game for Android that combines the elements of auto chess and MOBA. It offers a fair and balanced gameplay experience, a diverse and creative hero design, a unique and asymmetrical map, and an ingenious item system. It also has a beta apk that you can download and install to enjoy the latest features and updates of the game before anyone else. However, you should also be aware of the benefits and risks of doing so, as well as the steps and tips to download and install the beta apk. Finally, you can also learn how to play and enjoy AutoChess Moba by following some basic tips and tricks for beginners, some advanced strategies and tactics for experts, and some best resources and communities for AutoChess Moba players.</p>
- <h4>Call to action and invitation for feedback</h4>
-<p>If you are interested in AutoChess Moba, you can download it from the Google Play Store or from the official website. You can also download the beta apk from a reliable source or website if you want to try out the new features and updates of the game. You can also follow us on our social media pages to stay updated with the latest news, events, guides, videos, and more about the game. We hope that you enjoy playing AutoChess Moba as much as we do. We also welcome your feedback and suggestions on how to improve the game or this article. Please feel free to leave a comment below or contact us via email or chat. Thank you for reading this article and have fun playing AutoChess Moba!</p>
- <h2>FAQs</h2>
-<p>Here are some of the frequently asked questions (FAQs) about AutoChess Moba:</p>
-<ul>
-<li><b>Q: Is AutoChess Moba free to play?</b></li>
-<li><b>A: Yes, AutoChess Moba is free to play. You can download and play it without paying anything. However However, you can also purchase some optional items or services with real money, such as skins, emotes, or VIP membership. These items or services do not affect the gameplay or the balance of the game, but they can enhance your appearance or your experience.</li>
-<li><b>Q: Is AutoChess Moba available for iOS devices?</b></li>
-<li><b>A: No, AutoChess Moba is currently only available for Android devices. However, the developers have stated that they are working on an iOS version of the game, and they will announce it when it is ready. You can follow their official website or social media pages to stay updated with the progress of the iOS version.</li>
-<li><b>Q: How can I play AutoChess Moba on PC?</b></li>
-<li><b>A: You can play AutoChess Moba on PC by using an Android emulator, which is a software that allows you to run Android applications on your PC. Some of the popular Android emulators are BlueStacks, NoxPlayer, LDPlayer, or MEmu. You can download and install any of these emulators on your PC, and then download and install AutoChess Moba from the Google Play Store or from the official website. You can also adjust the settings of the emulator to optimize the performance and the graphics of the game.</li>
-<li><b>Q: How can I get more heroes or items in AutoChess Moba?</b></li>
-<li><b>A: You can get more heroes or items in AutoChess Moba by playing the game and earning rewards. You can earn gold, gems, coins, chests, or tickets by completing quests, achievements, events, or matches. You can use these rewards to buy or unlock more heroes or items from the shop or the inventory. You can also get more heroes or items by participating in lucky draws, giveaways, or promotions that are held by the developers or the partners of the game.</li>
-<li><b>Q: How can I contact the customer service or support team of AutoChess Moba?</b></li>
-<li><b>A: You can contact the customer service or support team of AutoChess Moba by using any of these methods:</b>
-<ul>
-<li>Email: You can send an email to <a href="">support@autochessmoba.com</a> with your inquiry, issue, feedback, or suggestion.</li>
-<li>Chat: You can use the chat feature in the game to talk to a customer service representative online.</li>
-<li>Feedback: You can use the feedback feature in the game to submit your inquiry, issue, feedback, or suggestion.</li>
-</ul>
-</li>
-</ul></p> 197e85843d<br />
-<br />
-<br />
\ No newline at end of file
diff --git a/spaces/congsaPfin/Manga-OCR/logs/Cara Download Komentar Facebook dengan SaveFrom.net.md b/spaces/congsaPfin/Manga-OCR/logs/Cara Download Komentar Facebook dengan SaveFrom.net.md
deleted file mode 100644
index f5d2acec328c4dbef337a705da1f11e47027bbb2..0000000000000000000000000000000000000000
--- a/spaces/congsaPfin/Manga-OCR/logs/Cara Download Komentar Facebook dengan SaveFrom.net.md	
+++ /dev/null
@@ -1,152 +0,0 @@
-<br />
-<h1>How to Download Komentar Facebook Easily and Quickly</h1>
-<p>Komentar Facebook is a feature that allows users to post videos in the comments section of a Facebook post. It can be a fun and engaging way to interact with your friends, followers, or customers on the social media platform. However, sometimes you might want to download these videos for various reasons, such as saving them for offline viewing, sharing them on other platforms, or analyzing them for feedback or research purposes. In this article, we will show you how to download komentar Facebook easily and quickly using different methods, such as online tools, browser extensions, and mobile apps. We will also compare the pros and cons of each method and answer some frequently asked questions about downloading komentar Facebook.</p>
-<h2>download komentar facebook</h2><br /><p><b><b>Download File</b> &#9734;&#9734;&#9734;&#9734;&#9734; <a href="https://urlca.com/2uOd1G">https://urlca.com/2uOd1G</a></b></p><br /><br />
- <h2>What is Komentar Facebook and Why You Might Want to Download It</h2>
-<h3>Komentar Facebook is a feature that allows users to post videos in the comments section of a Facebook post</h3>
-<p>Komentar Facebook is a feature that was introduced by Facebook in 2016 as a way to make the comments section more lively and interactive. Users can upload videos from their devices or record them using their cameras and post them as comments on any public or private post on Facebook. The videos can be up to 15 seconds long and can have sound or captions. Users can also react to or reply to other users' komentar Facebook with emojis, text, or more videos.</p>
- <h3>Downloading komentar Facebook can help you save, share, or analyze the videos for various purposes</h3>
-<p>Downloading komentar Facebook can be useful for many reasons, depending on your needs and goals. For example, you might want to download komentar Facebook to:</p>
-<ul>
-<li>Save them for offline viewing or backup in case they are deleted or removed by the original poster or Facebook.</li>
-<li>Share them on other platforms or channels, such as YouTube, Instagram, WhatsApp, or your own website or blog.</li>
-<li>Analyze them for feedback or research purposes, such as measuring customer satisfaction, sentiment analysis, market research, or content creation.</li>
-</ul>
-<p>However, downloading komentar Facebook is not as easy as downloading regular videos from Facebook. This is because komentar Facebook are not stored as separate files on the server, but rather embedded in the HTML code of the web page. Therefore, you need to use some special tools or techniques to extract and download them. In the next sections, we will show you some of the best ways to do so.</p>
- <h2>How to Download Komentar Facebook Using Online Tools</h2>
-<h3>Comment Exporter: A tool that lets you download all your Facebook page comments with a single click</h3>
-<h4>How to use Comment Exporter</h4>
-<p>Comment Exporter ([5](https://cmntexport.com)) is an online tool that allows you to download all your Facebook page comments with a single click. It can download both text and video comments, including komentar Facebook, in a CSV or Excel file. You can also filter the comments by date, keyword, or sentiment. To use Comment Exporter, you need to follow these steps:</p>
-<ol>
-<li>Visit the website of Comment Exporter ([5](https://cmntexport.com)) and sign up for a free account.</li>
-<li>Connect your Facebook account and select the page you want to download the comments from.</li>
-<li>Choose the post you want to download the comments from and click on "Export Comments".</li>
-<li>Select the format (CSV or Excel) and the filters (date, keyword, or sentiment) you want to apply and click on "Download".</li>
-<li>Wait for a few minutes until the file is ready and download it to your device.</li>
-</ol>
-<h4>The benefits and features of Comment Exporter</h4>
-<p>Comment Exporter is a powerful and easy-to-use tool that can help you download komentar Facebook in bulk. Some of the benefits and features of Comment Exporter are:</p>
-<ul>
-<li>It can download both text and video comments, including komentar Facebook, in a single file.</li>
-<li>It can download up to 10,000 comments per post, which is more than the limit of Facebook's API.</li>
-<li>It can filter the comments by date, keyword, or sentiment, which can help you find the most relevant or interesting ones.</li>
-<li>It can export the comments in a CSV or Excel file, which can be easily opened and analyzed by any spreadsheet software.</li>
-<li>It can also provide some basic statistics and insights on the comments, such as the number of comments, likes, replies, reactions, and sentiments.</li>
-</ul>
- <h3>Export Comments: A tool that lets you download Facebook comments by post URL</h3>
-<h4>How to use Export Comments</h4>
-<p>Export Comments ([4](https://exportcomments.com)) is another online tool that allows you to download Facebook comments by post URL. It can download both text and video comments, including komentar Facebook, in a JSON or CSV file. You can also choose to include or exclude replies, reactions, attachments, or user profiles. To use Export Comments, you need to follow these steps:</p>
-<ol>
-<li>Visit the website of Export Comments ([4](https://exportcomments.com)) and sign up for a free account.</li>
-<li>Paste the URL of the Facebook post you want to download the comments from and click on "Start".</li>
-<li>Select the options (JSON or CSV, include or exclude replies, reactions, attachments, or user profiles) you want to apply and click on "Continue".</li>
-<li>Wait for a few seconds until the file is ready and download it to your device.</li>
-</ol>
- <h4>The limitations and drawbacks of Export Comments</h4>
-<p>Export Comments is a simple and fast tool that can help you download komentar Facebook by post URL. However, it also has some limitations and drawbacks that you should be aware of:</p>
-<ul>
-<li>It can only download up to 500 comments per post, which is less than the limit of Facebook's API.</li>
-<li>It cannot filter the comments by date, keyword, or sentiment, which can make it harder to find the most relevant or interesting ones.</li>
-<li>It cannot export the comments in an Excel file, which can be more convenient and user-friendly than a JSON or CSV file.</li>
-<li>It does not provide any statistics or insights on the comments, such as the number of comments, likes, replies, reactions, and sentiments.</li>
-</ul>
- <h2>How to Download Komentar Facebook Using Browser Extensions</h2>
- <h3>FBDown Video Downloader: A Chrome extension that lets you download any video from Facebook, including komentar Facebook</h3>
-<h4>How to use FBDown Video Downloader</h4>
-<p>FBDown Video Downloader ([3](https://chrome.google.com/webstore/detail/fbdown-video-downloader/fhplmmllnpjjlncfjpbbpjadoeijkogc)) is a Chrome extension that lets you download any video from Facebook, including komentar Facebook, with a few clicks. It can download videos in HD or SD quality and save them to your device. To use FBDown Video Downloader, you need to follow these steps:</p>
-<p>download komentar facebook di pc<br />
-download komentar facebook dengan savefrom.net<br />
-download komentar facebook menggunakan comment exporter<br />
-download komentar facebook ke galeri hp<br />
-download komentar facebook tanpa aplikasi<br />
-download komentar facebook dengan exportcomments.com<br />
-download komentar facebook secara online<br />
-download komentar facebook berisi video<br />
-download komentar facebook dengan juphy<br />
-download komentar facebook dengan fbdown.net<br />
-download komentar facebook dengan idm<br />
-download komentar facebook dengan fb video saver<br />
-download komentar facebook dengan getfvid<br />
-download komentar facebook dengan fbdownloader.net<br />
-download komentar facebook dengan fb video downloader<br />
-download komentar facebook dengan bitdownloader<br />
-download komentar facebook dengan fb video converter<br />
-download komentar facebook dengan fb comment downloader<br />
-download komentar facebook dengan fb comment extractor<br />
-download komentar facebook dengan fb comment scraper<br />
-download komentar facebook dengan fb comment analyzer<br />
-download komentar facebook dengan fb comment export tool<br />
-download komentar facebook dengan fb comment grabber<br />
-download komentar facebook dengan fb comment generator<br />
-download komentar facebook dengan fb comment manager<br />
-download komentar facebook dengan fb comment monitor<br />
-download komentar facebook dengan fb comment poster<br />
-download komentar facebook dengan fb comment saver<br />
-download komentar facebook dengan fb comment tracker<br />
-download komentar facebook dengan fb comment viewer</p>
-<ol>
-<li>Visit the Chrome Web Store and install the FBDown Video Downloader extension ([3](https://chrome.google.com/webstore/detail/fbdown-video-downloader/fhplmmllnpjjlncfjpbbpjadoeijkogc)).</li>
-<li>Go to the Facebook post that contains the komentar Facebook you want to download and click on the video to play it.</li>
-<li>Click on the FBDown icon in the top right corner of your browser and select the quality (HD or SD) you want to download.</li>
-<li>Click on "Download" and choose a location to save the video to your device.</li>
-</ol>
- <h4>The advantages and disadvantages of FBDown Video Downloader</h4>
-<p>FBDown Video Downloader is a convenient and easy-to-use tool that can help you download komentar Facebook from any Facebook post. However, it also has some advantages and disadvantages that you should be aware of:</p>
-<ul>
-<li>The advantages of FBDown Video Downloader are:</li>
-  <ul>
-  <li>It can download any video from Facebook, including komentar Facebook, in HD or SD quality.</li>
-  <li>It can download videos without leaving the Facebook page or opening a new tab.</li>
-  <li>It can download videos quickly and smoothly without any interruptions or errors.</li>
-  </ul>
-<li>The disadvantages of FBDown Video Downloader are:</li>
-  <ul>
-  <li>It can only download one video at a time, which can be time-consuming if you want to download multiple komentar Facebook.</li>
-  <li>It cannot download videos that are private, restricted, or encrypted by Facebook.</li>
-  <li>It does not support other browsers than Chrome, which can limit your options and preferences.</li>
-  </ul>
-</ul>
- <h2>How to Download Komentar Facebook Using Mobile Apps</h2>
- <h3>Video Downloader for Facebook: An Android app that lets you download videos from Facebook, including komentar Facebook, directly to your gallery</h3>
- <h4>How to use Video Downloader for Facebook</h4>
- <p>Video Downloader for Facebook ([2](https://play.google.com/store/apps/details?id=fb.video.downloader&hl=en_US&gl=US)) is an Android app that lets you download videos from Facebook, including komentar Facebook, directly to your gallery. It can download videos in HD or SD quality and play them offline. To use Video Downloader for Facebook, you need to follow these steps:</p>
- <ol>
-<li>Visit the Google Play Store and install the Video Downloader for Facebook app ([2](https://play.google.com/store/apps/details?id=fb.video.downloader&hl=en_US&gl=US)).</li>
-<li>Open the app and log in with your Facebook account.</li>
-<li>Browse the Facebook posts that contain the komentar Facebook you want to download and tap on the video to play it.</li>
-<li>Tap on the "Download" button at the bottom of the screen and select the quality (HD or SD) you want to download.</li>
-<li>Wait for a few seconds until the video is downloaded and check it in your gallery.</li>
-</ol>
- <h4>The pros and cons of Video Downloader for Facebook</h4>
- <p>Video Downloader for Facebook is a handy and user-friendly app that can help you download komentar Facebook from any Facebook post on your Android device. However, it also has some pros and cons that you should be aware of:</p>
- <ul>
-<li>The pros of Video Downloader for Facebook are:</li>
-  <ul>
-  <li>It can download any video from Facebook, including komentar Facebook, in HD or SD quality directly to your gallery.</li>
-  <li>It can play the downloaded videos offline without any internet connection.</li>
-  <li>It can also share the downloaded videos with other apps or social media platforms.</li>
-  </ul>
-<li>The cons of Video Downloader for Facebook are:</li>
-  <ul>
-  <li>It can only download one video at a time, which can be time-consuming if you want to download multiple komentar Facebook.</li>
-  <li>It cannot download videos that are private , restricted, or encrypted by Facebook.</li>
-  <li>It does not support other devices than Android, which can limit your options and preferences.</li>
-  </ul>
-</ul>
- <h2>Conclusion and FAQs</h2>
- <p>In conclusion, downloading komentar Facebook can be a useful and fun way to save, share, or analyze the videos posted in the comments section of a Facebook post. However, it can also be a challenging and tricky task that requires some special tools or techniques. In this article, we have shown you some of the best ways to download komentar Facebook easily and quickly using different methods, such as online tools, browser extensions, and mobile apps. We have also compared the pros and cons of each method and answered some frequently asked questions about downloading komentar Facebook. We hope you have found this article helpful and informative. If you have any questions or feedback, please feel free to leave a comment below.</p>
- <p>Here are some FAQs about downloading komentar Facebook:</p>
- <ol>
-<li><b>Can I download komentar Facebook from a private or restricted post?</b></li>
-<p>It depends on the method you use. Some methods, such as online tools or browser extensions, may not be able to download komentar Facebook from a private or restricted post due to Facebook's privacy settings or encryption. However, some methods, such as mobile apps, may be able to download komentar Facebook from a private or restricted post if you have access to it with your Facebook account.</p>
-<li><b>Can I download komentar Facebook in bulk?</b></li>
-<p>It depends on the method you use. Some methods, such as online tools, may be able to download komentar Facebook in bulk by exporting all the comments from a post or a page in a single file. However, some methods, such as browser extensions or mobile apps, may only be able to download komentar Facebook one by one, which can be time-consuming if you want to download multiple komentar Facebook.</p>
-<li><b>Can I download komentar Facebook in HD quality?</b></li>
-<p>It depends on the method you use and the quality of the original video. Some methods, such as online tools or browser extensions, may allow you to choose the quality (HD or SD) you want to download. However, some methods, such as mobile apps, may only download the videos in the default quality. Also, if the original video is not in HD quality, you may not be able to download it in HD quality either.</p>
-<li><b>Can I download komentar Facebook without logging in to Facebook?</b></li>
-<p>It depends on the method you use. Some methods, such as online tools or browser extensions, may allow you to download komentar Facebook without logging in to Facebook by using the post URL. However, some methods, such as mobile apps, may require you to log in to Facebook with your account to access the videos.</p>
-<li><b>Can I download komentar Facebook for free?</b></li>
-<p>It depends on the method you use. Some methods, such as online tools or browser extensions, may offer free trials or limited features for downloading komentar Facebook. However, some methods, such as mobile apps, may charge a fee or display ads for downloading komentar Facebook.</p>
-</ol></p> 401be4b1e0<br />
-<br />
-<br />
\ No newline at end of file
diff --git a/spaces/congsaPfin/Manga-OCR/logs/Download Quanzhi Fashi Season 5 English Subbed The Complete Guide to Watch Full-Time Magister 5 on Any Device.md b/spaces/congsaPfin/Manga-OCR/logs/Download Quanzhi Fashi Season 5 English Subbed The Complete Guide to Watch Full-Time Magister 5 on Any Device.md
deleted file mode 100644
index 26c2e94a2782541504d3bfe4cdf333c3a14a760b..0000000000000000000000000000000000000000
--- a/spaces/congsaPfin/Manga-OCR/logs/Download Quanzhi Fashi Season 5 English Subbed The Complete Guide to Watch Full-Time Magister 5 on Any Device.md	
+++ /dev/null
@@ -1,135 +0,0 @@
-
-<h1>How to Download Quanzhi Fashi Season 5</h1>
-<p>If you are a fan of Chinese anime, you might have heard of Quanzhi Fashi, also known as Full-Time Magister. This is one of the most popular and successful Chinese anime series, with four seasons already aired and a fifth one recently completed. In this article, we will tell you everything you need to know about Quanzhi Fashi Season 5, including what it is about, why you should watch it, where you can watch it, and how you can download it for offline viewing. Let's get started!</p>
- <h2>What is Quanzhi Fashi?</h2>
-<p>Quanzhi Fashi is a Chinese anime series based on a web novel of the same name by Luan. It follows the story of Mo Fan, a young man who lives in a world where magic and technology coexist. Mo Fan is a poor student who has no talent for magic, but he dreams of becoming a powerful mage. One day, he wakes up in a parallel world where magic is the only way to survive. He discovers that he has inherited a rare dual-elemental magic system, which gives him an edge over his enemies and rivals. He also meets many friends and foes along his journey to become a full-time magister.</p>
-<h2>download quanzhi fashi season 5</h2><br /><p><b><b>Download Zip</b> &#9675; <a href="https://urlca.com/2uOfPG">https://urlca.com/2uOfPG</a></b></p><br /><br />
- <h3>The plot of Quanzhi Fashi</h3>
-<p>The plot of Quanzhi Fashi is divided into several arcs, each focusing on a different aspect of Mo Fan's life and adventures. The first season introduces Mo Fan and his new world, where he attends a prestigious magic school and learns the basics of magic. He also faces various threats from monsters, bandits, and corrupt magicians. The second season follows Mo Fan as he travels to different cities and countries, where he encounters different cultures and challenges. He also learns more about his mysterious father and his past. The third season shows Mo Fan as he participates in an international tournament, where he competes with other talented magicians from around the world. He also discovers a conspiracy that threatens the balance of the world. The fourth season depicts Mo Fan as he returns to his original world, where he tries to find his missing friends and family. He also confronts a powerful enemy who wants to destroy both worlds. The fifth season continues Mo Fan's story as he faces new dangers and enemies in both worlds. He also develops his relationships with his friends and allies, as well as his powers and abilities.</p>
- <h3>The popularity of Quanzhi Fashi</h3>
-<p>Quanzhi Fashi is one of the most popular and successful Chinese anime series, with millions of fans and viewers around the world. It has received positive reviews from critics and audiences alike, who praise its engaging story, dynamic characters, stunning animation, and thrilling action scenes. It has also won several awards and nominations, such as the Best Web Anime Award at the China Animation & Comic Competition Golden Dragon Award in 2017. It has also spawned several spin-offs and adaptations, such as comics, games, audio dramas, and live-action films.</p>
- <h2>Why You Should Watch Quanzhi Fashi Season 5</h2>
-<p>If you are already a fan of Quanzhi Fashi, you probably don't need any convincing to watch the fifth season. But if you are new to the series or haven't watched it yet, here are some reasons why you should give it a try:</p>
- <h3>The new challenges and enemies for Mo Fan</h3>
-<p>In the fifth season of Quanzhi Fashi, Mo Fan faces new challenges and enemies in both worlds. In the magic world, he has to deal with the invasion of the dark creatures, who are led by a mysterious and powerful leader. He also has to face the hostility and jealousy of some of his fellow magicians, who see him as a threat or a rival. In the original world, he has to cope with the chaos and destruction caused by the enemy's attack, which has affected his friends and family. He also has to find a way to stop the enemy from destroying both worlds.</p>
- <h3>The development of Mo Fan's relationships and powers</h3>
-<p>In the fifth season of Quanzhi Fashi, Mo Fan also develops his relationships and powers in both worlds. He becomes closer with some of his friends and allies, such as Mu Ningxue, Xinxia, Ai Tutu, and Zhang Xiaohou. He also meets new characters who help him or hinder him in his journey, such as Ling Ling, Tang Yue, and Ye Xinxia. He also improves his skills and abilities as a dual-elemental magician, learning new spells and techniques. He also discovers some secrets and mysteries about his origin and destiny, which will affect his future.</p>
- <h3>The stunning animation and sound effects</h3>
-<p>In the fifth season of Quanzhi Fashi, the animation and sound effects are also stunning and impressive. The animation is smooth and detailed, showing the vivid and colorful scenes of both worlds. The action scenes are fast-paced and exciting, showing the spectacular and realistic battles between Mo Fan and his enemies. The sound effects are also immersive and realistic, enhancing the atmosphere and mood of the story. The voice actors are also talented and expressive, bringing the characters to life.</p>
- <h2>Where to Watch Quanzhi Fashi Season 5</h2>
-<p>If you are interested in watching Quanzhi Fashi Season 5, you might be wondering where you can watch it online. Here are some of the best options for you:</p>
-<p>download quanzhi fashi season 5 english subbed<br />
-download quanzhi fashi season 5 episode 12<br />
-download quanzhi fashi season 5 full episodes<br />
-download quanzhi fashi season 5 sub indo<br />
-download quanzhi fashi season 5 chinese anime<br />
-download quanzhi fashi season 5 myanimelist<br />
-download quanzhi fashi season 5 episode 1<br />
-download quanzhi fashi season 5 mp4<br />
-download quanzhi fashi season 5 mkv<br />
-download quanzhi fashi season 5 hd<br />
-download quanzhi fashi season 5 online free<br />
-download quanzhi fashi season 5 eng dub<br />
-download quanzhi fashi season 5 synopsis<br />
-download quanzhi fashi season 5 opening song<br />
-download quanzhi fashi season 5 ending theme<br />
-download quanzhi fashi season 5 torrent<br />
-download quanzhi fashi season 5 mega<br />
-download quanzhi fashi season 5 google drive<br />
-download quanzhi fashi season 5 kissanime<br />
-download quanzhi fashi season 5 crunchyroll<br />
-download quanzhi fashi season 5 netflix<br />
-download quanzhi fashi season 5 youtube<br />
-download quanzhi fashi season 5 dailymotion<br />
-download quanzhi fashi season 5 review<br />
-download quanzhi fashi season 5 rating<br />
-download quanzhi fashi season 5 characters<br />
-download quanzhi fashi season 5 mo fan<br />
-download quanzhi fashi season 5 tang yue<br />
-download quanzhi fashi season 5 ye xinxia<br />
-download quanzhi fashi season 5 zhang xiaohou<br />
-download quanzhi fashi season 5 novel<br />
-download quanzhi fashi season 5 manga<br />
-download quanzhi fashi season 5 comic<br />
-download quanzhi fashi season 5 manhua<br />
-download quanzhi fashi season 5 light novel<br />
-download quanzhi fashi season 5 web novel<br />
-download quanzhi fashi season 5 spoilers<br />
-download quanzhi fashi season 5 trailer<br />
-download quanzhi fashi season 5 release date<br />
-download quanzhi fashi season 5 update<br />
-download quanzhi fashi season 6 preview<br />
-download full time magister season 5 english subbed<br />
-download full time magister season 5 episode list <br />
-download full time magister season 5 action fantasy <br />
-download full time magister season 5 school theme <br />
-download full time magister season 5 white eagle <br />
-download full time magister season 5 skyscraper mystical snake <br />
-watch and download full time magister season 5 <br />
-how to download full time magister season 5</p>
- <h3>The official website of Quanzhi Fashi</h3>
-<p>The official website of Quanzhi Fashi is [quanzhifashi.com], where you can watch all the episodes of the series for free. The website is in Chinese, but you can use a translator tool to navigate it. The website also provides some information and news about the series, such as the synopsis, the cast, the staff, and the release dates. The website also has a forum where you can interact with other fans and share your opinions and feedback.</p>
- <h3>The best anime streaming services for Quanzhi Fashi</h3>
-<p>If you prefer to watch Quanzhi Fashi on an anime streaming service, you have several options to choose from. Here are some of the best ones:</p>
- <h4>Crunchyroll</h4>
-<p>Crunchyroll is one of the most popular and reliable anime streaming services in the world, with over 1200 titles in its library. You can watch Quanzhi Fashi Season 5 on Crunchyroll for free with ads, or you can subscribe to a premium plan for $7.99 per month or $79.99 per year. With a premium plan, you can enjoy ad-free streaming, HD quality, offline viewing, simulcasts, and exclusive content. You can also access Crunchyroll on various devices, such as smartphones, tablets, computers, TVs, game consoles, and more.</p>
- <h4>Funimation</h4>
-<p>Funimation is another popular and reliable anime streaming service in the world, with over 1000 titles in its library. You can watch Quanzhi Fashi Season 5 on Funimation for free with ads, or you can subscribe to a premium plan for $5.99 per month or $59.99 per year. With a premium plan, you can enjoy ad-free streaming, HD quality, offline viewing, simulcasts, and exclusive content. You can also access Funimation on various devices, such as smartphones, tablets, computers, TVs, game consoles, and more.</p>
- <h4>VRV</h4>
-<p>VRV is a streaming service that offers a variety of channels and genres, including anime, cartoons, gaming, comedy, and more. You can watch Quanzhi Fashi Season 5 on VRV for free with ads, or you can subscribe to a premium plan for $9.99 per month. With a premium plan, you can enjoy ad-free streaming, HD quality, offline viewing, simulcasts, and exclusive content. You can also access VRV on various devices, such as smartphones, tablets, computers, TVs, game consoles, and more.</p>
- <h3>How to download Quanzhi Fashi Season 5 from these platforms</h3>
-<p>If you want to download Quanzhi Fashi Season 5 from these platforms for offline viewing, you need to have a premium subscription and a compatible device. Here are the steps to download Quanzhi Fashi Season 5 from each platform:</p>
- <table>
-<tr>
-<th>Platform</th>
-<th>Steps</th>
-</tr>
-<tr>
-<td>Crunchyroll</td>
-<td>
-<ol>
-<li>Open the Crunchyroll app on your device and log in with your premium account.</li>
-<li>Search for Quanzhi Fashi Season 5 and select the episode you want to download.</li>
-<li>Tap on the download icon at the bottom of the screen and choose the quality you prefer.</li>
-<li>Wait for the download to finish and enjoy watching Quanzhi Fashi Season 5 offline.</li>
-</ol>
-</td>
-</tr>
-<tr>
-<td>Funimation</td>
-<td>
-<ol>
-<li>Open the Funimation app on your device and log in with your premium account.</li>
-<li>Search for Quanzhi Fashi Season 5 and select the episode you want to download.</li>
-<li>Tap on the download icon at the top of the screen and choose the quality you prefer.</li>
-<li>Wait for the download to finish and enjoy watching Quanzhi Fashi Season 5 offline.</li>
-</ol>
-</td>
-</tr>
-<tr>
-<td>VRV</td>
-<td>
-<ol>
-<li>Open the VRV app on your device and log in with your premium account.</li>
-<li>Search for Quanzhi Fashi Season 5 and select the episode you want to download.</li>
-<li>Tap on the download icon at the bottom of the screen and choose the quality you prefer.</li>
-<li>Wait for the download to finish and enjoy watching Quanzhi Fashi Season 5 offline.</li>
-</ol>
-</td>
-</tr>
-</table>
- <h2>Conclusion</h2>
-<p>In conclusion, Quanzhi Fashi Season 5 is a must-watch for any anime fan who loves magic, action, adventure, and drama. It is one of the best Chinese anime series ever made, with an engaging story, dynamic characters, stunning animation, and thrilling action scenes. You can watch Quanzhi Fashi Season 5 online on various platforms, such as the official website of Quanzhi Fashi, Crunchyroll, Funimation, or VRV. You can also download Quanzhi Fashi Season 5 from these platforms for offline viewing with a premium subscription and a compatible device. We hope this article has helped you learn more about Quanzhi Fashi Season 5 and how to watch it online or offline. Enjoy watching Quanzhi Fashi Season 5!</p>
- <h2>FAQs</h2>
- <h3>Q: How many episodes are there in Quanzhi Fashi Season 5?</h3>
- <p>A: There are 12 episodes in Quanzhi Fashi Season 5, each lasting about 20 minutes.</p>
- <h3>Q: When was Quanzhi Fashi Season 5 released?</h3>
- <p>A: Quanzhi Fashi Season 5 was released on June 16th, 2023 in China. It was also simulcasted on some of the streaming platforms mentioned above.</p>
- <h3>Q: Is there a dub version of Quanzhi Fashi Season 5?</h3>
- <p>A: No, there is no dub version of Quanzhi Fashi Season 5 yet. However, there are subtitles available in various languages, such as English, Spanish, French, German, Portuguese, Arabic, and more.</p>
- <h3>Q: Will there be a Quanzhi Fashi Season 6?</h3>
- <p>A: There is no official confirmation or announcement about Quanzhi Fashi Season 6 yet. However, given the popularity and success of the series, it is likely that there will be a sixth season in the future. </p>
- <h3>Q: Where can I read the web novel of Quanzhi Fashi?</h3>
- <p>A: You can read the web novel of Quanzhi Fashi on various websites, such as [novelupdates.com], [wuxiaworld.com], or [boxnovel.com]. However, be aware that the web novel is not fully translated into English yet, and there might be some differences between the web novel and the anime adaptation.</p> 197e85843d<br />
-<br />
-<br />
\ No newline at end of file
diff --git a/spaces/congsaPfin/Manga-OCR/logs/Free Super Cars and More with Pixel Car Racer MOD APK Hack Download.md b/spaces/congsaPfin/Manga-OCR/logs/Free Super Cars and More with Pixel Car Racer MOD APK Hack Download.md
deleted file mode 100644
index 3cf5d3988adfe4e899bf32067eda354b339be0f2..0000000000000000000000000000000000000000
--- a/spaces/congsaPfin/Manga-OCR/logs/Free Super Cars and More with Pixel Car Racer MOD APK Hack Download.md	
+++ /dev/null
@@ -1,99 +0,0 @@
-
-<h1>Download Pixel Car Racer Mod APK Hack: A Guide for Android Gamers</h1>
-<p>If you are a fan of racing games, you might have heard of Pixel Car Racer, a retro-style arcade racing game that lets you customize your car and race against other players. But did you know that you can download Pixel Car Racer mod apk hack and enjoy unlimited money, unlocked cars, and more? In this article, we will show you how to download Pixel Car Racer mod apk hack for Android devices, and give you some tips and tricks to make the most out of this amazing game.</p>
-<h2>download pixel car racer mod apk hack</h2><br /><p><b><b>Download</b> &#10040;&#10040;&#10040; <a href="https://urlca.com/2uO8S0">https://urlca.com/2uO8S0</a></b></p><br /><br />
- <h2>What is Pixel Car Racer?</h2>
-<p>Pixel Car Racer is a racing game developed by Studio Furukawa, a small indie game studio based in Canada. The game was released in 2016 and has since gained a loyal fan base of over 10 million downloads on Google Play Store. Pixel Car Racer is inspired by the classic arcade racing games of the 80s and 90s, with pixelated graphics, retro music, and simple gameplay. The game features over 1000 cars to choose from, ranging from vintage models to modern supercars. You can also customize your car with various parts, decals, and colors, and tune it to your liking. The game offers several modes to play, such as drag racing, street racing, story mode, and online multiplayer. You can also collect crates, trophies, and achievements as you progress in the game.</p>
- <h3>Features of Pixel Car Racer</h3>
-<p>Some of the features that make Pixel Car Racer stand out from other racing games are:</p>
-<ul>
-<li>Beautiful pixel art graphics that create a nostalgic atmosphere.</li>
-<li>Over 1000 cars to unlock and collect, each with their own stats and performance.</li>
-<li>Thousands of car parts and accessories to customize your car, such as engines, turbochargers, tires, spoilers, exhausts, and more.</li>
-<li>A realistic car tuning system that lets you adjust your car's power, torque, weight, gear ratio, and more.</li>
-<li>A dynamic weather system that affects the driving conditions and visibility.</li>
-<li>A variety of tracks and environments to race on, such as city streets, highways, deserts, forests, and snow.</li>
-<li>Several game modes to challenge yourself and other players, such as drag racing, street racing, story mode, ladder mode, tournament mode, and online multiplayer mode.</li>
-<li>A garage system that lets you store and manage your cars.</li>
-<li>A shop system that lets you buy new cars and parts with in-game currency or real money.</li>
-<li>A crate system that lets you earn random rewards by opening crates.</li>
-<li>A trophy system that lets you earn trophies by completing certain tasks or achievements.</li>
-</ul>
- <h3>Why download Pixel Car Racer mod apk hack?</h3>
-<p>While Pixel Car Racer is a fun and addictive game to play, it can also be frustrating and time-consuming at times. You might find yourself running out of money to buy new cars or parts, or struggling to win races against tougher opponents. You might also encounter annoying ads that interrupt your gameplay or tempt you to spend real money on in-app purchases. That's why downloading Pixel Car Racer mod apk hack can be a great solution for Android gamers who want to enjoy the game without any limitations or hassles. Here are some of the benefits of downloading Pixel Car Racer mod apk hack:</p>
-<ul>
-<li>You can get unlimited money to buy any car or part you want.</li>
-<li>You can unlock all the cars and parts available in the game, so you can try them all and find your favorite one.</li>
-<li>You can remove all the ads that might annoy you or slow down your device.</li>
-<li>You can bypass the verification process that might prevent you from installing the game.</li>
-<li>You can enjoy the game with enhanced graphics and sound quality.</li>
-<li>You can play the game offline without any internet connection.</li>
-</ul>
- <h2>How to download Pixel Car Racer mod apk hack?</h2>
-<p>Downloading Pixel Car Racer mod apk hack is not a difficult task, but you need to follow some steps carefully to avoid any errors or problems. Here are the steps you need to follow:</p>
- <h3>Step 1: Find a reliable source</h3>
-<p>The first thing you need to do is to find a reliable source that provides the Pixel Car Racer mod apk hack file. There are many websites and blogs that claim to offer the mod apk file, but not all of them are trustworthy or safe. Some of them might contain viruses, malware, or spyware that can harm your device or steal your personal information. Some of them might also provide fake or outdated files that won't work properly or at all. Therefore, you need to be careful and do some research before downloading anything from the internet. You can check the reviews, ratings, comments, and feedback of other users who have downloaded the file before. You can also use antivirus software or online scanners to scan the file for any potential threats. One of the sources that we recommend is [Pixel Car Racer Mod APK Hack], which is a reputable and secure website that provides the latest version of the mod apk file.</p>
- <h3>Step 2: Enable unknown sources</h3>
-<p>The next thing you need to do is to enable unknown sources on your Android device. This is a security setting that prevents you from installing apps from sources other than Google Play Store. Since Pixel Car Racer mod apk hack is not available on Google Play Store, you need to enable unknown sources to install it. To do this, go to your device's settings, then security, then unknown sources, and toggle it on. You might see a warning message that says installing apps from unknown sources can be harmful, but don't worry, as long as you download the file from a reliable source, there is nothing to be afraid of.</p>
-<p>How to download pixel car racer mod apk hack for free<br />
-Pixel car racer mod apk hack unlimited money and diamonds<br />
-Pixel car racer mod apk hack latest version 2023<br />
-Pixel car racer mod apk hack no root required<br />
-Pixel car racer mod apk hack online generator<br />
-Download pixel car racer mod apk hack for android devices<br />
-Download pixel car racer mod apk hack for ios devices<br />
-Download pixel car racer mod apk hack for pc windows 10<br />
-Download pixel car racer mod apk hack from apkdone.com[^1^]<br />
-Download pixel car racer mod apk hack with obb data<br />
-Pixel car racer mod apk hack features and benefits<br />
-Pixel car racer mod apk hack gameplay and review<br />
-Pixel car racer mod apk hack tips and tricks<br />
-Pixel car racer mod apk hack best cars and upgrades<br />
-Pixel car racer mod apk hack cheats and codes<br />
-Pixel car racer mod apk hack offline mode<br />
-Pixel car racer mod apk hack multiplayer mode<br />
-Pixel car racer mod apk hack customizations and tuning<br />
-Pixel car racer mod apk hack graphics and sound quality<br />
-Pixel car racer mod apk hack bugs and issues<br />
-Download pixel car racer mod apk hack safely and securely<br />
-Download pixel car racer mod apk hack without surveys or verification<br />
-Download pixel car racer mod apk hack from trusted sources<br />
-Download pixel car racer mod apk hack fast and easy<br />
-Download pixel car racer mod apk hack with direct link<br />
-Pixel car racer mod apk hack comparison with original version<br />
-Pixel car racer mod apk hack pros and cons<br />
-Pixel car racer mod apk hack user ratings and feedback<br />
-Pixel car racer mod apk hack updates and news<br />
-Pixel car racer mod apk hack support and contact information</p>
- <h3>Step 3: Install the mod apk file</h3>
-<p>The third thing you need to do is to install the Pixel Car Racer mod apk hack file on your device. To do this, go to your device's file manager, then locate the downloaded file (usually in the downloads folder), and tap on it. You might see a pop-up window that asks you for permission to install the app, just tap on install and wait for a few seconds until the installation is complete. You might also see another pop-up window that asks you if you want to open the app or done, just tap on done and exit the file manager.</p>
- <h3>Step 4: Enjoy the game</h3>
-<p>The last thing you need to do is to enjoy the game with all its features and benefits. To do this, go to your device's app drawer, then find and tap on the Pixel Car Racer icon. You will see a loading screen that says "Pixel Car Racer mod apk hack by PixelCarRacerModApkHack.com", which means that you have successfully installed the mod apk file. You can now start playing the game with unlimited money, unlocked cars, no ads, and more.</p>
- <h2>Tips and tricks for playing Pixel Car Racer mod apk hack</h2>
-<p>Now that you have downloaded and installed Pixel Car Racer mod apk hack, you might want to know some tips and tricks to make your gaming experience more enjoyable and rewarding. Here are some of them:</p>
- <h3>Customize your car</h3>
-<p>One of the best things about Pixel Car Racer is that you can customize your car with various parts and accessories. You can change your car's color, decals, wheels, tires, spoilers, exhausts, and more. You can also tune your car's engine, transmission, suspension, brakes, and more. Customizing your car not only makes it look cooler and unique, but also improves its performance and stats. You can experiment with different combinations and find what suits your style and preference.</p>
- <h3>Upgrade your engine and parts</h3>
-<p>Another thing you can do to improve your car's performance is to upgrade your engine and parts. You can buy new engines and parts with money or crates in the shop system. You can also find rare and legendary engines and parts by opening crates or completing achievements. Upgrading your engine and parts will increase your car's power, torque, speed, acceleration, handling, and more. You can also unlock new features and modes by upgrading your engine and parts. For example, you can unlock the turbocharger feature by upgrading your engine to level 10, or the nitrous feature by upgrading your engine to level 20. You can also unlock the story mode by upgrading your engine to level 30, or the online multiplayer mode by upgrading your engine to level 40.</p>
- <h3>Race in different modes and tracks</h3>
-<p>Another way to enjoy Pixel Car Racer is to race in different modes and tracks. You can choose from several game modes, such as drag racing, street racing, story mode, ladder mode, tournament mode, and online multiplayer mode. Each mode has its own rules, objectives, and rewards. You can also choose from various tracks and environments, such as city streets, highways, deserts, forests, and snow. Each track has its own layout, obstacles, and weather conditions. Racing in different modes and tracks will test your skills, strategy, and adaptability.</p>
- <h3>Collect rewards and achievements</h3>
-<p>Another thing you can do to make Pixel Car Racer more fun and rewarding is to collect rewards and achievements. You can earn money and crates by winning races, completing tasks, or watching ads. You can use money to buy new cars and parts, or crates to get random rewards. You can also earn trophies and achievements by completing certain challenges or milestones. You can view your trophies and achievements in the trophy system. Collecting rewards and achievements will motivate you to play more and improve your performance.</p>
- <h2>Conclusion</h2>
-<p>Pixel Car Racer is a great racing game that combines retro-style graphics, simple gameplay, and realistic car tuning. It offers a lot of features and options to customize your car and race against other players. However, it can also be frustrating and time-consuming at times, especially if you run out of money or face tough opponents. That's why downloading Pixel Car Racer mod apk hack can be a good idea for Android gamers who want to enjoy the game without any limitations or hassles. By downloading Pixel Car Racer mod apk hack, you can get unlimited money, unlocked cars, no ads, and more. You can also follow some tips and tricks to make your gaming experience more enjoyable and rewarding. We hope this article has helped you learn how to download Pixel Car Racer mod apk hack and play it on your Android device.</p>
- <h2>FAQs</h2>
-<p>Here are some frequently asked questions about Pixel Car Racer mod apk hack:</p>
-<ul>
-<li><b>Is Pixel Car Racer mod apk hack safe to download?</b><br>
-Yes, as long as you download it from a reliable source like [Pixel Car Racer Mod APK Hack], which is a reputable and secure website that provides the latest version of the mod apk file. You can also scan the file with antivirus software or online scanners before installing it.</li>
-<li><b>Is Pixel Car Racer mod apk hack compatible with my device?</b><br>
-Yes, Pixel Car Racer mod apk hack is compatible with most Android devices that run on Android 4.0.3 or higher. However, some devices might have different specifications or settings that might affect the game's performance or functionality. If you encounter any issues or errors while playing the game, you can try clearing the cache, restarting the device, or reinstalling the game.</li>
-<li><b>Can I play Pixel Car Racer mod apk hack online with other players?</b><br>
-Yes, you can play Pixel Car Racer mod apk hack online with other players in the online multiplayer mode. However, you might face some disadvantages or risks while doing so. For example, you might not be able to join some servers or rooms that have anti-cheat systems or filters. You might also get banned or reported by other players who notice that you are using a modded version of the game. Therefore, we advise you to play online with caution and respect.</li>
-<li><b>Can I update Pixel Car Racer mod apk hack to the latest version?</b><br>
-Yes, you can update Pixel Car Racer mod apk hack to the latest version by downloading it again from [Pixel Car Racer Mod APK Hack] whenever there is a new update available. However, you might lose some of your progress or data if you update the game without backing it up first. Therefore, we recommend you to backup your game data before updating the game.</li>
-<li><b>Can I request a new feature or report a bug for Pixel Car Racer mod apk hack?</b><br>
-Yes, you can request a new feature or report a bug for Pixel Car Racer mod apk hack by contacting the developers of [Pixel Car Racer Mod APK Hack] through their website or social media platforms. They are always open to feedback and suggestions from their users.</li>
-</ul></p> 401be4b1e0<br />
-<br />
-<br />
\ No newline at end of file
diff --git a/spaces/congsaPfin/Manga-OCR/logs/Miniforce X Battle Heroes Game A Fun and Exciting Game for Fans of Miniforce Cartoon.md b/spaces/congsaPfin/Manga-OCR/logs/Miniforce X Battle Heroes Game A Fun and Exciting Game for Fans of Miniforce Cartoon.md
deleted file mode 100644
index 0c6b2a8ac2912825bf50439c58e5f57e4cf33720..0000000000000000000000000000000000000000
--- a/spaces/congsaPfin/Manga-OCR/logs/Miniforce X Battle Heroes Game A Fun and Exciting Game for Fans of Miniforce Cartoon.md	
+++ /dev/null
@@ -1,137 +0,0 @@
-
-<h1>Miniforce X Battle Heroes: A Fun and Exciting Game for Kids</h1>
-<p>Do you love watching the Miniforce cartoon series? Do you want to join the adventures of Volt, Sammy, Lucy, Max, and X as they fight against the evil Zenos and his army? If you answered yes, then you will love playing Miniforce X Battle Heroes, a fun and exciting game for kids based on the popular animation. In this article, we will tell you everything you need to know about this game, including what it is, how to download and play it, and why you should play it. Read on to find out more!</p>
- <h2>What is Miniforce X Battle Heroes?</h2>
-<p>Miniforce X Battle Heroes is an action shooting game that takes original content and images from the famous Special Force MiniForce cartoon series from Korea. The game’s content tells about small, weak creatures that cannot defend themselves against invading invaders, so they elected their supernatural companions to form an organization that carries. Miniforce X names include 4 people, VOLT, SAMMY, LUCY and MAX. Accordingly, these small creatures have the ability to transform into superheroes thanks to the advanced technology of the old White Cat commander with each person a unique combat ability.</p>
-<h2>miniforce x battle heroes game download</h2><br /><p><b><b>Download</b> &rarr;&rarr;&rarr; <a href="https://urlca.com/2uOd8t">https://urlca.com/2uOd8t</a></b></p><br /><br />
- <h3>The story and characters of the game</h3>
-<p>The story of the game follows the plot of the cartoon series, where Dr. Jeremy of Miniforce Lab is investigating “Ellinium” the unknown substance containing mighty power. Zeus, the captain of Lizard Army eyes on Ellinium with a plan to threat humans by the weapons made of it. One day, he ambushes the lab and steals Ellinium. Miniforce Lab organizes a special squad to take it back–our Volt, Sammy, Max, Lucy from different regions gather to form Miniforce! Finally, Miniforce dispatches with Anna the daughter of Dr. Jeremy to fight against Lizard Army. Then soon they find unimaginable truth hidden under the villains’ evil conspiracy.</p>
-<p>The characters of the game are based on the cartoon series as well. You can choose from four main characters: Volt, Sammy, Lucy, and Max. Each character has their own personality, weapon, armor, and skill. For example:</p>
-<ul>
-<li>Volt is a blue superman with weapons and armor from the deep sea capable of firing bullets. He is brave, loyal, and energetic.</li>
-<li>Sammy is a red superman with weapons and armor from the Volcano capable of firing penetrating bullets. He is smart, calm, and strategic.</li>
-<li>Lucy is a pink superman with weapons and armor from the green forest capable of firing magical orbs to help her teammates recover HP. She is kind, cheerful, and caring.</li>
-<li>Max is a golden superman with weapons and armor from the barren desert has the most comprehensive skill in the team. He is strong, confident, and cool.</li>
-</ul>
-<p>You can also meet other characters from the cartoon series, such as Anna, Dr. Jeremy, White Cat Commander, Zeus, Lizard Army soldiers, and more.</p>
- <h3>The features and gameplay of the game</h3>
-<p>The game has many features and gameplay modes that make it fun and exciting for kids. Some of them are:</p>
-<ul>
-<li>The game has high-quality graphics and sound effects that make it look like an animated movie. You can enjoy watching your favorite characters in action on your screen.</li>
-<li>The game has various minigames that you can play with your chosen character. You can fight against Zenos and his army in a shooting mode, collect coins and items in a running mode, and solve puzzles and quizzes in a brain mode. You can also unlock new weapons, armors, and skills as you progress in the game.</li>
-<li>The game has a multiplayer mode that allows you to play with your friends online. You can team up with up to four players and cooperate to complete missions and challenges. You can also chat with your friends and send them gifts in the game.</li>
-<li>The game has a story mode that follows the cartoon series. You can watch cutscenes and dialogues that reveal the plot and the characters' emotions. You can also choose different paths and endings depending on your choices in the game.</li>
-</ul>
-<p>The gameplay of the game is simple and easy to learn. You can control your character using the virtual joystick and buttons on your screen. You can move, jump, shoot, use skills, and interact with objects in the game. You can also customize your character's appearance and equipment in the game menu.</p>
- <h2>How to download and play Miniforce X Battle Heroes?</h2>
-<p>If you are interested in playing Miniforce X Battle Heroes, you will need to download it from the official website or the app store. Here are the requirements and steps to download the game:</p>
- <h3>The requirements and steps to download the game</h3>
-<p>The game is compatible with Android and iOS devices. You will need at least 1 GB of free space on your device and a stable internet connection to download and play the game. The game is free to download and play, but it contains in-app purchases that you can buy with real money if you want to enhance your gaming experience.</p>
-<p>To download the game, you can follow these steps:</p>
-<p>miniforce x battle heroes game apk<br />
-miniforce x battle heroes game online<br />
-miniforce x battle heroes game play store<br />
-miniforce x battle heroes game for pc<br />
-miniforce x battle heroes game free download<br />
-miniforce x battle heroes game android<br />
-miniforce x battle heroes game ios<br />
-miniforce x battle heroes game review<br />
-miniforce x battle heroes game hack<br />
-miniforce x battle heroes game cheats<br />
-miniforce x battle heroes game mod apk<br />
-miniforce x battle heroes game tips and tricks<br />
-miniforce x battle heroes game walkthrough<br />
-miniforce x battle heroes game guide<br />
-miniforce x battle heroes game wiki<br />
-miniforce x battle heroes game characters<br />
-miniforce x battle heroes game gameplay<br />
-miniforce x battle heroes game trailer<br />
-miniforce x battle heroes game features<br />
-miniforce x battle heroes game updates<br />
-miniforce x battle heroes game release date<br />
-miniforce x battle heroes game system requirements<br />
-miniforce x battle heroes game how to play<br />
-miniforce x battle heroes game how to download<br />
-miniforce x battle heroes game how to install<br />
-miniforce x battle heroes game how to unlock characters<br />
-miniforce x battle heroes game how to get coins<br />
-miniforce x battle heroes game how to level up<br />
-miniforce x battle heroes game how to win battles<br />
-miniforce x battle heroes game best character<br />
-miniforce x battle heroes game best weapon<br />
-miniforce x battle heroes game best strategy<br />
-miniforce x battle heroes game best team<br />
-miniforce x battle heroes game best skills<br />
-miniforce x battle heroes game best mode<br />
-miniforce x battle heroes game best stage<br />
-miniforce x battle heroes game best score<br />
-miniforce x battle heroes game best rank<br />
-miniforce x battle heroes game best outfit<br />
-miniforce x battle heroes game best emulator<br />
-miniforce x h5 action shooting game online <br />
-play free html5 games like Minforce X H5 <br />
-Minforce X H5 mobile browser games <br />
-Minforce X H5 web games for kids <br />
-Minforce X H5 cartoon games for android <br />
-Minforce X H5 korean animation games <br />
-Minforce X H5 super hero games for ios <br />
-Minforce X H5 multiplayer games with friends <br />
-Minforce X H5 fun and addictive games </p>
-<ol>
-<li>Go to the official website of Miniforce X Battle Heroes at [https://miniforcex.com/] or search for it on Google Play Store or App Store.</li>
-<li>Click on the download button or the install button depending on your device.</li>
-<li>Wait for the game to download and install on your device.</li>
-<li>Open the game and follow the instructions to create your account and choose your character.</li>
-<li>Enjoy playing Miniforce X Battle Heroes!</li>
-</ol>
- <h3>The tips and tricks to enjoy the game</h3>
-<p>To enjoy the game more, you can use some tips and tricks that will help you improve your skills and have more fun. Here are some of them:</p>
-<ul>
-<li>Try different characters and weapons to find out which one suits your playstyle best. Each character has their own strengths and weaknesses, so experiment with them and see what works for you.</li>
-<li>Collect coins and items in the game to upgrade your weapons, armors, and skills. You can also buy them with real money if you want to save time and effort.</li>
-<li>Play with your friends online to cooperate and compete with them. You can also make new friends in the game by chatting and sending gifts to them.</li>
-<li>Follow the story mode to learn more about the plot and the characters. You can also choose different paths and endings depending on your choices in the game.</li>
-<li>Have fun playing Miniforce X Battle Heroes!</li>
-</ul>
- <h2>Why should you play Miniforce X Battle Heroes?</h2>
-<p>You might be wondering why you should play Miniforce X Battle Heroes instead of other games. Well, there are many reasons why this game is worth playing. Here are some of them:</p>
- <h3>The benefits and advantages of playing the game</h3>
-<p>Playing Miniforce X Battle Heroes can bring you many benefits and advantages, such as:</p>
-<ul>
-<li>You can have fun and entertainment by playing a fun and exciting game that is based on a popular cartoon series.</li>
-<li>You can improve your cognitive skills by playing a game that requires concentration, memory, logic, problem-solving, creativity, and decision-making.</li>
-<li>You can learn more about science, technology, engineering, art, math (STEAM) by playing a game that features advanced technology, superpowers, robots, aliens, etc.</li>
-<li>You can develop your social skills by playing a game that allows you to communicate, cooperate, compete, and make friends with other players online.</li>
-<li>You can express yourself by playing a game that allows you to customize your character's appearance and equipment according to your preferences.</li>
-</ul>
- <h3>The reviews and ratings of the game</h3>
-<p>If you are still not convinced that Miniforce X Battle Heroes is a good game to play, you can check out the reviews and ratings of the game from other players and sources. You can see that the game has received many positive feedbacks and high scores from its fans and critics. For example:</p>
-<ul>
-<li>The game has a 4.5 out of 5 stars rating on Google Play Store and a 4.6 out of 5 stars rating on App Store based on thousands of reviews. Many players praised the game for its graphics, gameplay, story, and characters.</li>
-<li>The game has a 5 out of 5 stars rating on Amazon.com based on 8 customer reviews. Some customers wrote that they loved the game, that it was fun and entertaining, and that their kids enjoyed watching and playing it.</li>
-<li>The game has a 9.2 out of 10 rating on Romance University based on 15 best Miniforce toys of 2023. The website ranked the game as the best Miniforce toy of 2023 and highlighted its features and benefits.</li>
-</ul>
-<p>These reviews and ratings show that Miniforce X Battle Heroes is a well-made and well-received game that many people love and recommend.</p>
- <h2>Conclusion</h2>
-<p>In conclusion, Miniforce X Battle Heroes is a fun and exciting game for kids that is based on the popular cartoon series Miniforce. The game allows you to join the adventures of Volt, Sammy, Lucy, Max, and X as they fight against the evil Zenos and his army. The game has many features and gameplay modes that make it fun and exciting for kids. You can choose from four main characters, each with their own personality, weapon, armor, and skill. You can play various minigames, such as shooting, running, and brain modes. You can play with your friends online in a multiplayer mode. You can follow the story mode that follows the cartoon series. You can also enjoy the high-quality graphics and sound effects that make the game look like an animated movie.</p>
-<p>To play the game, you will need to download it from the official website or the app store. The game is compatible with Android and iOS devices. The game is free to download and play, but it contains in-app purchases that you can buy with real money if you want to enhance your gaming experience. To enjoy the game more, you can use some tips and tricks that will help you improve your skills and have more fun.</p>
-<p>Playing Miniforce X Battle Heroes can bring you many benefits and advantages, such as having fun and entertainment, improving your cognitive skills, learning more about STEAM, developing your social skills, and expressing yourself. The game has received many positive feedbacks and high scores from its fans and critics, showing that it is a well-made and well-received game that many people love and recommend.</p>
-<p>If you are a fan of Miniforce or if you are looking for a fun and exciting game for kids, you should definitely try Miniforce X Battle Heroes. You will not regret it!</p>
- <h3>A call to action for the readers</h3>
-<p>Are you ready to play Miniforce X Battle Heroes? If yes, then what are you waiting for? Download the game now from the official website or the app store and join the adventures of Volt, Sammy, Lucy, Max, and X as they fight against the evil Zenos and his army. Have fun playing Miniforce X Battle Heroes!</p>
- <h2>FAQs</h2>
-<p>Here are some frequently asked questions about Miniforce X Battle Heroes:</p>
-<ol>
-<li>What is Miniforce?</li>
-<p>Miniforce is a popular cartoon series from Korea that features four small animals who transform into superheroes thanks to the advanced technology of the old White Cat commander. They fight against the evil Zenos and his army who threaten humans with weapons made of Ellinium, an unknown substance containing mighty power.</p>
-<li>Who are the main characters of Miniforce X Battle Heroes?</li>
-<p>The main characters of Miniforce X Battle Heroes are Volt, Sammy, Lucy, Max, and X. They are four members of Miniforce who have different personalities, weapons, armors, and skills. They also have animal forms that they can transform into.</p>
-<li>How do I download Miniforce X Battle Heroes?</li>
-<p>You can download Miniforce X Battle Heroes from the official website or the app store. The game is compatible with Android and iOS devices. You will need at least 1 GB of free space on your device and a stable internet connection to download and play the game. The game is free to download and play, but it contains in-app purchases that you can buy with real money if you want to enhance your gaming experience.</p>
-<li>What are the features and gameplay modes of Miniforce X Battle Heroes?</li>
-<p>Miniforce X Battle Heroes has many features and gameplay modes that make it fun and exciting for kids. Some of them are: high-quality graphics and sound effects, various minigames, multiplayer mode, story mode, and character customization.</p>
-<li>Why should I play Miniforce X Battle Heroes?</li>
-<p>You should play Miniforce X Battle Heroes because it is a fun and exciting game for kids that is based on a popular cartoon series. Playing the game can bring you many benefits and advantages, such as having fun and entertainment, improving your cognitive skills, learning more about STEAM, developing your social skills, and expressing yourself. The game has also received many positive feedbacks and high scores from its fans and critics.</p>
-</ol></p> 197e85843d<br />
-<br />
-<br />
\ No newline at end of file
diff --git a/spaces/congsaPfin/Manga-OCR/logs/My Hotel Life Mod Apk v1.0.8 - Free Rewards No Ads Latest Version.md b/spaces/congsaPfin/Manga-OCR/logs/My Hotel Life Mod Apk v1.0.8 - Free Rewards No Ads Latest Version.md
deleted file mode 100644
index c44ce0f2f541266f2add37df97b29a1b175b79af..0000000000000000000000000000000000000000
--- a/spaces/congsaPfin/Manga-OCR/logs/My Hotel Life Mod Apk v1.0.8 - Free Rewards No Ads Latest Version.md	
+++ /dev/null
@@ -1,87 +0,0 @@
-<br />
-<h1>My Hotel Life APK Mod: A Fun and Relaxing Simulation Game</h1>
-<p>Do you love hotel management games? Do you want to experience the life of a hotel owner and manager? If yes, then you should try My Hotel Life, a new simulation game that lets you run your own hotel and make it the best in the world. In this game, you can design your hotel, decorate your rooms, hire staff, serve guests, and earn money. You can also enjoy various mini-games, such as cooking, cleaning, gardening, and more. My Hotel Life is a fun and relaxing game that will keep you entertained for hours.</p>
-<h2>my hotel life apk mod</h2><br /><p><b><b>DOWNLOAD</b> ->>> <a href="https://urlca.com/2uOa8N">https://urlca.com/2uOa8N</a></b></p><br /><br />
-<p>But what if you want to enjoy the game without any ads or limitations? What if you want to have unlimited money and gems to buy anything you want? Well, there is a way to do that. You can download My Hotel Life APK Mod, a modified version of the game that gives you many advantages and benefits. In this article, we will tell you what is My Hotel Life APK Mod, why you should download it, and how to download and install it on your device.</p>
- <h2>What is My Hotel Life?</h2>
-<p>My Hotel Life is a simulation game developed by CookApps, a popular game studio that has created many other games, such as Farm Snow, Home Design Makeover, and Solitaire Tripeaks. My Hotel Life was released in June 2021 and has received positive reviews from players and critics. The game has over 1 million downloads on Google Play Store and has a rating of 4.4 out of 5 stars.</p>
- <h3>The gameplay of My Hotel Life</h3>
-<p>The gameplay of My Hotel Life is simple and intuitive. You start with a small hotel and your goal is to make it bigger and better. You can customize your hotel with different themes, colors, furniture, and decorations. You can also upgrade your facilities, such as the lobby, restaurant, spa, pool, gym, and more. You can hire staff to help you run your hotel, such as receptionists, chefs, cleaners, gardeners, and security guards. You can also interact with your guests and fulfill their requests. You can earn money from your guests and use it to improve your hotel. You can also earn gems by completing achievements and daily tasks.</p>
- <h3>The features of My Hotel Life</h3>
-<p>My Hotel Life has many features that make it an enjoyable and addictive game. Some of these features are:</p>
-<ul>
-<li>A variety of mini-games that test your skills and creativity.</li>
-<li>A wide range of items and options to decorate your hotel.</li>
-<li>A colorful and vibrant graphics style that creates a cheerful atmosphere.</li>
-<li>A relaxing and soothing soundtrack that matches the mood of the game.</li>
-<li>A friendly and helpful customer support team that responds to your queries and feedback.</li>
-</ul>
- <h2>Why download My Hotel Life APK Mod?</h2>
-<p>My Hotel Life is a free-to-play game that you can download from Google Play Store or App Store. However, the game also has some drawbacks that may affect your gaming experience. For example:</p>
-<ul>
-<li>The game has ads that pop up frequently and interrupt your gameplay.</li>
-<li>The game has in-app purchases that require real money to buy certain items or features.</li>
-<li>The game has limited resources that restrict your progress and creativity.</li>
-</ul>
-<p>That's why you may want to download My Hotel Life APK Mod instead. This is a modified version of the game that gives you many benefits and advantages over the original version. Some of these benefits are:</p>
- <h3>No ads and free rewards</h3>
-<p>With My Hotel Life APK Mod, you can enjoy the game without any ads or interruptions. You can also get free rewards every day, such as coins, gems, boosters, and more. You can use these rewards to buy anything you want in the game.</p>
- <h3>Unlimited money and gems</h3>
-<p>With My Hotel Life APK Mod, you can have unlimited money and gems in your account. You can use this money and gems to upgrade your hotel, buy new items, unlock new features, and more. You can also spend them without worrying about running out of them. You can make your hotel as luxurious and beautiful as you want.</p>
-<p>My Hotel Life Mod Apk Unlimited Money<br />
-How to Download My Hotel Life Mod Apk for Android<br />
-My Hotel Life Mod Apk No Ads Free Rewards<br />
-My Hotel Life Mod Apk Latest Version 1.0.8<br />
-My Hotel Life Mod Apk Gameplay and Review<br />
-My Hotel Life Mod Apk Hack Cheat Codes<br />
-My Hotel Life Mod Apk Offline Mode<br />
-My Hotel Life Mod Apk Free Download Link<br />
-My Hotel Life Mod Apk Features and Benefits<br />
-My Hotel Life Mod Apk Tips and Tricks<br />
-My Hotel Life Mod Apk Best Hotels and Rooms<br />
-My Hotel Life Mod Apk VIP Membership<br />
-My Hotel Life Mod Apk Online Multiplayer<br />
-My Hotel Life Mod Apk Bug Fixes and Updates<br />
-My Hotel Life Mod Apk Requirements and Compatibility<br />
-My Hotel Life Mod Apk Installation Guide and Tutorial<br />
-My Hotel Life Mod Apk Customer Support and Feedback<br />
-My Hotel Life Mod Apk Alternatives and Similar Games<br />
-My Hotel Life Mod Apk Pros and Cons<br />
-My Hotel Life Mod Apk Ratings and Reviews<br />
-My Hotel Life Mod Apk Fun and Addictive Game<br />
-My Hotel Life Mod Apk Simulation and Management Game<br />
-My Hotel Life Mod Apk Build Your Own Hotel Empire<br />
-My Hotel Life Mod Apk Customize Your Hotel Design<br />
-My Hotel Life Mod Apk Hire and Train Your Staff<br />
-My Hotel Life Mod Apk Serve Your Guests and Earn Money<br />
-My Hotel Life Mod Apk Upgrade Your Facilities and Services<br />
-My Hotel Life Mod Apk Unlock New Locations and Themes<br />
-My Hotel Life Mod Apk Complete Challenges and Achievements<br />
-My Hotel Life Mod Apk Enjoy the Story and Characters</p>
- <h3>Easy installation and compatibility</h3>
-<p>With My Hotel Life APK Mod, you can install the game easily and quickly on your device. You don't need to root or jailbreak your device to use the mod. You also don't need to uninstall the original version of the game. You can simply download the APK file and install it over the existing game. The mod is compatible with most Android and iOS devices and works smoothly and flawlessly.</p>
- <h2>How to download and install My Hotel Life APK Mod?</h2>
-<p>If you are interested in downloading and installing My Hotel Life APK Mod, you can follow these simple steps:</p>
- <h3>Download the APK file from a trusted source</h3>
-<p>The first step is to download the APK file of My Hotel Life APK Mod from a trusted source. You can find many websites that offer the mod, but be careful of fake or malicious links that may harm your device or steal your data. We recommend you to use this link to download the mod safely and securely.</p>
- <h3>Enable unknown sources on your device</h3>
-<p>The next step is to enable unknown sources on your device. This is a security setting that allows you to install apps from sources other than Google Play Store or App Store. To enable unknown sources, you can go to your device settings, then security, then unknown sources, and toggle it on.</p>
- <h3>Install the APK file and enjoy the game</h3>
-<p>The final step is to install the APK file and enjoy the game. You can locate the downloaded file in your file manager or downloads folder, then tap on it to start the installation process. Follow the instructions on the screen and wait for the installation to finish. Once done, you can open the game and enjoy My Hotel Life APK Mod.</p>
- <h2>Conclusion</h2>
-<p>My Hotel Life is a fun and relaxing simulation game that lets you run your own hotel and make it the best in the world. You can design your hotel, decorate your rooms, hire staff, serve guests, and earn money. You can also enjoy various mini-games, such as cooking, cleaning, gardening, and more. However, if you want to have a better gaming experience, you should download My Hotel Life APK Mod, a modified version of the game that gives you many benefits and advantages, such as no ads, free rewards, unlimited money and gems, easy installation and compatibility. You can download My Hotel Life APK Mod from this link and follow the steps above to install it on your device. We hope you enjoy playing My Hotel Life APK Mod and have a great time.</p>
- <h2>FAQs</h2>
-<ul>
-<li><b>Q: Is My Hotel Life APK Mod safe to use?</b></li>
-<li>A: Yes, My Hotel Life APK Mod is safe to use as long as you download it from a trusted source like this link. The mod does not contain any viruses or malware that may harm your device or data.</li>
-<li><b>Q: Do I need an internet connection to play My Hotel Life APK Mod?</b></li>
-<li>A: No, you don't need an internet connection to play My Hotel Life APK Mod. You can play the game offline without any problems.</li>
-<li><b>Q: Will I lose my progress if I update the game?</b></li>
-<li>A: No, you won't lose your progress if you update the game. The mod will automatically update itself with the latest version of the game without affecting your data or settings.</li>
-<li><b>Q: Can I play My Hotel Life APK Mod with my friends?</b></li>
-<li>A: Yes, you can play My Hotel Life APK Mod with your friends. The game has a social feature that allows you to connect with your Facebook friends and visit their hotels. You can also chat with them and send them gifts.</li>
-<li><b>Q: How can I contact the customer support team of My Hotel Life?</b></li>
-<li>A: If you have any questions or issues regarding My Hotel Life or My Hotel Life APK Mod, you can contact the customer support team of CookApps by sending an email to support@cookapps.com or by filling out this form. They will respond to you as soon as possible.</li>
-</ul></p> 197e85843d<br />
-<br />
-<br />
\ No newline at end of file
diff --git a/spaces/congsaPfin/Manga-OCR/logs/Thanks Music APK The Best App for Sharing Music with Friends.md b/spaces/congsaPfin/Manga-OCR/logs/Thanks Music APK The Best App for Sharing Music with Friends.md
deleted file mode 100644
index feafa6c70f8daf2f61269e8460b2a01e61430470..0000000000000000000000000000000000000000
--- a/spaces/congsaPfin/Manga-OCR/logs/Thanks Music APK The Best App for Sharing Music with Friends.md	
+++ /dev/null
@@ -1,107 +0,0 @@
-
-<h1>Thanks Music APK Download: How to Play Two Songs at the Same Time on Your Android Device</h1>
- <p>Do you love listening to music with your friends, but hate having to compromise on what song to play? Do you wish you could play two different songs at the same time on your Android device, and share your headphones with someone else? If you answered yes to any of these questions, then you need to download Thanks Music APK, the only streaming music player that lets you do just that.</p>
-<h2>thanks music apk download</h2><br /><p><b><b>Download</b> &#9734; <a href="https://urlca.com/2uO7du">https://urlca.com/2uO7du</a></b></p><br /><br />
- <h2>What is Thanks Music?</h2>
- <p>Thanks Music is an innovative app that allows you to play two songs at the same time on your Android device, and share your headphones with another person. You can choose any song from your local library or from online sources like YouTube, Spotify, SoundCloud, and more. You can also adjust the volume of each song independently, and switch between them with a simple tap.</p>
- <h3>Features of Thanks Music</h3>
- <ul>
-<li>Play two songs at the same time on your Android device</li>
-<li>Share your headphones with another person</li>
-<li>Choose any song from your local library or online sources</li>
-<li>Adjust the volume of each song independently</li>
-<li>Switch between songs with a simple tap</li>
-<li>Elegant use of screen space allows you to browse music at a glance</li>
-<li>Dual Music mode lets you play two songs in sync or in shuffle</li>
-<li>Supports various audio formats like MP3, WAV, OGG, FLAC, etc.</li>
-<li>No ads, no subscription fees, no registration required</li>
-</ul>
- <h3>Benefits of Thanks Music</h3>
- <ul>
-<li>Enjoy music with your friends without compromising on your preferences</li>
-<li>Discover new songs and genres by listening to what others like</li>
-<li>Create a unique musical experience by mixing and matching different songs</li>
-<li>Save battery and data by playing local songs instead of streaming online</li>
-<li>Have fun and be creative with your music choices</li>
-</ul>
- <h2>How to Download and Install Thanks Music APK</h2>
- <p>If you want to try out Thanks Music for yourself, you will need to download and install the APK file on your Android device. Here are the steps you need to follow:</p>
- <h3>Step 1: Enable Unknown Sources</h3>
- <p>Since Thanks Music is not available on the Google Play Store, you will need to enable unknown sources on your device settings. This will allow you to install apps from sources other than the official store. To do this, go to Settings > Security > Unknown Sources and toggle it on.</p>
-<p>thanks music app download<br />
-thanks music apk free download<br />
-thanks music dual player apk<br />
-thanks music streaming apk<br />
-thanks music play two songs apk<br />
-download thanks music for android<br />
-thanks music apk latest version<br />
-thanks music apk mod<br />
-thanks music premium apk<br />
-thanks music offline apk<br />
-thanks music apk download for pc<br />
-thanks music apk mirror<br />
-thanks music apk old version<br />
-thanks music apk no ads<br />
-thanks music apk pro<br />
-thanks music share headphones apk<br />
-thanks music split screen apk<br />
-thanks music apk pure<br />
-thanks music apk uptodown<br />
-thanks music apk 2023<br />
-thanks music beta apk download<br />
-thanks music cracked apk download<br />
-thanks music full version apk download<br />
-thanks music hack apk download<br />
-thanks music plus apk download<br />
-download thanks music app for free<br />
-download thanks music app for android phone<br />
-download thanks music app from google play store<br />
-download thanks music app from apkpure.com<br />
-download thanks music app from uptodown.com<br />
-how to download thanks music app on android device<br />
-how to download thanks music app on pc using bluestacks emulator<br />
-how to download thanks music app on mac using nox player emulator<br />
-how to download thanks music app on iphone using ios emulator<br />
-how to download thanks music app on firestick using downloader app<br />
-how to install thanks music app on android device after downloading the apk file<br />
-how to install thanks music app on pc using bluestacks emulator after downloading the apk file<br />
-how to install thanks music app on mac using nox player emulator after downloading the apk file<br />
-how to install thanks music app on iphone using ios emulator after downloading the ipa file<br />
-how to install thanks music app on firestick using downloader app after downloading the apk file<br />
-how to use thanks music app to play two songs at the same time on android device<br />
-how to use thanks music app to play two songs at the same time on pc using bluestacks emulator <br />
-how to use thanks music app to play two songs at the same time on mac using nox player emulator <br />
-how to use thanks music app to play two songs at the same time on iphone using ios emulator <br />
-how to use thanks music app to play two songs at the same time on firestick using downloader app <br />
-how to share headphones with someone using thanks music app on android device <br />
-how to share headphones with someone using thanks music app on pc using bluestacks emulator <br />
-how to share headphones with someone using thanks music app on mac using nox player emulator</p>
- <h3>Step 2: Download the APK File</h3>
- <p>Next, you will need to download the APK file of Thanks Music from a reliable source. You can use this link to download it directly from the Google Play Store. Alternatively, you can search for "Thanks Music APK" on any web browser and find a suitable site that offers it.</p>
- <h3>Step 3: Install the APK File</h3>
- <p>Once you have downloaded the APK file, locate it on your device storage and tap on it. You will see a prompt asking you to confirm the installation. Tap on "Install" and wait for a few seconds until the app is installed. You will see a notification when it is done.</p>
- <h2>How to Use Thanks Music to Play Two Songs at the Same Time</h2>
- <p>Now that you have installed Thanks Music on your device, you are ready to use it to play two songs at the same time. Here are the steps you need to follow:</p>
- <h3>Step 1: Launch the App and Grant Permissions</h3>
- <p>Open the Thanks Music app on your device and grant the necessary permissions to access your storage and microphone. This will allow the app to play songs from your local library and online sources, and to record your voice if you want to sing along.</p>
- <h3>Step 2: Choose Your Songs and Adjust the Volume</h3>
- <p>On the main screen of the app, you will see two tabs: Left and Right. These correspond to the left and right earphones that you will share with another person. Tap on either tab to choose a song from your local library or online sources. You can also search for a song by typing its name or artist in the search bar. Once you have chosen a song, you can adjust its volume by dragging the slider below it. You can also mute or pause the song by tapping on the icons next to the slider.</p>
- <h3>Step 3: Share Your Headphones and Enjoy the Music</h3>
- <p>Now that you have selected and adjusted your songs, you are ready to share your headphones with another person. Plug in your headphones to your device and give one earphone to your friend. You can also use a splitter or a Bluetooth device to connect two pairs of headphones. Then, tap on the play button at the bottom of the screen to start playing both songs at the same time. You can also switch between songs by tapping on the left or right tab. Enjoy the music with your friend and have fun!</p>
- <h2>Conclusion</h2>
- <p>Thanks Music is a unique app that lets you play two songs at the same time on your Android device, and share your headphones with another person. You can choose any song from your local library or online sources, and adjust the volume of each song independently. You can also switch between songs with a simple tap, and create a unique musical experience by mixing and matching different songs. Thanks Music is easy to download and install, and requires no ads, no subscription fees, no registration. It is a great way to enjoy music with your friends without compromising on your preferences, and discover new songs and genres by listening to what others like. Download Thanks Music APK today and try it out for yourself!</p>
- <h2>FAQs</h2>
- <ul>
-<li><b>Q: Is Thanks Music safe to use?</b></li>
-<li>A: Yes, Thanks Music is safe to use as long as you download it from a reliable source. The app does not contain any malware or viruses, and does not collect any personal information from you.</li>
-<li><b>Q: Does Thanks Music work offline?</b></li>
-<li>A: Yes, Thanks Music works offline if you play songs from your local library. However, if you want to play songs from online sources, you will need an internet connection.</li>
-<li><b>Q: Can I play more than two songs at the same time?</b></li>
-<li>A: No, Thanks Music only allows you to play two songs at the same time. However, you can switch between songs as many times as you want.</li>
-<li><b>Q: Can I use Thanks Music with other apps?</b></li>
-<li>A: Yes, you can use Thanks Music with other apps that support background playback, such as YouTube, Spotify, SoundCloud, etc. However, you may experience some interference or lag if you play too many apps at the same time.</li>
-<li><b>Q: How can I contact the developer of Thanks Music?</b></li>
-<li>A: You can contact the developer of Thanks Music by sending an email to thanksmusicapp@gmail.com. You can also leave a review or feedback on the Google Play Store page of the app.</li>
-</ul></p> 401be4b1e0<br />
-<br />
-<br />
\ No newline at end of file
diff --git a/spaces/contluForse/HuggingGPT/assets/Dekart Sim Manager 3 2 Keygen 18 The Ultimate Solution for SIM Card Processing.md b/spaces/contluForse/HuggingGPT/assets/Dekart Sim Manager 3 2 Keygen 18 The Ultimate Solution for SIM Card Processing.md
deleted file mode 100644
index f3f3cff54cce96b4dba06149d6c0dd93158cc8e7..0000000000000000000000000000000000000000
--- a/spaces/contluForse/HuggingGPT/assets/Dekart Sim Manager 3 2 Keygen 18 The Ultimate Solution for SIM Card Processing.md	
+++ /dev/null
@@ -1,6 +0,0 @@
-<h2>Dekart Sim Manager 3 2 Keygen 18</h2><br /><p><b><b>Download</b> &#10022; <a href="https://ssurll.com/2uzyuQ">https://ssurll.com/2uzyuQ</a></b></p><br /><br />
-
- aaccfb2cb3<br />
-<br />
-<br />
-<p></p>
diff --git a/spaces/coreml-community/ControlNet-v1-1-Annotators-cpu/annotator/mmpkg/mmcv/image/geometric.py b/spaces/coreml-community/ControlNet-v1-1-Annotators-cpu/annotator/mmpkg/mmcv/image/geometric.py
deleted file mode 100644
index cf97c201cb4e43796c911919d03fb26a07ed817d..0000000000000000000000000000000000000000
--- a/spaces/coreml-community/ControlNet-v1-1-Annotators-cpu/annotator/mmpkg/mmcv/image/geometric.py
+++ /dev/null
@@ -1,728 +0,0 @@
-# Copyright (c) OpenMMLab. All rights reserved.
-import numbers
-
-import cv2
-import numpy as np
-
-from ..utils import to_2tuple
-from .io import imread_backend
-
-try:
-    from PIL import Image
-except ImportError:
-    Image = None
-
-
-def _scale_size(size, scale):
-    """Rescale a size by a ratio.
-
-    Args:
-        size (tuple[int]): (w, h).
-        scale (float | tuple(float)): Scaling factor.
-
-    Returns:
-        tuple[int]: scaled size.
-    """
-    if isinstance(scale, (float, int)):
-        scale = (scale, scale)
-    w, h = size
-    return int(w * float(scale[0]) + 0.5), int(h * float(scale[1]) + 0.5)
-
-
-cv2_interp_codes = {
-    'nearest': cv2.INTER_NEAREST,
-    'bilinear': cv2.INTER_LINEAR,
-    'bicubic': cv2.INTER_CUBIC,
-    'area': cv2.INTER_AREA,
-    'lanczos': cv2.INTER_LANCZOS4
-}
-
-if Image is not None:
-    pillow_interp_codes = {
-        'nearest': Image.NEAREST,
-        'bilinear': Image.BILINEAR,
-        'bicubic': Image.BICUBIC,
-        'box': Image.BOX,
-        'lanczos': Image.LANCZOS,
-        'hamming': Image.HAMMING
-    }
-
-
-def imresize(img,
-             size,
-             return_scale=False,
-             interpolation='bilinear',
-             out=None,
-             backend=None):
-    """Resize image to a given size.
-
-    Args:
-        img (ndarray): The input image.
-        size (tuple[int]): Target size (w, h).
-        return_scale (bool): Whether to return `w_scale` and `h_scale`.
-        interpolation (str): Interpolation method, accepted values are
-            "nearest", "bilinear", "bicubic", "area", "lanczos" for 'cv2'
-            backend, "nearest", "bilinear" for 'pillow' backend.
-        out (ndarray): The output destination.
-        backend (str | None): The image resize backend type. Options are `cv2`,
-            `pillow`, `None`. If backend is None, the global imread_backend
-            specified by ``mmcv.use_backend()`` will be used. Default: None.
-
-    Returns:
-        tuple | ndarray: (`resized_img`, `w_scale`, `h_scale`) or
-            `resized_img`.
-    """
-    h, w = img.shape[:2]
-    if backend is None:
-        backend = imread_backend
-    if backend not in ['cv2', 'pillow']:
-        raise ValueError(f'backend: {backend} is not supported for resize.'
-                         f"Supported backends are 'cv2', 'pillow'")
-
-    if backend == 'pillow':
-        assert img.dtype == np.uint8, 'Pillow backend only support uint8 type'
-        pil_image = Image.fromarray(img)
-        pil_image = pil_image.resize(size, pillow_interp_codes[interpolation])
-        resized_img = np.array(pil_image)
-    else:
-        resized_img = cv2.resize(
-            img, size, dst=out, interpolation=cv2_interp_codes[interpolation])
-    if not return_scale:
-        return resized_img
-    else:
-        w_scale = size[0] / w
-        h_scale = size[1] / h
-        return resized_img, w_scale, h_scale
-
-
-def imresize_to_multiple(img,
-                         divisor,
-                         size=None,
-                         scale_factor=None,
-                         keep_ratio=False,
-                         return_scale=False,
-                         interpolation='bilinear',
-                         out=None,
-                         backend=None):
-    """Resize image according to a given size or scale factor and then rounds
-    up the the resized or rescaled image size to the nearest value that can be
-    divided by the divisor.
-
-    Args:
-        img (ndarray): The input image.
-        divisor (int | tuple): Resized image size will be a multiple of
-            divisor. If divisor is a tuple, divisor should be
-            (w_divisor, h_divisor).
-        size (None | int | tuple[int]): Target size (w, h). Default: None.
-        scale_factor (None | float | tuple[float]): Multiplier for spatial
-            size. Should match input size if it is a tuple and the 2D style is
-            (w_scale_factor, h_scale_factor). Default: None.
-        keep_ratio (bool): Whether to keep the aspect ratio when resizing the
-            image. Default: False.
-        return_scale (bool): Whether to return `w_scale` and `h_scale`.
-        interpolation (str): Interpolation method, accepted values are
-            "nearest", "bilinear", "bicubic", "area", "lanczos" for 'cv2'
-            backend, "nearest", "bilinear" for 'pillow' backend.
-        out (ndarray): The output destination.
-        backend (str | None): The image resize backend type. Options are `cv2`,
-            `pillow`, `None`. If backend is None, the global imread_backend
-            specified by ``mmcv.use_backend()`` will be used. Default: None.
-
-    Returns:
-        tuple | ndarray: (`resized_img`, `w_scale`, `h_scale`) or
-            `resized_img`.
-    """
-    h, w = img.shape[:2]
-    if size is not None and scale_factor is not None:
-        raise ValueError('only one of size or scale_factor should be defined')
-    elif size is None and scale_factor is None:
-        raise ValueError('one of size or scale_factor should be defined')
-    elif size is not None:
-        size = to_2tuple(size)
-        if keep_ratio:
-            size = rescale_size((w, h), size, return_scale=False)
-    else:
-        size = _scale_size((w, h), scale_factor)
-
-    divisor = to_2tuple(divisor)
-    size = tuple([int(np.ceil(s / d)) * d for s, d in zip(size, divisor)])
-    resized_img, w_scale, h_scale = imresize(
-        img,
-        size,
-        return_scale=True,
-        interpolation=interpolation,
-        out=out,
-        backend=backend)
-    if return_scale:
-        return resized_img, w_scale, h_scale
-    else:
-        return resized_img
-
-
-def imresize_like(img,
-                  dst_img,
-                  return_scale=False,
-                  interpolation='bilinear',
-                  backend=None):
-    """Resize image to the same size of a given image.
-
-    Args:
-        img (ndarray): The input image.
-        dst_img (ndarray): The target image.
-        return_scale (bool): Whether to return `w_scale` and `h_scale`.
-        interpolation (str): Same as :func:`resize`.
-        backend (str | None): Same as :func:`resize`.
-
-    Returns:
-        tuple or ndarray: (`resized_img`, `w_scale`, `h_scale`) or
-            `resized_img`.
-    """
-    h, w = dst_img.shape[:2]
-    return imresize(img, (w, h), return_scale, interpolation, backend=backend)
-
-
-def rescale_size(old_size, scale, return_scale=False):
-    """Calculate the new size to be rescaled to.
-
-    Args:
-        old_size (tuple[int]): The old size (w, h) of image.
-        scale (float | tuple[int]): The scaling factor or maximum size.
-            If it is a float number, then the image will be rescaled by this
-            factor, else if it is a tuple of 2 integers, then the image will
-            be rescaled as large as possible within the scale.
-        return_scale (bool): Whether to return the scaling factor besides the
-            rescaled image size.
-
-    Returns:
-        tuple[int]: The new rescaled image size.
-    """
-    w, h = old_size
-    if isinstance(scale, (float, int)):
-        if scale <= 0:
-            raise ValueError(f'Invalid scale {scale}, must be positive.')
-        scale_factor = scale
-    elif isinstance(scale, tuple):
-        max_long_edge = max(scale)
-        max_short_edge = min(scale)
-        scale_factor = min(max_long_edge / max(h, w),
-                           max_short_edge / min(h, w))
-    else:
-        raise TypeError(
-            f'Scale must be a number or tuple of int, but got {type(scale)}')
-
-    new_size = _scale_size((w, h), scale_factor)
-
-    if return_scale:
-        return new_size, scale_factor
-    else:
-        return new_size
-
-
-def imrescale(img,
-              scale,
-              return_scale=False,
-              interpolation='bilinear',
-              backend=None):
-    """Resize image while keeping the aspect ratio.
-
-    Args:
-        img (ndarray): The input image.
-        scale (float | tuple[int]): The scaling factor or maximum size.
-            If it is a float number, then the image will be rescaled by this
-            factor, else if it is a tuple of 2 integers, then the image will
-            be rescaled as large as possible within the scale.
-        return_scale (bool): Whether to return the scaling factor besides the
-            rescaled image.
-        interpolation (str): Same as :func:`resize`.
-        backend (str | None): Same as :func:`resize`.
-
-    Returns:
-        ndarray: The rescaled image.
-    """
-    h, w = img.shape[:2]
-    new_size, scale_factor = rescale_size((w, h), scale, return_scale=True)
-    rescaled_img = imresize(
-        img, new_size, interpolation=interpolation, backend=backend)
-    if return_scale:
-        return rescaled_img, scale_factor
-    else:
-        return rescaled_img
-
-
-def imflip(img, direction='horizontal'):
-    """Flip an image horizontally or vertically.
-
-    Args:
-        img (ndarray): Image to be flipped.
-        direction (str): The flip direction, either "horizontal" or
-            "vertical" or "diagonal".
-
-    Returns:
-        ndarray: The flipped image.
-    """
-    assert direction in ['horizontal', 'vertical', 'diagonal']
-    if direction == 'horizontal':
-        return np.flip(img, axis=1)
-    elif direction == 'vertical':
-        return np.flip(img, axis=0)
-    else:
-        return np.flip(img, axis=(0, 1))
-
-
-def imflip_(img, direction='horizontal'):
-    """Inplace flip an image horizontally or vertically.
-
-    Args:
-        img (ndarray): Image to be flipped.
-        direction (str): The flip direction, either "horizontal" or
-            "vertical" or "diagonal".
-
-    Returns:
-        ndarray: The flipped image (inplace).
-    """
-    assert direction in ['horizontal', 'vertical', 'diagonal']
-    if direction == 'horizontal':
-        return cv2.flip(img, 1, img)
-    elif direction == 'vertical':
-        return cv2.flip(img, 0, img)
-    else:
-        return cv2.flip(img, -1, img)
-
-
-def imrotate(img,
-             angle,
-             center=None,
-             scale=1.0,
-             border_value=0,
-             interpolation='bilinear',
-             auto_bound=False):
-    """Rotate an image.
-
-    Args:
-        img (ndarray): Image to be rotated.
-        angle (float): Rotation angle in degrees, positive values mean
-            clockwise rotation.
-        center (tuple[float], optional): Center point (w, h) of the rotation in
-            the source image. If not specified, the center of the image will be
-            used.
-        scale (float): Isotropic scale factor.
-        border_value (int): Border value.
-        interpolation (str): Same as :func:`resize`.
-        auto_bound (bool): Whether to adjust the image size to cover the whole
-            rotated image.
-
-    Returns:
-        ndarray: The rotated image.
-    """
-    if center is not None and auto_bound:
-        raise ValueError('`auto_bound` conflicts with `center`')
-    h, w = img.shape[:2]
-    if center is None:
-        center = ((w - 1) * 0.5, (h - 1) * 0.5)
-    assert isinstance(center, tuple)
-
-    matrix = cv2.getRotationMatrix2D(center, -angle, scale)
-    if auto_bound:
-        cos = np.abs(matrix[0, 0])
-        sin = np.abs(matrix[0, 1])
-        new_w = h * sin + w * cos
-        new_h = h * cos + w * sin
-        matrix[0, 2] += (new_w - w) * 0.5
-        matrix[1, 2] += (new_h - h) * 0.5
-        w = int(np.round(new_w))
-        h = int(np.round(new_h))
-    rotated = cv2.warpAffine(
-        img,
-        matrix, (w, h),
-        flags=cv2_interp_codes[interpolation],
-        borderValue=border_value)
-    return rotated
-
-
-def bbox_clip(bboxes, img_shape):
-    """Clip bboxes to fit the image shape.
-
-    Args:
-        bboxes (ndarray): Shape (..., 4*k)
-        img_shape (tuple[int]): (height, width) of the image.
-
-    Returns:
-        ndarray: Clipped bboxes.
-    """
-    assert bboxes.shape[-1] % 4 == 0
-    cmin = np.empty(bboxes.shape[-1], dtype=bboxes.dtype)
-    cmin[0::2] = img_shape[1] - 1
-    cmin[1::2] = img_shape[0] - 1
-    clipped_bboxes = np.maximum(np.minimum(bboxes, cmin), 0)
-    return clipped_bboxes
-
-
-def bbox_scaling(bboxes, scale, clip_shape=None):
-    """Scaling bboxes w.r.t the box center.
-
-    Args:
-        bboxes (ndarray): Shape(..., 4).
-        scale (float): Scaling factor.
-        clip_shape (tuple[int], optional): If specified, bboxes that exceed the
-            boundary will be clipped according to the given shape (h, w).
-
-    Returns:
-        ndarray: Scaled bboxes.
-    """
-    if float(scale) == 1.0:
-        scaled_bboxes = bboxes.copy()
-    else:
-        w = bboxes[..., 2] - bboxes[..., 0] + 1
-        h = bboxes[..., 3] - bboxes[..., 1] + 1
-        dw = (w * (scale - 1)) * 0.5
-        dh = (h * (scale - 1)) * 0.5
-        scaled_bboxes = bboxes + np.stack((-dw, -dh, dw, dh), axis=-1)
-    if clip_shape is not None:
-        return bbox_clip(scaled_bboxes, clip_shape)
-    else:
-        return scaled_bboxes
-
-
-def imcrop(img, bboxes, scale=1.0, pad_fill=None):
-    """Crop image patches.
-
-    3 steps: scale the bboxes -> clip bboxes -> crop and pad.
-
-    Args:
-        img (ndarray): Image to be cropped.
-        bboxes (ndarray): Shape (k, 4) or (4, ), location of cropped bboxes.
-        scale (float, optional): Scale ratio of bboxes, the default value
-            1.0 means no padding.
-        pad_fill (Number | list[Number]): Value to be filled for padding.
-            Default: None, which means no padding.
-
-    Returns:
-        list[ndarray] | ndarray: The cropped image patches.
-    """
-    chn = 1 if img.ndim == 2 else img.shape[2]
-    if pad_fill is not None:
-        if isinstance(pad_fill, (int, float)):
-            pad_fill = [pad_fill for _ in range(chn)]
-        assert len(pad_fill) == chn
-
-    _bboxes = bboxes[None, ...] if bboxes.ndim == 1 else bboxes
-    scaled_bboxes = bbox_scaling(_bboxes, scale).astype(np.int32)
-    clipped_bbox = bbox_clip(scaled_bboxes, img.shape)
-
-    patches = []
-    for i in range(clipped_bbox.shape[0]):
-        x1, y1, x2, y2 = tuple(clipped_bbox[i, :])
-        if pad_fill is None:
-            patch = img[y1:y2 + 1, x1:x2 + 1, ...]
-        else:
-            _x1, _y1, _x2, _y2 = tuple(scaled_bboxes[i, :])
-            if chn == 1:
-                patch_shape = (_y2 - _y1 + 1, _x2 - _x1 + 1)
-            else:
-                patch_shape = (_y2 - _y1 + 1, _x2 - _x1 + 1, chn)
-            patch = np.array(
-                pad_fill, dtype=img.dtype) * np.ones(
-                    patch_shape, dtype=img.dtype)
-            x_start = 0 if _x1 >= 0 else -_x1
-            y_start = 0 if _y1 >= 0 else -_y1
-            w = x2 - x1 + 1
-            h = y2 - y1 + 1
-            patch[y_start:y_start + h, x_start:x_start + w,
-                  ...] = img[y1:y1 + h, x1:x1 + w, ...]
-        patches.append(patch)
-
-    if bboxes.ndim == 1:
-        return patches[0]
-    else:
-        return patches
-
-
-def impad(img,
-          *,
-          shape=None,
-          padding=None,
-          pad_val=0,
-          padding_mode='constant'):
-    """Pad the given image to a certain shape or pad on all sides with
-    specified padding mode and padding value.
-
-    Args:
-        img (ndarray): Image to be padded.
-        shape (tuple[int]): Expected padding shape (h, w). Default: None.
-        padding (int or tuple[int]): Padding on each border. If a single int is
-            provided this is used to pad all borders. If tuple of length 2 is
-            provided this is the padding on left/right and top/bottom
-            respectively. If a tuple of length 4 is provided this is the
-            padding for the left, top, right and bottom borders respectively.
-            Default: None. Note that `shape` and `padding` can not be both
-            set.
-        pad_val (Number | Sequence[Number]): Values to be filled in padding
-            areas when padding_mode is 'constant'. Default: 0.
-        padding_mode (str): Type of padding. Should be: constant, edge,
-            reflect or symmetric. Default: constant.
-
-            - constant: pads with a constant value, this value is specified
-                with pad_val.
-            - edge: pads with the last value at the edge of the image.
-            - reflect: pads with reflection of image without repeating the
-                last value on the edge. For example, padding [1, 2, 3, 4]
-                with 2 elements on both sides in reflect mode will result
-                in [3, 2, 1, 2, 3, 4, 3, 2].
-            - symmetric: pads with reflection of image repeating the last
-                value on the edge. For example, padding [1, 2, 3, 4] with
-                2 elements on both sides in symmetric mode will result in
-                [2, 1, 1, 2, 3, 4, 4, 3]
-
-    Returns:
-        ndarray: The padded image.
-    """
-
-    assert (shape is not None) ^ (padding is not None)
-    if shape is not None:
-        padding = (0, 0, shape[1] - img.shape[1], shape[0] - img.shape[0])
-
-    # check pad_val
-    if isinstance(pad_val, tuple):
-        assert len(pad_val) == img.shape[-1]
-    elif not isinstance(pad_val, numbers.Number):
-        raise TypeError('pad_val must be a int or a tuple. '
-                        f'But received {type(pad_val)}')
-
-    # check padding
-    if isinstance(padding, tuple) and len(padding) in [2, 4]:
-        if len(padding) == 2:
-            padding = (padding[0], padding[1], padding[0], padding[1])
-    elif isinstance(padding, numbers.Number):
-        padding = (padding, padding, padding, padding)
-    else:
-        raise ValueError('Padding must be a int or a 2, or 4 element tuple.'
-                         f'But received {padding}')
-
-    # check padding mode
-    assert padding_mode in ['constant', 'edge', 'reflect', 'symmetric']
-
-    border_type = {
-        'constant': cv2.BORDER_CONSTANT,
-        'edge': cv2.BORDER_REPLICATE,
-        'reflect': cv2.BORDER_REFLECT_101,
-        'symmetric': cv2.BORDER_REFLECT
-    }
-    img = cv2.copyMakeBorder(
-        img,
-        padding[1],
-        padding[3],
-        padding[0],
-        padding[2],
-        border_type[padding_mode],
-        value=pad_val)
-
-    return img
-
-
-def impad_to_multiple(img, divisor, pad_val=0):
-    """Pad an image to ensure each edge to be multiple to some number.
-
-    Args:
-        img (ndarray): Image to be padded.
-        divisor (int): Padded image edges will be multiple to divisor.
-        pad_val (Number | Sequence[Number]): Same as :func:`impad`.
-
-    Returns:
-        ndarray: The padded image.
-    """
-    pad_h = int(np.ceil(img.shape[0] / divisor)) * divisor
-    pad_w = int(np.ceil(img.shape[1] / divisor)) * divisor
-    return impad(img, shape=(pad_h, pad_w), pad_val=pad_val)
-
-
-def cutout(img, shape, pad_val=0):
-    """Randomly cut out a rectangle from the original img.
-
-    Args:
-        img (ndarray): Image to be cutout.
-        shape (int | tuple[int]): Expected cutout shape (h, w). If given as a
-            int, the value will be used for both h and w.
-        pad_val (int | float | tuple[int | float]): Values to be filled in the
-            cut area. Defaults to 0.
-
-    Returns:
-        ndarray: The cutout image.
-    """
-
-    channels = 1 if img.ndim == 2 else img.shape[2]
-    if isinstance(shape, int):
-        cut_h, cut_w = shape, shape
-    else:
-        assert isinstance(shape, tuple) and len(shape) == 2, \
-            f'shape must be a int or a tuple with length 2, but got type ' \
-            f'{type(shape)} instead.'
-        cut_h, cut_w = shape
-    if isinstance(pad_val, (int, float)):
-        pad_val = tuple([pad_val] * channels)
-    elif isinstance(pad_val, tuple):
-        assert len(pad_val) == channels, \
-            'Expected the num of elements in tuple equals the channels' \
-            'of input image. Found {} vs {}'.format(
-                len(pad_val), channels)
-    else:
-        raise TypeError(f'Invalid type {type(pad_val)} for `pad_val`')
-
-    img_h, img_w = img.shape[:2]
-    y0 = np.random.uniform(img_h)
-    x0 = np.random.uniform(img_w)
-
-    y1 = int(max(0, y0 - cut_h / 2.))
-    x1 = int(max(0, x0 - cut_w / 2.))
-    y2 = min(img_h, y1 + cut_h)
-    x2 = min(img_w, x1 + cut_w)
-
-    if img.ndim == 2:
-        patch_shape = (y2 - y1, x2 - x1)
-    else:
-        patch_shape = (y2 - y1, x2 - x1, channels)
-
-    img_cutout = img.copy()
-    patch = np.array(
-        pad_val, dtype=img.dtype) * np.ones(
-            patch_shape, dtype=img.dtype)
-    img_cutout[y1:y2, x1:x2, ...] = patch
-
-    return img_cutout
-
-
-def _get_shear_matrix(magnitude, direction='horizontal'):
-    """Generate the shear matrix for transformation.
-
-    Args:
-        magnitude (int | float): The magnitude used for shear.
-        direction (str): The flip direction, either "horizontal"
-            or "vertical".
-
-    Returns:
-        ndarray: The shear matrix with dtype float32.
-    """
-    if direction == 'horizontal':
-        shear_matrix = np.float32([[1, magnitude, 0], [0, 1, 0]])
-    elif direction == 'vertical':
-        shear_matrix = np.float32([[1, 0, 0], [magnitude, 1, 0]])
-    return shear_matrix
-
-
-def imshear(img,
-            magnitude,
-            direction='horizontal',
-            border_value=0,
-            interpolation='bilinear'):
-    """Shear an image.
-
-    Args:
-        img (ndarray): Image to be sheared with format (h, w)
-            or (h, w, c).
-        magnitude (int | float): The magnitude used for shear.
-        direction (str): The flip direction, either "horizontal"
-            or "vertical".
-        border_value (int | tuple[int]): Value used in case of a
-            constant border.
-        interpolation (str): Same as :func:`resize`.
-
-    Returns:
-        ndarray: The sheared image.
-    """
-    assert direction in ['horizontal',
-                         'vertical'], f'Invalid direction: {direction}'
-    height, width = img.shape[:2]
-    if img.ndim == 2:
-        channels = 1
-    elif img.ndim == 3:
-        channels = img.shape[-1]
-    if isinstance(border_value, int):
-        border_value = tuple([border_value] * channels)
-    elif isinstance(border_value, tuple):
-        assert len(border_value) == channels, \
-            'Expected the num of elements in tuple equals the channels' \
-            'of input image. Found {} vs {}'.format(
-                len(border_value), channels)
-    else:
-        raise ValueError(
-            f'Invalid type {type(border_value)} for `border_value`')
-    shear_matrix = _get_shear_matrix(magnitude, direction)
-    sheared = cv2.warpAffine(
-        img,
-        shear_matrix,
-        (width, height),
-        # Note case when the number elements in `border_value`
-        # greater than 3 (e.g. shearing masks whose channels large
-        # than 3) will raise TypeError in `cv2.warpAffine`.
-        # Here simply slice the first 3 values in `border_value`.
-        borderValue=border_value[:3],
-        flags=cv2_interp_codes[interpolation])
-    return sheared
-
-
-def _get_translate_matrix(offset, direction='horizontal'):
-    """Generate the translate matrix.
-
-    Args:
-        offset (int | float): The offset used for translate.
-        direction (str): The translate direction, either
-            "horizontal" or "vertical".
-
-    Returns:
-        ndarray: The translate matrix with dtype float32.
-    """
-    if direction == 'horizontal':
-        translate_matrix = np.float32([[1, 0, offset], [0, 1, 0]])
-    elif direction == 'vertical':
-        translate_matrix = np.float32([[1, 0, 0], [0, 1, offset]])
-    return translate_matrix
-
-
-def imtranslate(img,
-                offset,
-                direction='horizontal',
-                border_value=0,
-                interpolation='bilinear'):
-    """Translate an image.
-
-    Args:
-        img (ndarray): Image to be translated with format
-            (h, w) or (h, w, c).
-        offset (int | float): The offset used for translate.
-        direction (str): The translate direction, either "horizontal"
-            or "vertical".
-        border_value (int | tuple[int]): Value used in case of a
-            constant border.
-        interpolation (str): Same as :func:`resize`.
-
-    Returns:
-        ndarray: The translated image.
-    """
-    assert direction in ['horizontal',
-                         'vertical'], f'Invalid direction: {direction}'
-    height, width = img.shape[:2]
-    if img.ndim == 2:
-        channels = 1
-    elif img.ndim == 3:
-        channels = img.shape[-1]
-    if isinstance(border_value, int):
-        border_value = tuple([border_value] * channels)
-    elif isinstance(border_value, tuple):
-        assert len(border_value) == channels, \
-            'Expected the num of elements in tuple equals the channels' \
-            'of input image. Found {} vs {}'.format(
-                len(border_value), channels)
-    else:
-        raise ValueError(
-            f'Invalid type {type(border_value)} for `border_value`.')
-    translate_matrix = _get_translate_matrix(offset, direction)
-    translated = cv2.warpAffine(
-        img,
-        translate_matrix,
-        (width, height),
-        # Note case when the number elements in `border_value`
-        # greater than 3 (e.g. translating masks whose channels
-        # large than 3) will raise TypeError in `cv2.warpAffine`.
-        # Here simply slice the first 3 values in `border_value`.
-        borderValue=border_value[:3],
-        flags=cv2_interp_codes[interpolation])
-    return translated
diff --git a/spaces/coreml-community/ControlNet-v1-1-Annotators-cpu/annotator/mmpkg/mmcv/ops/contour_expand.py b/spaces/coreml-community/ControlNet-v1-1-Annotators-cpu/annotator/mmpkg/mmcv/ops/contour_expand.py
deleted file mode 100644
index ea1111e1768b5f27e118bf7dbc0d9c70a7afd6d7..0000000000000000000000000000000000000000
--- a/spaces/coreml-community/ControlNet-v1-1-Annotators-cpu/annotator/mmpkg/mmcv/ops/contour_expand.py
+++ /dev/null
@@ -1,49 +0,0 @@
-# Copyright (c) OpenMMLab. All rights reserved.
-import numpy as np
-import torch
-
-from ..utils import ext_loader
-
-ext_module = ext_loader.load_ext('_ext', ['contour_expand'])
-
-
-def contour_expand(kernel_mask, internal_kernel_label, min_kernel_area,
-                   kernel_num):
-    """Expand kernel contours so that foreground pixels are assigned into
-    instances.
-
-    Arguments:
-        kernel_mask (np.array or Tensor): The instance kernel mask with
-            size hxw.
-        internal_kernel_label (np.array or Tensor): The instance internal
-            kernel label with size hxw.
-        min_kernel_area (int): The minimum kernel area.
-        kernel_num (int): The instance kernel number.
-
-    Returns:
-        label (list): The instance index map with size hxw.
-    """
-    assert isinstance(kernel_mask, (torch.Tensor, np.ndarray))
-    assert isinstance(internal_kernel_label, (torch.Tensor, np.ndarray))
-    assert isinstance(min_kernel_area, int)
-    assert isinstance(kernel_num, int)
-
-    if isinstance(kernel_mask, np.ndarray):
-        kernel_mask = torch.from_numpy(kernel_mask)
-    if isinstance(internal_kernel_label, np.ndarray):
-        internal_kernel_label = torch.from_numpy(internal_kernel_label)
-
-    if torch.__version__ == 'parrots':
-        if kernel_mask.shape[0] == 0 or internal_kernel_label.shape[0] == 0:
-            label = []
-        else:
-            label = ext_module.contour_expand(
-                kernel_mask,
-                internal_kernel_label,
-                min_kernel_area=min_kernel_area,
-                kernel_num=kernel_num)
-            label = label.tolist()
-    else:
-        label = ext_module.contour_expand(kernel_mask, internal_kernel_label,
-                                          min_kernel_area, kernel_num)
-    return label
diff --git a/spaces/coreml-community/ControlNet-v1-1-Annotators-cpu/annotator/uniformer/mmcv/ops/roi_align_rotated.py b/spaces/coreml-community/ControlNet-v1-1-Annotators-cpu/annotator/uniformer/mmcv/ops/roi_align_rotated.py
deleted file mode 100644
index 0ce4961a3555d4da8bc3e32f1f7d5ad50036587d..0000000000000000000000000000000000000000
--- a/spaces/coreml-community/ControlNet-v1-1-Annotators-cpu/annotator/uniformer/mmcv/ops/roi_align_rotated.py
+++ /dev/null
@@ -1,177 +0,0 @@
-# Copyright (c) OpenMMLab. All rights reserved.
-import torch.nn as nn
-from torch.autograd import Function
-
-from ..utils import ext_loader
-
-ext_module = ext_loader.load_ext(
-    '_ext', ['roi_align_rotated_forward', 'roi_align_rotated_backward'])
-
-
-class RoIAlignRotatedFunction(Function):
-
-    @staticmethod
-    def symbolic(g, features, rois, out_size, spatial_scale, sample_num,
-                 aligned, clockwise):
-        if isinstance(out_size, int):
-            out_h = out_size
-            out_w = out_size
-        elif isinstance(out_size, tuple):
-            assert len(out_size) == 2
-            assert isinstance(out_size[0], int)
-            assert isinstance(out_size[1], int)
-            out_h, out_w = out_size
-        else:
-            raise TypeError(
-                '"out_size" must be an integer or tuple of integers')
-        return g.op(
-            'mmcv::MMCVRoIAlignRotated',
-            features,
-            rois,
-            output_height_i=out_h,
-            output_width_i=out_h,
-            spatial_scale_f=spatial_scale,
-            sampling_ratio_i=sample_num,
-            aligned_i=aligned,
-            clockwise_i=clockwise)
-
-    @staticmethod
-    def forward(ctx,
-                features,
-                rois,
-                out_size,
-                spatial_scale,
-                sample_num=0,
-                aligned=True,
-                clockwise=False):
-        if isinstance(out_size, int):
-            out_h = out_size
-            out_w = out_size
-        elif isinstance(out_size, tuple):
-            assert len(out_size) == 2
-            assert isinstance(out_size[0], int)
-            assert isinstance(out_size[1], int)
-            out_h, out_w = out_size
-        else:
-            raise TypeError(
-                '"out_size" must be an integer or tuple of integers')
-        ctx.spatial_scale = spatial_scale
-        ctx.sample_num = sample_num
-        ctx.aligned = aligned
-        ctx.clockwise = clockwise
-        ctx.save_for_backward(rois)
-        ctx.feature_size = features.size()
-
-        batch_size, num_channels, data_height, data_width = features.size()
-        num_rois = rois.size(0)
-
-        output = features.new_zeros(num_rois, num_channels, out_h, out_w)
-        ext_module.roi_align_rotated_forward(
-            features,
-            rois,
-            output,
-            pooled_height=out_h,
-            pooled_width=out_w,
-            spatial_scale=spatial_scale,
-            sample_num=sample_num,
-            aligned=aligned,
-            clockwise=clockwise)
-        return output
-
-    @staticmethod
-    def backward(ctx, grad_output):
-        feature_size = ctx.feature_size
-        spatial_scale = ctx.spatial_scale
-        aligned = ctx.aligned
-        clockwise = ctx.clockwise
-        sample_num = ctx.sample_num
-        rois = ctx.saved_tensors[0]
-        assert feature_size is not None
-        batch_size, num_channels, data_height, data_width = feature_size
-
-        out_w = grad_output.size(3)
-        out_h = grad_output.size(2)
-
-        grad_input = grad_rois = None
-
-        if ctx.needs_input_grad[0]:
-            grad_input = rois.new_zeros(batch_size, num_channels, data_height,
-                                        data_width)
-            ext_module.roi_align_rotated_backward(
-                grad_output.contiguous(),
-                rois,
-                grad_input,
-                pooled_height=out_h,
-                pooled_width=out_w,
-                spatial_scale=spatial_scale,
-                sample_num=sample_num,
-                aligned=aligned,
-                clockwise=clockwise)
-        return grad_input, grad_rois, None, None, None, None, None
-
-
-roi_align_rotated = RoIAlignRotatedFunction.apply
-
-
-class RoIAlignRotated(nn.Module):
-    """RoI align pooling layer for rotated proposals.
-
-    It accepts a feature map of shape (N, C, H, W) and rois with shape
-    (n, 6) with each roi decoded as (batch_index, center_x, center_y,
-    w, h, angle). The angle is in radian.
-
-    Args:
-        out_size (tuple): h, w
-        spatial_scale (float): scale the input boxes by this number
-        sample_num (int): number of inputs samples to take for each
-            output sample. 0 to take samples densely for current models.
-        aligned (bool): if False, use the legacy implementation in
-            MMDetection. If True, align the results more perfectly.
-            Default: True.
-        clockwise (bool): If True, the angle in each proposal follows a
-            clockwise fashion in image space, otherwise, the angle is
-            counterclockwise. Default: False.
-
-    Note:
-        The implementation of RoIAlign when aligned=True is modified from
-        https://github.com/facebookresearch/detectron2/
-
-        The meaning of aligned=True:
-
-        Given a continuous coordinate c, its two neighboring pixel
-        indices (in our pixel model) are computed by floor(c - 0.5) and
-        ceil(c - 0.5). For example, c=1.3 has pixel neighbors with discrete
-        indices [0] and [1] (which are sampled from the underlying signal
-        at continuous coordinates 0.5 and 1.5). But the original roi_align
-        (aligned=False) does not subtract the 0.5 when computing
-        neighboring pixel indices and therefore it uses pixels with a
-        slightly incorrect alignment (relative to our pixel model) when
-        performing bilinear interpolation.
-
-        With `aligned=True`,
-        we first appropriately scale the ROI and then shift it by -0.5
-        prior to calling roi_align. This produces the correct neighbors;
-
-        The difference does not make a difference to the model's
-        performance if ROIAlign is used together with conv layers.
-    """
-
-    def __init__(self,
-                 out_size,
-                 spatial_scale,
-                 sample_num=0,
-                 aligned=True,
-                 clockwise=False):
-        super(RoIAlignRotated, self).__init__()
-
-        self.out_size = out_size
-        self.spatial_scale = float(spatial_scale)
-        self.sample_num = int(sample_num)
-        self.aligned = aligned
-        self.clockwise = clockwise
-
-    def forward(self, features, rois):
-        return RoIAlignRotatedFunction.apply(features, rois, self.out_size,
-                                             self.spatial_scale,
-                                             self.sample_num, self.aligned,
-                                             self.clockwise)
diff --git a/spaces/coreml-community/ControlNet-v1-1-Annotators-cpu/annotator/zoe/zoedepth/models/layers/localbins_layers.py b/spaces/coreml-community/ControlNet-v1-1-Annotators-cpu/annotator/zoe/zoedepth/models/layers/localbins_layers.py
deleted file mode 100644
index f94481605c3e6958ce50e73b2eb31d9f0c07dc67..0000000000000000000000000000000000000000
--- a/spaces/coreml-community/ControlNet-v1-1-Annotators-cpu/annotator/zoe/zoedepth/models/layers/localbins_layers.py
+++ /dev/null
@@ -1,169 +0,0 @@
-# MIT License
-
-# Copyright (c) 2022 Intelligent Systems Lab Org
-
-# Permission is hereby granted, free of charge, to any person obtaining a copy
-# of this software and associated documentation files (the "Software"), to deal
-# in the Software without restriction, including without limitation the rights
-# to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
-# copies of the Software, and to permit persons to whom the Software is
-# furnished to do so, subject to the following conditions:
-
-# The above copyright notice and this permission notice shall be included in all
-# copies or substantial portions of the Software.
-
-# THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
-# IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
-# FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
-# AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
-# LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
-# OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
-# SOFTWARE.
-
-# File author: Shariq Farooq Bhat
-
-import torch
-import torch.nn as nn
-
-
-class SeedBinRegressor(nn.Module):
-    def __init__(self, in_features, n_bins=16, mlp_dim=256, min_depth=1e-3, max_depth=10):
-        """Bin center regressor network. Bin centers are bounded on (min_depth, max_depth) interval.
-
-        Args:
-            in_features (int): input channels
-            n_bins (int, optional): Number of bin centers. Defaults to 16.
-            mlp_dim (int, optional): Hidden dimension. Defaults to 256.
-            min_depth (float, optional): Min depth value. Defaults to 1e-3.
-            max_depth (float, optional): Max depth value. Defaults to 10.
-        """
-        super().__init__()
-        self.version = "1_1"
-        self.min_depth = min_depth
-        self.max_depth = max_depth
-
-        self._net = nn.Sequential(
-            nn.Conv2d(in_features, mlp_dim, 1, 1, 0),
-            nn.ReLU(inplace=True),
-            nn.Conv2d(mlp_dim, n_bins, 1, 1, 0),
-            nn.ReLU(inplace=True)
-        )
-
-    def forward(self, x):
-        """
-        Returns tensor of bin_width vectors (centers). One vector b for every pixel
-        """
-        B = self._net(x)
-        eps = 1e-3
-        B = B + eps
-        B_widths_normed = B / B.sum(dim=1, keepdim=True)
-        B_widths = (self.max_depth - self.min_depth) * \
-            B_widths_normed  # .shape NCHW
-        # pad has the form (left, right, top, bottom, front, back)
-        B_widths = nn.functional.pad(
-            B_widths, (0, 0, 0, 0, 1, 0), mode='constant', value=self.min_depth)
-        B_edges = torch.cumsum(B_widths, dim=1)  # .shape NCHW
-
-        B_centers = 0.5 * (B_edges[:, :-1, ...] + B_edges[:, 1:, ...])
-        return B_widths_normed, B_centers
-
-
-class SeedBinRegressorUnnormed(nn.Module):
-    def __init__(self, in_features, n_bins=16, mlp_dim=256, min_depth=1e-3, max_depth=10):
-        """Bin center regressor network. Bin centers are unbounded
-
-        Args:
-            in_features (int): input channels
-            n_bins (int, optional): Number of bin centers. Defaults to 16.
-            mlp_dim (int, optional): Hidden dimension. Defaults to 256.
-            min_depth (float, optional): Not used. (for compatibility with SeedBinRegressor)
-            max_depth (float, optional): Not used. (for compatibility with SeedBinRegressor)
-        """
-        super().__init__()
-        self.version = "1_1"
-        self._net = nn.Sequential(
-            nn.Conv2d(in_features, mlp_dim, 1, 1, 0),
-            nn.ReLU(inplace=True),
-            nn.Conv2d(mlp_dim, n_bins, 1, 1, 0),
-            nn.Softplus()
-        )
-
-    def forward(self, x):
-        """
-        Returns tensor of bin_width vectors (centers). One vector b for every pixel
-        """
-        B_centers = self._net(x)
-        return B_centers, B_centers
-
-
-class Projector(nn.Module):
-    def __init__(self, in_features, out_features, mlp_dim=128):
-        """Projector MLP
-
-        Args:
-            in_features (int): input channels
-            out_features (int): output channels
-            mlp_dim (int, optional): hidden dimension. Defaults to 128.
-        """
-        super().__init__()
-
-        self._net = nn.Sequential(
-            nn.Conv2d(in_features, mlp_dim, 1, 1, 0),
-            nn.ReLU(inplace=True),
-            nn.Conv2d(mlp_dim, out_features, 1, 1, 0),
-        )
-
-    def forward(self, x):
-        return self._net(x)
-
-
-
-class LinearSplitter(nn.Module):
-    def __init__(self, in_features, prev_nbins, split_factor=2, mlp_dim=128, min_depth=1e-3, max_depth=10):
-        super().__init__()
-
-        self.prev_nbins = prev_nbins
-        self.split_factor = split_factor
-        self.min_depth = min_depth
-        self.max_depth = max_depth
-
-        self._net = nn.Sequential(
-            nn.Conv2d(in_features, mlp_dim, 1, 1, 0),
-            nn.GELU(),
-            nn.Conv2d(mlp_dim, prev_nbins * split_factor, 1, 1, 0),
-            nn.ReLU()
-        )
-    
-    def forward(self, x, b_prev, prev_b_embedding=None, interpolate=True, is_for_query=False):
-        """
-        x : feature block; shape - n, c, h, w
-        b_prev : previous bin widths normed; shape - n, prev_nbins, h, w
-        """
-        if prev_b_embedding is not None:
-            if interpolate:
-                prev_b_embedding = nn.functional.interpolate(prev_b_embedding, x.shape[-2:], mode='bilinear', align_corners=True)
-            x = x + prev_b_embedding
-        S = self._net(x)
-        eps = 1e-3
-        S = S + eps
-        n, c, h, w = S.shape
-        S = S.view(n, self.prev_nbins, self.split_factor, h, w)
-        S_normed = S / S.sum(dim=2, keepdim=True)  # fractional splits
-
-        b_prev = nn.functional.interpolate(b_prev, (h,w), mode='bilinear', align_corners=True)
-        
-
-        b_prev = b_prev / b_prev.sum(dim=1, keepdim=True)  # renormalize for gurantees
-        # print(b_prev.shape, S_normed.shape)
-        # if is_for_query:(1).expand(-1, b_prev.size(0)//n, -1, -1, -1, -1).flatten(0,1)  # TODO ? can replace all this with a single torch.repeat?
-        b = b_prev.unsqueeze(2) * S_normed
-        b = b.flatten(1,2)  # .shape n, prev_nbins * split_factor, h, w
-
-        # calculate bin centers for loss calculation
-        B_widths = (self.max_depth - self.min_depth) * b  # .shape N, nprev * splitfactor, H, W
-        # pad has the form (left, right, top, bottom, front, back)
-        B_widths = nn.functional.pad(B_widths, (0,0,0,0,1,0), mode='constant', value=self.min_depth)
-        B_edges = torch.cumsum(B_widths, dim=1)  # .shape NCHW
-
-        B_centers = 0.5 * (B_edges[:, :-1, ...] + B_edges[:,1:,...])
-        return b, B_centers
\ No newline at end of file
diff --git a/spaces/csuhan/opendet2/opendet2/modeling/losses/instance_contrastive_loss.py b/spaces/csuhan/opendet2/opendet2/modeling/losses/instance_contrastive_loss.py
deleted file mode 100644
index bad5320c256289a8b38acf957d58ed962988ad71..0000000000000000000000000000000000000000
--- a/spaces/csuhan/opendet2/opendet2/modeling/losses/instance_contrastive_loss.py
+++ /dev/null
@@ -1,40 +0,0 @@
-import torch
-import torch.nn as nn
-import torch.nn.functional as F
-
-
-class ICLoss(nn.Module):
-    """ Instance Contrastive Loss
-    """
-    def __init__(self, tau=0.1):
-        super().__init__()
-        self.tau = tau
-
-    def forward(self, features, labels, queue_features, queue_labels):
-        device = features.device
-        mask = torch.eq(labels[:, None], queue_labels[:, None].T).float().to(device)
-
-        # compute logits
-        anchor_dot_contrast = torch.div(
-            torch.matmul(features, queue_features.T), self.tau)
-
-        # for numerical stability
-        logits_max, _ = torch.max(anchor_dot_contrast, dim=1, keepdim=True)
-        logits = anchor_dot_contrast - logits_max.detach()
-
-        logits_mask = torch.ones_like(logits)
-        # mask itself
-        logits_mask[logits == 0] = 0
-
-        mask = mask * logits_mask
-
-        # compute log_prob
-        exp_logits = torch.exp(logits) * logits_mask
-        log_prob = logits - torch.log(exp_logits.sum(1, keepdim=True))
-
-        # compute mean of log-likelihood over positive
-        mean_log_prob_pos = (mask * log_prob).sum(1) / mask.sum(1)
-        # loss
-        loss = - mean_log_prob_pos.mean()
-        # trick: avoid loss nan
-        return loss if not torch.isnan(loss) else features.new_tensor(0.0)
diff --git a/spaces/damian0815/Erasing-Concepts-In-Diffusion/StableDiffuser.py b/spaces/damian0815/Erasing-Concepts-In-Diffusion/StableDiffuser.py
deleted file mode 100644
index 476b673392825ff9f2faf7d742a82e93b87e7bc8..0000000000000000000000000000000000000000
--- a/spaces/damian0815/Erasing-Concepts-In-Diffusion/StableDiffuser.py
+++ /dev/null
@@ -1,265 +0,0 @@
-import argparse
-
-import torch
-from baukit import TraceDict
-from diffusers import StableDiffusionPipeline
-from PIL import Image
-from torch.cuda.amp import autocast
-from tqdm.auto import tqdm
-from diffusers.schedulers.scheduling_ddim import DDIMScheduler
-from diffusers.schedulers.scheduling_ddpm import DDPMScheduler
-from diffusers.schedulers.scheduling_lms_discrete import LMSDiscreteScheduler
-import util
-
-
-def default_parser():
-
-    parser = argparse.ArgumentParser()
-
-    parser.add_argument('prompts', type=str, nargs='+')
-    parser.add_argument('outpath', type=str)
-
-    parser.add_argument('--images', type=str, nargs='+', default=None)
-    parser.add_argument('--nsteps', type=int, default=1000)
-    parser.add_argument('--nimgs', type=int, default=1)
-    parser.add_argument('--start_itr', type=int, default=0)
-    parser.add_argument('--return_steps', action='store_true', default=False)
-    parser.add_argument('--pred_x0', action='store_true', default=False)
-    parser.add_argument('--device', type=str, default='cuda:0')
-    parser.add_argument('--seed', type=int, default=42)
-
-    return parser
-
-
-class StableDiffuser(torch.nn.Module):
-
-    def __init__(self,
-                scheduler='LMS',
-                 keep_pipeline=False,
-                 native_img_size=512,
-                 repo_id_or_path="CompVis/stable-diffusion-v1-4"):
-
-        super().__init__()
-
-        self.pipeline = StableDiffusionPipeline.from_pretrained(repo_id_or_path)
-        self.native_image_size = native_img_size
-
-        self.vae = self.pipeline.vae
-        self.unet = self.pipeline.unet
-        self.tokenizer = self.pipeline.tokenizer
-        self.text_encoder = self.pipeline.text_encoder
-        self.safety_checker = self.pipeline.safety_checker
-        self.feature_extractor = self.pipeline.feature_extractor
-
-        if scheduler == 'LMS':
-            self.scheduler = LMSDiscreteScheduler(beta_start=0.00085, beta_end=0.012, beta_schedule="scaled_linear", num_train_timesteps=1000)
-        elif scheduler == 'DDIM':
-            self.scheduler = DDIMScheduler.from_pretrained(repo_id_or_path, subfolder="scheduler")
-        elif scheduler == 'DDPM':
-            self.scheduler = DDPMScheduler.from_pretrained(repo_id_or_path, subfolder="scheduler")
-
-        self.eval()
-        if not keep_pipeline:
-            del self.pipeline
-
-    def get_noise(self, batch_size, width=None, height=None, generator=None):
-        param = list(self.parameters())[0]
-        width = width or self.native_image_size
-        height = height or self.native_image_size
-        return torch.randn(
-            (batch_size, self.unet.config.in_channels, width // 8, height // 8),
-            generator=generator).type(param.dtype).to(param.device)
-
-    def add_noise(self, latents, noise, step):
-        return self.scheduler.add_noise(latents, noise, torch.tensor([self.scheduler.timesteps[step]]))
-
-    def text_tokenize(self, prompts):
-        return self.tokenizer(prompts, padding="max_length", max_length=self.tokenizer.model_max_length, truncation=True, return_tensors="pt")
-
-    def text_detokenize(self, tokens):
-        return [self.tokenizer.decode(token) for token in tokens if token != self.tokenizer.vocab_size - 1]
-
-    def text_encode(self, tokens):
-        return self.text_encoder(tokens.input_ids.to(self.unet.device))[0]
-
-    def decode(self, latents):
-        return self.vae.decode(1 / self.vae.config.scaling_factor * latents).sample
-
-    def encode(self, tensors):
-        return self.vae.encode(tensors).latent_dist.mode() * 0.18215
-
-    def to_image(self, image):
-        image = (image / 2 + 0.5).clamp(0, 1)
-        image = image.detach().cpu().permute(0, 2, 3, 1).numpy()
-        images = (image * 255).round().astype("uint8")
-        pil_images = [Image.fromarray(image) for image in images]
-
-        return pil_images
-
-    def set_scheduler_timesteps(self, n_steps):
-        self.scheduler.set_timesteps(n_steps, device=self.unet.device)
-
-    def get_initial_latents(self, n_imgs, height=None, width=None, n_prompts=1, generator=None):
-        height = height or self.native_image_size
-        width = width or self.native_image_size
-        noise = self.get_noise(n_imgs, height, width, generator=generator).repeat(n_prompts, 1, 1, 1)
-        latents = noise * self.scheduler.init_noise_sigma
-        return latents
-
-    def get_cond_and_uncond_embeddings(self, prompts, negative_prompts=None, n_imgs=1):
-        assert n_imgs == 1
-        text_tokens = self.text_tokenize(prompts)
-        text_embeddings = self.text_encode(text_tokens)
-        if negative_prompts is None:
-            negative_prompts = []
-        while len(negative_prompts) < len(prompts):
-            negative_prompts.append("")
-        unconditional_tokens = self.text_tokenize(negative_prompts)
-        unconditional_embeddings = self.text_encode(unconditional_tokens)
-        combined_embeddings = [torch.cat([unconditional_embeddings[i:i+1], text_embeddings[i:i+1]]) for i in range(len(prompts))]
-        combined_embeddings = torch.cat(combined_embeddings)
-        return combined_embeddings
-
-    def predict_noise(self,
-             iteration,
-             latents,
-             text_embeddings,
-             guidance_scale=7.5
-             ):
-
-        # expand the latents if we are doing classifier-free guidance to avoid doing two forward passes.
-        latents = torch.cat([latents] * 2)
-        latents = self.scheduler.scale_model_input(
-            latents, self.scheduler.timesteps[iteration])
-
-        # predict the noise residual
-        noise_prediction = self.unet(
-            latents, self.scheduler.timesteps[iteration], encoder_hidden_states=text_embeddings).sample
-
-        # perform guidance
-        noise_prediction_uncond, noise_prediction_text = noise_prediction.chunk(2)
-        noise_prediction = noise_prediction_uncond + guidance_scale * \
-            (noise_prediction_text - noise_prediction_uncond)
-
-        return noise_prediction
-
-    @torch.no_grad()
-    def diffusion(self,
-                  latents,
-                  uncond_and_cond_embeddings,
-                  end_iteration=1000,
-                  start_iteration=0,
-                  return_steps=False,
-                  pred_x0=False,
-                  trace_args=None,
-                  show_progress=True,
-                  use_amp=False,
-                  **kwargs):
-
-        latents_steps = []
-        trace_steps = []
-
-        trace = None
-
-        for iteration in tqdm(range(start_iteration, end_iteration), disable=not show_progress):
-            if trace_args:
-                trace = TraceDict(self, **trace_args)
-
-            with autocast(enabled=use_amp):
-                noise_pred = self.predict_noise(
-                    iteration,
-                    latents,
-                    uncond_and_cond_embeddings,
-                    **kwargs)
-
-            # compute the previous noisy sample x_t -> x_t-1
-            output = self.scheduler.step(noise_pred, self.scheduler.timesteps[iteration], latents)
-
-            if trace_args:
-                trace.close()
-                trace_steps.append(trace)
-
-            latents = output.prev_sample
-
-            if return_steps or iteration == end_iteration - 1:
-                output = output.pred_original_sample if pred_x0 else latents
-                if return_steps:
-                    latents_steps.append(output.cpu())
-                else:
-                    latents_steps.append(output)
-
-        return latents_steps, trace_steps
-
-    @torch.no_grad()
-    def __call__(self,
-                 prompts=None,
-                 negative_prompts=None,
-                 combined_embeddings=None, # uncond first, then cond
-                 width=None,
-                 height=None,
-                 n_steps=50,
-                 n_imgs=1,
-                 end_iteration=None,
-                 generator=None,
-                 use_amp=False,
-                 **kwargs
-                 ):
-
-        assert 0 <= n_steps <= 1000
-
-        if combined_embeddings is None:
-            assert prompts is not None, "missing prompts or combined_embeddings"
-            combined_embeddings = self.get_cond_and_uncond_embeddings(prompts, negative_prompts, n_imgs=n_imgs)
-
-        width = width or self.native_image_size
-        height = height or self.native_image_size
-        num_prompts = combined_embeddings.shape[0] // 2
-
-        self.set_scheduler_timesteps(n_steps)
-        latents = self.get_initial_latents(n_imgs, height, width, num_prompts, generator=generator)
-
-        end_iteration = end_iteration or n_steps
-        latents_steps, trace_steps = self.diffusion(
-            latents,
-            combined_embeddings,
-            end_iteration=end_iteration,
-            use_amp=use_amp,
-            **kwargs
-        )
-
-        latents_steps = [self.decode(latents.to(self.unet.device)) for latents in latents_steps]
-        images_steps = [self.to_image(latents) for latents in latents_steps]
-
-        if self.safety_checker is not None:
-            for i in range(len(images_steps)):
-                self.safety_checker = self.safety_checker.float()
-                safety_checker_input = self.feature_extractor(images_steps[i], return_tensors="pt").to(latents_steps[0].device)
-                image, has_nsfw_concept = self.safety_checker(
-                    images=latents_steps[i], clip_input=safety_checker_input.pixel_values.float()
-                )
-                images_steps[i][0] = self.to_image(image)[0]
-
-        images_steps = list(zip(*images_steps))
-
-        if trace_steps:
-            return images_steps, trace_steps
-
-        return images_steps
-
-
-if __name__ == '__main__':
-
-    parser = default_parser()
-    args = parser.parse_args()
-
-    diffuser = StableDiffuser(scheduler='DDIM').to(torch.device(args.device)).half()
-
-    images = diffuser(args.prompts,
-                      n_steps=args.nsteps,
-                      n_imgs=args.nimgs,
-                      start_iteration=args.start_itr,
-                      return_steps=args.return_steps,
-                      pred_x0=args.pred_x0
-                      )
-
-    util.image_grid(images, args.outpath)
\ No newline at end of file
diff --git a/spaces/dandan4272/hand_gesture_rec/util/SHREC_parse_data.py b/spaces/dandan4272/hand_gesture_rec/util/SHREC_parse_data.py
deleted file mode 100644
index 1a94f8e47de83356de59258a68cdc430c337fb85..0000000000000000000000000000000000000000
--- a/spaces/dandan4272/hand_gesture_rec/util/SHREC_parse_data.py
+++ /dev/null
@@ -1,59 +0,0 @@
-import numpy as np
-min_seq = 8
-
-#Change the path to your downloaded SHREC2017 dataset
-dataset_fold = "/gpu2/yc984/hand/dataset/SHREC17/HandGestureDataset_SHREC2017"
-
-def split_train_test(data_cfg):
-    def parse_file(data_file,data_cfg):
-        #parse train / test file
-
-
-        label_list = []
-        all_data = []
-        for line in data_file:
-            data_ele = {}
-            data = line.split() #【id_gesture， id_finger， id_subject， id_essai， 14_labels， 28_labels size_sequence】
-            #video label
-            if data_cfg == 0:
-                label = int(data[4])
-            elif data_cfg == 1:
-                label = int(data[5])
-            label_list.append(label) #add label to label list
-            data_ele["label"] = label
-            #video
-            video = []
-            joint_path = dataset_fold + "/gesture_{}/finger_{}/subject_{}/essai_{}/skeletons_world.txt".format(data[0],data[1],data[2],data[3])
-            joint_file = open(joint_path)
-            for joint_line in joint_file:
-                joint_data = joint_line.split()
-                joint_data = [float(ele) for ele in joint_data]#convert to float
-                joint_data = np.array(joint_data).reshape(22,3)#[[x1,y1,z1], [x2,y2,z2],.....]
-                video.append(joint_data)
-            while len(video) < min_seq:
-                video.append(video[-1])
-            data_ele["skeleton"] = video
-            data_ele["name"] = line
-            all_data.append(data_ele)
-            joint_file.close()
-        return all_data, label_list
-
-
-
-    print("loading training data........")
-    train_path = dataset_fold + "/train_gestures.txt"
-    train_file = open(train_path)
-    train_data, train_label = parse_file(train_file,data_cfg)
-    assert len(train_data) == len(train_label)
-
-    print("training data num {}".format(len(train_data)))
-
-    print("loading testing data........")
-    test_path = dataset_fold + "/test_gestures.txt"
-    test_file = open(test_path)
-    test_data, test_label = parse_file(test_file, data_cfg)
-    assert len(test_data) == len(test_label)
-
-    print("testing data num {}".format(len(test_data)))
-
-    return train_data, test_data
\ No newline at end of file
diff --git a/spaces/dcarpintero/nlp-summarizer-pegasus/.venv/lib/python3.9/site-packages/aiohttp/payload.py b/spaces/dcarpintero/nlp-summarizer-pegasus/.venv/lib/python3.9/site-packages/aiohttp/payload.py
deleted file mode 100644
index a2340e2945edcc21de4cf99479670a3361180816..0000000000000000000000000000000000000000
--- a/spaces/dcarpintero/nlp-summarizer-pegasus/.venv/lib/python3.9/site-packages/aiohttp/payload.py
+++ /dev/null
@@ -1,465 +0,0 @@
-import asyncio
-import enum
-import io
-import json
-import mimetypes
-import os
-import warnings
-from abc import ABC, abstractmethod
-from itertools import chain
-from typing import (
-    IO,
-    TYPE_CHECKING,
-    Any,
-    ByteString,
-    Dict,
-    Iterable,
-    Optional,
-    TextIO,
-    Tuple,
-    Type,
-    Union,
-)
-
-from multidict import CIMultiDict
-
-from . import hdrs
-from .abc import AbstractStreamWriter
-from .helpers import (
-    PY_36,
-    content_disposition_header,
-    guess_filename,
-    parse_mimetype,
-    sentinel,
-)
-from .streams import StreamReader
-from .typedefs import Final, JSONEncoder, _CIMultiDict
-
-__all__ = (
-    "PAYLOAD_REGISTRY",
-    "get_payload",
-    "payload_type",
-    "Payload",
-    "BytesPayload",
-    "StringPayload",
-    "IOBasePayload",
-    "BytesIOPayload",
-    "BufferedReaderPayload",
-    "TextIOPayload",
-    "StringIOPayload",
-    "JsonPayload",
-    "AsyncIterablePayload",
-)
-
-TOO_LARGE_BYTES_BODY: Final[int] = 2**20  # 1 MB
-
-if TYPE_CHECKING:  # pragma: no cover
-    from typing import List
-
-
-class LookupError(Exception):
-    pass
-
-
-class Order(str, enum.Enum):
-    normal = "normal"
-    try_first = "try_first"
-    try_last = "try_last"
-
-
-def get_payload(data: Any, *args: Any, **kwargs: Any) -> "Payload":
-    return PAYLOAD_REGISTRY.get(data, *args, **kwargs)
-
-
-def register_payload(
-    factory: Type["Payload"], type: Any, *, order: Order = Order.normal
-) -> None:
-    PAYLOAD_REGISTRY.register(factory, type, order=order)
-
-
-class payload_type:
-    def __init__(self, type: Any, *, order: Order = Order.normal) -> None:
-        self.type = type
-        self.order = order
-
-    def __call__(self, factory: Type["Payload"]) -> Type["Payload"]:
-        register_payload(factory, self.type, order=self.order)
-        return factory
-
-
-PayloadType = Type["Payload"]
-_PayloadRegistryItem = Tuple[PayloadType, Any]
-
-
-class PayloadRegistry:
-    """Payload registry.
-
-    note: we need zope.interface for more efficient adapter search
-    """
-
-    def __init__(self) -> None:
-        self._first: List[_PayloadRegistryItem] = []
-        self._normal: List[_PayloadRegistryItem] = []
-        self._last: List[_PayloadRegistryItem] = []
-
-    def get(
-        self,
-        data: Any,
-        *args: Any,
-        _CHAIN: "Type[chain[_PayloadRegistryItem]]" = chain,
-        **kwargs: Any,
-    ) -> "Payload":
-        if isinstance(data, Payload):
-            return data
-        for factory, type in _CHAIN(self._first, self._normal, self._last):
-            if isinstance(data, type):
-                return factory(data, *args, **kwargs)
-
-        raise LookupError()
-
-    def register(
-        self, factory: PayloadType, type: Any, *, order: Order = Order.normal
-    ) -> None:
-        if order is Order.try_first:
-            self._first.append((factory, type))
-        elif order is Order.normal:
-            self._normal.append((factory, type))
-        elif order is Order.try_last:
-            self._last.append((factory, type))
-        else:
-            raise ValueError(f"Unsupported order {order!r}")
-
-
-class Payload(ABC):
-
-    _default_content_type: str = "application/octet-stream"
-    _size: Optional[int] = None
-
-    def __init__(
-        self,
-        value: Any,
-        headers: Optional[
-            Union[_CIMultiDict, Dict[str, str], Iterable[Tuple[str, str]]]
-        ] = None,
-        content_type: Optional[str] = sentinel,
-        filename: Optional[str] = None,
-        encoding: Optional[str] = None,
-        **kwargs: Any,
-    ) -> None:
-        self._encoding = encoding
-        self._filename = filename
-        self._headers: _CIMultiDict = CIMultiDict()
-        self._value = value
-        if content_type is not sentinel and content_type is not None:
-            self._headers[hdrs.CONTENT_TYPE] = content_type
-        elif self._filename is not None:
-            content_type = mimetypes.guess_type(self._filename)[0]
-            if content_type is None:
-                content_type = self._default_content_type
-            self._headers[hdrs.CONTENT_TYPE] = content_type
-        else:
-            self._headers[hdrs.CONTENT_TYPE] = self._default_content_type
-        self._headers.update(headers or {})
-
-    @property
-    def size(self) -> Optional[int]:
-        """Size of the payload."""
-        return self._size
-
-    @property
-    def filename(self) -> Optional[str]:
-        """Filename of the payload."""
-        return self._filename
-
-    @property
-    def headers(self) -> _CIMultiDict:
-        """Custom item headers"""
-        return self._headers
-
-    @property
-    def _binary_headers(self) -> bytes:
-        return (
-            "".join([k + ": " + v + "\r\n" for k, v in self.headers.items()]).encode(
-                "utf-8"
-            )
-            + b"\r\n"
-        )
-
-    @property
-    def encoding(self) -> Optional[str]:
-        """Payload encoding"""
-        return self._encoding
-
-    @property
-    def content_type(self) -> str:
-        """Content type"""
-        return self._headers[hdrs.CONTENT_TYPE]
-
-    def set_content_disposition(
-        self,
-        disptype: str,
-        quote_fields: bool = True,
-        _charset: str = "utf-8",
-        **params: Any,
-    ) -> None:
-        """Sets ``Content-Disposition`` header."""
-        self._headers[hdrs.CONTENT_DISPOSITION] = content_disposition_header(
-            disptype, quote_fields=quote_fields, _charset=_charset, **params
-        )
-
-    @abstractmethod
-    async def write(self, writer: AbstractStreamWriter) -> None:
-        """Write payload.
-
-        writer is an AbstractStreamWriter instance:
-        """
-
-
-class BytesPayload(Payload):
-    def __init__(self, value: ByteString, *args: Any, **kwargs: Any) -> None:
-        if not isinstance(value, (bytes, bytearray, memoryview)):
-            raise TypeError(f"value argument must be byte-ish, not {type(value)!r}")
-
-        if "content_type" not in kwargs:
-            kwargs["content_type"] = "application/octet-stream"
-
-        super().__init__(value, *args, **kwargs)
-
-        if isinstance(value, memoryview):
-            self._size = value.nbytes
-        else:
-            self._size = len(value)
-
-        if self._size > TOO_LARGE_BYTES_BODY:
-            if PY_36:
-                kwargs = {"source": self}
-            else:
-                kwargs = {}
-            warnings.warn(
-                "Sending a large body directly with raw bytes might"
-                " lock the event loop. You should probably pass an "
-                "io.BytesIO object instead",
-                ResourceWarning,
-                **kwargs,
-            )
-
-    async def write(self, writer: AbstractStreamWriter) -> None:
-        await writer.write(self._value)
-
-
-class StringPayload(BytesPayload):
-    def __init__(
-        self,
-        value: str,
-        *args: Any,
-        encoding: Optional[str] = None,
-        content_type: Optional[str] = None,
-        **kwargs: Any,
-    ) -> None:
-
-        if encoding is None:
-            if content_type is None:
-                real_encoding = "utf-8"
-                content_type = "text/plain; charset=utf-8"
-            else:
-                mimetype = parse_mimetype(content_type)
-                real_encoding = mimetype.parameters.get("charset", "utf-8")
-        else:
-            if content_type is None:
-                content_type = "text/plain; charset=%s" % encoding
-            real_encoding = encoding
-
-        super().__init__(
-            value.encode(real_encoding),
-            encoding=real_encoding,
-            content_type=content_type,
-            *args,
-            **kwargs,
-        )
-
-
-class StringIOPayload(StringPayload):
-    def __init__(self, value: IO[str], *args: Any, **kwargs: Any) -> None:
-        super().__init__(value.read(), *args, **kwargs)
-
-
-class IOBasePayload(Payload):
-    _value: IO[Any]
-
-    def __init__(
-        self, value: IO[Any], disposition: str = "attachment", *args: Any, **kwargs: Any
-    ) -> None:
-        if "filename" not in kwargs:
-            kwargs["filename"] = guess_filename(value)
-
-        super().__init__(value, *args, **kwargs)
-
-        if self._filename is not None and disposition is not None:
-            if hdrs.CONTENT_DISPOSITION not in self.headers:
-                self.set_content_disposition(disposition, filename=self._filename)
-
-    async def write(self, writer: AbstractStreamWriter) -> None:
-        loop = asyncio.get_event_loop()
-        try:
-            chunk = await loop.run_in_executor(None, self._value.read, 2**16)
-            while chunk:
-                await writer.write(chunk)
-                chunk = await loop.run_in_executor(None, self._value.read, 2**16)
-        finally:
-            await loop.run_in_executor(None, self._value.close)
-
-
-class TextIOPayload(IOBasePayload):
-    _value: TextIO
-
-    def __init__(
-        self,
-        value: TextIO,
-        *args: Any,
-        encoding: Optional[str] = None,
-        content_type: Optional[str] = None,
-        **kwargs: Any,
-    ) -> None:
-
-        if encoding is None:
-            if content_type is None:
-                encoding = "utf-8"
-                content_type = "text/plain; charset=utf-8"
-            else:
-                mimetype = parse_mimetype(content_type)
-                encoding = mimetype.parameters.get("charset", "utf-8")
-        else:
-            if content_type is None:
-                content_type = "text/plain; charset=%s" % encoding
-
-        super().__init__(
-            value,
-            content_type=content_type,
-            encoding=encoding,
-            *args,
-            **kwargs,
-        )
-
-    @property
-    def size(self) -> Optional[int]:
-        try:
-            return os.fstat(self._value.fileno()).st_size - self._value.tell()
-        except OSError:
-            return None
-
-    async def write(self, writer: AbstractStreamWriter) -> None:
-        loop = asyncio.get_event_loop()
-        try:
-            chunk = await loop.run_in_executor(None, self._value.read, 2**16)
-            while chunk:
-                data = (
-                    chunk.encode(encoding=self._encoding)
-                    if self._encoding
-                    else chunk.encode()
-                )
-                await writer.write(data)
-                chunk = await loop.run_in_executor(None, self._value.read, 2**16)
-        finally:
-            await loop.run_in_executor(None, self._value.close)
-
-
-class BytesIOPayload(IOBasePayload):
-    @property
-    def size(self) -> int:
-        position = self._value.tell()
-        end = self._value.seek(0, os.SEEK_END)
-        self._value.seek(position)
-        return end - position
-
-
-class BufferedReaderPayload(IOBasePayload):
-    @property
-    def size(self) -> Optional[int]:
-        try:
-            return os.fstat(self._value.fileno()).st_size - self._value.tell()
-        except OSError:
-            # data.fileno() is not supported, e.g.
-            # io.BufferedReader(io.BytesIO(b'data'))
-            return None
-
-
-class JsonPayload(BytesPayload):
-    def __init__(
-        self,
-        value: Any,
-        encoding: str = "utf-8",
-        content_type: str = "application/json",
-        dumps: JSONEncoder = json.dumps,
-        *args: Any,
-        **kwargs: Any,
-    ) -> None:
-
-        super().__init__(
-            dumps(value).encode(encoding),
-            content_type=content_type,
-            encoding=encoding,
-            *args,
-            **kwargs,
-        )
-
-
-if TYPE_CHECKING:  # pragma: no cover
-    from typing import AsyncIterable, AsyncIterator
-
-    _AsyncIterator = AsyncIterator[bytes]
-    _AsyncIterable = AsyncIterable[bytes]
-else:
-    from collections.abc import AsyncIterable, AsyncIterator
-
-    _AsyncIterator = AsyncIterator
-    _AsyncIterable = AsyncIterable
-
-
-class AsyncIterablePayload(Payload):
-
-    _iter: Optional[_AsyncIterator] = None
-
-    def __init__(self, value: _AsyncIterable, *args: Any, **kwargs: Any) -> None:
-        if not isinstance(value, AsyncIterable):
-            raise TypeError(
-                "value argument must support "
-                "collections.abc.AsyncIterable interface, "
-                "got {!r}".format(type(value))
-            )
-
-        if "content_type" not in kwargs:
-            kwargs["content_type"] = "application/octet-stream"
-
-        super().__init__(value, *args, **kwargs)
-
-        self._iter = value.__aiter__()
-
-    async def write(self, writer: AbstractStreamWriter) -> None:
-        if self._iter:
-            try:
-                # iter is not None check prevents rare cases
-                # when the case iterable is used twice
-                while True:
-                    chunk = await self._iter.__anext__()
-                    await writer.write(chunk)
-            except StopAsyncIteration:
-                self._iter = None
-
-
-class StreamReaderPayload(AsyncIterablePayload):
-    def __init__(self, value: StreamReader, *args: Any, **kwargs: Any) -> None:
-        super().__init__(value.iter_any(), *args, **kwargs)
-
-
-PAYLOAD_REGISTRY = PayloadRegistry()
-PAYLOAD_REGISTRY.register(BytesPayload, (bytes, bytearray, memoryview))
-PAYLOAD_REGISTRY.register(StringPayload, str)
-PAYLOAD_REGISTRY.register(StringIOPayload, io.StringIO)
-PAYLOAD_REGISTRY.register(TextIOPayload, io.TextIOBase)
-PAYLOAD_REGISTRY.register(BytesIOPayload, io.BytesIO)
-PAYLOAD_REGISTRY.register(BufferedReaderPayload, (io.BufferedReader, io.BufferedRandom))
-PAYLOAD_REGISTRY.register(IOBasePayload, io.IOBase)
-PAYLOAD_REGISTRY.register(StreamReaderPayload, StreamReader)
-# try_last for giving a chance to more specialized async interables like
-# multidict.BodyPartReaderPayload override the default
-PAYLOAD_REGISTRY.register(AsyncIterablePayload, AsyncIterable, order=Order.try_last)
diff --git a/spaces/dcarpintero/nlp-summarizer-pegasus/.venv/lib/python3.9/site-packages/gradio/templates/cdn/assets/index-642779d3.js b/spaces/dcarpintero/nlp-summarizer-pegasus/.venv/lib/python3.9/site-packages/gradio/templates/cdn/assets/index-642779d3.js
deleted file mode 100644
index 9c474bab7e2445653546145ecb6cc09b9849cdac..0000000000000000000000000000000000000000
--- a/spaces/dcarpintero/nlp-summarizer-pegasus/.venv/lib/python3.9/site-packages/gradio/templates/cdn/assets/index-642779d3.js
+++ /dev/null
@@ -1,2 +0,0 @@
-import{S as m,e as u,s as r,F as d,G as b,w as _,u as f,H as g,a9 as v,ab as S,ac as h,ad as k}from"./index-9e76ffee.js";import{B as p}from"./Button-30a08c0b.js";function w(a){let t;const l=a[3].default,e=v(l,a,a[4],null);return{c(){e&&e.c()},m(s,n){e&&e.m(s,n),t=!0},p(s,n){e&&e.p&&(!t||n&16)&&S(e,l,s,s[4],t?k(l,s[4],n,null):h(s[4]),null)},i(s){t||(_(e,s),t=!0)},o(s){f(e,s),t=!1},d(s){e&&e.d(s)}}}function B(a){let t,l;return t=new p({props:{elem_id:a[0],elem_classes:a[1],visible:a[2],explicit_call:!0,$$slots:{default:[w]},$$scope:{ctx:a}}}),{c(){d(t.$$.fragment)},m(e,s){b(t,e,s),l=!0},p(e,[s]){const n={};s&1&&(n.elem_id=e[0]),s&2&&(n.elem_classes=e[1]),s&4&&(n.visible=e[2]),s&16&&(n.$$scope={dirty:s,ctx:e}),t.$set(n)},i(e){l||(_(t.$$.fragment,e),l=!0)},o(e){f(t.$$.fragment,e),l=!1},d(e){g(t,e)}}}function C(a,t,l){let{$$slots:e={},$$scope:s}=t,{elem_id:n}=t,{elem_classes:o}=t,{visible:c=!0}=t;return a.$$set=i=>{"elem_id"in i&&l(0,n=i.elem_id),"elem_classes"in i&&l(1,o=i.elem_classes),"visible"in i&&l(2,c=i.visible),"$$scope"in i&&l(4,s=i.$$scope)},[n,o,c,e,s]}class q extends m{constructor(t){super(),u(this,t,C,B,r,{elem_id:0,elem_classes:1,visible:2})}}const H=q,j=["static"];export{H as Component,j as modes};
-//# sourceMappingURL=index-642779d3.js.map
diff --git a/spaces/dcarpintero/nlp-summarizer-pegasus/.venv/lib/python3.9/site-packages/gradio/templates/frontend/assets/Image-6dd8ae4a.js b/spaces/dcarpintero/nlp-summarizer-pegasus/.venv/lib/python3.9/site-packages/gradio/templates/frontend/assets/Image-6dd8ae4a.js
deleted file mode 100644
index c5cce59736ce7af5886b3cd5ac37c8060ca6d2bc..0000000000000000000000000000000000000000
--- a/spaces/dcarpintero/nlp-summarizer-pegasus/.venv/lib/python3.9/site-packages/gradio/templates/frontend/assets/Image-6dd8ae4a.js
+++ /dev/null
@@ -1,2 +0,0 @@
-import{S as r,e as u,s as d,m as y,X as f,g as m,Y as i,h as o,n as g,k as v}from"./index-39fce9e2.js";function b(t){let e,s;return{c(){e=y("img"),f(e.src,s=t[1]+t[0])||m(e,"src",s),m(e,"class","svelte-gqt00k"),i(e,"table",t[2]==="table"),i(e,"gallery",t[2]==="gallery"),i(e,"selected",t[3])},m(l,a){o(l,e,a)},p(l,[a]){a&3&&!f(e.src,s=l[1]+l[0])&&m(e,"src",s),a&4&&i(e,"table",l[2]==="table"),a&4&&i(e,"gallery",l[2]==="gallery"),a&8&&i(e,"selected",l[3])},i:g,o:g,d(l){l&&v(e)}}}function h(t,e,s){let{value:l}=e,{samples_dir:a}=e,{type:c}=e,{selected:_=!1}=e;return t.$$set=n=>{"value"in n&&s(0,l=n.value),"samples_dir"in n&&s(1,a=n.samples_dir),"type"in n&&s(2,c=n.type),"selected"in n&&s(3,_=n.selected)},[l,a,c,_]}class q extends r{constructor(e){super(),u(this,e,h,b,d,{value:0,samples_dir:1,type:2,selected:3})}}const k=q;export{k as E};
-//# sourceMappingURL=Image-6dd8ae4a.js.map
diff --git a/spaces/dcarpintero/nlp-summarizer-pegasus/.venv/lib/python3.9/site-packages/huggingface_hub/_webhooks_payload.py b/spaces/dcarpintero/nlp-summarizer-pegasus/.venv/lib/python3.9/site-packages/huggingface_hub/_webhooks_payload.py
deleted file mode 100644
index bc9aa7be046065e0521a8654290d520fa3f917dc..0000000000000000000000000000000000000000
--- a/spaces/dcarpintero/nlp-summarizer-pegasus/.venv/lib/python3.9/site-packages/huggingface_hub/_webhooks_payload.py
+++ /dev/null
@@ -1,117 +0,0 @@
-# coding=utf-8
-# Copyright 2023-present, the HuggingFace Inc. team.
-#
-# Licensed under the Apache License, Version 2.0 (the "License");
-# you may not use this file except in compliance with the License.
-# You may obtain a copy of the License at
-#
-#     http://www.apache.org/licenses/LICENSE-2.0
-#
-# Unless required by applicable law or agreed to in writing, software
-# distributed under the License is distributed on an "AS IS" BASIS,
-# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
-# See the License for the specific language governing permissions and
-# limitations under the License.
-"""Contains data structures to parse the webhooks payload."""
-from typing import List, Optional
-
-from pydantic import BaseModel
-
-from .utils._typing import Literal
-
-
-# This is an adaptation of the ReportV3 interface implemented in moon-landing. V0, V1 and V2 have been ignored as they
-# are not in used anymore. To keep in sync when format is updated in
-# https://github.com/huggingface/moon-landing/blob/main/server/lib/HFWebhooks.ts (internal link).
-
-
-WebhookEvent_T = Literal[
-    "create",
-    "delete",
-    "move",
-    "update",
-]
-RepoChangeEvent_T = Literal[
-    "add",
-    "move",
-    "remove",
-    "update",
-]
-RepoType_T = Literal[
-    "dataset",
-    "model",
-    "space",
-]
-DiscussionStatus_T = Literal[
-    "closed",
-    "draft",
-    "open",
-    "merged",
-]
-SupportedWebhookVersion = Literal[3]
-
-
-class ObjectId(BaseModel):
-    id: str
-
-
-class WebhookPayloadUrl(BaseModel):
-    web: str
-    api: Optional[str]
-
-
-class WebhookPayloadMovedTo(BaseModel):
-    name: str
-    owner: ObjectId
-
-
-class WebhookPayloadWebhook(ObjectId):
-    version: SupportedWebhookVersion
-
-
-class WebhookPayloadEvent(BaseModel):
-    action: WebhookEvent_T
-    scope: str
-
-
-class WebhookPayloadDiscussionChanges(BaseModel):
-    base: str
-    mergeCommitId: Optional[str]
-
-
-class WebhookPayloadComment(ObjectId):
-    author: ObjectId
-    hidden: bool
-    content: Optional[str]
-    url: WebhookPayloadUrl
-
-
-class WebhookPayloadDiscussion(ObjectId):
-    num: int
-    author: ObjectId
-    url: WebhookPayloadUrl
-    title: str
-    isPullRequest: bool
-    status: DiscussionStatus_T
-    changes: Optional[WebhookPayloadDiscussionChanges]
-    pinned: Optional[bool]
-
-
-class WebhookPayloadRepo(ObjectId):
-    owner: ObjectId
-    head_sha: Optional[str]
-    name: str
-    private: bool
-    subdomain: Optional[str]
-    tags: Optional[List[str]]
-    type: Literal["dataset", "model", "space"]
-    url: WebhookPayloadUrl
-
-
-class WebhookPayload(BaseModel):
-    event: WebhookPayloadEvent
-    repo: WebhookPayloadRepo
-    discussion: Optional[WebhookPayloadDiscussion]
-    comment: Optional[WebhookPayloadComment]
-    webhook: WebhookPayloadWebhook
-    movedTo: Optional[WebhookPayloadMovedTo]
diff --git a/spaces/declare-lab/tango/diffusers/src/diffusers/pipelines/unclip/pipeline_unclip.py b/spaces/declare-lab/tango/diffusers/src/diffusers/pipelines/unclip/pipeline_unclip.py
deleted file mode 100644
index 3aac39b3a3b022724c67cfa5d387a08f03e5bbe7..0000000000000000000000000000000000000000
--- a/spaces/declare-lab/tango/diffusers/src/diffusers/pipelines/unclip/pipeline_unclip.py
+++ /dev/null
@@ -1,534 +0,0 @@
-# Copyright 2023 Kakao Brain and The HuggingFace Team. All rights reserved.
-#
-# Licensed under the Apache License, Version 2.0 (the "License");
-# you may not use this file except in compliance with the License.
-# You may obtain a copy of the License at
-#
-#     http://www.apache.org/licenses/LICENSE-2.0
-#
-# Unless required by applicable law or agreed to in writing, software
-# distributed under the License is distributed on an "AS IS" BASIS,
-# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
-# See the License for the specific language governing permissions and
-# limitations under the License.
-
-import inspect
-from typing import List, Optional, Tuple, Union
-
-import torch
-from torch.nn import functional as F
-from transformers import CLIPTextModelWithProjection, CLIPTokenizer
-from transformers.models.clip.modeling_clip import CLIPTextModelOutput
-
-from ...models import PriorTransformer, UNet2DConditionModel, UNet2DModel
-from ...pipelines import DiffusionPipeline
-from ...pipelines.pipeline_utils import ImagePipelineOutput
-from ...schedulers import UnCLIPScheduler
-from ...utils import is_accelerate_available, logging, randn_tensor
-from .text_proj import UnCLIPTextProjModel
-
-
-logger = logging.get_logger(__name__)  # pylint: disable=invalid-name
-
-
-class UnCLIPPipeline(DiffusionPipeline):
-    """
-    Pipeline for text-to-image generation using unCLIP
-
-    This model inherits from [`DiffusionPipeline`]. Check the superclass documentation for the generic methods the
-    library implements for all the pipelines (such as downloading or saving, running on a particular device, etc.)
-
-    Args:
-        text_encoder ([`CLIPTextModelWithProjection`]):
-            Frozen text-encoder.
-        tokenizer (`CLIPTokenizer`):
-            Tokenizer of class
-            [CLIPTokenizer](https://huggingface.co/docs/transformers/v4.21.0/en/model_doc/clip#transformers.CLIPTokenizer).
-        prior ([`PriorTransformer`]):
-            The canonincal unCLIP prior to approximate the image embedding from the text embedding.
-        text_proj ([`UnCLIPTextProjModel`]):
-            Utility class to prepare and combine the embeddings before they are passed to the decoder.
-        decoder ([`UNet2DConditionModel`]):
-            The decoder to invert the image embedding into an image.
-        super_res_first ([`UNet2DModel`]):
-            Super resolution unet. Used in all but the last step of the super resolution diffusion process.
-        super_res_last ([`UNet2DModel`]):
-            Super resolution unet. Used in the last step of the super resolution diffusion process.
-        prior_scheduler ([`UnCLIPScheduler`]):
-            Scheduler used in the prior denoising process. Just a modified DDPMScheduler.
-        decoder_scheduler ([`UnCLIPScheduler`]):
-            Scheduler used in the decoder denoising process. Just a modified DDPMScheduler.
-        super_res_scheduler ([`UnCLIPScheduler`]):
-            Scheduler used in the super resolution denoising process. Just a modified DDPMScheduler.
-
-    """
-
-    prior: PriorTransformer
-    decoder: UNet2DConditionModel
-    text_proj: UnCLIPTextProjModel
-    text_encoder: CLIPTextModelWithProjection
-    tokenizer: CLIPTokenizer
-    super_res_first: UNet2DModel
-    super_res_last: UNet2DModel
-
-    prior_scheduler: UnCLIPScheduler
-    decoder_scheduler: UnCLIPScheduler
-    super_res_scheduler: UnCLIPScheduler
-
-    def __init__(
-        self,
-        prior: PriorTransformer,
-        decoder: UNet2DConditionModel,
-        text_encoder: CLIPTextModelWithProjection,
-        tokenizer: CLIPTokenizer,
-        text_proj: UnCLIPTextProjModel,
-        super_res_first: UNet2DModel,
-        super_res_last: UNet2DModel,
-        prior_scheduler: UnCLIPScheduler,
-        decoder_scheduler: UnCLIPScheduler,
-        super_res_scheduler: UnCLIPScheduler,
-    ):
-        super().__init__()
-
-        self.register_modules(
-            prior=prior,
-            decoder=decoder,
-            text_encoder=text_encoder,
-            tokenizer=tokenizer,
-            text_proj=text_proj,
-            super_res_first=super_res_first,
-            super_res_last=super_res_last,
-            prior_scheduler=prior_scheduler,
-            decoder_scheduler=decoder_scheduler,
-            super_res_scheduler=super_res_scheduler,
-        )
-
-    def prepare_latents(self, shape, dtype, device, generator, latents, scheduler):
-        if latents is None:
-            latents = randn_tensor(shape, generator=generator, device=device, dtype=dtype)
-        else:
-            if latents.shape != shape:
-                raise ValueError(f"Unexpected latents shape, got {latents.shape}, expected {shape}")
-            latents = latents.to(device)
-
-        latents = latents * scheduler.init_noise_sigma
-        return latents
-
-    def _encode_prompt(
-        self,
-        prompt,
-        device,
-        num_images_per_prompt,
-        do_classifier_free_guidance,
-        text_model_output: Optional[Union[CLIPTextModelOutput, Tuple]] = None,
-        text_attention_mask: Optional[torch.Tensor] = None,
-    ):
-        if text_model_output is None:
-            batch_size = len(prompt) if isinstance(prompt, list) else 1
-            # get prompt text embeddings
-            text_inputs = self.tokenizer(
-                prompt,
-                padding="max_length",
-                max_length=self.tokenizer.model_max_length,
-                truncation=True,
-                return_tensors="pt",
-            )
-            text_input_ids = text_inputs.input_ids
-            text_mask = text_inputs.attention_mask.bool().to(device)
-
-            untruncated_ids = self.tokenizer(prompt, padding="longest", return_tensors="pt").input_ids
-
-            if untruncated_ids.shape[-1] >= text_input_ids.shape[-1] and not torch.equal(
-                text_input_ids, untruncated_ids
-            ):
-                removed_text = self.tokenizer.batch_decode(
-                    untruncated_ids[:, self.tokenizer.model_max_length - 1 : -1]
-                )
-                logger.warning(
-                    "The following part of your input was truncated because CLIP can only handle sequences up to"
-                    f" {self.tokenizer.model_max_length} tokens: {removed_text}"
-                )
-                text_input_ids = text_input_ids[:, : self.tokenizer.model_max_length]
-
-            text_encoder_output = self.text_encoder(text_input_ids.to(device))
-
-            prompt_embeds = text_encoder_output.text_embeds
-            text_encoder_hidden_states = text_encoder_output.last_hidden_state
-
-        else:
-            batch_size = text_model_output[0].shape[0]
-            prompt_embeds, text_encoder_hidden_states = text_model_output[0], text_model_output[1]
-            text_mask = text_attention_mask
-
-        prompt_embeds = prompt_embeds.repeat_interleave(num_images_per_prompt, dim=0)
-        text_encoder_hidden_states = text_encoder_hidden_states.repeat_interleave(num_images_per_prompt, dim=0)
-        text_mask = text_mask.repeat_interleave(num_images_per_prompt, dim=0)
-
-        if do_classifier_free_guidance:
-            uncond_tokens = [""] * batch_size
-
-            uncond_input = self.tokenizer(
-                uncond_tokens,
-                padding="max_length",
-                max_length=self.tokenizer.model_max_length,
-                truncation=True,
-                return_tensors="pt",
-            )
-            uncond_text_mask = uncond_input.attention_mask.bool().to(device)
-            negative_prompt_embeds_text_encoder_output = self.text_encoder(uncond_input.input_ids.to(device))
-
-            negative_prompt_embeds = negative_prompt_embeds_text_encoder_output.text_embeds
-            uncond_text_encoder_hidden_states = negative_prompt_embeds_text_encoder_output.last_hidden_state
-
-            # duplicate unconditional embeddings for each generation per prompt, using mps friendly method
-
-            seq_len = negative_prompt_embeds.shape[1]
-            negative_prompt_embeds = negative_prompt_embeds.repeat(1, num_images_per_prompt)
-            negative_prompt_embeds = negative_prompt_embeds.view(batch_size * num_images_per_prompt, seq_len)
-
-            seq_len = uncond_text_encoder_hidden_states.shape[1]
-            uncond_text_encoder_hidden_states = uncond_text_encoder_hidden_states.repeat(1, num_images_per_prompt, 1)
-            uncond_text_encoder_hidden_states = uncond_text_encoder_hidden_states.view(
-                batch_size * num_images_per_prompt, seq_len, -1
-            )
-            uncond_text_mask = uncond_text_mask.repeat_interleave(num_images_per_prompt, dim=0)
-
-            # done duplicates
-
-            # For classifier free guidance, we need to do two forward passes.
-            # Here we concatenate the unconditional and text embeddings into a single batch
-            # to avoid doing two forward passes
-            prompt_embeds = torch.cat([negative_prompt_embeds, prompt_embeds])
-            text_encoder_hidden_states = torch.cat([uncond_text_encoder_hidden_states, text_encoder_hidden_states])
-
-            text_mask = torch.cat([uncond_text_mask, text_mask])
-
-        return prompt_embeds, text_encoder_hidden_states, text_mask
-
-    def enable_sequential_cpu_offload(self, gpu_id=0):
-        r"""
-        Offloads all models to CPU using accelerate, significantly reducing memory usage. When called, the pipeline's
-        models have their state dicts saved to CPU and then are moved to a `torch.device('meta') and loaded to GPU only
-        when their specific submodule has its `forward` method called.
-        """
-        if is_accelerate_available():
-            from accelerate import cpu_offload
-        else:
-            raise ImportError("Please install accelerate via `pip install accelerate`")
-
-        device = torch.device(f"cuda:{gpu_id}")
-
-        # TODO: self.prior.post_process_latents is not covered by the offload hooks, so it fails if added to the list
-        models = [
-            self.decoder,
-            self.text_proj,
-            self.text_encoder,
-            self.super_res_first,
-            self.super_res_last,
-        ]
-        for cpu_offloaded_model in models:
-            if cpu_offloaded_model is not None:
-                cpu_offload(cpu_offloaded_model, device)
-
-    @property
-    def _execution_device(self):
-        r"""
-        Returns the device on which the pipeline's models will be executed. After calling
-        `pipeline.enable_sequential_cpu_offload()` the execution device can only be inferred from Accelerate's module
-        hooks.
-        """
-        if self.device != torch.device("meta") or not hasattr(self.decoder, "_hf_hook"):
-            return self.device
-        for module in self.decoder.modules():
-            if (
-                hasattr(module, "_hf_hook")
-                and hasattr(module._hf_hook, "execution_device")
-                and module._hf_hook.execution_device is not None
-            ):
-                return torch.device(module._hf_hook.execution_device)
-        return self.device
-
-    @torch.no_grad()
-    def __call__(
-        self,
-        prompt: Optional[Union[str, List[str]]] = None,
-        num_images_per_prompt: int = 1,
-        prior_num_inference_steps: int = 25,
-        decoder_num_inference_steps: int = 25,
-        super_res_num_inference_steps: int = 7,
-        generator: Optional[Union[torch.Generator, List[torch.Generator]]] = None,
-        prior_latents: Optional[torch.FloatTensor] = None,
-        decoder_latents: Optional[torch.FloatTensor] = None,
-        super_res_latents: Optional[torch.FloatTensor] = None,
-        text_model_output: Optional[Union[CLIPTextModelOutput, Tuple]] = None,
-        text_attention_mask: Optional[torch.Tensor] = None,
-        prior_guidance_scale: float = 4.0,
-        decoder_guidance_scale: float = 8.0,
-        output_type: Optional[str] = "pil",
-        return_dict: bool = True,
-    ):
-        """
-        Function invoked when calling the pipeline for generation.
-
-        Args:
-            prompt (`str` or `List[str]`):
-                The prompt or prompts to guide the image generation. This can only be left undefined if
-                `text_model_output` and `text_attention_mask` is passed.
-            num_images_per_prompt (`int`, *optional*, defaults to 1):
-                The number of images to generate per prompt.
-            prior_num_inference_steps (`int`, *optional*, defaults to 25):
-                The number of denoising steps for the prior. More denoising steps usually lead to a higher quality
-                image at the expense of slower inference.
-            decoder_num_inference_steps (`int`, *optional*, defaults to 25):
-                The number of denoising steps for the decoder. More denoising steps usually lead to a higher quality
-                image at the expense of slower inference.
-            super_res_num_inference_steps (`int`, *optional*, defaults to 7):
-                The number of denoising steps for super resolution. More denoising steps usually lead to a higher
-                quality image at the expense of slower inference.
-            generator (`torch.Generator` or `List[torch.Generator]`, *optional*):
-                One or a list of [torch generator(s)](https://pytorch.org/docs/stable/generated/torch.Generator.html)
-                to make generation deterministic.
-            prior_latents (`torch.FloatTensor` of shape (batch size, embeddings dimension), *optional*):
-                Pre-generated noisy latents to be used as inputs for the prior.
-            decoder_latents (`torch.FloatTensor` of shape (batch size, channels, height, width), *optional*):
-                Pre-generated noisy latents to be used as inputs for the decoder.
-            super_res_latents (`torch.FloatTensor` of shape (batch size, channels, super res height, super res width), *optional*):
-                Pre-generated noisy latents to be used as inputs for the decoder.
-            prior_guidance_scale (`float`, *optional*, defaults to 4.0):
-                Guidance scale as defined in [Classifier-Free Diffusion Guidance](https://arxiv.org/abs/2207.12598).
-                `guidance_scale` is defined as `w` of equation 2. of [Imagen
-                Paper](https://arxiv.org/pdf/2205.11487.pdf). Guidance scale is enabled by setting `guidance_scale >
-                1`. Higher guidance scale encourages to generate images that are closely linked to the text `prompt`,
-                usually at the expense of lower image quality.
-            decoder_guidance_scale (`float`, *optional*, defaults to 4.0):
-                Guidance scale as defined in [Classifier-Free Diffusion Guidance](https://arxiv.org/abs/2207.12598).
-                `guidance_scale` is defined as `w` of equation 2. of [Imagen
-                Paper](https://arxiv.org/pdf/2205.11487.pdf). Guidance scale is enabled by setting `guidance_scale >
-                1`. Higher guidance scale encourages to generate images that are closely linked to the text `prompt`,
-                usually at the expense of lower image quality.
-            text_model_output (`CLIPTextModelOutput`, *optional*):
-                Pre-defined CLIPTextModel outputs that can be derived from the text encoder. Pre-defined text outputs
-                can be passed for tasks like text embedding interpolations. Make sure to also pass
-                `text_attention_mask` in this case. `prompt` can the be left to `None`.
-            text_attention_mask (`torch.Tensor`, *optional*):
-                Pre-defined CLIP text attention mask that can be derived from the tokenizer. Pre-defined text attention
-                masks are necessary when passing `text_model_output`.
-            output_type (`str`, *optional*, defaults to `"pil"`):
-                The output format of the generated image. Choose between
-                [PIL](https://pillow.readthedocs.io/en/stable/): `PIL.Image.Image` or `np.array`.
-            return_dict (`bool`, *optional*, defaults to `True`):
-                Whether or not to return a [`~pipelines.ImagePipelineOutput`] instead of a plain tuple.
-        """
-        if prompt is not None:
-            if isinstance(prompt, str):
-                batch_size = 1
-            elif isinstance(prompt, list):
-                batch_size = len(prompt)
-            else:
-                raise ValueError(f"`prompt` has to be of type `str` or `list` but is {type(prompt)}")
-        else:
-            batch_size = text_model_output[0].shape[0]
-
-        device = self._execution_device
-
-        batch_size = batch_size * num_images_per_prompt
-
-        do_classifier_free_guidance = prior_guidance_scale > 1.0 or decoder_guidance_scale > 1.0
-
-        prompt_embeds, text_encoder_hidden_states, text_mask = self._encode_prompt(
-            prompt, device, num_images_per_prompt, do_classifier_free_guidance, text_model_output, text_attention_mask
-        )
-
-        # prior
-
-        self.prior_scheduler.set_timesteps(prior_num_inference_steps, device=device)
-        prior_timesteps_tensor = self.prior_scheduler.timesteps
-
-        embedding_dim = self.prior.config.embedding_dim
-
-        prior_latents = self.prepare_latents(
-            (batch_size, embedding_dim),
-            prompt_embeds.dtype,
-            device,
-            generator,
-            prior_latents,
-            self.prior_scheduler,
-        )
-
-        for i, t in enumerate(self.progress_bar(prior_timesteps_tensor)):
-            # expand the latents if we are doing classifier free guidance
-            latent_model_input = torch.cat([prior_latents] * 2) if do_classifier_free_guidance else prior_latents
-
-            predicted_image_embedding = self.prior(
-                latent_model_input,
-                timestep=t,
-                proj_embedding=prompt_embeds,
-                encoder_hidden_states=text_encoder_hidden_states,
-                attention_mask=text_mask,
-            ).predicted_image_embedding
-
-            if do_classifier_free_guidance:
-                predicted_image_embedding_uncond, predicted_image_embedding_text = predicted_image_embedding.chunk(2)
-                predicted_image_embedding = predicted_image_embedding_uncond + prior_guidance_scale * (
-                    predicted_image_embedding_text - predicted_image_embedding_uncond
-                )
-
-            if i + 1 == prior_timesteps_tensor.shape[0]:
-                prev_timestep = None
-            else:
-                prev_timestep = prior_timesteps_tensor[i + 1]
-
-            prior_latents = self.prior_scheduler.step(
-                predicted_image_embedding,
-                timestep=t,
-                sample=prior_latents,
-                generator=generator,
-                prev_timestep=prev_timestep,
-            ).prev_sample
-
-        prior_latents = self.prior.post_process_latents(prior_latents)
-
-        image_embeddings = prior_latents
-
-        # done prior
-
-        # decoder
-
-        text_encoder_hidden_states, additive_clip_time_embeddings = self.text_proj(
-            image_embeddings=image_embeddings,
-            prompt_embeds=prompt_embeds,
-            text_encoder_hidden_states=text_encoder_hidden_states,
-            do_classifier_free_guidance=do_classifier_free_guidance,
-        )
-
-        if device.type == "mps":
-            # HACK: MPS: There is a panic when padding bool tensors,
-            # so cast to int tensor for the pad and back to bool afterwards
-            text_mask = text_mask.type(torch.int)
-            decoder_text_mask = F.pad(text_mask, (self.text_proj.clip_extra_context_tokens, 0), value=1)
-            decoder_text_mask = decoder_text_mask.type(torch.bool)
-        else:
-            decoder_text_mask = F.pad(text_mask, (self.text_proj.clip_extra_context_tokens, 0), value=True)
-
-        self.decoder_scheduler.set_timesteps(decoder_num_inference_steps, device=device)
-        decoder_timesteps_tensor = self.decoder_scheduler.timesteps
-
-        num_channels_latents = self.decoder.in_channels
-        height = self.decoder.sample_size
-        width = self.decoder.sample_size
-
-        decoder_latents = self.prepare_latents(
-            (batch_size, num_channels_latents, height, width),
-            text_encoder_hidden_states.dtype,
-            device,
-            generator,
-            decoder_latents,
-            self.decoder_scheduler,
-        )
-
-        for i, t in enumerate(self.progress_bar(decoder_timesteps_tensor)):
-            # expand the latents if we are doing classifier free guidance
-            latent_model_input = torch.cat([decoder_latents] * 2) if do_classifier_free_guidance else decoder_latents
-
-            noise_pred = self.decoder(
-                sample=latent_model_input,
-                timestep=t,
-                encoder_hidden_states=text_encoder_hidden_states,
-                class_labels=additive_clip_time_embeddings,
-                attention_mask=decoder_text_mask,
-            ).sample
-
-            if do_classifier_free_guidance:
-                noise_pred_uncond, noise_pred_text = noise_pred.chunk(2)
-                noise_pred_uncond, _ = noise_pred_uncond.split(latent_model_input.shape[1], dim=1)
-                noise_pred_text, predicted_variance = noise_pred_text.split(latent_model_input.shape[1], dim=1)
-                noise_pred = noise_pred_uncond + decoder_guidance_scale * (noise_pred_text - noise_pred_uncond)
-                noise_pred = torch.cat([noise_pred, predicted_variance], dim=1)
-
-            if i + 1 == decoder_timesteps_tensor.shape[0]:
-                prev_timestep = None
-            else:
-                prev_timestep = decoder_timesteps_tensor[i + 1]
-
-            # compute the previous noisy sample x_t -> x_t-1
-            decoder_latents = self.decoder_scheduler.step(
-                noise_pred, t, decoder_latents, prev_timestep=prev_timestep, generator=generator
-            ).prev_sample
-
-        decoder_latents = decoder_latents.clamp(-1, 1)
-
-        image_small = decoder_latents
-
-        # done decoder
-
-        # super res
-
-        self.super_res_scheduler.set_timesteps(super_res_num_inference_steps, device=device)
-        super_res_timesteps_tensor = self.super_res_scheduler.timesteps
-
-        channels = self.super_res_first.in_channels // 2
-        height = self.super_res_first.sample_size
-        width = self.super_res_first.sample_size
-
-        super_res_latents = self.prepare_latents(
-            (batch_size, channels, height, width),
-            image_small.dtype,
-            device,
-            generator,
-            super_res_latents,
-            self.super_res_scheduler,
-        )
-
-        if device.type == "mps":
-            # MPS does not support many interpolations
-            image_upscaled = F.interpolate(image_small, size=[height, width])
-        else:
-            interpolate_antialias = {}
-            if "antialias" in inspect.signature(F.interpolate).parameters:
-                interpolate_antialias["antialias"] = True
-
-            image_upscaled = F.interpolate(
-                image_small, size=[height, width], mode="bicubic", align_corners=False, **interpolate_antialias
-            )
-
-        for i, t in enumerate(self.progress_bar(super_res_timesteps_tensor)):
-            # no classifier free guidance
-
-            if i == super_res_timesteps_tensor.shape[0] - 1:
-                unet = self.super_res_last
-            else:
-                unet = self.super_res_first
-
-            latent_model_input = torch.cat([super_res_latents, image_upscaled], dim=1)
-
-            noise_pred = unet(
-                sample=latent_model_input,
-                timestep=t,
-            ).sample
-
-            if i + 1 == super_res_timesteps_tensor.shape[0]:
-                prev_timestep = None
-            else:
-                prev_timestep = super_res_timesteps_tensor[i + 1]
-
-            # compute the previous noisy sample x_t -> x_t-1
-            super_res_latents = self.super_res_scheduler.step(
-                noise_pred, t, super_res_latents, prev_timestep=prev_timestep, generator=generator
-            ).prev_sample
-
-        image = super_res_latents
-        # done super res
-
-        # post processing
-
-        image = image * 0.5 + 0.5
-        image = image.clamp(0, 1)
-        image = image.cpu().permute(0, 2, 3, 1).float().numpy()
-
-        if output_type == "pil":
-            image = self.numpy_to_pil(image)
-
-        if not return_dict:
-            return (image,)
-
-        return ImagePipelineOutput(images=image)
diff --git a/spaces/derek-thomas/disc-golf-simulator/shotshaper/environment.py b/spaces/derek-thomas/disc-golf-simulator/shotshaper/environment.py
deleted file mode 100644
index 4b6087bd026af49bdc0b6e8281be3ab9645453a8..0000000000000000000000000000000000000000
--- a/spaces/derek-thomas/disc-golf-simulator/shotshaper/environment.py
+++ /dev/null
@@ -1,27 +0,0 @@
-# -*- coding: utf-8 -*-
-"""
-"""
-import numpy as np
-
-g = -9.81
-# Air
-rho = 1.225
-mu = 1.81e-5
-
-winddir = np.array((1,0,0))
-z0 = 0.1
-Uref = 0.0
-zref = 1.5
-kappa = 0.41
-
-def wind_abl(z):
-    # For a constant wind:
-    # return Uref*winddir
-
-    if z < 0.0:
-        z = 0.0
-    
-    ustar = Uref*kappa/(np.log((zref+z0)/z0))
-    u = ustar/kappa*np.log((z+z0)/z0)
-    
-    return u*winddir
diff --git a/spaces/diacanFperku/AutoGPT/Fifa 08 Highly Compressed 10mb Free 95 Free.md b/spaces/diacanFperku/AutoGPT/Fifa 08 Highly Compressed 10mb Free 95 Free.md
deleted file mode 100644
index 82c729e0f812c651756a30b0ca26b8a3c33b2c8e..0000000000000000000000000000000000000000
--- a/spaces/diacanFperku/AutoGPT/Fifa 08 Highly Compressed 10mb Free 95 Free.md	
+++ /dev/null
@@ -1,6 +0,0 @@
-<h2>fifa 08 highly compressed 10mb free 95</h2><br /><p><b><b>Download Zip</b> &raquo; <a href="https://gohhs.com/2uFTvK">https://gohhs.com/2uFTvK</a></b></p><br /><br />
-<br />
-06/01/2019 · Fifa 13 highly compressed codex cpy crack free download game for PC only from here If you want fifa 13 game free download full version for PC ... 1fdad05405<br />
-<br />
-<br />
-<p></p>
diff --git a/spaces/diacanFperku/AutoGPT/Gerenciamentoemenfermagemkurcgantpdfdownload [NEW].md b/spaces/diacanFperku/AutoGPT/Gerenciamentoemenfermagemkurcgantpdfdownload [NEW].md
deleted file mode 100644
index 79d2232b8a4d557dfde95289fef2ec56fc9d6f75..0000000000000000000000000000000000000000
--- a/spaces/diacanFperku/AutoGPT/Gerenciamentoemenfermagemkurcgantpdfdownload [NEW].md	
+++ /dev/null
@@ -1,6 +0,0 @@
-<h2>gerenciamentoemenfermagemkurcgantpdfdownload</h2><br /><p><b><b>Download</b> &#10004; <a href="https://gohhs.com/2uFTL8">https://gohhs.com/2uFTL8</a></b></p><br /><br />
-
-treemlmerpfepnepgpnpfpnpfepgpppgnpgfgpgengpgepgfgepgfgepgfeplgfpplggpgfplpgfgpplgpplgphjhjphjphjjhpjhjphjjpjhjhjphjpphhphpphjjpjhjhjhpjpjjhpjpjjhpjhjpphjhjhjhpjhpjpjhjphjpjjhpjjhpjjhpjhjphjjhpjhjphjjhpjhjhpphjjhpjjhpjjhpjhjhphjhpjhjhphjhphjjhpjhjhphjjhpjhjhphjjhpjhphjjhpjhjhpphjjhpjjhpjjhpjhjhphjjhpjhjhpphjhjhjjhpjjhpjjhpjhjhphjjhpjhjhppjhjhjhjjhpjhjjhpjjhpjhjhppjjhpjhjphjjhpjhjhpphjhjhppjhjjhjhjhjhjjhjjppjhjhjhjjhjhjhjhjhjhjhjjhjhjhjhjhjhjhjhjhjhjhjhjhjhjhjjhjhjhjhjhjhjhjhjjhjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjj 4fefd39f24<br />
-<br />
-<br />
-<p></p>
diff --git a/spaces/diacanFperku/AutoGPT/Hourly Analysis Program 4.91 Serial Key Gen.epub.md b/spaces/diacanFperku/AutoGPT/Hourly Analysis Program 4.91 Serial Key Gen.epub.md
deleted file mode 100644
index d4d18078c4c2d019cee462c24365fb91ff7c45d0..0000000000000000000000000000000000000000
--- a/spaces/diacanFperku/AutoGPT/Hourly Analysis Program 4.91 Serial Key Gen.epub.md	
+++ /dev/null
@@ -1,12 +0,0 @@
-<h2>Hourly Analysis Program 4.91 Serial Key Gen.epub</h2><br /><p><b><b>Download Zip</b> &#9733; <a href="https://gohhs.com/2uFUu1">https://gohhs.com/2uFUu1</a></b></p><br /><br />
-
-D Kazieva · 2021 · Cited at 4 — Scenario analysis positively evaluates the level of complexity of the model, . The model code is implemented in a high-level, intuitive GAMA modeling language. The land use dataset contains a unique identifier, a land use code, and a . The object code is a unique number that identifies an object in . Description code is a unique string, .
-An object code is a unique number that identifies an object in a data set.
-There are two types of feature codes.
-Description of the object code.
-The object code is used to describe the .
-The model code is implemented in the GAMA language.
-The land use dataset contains a unique identifier, a land use code, and . 8a78ff9644<br />
-<br />
-<br />
-<p></p>
diff --git a/spaces/digitalxingtong/Bufeiyan-b-Bert-VITS2/mel_processing.py b/spaces/digitalxingtong/Bufeiyan-b-Bert-VITS2/mel_processing.py
deleted file mode 100644
index 50435ecf88ef4fb6c1d47f3e6edd04c3ea7d3e80..0000000000000000000000000000000000000000
--- a/spaces/digitalxingtong/Bufeiyan-b-Bert-VITS2/mel_processing.py
+++ /dev/null
@@ -1,112 +0,0 @@
-import math
-import os
-import random
-import torch
-from torch import nn
-import torch.nn.functional as F
-import torch.utils.data
-import numpy as np
-import librosa
-import librosa.util as librosa_util
-from librosa.util import normalize, pad_center, tiny
-from scipy.signal import get_window
-from scipy.io.wavfile import read
-from librosa.filters import mel as librosa_mel_fn
-
-MAX_WAV_VALUE = 32768.0
-
-
-def dynamic_range_compression_torch(x, C=1, clip_val=1e-5):
-    """
-    PARAMS
-    ------
-    C: compression factor
-    """
-    return torch.log(torch.clamp(x, min=clip_val) * C)
-
-
-def dynamic_range_decompression_torch(x, C=1):
-    """
-    PARAMS
-    ------
-    C: compression factor used to compress
-    """
-    return torch.exp(x) / C
-
-
-def spectral_normalize_torch(magnitudes):
-    output = dynamic_range_compression_torch(magnitudes)
-    return output
-
-
-def spectral_de_normalize_torch(magnitudes):
-    output = dynamic_range_decompression_torch(magnitudes)
-    return output
-
-
-mel_basis = {}
-hann_window = {}
-
-
-def spectrogram_torch(y, n_fft, sampling_rate, hop_size, win_size, center=False):
-    if torch.min(y) < -1.:
-        print('min value is ', torch.min(y))
-    if torch.max(y) > 1.:
-        print('max value is ', torch.max(y))
-
-    global hann_window
-    dtype_device = str(y.dtype) + '_' + str(y.device)
-    wnsize_dtype_device = str(win_size) + '_' + dtype_device
-    if wnsize_dtype_device not in hann_window:
-        hann_window[wnsize_dtype_device] = torch.hann_window(win_size).to(dtype=y.dtype, device=y.device)
-
-    y = torch.nn.functional.pad(y.unsqueeze(1), (int((n_fft-hop_size)/2), int((n_fft-hop_size)/2)), mode='reflect')
-    y = y.squeeze(1)
-
-    spec = torch.stft(y, n_fft, hop_length=hop_size, win_length=win_size, window=hann_window[wnsize_dtype_device],
-                      center=center, pad_mode='reflect', normalized=False, onesided=True, return_complex=False)
-
-    spec = torch.sqrt(spec.pow(2).sum(-1) + 1e-6)
-    return spec
-
-
-def spec_to_mel_torch(spec, n_fft, num_mels, sampling_rate, fmin, fmax):
-    global mel_basis
-    dtype_device = str(spec.dtype) + '_' + str(spec.device)
-    fmax_dtype_device = str(fmax) + '_' + dtype_device
-    if fmax_dtype_device not in mel_basis:
-        mel = librosa_mel_fn(sampling_rate, n_fft, num_mels, fmin, fmax)
-        mel_basis[fmax_dtype_device] = torch.from_numpy(mel).to(dtype=spec.dtype, device=spec.device)
-    spec = torch.matmul(mel_basis[fmax_dtype_device], spec)
-    spec = spectral_normalize_torch(spec)
-    return spec
-
-
-def mel_spectrogram_torch(y, n_fft, num_mels, sampling_rate, hop_size, win_size, fmin, fmax, center=False):
-    if torch.min(y) < -1.:
-        print('min value is ', torch.min(y))
-    if torch.max(y) > 1.:
-        print('max value is ', torch.max(y))
-
-    global mel_basis, hann_window
-    dtype_device = str(y.dtype) + '_' + str(y.device)
-    fmax_dtype_device = str(fmax) + '_' + dtype_device
-    wnsize_dtype_device = str(win_size) + '_' + dtype_device
-    if fmax_dtype_device not in mel_basis:
-        mel = librosa_mel_fn(sampling_rate, n_fft, num_mels, fmin, fmax)
-        mel_basis[fmax_dtype_device] = torch.from_numpy(mel).to(dtype=y.dtype, device=y.device)
-    if wnsize_dtype_device not in hann_window:
-        hann_window[wnsize_dtype_device] = torch.hann_window(win_size).to(dtype=y.dtype, device=y.device)
-
-    y = torch.nn.functional.pad(y.unsqueeze(1), (int((n_fft-hop_size)/2), int((n_fft-hop_size)/2)), mode='reflect')
-    y = y.squeeze(1)
-
-    spec = torch.stft(y, n_fft, hop_length=hop_size, win_length=win_size, window=hann_window[wnsize_dtype_device],
-                          center=center, pad_mode='reflect', normalized=False, onesided=True, return_complex=False)
-
-    spec = torch.sqrt(spec.pow(2).sum(-1) + 1e-6)
-
-    spec = torch.matmul(mel_basis[fmax_dtype_device], spec)
-    spec = spectral_normalize_torch(spec)
-
-    return spec
diff --git a/spaces/dineshreddy/WALT/mmdet/datasets/utils.py b/spaces/dineshreddy/WALT/mmdet/datasets/utils.py
deleted file mode 100644
index 157c9a2e1fe009552fdec9b9c9e7a33ed46d51ff..0000000000000000000000000000000000000000
--- a/spaces/dineshreddy/WALT/mmdet/datasets/utils.py
+++ /dev/null
@@ -1,158 +0,0 @@
-import copy
-import warnings
-
-from mmcv.cnn import VGG
-from mmcv.runner.hooks import HOOKS, Hook
-
-from mmdet.datasets.builder import PIPELINES
-from mmdet.datasets.pipelines import LoadAnnotations, LoadImageFromFile
-from mmdet.models.dense_heads import GARPNHead, RPNHead
-from mmdet.models.roi_heads.mask_heads import FusedSemanticHead
-
-
-def replace_ImageToTensor(pipelines):
-    """Replace the ImageToTensor transform in a data pipeline to
-    DefaultFormatBundle, which is normally useful in batch inference.
-
-    Args:
-        pipelines (list[dict]): Data pipeline configs.
-
-    Returns:
-        list: The new pipeline list with all ImageToTensor replaced by
-            DefaultFormatBundle.
-
-    Examples:
-        >>> pipelines = [
-        ...    dict(type='LoadImageFromFile'),
-        ...    dict(
-        ...        type='MultiScaleFlipAug',
-        ...        img_scale=(1333, 800),
-        ...        flip=False,
-        ...        transforms=[
-        ...            dict(type='Resize', keep_ratio=True),
-        ...            dict(type='RandomFlip'),
-        ...            dict(type='Normalize', mean=[0, 0, 0], std=[1, 1, 1]),
-        ...            dict(type='Pad', size_divisor=32),
-        ...            dict(type='ImageToTensor', keys=['img']),
-        ...            dict(type='Collect', keys=['img']),
-        ...        ])
-        ...    ]
-        >>> expected_pipelines = [
-        ...    dict(type='LoadImageFromFile'),
-        ...    dict(
-        ...        type='MultiScaleFlipAug',
-        ...        img_scale=(1333, 800),
-        ...        flip=False,
-        ...        transforms=[
-        ...            dict(type='Resize', keep_ratio=True),
-        ...            dict(type='RandomFlip'),
-        ...            dict(type='Normalize', mean=[0, 0, 0], std=[1, 1, 1]),
-        ...            dict(type='Pad', size_divisor=32),
-        ...            dict(type='DefaultFormatBundle'),
-        ...            dict(type='Collect', keys=['img']),
-        ...        ])
-        ...    ]
-        >>> assert expected_pipelines == replace_ImageToTensor(pipelines)
-    """
-    pipelines = copy.deepcopy(pipelines)
-    for i, pipeline in enumerate(pipelines):
-        if pipeline['type'] == 'MultiScaleFlipAug':
-            assert 'transforms' in pipeline
-            pipeline['transforms'] = replace_ImageToTensor(
-                pipeline['transforms'])
-        elif pipeline['type'] == 'ImageToTensor':
-            warnings.warn(
-                '"ImageToTensor" pipeline is replaced by '
-                '"DefaultFormatBundle" for batch inference. It is '
-                'recommended to manually replace it in the test '
-                'data pipeline in your config file.', UserWarning)
-            pipelines[i] = {'type': 'DefaultFormatBundle'}
-    return pipelines
-
-
-def get_loading_pipeline(pipeline):
-    """Only keep loading image and annotations related configuration.
-
-    Args:
-        pipeline (list[dict]): Data pipeline configs.
-
-    Returns:
-        list[dict]: The new pipeline list with only keep
-            loading image and annotations related configuration.
-
-    Examples:
-        >>> pipelines = [
-        ...    dict(type='LoadImageFromFile'),
-        ...    dict(type='LoadAnnotations', with_bbox=True),
-        ...    dict(type='Resize', img_scale=(1333, 800), keep_ratio=True),
-        ...    dict(type='RandomFlip', flip_ratio=0.5),
-        ...    dict(type='Normalize', **img_norm_cfg),
-        ...    dict(type='Pad', size_divisor=32),
-        ...    dict(type='DefaultFormatBundle'),
-        ...    dict(type='Collect', keys=['img', 'gt_bboxes', 'gt_labels'])
-        ...    ]
-        >>> expected_pipelines = [
-        ...    dict(type='LoadImageFromFile'),
-        ...    dict(type='LoadAnnotations', with_bbox=True)
-        ...    ]
-        >>> assert expected_pipelines ==\
-        ...        get_loading_pipeline(pipelines)
-    """
-    loading_pipeline_cfg = []
-    for cfg in pipeline:
-        obj_cls = PIPELINES.get(cfg['type'])
-        # TODO：use more elegant way to distinguish loading modules
-        if obj_cls is not None and obj_cls in (LoadImageFromFile,
-                                               LoadAnnotations):
-            loading_pipeline_cfg.append(cfg)
-    assert len(loading_pipeline_cfg) == 2, \
-        'The data pipeline in your config file must include ' \
-        'loading image and annotations related pipeline.'
-    return loading_pipeline_cfg
-
-
-@HOOKS.register_module()
-class NumClassCheckHook(Hook):
-
-    def _check_head(self, runner):
-        """Check whether the `num_classes` in head matches the length of
-        `CLASSSES` in `dataset`.
-
-        Args:
-            runner (obj:`EpochBasedRunner`): Epoch based Runner.
-        """
-        model = runner.model
-        dataset = runner.data_loader.dataset
-        if dataset.CLASSES is None:
-            runner.logger.warning(
-                f'Please set `CLASSES` '
-                f'in the {dataset.__class__.__name__} and'
-                f'check if it is consistent with the `num_classes` '
-                f'of head')
-        else:
-            for name, module in model.named_modules():
-                if hasattr(module, 'num_classes') and not isinstance(
-                        module, (RPNHead, VGG, FusedSemanticHead, GARPNHead)):
-                    assert module.num_classes == len(dataset.CLASSES), \
-                        (f'The `num_classes` ({module.num_classes}) in '
-                         f'{module.__class__.__name__} of '
-                         f'{model.__class__.__name__} does not matches '
-                         f'the length of `CLASSES` '
-                         f'{len(dataset.CLASSES)}) in '
-                         f'{dataset.__class__.__name__}')
-
-    def before_train_epoch(self, runner):
-        """Check whether the training dataset is compatible with head.
-
-        Args:
-            runner (obj:`EpochBasedRunner`): Epoch based Runner.
-        """
-        self._check_head(runner)
-
-    def before_val_epoch(self, runner):
-        """Check whether the dataset in val epoch is compatible with head.
-
-        Args:
-            runner (obj:`EpochBasedRunner`): Epoch based Runner.
-        """
-        self._check_head(runner)
diff --git a/spaces/dineshreddy/WALT/mmdet/models/necks/__init__.py b/spaces/dineshreddy/WALT/mmdet/models/necks/__init__.py
deleted file mode 100644
index 02f833a8a0f538a8c06fef622d1cadc1a1b66ea2..0000000000000000000000000000000000000000
--- a/spaces/dineshreddy/WALT/mmdet/models/necks/__init__.py
+++ /dev/null
@@ -1,16 +0,0 @@
-from .bfp import BFP
-from .channel_mapper import ChannelMapper
-from .fpg import FPG
-from .fpn import FPN
-from .fpn_carafe import FPN_CARAFE
-from .hrfpn import HRFPN
-from .nas_fpn import NASFPN
-from .nasfcos_fpn import NASFCOS_FPN
-from .pafpn import PAFPN
-from .rfp import RFP
-from .yolo_neck import YOLOV3Neck
-
-__all__ = [
-    'FPN', 'BFP', 'ChannelMapper', 'HRFPN', 'NASFPN', 'FPN_CARAFE', 'PAFPN',
-    'NASFCOS_FPN', 'RFP', 'YOLOV3Neck', 'FPG'
-]
diff --git a/spaces/dineshreddy/WALT/mmdet/models/utils/__init__.py b/spaces/dineshreddy/WALT/mmdet/models/utils/__init__.py
deleted file mode 100644
index 5165b22ce57d17f28392213e0f1b055c2b9360c1..0000000000000000000000000000000000000000
--- a/spaces/dineshreddy/WALT/mmdet/models/utils/__init__.py
+++ /dev/null
@@ -1,16 +0,0 @@
-from .builder import build_positional_encoding, build_transformer
-from .gaussian_target import gaussian_radius, gen_gaussian_target
-from .positional_encoding import (LearnedPositionalEncoding,
-                                  SinePositionalEncoding)
-from .res_layer import ResLayer, SimplifiedBasicBlock
-from .transformer import (FFN, DynamicConv, MultiheadAttention, Transformer,
-                          TransformerDecoder, TransformerDecoderLayer,
-                          TransformerEncoder, TransformerEncoderLayer)
-
-__all__ = [
-    'ResLayer', 'gaussian_radius', 'gen_gaussian_target', 'MultiheadAttention',
-    'FFN', 'TransformerEncoderLayer', 'TransformerEncoder',
-    'TransformerDecoderLayer', 'TransformerDecoder', 'Transformer',
-    'build_transformer', 'build_positional_encoding', 'SinePositionalEncoding',
-    'LearnedPositionalEncoding', 'DynamicConv', 'SimplifiedBasicBlock'
-]
diff --git a/spaces/divyahansg/text-generation-webui-space/convert-to-safetensors.py b/spaces/divyahansg/text-generation-webui-space/convert-to-safetensors.py
deleted file mode 100644
index 63baaa9726ab48025d2ba473d029bb3f1153aa3a..0000000000000000000000000000000000000000
--- a/spaces/divyahansg/text-generation-webui-space/convert-to-safetensors.py
+++ /dev/null
@@ -1,38 +0,0 @@
-'''
-
-Converts a transformers model to safetensors format and shards it.
-
-This makes it faster to load (because of safetensors) and lowers its RAM usage
-while loading (because of sharding).
-
-Based on the original script by 81300:
-
-https://gist.github.com/81300/fe5b08bff1cba45296a829b9d6b0f303
-
-'''
-
-import argparse
-from pathlib import Path
-
-import torch
-from transformers import AutoModelForCausalLM, AutoTokenizer
-
-parser = argparse.ArgumentParser(formatter_class=lambda prog: argparse.HelpFormatter(prog,max_help_position=54))
-parser.add_argument('MODEL', type=str, default=None, nargs='?', help="Path to the input model.")
-parser.add_argument('--output', type=str, default=None, help='Path to the output folder (default: models/{model_name}_safetensors).')
-parser.add_argument("--max-shard-size", type=str, default="2GB", help="Maximum size of a shard in GB or MB (default: %(default)s).")
-parser.add_argument('--bf16', action='store_true', help='Load the model with bfloat16 precision. Requires NVIDIA Ampere GPU.')
-args = parser.parse_args()
-
-if __name__ == '__main__':
-    path = Path(args.MODEL)
-    model_name = path.name
-
-    print(f"Loading {model_name}...")
-    model = AutoModelForCausalLM.from_pretrained(path, low_cpu_mem_usage=True, torch_dtype=torch.bfloat16 if args.bf16 else torch.float16)
-    tokenizer = AutoTokenizer.from_pretrained(path)
-
-    out_folder = args.output or Path(f"models/{model_name}_safetensors")
-    print(f"Saving the converted model to {out_folder} with a maximum shard size of {args.max_shard_size}...")
-    model.save_pretrained(out_folder, max_shard_size=args.max_shard_size, safe_serialization=True)
-    tokenizer.save_pretrained(out_folder)
diff --git a/spaces/dolceschokolade/chatbot-mini/prettier.config.js b/spaces/dolceschokolade/chatbot-mini/prettier.config.js
deleted file mode 100644
index daf4139177fd80181d50b1542647a69cd76fcac4..0000000000000000000000000000000000000000
--- a/spaces/dolceschokolade/chatbot-mini/prettier.config.js
+++ /dev/null
@@ -1,25 +0,0 @@
-module.exports = {
-  trailingComma: 'all',
-  singleQuote: true,
-  plugins: [
-    'prettier-plugin-tailwindcss',
-    '@trivago/prettier-plugin-sort-imports',
-  ],
-  importOrder: [
-    'react', // React
-    '^react-.*$', // React-related imports
-    '^next', // Next-related imports
-    '^next-.*$', // Next-related imports
-    '^next/.*$', // Next-related imports
-    '^.*/hooks/.*$', // Hooks
-    '^.*/services/.*$', // Services
-    '^.*/utils/.*$', // Utils
-    '^.*/types/.*$', // Types
-    '^.*/pages/.*$', // Components
-    '^.*/components/.*$', // Components
-    '^[./]', // Other imports
-    '.*', // Any uncaught imports
-  ],
-  importOrderSeparation: true,
-  importOrderSortSpecifiers: true,
-};
diff --git a/spaces/dorkai/ChatUIPro/app/styles/globals.css b/spaces/dorkai/ChatUIPro/app/styles/globals.css
deleted file mode 100644
index f48bf01edfbe9cc506b97a68bd953154e63a25f4..0000000000000000000000000000000000000000
--- a/spaces/dorkai/ChatUIPro/app/styles/globals.css
+++ /dev/null
@@ -1,128 +0,0 @@
-@tailwind base;
-@tailwind components;
-@tailwind utilities;
-
-:root {
-  --max-width: 1100px;
-  --border-radius: 12px;
-  --font-mono: ui-monospace, Menlo, Monaco, "Cascadia Mono", "Segoe UI Mono",
-    "Roboto Mono", "Oxygen Mono", "Ubuntu Monospace", "Source Code Pro",
-    "Fira Mono", "Droid Sans Mono", "Courier New", monospace;
-
-  --foreground-rgb: 0, 0, 0;
-  --background-start-rgb: 214, 219, 220;
-  --background-end-rgb: 255, 255, 255;
-
-  --primary-glow: conic-gradient(from 180deg at 50% 50%,
-      #16abff33 0deg,
-      #0885ff33 55deg,
-      #54d6ff33 120deg,
-      #0071ff33 160deg,
-      transparent 360deg);
-  --secondary-glow: radial-gradient(rgba(255, 255, 255, 1),
-      rgba(255, 255, 255, 0));
-
-  --tile-start-rgb: 239, 245, 249;
-  --tile-end-rgb: 228, 232, 233;
-  --tile-border: conic-gradient(#00000080,
-      #00000040,
-      #00000030,
-      #00000020,
-      #00000010,
-      #00000010,
-      #00000080);
-
-  --callout-rgb: 238, 240, 241;
-  --callout-border-rgb: 172, 175, 176;
-  --card-rgb: 180, 185, 188;
-  --card-border-rgb: 131, 134, 135;
-}
-
-/* @media (prefers-color-scheme: dark) {
-  :root {
-    --foreground-rgb: 255, 255, 255;
-    --background-start-rgb: 0, 0, 0;
-    --background-end-rgb: 0, 0, 0;
-
-    --primary-glow: radial-gradient(rgba(1, 65, 255, 0.4), rgba(1, 65, 255, 0));
-    --secondary-glow: linear-gradient(to bottom right,
-        rgba(1, 65, 255, 0),
-        rgba(1, 65, 255, 0),
-        rgba(1, 65, 255, 0.3));
-
-    --tile-start-rgb: 2, 13, 46;
-    --tile-end-rgb: 2, 5, 19;
-    --tile-border: conic-gradient(#ffffff80,
-        #ffffff40,
-        #ffffff30,
-        #ffffff20,
-        #ffffff10,
-        #ffffff10,
-        #ffffff80);
-
-    --callout-rgb: 20, 20, 20;
-    --callout-border-rgb: 108, 108, 108;
-    --card-rgb: 100, 100, 100;
-    --card-border-rgb: 200, 200, 200;
-  }
-} */
-
-* {
-  box-sizing: border-box;
-  padding: 0;
-  margin: 0;
-}
-
-html,
-body {
-  max-width: 100vw;
-  overflow-x: hidden;
-}
-
-body {
-  color: rgb(var(--foreground-rgb));
-  /* background: linear-gradient(
-      to bottom,
-      transparent,
-      rgb(var(--background-end-rgb))
-    )
-    rgb(var(--background-start-rgb)); */
-}
-
-a {
-  color: inherit;
-  text-decoration: none;
-}
-
-/* @media (prefers-color-scheme: dark) {
-  html {
-    color-scheme: dark;
-  }
-} */
-
-/* CSS Utils */
-.h1 {
-  padding-bottom: 1.5rem;
-  line-height: 1.5;
-  font-size: 1.125rem;
-  color: #111928;
-}
-
-.h2 {
-  font-size: 14px;
-  font-weight: 500;
-  color: #111928;
-  line-height: 1.5;
-}
-
-.link {
-  @apply text-blue-600 cursor-pointer hover:opacity-80 transition-opacity duration-200 ease-in-out;
-}
-
-.text-gradient {
-  background: linear-gradient(91.58deg, #2250F2 -29.55%, #0EBCF3 75.22%);
-  -webkit-background-clip: text;
-  -webkit-text-fill-color: transparent;
-  background-clip: text;
-  text-fill-color: transparent;
-}
diff --git a/spaces/dorkai/text-generation-webui-main/modules/AutoGPTQ_loader.py b/spaces/dorkai/text-generation-webui-main/modules/AutoGPTQ_loader.py
deleted file mode 100644
index adbee7eb45c598d1ce06455e27781f2c9dd318f6..0000000000000000000000000000000000000000
--- a/spaces/dorkai/text-generation-webui-main/modules/AutoGPTQ_loader.py
+++ /dev/null
@@ -1,40 +0,0 @@
-import logging
-from pathlib import Path
-
-from auto_gptq import AutoGPTQForCausalLM
-
-import modules.shared as shared
-from modules.models import get_max_memory_dict
-
-
-def load_quantized(model_name):
-    path_to_model = Path(f'{shared.args.model_dir}/{model_name}')
-    pt_path = None
-    use_safetensors = False
-
-    # Find the model checkpoint
-    for ext in ['.safetensors', '.pt', '.bin']:
-        found = list(path_to_model.glob(f"*{ext}"))
-        if len(found) > 0:
-            if len(found) > 1:
-                logging.warning(f'More than one {ext} model has been found. The last one will be selected. It could be wrong.')
-
-            pt_path = found[-1]
-            break
-
-    if pt_path is None:
-        logging.error("The model could not be loaded because its checkpoint file in .bin/.pt/.safetensors format could not be located.")
-        return
-
-    # Define the params for AutoGPTQForCausalLM.from_quantized
-    params = {
-        'model_basename': pt_path.stem,
-        'device': "cuda:0" if not shared.args.cpu else "cpu",
-        'use_triton': shared.args.triton,
-        'use_safetensors': use_safetensors,
-        'max_memory': get_max_memory_dict()
-    }
-
-    logging.warning(f"The AutoGPTQ params are: {params}")
-    model = AutoGPTQForCausalLM.from_quantized(path_to_model, **params)
-    return model
diff --git a/spaces/duycse1603/math2tex/HybridViT/module/component/prediction_head/__init__.py b/spaces/duycse1603/math2tex/HybridViT/module/component/prediction_head/__init__.py
deleted file mode 100644
index 48614426ef60537fb63eaf08cc105c003f79aea1..0000000000000000000000000000000000000000
--- a/spaces/duycse1603/math2tex/HybridViT/module/component/prediction_head/__init__.py
+++ /dev/null
@@ -1,5 +0,0 @@
-from .seq2seq import Attention
-from .seq2seq_v2 import AttentionV2
-from .tfm import TransformerPrediction
-
-__all__ = ['Attention', 'AttentionV2', 'TransformerPrediction']
\ No newline at end of file
diff --git a/spaces/falterWliame/Face_Mask_Detection/Download Ntsd 2.6 2021 Full Version.md b/spaces/falterWliame/Face_Mask_Detection/Download Ntsd 2.6 2021 Full Version.md
deleted file mode 100644
index 33da81a34944f2780f540a27a33eac09d84bba07..0000000000000000000000000000000000000000
--- a/spaces/falterWliame/Face_Mask_Detection/Download Ntsd 2.6 2021 Full Version.md	
+++ /dev/null
@@ -1,6 +0,0 @@
-<h2>Download Ntsd 2.6 Full Version</h2><br /><p><b><b>DOWNLOAD</b> >> <a href="https://urlca.com/2uDcR9">https://urlca.com/2uDcR9</a></b></p><br /><br />
-
-Ntsd 2.6 Full Version Free To Download.rar. 0 Reads 0 Votes 1 Part Story. tektoneza · By tektoneza Updated Dec 20, 2018 08:36PM. Read. ntsd 2.6 full version ... 4d29de3e1b<br />
-<br />
-<br />
-<p></p>
diff --git a/spaces/fatiXbelha/sd/Buy and Sell Cars with Ease Download Carsales App Today.md b/spaces/fatiXbelha/sd/Buy and Sell Cars with Ease Download Carsales App Today.md
deleted file mode 100644
index 1d5653875f77c717a355f3f2bf55bd389e19f760..0000000000000000000000000000000000000000
--- a/spaces/fatiXbelha/sd/Buy and Sell Cars with Ease Download Carsales App Today.md	
+++ /dev/null
@@ -1,141 +0,0 @@
-
-<h1>Download Carsales App: The Ultimate Guide for Car Buyers and Sellers</h1>
-<p>If you are looking for a car or want to sell your car, you might be wondering what is the best way to do it. You could browse through various websites, magazines, newspapers, or visit dealerships, but that would take a lot of time and effort. Or you could download carsales app, the number one car app in Australia, and make your life easier.</p>
-<p>Carsales app is a free mobile app that allows you to search, buy, sell, and research cars on the go. It has more tools, features, and functionality than any other car app, and it connects you with Australia's largest online automotive marketplace. Whether you are looking for a new or used car, a family car or a sports car, a sedan or an SUV, you can find it on carsales app.</p>
-<h2>download carsales app</h2><br /><p><b><b>Download File</b> ===== <a href="https://urllie.com/2uNAvE">https://urllie.com/2uNAvE</a></b></p><br /><br />
-<p>In this article, we will show you the benefits of using carsales app, how to download it on your device, how to use it for buying or selling cars, and what other users are saying about it. By the end of this article, you will be convinced that carsales app is the ultimate guide for car buyers and sellers.</p>
- <h2>Benefits of Using Carsales App</h2>
-<p>Carsales app has many benefits that make it stand out from other car apps. Here are some of them:</p>
-<h3>Search from over 150,000 new and used cars</h3>
-<p>With carsales app, you have access to over 150,000 new and used cars from private sellers, dealers, and certified pre-owned programs. You can filter your search by make, model, price, location, body type, fuel type, transmission, colour, and more. You can also view detailed information about each car, such as photos, videos, features, specifications, history reports, seller comments, and contact details.</p>
-<h3>Select multiple makes, models and locations in a single search</h3>
-<p>If you are not sure what kind of car you want or where to find it, you can use the multi-select feature on carsales app. This feature allows you to select multiple makes, models and locations in a single search. For example, you can search for Toyota Corolla or Mazda 3 in Sydney or Melbourne. This way, you can compare different options and find the best deal for you.</p>
-<h3>Access your Member Centre and sync your saved cars, searches and email alerts</h3>
-<p>When you download carsales app, you can create a free account and access your Member Centre. This is where you can sync all your saved cars, searches and email alerts across all your devices. You can also communicate with buyers and sellers via messages or phone calls. You can also access member benefits such as fuel discounts and more.</p>
-<h3>List your car for sale with Snap n' Sell and get a seller toolkit</h3>
-<p>If you want to sell your car quickly and easily, you can use the Snap n' Sell feature on carsales app. This feature allows you to list your car for sale straight from your smartphone by taking photos and filling in some details. You can also edit your ad or see how many people have viewed your car. You can also get a seller toolkit that includes tips, guides, and tools to help you sell your car faster and for more money.</p>
-<p>How to download the carsales app on iPhone or iPad<br />
-Benefits of using the carsales app to buy and sell cars<br />
-Carsales app reviews and ratings from users<br />
-Carsales app features and functionality<br />
-Carsales app download link for Android devices<br />
-Carsales app vs other car buying and selling apps<br />
-Carsales app member centre and benefits<br />
-Carsales app live ad stats and tips<br />
-Carsales app snap n' sell feature<br />
-Carsales app news and reviews on cars<br />
-How to access fuel discounts with the carsales app<br />
-How to value your car with the carsales app<br />
-How to share listings from the carsales app to social media<br />
-How to sync your saved cars, searches and email alerts with the carsales app<br />
-How to communicate with buyers and sellers via the carsales app<br />
-How to edit your ad or see how many people are interested in your car with the carsales app<br />
-How to list your car for sale with the carsales app<br />
-How to search for new and used cars with the carsales app<br />
-How to select multiple makes, models and locations in a single search with the carsales app<br />
-How to get a CarFacts report with the carsales app<br />
-How to get a tyresales.com.au voucher with the carsales app<br />
-How to get a seller toolkit with the carsales app<br />
-How to get a pre-sale checklist with the carsales app<br />
-How to get an after-sale checklist with the carsales app<br />
-How to get a for sale sticker with the carsales app<br />
-How to get transfer forms with the carsales app<br />
-How to contribute to market research with the carsales app<br />
-How to opt out of Nielsen tracking with the carsales app<br />
-How to update your iOS device to iOS 15 or above for the carsales app<br />
-How to contact carsales customer support via the carsales app</p>
-<h3>Edit your ad and see live stats of your car's performance</h3>
-<p>With carsales app, you can edit your ad anytime and anywhere. You can change the price, add or remove photos, update the description, or mark your car as sold. You can also see live stats of your car's performance, such as views, enquiries, leads, and offers. You can also see how your car ranks against similar cars in the market.</p>
-<h3>Value your car or research via News & Reviews</h3>
-<p>If you want to know how much your car is worth or what other cars are selling for, you can use the valuation tool on carsales app. This tool gives you an instant and accurate estimate of your car's value based on its make, model, year, kilometres, and condition. You can also research different cars via News & Reviews, where you can read expert reviews, ratings, comparisons, and advice on various cars.</p>
-<h3>Share listings with your network via social media or SMS</h3>
-<p>If you find a car that you like or want to share with someone else, you can easily do so via carsales app. You can share listings with your network via social media platforms such as Facebook, Twitter, Instagram, or WhatsApp. You can also send listings via SMS or email. This way, you can get feedback from your friends and family or help them find their dream car.</p>
- <h2>How to Download Carsales App</h2>
-<p>Downloading carsales app is very simple and fast. Here are the steps to follow depending on your device:</p>
-<h3>For iOS devices</h3>
-<p>If you have an iPhone or iPad, you can download carsales app from the App Store. Here is how:</p>
-<ol>
-<li>Open the App Store on your device.</li>
-<li>Search for "carsales" in the search bar.</li>
-<li>Tap on the "GET" button next to the carsales app icon.</li>
-<li>Enter your Apple ID password or use Touch ID or Face ID to confirm.</li>
-<li>Wait for the app to download and install on your device.</li>
-<li>Open the app and enjoy!</li>
-</ol>
-<h3>For Android devices</h3>
-<p>If you have an Android phone or tablet, you can download carsales app from the Google Play Store. Here is how:</p>
-<ol>
-<li>Open the Google Play Store on your device.</li>
-<li>Search for "carsales" in the search bar.</li>
-<li>Tap on the "INSTALL" button next to the carsales app icon.</li>
-<li>Wait for the app to download and install on your device.</li>
-<li>Open the app and enjoy!</li>
-</ol>
- <h2>How to Use Carsales App</h2>
-<p>Carsales app is very easy and intuitive to use. Here are some tips on how to use it for buying or selling cars:</p>
-<h3>For buyers</h3>
-<p>If you are looking for a car to buy, here are some steps to follow:</p>
-<ol>
-<li>Open the app and tap on the "Buy" tab at the bottom of the screen.</li>
-<li>Select the type of car you want (new or used) and enter your search criteria (make, model, price, location, etc.).</li>
-<li>Browse through the results and tap on any car that interests you.</li>
-<li>View more details about the car, such as photos, videos, features, specifications, history reports, seller comments, and contact details.</li>
-<li>If you like the car, you can contact the seller via message or phone call. You can also save the car to your favourites or compare it with other cars.</li>
-<li>If you want to buy the car, you can arrange a test drive, inspection, payment, and delivery with the seller.</li>
-</ol>
- <h3>For sellers</h3>
- <p>If you want to sell your car quickly and easily, here are some steps to follow:</p>
- <ol>
- <li>Open the app and tap on the "Sell" tab at the bottom of the screen.</li>
- <li>Select the type of ad you want (free or premium) and enter your car details (make, model, year, kilometres, etc.).</li>
- <li>Take photos of your car using the Snap n' Sell feature or upload them from your gallery.</li>
- <li>Add a description of your car and set a price. You can use the valuation tool to get an estimate of your car's value.</li>
- <li>Publish your ad and wait for buyers to contact you via message or phone call. </li>
-<li>Edit your ad or see live stats of your car's performance. You can also access your seller toolkit for tips, guides, and tools to help you sell your car faster and for more money.</li>
-<li>If you find a buyer, you can arrange a test drive, inspection, payment, and delivery with them.</li>
-</ol>
- <h2>Carsales App Reviews</h2>
-<p>Carsales app has received many positive reviews from users who have downloaded and used it. Here are some of them:</p>
-<h3>What users are saying about the app</h3>
-<p>Here are some of the comments and ratings from users who have reviewed the app on the App Store and Google Play Store:</p>
-<ul>
-<li>"Best car app ever. Easy to use, lots of options, great features. Highly recommend it to anyone looking for a car or selling a car." - 5 stars</li>
-<li>"I love this app. It has everything you need to buy or sell a car. It's fast, reliable, and user-friendly. I sold my car in less than a week using this app." - 5 stars</li>
-<li>"This app is amazing. It has so many cars to choose from and you can filter your search by anything you want. It also has news and reviews on different cars and a valuation tool that tells you how much your car is worth." - 5 stars</li>
-<li>"This app is very helpful and convenient. It saves me a lot of time and hassle when looking for a car or selling my car. It also syncs with my account and I can access it from any device." - 4 stars</li>
-<li>"This app is good but it could be better. Sometimes it crashes or freezes and I have to restart it. Also, some of the ads are not updated or accurate. I hope they fix these issues soon." - 3 stars</li>
-</ul>
-<h3>How the app compares to other car apps</h3>
-<p>Carsales app is not the only car app available, but it is one of the best ones. Here are some of the reasons why carsales app is better than other car apps:</p>
-<ul>
-<li>It has more cars than any other car app in Australia, with over 150,000 new and used cars from private sellers, dealers, and certified pre-owned programs.</li>
-<li>It has more tools, features, and functionality than any other car app, such as multi-select, Snap n' Sell, valuation tool, news and reviews, seller toolkit, live stats, and more.</li>
-<li>It connects you with Australia's largest online automotive marketplace, where you can find the best deals and offers for buying or selling cars.</li>
-<li>It has a high rating and positive feedback from users who have downloaded and used it.</li>
-</ul>
- <h2>Conclusion</h2>
-<p>Carsales app is the ultimate guide for car buyers and sellers in Australia. It is a free mobile app that allows you to search, buy, sell, and research cars on the go. It has more cars, tools, features, and functionality than any other car app. It also connects you with Australia's largest online automotive marketplace.</p>
-<p>If you are looking for a car or want to sell your car, you should download carsales app today. You will not regret it. You will save time, money, and hassle when buying or selling cars. You will also enjoy the convenience and ease of using the app.</p>
-<p>So what are you waiting for? Download carsales app now and find your dream car or sell your car fast!</p>
- <h2>Frequently Asked Questions</h2>
- <p>Here are some of the frequently asked questions about carsales app:</p>
- <ol>
- <li><b>Is carsales app free?</b></li>
- <p>Yes, carsales app is free to download and use. However, some features may require a premium subscription or payment.</p>
- <li><b>Is carsales app safe?</b></li>
- <p>Yes, carsales app is safe to use. It uses encryption and security measures to protect your personal information and transactions. However, you should always be careful when dealing with strangers online and follow the safety tips provided by the app.</p>
- <li><b>Is carsales app available in other countries?</b></li>
- <p>No, carsales app is only available in Australia. However, you can use the website version of carsales.com.au in other countries.</p>
- <li><b>How do I contact carsales app support?</b></li>
- <p>If you have any questions or issues with the app, you can contact carsales app support via email at support@carsales.com.au or via phone at 13 72 53.</p>
- <li><b>How do I update carsales app?</b></li>
- <p <p>To update carsales app, you can follow these steps:</p>
-<ol>
-<li>Open the App Store or Google Play Store on your device.</li>
-<li>Search for "carsales" in the search bar.</li>
-<li>Tap on the "UPDATE" button next to the carsales app icon.</li>
-<li>Wait for the app to download and install the latest version on your device.</li>
-<li>Open the app and enjoy the new features and improvements.</li>
-</ol></p> 401be4b1e0<br />
-<br />
-<br />
\ No newline at end of file
diff --git "a/spaces/fb700/chatglm-fitness-RLHF/crazy_functions/\350\260\267\346\255\214\346\243\200\347\264\242\345\260\217\345\212\251\346\211\213.py" "b/spaces/fb700/chatglm-fitness-RLHF/crazy_functions/\350\260\267\346\255\214\346\243\200\347\264\242\345\260\217\345\212\251\346\211\213.py"
deleted file mode 100644
index 5a5dd93f6f9ca8c47c0de193b95e863e9bb82087..0000000000000000000000000000000000000000
--- "a/spaces/fb700/chatglm-fitness-RLHF/crazy_functions/\350\260\267\346\255\214\346\243\200\347\264\242\345\260\217\345\212\251\346\211\213.py"
+++ /dev/null
@@ -1,112 +0,0 @@
-from .crazy_utils import request_gpt_model_in_new_thread_with_ui_alive
-from toolbox import CatchException, report_execption, write_results_to_file
-from toolbox import update_ui
-
-def get_meta_information(url, chatbot, history):
-    import requests
-    import arxiv
-    import difflib
-    from bs4 import BeautifulSoup
-    from toolbox import get_conf
-    proxies, = get_conf('proxies')
-    headers = {
-        'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/105.0.0.0 Safari/537.36',
-    }
-    # 发送 GET 请求
-    response = requests.get(url, proxies=proxies, headers=headers)
-
-    # 解析网页内容
-    soup = BeautifulSoup(response.text, "html.parser")
-
-    def string_similar(s1, s2):
-        return difflib.SequenceMatcher(None, s1, s2).quick_ratio()
-
-    profile = []
-    # 获取所有文章的标题和作者
-    for result in soup.select(".gs_ri"):
-        title = result.a.text.replace('\n', ' ').replace('  ', ' ')
-        author = result.select_one(".gs_a").text
-        try:
-            citation = result.select_one(".gs_fl > a[href*='cites']").text  # 引用次数是链接中的文本，直接取出来
-        except:
-            citation = 'cited by 0'
-        abstract = result.select_one(".gs_rs").text.strip()  # 摘要在 .gs_rs 中的文本，需要清除首尾空格
-        search = arxiv.Search(
-            query = title,
-            max_results = 1,
-            sort_by = arxiv.SortCriterion.Relevance,
-        )
-        try:
-            paper = next(search.results())
-            if string_similar(title, paper.title) > 0.90: # same paper
-                abstract = paper.summary.replace('\n', ' ')
-                is_paper_in_arxiv = True
-            else:   # different paper
-                abstract = abstract
-                is_paper_in_arxiv = False
-            paper = next(search.results())
-        except:
-            abstract = abstract
-            is_paper_in_arxiv = False
-        print(title)
-        print(author)
-        print(citation)
-        profile.append({
-            'title':title,
-            'author':author,
-            'citation':citation,
-            'abstract':abstract,
-            'is_paper_in_arxiv':is_paper_in_arxiv,
-        })
-
-        chatbot[-1] = [chatbot[-1][0], title + f'\n\n是否在arxiv中（不在arxiv中无法获取完整摘要）:{is_paper_in_arxiv}\n\n' + abstract]
-        yield from update_ui(chatbot=chatbot, history=[]) # 刷新界面
-    return profile
-
-@CatchException
-def 谷歌检索小助手(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, web_port):
-    # 基本信息：功能、贡献者
-    chatbot.append([
-        "函数插件功能？",
-        "分析用户提供的谷歌学术（google scholar）搜索页面中，出现的所有文章: binary-husky，插件初始化中..."])
-    yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
-
-    # 尝试导入依赖，如果缺少依赖，则给出安装建议
-    try:
-        import arxiv
-        import math
-        from bs4 import BeautifulSoup
-    except:
-        report_execption(chatbot, history, 
-            a = f"解析项目: {txt}", 
-            b = f"导入软件依赖失败。使用该模块需要额外依赖，安装方法```pip install --upgrade beautifulsoup4 arxiv```。")
-        yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
-        return
-
-    # 清空历史，以免输入溢出
-    history = []
-    meta_paper_info_list = yield from get_meta_information(txt, chatbot, history)
-    batchsize = 5
-    for batch in range(math.ceil(len(meta_paper_info_list)/batchsize)):
-        if len(meta_paper_info_list[:batchsize]) > 0:
-            i_say = "下面是一些学术文献的数据，提取出以下内容：" + \
-            "1、英文题目；2、中文题目翻译；3、作者；4、arxiv公开（is_paper_in_arxiv）；4、引用数量（cite）；5、中文摘要翻译。" + \
-            f"以下是信息源：{str(meta_paper_info_list[:batchsize])}" 
-
-            inputs_show_user = f"请分析此页面中出现的所有文章：{txt}，这是第{batch+1}批"
-            gpt_say = yield from request_gpt_model_in_new_thread_with_ui_alive(
-                inputs=i_say, inputs_show_user=inputs_show_user,
-                llm_kwargs=llm_kwargs, chatbot=chatbot, history=[],
-                sys_prompt="你是一个学术翻译，请从数据中提取信息。你必须使用Markdown表格。你必须逐个文献进行处理。"
-            )
-
-            history.extend([ f"第{batch+1}批", gpt_say ])
-            meta_paper_info_list = meta_paper_info_list[batchsize:]
-
-    chatbot.append(["状态？", 
-        "已经全部完成，您可以试试让AI写一个Related Works，例如您可以继续输入Write an academic \"Related Works\" section about \"你搜索的研究领域\" for me."])
-    msg = '正常'
-    yield from update_ui(chatbot=chatbot, history=history, msg=msg) # 刷新界面
-    res = write_results_to_file(history)
-    chatbot.append(("完成了吗？", res)); 
-    yield from update_ui(chatbot=chatbot, history=history, msg=msg) # 刷新界面
diff --git a/spaces/fb700/chatglm-fitness-RLHF/docs/self_analysis.md b/spaces/fb700/chatglm-fitness-RLHF/docs/self_analysis.md
deleted file mode 100644
index ebc2337194974bf210794df7d858889010fecf08..0000000000000000000000000000000000000000
--- a/spaces/fb700/chatglm-fitness-RLHF/docs/self_analysis.md
+++ /dev/null
@@ -1,378 +0,0 @@
-# chatgpt-academic项目自译解报告
-（Author补充：以下分析均由本项目调用ChatGPT一键生成，如果有不准确的地方，全怪GPT😄）
-
-
-| 文件名 | 功能描述 |
-| ------ | ------ |
-| check_proxy.py | 检查代理有效性及地理位置 |
-| colorful.py | 控制台打印彩色文字 |
-| config.py | 配置和参数设置 |
-| config_private.py | 私人配置和参数设置 |
-| core_functional.py | 核心函数和参数设置 |
-| crazy_functional.py | 高级功能插件集合 |
-| main.py | 一个 Chatbot 程序，提供各种学术翻译、文本处理和其他查询服务 |
-| multi_language.py | 识别和翻译不同语言 |
-| theme.py | 自定义 gradio 应用程序主题 |
-| toolbox.py | 工具类库，用于协助实现各种功能 |
-| crazy_functions\crazy_functions_test.py | 测试 crazy_functions 中的各种函数 |
-| crazy_functions\crazy_utils.py | 工具函数，用于字符串处理、异常检测、Markdown 格式转换等 |
-| crazy_functions\Latex全文润色.py | 对整个 Latex 项目进行润色和纠错 |
-| crazy_functions\Latex全文翻译.py | 对整个 Latex 项目进行翻译 |
-| crazy_functions\\_\_init\_\_.py | 模块初始化文件，标识 `crazy_functions` 是一个包 |
-| crazy_functions\下载arxiv论文翻译摘要.py | 下载 `arxiv` 论文的 PDF 文件，并提取摘要和翻译 |
-| crazy_functions\代码重写为全英文_多线程.py | 将Python源代码文件中的中文内容转化为英文 |
-| crazy_functions\图片生成.py | 根据激励文本使用GPT模型生成相应的图像 |
-| crazy_functions\对话历史存档.py | 将每次对话记录写入Markdown格式的文件中 |
-| crazy_functions\总结word文档.py | 对输入的word文档进行摘要生成 |
-| crazy_functions\总结音视频.py | 对输入的音视频文件进行摘要生成 |
-| crazy_functions\批量Markdown翻译.py | 将指定目录下的Markdown文件进行中英文翻译 |
-| crazy_functions\批量总结PDF文档.py | 对PDF文件进行切割和摘要生成 |
-| crazy_functions\批量总结PDF文档pdfminer.py | 对PDF文件进行文本内容的提取和摘要生成 |
-| crazy_functions\批量翻译PDF文档_多线程.py | 将指定目录下的PDF文件进行中英文翻译 |
-| crazy_functions\理解PDF文档内容.py | 对PDF文件进行摘要生成和问题解答 |
-| crazy_functions\生成函数注释.py | 自动生成Python函数的注释 |
-| crazy_functions\联网的ChatGPT.py | 使用网络爬虫和ChatGPT模型进行聊天回答 |
-| crazy_functions\解析JupyterNotebook.py | 对Jupyter Notebook进行代码解析 |
-| crazy_functions\解析项目源代码.py | 对指定编程语言的源代码进行解析 |
-| crazy_functions\询问多个大语言模型.py | 使用多个大语言模型对输入进行处理和回复 |
-| crazy_functions\读文章写摘要.py | 对论文进行解析和全文摘要生成 |
-| crazy_functions\谷歌检索小助手.py | 提供谷歌学术搜索页面中相关文章的元数据信息。 |
-| crazy_functions\高级功能函数模板.py | 使用Unsplash API发送相关图片以回复用户的输入。 |
-| request_llm\bridge_all.py | 基于不同LLM模型进行对话。 |
-| request_llm\bridge_chatglm.py | 使用ChatGLM模型生成回复，支持单线程和多线程方式。 |
-| request_llm\bridge_chatgpt.py | 基于GPT模型完成对话。 |
-| request_llm\bridge_jittorllms_llama.py | 使用JittorLLMs模型完成对话，支持单线程和多线程方式。 |
-| request_llm\bridge_jittorllms_pangualpha.py | 使用JittorLLMs模型完成对话，基于多进程和多线程方式。 |
-| request_llm\bridge_jittorllms_rwkv.py | 使用JittorLLMs模型完成聊天功能，提供包括历史信息、参数调节等在内的多个功能选项。 |
-| request_llm\bridge_moss.py | 加载Moss模型完成对话功能。 |
-| request_llm\bridge_newbing.py | 使用Newbing聊天机器人进行对话，支持单线程和多线程方式。 |
-| request_llm\bridge_newbingfree.py | 基于Bing chatbot API实现聊天机器人的文本生成功能。 |
-| request_llm\bridge_stackclaude.py | 基于Slack API实现Claude与用户的交互。 |
-| request_llm\bridge_tgui.py | 通过websocket实现聊天机器人与UI界面交互。 |
-| request_llm\edge_gpt.py | 调用Bing chatbot API提供聊天机器人服务。 |
-| request_llm\edge_gpt_free.py | 实现聊天机器人API，采用aiohttp和httpx工具库。 |
-| request_llm\test_llms.py | 对llm模型进行单元测试。 |
-
-## 接下来请你逐文件分析下面的工程[0/48] 请对下面的程序文件做一个概述: check_proxy.py
-
-这个文件主要包含了五个函数：
-
-1. `check_proxy`：用于检查代理的有效性及地理位置，输出代理配置和所在地信息。
-
-2. `backup_and_download`：用于备份当前版本并下载新版本。
-
-3. `patch_and_restart`：用于覆盖更新当前版本并重新启动程序。
-
-4. `get_current_version`：用于获取当前程序的版本号。
-
-5. `auto_update`：用于自动检查新版本并提示用户更新。如果用户选择更新，则备份并下载新版本，覆盖更新当前版本并重新启动程序。如果更新失败，则输出错误信息，并不会向用户进行任何提示。
-
-还有一个没有函数名的语句`os.environ['no_proxy'] = '*'`，用于设置环境变量，避免代理网络产生意外污染。
-
-此外，该文件导入了以下三个模块/函数：
-
-- `requests`
-- `shutil`
-- `os`
-
-## [1/48] 请对下面的程序文件做一个概述: colorful.py
-
-该文件是一个Python脚本，用于在控制台中打印彩色文字。该文件包含了一些函数，用于以不同颜色打印文本。其中，红色、绿色、黄色、蓝色、紫色、靛色分别以函数 print红、print绿、print黄、print蓝、print紫、print靛 的形式定义；亮红色、亮绿色、亮黄色、亮蓝色、亮紫色、亮靛色分别以 print亮红、print亮绿、print亮黄、print亮蓝、print亮紫、print亮靛 的形式定义。它们使用 ANSI Escape Code 将彩色输出从控制台突出显示。如果运行在 Linux 操作系统上，文件所执行的操作被留空；否则，该文件导入了 colorama 库并调用 init() 函数进行初始化。最后，通过一系列条件语句，该文件通过将所有彩色输出函数的名称重新赋值为 print 函数的名称来避免输出文件的颜色问题。
-
-## [2/48] 请对下面的程序文件做一个概述: config.py
-
-这个程序文件是用来配置和参数设置的。它包含了许多设置，如API key，使用代理，线程数，默认模型，超时时间等等。此外，它还包含了一些高级功能，如URL重定向等。这些设置将会影响到程序的行为和性能。
-
-## [3/48] 请对下面的程序文件做一个概述: config_private.py
-
-这个程序文件是一个Python脚本，文件名为config_private.py。其中包含以下变量的赋值：
-
-1. API_KEY：API密钥。
-2. USE_PROXY：是否应用代理。
-3. proxies：如果使用代理，则设置代理网络的协议(socks5/http)、地址(localhost)和端口(11284)。
-4. DEFAULT_WORKER_NUM：默认的工作线程数量。
-5. SLACK_CLAUDE_BOT_ID：Slack机器人ID。
-6. SLACK_CLAUDE_USER_TOKEN：Slack用户令牌。
-
-## [4/48] 请对下面的程序文件做一个概述: core_functional.py
-
-这是一个名为core_functional.py的源代码文件，该文件定义了一个名为get_core_functions()的函数，该函数返回一个字典，该字典包含了各种学术翻译润色任务的说明和相关参数，如颜色、前缀、后缀等。这些任务包括英语学术润色、中文学术润色、查找语法错误、中译英、学术中英互译、英译中、找图片和参考文献转Bib。其中，一些任务还定义了预处理函数用于处理任务的输入文本。
-
-## [5/48] 请对下面的程序文件做一个概述: crazy_functional.py
-
-此程序文件（crazy_functional.py）是一个函数插件集合，包含了多个函数插件的定义和调用。这些函数插件旨在提供一些高级功能，如解析项目源代码、批量翻译PDF文档和Latex全文润色等。其中一些插件还支持热更新功能，不需要重启程序即可生效。文件中的函数插件按照功能进行了分类（第一组和第二组），并且有不同的调用方式（作为按钮或下拉菜单）。
-
-## [6/48] 请对下面的程序文件做一个概述: main.py
-
-这是一个Python程序文件，文件名为main.py。该程序包含一个名为main的函数，程序会自动运行该函数。程序要求已经安装了gradio、os等模块，会根据配置文件加载代理、model、API Key等信息。程序提供了Chatbot功能，实现了一个对话界面，用户可以输入问题，然后Chatbot可以回答问题或者提供相关功能。程序还包含了基础功能区、函数插件区、更换模型 & SysPrompt & 交互界面布局、备选输入区，用户可以在这些区域选择功能和插件进行使用。程序中还包含了一些辅助模块，如logging等。
-
-## [7/48] 请对下面的程序文件做一个概述: multi_language.py
-
-该文件multi_language.py是用于将项目翻译成不同语言的程序。它包含了以下函数和变量：lru_file_cache、contains_chinese、split_list、map_to_json、read_map_from_json、advanced_split、trans、trans_json、step_1_core_key_translate、CACHE_FOLDER、blacklist、LANG、TransPrompt、cached_translation等。注释和文档字符串提供了有关程序的说明，例如如何使用该程序，如何修改“LANG”和“TransPrompt”变量等。
-
-## [8/48] 请对下面的程序文件做一个概述: theme.py
-
-这是一个Python源代码文件，文件名为theme.py。此文件中定义了一个函数adjust_theme，其功能是自定义gradio应用程序的主题，包括调整颜色、字体、阴影等。如果允许，则添加一个看板娘。此文件还包括变量advanced_css，其中包含一些CSS样式，用于高亮显示代码和自定义聊天框样式。此文件还导入了get_conf函数和gradio库。
-
-## [9/48] 请对下面的程序文件做一个概述: toolbox.py
-
-toolbox.py是一个工具类库，其中主要包含了一些函数装饰器和小工具函数，用于协助实现聊天机器人所需的各种功能，包括文本处理、功能插件加载、异常检测、Markdown格式转换，文件读写等等。此外，该库还包含一些依赖、参数配置等信息。该库易于理解和维护。
-
-## [10/48] 请对下面的程序文件做一个概述: crazy_functions\crazy_functions_test.py
-
-这个文件是一个Python测试模块，用于测试crazy_functions中的各种函数插件。这些函数包括：解析Python项目源代码、解析Cpp项目源代码、Latex全文润色、Markdown中译英、批量翻译PDF文档、谷歌检索小助手、总结word文档、下载arxiv论文并翻译摘要、联网回答问题、和解析Jupyter Notebooks。对于每个函数插件，都有一个对应的测试函数来进行测试。
-
-## [11/48] 请对下面的程序文件做一个概述: crazy_functions\crazy_utils.py
-
-这个Python文件中包括了两个函数：
-
-1. `input_clipping`: 该函数用于裁剪输入文本长度，使其不超过一定的限制。
-2. `request_gpt_model_in_new_thread_with_ui_alive`: 该函数用于请求 GPT 模型并保持用户界面的响应，支持多线程和实时更新用户界面。
-
-这两个函数都依赖于从 `toolbox` 和 `request_llm` 中导入的一些工具函数。函数的输入和输出有详细的描述文档。
-
-## [12/48] 请对下面的程序文件做一个概述: crazy_functions\Latex全文润色.py
-
-这是一个Python程序文件，文件名为crazy_functions\Latex全文润色.py。文件包含了一个PaperFileGroup类和三个函数Latex英文润色，Latex中文润色和Latex英文纠错。程序使用了字符串处理、正则表达式、文件读写、多线程等技术，主要作用是对整个Latex项目进行润色和纠错。其中润色和纠错涉及到了对文本的语法、清晰度和整体可读性等方面的提升。此外，该程序还参考了第三方库，并封装了一些工具函数。
-
-## [13/48] 请对下面的程序文件做一个概述: crazy_functions\Latex全文翻译.py
-
-这个文件包含两个函数 `Latex英译中` 和 `Latex中译英`，它们都会对整个Latex项目进行翻译。这个文件还包含一个类 `PaperFileGroup`，它拥有一个方法 `run_file_split`，用于把长文本文件分成多个短文件。其中使用了工具库 `toolbox` 中的一些函数和从 `request_llm` 中导入了 `model_info`。接下来的函数把文件读取进来，把它们的注释删除，进行分割，并进行翻译。这个文件还包括了一些异常处理和界面更新的操作。
-
-## [14/48] 请对下面的程序文件做一个概述: crazy_functions\__init__.py
-
-这是一个Python模块的初始化文件（__init__.py），命名为"crazy_functions"。该模块包含了一些疯狂的函数，但该文件并没有实现这些函数，而是作为一个包（package）来导入其它的Python模块以实现这些函数。在该文件中，没有定义任何类或函数，它唯一的作用就是标识"crazy_functions"模块是一个包。
-
-## [15/48] 请对下面的程序文件做一个概述: crazy_functions\下载arxiv论文翻译摘要.py
-
-这是一个 Python 程序文件，文件名为 `下载arxiv论文翻译摘要.py`。程序包含多个函数，其中 `下载arxiv论文并翻译摘要` 函数的作用是下载 `arxiv` 论文的 PDF 文件，提取摘要并使用 GPT 对其进行翻译。其他函数包括用于下载 `arxiv` 论文的 `download_arxiv_` 函数和用于获取文章信息的 `get_name` 函数，其中涉及使用第三方库如 requests, BeautifulSoup 等。该文件还包含一些用于调试和存储文件的代码段。
-
-## [16/48] 请对下面的程序文件做一个概述: crazy_functions\代码重写为全英文_多线程.py
-
-该程序文件是一个多线程程序，主要功能是将指定目录下的所有Python代码文件中的中文内容转化为英文，并将转化后的代码存储到一个新的文件中。其中，程序使用了GPT-3等技术进行中文-英文的转化，同时也进行了一些Token限制下的处理，以防止程序发生错误。程序在执行过程中还会输出一些提示信息，并将所有转化过的代码文件存储到指定目录下。在程序执行结束后，还会生成一个任务执行报告，记录程序运行的详细信息。
-
-## [17/48] 请对下面的程序文件做一个概述: crazy_functions\图片生成.py
-
-该程序文件提供了一个用于生成图像的函数`图片生成`。函数实现的过程中，会调用`gen_image`函数来生成图像，并返回图像生成的网址和本地文件地址。函数有多个参数，包括`prompt`(激励文本)、`llm_kwargs`(GPT模型的参数)、`plugin_kwargs`(插件模型的参数)等。函数核心代码使用了`requests`库向OpenAI API请求图像，并做了简单的处理和保存。函数还更新了交互界面，清空聊天历史并显示正在生成图像的消息和最终的图像网址和预览。
-
-## [18/48] 请对下面的程序文件做一个概述: crazy_functions\对话历史存档.py
-
-这个文件是名为crazy_functions\对话历史存档.py的Python程序文件，包含了4个函数：
-
-1. write_chat_to_file(chatbot, history=None, file_name=None)：用来将对话记录以Markdown格式写入文件中，并且生成文件名，如果没指定文件名则用当前时间。写入完成后将文件路径打印出来。
-
-2. gen_file_preview(file_name)：从传入的文件中读取内容，解析出对话历史记录并返回前100个字符，用于文件预览。
-
-3. read_file_to_chat(chatbot, history, file_name)：从传入的文件中读取内容，解析出对话历史记录并更新聊天显示框。
-
-4. 对话历史存档(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, web_port)：一个主要函数，用于保存当前对话记录并提醒用户。如果用户希望加载历史记录，则调用read_file_to_chat()来更新聊天显示框。如果用户希望删除历史记录，调用删除所有本地对话历史记录()函数完成删除操作。
-
-## [19/48] 请对下面的程序文件做一个概述: crazy_functions\总结word文档.py
-
-该程序文件实现了一个总结Word文档的功能，使用Python的docx库读取docx格式的文件，使用pywin32库读取doc格式的文件。程序会先根据传入的txt参数搜索需要处理的文件，并逐个解析其中的内容，将内容拆分为指定长度的文章片段，然后使用另一个程序文件中的request_gpt_model_in_new_thread_with_ui_alive函数进行中文概述。最后将所有的总结结果写入一个文件中，并在界面上进行展示。
-
-## [20/48] 请对下面的程序文件做一个概述: crazy_functions\总结音视频.py
-
-该程序文件包括两个函数：split_audio_file()和AnalyAudio()，并且导入了一些必要的库并定义了一些工具函数。split_audio_file用于将音频文件分割成多个时长相等的片段，返回一个包含所有切割音频片段文件路径的列表，而AnalyAudio用来分析音频文件，通过调用whisper模型进行音频转文字并使用GPT模型对音频内容进行概述，最终将所有总结结果写入结果文件中。
-
-## [21/48] 请对下面的程序文件做一个概述: crazy_functions\批量Markdown翻译.py
-
-该程序文件名为`批量Markdown翻译.py`，包含了以下功能：读取Markdown文件，将长文本分离开来，将Markdown文件进行翻译（英译中和中译英），整理结果并退出。程序使用了多线程以提高效率。程序使用了`tiktoken`依赖库，可能需要额外安装。文件中还有一些其他的函数和类，但与文件名所描述的功能无关。
-
-## [22/48] 请对下面的程序文件做一个概述: crazy_functions\批量总结PDF文档.py
-
-该文件是一个Python脚本，名为crazy_functions\批量总结PDF文档.py。在导入了一系列库和工具函数后，主要定义了5个函数，其中包括一个错误处理装饰器（@CatchException），用于批量总结PDF文档。该函数主要实现对PDF文档的解析，并调用模型生成中英文摘要。
-
-## [23/48] 请对下面的程序文件做一个概述: crazy_functions\批量总结PDF文档pdfminer.py
-
-该程序文件是一个用于批量总结PDF文档的函数插件，使用了pdfminer插件和BeautifulSoup库来提取PDF文档的文本内容，对每个PDF文件分别进行处理并生成中英文摘要。同时，该程序文件还包括一些辅助工具函数和处理异常的装饰器。
-
-## [24/48] 请对下面的程序文件做一个概述: crazy_functions\批量翻译PDF文档_多线程.py
-
-这个程序文件是一个Python脚本，文件名为“批量翻译PDF文档_多线程.py”。它主要使用了“toolbox”、“request_gpt_model_in_new_thread_with_ui_alive”、“request_gpt_model_multi_threads_with_very_awesome_ui_and_high_efficiency”、“colorful”等Python库和自定义的模块“crazy_utils”的一些函数。程序实现了一个批量翻译PDF文档的功能，可以自动解析PDF文件中的基础信息，递归地切割PDF文件，翻译和处理PDF论文中的所有内容，并生成相应的翻译结果文件（包括md文件和html文件）。功能比较复杂，其中需要调用多个函数和依赖库，涉及到多线程操作和UI更新。文件中有详细的注释和变量命名，代码比较清晰易读。
-
-## [25/48] 请对下面的程序文件做一个概述: crazy_functions\理解PDF文档内容.py
-
-该程序文件实现了一个名为“理解PDF文档内容”的函数，该函数可以为输入的PDF文件提取摘要以及正文各部分的主要内容，并在提取过程中根据上下文关系进行学术性问题解答。该函数依赖于多个辅助函数和第三方库，并在执行过程中针对可能出现的异常进行了处理。
-
-## [26/48] 请对下面的程序文件做一个概述: crazy_functions\生成函数注释.py
-
-该程序文件是一个Python模块文件，文件名为“生成函数注释.py”，定义了两个函数：一个是生成函数注释的主函数“生成函数注释”，另一个是通过装饰器实现异常捕捉的函数“批量生成函数注释”。该程序文件依赖于“toolbox”和本地“crazy_utils”模块，并且在运行时使用了多线程技术和GPT模型来生成注释。函数生成的注释结果使用Markdown表格输出并写入历史记录文件。
-
-## [27/48] 请对下面的程序文件做一个概述: crazy_functions\联网的ChatGPT.py
-
-这是一个名为`联网的ChatGPT.py`的Python程序文件，其中定义了一个函数`连接网络回答问题`。该函数通过爬取搜索引擎的结果和访问网页来综合回答给定的问题，并使用ChatGPT模型完成回答。此外，该文件还包括一些工具函数，例如从网页中抓取文本和使用代理访问网页。
-
-## [28/48] 请对下面的程序文件做一个概述: crazy_functions\解析JupyterNotebook.py
-
-这个程序文件包含了两个函数： `parseNotebook()`和`解析ipynb文件()`，并且引入了一些工具函数和类。`parseNotebook()`函数将Jupyter Notebook文件解析为文本代码块，`解析ipynb文件()`函数则用于解析多个Jupyter Notebook文件，使用`parseNotebook()`解析每个文件和一些其他的处理。函数中使用了多线程处理输入和输出，并且将结果写入到文件中。
-
-## [29/48] 请对下面的程序文件做一个概述: crazy_functions\解析项目源代码.py
-
-这是一个源代码分析的Python代码文件，其中定义了多个函数，包括解析一个Python项目、解析一个C项目、解析一个C项目的头文件和解析一个Java项目等。其中解析源代码新函数是实际处理源代码分析并生成报告的函数。该函数首先会逐个读取传入的源代码文件，生成对应的请求内容，通过多线程发送到chatgpt进行分析。然后将结果写入文件，并进行汇总分析。最后通过调用update_ui函数刷新界面，完整实现了源代码的分析。
-
-## [30/48] 请对下面的程序文件做一个概述: crazy_functions\询问多个大语言模型.py
-
-该程序文件包含两个函数：同时问询()和同时问询_指定模型()，它们的作用是使用多个大语言模型同时对用户输入进行处理，返回对应模型的回复结果。同时问询()会默认使用ChatGPT和ChatGLM两个模型，而同时问询_指定模型()则可以指定要使用的模型。该程序文件还引用了其他的模块和函数库。
-
-## [31/48] 请对下面的程序文件做一个概述: crazy_functions\读文章写摘要.py
-
-这个程序文件是一个Python模块，文件名为crazy_functions\读文章写摘要.py。该模块包含了两个函数，其中主要函数是"读文章写摘要"函数，其实现了解析给定文件夹中的tex文件，对其中每个文件的内容进行摘要生成，并根据各论文片段的摘要，最终生成全文摘要。第二个函数是"解析Paper"函数，用于解析单篇论文文件。其中用到了一些工具函数和库，如update_ui、CatchException、report_execption、write_results_to_file等。
-
-## [32/48] 请对下面的程序文件做一个概述: crazy_functions\谷歌检索小助手.py
-
-该文件是一个Python模块，文件名为“谷歌检索小助手.py”。该模块包含两个函数，一个是“get_meta_information()”，用于从提供的网址中分析出所有相关的学术文献的元数据信息；另一个是“谷歌检索小助手()”，是主函数，用于分析用户提供的谷歌学术搜索页面中出现的文章，并提取相关信息。其中，“谷歌检索小助手()”函数依赖于“get_meta_information()”函数，并调用了其他一些Python模块，如“arxiv”、“math”、“bs4”等。
-
-## [33/48] 请对下面的程序文件做一个概述: crazy_functions\高级功能函数模板.py
-
-该程序文件定义了一个名为高阶功能模板函数的函数，该函数接受多个参数，包括输入的文本、gpt模型参数、插件模型参数、聊天显示框的句柄、聊天历史等，并利用送出请求，使用 Unsplash API 发送相关图片。其中，为了避免输入溢出，函数会在开始时清空历史。函数也有一些 UI 更新的语句。该程序文件还依赖于其他两个模块：CatchException 和 update_ui，以及一个名为 request_gpt_model_in_new_thread_with_ui_alive 的来自 crazy_utils 模块（应该是自定义的工具包）的函数。
-
-## [34/48] 请对下面的程序文件做一个概述: request_llm\bridge_all.py
-
-该文件包含两个函数：predict和predict_no_ui_long_connection，用于基于不同的LLM模型进行对话。该文件还包含一个lazyloadTiktoken类和一个LLM_CATCH_EXCEPTION修饰器函数。其中lazyloadTiktoken类用于懒加载模型的tokenizer，LLM_CATCH_EXCEPTION用于错误处理。整个文件还定义了一些全局变量和模型信息字典，用于引用和配置LLM模型。
-
-## [35/48] 请对下面的程序文件做一个概述: request_llm\bridge_chatglm.py
-
-这是一个Python程序文件，名为`bridge_chatglm.py`，其中定义了一个名为`GetGLMHandle`的类和三个方法：`predict_no_ui_long_connection`、 `predict`和 `stream_chat`。该文件依赖于多个Python库，如`transformers`和`sentencepiece`。该文件实现了一个聊天机器人，使用ChatGLM模型来生成回复，支持单线程和多线程方式。程序启动时需要加载ChatGLM的模型和tokenizer，需要一段时间。在配置文件`config.py`中设置参数会影响模型的内存和显存使用，因此程序可能会导致低配计算机卡死。
-
-## [36/48] 请对下面的程序文件做一个概述: request_llm\bridge_chatgpt.py
-
-该文件为 Python 代码文件，文件名为 request_llm\bridge_chatgpt.py。该代码文件主要提供三个函数：predict、predict_no_ui和 predict_no_ui_long_connection，用于发送至 chatGPT 并等待回复，获取输出。该代码文件还包含一些辅助函数，用于处理连接异常、生成 HTTP 请求等。该文件的代码架构清晰，使用了多个自定义函数和模块。
-
-## [37/48] 请对下面的程序文件做一个概述: request_llm\bridge_jittorllms_llama.py
-
-该代码文件实现了一个聊天机器人，其中使用了 JittorLLMs 模型。主要包括以下几个部分：
-1. GetGLMHandle 类：一个进程类，用于加载 JittorLLMs 模型并接收并处理请求。
-2. predict_no_ui_long_connection 函数：一个多线程方法，用于在后台运行聊天机器人。
-3. predict 函数：一个单线程方法，用于在前端页面上交互式调用聊天机器人，以获取用户输入并返回相应的回复。
-
-这个文件中还有一些辅助函数和全局变量，例如 importlib、time、threading 等。
-
-## [38/48] 请对下面的程序文件做一个概述: request_llm\bridge_jittorllms_pangualpha.py
-
-这个文件是为了实现使用jittorllms（一种机器学习模型）来进行聊天功能的代码。其中包括了模型加载、模型的参数加载、消息的收发等相关操作。其中使用了多进程和多线程来提高性能和效率。代码中还包括了处理依赖关系的函数和预处理函数等。
-
-## [39/48] 请对下面的程序文件做一个概述: request_llm\bridge_jittorllms_rwkv.py
-
-这个文件是一个Python程序，文件名为request_llm\bridge_jittorllms_rwkv.py。它依赖transformers、time、threading、importlib、multiprocessing等库。在文件中，通过定义GetGLMHandle类加载jittorllms模型参数和定义stream_chat方法来实现与jittorllms模型的交互。同时，该文件还定义了predict_no_ui_long_connection和predict方法来处理历史信息、调用jittorllms模型、接收回复信息并输出结果。
-
-## [40/48] 请对下面的程序文件做一个概述: request_llm\bridge_moss.py
-
-该文件为一个Python源代码文件，文件名为 request_llm\bridge_moss.py。代码定义了一个 GetGLMHandle 类和两个函数 predict_no_ui_long_connection 和 predict。
-
-GetGLMHandle 类继承自Process类（多进程），主要功能是启动一个子进程并加载 MOSS 模型参数，通过 Pipe 进行主子进程的通信。该类还定义了 check_dependency、moss_init、run 和 stream_chat 等方法，其中 check_dependency 和 moss_init 是子进程的初始化方法，run 是子进程运行方法，stream_chat 实现了主进程和子进程的交互过程。
-
-函数 predict_no_ui_long_connection 是多线程方法，调用 GetGLMHandle 类加载 MOSS 参数后使用 stream_chat 实现主进程和子进程的交互过程。
-
-函数 predict 是单线程方法，通过调用 update_ui 将交互过程中 MOSS 的回复实时更新到UI（User Interface）中，并执行一个 named function（additional_fn）指定的函数对输入进行预处理。
-
-## [41/48] 请对下面的程序文件做一个概述: request_llm\bridge_newbing.py
-
-这是一个名为`bridge_newbing.py`的程序文件，包含三个部分：
-
-第一部分使用from语句导入了`edge_gpt`模块的`NewbingChatbot`类。
-
-第二部分定义了一个名为`NewBingHandle`的继承自进程类的子类，该类会检查依赖性并启动进程。同时，该部分还定义了一个名为`predict_no_ui_long_connection`的多线程方法和一个名为`predict`的单线程方法，用于与NewBing进行通信。
-
-第三部分定义了一个名为`newbing_handle`的全局变量，并导出了`predict_no_ui_long_connection`和`predict`这两个方法，以供其他程序可以调用。
-
-## [42/48] 请对下面的程序文件做一个概述: request_llm\bridge_newbingfree.py
-
-这个Python文件包含了三部分内容。第一部分是来自edge_gpt_free.py文件的聊天机器人程序。第二部分是子进程Worker，用于调用主体。第三部分提供了两个函数：predict_no_ui_long_connection和predict用于调用NewBing聊天机器人和返回响应。其中predict函数还提供了一些参数用于控制聊天机器人的回复和更新UI界面。
-
-## [43/48] 请对下面的程序文件做一个概述: request_llm\bridge_stackclaude.py
-
-这是一个Python源代码文件，文件名为request_llm\bridge_stackclaude.py。代码分为三个主要部分：
-
-第一部分定义了Slack API Client类，实现Slack消息的发送、接收、循环监听，用于与Slack API进行交互。
-
-第二部分定义了ClaudeHandle类，继承Process类，用于创建子进程Worker，调用主体，实现Claude与用户交互的功能。
-
-第三部分定义了predict_no_ui_long_connection和predict两个函数，主要用于通过调用ClaudeHandle对象的stream_chat方法来获取Claude的回复，并更新ui以显示相关信息。其中predict函数采用单线程方法，而predict_no_ui_long_connection函数使用多线程方法。
-
-## [44/48] 请对下面的程序文件做一个概述: request_llm\bridge_tgui.py
-
-该文件是一个Python代码文件，名为request_llm\bridge_tgui.py。它包含了一些函数用于与chatbot UI交互，并通过WebSocket协议与远程LLM模型通信完成文本生成任务，其中最重要的函数是predict()和predict_no_ui_long_connection()。这个程序还有其他的辅助函数，如random_hash()。整个代码文件在协作的基础上完成了一次修改。
-
-## [45/48] 请对下面的程序文件做一个概述: request_llm\edge_gpt.py
-
-该文件是一个用于调用Bing chatbot API的Python程序，它由多个类和辅助函数构成，可以根据给定的对话连接在对话中提出问题，使用websocket与远程服务通信。程序实现了一个聊天机器人，可以为用户提供人工智能聊天。
-
-## [46/48] 请对下面的程序文件做一个概述: request_llm\edge_gpt_free.py
-
-该代码文件为一个会话API，可通过Chathub发送消息以返回响应。其中使用了 aiohttp 和 httpx 库进行网络请求并发送。代码中包含了一些函数和常量，多数用于生成请求数据或是请求头信息等。同时该代码文件还包含了一个 Conversation 类，调用该类可实现对话交互。
-
-## [47/48] 请对下面的程序文件做一个概述: request_llm\test_llms.py
-
-这个文件是用于对llm模型进行单元测试的Python程序。程序导入一个名为"request_llm.bridge_newbingfree"的模块，然后三次使用该模块中的predict_no_ui_long_connection()函数进行预测，并输出结果。此外，还有一些注释掉的代码段，这些代码段也是关于模型预测的。
-
-## 用一张Markdown表格简要描述以下文件的功能：
-check_proxy.py, colorful.py, config.py, config_private.py, core_functional.py, crazy_functional.py, main.py, multi_language.py, theme.py, toolbox.py, crazy_functions\crazy_functions_test.py, crazy_functions\crazy_utils.py, crazy_functions\Latex全文润色.py, crazy_functions\Latex全文翻译.py, crazy_functions\__init__.py, crazy_functions\下载arxiv论文翻译摘要.py。根据以上分析，用一句话概括程序的整体功能。
-
-| 文件名 | 功能描述 |
-| ------ | ------ |
-| check_proxy.py | 检查代理有效性及地理位置 |
-| colorful.py | 控制台打印彩色文字 |
-| config.py | 配置和参数设置 |
-| config_private.py | 私人配置和参数设置 |
-| core_functional.py | 核心函数和参数设置 |
-| crazy_functional.py | 高级功能插件集合 |
-| main.py | 一个 Chatbot 程序，提供各种学术翻译、文本处理和其他查询服务 |
-| multi_language.py | 识别和翻译不同语言 |
-| theme.py | 自定义 gradio 应用程序主题 |
-| toolbox.py | 工具类库，用于协助实现各种功能 |
-| crazy_functions\crazy_functions_test.py | 测试 crazy_functions 中的各种函数 |
-| crazy_functions\crazy_utils.py | 工具函数，用于字符串处理、异常检测、Markdown 格式转换等 |
-| crazy_functions\Latex全文润色.py | 对整个 Latex 项目进行润色和纠错 |
-| crazy_functions\Latex全文翻译.py | 对整个 Latex 项目进行翻译 |
-| crazy_functions\__init__.py | 模块初始化文件，标识 `crazy_functions` 是一个包 |
-| crazy_functions\下载arxiv论文翻译摘要.py | 下载 `arxiv` 论文的 PDF 文件，并提取摘要和翻译 |
-
-这些程序源文件提供了基础的文本和语言处理功能、工具函数和高级插件，使 Chatbot 能够处理各种复杂的学术文本问题，包括润色、翻译、搜索、下载、解析等。
-
-## 用一张Markdown表格简要描述以下文件的功能：
-crazy_functions\代码重写为全英文_多线程.py, crazy_functions\图片生成.py, crazy_functions\对话历史存档.py, crazy_functions\总结word文档.py, crazy_functions\总结音视频.py, crazy_functions\批量Markdown翻译.py, crazy_functions\批量总结PDF文档.py, crazy_functions\批量总结PDF文档pdfminer.py, crazy_functions\批量翻译PDF文档_多线程.py, crazy_functions\理解PDF文档内容.py, crazy_functions\生成函数注释.py, crazy_functions\联网的ChatGPT.py, crazy_functions\解析JupyterNotebook.py, crazy_functions\解析项目源代码.py, crazy_functions\询问多个大语言模型.py, crazy_functions\读文章写摘要.py。根据以上分析，用一句话概括程序的整体功能。
-
-| 文件名 | 功能简述 |
-| --- | --- |
-| 代码重写为全英文_多线程.py | 将Python源代码文件中的中文内容转化为英文 |
-| 图片生成.py | 根据激励文本使用GPT模型生成相应的图像 |
-| 对话历史存档.py | 将每次对话记录写入Markdown格式的文件中 |
-| 总结word文档.py | 对输入的word文档进行摘要生成 |
-| 总结音视频.py | 对输入的音视频文件进行摘要生成 |
-| 批量Markdown翻译.py | 将指定目录下的Markdown文件进行中英文翻译 |
-| 批量总结PDF文档.py | 对PDF文件进行切割和摘要生成 |
-| 批量总结PDF文档pdfminer.py | 对PDF文件进行文本内容的提取和摘要生成 |
-| 批量翻译PDF文档_多线程.py | 将指定目录下的PDF文件进行中英文翻译 |
-| 理解PDF文档内容.py | 对PDF文件进行摘要生成和问题解答 |
-| 生成函数注释.py | 自动生成Python函数的注释 |
-| 联网的ChatGPT.py | 使用网络爬虫和ChatGPT模型进行聊天回答 |
-| 解析JupyterNotebook.py | 对Jupyter Notebook进行代码解析 |
-| 解析项目源代码.py | 对指定编程语言的源代码进行解析 |
-| 询问多个大语言模型.py | 使用多个大语言模型对输入进行处理和回复 |
-| 读文章写摘要.py | 对论文进行解析和全文摘要生成 |
-
-概括程序的整体功能：提供了一系列处理文本、文件和代码的功能，使用了各类语言模型、多线程、网络请求和数据解析技术来提高效率和精度。
-
-## 用一张Markdown表格简要描述以下文件的功能：
-crazy_functions\谷歌检索小助手.py, crazy_functions\高级功能函数模板.py, request_llm\bridge_all.py, request_llm\bridge_chatglm.py, request_llm\bridge_chatgpt.py, request_llm\bridge_jittorllms_llama.py, request_llm\bridge_jittorllms_pangualpha.py, request_llm\bridge_jittorllms_rwkv.py, request_llm\bridge_moss.py, request_llm\bridge_newbing.py, request_llm\bridge_newbingfree.py, request_llm\bridge_stackclaude.py, request_llm\bridge_tgui.py, request_llm\edge_gpt.py, request_llm\edge_gpt_free.py, request_llm\test_llms.py。根据以上分析，用一句话概括程序的整体功能。
-
-| 文件名 | 功能描述 |
-| --- | --- |
-| crazy_functions\谷歌检索小助手.py | 提供谷歌学术搜索页面中相关文章的元数据信息。 |
-| crazy_functions\高级功能函数模板.py | 使用Unsplash API发送相关图片以回复用户的输入。 |
-| request_llm\bridge_all.py | 基于不同LLM模型进行对话。 |
-| request_llm\bridge_chatglm.py | 使用ChatGLM模型生成回复，支持单线程和多线程方式。 |
-| request_llm\bridge_chatgpt.py | 基于GPT模型完成对话。 |
-| request_llm\bridge_jittorllms_llama.py | 使用JittorLLMs模型完成对话，支持单线程和多线程方式。 |
-| request_llm\bridge_jittorllms_pangualpha.py | 使用JittorLLMs模型完成对话，基于多进程和多线程方式。 |
-| request_llm\bridge_jittorllms_rwkv.py | 使用JittorLLMs模型完成聊天功能，提供包括历史信息、参数调节等在内的多个功能选项。 |
-| request_llm\bridge_moss.py | 加载Moss模型完成对话功能。 |
-| request_llm\bridge_newbing.py | 使用Newbing聊天机器人进行对话，支持单线程和多线程方式。 |
-| request_llm\bridge_newbingfree.py | 基于Bing chatbot API实现聊天机器人的文本生成功能。 |
-| request_llm\bridge_stackclaude.py | 基于Slack API实现Claude与用户的交互。 |
-| request_llm\bridge_tgui.py | 通过websocket实现聊天机器人与UI界面交互。 |
-| request_llm\edge_gpt.py | 调用Bing chatbot API提供聊天机器人服务。 |
-| request_llm\edge_gpt_free.py | 实现聊天机器人API，采用aiohttp和httpx工具库。 |
-| request_llm\test_llms.py | 对llm模型进行单元测试。 |
-| 程序整体功能 | 实现不同种类的聊天机器人，可以根据输入进行文本生成。 |
diff --git a/spaces/fclong/summary/fengshen/data/data_utils/mask_utils.py b/spaces/fclong/summary/fengshen/data/data_utils/mask_utils.py
deleted file mode 100644
index 0009f00272bf6feff1dbd491153332584cb431e1..0000000000000000000000000000000000000000
--- a/spaces/fclong/summary/fengshen/data/data_utils/mask_utils.py
+++ /dev/null
@@ -1,285 +0,0 @@
-import collections
-
-import numpy as np
-
-MaskedLmInstance = collections.namedtuple("MaskedLmInstance",
-                                          ["index", "label"])
-
-
-def is_start_piece(piece):
-    """Check if the current word piece is the starting piece (BERT)."""
-    # When a word has been split into
-    # WordPieces, the first token does not have any marker and any subsequence
-    # tokens are prefixed with ##. So whenever we see the ## token, we
-    # append it to the previous set of word indexes.
-    return not piece.startswith("##")
-
-
-def create_masked_lm_predictions(tokens,
-                                 vocab_id_list, vocab_id_to_token_dict,
-                                 masked_lm_prob,
-                                 cls_id, sep_id, mask_id,
-                                 max_predictions_per_seq,
-                                 np_rng,
-                                 max_ngrams=3,
-                                 do_whole_word_mask=True,
-                                 favor_longer_ngram=False,
-                                 do_permutation=False,
-                                 geometric_dist=False,
-                                 masking_style="bert",
-                                 zh_tokenizer=None):
-    """Creates the predictions for the masked LM objective.
-    Note: Tokens here are vocab ids and not text tokens."""
-    '''
-    modified from Megatron-LM
-    Args:
-        tokens: 输入
-        vocab_id_list: 词表token_id_list
-        vocab_id_to_token_dict： token_id到token字典
-        masked_lm_prob：mask概率
-        cls_id、sep_id、mask_id：特殊token
-        max_predictions_per_seq：最大mask个数
-        np_rng：mask随机数
-        max_ngrams：最大词长度
-        do_whole_word_mask：是否做全词掩码
-        favor_longer_ngram：优先用长的词
-        do_permutation：是否打乱
-        geometric_dist：用np_rng.geometric做随机
-        masking_style：mask类型
-        zh_tokenizer：WWM的分词器，比如用jieba.lcut做分词之类的
-    '''
-    cand_indexes = []
-    # Note(mingdachen): We create a list for recording if the piece is
-    # the starting piece of current token, where 1 means true, so that
-    # on-the-fly whole word masking is possible.
-    token_boundary = [0] * len(tokens)
-    # 如果没有指定中文分词器，那就直接按##算
-    if zh_tokenizer is None:
-        for (i, token) in enumerate(tokens):
-            if token == cls_id or token == sep_id:
-                token_boundary[i] = 1
-                continue
-        # Whole Word Masking means that if we mask all of the wordpieces
-        # corresponding to an original word.
-        #
-        # Note that Whole Word Masking does *not* change the training code
-        # at all -- we still predict each WordPiece independently, softmaxed
-        # over the entire vocabulary.
-            if (do_whole_word_mask and len(cand_indexes) >= 1 and
-                    not is_start_piece(vocab_id_to_token_dict[token])):
-                cand_indexes[-1].append(i)
-            else:
-                cand_indexes.append([i])
-                if is_start_piece(vocab_id_to_token_dict[token]):
-                    token_boundary[i] = 1
-    else:
-        # 如果指定了中文分词器，那就先用分词器分词，然后再进行判断
-        # 获取去掉CLS SEP的原始文本
-        raw_tokens = []
-        for t in tokens:
-            if t != cls_id and t != sep_id:
-                raw_tokens.append(t)
-        raw_tokens = [vocab_id_to_token_dict[i] for i in raw_tokens]
-        # 分词然后获取每次字开头的最长词的长度
-        word_list = set(zh_tokenizer(''.join(raw_tokens), HMM=True))
-        word_length_dict = {}
-        for w in word_list:
-            if len(w) < 1:
-                continue
-            if w[0] not in word_length_dict:
-                word_length_dict[w[0]] = len(w)
-            elif word_length_dict[w[0]] < len(w):
-                word_length_dict[w[0]] = len(w)
-        i = 0
-        # 从词表里面检索
-        while i < len(tokens):
-            token_id = tokens[i]
-            token = vocab_id_to_token_dict[token_id]
-            if len(token) == 0 or token_id == cls_id or token_id == sep_id:
-                token_boundary[i] = 1
-                i += 1
-                continue
-            word_max_length = 1
-            if token[0] in word_length_dict:
-                word_max_length = word_length_dict[token[0]]
-            j = 0
-            word = ''
-            word_end = i+1
-            # 兼容以前##的形式，如果后面的词是##开头的，那么直接把后面的拼到前面当作一个词
-            old_style = False
-            while word_end < len(tokens) and vocab_id_to_token_dict[tokens[word_end]].startswith('##'):
-                old_style = True
-                word_end += 1
-            if not old_style:
-                while j < word_max_length and i+j < len(tokens):
-                    cur_token = tokens[i+j]
-                    word += vocab_id_to_token_dict[cur_token]
-                    j += 1
-                    if word in word_list:
-                        word_end = i+j
-            cand_indexes.append([p for p in range(i, word_end)])
-            token_boundary[i] = 1
-            i = word_end
-
-    output_tokens = list(tokens)
-
-    masked_lm_positions = []
-    masked_lm_labels = []
-
-    if masked_lm_prob == 0:
-        return (output_tokens, masked_lm_positions,
-                masked_lm_labels, token_boundary)
-
-    num_to_predict = min(max_predictions_per_seq,
-                         max(1, int(round(len(tokens) * masked_lm_prob))))
-
-    ngrams = np.arange(1, max_ngrams + 1, dtype=np.int64)
-    if not geometric_dist:
-        # Note(mingdachen):
-        # By default, we set the probilities to favor shorter ngram sequences.
-        pvals = 1. / np.arange(1, max_ngrams + 1)
-        pvals /= pvals.sum(keepdims=True)
-        if favor_longer_ngram:
-            pvals = pvals[::-1]
-    # 获取一个ngram的idx，对于每个word，记录他的ngram的word
-    ngram_indexes = []
-    for idx in range(len(cand_indexes)):
-        ngram_index = []
-        for n in ngrams:
-            ngram_index.append(cand_indexes[idx:idx + n])
-        ngram_indexes.append(ngram_index)
-
-    np_rng.shuffle(ngram_indexes)
-
-    (masked_lms, masked_spans) = ([], [])
-    covered_indexes = set()
-    for cand_index_set in ngram_indexes:
-        if len(masked_lms) >= num_to_predict:
-            break
-        if not cand_index_set:
-            continue
-        # Note(mingdachen):
-        # Skip current piece if they are covered in lm masking or previous ngrams.
-        for index_set in cand_index_set[0]:
-            for index in index_set:
-                if index in covered_indexes:
-                    continue
-
-        if not geometric_dist:
-            n = np_rng.choice(ngrams[:len(cand_index_set)],
-                              p=pvals[:len(cand_index_set)] /
-                              pvals[:len(cand_index_set)].sum(keepdims=True))
-        else:
-            # Sampling "n" from the geometric distribution and clipping it to
-            # the max_ngrams. Using p=0.2 default from the SpanBERT paper
-            # https://arxiv.org/pdf/1907.10529.pdf (Sec 3.1)
-            n = min(np_rng.geometric(0.2), max_ngrams)
-
-        index_set = sum(cand_index_set[n - 1], [])
-        n -= 1
-        # Note(mingdachen):
-        # Repeatedly looking for a candidate that does not exceed the
-        # maximum number of predictions by trying shorter ngrams.
-        while len(masked_lms) + len(index_set) > num_to_predict:
-            if n == 0:
-                break
-            index_set = sum(cand_index_set[n - 1], [])
-            n -= 1
-        # If adding a whole-word mask would exceed the maximum number of
-        # predictions, then just skip this candidate.
-        if len(masked_lms) + len(index_set) > num_to_predict:
-            continue
-        is_any_index_covered = False
-        for index in index_set:
-            if index in covered_indexes:
-                is_any_index_covered = True
-                break
-        if is_any_index_covered:
-            continue
-        for index in index_set:
-            covered_indexes.add(index)
-            masked_token = None
-            token_id = tokens[index]
-            if masking_style == "bert":
-                # 80% of the time, replace with [MASK]
-                if np_rng.random() < 0.8:
-                    masked_token = mask_id
-                else:
-                    # 10% of the time, keep original
-                    if np_rng.random() < 0.5:
-                        masked_token = tokens[index]
-                    # 10% of the time, replace with random word
-                    else:
-                        masked_token = vocab_id_list[np_rng.randint(0, len(vocab_id_list))]
-            elif masking_style == "t5":
-                masked_token = mask_id
-            else:
-                raise ValueError("invalid value of masking style")
-
-            output_tokens[index] = masked_token
-            masked_lms.append(MaskedLmInstance(index=index, label=token_id))
-
-        masked_spans.append(MaskedLmInstance(
-            index=index_set,
-            label=[tokens[index] for index in index_set]))
-
-    assert len(masked_lms) <= num_to_predict
-    np_rng.shuffle(ngram_indexes)
-
-    select_indexes = set()
-    if do_permutation:
-        for cand_index_set in ngram_indexes:
-            if len(select_indexes) >= num_to_predict:
-                break
-            if not cand_index_set:
-                continue
-            # Note(mingdachen):
-            # Skip current piece if they are covered in lm masking or previous ngrams.
-            for index_set in cand_index_set[0]:
-                for index in index_set:
-                    if index in covered_indexes or index in select_indexes:
-                        continue
-
-            n = np.random.choice(ngrams[:len(cand_index_set)],
-                                 p=pvals[:len(cand_index_set)] /
-                                 pvals[:len(cand_index_set)].sum(keepdims=True))
-            index_set = sum(cand_index_set[n - 1], [])
-            n -= 1
-
-            while len(select_indexes) + len(index_set) > num_to_predict:
-                if n == 0:
-                    break
-                index_set = sum(cand_index_set[n - 1], [])
-                n -= 1
-            # If adding a whole-word mask would exceed the maximum number of
-            # predictions, then just skip this candidate.
-            if len(select_indexes) + len(index_set) > num_to_predict:
-                continue
-            is_any_index_covered = False
-            for index in index_set:
-                if index in covered_indexes or index in select_indexes:
-                    is_any_index_covered = True
-                    break
-            if is_any_index_covered:
-                continue
-            for index in index_set:
-                select_indexes.add(index)
-        assert len(select_indexes) <= num_to_predict
-
-        select_indexes = sorted(select_indexes)
-        permute_indexes = list(select_indexes)
-        np_rng.shuffle(permute_indexes)
-        orig_token = list(output_tokens)
-
-        for src_i, tgt_i in zip(select_indexes, permute_indexes):
-            output_tokens[src_i] = orig_token[tgt_i]
-            masked_lms.append(MaskedLmInstance(index=src_i, label=orig_token[src_i]))
-
-    masked_lms = sorted(masked_lms, key=lambda x: x.index)
-    # Sort the spans by the index of the first span
-    masked_spans = sorted(masked_spans, key=lambda x: x.index[0])
-
-    for p in masked_lms:
-        masked_lm_positions.append(p.index)
-        masked_lm_labels.append(p.label)
-    return (output_tokens, masked_lm_positions, masked_lm_labels, token_boundary, masked_spans)
diff --git a/spaces/fclong/summary/fengshen/data/task_dataloader/task_datasets.py b/spaces/fclong/summary/fengshen/data/task_dataloader/task_datasets.py
deleted file mode 100644
index a8fe7bcf732c61725853df92d9422f207d55f785..0000000000000000000000000000000000000000
--- a/spaces/fclong/summary/fengshen/data/task_dataloader/task_datasets.py
+++ /dev/null
@@ -1,206 +0,0 @@
-# coding=utf8
-from torch.utils.data import Dataset, DataLoader
-from tqdm import tqdm
-from transformers import AutoTokenizer
-import json
-import torch
-import pytorch_lightning as pl
-import os
-
-
-class AbstractCollator:
-    """
-    collector for summary task
-    """
-
-    def __init__(self, tokenizer, max_enc_length, max_dec_length, prompt):
-        self.tokenizer = tokenizer
-        self.max_enc_length = max_enc_length
-        self.max_dec_length = max_dec_length
-        self.prompt = prompt
-
-    def __call__(self, samples):
-
-        labels = []
-        attn_mask = []
-        # decoder_attn_mask = []
-        source_inputs = []
-        for sample in samples:
-            encode_dict = self.tokenizer.encode_plus(
-                self.prompt + sample['text'],
-                max_length=self.max_enc_length,
-                padding='max_length',
-                truncation=True,
-                return_tensors='pt')
-            decode_dict = self.tokenizer.encode_plus(
-                sample['summary'],
-                max_length=self.max_dec_length,
-                padding='max_length',
-                truncation=True,
-                return_tensors='pt')
-            source_inputs.append(encode_dict['input_ids'].squeeze())
-            labels.append(decode_dict['input_ids'].squeeze())
-            attn_mask.append(encode_dict['attention_mask'].squeeze())
-            # decoder_attn_mask.append(decode_dict['attention_mask'].squeeze())
-        # labels = torch.tensor(decode_dict['input'])
-
-        source_inputs = torch.stack(source_inputs)
-        labels = torch.stack(labels)
-        attn_mask = torch.stack(attn_mask)
-        # decoder_attn_mask = torch.stack(decoder_attn_mask)
-        # decode_input_idxs = shift_tokens_right(labels, self.tokenizer.pad_token_id, self.tokenizer.pad_token_id)
-        end_token_index = torch.where(labels == self.tokenizer.eos_token_id)[1]
-        for idx, end_idx in enumerate(end_token_index):
-            labels[idx][end_idx + 1:] = -100
-
-        return {
-            "input_ids": source_inputs,
-            "attention_mask": attn_mask,
-            "labels": labels,
-            "text": [sample['text'] for sample in samples],
-            "summary": [sample['summary'] for sample in samples]
-        }
-
-
-class LCSTSDataset(Dataset):
-    '''
-    Dataset Used for LCSTS summary task.
-    '''
-
-    def __init__(self, data_path, args):
-        super().__init__()
-        self.tokenizer = AutoTokenizer.from_pretrained(
-            args.pretrained_model_path, use_fast=False)
-        self.data = self.load_data(data_path)
-        self.prompt = args.prompt
-        self.max_enc_length = args.max_enc_length
-        self.max_dec_length = args.max_dec_length
-
-    def __len__(self):
-        return len(self.data)
-
-    def __getitem__(self, index):
-        return self.encode(self.data[index])
-
-    def load_data(self, data_path):
-        with open(data_path, "r", encoding='utf8') as f:
-            lines = f.readlines()
-        samples = []
-        for line in tqdm(lines):
-            obj = json.loads(line)
-            source = obj['text']
-            target = obj['summary']
-            samples.append({
-                "text": source,
-                "summary": target
-            })
-        return samples
-
-    def cal_data(self, data_path):
-        with open(data_path, "r", encoding='utf8') as f:
-            lines = f.readlines()
-        samples = []
-        enc_sizes = []
-        dec_sizes = []
-        for line in tqdm(lines):
-            obj = json.loads(line.strip())
-            source = obj['text']
-            target = obj['summary']
-            enc_input_ids = self.tokenizer.encode(source)
-            target = self.tokenizer.encode(target)
-            enc_sizes.append(len(enc_input_ids))
-            dec_sizes.append(len(target)-1)
-            samples.append({
-                "enc_input_ids": enc_input_ids,
-                "dec_input_ids": target[:-1],
-                "label_ids": target[1:]
-            })
-        max_enc_len = max(enc_sizes)
-        max_dec_len = max(dec_sizes)
-        import numpy as np
-        # mean of len(enc_input_ids): 74.68041911345998
-        # mean of len(dec_input_ids): 14.02265483791283
-        # max of len(enc_input_ids): 132
-        # max of len(dec_input_ids): 31
-        print('mean of len(enc_input_ids):', np.mean(enc_sizes),
-              'mean of len(dec_input_ids):', np.mean(dec_sizes),
-              'max of len(enc_input_ids):', max_enc_len,
-              'max of len(dec_input_ids):', max_dec_len)
-        return samples
-
-    def encode(self, item):
-        encode_dict = self.tokenizer.encode_plus(
-            self.prompt + item['text'],
-            max_length=self.max_enc_length,
-            padding='max_length',
-            truncation=True,
-            return_tensors='pt')
-        decode_dict = self.tokenizer.encode_plus(
-            item['summary'],
-            max_length=self.max_dec_length,
-            padding='max_length',
-            truncation=True)
-
-        target = decode_dict['input_ids']
-        # print('encode_dict shape:', encode_dict['input_ids'].shape)
-        labels = torch.tensor(target)
-        labels[target == self.tokenizer.pad_token_id] = -100
-        return {
-            "input_ids": encode_dict['input_ids'].squeeze(),
-            "attention_mask": encode_dict['attention_mask'].squeeze(),
-            "labels": labels.squeeze(),
-            "text": item['text'],
-            "summary": item['summary']
-        }
-
-
-class LCSTSDataModel(pl.LightningDataModule):
-    @staticmethod
-    def add_data_specific_args(parent_args):
-        parser = parent_args.add_argument_group('LCSTSDataModel')
-        parser.add_argument(
-            '--data_dir', default='/cognitive_comp/ganruyi/data_datasets_LCSTS_LCSTS/', type=str)
-        parser.add_argument('--num_workers', default=8, type=int)
-        parser.add_argument('--train_data', default='train.jsonl', type=str)
-        parser.add_argument('--valid_data', default='valid.jsonl', type=str)
-        parser.add_argument('--test_data', default='test_public.jsonl', type=str)
-        parser.add_argument('--train_batchsize', default=128, type=int)
-        parser.add_argument('--valid_batchsize', default=128, type=int)
-        parser.add_argument('--max_enc_length', default=128, type=int)
-        parser.add_argument('--max_dec_length', default=30, type=int)
-        parser.add_argument('--prompt', default='summarize:', type=str)
-        return parent_args
-
-    def __init__(self, args):
-        super().__init__()
-        self.args = args
-        self.train_batchsize = args.train_batchsize
-        self.valid_batchsize = args.valid_batchsize
-        if not args.do_eval_only:
-            self.train_data = LCSTSDataset(os.path.join(
-                args.data_dir, args.train_data), args)
-        self.valid_data = LCSTSDataset(os.path.join(
-            args.data_dir, args.valid_data), args)
-        self.test_data = LCSTSDataset(os.path.join(
-            args.data_dir, args.test_data), args)
-
-    def train_dataloader(self):
-        return DataLoader(self.train_data,
-                          shuffle=True,
-                          batch_size=self.train_batchsize,
-                          pin_memory=False,
-                          num_workers=self.args.num_workers)
-
-    def val_dataloader(self):
-        return DataLoader(self.valid_data,
-                          shuffle=False,
-                          batch_size=self.valid_batchsize,
-                          pin_memory=False,
-                          num_workers=self.args.num_workers)
-
-    def predict_dataloader(self):
-        return DataLoader(self.test_data,
-                          shuffle=False,
-                          batch_size=self.valid_batchsize,
-                          pin_memory=False,
-                          num_workers=self.args.num_workers)
diff --git a/spaces/feng2022/styleganhuman_copy/torch_utils/ops/filtered_lrelu.h b/spaces/feng2022/styleganhuman_copy/torch_utils/ops/filtered_lrelu.h
deleted file mode 100644
index 524c804122a2582e20e2e4e9c49267e1a1b6db60..0000000000000000000000000000000000000000
--- a/spaces/feng2022/styleganhuman_copy/torch_utils/ops/filtered_lrelu.h
+++ /dev/null
@@ -1,90 +0,0 @@
-// Copyright (c) 2021, NVIDIA CORPORATION & AFFILIATES.  All rights reserved.
-//
-// NVIDIA CORPORATION and its licensors retain all intellectual property
-// and proprietary rights in and to this software, related documentation
-// and any modifications thereto.  Any use, reproduction, disclosure or
-// distribution of this software and related documentation without an express
-// license agreement from NVIDIA CORPORATION is strictly prohibited.
-
-#include <cuda_runtime.h>
-
-//------------------------------------------------------------------------
-// CUDA kernel parameters.
-
-struct filtered_lrelu_kernel_params
-{
-    // These parameters decide which kernel to use.
-    int             up;         // upsampling ratio (1, 2, 4)
-    int             down;       // downsampling ratio (1, 2, 4)
-    int2            fuShape;    // [size, 1] | [size, size]
-    int2            fdShape;    // [size, 1] | [size, size]
-
-    int             _dummy;     // Alignment.
-
-    // Rest of the parameters.
-    const void*     x;          // Input tensor.
-    void*           y;          // Output tensor.
-    const void*     b;          // Bias tensor.
-    unsigned char*  s;          // Sign tensor in/out. NULL if unused.
-    const float*    fu;         // Upsampling filter.
-    const float*    fd;         // Downsampling filter.
-
-    int2            pad0;       // Left/top padding.
-    float           gain;       // Additional gain factor.
-    float           slope;      // Leaky ReLU slope on negative side.
-    float           clamp;      // Clamp after nonlinearity.
-    int             flip;       // Filter kernel flip for gradient computation.
-
-    int             tilesXdim;  // Original number of horizontal output tiles.
-    int             tilesXrep;  // Number of horizontal tiles per CTA.
-    int             blockZofs;  // Block z offset to support large minibatch, channel dimensions.
-
-    int4            xShape;     // [width, height, channel, batch]
-    int4            yShape;     // [width, height, channel, batch]
-    int2            sShape;     // [width, height] - width is in bytes. Contiguous. Zeros if unused.
-    int2            sOfs;       // [ofs_x, ofs_y] - offset between upsampled data and sign tensor.
-    int             swLimit;    // Active width of sign tensor in bytes.
-
-    longlong4       xStride;    // Strides of all tensors except signs, same component order as shapes.
-    longlong4       yStride;    //
-    int64_t         bStride;    //
-    longlong3       fuStride;   //
-    longlong3       fdStride;   //
-};
-
-struct filtered_lrelu_act_kernel_params
-{
-    void*           x;          // Input/output, modified in-place.
-    unsigned char*  s;          // Sign tensor in/out. NULL if unused.
-
-    float           gain;       // Additional gain factor.
-    float           slope;      // Leaky ReLU slope on negative side.
-    float           clamp;      // Clamp after nonlinearity.
-
-    int4            xShape;     // [width, height, channel, batch]
-    longlong4       xStride;    // Input/output tensor strides, same order as in shape.
-    int2            sShape;     // [width, height] - width is in elements. Contiguous. Zeros if unused.
-    int2            sOfs;       // [ofs_x, ofs_y] - offset between upsampled data and sign tensor.
-};
-
-//------------------------------------------------------------------------
-// CUDA kernel specialization.
-
-struct filtered_lrelu_kernel_spec
-{
-    void*   setup;              // Function for filter kernel setup.
-    void*   exec;               // Function for main operation.
-    int2    tileOut;            // Width/height of launch tile.
-    int     numWarps;           // Number of warps per thread block, determines launch block size.
-    int     xrep;               // For processing multiple horizontal tiles per thread block.
-    int     dynamicSharedKB;    // How much dynamic shared memory the exec kernel wants.
-};
-
-//------------------------------------------------------------------------
-// CUDA kernel selection.
-
-template <class T, class index_t, bool signWrite, bool signRead> filtered_lrelu_kernel_spec choose_filtered_lrelu_kernel(const filtered_lrelu_kernel_params& p, int sharedKB);
-template <class T, bool signWrite, bool signRead> void* choose_filtered_lrelu_act_kernel(void);
-template <bool signWrite, bool signRead> cudaError_t copy_filters(cudaStream_t stream);
-
-//------------------------------------------------------------------------
\ No newline at end of file
diff --git a/spaces/fffiloni/Image-to-MusicGen/app.py b/spaces/fffiloni/Image-to-MusicGen/app.py
deleted file mode 100644
index 32212ca3379e99835937d4bda21c85714616ee36..0000000000000000000000000000000000000000
--- a/spaces/fffiloni/Image-to-MusicGen/app.py
+++ /dev/null
@@ -1,122 +0,0 @@
-"""
-Copyright (c) Meta Platforms, Inc. and affiliates.
-All rights reserved.
-
-This source code is licensed under the license found in the
-LICENSE file in the root directory of this source tree.
-"""
-
-from tempfile import NamedTemporaryFile
-import torch
-import gradio as gr
-from audiocraft.models import MusicGen
-
-from audiocraft.data.audio import audio_write
-
-
-MODEL = None
-
-img_to_text = gr.load(name="spaces/fffiloni/CLIP-Interrogator-2")
-
-
-def load_model(version):
-    print("Loading model", version)
-    return MusicGen.get_pretrained(version)
-
-
-def predict(uploaded_image, melody, duration):
-    text = img_to_text(uploaded_image, 'best', 4, fn_index=1)[0]
-    global MODEL
-    topk = int(250)
-    if MODEL is None or MODEL.name != "melody":
-        MODEL = load_model("melody")
-
-    if duration > MODEL.lm.cfg.dataset.segment_duration:
-        raise gr.Error("MusicGen currently supports durations of up to 30 seconds!")
-    MODEL.set_generation_params(
-        use_sampling=True,
-        top_k=250,
-        top_p=0,
-        temperature=1.0,
-        cfg_coef=3.0,
-        duration=duration,
-    )
-
-    if melody:
-        sr, melody = melody[0], torch.from_numpy(melody[1]).to(MODEL.device).float().t().unsqueeze(0)
-        print(melody.shape)
-        if melody.dim() == 2:
-            melody = melody[None]
-        melody = melody[..., :int(sr * MODEL.lm.cfg.dataset.segment_duration)]
-        output = MODEL.generate_with_chroma(
-            descriptions=[text],
-            melody_wavs=melody,
-            melody_sample_rate=sr,
-            progress=False
-        )
-    else:
-        output = MODEL.generate(descriptions=[text], progress=False)
-
-    output = output.detach().cpu().float()[0]
-    with NamedTemporaryFile("wb", suffix=".wav", delete=False) as file:
-        audio_write(file.name, output, MODEL.sample_rate, strategy="loudness", add_suffix=False)
-        #waveform_video = gr.make_waveform(file.name)
-    return file.name
-
-
-with gr.Blocks() as demo:
-    gr.Markdown(
-        """
-        # Image to MusicGen
-
-        This is the demo by @fffiloni for Image to [MusicGen](https://github.com/facebookresearch/audiocraft), a simple and controllable model for music generation
-        presented at: ["Simple and Controllable Music Generation"](https://huggingface.co/papers/2306.05284), using Clip Interrogator to get an image description as init text. 
-        <br/>
-        <a href="https://huggingface.co/spaces/musicgen/MusicGen?duplicate=true" style="display: inline-block;margin-top: .5em;margin-right: .25em;" target="_blank">
-        <img style="margin-bottom: 0em;display: inline;margin-top: -.25em;" src="https://bit.ly/3gLdBN6" alt="Duplicate Space"></a>
-        for longer sequences, more control and no queue.</p>
-        """
-    )
-    with gr.Row():
-        with gr.Column():
-            with gr.Column():
-                uploaded_image = gr.Image(label="Input Image", interactive=True, source="upload", type="filepath")
-                melody = gr.Audio(source="upload", type="numpy", label="Melody Condition (optional)", interactive=True)
-            with gr.Row():
-                submit = gr.Button("Submit")
-            #with gr.Row():
-            #   model = gr.Radio(["melody", "medium", "small", "large"], label="Model", value="melody", interactive=True)
-            with gr.Row():
-                duration = gr.Slider(minimum=1, maximum=30, value=10, step=1, label="Duration", interactive=True)
-            #with gr.Row():
-            #   topk = gr.Number(label="Top-k", value=250, interactive=True)
-            #   topp = gr.Number(label="Top-p", value=0, interactive=True)
-            #   temperature = gr.Number(label="Temperature", value=1.0, interactive=True)
-            #   cfg_coef = gr.Number(label="Classifier Free Guidance", value=3.0, interactive=True)
-        with gr.Column():
-            output = gr.Audio(label="Generated Music")
-    submit.click(predict, inputs=[uploaded_image, melody, duration], outputs=[output])
-    
-    gr.Markdown(
-        """
-        ### More details
-
-        The model will generate a short music extract based on the image you provided.
-        You can generate up to 30 seconds of audio.
-
-        This demo is set to use only the Melody model
-        1. Melody -- a music generation model capable of generating music condition on text and melody inputs. **Note**, you can also use text only.
-        2. Small -- a 300M transformer decoder conditioned on text only.
-        3. Medium -- a 1.5B transformer decoder conditioned on text only.
-        4. Large -- a 3.3B transformer decoder conditioned on text only (might OOM for the longest sequences.)
-
-        When using `melody`, ou can optionaly provide a reference audio from
-        which a broad melody will be extracted. The model will then try to follow both the description and melody provided.
-
-        You can also use your own GPU or a Google Colab by following the instructions on our repo.
-        See [github.com/facebookresearch/audiocraft](https://github.com/facebookresearch/audiocraft)
-        for more details.
-        """
-    )
-
-demo.queue(max_size=32).launch()
diff --git a/spaces/fffiloni/Video-Matting-Anything/GroundingDINO/groundingdino/util/__init__.py b/spaces/fffiloni/Video-Matting-Anything/GroundingDINO/groundingdino/util/__init__.py
deleted file mode 100644
index 168f9979a4623806934b0ff1102ac166704e7dec..0000000000000000000000000000000000000000
--- a/spaces/fffiloni/Video-Matting-Anything/GroundingDINO/groundingdino/util/__init__.py
+++ /dev/null
@@ -1 +0,0 @@
-# Copyright (c) Facebook, Inc. and its affiliates. All Rights Reserved
diff --git a/spaces/fffiloni/controlnet-animation-doodle/node_modules/@types/node/ts4.8/crypto.d.ts b/spaces/fffiloni/controlnet-animation-doodle/node_modules/@types/node/ts4.8/crypto.d.ts
deleted file mode 100644
index 66dc8e54a2b3ae6119f7f6964eb295767cbc90bc..0000000000000000000000000000000000000000
--- a/spaces/fffiloni/controlnet-animation-doodle/node_modules/@types/node/ts4.8/crypto.d.ts
+++ /dev/null
@@ -1,3966 +0,0 @@
-/**
- * The `crypto` module provides cryptographic functionality that includes a set of
- * wrappers for OpenSSL's hash, HMAC, cipher, decipher, sign, and verify functions.
- *
- * ```js
- * const { createHmac } = await import('crypto');
- *
- * const secret = 'abcdefg';
- * const hash = createHmac('sha256', secret)
- *                .update('I love cupcakes')
- *                .digest('hex');
- * console.log(hash);
- * // Prints:
- * //   c0fa1bc00531bd78ef38c628449c5102aeabd49b5dc3a2a516ea6ea959d6658e
- * ```
- * @see [source](https://github.com/nodejs/node/blob/v18.0.0/lib/crypto.js)
- */
-declare module 'crypto' {
-    import * as stream from 'node:stream';
-    import { PeerCertificate } from 'node:tls';
-    /**
-     * SPKAC is a Certificate Signing Request mechanism originally implemented by
-     * Netscape and was specified formally as part of [HTML5's `keygen` element](https://developer.mozilla.org/en-US/docs/Web/HTML/Element/keygen).
-     *
-     * `<keygen>` is deprecated since [HTML 5.2](https://www.w3.org/TR/html52/changes.html#features-removed) and new projects
-     * should not use this element anymore.
-     *
-     * The `crypto` module provides the `Certificate` class for working with SPKAC
-     * data. The most common usage is handling output generated by the HTML5`<keygen>` element. Node.js uses [OpenSSL's SPKAC
-     * implementation](https://www.openssl.org/docs/man1.1.0/apps/openssl-spkac.html) internally.
-     * @since v0.11.8
-     */
-    class Certificate {
-        /**
-         * ```js
-         * const { Certificate } = await import('crypto');
-         * const spkac = getSpkacSomehow();
-         * const challenge = Certificate.exportChallenge(spkac);
-         * console.log(challenge.toString('utf8'));
-         * // Prints: the challenge as a UTF8 string
-         * ```
-         * @since v9.0.0
-         * @param encoding The `encoding` of the `spkac` string.
-         * @return The challenge component of the `spkac` data structure, which includes a public key and a challenge.
-         */
-        static exportChallenge(spkac: BinaryLike): Buffer;
-        /**
-         * ```js
-         * const { Certificate } = await import('crypto');
-         * const spkac = getSpkacSomehow();
-         * const publicKey = Certificate.exportPublicKey(spkac);
-         * console.log(publicKey);
-         * // Prints: the public key as <Buffer ...>
-         * ```
-         * @since v9.0.0
-         * @param encoding The `encoding` of the `spkac` string.
-         * @return The public key component of the `spkac` data structure, which includes a public key and a challenge.
-         */
-        static exportPublicKey(spkac: BinaryLike, encoding?: string): Buffer;
-        /**
-         * ```js
-         * import { Buffer } from 'buffer';
-         * const { Certificate } = await import('crypto');
-         *
-         * const spkac = getSpkacSomehow();
-         * console.log(Certificate.verifySpkac(Buffer.from(spkac)));
-         * // Prints: true or false
-         * ```
-         * @since v9.0.0
-         * @param encoding The `encoding` of the `spkac` string.
-         * @return `true` if the given `spkac` data structure is valid, `false` otherwise.
-         */
-        static verifySpkac(spkac: NodeJS.ArrayBufferView): boolean;
-        /**
-         * @deprecated
-         * @param spkac
-         * @returns The challenge component of the `spkac` data structure,
-         * which includes a public key and a challenge.
-         */
-        exportChallenge(spkac: BinaryLike): Buffer;
-        /**
-         * @deprecated
-         * @param spkac
-         * @param encoding The encoding of the spkac string.
-         * @returns The public key component of the `spkac` data structure,
-         * which includes a public key and a challenge.
-         */
-        exportPublicKey(spkac: BinaryLike, encoding?: string): Buffer;
-        /**
-         * @deprecated
-         * @param spkac
-         * @returns `true` if the given `spkac` data structure is valid,
-         * `false` otherwise.
-         */
-        verifySpkac(spkac: NodeJS.ArrayBufferView): boolean;
-    }
-    namespace constants {
-        // https://nodejs.org/dist/latest-v10.x/docs/api/crypto.html#crypto_crypto_constants
-        const OPENSSL_VERSION_NUMBER: number;
-        /** Applies multiple bug workarounds within OpenSSL. See https://www.openssl.org/docs/man1.0.2/ssl/SSL_CTX_set_options.html for detail. */
-        const SSL_OP_ALL: number;
-        /** Allows legacy insecure renegotiation between OpenSSL and unpatched clients or servers. See https://www.openssl.org/docs/man1.0.2/ssl/SSL_CTX_set_options.html. */
-        const SSL_OP_ALLOW_UNSAFE_LEGACY_RENEGOTIATION: number;
-        /** Attempts to use the server's preferences instead of the client's when selecting a cipher. See https://www.openssl.org/docs/man1.0.2/ssl/SSL_CTX_set_options.html. */
-        const SSL_OP_CIPHER_SERVER_PREFERENCE: number;
-        /** Instructs OpenSSL to use Cisco's "speshul" version of DTLS_BAD_VER. */
-        const SSL_OP_CISCO_ANYCONNECT: number;
-        /** Instructs OpenSSL to turn on cookie exchange. */
-        const SSL_OP_COOKIE_EXCHANGE: number;
-        /** Instructs OpenSSL to add server-hello extension from an early version of the cryptopro draft. */
-        const SSL_OP_CRYPTOPRO_TLSEXT_BUG: number;
-        /** Instructs OpenSSL to disable a SSL 3.0/TLS 1.0 vulnerability workaround added in OpenSSL 0.9.6d. */
-        const SSL_OP_DONT_INSERT_EMPTY_FRAGMENTS: number;
-        /** Instructs OpenSSL to always use the tmp_rsa key when performing RSA operations. */
-        const SSL_OP_EPHEMERAL_RSA: number;
-        /** Allows initial connection to servers that do not support RI. */
-        const SSL_OP_LEGACY_SERVER_CONNECT: number;
-        const SSL_OP_MICROSOFT_BIG_SSLV3_BUFFER: number;
-        const SSL_OP_MICROSOFT_SESS_ID_BUG: number;
-        /** Instructs OpenSSL to disable the workaround for a man-in-the-middle protocol-version vulnerability in the SSL 2.0 server implementation. */
-        const SSL_OP_MSIE_SSLV2_RSA_PADDING: number;
-        const SSL_OP_NETSCAPE_CA_DN_BUG: number;
-        const SSL_OP_NETSCAPE_CHALLENGE_BUG: number;
-        const SSL_OP_NETSCAPE_DEMO_CIPHER_CHANGE_BUG: number;
-        const SSL_OP_NETSCAPE_REUSE_CIPHER_CHANGE_BUG: number;
-        /** Instructs OpenSSL to disable support for SSL/TLS compression. */
-        const SSL_OP_NO_COMPRESSION: number;
-        const SSL_OP_NO_QUERY_MTU: number;
-        /** Instructs OpenSSL to always start a new session when performing renegotiation. */
-        const SSL_OP_NO_SESSION_RESUMPTION_ON_RENEGOTIATION: number;
-        const SSL_OP_NO_SSLv2: number;
-        const SSL_OP_NO_SSLv3: number;
-        const SSL_OP_NO_TICKET: number;
-        const SSL_OP_NO_TLSv1: number;
-        const SSL_OP_NO_TLSv1_1: number;
-        const SSL_OP_NO_TLSv1_2: number;
-        const SSL_OP_PKCS1_CHECK_1: number;
-        const SSL_OP_PKCS1_CHECK_2: number;
-        /** Instructs OpenSSL to always create a new key when using temporary/ephemeral DH parameters. */
-        const SSL_OP_SINGLE_DH_USE: number;
-        /** Instructs OpenSSL to always create a new key when using temporary/ephemeral ECDH parameters. */
-        const SSL_OP_SINGLE_ECDH_USE: number;
-        const SSL_OP_SSLEAY_080_CLIENT_DH_BUG: number;
-        const SSL_OP_SSLREF2_REUSE_CERT_TYPE_BUG: number;
-        const SSL_OP_TLS_BLOCK_PADDING_BUG: number;
-        const SSL_OP_TLS_D5_BUG: number;
-        /** Instructs OpenSSL to disable version rollback attack detection. */
-        const SSL_OP_TLS_ROLLBACK_BUG: number;
-        const ENGINE_METHOD_RSA: number;
-        const ENGINE_METHOD_DSA: number;
-        const ENGINE_METHOD_DH: number;
-        const ENGINE_METHOD_RAND: number;
-        const ENGINE_METHOD_EC: number;
-        const ENGINE_METHOD_CIPHERS: number;
-        const ENGINE_METHOD_DIGESTS: number;
-        const ENGINE_METHOD_PKEY_METHS: number;
-        const ENGINE_METHOD_PKEY_ASN1_METHS: number;
-        const ENGINE_METHOD_ALL: number;
-        const ENGINE_METHOD_NONE: number;
-        const DH_CHECK_P_NOT_SAFE_PRIME: number;
-        const DH_CHECK_P_NOT_PRIME: number;
-        const DH_UNABLE_TO_CHECK_GENERATOR: number;
-        const DH_NOT_SUITABLE_GENERATOR: number;
-        const ALPN_ENABLED: number;
-        const RSA_PKCS1_PADDING: number;
-        const RSA_SSLV23_PADDING: number;
-        const RSA_NO_PADDING: number;
-        const RSA_PKCS1_OAEP_PADDING: number;
-        const RSA_X931_PADDING: number;
-        const RSA_PKCS1_PSS_PADDING: number;
-        /** Sets the salt length for RSA_PKCS1_PSS_PADDING to the digest size when signing or verifying. */
-        const RSA_PSS_SALTLEN_DIGEST: number;
-        /** Sets the salt length for RSA_PKCS1_PSS_PADDING to the maximum permissible value when signing data. */
-        const RSA_PSS_SALTLEN_MAX_SIGN: number;
-        /** Causes the salt length for RSA_PKCS1_PSS_PADDING to be determined automatically when verifying a signature. */
-        const RSA_PSS_SALTLEN_AUTO: number;
-        const POINT_CONVERSION_COMPRESSED: number;
-        const POINT_CONVERSION_UNCOMPRESSED: number;
-        const POINT_CONVERSION_HYBRID: number;
-        /** Specifies the built-in default cipher list used by Node.js (colon-separated values). */
-        const defaultCoreCipherList: string;
-        /** Specifies the active default cipher list used by the current Node.js process  (colon-separated values). */
-        const defaultCipherList: string;
-    }
-    interface HashOptions extends stream.TransformOptions {
-        /**
-         * For XOF hash functions such as `shake256`, the
-         * outputLength option can be used to specify the desired output length in bytes.
-         */
-        outputLength?: number | undefined;
-    }
-    /** @deprecated since v10.0.0 */
-    const fips: boolean;
-    /**
-     * Creates and returns a `Hash` object that can be used to generate hash digests
-     * using the given `algorithm`. Optional `options` argument controls stream
-     * behavior. For XOF hash functions such as `'shake256'`, the `outputLength` option
-     * can be used to specify the desired output length in bytes.
-     *
-     * The `algorithm` is dependent on the available algorithms supported by the
-     * version of OpenSSL on the platform. Examples are `'sha256'`, `'sha512'`, etc.
-     * On recent releases of OpenSSL, `openssl list -digest-algorithms` will
-     * display the available digest algorithms.
-     *
-     * Example: generating the sha256 sum of a file
-     *
-     * ```js
-     * import {
-     *   createReadStream
-     * } from 'fs';
-     * import { argv } from 'process';
-     * const {
-     *   createHash
-     * } = await import('crypto');
-     *
-     * const filename = argv[2];
-     *
-     * const hash = createHash('sha256');
-     *
-     * const input = createReadStream(filename);
-     * input.on('readable', () => {
-     *   // Only one element is going to be produced by the
-     *   // hash stream.
-     *   const data = input.read();
-     *   if (data)
-     *     hash.update(data);
-     *   else {
-     *     console.log(`${hash.digest('hex')} ${filename}`);
-     *   }
-     * });
-     * ```
-     * @since v0.1.92
-     * @param options `stream.transform` options
-     */
-    function createHash(algorithm: string, options?: HashOptions): Hash;
-    /**
-     * Creates and returns an `Hmac` object that uses the given `algorithm` and `key`.
-     * Optional `options` argument controls stream behavior.
-     *
-     * The `algorithm` is dependent on the available algorithms supported by the
-     * version of OpenSSL on the platform. Examples are `'sha256'`, `'sha512'`, etc.
-     * On recent releases of OpenSSL, `openssl list -digest-algorithms` will
-     * display the available digest algorithms.
-     *
-     * The `key` is the HMAC key used to generate the cryptographic HMAC hash. If it is
-     * a `KeyObject`, its type must be `secret`.
-     *
-     * Example: generating the sha256 HMAC of a file
-     *
-     * ```js
-     * import {
-     *   createReadStream
-     * } from 'fs';
-     * import { argv } from 'process';
-     * const {
-     *   createHmac
-     * } = await import('crypto');
-     *
-     * const filename = argv[2];
-     *
-     * const hmac = createHmac('sha256', 'a secret');
-     *
-     * const input = createReadStream(filename);
-     * input.on('readable', () => {
-     *   // Only one element is going to be produced by the
-     *   // hash stream.
-     *   const data = input.read();
-     *   if (data)
-     *     hmac.update(data);
-     *   else {
-     *     console.log(`${hmac.digest('hex')} ${filename}`);
-     *   }
-     * });
-     * ```
-     * @since v0.1.94
-     * @param options `stream.transform` options
-     */
-    function createHmac(algorithm: string, key: BinaryLike | KeyObject, options?: stream.TransformOptions): Hmac;
-    // https://nodejs.org/api/buffer.html#buffer_buffers_and_character_encodings
-    type BinaryToTextEncoding = 'base64' | 'base64url' | 'hex' | 'binary';
-    type CharacterEncoding = 'utf8' | 'utf-8' | 'utf16le' | 'latin1';
-    type LegacyCharacterEncoding = 'ascii' | 'binary' | 'ucs2' | 'ucs-2';
-    type Encoding = BinaryToTextEncoding | CharacterEncoding | LegacyCharacterEncoding;
-    type ECDHKeyFormat = 'compressed' | 'uncompressed' | 'hybrid';
-    /**
-     * The `Hash` class is a utility for creating hash digests of data. It can be
-     * used in one of two ways:
-     *
-     * * As a `stream` that is both readable and writable, where data is written
-     * to produce a computed hash digest on the readable side, or
-     * * Using the `hash.update()` and `hash.digest()` methods to produce the
-     * computed hash.
-     *
-     * The {@link createHash} method is used to create `Hash` instances. `Hash`objects are not to be created directly using the `new` keyword.
-     *
-     * Example: Using `Hash` objects as streams:
-     *
-     * ```js
-     * const {
-     *   createHash
-     * } = await import('crypto');
-     *
-     * const hash = createHash('sha256');
-     *
-     * hash.on('readable', () => {
-     *   // Only one element is going to be produced by the
-     *   // hash stream.
-     *   const data = hash.read();
-     *   if (data) {
-     *     console.log(data.toString('hex'));
-     *     // Prints:
-     *     //   6a2da20943931e9834fc12cfe5bb47bbd9ae43489a30726962b576f4e3993e50
-     *   }
-     * });
-     *
-     * hash.write('some data to hash');
-     * hash.end();
-     * ```
-     *
-     * Example: Using `Hash` and piped streams:
-     *
-     * ```js
-     * import { createReadStream } from 'fs';
-     * import { stdout } from 'process';
-     * const { createHash } = await import('crypto');
-     *
-     * const hash = createHash('sha256');
-     *
-     * const input = createReadStream('test.js');
-     * input.pipe(hash).setEncoding('hex').pipe(stdout);
-     * ```
-     *
-     * Example: Using the `hash.update()` and `hash.digest()` methods:
-     *
-     * ```js
-     * const {
-     *   createHash
-     * } = await import('crypto');
-     *
-     * const hash = createHash('sha256');
-     *
-     * hash.update('some data to hash');
-     * console.log(hash.digest('hex'));
-     * // Prints:
-     * //   6a2da20943931e9834fc12cfe5bb47bbd9ae43489a30726962b576f4e3993e50
-     * ```
-     * @since v0.1.92
-     */
-    class Hash extends stream.Transform {
-        private constructor();
-        /**
-         * Creates a new `Hash` object that contains a deep copy of the internal state
-         * of the current `Hash` object.
-         *
-         * The optional `options` argument controls stream behavior. For XOF hash
-         * functions such as `'shake256'`, the `outputLength` option can be used to
-         * specify the desired output length in bytes.
-         *
-         * An error is thrown when an attempt is made to copy the `Hash` object after
-         * its `hash.digest()` method has been called.
-         *
-         * ```js
-         * // Calculate a rolling hash.
-         * const {
-         *   createHash
-         * } = await import('crypto');
-         *
-         * const hash = createHash('sha256');
-         *
-         * hash.update('one');
-         * console.log(hash.copy().digest('hex'));
-         *
-         * hash.update('two');
-         * console.log(hash.copy().digest('hex'));
-         *
-         * hash.update('three');
-         * console.log(hash.copy().digest('hex'));
-         *
-         * // Etc.
-         * ```
-         * @since v13.1.0
-         * @param options `stream.transform` options
-         */
-        copy(options?: stream.TransformOptions): Hash;
-        /**
-         * Updates the hash content with the given `data`, the encoding of which
-         * is given in `inputEncoding`.
-         * If `encoding` is not provided, and the `data` is a string, an
-         * encoding of `'utf8'` is enforced. If `data` is a `Buffer`, `TypedArray`, or`DataView`, then `inputEncoding` is ignored.
-         *
-         * This can be called many times with new data as it is streamed.
-         * @since v0.1.92
-         * @param inputEncoding The `encoding` of the `data` string.
-         */
-        update(data: BinaryLike): Hash;
-        update(data: string, inputEncoding: Encoding): Hash;
-        /**
-         * Calculates the digest of all of the data passed to be hashed (using the `hash.update()` method).
-         * If `encoding` is provided a string will be returned; otherwise
-         * a `Buffer` is returned.
-         *
-         * The `Hash` object can not be used again after `hash.digest()` method has been
-         * called. Multiple calls will cause an error to be thrown.
-         * @since v0.1.92
-         * @param encoding The `encoding` of the return value.
-         */
-        digest(): Buffer;
-        digest(encoding: BinaryToTextEncoding): string;
-    }
-    /**
-     * The `Hmac` class is a utility for creating cryptographic HMAC digests. It can
-     * be used in one of two ways:
-     *
-     * * As a `stream` that is both readable and writable, where data is written
-     * to produce a computed HMAC digest on the readable side, or
-     * * Using the `hmac.update()` and `hmac.digest()` methods to produce the
-     * computed HMAC digest.
-     *
-     * The {@link createHmac} method is used to create `Hmac` instances. `Hmac`objects are not to be created directly using the `new` keyword.
-     *
-     * Example: Using `Hmac` objects as streams:
-     *
-     * ```js
-     * const {
-     *   createHmac
-     * } = await import('crypto');
-     *
-     * const hmac = createHmac('sha256', 'a secret');
-     *
-     * hmac.on('readable', () => {
-     *   // Only one element is going to be produced by the
-     *   // hash stream.
-     *   const data = hmac.read();
-     *   if (data) {
-     *     console.log(data.toString('hex'));
-     *     // Prints:
-     *     //   7fd04df92f636fd450bc841c9418e5825c17f33ad9c87c518115a45971f7f77e
-     *   }
-     * });
-     *
-     * hmac.write('some data to hash');
-     * hmac.end();
-     * ```
-     *
-     * Example: Using `Hmac` and piped streams:
-     *
-     * ```js
-     * import { createReadStream } from 'fs';
-     * import { stdout } from 'process';
-     * const {
-     *   createHmac
-     * } = await import('crypto');
-     *
-     * const hmac = createHmac('sha256', 'a secret');
-     *
-     * const input = createReadStream('test.js');
-     * input.pipe(hmac).pipe(stdout);
-     * ```
-     *
-     * Example: Using the `hmac.update()` and `hmac.digest()` methods:
-     *
-     * ```js
-     * const {
-     *   createHmac
-     * } = await import('crypto');
-     *
-     * const hmac = createHmac('sha256', 'a secret');
-     *
-     * hmac.update('some data to hash');
-     * console.log(hmac.digest('hex'));
-     * // Prints:
-     * //   7fd04df92f636fd450bc841c9418e5825c17f33ad9c87c518115a45971f7f77e
-     * ```
-     * @since v0.1.94
-     */
-    class Hmac extends stream.Transform {
-        private constructor();
-        /**
-         * Updates the `Hmac` content with the given `data`, the encoding of which
-         * is given in `inputEncoding`.
-         * If `encoding` is not provided, and the `data` is a string, an
-         * encoding of `'utf8'` is enforced. If `data` is a `Buffer`, `TypedArray`, or`DataView`, then `inputEncoding` is ignored.
-         *
-         * This can be called many times with new data as it is streamed.
-         * @since v0.1.94
-         * @param inputEncoding The `encoding` of the `data` string.
-         */
-        update(data: BinaryLike): Hmac;
-        update(data: string, inputEncoding: Encoding): Hmac;
-        /**
-         * Calculates the HMAC digest of all of the data passed using `hmac.update()`.
-         * If `encoding` is
-         * provided a string is returned; otherwise a `Buffer` is returned;
-         *
-         * The `Hmac` object can not be used again after `hmac.digest()` has been
-         * called. Multiple calls to `hmac.digest()` will result in an error being thrown.
-         * @since v0.1.94
-         * @param encoding The `encoding` of the return value.
-         */
-        digest(): Buffer;
-        digest(encoding: BinaryToTextEncoding): string;
-    }
-    type KeyObjectType = 'secret' | 'public' | 'private';
-    interface KeyExportOptions<T extends KeyFormat> {
-        type: 'pkcs1' | 'spki' | 'pkcs8' | 'sec1';
-        format: T;
-        cipher?: string | undefined;
-        passphrase?: string | Buffer | undefined;
-    }
-    interface JwkKeyExportOptions {
-        format: 'jwk';
-    }
-    interface JsonWebKey {
-        crv?: string | undefined;
-        d?: string | undefined;
-        dp?: string | undefined;
-        dq?: string | undefined;
-        e?: string | undefined;
-        k?: string | undefined;
-        kty?: string | undefined;
-        n?: string | undefined;
-        p?: string | undefined;
-        q?: string | undefined;
-        qi?: string | undefined;
-        x?: string | undefined;
-        y?: string | undefined;
-        [key: string]: unknown;
-    }
-    interface AsymmetricKeyDetails {
-        /**
-         * Key size in bits (RSA, DSA).
-         */
-        modulusLength?: number | undefined;
-        /**
-         * Public exponent (RSA).
-         */
-        publicExponent?: bigint | undefined;
-        /**
-         * Name of the message digest (RSA-PSS).
-         */
-        hashAlgorithm?: string | undefined;
-        /**
-         * Name of the message digest used by MGF1 (RSA-PSS).
-         */
-        mgf1HashAlgorithm?: string | undefined;
-        /**
-         * Minimal salt length in bytes (RSA-PSS).
-         */
-        saltLength?: number | undefined;
-        /**
-         * Size of q in bits (DSA).
-         */
-        divisorLength?: number | undefined;
-        /**
-         * Name of the curve (EC).
-         */
-        namedCurve?: string | undefined;
-    }
-    /**
-     * Node.js uses a `KeyObject` class to represent a symmetric or asymmetric key,
-     * and each kind of key exposes different functions. The {@link createSecretKey}, {@link createPublicKey} and {@link createPrivateKey} methods are used to create `KeyObject`instances. `KeyObject`
-     * objects are not to be created directly using the `new`keyword.
-     *
-     * Most applications should consider using the new `KeyObject` API instead of
-     * passing keys as strings or `Buffer`s due to improved security features.
-     *
-     * `KeyObject` instances can be passed to other threads via `postMessage()`.
-     * The receiver obtains a cloned `KeyObject`, and the `KeyObject` does not need to
-     * be listed in the `transferList` argument.
-     * @since v11.6.0
-     */
-    class KeyObject {
-        private constructor();
-        /**
-         * Example: Converting a `CryptoKey` instance to a `KeyObject`:
-         *
-         * ```js
-         * const { webcrypto, KeyObject } = await import('crypto');
-         * const { subtle } = webcrypto;
-         *
-         * const key = await subtle.generateKey({
-         *   name: 'HMAC',
-         *   hash: 'SHA-256',
-         *   length: 256
-         * }, true, ['sign', 'verify']);
-         *
-         * const keyObject = KeyObject.from(key);
-         * console.log(keyObject.symmetricKeySize);
-         * // Prints: 32 (symmetric key size in bytes)
-         * ```
-         * @since v15.0.0
-         */
-        static from(key: webcrypto.CryptoKey): KeyObject;
-        /**
-         * For asymmetric keys, this property represents the type of the key. Supported key
-         * types are:
-         *
-         * * `'rsa'` (OID 1.2.840.113549.1.1.1)
-         * * `'rsa-pss'` (OID 1.2.840.113549.1.1.10)
-         * * `'dsa'` (OID 1.2.840.10040.4.1)
-         * * `'ec'` (OID 1.2.840.10045.2.1)
-         * * `'x25519'` (OID 1.3.101.110)
-         * * `'x448'` (OID 1.3.101.111)
-         * * `'ed25519'` (OID 1.3.101.112)
-         * * `'ed448'` (OID 1.3.101.113)
-         * * `'dh'` (OID 1.2.840.113549.1.3.1)
-         *
-         * This property is `undefined` for unrecognized `KeyObject` types and symmetric
-         * keys.
-         * @since v11.6.0
-         */
-        asymmetricKeyType?: KeyType | undefined;
-        /**
-         * For asymmetric keys, this property represents the size of the embedded key in
-         * bytes. This property is `undefined` for symmetric keys.
-         */
-        asymmetricKeySize?: number | undefined;
-        /**
-         * This property exists only on asymmetric keys. Depending on the type of the key,
-         * this object contains information about the key. None of the information obtained
-         * through this property can be used to uniquely identify a key or to compromise
-         * the security of the key.
-         *
-         * For RSA-PSS keys, if the key material contains a `RSASSA-PSS-params` sequence,
-         * the `hashAlgorithm`, `mgf1HashAlgorithm`, and `saltLength` properties will be
-         * set.
-         *
-         * Other key details might be exposed via this API using additional attributes.
-         * @since v15.7.0
-         */
-        asymmetricKeyDetails?: AsymmetricKeyDetails | undefined;
-        /**
-         * For symmetric keys, the following encoding options can be used:
-         *
-         * For public keys, the following encoding options can be used:
-         *
-         * For private keys, the following encoding options can be used:
-         *
-         * The result type depends on the selected encoding format, when PEM the
-         * result is a string, when DER it will be a buffer containing the data
-         * encoded as DER, when [JWK](https://tools.ietf.org/html/rfc7517) it will be an object.
-         *
-         * When [JWK](https://tools.ietf.org/html/rfc7517) encoding format was selected, all other encoding options are
-         * ignored.
-         *
-         * PKCS#1, SEC1, and PKCS#8 type keys can be encrypted by using a combination of
-         * the `cipher` and `format` options. The PKCS#8 `type` can be used with any`format` to encrypt any key algorithm (RSA, EC, or DH) by specifying a`cipher`. PKCS#1 and SEC1 can only be
-         * encrypted by specifying a `cipher`when the PEM `format` is used. For maximum compatibility, use PKCS#8 for
-         * encrypted private keys. Since PKCS#8 defines its own
-         * encryption mechanism, PEM-level encryption is not supported when encrypting
-         * a PKCS#8 key. See [RFC 5208](https://www.rfc-editor.org/rfc/rfc5208.txt) for PKCS#8 encryption and [RFC 1421](https://www.rfc-editor.org/rfc/rfc1421.txt) for
-         * PKCS#1 and SEC1 encryption.
-         * @since v11.6.0
-         */
-        export(options: KeyExportOptions<'pem'>): string | Buffer;
-        export(options?: KeyExportOptions<'der'>): Buffer;
-        export(options?: JwkKeyExportOptions): JsonWebKey;
-        /**
-         * For secret keys, this property represents the size of the key in bytes. This
-         * property is `undefined` for asymmetric keys.
-         * @since v11.6.0
-         */
-        symmetricKeySize?: number | undefined;
-        /**
-         * Depending on the type of this `KeyObject`, this property is either`'secret'` for secret (symmetric) keys, `'public'` for public (asymmetric) keys
-         * or `'private'` for private (asymmetric) keys.
-         * @since v11.6.0
-         */
-        type: KeyObjectType;
-    }
-    type CipherCCMTypes = 'aes-128-ccm' | 'aes-192-ccm' | 'aes-256-ccm' | 'chacha20-poly1305';
-    type CipherGCMTypes = 'aes-128-gcm' | 'aes-192-gcm' | 'aes-256-gcm';
-    type CipherOCBTypes = 'aes-128-ocb' | 'aes-192-ocb' | 'aes-256-ocb';
-    type BinaryLike = string | NodeJS.ArrayBufferView;
-    type CipherKey = BinaryLike | KeyObject;
-    interface CipherCCMOptions extends stream.TransformOptions {
-        authTagLength: number;
-    }
-    interface CipherGCMOptions extends stream.TransformOptions {
-        authTagLength?: number | undefined;
-    }
-    interface CipherOCBOptions extends stream.TransformOptions {
-        authTagLength: number;
-    }
-    /**
-     * Creates and returns a `Cipher` object that uses the given `algorithm` and`password`.
-     *
-     * The `options` argument controls stream behavior and is optional except when a
-     * cipher in CCM or OCB mode (e.g. `'aes-128-ccm'`) is used. In that case, the`authTagLength` option is required and specifies the length of the
-     * authentication tag in bytes, see `CCM mode`. In GCM mode, the `authTagLength`option is not required but can be used to set the length of the authentication
-     * tag that will be returned by `getAuthTag()` and defaults to 16 bytes.
-     * For `chacha20-poly1305`, the `authTagLength` option defaults to 16 bytes.
-     *
-     * The `algorithm` is dependent on OpenSSL, examples are `'aes192'`, etc. On
-     * recent OpenSSL releases, `openssl list -cipher-algorithms` will
-     * display the available cipher algorithms.
-     *
-     * The `password` is used to derive the cipher key and initialization vector (IV).
-     * The value must be either a `'latin1'` encoded string, a `Buffer`, a`TypedArray`, or a `DataView`.
-     *
-     * The implementation of `crypto.createCipher()` derives keys using the OpenSSL
-     * function [`EVP_BytesToKey`](https://www.openssl.org/docs/man1.1.0/crypto/EVP_BytesToKey.html) with the digest algorithm set to MD5, one
-     * iteration, and no salt. The lack of salt allows dictionary attacks as the same
-     * password always creates the same key. The low iteration count and
-     * non-cryptographically secure hash algorithm allow passwords to be tested very
-     * rapidly.
-     *
-     * In line with OpenSSL's recommendation to use a more modern algorithm instead of [`EVP_BytesToKey`](https://www.openssl.org/docs/man1.1.0/crypto/EVP_BytesToKey.html) it is recommended that
-     * developers derive a key and IV on
-     * their own using {@link scrypt} and to use {@link createCipheriv} to create the `Cipher` object. Users should not use ciphers with counter mode
-     * (e.g. CTR, GCM, or CCM) in `crypto.createCipher()`. A warning is emitted when
-     * they are used in order to avoid the risk of IV reuse that causes
-     * vulnerabilities. For the case when IV is reused in GCM, see [Nonce-Disrespecting Adversaries](https://github.com/nonce-disrespect/nonce-disrespect) for details.
-     * @since v0.1.94
-     * @deprecated Since v10.0.0 - Use {@link createCipheriv} instead.
-     * @param options `stream.transform` options
-     */
-    function createCipher(algorithm: CipherCCMTypes, password: BinaryLike, options: CipherCCMOptions): CipherCCM;
-    /** @deprecated since v10.0.0 use `createCipheriv()` */
-    function createCipher(algorithm: CipherGCMTypes, password: BinaryLike, options?: CipherGCMOptions): CipherGCM;
-    /** @deprecated since v10.0.0 use `createCipheriv()` */
-    function createCipher(algorithm: string, password: BinaryLike, options?: stream.TransformOptions): Cipher;
-    /**
-     * Creates and returns a `Cipher` object, with the given `algorithm`, `key` and
-     * initialization vector (`iv`).
-     *
-     * The `options` argument controls stream behavior and is optional except when a
-     * cipher in CCM or OCB mode (e.g. `'aes-128-ccm'`) is used. In that case, the`authTagLength` option is required and specifies the length of the
-     * authentication tag in bytes, see `CCM mode`. In GCM mode, the `authTagLength`option is not required but can be used to set the length of the authentication
-     * tag that will be returned by `getAuthTag()` and defaults to 16 bytes.
-     * For `chacha20-poly1305`, the `authTagLength` option defaults to 16 bytes.
-     *
-     * The `algorithm` is dependent on OpenSSL, examples are `'aes192'`, etc. On
-     * recent OpenSSL releases, `openssl list -cipher-algorithms` will
-     * display the available cipher algorithms.
-     *
-     * The `key` is the raw key used by the `algorithm` and `iv` is an [initialization vector](https://en.wikipedia.org/wiki/Initialization_vector). Both arguments must be `'utf8'` encoded
-     * strings,`Buffers`, `TypedArray`, or `DataView`s. The `key` may optionally be
-     * a `KeyObject` of type `secret`. If the cipher does not need
-     * an initialization vector, `iv` may be `null`.
-     *
-     * When passing strings for `key` or `iv`, please consider `caveats when using strings as inputs to cryptographic APIs`.
-     *
-     * Initialization vectors should be unpredictable and unique; ideally, they will be
-     * cryptographically random. They do not have to be secret: IVs are typically just
-     * added to ciphertext messages unencrypted. It may sound contradictory that
-     * something has to be unpredictable and unique, but does not have to be secret;
-     * remember that an attacker must not be able to predict ahead of time what a
-     * given IV will be.
-     * @since v0.1.94
-     * @param options `stream.transform` options
-     */
-    function createCipheriv(algorithm: CipherCCMTypes, key: CipherKey, iv: BinaryLike, options: CipherCCMOptions): CipherCCM;
-    function createCipheriv(algorithm: CipherOCBTypes, key: CipherKey, iv: BinaryLike, options: CipherOCBOptions): CipherOCB;
-    function createCipheriv(algorithm: CipherGCMTypes, key: CipherKey, iv: BinaryLike, options?: CipherGCMOptions): CipherGCM;
-    function createCipheriv(algorithm: string, key: CipherKey, iv: BinaryLike | null, options?: stream.TransformOptions): Cipher;
-    /**
-     * Instances of the `Cipher` class are used to encrypt data. The class can be
-     * used in one of two ways:
-     *
-     * * As a `stream` that is both readable and writable, where plain unencrypted
-     * data is written to produce encrypted data on the readable side, or
-     * * Using the `cipher.update()` and `cipher.final()` methods to produce
-     * the encrypted data.
-     *
-     * The {@link createCipher} or {@link createCipheriv} methods are
-     * used to create `Cipher` instances. `Cipher` objects are not to be created
-     * directly using the `new` keyword.
-     *
-     * Example: Using `Cipher` objects as streams:
-     *
-     * ```js
-     * const {
-     *   scrypt,
-     *   randomFill,
-     *   createCipheriv
-     * } = await import('crypto');
-     *
-     * const algorithm = 'aes-192-cbc';
-     * const password = 'Password used to generate key';
-     *
-     * // First, we'll generate the key. The key length is dependent on the algorithm.
-     * // In this case for aes192, it is 24 bytes (192 bits).
-     * scrypt(password, 'salt', 24, (err, key) => {
-     *   if (err) throw err;
-     *   // Then, we'll generate a random initialization vector
-     *   randomFill(new Uint8Array(16), (err, iv) => {
-     *     if (err) throw err;
-     *
-     *     // Once we have the key and iv, we can create and use the cipher...
-     *     const cipher = createCipheriv(algorithm, key, iv);
-     *
-     *     let encrypted = '';
-     *     cipher.setEncoding('hex');
-     *
-     *     cipher.on('data', (chunk) => encrypted += chunk);
-     *     cipher.on('end', () => console.log(encrypted));
-     *
-     *     cipher.write('some clear text data');
-     *     cipher.end();
-     *   });
-     * });
-     * ```
-     *
-     * Example: Using `Cipher` and piped streams:
-     *
-     * ```js
-     * import {
-     *   createReadStream,
-     *   createWriteStream,
-     * } from 'fs';
-     *
-     * import {
-     *   pipeline
-     * } from 'stream';
-     *
-     * const {
-     *   scrypt,
-     *   randomFill,
-     *   createCipheriv
-     * } = await import('crypto');
-     *
-     * const algorithm = 'aes-192-cbc';
-     * const password = 'Password used to generate key';
-     *
-     * // First, we'll generate the key. The key length is dependent on the algorithm.
-     * // In this case for aes192, it is 24 bytes (192 bits).
-     * scrypt(password, 'salt', 24, (err, key) => {
-     *   if (err) throw err;
-     *   // Then, we'll generate a random initialization vector
-     *   randomFill(new Uint8Array(16), (err, iv) => {
-     *     if (err) throw err;
-     *
-     *     const cipher = createCipheriv(algorithm, key, iv);
-     *
-     *     const input = createReadStream('test.js');
-     *     const output = createWriteStream('test.enc');
-     *
-     *     pipeline(input, cipher, output, (err) => {
-     *       if (err) throw err;
-     *     });
-     *   });
-     * });
-     * ```
-     *
-     * Example: Using the `cipher.update()` and `cipher.final()` methods:
-     *
-     * ```js
-     * const {
-     *   scrypt,
-     *   randomFill,
-     *   createCipheriv
-     * } = await import('crypto');
-     *
-     * const algorithm = 'aes-192-cbc';
-     * const password = 'Password used to generate key';
-     *
-     * // First, we'll generate the key. The key length is dependent on the algorithm.
-     * // In this case for aes192, it is 24 bytes (192 bits).
-     * scrypt(password, 'salt', 24, (err, key) => {
-     *   if (err) throw err;
-     *   // Then, we'll generate a random initialization vector
-     *   randomFill(new Uint8Array(16), (err, iv) => {
-     *     if (err) throw err;
-     *
-     *     const cipher = createCipheriv(algorithm, key, iv);
-     *
-     *     let encrypted = cipher.update('some clear text data', 'utf8', 'hex');
-     *     encrypted += cipher.final('hex');
-     *     console.log(encrypted);
-     *   });
-     * });
-     * ```
-     * @since v0.1.94
-     */
-    class Cipher extends stream.Transform {
-        private constructor();
-        /**
-         * Updates the cipher with `data`. If the `inputEncoding` argument is given,
-         * the `data`argument is a string using the specified encoding. If the `inputEncoding`argument is not given, `data` must be a `Buffer`, `TypedArray`, or`DataView`. If `data` is a `Buffer`,
-         * `TypedArray`, or `DataView`, then`inputEncoding` is ignored.
-         *
-         * The `outputEncoding` specifies the output format of the enciphered
-         * data. If the `outputEncoding`is specified, a string using the specified encoding is returned. If no`outputEncoding` is provided, a `Buffer` is returned.
-         *
-         * The `cipher.update()` method can be called multiple times with new data until `cipher.final()` is called. Calling `cipher.update()` after `cipher.final()` will result in an error being
-         * thrown.
-         * @since v0.1.94
-         * @param inputEncoding The `encoding` of the data.
-         * @param outputEncoding The `encoding` of the return value.
-         */
-        update(data: BinaryLike): Buffer;
-        update(data: string, inputEncoding: Encoding): Buffer;
-        update(data: NodeJS.ArrayBufferView, inputEncoding: undefined, outputEncoding: Encoding): string;
-        update(data: string, inputEncoding: Encoding | undefined, outputEncoding: Encoding): string;
-        /**
-         * Once the `cipher.final()` method has been called, the `Cipher` object can no
-         * longer be used to encrypt data. Attempts to call `cipher.final()` more than
-         * once will result in an error being thrown.
-         * @since v0.1.94
-         * @param outputEncoding The `encoding` of the return value.
-         * @return Any remaining enciphered contents. If `outputEncoding` is specified, a string is returned. If an `outputEncoding` is not provided, a {@link Buffer} is returned.
-         */
-        final(): Buffer;
-        final(outputEncoding: BufferEncoding): string;
-        /**
-         * When using block encryption algorithms, the `Cipher` class will automatically
-         * add padding to the input data to the appropriate block size. To disable the
-         * default padding call `cipher.setAutoPadding(false)`.
-         *
-         * When `autoPadding` is `false`, the length of the entire input data must be a
-         * multiple of the cipher's block size or `cipher.final()` will throw an error.
-         * Disabling automatic padding is useful for non-standard padding, for instance
-         * using `0x0` instead of PKCS padding.
-         *
-         * The `cipher.setAutoPadding()` method must be called before `cipher.final()`.
-         * @since v0.7.1
-         * @param [autoPadding=true]
-         * @return for method chaining.
-         */
-        setAutoPadding(autoPadding?: boolean): this;
-    }
-    interface CipherCCM extends Cipher {
-        setAAD(
-            buffer: NodeJS.ArrayBufferView,
-            options: {
-                plaintextLength: number;
-            }
-        ): this;
-        getAuthTag(): Buffer;
-    }
-    interface CipherGCM extends Cipher {
-        setAAD(
-            buffer: NodeJS.ArrayBufferView,
-            options?: {
-                plaintextLength: number;
-            }
-        ): this;
-        getAuthTag(): Buffer;
-    }
-    interface CipherOCB extends Cipher {
-        setAAD(
-            buffer: NodeJS.ArrayBufferView,
-            options?: {
-                plaintextLength: number;
-            }
-        ): this;
-        getAuthTag(): Buffer;
-    }
-    /**
-     * Creates and returns a `Decipher` object that uses the given `algorithm` and`password` (key).
-     *
-     * The `options` argument controls stream behavior and is optional except when a
-     * cipher in CCM or OCB mode (e.g. `'aes-128-ccm'`) is used. In that case, the`authTagLength` option is required and specifies the length of the
-     * authentication tag in bytes, see `CCM mode`.
-     * For `chacha20-poly1305`, the `authTagLength` option defaults to 16 bytes.
-     *
-     * The implementation of `crypto.createDecipher()` derives keys using the OpenSSL
-     * function [`EVP_BytesToKey`](https://www.openssl.org/docs/man1.1.0/crypto/EVP_BytesToKey.html) with the digest algorithm set to MD5, one
-     * iteration, and no salt. The lack of salt allows dictionary attacks as the same
-     * password always creates the same key. The low iteration count and
-     * non-cryptographically secure hash algorithm allow passwords to be tested very
-     * rapidly.
-     *
-     * In line with OpenSSL's recommendation to use a more modern algorithm instead of [`EVP_BytesToKey`](https://www.openssl.org/docs/man1.1.0/crypto/EVP_BytesToKey.html) it is recommended that
-     * developers derive a key and IV on
-     * their own using {@link scrypt} and to use {@link createDecipheriv} to create the `Decipher` object.
-     * @since v0.1.94
-     * @deprecated Since v10.0.0 - Use {@link createDecipheriv} instead.
-     * @param options `stream.transform` options
-     */
-    function createDecipher(algorithm: CipherCCMTypes, password: BinaryLike, options: CipherCCMOptions): DecipherCCM;
-    /** @deprecated since v10.0.0 use `createDecipheriv()` */
-    function createDecipher(algorithm: CipherGCMTypes, password: BinaryLike, options?: CipherGCMOptions): DecipherGCM;
-    /** @deprecated since v10.0.0 use `createDecipheriv()` */
-    function createDecipher(algorithm: string, password: BinaryLike, options?: stream.TransformOptions): Decipher;
-    /**
-     * Creates and returns a `Decipher` object that uses the given `algorithm`, `key`and initialization vector (`iv`).
-     *
-     * The `options` argument controls stream behavior and is optional except when a
-     * cipher in CCM or OCB mode (e.g. `'aes-128-ccm'`) is used. In that case, the`authTagLength` option is required and specifies the length of the
-     * authentication tag in bytes, see `CCM mode`. In GCM mode, the `authTagLength`option is not required but can be used to restrict accepted authentication tags
-     * to those with the specified length.
-     * For `chacha20-poly1305`, the `authTagLength` option defaults to 16 bytes.
-     *
-     * The `algorithm` is dependent on OpenSSL, examples are `'aes192'`, etc. On
-     * recent OpenSSL releases, `openssl list -cipher-algorithms` will
-     * display the available cipher algorithms.
-     *
-     * The `key` is the raw key used by the `algorithm` and `iv` is an [initialization vector](https://en.wikipedia.org/wiki/Initialization_vector). Both arguments must be `'utf8'` encoded
-     * strings,`Buffers`, `TypedArray`, or `DataView`s. The `key` may optionally be
-     * a `KeyObject` of type `secret`. If the cipher does not need
-     * an initialization vector, `iv` may be `null`.
-     *
-     * When passing strings for `key` or `iv`, please consider `caveats when using strings as inputs to cryptographic APIs`.
-     *
-     * Initialization vectors should be unpredictable and unique; ideally, they will be
-     * cryptographically random. They do not have to be secret: IVs are typically just
-     * added to ciphertext messages unencrypted. It may sound contradictory that
-     * something has to be unpredictable and unique, but does not have to be secret;
-     * remember that an attacker must not be able to predict ahead of time what a given
-     * IV will be.
-     * @since v0.1.94
-     * @param options `stream.transform` options
-     */
-    function createDecipheriv(algorithm: CipherCCMTypes, key: CipherKey, iv: BinaryLike, options: CipherCCMOptions): DecipherCCM;
-    function createDecipheriv(algorithm: CipherOCBTypes, key: CipherKey, iv: BinaryLike, options: CipherOCBOptions): DecipherOCB;
-    function createDecipheriv(algorithm: CipherGCMTypes, key: CipherKey, iv: BinaryLike, options?: CipherGCMOptions): DecipherGCM;
-    function createDecipheriv(algorithm: string, key: CipherKey, iv: BinaryLike | null, options?: stream.TransformOptions): Decipher;
-    /**
-     * Instances of the `Decipher` class are used to decrypt data. The class can be
-     * used in one of two ways:
-     *
-     * * As a `stream` that is both readable and writable, where plain encrypted
-     * data is written to produce unencrypted data on the readable side, or
-     * * Using the `decipher.update()` and `decipher.final()` methods to
-     * produce the unencrypted data.
-     *
-     * The {@link createDecipher} or {@link createDecipheriv} methods are
-     * used to create `Decipher` instances. `Decipher` objects are not to be created
-     * directly using the `new` keyword.
-     *
-     * Example: Using `Decipher` objects as streams:
-     *
-     * ```js
-     * import { Buffer } from 'buffer';
-     * const {
-     *   scryptSync,
-     *   createDecipheriv
-     * } = await import('crypto');
-     *
-     * const algorithm = 'aes-192-cbc';
-     * const password = 'Password used to generate key';
-     * // Key length is dependent on the algorithm. In this case for aes192, it is
-     * // 24 bytes (192 bits).
-     * // Use the async `crypto.scrypt()` instead.
-     * const key = scryptSync(password, 'salt', 24);
-     * // The IV is usually passed along with the ciphertext.
-     * const iv = Buffer.alloc(16, 0); // Initialization vector.
-     *
-     * const decipher = createDecipheriv(algorithm, key, iv);
-     *
-     * let decrypted = '';
-     * decipher.on('readable', () => {
-     *   while (null !== (chunk = decipher.read())) {
-     *     decrypted += chunk.toString('utf8');
-     *   }
-     * });
-     * decipher.on('end', () => {
-     *   console.log(decrypted);
-     *   // Prints: some clear text data
-     * });
-     *
-     * // Encrypted with same algorithm, key and iv.
-     * const encrypted =
-     *   'e5f79c5915c02171eec6b212d5520d44480993d7d622a7c4c2da32f6efda0ffa';
-     * decipher.write(encrypted, 'hex');
-     * decipher.end();
-     * ```
-     *
-     * Example: Using `Decipher` and piped streams:
-     *
-     * ```js
-     * import {
-     *   createReadStream,
-     *   createWriteStream,
-     * } from 'fs';
-     * import { Buffer } from 'buffer';
-     * const {
-     *   scryptSync,
-     *   createDecipheriv
-     * } = await import('crypto');
-     *
-     * const algorithm = 'aes-192-cbc';
-     * const password = 'Password used to generate key';
-     * // Use the async `crypto.scrypt()` instead.
-     * const key = scryptSync(password, 'salt', 24);
-     * // The IV is usually passed along with the ciphertext.
-     * const iv = Buffer.alloc(16, 0); // Initialization vector.
-     *
-     * const decipher = createDecipheriv(algorithm, key, iv);
-     *
-     * const input = createReadStream('test.enc');
-     * const output = createWriteStream('test.js');
-     *
-     * input.pipe(decipher).pipe(output);
-     * ```
-     *
-     * Example: Using the `decipher.update()` and `decipher.final()` methods:
-     *
-     * ```js
-     * import { Buffer } from 'buffer';
-     * const {
-     *   scryptSync,
-     *   createDecipheriv
-     * } = await import('crypto');
-     *
-     * const algorithm = 'aes-192-cbc';
-     * const password = 'Password used to generate key';
-     * // Use the async `crypto.scrypt()` instead.
-     * const key = scryptSync(password, 'salt', 24);
-     * // The IV is usually passed along with the ciphertext.
-     * const iv = Buffer.alloc(16, 0); // Initialization vector.
-     *
-     * const decipher = createDecipheriv(algorithm, key, iv);
-     *
-     * // Encrypted using same algorithm, key and iv.
-     * const encrypted =
-     *   'e5f79c5915c02171eec6b212d5520d44480993d7d622a7c4c2da32f6efda0ffa';
-     * let decrypted = decipher.update(encrypted, 'hex', 'utf8');
-     * decrypted += decipher.final('utf8');
-     * console.log(decrypted);
-     * // Prints: some clear text data
-     * ```
-     * @since v0.1.94
-     */
-    class Decipher extends stream.Transform {
-        private constructor();
-        /**
-         * Updates the decipher with `data`. If the `inputEncoding` argument is given,
-         * the `data`argument is a string using the specified encoding. If the `inputEncoding`argument is not given, `data` must be a `Buffer`. If `data` is a `Buffer` then `inputEncoding` is
-         * ignored.
-         *
-         * The `outputEncoding` specifies the output format of the enciphered
-         * data. If the `outputEncoding`is specified, a string using the specified encoding is returned. If no`outputEncoding` is provided, a `Buffer` is returned.
-         *
-         * The `decipher.update()` method can be called multiple times with new data until `decipher.final()` is called. Calling `decipher.update()` after `decipher.final()` will result in an error
-         * being thrown.
-         * @since v0.1.94
-         * @param inputEncoding The `encoding` of the `data` string.
-         * @param outputEncoding The `encoding` of the return value.
-         */
-        update(data: NodeJS.ArrayBufferView): Buffer;
-        update(data: string, inputEncoding: Encoding): Buffer;
-        update(data: NodeJS.ArrayBufferView, inputEncoding: undefined, outputEncoding: Encoding): string;
-        update(data: string, inputEncoding: Encoding | undefined, outputEncoding: Encoding): string;
-        /**
-         * Once the `decipher.final()` method has been called, the `Decipher` object can
-         * no longer be used to decrypt data. Attempts to call `decipher.final()` more
-         * than once will result in an error being thrown.
-         * @since v0.1.94
-         * @param outputEncoding The `encoding` of the return value.
-         * @return Any remaining deciphered contents. If `outputEncoding` is specified, a string is returned. If an `outputEncoding` is not provided, a {@link Buffer} is returned.
-         */
-        final(): Buffer;
-        final(outputEncoding: BufferEncoding): string;
-        /**
-         * When data has been encrypted without standard block padding, calling`decipher.setAutoPadding(false)` will disable automatic padding to prevent `decipher.final()` from checking for and
-         * removing padding.
-         *
-         * Turning auto padding off will only work if the input data's length is a
-         * multiple of the ciphers block size.
-         *
-         * The `decipher.setAutoPadding()` method must be called before `decipher.final()`.
-         * @since v0.7.1
-         * @param [autoPadding=true]
-         * @return for method chaining.
-         */
-        setAutoPadding(auto_padding?: boolean): this;
-    }
-    interface DecipherCCM extends Decipher {
-        setAuthTag(buffer: NodeJS.ArrayBufferView): this;
-        setAAD(
-            buffer: NodeJS.ArrayBufferView,
-            options: {
-                plaintextLength: number;
-            }
-        ): this;
-    }
-    interface DecipherGCM extends Decipher {
-        setAuthTag(buffer: NodeJS.ArrayBufferView): this;
-        setAAD(
-            buffer: NodeJS.ArrayBufferView,
-            options?: {
-                plaintextLength: number;
-            }
-        ): this;
-    }
-    interface DecipherOCB extends Decipher {
-        setAuthTag(buffer: NodeJS.ArrayBufferView): this;
-        setAAD(
-            buffer: NodeJS.ArrayBufferView,
-            options?: {
-                plaintextLength: number;
-            }
-        ): this;
-    }
-    interface PrivateKeyInput {
-        key: string | Buffer;
-        format?: KeyFormat | undefined;
-        type?: 'pkcs1' | 'pkcs8' | 'sec1' | undefined;
-        passphrase?: string | Buffer | undefined;
-        encoding?: string | undefined;
-    }
-    interface PublicKeyInput {
-        key: string | Buffer;
-        format?: KeyFormat | undefined;
-        type?: 'pkcs1' | 'spki' | undefined;
-        encoding?: string | undefined;
-    }
-    /**
-     * Asynchronously generates a new random secret key of the given `length`. The`type` will determine which validations will be performed on the `length`.
-     *
-     * ```js
-     * const {
-     *   generateKey
-     * } = await import('crypto');
-     *
-     * generateKey('hmac', { length: 64 }, (err, key) => {
-     *   if (err) throw err;
-     *   console.log(key.export().toString('hex'));  // 46e..........620
-     * });
-     * ```
-     * @since v15.0.0
-     * @param type The intended use of the generated secret key. Currently accepted values are `'hmac'` and `'aes'`.
-     */
-    function generateKey(
-        type: 'hmac' | 'aes',
-        options: {
-            length: number;
-        },
-        callback: (err: Error | null, key: KeyObject) => void
-    ): void;
-    /**
-     * Synchronously generates a new random secret key of the given `length`. The`type` will determine which validations will be performed on the `length`.
-     *
-     * ```js
-     * const {
-     *   generateKeySync
-     * } = await import('crypto');
-     *
-     * const key = generateKeySync('hmac', { length: 64 });
-     * console.log(key.export().toString('hex'));  // e89..........41e
-     * ```
-     * @since v15.0.0
-     * @param type The intended use of the generated secret key. Currently accepted values are `'hmac'` and `'aes'`.
-     */
-    function generateKeySync(
-        type: 'hmac' | 'aes',
-        options: {
-            length: number;
-        }
-    ): KeyObject;
-    interface JsonWebKeyInput {
-        key: JsonWebKey;
-        format: 'jwk';
-    }
-    /**
-     * Creates and returns a new key object containing a private key. If `key` is a
-     * string or `Buffer`, `format` is assumed to be `'pem'`; otherwise, `key`must be an object with the properties described above.
-     *
-     * If the private key is encrypted, a `passphrase` must be specified. The length
-     * of the passphrase is limited to 1024 bytes.
-     * @since v11.6.0
-     */
-    function createPrivateKey(key: PrivateKeyInput | string | Buffer | JsonWebKeyInput): KeyObject;
-    /**
-     * Creates and returns a new key object containing a public key. If `key` is a
-     * string or `Buffer`, `format` is assumed to be `'pem'`; if `key` is a `KeyObject`with type `'private'`, the public key is derived from the given private key;
-     * otherwise, `key` must be an object with the properties described above.
-     *
-     * If the format is `'pem'`, the `'key'` may also be an X.509 certificate.
-     *
-     * Because public keys can be derived from private keys, a private key may be
-     * passed instead of a public key. In that case, this function behaves as if {@link createPrivateKey} had been called, except that the type of the
-     * returned `KeyObject` will be `'public'` and that the private key cannot be
-     * extracted from the returned `KeyObject`. Similarly, if a `KeyObject` with type`'private'` is given, a new `KeyObject` with type `'public'` will be returned
-     * and it will be impossible to extract the private key from the returned object.
-     * @since v11.6.0
-     */
-    function createPublicKey(key: PublicKeyInput | string | Buffer | KeyObject | JsonWebKeyInput): KeyObject;
-    /**
-     * Creates and returns a new key object containing a secret key for symmetric
-     * encryption or `Hmac`.
-     * @since v11.6.0
-     * @param encoding The string encoding when `key` is a string.
-     */
-    function createSecretKey(key: NodeJS.ArrayBufferView): KeyObject;
-    function createSecretKey(key: string, encoding: BufferEncoding): KeyObject;
-    /**
-     * Creates and returns a `Sign` object that uses the given `algorithm`. Use {@link getHashes} to obtain the names of the available digest algorithms.
-     * Optional `options` argument controls the `stream.Writable` behavior.
-     *
-     * In some cases, a `Sign` instance can be created using the name of a signature
-     * algorithm, such as `'RSA-SHA256'`, instead of a digest algorithm. This will use
-     * the corresponding digest algorithm. This does not work for all signature
-     * algorithms, such as `'ecdsa-with-SHA256'`, so it is best to always use digest
-     * algorithm names.
-     * @since v0.1.92
-     * @param options `stream.Writable` options
-     */
-    function createSign(algorithm: string, options?: stream.WritableOptions): Sign;
-    type DSAEncoding = 'der' | 'ieee-p1363';
-    interface SigningOptions {
-        /**
-         * @See crypto.constants.RSA_PKCS1_PADDING
-         */
-        padding?: number | undefined;
-        saltLength?: number | undefined;
-        dsaEncoding?: DSAEncoding | undefined;
-    }
-    interface SignPrivateKeyInput extends PrivateKeyInput, SigningOptions {}
-    interface SignKeyObjectInput extends SigningOptions {
-        key: KeyObject;
-    }
-    interface VerifyPublicKeyInput extends PublicKeyInput, SigningOptions {}
-    interface VerifyKeyObjectInput extends SigningOptions {
-        key: KeyObject;
-    }
-    type KeyLike = string | Buffer | KeyObject;
-    /**
-     * The `Sign` class is a utility for generating signatures. It can be used in one
-     * of two ways:
-     *
-     * * As a writable `stream`, where data to be signed is written and the `sign.sign()` method is used to generate and return the signature, or
-     * * Using the `sign.update()` and `sign.sign()` methods to produce the
-     * signature.
-     *
-     * The {@link createSign} method is used to create `Sign` instances. The
-     * argument is the string name of the hash function to use. `Sign` objects are not
-     * to be created directly using the `new` keyword.
-     *
-     * Example: Using `Sign` and `Verify` objects as streams:
-     *
-     * ```js
-     * const {
-     *   generateKeyPairSync,
-     *   createSign,
-     *   createVerify
-     * } = await import('crypto');
-     *
-     * const { privateKey, publicKey } = generateKeyPairSync('ec', {
-     *   namedCurve: 'sect239k1'
-     * });
-     *
-     * const sign = createSign('SHA256');
-     * sign.write('some data to sign');
-     * sign.end();
-     * const signature = sign.sign(privateKey, 'hex');
-     *
-     * const verify = createVerify('SHA256');
-     * verify.write('some data to sign');
-     * verify.end();
-     * console.log(verify.verify(publicKey, signature, 'hex'));
-     * // Prints: true
-     * ```
-     *
-     * Example: Using the `sign.update()` and `verify.update()` methods:
-     *
-     * ```js
-     * const {
-     *   generateKeyPairSync,
-     *   createSign,
-     *   createVerify
-     * } = await import('crypto');
-     *
-     * const { privateKey, publicKey } = generateKeyPairSync('rsa', {
-     *   modulusLength: 2048,
-     * });
-     *
-     * const sign = createSign('SHA256');
-     * sign.update('some data to sign');
-     * sign.end();
-     * const signature = sign.sign(privateKey);
-     *
-     * const verify = createVerify('SHA256');
-     * verify.update('some data to sign');
-     * verify.end();
-     * console.log(verify.verify(publicKey, signature));
-     * // Prints: true
-     * ```
-     * @since v0.1.92
-     */
-    class Sign extends stream.Writable {
-        private constructor();
-        /**
-         * Updates the `Sign` content with the given `data`, the encoding of which
-         * is given in `inputEncoding`.
-         * If `encoding` is not provided, and the `data` is a string, an
-         * encoding of `'utf8'` is enforced. If `data` is a `Buffer`, `TypedArray`, or`DataView`, then `inputEncoding` is ignored.
-         *
-         * This can be called many times with new data as it is streamed.
-         * @since v0.1.92
-         * @param inputEncoding The `encoding` of the `data` string.
-         */
-        update(data: BinaryLike): this;
-        update(data: string, inputEncoding: Encoding): this;
-        /**
-         * Calculates the signature on all the data passed through using either `sign.update()` or `sign.write()`.
-         *
-         * If `privateKey` is not a `KeyObject`, this function behaves as if`privateKey` had been passed to {@link createPrivateKey}. If it is an
-         * object, the following additional properties can be passed:
-         *
-         * If `outputEncoding` is provided a string is returned; otherwise a `Buffer` is returned.
-         *
-         * The `Sign` object can not be again used after `sign.sign()` method has been
-         * called. Multiple calls to `sign.sign()` will result in an error being thrown.
-         * @since v0.1.92
-         */
-        sign(privateKey: KeyLike | SignKeyObjectInput | SignPrivateKeyInput): Buffer;
-        sign(privateKey: KeyLike | SignKeyObjectInput | SignPrivateKeyInput, outputFormat: BinaryToTextEncoding): string;
-    }
-    /**
-     * Creates and returns a `Verify` object that uses the given algorithm.
-     * Use {@link getHashes} to obtain an array of names of the available
-     * signing algorithms. Optional `options` argument controls the`stream.Writable` behavior.
-     *
-     * In some cases, a `Verify` instance can be created using the name of a signature
-     * algorithm, such as `'RSA-SHA256'`, instead of a digest algorithm. This will use
-     * the corresponding digest algorithm. This does not work for all signature
-     * algorithms, such as `'ecdsa-with-SHA256'`, so it is best to always use digest
-     * algorithm names.
-     * @since v0.1.92
-     * @param options `stream.Writable` options
-     */
-    function createVerify(algorithm: string, options?: stream.WritableOptions): Verify;
-    /**
-     * The `Verify` class is a utility for verifying signatures. It can be used in one
-     * of two ways:
-     *
-     * * As a writable `stream` where written data is used to validate against the
-     * supplied signature, or
-     * * Using the `verify.update()` and `verify.verify()` methods to verify
-     * the signature.
-     *
-     * The {@link createVerify} method is used to create `Verify` instances.`Verify` objects are not to be created directly using the `new` keyword.
-     *
-     * See `Sign` for examples.
-     * @since v0.1.92
-     */
-    class Verify extends stream.Writable {
-        private constructor();
-        /**
-         * Updates the `Verify` content with the given `data`, the encoding of which
-         * is given in `inputEncoding`.
-         * If `inputEncoding` is not provided, and the `data` is a string, an
-         * encoding of `'utf8'` is enforced. If `data` is a `Buffer`, `TypedArray`, or`DataView`, then `inputEncoding` is ignored.
-         *
-         * This can be called many times with new data as it is streamed.
-         * @since v0.1.92
-         * @param inputEncoding The `encoding` of the `data` string.
-         */
-        update(data: BinaryLike): Verify;
-        update(data: string, inputEncoding: Encoding): Verify;
-        /**
-         * Verifies the provided data using the given `object` and `signature`.
-         *
-         * If `object` is not a `KeyObject`, this function behaves as if`object` had been passed to {@link createPublicKey}. If it is an
-         * object, the following additional properties can be passed:
-         *
-         * The `signature` argument is the previously calculated signature for the data, in
-         * the `signatureEncoding`.
-         * If a `signatureEncoding` is specified, the `signature` is expected to be a
-         * string; otherwise `signature` is expected to be a `Buffer`,`TypedArray`, or `DataView`.
-         *
-         * The `verify` object can not be used again after `verify.verify()` has been
-         * called. Multiple calls to `verify.verify()` will result in an error being
-         * thrown.
-         *
-         * Because public keys can be derived from private keys, a private key may
-         * be passed instead of a public key.
-         * @since v0.1.92
-         */
-        verify(object: KeyLike | VerifyKeyObjectInput | VerifyPublicKeyInput, signature: NodeJS.ArrayBufferView): boolean;
-        verify(object: KeyLike | VerifyKeyObjectInput | VerifyPublicKeyInput, signature: string, signature_format?: BinaryToTextEncoding): boolean;
-    }
-    /**
-     * Creates a `DiffieHellman` key exchange object using the supplied `prime` and an
-     * optional specific `generator`.
-     *
-     * The `generator` argument can be a number, string, or `Buffer`. If`generator` is not specified, the value `2` is used.
-     *
-     * If `primeEncoding` is specified, `prime` is expected to be a string; otherwise
-     * a `Buffer`, `TypedArray`, or `DataView` is expected.
-     *
-     * If `generatorEncoding` is specified, `generator` is expected to be a string;
-     * otherwise a number, `Buffer`, `TypedArray`, or `DataView` is expected.
-     * @since v0.11.12
-     * @param primeEncoding The `encoding` of the `prime` string.
-     * @param [generator=2]
-     * @param generatorEncoding The `encoding` of the `generator` string.
-     */
-    function createDiffieHellman(primeLength: number, generator?: number): DiffieHellman;
-    function createDiffieHellman(prime: ArrayBuffer | NodeJS.ArrayBufferView, generator?: number | ArrayBuffer | NodeJS.ArrayBufferView): DiffieHellman;
-    function createDiffieHellman(prime: ArrayBuffer | NodeJS.ArrayBufferView, generator: string, generatorEncoding: BinaryToTextEncoding): DiffieHellman;
-    function createDiffieHellman(prime: string, primeEncoding: BinaryToTextEncoding, generator?: number | ArrayBuffer | NodeJS.ArrayBufferView): DiffieHellman;
-    function createDiffieHellman(prime: string, primeEncoding: BinaryToTextEncoding, generator: string, generatorEncoding: BinaryToTextEncoding): DiffieHellman;
-    /**
-     * The `DiffieHellman` class is a utility for creating Diffie-Hellman key
-     * exchanges.
-     *
-     * Instances of the `DiffieHellman` class can be created using the {@link createDiffieHellman} function.
-     *
-     * ```js
-     * import assert from 'assert';
-     *
-     * const {
-     *   createDiffieHellman
-     * } = await import('crypto');
-     *
-     * // Generate Alice's keys...
-     * const alice = createDiffieHellman(2048);
-     * const aliceKey = alice.generateKeys();
-     *
-     * // Generate Bob's keys...
-     * const bob = createDiffieHellman(alice.getPrime(), alice.getGenerator());
-     * const bobKey = bob.generateKeys();
-     *
-     * // Exchange and generate the secret...
-     * const aliceSecret = alice.computeSecret(bobKey);
-     * const bobSecret = bob.computeSecret(aliceKey);
-     *
-     * // OK
-     * assert.strictEqual(aliceSecret.toString('hex'), bobSecret.toString('hex'));
-     * ```
-     * @since v0.5.0
-     */
-    class DiffieHellman {
-        private constructor();
-        /**
-         * Generates private and public Diffie-Hellman key values, and returns
-         * the public key in the specified `encoding`. This key should be
-         * transferred to the other party.
-         * If `encoding` is provided a string is returned; otherwise a `Buffer` is returned.
-         * @since v0.5.0
-         * @param encoding The `encoding` of the return value.
-         */
-        generateKeys(): Buffer;
-        generateKeys(encoding: BinaryToTextEncoding): string;
-        /**
-         * Computes the shared secret using `otherPublicKey` as the other
-         * party's public key and returns the computed shared secret. The supplied
-         * key is interpreted using the specified `inputEncoding`, and secret is
-         * encoded using specified `outputEncoding`.
-         * If the `inputEncoding` is not
-         * provided, `otherPublicKey` is expected to be a `Buffer`,`TypedArray`, or `DataView`.
-         *
-         * If `outputEncoding` is given a string is returned; otherwise, a `Buffer` is returned.
-         * @since v0.5.0
-         * @param inputEncoding The `encoding` of an `otherPublicKey` string.
-         * @param outputEncoding The `encoding` of the return value.
-         */
-        computeSecret(otherPublicKey: NodeJS.ArrayBufferView, inputEncoding?: null, outputEncoding?: null): Buffer;
-        computeSecret(otherPublicKey: string, inputEncoding: BinaryToTextEncoding, outputEncoding?: null): Buffer;
-        computeSecret(otherPublicKey: NodeJS.ArrayBufferView, inputEncoding: null, outputEncoding: BinaryToTextEncoding): string;
-        computeSecret(otherPublicKey: string, inputEncoding: BinaryToTextEncoding, outputEncoding: BinaryToTextEncoding): string;
-        /**
-         * Returns the Diffie-Hellman prime in the specified `encoding`.
-         * If `encoding` is provided a string is
-         * returned; otherwise a `Buffer` is returned.
-         * @since v0.5.0
-         * @param encoding The `encoding` of the return value.
-         */
-        getPrime(): Buffer;
-        getPrime(encoding: BinaryToTextEncoding): string;
-        /**
-         * Returns the Diffie-Hellman generator in the specified `encoding`.
-         * If `encoding` is provided a string is
-         * returned; otherwise a `Buffer` is returned.
-         * @since v0.5.0
-         * @param encoding The `encoding` of the return value.
-         */
-        getGenerator(): Buffer;
-        getGenerator(encoding: BinaryToTextEncoding): string;
-        /**
-         * Returns the Diffie-Hellman public key in the specified `encoding`.
-         * If `encoding` is provided a
-         * string is returned; otherwise a `Buffer` is returned.
-         * @since v0.5.0
-         * @param encoding The `encoding` of the return value.
-         */
-        getPublicKey(): Buffer;
-        getPublicKey(encoding: BinaryToTextEncoding): string;
-        /**
-         * Returns the Diffie-Hellman private key in the specified `encoding`.
-         * If `encoding` is provided a
-         * string is returned; otherwise a `Buffer` is returned.
-         * @since v0.5.0
-         * @param encoding The `encoding` of the return value.
-         */
-        getPrivateKey(): Buffer;
-        getPrivateKey(encoding: BinaryToTextEncoding): string;
-        /**
-         * Sets the Diffie-Hellman public key. If the `encoding` argument is provided,`publicKey` is expected
-         * to be a string. If no `encoding` is provided, `publicKey` is expected
-         * to be a `Buffer`, `TypedArray`, or `DataView`.
-         * @since v0.5.0
-         * @param encoding The `encoding` of the `publicKey` string.
-         */
-        setPublicKey(publicKey: NodeJS.ArrayBufferView): void;
-        setPublicKey(publicKey: string, encoding: BufferEncoding): void;
-        /**
-         * Sets the Diffie-Hellman private key. If the `encoding` argument is provided,`privateKey` is expected
-         * to be a string. If no `encoding` is provided, `privateKey` is expected
-         * to be a `Buffer`, `TypedArray`, or `DataView`.
-         * @since v0.5.0
-         * @param encoding The `encoding` of the `privateKey` string.
-         */
-        setPrivateKey(privateKey: NodeJS.ArrayBufferView): void;
-        setPrivateKey(privateKey: string, encoding: BufferEncoding): void;
-        /**
-         * A bit field containing any warnings and/or errors resulting from a check
-         * performed during initialization of the `DiffieHellman` object.
-         *
-         * The following values are valid for this property (as defined in `constants`module):
-         *
-         * * `DH_CHECK_P_NOT_SAFE_PRIME`
-         * * `DH_CHECK_P_NOT_PRIME`
-         * * `DH_UNABLE_TO_CHECK_GENERATOR`
-         * * `DH_NOT_SUITABLE_GENERATOR`
-         * @since v0.11.12
-         */
-        verifyError: number;
-    }
-    /**
-     * The `DiffieHellmanGroup` class takes a well-known modp group as its argument.
-     * It works the same as `DiffieHellman`, except that it does not allow changing its keys after creation.
-     * In other words, it does not implement `setPublicKey()` or `setPrivateKey()` methods.
-     *
-     * ```js
-     * const { createDiffieHellmanGroup } = await import('node:crypto');
-     * const dh = createDiffieHellmanGroup('modp1');
-     * ```
-     * The name (e.g. `'modp1'`) is taken from [RFC 2412](https://www.rfc-editor.org/rfc/rfc2412.txt) (modp1 and 2) and [RFC 3526](https://www.rfc-editor.org/rfc/rfc3526.txt):
-     * ```bash
-     * $ perl -ne 'print "$1\n" if /"(modp\d+)"/' src/node_crypto_groups.h
-     * modp1  #  768 bits
-     * modp2  # 1024 bits
-     * modp5  # 1536 bits
-     * modp14 # 2048 bits
-     * modp15 # etc.
-     * modp16
-     * modp17
-     * modp18
-     * ```
-     * @since v0.7.5
-     */
-    const DiffieHellmanGroup: DiffieHellmanGroupConstructor;
-    interface DiffieHellmanGroupConstructor {
-        new(name: string): DiffieHellmanGroup;
-        (name: string): DiffieHellmanGroup;
-        readonly prototype: DiffieHellmanGroup;
-    }
-    type DiffieHellmanGroup = Omit<DiffieHellman, 'setPublicKey' | 'setPrivateKey'>;
-    /**
-     * Creates a predefined `DiffieHellmanGroup` key exchange object. The
-     * supported groups are: `'modp1'`, `'modp2'`, `'modp5'` (defined in [RFC 2412](https://www.rfc-editor.org/rfc/rfc2412.txt), but see `Caveats`) and `'modp14'`, `'modp15'`,`'modp16'`, `'modp17'`,
-     * `'modp18'` (defined in [RFC 3526](https://www.rfc-editor.org/rfc/rfc3526.txt)). The
-     * returned object mimics the interface of objects created by {@link createDiffieHellman}, but will not allow changing
-     * the keys (with `diffieHellman.setPublicKey()`, for example). The
-     * advantage of using this method is that the parties do not have to
-     * generate nor exchange a group modulus beforehand, saving both processor
-     * and communication time.
-     *
-     * Example (obtaining a shared secret):
-     *
-     * ```js
-     * const {
-     *   getDiffieHellman
-     * } = await import('crypto');
-     * const alice = getDiffieHellman('modp14');
-     * const bob = getDiffieHellman('modp14');
-     *
-     * alice.generateKeys();
-     * bob.generateKeys();
-     *
-     * const aliceSecret = alice.computeSecret(bob.getPublicKey(), null, 'hex');
-     * const bobSecret = bob.computeSecret(alice.getPublicKey(), null, 'hex');
-     *
-     * // aliceSecret and bobSecret should be the same
-     * console.log(aliceSecret === bobSecret);
-     * ```
-     * @since v0.7.5
-     */
-    function getDiffieHellman(groupName: string): DiffieHellmanGroup;
-    /**
-     * An alias for {@link getDiffieHellman}
-     * @since v0.9.3
-     */
-    function createDiffieHellmanGroup(name: string): DiffieHellmanGroup;
-    /**
-     * Provides an asynchronous Password-Based Key Derivation Function 2 (PBKDF2)
-     * implementation. A selected HMAC digest algorithm specified by `digest` is
-     * applied to derive a key of the requested byte length (`keylen`) from the`password`, `salt` and `iterations`.
-     *
-     * The supplied `callback` function is called with two arguments: `err` and`derivedKey`. If an error occurs while deriving the key, `err` will be set;
-     * otherwise `err` will be `null`. By default, the successfully generated`derivedKey` will be passed to the callback as a `Buffer`. An error will be
-     * thrown if any of the input arguments specify invalid values or types.
-     *
-     * If `digest` is `null`, `'sha1'` will be used. This behavior is deprecated,
-     * please specify a `digest` explicitly.
-     *
-     * The `iterations` argument must be a number set as high as possible. The
-     * higher the number of iterations, the more secure the derived key will be,
-     * but will take a longer amount of time to complete.
-     *
-     * The `salt` should be as unique as possible. It is recommended that a salt is
-     * random and at least 16 bytes long. See [NIST SP 800-132](https://nvlpubs.nist.gov/nistpubs/Legacy/SP/nistspecialpublication800-132.pdf) for details.
-     *
-     * When passing strings for `password` or `salt`, please consider `caveats when using strings as inputs to cryptographic APIs`.
-     *
-     * ```js
-     * const {
-     *   pbkdf2
-     * } = await import('crypto');
-     *
-     * pbkdf2('secret', 'salt', 100000, 64, 'sha512', (err, derivedKey) => {
-     *   if (err) throw err;
-     *   console.log(derivedKey.toString('hex'));  // '3745e48...08d59ae'
-     * });
-     * ```
-     *
-     * The `crypto.DEFAULT_ENCODING` property can be used to change the way the`derivedKey` is passed to the callback. This property, however, has been
-     * deprecated and use should be avoided.
-     *
-     * ```js
-     * import crypto from 'crypto';
-     * crypto.DEFAULT_ENCODING = 'hex';
-     * crypto.pbkdf2('secret', 'salt', 100000, 512, 'sha512', (err, derivedKey) => {
-     *   if (err) throw err;
-     *   console.log(derivedKey);  // '3745e48...aa39b34'
-     * });
-     * ```
-     *
-     * An array of supported digest functions can be retrieved using {@link getHashes}.
-     *
-     * This API uses libuv's threadpool, which can have surprising and
-     * negative performance implications for some applications; see the `UV_THREADPOOL_SIZE` documentation for more information.
-     * @since v0.5.5
-     */
-    function pbkdf2(password: BinaryLike, salt: BinaryLike, iterations: number, keylen: number, digest: string, callback: (err: Error | null, derivedKey: Buffer) => void): void;
-    /**
-     * Provides a synchronous Password-Based Key Derivation Function 2 (PBKDF2)
-     * implementation. A selected HMAC digest algorithm specified by `digest` is
-     * applied to derive a key of the requested byte length (`keylen`) from the`password`, `salt` and `iterations`.
-     *
-     * If an error occurs an `Error` will be thrown, otherwise the derived key will be
-     * returned as a `Buffer`.
-     *
-     * If `digest` is `null`, `'sha1'` will be used. This behavior is deprecated,
-     * please specify a `digest` explicitly.
-     *
-     * The `iterations` argument must be a number set as high as possible. The
-     * higher the number of iterations, the more secure the derived key will be,
-     * but will take a longer amount of time to complete.
-     *
-     * The `salt` should be as unique as possible. It is recommended that a salt is
-     * random and at least 16 bytes long. See [NIST SP 800-132](https://nvlpubs.nist.gov/nistpubs/Legacy/SP/nistspecialpublication800-132.pdf) for details.
-     *
-     * When passing strings for `password` or `salt`, please consider `caveats when using strings as inputs to cryptographic APIs`.
-     *
-     * ```js
-     * const {
-     *   pbkdf2Sync
-     * } = await import('crypto');
-     *
-     * const key = pbkdf2Sync('secret', 'salt', 100000, 64, 'sha512');
-     * console.log(key.toString('hex'));  // '3745e48...08d59ae'
-     * ```
-     *
-     * The `crypto.DEFAULT_ENCODING` property may be used to change the way the`derivedKey` is returned. This property, however, is deprecated and use
-     * should be avoided.
-     *
-     * ```js
-     * import crypto from 'crypto';
-     * crypto.DEFAULT_ENCODING = 'hex';
-     * const key = crypto.pbkdf2Sync('secret', 'salt', 100000, 512, 'sha512');
-     * console.log(key);  // '3745e48...aa39b34'
-     * ```
-     *
-     * An array of supported digest functions can be retrieved using {@link getHashes}.
-     * @since v0.9.3
-     */
-    function pbkdf2Sync(password: BinaryLike, salt: BinaryLike, iterations: number, keylen: number, digest: string): Buffer;
-    /**
-     * Generates cryptographically strong pseudorandom data. The `size` argument
-     * is a number indicating the number of bytes to generate.
-     *
-     * If a `callback` function is provided, the bytes are generated asynchronously
-     * and the `callback` function is invoked with two arguments: `err` and `buf`.
-     * If an error occurs, `err` will be an `Error` object; otherwise it is `null`. The`buf` argument is a `Buffer` containing the generated bytes.
-     *
-     * ```js
-     * // Asynchronous
-     * const {
-     *   randomBytes
-     * } = await import('crypto');
-     *
-     * randomBytes(256, (err, buf) => {
-     *   if (err) throw err;
-     *   console.log(`${buf.length} bytes of random data: ${buf.toString('hex')}`);
-     * });
-     * ```
-     *
-     * If the `callback` function is not provided, the random bytes are generated
-     * synchronously and returned as a `Buffer`. An error will be thrown if
-     * there is a problem generating the bytes.
-     *
-     * ```js
-     * // Synchronous
-     * const {
-     *   randomBytes
-     * } = await import('crypto');
-     *
-     * const buf = randomBytes(256);
-     * console.log(
-     *   `${buf.length} bytes of random data: ${buf.toString('hex')}`);
-     * ```
-     *
-     * The `crypto.randomBytes()` method will not complete until there is
-     * sufficient entropy available.
-     * This should normally never take longer than a few milliseconds. The only time
-     * when generating the random bytes may conceivably block for a longer period of
-     * time is right after boot, when the whole system is still low on entropy.
-     *
-     * This API uses libuv's threadpool, which can have surprising and
-     * negative performance implications for some applications; see the `UV_THREADPOOL_SIZE` documentation for more information.
-     *
-     * The asynchronous version of `crypto.randomBytes()` is carried out in a single
-     * threadpool request. To minimize threadpool task length variation, partition
-     * large `randomBytes` requests when doing so as part of fulfilling a client
-     * request.
-     * @since v0.5.8
-     * @param size The number of bytes to generate. The `size` must not be larger than `2**31 - 1`.
-     * @return if the `callback` function is not provided.
-     */
-    function randomBytes(size: number): Buffer;
-    function randomBytes(size: number, callback: (err: Error | null, buf: Buffer) => void): void;
-    function pseudoRandomBytes(size: number): Buffer;
-    function pseudoRandomBytes(size: number, callback: (err: Error | null, buf: Buffer) => void): void;
-    /**
-     * Return a random integer `n` such that `min <= n < max`.  This
-     * implementation avoids [modulo bias](https://en.wikipedia.org/wiki/Fisher%E2%80%93Yates_shuffle#Modulo_bias).
-     *
-     * The range (`max - min`) must be less than 2^48. `min` and `max` must
-     * be [safe integers](https://developer.mozilla.org/en-US/docs/Web/JavaScript/Reference/Global_Objects/Number/isSafeInteger).
-     *
-     * If the `callback` function is not provided, the random integer is
-     * generated synchronously.
-     *
-     * ```js
-     * // Asynchronous
-     * const {
-     *   randomInt
-     * } = await import('crypto');
-     *
-     * randomInt(3, (err, n) => {
-     *   if (err) throw err;
-     *   console.log(`Random number chosen from (0, 1, 2): ${n}`);
-     * });
-     * ```
-     *
-     * ```js
-     * // Synchronous
-     * const {
-     *   randomInt
-     * } = await import('crypto');
-     *
-     * const n = randomInt(3);
-     * console.log(`Random number chosen from (0, 1, 2): ${n}`);
-     * ```
-     *
-     * ```js
-     * // With `min` argument
-     * const {
-     *   randomInt
-     * } = await import('crypto');
-     *
-     * const n = randomInt(1, 7);
-     * console.log(`The dice rolled: ${n}`);
-     * ```
-     * @since v14.10.0, v12.19.0
-     * @param [min=0] Start of random range (inclusive).
-     * @param max End of random range (exclusive).
-     * @param callback `function(err, n) {}`.
-     */
-    function randomInt(max: number): number;
-    function randomInt(min: number, max: number): number;
-    function randomInt(max: number, callback: (err: Error | null, value: number) => void): void;
-    function randomInt(min: number, max: number, callback: (err: Error | null, value: number) => void): void;
-    /**
-     * Synchronous version of {@link randomFill}.
-     *
-     * ```js
-     * import { Buffer } from 'buffer';
-     * const { randomFillSync } = await import('crypto');
-     *
-     * const buf = Buffer.alloc(10);
-     * console.log(randomFillSync(buf).toString('hex'));
-     *
-     * randomFillSync(buf, 5);
-     * console.log(buf.toString('hex'));
-     *
-     * // The above is equivalent to the following:
-     * randomFillSync(buf, 5, 5);
-     * console.log(buf.toString('hex'));
-     * ```
-     *
-     * Any `ArrayBuffer`, `TypedArray` or `DataView` instance may be passed as`buffer`.
-     *
-     * ```js
-     * import { Buffer } from 'buffer';
-     * const { randomFillSync } = await import('crypto');
-     *
-     * const a = new Uint32Array(10);
-     * console.log(Buffer.from(randomFillSync(a).buffer,
-     *                         a.byteOffset, a.byteLength).toString('hex'));
-     *
-     * const b = new DataView(new ArrayBuffer(10));
-     * console.log(Buffer.from(randomFillSync(b).buffer,
-     *                         b.byteOffset, b.byteLength).toString('hex'));
-     *
-     * const c = new ArrayBuffer(10);
-     * console.log(Buffer.from(randomFillSync(c)).toString('hex'));
-     * ```
-     * @since v7.10.0, v6.13.0
-     * @param buffer Must be supplied. The size of the provided `buffer` must not be larger than `2**31 - 1`.
-     * @param [offset=0]
-     * @param [size=buffer.length - offset]
-     * @return The object passed as `buffer` argument.
-     */
-    function randomFillSync<T extends NodeJS.ArrayBufferView>(buffer: T, offset?: number, size?: number): T;
-    /**
-     * This function is similar to {@link randomBytes} but requires the first
-     * argument to be a `Buffer` that will be filled. It also
-     * requires that a callback is passed in.
-     *
-     * If the `callback` function is not provided, an error will be thrown.
-     *
-     * ```js
-     * import { Buffer } from 'buffer';
-     * const { randomFill } = await import('crypto');
-     *
-     * const buf = Buffer.alloc(10);
-     * randomFill(buf, (err, buf) => {
-     *   if (err) throw err;
-     *   console.log(buf.toString('hex'));
-     * });
-     *
-     * randomFill(buf, 5, (err, buf) => {
-     *   if (err) throw err;
-     *   console.log(buf.toString('hex'));
-     * });
-     *
-     * // The above is equivalent to the following:
-     * randomFill(buf, 5, 5, (err, buf) => {
-     *   if (err) throw err;
-     *   console.log(buf.toString('hex'));
-     * });
-     * ```
-     *
-     * Any `ArrayBuffer`, `TypedArray`, or `DataView` instance may be passed as`buffer`.
-     *
-     * While this includes instances of `Float32Array` and `Float64Array`, this
-     * function should not be used to generate random floating-point numbers. The
-     * result may contain `+Infinity`, `-Infinity`, and `NaN`, and even if the array
-     * contains finite numbers only, they are not drawn from a uniform random
-     * distribution and have no meaningful lower or upper bounds.
-     *
-     * ```js
-     * import { Buffer } from 'buffer';
-     * const { randomFill } = await import('crypto');
-     *
-     * const a = new Uint32Array(10);
-     * randomFill(a, (err, buf) => {
-     *   if (err) throw err;
-     *   console.log(Buffer.from(buf.buffer, buf.byteOffset, buf.byteLength)
-     *     .toString('hex'));
-     * });
-     *
-     * const b = new DataView(new ArrayBuffer(10));
-     * randomFill(b, (err, buf) => {
-     *   if (err) throw err;
-     *   console.log(Buffer.from(buf.buffer, buf.byteOffset, buf.byteLength)
-     *     .toString('hex'));
-     * });
-     *
-     * const c = new ArrayBuffer(10);
-     * randomFill(c, (err, buf) => {
-     *   if (err) throw err;
-     *   console.log(Buffer.from(buf).toString('hex'));
-     * });
-     * ```
-     *
-     * This API uses libuv's threadpool, which can have surprising and
-     * negative performance implications for some applications; see the `UV_THREADPOOL_SIZE` documentation for more information.
-     *
-     * The asynchronous version of `crypto.randomFill()` is carried out in a single
-     * threadpool request. To minimize threadpool task length variation, partition
-     * large `randomFill` requests when doing so as part of fulfilling a client
-     * request.
-     * @since v7.10.0, v6.13.0
-     * @param buffer Must be supplied. The size of the provided `buffer` must not be larger than `2**31 - 1`.
-     * @param [offset=0]
-     * @param [size=buffer.length - offset]
-     * @param callback `function(err, buf) {}`.
-     */
-    function randomFill<T extends NodeJS.ArrayBufferView>(buffer: T, callback: (err: Error | null, buf: T) => void): void;
-    function randomFill<T extends NodeJS.ArrayBufferView>(buffer: T, offset: number, callback: (err: Error | null, buf: T) => void): void;
-    function randomFill<T extends NodeJS.ArrayBufferView>(buffer: T, offset: number, size: number, callback: (err: Error | null, buf: T) => void): void;
-    interface ScryptOptions {
-        cost?: number | undefined;
-        blockSize?: number | undefined;
-        parallelization?: number | undefined;
-        N?: number | undefined;
-        r?: number | undefined;
-        p?: number | undefined;
-        maxmem?: number | undefined;
-    }
-    /**
-     * Provides an asynchronous [scrypt](https://en.wikipedia.org/wiki/Scrypt) implementation. Scrypt is a password-based
-     * key derivation function that is designed to be expensive computationally and
-     * memory-wise in order to make brute-force attacks unrewarding.
-     *
-     * The `salt` should be as unique as possible. It is recommended that a salt is
-     * random and at least 16 bytes long. See [NIST SP 800-132](https://nvlpubs.nist.gov/nistpubs/Legacy/SP/nistspecialpublication800-132.pdf) for details.
-     *
-     * When passing strings for `password` or `salt`, please consider `caveats when using strings as inputs to cryptographic APIs`.
-     *
-     * The `callback` function is called with two arguments: `err` and `derivedKey`.`err` is an exception object when key derivation fails, otherwise `err` is`null`. `derivedKey` is passed to the
-     * callback as a `Buffer`.
-     *
-     * An exception is thrown when any of the input arguments specify invalid values
-     * or types.
-     *
-     * ```js
-     * const {
-     *   scrypt
-     * } = await import('crypto');
-     *
-     * // Using the factory defaults.
-     * scrypt('password', 'salt', 64, (err, derivedKey) => {
-     *   if (err) throw err;
-     *   console.log(derivedKey.toString('hex'));  // '3745e48...08d59ae'
-     * });
-     * // Using a custom N parameter. Must be a power of two.
-     * scrypt('password', 'salt', 64, { N: 1024 }, (err, derivedKey) => {
-     *   if (err) throw err;
-     *   console.log(derivedKey.toString('hex'));  // '3745e48...aa39b34'
-     * });
-     * ```
-     * @since v10.5.0
-     */
-    function scrypt(password: BinaryLike, salt: BinaryLike, keylen: number, callback: (err: Error | null, derivedKey: Buffer) => void): void;
-    function scrypt(password: BinaryLike, salt: BinaryLike, keylen: number, options: ScryptOptions, callback: (err: Error | null, derivedKey: Buffer) => void): void;
-    /**
-     * Provides a synchronous [scrypt](https://en.wikipedia.org/wiki/Scrypt) implementation. Scrypt is a password-based
-     * key derivation function that is designed to be expensive computationally and
-     * memory-wise in order to make brute-force attacks unrewarding.
-     *
-     * The `salt` should be as unique as possible. It is recommended that a salt is
-     * random and at least 16 bytes long. See [NIST SP 800-132](https://nvlpubs.nist.gov/nistpubs/Legacy/SP/nistspecialpublication800-132.pdf) for details.
-     *
-     * When passing strings for `password` or `salt`, please consider `caveats when using strings as inputs to cryptographic APIs`.
-     *
-     * An exception is thrown when key derivation fails, otherwise the derived key is
-     * returned as a `Buffer`.
-     *
-     * An exception is thrown when any of the input arguments specify invalid values
-     * or types.
-     *
-     * ```js
-     * const {
-     *   scryptSync
-     * } = await import('crypto');
-     * // Using the factory defaults.
-     *
-     * const key1 = scryptSync('password', 'salt', 64);
-     * console.log(key1.toString('hex'));  // '3745e48...08d59ae'
-     * // Using a custom N parameter. Must be a power of two.
-     * const key2 = scryptSync('password', 'salt', 64, { N: 1024 });
-     * console.log(key2.toString('hex'));  // '3745e48...aa39b34'
-     * ```
-     * @since v10.5.0
-     */
-    function scryptSync(password: BinaryLike, salt: BinaryLike, keylen: number, options?: ScryptOptions): Buffer;
-    interface RsaPublicKey {
-        key: KeyLike;
-        padding?: number | undefined;
-    }
-    interface RsaPrivateKey {
-        key: KeyLike;
-        passphrase?: string | undefined;
-        /**
-         * @default 'sha1'
-         */
-        oaepHash?: string | undefined;
-        oaepLabel?: NodeJS.TypedArray | undefined;
-        padding?: number | undefined;
-    }
-    /**
-     * Encrypts the content of `buffer` with `key` and returns a new `Buffer` with encrypted content. The returned data can be decrypted using
-     * the corresponding private key, for example using {@link privateDecrypt}.
-     *
-     * If `key` is not a `KeyObject`, this function behaves as if`key` had been passed to {@link createPublicKey}. If it is an
-     * object, the `padding` property can be passed. Otherwise, this function uses`RSA_PKCS1_OAEP_PADDING`.
-     *
-     * Because RSA public keys can be derived from private keys, a private key may
-     * be passed instead of a public key.
-     * @since v0.11.14
-     */
-    function publicEncrypt(key: RsaPublicKey | RsaPrivateKey | KeyLike, buffer: NodeJS.ArrayBufferView): Buffer;
-    /**
-     * Decrypts `buffer` with `key`.`buffer` was previously encrypted using
-     * the corresponding private key, for example using {@link privateEncrypt}.
-     *
-     * If `key` is not a `KeyObject`, this function behaves as if`key` had been passed to {@link createPublicKey}. If it is an
-     * object, the `padding` property can be passed. Otherwise, this function uses`RSA_PKCS1_PADDING`.
-     *
-     * Because RSA public keys can be derived from private keys, a private key may
-     * be passed instead of a public key.
-     * @since v1.1.0
-     */
-    function publicDecrypt(key: RsaPublicKey | RsaPrivateKey | KeyLike, buffer: NodeJS.ArrayBufferView): Buffer;
-    /**
-     * Decrypts `buffer` with `privateKey`. `buffer` was previously encrypted using
-     * the corresponding public key, for example using {@link publicEncrypt}.
-     *
-     * If `privateKey` is not a `KeyObject`, this function behaves as if`privateKey` had been passed to {@link createPrivateKey}. If it is an
-     * object, the `padding` property can be passed. Otherwise, this function uses`RSA_PKCS1_OAEP_PADDING`.
-     * @since v0.11.14
-     */
-    function privateDecrypt(privateKey: RsaPrivateKey | KeyLike, buffer: NodeJS.ArrayBufferView): Buffer;
-    /**
-     * Encrypts `buffer` with `privateKey`. The returned data can be decrypted using
-     * the corresponding public key, for example using {@link publicDecrypt}.
-     *
-     * If `privateKey` is not a `KeyObject`, this function behaves as if`privateKey` had been passed to {@link createPrivateKey}. If it is an
-     * object, the `padding` property can be passed. Otherwise, this function uses`RSA_PKCS1_PADDING`.
-     * @since v1.1.0
-     */
-    function privateEncrypt(privateKey: RsaPrivateKey | KeyLike, buffer: NodeJS.ArrayBufferView): Buffer;
-    /**
-     * ```js
-     * const {
-     *   getCiphers
-     * } = await import('crypto');
-     *
-     * console.log(getCiphers()); // ['aes-128-cbc', 'aes-128-ccm', ...]
-     * ```
-     * @since v0.9.3
-     * @return An array with the names of the supported cipher algorithms.
-     */
-    function getCiphers(): string[];
-    /**
-     * ```js
-     * const {
-     *   getCurves
-     * } = await import('crypto');
-     *
-     * console.log(getCurves()); // ['Oakley-EC2N-3', 'Oakley-EC2N-4', ...]
-     * ```
-     * @since v2.3.0
-     * @return An array with the names of the supported elliptic curves.
-     */
-    function getCurves(): string[];
-    /**
-     * @since v10.0.0
-     * @return `1` if and only if a FIPS compliant crypto provider is currently in use, `0` otherwise. A future semver-major release may change the return type of this API to a {boolean}.
-     */
-    function getFips(): 1 | 0;
-    /**
-     * Enables the FIPS compliant crypto provider in a FIPS-enabled Node.js build. Throws an error if FIPS mode is not available.
-     * @since v10.0.0
-     * @param bool `true` to enable FIPS mode.
-     */
-    function setFips(bool: boolean): void;
-    /**
-     * ```js
-     * const {
-     *   getHashes
-     * } = await import('crypto');
-     *
-     * console.log(getHashes()); // ['DSA', 'DSA-SHA', 'DSA-SHA1', ...]
-     * ```
-     * @since v0.9.3
-     * @return An array of the names of the supported hash algorithms, such as `'RSA-SHA256'`. Hash algorithms are also called "digest" algorithms.
-     */
-    function getHashes(): string[];
-    /**
-     * The `ECDH` class is a utility for creating Elliptic Curve Diffie-Hellman (ECDH)
-     * key exchanges.
-     *
-     * Instances of the `ECDH` class can be created using the {@link createECDH} function.
-     *
-     * ```js
-     * import assert from 'assert';
-     *
-     * const {
-     *   createECDH
-     * } = await import('crypto');
-     *
-     * // Generate Alice's keys...
-     * const alice = createECDH('secp521r1');
-     * const aliceKey = alice.generateKeys();
-     *
-     * // Generate Bob's keys...
-     * const bob = createECDH('secp521r1');
-     * const bobKey = bob.generateKeys();
-     *
-     * // Exchange and generate the secret...
-     * const aliceSecret = alice.computeSecret(bobKey);
-     * const bobSecret = bob.computeSecret(aliceKey);
-     *
-     * assert.strictEqual(aliceSecret.toString('hex'), bobSecret.toString('hex'));
-     * // OK
-     * ```
-     * @since v0.11.14
-     */
-    class ECDH {
-        private constructor();
-        /**
-         * Converts the EC Diffie-Hellman public key specified by `key` and `curve` to the
-         * format specified by `format`. The `format` argument specifies point encoding
-         * and can be `'compressed'`, `'uncompressed'` or `'hybrid'`. The supplied key is
-         * interpreted using the specified `inputEncoding`, and the returned key is encoded
-         * using the specified `outputEncoding`.
-         *
-         * Use {@link getCurves} to obtain a list of available curve names.
-         * On recent OpenSSL releases, `openssl ecparam -list_curves` will also display
-         * the name and description of each available elliptic curve.
-         *
-         * If `format` is not specified the point will be returned in `'uncompressed'`format.
-         *
-         * If the `inputEncoding` is not provided, `key` is expected to be a `Buffer`,`TypedArray`, or `DataView`.
-         *
-         * Example (uncompressing a key):
-         *
-         * ```js
-         * const {
-         *   createECDH,
-         *   ECDH
-         * } = await import('crypto');
-         *
-         * const ecdh = createECDH('secp256k1');
-         * ecdh.generateKeys();
-         *
-         * const compressedKey = ecdh.getPublicKey('hex', 'compressed');
-         *
-         * const uncompressedKey = ECDH.convertKey(compressedKey,
-         *                                         'secp256k1',
-         *                                         'hex',
-         *                                         'hex',
-         *                                         'uncompressed');
-         *
-         * // The converted key and the uncompressed public key should be the same
-         * console.log(uncompressedKey === ecdh.getPublicKey('hex'));
-         * ```
-         * @since v10.0.0
-         * @param inputEncoding The `encoding` of the `key` string.
-         * @param outputEncoding The `encoding` of the return value.
-         * @param [format='uncompressed']
-         */
-        static convertKey(
-            key: BinaryLike,
-            curve: string,
-            inputEncoding?: BinaryToTextEncoding,
-            outputEncoding?: 'latin1' | 'hex' | 'base64' | 'base64url',
-            format?: 'uncompressed' | 'compressed' | 'hybrid'
-        ): Buffer | string;
-        /**
-         * Generates private and public EC Diffie-Hellman key values, and returns
-         * the public key in the specified `format` and `encoding`. This key should be
-         * transferred to the other party.
-         *
-         * The `format` argument specifies point encoding and can be `'compressed'` or`'uncompressed'`. If `format` is not specified, the point will be returned in`'uncompressed'` format.
-         *
-         * If `encoding` is provided a string is returned; otherwise a `Buffer` is returned.
-         * @since v0.11.14
-         * @param encoding The `encoding` of the return value.
-         * @param [format='uncompressed']
-         */
-        generateKeys(): Buffer;
-        generateKeys(encoding: BinaryToTextEncoding, format?: ECDHKeyFormat): string;
-        /**
-         * Computes the shared secret using `otherPublicKey` as the other
-         * party's public key and returns the computed shared secret. The supplied
-         * key is interpreted using specified `inputEncoding`, and the returned secret
-         * is encoded using the specified `outputEncoding`.
-         * If the `inputEncoding` is not
-         * provided, `otherPublicKey` is expected to be a `Buffer`, `TypedArray`, or`DataView`.
-         *
-         * If `outputEncoding` is given a string will be returned; otherwise a `Buffer` is returned.
-         *
-         * `ecdh.computeSecret` will throw an`ERR_CRYPTO_ECDH_INVALID_PUBLIC_KEY` error when `otherPublicKey`lies outside of the elliptic curve. Since `otherPublicKey` is
-         * usually supplied from a remote user over an insecure network,
-         * be sure to handle this exception accordingly.
-         * @since v0.11.14
-         * @param inputEncoding The `encoding` of the `otherPublicKey` string.
-         * @param outputEncoding The `encoding` of the return value.
-         */
-        computeSecret(otherPublicKey: NodeJS.ArrayBufferView): Buffer;
-        computeSecret(otherPublicKey: string, inputEncoding: BinaryToTextEncoding): Buffer;
-        computeSecret(otherPublicKey: NodeJS.ArrayBufferView, outputEncoding: BinaryToTextEncoding): string;
-        computeSecret(otherPublicKey: string, inputEncoding: BinaryToTextEncoding, outputEncoding: BinaryToTextEncoding): string;
-        /**
-         * If `encoding` is specified, a string is returned; otherwise a `Buffer` is
-         * returned.
-         * @since v0.11.14
-         * @param encoding The `encoding` of the return value.
-         * @return The EC Diffie-Hellman in the specified `encoding`.
-         */
-        getPrivateKey(): Buffer;
-        getPrivateKey(encoding: BinaryToTextEncoding): string;
-        /**
-         * The `format` argument specifies point encoding and can be `'compressed'` or`'uncompressed'`. If `format` is not specified the point will be returned in`'uncompressed'` format.
-         *
-         * If `encoding` is specified, a string is returned; otherwise a `Buffer` is
-         * returned.
-         * @since v0.11.14
-         * @param [encoding] The `encoding` of the return value.
-         * @param [format='uncompressed']
-         * @return The EC Diffie-Hellman public key in the specified `encoding` and `format`.
-         */
-        getPublicKey(encoding?: null, format?: ECDHKeyFormat): Buffer;
-        getPublicKey(encoding: BinaryToTextEncoding, format?: ECDHKeyFormat): string;
-        /**
-         * Sets the EC Diffie-Hellman private key.
-         * If `encoding` is provided, `privateKey` is expected
-         * to be a string; otherwise `privateKey` is expected to be a `Buffer`,`TypedArray`, or `DataView`.
-         *
-         * If `privateKey` is not valid for the curve specified when the `ECDH` object was
-         * created, an error is thrown. Upon setting the private key, the associated
-         * public point (key) is also generated and set in the `ECDH` object.
-         * @since v0.11.14
-         * @param encoding The `encoding` of the `privateKey` string.
-         */
-        setPrivateKey(privateKey: NodeJS.ArrayBufferView): void;
-        setPrivateKey(privateKey: string, encoding: BinaryToTextEncoding): void;
-    }
-    /**
-     * Creates an Elliptic Curve Diffie-Hellman (`ECDH`) key exchange object using a
-     * predefined curve specified by the `curveName` string. Use {@link getCurves} to obtain a list of available curve names. On recent
-     * OpenSSL releases, `openssl ecparam -list_curves` will also display the name
-     * and description of each available elliptic curve.
-     * @since v0.11.14
-     */
-    function createECDH(curveName: string): ECDH;
-    /**
-     * This function is based on a constant-time algorithm.
-     * Returns true if `a` is equal to `b`, without leaking timing information that
-     * would allow an attacker to guess one of the values. This is suitable for
-     * comparing HMAC digests or secret values like authentication cookies or [capability urls](https://www.w3.org/TR/capability-urls/).
-     *
-     * `a` and `b` must both be `Buffer`s, `TypedArray`s, or `DataView`s, and they
-     * must have the same byte length. An error is thrown if `a` and `b` have
-     * different byte lengths.
-     *
-     * If at least one of `a` and `b` is a `TypedArray` with more than one byte per
-     * entry, such as `Uint16Array`, the result will be computed using the platform
-     * byte order.
-     *
-     * Use of `crypto.timingSafeEqual` does not guarantee that the _surrounding_ code
-     * is timing-safe. Care should be taken to ensure that the surrounding code does
-     * not introduce timing vulnerabilities.
-     * @since v6.6.0
-     */
-    function timingSafeEqual(a: NodeJS.ArrayBufferView, b: NodeJS.ArrayBufferView): boolean;
-    /** @deprecated since v10.0.0 */
-    const DEFAULT_ENCODING: BufferEncoding;
-    type KeyType = 'rsa' | 'rsa-pss' | 'dsa' | 'ec' | 'ed25519' | 'ed448' | 'x25519' | 'x448';
-    type KeyFormat = 'pem' | 'der' | 'jwk';
-    interface BasePrivateKeyEncodingOptions<T extends KeyFormat> {
-        format: T;
-        cipher?: string | undefined;
-        passphrase?: string | undefined;
-    }
-    interface KeyPairKeyObjectResult {
-        publicKey: KeyObject;
-        privateKey: KeyObject;
-    }
-    interface ED25519KeyPairKeyObjectOptions {}
-    interface ED448KeyPairKeyObjectOptions {}
-    interface X25519KeyPairKeyObjectOptions {}
-    interface X448KeyPairKeyObjectOptions {}
-    interface ECKeyPairKeyObjectOptions {
-        /**
-         * Name of the curve to use
-         */
-        namedCurve: string;
-    }
-    interface RSAKeyPairKeyObjectOptions {
-        /**
-         * Key size in bits
-         */
-        modulusLength: number;
-        /**
-         * Public exponent
-         * @default 0x10001
-         */
-        publicExponent?: number | undefined;
-    }
-    interface RSAPSSKeyPairKeyObjectOptions {
-        /**
-         * Key size in bits
-         */
-        modulusLength: number;
-        /**
-         * Public exponent
-         * @default 0x10001
-         */
-        publicExponent?: number | undefined;
-        /**
-         * Name of the message digest
-         */
-        hashAlgorithm?: string;
-        /**
-         * Name of the message digest used by MGF1
-         */
-        mgf1HashAlgorithm?: string;
-        /**
-         * Minimal salt length in bytes
-         */
-        saltLength?: string;
-    }
-    interface DSAKeyPairKeyObjectOptions {
-        /**
-         * Key size in bits
-         */
-        modulusLength: number;
-        /**
-         * Size of q in bits
-         */
-        divisorLength: number;
-    }
-    interface RSAKeyPairOptions<PubF extends KeyFormat, PrivF extends KeyFormat> {
-        /**
-         * Key size in bits
-         */
-        modulusLength: number;
-        /**
-         * Public exponent
-         * @default 0x10001
-         */
-        publicExponent?: number | undefined;
-        publicKeyEncoding: {
-            type: 'pkcs1' | 'spki';
-            format: PubF;
-        };
-        privateKeyEncoding: BasePrivateKeyEncodingOptions<PrivF> & {
-            type: 'pkcs1' | 'pkcs8';
-        };
-    }
-    interface RSAPSSKeyPairOptions<PubF extends KeyFormat, PrivF extends KeyFormat> {
-        /**
-         * Key size in bits
-         */
-        modulusLength: number;
-        /**
-         * Public exponent
-         * @default 0x10001
-         */
-        publicExponent?: number | undefined;
-        /**
-         * Name of the message digest
-         */
-        hashAlgorithm?: string;
-        /**
-         * Name of the message digest used by MGF1
-         */
-        mgf1HashAlgorithm?: string;
-        /**
-         * Minimal salt length in bytes
-         */
-        saltLength?: string;
-        publicKeyEncoding: {
-            type: 'spki';
-            format: PubF;
-        };
-        privateKeyEncoding: BasePrivateKeyEncodingOptions<PrivF> & {
-            type: 'pkcs8';
-        };
-    }
-    interface DSAKeyPairOptions<PubF extends KeyFormat, PrivF extends KeyFormat> {
-        /**
-         * Key size in bits
-         */
-        modulusLength: number;
-        /**
-         * Size of q in bits
-         */
-        divisorLength: number;
-        publicKeyEncoding: {
-            type: 'spki';
-            format: PubF;
-        };
-        privateKeyEncoding: BasePrivateKeyEncodingOptions<PrivF> & {
-            type: 'pkcs8';
-        };
-    }
-    interface ECKeyPairOptions<PubF extends KeyFormat, PrivF extends KeyFormat> {
-        /**
-         * Name of the curve to use.
-         */
-        namedCurve: string;
-        publicKeyEncoding: {
-            type: 'pkcs1' | 'spki';
-            format: PubF;
-        };
-        privateKeyEncoding: BasePrivateKeyEncodingOptions<PrivF> & {
-            type: 'sec1' | 'pkcs8';
-        };
-    }
-    interface ED25519KeyPairOptions<PubF extends KeyFormat, PrivF extends KeyFormat> {
-        publicKeyEncoding: {
-            type: 'spki';
-            format: PubF;
-        };
-        privateKeyEncoding: BasePrivateKeyEncodingOptions<PrivF> & {
-            type: 'pkcs8';
-        };
-    }
-    interface ED448KeyPairOptions<PubF extends KeyFormat, PrivF extends KeyFormat> {
-        publicKeyEncoding: {
-            type: 'spki';
-            format: PubF;
-        };
-        privateKeyEncoding: BasePrivateKeyEncodingOptions<PrivF> & {
-            type: 'pkcs8';
-        };
-    }
-    interface X25519KeyPairOptions<PubF extends KeyFormat, PrivF extends KeyFormat> {
-        publicKeyEncoding: {
-            type: 'spki';
-            format: PubF;
-        };
-        privateKeyEncoding: BasePrivateKeyEncodingOptions<PrivF> & {
-            type: 'pkcs8';
-        };
-    }
-    interface X448KeyPairOptions<PubF extends KeyFormat, PrivF extends KeyFormat> {
-        publicKeyEncoding: {
-            type: 'spki';
-            format: PubF;
-        };
-        privateKeyEncoding: BasePrivateKeyEncodingOptions<PrivF> & {
-            type: 'pkcs8';
-        };
-    }
-    interface KeyPairSyncResult<T1 extends string | Buffer, T2 extends string | Buffer> {
-        publicKey: T1;
-        privateKey: T2;
-    }
-    /**
-     * Generates a new asymmetric key pair of the given `type`. RSA, RSA-PSS, DSA, EC,
-     * Ed25519, Ed448, X25519, X448, and DH are currently supported.
-     *
-     * If a `publicKeyEncoding` or `privateKeyEncoding` was specified, this function
-     * behaves as if `keyObject.export()` had been called on its result. Otherwise,
-     * the respective part of the key is returned as a `KeyObject`.
-     *
-     * When encoding public keys, it is recommended to use `'spki'`. When encoding
-     * private keys, it is recommended to use `'pkcs8'` with a strong passphrase,
-     * and to keep the passphrase confidential.
-     *
-     * ```js
-     * const {
-     *   generateKeyPairSync
-     * } = await import('crypto');
-     *
-     * const {
-     *   publicKey,
-     *   privateKey,
-     * } = generateKeyPairSync('rsa', {
-     *   modulusLength: 4096,
-     *   publicKeyEncoding: {
-     *     type: 'spki',
-     *     format: 'pem'
-     *   },
-     *   privateKeyEncoding: {
-     *     type: 'pkcs8',
-     *     format: 'pem',
-     *     cipher: 'aes-256-cbc',
-     *     passphrase: 'top secret'
-     *   }
-     * });
-     * ```
-     *
-     * The return value `{ publicKey, privateKey }` represents the generated key pair.
-     * When PEM encoding was selected, the respective key will be a string, otherwise
-     * it will be a buffer containing the data encoded as DER.
-     * @since v10.12.0
-     * @param type Must be `'rsa'`, `'rsa-pss'`, `'dsa'`, `'ec'`, `'ed25519'`, `'ed448'`, `'x25519'`, `'x448'`, or `'dh'`.
-     */
-    function generateKeyPairSync(type: 'rsa', options: RSAKeyPairOptions<'pem', 'pem'>): KeyPairSyncResult<string, string>;
-    function generateKeyPairSync(type: 'rsa', options: RSAKeyPairOptions<'pem', 'der'>): KeyPairSyncResult<string, Buffer>;
-    function generateKeyPairSync(type: 'rsa', options: RSAKeyPairOptions<'der', 'pem'>): KeyPairSyncResult<Buffer, string>;
-    function generateKeyPairSync(type: 'rsa', options: RSAKeyPairOptions<'der', 'der'>): KeyPairSyncResult<Buffer, Buffer>;
-    function generateKeyPairSync(type: 'rsa', options: RSAKeyPairKeyObjectOptions): KeyPairKeyObjectResult;
-    function generateKeyPairSync(type: 'rsa-pss', options: RSAPSSKeyPairOptions<'pem', 'pem'>): KeyPairSyncResult<string, string>;
-    function generateKeyPairSync(type: 'rsa-pss', options: RSAPSSKeyPairOptions<'pem', 'der'>): KeyPairSyncResult<string, Buffer>;
-    function generateKeyPairSync(type: 'rsa-pss', options: RSAPSSKeyPairOptions<'der', 'pem'>): KeyPairSyncResult<Buffer, string>;
-    function generateKeyPairSync(type: 'rsa-pss', options: RSAPSSKeyPairOptions<'der', 'der'>): KeyPairSyncResult<Buffer, Buffer>;
-    function generateKeyPairSync(type: 'rsa-pss', options: RSAPSSKeyPairKeyObjectOptions): KeyPairKeyObjectResult;
-    function generateKeyPairSync(type: 'dsa', options: DSAKeyPairOptions<'pem', 'pem'>): KeyPairSyncResult<string, string>;
-    function generateKeyPairSync(type: 'dsa', options: DSAKeyPairOptions<'pem', 'der'>): KeyPairSyncResult<string, Buffer>;
-    function generateKeyPairSync(type: 'dsa', options: DSAKeyPairOptions<'der', 'pem'>): KeyPairSyncResult<Buffer, string>;
-    function generateKeyPairSync(type: 'dsa', options: DSAKeyPairOptions<'der', 'der'>): KeyPairSyncResult<Buffer, Buffer>;
-    function generateKeyPairSync(type: 'dsa', options: DSAKeyPairKeyObjectOptions): KeyPairKeyObjectResult;
-    function generateKeyPairSync(type: 'ec', options: ECKeyPairOptions<'pem', 'pem'>): KeyPairSyncResult<string, string>;
-    function generateKeyPairSync(type: 'ec', options: ECKeyPairOptions<'pem', 'der'>): KeyPairSyncResult<string, Buffer>;
-    function generateKeyPairSync(type: 'ec', options: ECKeyPairOptions<'der', 'pem'>): KeyPairSyncResult<Buffer, string>;
-    function generateKeyPairSync(type: 'ec', options: ECKeyPairOptions<'der', 'der'>): KeyPairSyncResult<Buffer, Buffer>;
-    function generateKeyPairSync(type: 'ec', options: ECKeyPairKeyObjectOptions): KeyPairKeyObjectResult;
-    function generateKeyPairSync(type: 'ed25519', options: ED25519KeyPairOptions<'pem', 'pem'>): KeyPairSyncResult<string, string>;
-    function generateKeyPairSync(type: 'ed25519', options: ED25519KeyPairOptions<'pem', 'der'>): KeyPairSyncResult<string, Buffer>;
-    function generateKeyPairSync(type: 'ed25519', options: ED25519KeyPairOptions<'der', 'pem'>): KeyPairSyncResult<Buffer, string>;
-    function generateKeyPairSync(type: 'ed25519', options: ED25519KeyPairOptions<'der', 'der'>): KeyPairSyncResult<Buffer, Buffer>;
-    function generateKeyPairSync(type: 'ed25519', options?: ED25519KeyPairKeyObjectOptions): KeyPairKeyObjectResult;
-    function generateKeyPairSync(type: 'ed448', options: ED448KeyPairOptions<'pem', 'pem'>): KeyPairSyncResult<string, string>;
-    function generateKeyPairSync(type: 'ed448', options: ED448KeyPairOptions<'pem', 'der'>): KeyPairSyncResult<string, Buffer>;
-    function generateKeyPairSync(type: 'ed448', options: ED448KeyPairOptions<'der', 'pem'>): KeyPairSyncResult<Buffer, string>;
-    function generateKeyPairSync(type: 'ed448', options: ED448KeyPairOptions<'der', 'der'>): KeyPairSyncResult<Buffer, Buffer>;
-    function generateKeyPairSync(type: 'ed448', options?: ED448KeyPairKeyObjectOptions): KeyPairKeyObjectResult;
-    function generateKeyPairSync(type: 'x25519', options: X25519KeyPairOptions<'pem', 'pem'>): KeyPairSyncResult<string, string>;
-    function generateKeyPairSync(type: 'x25519', options: X25519KeyPairOptions<'pem', 'der'>): KeyPairSyncResult<string, Buffer>;
-    function generateKeyPairSync(type: 'x25519', options: X25519KeyPairOptions<'der', 'pem'>): KeyPairSyncResult<Buffer, string>;
-    function generateKeyPairSync(type: 'x25519', options: X25519KeyPairOptions<'der', 'der'>): KeyPairSyncResult<Buffer, Buffer>;
-    function generateKeyPairSync(type: 'x25519', options?: X25519KeyPairKeyObjectOptions): KeyPairKeyObjectResult;
-    function generateKeyPairSync(type: 'x448', options: X448KeyPairOptions<'pem', 'pem'>): KeyPairSyncResult<string, string>;
-    function generateKeyPairSync(type: 'x448', options: X448KeyPairOptions<'pem', 'der'>): KeyPairSyncResult<string, Buffer>;
-    function generateKeyPairSync(type: 'x448', options: X448KeyPairOptions<'der', 'pem'>): KeyPairSyncResult<Buffer, string>;
-    function generateKeyPairSync(type: 'x448', options: X448KeyPairOptions<'der', 'der'>): KeyPairSyncResult<Buffer, Buffer>;
-    function generateKeyPairSync(type: 'x448', options?: X448KeyPairKeyObjectOptions): KeyPairKeyObjectResult;
-    /**
-     * Generates a new asymmetric key pair of the given `type`. RSA, RSA-PSS, DSA, EC,
-     * Ed25519, Ed448, X25519, X448, and DH are currently supported.
-     *
-     * If a `publicKeyEncoding` or `privateKeyEncoding` was specified, this function
-     * behaves as if `keyObject.export()` had been called on its result. Otherwise,
-     * the respective part of the key is returned as a `KeyObject`.
-     *
-     * It is recommended to encode public keys as `'spki'` and private keys as`'pkcs8'` with encryption for long-term storage:
-     *
-     * ```js
-     * const {
-     *   generateKeyPair
-     * } = await import('crypto');
-     *
-     * generateKeyPair('rsa', {
-     *   modulusLength: 4096,
-     *   publicKeyEncoding: {
-     *     type: 'spki',
-     *     format: 'pem'
-     *   },
-     *   privateKeyEncoding: {
-     *     type: 'pkcs8',
-     *     format: 'pem',
-     *     cipher: 'aes-256-cbc',
-     *     passphrase: 'top secret'
-     *   }
-     * }, (err, publicKey, privateKey) => {
-     *   // Handle errors and use the generated key pair.
-     * });
-     * ```
-     *
-     * On completion, `callback` will be called with `err` set to `undefined` and`publicKey` / `privateKey` representing the generated key pair.
-     *
-     * If this method is invoked as its `util.promisify()` ed version, it returns
-     * a `Promise` for an `Object` with `publicKey` and `privateKey` properties.
-     * @since v10.12.0
-     * @param type Must be `'rsa'`, `'rsa-pss'`, `'dsa'`, `'ec'`, `'ed25519'`, `'ed448'`, `'x25519'`, `'x448'`, or `'dh'`.
-     */
-    function generateKeyPair(type: 'rsa', options: RSAKeyPairOptions<'pem', 'pem'>, callback: (err: Error | null, publicKey: string, privateKey: string) => void): void;
-    function generateKeyPair(type: 'rsa', options: RSAKeyPairOptions<'pem', 'der'>, callback: (err: Error | null, publicKey: string, privateKey: Buffer) => void): void;
-    function generateKeyPair(type: 'rsa', options: RSAKeyPairOptions<'der', 'pem'>, callback: (err: Error | null, publicKey: Buffer, privateKey: string) => void): void;
-    function generateKeyPair(type: 'rsa', options: RSAKeyPairOptions<'der', 'der'>, callback: (err: Error | null, publicKey: Buffer, privateKey: Buffer) => void): void;
-    function generateKeyPair(type: 'rsa', options: RSAKeyPairKeyObjectOptions, callback: (err: Error | null, publicKey: KeyObject, privateKey: KeyObject) => void): void;
-    function generateKeyPair(type: 'rsa-pss', options: RSAPSSKeyPairOptions<'pem', 'pem'>, callback: (err: Error | null, publicKey: string, privateKey: string) => void): void;
-    function generateKeyPair(type: 'rsa-pss', options: RSAPSSKeyPairOptions<'pem', 'der'>, callback: (err: Error | null, publicKey: string, privateKey: Buffer) => void): void;
-    function generateKeyPair(type: 'rsa-pss', options: RSAPSSKeyPairOptions<'der', 'pem'>, callback: (err: Error | null, publicKey: Buffer, privateKey: string) => void): void;
-    function generateKeyPair(type: 'rsa-pss', options: RSAPSSKeyPairOptions<'der', 'der'>, callback: (err: Error | null, publicKey: Buffer, privateKey: Buffer) => void): void;
-    function generateKeyPair(type: 'rsa-pss', options: RSAPSSKeyPairKeyObjectOptions, callback: (err: Error | null, publicKey: KeyObject, privateKey: KeyObject) => void): void;
-    function generateKeyPair(type: 'dsa', options: DSAKeyPairOptions<'pem', 'pem'>, callback: (err: Error | null, publicKey: string, privateKey: string) => void): void;
-    function generateKeyPair(type: 'dsa', options: DSAKeyPairOptions<'pem', 'der'>, callback: (err: Error | null, publicKey: string, privateKey: Buffer) => void): void;
-    function generateKeyPair(type: 'dsa', options: DSAKeyPairOptions<'der', 'pem'>, callback: (err: Error | null, publicKey: Buffer, privateKey: string) => void): void;
-    function generateKeyPair(type: 'dsa', options: DSAKeyPairOptions<'der', 'der'>, callback: (err: Error | null, publicKey: Buffer, privateKey: Buffer) => void): void;
-    function generateKeyPair(type: 'dsa', options: DSAKeyPairKeyObjectOptions, callback: (err: Error | null, publicKey: KeyObject, privateKey: KeyObject) => void): void;
-    function generateKeyPair(type: 'ec', options: ECKeyPairOptions<'pem', 'pem'>, callback: (err: Error | null, publicKey: string, privateKey: string) => void): void;
-    function generateKeyPair(type: 'ec', options: ECKeyPairOptions<'pem', 'der'>, callback: (err: Error | null, publicKey: string, privateKey: Buffer) => void): void;
-    function generateKeyPair(type: 'ec', options: ECKeyPairOptions<'der', 'pem'>, callback: (err: Error | null, publicKey: Buffer, privateKey: string) => void): void;
-    function generateKeyPair(type: 'ec', options: ECKeyPairOptions<'der', 'der'>, callback: (err: Error | null, publicKey: Buffer, privateKey: Buffer) => void): void;
-    function generateKeyPair(type: 'ec', options: ECKeyPairKeyObjectOptions, callback: (err: Error | null, publicKey: KeyObject, privateKey: KeyObject) => void): void;
-    function generateKeyPair(type: 'ed25519', options: ED25519KeyPairOptions<'pem', 'pem'>, callback: (err: Error | null, publicKey: string, privateKey: string) => void): void;
-    function generateKeyPair(type: 'ed25519', options: ED25519KeyPairOptions<'pem', 'der'>, callback: (err: Error | null, publicKey: string, privateKey: Buffer) => void): void;
-    function generateKeyPair(type: 'ed25519', options: ED25519KeyPairOptions<'der', 'pem'>, callback: (err: Error | null, publicKey: Buffer, privateKey: string) => void): void;
-    function generateKeyPair(type: 'ed25519', options: ED25519KeyPairOptions<'der', 'der'>, callback: (err: Error | null, publicKey: Buffer, privateKey: Buffer) => void): void;
-    function generateKeyPair(type: 'ed25519', options: ED25519KeyPairKeyObjectOptions | undefined, callback: (err: Error | null, publicKey: KeyObject, privateKey: KeyObject) => void): void;
-    function generateKeyPair(type: 'ed448', options: ED448KeyPairOptions<'pem', 'pem'>, callback: (err: Error | null, publicKey: string, privateKey: string) => void): void;
-    function generateKeyPair(type: 'ed448', options: ED448KeyPairOptions<'pem', 'der'>, callback: (err: Error | null, publicKey: string, privateKey: Buffer) => void): void;
-    function generateKeyPair(type: 'ed448', options: ED448KeyPairOptions<'der', 'pem'>, callback: (err: Error | null, publicKey: Buffer, privateKey: string) => void): void;
-    function generateKeyPair(type: 'ed448', options: ED448KeyPairOptions<'der', 'der'>, callback: (err: Error | null, publicKey: Buffer, privateKey: Buffer) => void): void;
-    function generateKeyPair(type: 'ed448', options: ED448KeyPairKeyObjectOptions | undefined, callback: (err: Error | null, publicKey: KeyObject, privateKey: KeyObject) => void): void;
-    function generateKeyPair(type: 'x25519', options: X25519KeyPairOptions<'pem', 'pem'>, callback: (err: Error | null, publicKey: string, privateKey: string) => void): void;
-    function generateKeyPair(type: 'x25519', options: X25519KeyPairOptions<'pem', 'der'>, callback: (err: Error | null, publicKey: string, privateKey: Buffer) => void): void;
-    function generateKeyPair(type: 'x25519', options: X25519KeyPairOptions<'der', 'pem'>, callback: (err: Error | null, publicKey: Buffer, privateKey: string) => void): void;
-    function generateKeyPair(type: 'x25519', options: X25519KeyPairOptions<'der', 'der'>, callback: (err: Error | null, publicKey: Buffer, privateKey: Buffer) => void): void;
-    function generateKeyPair(type: 'x25519', options: X25519KeyPairKeyObjectOptions | undefined, callback: (err: Error | null, publicKey: KeyObject, privateKey: KeyObject) => void): void;
-    function generateKeyPair(type: 'x448', options: X448KeyPairOptions<'pem', 'pem'>, callback: (err: Error | null, publicKey: string, privateKey: string) => void): void;
-    function generateKeyPair(type: 'x448', options: X448KeyPairOptions<'pem', 'der'>, callback: (err: Error | null, publicKey: string, privateKey: Buffer) => void): void;
-    function generateKeyPair(type: 'x448', options: X448KeyPairOptions<'der', 'pem'>, callback: (err: Error | null, publicKey: Buffer, privateKey: string) => void): void;
-    function generateKeyPair(type: 'x448', options: X448KeyPairOptions<'der', 'der'>, callback: (err: Error | null, publicKey: Buffer, privateKey: Buffer) => void): void;
-    function generateKeyPair(type: 'x448', options: X448KeyPairKeyObjectOptions | undefined, callback: (err: Error | null, publicKey: KeyObject, privateKey: KeyObject) => void): void;
-    namespace generateKeyPair {
-        function __promisify__(
-            type: 'rsa',
-            options: RSAKeyPairOptions<'pem', 'pem'>
-        ): Promise<{
-            publicKey: string;
-            privateKey: string;
-        }>;
-        function __promisify__(
-            type: 'rsa',
-            options: RSAKeyPairOptions<'pem', 'der'>
-        ): Promise<{
-            publicKey: string;
-            privateKey: Buffer;
-        }>;
-        function __promisify__(
-            type: 'rsa',
-            options: RSAKeyPairOptions<'der', 'pem'>
-        ): Promise<{
-            publicKey: Buffer;
-            privateKey: string;
-        }>;
-        function __promisify__(
-            type: 'rsa',
-            options: RSAKeyPairOptions<'der', 'der'>
-        ): Promise<{
-            publicKey: Buffer;
-            privateKey: Buffer;
-        }>;
-        function __promisify__(type: 'rsa', options: RSAKeyPairKeyObjectOptions): Promise<KeyPairKeyObjectResult>;
-        function __promisify__(
-            type: 'rsa-pss',
-            options: RSAPSSKeyPairOptions<'pem', 'pem'>
-        ): Promise<{
-            publicKey: string;
-            privateKey: string;
-        }>;
-        function __promisify__(
-            type: 'rsa-pss',
-            options: RSAPSSKeyPairOptions<'pem', 'der'>
-        ): Promise<{
-            publicKey: string;
-            privateKey: Buffer;
-        }>;
-        function __promisify__(
-            type: 'rsa-pss',
-            options: RSAPSSKeyPairOptions<'der', 'pem'>
-        ): Promise<{
-            publicKey: Buffer;
-            privateKey: string;
-        }>;
-        function __promisify__(
-            type: 'rsa-pss',
-            options: RSAPSSKeyPairOptions<'der', 'der'>
-        ): Promise<{
-            publicKey: Buffer;
-            privateKey: Buffer;
-        }>;
-        function __promisify__(type: 'rsa-pss', options: RSAPSSKeyPairKeyObjectOptions): Promise<KeyPairKeyObjectResult>;
-        function __promisify__(
-            type: 'dsa',
-            options: DSAKeyPairOptions<'pem', 'pem'>
-        ): Promise<{
-            publicKey: string;
-            privateKey: string;
-        }>;
-        function __promisify__(
-            type: 'dsa',
-            options: DSAKeyPairOptions<'pem', 'der'>
-        ): Promise<{
-            publicKey: string;
-            privateKey: Buffer;
-        }>;
-        function __promisify__(
-            type: 'dsa',
-            options: DSAKeyPairOptions<'der', 'pem'>
-        ): Promise<{
-            publicKey: Buffer;
-            privateKey: string;
-        }>;
-        function __promisify__(
-            type: 'dsa',
-            options: DSAKeyPairOptions<'der', 'der'>
-        ): Promise<{
-            publicKey: Buffer;
-            privateKey: Buffer;
-        }>;
-        function __promisify__(type: 'dsa', options: DSAKeyPairKeyObjectOptions): Promise<KeyPairKeyObjectResult>;
-        function __promisify__(
-            type: 'ec',
-            options: ECKeyPairOptions<'pem', 'pem'>
-        ): Promise<{
-            publicKey: string;
-            privateKey: string;
-        }>;
-        function __promisify__(
-            type: 'ec',
-            options: ECKeyPairOptions<'pem', 'der'>
-        ): Promise<{
-            publicKey: string;
-            privateKey: Buffer;
-        }>;
-        function __promisify__(
-            type: 'ec',
-            options: ECKeyPairOptions<'der', 'pem'>
-        ): Promise<{
-            publicKey: Buffer;
-            privateKey: string;
-        }>;
-        function __promisify__(
-            type: 'ec',
-            options: ECKeyPairOptions<'der', 'der'>
-        ): Promise<{
-            publicKey: Buffer;
-            privateKey: Buffer;
-        }>;
-        function __promisify__(type: 'ec', options: ECKeyPairKeyObjectOptions): Promise<KeyPairKeyObjectResult>;
-        function __promisify__(
-            type: 'ed25519',
-            options: ED25519KeyPairOptions<'pem', 'pem'>
-        ): Promise<{
-            publicKey: string;
-            privateKey: string;
-        }>;
-        function __promisify__(
-            type: 'ed25519',
-            options: ED25519KeyPairOptions<'pem', 'der'>
-        ): Promise<{
-            publicKey: string;
-            privateKey: Buffer;
-        }>;
-        function __promisify__(
-            type: 'ed25519',
-            options: ED25519KeyPairOptions<'der', 'pem'>
-        ): Promise<{
-            publicKey: Buffer;
-            privateKey: string;
-        }>;
-        function __promisify__(
-            type: 'ed25519',
-            options: ED25519KeyPairOptions<'der', 'der'>
-        ): Promise<{
-            publicKey: Buffer;
-            privateKey: Buffer;
-        }>;
-        function __promisify__(type: 'ed25519', options?: ED25519KeyPairKeyObjectOptions): Promise<KeyPairKeyObjectResult>;
-        function __promisify__(
-            type: 'ed448',
-            options: ED448KeyPairOptions<'pem', 'pem'>
-        ): Promise<{
-            publicKey: string;
-            privateKey: string;
-        }>;
-        function __promisify__(
-            type: 'ed448',
-            options: ED448KeyPairOptions<'pem', 'der'>
-        ): Promise<{
-            publicKey: string;
-            privateKey: Buffer;
-        }>;
-        function __promisify__(
-            type: 'ed448',
-            options: ED448KeyPairOptions<'der', 'pem'>
-        ): Promise<{
-            publicKey: Buffer;
-            privateKey: string;
-        }>;
-        function __promisify__(
-            type: 'ed448',
-            options: ED448KeyPairOptions<'der', 'der'>
-        ): Promise<{
-            publicKey: Buffer;
-            privateKey: Buffer;
-        }>;
-        function __promisify__(type: 'ed448', options?: ED448KeyPairKeyObjectOptions): Promise<KeyPairKeyObjectResult>;
-        function __promisify__(
-            type: 'x25519',
-            options: X25519KeyPairOptions<'pem', 'pem'>
-        ): Promise<{
-            publicKey: string;
-            privateKey: string;
-        }>;
-        function __promisify__(
-            type: 'x25519',
-            options: X25519KeyPairOptions<'pem', 'der'>
-        ): Promise<{
-            publicKey: string;
-            privateKey: Buffer;
-        }>;
-        function __promisify__(
-            type: 'x25519',
-            options: X25519KeyPairOptions<'der', 'pem'>
-        ): Promise<{
-            publicKey: Buffer;
-            privateKey: string;
-        }>;
-        function __promisify__(
-            type: 'x25519',
-            options: X25519KeyPairOptions<'der', 'der'>
-        ): Promise<{
-            publicKey: Buffer;
-            privateKey: Buffer;
-        }>;
-        function __promisify__(type: 'x25519', options?: X25519KeyPairKeyObjectOptions): Promise<KeyPairKeyObjectResult>;
-        function __promisify__(
-            type: 'x448',
-            options: X448KeyPairOptions<'pem', 'pem'>
-        ): Promise<{
-            publicKey: string;
-            privateKey: string;
-        }>;
-        function __promisify__(
-            type: 'x448',
-            options: X448KeyPairOptions<'pem', 'der'>
-        ): Promise<{
-            publicKey: string;
-            privateKey: Buffer;
-        }>;
-        function __promisify__(
-            type: 'x448',
-            options: X448KeyPairOptions<'der', 'pem'>
-        ): Promise<{
-            publicKey: Buffer;
-            privateKey: string;
-        }>;
-        function __promisify__(
-            type: 'x448',
-            options: X448KeyPairOptions<'der', 'der'>
-        ): Promise<{
-            publicKey: Buffer;
-            privateKey: Buffer;
-        }>;
-        function __promisify__(type: 'x448', options?: X448KeyPairKeyObjectOptions): Promise<KeyPairKeyObjectResult>;
-    }
-    /**
-     * Calculates and returns the signature for `data` using the given private key and
-     * algorithm. If `algorithm` is `null` or `undefined`, then the algorithm is
-     * dependent upon the key type (especially Ed25519 and Ed448).
-     *
-     * If `key` is not a `KeyObject`, this function behaves as if `key` had been
-     * passed to {@link createPrivateKey}. If it is an object, the following
-     * additional properties can be passed:
-     *
-     * If the `callback` function is provided this function uses libuv's threadpool.
-     * @since v12.0.0
-     */
-    function sign(algorithm: string | null | undefined, data: NodeJS.ArrayBufferView, key: KeyLike | SignKeyObjectInput | SignPrivateKeyInput): Buffer;
-    function sign(
-        algorithm: string | null | undefined,
-        data: NodeJS.ArrayBufferView,
-        key: KeyLike | SignKeyObjectInput | SignPrivateKeyInput,
-        callback: (error: Error | null, data: Buffer) => void
-    ): void;
-    /**
-     * Verifies the given signature for `data` using the given key and algorithm. If`algorithm` is `null` or `undefined`, then the algorithm is dependent upon the
-     * key type (especially Ed25519 and Ed448).
-     *
-     * If `key` is not a `KeyObject`, this function behaves as if `key` had been
-     * passed to {@link createPublicKey}. If it is an object, the following
-     * additional properties can be passed:
-     *
-     * The `signature` argument is the previously calculated signature for the `data`.
-     *
-     * Because public keys can be derived from private keys, a private key or a public
-     * key may be passed for `key`.
-     *
-     * If the `callback` function is provided this function uses libuv's threadpool.
-     * @since v12.0.0
-     */
-    function verify(algorithm: string | null | undefined, data: NodeJS.ArrayBufferView, key: KeyLike | VerifyKeyObjectInput | VerifyPublicKeyInput, signature: NodeJS.ArrayBufferView): boolean;
-    function verify(
-        algorithm: string | null | undefined,
-        data: NodeJS.ArrayBufferView,
-        key: KeyLike | VerifyKeyObjectInput | VerifyPublicKeyInput,
-        signature: NodeJS.ArrayBufferView,
-        callback: (error: Error | null, result: boolean) => void
-    ): void;
-    /**
-     * Computes the Diffie-Hellman secret based on a `privateKey` and a `publicKey`.
-     * Both keys must have the same `asymmetricKeyType`, which must be one of `'dh'`(for Diffie-Hellman), `'ec'` (for ECDH), `'x448'`, or `'x25519'` (for ECDH-ES).
-     * @since v13.9.0, v12.17.0
-     */
-    function diffieHellman(options: { privateKey: KeyObject; publicKey: KeyObject }): Buffer;
-    type CipherMode = 'cbc' | 'ccm' | 'cfb' | 'ctr' | 'ecb' | 'gcm' | 'ocb' | 'ofb' | 'stream' | 'wrap' | 'xts';
-    interface CipherInfoOptions {
-        /**
-         * A test key length.
-         */
-        keyLength?: number | undefined;
-        /**
-         * A test IV length.
-         */
-        ivLength?: number | undefined;
-    }
-    interface CipherInfo {
-        /**
-         * The name of the cipher.
-         */
-        name: string;
-        /**
-         * The nid of the cipher.
-         */
-        nid: number;
-        /**
-         * The block size of the cipher in bytes.
-         * This property is omitted when mode is 'stream'.
-         */
-        blockSize?: number | undefined;
-        /**
-         * The expected or default initialization vector length in bytes.
-         * This property is omitted if the cipher does not use an initialization vector.
-         */
-        ivLength?: number | undefined;
-        /**
-         * The expected or default key length in bytes.
-         */
-        keyLength: number;
-        /**
-         * The cipher mode.
-         */
-        mode: CipherMode;
-    }
-    /**
-     * Returns information about a given cipher.
-     *
-     * Some ciphers accept variable length keys and initialization vectors. By default,
-     * the `crypto.getCipherInfo()` method will return the default values for these
-     * ciphers. To test if a given key length or iv length is acceptable for given
-     * cipher, use the `keyLength` and `ivLength` options. If the given values are
-     * unacceptable, `undefined` will be returned.
-     * @since v15.0.0
-     * @param nameOrNid The name or nid of the cipher to query.
-     */
-    function getCipherInfo(nameOrNid: string | number, options?: CipherInfoOptions): CipherInfo | undefined;
-    /**
-     * HKDF is a simple key derivation function defined in RFC 5869\. The given `ikm`,`salt` and `info` are used with the `digest` to derive a key of `keylen` bytes.
-     *
-     * The supplied `callback` function is called with two arguments: `err` and`derivedKey`. If an errors occurs while deriving the key, `err` will be set;
-     * otherwise `err` will be `null`. The successfully generated `derivedKey` will
-     * be passed to the callback as an [ArrayBuffer](https://developer.mozilla.org/en-US/docs/Web/JavaScript/Reference/Global_Objects/ArrayBuffer). An error will be thrown if any
-     * of the input arguments specify invalid values or types.
-     *
-     * ```js
-     * import { Buffer } from 'buffer';
-     * const {
-     *   hkdf
-     * } = await import('crypto');
-     *
-     * hkdf('sha512', 'key', 'salt', 'info', 64, (err, derivedKey) => {
-     *   if (err) throw err;
-     *   console.log(Buffer.from(derivedKey).toString('hex'));  // '24156e2...5391653'
-     * });
-     * ```
-     * @since v15.0.0
-     * @param digest The digest algorithm to use.
-     * @param ikm The input keying material. It must be at least one byte in length.
-     * @param salt The salt value. Must be provided but can be zero-length.
-     * @param info Additional info value. Must be provided but can be zero-length, and cannot be more than 1024 bytes.
-     * @param keylen The length of the key to generate. Must be greater than 0. The maximum allowable value is `255` times the number of bytes produced by the selected digest function (e.g. `sha512`
-     * generates 64-byte hashes, making the maximum HKDF output 16320 bytes).
-     */
-    function hkdf(digest: string, irm: BinaryLike | KeyObject, salt: BinaryLike, info: BinaryLike, keylen: number, callback: (err: Error | null, derivedKey: ArrayBuffer) => void): void;
-    /**
-     * Provides a synchronous HKDF key derivation function as defined in RFC 5869\. The
-     * given `ikm`, `salt` and `info` are used with the `digest` to derive a key of`keylen` bytes.
-     *
-     * The successfully generated `derivedKey` will be returned as an [ArrayBuffer](https://developer.mozilla.org/en-US/docs/Web/JavaScript/Reference/Global_Objects/ArrayBuffer).
-     *
-     * An error will be thrown if any of the input arguments specify invalid values or
-     * types, or if the derived key cannot be generated.
-     *
-     * ```js
-     * import { Buffer } from 'buffer';
-     * const {
-     *   hkdfSync
-     * } = await import('crypto');
-     *
-     * const derivedKey = hkdfSync('sha512', 'key', 'salt', 'info', 64);
-     * console.log(Buffer.from(derivedKey).toString('hex'));  // '24156e2...5391653'
-     * ```
-     * @since v15.0.0
-     * @param digest The digest algorithm to use.
-     * @param ikm The input keying material. It must be at least one byte in length.
-     * @param salt The salt value. Must be provided but can be zero-length.
-     * @param info Additional info value. Must be provided but can be zero-length, and cannot be more than 1024 bytes.
-     * @param keylen The length of the key to generate. Must be greater than 0. The maximum allowable value is `255` times the number of bytes produced by the selected digest function (e.g. `sha512`
-     * generates 64-byte hashes, making the maximum HKDF output 16320 bytes).
-     */
-    function hkdfSync(digest: string, ikm: BinaryLike | KeyObject, salt: BinaryLike, info: BinaryLike, keylen: number): ArrayBuffer;
-    interface SecureHeapUsage {
-        /**
-         * The total allocated secure heap size as specified using the `--secure-heap=n` command-line flag.
-         */
-        total: number;
-        /**
-         * The minimum allocation from the secure heap as specified using the `--secure-heap-min` command-line flag.
-         */
-        min: number;
-        /**
-         * The total number of bytes currently allocated from the secure heap.
-         */
-        used: number;
-        /**
-         * The calculated ratio of `used` to `total` allocated bytes.
-         */
-        utilization: number;
-    }
-    /**
-     * @since v15.6.0
-     */
-    function secureHeapUsed(): SecureHeapUsage;
-    interface RandomUUIDOptions {
-        /**
-         * By default, to improve performance,
-         * Node.js will pre-emptively generate and persistently cache enough
-         * random data to generate up to 128 random UUIDs. To generate a UUID
-         * without using the cache, set `disableEntropyCache` to `true`.
-         *
-         * @default `false`
-         */
-        disableEntropyCache?: boolean | undefined;
-    }
-    /**
-     * Generates a random [RFC 4122](https://www.rfc-editor.org/rfc/rfc4122.txt) version 4 UUID. The UUID is generated using a
-     * cryptographic pseudorandom number generator.
-     * @since v15.6.0, v14.17.0
-     */
-    function randomUUID(options?: RandomUUIDOptions): string;
-    interface X509CheckOptions {
-        /**
-         * @default 'always'
-         */
-        subject?: 'always' | 'default' | 'never';
-        /**
-         * @default true
-         */
-        wildcards?: boolean;
-        /**
-         * @default true
-         */
-        partialWildcards?: boolean;
-        /**
-         * @default false
-         */
-        multiLabelWildcards?: boolean;
-        /**
-         * @default false
-         */
-        singleLabelSubdomains?: boolean;
-    }
-    /**
-     * Encapsulates an X509 certificate and provides read-only access to
-     * its information.
-     *
-     * ```js
-     * const { X509Certificate } = await import('crypto');
-     *
-     * const x509 = new X509Certificate('{... pem encoded cert ...}');
-     *
-     * console.log(x509.subject);
-     * ```
-     * @since v15.6.0
-     */
-    class X509Certificate {
-        /**
-         * Will be \`true\` if this is a Certificate Authority (CA) certificate.
-         * @since v15.6.0
-         */
-        readonly ca: boolean;
-        /**
-         * The SHA-1 fingerprint of this certificate.
-         *
-         * Because SHA-1 is cryptographically broken and because the security of SHA-1 is
-         * significantly worse than that of algorithms that are commonly used to sign
-         * certificates, consider using `x509.fingerprint256` instead.
-         * @since v15.6.0
-         */
-        readonly fingerprint: string;
-        /**
-         * The SHA-256 fingerprint of this certificate.
-         * @since v15.6.0
-         */
-        readonly fingerprint256: string;
-        /**
-         * The SHA-512 fingerprint of this certificate.
-         * @since v16.14.0
-         */
-         readonly fingerprint512: string;
-        /**
-         * The complete subject of this certificate.
-         * @since v15.6.0
-         */
-        readonly subject: string;
-        /**
-         * The subject alternative name specified for this certificate or `undefined`
-         * if not available.
-         * @since v15.6.0
-         */
-        readonly subjectAltName: string | undefined;
-        /**
-         * The information access content of this certificate or `undefined` if not
-         * available.
-         * @since v15.6.0
-         */
-        readonly infoAccess: string | undefined;
-        /**
-         * An array detailing the key usages for this certificate.
-         * @since v15.6.0
-         */
-        readonly keyUsage: string[];
-        /**
-         * The issuer identification included in this certificate.
-         * @since v15.6.0
-         */
-        readonly issuer: string;
-        /**
-         * The issuer certificate or `undefined` if the issuer certificate is not
-         * available.
-         * @since v15.9.0
-         */
-        readonly issuerCertificate?: X509Certificate | undefined;
-        /**
-         * The public key `KeyObject` for this certificate.
-         * @since v15.6.0
-         */
-        readonly publicKey: KeyObject;
-        /**
-         * A `Buffer` containing the DER encoding of this certificate.
-         * @since v15.6.0
-         */
-        readonly raw: Buffer;
-        /**
-         * The serial number of this certificate.
-         *
-         * Serial numbers are assigned by certificate authorities and do not uniquely
-         * identify certificates. Consider using `x509.fingerprint256` as a unique
-         * identifier instead.
-         * @since v15.6.0
-         */
-        readonly serialNumber: string;
-        /**
-         * The date/time from which this certificate is considered valid.
-         * @since v15.6.0
-         */
-        readonly validFrom: string;
-        /**
-         * The date/time until which this certificate is considered valid.
-         * @since v15.6.0
-         */
-        readonly validTo: string;
-        constructor(buffer: BinaryLike);
-        /**
-         * Checks whether the certificate matches the given email address.
-         *
-         * If the `'subject'` option is undefined or set to `'default'`, the certificate
-         * subject is only considered if the subject alternative name extension either does
-         * not exist or does not contain any email addresses.
-         *
-         * If the `'subject'` option is set to `'always'` and if the subject alternative
-         * name extension either does not exist or does not contain a matching email
-         * address, the certificate subject is considered.
-         *
-         * If the `'subject'` option is set to `'never'`, the certificate subject is never
-         * considered, even if the certificate contains no subject alternative names.
-         * @since v15.6.0
-         * @return Returns `email` if the certificate matches, `undefined` if it does not.
-         */
-        checkEmail(email: string, options?: Pick<X509CheckOptions, 'subject'>): string | undefined;
-        /**
-         * Checks whether the certificate matches the given host name.
-         *
-         * If the certificate matches the given host name, the matching subject name is
-         * returned. The returned name might be an exact match (e.g., `foo.example.com`)
-         * or it might contain wildcards (e.g., `*.example.com`). Because host name
-         * comparisons are case-insensitive, the returned subject name might also differ
-         * from the given `name` in capitalization.
-         *
-         * If the `'subject'` option is undefined or set to `'default'`, the certificate
-         * subject is only considered if the subject alternative name extension either does
-         * not exist or does not contain any DNS names. This behavior is consistent with [RFC 2818](https://www.rfc-editor.org/rfc/rfc2818.txt) ("HTTP Over TLS").
-         *
-         * If the `'subject'` option is set to `'always'` and if the subject alternative
-         * name extension either does not exist or does not contain a matching DNS name,
-         * the certificate subject is considered.
-         *
-         * If the `'subject'` option is set to `'never'`, the certificate subject is never
-         * considered, even if the certificate contains no subject alternative names.
-         * @since v15.6.0
-         * @return Returns a subject name that matches `name`, or `undefined` if no subject name matches `name`.
-         */
-        checkHost(name: string, options?: X509CheckOptions): string | undefined;
-        /**
-         * Checks whether the certificate matches the given IP address (IPv4 or IPv6).
-         *
-         * Only [RFC 5280](https://www.rfc-editor.org/rfc/rfc5280.txt) `iPAddress` subject alternative names are considered, and they
-         * must match the given `ip` address exactly. Other subject alternative names as
-         * well as the subject field of the certificate are ignored.
-         * @since v15.6.0
-         * @return Returns `ip` if the certificate matches, `undefined` if it does not.
-         */
-        checkIP(ip: string): string | undefined;
-        /**
-         * Checks whether this certificate was issued by the given `otherCert`.
-         * @since v15.6.0
-         */
-        checkIssued(otherCert: X509Certificate): boolean;
-        /**
-         * Checks whether the public key for this certificate is consistent with
-         * the given private key.
-         * @since v15.6.0
-         * @param privateKey A private key.
-         */
-        checkPrivateKey(privateKey: KeyObject): boolean;
-        /**
-         * There is no standard JSON encoding for X509 certificates. The`toJSON()` method returns a string containing the PEM encoded
-         * certificate.
-         * @since v15.6.0
-         */
-        toJSON(): string;
-        /**
-         * Returns information about this certificate using the legacy `certificate object` encoding.
-         * @since v15.6.0
-         */
-        toLegacyObject(): PeerCertificate;
-        /**
-         * Returns the PEM-encoded certificate.
-         * @since v15.6.0
-         */
-        toString(): string;
-        /**
-         * Verifies that this certificate was signed by the given public key.
-         * Does not perform any other validation checks on the certificate.
-         * @since v15.6.0
-         * @param publicKey A public key.
-         */
-        verify(publicKey: KeyObject): boolean;
-    }
-    type LargeNumberLike = NodeJS.ArrayBufferView | SharedArrayBuffer | ArrayBuffer | bigint;
-    interface GeneratePrimeOptions {
-        add?: LargeNumberLike | undefined;
-        rem?: LargeNumberLike | undefined;
-        /**
-         * @default false
-         */
-        safe?: boolean | undefined;
-        bigint?: boolean | undefined;
-    }
-    interface GeneratePrimeOptionsBigInt extends GeneratePrimeOptions {
-        bigint: true;
-    }
-    interface GeneratePrimeOptionsArrayBuffer extends GeneratePrimeOptions {
-        bigint?: false | undefined;
-    }
-    /**
-     * Generates a pseudorandom prime of `size` bits.
-     *
-     * If `options.safe` is `true`, the prime will be a safe prime -- that is,`(prime - 1) / 2` will also be a prime.
-     *
-     * The `options.add` and `options.rem` parameters can be used to enforce additional
-     * requirements, e.g., for Diffie-Hellman:
-     *
-     * * If `options.add` and `options.rem` are both set, the prime will satisfy the
-     * condition that `prime % add = rem`.
-     * * If only `options.add` is set and `options.safe` is not `true`, the prime will
-     * satisfy the condition that `prime % add = 1`.
-     * * If only `options.add` is set and `options.safe` is set to `true`, the prime
-     * will instead satisfy the condition that `prime % add = 3`. This is necessary
-     * because `prime % add = 1` for `options.add > 2` would contradict the condition
-     * enforced by `options.safe`.
-     * * `options.rem` is ignored if `options.add` is not given.
-     *
-     * Both `options.add` and `options.rem` must be encoded as big-endian sequences
-     * if given as an `ArrayBuffer`, `SharedArrayBuffer`, `TypedArray`, `Buffer`, or`DataView`.
-     *
-     * By default, the prime is encoded as a big-endian sequence of octets
-     * in an [ArrayBuffer](https://developer.mozilla.org/en-US/docs/Web/JavaScript/Reference/Global_Objects/ArrayBuffer). If the `bigint` option is `true`, then a
-     * [bigint](https://developer.mozilla.org/en-US/docs/Web/JavaScript/Reference/Global_Objects/BigInt) is provided.
-     * @since v15.8.0
-     * @param size The size (in bits) of the prime to generate.
-     */
-    function generatePrime(size: number, callback: (err: Error | null, prime: ArrayBuffer) => void): void;
-    function generatePrime(size: number, options: GeneratePrimeOptionsBigInt, callback: (err: Error | null, prime: bigint) => void): void;
-    function generatePrime(size: number, options: GeneratePrimeOptionsArrayBuffer, callback: (err: Error | null, prime: ArrayBuffer) => void): void;
-    function generatePrime(size: number, options: GeneratePrimeOptions, callback: (err: Error | null, prime: ArrayBuffer | bigint) => void): void;
-    /**
-     * Generates a pseudorandom prime of `size` bits.
-     *
-     * If `options.safe` is `true`, the prime will be a safe prime -- that is,`(prime - 1) / 2` will also be a prime.
-     *
-     * The `options.add` and `options.rem` parameters can be used to enforce additional
-     * requirements, e.g., for Diffie-Hellman:
-     *
-     * * If `options.add` and `options.rem` are both set, the prime will satisfy the
-     * condition that `prime % add = rem`.
-     * * If only `options.add` is set and `options.safe` is not `true`, the prime will
-     * satisfy the condition that `prime % add = 1`.
-     * * If only `options.add` is set and `options.safe` is set to `true`, the prime
-     * will instead satisfy the condition that `prime % add = 3`. This is necessary
-     * because `prime % add = 1` for `options.add > 2` would contradict the condition
-     * enforced by `options.safe`.
-     * * `options.rem` is ignored if `options.add` is not given.
-     *
-     * Both `options.add` and `options.rem` must be encoded as big-endian sequences
-     * if given as an `ArrayBuffer`, `SharedArrayBuffer`, `TypedArray`, `Buffer`, or`DataView`.
-     *
-     * By default, the prime is encoded as a big-endian sequence of octets
-     * in an [ArrayBuffer](https://developer.mozilla.org/en-US/docs/Web/JavaScript/Reference/Global_Objects/ArrayBuffer). If the `bigint` option is `true`, then a
-     * [bigint](https://developer.mozilla.org/en-US/docs/Web/JavaScript/Reference/Global_Objects/BigInt) is provided.
-     * @since v15.8.0
-     * @param size The size (in bits) of the prime to generate.
-     */
-    function generatePrimeSync(size: number): ArrayBuffer;
-    function generatePrimeSync(size: number, options: GeneratePrimeOptionsBigInt): bigint;
-    function generatePrimeSync(size: number, options: GeneratePrimeOptionsArrayBuffer): ArrayBuffer;
-    function generatePrimeSync(size: number, options: GeneratePrimeOptions): ArrayBuffer | bigint;
-    interface CheckPrimeOptions {
-        /**
-         * The number of Miller-Rabin probabilistic primality iterations to perform.
-         * When the value is 0 (zero), a number of checks is used that yields a false positive rate of at most `2**-64` for random input.
-         * Care must be used when selecting a number of checks.
-         * Refer to the OpenSSL documentation for the BN_is_prime_ex function nchecks options for more details.
-         *
-         * @default 0
-         */
-        checks?: number | undefined;
-    }
-    /**
-     * Checks the primality of the `candidate`.
-     * @since v15.8.0
-     * @param candidate A possible prime encoded as a sequence of big endian octets of arbitrary length.
-     */
-    function checkPrime(value: LargeNumberLike, callback: (err: Error | null, result: boolean) => void): void;
-    function checkPrime(value: LargeNumberLike, options: CheckPrimeOptions, callback: (err: Error | null, result: boolean) => void): void;
-    /**
-     * Checks the primality of the `candidate`.
-     * @since v15.8.0
-     * @param candidate A possible prime encoded as a sequence of big endian octets of arbitrary length.
-     * @return `true` if the candidate is a prime with an error probability less than `0.25 ** options.checks`.
-     */
-    function checkPrimeSync(candidate: LargeNumberLike, options?: CheckPrimeOptions): boolean;
-    /**
-     * Load and set the `engine` for some or all OpenSSL functions (selected by flags).
-     *
-     * `engine` could be either an id or a path to the engine's shared library.
-     *
-     * The optional `flags` argument uses `ENGINE_METHOD_ALL` by default.
-     * The `flags` is a bit field taking one of or a mix of the following flags (defined in `crypto.constants`):
-     *
-     * - `crypto.constants.ENGINE_METHOD_RSA`
-     * - `crypto.constants.ENGINE_METHOD_DSA`
-     * - `crypto.constants.ENGINE_METHOD_DH`
-     * - `crypto.constants.ENGINE_METHOD_RAND`
-     * - `crypto.constants.ENGINE_METHOD_EC`
-     * - `crypto.constants.ENGINE_METHOD_CIPHERS`
-     * - `crypto.constants.ENGINE_METHOD_DIGESTS`
-     * - `crypto.constants.ENGINE_METHOD_PKEY_METHS`
-     * - `crypto.constants.ENGINE_METHOD_PKEY_ASN1_METHS`
-     * - `crypto.constants.ENGINE_METHOD_ALL`
-     * - `crypto.constants.ENGINE_METHOD_NONE`
-     *
-     * The flags below are deprecated in OpenSSL-1.1.0.
-     *
-     * - `crypto.constants.ENGINE_METHOD_ECDH`
-     * - `crypto.constants.ENGINE_METHOD_ECDSA`
-     * - `crypto.constants.ENGINE_METHOD_STORE`
-     * @since v0.11.11
-     * @param [flags=crypto.constants.ENGINE_METHOD_ALL]
-     */
-    function setEngine(engine: string, flags?: number): void;
-    /**
-     * A convenient alias for `crypto.webcrypto.getRandomValues()`.
-     * This implementation is not compliant with the Web Crypto spec,
-     * to write web-compatible code use `crypto.webcrypto.getRandomValues()` instead.
-     * @since v17.4.0
-     * @returns Returns `typedArray`.
-     */
-    function getRandomValues<T extends webcrypto.BufferSource>(typedArray: T): T;
-    /**
-     * A convenient alias for `crypto.webcrypto.subtle`.
-     * @since v17.4.0
-     */
-    const subtle: webcrypto.SubtleCrypto;
-    /**
-     * An implementation of the Web Crypto API standard.
-     *
-     * See the {@link https://nodejs.org/docs/latest/api/webcrypto.html Web Crypto API documentation} for details.
-     * @since v15.0.0
-     */
-    const webcrypto: webcrypto.Crypto;
-    namespace webcrypto {
-        type BufferSource = ArrayBufferView | ArrayBuffer;
-        type KeyFormat = 'jwk' | 'pkcs8' | 'raw' | 'spki';
-        type KeyType = 'private' | 'public' | 'secret';
-        type KeyUsage = 'decrypt' | 'deriveBits' | 'deriveKey' | 'encrypt' | 'sign' | 'unwrapKey' | 'verify' | 'wrapKey';
-        type AlgorithmIdentifier = Algorithm | string;
-        type HashAlgorithmIdentifier = AlgorithmIdentifier;
-        type NamedCurve = string;
-        type BigInteger = Uint8Array;
-        interface AesCbcParams extends Algorithm {
-            iv: BufferSource;
-        }
-        interface AesCtrParams extends Algorithm {
-            counter: BufferSource;
-            length: number;
-        }
-        interface AesDerivedKeyParams extends Algorithm {
-            length: number;
-        }
-        interface AesGcmParams extends Algorithm {
-            additionalData?: BufferSource;
-            iv: BufferSource;
-            tagLength?: number;
-        }
-        interface AesKeyAlgorithm extends KeyAlgorithm {
-            length: number;
-        }
-        interface AesKeyGenParams extends Algorithm {
-            length: number;
-        }
-        interface Algorithm {
-            name: string;
-        }
-        interface EcKeyAlgorithm extends KeyAlgorithm {
-            namedCurve: NamedCurve;
-        }
-        interface EcKeyGenParams extends Algorithm {
-            namedCurve: NamedCurve;
-        }
-        interface EcKeyImportParams extends Algorithm {
-            namedCurve: NamedCurve;
-        }
-        interface EcdhKeyDeriveParams extends Algorithm {
-            public: CryptoKey;
-        }
-        interface EcdsaParams extends Algorithm {
-            hash: HashAlgorithmIdentifier;
-        }
-        interface Ed448Params extends Algorithm {
-            context?: BufferSource;
-        }
-        interface HkdfParams extends Algorithm {
-            hash: HashAlgorithmIdentifier;
-            info: BufferSource;
-            salt: BufferSource;
-        }
-        interface HmacImportParams extends Algorithm {
-            hash: HashAlgorithmIdentifier;
-            length?: number;
-        }
-        interface HmacKeyAlgorithm extends KeyAlgorithm {
-            hash: KeyAlgorithm;
-            length: number;
-        }
-        interface HmacKeyGenParams extends Algorithm {
-            hash: HashAlgorithmIdentifier;
-            length?: number;
-        }
-        interface JsonWebKey {
-            alg?: string;
-            crv?: string;
-            d?: string;
-            dp?: string;
-            dq?: string;
-            e?: string;
-            ext?: boolean;
-            k?: string;
-            key_ops?: string[];
-            kty?: string;
-            n?: string;
-            oth?: RsaOtherPrimesInfo[];
-            p?: string;
-            q?: string;
-            qi?: string;
-            use?: string;
-            x?: string;
-            y?: string;
-        }
-        interface KeyAlgorithm {
-            name: string;
-        }
-        interface Pbkdf2Params extends Algorithm {
-            hash: HashAlgorithmIdentifier;
-            iterations: number;
-            salt: BufferSource;
-        }
-        interface RsaHashedImportParams extends Algorithm {
-            hash: HashAlgorithmIdentifier;
-        }
-        interface RsaHashedKeyAlgorithm extends RsaKeyAlgorithm {
-            hash: KeyAlgorithm;
-        }
-        interface RsaHashedKeyGenParams extends RsaKeyGenParams {
-            hash: HashAlgorithmIdentifier;
-        }
-        interface RsaKeyAlgorithm extends KeyAlgorithm {
-            modulusLength: number;
-            publicExponent: BigInteger;
-        }
-        interface RsaKeyGenParams extends Algorithm {
-            modulusLength: number;
-            publicExponent: BigInteger;
-        }
-        interface RsaOaepParams extends Algorithm {
-            label?: BufferSource;
-        }
-        interface RsaOtherPrimesInfo {
-            d?: string;
-            r?: string;
-            t?: string;
-        }
-        interface RsaPssParams extends Algorithm {
-            saltLength: number;
-        }
-        /**
-         * Calling `require('node:crypto').webcrypto` returns an instance of the `Crypto` class.
-         * `Crypto` is a singleton that provides access to the remainder of the crypto API.
-         * @since v15.0.0
-         */
-        interface Crypto {
-            /**
-             * Provides access to the `SubtleCrypto` API.
-             * @since v15.0.0
-             */
-            readonly subtle: SubtleCrypto;
-            /**
-             * Generates cryptographically strong random values.
-             * The given `typedArray` is filled with random values, and a reference to `typedArray` is returned.
-             *
-             * The given `typedArray` must be an integer-based instance of {@link NodeJS.TypedArray}, i.e. `Float32Array` and `Float64Array` are not accepted.
-             *
-             * An error will be thrown if the given `typedArray` is larger than 65,536 bytes.
-             * @since v15.0.0
-             */
-            getRandomValues<T extends Exclude<NodeJS.TypedArray, Float32Array | Float64Array>>(typedArray: T): T;
-            /**
-             * Generates a random {@link https://www.rfc-editor.org/rfc/rfc4122.txt RFC 4122} version 4 UUID.
-             * The UUID is generated using a cryptographic pseudorandom number generator.
-             * @since v16.7.0
-             */
-            randomUUID(): string;
-            CryptoKey: CryptoKeyConstructor;
-        }
-        // This constructor throws ILLEGAL_CONSTRUCTOR so it should not be newable.
-        interface CryptoKeyConstructor {
-            /** Illegal constructor */
-            (_: { readonly _: unique symbol }): never; // Allows instanceof to work but not be callable by the user.
-            readonly length: 0;
-            readonly name: 'CryptoKey';
-            readonly prototype: CryptoKey;
-        }
-        /**
-         * @since v15.0.0
-         */
-        interface CryptoKey {
-            /**
-             * An object detailing the algorithm for which the key can be used along with additional algorithm-specific parameters.
-             * @since v15.0.0
-             */
-            readonly algorithm: KeyAlgorithm;
-            /**
-             * When `true`, the {@link CryptoKey} can be extracted using either `subtleCrypto.exportKey()` or `subtleCrypto.wrapKey()`.
-             * @since v15.0.0
-             */
-            readonly extractable: boolean;
-            /**
-             * A string identifying whether the key is a symmetric (`'secret'`) or asymmetric (`'private'` or `'public'`) key.
-             * @since v15.0.0
-             */
-            readonly type: KeyType;
-            /**
-             * An array of strings identifying the operations for which the key may be used.
-             *
-             * The possible usages are:
-             * - `'encrypt'` - The key may be used to encrypt data.
-             * - `'decrypt'` - The key may be used to decrypt data.
-             * - `'sign'` - The key may be used to generate digital signatures.
-             * - `'verify'` - The key may be used to verify digital signatures.
-             * - `'deriveKey'` - The key may be used to derive a new key.
-             * - `'deriveBits'` - The key may be used to derive bits.
-             * - `'wrapKey'` - The key may be used to wrap another key.
-             * - `'unwrapKey'` - The key may be used to unwrap another key.
-             *
-             * Valid key usages depend on the key algorithm (identified by `cryptokey.algorithm.name`).
-             * @since v15.0.0
-             */
-            readonly usages: KeyUsage[];
-        }
-        /**
-         * The `CryptoKeyPair` is a simple dictionary object with `publicKey` and `privateKey` properties, representing an asymmetric key pair.
-         * @since v15.0.0
-         */
-        interface CryptoKeyPair {
-            /**
-             * A {@link CryptoKey} whose type will be `'private'`.
-             * @since v15.0.0
-             */
-            privateKey: CryptoKey;
-            /**
-             * A {@link CryptoKey} whose type will be `'public'`.
-             * @since v15.0.0
-             */
-            publicKey: CryptoKey;
-        }
-        /**
-         * @since v15.0.0
-         */
-        interface SubtleCrypto {
-            /**
-             * Using the method and parameters specified in `algorithm` and the keying material provided by `key`,
-             * `subtle.decrypt()` attempts to decipher the provided `data`. If successful,
-             * the returned promise will be resolved with an `<ArrayBuffer>` containing the plaintext result.
-             *
-             * The algorithms currently supported include:
-             *
-             * - `'RSA-OAEP'`
-             * - `'AES-CTR'`
-             * - `'AES-CBC'`
-             * - `'AES-GCM'`
-             * @since v15.0.0
-             */
-            decrypt(algorithm: AlgorithmIdentifier | RsaOaepParams | AesCtrParams | AesCbcParams | AesGcmParams, key: CryptoKey, data: BufferSource): Promise<ArrayBuffer>;
-            /**
-             * Using the method and parameters specified in `algorithm` and the keying material provided by `baseKey`,
-             * `subtle.deriveBits()` attempts to generate `length` bits.
-             * The Node.js implementation requires that when `length` is a number it must be multiple of `8`.
-             * When `length` is `null` the maximum number of bits for a given algorithm is generated. This is allowed
-             * for the `'ECDH'`, `'X25519'`, and `'X448'` algorithms.
-             * If successful, the returned promise will be resolved with an `<ArrayBuffer>` containing the generated data.
-             *
-             * The algorithms currently supported include:
-             *
-             * - `'ECDH'`
-             * - `'X25519'`
-             * - `'X448'`
-             * - `'HKDF'`
-             * - `'PBKDF2'`
-             * @since v15.0.0
-             */
-            deriveBits(algorithm: EcdhKeyDeriveParams, baseKey: CryptoKey, length: number | null): Promise<ArrayBuffer>;
-            deriveBits(algorithm: AlgorithmIdentifier | HkdfParams | Pbkdf2Params, baseKey: CryptoKey, length: number): Promise<ArrayBuffer>;
-            /**
-             * Using the method and parameters specified in `algorithm`, and the keying material provided by `baseKey`,
-             * `subtle.deriveKey()` attempts to generate a new <CryptoKey>` based on the method and parameters in `derivedKeyAlgorithm`.
-             *
-             * Calling `subtle.deriveKey()` is equivalent to calling `subtle.deriveBits()` to generate raw keying material,
-             * then passing the result into the `subtle.importKey()` method using the `deriveKeyAlgorithm`, `extractable`, and `keyUsages` parameters as input.
-             *
-             * The algorithms currently supported include:
-             *
-             * - `'ECDH'`
-             * - `'X25519'`
-             * - `'X448'`
-             * - `'HKDF'`
-             * - `'PBKDF2'`
-             * @param keyUsages See {@link https://nodejs.org/docs/latest/api/webcrypto.html#cryptokeyusages Key usages}.
-             * @since v15.0.0
-             */
-            deriveKey(
-                algorithm: AlgorithmIdentifier | EcdhKeyDeriveParams | HkdfParams | Pbkdf2Params,
-                baseKey: CryptoKey,
-                derivedKeyAlgorithm: AlgorithmIdentifier | AesDerivedKeyParams | HmacImportParams | HkdfParams | Pbkdf2Params,
-                extractable: boolean,
-                keyUsages: ReadonlyArray<KeyUsage>
-            ): Promise<CryptoKey>;
-            /**
-             * Using the method identified by `algorithm`, `subtle.digest()` attempts to generate a digest of `data`.
-             * If successful, the returned promise is resolved with an `<ArrayBuffer>` containing the computed digest.
-             *
-             * If `algorithm` is provided as a `<string>`, it must be one of:
-             *
-             * - `'SHA-1'`
-             * - `'SHA-256'`
-             * - `'SHA-384'`
-             * - `'SHA-512'`
-             *
-             * If `algorithm` is provided as an `<Object>`, it must have a `name` property whose value is one of the above.
-             * @since v15.0.0
-             */
-            digest(algorithm: AlgorithmIdentifier, data: BufferSource): Promise<ArrayBuffer>;
-            /**
-             * Using the method and parameters specified by `algorithm` and the keying material provided by `key`,
-             * `subtle.encrypt()` attempts to encipher `data`. If successful,
-             * the returned promise is resolved with an `<ArrayBuffer>` containing the encrypted result.
-             *
-             * The algorithms currently supported include:
-             *
-             * - `'RSA-OAEP'`
-             * - `'AES-CTR'`
-             * - `'AES-CBC'`
-             * - `'AES-GCM'`
-             * @since v15.0.0
-             */
-            encrypt(algorithm: AlgorithmIdentifier | RsaOaepParams | AesCtrParams | AesCbcParams | AesGcmParams, key: CryptoKey, data: BufferSource): Promise<ArrayBuffer>;
-            /**
-             * Exports the given key into the specified format, if supported.
-             *
-             * If the `<CryptoKey>` is not extractable, the returned promise will reject.
-             *
-             * When `format` is either `'pkcs8'` or `'spki'` and the export is successful,
-             * the returned promise will be resolved with an `<ArrayBuffer>` containing the exported key data.
-             *
-             * When `format` is `'jwk'` and the export is successful, the returned promise will be resolved with a
-             * JavaScript object conforming to the {@link https://tools.ietf.org/html/rfc7517 JSON Web Key} specification.
-             * @param format Must be one of `'raw'`, `'pkcs8'`, `'spki'`, or `'jwk'`.
-             * @returns `<Promise>` containing `<ArrayBuffer>`.
-             * @since v15.0.0
-             */
-            exportKey(format: 'jwk', key: CryptoKey): Promise<JsonWebKey>;
-            exportKey(format: Exclude<KeyFormat, 'jwk'>, key: CryptoKey): Promise<ArrayBuffer>;
-            /**
-             * Using the method and parameters provided in `algorithm`,
-             * `subtle.generateKey()` attempts to generate new keying material.
-             * Depending the method used, the method may generate either a single `<CryptoKey>` or a `<CryptoKeyPair>`.
-             *
-             * The `<CryptoKeyPair>` (public and private key) generating algorithms supported include:
-             *
-             * - `'RSASSA-PKCS1-v1_5'`
-             * - `'RSA-PSS'`
-             * - `'RSA-OAEP'`
-             * - `'ECDSA'`
-             * - `'Ed25519'`
-             * - `'Ed448'`
-             * - `'ECDH'`
-             * - `'X25519'`
-             * - `'X448'`
-             * The `<CryptoKey>` (secret key) generating algorithms supported include:
-             *
-             * - `'HMAC'`
-             * - `'AES-CTR'`
-             * - `'AES-CBC'`
-             * - `'AES-GCM'`
-             * - `'AES-KW'`
-             * @param keyUsages See {@link https://nodejs.org/docs/latest/api/webcrypto.html#cryptokeyusages Key usages}.
-             * @since v15.0.0
-             */
-            generateKey(algorithm: RsaHashedKeyGenParams | EcKeyGenParams, extractable: boolean, keyUsages: ReadonlyArray<KeyUsage>): Promise<CryptoKeyPair>;
-            generateKey(algorithm: AesKeyGenParams | HmacKeyGenParams | Pbkdf2Params, extractable: boolean, keyUsages: ReadonlyArray<KeyUsage>): Promise<CryptoKey>;
-            generateKey(algorithm: AlgorithmIdentifier, extractable: boolean, keyUsages: KeyUsage[]): Promise<CryptoKeyPair | CryptoKey>;
-            /**
-             * The `subtle.importKey()` method attempts to interpret the provided `keyData` as the given `format`
-             * to create a `<CryptoKey>` instance using the provided `algorithm`, `extractable`, and `keyUsages` arguments.
-             * If the import is successful, the returned promise will be resolved with the created `<CryptoKey>`.
-             *
-             * If importing a `'PBKDF2'` key, `extractable` must be `false`.
-             * @param format Must be one of `'raw'`, `'pkcs8'`, `'spki'`, or `'jwk'`.
-             * @param keyUsages See {@link https://nodejs.org/docs/latest/api/webcrypto.html#cryptokeyusages Key usages}.
-             * @since v15.0.0
-             */
-            importKey(
-                format: 'jwk',
-                keyData: JsonWebKey,
-                algorithm: AlgorithmIdentifier | RsaHashedImportParams | EcKeyImportParams | HmacImportParams | AesKeyAlgorithm,
-                extractable: boolean,
-                keyUsages: ReadonlyArray<KeyUsage>
-            ): Promise<CryptoKey>;
-            importKey(
-                format: Exclude<KeyFormat, 'jwk'>,
-                keyData: BufferSource,
-                algorithm: AlgorithmIdentifier | RsaHashedImportParams | EcKeyImportParams | HmacImportParams | AesKeyAlgorithm,
-                extractable: boolean,
-                keyUsages: KeyUsage[]
-            ): Promise<CryptoKey>;
-            /**
-             * Using the method and parameters given by `algorithm` and the keying material provided by `key`,
-             * `subtle.sign()` attempts to generate a cryptographic signature of `data`. If successful,
-             * the returned promise is resolved with an `<ArrayBuffer>` containing the generated signature.
-             *
-             * The algorithms currently supported include:
-             *
-             * - `'RSASSA-PKCS1-v1_5'`
-             * - `'RSA-PSS'`
-             * - `'ECDSA'`
-             * - `'Ed25519'`
-             * - `'Ed448'`
-             * - `'HMAC'`
-             * @since v15.0.0
-             */
-            sign(algorithm: AlgorithmIdentifier | RsaPssParams | EcdsaParams | Ed448Params, key: CryptoKey, data: BufferSource): Promise<ArrayBuffer>;
-            /**
-             * In cryptography, "wrapping a key" refers to exporting and then encrypting the keying material.
-             * The `subtle.unwrapKey()` method attempts to decrypt a wrapped key and create a `<CryptoKey>` instance.
-             * It is equivalent to calling `subtle.decrypt()` first on the encrypted key data (using the `wrappedKey`, `unwrapAlgo`, and `unwrappingKey` arguments as input)
-             * then passing the results in to the `subtle.importKey()` method using the `unwrappedKeyAlgo`, `extractable`, and `keyUsages` arguments as inputs.
-             * If successful, the returned promise is resolved with a `<CryptoKey>` object.
-             *
-             * The wrapping algorithms currently supported include:
-             *
-             * - `'RSA-OAEP'`
-             * - `'AES-CTR'`
-             * - `'AES-CBC'`
-             * - `'AES-GCM'`
-             * - `'AES-KW'`
-             *
-             * The unwrapped key algorithms supported include:
-             *
-             * - `'RSASSA-PKCS1-v1_5'`
-             * - `'RSA-PSS'`
-             * - `'RSA-OAEP'`
-             * - `'ECDSA'`
-             * - `'Ed25519'`
-             * - `'Ed448'`
-             * - `'ECDH'`
-             * - `'X25519'`
-             * - `'X448'`
-             * - `'HMAC'`
-             * - `'AES-CTR'`
-             * - `'AES-CBC'`
-             * - `'AES-GCM'`
-             * - `'AES-KW'`
-             * @param format Must be one of `'raw'`, `'pkcs8'`, `'spki'`, or `'jwk'`.
-             * @param keyUsages See {@link https://nodejs.org/docs/latest/api/webcrypto.html#cryptokeyusages Key usages}.
-             * @since v15.0.0
-             */
-            unwrapKey(
-                format: KeyFormat,
-                wrappedKey: BufferSource,
-                unwrappingKey: CryptoKey,
-                unwrapAlgorithm: AlgorithmIdentifier | RsaOaepParams | AesCtrParams | AesCbcParams | AesGcmParams,
-                unwrappedKeyAlgorithm: AlgorithmIdentifier | RsaHashedImportParams | EcKeyImportParams | HmacImportParams | AesKeyAlgorithm,
-                extractable: boolean,
-                keyUsages: KeyUsage[]
-            ): Promise<CryptoKey>;
-            /**
-             * Using the method and parameters given in `algorithm` and the keying material provided by `key`,
-             * `subtle.verify()` attempts to verify that `signature` is a valid cryptographic signature of `data`.
-             * The returned promise is resolved with either `true` or `false`.
-             *
-             * The algorithms currently supported include:
-             *
-             * - `'RSASSA-PKCS1-v1_5'`
-             * - `'RSA-PSS'`
-             * - `'ECDSA'`
-             * - `'Ed25519'`
-             * - `'Ed448'`
-             * - `'HMAC'`
-             * @since v15.0.0
-             */
-            verify(algorithm: AlgorithmIdentifier | RsaPssParams | EcdsaParams | Ed448Params, key: CryptoKey, signature: BufferSource, data: BufferSource): Promise<boolean>;
-            /**
-             * In cryptography, "wrapping a key" refers to exporting and then encrypting the keying material.
-             * The `subtle.wrapKey()` method exports the keying material into the format identified by `format`,
-             * then encrypts it using the method and parameters specified by `wrapAlgo` and the keying material provided by `wrappingKey`.
-             * It is the equivalent to calling `subtle.exportKey()` using `format` and `key` as the arguments,
-             * then passing the result to the `subtle.encrypt()` method using `wrappingKey` and `wrapAlgo` as inputs.
-             * If successful, the returned promise will be resolved with an `<ArrayBuffer>` containing the encrypted key data.
-             *
-             * The wrapping algorithms currently supported include:
-             *
-             * - `'RSA-OAEP'`
-             * - `'AES-CTR'`
-             * - `'AES-CBC'`
-             * - `'AES-GCM'`
-             * - `'AES-KW'`
-             * @param format Must be one of `'raw'`, `'pkcs8'`, `'spki'`, or `'jwk'`.
-             * @since v15.0.0
-             */
-            wrapKey(format: KeyFormat, key: CryptoKey, wrappingKey: CryptoKey, wrapAlgorithm: AlgorithmIdentifier | RsaOaepParams | AesCtrParams | AesCbcParams | AesGcmParams): Promise<ArrayBuffer>;
-        }
-    }
-}
-declare module 'node:crypto' {
-    export * from 'crypto';
-}
diff --git a/spaces/fffiloni/controlnet-animation-doodle/node_modules/raw-body/index.d.ts b/spaces/fffiloni/controlnet-animation-doodle/node_modules/raw-body/index.d.ts
deleted file mode 100644
index dcbbebd4c8f3a6f2cc12c4f862d90b8f2e4eaa28..0000000000000000000000000000000000000000
--- a/spaces/fffiloni/controlnet-animation-doodle/node_modules/raw-body/index.d.ts
+++ /dev/null
@@ -1,87 +0,0 @@
-import { Readable } from 'stream';
-
-declare namespace getRawBody {
-  export type Encoding = string | true;
-
-  export interface Options {
-    /**
-     * The expected length of the stream.
-     */
-    length?: number | string | null;
-    /**
-     * The byte limit of the body. This is the number of bytes or any string
-     * format supported by `bytes`, for example `1000`, `'500kb'` or `'3mb'`.
-     */
-    limit?: number | string | null;
-    /**
-     * The encoding to use to decode the body into a string. By default, a
-     * `Buffer` instance will be returned when no encoding is specified. Most
-     * likely, you want `utf-8`, so setting encoding to `true` will decode as
-     * `utf-8`. You can use any type of encoding supported by `iconv-lite`.
-     */
-    encoding?: Encoding | null;
-  }
-
-  export interface RawBodyError extends Error {
-    /**
-     * The limit in bytes.
-     */
-    limit?: number;
-    /**
-     * The expected length of the stream.
-     */
-    length?: number;
-    expected?: number;
-    /**
-     * The received bytes.
-     */
-    received?: number;
-    /**
-     * The encoding.
-     */
-    encoding?: string;
-    /**
-     * The corresponding status code for the error.
-     */
-    status: number;
-    statusCode: number;
-    /**
-     * The error type.
-     */
-    type: string;
-  }
-}
-
-/**
- * Gets the entire buffer of a stream either as a `Buffer` or a string.
- * Validates the stream's length against an expected length and maximum
- * limit. Ideal for parsing request bodies.
- */
-declare function getRawBody(
-  stream: Readable,
-  callback: (err: getRawBody.RawBodyError, body: Buffer) => void
-): void;
-
-declare function getRawBody(
-  stream: Readable,
-  options: (getRawBody.Options & { encoding: getRawBody.Encoding }) | getRawBody.Encoding,
-  callback: (err: getRawBody.RawBodyError, body: string) => void
-): void;
-
-declare function getRawBody(
-  stream: Readable,
-  options: getRawBody.Options,
-  callback: (err: getRawBody.RawBodyError, body: Buffer) => void
-): void;
-
-declare function getRawBody(
-  stream: Readable,
-  options: (getRawBody.Options & { encoding: getRawBody.Encoding }) | getRawBody.Encoding
-): Promise<string>;
-
-declare function getRawBody(
-  stream: Readable,
-  options?: getRawBody.Options
-): Promise<Buffer>;
-
-export = getRawBody;
diff --git a/spaces/flax-community/DietNerf-Demo/jaxnerf/nerf/clip_utils.py b/spaces/flax-community/DietNerf-Demo/jaxnerf/nerf/clip_utils.py
deleted file mode 100644
index 0beed2c519448d33bc0400d6313398eb7acf2aa8..0000000000000000000000000000000000000000
--- a/spaces/flax-community/DietNerf-Demo/jaxnerf/nerf/clip_utils.py
+++ /dev/null
@@ -1,118 +0,0 @@
-import math
-from typing import Optional
-from absl import flags
-from functools import partial
-
-import jax
-from jax import random
-import jax.numpy as jnp
-import numpy as np
-from transformers import FlaxCLIPModel
-
-from jaxnerf.nerf import utils
-
-FLAGS = flags.FLAGS
-
-@partial(jax.jit, static_argnums=[0])
-def semantic_loss(clip_model, src_image, target_embedding): 
-    src_image = utils.unshard(src_image)
-    w = int(math.sqrt(src_image.size//3))
-    src_image = src_image.reshape([w, w, 3])
- 
-    src_embedding = clip_model.get_image_features(pixel_values=preprocess_for_CLIP(jnp.expand_dims(src_image,0).transpose(0, 3, 1, 2)))
-    src_embedding /= jnp.linalg.norm(src_embedding, axis=-1, keepdims=True)
-    src_embedding = jnp.array(src_embedding)
-    sc_loss = 0.5 * jnp.sum((src_embedding - target_embedding) ** 2) / src_embedding.shape[0]
-    return sc_loss, src_image
-
-def semantic_step_multi(render_pfn, clip_model, rng, state, batch, lr):
-    random_rays = jax.tree_map(lambda x: utils.shard(x).astype(jnp.float16), batch["random_rays"])
-    target_embedding = batch["embedding"].astype(jnp.float16)
-    rng, key_0, key_1 = random.split(rng,3)
-
-    def loss_fn(variables):
-        src_image = render_pfn(variables, key_0, key_1, random_rays)
-        sc_loss, src_image = semantic_loss(clip_model, src_image, target_embedding)
-        return sc_loss * FLAGS.sc_loss_mult, src_image
-    (sc_loss, src_image), grad = jax.value_and_grad(loss_fn, has_aux = True)(jax.device_get(jax.tree_map(lambda x:x[0].astype(jnp.float16), state)).optimizer.target)
-    return sc_loss, grad, src_image
-
-@partial(jax.jit, static_argnums=[0, 1])
-def semantic_step_single(model, clip_model, rng, state, batch, lr):
-    # the batch is without shard
-    random_rays = batch["random_rays"]
-    rng, key_0, key_1 = random.split(rng,3)
-
-    def semantic_loss(variables):
-        src_image = model.apply(variables, key_0, key_1, random_rays, False, rgb_only = True)
-        # reshape flat pixel to an image (assume 3 channels & square shape)
-        w = int(math.sqrt(src_image.shape[0]))
-        src_image = src_image.reshape([w, w, 3])
-        src_embedding = clip_model.get_image_features(pixel_values=preprocess_for_CLIP(jnp.expand_dims(src_image,0).transpose(0, 3, 1, 2)))
-        src_embedding /= jnp.linalg.norm(src_embedding, axis=-1, keepdims=True)
-        src_embedding = jnp.array(src_embedding)
-        target_embedding = batch["embedding"]
-        sc_loss = 0.5 * jnp.sum((src_embedding - target_embedding) ** 2) / src_embedding.shape[0]
-        return sc_loss * FLAGS.sc_loss_mult, src_image
-    (sc_loss, src_image), grad = jax.value_and_grad(semantic_loss, has_aux = True)(jax.device_get(jax.tree_map(lambda x:x[0], state)).optimizer.target)
-    return sc_loss, grad, src_image
-
-def trans_t(t):
-    return jnp.array([
-        [1, 0, 0, 0],
-        [0, 1, 0, 0],
-        [0, 0, 1, t],
-        [0, 0, 0, 1]], dtype=jnp.float32)
-
-def rot_phi(phi):
-    return jnp.array([
-        [1, 0, 0, 0],
-        [0, jnp.cos(phi), jnp.sin(phi), 0],
-        [0,-jnp.sin(phi), jnp.cos(phi), 0],
-        [0, 0, 0, 1]], dtype=jnp.float32)
-
-def rot_theta(th):
-    return jnp.array([
-        [jnp.cos(th), 0,-jnp.sin(th), 0],
-        [0, 1, 0, 0],
-        [jnp.sin(th), 0, jnp.cos(th), 0],
-        [0, 0, 0, 1]], dtype=jnp.float32)
-
-def pose_spherical(radius, theta, phi):
-    c2w = trans_t(radius)
-    c2w = rot_phi(phi) @ c2w
-    c2w = rot_theta(theta) @ c2w
-    c2w = jnp.array([[-1, 0, 0, 0], [0, 0, 1, 0], [0, 1, 0, 0], [0, 0, 0, 1]]) @ c2w
-    return c2w
-
-def random_pose(rng, bds):
-    rng, *rng_inputs = jax.random.split(rng, 3)
-    radius = random.uniform(rng_inputs[1], minval=bds[0], maxval=bds[1])
-    theta = random.uniform(rng_inputs[1], minval=-jnp.pi, maxval=jnp.pi)
-    phi = random.uniform(rng_inputs[1], minval=0, maxval=jnp.pi/2)
-    return pose_spherical(radius, theta, phi)
-
-def preprocess_for_CLIP(image):
-    """
-    jax-based preprocessing for CLIP
-    image  [B, 3, H, W]: batch image
-    return [B, 3, 224, 224]: pre-processed image for CLIP
-    """
-    B, D, H, W = image.shape
-    mean = jnp.array([0.48145466, 0.4578275, 0.40821073]).reshape(1, 3, 1, 1)
-    std = jnp.array([0.26862954, 0.26130258, 0.27577711]).reshape(1, 3, 1, 1)
-    image = jax.image.resize(image, (B, D, 224, 224), 'bicubic')  # assume that images have rectangle shape.
-    image = (image - mean.astype(image.dtype)) / std.astype(image.dtype)
-    return image
-
-def init_CLIP(dtype: str, model_name: Optional[str]) -> FlaxCLIPModel:
-    if dtype == 'float16':
-        dtype = jnp.float16
-    elif dtype == 'float32':
-        dtype = jnp.float32
-    else:
-        raise ValueError
-
-    if model_name is None:
-        model_name = 'openai/clip-vit-base-patch32'
-    return FlaxCLIPModel.from_pretrained(model_name, dtype=dtype)
diff --git a/spaces/fuckyoudeki/AutoGPT/autogpt/agent/agent_manager.py b/spaces/fuckyoudeki/AutoGPT/autogpt/agent/agent_manager.py
deleted file mode 100644
index 898767a485e50b5e62625a7883edf1b30d5fddf9..0000000000000000000000000000000000000000
--- a/spaces/fuckyoudeki/AutoGPT/autogpt/agent/agent_manager.py
+++ /dev/null
@@ -1,103 +0,0 @@
-"""Agent manager for managing GPT agents"""
-from __future__ import annotations
-
-from typing import Union
-
-from autogpt.config.config import Singleton
-from autogpt.llm_utils import create_chat_completion
-
-
-class AgentManager(metaclass=Singleton):
-    """Agent manager for managing GPT agents"""
-
-    def __init__(self):
-        self.next_key = 0
-        self.agents = {}  # key, (task, full_message_history, model)
-
-    # Create new GPT agent
-    # TODO: Centralise use of create_chat_completion() to globally enforce token limit
-
-    def create_agent(self, task: str, prompt: str, model: str) -> tuple[int, str]:
-        """Create a new agent and return its key
-
-        Args:
-            task: The task to perform
-            prompt: The prompt to use
-            model: The model to use
-
-        Returns:
-            The key of the new agent
-        """
-        messages = [
-            {"role": "user", "content": prompt},
-        ]
-
-        # Start GPT instance
-        agent_reply = create_chat_completion(
-            model=model,
-            messages=messages,
-        )
-
-        # Update full message history
-        messages.append({"role": "assistant", "content": agent_reply})
-
-        key = self.next_key
-        # This is done instead of len(agents) to make keys unique even if agents
-        # are deleted
-        self.next_key += 1
-
-        self.agents[key] = (task, messages, model)
-
-        return key, agent_reply
-
-    def message_agent(self, key: str | int, message: str) -> str:
-        """Send a message to an agent and return its response
-
-        Args:
-            key: The key of the agent to message
-            message: The message to send to the agent
-
-        Returns:
-            The agent's response
-        """
-        task, messages, model = self.agents[int(key)]
-
-        # Add user message to message history before sending to agent
-        messages.append({"role": "user", "content": message})
-
-        # Start GPT instance
-        agent_reply = create_chat_completion(
-            model=model,
-            messages=messages,
-        )
-
-        # Update full message history
-        messages.append({"role": "assistant", "content": agent_reply})
-
-        return agent_reply
-
-    def list_agents(self) -> list[tuple[str | int, str]]:
-        """Return a list of all agents
-
-        Returns:
-            A list of tuples of the form (key, task)
-        """
-
-        # Return a list of agent keys and their tasks
-        return [(key, task) for key, (task, _, _) in self.agents.items()]
-
-    def delete_agent(self, key: Union[str, int]) -> bool:
-        """Delete an agent from the agent manager
-
-        Args:
-            key: The key of the agent to delete
-
-        Returns:
-            True if successful, False otherwise
-        """
-
-        try:
-            del self.agents[int(key)]
-            return True
-        except KeyError:
-            return False
diff --git a/spaces/fuckyoudeki/AutoGPT/autogpt/setup.py b/spaces/fuckyoudeki/AutoGPT/autogpt/setup.py
deleted file mode 100644
index bfa68201b62bf67230a61fb1ecb00d1ab0ef0631..0000000000000000000000000000000000000000
--- a/spaces/fuckyoudeki/AutoGPT/autogpt/setup.py
+++ /dev/null
@@ -1,77 +0,0 @@
-"""Set up the AI and its goals"""
-from colorama import Fore, Style
-
-from autogpt import utils
-from autogpt.config.ai_config import AIConfig
-from autogpt.logs import logger
-
-
-def prompt_user() -> AIConfig:
-    """Prompt the user for input
-
-    Returns:
-        AIConfig: The AIConfig object containing the user's input
-    """
-    ai_name = ""
-    # Construct the prompt
-    logger.typewriter_log(
-        "Welcome to Auto-GPT! ",
-        Fore.GREEN,
-        "run with '--help' for more information.",
-        speak_text=True,
-    )
-
-    logger.typewriter_log(
-        "Create an AI-Assistant:",
-        Fore.GREEN,
-        "Enter the name of your AI and its role below. Entering nothing will load"
-        " defaults.",
-        speak_text=True,
-    )
-
-    # Get AI Name from User
-    logger.typewriter_log(
-        "Name your AI: ", Fore.GREEN, "For example, 'Entrepreneur-GPT'"
-    )
-    ai_name = utils.clean_input("AI Name: ")
-    if ai_name == "":
-        ai_name = "Entrepreneur-GPT"
-
-    logger.typewriter_log(
-        f"{ai_name} here!", Fore.LIGHTBLUE_EX, "I am at your service.", speak_text=True
-    )
-
-    # Get AI Role from User
-    logger.typewriter_log(
-        "Describe your AI's role: ",
-        Fore.GREEN,
-        "For example, 'an AI designed to autonomously develop and run businesses with"
-        " the sole goal of increasing your net worth.'",
-    )
-    ai_role = utils.clean_input(f"{ai_name} is: ")
-    if ai_role == "":
-        ai_role = "an AI designed to autonomously develop and run businesses with the"
-        " sole goal of increasing your net worth."
-
-    # Enter up to 5 goals for the AI
-    logger.typewriter_log(
-        "Enter up to 5 goals for your AI: ",
-        Fore.GREEN,
-        "For example: \nIncrease net worth, Grow Twitter Account, Develop and manage"
-        " multiple businesses autonomously'",
-    )
-    print("Enter nothing to load defaults, enter nothing when finished.", flush=True)
-    ai_goals = []
-    for i in range(5):
-        ai_goal = utils.clean_input(f"{Fore.LIGHTBLUE_EX}Goal{Style.RESET_ALL} {i+1}: ")
-        if ai_goal == "":
-            break
-        ai_goals.append(ai_goal)
-    if not ai_goals:
-        ai_goals = [
-            "Increase net worth",
-            "Grow Twitter Account",
-            "Develop and manage multiple businesses autonomously",
-        ]
-
-    return AIConfig(ai_name, ai_role, ai_goals)
diff --git a/spaces/fuckyoudeki/AutoGPT/run_continuous.bat b/spaces/fuckyoudeki/AutoGPT/run_continuous.bat
deleted file mode 100644
index 812aa01c1c5506c452665610c0e9e83a17c426f2..0000000000000000000000000000000000000000
--- a/spaces/fuckyoudeki/AutoGPT/run_continuous.bat
+++ /dev/null
@@ -1,3 +0,0 @@
-@echo off
-set argument=--continuous
-call run.bat %argument%
diff --git a/spaces/fun-research/FC-CLIP/fcclip/data/datasets/register_ade20k_instance.py b/spaces/fun-research/FC-CLIP/fcclip/data/datasets/register_ade20k_instance.py
deleted file mode 100644
index ab6b614b1a8a5fdcd905e49fcbb3037cd1431117..0000000000000000000000000000000000000000
--- a/spaces/fun-research/FC-CLIP/fcclip/data/datasets/register_ade20k_instance.py
+++ /dev/null
@@ -1,55 +0,0 @@
-# Copyright (c) Facebook, Inc. and its affiliates.
-import json
-import logging
-import numpy as np
-import os
-from PIL import Image
-
-from detectron2.data import DatasetCatalog, MetadataCatalog
-from detectron2.data.datasets.coco import load_coco_json, register_coco_instances
-from detectron2.utils.file_io import PathManager
-
-from . import openseg_classes
-import copy
-ADE_CATEGORIES = copy.deepcopy(openseg_classes.ADE20K_150_CATEGORIES)
-ADE_CATEGORIES = [x for x in ADE_CATEGORIES if x["isthing"] == 1]
-
-_PREDEFINED_SPLITS = {
-    # point annotations without masks
-    "openvocab_ade20k_instance_train": (
-        "ADEChallengeData2016/images/training",
-        "ADEChallengeData2016/ade20k_instance_train.json",
-    ),
-    "openvocab_ade20k_instance_val": (
-        "ADEChallengeData2016/images/validation",
-        "ADEChallengeData2016/ade20k_instance_val.json",
-    ),
-}
-
-
-def _get_ade_instances_meta():
-    thing_ids = [k["id"] for k in ADE_CATEGORIES]
-    assert len(thing_ids) == 100, len(thing_ids)
-    # Mapping from the incontiguous ADE category id to an id in [0, 99]
-    thing_dataset_id_to_contiguous_id = {k: i for i, k in enumerate(thing_ids)}
-    thing_classes = [k["name"] for k in ADE_CATEGORIES]
-    ret = {
-        "thing_dataset_id_to_contiguous_id": thing_dataset_id_to_contiguous_id,
-        "thing_classes": thing_classes,
-    }
-    return ret
-
-
-def register_all_ade20k_instance(root):
-    for key, (image_root, json_file) in _PREDEFINED_SPLITS.items():
-        # Assume pre-defined datasets live in `./datasets`.
-        register_coco_instances(
-            key,
-            _get_ade_instances_meta(),
-            os.path.join(root, json_file) if "://" not in json_file else json_file,
-            os.path.join(root, image_root),
-        )
-
-
-_root = os.getenv("DETECTRON2_DATASETS", "datasets")
-register_all_ade20k_instance(_root)
diff --git a/spaces/fun-research/FC-CLIP/fcclip/modeling/__init__.py b/spaces/fun-research/FC-CLIP/fcclip/modeling/__init__.py
deleted file mode 100644
index 25d28b0fdf594f58dbb6038e82412425d7c312bf..0000000000000000000000000000000000000000
--- a/spaces/fun-research/FC-CLIP/fcclip/modeling/__init__.py
+++ /dev/null
@@ -1,4 +0,0 @@
-# Copyright (c) Facebook, Inc. and its affiliates.
-from .backbone.clip import CLIP
-from .pixel_decoder.msdeformattn import MSDeformAttnPixelDecoder
-from .meta_arch.fcclip_head import FCCLIPHead
\ No newline at end of file
diff --git a/spaces/georgefen/Face-Landmark-ControlNet/ldm/modules/midas/midas/__init__.py b/spaces/georgefen/Face-Landmark-ControlNet/ldm/modules/midas/midas/__init__.py
deleted file mode 100644
index e69de29bb2d1d6434b8b29ae775ad8c2e48c5391..0000000000000000000000000000000000000000
diff --git a/spaces/georgescutelnicu/neural-style-transfer/model.py b/spaces/georgescutelnicu/neural-style-transfer/model.py
deleted file mode 100644
index 1ef52d2c23e2604089c91d11a7a215fdede68ec4..0000000000000000000000000000000000000000
--- a/spaces/georgescutelnicu/neural-style-transfer/model.py
+++ /dev/null
@@ -1,18 +0,0 @@
-
-import torchvision
-
-def create_vgg_model():
-   
-    # Create model
-    model_weights = torchvision.models.VGG19_Weights.DEFAULT
-    model = torchvision.models.vgg19(weights=model_weights)
-    
-
-    # Freeze layers
-    for param in model.parameters():
-      param.requires_grad = False
-
-    # Kepp only the features of the model
-    model = model.features
-    
-    return model
diff --git a/spaces/glyszt/vt/vtoonify/model/encoder/encoders/__init__.py b/spaces/glyszt/vt/vtoonify/model/encoder/encoders/__init__.py
deleted file mode 100644
index e69de29bb2d1d6434b8b29ae775ad8c2e48c5391..0000000000000000000000000000000000000000
diff --git a/spaces/gradio/HuBERT/examples/backtranslation/README.md b/spaces/gradio/HuBERT/examples/backtranslation/README.md
deleted file mode 100644
index 73675f1125d80f58aa824db67d8970504d4d6b2a..0000000000000000000000000000000000000000
--- a/spaces/gradio/HuBERT/examples/backtranslation/README.md
+++ /dev/null
@@ -1,297 +0,0 @@
-# Understanding Back-Translation at Scale (Edunov et al., 2018)
-
-This page includes pre-trained models from the paper [Understanding Back-Translation at Scale (Edunov et al., 2018)](https://arxiv.org/abs/1808.09381).
-
-## Pre-trained models
-
-Model | Description | Dataset | Download
----|---|---|---
-`transformer.wmt18.en-de` | Transformer <br> ([Edunov et al., 2018](https://arxiv.org/abs/1808.09381)) <br> WMT'18 winner | [WMT'18 English-German](http://www.statmt.org/wmt18/translation-task.html) | [download (.tar.gz)](https://dl.fbaipublicfiles.com/fairseq/models/wmt18.en-de.ensemble.tar.gz) <br> See NOTE in the archive
-
-## Example usage (torch.hub)
-
-We require a few additional Python dependencies for preprocessing:
-```bash
-pip install subword_nmt sacremoses
-```
-
-Then to generate translations from the full model ensemble:
-```python
-import torch
-
-# List available models
-torch.hub.list('pytorch/fairseq')  # [..., 'transformer.wmt18.en-de', ... ]
-
-# Load the WMT'18 En-De ensemble
-en2de_ensemble = torch.hub.load(
-    'pytorch/fairseq', 'transformer.wmt18.en-de',
-    checkpoint_file='wmt18.model1.pt:wmt18.model2.pt:wmt18.model3.pt:wmt18.model4.pt:wmt18.model5.pt',
-    tokenizer='moses', bpe='subword_nmt')
-
-# The ensemble contains 5 models
-len(en2de_ensemble.models)
-# 5
-
-# Translate
-en2de_ensemble.translate('Hello world!')
-# 'Hallo Welt!'
-```
-
-## Training your own model (WMT'18 English-German)
-
-The following instructions can be adapted to reproduce the models from the paper.
-
-
-#### Step 1. Prepare parallel data and optionally train a baseline (English-German) model
-
-First download and preprocess the data:
-```bash
-# Download and prepare the data
-cd examples/backtranslation/
-bash prepare-wmt18en2de.sh
-cd ../..
-
-# Binarize the data
-TEXT=examples/backtranslation/wmt18_en_de
-fairseq-preprocess \
-    --joined-dictionary \
-    --source-lang en --target-lang de \
-    --trainpref $TEXT/train --validpref $TEXT/valid --testpref $TEXT/test \
-    --destdir data-bin/wmt18_en_de --thresholdtgt 0 --thresholdsrc 0 \
-    --workers 20
-
-# Copy the BPE code into the data-bin directory for future use
-cp examples/backtranslation/wmt18_en_de/code data-bin/wmt18_en_de/code
-```
-
-(Optionally) Train a baseline model (English-German) using just the parallel data:
-```bash
-CHECKPOINT_DIR=checkpoints_en_de_parallel
-fairseq-train --fp16 \
-    data-bin/wmt18_en_de \
-    --source-lang en --target-lang de \
-    --arch transformer_wmt_en_de_big --share-all-embeddings \
-    --dropout 0.3 --weight-decay 0.0 \
-    --criterion label_smoothed_cross_entropy --label-smoothing 0.1 \
-    --optimizer adam --adam-betas '(0.9, 0.98)' --clip-norm 0.0 \
-    --lr 0.001 --lr-scheduler inverse_sqrt --warmup-updates 4000 \
-    --max-tokens 3584 --update-freq 16 \
-    --max-update 30000 \
-    --save-dir $CHECKPOINT_DIR
-# Note: the above command assumes 8 GPUs. Adjust `--update-freq` if you have a
-# different number of GPUs.
-```
-
-Average the last 10 checkpoints:
-```bash
-python scripts/average_checkpoints.py \
-    --inputs $CHECKPOINT_DIR \
-    --num-epoch-checkpoints 10 \
-    --output $CHECKPOINT_DIR/checkpoint.avg10.pt
-```
-
-Evaluate BLEU:
-```bash
-# tokenized BLEU on newstest2017:
-bash examples/backtranslation/tokenized_bleu.sh \
-    wmt17 \
-    en-de \
-    data-bin/wmt18_en_de \
-    data-bin/wmt18_en_de/code \
-    $CHECKPOINT_DIR/checkpoint.avg10.pt
-# BLEU4 = 29.57, 60.9/35.4/22.9/15.5 (BP=1.000, ratio=1.014, syslen=63049, reflen=62152)
-# compare to 29.46 in Table 1, which is also for tokenized BLEU
-
-# generally it's better to report (detokenized) sacrebleu though:
-bash examples/backtranslation/sacrebleu.sh \
-    wmt17 \
-    en-de \
-    data-bin/wmt18_en_de \
-    data-bin/wmt18_en_de/code \
-    $CHECKPOINT_DIR/checkpoint.avg10.pt
-# BLEU+case.mixed+lang.en-de+numrefs.1+smooth.exp+test.wmt17+tok.13a+version.1.4.3 = 29.0 60.6/34.7/22.4/14.9 (BP = 1.000 ratio = 1.013 hyp_len = 62099 ref_len = 61287)
-```
-
-
-#### Step 2. Back-translate monolingual German data
-
-Train a reverse model (German-English) to do the back-translation:
-```bash
-CHECKPOINT_DIR=checkpoints_de_en_parallel
-fairseq-train --fp16 \
-    data-bin/wmt18_en_de \
-    --source-lang de --target-lang en \
-    --arch transformer_wmt_en_de_big --share-all-embeddings \
-    --dropout 0.3 --weight-decay 0.0 \
-    --criterion label_smoothed_cross_entropy --label-smoothing 0.1 \
-    --optimizer adam --adam-betas '(0.9, 0.98)' --clip-norm 0.0 \
-    --lr 0.001 --lr-scheduler inverse_sqrt --warmup-updates 4000 \
-    --max-tokens 3584 --update-freq 16 \
-    --max-update 30000 \
-    --save-dir $CHECKPOINT_DIR
-# Note: the above command assumes 8 GPUs. Adjust `--update-freq` if you have a
-# different number of GPUs.
-```
-
-Let's evaluate the back-translation (BT) model to make sure it is well trained:
-```bash
-bash examples/backtranslation/sacrebleu.sh \
-    wmt17 \
-    de-en \
-    data-bin/wmt18_en_de \
-    data-bin/wmt18_en_de/code \
-    $CHECKPOINT_DIR/checkpoint_best.py
-# BLEU+case.mixed+lang.de-en+numrefs.1+smooth.exp+test.wmt17+tok.13a+version.1.4.3 = 34.9 66.9/41.8/28.5/19.9 (BP = 0.983 ratio = 0.984 hyp_len = 63342 ref_len = 64399)
-# compare to the best system from WMT'17 which scored 35.1: http://matrix.statmt.org/matrix/systems_list/1868
-```
-
-Next prepare the monolingual data:
-```bash
-# Download and prepare the monolingual data
-# By default the script samples 25M monolingual sentences, which after
-# deduplication should be just over 24M sentences. These are split into 25
-# shards, each with 1M sentences (except for the last shard).
-cd examples/backtranslation/
-bash prepare-de-monolingual.sh
-cd ../..
-
-# Binarize each shard of the monolingual data
-TEXT=examples/backtranslation/wmt18_de_mono
-for SHARD in $(seq -f "%02g" 0 24); do \
-    fairseq-preprocess \
-        --only-source \
-        --source-lang de --target-lang en \
-        --joined-dictionary \
-        --srcdict data-bin/wmt18_en_de/dict.de.txt \
-        --testpref $TEXT/bpe.monolingual.dedup.${SHARD} \
-        --destdir data-bin/wmt18_de_mono/shard${SHARD} \
-        --workers 20; \
-    cp data-bin/wmt18_en_de/dict.en.txt data-bin/wmt18_de_mono/shard${SHARD}/; \
-done
-```
-
-Now we're ready to perform back-translation over the monolingual data. The
-following command generates via sampling, but it's possible to use greedy
-decoding (`--beam 1`), beam search (`--beam 5`),
-top-k sampling (`--sampling --beam 1 --sampling-topk 10`), etc.:
-```bash
-mkdir backtranslation_output
-for SHARD in $(seq -f "%02g" 0 24); do \
-    fairseq-generate --fp16 \
-        data-bin/wmt18_de_mono/shard${SHARD} \
-        --path $CHECKPOINT_DIR/checkpoint_best.pt \
-        --skip-invalid-size-inputs-valid-test \
-        --max-tokens 4096 \
-        --sampling --beam 1 \
-    > backtranslation_output/sampling.shard${SHARD}.out; \
-done
-```
-
-After BT, use the `extract_bt_data.py` script to re-combine the shards, extract
-the back-translations and apply length ratio filters:
-```bash
-python examples/backtranslation/extract_bt_data.py \
-    --minlen 1 --maxlen 250 --ratio 1.5 \
-    --output backtranslation_output/bt_data --srclang en --tgtlang de \
-    backtranslation_output/sampling.shard*.out
-
-# Ensure lengths are the same:
-# wc -l backtranslation_output/bt_data.{en,de}
-#   21795614 backtranslation_output/bt_data.en
-#   21795614 backtranslation_output/bt_data.de
-#   43591228 total
-```
-
-Binarize the filtered BT data and combine it with the parallel data:
-```bash
-TEXT=backtranslation_output
-fairseq-preprocess \
-    --source-lang en --target-lang de \
-    --joined-dictionary \
-    --srcdict data-bin/wmt18_en_de/dict.en.txt \
-    --trainpref $TEXT/bt_data \
-    --destdir data-bin/wmt18_en_de_bt \
-    --workers 20
-
-# We want to train on the combined data, so we'll symlink the parallel + BT data
-# in the wmt18_en_de_para_plus_bt directory. We link the parallel data as "train"
-# and the BT data as "train1", so that fairseq will combine them automatically
-# and so that we can use the `--upsample-primary` option to upsample the
-# parallel data (if desired).
-PARA_DATA=$(readlink -f data-bin/wmt18_en_de)
-BT_DATA=$(readlink -f data-bin/wmt18_en_de_bt)
-COMB_DATA=data-bin/wmt18_en_de_para_plus_bt
-mkdir -p $COMB_DATA
-for LANG in en de; do \
-    ln -s ${PARA_DATA}/dict.$LANG.txt ${COMB_DATA}/dict.$LANG.txt; \
-    for EXT in bin idx; do \
-        ln -s ${PARA_DATA}/train.en-de.$LANG.$EXT ${COMB_DATA}/train.en-de.$LANG.$EXT; \
-        ln -s ${BT_DATA}/train.en-de.$LANG.$EXT ${COMB_DATA}/train1.en-de.$LANG.$EXT; \
-        ln -s ${PARA_DATA}/valid.en-de.$LANG.$EXT ${COMB_DATA}/valid.en-de.$LANG.$EXT; \
-        ln -s ${PARA_DATA}/test.en-de.$LANG.$EXT ${COMB_DATA}/test.en-de.$LANG.$EXT; \
-    done; \
-done
-```
-
-
-#### 3. Train an English-German model over the combined parallel + BT data
-
-Finally we can train a model over the parallel + BT data:
-```bash
-CHECKPOINT_DIR=checkpoints_en_de_parallel_plus_bt
-fairseq-train --fp16 \
-    data-bin/wmt18_en_de_para_plus_bt \
-    --upsample-primary 16 \
-    --source-lang en --target-lang de \
-    --arch transformer_wmt_en_de_big --share-all-embeddings \
-    --dropout 0.3 --weight-decay 0.0 \
-    --criterion label_smoothed_cross_entropy --label-smoothing 0.1 \
-    --optimizer adam --adam-betas '(0.9, 0.98)' --clip-norm 0.0 \
-    --lr 0.0007 --lr-scheduler inverse_sqrt --warmup-updates 4000 \
-    --max-tokens 3584 --update-freq 16 \
-    --max-update 100000 \
-    --save-dir $CHECKPOINT_DIR
-# Note: the above command assumes 8 GPUs. Adjust `--update-freq` if you have a
-# different number of GPUs.
-```
-
-Average the last 10 checkpoints:
-```bash
-python scripts/average_checkpoints.py \
-    --inputs $CHECKPOINT_DIR \
-    --num-epoch-checkpoints 10 \
-    --output $CHECKPOINT_DIR/checkpoint.avg10.pt
-```
-
-Evaluate BLEU:
-```bash
-# tokenized BLEU on newstest2017:
-bash examples/backtranslation/tokenized_bleu.sh \
-    wmt17 \
-    en-de \
-    data-bin/wmt18_en_de \
-    data-bin/wmt18_en_de/code \
-    $CHECKPOINT_DIR/checkpoint.avg10.pt
-# BLEU4 = 32.35, 64.4/38.9/26.2/18.3 (BP=0.977, ratio=0.977, syslen=60729, reflen=62152)
-# compare to 32.35 in Table 1, which is also for tokenized BLEU
-
-# generally it's better to report (detokenized) sacrebleu:
-bash examples/backtranslation/sacrebleu.sh \
-    wmt17 \
-    en-de \
-    data-bin/wmt18_en_de \
-    data-bin/wmt18_en_de/code \
-    $CHECKPOINT_DIR/checkpoint.avg10.pt
-# BLEU+case.mixed+lang.en-de+numrefs.1+smooth.exp+test.wmt17+tok.13a+version.1.4.3 = 31.5 64.3/38.2/25.6/17.6 (BP = 0.971 ratio = 0.971 hyp_len = 59515 ref_len = 61287)
-```
-
-
-## Citation
-```bibtex
-@inproceedings{edunov2018backtranslation,
-  title = {Understanding Back-Translation at Scale},
-  author = {Edunov, Sergey and Ott, Myle and Auli, Michael and Grangier, David},
-  booktitle = {Conference of the Association for Computational Linguistics (ACL)},
-  year = 2018,
-}
-```
diff --git a/spaces/grisiemjahand/Image-and-3D-Model-Creator/PIFu/lib/renderer/gl/init_gl.py b/spaces/grisiemjahand/Image-and-3D-Model-Creator/PIFu/lib/renderer/gl/init_gl.py
deleted file mode 100644
index 1d2c7e6ba0be20136b2be2e2f644894bee4af9c1..0000000000000000000000000000000000000000
--- a/spaces/grisiemjahand/Image-and-3D-Model-Creator/PIFu/lib/renderer/gl/init_gl.py
+++ /dev/null
@@ -1,24 +0,0 @@
-_glut_window = None
-_context_inited = None
-
-def initialize_GL_context(width=512, height=512, egl=False):
-    '''
-    default context uses GLUT
-    '''
-    if not egl:
-        import OpenGL.GLUT as GLUT      
-        display_mode = GLUT.GLUT_DOUBLE | GLUT.GLUT_RGB | GLUT.GLUT_DEPTH
-        global _glut_window
-        if _glut_window is None:
-            GLUT.glutInit()
-            GLUT.glutInitDisplayMode(display_mode)
-            GLUT.glutInitWindowSize(width, height)
-            GLUT.glutInitWindowPosition(0, 0)
-            _glut_window = GLUT.glutCreateWindow("My Render.")
-    else:
-        from .glcontext import create_opengl_context
-        global _context_inited
-        if _context_inited is None:
-            create_opengl_context((width, height))
-            _context_inited = True
-
diff --git a/spaces/gsaivinay/Llama-2-13B-GGML-UI/utils/app/settings.ts b/spaces/gsaivinay/Llama-2-13B-GGML-UI/utils/app/settings.ts
deleted file mode 100644
index acf371e92be468294267ee61d9a913bca60bf5a6..0000000000000000000000000000000000000000
--- a/spaces/gsaivinay/Llama-2-13B-GGML-UI/utils/app/settings.ts
+++ /dev/null
@@ -1,23 +0,0 @@
-import { Settings } from '@/types/settings';
-
-const STORAGE_KEY = 'settings';
-
-export const getSettings = (): Settings => {
-  let settings: Settings = {
-    theme: 'dark',
-  };
-  const settingsJson = localStorage.getItem(STORAGE_KEY);
-  if (settingsJson) {
-    try {
-      let savedSettings = JSON.parse(settingsJson) as Settings;
-      settings = Object.assign(settings, savedSettings);
-    } catch (e) {
-      console.error(e);
-    }
-  }
-  return settings;
-};
-
-export const saveSettings = (settings: Settings) => {
-  localStorage.setItem(STORAGE_KEY, JSON.stringify(settings));
-};
diff --git a/spaces/gundruke/ua-thesis-absa/models/__init__.py b/spaces/gundruke/ua-thesis-absa/models/__init__.py
deleted file mode 100644
index b3f7ac90efed853e8a0ffba7690e18472d1bc88c..0000000000000000000000000000000000000000
--- a/spaces/gundruke/ua-thesis-absa/models/__init__.py
+++ /dev/null
@@ -1 +0,0 @@
-from .BERT_LSTM_CRF import BERTLstmCRF
\ No newline at end of file
diff --git a/spaces/h2oai/h2ogpt-chatbot/src/gradio_runner.py b/spaces/h2oai/h2ogpt-chatbot/src/gradio_runner.py
deleted file mode 100644
index fc62418c977d1ce3b54e63547a667203745a2554..0000000000000000000000000000000000000000
--- a/spaces/h2oai/h2ogpt-chatbot/src/gradio_runner.py
+++ /dev/null
@@ -1,4601 +0,0 @@
-import ast
-import copy
-import functools
-import inspect
-import itertools
-import json
-import os
-import pprint
-import random
-import shutil
-import sys
-import time
-import traceback
-import uuid
-import filelock
-import numpy as np
-import pandas as pd
-import requests
-from iterators import TimeoutIterator
-
-from gradio_utils.css import get_css
-from gradio_utils.prompt_form import make_chatbots
-from src.db_utils import set_userid, get_username_direct
-
-# This is a hack to prevent Gradio from phoning home when it gets imported
-os.environ['GRADIO_ANALYTICS_ENABLED'] = 'False'
-
-
-def my_get(url, **kwargs):
-    print('Gradio HTTP request redirected to localhost :)', flush=True)
-    kwargs.setdefault('allow_redirects', True)
-    return requests.api.request('get', 'http://127.0.0.1/', **kwargs)
-
-
-original_get = requests.get
-requests.get = my_get
-import gradio as gr
-
-requests.get = original_get
-
-
-def fix_pydantic_duplicate_validators_error():
-    try:
-        from pydantic import class_validators
-
-        class_validators.in_ipython = lambda: True  # type: ignore[attr-defined]
-    except ImportError:
-        pass
-
-
-fix_pydantic_duplicate_validators_error()
-
-from enums import DocumentSubset, no_model_str, no_lora_str, no_server_str, LangChainAction, LangChainMode, \
-    DocumentChoice, langchain_modes_intrinsic, LangChainTypes, langchain_modes_non_db, gr_to_lg, invalid_key_msg, \
-    LangChainAgent, docs_ordering_types
-from gradio_themes import H2oTheme, SoftTheme, get_h2o_title, get_simple_title, \
-    get_dark_js, get_heap_js, wrap_js_to_lambda, \
-    spacing_xsm, radius_xsm, text_xsm
-from prompter import prompt_type_to_model_name, prompt_types_strings, inv_prompt_type_to_model_lower, non_hf_types, \
-    get_prompt
-from utils import flatten_list, zip_data, s3up, clear_torch_cache, get_torch_allocated, system_info_print, \
-    ping, makedirs, get_kwargs, system_info, ping_gpu, get_url, get_local_ip, \
-    save_generate_output, url_alive, remove, dict_to_html, text_to_html, lg_to_gr, str_to_dict, have_serpapi
-from gen import get_model, languages_covered, evaluate, score_qa, inputs_kwargs_list, \
-    get_max_max_new_tokens, get_minmax_top_k_docs, history_to_context, langchain_actions, langchain_agents_list, \
-    evaluate_fake, merge_chat_conversation_history
-from evaluate_params import eval_func_param_names, no_default_param_names, eval_func_param_names_defaults, \
-    input_args_list, key_overrides
-
-from apscheduler.schedulers.background import BackgroundScheduler
-
-
-def fix_text_for_gradio(text, fix_new_lines=False, fix_latex_dollars=True):
-    if fix_latex_dollars:
-        ts = text.split('```')
-        for parti, part in enumerate(ts):
-            inside = parti % 2 == 1
-            if not inside:
-                ts[parti] = ts[parti].replace('$', '﹩')
-        text = '```'.join(ts)
-
-    if fix_new_lines:
-        # let Gradio handle code, since got improved recently
-        ## FIXME: below conflicts with Gradio, but need to see if can handle multiple \n\n\n etc. properly as is.
-        # ensure good visually, else markdown ignores multiple \n
-        # handle code blocks
-        ts = text.split('```')
-        for parti, part in enumerate(ts):
-            inside = parti % 2 == 1
-            if not inside:
-                ts[parti] = ts[parti].replace('\n', '<br>')
-        text = '```'.join(ts)
-    return text
-
-
-def is_valid_key(enforce_h2ogpt_api_key, h2ogpt_api_keys, h2ogpt_key1, requests_state1=None):
-    valid_key = False
-    if not enforce_h2ogpt_api_key:
-        # no token barrier
-        valid_key = 'not enforced'
-    else:
-        if isinstance(h2ogpt_api_keys, list) and h2ogpt_key1 in h2ogpt_api_keys:
-            # passed token barrier
-            valid_key = True
-        elif isinstance(h2ogpt_api_keys, str) and os.path.isfile(h2ogpt_api_keys):
-            with filelock.FileLock(h2ogpt_api_keys + '.lock'):
-                with open(h2ogpt_api_keys, 'rt') as f:
-                    h2ogpt_api_keys = json.load(f)
-                if h2ogpt_key1 in h2ogpt_api_keys:
-                    valid_key = True
-    if isinstance(requests_state1, dict) and 'username' in requests_state1 and requests_state1['username']:
-        # no UI limit currently
-        valid_key = True
-    return valid_key
-
-
-def go_gradio(**kwargs):
-    allow_api = kwargs['allow_api']
-    is_public = kwargs['is_public']
-    is_hf = kwargs['is_hf']
-    memory_restriction_level = kwargs['memory_restriction_level']
-    n_gpus = kwargs['n_gpus']
-    admin_pass = kwargs['admin_pass']
-    model_states = kwargs['model_states']
-    dbs = kwargs['dbs']
-    db_type = kwargs['db_type']
-    visible_langchain_actions = kwargs['visible_langchain_actions']
-    visible_langchain_agents = kwargs['visible_langchain_agents']
-    allow_upload_to_user_data = kwargs['allow_upload_to_user_data']
-    allow_upload_to_my_data = kwargs['allow_upload_to_my_data']
-    enable_sources_list = kwargs['enable_sources_list']
-    enable_url_upload = kwargs['enable_url_upload']
-    enable_text_upload = kwargs['enable_text_upload']
-    use_openai_embedding = kwargs['use_openai_embedding']
-    hf_embedding_model = kwargs['hf_embedding_model']
-    load_db_if_exists = kwargs['load_db_if_exists']
-    migrate_embedding_model = kwargs['migrate_embedding_model']
-    auto_migrate_db = kwargs['auto_migrate_db']
-    captions_model = kwargs['captions_model']
-    caption_loader = kwargs['caption_loader']
-    doctr_loader = kwargs['doctr_loader']
-
-    n_jobs = kwargs['n_jobs']
-    verbose = kwargs['verbose']
-
-    # for dynamic state per user session in gradio
-    model_state0 = kwargs['model_state0']
-    score_model_state0 = kwargs['score_model_state0']
-    my_db_state0 = kwargs['my_db_state0']
-    selection_docs_state0 = kwargs['selection_docs_state0']
-    visible_models_state0 = kwargs['visible_models_state0']
-    # For Heap analytics
-    is_heap_analytics_enabled = kwargs['enable_heap_analytics']
-    heap_app_id = kwargs['heap_app_id']
-
-    # easy update of kwargs needed for evaluate() etc.
-    queue = True
-    allow_upload = allow_upload_to_user_data or allow_upload_to_my_data
-    allow_upload_api = allow_api and allow_upload
-
-    kwargs.update(locals())
-
-    # import control
-    if kwargs['langchain_mode'] != 'Disabled':
-        from gpt_langchain import file_types, have_arxiv
-    else:
-        have_arxiv = False
-        file_types = []
-
-    if 'mbart-' in kwargs['model_lower']:
-        instruction_label_nochat = "Text to translate"
-    else:
-        instruction_label_nochat = "Instruction (Shift-Enter or push Submit to send message," \
-                                   " use Enter for multiple input lines)"
-
-    title = 'h2oGPT'
-    if kwargs['visible_h2ogpt_header']:
-        description = """<iframe src="https://ghbtns.com/github-btn.html?user=h2oai&repo=h2ogpt&type=star&count=true&size=small" frameborder="0" scrolling="0" width="280" height="20" title="GitHub"></iframe><small><a href="https://github.com/h2oai/h2ogpt">h2oGPT</a> <a href="https://evalgpt.ai/">LLM Leaderboard</a> <a href="https://github.com/h2oai/h2o-llmstudio">LLM Studio</a><br /><a href="https://codellama.h2o.ai">CodeLlama</a> <br /><a href="https://huggingface.co/h2oai">🤗 Models</a>"""
-    else:
-        description = None
-    description_bottom = "If this host is busy, try<br>[Multi-Model](https://gpt.h2o.ai)<br>[CodeLlama](https://codellama.h2o.ai)<br>[Llama2 70B](https://llama.h2o.ai)<br>[Falcon 40B](https://falcon.h2o.ai)<br>[HF Spaces1](https://huggingface.co/spaces/h2oai/h2ogpt-chatbot)<br>[HF Spaces2](https://huggingface.co/spaces/h2oai/h2ogpt-chatbot2)<br>"
-    if is_hf:
-        description_bottom += '''<a href="https://huggingface.co/spaces/h2oai/h2ogpt-chatbot?duplicate=true"><img src="https://bit.ly/3gLdBN6" style="white-space: nowrap" alt="Duplicate Space"></a>'''
-    task_info_md = ''
-    css_code = get_css(kwargs)
-
-    if kwargs['gradio_offline_level'] >= 0:
-        # avoid GoogleFont that pulls from internet
-        if kwargs['gradio_offline_level'] == 1:
-            # front end would still have to download fonts or have cached it at some point
-            base_font = 'Source Sans Pro'
-        else:
-            base_font = 'Helvetica'
-        theme_kwargs = dict(font=(base_font, 'ui-sans-serif', 'system-ui', 'sans-serif'),
-                            font_mono=('IBM Plex Mono', 'ui-monospace', 'Consolas', 'monospace'))
-    else:
-        theme_kwargs = dict()
-    if kwargs['gradio_size'] == 'xsmall':
-        theme_kwargs.update(dict(spacing_size=spacing_xsm, text_size=text_xsm, radius_size=radius_xsm))
-    elif kwargs['gradio_size'] in [None, 'small']:
-        theme_kwargs.update(dict(spacing_size=gr.themes.sizes.spacing_sm, text_size=gr.themes.sizes.text_sm,
-                                 radius_size=gr.themes.sizes.spacing_sm))
-    elif kwargs['gradio_size'] == 'large':
-        theme_kwargs.update(dict(spacing_size=gr.themes.sizes.spacing_lg, text_size=gr.themes.sizes.text_lg),
-                            radius_size=gr.themes.sizes.spacing_lg)
-    elif kwargs['gradio_size'] == 'medium':
-        theme_kwargs.update(dict(spacing_size=gr.themes.sizes.spacing_md, text_size=gr.themes.sizes.text_md,
-                                 radius_size=gr.themes.sizes.spacing_md))
-
-    theme = H2oTheme(**theme_kwargs) if kwargs['h2ocolors'] else SoftTheme(**theme_kwargs)
-    demo = gr.Blocks(theme=theme, css=css_code, title="h2oGPT", analytics_enabled=False)
-    callback = gr.CSVLogger()
-
-    model_options0 = flatten_list(list(prompt_type_to_model_name.values())) + kwargs['extra_model_options']
-    if kwargs['base_model'].strip() not in model_options0:
-        model_options0 = [kwargs['base_model'].strip()] + model_options0
-    lora_options = kwargs['extra_lora_options']
-    if kwargs['lora_weights'].strip() not in lora_options:
-        lora_options = [kwargs['lora_weights'].strip()] + lora_options
-    server_options = kwargs['extra_server_options']
-    if kwargs['inference_server'].strip() not in server_options:
-        server_options = [kwargs['inference_server'].strip()] + server_options
-    if os.getenv('OPENAI_API_KEY'):
-        if 'openai_chat' not in server_options:
-            server_options += ['openai_chat']
-        if 'openai' not in server_options:
-            server_options += ['openai']
-
-    # always add in no lora case
-    # add fake space so doesn't go away in gradio dropdown
-    model_options0 = [no_model_str] + sorted(model_options0)
-    lora_options = [no_lora_str] + sorted(lora_options)
-    server_options = [no_server_str] + sorted(server_options)
-    # always add in no model case so can free memory
-    # add fake space so doesn't go away in gradio dropdown
-
-    # transcribe, will be detranscribed before use by evaluate()
-    if not kwargs['base_model'].strip():
-        kwargs['base_model'] = no_model_str
-
-    if not kwargs['lora_weights'].strip():
-        kwargs['lora_weights'] = no_lora_str
-
-    if not kwargs['inference_server'].strip():
-        kwargs['inference_server'] = no_server_str
-
-    # transcribe for gradio
-    kwargs['gpu_id'] = str(kwargs['gpu_id'])
-
-    no_model_msg = 'h2oGPT [   !!! Please Load Model in Models Tab !!!   ]'
-    output_label0 = f'h2oGPT [Model: {kwargs.get("base_model")}]' if kwargs.get(
-        'base_model') else no_model_msg
-    output_label0_model2 = no_model_msg
-
-    def update_prompt(prompt_type1, prompt_dict1, model_state1, which_model=0):
-        if not prompt_type1 or which_model != 0:
-            # keep prompt_type and prompt_dict in sync if possible
-            prompt_type1 = kwargs.get('prompt_type', prompt_type1)
-            prompt_dict1 = kwargs.get('prompt_dict', prompt_dict1)
-            # prefer model specific prompt type instead of global one
-            if not prompt_type1 or which_model != 0:
-                prompt_type1 = model_state1.get('prompt_type', prompt_type1)
-                prompt_dict1 = model_state1.get('prompt_dict', prompt_dict1)
-
-        if not prompt_dict1 or which_model != 0:
-            # if still not defined, try to get
-            prompt_dict1 = kwargs.get('prompt_dict', prompt_dict1)
-            if not prompt_dict1 or which_model != 0:
-                prompt_dict1 = model_state1.get('prompt_dict', prompt_dict1)
-        return prompt_type1, prompt_dict1
-
-    def visible_models_to_model_choice(visible_models1):
-        if isinstance(visible_models1, list):
-            assert len(
-                visible_models1) >= 1, "Invalid visible_models1=%s, can only be single entry" % visible_models1
-            # just take first
-            model_active_choice1 = visible_models1[0]
-        elif isinstance(visible_models1, (str, int)):
-            model_active_choice1 = visible_models1
-        else:
-            assert isinstance(visible_models1, type(None)), "Invalid visible_models1=%s" % visible_models1
-            model_active_choice1 = visible_models1
-        if model_active_choice1 is not None:
-            if isinstance(model_active_choice1, str):
-                base_model_list = [x['base_model'] for x in model_states]
-                if model_active_choice1 in base_model_list:
-                    # if dups, will just be first one
-                    model_active_choice1 = base_model_list.index(model_active_choice1)
-                else:
-                    # NOTE: Could raise, but sometimes raising in certain places fails too hard and requires UI restart
-                    model_active_choice1 = 0
-        else:
-            model_active_choice1 = 0
-        return model_active_choice1
-
-    default_kwargs = {k: kwargs[k] for k in eval_func_param_names_defaults}
-    # ensure prompt_type consistent with prep_bot(), so nochat API works same way
-    default_kwargs['prompt_type'], default_kwargs['prompt_dict'] = \
-        update_prompt(default_kwargs['prompt_type'], default_kwargs['prompt_dict'],
-                      model_state1=model_state0,
-                      which_model=visible_models_to_model_choice(kwargs['visible_models']))
-    for k in no_default_param_names:
-        default_kwargs[k] = ''
-
-    def dummy_fun(x):
-        # need dummy function to block new input from being sent until output is done,
-        # else gets input_list at time of submit that is old, and shows up as truncated in chatbot
-        return x
-
-    def update_auth_selection(auth_user, selection_docs_state1, save=False):
-        # in-place update of both
-        if 'selection_docs_state' not in auth_user:
-            auth_user['selection_docs_state'] = selection_docs_state0
-        for k, v in auth_user['selection_docs_state'].items():
-            if isinstance(selection_docs_state1[k], dict):
-                if save:
-                    auth_user['selection_docs_state'][k].clear()
-                    auth_user['selection_docs_state'][k].update(selection_docs_state1[k])
-                else:
-                    selection_docs_state1[k].clear()
-                    selection_docs_state1[k].update(auth_user['selection_docs_state'][k])
-            elif isinstance(selection_docs_state1[k], list):
-                if save:
-                    auth_user['selection_docs_state'][k].clear()
-                    auth_user['selection_docs_state'][k].extend(selection_docs_state1[k])
-                else:
-                    selection_docs_state1[k].clear()
-                    selection_docs_state1[k].extend(auth_user['selection_docs_state'][k])
-            else:
-                raise RuntimeError("Bad type: %s" % selection_docs_state1[k])
-
-    # BEGIN AUTH THINGS
-    def auth_func(username1, password1, auth_pairs=None, auth_filename=None,
-                  auth_access=None,
-                  auth_freeze=None,
-                  guest_name=None,
-                  selection_docs_state1=None,
-                  selection_docs_state00=None,
-                  **kwargs):
-        assert auth_freeze is not None
-        if selection_docs_state1 is None:
-            selection_docs_state1 = selection_docs_state00
-        assert selection_docs_state1 is not None
-        assert auth_filename and isinstance(auth_filename, str), "Auth file must be a non-empty string, got: %s" % str(
-            auth_filename)
-        if auth_access == 'open' and username1 == guest_name:
-            return True
-        if username1 == '':
-            # some issue with login
-            return False
-        with filelock.FileLock(auth_filename + '.lock'):
-            auth_dict = {}
-            if os.path.isfile(auth_filename):
-                try:
-                    with open(auth_filename, 'rt') as f:
-                        auth_dict = json.load(f)
-                except json.decoder.JSONDecodeError as e:
-                    print("Auth exception: %s" % str(e), flush=True)
-                    shutil.move(auth_filename, auth_filename + '.bak' + str(uuid.uuid4()))
-                    auth_dict = {}
-            if username1 in auth_dict and username1 in auth_pairs:
-                if password1 == auth_dict[username1]['password'] and password1 == auth_pairs[username1]:
-                    auth_user = auth_dict[username1]
-                    update_auth_selection(auth_user, selection_docs_state1)
-                    save_auth_dict(auth_dict, auth_filename)
-                    return True
-                else:
-                    return False
-            elif username1 in auth_dict:
-                if password1 == auth_dict[username1]['password']:
-                    auth_user = auth_dict[username1]
-                    update_auth_selection(auth_user, selection_docs_state1)
-                    save_auth_dict(auth_dict, auth_filename)
-                    return True
-                else:
-                    return False
-            elif username1 in auth_pairs:
-                # copy over CLI auth to file so only one state to manage
-                auth_dict[username1] = dict(password=auth_pairs[username1], userid=str(uuid.uuid4()))
-                auth_user = auth_dict[username1]
-                update_auth_selection(auth_user, selection_docs_state1)
-                save_auth_dict(auth_dict, auth_filename)
-                return True
-            else:
-                if auth_access == 'closed':
-                    return False
-                # open access
-                auth_dict[username1] = dict(password=password1, userid=str(uuid.uuid4()))
-                auth_user = auth_dict[username1]
-                update_auth_selection(auth_user, selection_docs_state1)
-                save_auth_dict(auth_dict, auth_filename)
-                if auth_access == 'open':
-                    return True
-                else:
-                    raise RuntimeError("Invalid auth_access: %s" % auth_access)
-
-    def auth_func_open(*args, **kwargs):
-        return True
-
-    def get_username(requests_state1):
-        username1 = None
-        if 'username' in requests_state1:
-            username1 = requests_state1['username']
-        return username1
-
-    def get_userid_auth_func(requests_state1, auth_filename=None, auth_access=None, guest_name=None, **kwargs):
-        if auth_filename and isinstance(auth_filename, str):
-            username1 = get_username(requests_state1)
-            if username1:
-                if username1 == guest_name:
-                    return str(uuid.uuid4())
-                with filelock.FileLock(auth_filename + '.lock'):
-                    if os.path.isfile(auth_filename):
-                        with open(auth_filename, 'rt') as f:
-                            auth_dict = json.load(f)
-                        if username1 in auth_dict:
-                            return auth_dict[username1]['userid']
-        # if here, then not persistently associated with username1,
-        # but should only be one-time asked if going to persist within a single session!
-        return str(uuid.uuid4())
-
-    get_userid_auth = functools.partial(get_userid_auth_func,
-                                        auth_filename=kwargs['auth_filename'],
-                                        auth_access=kwargs['auth_access'],
-                                        guest_name=kwargs['guest_name'],
-                                        )
-    if kwargs['auth_access'] == 'closed':
-        auth_message1 = "Closed access"
-    else:
-        auth_message1 = "WELCOME!  Open access" \
-                        " (%s/%s or any unique user/pass)" % (kwargs['guest_name'], kwargs['guest_name'])
-
-    if kwargs['auth_message'] is not None:
-        auth_message = kwargs['auth_message']
-    else:
-        auth_message = auth_message1
-
-    # always use same callable
-    auth_pairs0 = {}
-    if isinstance(kwargs['auth'], list):
-        for k, v in kwargs['auth']:
-            auth_pairs0[k] = v
-    authf = functools.partial(auth_func,
-                              auth_pairs=auth_pairs0,
-                              auth_filename=kwargs['auth_filename'],
-                              auth_access=kwargs['auth_access'],
-                              auth_freeze=kwargs['auth_freeze'],
-                              guest_name=kwargs['guest_name'],
-                              selection_docs_state00=copy.deepcopy(selection_docs_state0))
-
-    def get_request_state(requests_state1, request, db1s):
-        # if need to get state, do it now
-        if not requests_state1:
-            requests_state1 = requests_state0.copy()
-        if requests:
-            if not requests_state1.get('headers', '') and hasattr(request, 'headers'):
-                requests_state1.update(request.headers)
-            if not requests_state1.get('host', '') and hasattr(request, 'host'):
-                requests_state1.update(dict(host=request.host))
-            if not requests_state1.get('host2', '') and hasattr(request, 'client') and hasattr(request.client, 'host'):
-                requests_state1.update(dict(host2=request.client.host))
-            if not requests_state1.get('username', '') and hasattr(request, 'username'):
-                # use already-defined username instead of keep changing to new uuid
-                # should be same as in requests_state1
-                db_username = get_username_direct(db1s)
-                requests_state1.update(dict(username=request.username or db_username or str(uuid.uuid4())))
-        requests_state1 = {str(k): str(v) for k, v in requests_state1.items()}
-        return requests_state1
-
-    def user_state_setup(db1s, requests_state1, request: gr.Request, *args):
-        requests_state1 = get_request_state(requests_state1, request, db1s)
-        set_userid(db1s, requests_state1, get_userid_auth)
-        args_list = [db1s, requests_state1] + list(args)
-        return tuple(args_list)
-
-    # END AUTH THINGS
-
-    def allow_empty_instruction(langchain_mode1, document_subset1, langchain_action1):
-        allow = False
-        allow |= langchain_action1 not in LangChainAction.QUERY.value
-        allow |= document_subset1 in DocumentSubset.TopKSources.name
-        if langchain_mode1 in [LangChainMode.LLM.value]:
-            allow = False
-        return allow
-
-    image_loaders_options0, image_loaders_options, \
-        pdf_loaders_options0, pdf_loaders_options, \
-        url_loaders_options0, url_loaders_options = lg_to_gr(**kwargs)
-    jq_schema0 = '.[]'
-
-    with demo:
-        # avoid actual model/tokenizer here or anything that would be bad to deepcopy
-        # https://github.com/gradio-app/gradio/issues/3558
-        model_state = gr.State(
-            dict(model='model', tokenizer='tokenizer', device=kwargs['device'],
-                 base_model=kwargs['base_model'],
-                 tokenizer_base_model=kwargs['tokenizer_base_model'],
-                 lora_weights=kwargs['lora_weights'],
-                 inference_server=kwargs['inference_server'],
-                 prompt_type=kwargs['prompt_type'],
-                 prompt_dict=kwargs['prompt_dict'],
-                 visible_models=kwargs['visible_models'],
-                 h2ogpt_key=kwargs['h2ogpt_key'],
-                 )
-        )
-
-        def update_langchain_mode_paths(selection_docs_state1):
-            dup = selection_docs_state1['langchain_mode_paths'].copy()
-            for k, v in dup.items():
-                if k not in selection_docs_state1['langchain_modes']:
-                    selection_docs_state1['langchain_mode_paths'].pop(k)
-            for k in selection_docs_state1['langchain_modes']:
-                if k not in selection_docs_state1['langchain_mode_types']:
-                    # if didn't specify shared, then assume scratch if didn't login or personal if logged in
-                    selection_docs_state1['langchain_mode_types'][k] = LangChainTypes.PERSONAL.value
-            return selection_docs_state1
-
-        # Setup some gradio states for per-user dynamic state
-        model_state2 = gr.State(kwargs['model_state_none'].copy())
-        model_options_state = gr.State([model_options0])
-        lora_options_state = gr.State([lora_options])
-        server_options_state = gr.State([server_options])
-        my_db_state = gr.State(my_db_state0)
-        chat_state = gr.State({})
-        docs_state00 = kwargs['document_choice'] + [DocumentChoice.ALL.value]
-        docs_state0 = []
-        [docs_state0.append(x) for x in docs_state00 if x not in docs_state0]
-        docs_state = gr.State(docs_state0)
-        viewable_docs_state0 = []
-        viewable_docs_state = gr.State(viewable_docs_state0)
-        selection_docs_state0 = update_langchain_mode_paths(selection_docs_state0)
-        selection_docs_state = gr.State(selection_docs_state0)
-        requests_state0 = dict(headers='', host='', username='')
-        requests_state = gr.State(requests_state0)
-
-        if description is not None:
-            gr.Markdown(f"""
-                {get_h2o_title(title, description) if kwargs['h2ocolors'] else get_simple_title(title, description)}
-                """)
-
-        # go button visible if
-        base_wanted = kwargs['base_model'] != no_model_str and kwargs['login_mode_if_model0']
-        go_btn = gr.Button(value="ENTER", visible=base_wanted, variant="primary")
-
-        nas = ' '.join(['NA'] * len(kwargs['model_states']))
-        res_value = "Response Score: NA" if not kwargs[
-            'model_lock'] else "Response Scores: %s" % nas
-
-        user_can_do_sum = kwargs['langchain_mode'] != LangChainMode.DISABLED.value and \
-                          (kwargs['visible_side_bar'] or kwargs['visible_system_tab'])
-        if user_can_do_sum:
-            extra_prompt_form = ".  For summarization, no query required, just click submit"
-        else:
-            extra_prompt_form = ""
-        if kwargs['input_lines'] > 1:
-            instruction_label = "Shift-Enter to Submit, Enter for more lines%s" % extra_prompt_form
-        else:
-            instruction_label = "Enter to Submit, Shift-Enter for more lines%s" % extra_prompt_form
-
-        def get_langchain_choices(selection_docs_state1):
-            langchain_modes = selection_docs_state1['langchain_modes']
-
-            if is_hf:
-                # don't show 'wiki' since only usually useful for internal testing at moment
-                no_show_modes = ['Disabled', 'wiki']
-            else:
-                no_show_modes = ['Disabled']
-            allowed_modes = langchain_modes.copy()
-            # allowed_modes = [x for x in allowed_modes if x in dbs]
-            allowed_modes += ['LLM']
-            if allow_upload_to_my_data and 'MyData' not in allowed_modes:
-                allowed_modes += ['MyData']
-            if allow_upload_to_user_data and 'UserData' not in allowed_modes:
-                allowed_modes += ['UserData']
-            choices = [x for x in langchain_modes if x in allowed_modes and x not in no_show_modes]
-            return choices
-
-        def get_df_langchain_mode_paths(selection_docs_state1, db1s, dbs1=None):
-            langchain_choices1 = get_langchain_choices(selection_docs_state1)
-            langchain_mode_paths = selection_docs_state1['langchain_mode_paths']
-            langchain_mode_paths = {k: v for k, v in langchain_mode_paths.items() if k in langchain_choices1}
-            if langchain_mode_paths:
-                langchain_mode_paths = langchain_mode_paths.copy()
-                for langchain_mode1 in langchain_modes_non_db:
-                    langchain_mode_paths.pop(langchain_mode1, None)
-                df1 = pd.DataFrame.from_dict(langchain_mode_paths.items(), orient='columns')
-                df1.columns = ['Collection', 'Path']
-                df1 = df1.set_index('Collection')
-            else:
-                df1 = pd.DataFrame(None)
-            langchain_mode_types = selection_docs_state1['langchain_mode_types']
-            langchain_mode_types = {k: v for k, v in langchain_mode_types.items() if k in langchain_choices1}
-            if langchain_mode_types:
-                langchain_mode_types = langchain_mode_types.copy()
-                for langchain_mode1 in langchain_modes_non_db:
-                    langchain_mode_types.pop(langchain_mode1, None)
-
-                df2 = pd.DataFrame.from_dict(langchain_mode_types.items(), orient='columns')
-                df2.columns = ['Collection', 'Type']
-                df2 = df2.set_index('Collection')
-
-                from src.gpt_langchain import get_persist_directory, load_embed
-                persist_directory_dict = {}
-                embed_dict = {}
-                chroma_version_dict = {}
-                for langchain_mode3 in langchain_mode_types:
-                    langchain_type3 = langchain_mode_types.get(langchain_mode3, LangChainTypes.EITHER.value)
-                    persist_directory3, langchain_type3 = get_persist_directory(langchain_mode3,
-                                                                                langchain_type=langchain_type3,
-                                                                                db1s=db1s, dbs=dbs1)
-                    got_embedding3, use_openai_embedding3, hf_embedding_model3 = load_embed(
-                        persist_directory=persist_directory3)
-                    persist_directory_dict[langchain_mode3] = persist_directory3
-                    embed_dict[langchain_mode3] = 'OpenAI' if not hf_embedding_model3 else hf_embedding_model3
-
-                    if os.path.isfile(os.path.join(persist_directory3, 'chroma.sqlite3')):
-                        chroma_version_dict[langchain_mode3] = 'ChromaDB>=0.4'
-                    elif os.path.isdir(os.path.join(persist_directory3, 'index')):
-                        chroma_version_dict[langchain_mode3] = 'ChromaDB<0.4'
-                    elif not os.listdir(persist_directory3):
-                        if db_type == 'chroma':
-                            chroma_version_dict[langchain_mode3] = 'ChromaDB>=0.4'  # will be
-                        elif db_type == 'chroma_old':
-                            chroma_version_dict[langchain_mode3] = 'ChromaDB<0.4'  # will be
-                        else:
-                            chroma_version_dict[langchain_mode3] = 'Weaviate'  # will be
-                        if isinstance(hf_embedding_model, dict):
-                            hf_embedding_model3 = hf_embedding_model['name']
-                        else:
-                            hf_embedding_model3 = hf_embedding_model
-                        assert isinstance(hf_embedding_model3, str)
-                        embed_dict[langchain_mode3] = hf_embedding_model3  # will be
-                    else:
-                        chroma_version_dict[langchain_mode3] = 'Weaviate'
-
-                df3 = pd.DataFrame.from_dict(persist_directory_dict.items(), orient='columns')
-                df3.columns = ['Collection', 'Directory']
-                df3 = df3.set_index('Collection')
-
-                df4 = pd.DataFrame.from_dict(embed_dict.items(), orient='columns')
-                df4.columns = ['Collection', 'Embedding']
-                df4 = df4.set_index('Collection')
-
-                df5 = pd.DataFrame.from_dict(chroma_version_dict.items(), orient='columns')
-                df5.columns = ['Collection', 'DB']
-                df5 = df5.set_index('Collection')
-            else:
-                df2 = pd.DataFrame(None)
-                df3 = pd.DataFrame(None)
-                df4 = pd.DataFrame(None)
-                df5 = pd.DataFrame(None)
-            df_list = [df2, df1, df3, df4, df5]
-            df_list = [x for x in df_list if x.shape[1] > 0]
-            if len(df_list) > 1:
-                df = df_list[0].join(df_list[1:]).replace(np.nan, '').reset_index()
-            elif len(df_list) == 0:
-                df = df_list[0].replace(np.nan, '').reset_index()
-            else:
-                df = pd.DataFrame(None)
-            return df
-
-        normal_block = gr.Row(visible=not base_wanted, equal_height=False, elem_id="col_container")
-        with normal_block:
-            side_bar = gr.Column(elem_id="sidebar", scale=1, min_width=100, visible=kwargs['visible_side_bar'])
-            with side_bar:
-                with gr.Accordion("Chats", open=False, visible=True):
-                    radio_chats = gr.Radio(value=None, label="Saved Chats", show_label=False,
-                                           visible=True, interactive=True,
-                                           type='value')
-                upload_visible = kwargs['langchain_mode'] != 'Disabled' and allow_upload
-                with gr.Accordion("Upload", open=False, visible=upload_visible):
-                    with gr.Column():
-                        with gr.Row(equal_height=False):
-                            fileup_output = gr.File(show_label=False,
-                                                    file_types=['.' + x for x in file_types],
-                                                    # file_types=['*', '*.*'],  # for iPhone etc. needs to be unconstrained else doesn't work with extension-based restrictions
-                                                    file_count="multiple",
-                                                    scale=1,
-                                                    min_width=0,
-                                                    elem_id="warning", elem_classes="feedback",
-                                                    )
-                            fileup_output_text = gr.Textbox(visible=False)
-                    max_quality = gr.Checkbox(label="Maximum Ingest Quality", value=kwargs['max_quality'],
-                                              visible=not is_public)
-                    url_visible = kwargs['langchain_mode'] != 'Disabled' and allow_upload and enable_url_upload
-                    url_label = 'URL/ArXiv' if have_arxiv else 'URL'
-                    url_text = gr.Textbox(label=url_label,
-                                          # placeholder="Enter Submits",
-                                          max_lines=1,
-                                          interactive=True)
-                    text_visible = kwargs['langchain_mode'] != 'Disabled' and allow_upload and enable_text_upload
-                    user_text_text = gr.Textbox(label='Paste Text',
-                                                # placeholder="Enter Submits",
-                                                interactive=True,
-                                                visible=text_visible)
-                    github_textbox = gr.Textbox(label="Github URL", visible=False)  # FIXME WIP
-                database_visible = kwargs['langchain_mode'] != 'Disabled'
-                with gr.Accordion("Resources", open=False, visible=database_visible):
-                    langchain_choices0 = get_langchain_choices(selection_docs_state0)
-                    langchain_mode = gr.Radio(
-                        langchain_choices0,
-                        value=kwargs['langchain_mode'],
-                        label="Collections",
-                        show_label=True,
-                        visible=kwargs['langchain_mode'] != 'Disabled',
-                        min_width=100)
-                    add_chat_history_to_context = gr.Checkbox(label="Chat History",
-                                                              value=kwargs['add_chat_history_to_context'])
-                    add_search_to_context = gr.Checkbox(label="Web Search",
-                                                        value=kwargs['add_search_to_context'],
-                                                        visible=os.environ.get('SERPAPI_API_KEY') is not None \
-                                                                and have_serpapi)
-                    document_subset = gr.Radio([x.name for x in DocumentSubset],
-                                               label="Subset",
-                                               value=DocumentSubset.Relevant.name,
-                                               interactive=True,
-                                               )
-                    allowed_actions = [x for x in langchain_actions if x in visible_langchain_actions]
-                    langchain_action = gr.Radio(
-                        allowed_actions,
-                        value=allowed_actions[0] if len(allowed_actions) > 0 else None,
-                        label="Action",
-                        visible=True)
-                    allowed_agents = [x for x in langchain_agents_list if x in visible_langchain_agents]
-                    if os.getenv('OPENAI_API_KEY') is None and LangChainAgent.JSON.value in allowed_agents:
-                        allowed_agents.remove(LangChainAgent.JSON.value)
-                    if os.getenv('OPENAI_API_KEY') is None and LangChainAgent.PYTHON.value in allowed_agents:
-                        allowed_agents.remove(LangChainAgent.PYTHON.value)
-                    if LangChainAgent.PANDAS.value in allowed_agents:
-                        allowed_agents.remove(LangChainAgent.PANDAS.value)
-                    langchain_agents = gr.Dropdown(
-                        allowed_agents,
-                        value=None,
-                        label="Agents",
-                        multiselect=True,
-                        interactive=True,
-                        visible=True,
-                        elem_id="langchain_agents",
-                        filterable=False)
-                visible_doc_track = upload_visible and kwargs['visible_doc_track'] and not kwargs[
-                    'large_file_count_mode']
-                row_doc_track = gr.Row(visible=visible_doc_track)
-                with row_doc_track:
-                    if kwargs['langchain_mode'] in langchain_modes_non_db:
-                        doc_counts_str = "Pure LLM Mode"
-                    else:
-                        doc_counts_str = "Name: %s\nDocs: Unset\nChunks: Unset" % kwargs['langchain_mode']
-                    text_doc_count = gr.Textbox(lines=3, label="Doc Counts", value=doc_counts_str,
-                                                visible=visible_doc_track)
-                    text_file_last = gr.Textbox(lines=1, label="Newest Doc", value=None, visible=visible_doc_track)
-                    text_viewable_doc_count = gr.Textbox(lines=2, label=None, visible=False)
-            col_tabs = gr.Column(elem_id="col-tabs", scale=10)
-            with col_tabs, gr.Tabs():
-                if kwargs['chat_tables']:
-                    chat_tab = gr.Row(visible=True)
-                else:
-                    chat_tab = gr.TabItem("Chat") \
-                        if kwargs['visible_chat_tab'] else gr.Row(visible=False)
-                with chat_tab:
-                    if kwargs['langchain_mode'] == 'Disabled':
-                        text_output_nochat = gr.Textbox(lines=5, label=output_label0, show_copy_button=True,
-                                                        visible=not kwargs['chat'])
-                    else:
-                        # text looks a bit worse, but HTML links work
-                        text_output_nochat = gr.HTML(label=output_label0, visible=not kwargs['chat'])
-                    with gr.Row():
-                        # NOCHAT
-                        instruction_nochat = gr.Textbox(
-                            lines=kwargs['input_lines'],
-                            label=instruction_label_nochat,
-                            placeholder=kwargs['placeholder_instruction'],
-                            visible=not kwargs['chat'],
-                        )
-                        iinput_nochat = gr.Textbox(lines=4, label="Input context for Instruction",
-                                                   placeholder=kwargs['placeholder_input'],
-                                                   value=kwargs['iinput'],
-                                                   visible=not kwargs['chat'])
-                        submit_nochat = gr.Button("Submit", size='sm', visible=not kwargs['chat'])
-                        flag_btn_nochat = gr.Button("Flag", size='sm', visible=not kwargs['chat'])
-                        score_text_nochat = gr.Textbox("Response Score: NA", show_label=False,
-                                                       visible=not kwargs['chat'])
-                        submit_nochat_api = gr.Button("Submit nochat API", visible=False)
-                        submit_nochat_api_plain = gr.Button("Submit nochat API Plain", visible=False)
-                        inputs_dict_str = gr.Textbox(label='API input for nochat', show_label=False, visible=False)
-                        text_output_nochat_api = gr.Textbox(lines=5, label='API nochat output', visible=False,
-                                                            show_copy_button=True)
-
-                        visible_upload = (allow_upload_to_user_data or
-                                          allow_upload_to_my_data) and \
-                                         kwargs['langchain_mode'] != 'Disabled'
-                        # CHAT
-                        col_chat = gr.Column(visible=kwargs['chat'])
-                        with col_chat:
-                            with gr.Row():
-                                with gr.Column(scale=50):
-                                    with gr.Row(elem_id="prompt-form-row"):
-                                        label_instruction = 'Ask anything'
-                                        instruction = gr.Textbox(
-                                            lines=kwargs['input_lines'],
-                                            label=label_instruction,
-                                            placeholder=instruction_label,
-                                            info=None,
-                                            elem_id='prompt-form',
-                                            container=True,
-                                        )
-                                        attach_button = gr.UploadButton(
-                                            elem_id="attach-button" if visible_upload else None,
-                                            value="",
-                                            label="Upload File(s)",
-                                            size="sm",
-                                            min_width=24,
-                                            file_types=['.' + x for x in file_types],
-                                            file_count="multiple",
-                                            visible=visible_upload)
-
-                                submit_buttons = gr.Row(equal_height=False, visible=kwargs['visible_submit_buttons'])
-                                with submit_buttons:
-                                    mw1 = 50
-                                    mw2 = 50
-                                    with gr.Column(min_width=mw1):
-                                        submit = gr.Button(value='Submit', variant='primary', size='sm',
-                                                           min_width=mw1)
-                                        stop_btn = gr.Button(value="Stop", variant='secondary', size='sm',
-                                                             min_width=mw1)
-                                        save_chat_btn = gr.Button("Save", size='sm', min_width=mw1)
-                                    with gr.Column(min_width=mw2):
-                                        retry_btn = gr.Button("Redo", size='sm', min_width=mw2)
-                                        undo = gr.Button("Undo", size='sm', min_width=mw2)
-                                        clear_chat_btn = gr.Button(value="Clear", size='sm', min_width=mw2)
-
-                            visible_model_choice = bool(kwargs['model_lock']) and \
-                                                   len(model_states) > 1 and \
-                                                   kwargs['visible_visible_models']
-                            with gr.Row(visible=visible_model_choice):
-                                visible_models = gr.Dropdown(kwargs['all_models'],
-                                                             label="Visible Models",
-                                                             value=visible_models_state0,
-                                                             interactive=True,
-                                                             multiselect=True,
-                                                             visible=visible_model_choice,
-                                                             elem_id="visible-models",
-                                                             filterable=False,
-                                                             )
-
-                            text_output, text_output2, text_outputs = make_chatbots(output_label0, output_label0_model2,
-                                                                                    **kwargs)
-
-                            with gr.Row():
-                                with gr.Column(visible=kwargs['score_model']):
-                                    score_text = gr.Textbox(res_value,
-                                                            show_label=False,
-                                                            visible=True)
-                                    score_text2 = gr.Textbox("Response Score2: NA", show_label=False,
-                                                             visible=False and not kwargs['model_lock'])
-
-                doc_selection_tab = gr.TabItem("Document Selection") \
-                    if kwargs['visible_doc_selection_tab'] else gr.Row(visible=False)
-                with doc_selection_tab:
-                    if kwargs['langchain_mode'] in langchain_modes_non_db:
-                        dlabel1 = 'Choose Resources->Collections and Pick Collection'
-                        active_collection = gr.Markdown(value="#### Not Chatting with Any Collection\n%s" % dlabel1)
-                    else:
-                        dlabel1 = 'Select Subset of Document(s) for Chat with Collection: %s' % kwargs['langchain_mode']
-                        active_collection = gr.Markdown(
-                            value="#### Chatting with Collection: %s" % kwargs['langchain_mode'])
-                    document_choice = gr.Dropdown(docs_state0,
-                                                  label=dlabel1,
-                                                  value=[DocumentChoice.ALL.value],
-                                                  interactive=True,
-                                                  multiselect=True,
-                                                  visible=kwargs['langchain_mode'] != 'Disabled',
-                                                  )
-                    sources_visible = kwargs['langchain_mode'] != 'Disabled' and enable_sources_list
-                    with gr.Row():
-                        with gr.Column(scale=1):
-                            get_sources_btn = gr.Button(value="Update UI with Document(s) from DB", scale=0, size='sm',
-                                                        visible=sources_visible and kwargs['large_file_count_mode'])
-                            # handle API get sources
-                            get_sources_api_btn = gr.Button(visible=False)
-                            get_sources_api_text = gr.Textbox(visible=False)
-
-                            get_document_api_btn = gr.Button(visible=False)
-                            get_document_api_text = gr.Textbox(visible=False)
-
-                            show_sources_btn = gr.Button(value="Show Sources from DB", scale=0, size='sm',
-                                                         visible=sources_visible and kwargs['large_file_count_mode'])
-                            delete_sources_btn = gr.Button(value="Delete Selected Sources from DB", scale=0, size='sm',
-                                                           visible=sources_visible)
-                            refresh_sources_btn = gr.Button(value="Update DB with new/changed files on disk", scale=0,
-                                                            size='sm',
-                                                            visible=sources_visible and allow_upload_to_user_data)
-                        with gr.Column(scale=4):
-                            pass
-                    visible_add_remove_collection = visible_upload
-                    with gr.Row():
-                        with gr.Column(scale=1):
-                            add_placeholder = "e.g. UserData2, shared, user_path2" \
-                                if not is_public else "e.g. MyData2, personal (optional)"
-                            remove_placeholder = "e.g. UserData2" if not is_public else "e.g. MyData2"
-                            new_langchain_mode_text = gr.Textbox(value="", visible=visible_add_remove_collection,
-                                                                 label='Add Collection',
-                                                                 placeholder=add_placeholder,
-                                                                 interactive=True)
-                            remove_langchain_mode_text = gr.Textbox(value="", visible=visible_add_remove_collection,
-                                                                    label='Remove Collection from UI',
-                                                                    placeholder=remove_placeholder,
-                                                                    interactive=True)
-                            purge_langchain_mode_text = gr.Textbox(value="", visible=visible_add_remove_collection,
-                                                                   label='Purge Collection (UI, DB, & source files)',
-                                                                   placeholder=remove_placeholder,
-                                                                   interactive=True)
-                            sync_sources_btn = gr.Button(
-                                value="Synchronize DB and UI [only required if did not login and have shared docs]",
-                                scale=0, size='sm',
-                                visible=sources_visible and allow_upload_to_user_data and not kwargs[
-                                    'large_file_count_mode'])
-                            load_langchain = gr.Button(
-                                value="Load Collections State [only required if logged in another user ", scale=0,
-                                size='sm',
-                                visible=False and allow_upload_to_user_data and
-                                        kwargs['langchain_mode'] != 'Disabled')
-                        with gr.Column(scale=5):
-                            if kwargs['langchain_mode'] != 'Disabled' and visible_add_remove_collection:
-                                df0 = get_df_langchain_mode_paths(selection_docs_state0, None, dbs1=dbs)
-                            else:
-                                df0 = pd.DataFrame(None)
-                            langchain_mode_path_text = gr.Dataframe(value=df0,
-                                                                    visible=visible_add_remove_collection,
-                                                                    label='LangChain Mode-Path',
-                                                                    show_label=False,
-                                                                    interactive=False)
-
-                    sources_row = gr.Row(visible=kwargs['langchain_mode'] != 'Disabled' and enable_sources_list,
-                                         equal_height=False)
-                    with sources_row:
-                        with gr.Column(scale=1):
-                            file_source = gr.File(interactive=False,
-                                                  label="Download File w/Sources")
-                        with gr.Column(scale=2):
-                            sources_text = gr.HTML(label='Sources Added', interactive=False)
-
-                    doc_exception_text = gr.Textbox(value="", label='Document Exceptions',
-                                                    interactive=False,
-                                                    visible=kwargs['langchain_mode'] != 'Disabled')
-                    file_types_str = ' '.join(file_types) + ' URL ArXiv TEXT'
-                    gr.Textbox(value=file_types_str, label='Document Types Supported',
-                               lines=2,
-                               interactive=False,
-                               visible=kwargs['langchain_mode'] != 'Disabled')
-
-                doc_view_tab = gr.TabItem("Document Viewer") \
-                    if kwargs['visible_doc_view_tab'] else gr.Row(visible=False)
-                with doc_view_tab:
-                    with gr.Row(visible=kwargs['langchain_mode'] != 'Disabled'):
-                        with gr.Column(scale=2):
-                            get_viewable_sources_btn = gr.Button(value="Update UI with Document(s) from DB", scale=0,
-                                                                 size='sm',
-                                                                 visible=sources_visible and kwargs[
-                                                                     'large_file_count_mode'])
-                            view_document_choice = gr.Dropdown(viewable_docs_state0,
-                                                               label="Select Single Document to View",
-                                                               value=None,
-                                                               interactive=True,
-                                                               multiselect=False,
-                                                               visible=True,
-                                                               )
-                            info_view_raw = "Raw text shown if render of original doc fails"
-                            if is_public:
-                                info_view_raw += " (Up to %s chunks in public portal)" % kwargs['max_raw_chunks']
-                            view_raw_text_checkbox = gr.Checkbox(label="View Database Text", value=False,
-                                                                 info=info_view_raw,
-                                                                 visible=kwargs['db_type'] in ['chroma', 'chroma_old'])
-                        with gr.Column(scale=4):
-                            pass
-                    doc_view = gr.HTML(visible=False)
-                    doc_view2 = gr.Dataframe(visible=False)
-                    doc_view3 = gr.JSON(visible=False)
-                    doc_view4 = gr.Markdown(visible=False)
-                    doc_view5 = gr.HTML(visible=False)
-
-                chat_tab = gr.TabItem("Chat History") \
-                    if kwargs['visible_chat_history_tab'] else gr.Row(visible=False)
-                with chat_tab:
-                    with gr.Row():
-                        with gr.Column(scale=1):
-                            remove_chat_btn = gr.Button(value="Remove Selected Saved Chats", visible=True, size='sm')
-                            flag_btn = gr.Button("Flag Current Chat", size='sm')
-                            export_chats_btn = gr.Button(value="Export Chats to Download", size='sm')
-                        with gr.Column(scale=4):
-                            pass
-                    with gr.Row():
-                        chats_file = gr.File(interactive=False, label="Download Exported Chats")
-                        chatsup_output = gr.File(label="Upload Chat File(s)",
-                                                 file_types=['.json'],
-                                                 file_count='multiple',
-                                                 elem_id="warning", elem_classes="feedback")
-                    with gr.Row():
-                        if 'mbart-' in kwargs['model_lower']:
-                            src_lang = gr.Dropdown(list(languages_covered().keys()),
-                                                   value=kwargs['src_lang'],
-                                                   label="Input Language")
-                            tgt_lang = gr.Dropdown(list(languages_covered().keys()),
-                                                   value=kwargs['tgt_lang'],
-                                                   label="Output Language")
-
-                    chat_exception_text = gr.Textbox(value="", visible=True, label='Chat Exceptions',
-                                                     interactive=False)
-                expert_tab = gr.TabItem("Expert") \
-                    if kwargs['visible_expert_tab'] else gr.Row(visible=False)
-                with expert_tab:
-                    with gr.Row():
-                        with gr.Column():
-                            prompt_type = gr.Dropdown(prompt_types_strings,
-                                                      value=kwargs['prompt_type'], label="Prompt Type",
-                                                      visible=not kwargs['model_lock'],
-                                                      interactive=not is_public,
-                                                      )
-                            prompt_type2 = gr.Dropdown(prompt_types_strings,
-                                                       value=kwargs['prompt_type'], label="Prompt Type Model 2",
-                                                       visible=False and not kwargs['model_lock'],
-                                                       interactive=not is_public)
-                            system_prompt = gr.Textbox(label="System Prompt",
-                                                       info="If 'auto', then uses model's system prompt,"
-                                                            " else use this message."
-                                                            " If empty, no system message is used",
-                                                       value=kwargs['system_prompt'])
-                            context = gr.Textbox(lines=2, label="System Pre-Context",
-                                                 info="Directly pre-appended without prompt processing (before Pre-Conversation)",
-                                                 value=kwargs['context'])
-                            chat_conversation = gr.Textbox(lines=2, label="Pre-Conversation",
-                                                           info="Pre-append conversation for instruct/chat models as List of tuple of (human, bot)",
-                                                           value=kwargs['chat_conversation'])
-                            text_context_list = gr.Textbox(lines=2, label="Text Doc Q/A",
-                                                           info="List of strings, for document Q/A, for bypassing database (i.e. also works in LLM Mode)",
-                                                           value=kwargs['chat_conversation'],
-                                                           visible=not is_public,  # primarily meant for API
-                                                           )
-                            iinput = gr.Textbox(lines=2, label="Input for Instruct prompt types",
-                                                info="If given for document query, added after query",
-                                                value=kwargs['iinput'],
-                                                placeholder=kwargs['placeholder_input'],
-                                                interactive=not is_public)
-                        with gr.Column():
-                            pre_prompt_query = gr.Textbox(label="Query Pre-Prompt",
-                                                          info="Added before documents",
-                                                          value=kwargs['pre_prompt_query'] or '')
-                            prompt_query = gr.Textbox(label="Query Prompt",
-                                                      info="Added after documents",
-                                                      value=kwargs['prompt_query'] or '')
-                            pre_prompt_summary = gr.Textbox(label="Summary Pre-Prompt",
-                                                            info="Added before documents",
-                                                            value=kwargs['pre_prompt_summary'] or '')
-                            prompt_summary = gr.Textbox(label="Summary Prompt",
-                                                        info="Added after documents (if query given, 'Focusing on {query}, ' is pre-appended)",
-                                                        value=kwargs['prompt_summary'] or '')
-                    with gr.Row(visible=not is_public):
-                        image_loaders = gr.CheckboxGroup(image_loaders_options,
-                                                         label="Force Image Reader",
-                                                         value=image_loaders_options0)
-                        pdf_loaders = gr.CheckboxGroup(pdf_loaders_options,
-                                                       label="Force PDF Reader",
-                                                       value=pdf_loaders_options0)
-                        url_loaders = gr.CheckboxGroup(url_loaders_options,
-                                                       label="Force URL Reader", value=url_loaders_options0)
-                        jq_schema = gr.Textbox(label="JSON jq_schema", value=jq_schema0)
-
-                        min_top_k_docs, max_top_k_docs, label_top_k_docs = get_minmax_top_k_docs(is_public)
-                        top_k_docs = gr.Slider(minimum=min_top_k_docs, maximum=max_top_k_docs, step=1,
-                                               value=kwargs['top_k_docs'],
-                                               label=label_top_k_docs,
-                                               # info="For LangChain",
-                                               visible=kwargs['langchain_mode'] != 'Disabled',
-                                               interactive=not is_public)
-                        chunk_size = gr.Number(value=kwargs['chunk_size'],
-                                               label="Chunk size for document chunking",
-                                               info="For LangChain (ignored if chunk=False)",
-                                               minimum=128,
-                                               maximum=2048,
-                                               visible=kwargs['langchain_mode'] != 'Disabled',
-                                               interactive=not is_public,
-                                               precision=0)
-                        docs_ordering_type = gr.Radio(
-                            docs_ordering_types,
-                            value=kwargs['docs_ordering_type'],
-                            label="Document Sorting in LLM Context",
-                            visible=True)
-                        chunk = gr.components.Checkbox(value=kwargs['chunk'],
-                                                       label="Whether to chunk documents",
-                                                       info="For LangChain",
-                                                       visible=kwargs['langchain_mode'] != 'Disabled',
-                                                       interactive=not is_public)
-                        embed = gr.components.Checkbox(value=True,
-                                                       label="Whether to embed text",
-                                                       info="For LangChain",
-                                                       visible=False)
-                    with gr.Row():
-                        stream_output = gr.components.Checkbox(label="Stream output",
-                                                               value=kwargs['stream_output'])
-                        do_sample = gr.Checkbox(label="Sample",
-                                                info="Enable sampler (required for use of temperature, top_p, top_k)",
-                                                value=kwargs['do_sample'])
-                        max_time = gr.Slider(minimum=0, maximum=kwargs['max_max_time'], step=1,
-                                             value=min(kwargs['max_max_time'],
-                                                       kwargs['max_time']), label="Max. time",
-                                             info="Max. time to search optimal output.")
-                        temperature = gr.Slider(minimum=0.01, maximum=2,
-                                                value=kwargs['temperature'],
-                                                label="Temperature",
-                                                info="Lower is deterministic, higher more creative")
-                        top_p = gr.Slider(minimum=1e-3, maximum=1.0 - 1e-3,
-                                          value=kwargs['top_p'], label="Top p",
-                                          info="Cumulative probability of tokens to sample from")
-                        top_k = gr.Slider(
-                            minimum=1, maximum=100, step=1,
-                            value=kwargs['top_k'], label="Top k",
-                            info='Num. tokens to sample from'
-                        )
-                        # FIXME: https://github.com/h2oai/h2ogpt/issues/106
-                        if os.getenv('TESTINGFAIL'):
-                            max_beams = 8 if not (memory_restriction_level or is_public) else 1
-                        else:
-                            max_beams = 1
-                        num_beams = gr.Slider(minimum=1, maximum=max_beams, step=1,
-                                              value=min(max_beams, kwargs['num_beams']), label="Beams",
-                                              info="Number of searches for optimal overall probability.  "
-                                                   "Uses more GPU memory/compute",
-                                              interactive=False, visible=max_beams > 1)
-                        max_max_new_tokens = get_max_max_new_tokens(model_state0, **kwargs)
-                        max_new_tokens = gr.Slider(
-                            minimum=1, maximum=max_max_new_tokens, step=1,
-                            value=min(max_max_new_tokens, kwargs['max_new_tokens']), label="Max output length",
-                        )
-                        min_new_tokens = gr.Slider(
-                            minimum=0, maximum=max_max_new_tokens, step=1,
-                            value=min(max_max_new_tokens, kwargs['min_new_tokens']), label="Min output length",
-                        )
-                        max_new_tokens2 = gr.Slider(
-                            minimum=1, maximum=max_max_new_tokens, step=1,
-                            value=min(max_max_new_tokens, kwargs['max_new_tokens']), label="Max output length 2",
-                            visible=False and not kwargs['model_lock'],
-                        )
-                        min_new_tokens2 = gr.Slider(
-                            minimum=0, maximum=max_max_new_tokens, step=1,
-                            value=min(max_max_new_tokens, kwargs['min_new_tokens']), label="Min output length 2",
-                            visible=False and not kwargs['model_lock'],
-                        )
-                        min_max_new_tokens = gr.Slider(
-                            minimum=1, maximum=max_max_new_tokens, step=1,
-                            value=min(max_max_new_tokens, kwargs['min_max_new_tokens']),
-                            label="Min. of Max output length",
-                        )
-                        early_stopping = gr.Checkbox(label="EarlyStopping", info="Stop early in beam search",
-                                                     value=kwargs['early_stopping'], visible=max_beams > 1)
-                        repetition_penalty = gr.Slider(minimum=0.01, maximum=3.0,
-                                                       value=kwargs['repetition_penalty'],
-                                                       label="Repetition Penalty")
-                        num_return_sequences = gr.Slider(minimum=1, maximum=10, step=1,
-                                                         value=kwargs['num_return_sequences'],
-                                                         label="Number Returns", info="Must be <= num_beams",
-                                                         interactive=not is_public, visible=max_beams > 1)
-                        chat = gr.components.Checkbox(label="Chat mode", value=kwargs['chat'],
-                                                      visible=False,  # no longer support nochat in UI
-                                                      interactive=not is_public,
-                                                      )
-                    with gr.Row():
-                        count_chat_tokens_btn = gr.Button(value="Count Chat Tokens",
-                                                          visible=not is_public and not kwargs['model_lock'],
-                                                          interactive=not is_public, size='sm')
-                        chat_token_count = gr.Textbox(label="Chat Token Count Result", value=None,
-                                                      visible=not is_public and not kwargs['model_lock'],
-                                                      interactive=False)
-
-                models_tab = gr.TabItem("Models") \
-                    if kwargs['visible_models_tab'] and not bool(kwargs['model_lock']) else gr.Row(visible=False)
-                with models_tab:
-                    load_msg = "Download/Load Model" if not is_public \
-                        else "LOAD-UNLOAD DISABLED FOR HOSTED DEMO"
-                    if kwargs['base_model'] not in ['', None, no_model_str]:
-                        load_msg += '   [WARNING: Avoid --base_model on CLI for memory efficient Load-Unload]'
-                    load_msg2 = load_msg + "(Model 2)"
-                    variant_load_msg = 'primary' if not is_public else 'secondary'
-                    with gr.Row():
-                        n_gpus_list = [str(x) for x in list(range(-1, n_gpus))]
-                        with gr.Column():
-                            with gr.Row():
-                                with gr.Column(scale=20, visible=not kwargs['model_lock']):
-                                    load_model_button = gr.Button(load_msg, variant=variant_load_msg, scale=0,
-                                                                  size='sm', interactive=not is_public)
-                                    model_choice = gr.Dropdown(model_options_state.value[0], label="Choose Base Model",
-                                                               value=kwargs['base_model'])
-                                    lora_choice = gr.Dropdown(lora_options_state.value[0], label="Choose LORA",
-                                                              value=kwargs['lora_weights'], visible=kwargs['show_lora'])
-                                    server_choice = gr.Dropdown(server_options_state.value[0], label="Choose Server",
-                                                                value=kwargs['inference_server'], visible=not is_public)
-                                    max_seq_len = gr.Number(value=kwargs['max_seq_len'] or 2048,
-                                                            minimum=128,
-                                                            maximum=2 ** 18,
-                                                            info="If standard LLaMa-2, choose up to 4096",
-                                                            label="max_seq_len")
-                                    rope_scaling = gr.Textbox(value=str(kwargs['rope_scaling'] or {}),
-                                                              label="rope_scaling")
-                                    row_llama = gr.Row(visible=kwargs['show_llama'] and kwargs['base_model'] == 'llama')
-                                    with row_llama:
-                                        model_path_llama = gr.Textbox(value=kwargs['llamacpp_dict']['model_path_llama'],
-                                                                      lines=4,
-                                                                      label="Choose LLaMa.cpp Model Path/URL (for Base Model: llama)",
-                                                                      visible=kwargs['show_llama'])
-                                        n_gpu_layers = gr.Number(value=kwargs['llamacpp_dict']['n_gpu_layers'],
-                                                                 minimum=0, maximum=100,
-                                                                 label="LLaMa.cpp Num. GPU Layers Offloaded",
-                                                                 visible=kwargs['show_llama'])
-                                        n_batch = gr.Number(value=kwargs['llamacpp_dict']['n_batch'],
-                                                            minimum=0, maximum=2048,
-                                                            label="LLaMa.cpp Batch Size",
-                                                            visible=kwargs['show_llama'])
-                                        n_gqa = gr.Number(value=kwargs['llamacpp_dict']['n_gqa'],
-                                                          minimum=0, maximum=32,
-                                                          label="LLaMa.cpp Num. Group Query Attention (8 for 70B LLaMa2)",
-                                                          visible=kwargs['show_llama'])
-                                        llamacpp_dict_more = gr.Textbox(value="{}",
-                                                                        lines=4,
-                                                                        label="Dict for other LLaMa.cpp/GPT4All options",
-                                                                        visible=kwargs['show_llama'])
-                                    row_gpt4all = gr.Row(
-                                        visible=kwargs['show_gpt4all'] and kwargs['base_model'] in ['gptj',
-                                                                                                    'gpt4all_llama'])
-                                    with row_gpt4all:
-                                        model_name_gptj = gr.Textbox(value=kwargs['llamacpp_dict']['model_name_gptj'],
-                                                                     label="Choose GPT4All GPTJ Model Path/URL (for Base Model: gptj)",
-                                                                     visible=kwargs['show_gpt4all'])
-                                        model_name_gpt4all_llama = gr.Textbox(
-                                            value=kwargs['llamacpp_dict']['model_name_gpt4all_llama'],
-                                            label="Choose GPT4All LLaMa Model Path/URL (for Base Model: gpt4all_llama)",
-                                            visible=kwargs['show_gpt4all'])
-                                with gr.Column(scale=1, visible=not kwargs['model_lock']):
-                                    model_load8bit_checkbox = gr.components.Checkbox(
-                                        label="Load 8-bit [requires support]",
-                                        value=kwargs['load_8bit'], interactive=not is_public)
-                                    model_load4bit_checkbox = gr.components.Checkbox(
-                                        label="Load 4-bit [requires support]",
-                                        value=kwargs['load_4bit'], interactive=not is_public)
-                                    model_low_bit_mode = gr.Slider(value=kwargs['low_bit_mode'],
-                                                                   minimum=0, maximum=4, step=1,
-                                                                   label="low_bit_mode")
-                                    model_load_gptq = gr.Textbox(label="gptq", value=kwargs['load_gptq'],
-                                                                 interactive=not is_public)
-                                    model_load_exllama_checkbox = gr.components.Checkbox(
-                                        label="Load load_exllama [requires support]",
-                                        value=kwargs['load_exllama'], interactive=not is_public)
-                                    model_safetensors_checkbox = gr.components.Checkbox(
-                                        label="Safetensors [requires support]",
-                                        value=kwargs['use_safetensors'], interactive=not is_public)
-                                    model_revision = gr.Textbox(label="revision", value=kwargs['revision'],
-                                                                interactive=not is_public)
-                                    model_use_gpu_id_checkbox = gr.components.Checkbox(
-                                        label="Choose Devices [If not Checked, use all GPUs]",
-                                        value=kwargs['use_gpu_id'], interactive=not is_public,
-                                        visible=n_gpus != 0)
-                                    model_gpu = gr.Dropdown(n_gpus_list,
-                                                            label="GPU ID [-1 = all GPUs, if Choose is enabled]",
-                                                            value=kwargs['gpu_id'], interactive=not is_public,
-                                                            visible=n_gpus != 0)
-                                    model_used = gr.Textbox(label="Current Model", value=kwargs['base_model'],
-                                                            interactive=False)
-                                    lora_used = gr.Textbox(label="Current LORA", value=kwargs['lora_weights'],
-                                                           visible=kwargs['show_lora'], interactive=False)
-                                    server_used = gr.Textbox(label="Current Server",
-                                                             value=kwargs['inference_server'],
-                                                             visible=bool(kwargs['inference_server']) and not is_public,
-                                                             interactive=False)
-                                    prompt_dict = gr.Textbox(label="Prompt (or Custom)",
-                                                             value=pprint.pformat(kwargs['prompt_dict'], indent=4),
-                                                             interactive=not is_public, lines=4)
-                        col_model2 = gr.Column(visible=False)
-                        with col_model2:
-                            with gr.Row():
-                                with gr.Column(scale=20, visible=not kwargs['model_lock']):
-                                    load_model_button2 = gr.Button(load_msg2, variant=variant_load_msg, scale=0,
-                                                                   size='sm', interactive=not is_public)
-                                    model_choice2 = gr.Dropdown(model_options_state.value[0], label="Choose Model 2",
-                                                                value=no_model_str)
-                                    lora_choice2 = gr.Dropdown(lora_options_state.value[0], label="Choose LORA 2",
-                                                               value=no_lora_str,
-                                                               visible=kwargs['show_lora'])
-                                    server_choice2 = gr.Dropdown(server_options_state.value[0], label="Choose Server 2",
-                                                                 value=no_server_str,
-                                                                 visible=not is_public)
-                                    max_seq_len2 = gr.Number(value=kwargs['max_seq_len'] or 2048,
-                                                             minimum=128,
-                                                             maximum=2 ** 18,
-                                                             info="If standard LLaMa-2, choose up to 4096",
-                                                             label="max_seq_len Model 2")
-                                    rope_scaling2 = gr.Textbox(value=str(kwargs['rope_scaling'] or {}),
-                                                               label="rope_scaling Model 2")
-
-                                    row_llama2 = gr.Row(
-                                        visible=kwargs['show_llama'] and kwargs['base_model'] == 'llama')
-                                    with row_llama2:
-                                        model_path_llama2 = gr.Textbox(
-                                            value=kwargs['llamacpp_dict']['model_path_llama'],
-                                            label="Choose LLaMa.cpp Model 2 Path/URL (for Base Model: llama)",
-                                            lines=4,
-                                            visible=kwargs['show_llama'])
-                                        n_gpu_layers2 = gr.Number(value=kwargs['llamacpp_dict']['n_gpu_layers'],
-                                                                  minimum=0, maximum=100,
-                                                                  label="LLaMa.cpp Num. GPU 2 Layers Offloaded",
-                                                                  visible=kwargs['show_llama'])
-                                        n_batch2 = gr.Number(value=kwargs['llamacpp_dict']['n_batch'],
-                                                             minimum=0, maximum=2048,
-                                                             label="LLaMa.cpp Model 2 Batch Size",
-                                                             visible=kwargs['show_llama'])
-                                        n_gqa2 = gr.Number(value=kwargs['llamacpp_dict']['n_gqa'],
-                                                           minimum=0, maximum=32,
-                                                           label="LLaMa.cpp Model 2 Num. Group Query Attention (8 for 70B LLaMa2)",
-                                                           visible=kwargs['show_llama'])
-                                        llamacpp_dict_more2 = gr.Textbox(value="{}",
-                                                                         lines=4,
-                                                                         label="Model 2 Dict for other LLaMa.cpp/GPT4All options",
-                                                                         visible=kwargs['show_llama'])
-                                    row_gpt4all2 = gr.Row(
-                                        visible=kwargs['show_gpt4all'] and kwargs['base_model'] in ['gptj',
-                                                                                                    'gpt4all_llama'])
-                                    with row_gpt4all2:
-                                        model_name_gptj2 = gr.Textbox(value=kwargs['llamacpp_dict']['model_name_gptj'],
-                                                                      label="Choose GPT4All GPTJ Model 2 Path/URL (for Base Model: gptj)",
-                                                                      visible=kwargs['show_gpt4all'])
-                                        model_name_gpt4all_llama2 = gr.Textbox(
-                                            value=kwargs['llamacpp_dict']['model_name_gpt4all_llama'],
-                                            label="Choose GPT4All LLaMa Model 2 Path/URL (for Base Model: gpt4all_llama)",
-                                            visible=kwargs['show_gpt4all'])
-
-                                with gr.Column(scale=1, visible=not kwargs['model_lock']):
-                                    model_load8bit_checkbox2 = gr.components.Checkbox(
-                                        label="Load 8-bit (Model 2) [requires support]",
-                                        value=kwargs['load_8bit'], interactive=not is_public)
-                                    model_load4bit_checkbox2 = gr.components.Checkbox(
-                                        label="Load 4-bit (Model 2) [requires support]",
-                                        value=kwargs['load_4bit'], interactive=not is_public)
-                                    model_low_bit_mode2 = gr.Slider(value=kwargs['low_bit_mode'],
-                                                                    # ok that same as Model 1
-                                                                    minimum=0, maximum=4, step=1,
-                                                                    label="low_bit_mode (Model 2)")
-                                    model_load_gptq2 = gr.Textbox(label="gptq (Model 2)", value='',
-                                                                  interactive=not is_public)
-                                    model_load_exllama_checkbox2 = gr.components.Checkbox(
-                                        label="Load load_exllama (Model 2) [requires support]",
-                                        value=False, interactive=not is_public)
-                                    model_safetensors_checkbox2 = gr.components.Checkbox(
-                                        label="Safetensors (Model 2) [requires support]",
-                                        value=False, interactive=not is_public)
-                                    model_revision2 = gr.Textbox(label="revision (Model 2)", value='',
-                                                                 interactive=not is_public)
-                                    model_use_gpu_id_checkbox2 = gr.components.Checkbox(
-                                        label="Choose Devices (Model 2) [If not Checked, use all GPUs]",
-                                        value=kwargs[
-                                            'use_gpu_id'], interactive=not is_public)
-                                    model_gpu2 = gr.Dropdown(n_gpus_list,
-                                                             label="GPU ID (Model 2) [-1 = all GPUs, if choose is enabled]",
-                                                             value=kwargs['gpu_id'], interactive=not is_public)
-                                    # no model/lora loaded ever in model2 by default
-                                    model_used2 = gr.Textbox(label="Current Model 2", value=no_model_str,
-                                                             interactive=False)
-                                    lora_used2 = gr.Textbox(label="Current LORA (Model 2)", value=no_lora_str,
-                                                            visible=kwargs['show_lora'], interactive=False)
-                                    server_used2 = gr.Textbox(label="Current Server (Model 2)", value=no_server_str,
-                                                              interactive=False,
-                                                              visible=not is_public)
-                                    prompt_dict2 = gr.Textbox(label="Prompt (or Custom) (Model 2)",
-                                                              value=pprint.pformat(kwargs['prompt_dict'], indent=4),
-                                                              interactive=not is_public, lines=4)
-                    compare_checkbox = gr.components.Checkbox(label="Compare Two Models",
-                                                              value=kwargs['model_lock'],
-                                                              visible=not is_public and not kwargs['model_lock'])
-                    with gr.Row(visible=not kwargs['model_lock']):
-                        with gr.Column(scale=50):
-                            new_model = gr.Textbox(label="New Model name/path/URL", interactive=not is_public)
-                        with gr.Column(scale=50):
-                            new_lora = gr.Textbox(label="New LORA name/path/URL", visible=kwargs['show_lora'],
-                                                  interactive=not is_public)
-                        with gr.Column(scale=50):
-                            new_server = gr.Textbox(label="New Server url:port", interactive=not is_public)
-                        with gr.Row():
-                            add_model_lora_server_button = gr.Button("Add new Model, Lora, Server url:port", scale=0,
-                                                                     variant=variant_load_msg,
-                                                                     size='sm', interactive=not is_public)
-                system_tab = gr.TabItem("System") \
-                    if kwargs['visible_system_tab'] else gr.Row(visible=False)
-                with system_tab:
-                    with gr.Row():
-                        with gr.Column(scale=1):
-                            side_bar_text = gr.Textbox('on' if kwargs['visible_side_bar'] else 'off',
-                                                       visible=False, interactive=False)
-                            doc_count_text = gr.Textbox('on' if kwargs['visible_doc_track'] else 'off',
-                                                        visible=False, interactive=False)
-                            submit_buttons_text = gr.Textbox('on' if kwargs['visible_submit_buttons'] else 'off',
-                                                             visible=False, interactive=False)
-                            visible_models_text = gr.Textbox('on' if kwargs['visible_visible_models'] else 'off',
-                                                             visible=False, interactive=False)
-
-                            side_bar_btn = gr.Button("Toggle SideBar", variant="secondary", size="sm")
-                            doc_count_btn = gr.Button("Toggle SideBar Document Count/Show Newest", variant="secondary",
-                                                      size="sm")
-                            submit_buttons_btn = gr.Button("Toggle Submit Buttons", variant="secondary", size="sm")
-                            visible_model_btn = gr.Button("Toggle Visible Models", variant="secondary", size="sm")
-                            col_tabs_scale = gr.Slider(minimum=1, maximum=20, value=10, step=1, label='Window Size')
-                            text_outputs_height = gr.Slider(minimum=100, maximum=2000, value=kwargs['height'] or 400,
-                                                            step=50, label='Chat Height')
-                            dark_mode_btn = gr.Button("Dark Mode", variant="secondary", size="sm")
-                        with gr.Column(scale=4):
-                            pass
-                    system_visible0 = not is_public and not admin_pass
-                    admin_row = gr.Row()
-                    with admin_row:
-                        with gr.Column(scale=1):
-                            admin_pass_textbox = gr.Textbox(label="Admin Password",
-                                                            type='password',
-                                                            visible=not system_visible0)
-                        with gr.Column(scale=4):
-                            pass
-                    system_row = gr.Row(visible=system_visible0)
-                    with system_row:
-                        with gr.Column():
-                            with gr.Row():
-                                system_btn = gr.Button(value='Get System Info', size='sm')
-                                system_text = gr.Textbox(label='System Info', interactive=False, show_copy_button=True)
-                            with gr.Row():
-                                system_input = gr.Textbox(label='System Info Dict Password', interactive=True,
-                                                          visible=not is_public)
-                                system_btn2 = gr.Button(value='Get System Info Dict', visible=not is_public, size='sm')
-                                system_text2 = gr.Textbox(label='System Info Dict', interactive=False,
-                                                          visible=not is_public, show_copy_button=True)
-                            with gr.Row():
-                                system_btn3 = gr.Button(value='Get Hash', visible=not is_public, size='sm')
-                                system_text3 = gr.Textbox(label='Hash', interactive=False,
-                                                          visible=not is_public, show_copy_button=True)
-                                system_btn4 = gr.Button(value='Get Model Names', visible=not is_public, size='sm')
-                                system_text4 = gr.Textbox(label='Model Names', interactive=False,
-                                                          visible=not is_public, show_copy_button=True)
-
-                            with gr.Row():
-                                zip_btn = gr.Button("Zip", size='sm')
-                                zip_text = gr.Textbox(label="Zip file name", interactive=False)
-                                file_output = gr.File(interactive=False, label="Zip file to Download")
-                            with gr.Row():
-                                s3up_btn = gr.Button("S3UP", size='sm')
-                                s3up_text = gr.Textbox(label='S3UP result', interactive=False)
-
-                tos_tab = gr.TabItem("Terms of Service") \
-                    if kwargs['visible_tos_tab'] else gr.Row(visible=False)
-                with tos_tab:
-                    description = ""
-                    description += """<p><b> DISCLAIMERS: </b><ul><i><li>The model was trained on The Pile and other data, which may contain objectionable content.  Use at own risk.</i></li>"""
-                    if kwargs['load_8bit']:
-                        description += """<i><li> Model is loaded in 8-bit and has other restrictions on this host. UX can be worse than non-hosted version.</i></li>"""
-                    description += """<i><li>Conversations may be used to improve h2oGPT.  Do not share sensitive information.</i></li>"""
-                    if 'h2ogpt-research' in kwargs['base_model']:
-                        description += """<i><li>Research demonstration only, not used for commercial purposes.</i></li>"""
-                    description += """<i><li>By using h2oGPT, you accept our <a href="https://github.com/h2oai/h2ogpt/blob/main/docs/tos.md">Terms of Service</a></i></li></ul></p>"""
-                    gr.Markdown(value=description, show_label=False, interactive=False)
-
-                login_tab = gr.TabItem("Login") \
-                    if kwargs['visible_login_tab'] else gr.Row(visible=False)
-                with login_tab:
-                    gr.Markdown(
-                        value="#### Login page to persist your state (database, documents, chat, chat history)\nDaily maintenance at midnight PST will not allow reconnection to state otherwise.")
-                    username_text = gr.Textbox(label="Username")
-                    password_text = gr.Textbox(label="Password", type='password', visible=True)
-                    login_msg = "Login (pick unique user/pass to persist your state)" if kwargs[
-                                                                                             'auth_access'] == 'open' else "Login (closed access)"
-                    login_btn = gr.Button(value=login_msg)
-                    login_result_text = gr.Text(label="Login Result", interactive=False)
-                    h2ogpt_key = gr.Text(value=kwargs['h2ogpt_key'], label="h2oGPT Token for API access",
-                                         type='password', visible=False)
-
-                hosts_tab = gr.TabItem("Hosts") \
-                    if kwargs['visible_hosts_tab'] else gr.Row(visible=False)
-                with hosts_tab:
-                    gr.Markdown(f"""
-                        {description_bottom}
-                        {task_info_md}
-                        """)
-
-        # Get flagged data
-        zip_data1 = functools.partial(zip_data, root_dirs=['flagged_data_points', kwargs['save_dir']])
-        zip_event = zip_btn.click(zip_data1, inputs=None, outputs=[file_output, zip_text], queue=False,
-                                  api_name='zip_data' if allow_api else None)
-        s3up_event = s3up_btn.click(s3up, inputs=zip_text, outputs=s3up_text, queue=False,
-                                    api_name='s3up_data' if allow_api else None)
-
-        def clear_file_list():
-            return None
-
-        def set_loaders(max_quality1,
-                        image_loaders_options1=None,
-                        pdf_loaders_options1=None,
-                        url_loaders_options1=None,
-                        image_loaders_options01=None,
-                        pdf_loaders_options01=None,
-                        url_loaders_options01=None,
-                        ):
-            if not max_quality1:
-                return image_loaders_options01, pdf_loaders_options01, url_loaders_options01
-            else:
-                return image_loaders_options1, pdf_loaders_options1, url_loaders_options1
-
-        set_loaders_func = functools.partial(set_loaders,
-                                             image_loaders_options1=image_loaders_options,
-                                             pdf_loaders_options1=pdf_loaders_options,
-                                             url_loaders_options1=url_loaders_options,
-                                             image_loaders_options01=image_loaders_options0,
-                                             pdf_loaders_options01=pdf_loaders_options0,
-                                             url_loaders_options01=url_loaders_options0,
-                                             )
-
-        max_quality.change(fn=set_loaders_func,
-                           inputs=max_quality,
-                           outputs=[image_loaders, pdf_loaders, url_loaders])
-
-        def get_model_lock_visible_list(visible_models1, all_models):
-            visible_list = []
-            for modeli, model in enumerate(all_models):
-                if visible_models1 is None or model in visible_models1 or modeli in visible_models1:
-                    visible_list.append(True)
-                else:
-                    visible_list.append(False)
-            return visible_list
-
-        def set_visible_models(visible_models1, num_model_lock=0, all_models=None):
-            if num_model_lock == 0:
-                num_model_lock = 3  # 2 + 1 (which is dup of first)
-                ret_list = [gr.update(visible=True)] * num_model_lock
-            else:
-                assert isinstance(all_models, list)
-                assert num_model_lock == len(all_models)
-                visible_list = [False, False] + get_model_lock_visible_list(visible_models1, all_models)
-                ret_list = [gr.update(visible=x) for x in visible_list]
-            return tuple(ret_list)
-
-        visible_models_func = functools.partial(set_visible_models,
-                                                num_model_lock=len(text_outputs),
-                                                all_models=kwargs['all_models'])
-        visible_models.change(fn=visible_models_func,
-                              inputs=visible_models,
-                              outputs=[text_output, text_output2] + text_outputs,
-                              )
-
-        # Add to UserData or custom user db
-        update_db_func = functools.partial(update_user_db_gr,
-                                           dbs=dbs,
-                                           db_type=db_type,
-                                           use_openai_embedding=use_openai_embedding,
-                                           hf_embedding_model=hf_embedding_model,
-                                           migrate_embedding_model=migrate_embedding_model,
-                                           auto_migrate_db=auto_migrate_db,
-                                           captions_model=captions_model,
-                                           caption_loader=caption_loader,
-                                           doctr_loader=doctr_loader,
-                                           verbose=kwargs['verbose'],
-                                           n_jobs=kwargs['n_jobs'],
-                                           get_userid_auth=get_userid_auth,
-                                           image_loaders_options0=image_loaders_options0,
-                                           pdf_loaders_options0=pdf_loaders_options0,
-                                           url_loaders_options0=url_loaders_options0,
-                                           jq_schema0=jq_schema0,
-                                           enforce_h2ogpt_api_key=kwargs['enforce_h2ogpt_api_key'],
-                                           h2ogpt_api_keys=kwargs['h2ogpt_api_keys'],
-                                           )
-        add_file_outputs = [fileup_output, langchain_mode]
-        add_file_kwargs = dict(fn=update_db_func,
-                               inputs=[fileup_output, my_db_state, selection_docs_state, requests_state,
-                                       langchain_mode, chunk, chunk_size, embed,
-                                       image_loaders,
-                                       pdf_loaders,
-                                       url_loaders,
-                                       jq_schema,
-                                       h2ogpt_key,
-                                       ],
-                               outputs=add_file_outputs + [sources_text, doc_exception_text, text_file_last],
-                               queue=queue,
-                               api_name='add_file' if allow_upload_api else None)
-
-        # then no need for add buttons, only single changeable db
-        user_state_kwargs = dict(fn=user_state_setup,
-                                 inputs=[my_db_state, requests_state, langchain_mode],
-                                 outputs=[my_db_state, requests_state, langchain_mode],
-                                 show_progress='minimal')
-        eventdb1a = fileup_output.upload(**user_state_kwargs)
-        eventdb1 = eventdb1a.then(**add_file_kwargs, show_progress='full')
-
-        event_attach1 = attach_button.upload(**user_state_kwargs)
-        attach_file_kwargs = add_file_kwargs.copy()
-        attach_file_kwargs['inputs'][0] = attach_button
-        attach_file_kwargs['outputs'][0] = attach_button
-        attach_file_kwargs['api_name'] = 'attach_file'
-        event_attach2 = event_attach1.then(**attach_file_kwargs, show_progress='full')
-
-        sync1 = sync_sources_btn.click(**user_state_kwargs)
-
-        # deal with challenge to have fileup_output itself as input
-        add_file_kwargs2 = dict(fn=update_db_func,
-                                inputs=[fileup_output_text, my_db_state, selection_docs_state, requests_state,
-                                        langchain_mode, chunk, chunk_size, embed,
-                                        image_loaders,
-                                        pdf_loaders,
-                                        url_loaders,
-                                        jq_schema,
-                                        h2ogpt_key,
-                                        ],
-                                outputs=add_file_outputs + [sources_text, doc_exception_text, text_file_last],
-                                queue=queue,
-                                api_name='add_file_api' if allow_upload_api else None)
-        eventdb1_api = fileup_output_text.submit(**add_file_kwargs2, show_progress='full')
-
-        # note for update_user_db_func output is ignored for db
-
-        def clear_textbox():
-            return gr.Textbox.update(value='')
-
-        update_user_db_url_func = functools.partial(update_db_func, is_url=True)
-
-        add_url_outputs = [url_text, langchain_mode]
-        add_url_kwargs = dict(fn=update_user_db_url_func,
-                              inputs=[url_text, my_db_state, selection_docs_state, requests_state,
-                                      langchain_mode, chunk, chunk_size, embed,
-                                      image_loaders,
-                                      pdf_loaders,
-                                      url_loaders,
-                                      jq_schema,
-                                      h2ogpt_key,
-                                      ],
-                              outputs=add_url_outputs + [sources_text, doc_exception_text, text_file_last],
-                              queue=queue,
-                              api_name='add_url' if allow_upload_api else None)
-
-        eventdb2a = url_text.submit(fn=user_state_setup,
-                                    inputs=[my_db_state, requests_state, url_text, url_text],
-                                    outputs=[my_db_state, requests_state, url_text],
-                                    queue=queue,
-                                    show_progress='minimal')
-        # work around https://github.com/gradio-app/gradio/issues/4733
-        eventdb2 = eventdb2a.then(**add_url_kwargs, show_progress='full')
-
-        update_user_db_txt_func = functools.partial(update_db_func, is_txt=True)
-        add_text_outputs = [user_text_text, langchain_mode]
-        add_text_kwargs = dict(fn=update_user_db_txt_func,
-                               inputs=[user_text_text, my_db_state, selection_docs_state, requests_state,
-                                       langchain_mode, chunk, chunk_size, embed,
-                                       image_loaders,
-                                       pdf_loaders,
-                                       url_loaders,
-                                       jq_schema,
-                                       h2ogpt_key,
-                                       ],
-                               outputs=add_text_outputs + [sources_text, doc_exception_text, text_file_last],
-                               queue=queue,
-                               api_name='add_text' if allow_upload_api else None
-                               )
-        eventdb3a = user_text_text.submit(fn=user_state_setup,
-                                          inputs=[my_db_state, requests_state, user_text_text, user_text_text],
-                                          outputs=[my_db_state, requests_state, user_text_text],
-                                          queue=queue,
-                                          show_progress='minimal')
-        eventdb3 = eventdb3a.then(**add_text_kwargs, show_progress='full')
-
-        db_events = [eventdb1a, eventdb1, eventdb1_api,
-                     eventdb2a, eventdb2,
-                     eventdb3a, eventdb3]
-        db_events.extend([event_attach1, event_attach2])
-
-        get_sources1 = functools.partial(get_sources_gr, dbs=dbs, docs_state0=docs_state0,
-                                         load_db_if_exists=load_db_if_exists,
-                                         db_type=db_type,
-                                         use_openai_embedding=use_openai_embedding,
-                                         hf_embedding_model=hf_embedding_model,
-                                         migrate_embedding_model=migrate_embedding_model,
-                                         auto_migrate_db=auto_migrate_db,
-                                         verbose=verbose,
-                                         get_userid_auth=get_userid_auth,
-                                         n_jobs=n_jobs,
-                                         )
-
-        # if change collection source, must clear doc selections from it to avoid inconsistency
-        def clear_doc_choice(langchain_mode1):
-            if langchain_mode1 in langchain_modes_non_db:
-                label1 = 'Choose Resources->Collections and Pick Collection'
-                active_collection1 = "#### Not Chatting with Any Collection\n%s" % label1
-            else:
-                label1 = 'Select Subset of Document(s) for Chat with Collection: %s' % langchain_mode1
-                active_collection1 = "#### Chatting with Collection: %s" % langchain_mode1
-            return gr.Dropdown.update(choices=docs_state0, value=DocumentChoice.ALL.value,
-                                      label=label1), gr.Markdown.update(value=active_collection1)
-
-        lg_change_event = langchain_mode.change(clear_doc_choice, inputs=langchain_mode,
-                                                outputs=[document_choice, active_collection],
-                                                queue=not kwargs['large_file_count_mode'])
-
-        def change_visible_llama(x):
-            if x == 'llama':
-                return gr.update(visible=True), \
-                    gr.update(visible=True), \
-                    gr.update(visible=False), \
-                    gr.update(visible=False)
-            elif x in ['gptj', 'gpt4all_llama']:
-                return gr.update(visible=False), \
-                    gr.update(visible=False), \
-                    gr.update(visible=True), \
-                    gr.update(visible=True)
-            else:
-                return gr.update(visible=False), \
-                    gr.update(visible=False), \
-                    gr.update(visible=False), \
-                    gr.update(visible=False)
-
-        model_choice.change(change_visible_llama,
-                            inputs=model_choice,
-                            outputs=[row_llama, row_llama2, row_gpt4all, row_gpt4all2])
-
-        def resize_col_tabs(x):
-            return gr.Dropdown.update(scale=x)
-
-        col_tabs_scale.change(fn=resize_col_tabs, inputs=col_tabs_scale, outputs=col_tabs, queue=False)
-
-        def resize_chatbots(x, num_model_lock=0):
-            if num_model_lock == 0:
-                num_model_lock = 3  # 2 + 1 (which is dup of first)
-            else:
-                num_model_lock = 2 + num_model_lock
-            return tuple([gr.update(height=x)] * num_model_lock)
-
-        resize_chatbots_func = functools.partial(resize_chatbots, num_model_lock=len(text_outputs))
-        text_outputs_height.change(fn=resize_chatbots_func, inputs=text_outputs_height,
-                                   outputs=[text_output, text_output2] + text_outputs, queue=False)
-
-        def update_dropdown(x):
-            if DocumentChoice.ALL.value in x:
-                x.remove(DocumentChoice.ALL.value)
-            source_list = [DocumentChoice.ALL.value] + x
-            return gr.Dropdown.update(choices=source_list, value=[DocumentChoice.ALL.value])
-
-        get_sources_kwargs = dict(fn=get_sources1,
-                                  inputs=[my_db_state, selection_docs_state, requests_state, langchain_mode],
-                                  outputs=[file_source, docs_state, text_doc_count],
-                                  queue=queue)
-
-        eventdb7a = get_sources_btn.click(user_state_setup,
-                                          inputs=[my_db_state, requests_state, get_sources_btn, get_sources_btn],
-                                          outputs=[my_db_state, requests_state, get_sources_btn],
-                                          show_progress='minimal')
-        eventdb7 = eventdb7a.then(**get_sources_kwargs,
-                                  api_name='get_sources' if allow_api else None) \
-            .then(fn=update_dropdown, inputs=docs_state, outputs=document_choice)
-
-        get_sources_api_args = dict(fn=functools.partial(get_sources1, api=True),
-                                    inputs=[my_db_state, selection_docs_state, requests_state, langchain_mode],
-                                    outputs=get_sources_api_text,
-                                    queue=queue)
-        get_sources_api_btn.click(**get_sources_api_args,
-                                  api_name='get_sources_api' if allow_api else None)
-
-        # show button, else only show when add.
-        # Could add to above get_sources for download/dropdown, but bit much maybe
-        show_sources1 = functools.partial(get_source_files_given_langchain_mode_gr,
-                                          dbs=dbs,
-                                          load_db_if_exists=load_db_if_exists,
-                                          db_type=db_type,
-                                          use_openai_embedding=use_openai_embedding,
-                                          hf_embedding_model=hf_embedding_model,
-                                          migrate_embedding_model=migrate_embedding_model,
-                                          auto_migrate_db=auto_migrate_db,
-                                          verbose=verbose,
-                                          get_userid_auth=get_userid_auth,
-                                          n_jobs=n_jobs)
-        eventdb8a = show_sources_btn.click(user_state_setup,
-                                           inputs=[my_db_state, requests_state, show_sources_btn, show_sources_btn],
-                                           outputs=[my_db_state, requests_state, show_sources_btn],
-                                           show_progress='minimal')
-        show_sources_kwargs = dict(fn=show_sources1,
-                                   inputs=[my_db_state, selection_docs_state, requests_state, langchain_mode],
-                                   outputs=sources_text)
-        eventdb8 = eventdb8a.then(**show_sources_kwargs,
-                                  api_name='show_sources' if allow_api else None)
-
-        def update_viewable_dropdown(x):
-            return gr.Dropdown.update(choices=x,
-                                      value=viewable_docs_state0[0] if len(viewable_docs_state0) > 0 else None)
-
-        get_viewable_sources1 = functools.partial(get_sources_gr, dbs=dbs, docs_state0=viewable_docs_state0,
-                                                  load_db_if_exists=load_db_if_exists,
-                                                  db_type=db_type,
-                                                  use_openai_embedding=use_openai_embedding,
-                                                  hf_embedding_model=hf_embedding_model,
-                                                  migrate_embedding_model=migrate_embedding_model,
-                                                  auto_migrate_db=auto_migrate_db,
-                                                  verbose=kwargs['verbose'],
-                                                  get_userid_auth=get_userid_auth,
-                                                  n_jobs=n_jobs)
-        get_viewable_sources_args = dict(fn=get_viewable_sources1,
-                                         inputs=[my_db_state, selection_docs_state, requests_state, langchain_mode],
-                                         outputs=[file_source, viewable_docs_state, text_viewable_doc_count],
-                                         queue=queue)
-        eventdb12a = get_viewable_sources_btn.click(user_state_setup,
-                                                    inputs=[my_db_state, requests_state,
-                                                            get_viewable_sources_btn, get_viewable_sources_btn],
-                                                    outputs=[my_db_state, requests_state, get_viewable_sources_btn],
-                                                    show_progress='minimal')
-        viewable_kwargs = dict(fn=update_viewable_dropdown, inputs=viewable_docs_state, outputs=view_document_choice)
-        eventdb12 = eventdb12a.then(**get_viewable_sources_args,
-                                    api_name='get_viewable_sources' if allow_api else None) \
-            .then(**viewable_kwargs)
-
-        eventdb_viewa = view_document_choice.select(user_state_setup,
-                                                    inputs=[my_db_state, requests_state,
-                                                            view_document_choice, view_document_choice],
-                                                    outputs=[my_db_state, requests_state, view_document_choice],
-                                                    show_progress='minimal')
-        show_doc_func = functools.partial(show_doc,
-                                          dbs1=dbs,
-                                          load_db_if_exists1=load_db_if_exists,
-                                          db_type1=db_type,
-                                          use_openai_embedding1=use_openai_embedding,
-                                          hf_embedding_model1=hf_embedding_model,
-                                          migrate_embedding_model_or_db1=migrate_embedding_model,
-                                          auto_migrate_db1=auto_migrate_db,
-                                          verbose1=verbose,
-                                          get_userid_auth1=get_userid_auth,
-                                          max_raw_chunks=kwargs['max_raw_chunks'],
-                                          api=False,
-                                          n_jobs=n_jobs,
-                                          )
-        # Note: Not really useful for API, so no api_name
-        eventdb_viewa.then(fn=show_doc_func,
-                           inputs=[my_db_state, selection_docs_state, requests_state, langchain_mode,
-                                   view_document_choice, view_raw_text_checkbox,
-                                   text_context_list],
-                           outputs=[doc_view, doc_view2, doc_view3, doc_view4, doc_view5])
-
-        show_doc_func_api = functools.partial(show_doc_func, api=True)
-        get_document_api_btn.click(fn=show_doc_func_api,
-                                   inputs=[my_db_state, selection_docs_state, requests_state, langchain_mode,
-                                           view_document_choice, view_raw_text_checkbox,
-                                           text_context_list],
-                                   outputs=get_document_api_text, api_name='get_document_api')
-
-        # Get inputs to evaluate() and make_db()
-        # don't deepcopy, can contain model itself
-        all_kwargs = kwargs.copy()
-        all_kwargs.update(locals())
-
-        refresh_sources1 = functools.partial(update_and_get_source_files_given_langchain_mode_gr,
-                                             captions_model=captions_model,
-                                             caption_loader=caption_loader,
-                                             doctr_loader=doctr_loader,
-                                             dbs=dbs,
-                                             first_para=kwargs['first_para'],
-                                             hf_embedding_model=hf_embedding_model,
-                                             use_openai_embedding=use_openai_embedding,
-                                             migrate_embedding_model=migrate_embedding_model,
-                                             auto_migrate_db=auto_migrate_db,
-                                             text_limit=kwargs['text_limit'],
-                                             db_type=db_type,
-                                             load_db_if_exists=load_db_if_exists,
-                                             n_jobs=n_jobs, verbose=verbose,
-                                             get_userid_auth=get_userid_auth,
-                                             image_loaders_options0=image_loaders_options0,
-                                             pdf_loaders_options0=pdf_loaders_options0,
-                                             url_loaders_options0=url_loaders_options0,
-                                             jq_schema0=jq_schema0,
-                                             )
-        eventdb9a = refresh_sources_btn.click(user_state_setup,
-                                              inputs=[my_db_state, requests_state,
-                                                      refresh_sources_btn, refresh_sources_btn],
-                                              outputs=[my_db_state, requests_state, refresh_sources_btn],
-                                              show_progress='minimal')
-        eventdb9 = eventdb9a.then(fn=refresh_sources1,
-                                  inputs=[my_db_state, selection_docs_state, requests_state,
-                                          langchain_mode, chunk, chunk_size,
-                                          image_loaders,
-                                          pdf_loaders,
-                                          url_loaders,
-                                          jq_schema,
-                                          ],
-                                  outputs=sources_text,
-                                  api_name='refresh_sources' if allow_api else None)
-
-        delete_sources1 = functools.partial(del_source_files_given_langchain_mode_gr,
-                                            dbs=dbs,
-                                            load_db_if_exists=load_db_if_exists,
-                                            db_type=db_type,
-                                            use_openai_embedding=use_openai_embedding,
-                                            hf_embedding_model=hf_embedding_model,
-                                            migrate_embedding_model=migrate_embedding_model,
-                                            auto_migrate_db=auto_migrate_db,
-                                            verbose=verbose,
-                                            get_userid_auth=get_userid_auth,
-                                            n_jobs=n_jobs)
-        eventdb90a = delete_sources_btn.click(user_state_setup,
-                                              inputs=[my_db_state, requests_state,
-                                                      delete_sources_btn, delete_sources_btn],
-                                              outputs=[my_db_state, requests_state, delete_sources_btn],
-                                              show_progress='minimal')
-        eventdb90 = eventdb90a.then(fn=delete_sources1,
-                                    inputs=[my_db_state, selection_docs_state, requests_state, document_choice,
-                                            langchain_mode],
-                                    outputs=sources_text,
-                                    api_name='delete_sources' if allow_api else None)
-        db_events.extend([eventdb90a, eventdb90])
-
-        def check_admin_pass(x):
-            return gr.update(visible=x == admin_pass)
-
-        def close_admin(x):
-            return gr.update(visible=not (x == admin_pass))
-
-        eventdb_logina = login_btn.click(user_state_setup,
-                                         inputs=[my_db_state, requests_state, login_btn, login_btn],
-                                         outputs=[my_db_state, requests_state, login_btn],
-                                         show_progress='minimal')
-
-        def login(db1s, selection_docs_state1, requests_state1, chat_state1, langchain_mode1,
-                  username1, password1,
-                  text_output1, text_output21, *text_outputs1,
-                  auth_filename=None, num_model_lock=0, pre_authorized=False):
-            # use full auth login to allow new users if open access etc.
-            if pre_authorized:
-                username1 = requests_state1['username']
-                password1 = None
-                authorized1 = True
-            else:
-                authorized1 = authf(username1, password1, selection_docs_state1=selection_docs_state1)
-            if authorized1:
-                set_userid_gr(db1s, requests_state1, get_userid_auth)
-                username2 = get_username(requests_state1)
-                text_outputs1 = list(text_outputs1)
-
-                success1, text_result, text_output1, text_output21, text_outputs1, langchain_mode1 = \
-                    load_auth(db1s, requests_state1, auth_filename, selection_docs_state1=selection_docs_state1,
-                              chat_state1=chat_state1, langchain_mode1=langchain_mode1,
-                              text_output1=text_output1, text_output21=text_output21, text_outputs1=text_outputs1,
-                              username_override=username1, password_to_check=password1)
-            else:
-                success1 = False
-                text_result = "Wrong password for user %s" % username1
-            df_langchain_mode_paths1 = get_df_langchain_mode_paths(selection_docs_state1, db1s, dbs1=dbs)
-            if success1:
-                requests_state1['username'] = username1
-            label_instruction1 = 'Ask anything, %s' % requests_state1['username']
-            return db1s, selection_docs_state1, requests_state1, chat_state1, \
-                text_result, \
-                gr.update(label=label_instruction1), \
-                df_langchain_mode_paths1, \
-                gr.update(choices=list(chat_state1.keys()), value=None), \
-                gr.update(choices=get_langchain_choices(selection_docs_state1),
-                          value=langchain_mode1), \
-                text_output1, text_output21, *tuple(text_outputs1)
-
-        login_func = functools.partial(login,
-                                       auth_filename=kwargs['auth_filename'],
-                                       num_model_lock=len(text_outputs),
-                                       pre_authorized=False,
-                                       )
-        load_login_func = functools.partial(login,
-                                            auth_filename=kwargs['auth_filename'],
-                                            num_model_lock=len(text_outputs),
-                                            pre_authorized=True,
-                                            )
-        login_inputs = [my_db_state, selection_docs_state, requests_state, chat_state,
-                        langchain_mode,
-                        username_text, password_text,
-                        text_output, text_output2] + text_outputs
-        login_outputs = [my_db_state, selection_docs_state, requests_state, chat_state,
-                         login_result_text,
-                         instruction,
-                         langchain_mode_path_text,
-                         radio_chats,
-                         langchain_mode,
-                         text_output, text_output2] + text_outputs
-        eventdb_logina.then(login_func,
-                            inputs=login_inputs,
-                            outputs=login_outputs,
-                            queue=False)
-
-        admin_pass_textbox.submit(check_admin_pass, inputs=admin_pass_textbox, outputs=system_row, queue=False) \
-            .then(close_admin, inputs=admin_pass_textbox, outputs=admin_row, queue=False)
-
-        def load_auth(db1s, requests_state1, auth_filename=None, selection_docs_state1=None,
-                      chat_state1=None, langchain_mode1=None,
-                      text_output1=None, text_output21=None, text_outputs1=None,
-                      username_override=None, password_to_check=None):
-            # in-place assignment
-            if not auth_filename:
-                return False, "No auth file", text_output1, text_output21, text_outputs1
-            # if first time here, need to set userID
-            set_userid_gr(db1s, requests_state1, get_userid_auth)
-            if username_override:
-                username1 = username_override
-            else:
-                username1 = get_username(requests_state1)
-            success1 = False
-            with filelock.FileLock(auth_filename + '.lock'):
-                if os.path.isfile(auth_filename):
-                    with open(auth_filename, 'rt') as f:
-                        auth_dict = json.load(f)
-                        if username1 in auth_dict:
-                            auth_user = auth_dict[username1]
-                            if password_to_check:
-                                if auth_user['password'] != password_to_check:
-                                    return False, [], [], [], "Invalid password for user %s" % username1
-                            if username_override:
-                                # then use original user id
-                                set_userid_direct_gr(db1s, auth_dict[username1]['userid'], username1)
-                            if 'selection_docs_state' in auth_user:
-                                update_auth_selection(auth_user, selection_docs_state1)
-                            if 'chat_state' in auth_user:
-                                chat_state1.update(auth_user['chat_state'])
-                            if 'text_output' in auth_user:
-                                text_output1 = auth_user['text_output']
-                            if 'text_output2' in auth_user:
-                                text_output21 = auth_user['text_output2']
-                            if 'text_outputs' in auth_user:
-                                text_outputs1 = auth_user['text_outputs']
-                            if 'langchain_mode' in auth_user:
-                                langchain_mode1 = auth_user['langchain_mode']
-                            text_result = "Successful login for %s" % username1
-                            success1 = True
-                        else:
-                            text_result = "No user %s" % username1
-                else:
-                    text_result = "No auth file"
-            return success1, text_result, text_output1, text_output21, text_outputs1, langchain_mode1
-
-        def save_auth_dict(auth_dict, auth_filename):
-            backup_file = auth_filename + '.bak' + str(uuid.uuid4())
-            if os.path.isfile(auth_filename):
-                shutil.copy(auth_filename, backup_file)
-            try:
-                with open(auth_filename, 'wt') as f:
-                    f.write(json.dumps(auth_dict, indent=2))
-            except BaseException as e:
-                print("Failure to save auth %s, restored backup: %s: %s" % (auth_filename, backup_file, str(e)),
-                      flush=True)
-                shutil.copy(backup_file, auth_dict)
-                if os.getenv('HARD_ASSERTS'):
-                    # unexpected in testing or normally
-                    raise
-
-        def save_auth(requests_state1, auth_filename, auth_freeze,
-                      selection_docs_state1=None, chat_state1=None, langchain_mode1=None,
-                      text_output1=None, text_output21=None, text_outputs1=None):
-            if auth_freeze:
-                return
-            if not auth_filename:
-                return
-            # save to auth file
-            username1 = get_username(requests_state1)
-            with filelock.FileLock(auth_filename + '.lock'):
-                if os.path.isfile(auth_filename):
-                    with open(auth_filename, 'rt') as f:
-                        auth_dict = json.load(f)
-                    if username1 in auth_dict:
-                        auth_user = auth_dict[username1]
-                        if selection_docs_state1:
-                            update_auth_selection(auth_user, selection_docs_state1, save=True)
-                        if chat_state1:
-                            # overwrite
-                            auth_user['chat_state'] = chat_state1
-                        if text_output1:
-                            auth_user['text_output'] = text_output1
-                        if text_output21:
-                            auth_user['text_output2'] = text_output21
-                        if text_outputs1:
-                            auth_user['text_outputs'] = text_outputs1
-                        if langchain_mode1:
-                            auth_user['langchain_mode'] = langchain_mode1
-                        save_auth_dict(auth_dict, auth_filename)
-
-        def add_langchain_mode(db1s, selection_docs_state1, requests_state1, langchain_mode1, y,
-                               auth_filename=None, auth_freeze=None, guest_name=None):
-            assert auth_filename is not None
-            assert auth_freeze is not None
-
-            set_userid_gr(db1s, requests_state1, get_userid_auth)
-            username1 = get_username(requests_state1)
-            for k in db1s:
-                set_dbid_gr(db1s[k])
-            langchain_modes = selection_docs_state1['langchain_modes']
-            langchain_mode_paths = selection_docs_state1['langchain_mode_paths']
-            langchain_mode_types = selection_docs_state1['langchain_mode_types']
-
-            user_path = None
-            valid = True
-            y2 = y.strip().replace(' ', '').split(',')
-            if len(y2) >= 1:
-                langchain_mode2 = y2[0]
-                if len(langchain_mode2) >= 3 and langchain_mode2.isalnum():
-                    # real restriction is:
-                    # ValueError: Expected collection name that (1) contains 3-63 characters, (2) starts and ends with an alphanumeric character, (3) otherwise contains only alphanumeric characters, underscores or hyphens (-), (4) contains no two consecutive periods (..) and (5) is not a valid IPv4 address, got me
-                    # but just make simpler
-                    # assume personal if don't have user_path
-                    langchain_mode_type = y2[1] if len(y2) > 1 else LangChainTypes.PERSONAL.value
-                    user_path = y2[2] if len(y2) > 2 else None  # assume None if don't have user_path
-                    if user_path in ['', "''"]:
-                        # transcribe UI input
-                        user_path = None
-                    if langchain_mode_type not in [x.value for x in list(LangChainTypes)]:
-                        textbox = "Invalid type %s" % langchain_mode_type
-                        valid = False
-                        langchain_mode2 = langchain_mode1
-                    elif langchain_mode_type == LangChainTypes.SHARED.value and username1 == guest_name:
-                        textbox = "Guests cannot add shared collections"
-                        valid = False
-                        langchain_mode2 = langchain_mode1
-                    elif user_path is not None and langchain_mode_type == LangChainTypes.PERSONAL.value:
-                        textbox = "Do not pass user_path for personal/scratch types"
-                        valid = False
-                        langchain_mode2 = langchain_mode1
-                    elif user_path is not None and username1 == guest_name:
-                        textbox = "Guests cannot add collections with path"
-                        valid = False
-                        langchain_mode2 = langchain_mode1
-                    elif langchain_mode2 in langchain_modes_intrinsic:
-                        user_path = None
-                        textbox = "Invalid access to use internal name: %s" % langchain_mode2
-                        valid = False
-                        langchain_mode2 = langchain_mode1
-                    elif user_path and allow_upload_to_user_data or not user_path and allow_upload_to_my_data:
-                        if user_path:
-                            user_path = makedirs(user_path, exist_ok=True, use_base=True)
-                        langchain_mode_paths.update({langchain_mode2: user_path})
-                        langchain_mode_types.update({langchain_mode2: langchain_mode_type})
-                        if langchain_mode2 not in langchain_modes:
-                            langchain_modes.append(langchain_mode2)
-                        textbox = ''
-                    else:
-                        valid = False
-                        langchain_mode2 = langchain_mode1
-                        textbox = "Invalid access.  user allowed: %s " \
-                                  "personal/scratch allowed: %s" % (allow_upload_to_user_data, allow_upload_to_my_data)
-                else:
-                    valid = False
-                    langchain_mode2 = langchain_mode1
-                    textbox = "Invalid, collection must be >=3 characters and alphanumeric"
-            else:
-                valid = False
-                langchain_mode2 = langchain_mode1
-                textbox = "Invalid, must be like UserData2, user_path2"
-            selection_docs_state1 = update_langchain_mode_paths(selection_docs_state1)
-            df_langchain_mode_paths1 = get_df_langchain_mode_paths(selection_docs_state1, db1s, dbs1=dbs)
-            choices = get_langchain_choices(selection_docs_state1)
-
-            if valid and not user_path:
-                # needs to have key for it to make it known different from userdata case in _update_user_db()
-                from src.gpt_langchain import length_db1
-                db1s[langchain_mode2] = [None] * length_db1()
-            if valid:
-                save_auth(requests_state1, auth_filename, auth_freeze, selection_docs_state1=selection_docs_state1,
-                          langchain_mode1=langchain_mode2)
-
-            return db1s, selection_docs_state1, gr.update(choices=choices,
-                                                          value=langchain_mode2), textbox, df_langchain_mode_paths1
-
-        def remove_langchain_mode(db1s, selection_docs_state1, requests_state1,
-                                  langchain_mode1, langchain_mode2, dbsu=None, auth_filename=None, auth_freeze=None,
-                                  guest_name=None,
-                                  purge=False):
-            assert auth_filename is not None
-            assert auth_freeze is not None
-
-            set_userid_gr(db1s, requests_state1, get_userid_auth)
-            for k in db1s:
-                set_dbid_gr(db1s[k])
-            assert dbsu is not None
-            langchain_modes = selection_docs_state1['langchain_modes']
-            langchain_mode_paths = selection_docs_state1['langchain_mode_paths']
-            langchain_mode_types = selection_docs_state1['langchain_mode_types']
-            langchain_type2 = langchain_mode_types.get(langchain_mode2, LangChainTypes.EITHER.value)
-
-            changed_state = False
-            textbox = "Invalid access, cannot remove %s" % langchain_mode2
-            in_scratch_db = langchain_mode2 in db1s
-            in_user_db = dbsu is not None and langchain_mode2 in dbsu
-            if in_scratch_db and not allow_upload_to_my_data or \
-                    in_user_db and not allow_upload_to_user_data or \
-                    langchain_mode2 in langchain_modes_intrinsic:
-                can_remove = False
-                can_purge = False
-                if langchain_mode2 in langchain_modes_intrinsic:
-                    can_purge = True
-            else:
-                can_remove = True
-                can_purge = True
-
-            # change global variables
-            if langchain_mode2 in langchain_modes or langchain_mode2 in langchain_mode_paths or langchain_mode2 in db1s:
-                if can_purge and purge:
-                    # remove source files
-                    from src.gpt_langchain import get_sources, del_from_db
-                    sources_file, source_list, num_chunks, db = \
-                        get_sources(db1s, selection_docs_state1,
-                                    requests_state1, langchain_mode2, dbs=dbsu,
-                                    docs_state0=docs_state0,
-                                    load_db_if_exists=load_db_if_exists,
-                                    db_type=db_type,
-                                    use_openai_embedding=use_openai_embedding,
-                                    hf_embedding_model=hf_embedding_model,
-                                    migrate_embedding_model=migrate_embedding_model,
-                                    auto_migrate_db=auto_migrate_db,
-                                    verbose=verbose,
-                                    get_userid_auth=get_userid_auth,
-                                    n_jobs=n_jobs)
-                    del_from_db(db, source_list, db_type=db_type)
-                    for fil in source_list:
-                        if os.path.isfile(fil):
-                            print("Purged %s" % fil, flush=True)
-                            remove(fil)
-                    # remove db directory
-                    from src.gpt_langchain import get_persist_directory
-                    persist_directory, langchain_type2 = \
-                        get_persist_directory(langchain_mode2, langchain_type=langchain_type2,
-                                              db1s=db1s, dbs=dbsu)
-                    print("removed persist_directory %s" % persist_directory, flush=True)
-                    remove(persist_directory)
-                    textbox = "Purged, but did not remove %s" % langchain_mode2
-                if can_remove:
-                    if langchain_mode2 in langchain_modes:
-                        langchain_modes.remove(langchain_mode2)
-                    if langchain_mode2 in langchain_mode_paths:
-                        langchain_mode_paths.pop(langchain_mode2)
-                    if langchain_mode2 in langchain_mode_types:
-                        langchain_mode_types.pop(langchain_mode2)
-                    if langchain_mode2 in db1s and langchain_mode2 != LangChainMode.MY_DATA.value:
-                        # don't remove last MyData, used as user hash
-                        db1s.pop(langchain_mode2)
-                    textbox = ""
-                    changed_state = True
-            else:
-                textbox = "%s is not visible" % langchain_mode2
-
-            # update
-            selection_docs_state1 = update_langchain_mode_paths(selection_docs_state1)
-            df_langchain_mode_paths1 = get_df_langchain_mode_paths(selection_docs_state1, db1s, dbs1=dbs)
-
-            if changed_state:
-                save_auth(requests_state1, auth_filename, auth_freeze, selection_docs_state1=selection_docs_state1,
-                          langchain_mode1=langchain_mode2)
-
-            return db1s, selection_docs_state1, \
-                gr.update(choices=get_langchain_choices(selection_docs_state1),
-                          value=langchain_mode2), textbox, df_langchain_mode_paths1
-
-        eventdb20a = new_langchain_mode_text.submit(user_state_setup,
-                                                    inputs=[my_db_state, requests_state,
-                                                            new_langchain_mode_text, new_langchain_mode_text],
-                                                    outputs=[my_db_state, requests_state, new_langchain_mode_text],
-                                                    show_progress='minimal')
-        add_langchain_mode_func = functools.partial(add_langchain_mode,
-                                                    auth_filename=kwargs['auth_filename'],
-                                                    auth_freeze=kwargs['auth_freeze'],
-                                                    guest_name=kwargs['guest_name'],
-                                                    )
-        eventdb20b = eventdb20a.then(fn=add_langchain_mode_func,
-                                     inputs=[my_db_state, selection_docs_state, requests_state,
-                                             langchain_mode,
-                                             new_langchain_mode_text],
-                                     outputs=[my_db_state, selection_docs_state, langchain_mode,
-                                              new_langchain_mode_text,
-                                              langchain_mode_path_text],
-                                     api_name='new_langchain_mode_text' if allow_api and allow_upload_to_user_data else None)
-        db_events.extend([eventdb20a, eventdb20b])
-
-        remove_langchain_mode_func = functools.partial(remove_langchain_mode,
-                                                       dbsu=dbs,
-                                                       auth_filename=kwargs['auth_filename'],
-                                                       auth_freeze=kwargs['auth_freeze'],
-                                                       guest_name=kwargs['guest_name'],
-                                                       )
-        eventdb21a = remove_langchain_mode_text.submit(user_state_setup,
-                                                       inputs=[my_db_state,
-                                                               requests_state,
-                                                               remove_langchain_mode_text, remove_langchain_mode_text],
-                                                       outputs=[my_db_state,
-                                                                requests_state, remove_langchain_mode_text],
-                                                       show_progress='minimal')
-        remove_langchain_mode_kwargs = dict(fn=remove_langchain_mode_func,
-                                            inputs=[my_db_state, selection_docs_state, requests_state,
-                                                    langchain_mode,
-                                                    remove_langchain_mode_text],
-                                            outputs=[my_db_state, selection_docs_state, langchain_mode,
-                                                     remove_langchain_mode_text,
-                                                     langchain_mode_path_text])
-        eventdb21b = eventdb21a.then(**remove_langchain_mode_kwargs,
-                                     api_name='remove_langchain_mode_text' if allow_api and allow_upload_to_user_data else None)
-        db_events.extend([eventdb21a, eventdb21b])
-
-        eventdb22a = purge_langchain_mode_text.submit(user_state_setup,
-                                                      inputs=[my_db_state,
-                                                              requests_state,
-                                                              purge_langchain_mode_text, purge_langchain_mode_text],
-                                                      outputs=[my_db_state,
-                                                               requests_state, purge_langchain_mode_text],
-                                                      show_progress='minimal')
-        purge_langchain_mode_func = functools.partial(remove_langchain_mode_func, purge=True)
-        purge_langchain_mode_kwargs = dict(fn=purge_langchain_mode_func,
-                                           inputs=[my_db_state, selection_docs_state, requests_state,
-                                                   langchain_mode,
-                                                   purge_langchain_mode_text],
-                                           outputs=[my_db_state, selection_docs_state, langchain_mode,
-                                                    purge_langchain_mode_text,
-                                                    langchain_mode_path_text])
-        # purge_langchain_mode_kwargs = remove_langchain_mode_kwargs.copy()
-        # purge_langchain_mode_kwargs['fn'] = functools.partial(remove_langchain_mode_kwargs['fn'], purge=True)
-        eventdb22b = eventdb22a.then(**purge_langchain_mode_kwargs,
-                                     api_name='purge_langchain_mode_text' if allow_api and allow_upload_to_user_data else None)
-        db_events.extend([eventdb22a, eventdb22b])
-
-        def load_langchain_gr(db1s, selection_docs_state1, requests_state1, langchain_mode1, auth_filename=None):
-            load_auth(db1s, requests_state1, auth_filename, selection_docs_state1=selection_docs_state1)
-
-            selection_docs_state1 = update_langchain_mode_paths(selection_docs_state1)
-            df_langchain_mode_paths1 = get_df_langchain_mode_paths(selection_docs_state1, db1s, dbs1=dbs)
-            return selection_docs_state1, \
-                gr.update(choices=get_langchain_choices(selection_docs_state1),
-                          value=langchain_mode1), df_langchain_mode_paths1
-
-        eventdbloadla = load_langchain.click(user_state_setup,
-                                             inputs=[my_db_state, requests_state, langchain_mode],
-                                             outputs=[my_db_state, requests_state, langchain_mode],
-                                             show_progress='minimal')
-        load_langchain_gr_func = functools.partial(load_langchain_gr,
-                                                   auth_filename=kwargs['auth_filename'])
-        eventdbloadlb = eventdbloadla.then(fn=load_langchain_gr_func,
-                                           inputs=[my_db_state, selection_docs_state, requests_state, langchain_mode],
-                                           outputs=[selection_docs_state, langchain_mode, langchain_mode_path_text],
-                                           api_name='load_langchain' if allow_api and allow_upload_to_user_data else None)
-
-        if not kwargs['large_file_count_mode']:
-            # FIXME: Could add all these functions, inputs, outputs into single function for snappier GUI
-            # all update events when not doing large file count mode
-            # Note: Login touches langchain_mode, which triggers all these
-            lg_change_event2 = lg_change_event.then(**get_sources_kwargs)
-            lg_change_event3 = lg_change_event2.then(fn=update_dropdown, inputs=docs_state, outputs=document_choice)
-            lg_change_event4 = lg_change_event3.then(**show_sources_kwargs)
-            lg_change_event5 = lg_change_event4.then(**get_viewable_sources_args)
-            lg_change_event6 = lg_change_event5.then(**viewable_kwargs)
-
-            eventdb2c = eventdb2.then(**get_sources_kwargs)
-            eventdb2d = eventdb2c.then(fn=update_dropdown, inputs=docs_state, outputs=document_choice)
-            eventdb2e = eventdb2d.then(**show_sources_kwargs)
-            eventdb2f = eventdb2e.then(**get_viewable_sources_args)
-            eventdb2g = eventdb2f.then(**viewable_kwargs)
-
-            eventdb1c = eventdb1.then(**get_sources_kwargs)
-            eventdb1d = eventdb1c.then(fn=update_dropdown, inputs=docs_state, outputs=document_choice)
-            eventdb1e = eventdb1d.then(**show_sources_kwargs)
-            eventdb1f = eventdb1e.then(**get_viewable_sources_args)
-            eventdb1g = eventdb1f.then(**viewable_kwargs)
-
-            eventdb3c = eventdb3.then(**get_sources_kwargs)
-            eventdb3d = eventdb3c.then(fn=update_dropdown, inputs=docs_state, outputs=document_choice)
-            eventdb3e = eventdb3d.then(**show_sources_kwargs)
-            eventdb3f = eventdb3e.then(**get_viewable_sources_args)
-            eventdb3g = eventdb3f.then(**viewable_kwargs)
-
-            eventdb90ua = eventdb90.then(**get_sources_kwargs)
-            eventdb90ub = eventdb90ua.then(fn=update_dropdown, inputs=docs_state, outputs=document_choice)
-            eventdb90uc = eventdb90ub.then(**show_sources_kwargs)
-            eventdb90ud = eventdb90uc.then(**get_viewable_sources_args)
-            eventdb90ue = eventdb90ud.then(**viewable_kwargs)
-
-            eventdb20c = eventdb20b.then(**get_sources_kwargs)
-            eventdb20d = eventdb20c.then(fn=update_dropdown, inputs=docs_state, outputs=document_choice)
-            eventdb20e = eventdb20d.then(**show_sources_kwargs)
-            eventdb20f = eventdb20e.then(**get_viewable_sources_args)
-            eventdb20g = eventdb20f.then(**viewable_kwargs)
-
-            eventdb21c = eventdb21b.then(**get_sources_kwargs)
-            eventdb21d = eventdb21c.then(fn=update_dropdown, inputs=docs_state, outputs=document_choice)
-            eventdb21e = eventdb21d.then(**show_sources_kwargs)
-            eventdb21f = eventdb21e.then(**get_viewable_sources_args)
-            eventdb21g = eventdb21f.then(**viewable_kwargs)
-
-            eventdb22c = eventdb22b.then(**get_sources_kwargs)
-            eventdb22d = eventdb22c.then(fn=update_dropdown, inputs=docs_state, outputs=document_choice)
-            eventdb22e = eventdb22d.then(**show_sources_kwargs)
-            eventdb22f = eventdb22e.then(**get_viewable_sources_args)
-            eventdb22g = eventdb22f.then(**viewable_kwargs)
-
-            event_attach3 = event_attach2.then(**get_sources_kwargs)
-            event_attach4 = event_attach3.then(fn=update_dropdown, inputs=docs_state, outputs=document_choice)
-            event_attach5 = event_attach4.then(**show_sources_kwargs)
-            event_attach6 = event_attach5.then(**get_viewable_sources_args)
-            event_attach7 = event_attach6.then(**viewable_kwargs)
-
-            sync2 = sync1.then(**get_sources_kwargs)
-            sync3 = sync2.then(fn=update_dropdown, inputs=docs_state, outputs=document_choice)
-            sync4 = sync3.then(**show_sources_kwargs)
-            sync5 = sync4.then(**get_viewable_sources_args)
-            sync6 = sync5.then(**viewable_kwargs)
-
-            eventdb_loginb = eventdb_logina.then(**get_sources_kwargs)
-            eventdb_loginc = eventdb_loginb.then(fn=update_dropdown, inputs=docs_state, outputs=document_choice)
-            eventdb_logind = eventdb_loginc.then(**show_sources_kwargs)
-            eventdb_logine = eventdb_logind.then(**get_viewable_sources_args)
-            eventdb_loginf = eventdb_logine.then(**viewable_kwargs)
-
-            db_events.extend([lg_change_event, lg_change_event2, lg_change_event3, lg_change_event4, lg_change_event5,
-                              lg_change_event6] +
-                             [eventdb2c, eventdb2d, eventdb2e, eventdb2f, eventdb2g] +
-                             [eventdb1c, eventdb1d, eventdb1e, eventdb1f, eventdb1g] +
-                             [eventdb3c, eventdb3d, eventdb3e, eventdb3f, eventdb3g] +
-                             [eventdb90ua, eventdb90ub, eventdb90uc, eventdb90ud, eventdb90ue] +
-                             [eventdb20c, eventdb20d, eventdb20e, eventdb20f, eventdb20g] +
-                             [eventdb21c, eventdb21d, eventdb21e, eventdb21f, eventdb21g] +
-                             [eventdb22c, eventdb22d, eventdb22e, eventdb22f, eventdb22g] +
-                             [event_attach3, event_attach4, event_attach5, event_attach6, event_attach7] +
-                             [sync1, sync2, sync3, sync4, sync5, sync6] +
-                             [eventdb_logina, eventdb_loginb, eventdb_loginc, eventdb_logind, eventdb_logine,
-                              eventdb_loginf]
-                             ,
-                             )
-
-        inputs_list, inputs_dict = get_inputs_list(all_kwargs, kwargs['model_lower'], model_id=1)
-        inputs_list2, inputs_dict2 = get_inputs_list(all_kwargs, kwargs['model_lower'], model_id=2)
-        from functools import partial
-        kwargs_evaluate = {k: v for k, v in all_kwargs.items() if k in inputs_kwargs_list}
-        # ensure present
-        for k in inputs_kwargs_list:
-            assert k in kwargs_evaluate, "Missing %s" % k
-
-        def evaluate_nochat(*args1, default_kwargs1=None, str_api=False, plain_api=False, **kwargs1):
-            args_list = list(args1)
-            if str_api:
-                if plain_api:
-                    # i.e. not fresh model, tells evaluate to use model_state0
-                    args_list.insert(0, kwargs['model_state_none'].copy())
-                    args_list.insert(1, my_db_state0.copy())
-                    args_list.insert(2, selection_docs_state0.copy())
-                    args_list.insert(3, requests_state0.copy())
-                user_kwargs = args_list[len(input_args_list)]
-                assert isinstance(user_kwargs, str)
-                user_kwargs = ast.literal_eval(user_kwargs)
-            else:
-                assert not plain_api
-                user_kwargs = {k: v for k, v in zip(eval_func_param_names, args_list[len(input_args_list):])}
-            # control kwargs1 for evaluate
-            kwargs1['answer_with_sources'] = -1  # just text chunk, not URL etc.
-            kwargs1['show_accordions'] = False
-            kwargs1['append_sources_to_answer'] = False
-            kwargs1['show_link_in_sources'] = False
-            kwargs1['top_k_docs_max_show'] = 30
-
-            # only used for submit_nochat_api
-            user_kwargs['chat'] = False
-            if 'stream_output' not in user_kwargs:
-                user_kwargs['stream_output'] = False
-            if plain_api:
-                user_kwargs['stream_output'] = False
-            if 'langchain_mode' not in user_kwargs:
-                # if user doesn't specify, then assume disabled, not use default
-                if LangChainMode.LLM.value in kwargs['langchain_modes']:
-                    user_kwargs['langchain_mode'] = LangChainMode.LLM.value
-                elif len(kwargs['langchain_modes']) >= 1:
-                    user_kwargs['langchain_mode'] = kwargs['langchain_modes'][0]
-                else:
-                    # disabled should always be allowed
-                    user_kwargs['langchain_mode'] = LangChainMode.DISABLED.value
-            if 'langchain_action' not in user_kwargs:
-                user_kwargs['langchain_action'] = LangChainAction.QUERY.value
-            if 'langchain_agents' not in user_kwargs:
-                user_kwargs['langchain_agents'] = []
-            # be flexible
-            if 'instruction' in user_kwargs and 'instruction_nochat' not in user_kwargs:
-                user_kwargs['instruction_nochat'] = user_kwargs['instruction']
-            if 'iinput' in user_kwargs and 'iinput_nochat' not in user_kwargs:
-                user_kwargs['iinput_nochat'] = user_kwargs['iinput']
-            if 'visible_models' not in user_kwargs:
-                if kwargs['visible_models']:
-                    if isinstance(kwargs['visible_models'], int):
-                        user_kwargs['visible_models'] = [kwargs['visible_models']]
-                    elif isinstance(kwargs['visible_models'], list):
-                        # only take first one
-                        user_kwargs['visible_models'] = [kwargs['visible_models'][0]]
-                    else:
-                        user_kwargs['visible_models'] = [0]
-                else:
-                    # if no user version or default version, then just take first
-                    user_kwargs['visible_models'] = [0]
-
-            if 'h2ogpt_key' not in user_kwargs:
-                user_kwargs['h2ogpt_key'] = None
-            if 'system_prompt' in user_kwargs and user_kwargs['system_prompt'] is None:
-                # avoid worrying about below default_kwargs -> args_list that checks if None
-                user_kwargs['system_prompt'] = 'None'
-
-            set1 = set(list(default_kwargs1.keys()))
-            set2 = set(eval_func_param_names)
-            assert set1 == set2, "Set diff: %s %s: %s" % (set1, set2, set1.symmetric_difference(set2))
-            # correct ordering.  Note some things may not be in default_kwargs, so can't be default of user_kwargs.get()
-            model_state1 = args_list[0]
-            my_db_state1 = args_list[1]
-            selection_docs_state1 = args_list[2]
-            requests_state1 = args_list[3]
-            args_list = [user_kwargs[k] if k in user_kwargs and user_kwargs[k] is not None else default_kwargs1[k] for k
-                         in eval_func_param_names]
-            assert len(args_list) == len(eval_func_param_names)
-            stream_output1 = args_list[eval_func_param_names.index('stream_output')]
-            if len(model_states) > 1:
-                visible_models1 = args_list[eval_func_param_names.index('visible_models')]
-                model_active_choice1 = visible_models_to_model_choice(visible_models1)
-                model_state1 = model_states[model_active_choice1 % len(model_states)]
-                for key in key_overrides:
-                    if user_kwargs.get(key) is None and model_state1.get(key) is not None:
-                        args_list[eval_func_param_names.index(key)] = model_state1[key]
-                if hasattr(model_state1['tokenizer'], 'model_max_length'):
-                    # ensure listen to limit, with some buffer
-                    # buffer = 50
-                    buffer = 0
-                    args_list[eval_func_param_names.index('max_new_tokens')] = min(
-                        args_list[eval_func_param_names.index('max_new_tokens')],
-                        model_state1['tokenizer'].model_max_length - buffer)
-
-            # override overall visible_models and h2ogpt_key if have model_specific one
-            # NOTE: only applicable if len(model_states) > 1 at moment
-            # else controlled by evaluate()
-            if 'visible_models' in model_state1 and model_state1['visible_models'] is not None:
-                assert isinstance(model_state1['visible_models'], int)
-                args_list[eval_func_param_names.index('visible_models')] = model_state1['visible_models']
-            if 'h2ogpt_key' in model_state1 and model_state1['h2ogpt_key'] is not None:
-                # remote server key if present
-                # i.e. may be '' and used to override overall local key
-                assert isinstance(model_state1['h2ogpt_key'], str)
-                args_list[eval_func_param_names.index('h2ogpt_key')] = model_state1['h2ogpt_key']
-
-            # local key, not for remote server unless same, will be passed through
-            h2ogpt_key1 = args_list[eval_func_param_names.index('h2ogpt_key')]
-
-            # final full evaluate args list
-            args_list = [model_state1, my_db_state1, selection_docs_state1, requests_state1] + args_list
-
-            # NOTE: Don't allow UI-like access, in case modify state via API
-            valid_key = is_valid_key(kwargs['enforce_h2ogpt_api_key'], kwargs['h2ogpt_api_keys'], h2ogpt_key1,
-                                     requests_state1=None)
-            evaluate_local = evaluate if valid_key else evaluate_fake
-
-            save_dict = dict()
-            ret = {}
-            try:
-                for res_dict in evaluate_local(*tuple(args_list), **kwargs1):
-                    error = res_dict.get('error', '')
-                    extra = res_dict.get('extra', '')
-                    save_dict = res_dict.get('save_dict', {})
-
-                    # update save_dict
-                    save_dict['error'] = error
-                    save_dict['extra'] = extra
-                    save_dict['valid_key'] = valid_key
-                    save_dict['h2ogpt_key'] = h2ogpt_key1
-                    if str_api and plain_api:
-                        save_dict['which_api'] = 'str_plain_api'
-                    elif str_api:
-                        save_dict['which_api'] = 'str_api'
-                    elif plain_api:
-                        save_dict['which_api'] = 'plain_api'
-                    else:
-                        save_dict['which_api'] = 'nochat_api'
-                    if 'extra_dict' not in save_dict:
-                        save_dict['extra_dict'] = {}
-                    if requests_state1:
-                        save_dict['extra_dict'].update(requests_state1)
-                    else:
-                        save_dict['extra_dict'].update(dict(username='NO_REQUEST'))
-
-                    if is_public:
-                        # don't want to share actual endpoints
-                        if 'save_dict' in res_dict and isinstance(res_dict['save_dict'], dict):
-                            res_dict['save_dict'].pop('inference_server', None)
-                            if 'extra_dict' in res_dict['save_dict'] and isinstance(res_dict['save_dict']['extra_dict'],
-                                                                                    dict):
-                                res_dict['save_dict']['extra_dict'].pop('inference_server', None)
-
-                    # get response
-                    if str_api:
-                        # full return of dict
-                        ret = res_dict
-                    elif kwargs['langchain_mode'] == 'Disabled':
-                        ret = fix_text_for_gradio(res_dict['response'])
-                    else:
-                        ret = '<br>' + fix_text_for_gradio(res_dict['response'])
-                    if stream_output1:
-                        # yield as it goes, else need to wait since predict only returns first yield
-                        yield ret
-            finally:
-                clear_torch_cache()
-                clear_embeddings(user_kwargs['langchain_mode'], my_db_state1)
-            save_generate_output(**save_dict)
-            if not stream_output1:
-                # return back last ret
-                yield ret
-
-        kwargs_evaluate_nochat = kwargs_evaluate.copy()
-        # nominally never want sources appended for API calls, which is what nochat used for primarily
-        kwargs_evaluate_nochat.update(dict(append_sources_to_answer=False))
-        fun = partial(evaluate_nochat,
-                      default_kwargs1=default_kwargs,
-                      str_api=False,
-                      **kwargs_evaluate_nochat)
-        fun_with_dict_str = partial(evaluate_nochat,
-                                    default_kwargs1=default_kwargs,
-                                    str_api=True,
-                                    **kwargs_evaluate_nochat
-                                    )
-
-        fun_with_dict_str_plain = partial(evaluate_nochat,
-                                          default_kwargs1=default_kwargs,
-                                          str_api=True,
-                                          plain_api=True,
-                                          **kwargs_evaluate_nochat
-                                          )
-
-        dark_mode_btn.click(
-            None,
-            None,
-            None,
-            _js=wrap_js_to_lambda(0, get_dark_js()),
-            api_name="dark" if allow_api else None,
-            queue=False,
-        )
-
-        # Handle uploads from API
-        upload_api_btn = gr.UploadButton("Upload File Results", visible=False)
-        file_upload_api = gr.File(visible=False)
-        file_upload_text = gr.Textbox(visible=False)
-
-        def upload_file(files):
-            if isinstance(files, list):
-                file_paths = [file.name for file in files]
-            else:
-                file_paths = files.name
-            return file_paths, file_paths
-
-        upload_api_btn.upload(fn=upload_file,
-                              inputs=upload_api_btn,
-                              outputs=[file_upload_api, file_upload_text],
-                              api_name='upload_api' if allow_upload_api else None)
-
-        def visible_toggle(x):
-            x = 'off' if x == 'on' else 'on'
-            return x, gr.Column.update(visible=True if x == 'on' else False)
-
-        side_bar_btn.click(fn=visible_toggle,
-                           inputs=side_bar_text,
-                           outputs=[side_bar_text, side_bar],
-                           queue=False)
-
-        doc_count_btn.click(fn=visible_toggle,
-                            inputs=doc_count_text,
-                            outputs=[doc_count_text, row_doc_track],
-                            queue=False)
-
-        submit_buttons_btn.click(fn=visible_toggle,
-                                 inputs=submit_buttons_text,
-                                 outputs=[submit_buttons_text, submit_buttons],
-                                 queue=False)
-
-        visible_model_btn.click(fn=visible_toggle,
-                                inputs=visible_models_text,
-                                outputs=[visible_models_text, visible_models],
-                                queue=False)
-
-        # examples after submit or any other buttons for chat or no chat
-        if kwargs['examples'] is not None and kwargs['show_examples']:
-            gr.Examples(examples=kwargs['examples'], inputs=inputs_list)
-
-        # Score
-        def score_last_response(*args, nochat=False, num_model_lock=0):
-            try:
-                if num_model_lock > 0:
-                    # then lock way
-                    args_list = list(args).copy()
-                    outputs = args_list[-num_model_lock:]
-                    score_texts1 = []
-                    for output in outputs:
-                        # same input, put into form good for _score_last_response()
-                        args_list[-1] = output
-                        score_texts1.append(
-                            _score_last_response(*tuple(args_list), nochat=nochat,
-                                                 num_model_lock=num_model_lock, prefix=''))
-                    if len(score_texts1) > 1:
-                        return "Response Scores: %s" % ' '.join(score_texts1)
-                    else:
-                        return "Response Scores: %s" % score_texts1[0]
-                else:
-                    return _score_last_response(*args, nochat=nochat, num_model_lock=num_model_lock)
-            finally:
-                clear_torch_cache()
-
-        def _score_last_response(*args, nochat=False, num_model_lock=0, prefix='Response Score: '):
-            """ Similar to user() """
-            args_list = list(args)
-            smodel = score_model_state0['model']
-            stokenizer = score_model_state0['tokenizer']
-            sdevice = score_model_state0['device']
-
-            if memory_restriction_level > 0:
-                max_length_tokenize = 768 - 256 if memory_restriction_level <= 2 else 512 - 256
-            elif hasattr(stokenizer, 'model_max_length'):
-                max_length_tokenize = stokenizer.model_max_length
-            else:
-                # limit to 1024, not worth OOMing on reward score
-                max_length_tokenize = 2048 - 1024
-            cutoff_len = max_length_tokenize * 4  # restrict deberta related to max for LLM
-
-            if not nochat:
-                history = args_list[-1]
-                if history is None:
-                    history = []
-                if smodel is not None and \
-                        stokenizer is not None and \
-                        sdevice is not None and \
-                        history is not None and len(history) > 0 and \
-                        history[-1] is not None and \
-                        len(history[-1]) >= 2:
-                    os.environ['TOKENIZERS_PARALLELISM'] = 'false'
-
-                    question = history[-1][0]
-
-                    answer = history[-1][1]
-                else:
-                    return '%sNA' % prefix
-            else:
-                answer = args_list[-1]
-                instruction_nochat_arg_id = eval_func_param_names.index('instruction_nochat')
-                question = args_list[instruction_nochat_arg_id]
-
-            if question is None:
-                return '%sBad Question' % prefix
-            if answer is None:
-                return '%sBad Answer' % prefix
-            try:
-                score = score_qa(smodel, stokenizer, max_length_tokenize, question, answer, cutoff_len)
-            finally:
-                clear_torch_cache()
-            if isinstance(score, str):
-                return '%sNA' % prefix
-            return '{}{:.1%}'.format(prefix, score)
-
-        def noop_score_last_response(*args, **kwargs):
-            return "Response Score: Disabled"
-
-        if kwargs['score_model']:
-            score_fun = score_last_response
-        else:
-            score_fun = noop_score_last_response
-
-        score_args = dict(fn=score_fun,
-                          inputs=inputs_list + [text_output],
-                          outputs=[score_text],
-                          )
-        score_args2 = dict(fn=partial(score_fun),
-                           inputs=inputs_list2 + [text_output2],
-                           outputs=[score_text2],
-                           )
-        score_fun_func = functools.partial(score_fun, num_model_lock=len(text_outputs))
-        all_score_args = dict(fn=score_fun_func,
-                              inputs=inputs_list + text_outputs,
-                              outputs=score_text,
-                              )
-
-        score_args_nochat = dict(fn=partial(score_fun, nochat=True),
-                                 inputs=inputs_list + [text_output_nochat],
-                                 outputs=[score_text_nochat],
-                                 )
-
-        def update_history(*args, undo=False, retry=False, sanitize_user_prompt=False):
-            """
-            User that fills history for bot
-            :param args:
-            :param undo:
-            :param retry:
-            :param sanitize_user_prompt:
-            :return:
-            """
-            args_list = list(args)
-            user_message = args_list[eval_func_param_names.index('instruction')]  # chat only
-            input1 = args_list[eval_func_param_names.index('iinput')]  # chat only
-            prompt_type1 = args_list[eval_func_param_names.index('prompt_type')]
-            langchain_mode1 = args_list[eval_func_param_names.index('langchain_mode')]
-            langchain_action1 = args_list[eval_func_param_names.index('langchain_action')]
-            langchain_agents1 = args_list[eval_func_param_names.index('langchain_agents')]
-            document_subset1 = args_list[eval_func_param_names.index('document_subset')]
-            document_choice1 = args_list[eval_func_param_names.index('document_choice')]
-            if not prompt_type1:
-                # shouldn't have to specify if CLI launched model
-                prompt_type1 = kwargs['prompt_type']
-                # apply back
-                args_list[eval_func_param_names.index('prompt_type')] = prompt_type1
-            if input1 and not user_message.endswith(':'):
-                user_message1 = user_message + ":" + input1
-            elif input1:
-                user_message1 = user_message + input1
-            else:
-                user_message1 = user_message
-            if sanitize_user_prompt:
-                pass
-                # requirements.txt has comment that need to re-enable the below 2 lines
-                # from better_profanity import profanity
-                # user_message1 = profanity.censor(user_message1)
-
-            history = args_list[-1]
-            if history is None:
-                # bad history
-                history = []
-            history = history.copy()
-
-            if undo:
-                if len(history) > 0:
-                    history.pop()
-                return history
-            if retry:
-                if history:
-                    history[-1][1] = None
-                return history
-            if user_message1 in ['', None, '\n']:
-                if not allow_empty_instruction(langchain_mode1, document_subset1, langchain_action1):
-                    # reject non-retry submit/enter
-                    return history
-            user_message1 = fix_text_for_gradio(user_message1)
-            return history + [[user_message1, None]]
-
-        def user(*args, undo=False, retry=False, sanitize_user_prompt=False):
-            return update_history(*args, undo=undo, retry=retry, sanitize_user_prompt=sanitize_user_prompt)
-
-        def all_user(*args, undo=False, retry=False, sanitize_user_prompt=False, num_model_lock=0, all_models=None):
-            args_list = list(args)
-
-            visible_models1 = args_list[eval_func_param_names.index('visible_models')]
-            assert isinstance(all_models, list)
-            visible_list = get_model_lock_visible_list(visible_models1, all_models)
-
-            history_list = args_list[-num_model_lock:]
-            assert len(all_models) == len(history_list)
-            assert len(history_list) > 0, "Bad history list: %s" % history_list
-            for hi, history in enumerate(history_list):
-                if not visible_list[hi]:
-                    continue
-                if num_model_lock > 0:
-                    hargs = args_list[:-num_model_lock].copy()
-                else:
-                    hargs = args_list.copy()
-                hargs += [history]
-                history_list[hi] = update_history(*hargs, undo=undo, retry=retry,
-                                                  sanitize_user_prompt=sanitize_user_prompt)
-            if len(history_list) > 1:
-                return tuple(history_list)
-            else:
-                return history_list[0]
-
-        def get_model_max_length(model_state1):
-            if model_state1 and not isinstance(model_state1["tokenizer"], str):
-                tokenizer = model_state1["tokenizer"]
-            elif model_state0 and not isinstance(model_state0["tokenizer"], str):
-                tokenizer = model_state0["tokenizer"]
-            else:
-                tokenizer = None
-            if tokenizer is not None:
-                return tokenizer.model_max_length
-            else:
-                return 2000
-
-        def prep_bot(*args, retry=False, which_model=0):
-            """
-
-            :param args:
-            :param retry:
-            :param which_model: identifies which model if doing model_lock
-                 API only called for which_model=0, default for inputs_list, but rest should ignore inputs_list
-            :return: last element is True if should run bot, False if should just yield history
-            """
-            isize = len(input_args_list) + 1  # states + chat history
-            # don't deepcopy, can contain model itself
-            args_list = list(args).copy()
-            model_state1 = args_list[-isize]
-            my_db_state1 = args_list[-isize + 1]
-            selection_docs_state1 = args_list[-isize + 2]
-            requests_state1 = args_list[-isize + 3]
-            history = args_list[-1]
-            if not history:
-                history = []
-            prompt_type1 = args_list[eval_func_param_names.index('prompt_type')]
-            prompt_dict1 = args_list[eval_func_param_names.index('prompt_dict')]
-            langchain_mode1 = args_list[eval_func_param_names.index('langchain_mode')]
-            langchain_action1 = args_list[eval_func_param_names.index('langchain_action')]
-            document_subset1 = args_list[eval_func_param_names.index('document_subset')]
-            h2ogpt_key1 = args_list[eval_func_param_names.index('h2ogpt_key')]
-            chat_conversation1 = args_list[eval_func_param_names.index('chat_conversation')]
-            valid_key = is_valid_key(kwargs['enforce_h2ogpt_api_key'], kwargs['h2ogpt_api_keys'], h2ogpt_key1,
-                                     requests_state1=requests_state1)
-
-            dummy_return = history, None, langchain_mode1, my_db_state1, requests_state1, valid_key, h2ogpt_key1
-
-            if model_state1['model'] is None or model_state1['model'] == no_model_str:
-                return dummy_return
-
-            args_list = args_list[:-isize]  # only keep rest needed for evaluate()
-            if not history:
-                print("No history", flush=True)
-                return dummy_return
-            instruction1 = history[-1][0]
-            if retry and history:
-                # if retry, pop history and move onto bot stuff
-                instruction1 = history[-1][0]
-                history[-1][1] = None
-            elif not instruction1:
-                if not allow_empty_instruction(langchain_mode1, document_subset1, langchain_action1):
-                    # if not retrying, then reject empty query
-                    return dummy_return
-            elif len(history) > 0 and history[-1][1] not in [None, '']:
-                # reject submit button if already filled and not retrying
-                # None when not filling with '' to keep client happy
-                return dummy_return
-
-            evaluate_local = evaluate if valid_key else evaluate_fake
-
-            # shouldn't have to specify in API prompt_type if CLI launched model, so prefer global CLI one if have it
-            prompt_type1, prompt_dict1 = update_prompt(prompt_type1, prompt_dict1, model_state1,
-                                                       which_model=which_model)
-            # apply back to args_list for evaluate()
-            args_list[eval_func_param_names.index('prompt_type')] = prompt_type1
-            args_list[eval_func_param_names.index('prompt_dict')] = prompt_dict1
-            context1 = args_list[eval_func_param_names.index('context')]
-
-            chat_conversation1 = merge_chat_conversation_history(chat_conversation1, history)
-            args_list[eval_func_param_names.index('chat_conversation')] = chat_conversation1
-
-            if 'visible_models' in model_state1 and model_state1['visible_models'] is not None:
-                assert isinstance(model_state1['visible_models'], int)
-                args_list[eval_func_param_names.index('visible_models')] = model_state1['visible_models']
-            if 'h2ogpt_key' in model_state1 and model_state1['h2ogpt_key'] is not None:
-                # i.e. may be '' and used to override overall local key
-                assert isinstance(model_state1['h2ogpt_key'], str)
-                args_list[eval_func_param_names.index('h2ogpt_key')] = model_state1['h2ogpt_key']
-
-            args_list[0] = instruction1  # override original instruction with history from user
-            args_list[2] = context1
-
-            fun1 = partial(evaluate_local,
-                           model_state1,
-                           my_db_state1,
-                           selection_docs_state1,
-                           requests_state1,
-                           *tuple(args_list),
-                           **kwargs_evaluate)
-
-            return history, fun1, langchain_mode1, my_db_state1, requests_state1, valid_key, h2ogpt_key1
-
-        def gen1_fake(fun1, history):
-            error = ''
-            extra = ''
-            save_dict = dict()
-            yield history, error, extra, save_dict
-            return
-
-        def get_response(fun1, history):
-            """
-            bot that consumes history for user input
-            instruction (from input_list) itself is not consumed by bot
-            :return:
-            """
-            error = ''
-            extra = ''
-            save_dict = dict()
-            if not fun1:
-                yield history, error, extra, save_dict
-                return
-            try:
-                for output_fun in fun1():
-                    output = output_fun['response']
-                    extra = output_fun['sources']  # FIXME: can show sources in separate text box etc.
-                    save_dict = output_fun.get('save_dict', {})
-                    # ensure good visually, else markdown ignores multiple \n
-                    bot_message = fix_text_for_gradio(output)
-                    history[-1][1] = bot_message
-                    yield history, error, extra, save_dict
-            except StopIteration:
-                yield history, error, extra, save_dict
-            except RuntimeError as e:
-                if "generator raised StopIteration" in str(e):
-                    # assume last entry was bad, undo
-                    history.pop()
-                    yield history, error, extra, save_dict
-                else:
-                    if history and len(history) > 0 and len(history[0]) > 1 and history[-1][1] is None:
-                        history[-1][1] = ''
-                    yield history, str(e), extra, save_dict
-                    raise
-            except Exception as e:
-                # put error into user input
-                ex = "Exception: %s" % str(e)
-                if history and len(history) > 0 and len(history[0]) > 1 and history[-1][1] is None:
-                    history[-1][1] = ''
-                yield history, ex, extra, save_dict
-                raise
-            finally:
-                # clear_torch_cache()
-                # don't clear torch cache here, too early and stalls generation if used for all_bot()
-                pass
-            return
-
-        def clear_embeddings(langchain_mode1, db1s):
-            # clear any use of embedding that sits on GPU, else keeps accumulating GPU usage even if clear torch cache
-            if db_type in ['chroma', 'chroma_old'] and langchain_mode1 not in ['LLM', 'Disabled', None, '']:
-                from gpt_langchain import clear_embedding, length_db1
-                db = dbs.get('langchain_mode1')
-                if db is not None and not isinstance(db, str):
-                    clear_embedding(db)
-                if db1s is not None and langchain_mode1 in db1s:
-                    db1 = db1s[langchain_mode1]
-                    if len(db1) == length_db1():
-                        clear_embedding(db1[0])
-
-        def bot(*args, retry=False):
-            history, fun1, langchain_mode1, db1, requests_state1, valid_key, h2ogpt_key1 = prep_bot(*args, retry=retry)
-            save_dict = dict()
-            error = ''
-            extra = ''
-            try:
-                for res in get_response(fun1, history):
-                    history, error, extra, save_dict = res
-                    # pass back to gradio only these, rest are consumed in this function
-                    yield history, error
-            finally:
-                clear_torch_cache()
-                clear_embeddings(langchain_mode1, db1)
-            if 'extra_dict' not in save_dict:
-                save_dict['extra_dict'] = {}
-            save_dict['valid_key'] = valid_key
-            save_dict['h2ogpt_key'] = h2ogpt_key1
-            if requests_state1:
-                save_dict['extra_dict'].update(requests_state1)
-            else:
-                save_dict['extra_dict'].update(dict(username='NO_REQUEST'))
-            save_dict['error'] = error
-            save_dict['extra'] = extra
-            save_dict['which_api'] = 'bot'
-            save_generate_output(**save_dict)
-
-        def all_bot(*args, retry=False, model_states1=None, all_models=None):
-            args_list = list(args).copy()
-            chatbots = args_list[-len(model_states1):]
-            args_list0 = args_list[:-len(model_states1)]  # same for all models
-            exceptions = []
-            stream_output1 = args_list[eval_func_param_names.index('stream_output')]
-            max_time1 = args_list[eval_func_param_names.index('max_time')]
-            langchain_mode1 = args_list[eval_func_param_names.index('langchain_mode')]
-
-            visible_models1 = args_list[eval_func_param_names.index('visible_models')]
-            assert isinstance(all_models, list)
-            assert len(all_models) == len(model_states1)
-            visible_list = get_model_lock_visible_list(visible_models1, all_models)
-
-            isize = len(input_args_list) + 1  # states + chat history
-            db1s = None
-            requests_state1 = None
-            valid_key = False
-            h2ogpt_key1 = ''
-            extras = []
-            exceptions = []
-            save_dicts = []
-            try:
-                gen_list = []
-                for chatboti, (chatbot1, model_state1) in enumerate(zip(chatbots, model_states1)):
-                    args_list1 = args_list0.copy()
-                    args_list1.insert(-isize + 2,
-                                      model_state1)  # insert at -2 so is at -3, and after chatbot1 added, at -4
-                    # if at start, have None in response still, replace with '' so client etc. acts like normal
-                    # assumes other parts of code treat '' and None as if no response yet from bot
-                    # can't do this later in bot code as racy with threaded generators
-                    if len(chatbot1) > 0 and len(chatbot1[-1]) == 2 and chatbot1[-1][1] is None:
-                        chatbot1[-1][1] = ''
-                    args_list1.append(chatbot1)
-                    # so consistent with prep_bot()
-                    # with model_state1 at -3, my_db_state1 at -2, and history(chatbot) at -1
-                    # langchain_mode1 and my_db_state1 and requests_state1 should be same for every bot
-                    history, fun1, langchain_mode1, db1s, requests_state1, valid_key, h2ogpt_key1, = \
-                        prep_bot(*tuple(args_list1), retry=retry,
-                                 which_model=chatboti)
-                    if visible_list[chatboti]:
-                        gen1 = get_response(fun1, history)
-                        if stream_output1:
-                            gen1 = TimeoutIterator(gen1, timeout=0.01, sentinel=None, raise_on_exception=False)
-                        # else timeout will truncate output for non-streaming case
-                    else:
-                        gen1 = gen1_fake(fun1, history)
-                    gen_list.append(gen1)
-
-                bots_old = chatbots.copy()
-                exceptions_old = [''] * len(bots_old)
-                extras_old = [''] * len(bots_old)
-                save_dicts_old = [{}] * len(bots_old)
-                tgen0 = time.time()
-                for res1 in itertools.zip_longest(*gen_list):
-                    if time.time() - tgen0 > max_time1:
-                        print("Took too long: %s" % max_time1, flush=True)
-                        break
-
-                    bots = [x[0] if x is not None and not isinstance(x, BaseException) else y
-                            for x, y in zip(res1, bots_old)]
-                    bots_old = bots.copy()
-
-                    def larger_str(x, y):
-                        return x if len(x) > len(y) else y
-
-                    exceptions = [x[1] if x is not None and not isinstance(x, BaseException) else larger_str(str(x), y)
-                                  for x, y in zip(res1, exceptions_old)]
-                    exceptions_old = exceptions.copy()
-
-                    extras = [x[2] if x is not None and not isinstance(x, BaseException) else y
-                              for x, y in zip(res1, extras_old)]
-                    extras_old = extras.copy()
-
-                    save_dicts = [x[3] if x is not None and not isinstance(x, BaseException) else y
-                                  for x, y in zip(res1, save_dicts_old)]
-                    save_dicts_old = save_dicts.copy()
-
-                    def choose_exc(x):
-                        # don't expose ports etc. to exceptions window
-                        if is_public:
-                            return "Endpoint unavailable or failed"
-                        else:
-                            return x
-
-                    exceptions_str = '\n'.join(
-                        ['Model %s: %s' % (iix, choose_exc(x)) for iix, x in enumerate(exceptions) if
-                         x not in [None, '', 'None']])
-                    # yield back to gradio only is bots + exceptions, rest are consumed locally
-                    if len(bots) > 1:
-                        yield tuple(bots + [exceptions_str])
-                    else:
-                        yield bots[0], exceptions_str
-                if exceptions:
-                    exceptions_reduced = [x for x in exceptions if x not in ['', None, 'None']]
-                    if exceptions_reduced:
-                        print("Generate exceptions: %s" % exceptions_reduced, flush=True)
-            finally:
-                clear_torch_cache()
-                clear_embeddings(langchain_mode1, db1s)
-            for extra, error, save_dict, model_name in zip(extras, exceptions, save_dicts, all_models):
-                if 'extra_dict' not in save_dict:
-                    save_dict['extra_dict'] = {}
-                if requests_state1:
-                    save_dict['extra_dict'].update(requests_state1)
-                else:
-                    save_dict['extra_dict'].update(dict(username='NO_REQUEST'))
-                save_dict['error'] = error
-                save_dict['extra'] = extra
-                save_dict['which_api'] = 'all_bot_%s' % model_name
-                save_dict['valid_key'] = valid_key
-                save_dict['h2ogpt_key'] = h2ogpt_key1
-                save_generate_output(**save_dict)
-
-        # NORMAL MODEL
-        user_args = dict(fn=functools.partial(user, sanitize_user_prompt=kwargs['sanitize_user_prompt']),
-                         inputs=inputs_list + [text_output],
-                         outputs=text_output,
-                         )
-        bot_args = dict(fn=bot,
-                        inputs=inputs_list + [model_state, my_db_state, selection_docs_state, requests_state] + [
-                            text_output],
-                        outputs=[text_output, chat_exception_text],
-                        )
-        retry_bot_args = dict(fn=functools.partial(bot, retry=True),
-                              inputs=inputs_list + [model_state, my_db_state, selection_docs_state, requests_state] + [
-                                  text_output],
-                              outputs=[text_output, chat_exception_text],
-                              )
-        retry_user_args = dict(fn=functools.partial(user, retry=True),
-                               inputs=inputs_list + [text_output],
-                               outputs=text_output,
-                               )
-        undo_user_args = dict(fn=functools.partial(user, undo=True),
-                              inputs=inputs_list + [text_output],
-                              outputs=text_output,
-                              )
-
-        # MODEL2
-        user_args2 = dict(fn=functools.partial(user, sanitize_user_prompt=kwargs['sanitize_user_prompt']),
-                          inputs=inputs_list2 + [text_output2],
-                          outputs=text_output2,
-                          )
-        bot_args2 = dict(fn=bot,
-                         inputs=inputs_list2 + [model_state2, my_db_state, selection_docs_state, requests_state] + [
-                             text_output2],
-                         outputs=[text_output2, chat_exception_text],
-                         )
-        retry_bot_args2 = dict(fn=functools.partial(bot, retry=True),
-                               inputs=inputs_list2 + [model_state2, my_db_state, selection_docs_state,
-                                                      requests_state] + [text_output2],
-                               outputs=[text_output2, chat_exception_text],
-                               )
-        retry_user_args2 = dict(fn=functools.partial(user, retry=True),
-                                inputs=inputs_list2 + [text_output2],
-                                outputs=text_output2,
-                                )
-        undo_user_args2 = dict(fn=functools.partial(user, undo=True),
-                               inputs=inputs_list2 + [text_output2],
-                               outputs=text_output2,
-                               )
-
-        # MODEL N
-        all_user_args = dict(fn=functools.partial(all_user,
-                                                  sanitize_user_prompt=kwargs['sanitize_user_prompt'],
-                                                  num_model_lock=len(text_outputs),
-                                                  all_models=kwargs['all_models']
-                                                  ),
-                             inputs=inputs_list + text_outputs,
-                             outputs=text_outputs,
-                             )
-        all_bot_args = dict(fn=functools.partial(all_bot, model_states1=model_states,
-                                                 all_models=kwargs['all_models']),
-                            inputs=inputs_list + [my_db_state, selection_docs_state, requests_state] +
-                                   text_outputs,
-                            outputs=text_outputs + [chat_exception_text],
-                            )
-        all_retry_bot_args = dict(fn=functools.partial(all_bot, model_states1=model_states,
-                                                       all_models=kwargs['all_models'],
-                                                       retry=True),
-                                  inputs=inputs_list + [my_db_state, selection_docs_state, requests_state] +
-                                         text_outputs,
-                                  outputs=text_outputs + [chat_exception_text],
-                                  )
-        all_retry_user_args = dict(fn=functools.partial(all_user, retry=True,
-                                                        sanitize_user_prompt=kwargs['sanitize_user_prompt'],
-                                                        num_model_lock=len(text_outputs),
-                                                        all_models=kwargs['all_models']
-                                                        ),
-                                   inputs=inputs_list + text_outputs,
-                                   outputs=text_outputs,
-                                   )
-        all_undo_user_args = dict(fn=functools.partial(all_user, undo=True,
-                                                       sanitize_user_prompt=kwargs['sanitize_user_prompt'],
-                                                       num_model_lock=len(text_outputs),
-                                                       all_models=kwargs['all_models']
-                                                       ),
-                                  inputs=inputs_list + text_outputs,
-                                  outputs=text_outputs,
-                                  )
-
-        def clear_instruct():
-            return gr.Textbox.update(value='')
-
-        def deselect_radio_chats():
-            return gr.update(value=None)
-
-        def clear_all():
-            return gr.Textbox.update(value=''), gr.Textbox.update(value=''), gr.update(value=None), \
-                gr.Textbox.update(value=''), gr.Textbox.update(value='')
-
-        if kwargs['model_states']:
-            submits1 = submits2 = submits3 = []
-            submits4 = []
-
-            triggers = [instruction, submit, retry_btn]
-            fun_source = [instruction.submit, submit.click, retry_btn.click]
-            fun_name = ['instruction', 'submit', 'retry']
-            user_args = [all_user_args, all_user_args, all_retry_user_args]
-            bot_args = [all_bot_args, all_bot_args, all_retry_bot_args]
-            for userargs1, botarg1, funn1, funs1, trigger1, in zip(user_args, bot_args, fun_name, fun_source, triggers):
-                submit_event11 = funs1(fn=user_state_setup,
-                                       inputs=[my_db_state, requests_state, trigger1, trigger1],
-                                       outputs=[my_db_state, requests_state, trigger1],
-                                       queue=queue)
-                submit_event1a = submit_event11.then(**userargs1, queue=queue,
-                                                     api_name='%s' % funn1 if allow_api else None)
-                # if hit enter on new instruction for submitting new query, no longer the saved chat
-                submit_event1b = submit_event1a.then(clear_all, inputs=None,
-                                                     outputs=[instruction, iinput, radio_chats, score_text,
-                                                              score_text2],
-                                                     queue=queue)
-                submit_event1c = submit_event1b.then(**botarg1,
-                                                     api_name='%s_bot' % funn1 if allow_api else None,
-                                                     queue=queue)
-                submit_event1d = submit_event1c.then(**all_score_args,
-                                                     api_name='%s_bot_score' % funn1 if allow_api else None,
-                                                     queue=queue)
-
-                submits1.extend([submit_event1a, submit_event1b, submit_event1c, submit_event1d])
-
-            # if undo, no longer the saved chat
-            submit_event4 = undo.click(fn=user_state_setup,
-                                       inputs=[my_db_state, requests_state, undo, undo],
-                                       outputs=[my_db_state, requests_state, undo],
-                                       queue=queue) \
-                .then(**all_undo_user_args, api_name='undo' if allow_api else None) \
-                .then(clear_all, inputs=None, outputs=[instruction, iinput, radio_chats, score_text,
-                                                       score_text2], queue=queue) \
-                .then(**all_score_args, api_name='undo_score' if allow_api else None)
-            submits4 = [submit_event4]
-
-        else:
-            # in case 2nd model, consume instruction first, so can clear quickly
-            # bot doesn't consume instruction itself, just history from user, so why works
-            submit_event11 = instruction.submit(fn=user_state_setup,
-                                                inputs=[my_db_state, requests_state, instruction, instruction],
-                                                outputs=[my_db_state, requests_state, instruction],
-                                                queue=queue)
-            submit_event1a = submit_event11.then(**user_args, queue=queue,
-                                                 api_name='instruction' if allow_api else None)
-            # if hit enter on new instruction for submitting new query, no longer the saved chat
-            submit_event1a2 = submit_event1a.then(deselect_radio_chats, inputs=None, outputs=radio_chats, queue=queue)
-            submit_event1b = submit_event1a2.then(**user_args2, api_name='instruction2' if allow_api else None)
-            submit_event1c = submit_event1b.then(clear_instruct, None, instruction) \
-                .then(clear_instruct, None, iinput)
-            submit_event1d = submit_event1c.then(**bot_args, api_name='instruction_bot' if allow_api else None,
-                                                 queue=queue)
-            submit_event1e = submit_event1d.then(**score_args,
-                                                 api_name='instruction_bot_score' if allow_api else None,
-                                                 queue=queue)
-            submit_event1f = submit_event1e.then(**bot_args2, api_name='instruction_bot2' if allow_api else None,
-                                                 queue=queue)
-            submit_event1g = submit_event1f.then(**score_args2,
-                                                 api_name='instruction_bot_score2' if allow_api else None, queue=queue)
-
-            submits1 = [submit_event1a, submit_event1a2, submit_event1b, submit_event1c, submit_event1d,
-                        submit_event1e,
-                        submit_event1f, submit_event1g]
-
-            submit_event21 = submit.click(fn=user_state_setup,
-                                          inputs=[my_db_state, requests_state, submit, submit],
-                                          outputs=[my_db_state, requests_state, submit],
-                                          queue=queue)
-            submit_event2a = submit_event21.then(**user_args, api_name='submit' if allow_api else None)
-            # if submit new query, no longer the saved chat
-            submit_event2a2 = submit_event2a.then(deselect_radio_chats, inputs=None, outputs=radio_chats, queue=queue)
-            submit_event2b = submit_event2a2.then(**user_args2, api_name='submit2' if allow_api else None)
-            submit_event2c = submit_event2b.then(clear_all, inputs=None,
-                                                 outputs=[instruction, iinput, radio_chats, score_text, score_text2],
-                                                 queue=queue)
-            submit_event2d = submit_event2c.then(**bot_args, api_name='submit_bot' if allow_api else None, queue=queue)
-            submit_event2e = submit_event2d.then(**score_args,
-                                                 api_name='submit_bot_score' if allow_api else None,
-                                                 queue=queue)
-            submit_event2f = submit_event2e.then(**bot_args2, api_name='submit_bot2' if allow_api else None,
-                                                 queue=queue)
-            submit_event2g = submit_event2f.then(**score_args2,
-                                                 api_name='submit_bot_score2' if allow_api else None,
-                                                 queue=queue)
-
-            submits2 = [submit_event2a, submit_event2a2, submit_event2b, submit_event2c, submit_event2d,
-                        submit_event2e,
-                        submit_event2f, submit_event2g]
-
-            submit_event31 = retry_btn.click(fn=user_state_setup,
-                                             inputs=[my_db_state, requests_state, retry_btn, retry_btn],
-                                             outputs=[my_db_state, requests_state, retry_btn],
-                                             queue=queue)
-            submit_event3a = submit_event31.then(**user_args, api_name='retry' if allow_api else None)
-            # if retry, no longer the saved chat
-            submit_event3a2 = submit_event3a.then(deselect_radio_chats, inputs=None, outputs=radio_chats, queue=queue)
-            submit_event3b = submit_event3a2.then(**user_args2, api_name='retry2' if allow_api else None)
-            submit_event3c = submit_event3b.then(clear_instruct, None, instruction) \
-                .then(clear_instruct, None, iinput)
-            submit_event3d = submit_event3c.then(**retry_bot_args, api_name='retry_bot' if allow_api else None,
-                                                 queue=queue)
-            submit_event3e = submit_event3d.then(**score_args,
-                                                 api_name='retry_bot_score' if allow_api else None,
-                                                 queue=queue)
-            submit_event3f = submit_event3e.then(**retry_bot_args2, api_name='retry_bot2' if allow_api else None,
-                                                 queue=queue)
-            submit_event3g = submit_event3f.then(**score_args2,
-                                                 api_name='retry_bot_score2' if allow_api else None,
-                                                 queue=queue)
-
-            submits3 = [submit_event3a, submit_event3a2, submit_event3b, submit_event3c, submit_event3d,
-                        submit_event3e,
-                        submit_event3f, submit_event3g]
-
-            # if undo, no longer the saved chat
-            submit_event4 = undo.click(fn=user_state_setup,
-                                       inputs=[my_db_state, requests_state, undo, undo],
-                                       outputs=[my_db_state, requests_state, undo],
-                                       queue=queue) \
-                .then(**undo_user_args, api_name='undo' if allow_api else None) \
-                .then(**undo_user_args2, api_name='undo2' if allow_api else None) \
-                .then(clear_all, inputs=None, outputs=[instruction, iinput, radio_chats, score_text,
-                                                       score_text2], queue=queue) \
-                .then(**score_args, api_name='undo_score' if allow_api else None) \
-                .then(**score_args2, api_name='undo_score2' if allow_api else None)
-            submits4 = [submit_event4]
-
-        # MANAGE CHATS
-        def dedup(short_chat, short_chats):
-            if short_chat not in short_chats:
-                return short_chat
-            for i in range(1, 1000):
-                short_chat_try = short_chat + "_" + str(i)
-                if short_chat_try not in short_chats:
-                    return short_chat_try
-            # fallback and hope for best
-            short_chat = short_chat + "_" + str(random.random())
-            return short_chat
-
-        def get_short_chat(x, short_chats, short_len=20, words=4):
-            if x and len(x[0]) == 2 and x[0][0] is not None:
-                short_chat = ' '.join(x[0][0][:short_len].split(' ')[:words]).strip()
-                if not short_chat:
-                    # e.g.summarization, try using answer
-                    short_chat = ' '.join(x[0][1][:short_len].split(' ')[:words]).strip()
-                    if not short_chat:
-                        short_chat = 'Unk'
-                short_chat = dedup(short_chat, short_chats)
-            else:
-                short_chat = None
-            return short_chat
-
-        def is_chat_same(x, y):
-            # <p> etc. added in chat, try to remove some of that to help avoid dup entries when hit new conversation
-            is_same = True
-            # length of conversation has to be same
-            if len(x) != len(y):
-                return False
-            if len(x) != len(y):
-                return False
-            for stepx, stepy in zip(x, y):
-                if len(stepx) != len(stepy):
-                    # something off with a conversation
-                    return False
-                for stepxx, stepyy in zip(stepx, stepy):
-                    if len(stepxx) != len(stepyy):
-                        # something off with a conversation
-                        return False
-                    if len(stepxx) != 2:
-                        # something off
-                        return False
-                    if len(stepyy) != 2:
-                        # something off
-                        return False
-                    questionx = stepxx[0].replace('<p>', '').replace('</p>', '') if stepxx[0] is not None else None
-                    answerx = stepxx[1].replace('<p>', '').replace('</p>', '') if stepxx[1] is not None else None
-
-                    questiony = stepyy[0].replace('<p>', '').replace('</p>', '') if stepyy[0] is not None else None
-                    answery = stepyy[1].replace('<p>', '').replace('</p>', '') if stepyy[1] is not None else None
-
-                    if questionx != questiony or answerx != answery:
-                        return False
-            return is_same
-
-        def save_chat(*args, chat_is_list=False, auth_filename=None, auth_freeze=None):
-            args_list = list(args)
-            db1s = args_list[0]
-            requests_state1 = args_list[1]
-            args_list = args_list[2:]
-            if not chat_is_list:
-                # list of chatbot histories,
-                # can't pass in list with list of chatbot histories and state due to gradio limits
-                chat_list = args_list[:-1]
-            else:
-                assert len(args_list) == 2
-                chat_list = args_list[0]
-            # if old chat file with single chatbot, get into shape
-            if isinstance(chat_list, list) and len(chat_list) > 0 and isinstance(chat_list[0], list) and len(
-                    chat_list[0]) == 2 and isinstance(chat_list[0][0], str) and isinstance(chat_list[0][1], str):
-                chat_list = [chat_list]
-            # remove None histories
-            chat_list_not_none = [x for x in chat_list if x and len(x) > 0 and len(x[0]) == 2 and x[0][1] is not None]
-            chat_list_none = [x for x in chat_list if x not in chat_list_not_none]
-            if len(chat_list_none) > 0 and len(chat_list_not_none) == 0:
-                raise ValueError("Invalid chat file")
-            # dict with keys of short chat names, values of list of list of chatbot histories
-            chat_state1 = args_list[-1]
-            short_chats = list(chat_state1.keys())
-            if len(chat_list_not_none) > 0:
-                # make short_chat key from only first history, based upon question that is same anyways
-                chat_first = chat_list_not_none[0]
-                short_chat = get_short_chat(chat_first, short_chats)
-                if short_chat:
-                    old_chat_lists = list(chat_state1.values())
-                    already_exists = any([is_chat_same(chat_list, x) for x in old_chat_lists])
-                    if not already_exists:
-                        chat_state1[short_chat] = chat_list.copy()
-
-            # reverse so newest at top
-            choices = list(chat_state1.keys()).copy()
-            choices.reverse()
-
-            # save saved chats and chatbots to auth file
-            text_output1 = chat_list[0]
-            text_output21 = chat_list[1]
-            text_outputs1 = chat_list[2:]
-            save_auth(requests_state1, auth_filename, auth_freeze, chat_state1=chat_state1,
-                      text_output1=text_output1, text_output21=text_output21, text_outputs1=text_outputs1)
-
-            return chat_state1, gr.update(choices=choices, value=None)
-
-        def switch_chat(chat_key, chat_state1, num_model_lock=0):
-            chosen_chat = chat_state1[chat_key]
-            # deal with possible different size of chat list vs. current list
-            ret_chat = [None] * (2 + num_model_lock)
-            for chati in range(0, 2 + num_model_lock):
-                ret_chat[chati % len(ret_chat)] = chosen_chat[chati % len(chosen_chat)]
-            return tuple(ret_chat)
-
-        def clear_texts(*args):
-            return tuple([gr.Textbox.update(value='')] * len(args))
-
-        def clear_scores():
-            return gr.Textbox.update(value=res_value), \
-                gr.Textbox.update(value='Response Score: NA'), \
-                gr.Textbox.update(value='Response Score: NA')
-
-        switch_chat_fun = functools.partial(switch_chat, num_model_lock=len(text_outputs))
-        radio_chats.input(switch_chat_fun,
-                          inputs=[radio_chats, chat_state],
-                          outputs=[text_output, text_output2] + text_outputs) \
-            .then(clear_scores, outputs=[score_text, score_text2, score_text_nochat])
-
-        def remove_chat(chat_key, chat_state1):
-            if isinstance(chat_key, str):
-                chat_state1.pop(chat_key, None)
-            return gr.update(choices=list(chat_state1.keys()), value=None), chat_state1
-
-        remove_chat_event = remove_chat_btn.click(remove_chat,
-                                                  inputs=[radio_chats, chat_state],
-                                                  outputs=[radio_chats, chat_state],
-                                                  queue=False, api_name='remove_chat')
-
-        def get_chats1(chat_state1):
-            base = 'chats'
-            base = makedirs(base, exist_ok=True, tmp_ok=True, use_base=True)
-            filename = os.path.join(base, 'chats_%s.json' % str(uuid.uuid4()))
-            with open(filename, "wt") as f:
-                f.write(json.dumps(chat_state1, indent=2))
-            return filename
-
-        export_chat_event = export_chats_btn.click(get_chats1, inputs=chat_state, outputs=chats_file, queue=False,
-                                                   api_name='export_chats' if allow_api else None)
-
-        def add_chats_from_file(db1s, requests_state1, file, chat_state1, radio_chats1, chat_exception_text1,
-                                auth_filename=None, auth_freeze=None):
-            if not file:
-                return None, chat_state1, gr.update(choices=list(chat_state1.keys()), value=None), chat_exception_text1
-            if isinstance(file, str):
-                files = [file]
-            else:
-                files = file
-            if not files:
-                return None, chat_state1, gr.update(choices=list(chat_state1.keys()), value=None), chat_exception_text1
-            chat_exception_list = []
-            for file1 in files:
-                try:
-                    if hasattr(file1, 'name'):
-                        file1 = file1.name
-                    with open(file1, "rt") as f:
-                        new_chats = json.loads(f.read())
-                        for chat1_k, chat1_v in new_chats.items():
-                            # ignore chat1_k, regenerate and de-dup to avoid loss
-                            chat_state1, _ = save_chat(db1s, requests_state1, chat1_v, chat_state1, chat_is_list=True)
-                except BaseException as e:
-                    t, v, tb = sys.exc_info()
-                    ex = ''.join(traceback.format_exception(t, v, tb))
-                    ex_str = "File %s exception: %s" % (file1, str(e))
-                    print(ex_str, flush=True)
-                    chat_exception_list.append(ex_str)
-                    chat_exception_text1 = '\n'.join(chat_exception_list)
-            # save chat to auth file
-            save_auth(requests_state1, auth_filename, auth_freeze, chat_state1=chat_state1)
-            return None, chat_state1, gr.update(choices=list(chat_state1.keys()), value=None), chat_exception_text1
-
-        # note for update_user_db_func output is ignored for db
-        chatup_change_eventa = chatsup_output.change(user_state_setup,
-                                                     inputs=[my_db_state, requests_state, langchain_mode],
-                                                     outputs=[my_db_state, requests_state, langchain_mode],
-                                                     show_progress='minimal')
-        add_chats_from_file_func = functools.partial(add_chats_from_file,
-                                                     auth_filename=kwargs['auth_filename'],
-                                                     auth_freeze=kwargs['auth_freeze'],
-                                                     )
-        chatup_change_event = chatup_change_eventa.then(add_chats_from_file_func,
-                                                        inputs=[my_db_state, requests_state] +
-                                                               [chatsup_output, chat_state, radio_chats,
-                                                                chat_exception_text],
-                                                        outputs=[chatsup_output, chat_state, radio_chats,
-                                                                 chat_exception_text],
-                                                        queue=False,
-                                                        api_name='add_to_chats' if allow_api else None)
-
-        clear_chat_event = clear_chat_btn.click(fn=clear_texts,
-                                                inputs=[text_output, text_output2] + text_outputs,
-                                                outputs=[text_output, text_output2] + text_outputs,
-                                                queue=False, api_name='clear' if allow_api else None) \
-            .then(deselect_radio_chats, inputs=None, outputs=radio_chats, queue=False) \
-            .then(clear_scores, outputs=[score_text, score_text2, score_text_nochat])
-
-        clear_eventa = save_chat_btn.click(user_state_setup,
-                                           inputs=[my_db_state, requests_state, langchain_mode],
-                                           outputs=[my_db_state, requests_state, langchain_mode],
-                                           show_progress='minimal')
-        save_chat_func = functools.partial(save_chat,
-                                           auth_filename=kwargs['auth_filename'],
-                                           auth_freeze=kwargs['auth_freeze'],
-                                           )
-        clear_event = clear_eventa.then(save_chat_func,
-                                        inputs=[my_db_state, requests_state] +
-                                               [text_output, text_output2] + text_outputs +
-                                               [chat_state],
-                                        outputs=[chat_state, radio_chats],
-                                        api_name='save_chat' if allow_api else None)
-        if kwargs['score_model']:
-            clear_event2 = clear_event.then(clear_scores, outputs=[score_text, score_text2, score_text_nochat])
-
-        # NOTE: clear of instruction/iinput for nochat has to come after score,
-        # because score for nochat consumes actual textbox, while chat consumes chat history filled by user()
-        no_chat_args = dict(fn=fun,
-                            inputs=[model_state, my_db_state, selection_docs_state, requests_state] + inputs_list,
-                            outputs=text_output_nochat,
-                            queue=queue,
-                            )
-        submit_event_nochat = submit_nochat.click(**no_chat_args, api_name='submit_nochat' if allow_api else None) \
-            .then(clear_torch_cache) \
-            .then(**score_args_nochat, api_name='instruction_bot_score_nochat' if allow_api else None, queue=queue) \
-            .then(clear_instruct, None, instruction_nochat) \
-            .then(clear_instruct, None, iinput_nochat) \
-            .then(clear_torch_cache)
-        # copy of above with text box submission
-        submit_event_nochat2 = instruction_nochat.submit(**no_chat_args) \
-            .then(clear_torch_cache) \
-            .then(**score_args_nochat, queue=queue) \
-            .then(clear_instruct, None, instruction_nochat) \
-            .then(clear_instruct, None, iinput_nochat) \
-            .then(clear_torch_cache)
-
-        submit_event_nochat_api = submit_nochat_api.click(fun_with_dict_str,
-                                                          inputs=[model_state, my_db_state, selection_docs_state,
-                                                                  requests_state,
-                                                                  inputs_dict_str],
-                                                          outputs=text_output_nochat_api,
-                                                          queue=True,  # required for generator
-                                                          api_name='submit_nochat_api' if allow_api else None)
-
-        submit_event_nochat_api_plain = submit_nochat_api_plain.click(fun_with_dict_str_plain,
-                                                                      inputs=inputs_dict_str,
-                                                                      outputs=text_output_nochat_api,
-                                                                      queue=False,
-                                                                      api_name='submit_nochat_plain_api' if allow_api else None)
-
-        def load_model(model_name, lora_weights, server_name, model_state_old, prompt_type_old,
-                       load_8bit, load_4bit, low_bit_mode,
-                       load_gptq, load_exllama, use_safetensors, revision,
-                       use_gpu_id, gpu_id, max_seq_len1, rope_scaling1,
-                       model_path_llama1, model_name_gptj1, model_name_gpt4all_llama1,
-                       n_gpu_layers1, n_batch1, n_gqa1, llamacpp_dict_more1,
-                       system_prompt1):
-            try:
-                llamacpp_dict = ast.literal_eval(llamacpp_dict_more1)
-            except:
-                print("Failed to use user input for llamacpp_dict_more1 dict", flush=True)
-                llamacpp_dict = {}
-            llamacpp_dict.update(dict(model_path_llama=model_path_llama1,
-                                      model_name_gptj=model_name_gptj1,
-                                      model_name_gpt4all_llama=model_name_gpt4all_llama1,
-                                      n_gpu_layers=n_gpu_layers1,
-                                      n_batch=n_batch1,
-                                      n_gqa=n_gqa1,
-                                      ))
-
-            # ensure no API calls reach here
-            if is_public:
-                raise RuntimeError("Illegal access for %s" % model_name)
-            # ensure old model removed from GPU memory
-            if kwargs['debug']:
-                print("Pre-switch pre-del GPU memory: %s" % get_torch_allocated(), flush=True)
-
-            model0 = model_state0['model']
-            if isinstance(model_state_old['model'], str) and \
-                    model0 is not None and \
-                    hasattr(model0, 'cpu'):
-                # best can do, move model loaded at first to CPU
-                model0.cpu()
-
-            if model_state_old['model'] is not None and \
-                    not isinstance(model_state_old['model'], str):
-                if hasattr(model_state_old['model'], 'cpu'):
-                    try:
-                        model_state_old['model'].cpu()
-                    except Exception as e:
-                        # sometimes hit NotImplementedError: Cannot copy out of meta tensor; no data!
-                        print("Unable to put model on CPU: %s" % str(e), flush=True)
-                del model_state_old['model']
-                model_state_old['model'] = None
-
-            if model_state_old['tokenizer'] is not None and not isinstance(model_state_old['tokenizer'], str):
-                del model_state_old['tokenizer']
-                model_state_old['tokenizer'] = None
-
-            clear_torch_cache()
-            if kwargs['debug']:
-                print("Pre-switch post-del GPU memory: %s" % get_torch_allocated(), flush=True)
-            if not model_name:
-                model_name = no_model_str
-            if model_name == no_model_str:
-                # no-op if no model, just free memory
-                # no detranscribe needed for model, never go into evaluate
-                lora_weights = no_lora_str
-                server_name = no_server_str
-                return kwargs['model_state_none'].copy(), \
-                    model_name, lora_weights, server_name, prompt_type_old, \
-                    gr.Slider.update(maximum=256), \
-                    gr.Slider.update(maximum=256)
-
-            # don't deepcopy, can contain model itself
-            all_kwargs1 = all_kwargs.copy()
-            all_kwargs1['base_model'] = model_name.strip()
-            all_kwargs1['load_8bit'] = load_8bit
-            all_kwargs1['load_4bit'] = load_4bit
-            all_kwargs1['low_bit_mode'] = low_bit_mode
-            all_kwargs1['load_gptq'] = load_gptq
-            all_kwargs1['load_exllama'] = load_exllama
-            all_kwargs1['use_safetensors'] = use_safetensors
-            all_kwargs1['revision'] = None if not revision else revision  # transcribe, don't pass ''
-            all_kwargs1['use_gpu_id'] = use_gpu_id
-            all_kwargs1['gpu_id'] = int(gpu_id) if gpu_id not in [None, 'None'] else None  # detranscribe
-            all_kwargs1['llamacpp_dict'] = llamacpp_dict
-            all_kwargs1['max_seq_len'] = max_seq_len1
-            try:
-                all_kwargs1['rope_scaling'] = str_to_dict(rope_scaling1)  # transcribe
-            except:
-                print("Failed to use user input for rope_scaling dict", flush=True)
-                all_kwargs1['rope_scaling'] = {}
-            model_lower = model_name.strip().lower()
-            if model_lower in inv_prompt_type_to_model_lower:
-                prompt_type1 = inv_prompt_type_to_model_lower[model_lower]
-            else:
-                prompt_type1 = prompt_type_old
-
-            # detranscribe
-            if lora_weights == no_lora_str:
-                lora_weights = ''
-            all_kwargs1['lora_weights'] = lora_weights.strip()
-            if server_name == no_server_str:
-                server_name = ''
-            all_kwargs1['inference_server'] = server_name.strip()
-
-            model1, tokenizer1, device1 = get_model(reward_type=False,
-                                                    **get_kwargs(get_model, exclude_names=['reward_type'],
-                                                                 **all_kwargs1))
-            clear_torch_cache()
-
-            tokenizer_base_model = model_name
-            prompt_dict1, error0 = get_prompt(prompt_type1, '',
-                                              chat=False, context='', reduced=False, making_context=False,
-                                              return_dict=True, system_prompt=system_prompt1)
-            model_state_new = dict(model=model1, tokenizer=tokenizer1, device=device1,
-                                   base_model=model_name, tokenizer_base_model=tokenizer_base_model,
-                                   lora_weights=lora_weights, inference_server=server_name,
-                                   prompt_type=prompt_type1, prompt_dict=prompt_dict1,
-                                   # FIXME: not typically required, unless want to expose adding h2ogpt endpoint in UI
-                                   visible_models=None, h2ogpt_key=None,
-                                   )
-
-            max_max_new_tokens1 = get_max_max_new_tokens(model_state_new, **kwargs)
-
-            if kwargs['debug']:
-                print("Post-switch GPU memory: %s" % get_torch_allocated(), flush=True)
-            return model_state_new, model_name, lora_weights, server_name, prompt_type1, \
-                gr.Slider.update(maximum=max_max_new_tokens1), \
-                gr.Slider.update(maximum=max_max_new_tokens1)
-
-        def get_prompt_str(prompt_type1, prompt_dict1, system_prompt1, which=0):
-            if prompt_type1 in ['', None]:
-                print("Got prompt_type %s: %s" % (which, prompt_type1), flush=True)
-                return str({})
-            prompt_dict1, prompt_dict_error = get_prompt(prompt_type1, prompt_dict1, chat=False, context='',
-                                                         reduced=False, making_context=False, return_dict=True,
-                                                         system_prompt=system_prompt1)
-            if prompt_dict_error:
-                return str(prompt_dict_error)
-            else:
-                # return so user can manipulate if want and use as custom
-                return str(prompt_dict1)
-
-        get_prompt_str_func1 = functools.partial(get_prompt_str, which=1)
-        get_prompt_str_func2 = functools.partial(get_prompt_str, which=2)
-        prompt_type.change(fn=get_prompt_str_func1, inputs=[prompt_type, prompt_dict, system_prompt],
-                           outputs=prompt_dict, queue=False)
-        prompt_type2.change(fn=get_prompt_str_func2, inputs=[prompt_type2, prompt_dict2, system_prompt],
-                            outputs=prompt_dict2,
-                            queue=False)
-
-        def dropdown_prompt_type_list(x):
-            return gr.Dropdown.update(value=x)
-
-        def chatbot_list(x, model_used_in):
-            return gr.Textbox.update(label=f'h2oGPT [Model: {model_used_in}]')
-
-        load_model_args = dict(fn=load_model,
-                               inputs=[model_choice, lora_choice, server_choice, model_state, prompt_type,
-                                       model_load8bit_checkbox, model_load4bit_checkbox, model_low_bit_mode,
-                                       model_load_gptq, model_load_exllama_checkbox,
-                                       model_safetensors_checkbox, model_revision,
-                                       model_use_gpu_id_checkbox, model_gpu,
-                                       max_seq_len, rope_scaling,
-                                       model_path_llama, model_name_gptj, model_name_gpt4all_llama,
-                                       n_gpu_layers, n_batch, n_gqa, llamacpp_dict_more,
-                                       system_prompt],
-                               outputs=[model_state, model_used, lora_used, server_used,
-                                        # if prompt_type changes, prompt_dict will change via change rule
-                                        prompt_type, max_new_tokens, min_new_tokens,
-                                        ])
-        prompt_update_args = dict(fn=dropdown_prompt_type_list, inputs=prompt_type, outputs=prompt_type)
-        chatbot_update_args = dict(fn=chatbot_list, inputs=[text_output, model_used], outputs=text_output)
-        nochat_update_args = dict(fn=chatbot_list, inputs=[text_output_nochat, model_used], outputs=text_output_nochat)
-        load_model_event = load_model_button.click(**load_model_args,
-                                                   api_name='load_model' if allow_api and not is_public else None) \
-            .then(**prompt_update_args) \
-            .then(**chatbot_update_args) \
-            .then(**nochat_update_args) \
-            .then(clear_torch_cache)
-
-        load_model_args2 = dict(fn=load_model,
-                                inputs=[model_choice2, lora_choice2, server_choice2, model_state2, prompt_type2,
-                                        model_load8bit_checkbox2, model_load4bit_checkbox2, model_low_bit_mode2,
-                                        model_load_gptq2, model_load_exllama_checkbox2,
-                                        model_safetensors_checkbox2, model_revision2,
-                                        model_use_gpu_id_checkbox2, model_gpu2,
-                                        max_seq_len2, rope_scaling2,
-                                        model_path_llama2, model_name_gptj2, model_name_gpt4all_llama2,
-                                        n_gpu_layers2, n_batch2, n_gqa2, llamacpp_dict_more2,
-                                        system_prompt],
-                                outputs=[model_state2, model_used2, lora_used2, server_used2,
-                                         # if prompt_type2 changes, prompt_dict2 will change via change rule
-                                         prompt_type2, max_new_tokens2, min_new_tokens2
-                                         ])
-        prompt_update_args2 = dict(fn=dropdown_prompt_type_list, inputs=prompt_type2, outputs=prompt_type2)
-        chatbot_update_args2 = dict(fn=chatbot_list, inputs=[text_output2, model_used2], outputs=text_output2)
-        load_model_event2 = load_model_button2.click(**load_model_args2,
-                                                     api_name='load_model2' if allow_api and not is_public else None) \
-            .then(**prompt_update_args2) \
-            .then(**chatbot_update_args2) \
-            .then(clear_torch_cache)
-
-        def dropdown_model_lora_server_list(model_list0, model_x,
-                                            lora_list0, lora_x,
-                                            server_list0, server_x,
-                                            model_used1, lora_used1, server_used1,
-                                            model_used2, lora_used2, server_used2,
-                                            ):
-            model_new_state = [model_list0[0] + [model_x]]
-            model_new_options = [*model_new_state[0]]
-            if no_model_str in model_new_options:
-                model_new_options.remove(no_model_str)
-            model_new_options = [no_model_str] + sorted(model_new_options)
-            x1 = model_x if model_used1 == no_model_str else model_used1
-            x2 = model_x if model_used2 == no_model_str else model_used2
-            ret1 = [gr.Dropdown.update(value=x1, choices=model_new_options),
-                    gr.Dropdown.update(value=x2, choices=model_new_options),
-                    '', model_new_state]
-
-            lora_new_state = [lora_list0[0] + [lora_x]]
-            lora_new_options = [*lora_new_state[0]]
-            if no_lora_str in lora_new_options:
-                lora_new_options.remove(no_lora_str)
-            lora_new_options = [no_lora_str] + sorted(lora_new_options)
-            # don't switch drop-down to added lora if already have model loaded
-            x1 = lora_x if model_used1 == no_model_str else lora_used1
-            x2 = lora_x if model_used2 == no_model_str else lora_used2
-            ret2 = [gr.Dropdown.update(value=x1, choices=lora_new_options),
-                    gr.Dropdown.update(value=x2, choices=lora_new_options),
-                    '', lora_new_state]
-
-            server_new_state = [server_list0[0] + [server_x]]
-            server_new_options = [*server_new_state[0]]
-            if no_server_str in server_new_options:
-                server_new_options.remove(no_server_str)
-            server_new_options = [no_server_str] + sorted(server_new_options)
-            # don't switch drop-down to added server if already have model loaded
-            x1 = server_x if model_used1 == no_model_str else server_used1
-            x2 = server_x if model_used2 == no_model_str else server_used2
-            ret3 = [gr.Dropdown.update(value=x1, choices=server_new_options),
-                    gr.Dropdown.update(value=x2, choices=server_new_options),
-                    '', server_new_state]
-
-            return tuple(ret1 + ret2 + ret3)
-
-        add_model_lora_server_event = \
-            add_model_lora_server_button.click(fn=dropdown_model_lora_server_list,
-                                               inputs=[model_options_state, new_model] +
-                                                      [lora_options_state, new_lora] +
-                                                      [server_options_state, new_server] +
-                                                      [model_used, lora_used, server_used] +
-                                                      [model_used2, lora_used2, server_used2],
-                                               outputs=[model_choice, model_choice2, new_model, model_options_state] +
-                                                       [lora_choice, lora_choice2, new_lora, lora_options_state] +
-                                                       [server_choice, server_choice2, new_server,
-                                                        server_options_state],
-                                               queue=False)
-
-        go_event = go_btn.click(lambda: gr.update(visible=False), None, go_btn, api_name="go" if allow_api else None,
-                                queue=False) \
-            .then(lambda: gr.update(visible=True), None, normal_block, queue=False) \
-            .then(**load_model_args, queue=False).then(**prompt_update_args, queue=False)
-
-        def compare_textbox_fun(x):
-            return gr.Textbox.update(visible=x)
-
-        def compare_column_fun(x):
-            return gr.Column.update(visible=x)
-
-        def compare_prompt_fun(x):
-            return gr.Dropdown.update(visible=x)
-
-        def slider_fun(x):
-            return gr.Slider.update(visible=x)
-
-        compare_checkbox.select(compare_textbox_fun, compare_checkbox, text_output2,
-                                api_name="compare_checkbox" if allow_api else None) \
-            .then(compare_column_fun, compare_checkbox, col_model2) \
-            .then(compare_prompt_fun, compare_checkbox, prompt_type2) \
-            .then(compare_textbox_fun, compare_checkbox, score_text2) \
-            .then(slider_fun, compare_checkbox, max_new_tokens2) \
-            .then(slider_fun, compare_checkbox, min_new_tokens2)
-        # FIXME: add score_res2 in condition, but do better
-
-        # callback for logging flagged input/output
-        callback.setup(inputs_list + [text_output, text_output2] + text_outputs, "flagged_data_points")
-        flag_btn.click(lambda *args: callback.flag(args), inputs_list + [text_output, text_output2] + text_outputs,
-                       None,
-                       preprocess=False,
-                       api_name='flag' if allow_api else None, queue=False)
-        flag_btn_nochat.click(lambda *args: callback.flag(args), inputs_list + [text_output_nochat], None,
-                              preprocess=False,
-                              api_name='flag_nochat' if allow_api else None, queue=False)
-
-        def get_system_info():
-            if is_public:
-                time.sleep(10)  # delay to avoid spam since queue=False
-            return gr.Textbox.update(value=system_info_print())
-
-        system_event = system_btn.click(get_system_info, outputs=system_text,
-                                        api_name='system_info' if allow_api else None, queue=False)
-
-        def get_system_info_dict(system_input1, **kwargs1):
-            if system_input1 != os.getenv("ADMIN_PASS", ""):
-                return json.dumps({})
-            exclude_list = ['admin_pass', 'examples']
-            sys_dict = {k: v for k, v in kwargs1.items() if
-                        isinstance(v, (str, int, bool, float)) and k not in exclude_list}
-            try:
-                sys_dict.update(system_info())
-            except Exception as e:
-                # protection
-                print("Exception: %s" % str(e), flush=True)
-            return json.dumps(sys_dict)
-
-        system_kwargs = all_kwargs.copy()
-        system_kwargs.update(dict(command=str(' '.join(sys.argv))))
-        get_system_info_dict_func = functools.partial(get_system_info_dict, **all_kwargs)
-
-        system_dict_event = system_btn2.click(get_system_info_dict_func,
-                                              inputs=system_input,
-                                              outputs=system_text2,
-                                              api_name='system_info_dict' if allow_api else None,
-                                              queue=False,  # queue to avoid spam
-                                              )
-
-        def get_hash():
-            return kwargs['git_hash']
-
-        system_event = system_btn3.click(get_hash,
-                                         outputs=system_text3,
-                                         api_name='system_hash' if allow_api else None,
-                                         queue=False,
-                                         )
-
-        def get_model_names():
-            key_list = ['base_model', 'prompt_type', 'prompt_dict'] + list(kwargs['other_model_state_defaults'].keys())
-            # don't want to expose backend inference server IP etc.
-            # key_list += ['inference_server']
-            return [{k: x[k] for k in key_list if k in x} for x in model_states]
-
-        models_list_event = system_btn4.click(get_model_names,
-                                              outputs=system_text4,
-                                              api_name='model_names' if allow_api else None,
-                                              queue=False,
-                                              )
-
-        def count_chat_tokens(model_state1, chat1, prompt_type1, prompt_dict1,
-                              system_prompt1, chat_conversation1,
-                              memory_restriction_level1=0,
-                              keep_sources_in_context1=False,
-                              ):
-            if model_state1 and not isinstance(model_state1['tokenizer'], str):
-                tokenizer = model_state1['tokenizer']
-            elif model_state0 and not isinstance(model_state0['tokenizer'], str):
-                tokenizer = model_state0['tokenizer']
-            else:
-                tokenizer = None
-            if tokenizer is not None:
-                langchain_mode1 = 'LLM'
-                add_chat_history_to_context1 = True
-                # fake user message to mimic bot()
-                chat1 = copy.deepcopy(chat1)
-                chat1 = chat1 + [['user_message1', None]]
-                model_max_length1 = tokenizer.model_max_length
-                context1 = history_to_context(chat1,
-                                              langchain_mode=langchain_mode1,
-                                              add_chat_history_to_context=add_chat_history_to_context1,
-                                              prompt_type=prompt_type1,
-                                              prompt_dict=prompt_dict1,
-                                              chat=True,
-                                              model_max_length=model_max_length1,
-                                              memory_restriction_level=memory_restriction_level1,
-                                              keep_sources_in_context=keep_sources_in_context1,
-                                              system_prompt=system_prompt1,
-                                              chat_conversation=chat_conversation1)
-                tokens = tokenizer(context1, return_tensors="pt")['input_ids']
-                if len(tokens.shape) == 1:
-                    return str(tokens.shape[0])
-                elif len(tokens.shape) == 2:
-                    return str(tokens.shape[1])
-                else:
-                    return "N/A"
-            else:
-                return "N/A"
-
-        count_chat_tokens_func = functools.partial(count_chat_tokens,
-                                                   memory_restriction_level1=memory_restriction_level,
-                                                   keep_sources_in_context1=kwargs['keep_sources_in_context'])
-        count_tokens_event = count_chat_tokens_btn.click(fn=count_chat_tokens_func,
-                                                         inputs=[model_state, text_output, prompt_type, prompt_dict,
-                                                                 system_prompt, chat_conversation],
-                                                         outputs=chat_token_count,
-                                                         api_name='count_tokens' if allow_api else None)
-
-        # don't pass text_output, don't want to clear output, just stop it
-        # cancel only stops outer generation, not inner generation or non-generation
-        stop_btn.click(lambda: None, None, None,
-                       cancels=submits1 + submits2 + submits3 + submits4 +
-                               [submit_event_nochat, submit_event_nochat2] +
-                               [eventdb1, eventdb2, eventdb3] +
-                               [eventdb7a, eventdb7, eventdb8a, eventdb8, eventdb9a, eventdb9, eventdb12a, eventdb12] +
-                               db_events +
-                               [eventdbloadla, eventdbloadlb] +
-                               [clear_event] +
-                               [submit_event_nochat_api, submit_event_nochat] +
-                               [load_model_event, load_model_event2] +
-                               [count_tokens_event]
-                       ,
-                       queue=False, api_name='stop' if allow_api else None).then(clear_torch_cache, queue=False)
-
-        if kwargs['auth'] is not None:
-            auth = authf
-            load_func = user_state_setup
-            load_inputs = [my_db_state, requests_state, login_btn, login_btn]
-            load_outputs = [my_db_state, requests_state, login_btn]
-        else:
-            auth = None
-            load_func, load_inputs, load_outputs = None, None, None
-
-        app_js = wrap_js_to_lambda(
-            len(load_inputs) if load_inputs else 0,
-            get_dark_js() if kwargs['dark'] else None,
-            get_heap_js(heap_app_id) if is_heap_analytics_enabled else None)
-
-        load_event = demo.load(fn=load_func, inputs=load_inputs, outputs=load_outputs, _js=app_js)
-
-        if load_func:
-            load_event2 = load_event.then(load_login_func,
-                                          inputs=login_inputs,
-                                          outputs=login_outputs)
-            if not kwargs['large_file_count_mode']:
-                load_event3 = load_event2.then(**get_sources_kwargs)
-                load_event4 = load_event3.then(fn=update_dropdown, inputs=docs_state, outputs=document_choice)
-                load_event5 = load_event4.then(**show_sources_kwargs)
-                load_event6 = load_event5.then(**get_viewable_sources_args)
-                load_event7 = load_event6.then(**viewable_kwargs)
-
-    demo.queue(concurrency_count=kwargs['concurrency_count'], api_open=kwargs['api_open'])
-    favicon_file = "h2o-logo.svg"
-    favicon_path = favicon_file
-    if not os.path.isfile(favicon_file):
-        print("favicon_path1=%s not found" % favicon_file, flush=True)
-        alt_path = os.path.dirname(os.path.abspath(__file__))
-        favicon_path = os.path.join(alt_path, favicon_file)
-        if not os.path.isfile(favicon_path):
-            print("favicon_path2: %s not found in %s" % (favicon_file, alt_path), flush=True)
-            alt_path = os.path.dirname(alt_path)
-            favicon_path = os.path.join(alt_path, favicon_file)
-            if not os.path.isfile(favicon_path):
-                print("favicon_path3: %s not found in %s" % (favicon_file, alt_path), flush=True)
-                favicon_path = None
-
-    if kwargs['prepare_offline_level'] > 0:
-        from src.prepare_offline import go_prepare_offline
-        go_prepare_offline(**locals())
-        return
-
-    scheduler = BackgroundScheduler()
-    scheduler.add_job(func=clear_torch_cache, trigger="interval", seconds=20)
-    if is_public and \
-            kwargs['base_model'] not in non_hf_types:
-        # FIXME: disable for gptj, langchain or gpt4all modify print itself
-        # FIXME: and any multi-threaded/async print will enter model output!
-        scheduler.add_job(func=ping, trigger="interval", seconds=60)
-    if is_public or os.getenv('PING_GPU'):
-        scheduler.add_job(func=ping_gpu, trigger="interval", seconds=60 * 10)
-    scheduler.start()
-
-    # import control
-    if kwargs['langchain_mode'] == 'Disabled' and \
-            os.environ.get("TEST_LANGCHAIN_IMPORT") and \
-            kwargs['base_model'] not in non_hf_types:
-        assert 'gpt_langchain' not in sys.modules, "Dev bug, import of langchain when should not have"
-        assert 'langchain' not in sys.modules, "Dev bug, import of langchain when should not have"
-
-    # set port in case GRADIO_SERVER_PORT was already set in prior main() call,
-    # gradio does not listen if change after import
-    # Keep None if not set so can find an open port above used ports
-    server_port = os.getenv('GRADIO_SERVER_PORT')
-    if server_port is not None:
-        server_port = int(server_port)
-
-    demo.launch(share=kwargs['share'],
-                server_name=kwargs['server_name'],
-                show_error=True,
-                server_port=server_port,
-                favicon_path=favicon_path,
-                prevent_thread_lock=True,
-                auth=auth,
-                auth_message=auth_message,
-                root_path=kwargs['root_path'])
-    if kwargs['verbose'] or not (kwargs['base_model'] in ['gptj', 'gpt4all_llama']):
-        print("Started Gradio Server and/or GUI: server_name: %s port: %s" % (kwargs['server_name'], server_port),
-              flush=True)
-    if kwargs['block_gradio_exit']:
-        demo.block_thread()
-
-
-def show_doc(db1s, selection_docs_state1, requests_state1,
-             langchain_mode1,
-             single_document_choice1,
-             view_raw_text_checkbox1,
-             text_context_list1,
-             dbs1=None,
-             load_db_if_exists1=None,
-             db_type1=None,
-             use_openai_embedding1=None,
-             hf_embedding_model1=None,
-             migrate_embedding_model_or_db1=None,
-             auto_migrate_db1=None,
-             verbose1=False,
-             get_userid_auth1=None,
-             max_raw_chunks=1000000,
-             api=False,
-             n_jobs=-1):
-    file = single_document_choice1
-    document_choice1 = [single_document_choice1]
-    content = None
-    db_documents = []
-    db_metadatas = []
-    if db_type1 in ['chroma', 'chroma_old']:
-        assert langchain_mode1 is not None
-        langchain_mode_paths = selection_docs_state1['langchain_mode_paths']
-        langchain_mode_types = selection_docs_state1['langchain_mode_types']
-        from src.gpt_langchain import set_userid, get_any_db, get_docs_and_meta
-        set_userid(db1s, requests_state1, get_userid_auth1)
-        top_k_docs = -1
-        db = get_any_db(db1s, langchain_mode1, langchain_mode_paths, langchain_mode_types,
-                        dbs=dbs1,
-                        load_db_if_exists=load_db_if_exists1,
-                        db_type=db_type1,
-                        use_openai_embedding=use_openai_embedding1,
-                        hf_embedding_model=hf_embedding_model1,
-                        migrate_embedding_model=migrate_embedding_model_or_db1,
-                        auto_migrate_db=auto_migrate_db1,
-                        for_sources_list=True,
-                        verbose=verbose1,
-                        n_jobs=n_jobs,
-                        )
-        query_action = False  # long chunks like would be used for summarize
-        # the below is as or filter, so will show doc or by chunk, unrestricted
-        from langchain.vectorstores import Chroma
-        if isinstance(db, Chroma):
-            # chroma >= 0.4
-            if view_raw_text_checkbox1:
-                one_filter = \
-                    [{"source": {"$eq": x}, "chunk_id": {"$gte": 0}} if query_action else {"source": {"$eq": x},
-                                                                                           "chunk_id": {
-                                                                                               "$gte": -1}}
-                     for x in document_choice1][0]
-            else:
-                one_filter = \
-                    [{"source": {"$eq": x}, "chunk_id": {"$gte": 0}} if query_action else {"source": {"$eq": x},
-                                                                                           "chunk_id": {
-                                                                                               "$eq": -1}}
-                     for x in document_choice1][0]
-            filter_kwargs = dict(filter={"$and": [dict(source=one_filter['source']),
-                                                  dict(chunk_id=one_filter['chunk_id'])]})
-        else:
-            # migration for chroma < 0.4
-            one_filter = \
-                [{"source": {"$eq": x}, "chunk_id": {"$gte": 0}} if query_action else {"source": {"$eq": x},
-                                                                                       "chunk_id": {
-                                                                                           "$eq": -1}}
-                 for x in document_choice1][0]
-            if view_raw_text_checkbox1:
-                # like or, full raw all chunk types
-                filter_kwargs = dict(filter=one_filter)
-            else:
-                filter_kwargs = dict(filter={"$and": [dict(source=one_filter['source']),
-                                                      dict(chunk_id=one_filter['chunk_id'])]})
-        db_documents, db_metadatas = get_docs_and_meta(db, top_k_docs, filter_kwargs=filter_kwargs,
-                                                       text_context_list=text_context_list1)
-        # order documents
-        from langchain.docstore.document import Document
-        docs_with_score = [(Document(page_content=result[0], metadata=result[1] or {}), 0)
-                           for result in zip(db_documents, db_metadatas)]
-        doc_chunk_ids = [x.get('chunk_id', -1) for x in db_metadatas]
-        doc_page_ids = [x.get('page', 0) for x in db_metadatas]
-        doc_hashes = [x.get('doc_hash', 'None') for x in db_metadatas]
-        docs_with_score = [x for hx, px, cx, x in
-                           sorted(zip(doc_hashes, doc_page_ids, doc_chunk_ids, docs_with_score),
-                                  key=lambda x: (x[0], x[1], x[2]))
-                           # if cx == -1
-                           ]
-        db_metadatas = [x[0].metadata for x in docs_with_score][:max_raw_chunks]
-        db_documents = [x[0].page_content for x in docs_with_score][:max_raw_chunks]
-        # done reordering
-        if view_raw_text_checkbox1:
-            content = [dict_to_html(x) + '\n' + text_to_html(y) for x, y in zip(db_metadatas, db_documents)]
-        else:
-            content = [text_to_html(y) for x, y in zip(db_metadatas, db_documents)]
-        content = '\n'.join(content)
-        content = f"""<!DOCTYPE html>
-<html>
-<head>
-<title>{file}</title>
-</head>
-<body>
-{content}
-</body>
-</html>"""
-    if api:
-        if view_raw_text_checkbox1:
-            return dict(contents=db_documents, metadatas=db_metadatas)
-        else:
-            contents = [text_to_html(y, api=api) for y in db_documents]
-            metadatas = [dict_to_html(x, api=api) for x in db_metadatas]
-            return dict(contents=contents, metadatas=metadatas)
-    else:
-        assert not api, "API mode for get_document only supported for chroma"
-
-    dummy1 = gr.update(visible=False, value=None)
-    # backup is text dump of db version
-    if content:
-        dummy_ret = dummy1, dummy1, dummy1, dummy1, gr.update(visible=True, value=content)
-        if view_raw_text_checkbox1:
-            return dummy_ret
-    else:
-        dummy_ret = dummy1, dummy1, dummy1, dummy1, dummy1
-
-    if not isinstance(file, str):
-        return dummy_ret
-
-    if file.lower().endswith('.html') or file.lower().endswith('.mhtml') or file.lower().endswith('.htm') or \
-            file.lower().endswith('.xml'):
-        try:
-            with open(file, 'rt') as f:
-                content = f.read()
-            return gr.update(visible=True, value=content), dummy1, dummy1, dummy1, dummy1
-        except:
-            return dummy_ret
-
-    if file.lower().endswith('.md'):
-        try:
-            with open(file, 'rt') as f:
-                content = f.read()
-            return dummy1, dummy1, dummy1, gr.update(visible=True, value=content), dummy1
-        except:
-            return dummy_ret
-
-    if file.lower().endswith('.py'):
-        try:
-            with open(file, 'rt') as f:
-                content = f.read()
-            content = f"```python\n{content}\n```"
-            return dummy1, dummy1, dummy1, gr.update(visible=True, value=content), dummy1
-        except:
-            return dummy_ret
-
-    if file.lower().endswith('.txt') or file.lower().endswith('.rst') or file.lower().endswith(
-            '.rtf') or file.lower().endswith('.toml'):
-        try:
-            with open(file, 'rt') as f:
-                content = f.read()
-            content = f"```text\n{content}\n```"
-            return dummy1, dummy1, dummy1, gr.update(visible=True, value=content), dummy1
-        except:
-            return dummy_ret
-
-    func = None
-    if file.lower().endswith(".csv"):
-        func = pd.read_csv
-    elif file.lower().endswith(".pickle"):
-        func = pd.read_pickle
-    elif file.lower().endswith(".xls") or file.lower().endswith("xlsx"):
-        func = pd.read_excel
-    elif file.lower().endswith('.json'):
-        func = pd.read_json
-    # pandas doesn't show full thing, even if html view shows broken things still better
-    # elif file.lower().endswith('.xml'):
-    #    func = pd.read_xml
-    if func is not None:
-        try:
-            df = func(file).head(100)
-        except:
-            return dummy_ret
-        return dummy1, gr.update(visible=True, value=df), dummy1, dummy1, dummy1
-    port = int(os.getenv('GRADIO_SERVER_PORT', '7860'))
-    import pathlib
-    absolute_path_string = os.path.abspath(file)
-    url_path = pathlib.Path(absolute_path_string).as_uri()
-    url = get_url(absolute_path_string, from_str=True)
-    img_url = url.replace("""<a href=""", """<img src=""")
-    if file.lower().endswith('.png') or file.lower().endswith('.jpg') or file.lower().endswith('.jpeg'):
-        return gr.update(visible=True, value=img_url), dummy1, dummy1, dummy1, dummy1
-    elif file.lower().endswith('.pdf') or 'arxiv.org/pdf' in file:
-
-        # account for when use `wget -b -m -k -o wget.log -e robots=off`
-        if url_alive('http://' + file):
-            file = 'http://' + file
-        if url_alive('https://' + file):
-            file = 'https://' + file
-
-        if file.lower().startswith('http') or file.lower().startswith('https'):
-            # if file is online, then might as well use google(?)
-            document1 = file
-            return gr.update(visible=True,
-                             value=f"""<iframe width="1000" height="800" src="https://docs.google.com/viewerng/viewer?url={document1}&embedded=true" frameborder="0" height="100%" width="100%">
-</iframe>
-"""), dummy1, dummy1, dummy1, dummy1
-        else:
-            # FIXME: This doesn't work yet, just return dummy result for now
-            if False:
-                ip = get_local_ip()
-                document1 = url_path.replace('file://', f'http://{ip}:{port}/')
-                # document1 = url
-                return gr.update(visible=True, value=f"""<object data="{document1}" type="application/pdf">
-<iframe src="https://docs.google.com/viewer?url={document1}&embedded=true"></iframe>
-</object>"""), dummy1, dummy1, dummy1, dummy1
-            else:
-                return dummy_ret
-    else:
-        return dummy_ret
-
-
-def get_inputs_list(inputs_dict, model_lower, model_id=1):
-    """
-    map gradio objects in locals() to inputs for evaluate().
-    :param inputs_dict:
-    :param model_lower:
-    :param model_id: Which model (1 or 2) of 2
-    :return:
-    """
-    inputs_list_names = list(inspect.signature(evaluate).parameters)
-    inputs_list = []
-    inputs_dict_out = {}
-    for k in inputs_list_names:
-        if k == 'kwargs':
-            continue
-        if k in input_args_list + inputs_kwargs_list:
-            # these are added at use time for args or partial for kwargs, not taken as input
-            continue
-        if 'mbart-' not in model_lower and k in ['src_lang', 'tgt_lang']:
-            continue
-        if model_id == 2:
-            if k == 'prompt_type':
-                k = 'prompt_type2'
-            if k == 'prompt_used':
-                k = 'prompt_used2'
-            if k == 'max_new_tokens':
-                k = 'max_new_tokens2'
-            if k == 'min_new_tokens':
-                k = 'min_new_tokens2'
-        inputs_list.append(inputs_dict[k])
-        inputs_dict_out[k] = inputs_dict[k]
-    return inputs_list, inputs_dict_out
-
-
-def update_user_db_gr(file, db1s, selection_docs_state1, requests_state1,
-                      langchain_mode, chunk, chunk_size, embed,
-
-                      image_loaders,
-                      pdf_loaders,
-                      url_loaders,
-                      jq_schema,
-                      h2ogpt_key,
-
-                      captions_model=None,
-                      caption_loader=None,
-                      doctr_loader=None,
-
-                      dbs=None,
-                      get_userid_auth=None,
-                      **kwargs):
-    valid_key = is_valid_key(kwargs.pop('enforce_h2ogpt_api_key', None),
-                             kwargs.pop('h2ogpt_api_keys', []), h2ogpt_key,
-                             requests_state1=requests_state1)
-    if not valid_key:
-        raise ValueError(invalid_key_msg)
-    loaders_dict, captions_model = gr_to_lg(image_loaders,
-                                            pdf_loaders,
-                                            url_loaders,
-                                            captions_model=captions_model,
-                                            **kwargs,
-                                            )
-    if jq_schema is None:
-        jq_schema = kwargs['jq_schema0']
-    loaders_dict.update(dict(captions_model=captions_model,
-                             caption_loader=caption_loader,
-                             doctr_loader=doctr_loader,
-                             jq_schema=jq_schema,
-                             ))
-    kwargs.pop('image_loaders_options0', None)
-    kwargs.pop('pdf_loaders_options0', None)
-    kwargs.pop('url_loaders_options0', None)
-    kwargs.pop('jq_schema0', None)
-    if not embed:
-        kwargs['use_openai_embedding'] = False
-        kwargs['hf_embedding_model'] = 'fake'
-        kwargs['migrate_embedding_model'] = False
-
-    from src.gpt_langchain import update_user_db
-    return update_user_db(file, db1s, selection_docs_state1, requests_state1,
-                          langchain_mode=langchain_mode, chunk=chunk, chunk_size=chunk_size,
-                          **loaders_dict,
-                          dbs=dbs,
-                          get_userid_auth=get_userid_auth,
-                          **kwargs)
-
-
-def get_sources_gr(db1s, selection_docs_state1, requests_state1, langchain_mode, dbs=None, docs_state0=None,
-                   load_db_if_exists=None,
-                   db_type=None,
-                   use_openai_embedding=None,
-                   hf_embedding_model=None,
-                   migrate_embedding_model=None,
-                   auto_migrate_db=None,
-                   verbose=False,
-                   get_userid_auth=None,
-                   api=False,
-                   n_jobs=-1):
-    from src.gpt_langchain import get_sources
-    sources_file, source_list, num_chunks, db = \
-        get_sources(db1s, selection_docs_state1, requests_state1, langchain_mode,
-                    dbs=dbs, docs_state0=docs_state0,
-                    load_db_if_exists=load_db_if_exists,
-                    db_type=db_type,
-                    use_openai_embedding=use_openai_embedding,
-                    hf_embedding_model=hf_embedding_model,
-                    migrate_embedding_model=migrate_embedding_model,
-                    auto_migrate_db=auto_migrate_db,
-                    verbose=verbose,
-                    get_userid_auth=get_userid_auth,
-                    n_jobs=n_jobs,
-                    )
-    if api:
-        return source_list
-    if langchain_mode in langchain_modes_non_db:
-        doc_counts_str = "LLM Mode\nNo Collection"
-    else:
-        doc_counts_str = "Collection: %s\nDocs: %d\nChunks: %d" % (langchain_mode, len(source_list), num_chunks)
-    return sources_file, source_list, doc_counts_str
-
-
-def get_source_files_given_langchain_mode_gr(db1s, selection_docs_state1, requests_state1,
-                                             langchain_mode,
-                                             dbs=None,
-                                             load_db_if_exists=None,
-                                             db_type=None,
-                                             use_openai_embedding=None,
-                                             hf_embedding_model=None,
-                                             migrate_embedding_model=None,
-                                             auto_migrate_db=None,
-                                             verbose=False,
-                                             get_userid_auth=None,
-                                             n_jobs=-1):
-    from src.gpt_langchain import get_source_files_given_langchain_mode
-    return get_source_files_given_langchain_mode(db1s, selection_docs_state1, requests_state1, None,
-                                                 langchain_mode,
-                                                 dbs=dbs,
-                                                 load_db_if_exists=load_db_if_exists,
-                                                 db_type=db_type,
-                                                 use_openai_embedding=use_openai_embedding,
-                                                 hf_embedding_model=hf_embedding_model,
-                                                 migrate_embedding_model=migrate_embedding_model,
-                                                 auto_migrate_db=auto_migrate_db,
-                                                 verbose=verbose,
-                                                 get_userid_auth=get_userid_auth,
-                                                 delete_sources=False,
-                                                 n_jobs=n_jobs)
-
-
-def del_source_files_given_langchain_mode_gr(db1s, selection_docs_state1, requests_state1, document_choice1,
-                                             langchain_mode,
-                                             dbs=None,
-                                             load_db_if_exists=None,
-                                             db_type=None,
-                                             use_openai_embedding=None,
-                                             hf_embedding_model=None,
-                                             migrate_embedding_model=None,
-                                             auto_migrate_db=None,
-                                             verbose=False,
-                                             get_userid_auth=None,
-                                             n_jobs=-1):
-    from src.gpt_langchain import get_source_files_given_langchain_mode
-    return get_source_files_given_langchain_mode(db1s, selection_docs_state1, requests_state1, document_choice1,
-                                                 langchain_mode,
-                                                 dbs=dbs,
-                                                 load_db_if_exists=load_db_if_exists,
-                                                 db_type=db_type,
-                                                 use_openai_embedding=use_openai_embedding,
-                                                 hf_embedding_model=hf_embedding_model,
-                                                 migrate_embedding_model=migrate_embedding_model,
-                                                 auto_migrate_db=auto_migrate_db,
-                                                 verbose=verbose,
-                                                 get_userid_auth=get_userid_auth,
-                                                 delete_sources=True,
-                                                 n_jobs=n_jobs)
-
-
-def update_and_get_source_files_given_langchain_mode_gr(db1s,
-                                                        selection_docs_state,
-                                                        requests_state,
-                                                        langchain_mode, chunk, chunk_size,
-
-                                                        image_loaders,
-                                                        pdf_loaders,
-                                                        url_loaders,
-                                                        jq_schema,
-
-                                                        captions_model=None,
-                                                        caption_loader=None,
-                                                        doctr_loader=None,
-
-                                                        dbs=None, first_para=None,
-                                                        hf_embedding_model=None,
-                                                        use_openai_embedding=None,
-                                                        migrate_embedding_model=None,
-                                                        auto_migrate_db=None,
-                                                        text_limit=None,
-                                                        db_type=None, load_db_if_exists=None,
-                                                        n_jobs=None, verbose=None, get_userid_auth=None,
-                                                        image_loaders_options0=None,
-                                                        pdf_loaders_options0=None,
-                                                        url_loaders_options0=None,
-                                                        jq_schema0=None):
-    from src.gpt_langchain import update_and_get_source_files_given_langchain_mode
-
-    loaders_dict, captions_model = gr_to_lg(image_loaders,
-                                            pdf_loaders,
-                                            url_loaders,
-                                            image_loaders_options0=image_loaders_options0,
-                                            pdf_loaders_options0=pdf_loaders_options0,
-                                            url_loaders_options0=url_loaders_options0,
-                                            captions_model=captions_model,
-                                            )
-    if jq_schema is None:
-        jq_schema = jq_schema0
-    loaders_dict.update(dict(captions_model=captions_model,
-                             caption_loader=caption_loader,
-                             doctr_loader=doctr_loader,
-                             jq_schema=jq_schema,
-                             ))
-
-    return update_and_get_source_files_given_langchain_mode(db1s,
-                                                            selection_docs_state,
-                                                            requests_state,
-                                                            langchain_mode, chunk, chunk_size,
-                                                            **loaders_dict,
-                                                            dbs=dbs, first_para=first_para,
-                                                            hf_embedding_model=hf_embedding_model,
-                                                            use_openai_embedding=use_openai_embedding,
-                                                            migrate_embedding_model=migrate_embedding_model,
-                                                            auto_migrate_db=auto_migrate_db,
-                                                            text_limit=text_limit,
-                                                            db_type=db_type, load_db_if_exists=load_db_if_exists,
-                                                            n_jobs=n_jobs, verbose=verbose,
-                                                            get_userid_auth=get_userid_auth)
-
-
-def set_userid_gr(db1s, requests_state1, get_userid_auth):
-    from src.gpt_langchain import set_userid
-    return set_userid(db1s, requests_state1, get_userid_auth)
-
-
-def set_dbid_gr(db1):
-    from src.gpt_langchain import set_dbid
-    return set_dbid(db1)
-
-
-def set_userid_direct_gr(db1s, userid, username):
-    from src.gpt_langchain import set_userid_direct
-    return set_userid_direct(db1s, userid, username)
diff --git a/spaces/h2oai/wave-tour/examples/ml_dai_categorical.py b/spaces/h2oai/wave-tour/examples/ml_dai_categorical.py
deleted file mode 100644
index a674a18da27f84c13f58184902123d23aeb9cec0..0000000000000000000000000000000000000000
--- a/spaces/h2oai/wave-tour/examples/ml_dai_categorical.py
+++ /dev/null
@@ -1,190 +0,0 @@
-# WaveML / DAI / Categorical
-# Configure categorical columns for Wave Models built using Driverless AI.
-# ---
-import os
-
-from h2o_wave import main, app, Q, copy_expando, ui
-from h2o_wave_ml import build_model, ModelType
-from h2o_wave_ml.utils import list_dai_instances
-
-from sklearn.datasets import load_wine
-from sklearn.model_selection import train_test_split
-
-STEAM_URL = os.environ.get('STEAM_URL')
-MLOPS_URL = os.environ.get('MLOPS_URL')
-
-DATASET_TEXT = '''The sample dataset used is the
-    <a href="https://scikit-learn.org/stable/modules/generated/sklearn.datasets.load_wine.html" target="_blank">wine dataset</a>.'''
-STEAM_TEXT = f'''No Driverless AI instances available. You may create one in 
-    <a href="{STEAM_URL}/#/driverless/instances" target="_blank">AI Engines</a> and refresh the page.'''
-
-
-def dai_experiment_url(instance_id: str, instance_name: str):
-    # URL link to Driverless AI experiment
-    return f'''**Driverless AI Experiment:**
-        <a href="{STEAM_URL}/oidc-login-start?forward=/proxy/driverless/{instance_id}/openid/callback" target="_blank">{instance_name}</a>'''
-
-
-def mlops_deployment_url(project_id: str):
-    # URL link to MLOps deployment
-    return f'**MLOps Deployment:** <a href="{MLOPS_URL}/projects/{project_id}" target="_blank">{project_id}'
-
-
-def form_unsupported():
-    # display when app is not running on cloud
-    return [
-        ui.text('''This example requires access to Driverless AI running on
-            <a href="https://h2oai.github.io/h2o-ai-cloud" target="_blank">H2O AI Cloud</a> 
-            and does not support standalone app instances.'''),
-        ui.text('''Sign up at <a href="https://h2o.ai/free" target="_blank">https://h2o.ai/free</a>
-            to run apps on cloud.''')
-    ]
-
-
-def form_default(q: Q):
-    # display when app is initialized
-    return [
-        ui.text(content=DATASET_TEXT),
-        ui.dropdown(name='dai_instance_id', label='Select Driverless AI instance', value=q.client.dai_instance_id,
-                    choices=q.client.choices_dai_instances, required=True),
-        ui.text(content=STEAM_TEXT, visible=q.client.disable_training),
-        ui.dropdown(name='categorical_columns', label='Select categorical columns',
-                    choices=q.client.column_choices, values=[]),
-        ui.buttons(items=[
-            ui.button(name='train', label='Train', primary=True, disabled=q.client.disable_training),
-            ui.button(name='predict', label='Predict', primary=True, disabled=True),
-        ])
-    ]
-
-
-def form_training_progress(q: Q):
-    # display when model training is in progress
-    return [
-        ui.text(content=DATASET_TEXT),
-        ui.dropdown(name='dai_instance_id', label='Select Driverless AI instance', value=q.client.dai_instance_id,
-                    choices=q.client.choices_dai_instances, required=True),
-        ui.dropdown(name='categorical_columns', label='Select categorical columns',
-                    choices=q.client.column_choices, values=q.client.categorical_columns),
-        ui.buttons(items=[
-            ui.button(name='train', label='Train', primary=True, disabled=True),
-            ui.button(name='predict', label='Predict', primary=True, disabled=True)
-        ]),
-        ui.progress(label='Training in progress...', caption='This can take a few minutes...'),
-        ui.text(content=q.client.model_details)
-    ]
-
-
-def form_training_completed(q: Q):
-    # display when model training is completed
-    return [
-        ui.text(content=DATASET_TEXT),
-        ui.dropdown(name='dai_instance_id', label='Select Driverless AI instance', value=q.client.dai_instance_id,
-                    choices=q.client.choices_dai_instances, required=True),
-        ui.dropdown(name='categorical_columns', label='Select categorical columns',
-                    choices=q.client.column_choices, values=q.client.categorical_columns),
-        ui.buttons(items=[
-            ui.button(name='train', label='Train', primary=True),
-            ui.button(name='predict', label='Predict', primary=True)
-        ]),
-        ui.message_bar(type='success', text='Training successfully completed!'),
-        ui.text(content=q.client.model_details)
-    ]
-
-
-def form_prediction_completed(q: Q):
-    # display when model prediction is completed
-    return [
-        ui.text(content=DATASET_TEXT),
-        ui.dropdown(name='dai_instance_id', label='Select Driverless AI instance', value=q.client.dai_instance_id,
-                    choices=q.client.choices_dai_instances, required=True),
-        ui.dropdown(name='categorical_columns', label='Select categorical columns',
-                    choices=q.client.column_choices, values=q.client.categorical_columns),
-        ui.buttons(items=[
-            ui.button(name='train', label='Train', primary=True),
-            ui.button(name='predict', label='Predict', primary=True)
-        ]),
-        ui.message_bar(type='success', text='Prediction successfully completed!'),
-        ui.text(content=q.client.model_details),
-        ui.text(content=f'''**Example predictions:** <br />
-            {q.client.preds[0]} <br /> {q.client.preds[1]} <br /> {q.client.preds[2]}''')
-    ]
-
-
-@app('/demo')
-async def serve(q: Q):
-    if 'H2O_CLOUD_ENVIRONMENT' not in os.environ:
-        # show appropriate message if app is not running on cloud
-        q.page['example'] = ui.form_card(
-            box='1 1 -1 -1',
-            items=form_unsupported()
-        )
-    elif q.args.train:
-        # get DAI instance name
-        copy_expando(q.args, q.client)
-
-        for dai_instance in q.client.dai_instances:
-            if dai_instance['id'] == int(q.client.dai_instance_id):
-                q.client.dai_instance_name = dai_instance['name']
-
-        # set DAI model details
-        q.client.model_details = dai_experiment_url(q.client.dai_instance_id, q.client.dai_instance_name)
-
-        # show training progress and details
-        q.page['example'].items = form_training_progress(q)
-        await q.page.save()
-
-        # train WaveML Model using Driverless AI
-        q.client.wave_model = await q.run(
-            func=build_model,
-            train_df=q.client.train_df,
-            target_column='target',
-            model_type=ModelType.DAI,
-            categorical_columns=q.client.categorical_columns,
-            refresh_token=q.auth.refresh_token,
-            _steam_dai_instance_name=q.client.dai_instance_name,
-            _dai_accuracy=1,
-            _dai_time=1,
-            _dai_interpretability=10
-        )
-
-        # update DAI model details
-        q.client.project_id = q.client.wave_model.project_id
-        q.client.model_details += f'<br />{mlops_deployment_url(q.client.project_id)}'
-
-        # show prediction option
-        q.page['example'].items = form_training_completed(q)
-    elif q.args.predict:
-        # predict on test data
-        q.client.preds = q.client.wave_model.predict(test_df=q.client.test_df)
-
-        # show predictions
-        q.page['example'].items = form_prediction_completed(q)
-    else:
-        # prepare sample train and test dataframes
-        data = load_wine(as_frame=True)['frame']
-        q.client.train_df, q.client.test_df = train_test_split(data, train_size=0.8)
-
-        # columns
-        q.client.column_choices = [ui.choice(x, x) for x in q.client.train_df.columns]
-
-        # DAI instances
-        q.client.dai_instances = list_dai_instances(refresh_token=q.auth.refresh_token)
-        q.client.choices_dai_instances = [
-            ui.choice(
-                name=str(x['id']),
-                label=f'{x["name"]} ({x["status"].capitalize()})',
-                disabled=x['status'] != 'running'
-            ) for x in q.client.dai_instances
-        ]
-
-        running_dai_instances = [x['id'] for x in q.client.dai_instances if x['status'] == 'running']
-        q.client.disable_training = False if running_dai_instances else True
-        q.client.dai_instance_id = str(running_dai_instances[0]) if running_dai_instances else ''
-
-        # display ui
-        q.page['example'] = ui.form_card(
-            box='1 1 -1 -1',
-            items=form_default(q)
-        )
-
-    await q.page.save()
diff --git a/spaces/h2oai/wave-tour/examples/table.py b/spaces/h2oai/wave-tour/examples/table.py
deleted file mode 100644
index aabe6d3ae0c6e96b312266de0be06974fbea629f..0000000000000000000000000000000000000000
--- a/spaces/h2oai/wave-tour/examples/table.py
+++ /dev/null
@@ -1,81 +0,0 @@
-# Table
-# Use a #table to display tabular data.
-# ---
-import random
-
-from faker import Faker
-
-from h2o_wave import main, app, Q, ui
-
-fake = Faker()
-
-_id = 0
-
-
-class Issue:
-    def __init__(self, text: str, status: str, progress: float, icon: str, state: str, created: str):
-        global _id
-        _id += 1
-        self.id = f'I{_id}'
-        self.text = text
-        self.status = status
-        self.views = 0
-        self.progress = progress
-        self.icon = icon
-        self.created = created
-        self.state = state
-
-
-# Create some issues
-issues = [
-    Issue(
-        text=fake.sentence(),
-        status=('Closed' if i % 2 == 0 else 'Open'),
-        progress=random.random(),
-        icon=('BoxCheckmarkSolid' if random.random() > 0.5 else 'BoxMultiplySolid'),
-        state=('RUNNING' if random.random() > 0.5 else 'DONE,SUCCESS'),
-        created='1655927271') for i in range(100)
-]
-
-# Create columns for our issue table.
-columns = [
-    ui.table_column(name='text', label='Issue', sortable=True, searchable=True, max_width='300', cell_overflow='wrap'),
-    ui.table_column(name='status', label='Status', filterable=True),
-    ui.table_column(name='done', label='Done', cell_type=ui.icon_table_cell_type()),
-    ui.table_column(name='views', label='Views', sortable=True, data_type='number'),
-    ui.table_column(name='progress', label='Progress', cell_type=ui.progress_table_cell_type()),
-    ui.table_column(name='tag', label='State', min_width='170px', cell_type=ui.tag_table_cell_type(name='tags', tags=[
-                    ui.tag(label='RUNNING', color='#D2E3F8'),
-                    ui.tag(label='DONE', color='$red'),
-                    ui.tag(label='SUCCESS', color='$mint'),
-                    ]
-    )),
-    ui.table_column(name='created', label='Created', sortable=True, data_type='time'),
-]
-
-
-@app('/demo')
-async def serve(q: Q):
-    if q.args.issues:
-        q.page['form'] = ui.form_card(box='1 1 -1 -1', items=[
-            ui.text(f'You clicked on: {q.args.issues}'),
-            ui.button(name='back', label='Back'),
-        ])
-    else:
-        q.page['form'] = ui.form_card(box='1 1 -1 -1', items=[
-            ui.table(
-                name='issues',
-                columns=columns,
-                rows=[ui.table_row(
-                    name=issue.id,
-                    cells=[issue.text, issue.status, issue.icon, str(issue.views), str(issue.progress),
-                          issue.state, issue.created]
-                ) for issue in issues],
-                groupable=True,
-                downloadable=True,
-                resettable=True,
-                height='600px'
-            )
-        ])
-
-    await q.page.save()
diff --git a/spaces/h2oai/wave-tour/examples/table_sort.py b/spaces/h2oai/wave-tour/examples/table_sort.py
deleted file mode 100644
index 42074549d8441d70752498ffaa3ea0728b9198b8..0000000000000000000000000000000000000000
--- a/spaces/h2oai/wave-tour/examples/table_sort.py
+++ /dev/null
@@ -1,59 +0,0 @@
-# Table / Sort
-# Allow sorting a #table by specific columns.
-# ---
-import random
-from faker import Faker
-from h2o_wave import main, app, Q, ui
-
-fake = Faker()
-
-_id = 0
-
-
-class Issue:
-    def __init__(self, text: str, status: str, progress: float, icon: str, notifications: str):
-        global _id
-        _id += 1
-        self.id = f'I{_id}'
-        self.text = text
-        self.status = status
-        self.views = 0
-        self.progress = progress
-        self.icon = icon
-        self.notifications = notifications
-
-
-# Create some issues
-issues = [
-    Issue(
-        text=fake.sentence(),
-        status=('Closed' if i % 2 == 0 else 'Open'),
-        progress=random.random(),
-        icon=('BoxCheckmarkSolid' if random.random() > 0.5 else 'BoxMultiplySolid'),
-        notifications=('Off' if random.random() > 0.5 else 'On')) for i in range(100)
-]
-
-# Create columns for our issue table.
-columns = [
-    ui.table_column(name='text', label='Issue', sortable=True, ),
-    ui.table_column(name='status', label='Status'),
-    ui.table_column(name='notifications', label='Notifications'),
-    ui.table_column(name='done', label='Done', cell_type=ui.icon_table_cell_type()),
-    ui.table_column(name='views', label='Views', sortable=True),
-    ui.table_column(name='progress', label='Progress', cell_type=ui.progress_table_cell_type()),
-]
-
-
-@app('/demo')
-async def serve(q: Q):
-    q.page['form'] = ui.form_card(box='1 1 -1 7', items=[
-        ui.table(
-            name='issues',
-            columns=columns,
-            rows=[ui.table_row(
-                name=issue.id,
-                cells=[issue.text, issue.status, issue.notifications, issue.icon, str(issue.views),
-                       str(issue.progress)]) for issue in issues],
-        )
-    ])
-    await q.page.save()
diff --git a/spaces/hamacojr/CAT-Seg/datasets/prepare_coco_stuff.py b/spaces/hamacojr/CAT-Seg/datasets/prepare_coco_stuff.py
deleted file mode 100644
index ba1a3671ff982c409b12d3e7d21f438a11f530e9..0000000000000000000000000000000000000000
--- a/spaces/hamacojr/CAT-Seg/datasets/prepare_coco_stuff.py
+++ /dev/null
@@ -1,205 +0,0 @@
-import os
-import os.path as osp
-from pathlib import Path
-import tqdm
-from glob import glob
-
-import numpy as np
-from PIL import Image
-
-COCO_CATEGORIES = [{'color': [220, 20, 60], 'isthing': 1, 'id': 0, 'name': 'person', 'trainId': 0}, 
-                   {'color': [119, 11, 32], 'isthing': 1, 'id': 1, 'name': 'bicycle', 'trainId': 1}, 
-                   {'color': [0, 0, 142], 'isthing': 1, 'id': 2, 'name': 'car', 'trainId': 2}, 
-                   {'color': [0, 0, 230], 'isthing': 1, 'id': 3, 'name': 'motorcycle', 'trainId': 3},
-                   {'color': [106, 0, 228], 'isthing': 1, 'id': 4, 'name': 'airplane', 'trainId': 4}, 
-                   {'color': [0, 60, 100], 'isthing': 1, 'id': 5, 'name': 'bus', 'trainId': 5}, 
-                   {'color': [0, 80, 100], 'isthing': 1, 'id': 6, 'name': 'train', 'trainId': 6},
-                   {'color': [0, 0, 70], 'isthing': 1, 'id': 7, 'name': 'truck', 'trainId': 7},
-                   {'color': [0, 0, 192], 'isthing': 1, 'id': 8, 'name': 'boat', 'trainId': 8}, 
-                   {'color': [250, 170, 30], 'isthing': 1, 'id': 9, 'name': 'traffic light', 'trainId': 9}, 
-                   {'color': [100, 170, 30], 'isthing': 1, 'id': 10, 'name': 'fire hydrant', 'trainId': 10},
-                   {'color': [220, 220, 0], 'isthing': 1, 'id': 12, 'name': 'stop sign', 'trainId': 11},
-                   {'color': [175, 116, 175], 'isthing': 1, 'id': 13, 'name': 'parking meter', 'trainId': 12},
-                   {'color': [250, 0, 30], 'isthing': 1, 'id': 14, 'name': 'bench', 'trainId': 13},
-                   {'color': [165, 42, 42], 'isthing': 1, 'id': 15, 'name': 'bird', 'trainId': 14},
-                   {'color': [255, 77, 255], 'isthing': 1, 'id': 16, 'name': 'cat', 'trainId': 15},
-                   {'color': [0, 226, 252], 'isthing': 1, 'id': 17, 'name': 'dog', 'trainId': 16},
-                   {'color': [182, 182, 255], 'isthing': 1, 'id': 18, 'name': 'horse', 'trainId': 17},
-                   {'color': [0, 82, 0], 'isthing': 1, 'id': 19, 'name': 'sheep', 'trainId': 18},
-                   {'color': [120, 166, 157], 'isthing': 1, 'id': 20, 'name': 'cow', 'trainId': 19},
-                   {'color': [110, 76, 0], 'isthing': 1, 'id': 21, 'name': 'elephant', 'trainId': 20},
-                   {'color': [174, 57, 255], 'isthing': 1, 'id': 22, 'name': 'bear', 'trainId': 21},
-                   {'color': [199, 100, 0], 'isthing': 1, 'id': 23, 'name': 'zebra', 'trainId': 22},
-                   {'color': [72, 0, 118], 'isthing': 1, 'id': 24, 'name': 'giraffe', 'trainId': 23},
-                   {'color': [255, 179, 240], 'isthing': 1, 'id': 26, 'name': 'backpack', 'trainId': 24},
-                   {'color': [0, 125, 92], 'isthing': 1, 'id': 27, 'name': 'umbrella', 'trainId': 25},
-                   {'color': [209, 0, 151], 'isthing': 1, 'id': 30, 'name': 'handbag', 'trainId': 26},
-                   {'color': [188, 208, 182], 'isthing': 1, 'id': 31, 'name': 'tie', 'trainId': 27},
-                   {'color': [0, 220, 176], 'isthing': 1, 'id': 32, 'name': 'suitcase', 'trainId': 28},
-                   {'color': [255, 99, 164], 'isthing': 1, 'id': 33, 'name': 'frisbee', 'trainId': 29},
-                   {'color': [92, 0, 73], 'isthing': 1, 'id': 34, 'name': 'skis', 'trainId': 30},
-                   {'color': [133, 129, 255], 'isthing': 1, 'id': 35, 'name': 'snowboard', 'trainId': 31},
-                   {'color': [78, 180, 255], 'isthing': 1, 'id': 36, 'name': 'sports ball', 'trainId': 32},
-                   {'color': [0, 228, 0], 'isthing': 1, 'id': 37, 'name': 'kite', 'trainId': 33},
-                   {'color': [174, 255, 243], 'isthing': 1, 'id': 38, 'name': 'baseball bat', 'trainId': 34},
-                   {'color': [45, 89, 255], 'isthing': 1, 'id': 39, 'name': 'baseball glove', 'trainId': 35},
-                   {'color': [134, 134, 103], 'isthing': 1, 'id': 40, 'name': 'skateboard', 'trainId': 36},
-                   {'color': [145, 148, 174], 'isthing': 1, 'id': 41, 'name': 'surfboard', 'trainId': 37},
-                   {'color': [255, 208, 186], 'isthing': 1, 'id': 42, 'name': 'tennis racket', 'trainId': 38},
-                   {'color': [197, 226, 255], 'isthing': 1, 'id': 43, 'name': 'bottle', 'trainId': 39},
-                   {'color': [171, 134, 1], 'isthing': 1, 'id': 45, 'name': 'wine glass', 'trainId': 40},
-                   {'color': [109, 63, 54], 'isthing': 1, 'id': 46, 'name': 'cup', 'trainId': 41},
-                   {'color': [207, 138, 255], 'isthing': 1, 'id': 47, 'name': 'fork', 'trainId': 42},
-                   {'color': [151, 0, 95], 'isthing': 1, 'id': 48, 'name': 'knife', 'trainId': 43},
-                   {'color': [9, 80, 61], 'isthing': 1, 'id': 49, 'name': 'spoon', 'trainId': 44},
-                   {'color': [84, 105, 51], 'isthing': 1, 'id': 50, 'name': 'bowl', 'trainId': 45},
-                   {'color': [74, 65, 105], 'isthing': 1, 'id': 51, 'name': 'banana', 'trainId': 46},
-                   {'color': [166, 196, 102], 'isthing': 1, 'id': 52, 'name': 'apple', 'trainId': 47},
-                   {'color': [208, 195, 210], 'isthing': 1, 'id': 53, 'name': 'sandwich', 'trainId': 48},
-                   {'color': [255, 109, 65], 'isthing': 1, 'id': 54, 'name': 'orange', 'trainId': 49},
-                   {'color': [0, 143, 149], 'isthing': 1, 'id': 55, 'name': 'broccoli', 'trainId': 50},
-                   {'color': [179, 0, 194], 'isthing': 1, 'id': 56, 'name': 'carrot', 'trainId': 51},
-                   {'color': [209, 99, 106], 'isthing': 1, 'id': 57, 'name': 'hot dog', 'trainId': 52},
-                   {'color': [5, 121, 0], 'isthing': 1, 'id': 58, 'name': 'pizza', 'trainId': 53},
-                   {'color': [227, 255, 205], 'isthing': 1, 'id': 59, 'name': 'donut', 'trainId': 54},
-                   {'color': [147, 186, 208], 'isthing': 1, 'id': 60, 'name': 'cake', 'trainId': 55},
-                   {'color': [153, 69, 1], 'isthing': 1, 'id': 61, 'name': 'chair', 'trainId': 56},
-                   {'color': [3, 95, 161], 'isthing': 1, 'id': 62, 'name': 'couch', 'trainId': 57},
-                   {'color': [163, 255, 0], 'isthing': 1, 'id': 63, 'name': 'potted plant', 'trainId': 58},
-                   {'color': [119, 0, 170], 'isthing': 1, 'id': 64, 'name': 'bed', 'trainId': 59},
-                   {'color': [0, 182, 199], 'isthing': 1, 'id': 66, 'name': 'dining table', 'trainId': 60},
-                   {'color': [0, 165, 120], 'isthing': 1, 'id': 69, 'name': 'toilet', 'trainId': 61},
-                   {'color': [183, 130, 88], 'isthing': 1, 'id': 71, 'name': 'tv', 'trainId': 62},
-                   {'color': [95, 32, 0], 'isthing': 1, 'id': 72, 'name': 'laptop', 'trainId': 63},
-                   {'color': [130, 114, 135], 'isthing': 1, 'id': 73, 'name': 'mouse', 'trainId': 64},
-                   {'color': [110, 129, 133], 'isthing': 1, 'id': 74, 'name': 'remote', 'trainId': 65},
-                   {'color': [166, 74, 118], 'isthing': 1, 'id': 75, 'name': 'keyboard', 'trainId': 66},
-                   {'color': [219, 142, 185], 'isthing': 1, 'id': 76, 'name': 'cell phone', 'trainId': 67},
-                   {'color': [79, 210, 114], 'isthing': 1, 'id': 77, 'name': 'microwave', 'trainId': 68},
-                   {'color': [178, 90, 62], 'isthing': 1, 'id': 78, 'name': 'oven', 'trainId': 69},
-                   {'color': [65, 70, 15], 'isthing': 1, 'id': 79, 'name': 'toaster', 'trainId': 70},
-                   {'color': [127, 167, 115], 'isthing': 1, 'id': 80, 'name': 'sink', 'trainId': 71},
-                   {'color': [59, 105, 106], 'isthing': 1, 'id': 81, 'name': 'refrigerator', 'trainId': 72},
-                   {'color': [142, 108, 45], 'isthing': 1, 'id': 83, 'name': 'book', 'trainId': 73},
-                   {'color': [196, 172, 0], 'isthing': 1, 'id': 84, 'name': 'clock', 'trainId': 74},
-                   {'color': [95, 54, 80], 'isthing': 1, 'id': 85, 'name': 'vase', 'trainId': 75},
-                   {'color': [128, 76, 255], 'isthing': 1, 'id': 86, 'name': 'scissors', 'trainId': 76},
-                   {'color': [201, 57, 1], 'isthing': 1, 'id': 87, 'name': 'teddy bear', 'trainId': 77},
-                   {'color': [246, 0, 122], 'isthing': 1, 'id': 88, 'name': 'hair drier', 'trainId': 78},
-                   {'color': [191, 162, 208], 'isthing': 1, 'id': 89, 'name': 'toothbrush', 'trainId': 79},
-                   {'id': 91, 'name': 'banner', 'supercategory': 'textile', 'trainId': 80},
-                   {'id': 92, 'name': 'blanket', 'supercategory': 'textile', 'trainId': 81},
-                   {'id': 93, 'name': 'branch', 'supercategory': 'plant', 'trainId': 82},
-                   {'id': 94, 'name': 'bridge', 'supercategory': 'building', 'trainId': 83},
-                   {'id': 95, 'name': 'building-other', 'supercategory': 'building', 'trainId': 84},
-                   {'id': 96, 'name': 'bush', 'supercategory': 'plant', 'trainId': 85},
-                   {'id': 97, 'name': 'cabinet', 'supercategory': 'furniture-stuff', 'trainId': 86},
-                   {'id': 98, 'name': 'cage', 'supercategory': 'structural', 'trainId': 87},
-                   {'id': 99, 'name': 'cardboard', 'supercategory': 'raw-material', 'trainId': 88},
-                   {'id': 100, 'name': 'carpet', 'supercategory': 'floor', 'trainId': 89},
-                   {'id': 101, 'name': 'ceiling-other', 'supercategory': 'ceiling', 'trainId': 90},
-                   {'id': 102, 'name': 'ceiling-tile', 'supercategory': 'ceiling', 'trainId': 91},
-                   {'id': 103, 'name': 'cloth', 'supercategory': 'textile', 'trainId': 92},
-                   {'id': 104, 'name': 'clothes', 'supercategory': 'textile', 'trainId': 93},
-                   {'id': 105, 'name': 'clouds', 'supercategory': 'sky', 'trainId': 94},
-                   {'id': 106, 'name': 'counter', 'supercategory': 'furniture-stuff', 'trainId': 95},
-                   {'id': 107, 'name': 'cupboard', 'supercategory': 'furniture-stuff', 'trainId': 96},
-                   {'id': 108, 'name': 'curtain', 'supercategory': 'textile', 'trainId': 97},
-                   {'id': 109, 'name': 'desk-stuff', 'supercategory': 'furniture-stuff', 'trainId': 98},
-                   {'id': 110, 'name': 'dirt', 'supercategory': 'ground', 'trainId': 99},
-                   {'id': 111, 'name': 'door-stuff', 'supercategory': 'furniture-stuff', 'trainId': 100},
-                   {'id': 112, 'name': 'fence', 'supercategory': 'structural', 'trainId': 101},
-                   {'id': 113, 'name': 'floor-marble', 'supercategory': 'floor', 'trainId': 102},
-                   {'id': 114, 'name': 'floor-other', 'supercategory': 'floor', 'trainId': 103},
-                   {'id': 115, 'name': 'floor-stone', 'supercategory': 'floor', 'trainId': 104},
-                   {'id': 116, 'name': 'floor-tile', 'supercategory': 'floor', 'trainId': 105},
-                   {'id': 117, 'name': 'floor-wood', 'supercategory': 'floor', 'trainId': 106},
-                   {'id': 118, 'name': 'flower', 'supercategory': 'plant', 'trainId': 107},
-                   {'id': 119, 'name': 'fog', 'supercategory': 'water', 'trainId': 108},
-                   {'id': 120, 'name': 'food-other', 'supercategory': 'food-stuff', 'trainId': 109},
-                   {'id': 121, 'name': 'fruit', 'supercategory': 'food-stuff', 'trainId': 110},
-                   {'id': 122, 'name': 'furniture-other', 'supercategory': 'furniture-stuff', 'trainId': 111},
-                   {'id': 123, 'name': 'grass', 'supercategory': 'plant', 'trainId': 112},
-                   {'id': 124, 'name': 'gravel', 'supercategory': 'ground', 'trainId': 113},
-                   {'id': 125, 'name': 'ground-other', 'supercategory': 'ground', 'trainId': 114},
-                   {'id': 126, 'name': 'hill', 'supercategory': 'solid', 'trainId': 115},
-                   {'id': 127, 'name': 'house', 'supercategory': 'building', 'trainId': 116},
-                   {'id': 128, 'name': 'leaves', 'supercategory': 'plant', 'trainId': 117},
-                   {'id': 129, 'name': 'light', 'supercategory': 'furniture-stuff', 'trainId': 118},
-                   {'id': 130, 'name': 'mat', 'supercategory': 'textile', 'trainId': 119},
-                   {'id': 131, 'name': 'metal', 'supercategory': 'raw-material', 'trainId': 120},
-                   {'id': 132, 'name': 'mirror-stuff', 'supercategory': 'furniture-stuff', 'trainId': 121},
-                   {'id': 133, 'name': 'moss', 'supercategory': 'plant', 'trainId': 122},
-                   {'id': 134, 'name': 'mountain', 'supercategory': 'solid', 'trainId': 123},
-                   {'id': 135, 'name': 'mud', 'supercategory': 'ground', 'trainId': 124},
-                   {'id': 136, 'name': 'napkin', 'supercategory': 'textile', 'trainId': 125},
-                   {'id': 137, 'name': 'net', 'supercategory': 'structural', 'trainId': 126},
-                   {'id': 138, 'name': 'paper', 'supercategory': 'raw-material', 'trainId': 127},
-                   {'id': 139, 'name': 'pavement', 'supercategory': 'ground', 'trainId': 128},
-                   {'id': 140, 'name': 'pillow', 'supercategory': 'textile', 'trainId': 129},
-                   {'id': 141, 'name': 'plant-other', 'supercategory': 'plant', 'trainId': 130},
-                   {'id': 142, 'name': 'plastic', 'supercategory': 'raw-material', 'trainId': 131},
-                   {'id': 143, 'name': 'platform', 'supercategory': 'ground', 'trainId': 132},
-                   {'id': 144, 'name': 'playingfield', 'supercategory': 'ground', 'trainId': 133},
-                   {'id': 145, 'name': 'railing', 'supercategory': 'structural', 'trainId': 134},
-                   {'id': 146, 'name': 'railroad', 'supercategory': 'ground', 'trainId': 135},
-                   {'id': 147, 'name': 'river', 'supercategory': 'water', 'trainId': 136},
-                   {'id': 148, 'name': 'road', 'supercategory': 'ground', 'trainId': 137},
-                   {'id': 149, 'name': 'rock', 'supercategory': 'solid', 'trainId': 138},
-                   {'id': 150, 'name': 'roof', 'supercategory': 'building', 'trainId': 139},
-                   {'id': 151, 'name': 'rug', 'supercategory': 'textile', 'trainId': 140},
-                   {'id': 152, 'name': 'salad', 'supercategory': 'food-stuff', 'trainId': 141},
-                   {'id': 153, 'name': 'sand', 'supercategory': 'ground', 'trainId': 142},
-                   {'id': 154, 'name': 'sea', 'supercategory': 'water', 'trainId': 143},
-                   {'id': 155, 'name': 'shelf', 'supercategory': 'furniture-stuff', 'trainId': 144},
-                   {'id': 156, 'name': 'sky-other', 'supercategory': 'sky', 'trainId': 145},
-                   {'id': 157, 'name': 'skyscraper', 'supercategory': 'building', 'trainId': 146},
-                   {'id': 158, 'name': 'snow', 'supercategory': 'ground', 'trainId': 147},
-                   {'id': 159, 'name': 'solid-other', 'supercategory': 'solid', 'trainId': 148},
-                   {'id': 160, 'name': 'stairs', 'supercategory': 'furniture-stuff', 'trainId': 149},
-                   {'id': 161, 'name': 'stone', 'supercategory': 'solid', 'trainId': 150},
-                   {'id': 162, 'name': 'straw', 'supercategory': 'plant', 'trainId': 151},
-                   {'id': 163, 'name': 'structural-other', 'supercategory': 'structural', 'trainId': 152},
-                   {'id': 164, 'name': 'table', 'supercategory': 'furniture-stuff', 'trainId': 153},
-                   {'id': 165, 'name': 'tent', 'supercategory': 'building', 'trainId': 154},
-                   {'id': 166, 'name': 'textile-other', 'supercategory': 'textile', 'trainId': 155},
-                   {'id': 167, 'name': 'towel', 'supercategory': 'textile', 'trainId': 156},
-                   {'id': 168, 'name': 'tree', 'supercategory': 'plant', 'trainId': 157},
-                   {'id': 169, 'name': 'vegetable', 'supercategory': 'food-stuff', 'trainId': 158},
-                   {'id': 170, 'name': 'wall-brick', 'supercategory': 'wall', 'trainId': 159},
-                   {'id': 171, 'name': 'wall-concrete', 'supercategory': 'wall', 'trainId': 160},
-                   {'id': 172, 'name': 'wall-other', 'supercategory': 'wall', 'trainId': 161},
-                   {'id': 173, 'name': 'wall-panel', 'supercategory': 'wall', 'trainId': 162},
-                   {'id': 174, 'name': 'wall-stone', 'supercategory': 'wall', 'trainId': 163},
-                   {'id': 175, 'name': 'wall-tile', 'supercategory': 'wall', 'trainId': 164},
-                   {'id': 176, 'name': 'wall-wood', 'supercategory': 'wall', 'trainId': 165},
-                   {'id': 177, 'name': 'water-other', 'supercategory': 'water', 'trainId': 166},
-                   {'id': 178, 'name': 'waterdrops', 'supercategory': 'water', 'trainId': 167},
-                   {'id': 179, 'name': 'window-blind', 'supercategory': 'window', 'trainId': 168},
-                   {'id': 180, 'name': 'window-other', 'supercategory': 'window', 'trainId': 169},
-                   {'id': 181, 'name': 'wood', 'supercategory': 'solid', 'trainId': 170}]
-
-
-if __name__ == "__main__":
-    dataset_dir = Path(os.getenv("DETECTRON2_DATASETS", "datasets")) / "coco-stuff"
-
-    id_map = {}
-    for cat in COCO_CATEGORIES:
-        id_map[cat["id"]] = cat["trainId"]
-
-    for name in ["train2017", "val2017"]:
-        annotation_dir = dataset_dir / "annotations" / name
-        output_dir = dataset_dir / "annotations_detectron2" / name
-        output_dir.mkdir(parents=True, exist_ok=True)
-
-        for file in tqdm.tqdm(list(annotation_dir.iterdir())):
-            output_file = output_dir / file.name
-            lab = np.asarray(Image.open(file))
-            assert lab.dtype == np.uint8
-
-            output = np.zeros_like(lab, dtype=np.uint8) + 255
-            for obj_id in np.unique(lab):
-                if obj_id in id_map:
-                    output[lab == obj_id] = id_map[obj_id]
-
-            Image.fromarray(output).save(output_file)
\ No newline at end of file
diff --git a/spaces/hamacojr/SAM-CAT-Seg/datasets/prepare_ade20k_full.py b/spaces/hamacojr/SAM-CAT-Seg/datasets/prepare_ade20k_full.py
deleted file mode 100644
index 4a55e039549ff0aaf928a4dddee7a94ea8d0f6bf..0000000000000000000000000000000000000000
--- a/spaces/hamacojr/SAM-CAT-Seg/datasets/prepare_ade20k_full.py
+++ /dev/null
@@ -1,1011 +0,0 @@
-# Copyright (c) Facebook, Inc. and its affiliates.
-# Copyright (c) Meta Platforms, Inc. All Rights Reserved
-
-import os
-import pickle as pkl
-from pathlib import Path
-
-import cv2
-import numpy as np
-import tqdm
-from PIL import Image
-
-ADE20K_SEM_SEG_FULL_CATEGORIES = [
-    {"name": "wall", "id": 2978, "trainId": 0},
-    {"name": "building, edifice", "id": 312, "trainId": 1},
-    {"name": "sky", "id": 2420, "trainId": 2},
-    {"name": "tree", "id": 2855, "trainId": 3},
-    {"name": "road, route", "id": 2131, "trainId": 4},
-    {"name": "floor, flooring", "id": 976, "trainId": 5},
-    {"name": "ceiling", "id": 447, "trainId": 6},
-    {"name": "bed", "id": 165, "trainId": 7},
-    {"name": "sidewalk, pavement", "id": 2377, "trainId": 8},
-    {"name": "earth, ground", "id": 838, "trainId": 9},
-    {"name": "cabinet", "id": 350, "trainId": 10},
-    {"name": "person, individual, someone, somebody, mortal, soul", "id": 1831, "trainId": 11},
-    {"name": "grass", "id": 1125, "trainId": 12},
-    {"name": "windowpane, window", "id": 3055, "trainId": 13},
-    {"name": "car, auto, automobile, machine, motorcar", "id": 401, "trainId": 14},
-    {"name": "mountain, mount", "id": 1610, "trainId": 15},
-    {"name": "plant, flora, plant life", "id": 1910, "trainId": 16},
-    {"name": "table", "id": 2684, "trainId": 17},
-    {"name": "chair", "id": 471, "trainId": 18},
-    {"name": "curtain, drape, drapery, mantle, pall", "id": 687, "trainId": 19},
-    {"name": "door", "id": 774, "trainId": 20},
-    {"name": "sofa, couch, lounge", "id": 2473, "trainId": 21},
-    {"name": "sea", "id": 2264, "trainId": 22},
-    {"name": "painting, picture", "id": 1735, "trainId": 23},
-    {"name": "water", "id": 2994, "trainId": 24},
-    {"name": "mirror", "id": 1564, "trainId": 25},
-    {"name": "house", "id": 1276, "trainId": 26},
-    {"name": "rug, carpet, carpeting", "id": 2178, "trainId": 27},
-    {"name": "shelf", "id": 2329, "trainId": 28},
-    {"name": "armchair", "id": 57, "trainId": 29},
-    {"name": "fence, fencing", "id": 907, "trainId": 30},
-    {"name": "field", "id": 913, "trainId": 31},
-    {"name": "lamp", "id": 1395, "trainId": 32},
-    {"name": "rock, stone", "id": 2138, "trainId": 33},
-    {"name": "seat", "id": 2272, "trainId": 34},
-    {"name": "river", "id": 2128, "trainId": 35},
-    {"name": "desk", "id": 724, "trainId": 36},
-    {"name": "bathtub, bathing tub, bath, tub", "id": 155, "trainId": 37},
-    {"name": "railing, rail", "id": 2053, "trainId": 38},
-    {"name": "signboard, sign", "id": 2380, "trainId": 39},
-    {"name": "cushion", "id": 689, "trainId": 40},
-    {"name": "path", "id": 1788, "trainId": 41},
-    {"name": "work surface", "id": 3087, "trainId": 42},
-    {"name": "stairs, steps", "id": 2530, "trainId": 43},
-    {"name": "column, pillar", "id": 581, "trainId": 44},
-    {"name": "sink", "id": 2388, "trainId": 45},
-    {"name": "wardrobe, closet, press", "id": 2985, "trainId": 46},
-    {"name": "snow", "id": 2454, "trainId": 47},
-    {"name": "refrigerator, icebox", "id": 2096, "trainId": 48},
-    {"name": "base, pedestal, stand", "id": 137, "trainId": 49},
-    {"name": "bridge, span", "id": 294, "trainId": 50},
-    {"name": "blind, screen", "id": 212, "trainId": 51},
-    {"name": "runway", "id": 2185, "trainId": 52},
-    {"name": "cliff, drop, drop-off", "id": 524, "trainId": 53},
-    {"name": "sand", "id": 2212, "trainId": 54},
-    {"name": "fireplace, hearth, open fireplace", "id": 943, "trainId": 55},
-    {"name": "pillow", "id": 1869, "trainId": 56},
-    {"name": "screen door, screen", "id": 2251, "trainId": 57},
-    {"name": "toilet, can, commode, crapper, pot, potty, stool, throne", "id": 2793, "trainId": 58},
-    {"name": "skyscraper", "id": 2423, "trainId": 59},
-    {"name": "grandstand, covered stand", "id": 1121, "trainId": 60},
-    {"name": "box", "id": 266, "trainId": 61},
-    {"name": "pool table, billiard table, snooker table", "id": 1948, "trainId": 62},
-    {"name": "palm, palm tree", "id": 1744, "trainId": 63},
-    {"name": "double door", "id": 783, "trainId": 64},
-    {"name": "coffee table, cocktail table", "id": 571, "trainId": 65},
-    {"name": "counter", "id": 627, "trainId": 66},
-    {"name": "countertop", "id": 629, "trainId": 67},
-    {"name": "chest of drawers, chest, bureau, dresser", "id": 491, "trainId": 68},
-    {"name": "kitchen island", "id": 1374, "trainId": 69},
-    {"name": "boat", "id": 223, "trainId": 70},
-    {"name": "waterfall, falls", "id": 3016, "trainId": 71},
-    {
-        "name": "stove, kitchen stove, range, kitchen range, cooking stove",
-        "id": 2598,
-        "trainId": 72,
-    },
-    {"name": "flower", "id": 978, "trainId": 73},
-    {"name": "bookcase", "id": 239, "trainId": 74},
-    {"name": "controls", "id": 608, "trainId": 75},
-    {"name": "book", "id": 236, "trainId": 76},
-    {"name": "stairway, staircase", "id": 2531, "trainId": 77},
-    {"name": "streetlight, street lamp", "id": 2616, "trainId": 78},
-    {
-        "name": "computer, computing machine, computing device, data processor, electronic computer, information processing system",
-        "id": 591,
-        "trainId": 79,
-    },
-    {
-        "name": "bus, autobus, coach, charabanc, double-decker, jitney, motorbus, motorcoach, omnibus, passenger vehicle",
-        "id": 327,
-        "trainId": 80,
-    },
-    {"name": "swivel chair", "id": 2679, "trainId": 81},
-    {"name": "light, light source", "id": 1451, "trainId": 82},
-    {"name": "bench", "id": 181, "trainId": 83},
-    {"name": "case, display case, showcase, vitrine", "id": 420, "trainId": 84},
-    {"name": "towel", "id": 2821, "trainId": 85},
-    {"name": "fountain", "id": 1023, "trainId": 86},
-    {"name": "embankment", "id": 855, "trainId": 87},
-    {
-        "name": "television receiver, television, television set, tv, tv set, idiot box, boob tube, telly, goggle box",
-        "id": 2733,
-        "trainId": 88,
-    },
-    {"name": "van", "id": 2928, "trainId": 89},
-    {"name": "hill", "id": 1240, "trainId": 90},
-    {"name": "awning, sunshade, sunblind", "id": 77, "trainId": 91},
-    {"name": "poster, posting, placard, notice, bill, card", "id": 1969, "trainId": 92},
-    {"name": "truck, motortruck", "id": 2880, "trainId": 93},
-    {"name": "airplane, aeroplane, plane", "id": 14, "trainId": 94},
-    {"name": "pole", "id": 1936, "trainId": 95},
-    {"name": "tower", "id": 2828, "trainId": 96},
-    {"name": "court", "id": 631, "trainId": 97},
-    {"name": "ball", "id": 103, "trainId": 98},
-    {
-        "name": "aircraft carrier, carrier, flattop, attack aircraft carrier",
-        "id": 3144,
-        "trainId": 99,
-    },
-    {"name": "buffet, counter, sideboard", "id": 308, "trainId": 100},
-    {"name": "hovel, hut, hutch, shack, shanty", "id": 1282, "trainId": 101},
-    {"name": "apparel, wearing apparel, dress, clothes", "id": 38, "trainId": 102},
-    {"name": "minibike, motorbike", "id": 1563, "trainId": 103},
-    {"name": "animal, animate being, beast, brute, creature, fauna", "id": 29, "trainId": 104},
-    {"name": "chandelier, pendant, pendent", "id": 480, "trainId": 105},
-    {"name": "step, stair", "id": 2569, "trainId": 106},
-    {"name": "booth, cubicle, stall, kiosk", "id": 247, "trainId": 107},
-    {"name": "bicycle, bike, wheel, cycle", "id": 187, "trainId": 108},
-    {"name": "doorframe, doorcase", "id": 778, "trainId": 109},
-    {"name": "sconce", "id": 2243, "trainId": 110},
-    {"name": "pond", "id": 1941, "trainId": 111},
-    {"name": "trade name, brand name, brand, marque", "id": 2833, "trainId": 112},
-    {"name": "bannister, banister, balustrade, balusters, handrail", "id": 120, "trainId": 113},
-    {"name": "bag", "id": 95, "trainId": 114},
-    {"name": "traffic light, traffic signal, stoplight", "id": 2836, "trainId": 115},
-    {"name": "gazebo", "id": 1087, "trainId": 116},
-    {"name": "escalator, moving staircase, moving stairway", "id": 868, "trainId": 117},
-    {"name": "land, ground, soil", "id": 1401, "trainId": 118},
-    {"name": "board, plank", "id": 220, "trainId": 119},
-    {"name": "arcade machine", "id": 47, "trainId": 120},
-    {"name": "eiderdown, duvet, continental quilt", "id": 843, "trainId": 121},
-    {"name": "bar", "id": 123, "trainId": 122},
-    {"name": "stall, stand, sales booth", "id": 2537, "trainId": 123},
-    {"name": "playground", "id": 1927, "trainId": 124},
-    {"name": "ship", "id": 2337, "trainId": 125},
-    {"name": "ottoman, pouf, pouffe, puff, hassock", "id": 1702, "trainId": 126},
-    {
-        "name": "ashcan, trash can, garbage can, wastebin, ash bin, ash-bin, ashbin, dustbin, trash barrel, trash bin",
-        "id": 64,
-        "trainId": 127,
-    },
-    {"name": "bottle", "id": 249, "trainId": 128},
-    {"name": "cradle", "id": 642, "trainId": 129},
-    {"name": "pot, flowerpot", "id": 1981, "trainId": 130},
-    {
-        "name": "conveyer belt, conveyor belt, conveyer, conveyor, transporter",
-        "id": 609,
-        "trainId": 131,
-    },
-    {"name": "train, railroad train", "id": 2840, "trainId": 132},
-    {"name": "stool", "id": 2586, "trainId": 133},
-    {"name": "lake", "id": 1393, "trainId": 134},
-    {"name": "tank, storage tank", "id": 2704, "trainId": 135},
-    {"name": "ice, water ice", "id": 1304, "trainId": 136},
-    {"name": "basket, handbasket", "id": 146, "trainId": 137},
-    {"name": "manhole", "id": 1494, "trainId": 138},
-    {"name": "tent, collapsible shelter", "id": 2739, "trainId": 139},
-    {"name": "canopy", "id": 389, "trainId": 140},
-    {"name": "microwave, microwave oven", "id": 1551, "trainId": 141},
-    {"name": "barrel, cask", "id": 131, "trainId": 142},
-    {"name": "dirt track", "id": 738, "trainId": 143},
-    {"name": "beam", "id": 161, "trainId": 144},
-    {"name": "dishwasher, dish washer, dishwashing machine", "id": 747, "trainId": 145},
-    {"name": "plate", "id": 1919, "trainId": 146},
-    {"name": "screen, crt screen", "id": 3109, "trainId": 147},
-    {"name": "ruins", "id": 2179, "trainId": 148},
-    {"name": "washer, automatic washer, washing machine", "id": 2989, "trainId": 149},
-    {"name": "blanket, cover", "id": 206, "trainId": 150},
-    {"name": "plaything, toy", "id": 1930, "trainId": 151},
-    {"name": "food, solid food", "id": 1002, "trainId": 152},
-    {"name": "screen, silver screen, projection screen", "id": 2254, "trainId": 153},
-    {"name": "oven", "id": 1708, "trainId": 154},
-    {"name": "stage", "id": 2526, "trainId": 155},
-    {"name": "beacon, lighthouse, beacon light, pharos", "id": 160, "trainId": 156},
-    {"name": "umbrella", "id": 2901, "trainId": 157},
-    {"name": "sculpture", "id": 2262, "trainId": 158},
-    {"name": "aqueduct", "id": 44, "trainId": 159},
-    {"name": "container", "id": 597, "trainId": 160},
-    {"name": "scaffolding, staging", "id": 2235, "trainId": 161},
-    {"name": "hood, exhaust hood", "id": 1260, "trainId": 162},
-    {"name": "curb, curbing, kerb", "id": 682, "trainId": 163},
-    {"name": "roller coaster", "id": 2151, "trainId": 164},
-    {"name": "horse, equus caballus", "id": 3107, "trainId": 165},
-    {"name": "catwalk", "id": 432, "trainId": 166},
-    {"name": "glass, drinking glass", "id": 1098, "trainId": 167},
-    {"name": "vase", "id": 2932, "trainId": 168},
-    {"name": "central reservation", "id": 461, "trainId": 169},
-    {"name": "carousel", "id": 410, "trainId": 170},
-    {"name": "radiator", "id": 2046, "trainId": 171},
-    {"name": "closet", "id": 533, "trainId": 172},
-    {"name": "machine", "id": 1481, "trainId": 173},
-    {"name": "pier, wharf, wharfage, dock", "id": 1858, "trainId": 174},
-    {"name": "fan", "id": 894, "trainId": 175},
-    {"name": "inflatable bounce game", "id": 1322, "trainId": 176},
-    {"name": "pitch", "id": 1891, "trainId": 177},
-    {"name": "paper", "id": 1756, "trainId": 178},
-    {"name": "arcade, colonnade", "id": 49, "trainId": 179},
-    {"name": "hot tub", "id": 1272, "trainId": 180},
-    {"name": "helicopter", "id": 1229, "trainId": 181},
-    {"name": "tray", "id": 2850, "trainId": 182},
-    {"name": "partition, divider", "id": 1784, "trainId": 183},
-    {"name": "vineyard", "id": 2962, "trainId": 184},
-    {"name": "bowl", "id": 259, "trainId": 185},
-    {"name": "bullring", "id": 319, "trainId": 186},
-    {"name": "flag", "id": 954, "trainId": 187},
-    {"name": "pot", "id": 1974, "trainId": 188},
-    {"name": "footbridge, overcrossing, pedestrian bridge", "id": 1013, "trainId": 189},
-    {"name": "shower", "id": 2356, "trainId": 190},
-    {"name": "bag, traveling bag, travelling bag, grip, suitcase", "id": 97, "trainId": 191},
-    {"name": "bulletin board, notice board", "id": 318, "trainId": 192},
-    {"name": "confessional booth", "id": 592, "trainId": 193},
-    {"name": "trunk, tree trunk, bole", "id": 2885, "trainId": 194},
-    {"name": "forest", "id": 1017, "trainId": 195},
-    {"name": "elevator door", "id": 851, "trainId": 196},
-    {"name": "laptop, laptop computer", "id": 1407, "trainId": 197},
-    {"name": "instrument panel", "id": 1332, "trainId": 198},
-    {"name": "bucket, pail", "id": 303, "trainId": 199},
-    {"name": "tapestry, tapis", "id": 2714, "trainId": 200},
-    {"name": "platform", "id": 1924, "trainId": 201},
-    {"name": "jacket", "id": 1346, "trainId": 202},
-    {"name": "gate", "id": 1081, "trainId": 203},
-    {"name": "monitor, monitoring device", "id": 1583, "trainId": 204},
-    {
-        "name": "telephone booth, phone booth, call box, telephone box, telephone kiosk",
-        "id": 2727,
-        "trainId": 205,
-    },
-    {"name": "spotlight, spot", "id": 2509, "trainId": 206},
-    {"name": "ring", "id": 2123, "trainId": 207},
-    {"name": "control panel", "id": 602, "trainId": 208},
-    {"name": "blackboard, chalkboard", "id": 202, "trainId": 209},
-    {"name": "air conditioner, air conditioning", "id": 10, "trainId": 210},
-    {"name": "chest", "id": 490, "trainId": 211},
-    {"name": "clock", "id": 530, "trainId": 212},
-    {"name": "sand dune", "id": 2213, "trainId": 213},
-    {"name": "pipe, pipage, piping", "id": 1884, "trainId": 214},
-    {"name": "vault", "id": 2934, "trainId": 215},
-    {"name": "table football", "id": 2687, "trainId": 216},
-    {"name": "cannon", "id": 387, "trainId": 217},
-    {"name": "swimming pool, swimming bath, natatorium", "id": 2668, "trainId": 218},
-    {"name": "fluorescent, fluorescent fixture", "id": 982, "trainId": 219},
-    {"name": "statue", "id": 2547, "trainId": 220},
-    {
-        "name": "loudspeaker, speaker, speaker unit, loudspeaker system, speaker system",
-        "id": 1474,
-        "trainId": 221,
-    },
-    {"name": "exhibitor", "id": 877, "trainId": 222},
-    {"name": "ladder", "id": 1391, "trainId": 223},
-    {"name": "carport", "id": 414, "trainId": 224},
-    {"name": "dam", "id": 698, "trainId": 225},
-    {"name": "pulpit", "id": 2019, "trainId": 226},
-    {"name": "skylight, fanlight", "id": 2422, "trainId": 227},
-    {"name": "water tower", "id": 3010, "trainId": 228},
-    {"name": "grill, grille, grillwork", "id": 1139, "trainId": 229},
-    {"name": "display board", "id": 753, "trainId": 230},
-    {"name": "pane, pane of glass, window glass", "id": 1747, "trainId": 231},
-    {"name": "rubbish, trash, scrap", "id": 2175, "trainId": 232},
-    {"name": "ice rink", "id": 1301, "trainId": 233},
-    {"name": "fruit", "id": 1033, "trainId": 234},
-    {"name": "patio", "id": 1789, "trainId": 235},
-    {"name": "vending machine", "id": 2939, "trainId": 236},
-    {"name": "telephone, phone, telephone set", "id": 2730, "trainId": 237},
-    {"name": "net", "id": 1652, "trainId": 238},
-    {
-        "name": "backpack, back pack, knapsack, packsack, rucksack, haversack",
-        "id": 90,
-        "trainId": 239,
-    },
-    {"name": "jar", "id": 1349, "trainId": 240},
-    {"name": "track", "id": 2830, "trainId": 241},
-    {"name": "magazine", "id": 1485, "trainId": 242},
-    {"name": "shutter", "id": 2370, "trainId": 243},
-    {"name": "roof", "id": 2155, "trainId": 244},
-    {"name": "banner, streamer", "id": 118, "trainId": 245},
-    {"name": "landfill", "id": 1402, "trainId": 246},
-    {"name": "post", "id": 1957, "trainId": 247},
-    {"name": "altarpiece, reredos", "id": 3130, "trainId": 248},
-    {"name": "hat, chapeau, lid", "id": 1197, "trainId": 249},
-    {"name": "arch, archway", "id": 52, "trainId": 250},
-    {"name": "table game", "id": 2688, "trainId": 251},
-    {"name": "bag, handbag, pocketbook, purse", "id": 96, "trainId": 252},
-    {"name": "document, written document, papers", "id": 762, "trainId": 253},
-    {"name": "dome", "id": 772, "trainId": 254},
-    {"name": "pier", "id": 1857, "trainId": 255},
-    {"name": "shanties", "id": 2315, "trainId": 256},
-    {"name": "forecourt", "id": 1016, "trainId": 257},
-    {"name": "crane", "id": 643, "trainId": 258},
-    {"name": "dog, domestic dog, canis familiaris", "id": 3105, "trainId": 259},
-    {"name": "piano, pianoforte, forte-piano", "id": 1849, "trainId": 260},
-    {"name": "drawing", "id": 791, "trainId": 261},
-    {"name": "cabin", "id": 349, "trainId": 262},
-    {
-        "name": "ad, advertisement, advertizement, advertising, advertizing, advert",
-        "id": 6,
-        "trainId": 263,
-    },
-    {"name": "amphitheater, amphitheatre, coliseum", "id": 3114, "trainId": 264},
-    {"name": "monument", "id": 1587, "trainId": 265},
-    {"name": "henhouse", "id": 1233, "trainId": 266},
-    {"name": "cockpit", "id": 559, "trainId": 267},
-    {"name": "heater, warmer", "id": 1223, "trainId": 268},
-    {"name": "windmill, aerogenerator, wind generator", "id": 3049, "trainId": 269},
-    {"name": "pool", "id": 1943, "trainId": 270},
-    {"name": "elevator, lift", "id": 853, "trainId": 271},
-    {"name": "decoration, ornament, ornamentation", "id": 709, "trainId": 272},
-    {"name": "labyrinth", "id": 1390, "trainId": 273},
-    {"name": "text, textual matter", "id": 2748, "trainId": 274},
-    {"name": "printer", "id": 2007, "trainId": 275},
-    {"name": "mezzanine, first balcony", "id": 1546, "trainId": 276},
-    {"name": "mattress", "id": 1513, "trainId": 277},
-    {"name": "straw", "id": 2600, "trainId": 278},
-    {"name": "stalls", "id": 2538, "trainId": 279},
-    {"name": "patio, terrace", "id": 1790, "trainId": 280},
-    {"name": "billboard, hoarding", "id": 194, "trainId": 281},
-    {"name": "bus stop", "id": 326, "trainId": 282},
-    {"name": "trouser, pant", "id": 2877, "trainId": 283},
-    {"name": "console table, console", "id": 594, "trainId": 284},
-    {"name": "rack", "id": 2036, "trainId": 285},
-    {"name": "notebook", "id": 1662, "trainId": 286},
-    {"name": "shrine", "id": 2366, "trainId": 287},
-    {"name": "pantry", "id": 1754, "trainId": 288},
-    {"name": "cart", "id": 418, "trainId": 289},
-    {"name": "steam shovel", "id": 2553, "trainId": 290},
-    {"name": "porch", "id": 1951, "trainId": 291},
-    {"name": "postbox, mailbox, letter box", "id": 1963, "trainId": 292},
-    {"name": "figurine, statuette", "id": 918, "trainId": 293},
-    {"name": "recycling bin", "id": 2086, "trainId": 294},
-    {"name": "folding screen", "id": 997, "trainId": 295},
-    {"name": "telescope", "id": 2731, "trainId": 296},
-    {"name": "deck chair, beach chair", "id": 704, "trainId": 297},
-    {"name": "kennel", "id": 1365, "trainId": 298},
-    {"name": "coffee maker", "id": 569, "trainId": 299},
-    {"name": "altar, communion table, lord's table", "id": 3108, "trainId": 300},
-    {"name": "fish", "id": 948, "trainId": 301},
-    {"name": "easel", "id": 839, "trainId": 302},
-    {"name": "artificial golf green", "id": 63, "trainId": 303},
-    {"name": "iceberg", "id": 1305, "trainId": 304},
-    {"name": "candlestick, candle holder", "id": 378, "trainId": 305},
-    {"name": "shower stall, shower bath", "id": 2362, "trainId": 306},
-    {"name": "television stand", "id": 2734, "trainId": 307},
-    {
-        "name": "wall socket, wall plug, electric outlet, electrical outlet, outlet, electric receptacle",
-        "id": 2982,
-        "trainId": 308,
-    },
-    {"name": "skeleton", "id": 2398, "trainId": 309},
-    {"name": "grand piano, grand", "id": 1119, "trainId": 310},
-    {"name": "candy, confect", "id": 382, "trainId": 311},
-    {"name": "grille door", "id": 1141, "trainId": 312},
-    {"name": "pedestal, plinth, footstall", "id": 1805, "trainId": 313},
-    {"name": "jersey, t-shirt, tee shirt", "id": 3102, "trainId": 314},
-    {"name": "shoe", "id": 2341, "trainId": 315},
-    {"name": "gravestone, headstone, tombstone", "id": 1131, "trainId": 316},
-    {"name": "shanty", "id": 2316, "trainId": 317},
-    {"name": "structure", "id": 2626, "trainId": 318},
-    {"name": "rocking chair, rocker", "id": 3104, "trainId": 319},
-    {"name": "bird", "id": 198, "trainId": 320},
-    {"name": "place mat", "id": 1896, "trainId": 321},
-    {"name": "tomb", "id": 2800, "trainId": 322},
-    {"name": "big top", "id": 190, "trainId": 323},
-    {"name": "gas pump, gasoline pump, petrol pump, island dispenser", "id": 3131, "trainId": 324},
-    {"name": "lockers", "id": 1463, "trainId": 325},
-    {"name": "cage", "id": 357, "trainId": 326},
-    {"name": "finger", "id": 929, "trainId": 327},
-    {"name": "bleachers", "id": 209, "trainId": 328},
-    {"name": "ferris wheel", "id": 912, "trainId": 329},
-    {"name": "hairdresser chair", "id": 1164, "trainId": 330},
-    {"name": "mat", "id": 1509, "trainId": 331},
-    {"name": "stands", "id": 2539, "trainId": 332},
-    {"name": "aquarium, fish tank, marine museum", "id": 3116, "trainId": 333},
-    {"name": "streetcar, tram, tramcar, trolley, trolley car", "id": 2615, "trainId": 334},
-    {"name": "napkin, table napkin, serviette", "id": 1644, "trainId": 335},
-    {"name": "dummy", "id": 818, "trainId": 336},
-    {"name": "booklet, brochure, folder, leaflet, pamphlet", "id": 242, "trainId": 337},
-    {"name": "sand trap", "id": 2217, "trainId": 338},
-    {"name": "shop, store", "id": 2347, "trainId": 339},
-    {"name": "table cloth", "id": 2686, "trainId": 340},
-    {"name": "service station", "id": 2300, "trainId": 341},
-    {"name": "coffin", "id": 572, "trainId": 342},
-    {"name": "drawer", "id": 789, "trainId": 343},
-    {"name": "cages", "id": 358, "trainId": 344},
-    {"name": "slot machine, coin machine", "id": 2443, "trainId": 345},
-    {"name": "balcony", "id": 101, "trainId": 346},
-    {"name": "volleyball court", "id": 2969, "trainId": 347},
-    {"name": "table tennis", "id": 2692, "trainId": 348},
-    {"name": "control table", "id": 606, "trainId": 349},
-    {"name": "shirt", "id": 2339, "trainId": 350},
-    {"name": "merchandise, ware, product", "id": 1533, "trainId": 351},
-    {"name": "railway", "id": 2060, "trainId": 352},
-    {"name": "parterre", "id": 1782, "trainId": 353},
-    {"name": "chimney", "id": 495, "trainId": 354},
-    {"name": "can, tin, tin can", "id": 371, "trainId": 355},
-    {"name": "tanks", "id": 2707, "trainId": 356},
-    {"name": "fabric, cloth, material, textile", "id": 889, "trainId": 357},
-    {"name": "alga, algae", "id": 3156, "trainId": 358},
-    {"name": "system", "id": 2683, "trainId": 359},
-    {"name": "map", "id": 1499, "trainId": 360},
-    {"name": "greenhouse", "id": 1135, "trainId": 361},
-    {"name": "mug", "id": 1619, "trainId": 362},
-    {"name": "barbecue", "id": 125, "trainId": 363},
-    {"name": "trailer", "id": 2838, "trainId": 364},
-    {"name": "toilet tissue, toilet paper, bathroom tissue", "id": 2792, "trainId": 365},
-    {"name": "organ", "id": 1695, "trainId": 366},
-    {"name": "dishrag, dishcloth", "id": 746, "trainId": 367},
-    {"name": "island", "id": 1343, "trainId": 368},
-    {"name": "keyboard", "id": 1370, "trainId": 369},
-    {"name": "trench", "id": 2858, "trainId": 370},
-    {"name": "basket, basketball hoop, hoop", "id": 145, "trainId": 371},
-    {"name": "steering wheel, wheel", "id": 2565, "trainId": 372},
-    {"name": "pitcher, ewer", "id": 1892, "trainId": 373},
-    {"name": "goal", "id": 1103, "trainId": 374},
-    {"name": "bread, breadstuff, staff of life", "id": 286, "trainId": 375},
-    {"name": "beds", "id": 170, "trainId": 376},
-    {"name": "wood", "id": 3073, "trainId": 377},
-    {"name": "file cabinet", "id": 922, "trainId": 378},
-    {"name": "newspaper, paper", "id": 1655, "trainId": 379},
-    {"name": "motorboat", "id": 1602, "trainId": 380},
-    {"name": "rope", "id": 2160, "trainId": 381},
-    {"name": "guitar", "id": 1151, "trainId": 382},
-    {"name": "rubble", "id": 2176, "trainId": 383},
-    {"name": "scarf", "id": 2239, "trainId": 384},
-    {"name": "barrels", "id": 132, "trainId": 385},
-    {"name": "cap", "id": 394, "trainId": 386},
-    {"name": "leaves", "id": 1424, "trainId": 387},
-    {"name": "control tower", "id": 607, "trainId": 388},
-    {"name": "dashboard", "id": 700, "trainId": 389},
-    {"name": "bandstand", "id": 116, "trainId": 390},
-    {"name": "lectern", "id": 1425, "trainId": 391},
-    {"name": "switch, electric switch, electrical switch", "id": 2676, "trainId": 392},
-    {"name": "baseboard, mopboard, skirting board", "id": 141, "trainId": 393},
-    {"name": "shower room", "id": 2360, "trainId": 394},
-    {"name": "smoke", "id": 2449, "trainId": 395},
-    {"name": "faucet, spigot", "id": 897, "trainId": 396},
-    {"name": "bulldozer", "id": 317, "trainId": 397},
-    {"name": "saucepan", "id": 2228, "trainId": 398},
-    {"name": "shops", "id": 2351, "trainId": 399},
-    {"name": "meter", "id": 1543, "trainId": 400},
-    {"name": "crevasse", "id": 656, "trainId": 401},
-    {"name": "gear", "id": 1088, "trainId": 402},
-    {"name": "candelabrum, candelabra", "id": 373, "trainId": 403},
-    {"name": "sofa bed", "id": 2472, "trainId": 404},
-    {"name": "tunnel", "id": 2892, "trainId": 405},
-    {"name": "pallet", "id": 1740, "trainId": 406},
-    {"name": "wire, conducting wire", "id": 3067, "trainId": 407},
-    {"name": "kettle, boiler", "id": 1367, "trainId": 408},
-    {"name": "bidet", "id": 188, "trainId": 409},
-    {
-        "name": "baby buggy, baby carriage, carriage, perambulator, pram, stroller, go-cart, pushchair, pusher",
-        "id": 79,
-        "trainId": 410,
-    },
-    {"name": "music stand", "id": 1633, "trainId": 411},
-    {"name": "pipe, tube", "id": 1885, "trainId": 412},
-    {"name": "cup", "id": 677, "trainId": 413},
-    {"name": "parking meter", "id": 1779, "trainId": 414},
-    {"name": "ice hockey rink", "id": 1297, "trainId": 415},
-    {"name": "shelter", "id": 2334, "trainId": 416},
-    {"name": "weeds", "id": 3027, "trainId": 417},
-    {"name": "temple", "id": 2735, "trainId": 418},
-    {"name": "patty, cake", "id": 1791, "trainId": 419},
-    {"name": "ski slope", "id": 2405, "trainId": 420},
-    {"name": "panel", "id": 1748, "trainId": 421},
-    {"name": "wallet", "id": 2983, "trainId": 422},
-    {"name": "wheel", "id": 3035, "trainId": 423},
-    {"name": "towel rack, towel horse", "id": 2824, "trainId": 424},
-    {"name": "roundabout", "id": 2168, "trainId": 425},
-    {"name": "canister, cannister, tin", "id": 385, "trainId": 426},
-    {"name": "rod", "id": 2148, "trainId": 427},
-    {"name": "soap dispenser", "id": 2465, "trainId": 428},
-    {"name": "bell", "id": 175, "trainId": 429},
-    {"name": "canvas", "id": 390, "trainId": 430},
-    {"name": "box office, ticket office, ticket booth", "id": 268, "trainId": 431},
-    {"name": "teacup", "id": 2722, "trainId": 432},
-    {"name": "trellis", "id": 2857, "trainId": 433},
-    {"name": "workbench", "id": 3088, "trainId": 434},
-    {"name": "valley, vale", "id": 2926, "trainId": 435},
-    {"name": "toaster", "id": 2782, "trainId": 436},
-    {"name": "knife", "id": 1378, "trainId": 437},
-    {"name": "podium", "id": 1934, "trainId": 438},
-    {"name": "ramp", "id": 2072, "trainId": 439},
-    {"name": "tumble dryer", "id": 2889, "trainId": 440},
-    {"name": "fireplug, fire hydrant, plug", "id": 944, "trainId": 441},
-    {"name": "gym shoe, sneaker, tennis shoe", "id": 1158, "trainId": 442},
-    {"name": "lab bench", "id": 1383, "trainId": 443},
-    {"name": "equipment", "id": 867, "trainId": 444},
-    {"name": "rocky formation", "id": 2145, "trainId": 445},
-    {"name": "plastic", "id": 1915, "trainId": 446},
-    {"name": "calendar", "id": 361, "trainId": 447},
-    {"name": "caravan", "id": 402, "trainId": 448},
-    {"name": "check-in-desk", "id": 482, "trainId": 449},
-    {"name": "ticket counter", "id": 2761, "trainId": 450},
-    {"name": "brush", "id": 300, "trainId": 451},
-    {"name": "mill", "id": 1554, "trainId": 452},
-    {"name": "covered bridge", "id": 636, "trainId": 453},
-    {"name": "bowling alley", "id": 260, "trainId": 454},
-    {"name": "hanger", "id": 1186, "trainId": 455},
-    {"name": "excavator", "id": 871, "trainId": 456},
-    {"name": "trestle", "id": 2859, "trainId": 457},
-    {"name": "revolving door", "id": 2103, "trainId": 458},
-    {"name": "blast furnace", "id": 208, "trainId": 459},
-    {"name": "scale, weighing machine", "id": 2236, "trainId": 460},
-    {"name": "projector", "id": 2012, "trainId": 461},
-    {"name": "soap", "id": 2462, "trainId": 462},
-    {"name": "locker", "id": 1462, "trainId": 463},
-    {"name": "tractor", "id": 2832, "trainId": 464},
-    {"name": "stretcher", "id": 2617, "trainId": 465},
-    {"name": "frame", "id": 1024, "trainId": 466},
-    {"name": "grating", "id": 1129, "trainId": 467},
-    {"name": "alembic", "id": 18, "trainId": 468},
-    {"name": "candle, taper, wax light", "id": 376, "trainId": 469},
-    {"name": "barrier", "id": 134, "trainId": 470},
-    {"name": "cardboard", "id": 407, "trainId": 471},
-    {"name": "cave", "id": 434, "trainId": 472},
-    {"name": "puddle", "id": 2017, "trainId": 473},
-    {"name": "tarp", "id": 2717, "trainId": 474},
-    {"name": "price tag", "id": 2005, "trainId": 475},
-    {"name": "watchtower", "id": 2993, "trainId": 476},
-    {"name": "meters", "id": 1545, "trainId": 477},
-    {
-        "name": "light bulb, lightbulb, bulb, incandescent lamp, electric light, electric-light bulb",
-        "id": 1445,
-        "trainId": 478,
-    },
-    {"name": "tracks", "id": 2831, "trainId": 479},
-    {"name": "hair dryer", "id": 1161, "trainId": 480},
-    {"name": "skirt", "id": 2411, "trainId": 481},
-    {"name": "viaduct", "id": 2949, "trainId": 482},
-    {"name": "paper towel", "id": 1769, "trainId": 483},
-    {"name": "coat", "id": 552, "trainId": 484},
-    {"name": "sheet", "id": 2327, "trainId": 485},
-    {"name": "fire extinguisher, extinguisher, asphyxiator", "id": 939, "trainId": 486},
-    {"name": "water wheel", "id": 3013, "trainId": 487},
-    {"name": "pottery, clayware", "id": 1986, "trainId": 488},
-    {"name": "magazine rack", "id": 1486, "trainId": 489},
-    {"name": "teapot", "id": 2723, "trainId": 490},
-    {"name": "microphone, mike", "id": 1549, "trainId": 491},
-    {"name": "support", "id": 2649, "trainId": 492},
-    {"name": "forklift", "id": 1020, "trainId": 493},
-    {"name": "canyon", "id": 392, "trainId": 494},
-    {"name": "cash register, register", "id": 422, "trainId": 495},
-    {"name": "leaf, leafage, foliage", "id": 1419, "trainId": 496},
-    {"name": "remote control, remote", "id": 2099, "trainId": 497},
-    {"name": "soap dish", "id": 2464, "trainId": 498},
-    {"name": "windshield, windscreen", "id": 3058, "trainId": 499},
-    {"name": "cat", "id": 430, "trainId": 500},
-    {"name": "cue, cue stick, pool cue, pool stick", "id": 675, "trainId": 501},
-    {"name": "vent, venthole, vent-hole, blowhole", "id": 2941, "trainId": 502},
-    {"name": "videos", "id": 2955, "trainId": 503},
-    {"name": "shovel", "id": 2355, "trainId": 504},
-    {"name": "eaves", "id": 840, "trainId": 505},
-    {"name": "antenna, aerial, transmitting aerial", "id": 32, "trainId": 506},
-    {"name": "shipyard", "id": 2338, "trainId": 507},
-    {"name": "hen, biddy", "id": 1232, "trainId": 508},
-    {"name": "traffic cone", "id": 2834, "trainId": 509},
-    {"name": "washing machines", "id": 2991, "trainId": 510},
-    {"name": "truck crane", "id": 2879, "trainId": 511},
-    {"name": "cds", "id": 444, "trainId": 512},
-    {"name": "niche", "id": 1657, "trainId": 513},
-    {"name": "scoreboard", "id": 2246, "trainId": 514},
-    {"name": "briefcase", "id": 296, "trainId": 515},
-    {"name": "boot", "id": 245, "trainId": 516},
-    {"name": "sweater, jumper", "id": 2661, "trainId": 517},
-    {"name": "hay", "id": 1202, "trainId": 518},
-    {"name": "pack", "id": 1714, "trainId": 519},
-    {"name": "bottle rack", "id": 251, "trainId": 520},
-    {"name": "glacier", "id": 1095, "trainId": 521},
-    {"name": "pergola", "id": 1828, "trainId": 522},
-    {"name": "building materials", "id": 311, "trainId": 523},
-    {"name": "television camera", "id": 2732, "trainId": 524},
-    {"name": "first floor", "id": 947, "trainId": 525},
-    {"name": "rifle", "id": 2115, "trainId": 526},
-    {"name": "tennis table", "id": 2738, "trainId": 527},
-    {"name": "stadium", "id": 2525, "trainId": 528},
-    {"name": "safety belt", "id": 2194, "trainId": 529},
-    {"name": "cover", "id": 634, "trainId": 530},
-    {"name": "dish rack", "id": 740, "trainId": 531},
-    {"name": "synthesizer", "id": 2682, "trainId": 532},
-    {"name": "pumpkin", "id": 2020, "trainId": 533},
-    {"name": "gutter", "id": 1156, "trainId": 534},
-    {"name": "fruit stand", "id": 1036, "trainId": 535},
-    {"name": "ice floe, floe", "id": 1295, "trainId": 536},
-    {"name": "handle, grip, handgrip, hold", "id": 1181, "trainId": 537},
-    {"name": "wheelchair", "id": 3037, "trainId": 538},
-    {"name": "mousepad, mouse mat", "id": 1614, "trainId": 539},
-    {"name": "diploma", "id": 736, "trainId": 540},
-    {"name": "fairground ride", "id": 893, "trainId": 541},
-    {"name": "radio", "id": 2047, "trainId": 542},
-    {"name": "hotplate", "id": 1274, "trainId": 543},
-    {"name": "junk", "id": 1361, "trainId": 544},
-    {"name": "wheelbarrow", "id": 3036, "trainId": 545},
-    {"name": "stream", "id": 2606, "trainId": 546},
-    {"name": "toll plaza", "id": 2797, "trainId": 547},
-    {"name": "punching bag", "id": 2022, "trainId": 548},
-    {"name": "trough", "id": 2876, "trainId": 549},
-    {"name": "throne", "id": 2758, "trainId": 550},
-    {"name": "chair desk", "id": 472, "trainId": 551},
-    {"name": "weighbridge", "id": 3028, "trainId": 552},
-    {"name": "extractor fan", "id": 882, "trainId": 553},
-    {"name": "hanging clothes", "id": 1189, "trainId": 554},
-    {"name": "dish, dish aerial, dish antenna, saucer", "id": 743, "trainId": 555},
-    {"name": "alarm clock, alarm", "id": 3122, "trainId": 556},
-    {"name": "ski lift", "id": 2401, "trainId": 557},
-    {"name": "chain", "id": 468, "trainId": 558},
-    {"name": "garage", "id": 1061, "trainId": 559},
-    {"name": "mechanical shovel", "id": 1523, "trainId": 560},
-    {"name": "wine rack", "id": 3059, "trainId": 561},
-    {"name": "tramway", "id": 2843, "trainId": 562},
-    {"name": "treadmill", "id": 2853, "trainId": 563},
-    {"name": "menu", "id": 1529, "trainId": 564},
-    {"name": "block", "id": 214, "trainId": 565},
-    {"name": "well", "id": 3032, "trainId": 566},
-    {"name": "witness stand", "id": 3071, "trainId": 567},
-    {"name": "branch", "id": 277, "trainId": 568},
-    {"name": "duck", "id": 813, "trainId": 569},
-    {"name": "casserole", "id": 426, "trainId": 570},
-    {"name": "frying pan", "id": 1039, "trainId": 571},
-    {"name": "desk organizer", "id": 727, "trainId": 572},
-    {"name": "mast", "id": 1508, "trainId": 573},
-    {"name": "spectacles, specs, eyeglasses, glasses", "id": 2490, "trainId": 574},
-    {"name": "service elevator", "id": 2299, "trainId": 575},
-    {"name": "dollhouse", "id": 768, "trainId": 576},
-    {"name": "hammock", "id": 1172, "trainId": 577},
-    {"name": "clothes hanging", "id": 537, "trainId": 578},
-    {"name": "photocopier", "id": 1847, "trainId": 579},
-    {"name": "notepad", "id": 1664, "trainId": 580},
-    {"name": "golf cart", "id": 1110, "trainId": 581},
-    {"name": "footpath", "id": 1014, "trainId": 582},
-    {"name": "cross", "id": 662, "trainId": 583},
-    {"name": "baptismal font", "id": 121, "trainId": 584},
-    {"name": "boiler", "id": 227, "trainId": 585},
-    {"name": "skip", "id": 2410, "trainId": 586},
-    {"name": "rotisserie", "id": 2165, "trainId": 587},
-    {"name": "tables", "id": 2696, "trainId": 588},
-    {"name": "water mill", "id": 3005, "trainId": 589},
-    {"name": "helmet", "id": 1231, "trainId": 590},
-    {"name": "cover curtain", "id": 635, "trainId": 591},
-    {"name": "brick", "id": 292, "trainId": 592},
-    {"name": "table runner", "id": 2690, "trainId": 593},
-    {"name": "ashtray", "id": 65, "trainId": 594},
-    {"name": "street box", "id": 2607, "trainId": 595},
-    {"name": "stick", "id": 2574, "trainId": 596},
-    {"name": "hangers", "id": 1188, "trainId": 597},
-    {"name": "cells", "id": 456, "trainId": 598},
-    {"name": "urinal", "id": 2913, "trainId": 599},
-    {"name": "centerpiece", "id": 459, "trainId": 600},
-    {"name": "portable fridge", "id": 1955, "trainId": 601},
-    {"name": "dvds", "id": 827, "trainId": 602},
-    {"name": "golf club", "id": 1111, "trainId": 603},
-    {"name": "skirting board", "id": 2412, "trainId": 604},
-    {"name": "water cooler", "id": 2997, "trainId": 605},
-    {"name": "clipboard", "id": 528, "trainId": 606},
-    {"name": "camera, photographic camera", "id": 366, "trainId": 607},
-    {"name": "pigeonhole", "id": 1863, "trainId": 608},
-    {"name": "chips", "id": 500, "trainId": 609},
-    {"name": "food processor", "id": 1001, "trainId": 610},
-    {"name": "post box", "id": 1958, "trainId": 611},
-    {"name": "lid", "id": 1441, "trainId": 612},
-    {"name": "drum", "id": 809, "trainId": 613},
-    {"name": "blender", "id": 210, "trainId": 614},
-    {"name": "cave entrance", "id": 435, "trainId": 615},
-    {"name": "dental chair", "id": 718, "trainId": 616},
-    {"name": "obelisk", "id": 1674, "trainId": 617},
-    {"name": "canoe", "id": 388, "trainId": 618},
-    {"name": "mobile", "id": 1572, "trainId": 619},
-    {"name": "monitors", "id": 1584, "trainId": 620},
-    {"name": "pool ball", "id": 1944, "trainId": 621},
-    {"name": "cue rack", "id": 674, "trainId": 622},
-    {"name": "baggage carts", "id": 99, "trainId": 623},
-    {"name": "shore", "id": 2352, "trainId": 624},
-    {"name": "fork", "id": 1019, "trainId": 625},
-    {"name": "paper filer", "id": 1763, "trainId": 626},
-    {"name": "bicycle rack", "id": 185, "trainId": 627},
-    {"name": "coat rack", "id": 554, "trainId": 628},
-    {"name": "garland", "id": 1066, "trainId": 629},
-    {"name": "sports bag", "id": 2508, "trainId": 630},
-    {"name": "fish tank", "id": 951, "trainId": 631},
-    {"name": "towel dispenser", "id": 2822, "trainId": 632},
-    {"name": "carriage", "id": 415, "trainId": 633},
-    {"name": "brochure", "id": 297, "trainId": 634},
-    {"name": "plaque", "id": 1914, "trainId": 635},
-    {"name": "stringer", "id": 2619, "trainId": 636},
-    {"name": "iron", "id": 1338, "trainId": 637},
-    {"name": "spoon", "id": 2505, "trainId": 638},
-    {"name": "flag pole", "id": 955, "trainId": 639},
-    {"name": "toilet brush", "id": 2786, "trainId": 640},
-    {"name": "book stand", "id": 238, "trainId": 641},
-    {"name": "water faucet, water tap, tap, hydrant", "id": 3000, "trainId": 642},
-    {"name": "ticket office", "id": 2763, "trainId": 643},
-    {"name": "broom", "id": 299, "trainId": 644},
-    {"name": "dvd", "id": 822, "trainId": 645},
-    {"name": "ice bucket", "id": 1288, "trainId": 646},
-    {"name": "carapace, shell, cuticle, shield", "id": 3101, "trainId": 647},
-    {"name": "tureen", "id": 2894, "trainId": 648},
-    {"name": "folders", "id": 992, "trainId": 649},
-    {"name": "chess", "id": 489, "trainId": 650},
-    {"name": "root", "id": 2157, "trainId": 651},
-    {"name": "sewing machine", "id": 2309, "trainId": 652},
-    {"name": "model", "id": 1576, "trainId": 653},
-    {"name": "pen", "id": 1810, "trainId": 654},
-    {"name": "violin", "id": 2964, "trainId": 655},
-    {"name": "sweatshirt", "id": 2662, "trainId": 656},
-    {"name": "recycling materials", "id": 2087, "trainId": 657},
-    {"name": "mitten", "id": 1569, "trainId": 658},
-    {"name": "chopping board, cutting board", "id": 503, "trainId": 659},
-    {"name": "mask", "id": 1505, "trainId": 660},
-    {"name": "log", "id": 1468, "trainId": 661},
-    {"name": "mouse, computer mouse", "id": 1613, "trainId": 662},
-    {"name": "grill", "id": 1138, "trainId": 663},
-    {"name": "hole", "id": 1256, "trainId": 664},
-    {"name": "target", "id": 2715, "trainId": 665},
-    {"name": "trash bag", "id": 2846, "trainId": 666},
-    {"name": "chalk", "id": 477, "trainId": 667},
-    {"name": "sticks", "id": 2576, "trainId": 668},
-    {"name": "balloon", "id": 108, "trainId": 669},
-    {"name": "score", "id": 2245, "trainId": 670},
-    {"name": "hair spray", "id": 1162, "trainId": 671},
-    {"name": "roll", "id": 2149, "trainId": 672},
-    {"name": "runner", "id": 2183, "trainId": 673},
-    {"name": "engine", "id": 858, "trainId": 674},
-    {"name": "inflatable glove", "id": 1324, "trainId": 675},
-    {"name": "games", "id": 1055, "trainId": 676},
-    {"name": "pallets", "id": 1741, "trainId": 677},
-    {"name": "baskets", "id": 149, "trainId": 678},
-    {"name": "coop", "id": 615, "trainId": 679},
-    {"name": "dvd player", "id": 825, "trainId": 680},
-    {"name": "rocking horse", "id": 2143, "trainId": 681},
-    {"name": "buckets", "id": 304, "trainId": 682},
-    {"name": "bread rolls", "id": 283, "trainId": 683},
-    {"name": "shawl", "id": 2322, "trainId": 684},
-    {"name": "watering can", "id": 3017, "trainId": 685},
-    {"name": "spotlights", "id": 2510, "trainId": 686},
-    {"name": "post-it", "id": 1960, "trainId": 687},
-    {"name": "bowls", "id": 265, "trainId": 688},
-    {"name": "security camera", "id": 2282, "trainId": 689},
-    {"name": "runner cloth", "id": 2184, "trainId": 690},
-    {"name": "lock", "id": 1461, "trainId": 691},
-    {"name": "alarm, warning device, alarm system", "id": 3113, "trainId": 692},
-    {"name": "side", "id": 2372, "trainId": 693},
-    {"name": "roulette", "id": 2166, "trainId": 694},
-    {"name": "bone", "id": 232, "trainId": 695},
-    {"name": "cutlery", "id": 693, "trainId": 696},
-    {"name": "pool balls", "id": 1945, "trainId": 697},
-    {"name": "wheels", "id": 3039, "trainId": 698},
-    {"name": "spice rack", "id": 2494, "trainId": 699},
-    {"name": "plant pots", "id": 1908, "trainId": 700},
-    {"name": "towel ring", "id": 2827, "trainId": 701},
-    {"name": "bread box", "id": 280, "trainId": 702},
-    {"name": "video", "id": 2950, "trainId": 703},
-    {"name": "funfair", "id": 1044, "trainId": 704},
-    {"name": "breads", "id": 288, "trainId": 705},
-    {"name": "tripod", "id": 2863, "trainId": 706},
-    {"name": "ironing board", "id": 1342, "trainId": 707},
-    {"name": "skimmer", "id": 2409, "trainId": 708},
-    {"name": "hollow", "id": 1258, "trainId": 709},
-    {"name": "scratching post", "id": 2249, "trainId": 710},
-    {"name": "tricycle", "id": 2862, "trainId": 711},
-    {"name": "file box", "id": 920, "trainId": 712},
-    {"name": "mountain pass", "id": 1607, "trainId": 713},
-    {"name": "tombstones", "id": 2802, "trainId": 714},
-    {"name": "cooker", "id": 610, "trainId": 715},
-    {"name": "card game, cards", "id": 3129, "trainId": 716},
-    {"name": "golf bag", "id": 1108, "trainId": 717},
-    {"name": "towel paper", "id": 2823, "trainId": 718},
-    {"name": "chaise lounge", "id": 476, "trainId": 719},
-    {"name": "sun", "id": 2641, "trainId": 720},
-    {"name": "toilet paper holder", "id": 2788, "trainId": 721},
-    {"name": "rake", "id": 2070, "trainId": 722},
-    {"name": "key", "id": 1368, "trainId": 723},
-    {"name": "umbrella stand", "id": 2903, "trainId": 724},
-    {"name": "dartboard", "id": 699, "trainId": 725},
-    {"name": "transformer", "id": 2844, "trainId": 726},
-    {"name": "fireplace utensils", "id": 942, "trainId": 727},
-    {"name": "sweatshirts", "id": 2663, "trainId": 728},
-    {
-        "name": "cellular telephone, cellular phone, cellphone, cell, mobile phone",
-        "id": 457,
-        "trainId": 729,
-    },
-    {"name": "tallboy", "id": 2701, "trainId": 730},
-    {"name": "stapler", "id": 2540, "trainId": 731},
-    {"name": "sauna", "id": 2231, "trainId": 732},
-    {"name": "test tube", "id": 2746, "trainId": 733},
-    {"name": "palette", "id": 1738, "trainId": 734},
-    {"name": "shopping carts", "id": 2350, "trainId": 735},
-    {"name": "tools", "id": 2808, "trainId": 736},
-    {"name": "push button, push, button", "id": 2025, "trainId": 737},
-    {"name": "star", "id": 2541, "trainId": 738},
-    {"name": "roof rack", "id": 2156, "trainId": 739},
-    {"name": "barbed wire", "id": 126, "trainId": 740},
-    {"name": "spray", "id": 2512, "trainId": 741},
-    {"name": "ear", "id": 831, "trainId": 742},
-    {"name": "sponge", "id": 2503, "trainId": 743},
-    {"name": "racket", "id": 2039, "trainId": 744},
-    {"name": "tins", "id": 2774, "trainId": 745},
-    {"name": "eyeglasses", "id": 886, "trainId": 746},
-    {"name": "file", "id": 919, "trainId": 747},
-    {"name": "scarfs", "id": 2240, "trainId": 748},
-    {"name": "sugar bowl", "id": 2636, "trainId": 749},
-    {"name": "flip flop", "id": 963, "trainId": 750},
-    {"name": "headstones", "id": 1218, "trainId": 751},
-    {"name": "laptop bag", "id": 1406, "trainId": 752},
-    {"name": "leash", "id": 1420, "trainId": 753},
-    {"name": "climbing frame", "id": 526, "trainId": 754},
-    {"name": "suit hanger", "id": 2639, "trainId": 755},
-    {"name": "floor spotlight", "id": 975, "trainId": 756},
-    {"name": "plate rack", "id": 1921, "trainId": 757},
-    {"name": "sewer", "id": 2305, "trainId": 758},
-    {"name": "hard drive", "id": 1193, "trainId": 759},
-    {"name": "sprinkler", "id": 2517, "trainId": 760},
-    {"name": "tools box", "id": 2809, "trainId": 761},
-    {"name": "necklace", "id": 1647, "trainId": 762},
-    {"name": "bulbs", "id": 314, "trainId": 763},
-    {"name": "steel industry", "id": 2560, "trainId": 764},
-    {"name": "club", "id": 545, "trainId": 765},
-    {"name": "jack", "id": 1345, "trainId": 766},
-    {"name": "door bars", "id": 775, "trainId": 767},
-    {
-        "name": "control panel, instrument panel, control board, board, panel",
-        "id": 603,
-        "trainId": 768,
-    },
-    {"name": "hairbrush", "id": 1163, "trainId": 769},
-    {"name": "napkin holder", "id": 1641, "trainId": 770},
-    {"name": "office", "id": 1678, "trainId": 771},
-    {"name": "smoke detector", "id": 2450, "trainId": 772},
-    {"name": "utensils", "id": 2915, "trainId": 773},
-    {"name": "apron", "id": 42, "trainId": 774},
-    {"name": "scissors", "id": 2242, "trainId": 775},
-    {"name": "terminal", "id": 2741, "trainId": 776},
-    {"name": "grinder", "id": 1143, "trainId": 777},
-    {"name": "entry phone", "id": 862, "trainId": 778},
-    {"name": "newspaper stand", "id": 1654, "trainId": 779},
-    {"name": "pepper shaker", "id": 1826, "trainId": 780},
-    {"name": "onions", "id": 1689, "trainId": 781},
-    {
-        "name": "central processing unit, cpu, c p u , central processor, processor, mainframe",
-        "id": 3124,
-        "trainId": 782,
-    },
-    {"name": "tape", "id": 2710, "trainId": 783},
-    {"name": "bat", "id": 152, "trainId": 784},
-    {"name": "coaster", "id": 549, "trainId": 785},
-    {"name": "calculator", "id": 360, "trainId": 786},
-    {"name": "potatoes", "id": 1982, "trainId": 787},
-    {"name": "luggage rack", "id": 1478, "trainId": 788},
-    {"name": "salt", "id": 2203, "trainId": 789},
-    {"name": "street number", "id": 2612, "trainId": 790},
-    {"name": "viewpoint", "id": 2956, "trainId": 791},
-    {"name": "sword", "id": 2681, "trainId": 792},
-    {"name": "cd", "id": 437, "trainId": 793},
-    {"name": "rowing machine", "id": 2171, "trainId": 794},
-    {"name": "plug", "id": 1933, "trainId": 795},
-    {"name": "andiron, firedog, dog, dog-iron", "id": 3110, "trainId": 796},
-    {"name": "pepper", "id": 1824, "trainId": 797},
-    {"name": "tongs", "id": 2803, "trainId": 798},
-    {"name": "bonfire", "id": 234, "trainId": 799},
-    {"name": "dog dish", "id": 764, "trainId": 800},
-    {"name": "belt", "id": 177, "trainId": 801},
-    {"name": "dumbbells", "id": 817, "trainId": 802},
-    {"name": "videocassette recorder, vcr", "id": 3145, "trainId": 803},
-    {"name": "hook", "id": 1262, "trainId": 804},
-    {"name": "envelopes", "id": 864, "trainId": 805},
-    {"name": "shower faucet", "id": 2359, "trainId": 806},
-    {"name": "watch", "id": 2992, "trainId": 807},
-    {"name": "padlock", "id": 1725, "trainId": 808},
-    {"name": "swimming pool ladder", "id": 2667, "trainId": 809},
-    {"name": "spanners", "id": 2484, "trainId": 810},
-    {"name": "gravy boat", "id": 1133, "trainId": 811},
-    {"name": "notice board", "id": 1667, "trainId": 812},
-    {"name": "trash bags", "id": 2847, "trainId": 813},
-    {"name": "fire alarm", "id": 932, "trainId": 814},
-    {"name": "ladle", "id": 1392, "trainId": 815},
-    {"name": "stethoscope", "id": 2573, "trainId": 816},
-    {"name": "rocket", "id": 2140, "trainId": 817},
-    {"name": "funnel", "id": 1046, "trainId": 818},
-    {"name": "bowling pins", "id": 264, "trainId": 819},
-    {"name": "valve", "id": 2927, "trainId": 820},
-    {"name": "thermometer", "id": 2752, "trainId": 821},
-    {"name": "cups", "id": 679, "trainId": 822},
-    {"name": "spice jar", "id": 2493, "trainId": 823},
-    {"name": "night light", "id": 1658, "trainId": 824},
-    {"name": "soaps", "id": 2466, "trainId": 825},
-    {"name": "games table", "id": 1057, "trainId": 826},
-    {"name": "slotted spoon", "id": 2444, "trainId": 827},
-    {"name": "reel", "id": 2093, "trainId": 828},
-    {"name": "scourer", "id": 2248, "trainId": 829},
-    {"name": "sleeping robe", "id": 2432, "trainId": 830},
-    {"name": "desk mat", "id": 726, "trainId": 831},
-    {"name": "dumbbell", "id": 816, "trainId": 832},
-    {"name": "hammer", "id": 1171, "trainId": 833},
-    {"name": "tie", "id": 2766, "trainId": 834},
-    {"name": "typewriter", "id": 2900, "trainId": 835},
-    {"name": "shaker", "id": 2313, "trainId": 836},
-    {"name": "cheese dish", "id": 488, "trainId": 837},
-    {"name": "sea star", "id": 2265, "trainId": 838},
-    {"name": "racquet", "id": 2043, "trainId": 839},
-    {"name": "butane gas cylinder", "id": 332, "trainId": 840},
-    {"name": "paper weight", "id": 1771, "trainId": 841},
-    {"name": "shaving brush", "id": 2320, "trainId": 842},
-    {"name": "sunglasses", "id": 2646, "trainId": 843},
-    {"name": "gear shift", "id": 1089, "trainId": 844},
-    {"name": "towel rail", "id": 2826, "trainId": 845},
-    {"name": "adding machine, totalizer, totaliser", "id": 3148, "trainId": 846},
-]
-
-
-def loadAde20K(file):
-    fileseg = file.replace(".jpg", "_seg.png")
-    with Image.open(fileseg) as io:
-        seg = np.array(io)
-
-    R = seg[:, :, 0]
-    G = seg[:, :, 1]
-    ObjectClassMasks = (R / 10).astype(np.int32) * 256 + (G.astype(np.int32))
-
-    return {"img_name": file, "segm_name": fileseg, "class_mask": ObjectClassMasks}
-
-
-if __name__ == "__main__":
-    dataset_dir = Path(os.getenv("DETECTRON2_DATASETS", "datasets"))
-    index_file = dataset_dir / "ADE20K_2021_17_01" / "index_ade20k.pkl"
-    print('Caution: we only generate the validation set!')
-    with open(index_file, "rb") as f:
-        index_ade20k = pkl.load(f)
-
-    id_map = {}
-    for cat in ADE20K_SEM_SEG_FULL_CATEGORIES:
-        id_map[cat["id"]] = cat["trainId"]
-
-    # make output dir
-    for name in ["training", "validation"]:
-        image_dir = dataset_dir / "ADE20K_2021_17_01" / "images_detectron2" / name
-        image_dir.mkdir(parents=True, exist_ok=True)
-        annotation_dir = dataset_dir / "ADE20K_2021_17_01" / "annotations_detectron2" / name
-        annotation_dir.mkdir(parents=True, exist_ok=True)
-
-    # process image and gt
-    for i, (folder_name, file_name) in tqdm.tqdm(
-        enumerate(zip(index_ade20k["folder"], index_ade20k["filename"])),
-        total=len(index_ade20k["filename"]),
-    ):
-        split = "validation" if file_name.split("_")[1] == "val" else "training"
-        if split == 'training':
-            # FIXME: If you want to generate training set, delete this condition
-            continue
-        info = loadAde20K(str(dataset_dir / folder_name / file_name))
-
-        # resize image and label
-        img = np.asarray(Image.open(info["img_name"]))
-        lab = np.asarray(info["class_mask"])
-
-        h, w = img.shape[0], img.shape[1]
-        max_size = 512
-        resize = True
-        if w >= h > max_size:
-            h_new, w_new = max_size, round(w / float(h) * max_size)
-        elif h >= w > max_size:
-            h_new, w_new = round(h / float(w) * max_size), max_size
-        else:
-            resize = False
-
-        if resize:
-            img = cv2.resize(img, (w_new, h_new), interpolation=cv2.INTER_LINEAR)
-            lab = cv2.resize(lab, (w_new, h_new), interpolation=cv2.INTER_NEAREST)
-
-        assert img.dtype == np.uint8
-        assert lab.dtype == np.int32
-
-        # apply label conversion and save into uint16 images
-        output = np.zeros_like(lab, dtype=np.uint16) + 65535
-        for obj_id in np.unique(lab):
-            if obj_id in id_map:
-                output[lab == obj_id] = id_map[obj_id]
-
-        output_img = dataset_dir / "ADE20K_2021_17_01" / "images_detectron2" / split / file_name
-        output_lab = (
-            dataset_dir
-            / "ADE20K_2021_17_01"
-            / "annotations_detectron2"
-            / split
-            / file_name.replace(".jpg", ".tif")
-        )
-        Image.fromarray(img).save(output_img)
-
-        assert output.dtype == np.uint16
-        Image.fromarray(output).save(output_lab)
\ No newline at end of file
diff --git a/spaces/haotiz/glip-zeroshot-demo/maskrcnn_benchmark/data/samplers/distributed.py b/spaces/haotiz/glip-zeroshot-demo/maskrcnn_benchmark/data/samplers/distributed.py
deleted file mode 100644
index 5b1552f68eb139f8c526b8376e81869efd370ccd..0000000000000000000000000000000000000000
--- a/spaces/haotiz/glip-zeroshot-demo/maskrcnn_benchmark/data/samplers/distributed.py
+++ /dev/null
@@ -1,72 +0,0 @@
-# Copyright (c) Facebook, Inc. and its affiliates. All Rights Reserved.
-# Code is copy-pasted exactly as in torch.utils.data.distributed.
-# FIXME remove this once c10d fixes the bug it has
-import math
-import torch
-import torch.distributed as dist
-from torch.utils.data.sampler import Sampler
-
-from maskrcnn_benchmark.utils.comm import shared_random_seed
-
-
-class DistributedSampler(Sampler):
-    """Sampler that restricts data loading to a subset of the dataset.
-    It is especially useful in conjunction with
-    :class:`torch.nn.parallel.DistributedDataParallel`. In such case, each
-    process can pass a DistributedSampler instance as a DataLoader sampler,
-    and load a subset of the original dataset that is exclusive to it.
-    .. note::
-        Dataset is assumed to be of constant size.
-    Arguments:
-        dataset: Dataset used for sampling.
-        num_replicas (optional): Number of processes participating in
-            distributed training.
-        rank (optional): Rank of the current process within num_replicas.
-    """
-
-    def __init__(self, dataset, num_replicas=None, rank=None, shuffle=True, use_random=False):
-        if num_replicas is None:
-            if not dist.is_available():
-                raise RuntimeError("Requires distributed package to be available")
-            num_replicas = dist.get_world_size()
-        if rank is None:
-            if not dist.is_available():
-                raise RuntimeError("Requires distributed package to be available")
-            rank = dist.get_rank()
-        self.dataset = dataset
-        self.num_replicas = num_replicas
-        self.rank = rank
-        self.epoch = 0
-        self.num_samples = int(math.ceil(len(self.dataset) * 1.0 / self.num_replicas))
-        self.total_size = self.num_samples * self.num_replicas
-        self.shuffle = shuffle
-        self.use_random = use_random
-
-    def __iter__(self):
-        if self.shuffle:
-            # deterministically shuffle based on epoch
-            _seed = self.epoch
-            if self.use_random:
-                _seed = int(shared_random_seed())
-            g = torch.Generator()
-            g.manual_seed(_seed)
-            indices = torch.randperm(len(self.dataset), generator=g).tolist()
-        else:
-            indices = torch.arange(len(self.dataset)).tolist()
-
-        # add extra samples to make it evenly divisible
-        indices += indices[: (self.total_size - len(indices))]
-        assert len(indices) == self.total_size
-
-        # subsample
-        offset = self.num_samples * self.rank
-        indices = indices[offset : offset + self.num_samples]
-        assert len(indices) == self.num_samples
-
-        return iter(indices)
-
-    def __len__(self):
-        return self.num_samples
-
-    def set_epoch(self, epoch):
-        self.epoch = epoch
diff --git a/spaces/haseena97/malaysian_dessert/README.md b/spaces/haseena97/malaysian_dessert/README.md
deleted file mode 100644
index e3da706f5e8f41eb86fd57f85fc4aeec74d74585..0000000000000000000000000000000000000000
--- a/spaces/haseena97/malaysian_dessert/README.md
+++ /dev/null
@@ -1,13 +0,0 @@
----
-title: Malaysian Dessert
-emoji: 🏃
-colorFrom: blue
-colorTo: gray
-sdk: gradio
-sdk_version: 3.3
-app_file: app.py
-pinned: false
-license: apache-2.0
----
-
-Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
diff --git a/spaces/hasibzunair/fifa-tryon-demo/models/models.py b/spaces/hasibzunair/fifa-tryon-demo/models/models.py
deleted file mode 100644
index 507144261ccd890685196f1c5f75378f2973c004..0000000000000000000000000000000000000000
--- a/spaces/hasibzunair/fifa-tryon-demo/models/models.py
+++ /dev/null
@@ -1,23 +0,0 @@
-# Copyright (C) 2017 NVIDIA Corporation. All rights reserved.
-# Licensed under the CC BY-NC-SA 4.0 license (https://creativecommons.org/licenses/by-nc-sa/4.0/legalcode).
-import torch
-#import ipdb
-
-
-def create_model(opt):
-    if opt.model == 'pix2pixHD':
-        from .pix2pixHD_model import Pix2PixHDModel, InferenceModel
-        if opt.isTrain:
-            model = Pix2PixHDModel()
-            # ipdb.set_trace()
-        else:
-            model = InferenceModel()
-
-    model.initialize(opt)
-    if opt.verbose:
-        print("model [%s] was created" % (model.name()))
-
-    if opt.isTrain and len(opt.gpu_ids):
-        model = torch.nn.DataParallel(model, device_ids=opt.gpu_ids)
-
-    return model
diff --git a/spaces/hekbobo/bingo/src/components/markdown.tsx b/spaces/hekbobo/bingo/src/components/markdown.tsx
deleted file mode 100644
index d4491467a1f14d1d72e535caac9c40636054e5df..0000000000000000000000000000000000000000
--- a/spaces/hekbobo/bingo/src/components/markdown.tsx
+++ /dev/null
@@ -1,9 +0,0 @@
-import { FC, memo } from 'react'
-import ReactMarkdown, { Options } from 'react-markdown'
-
-export const MemoizedReactMarkdown: FC<Options> = memo(
-  ReactMarkdown,
-  (prevProps, nextProps) =>
-    prevProps.children === nextProps.children &&
-    prevProps.className === nextProps.className
-)
diff --git a/spaces/hero-intelligent/MT3/app.py b/spaces/hero-intelligent/MT3/app.py
deleted file mode 100644
index 07f33a360b9b291054d9f086bb2d81735ac2af0b..0000000000000000000000000000000000000000
--- a/spaces/hero-intelligent/MT3/app.py
+++ /dev/null
@@ -1,55 +0,0 @@
-import installation
-installation
-
-import gradio as gr
-from pathlib import Path
-
-from imports_and_definitions import InferenceModel
-from imports_and_definitions import upload_audio
-import note_seq
-
-def inference(audio,model):
-  with open(audio, 'rb') as fd:
-      contents = fd.read()
-  audio = upload_audio(contents,sample_rate=16000)
-  inference_model = InferenceModel('/home/user/app/checkpoints/' + str(model) + '/', str(model))
-  est_ns = inference_model(audio)
-  note_seq.sequence_proto_to_midi_file(est_ns, './transcribed.mid')
-  return './transcribed.mid'
-  
-title = "MT3"
-description = """
-Gradio demo for MT3: Multi-Task Multitrack Music Transcription. To use it, simply upload your audio file, then choose either ismir2021 for piano transcription or mt3 for multi-instrument transcription. Read more at the links below.
-It will be of better quality if pure music is inputted. It is recomended to remove the voice in a song first using UVR5. Check it out in the links below.
-"""
-
-article = """
-<p style='text-align: center'>
-    MT3: 
-    <a href='https://arxiv.org/abs/2111.03017' target='_blank'>Multi-Task Multitrack Music Transcription</a> | 
-    <a href='https://github.com/magenta/mt3' target='_blank'>Github Repo</a> | 
-    <a href='https://huggingface.co/spaces/oniati/mrt/tree/main' target='_blank'>Huggingface</a> | 
-    <a href='https://github.com/hero-intelligent/MT3-Docker' target='_blank'>Docker Source Code</a>
-</p>
-<p style='text-align: center'>
-    UVR5: 
-    <a href='https://ultimatevocalremover.com/' target='_blank'>Official Site</a> | 
-    <a href='https://github.com/Anjok07/ultimatevocalremovergui' target='_blank'>Github Repo</a>
-</p>
-"""
-
-demo = gr.Interface(
-    fn=inference, 
-    inputs=[
-      gr.inputs.Audio(type="filepath", label="Input"), 
-      gr.Dropdown(choices=["mt3", "ismir2021"], value="mt3")
-    ],
-    outputs=[gr.outputs.File(label="Output")],
-    title=title,
-    description=description,
-    article=article,
-    allow_flagging=False,
-    allow_screenshot=False,
-    enable_queue=True
-    )
-demo.launch(server_name="0.0.0.0")
diff --git a/spaces/hlydecker/RA-document-QAchat/streamlit_langchain_chat/customized_langchain/__init__.py b/spaces/hlydecker/RA-document-QAchat/streamlit_langchain_chat/customized_langchain/__init__.py
deleted file mode 100644
index a2f5835bbc2e5b03a8b33464008e8183c04307da..0000000000000000000000000000000000000000
--- a/spaces/hlydecker/RA-document-QAchat/streamlit_langchain_chat/customized_langchain/__init__.py
+++ /dev/null
@@ -1,10 +0,0 @@
-from streamlit_langchain_chat.customized_langchain.docstore.in_memory import InMemoryDocstore
-from streamlit_langchain_chat.customized_langchain.vectorstores import FAISS
-from streamlit_langchain_chat.customized_langchain.vectorstores import Pinecone
-
-
-__all__ = [
-    "FAISS",
-    "InMemoryDocstore",
-    "Pinecone",
-]
diff --git a/spaces/hlydecker/RA-document-QAchat/streamlit_langchain_chat/customized_langchain/vectorstores/faiss.py b/spaces/hlydecker/RA-document-QAchat/streamlit_langchain_chat/customized_langchain/vectorstores/faiss.py
deleted file mode 100644
index 1caf619aa213aef66d0bbb1fdf631b8d72c20970..0000000000000000000000000000000000000000
--- a/spaces/hlydecker/RA-document-QAchat/streamlit_langchain_chat/customized_langchain/vectorstores/faiss.py
+++ /dev/null
@@ -1,100 +0,0 @@
-# import hashlib
-
-from langchain.vectorstores.faiss import *
-from langchain.vectorstores.faiss import FAISS as OriginalFAISS
-
-from streamlit_langchain_chat.customized_langchain.docstore.in_memory import InMemoryDocstore
-
-
-class FAISS(OriginalFAISS):
-    def __add(
-        self,
-        texts: Iterable[str],
-        embeddings: Iterable[List[float]],
-        metadatas: Optional[List[dict]] = None,
-        **kwargs: Any,
-    ) -> List[str]:
-        if not isinstance(self.docstore, AddableMixin):
-            raise ValueError(
-                "If trying to add texts, the underlying docstore should support "
-                f"adding items, which {self.docstore} does not"
-            )
-        documents = []
-        for i, text in enumerate(texts):
-            metadata = metadatas[i] if metadatas else {}
-            documents.append(Document(page_content=text, metadata=metadata))
-        # Add to the index, the index_to_id mapping, and the docstore.
-        starting_len = len(self.index_to_docstore_id)
-        self.index.add(np.array(embeddings, dtype=np.float32))
-        # Get list of index, id, and docs.
-        full_info = [
-            (starting_len + i, str(uuid.uuid4()), doc)
-            for i, doc in enumerate(documents)
-        ]
-        # Add information to docstore and index.
-        self.docstore.add({_id: doc for _, _id, doc in full_info})
-        index_to_id = {index: _id for index, _id, _ in full_info}
-        self.index_to_docstore_id.update(index_to_id)
-        return [_id for _, _id, _ in full_info]
-
-    @classmethod
-    def __from(
-            cls,
-            texts: List[str],
-            embeddings: List[List[float]],
-            embedding: Embeddings,
-            metadatas: Optional[List[dict]] = None,
-            **kwargs: Any,
-    ) -> FAISS:
-        faiss = dependable_faiss_import()
-        index = faiss.IndexFlatL2(len(embeddings[0]))
-        index.add(np.array(embeddings, dtype=np.float32))
-        documents = []
-        for i, text in enumerate(texts):
-            metadata = metadatas[i] if metadatas else {}
-            documents.append(Document(page_content=text, metadata=metadata))
-        index_to_id = {i: str(uuid.uuid4()) for i in range(len(documents))}
-
-        # # TODO: cambiar para usar el hash. Y ver donde se pondria para que no cargara el chunk en el dataset
-        # index_to_id_2 = dict()
-        # for i in range(len(documents)):
-        #     h = hashlib.new('sha256')
-        #     text_ = documents[i].page_content
-        #     h.update(text_.encode())
-        #     index_to_id_2[i] = str(h.hexdigest())
-        # #
-        docstore = InMemoryDocstore(
-            {index_to_id[i]: doc for i, doc in enumerate(documents)}
-        )
-        return cls(embedding.embed_query, index, docstore, index_to_id)
-
-    @classmethod
-    def from_texts(
-            cls,
-            texts: List[str],
-            embedding: Embeddings,
-            metadatas: Optional[List[dict]] = None,
-            **kwargs: Any,
-    ) -> FAISS:
-        """Construct FAISS wrapper from raw documents.
-
-        This is a user friendly interface that:
-            1. Embeds documents.
-            2. Creates an in memory docstore
-            3. Initializes the FAISS database
-
-        This is intended to be a quick way to get started.
-
-        Example:
-            .. code-block:: python
-
-                from langchain import FAISS
-                from langchain.embeddings import OpenAIEmbeddings
-                embeddings = OpenAIEmbeddings()
-                faiss = FAISS.from_texts(texts, embeddings)
-        """
-        # embeddings = embedding.embed_documents(texts)
-        print(f"len(texts): {len(texts)}")  # TODO: borrar
-        embeddings = [embedding.embed_documents([text])[0] for text in texts]
-        print(f"len(embeddings): {len(embeddings)}")  # TODO: borrar
-        return cls.__from(texts, embeddings, embedding, metadatas, **kwargs)
diff --git a/spaces/hra/ChatGPT-Tech-Radar/app.py b/spaces/hra/ChatGPT-Tech-Radar/app.py
deleted file mode 100644
index dcfe1cd13b47065566b51ea1af8d61a210826341..0000000000000000000000000000000000000000
--- a/spaces/hra/ChatGPT-Tech-Radar/app.py
+++ /dev/null
@@ -1,233 +0,0 @@
-from gpt_index import GPTListIndex, SimpleWebPageReader, BeautifulSoupWebReader, GPTSimpleVectorIndex,LLMPredictor
-from IPython.display import Markdown, display
-from langchain.agents import load_tools, Tool, initialize_agent
-from langchain.llms import OpenAI
-from langchain.agents import ZeroShotAgent, Tool, AgentExecutor
-from langchain.agents import initialize_agent, Tool
-from langchain import LLMChain
-from langchain import PromptTemplate
-import gradio as gr
-import pandas as pd
-import openai
-from sklearn.manifold import TSNE
-from sklearn.cluster import KMeans
-from openai.embeddings_utils import get_embedding
-
-import numpy as np
-import matplotlib.pyplot as plt
-import matplotlib
-import datetime
-from datetime import datetime, date, time, timedelta
-import os
-from PIL import Image
-from PIL import ImageOps
-from PIL import Image, ImageDraw, ImageFont
-from io import BytesIO
-import requests
-
-import gcsfs
-fs = gcsfs.GCSFileSystem(project='createinsightsproject',token='anon')
-fs.ls('trends_chrome_extension_bucket')
-print('Started')
-###download both text and image from cloud to display
-with fs.open('trends_chrome_extension_bucket/lastradartext.txt', 'rb') as file:
-    data_old = file.read()
-print(data_old)
-value1,value2,value3,value4,value5,value6=str(data_old.decode()).split('SEPERATOR')
-
-img_data = requests.get('https://storage.googleapis.com/trends_chrome_extension_bucket/lasttechradar.png').content
-with open('lasttechradar.png', 'wb') as handler:
-    handler.write(img_data)
-
-def getlastimage():
-    #print('Came into getlastimage')
-    img_data = requests.get('https://storage.googleapis.com/trends_chrome_extension_bucket/lasttechradar.png').content
-    with open('lasttechradar1.png', 'wb') as handler:
-        handler.write(img_data)
-
-    with fs.open('trends_chrome_extension_bucket/lastradartext.txt', 'rb') as file:
-        data_old = file.read()
-    #print(data_old)
-    value1,value2,value3,value4,value5,value6=str(data_old.decode()).split('SEPERATOR')
-    return 'lasttechradar1.png',value1.strip(),value2.strip(),value3.strip(),value4.strip(),value5.strip(),value6.strip()
-
-
-def getstuff(openapikey):
-  dateforfilesave=datetime.today().strftime("%d-%m-%Y %I:%M%p")
-  print(dateforfilesave)
-  os.environ['OPENAI_API_KEY'] = str(openapikey)
-
-  mainlistofanswers=[]
-  for each in ['www.mckinsey.com','www.bcg.com','www.bain.com','www.accenture.com']:
-    print(each)
-    Input_URL = "https://"+each 
-    documents = SimpleWebPageReader(html_to_text=True).load_data([Input_URL])
-    index = GPTSimpleVectorIndex(documents)
-    print('Came here 0')
-    #@title # Creating your Langchain Agent
-    def querying_db(query: str):
-      response = index.query(query)
-      return response
-
-    tools = [
-        Tool(
-            name = "QueryingDB",
-            func=querying_db,
-            description="This function takes a query string as input and returns the most relevant answer from the documentation as output"
-        )]
-    llm = OpenAI(temperature=0,openai_api_key=openapikey)
-    print('Came here 1')
-    query_string = "what are the top technologies mentioned?" 
-
-    agent = initialize_agent(tools, llm, agent="zero-shot-react-description", verbose=True)
-    result = agent.run(query_string)
-    mainlistofanswers.append(result)
-  
-  print('Came here 2')
-  print(mainlistofanswers)
-  newlistoftech=[]
-  newlistofcompanies=[]
-  for i in range(len(mainlistofanswers)):
-    each=mainlistofanswers[i]
-    each=each.replace("The top technologies mentioned are ","").replace("The technologies mentioned are ","")
-    each=each.replace(":","").replace(" and ",",").replace("and ",",").replace(" and",",").replace(" the "," ").replace("the "," ").replace(" the"," ").strip()
-    for item in each.split(","):
-        if item!='':
-          newlistoftech.append(item.strip())
-          newlistofcompanies.append(i)
-  tech_df=pd.DataFrame()
-  tech_df['tech']=newlistoftech
-  tech_df['company']=newlistofcompanies
-  print(newlistoftech)
-  print('Came here 3')
-  embedding_model = "text-embedding-ada-002"
-  embedding_encoding = "cl100k_base"  # this the encoding for text-embedding-ada-002
-  max_tokens = 8000  # the maximum for text-embedding-ada-002 is 8191
-
-  tech_df["embedding"] = tech_df['tech'].apply(lambda x: get_embedding(x, engine=embedding_model))
-
-  print('Came here 4')
-
-  # Load the embeddings
-
-  # Convert to a list of lists of floats
-  matrix = np.array(tech_df['embedding'].to_list())
-  perplexityvalue=max(int(len(tech_df['embedding'].to_list()))/2,5) ###original value was a constant of 15
-    
-  # Create a t-SNE model and transform the data
-  tsne = TSNE(n_components=2, perplexity=perplexityvalue, random_state=42, init='random', learning_rate=200)
-  vis_dims = tsne.fit_transform(matrix)
-
-  n_clusters = 5
-
-  kmeans = KMeans(n_clusters=n_clusters, init="k-means++", random_state=42)
-  kmeans.fit(matrix)
-  labels = kmeans.labels_
-  tech_df["Cluster"] = labels
-  print('Came here 5')
-  colors = ["red", "darkorange", "darkgrey", "blue", "darkgreen"]
-  x = [x for x,y in vis_dims]
-  y = [y for x,y in vis_dims]
-  color_indices = tech_df['Cluster'].values 
-
-  colormap = matplotlib.colors.ListedColormap(colors)
-  #plt.scatter(x, y, c=color_indices, cmap=colormap, alpha=0.3,)
-  fig, ax = plt.subplots(figsize=(12,8))
-  ax.scatter(x, y, c=color_indices, cmap=colormap, alpha=1, s=100)
-
-  for i, txt in enumerate(tech_df['tech'].tolist()):
-      ax.annotate(txt, (x[i], y[i]),fontsize=14)
-
-  plt.title("Top Technologies as of "+dateforfilesave,fontsize=20)
-  plt.axis('off')
-  plt.savefig('lasttechradar.png', bbox_inches='tight')
-  print('Came here 6')
-  response = openai.Completion.create(
-        engine="text-davinci-003",
-        prompt=f'I will give you top technologies list. Write a paragraph on it.\n\nTechnologies:'+",".join(tech_df['tech'].tolist()),
-        temperature=0,
-        max_tokens=1024,
-        top_p=1,
-        frequency_penalty=0,
-        presence_penalty=0,
-    )
-  print(response["choices"][0]["text"].replace("\n", ""))
-  desc_tmp=response["choices"][0]["text"].replace("\n", "")
-  print('Came here 7')
-  # Reading a review which belong to each group.
-  rev_per_cluster = 5
-
-  clusterstextlist=[]
-  for i in range(n_clusters):
-      print(f"Cluster {i} Theme:", end=" ")
-
-      reviews = "\n".join(tech_df[tech_df['Cluster'] == i]['tech'].tolist())
-      response = openai.Completion.create(
-          engine="text-davinci-003",
-          prompt=f'What do the following technologies have in common?\n\nCustomer reviews:\n"""\n{reviews}\n"""\n\nTheme:',
-          temperature=0,
-          max_tokens=64,
-          top_p=1,
-          frequency_penalty=0,
-          presence_penalty=0,
-      )
-      print(response["choices"][0]["text"].replace("\n", ""))
-
-      print(reviews)
-      clusterstextlist.append("Cluster "+str(i)+"\nTheme:"+response["choices"][0]["text"].replace("\n", "")+'\n'+reviews+'\n'+"-" * 10+'\n\n')
-  
-  textlist=[mainlistofanswers[0],"SEPERATOR",mainlistofanswers[1],"SEPERATOR",mainlistofanswers[2],"SEPERATOR",mainlistofanswers[3],"SEPERATOR",desc_tmp,"SEPERATOR","".join(clusterstextlist)]
-  ###create file with new info locally & upload to bucket
-  with open('lastradartext.txt', 'w') as f:
-    for line in textlist:
-        f.write(f"{line}\n")
-        
-  with fs.open('trends_chrome_extension_bucket/lastradartext.txt', 'wb') as file:
-      for line in textlist:
-        file.write(f"{line}\n".encode())
-          
-  print('Came here 8')   
-
-  ###read it and put in output
-
-  with open('lastradartext.txt', 'r') as file:
-    data_old = file.read()
-  value1,value2,value3,value4,value5,value6=str(data_old).split('SEPERATOR')
-
-  ###upload image to cloud for next run display
-  with open('lasttechradar.png','rb') as image_file:
-    image_string = image_file.read()
-    with fs.open('trends_chrome_extension_bucket/lasttechradar.png', 'wb') as file:
-        file.write(image_string)
-    
-  return 'lasttechradar.png',mainlistofanswers[0],mainlistofanswers[1],mainlistofanswers[2],mainlistofanswers[3],desc_tmp,"".join(clusterstextlist)
-
-with gr.Blocks() as demo:
-    gr.Markdown("<h1><center>ChatGPT Technology Radar</center></h1>")
-    gr.Markdown(
-        """What are the top technologies as of now? Let us query top consulting company websites & use ChatGPT to understand. \n\nShowcases ChatGPT integrated with real data. It shows how to get real-time data and marry it with ChatGPT capabilities. This demonstrates 'Chain of Thought' thinking using ChatGPT.\nLangChain & GPT-Index are both used.\n ![visitors](https://visitor-badge.glitch.me/badge?page_id=hra.ChatGPT-Tech-Radar)"""
-        )
-    
-    with gr.Row() as row:
-      textboxopenapi = gr.Textbox(placeholder="Enter OpenAPI Key...", lines=1,label='OpenAPI Key')
-      btn = gr.Button("Refresh")
-    with gr.Row() as row:
-      with gr.Column():
-        output_image = gr.components.Image(label="Tech Radar",value='lasttechradar.png')    
-      with gr.Column():
-        outputMck = gr.Textbox(placeholder=value1, lines=1,label='McKinsey View')
-        outputBcg = gr.Textbox(placeholder=value2, lines=1,label='BCG View')
-        outputBain = gr.Textbox(placeholder=value3, lines=1,label='Bain View')
-        outputAcc = gr.Textbox(placeholder=value4, lines=1,label='Accenture View')
-    with gr.Row() as row:
-      with gr.Column():
-        outputdesc = gr.Textbox(placeholder=value5, lines=1,label='Description')
-      with gr.Column():
-        outputclusters = gr.Textbox(placeholder=value6, lines=1,label='Clusters')
-
-
-    btn.click(getstuff, inputs=[textboxopenapi],outputs=[output_image,outputMck,outputBcg,outputBain,outputAcc,outputdesc,outputclusters])
-    
-    demo.load(getlastimage,[],[output_image,outputMck,outputBcg,outputBain,outputAcc,outputdesc,outputclusters])
-    
-demo.launch(debug=True)
\ No newline at end of file
diff --git a/spaces/huggingface-projects/color-palette-generator-sd/static/_app/immutable/components/error.svelte-130ca573.js b/spaces/huggingface-projects/color-palette-generator-sd/static/_app/immutable/components/error.svelte-130ca573.js
deleted file mode 100644
index 50d1d606292f7e877245f73c60c5ef6ef4042e54..0000000000000000000000000000000000000000
--- a/spaces/huggingface-projects/color-palette-generator-sd/static/_app/immutable/components/error.svelte-130ca573.js
+++ /dev/null
@@ -1 +0,0 @@
-import{S as A,i as C,s as F,k as v,q as k,a as h,e as q,l as g,m as E,r as $,h as p,c as R,b as u,F as P,u as S,A as w,G}from"../chunks/index-5559954d.js";import{s as H}from"../chunks/singletons-57086789.js";const O=()=>{const t=H,s={page:{subscribe:t.page.subscribe},navigating:{subscribe:t.navigating.subscribe},updated:t.updated};return Object.defineProperties(s,{preloading:{get(){return console.error("stores.preloading is deprecated; use stores.navigating instead"),{subscribe:t.navigating.subscribe}},enumerable:!1},session:{get(){return B(),{}},enumerable:!1}}),s},z={subscribe(t){return O().page.subscribe(t)}};function B(){throw new Error("stores.session is no longer available. See https://github.com/sveltejs/kit/discussions/5883")}function N(t){let s,i=t[0].error.frame+"",o;return{c(){s=v("pre"),o=k(i)},l(r){s=g(r,"PRE",{});var a=E(s);o=$(a,i),a.forEach(p)},m(r,a){u(r,s,a),P(s,o)},p(r,a){a&1&&i!==(i=r[0].error.frame+"")&&S(o,i)},d(r){r&&p(s)}}}function y(t){let s,i=t[0].error.stack+"",o;return{c(){s=v("pre"),o=k(i)},l(r){s=g(r,"PRE",{});var a=E(s);o=$(a,i),a.forEach(p)},m(r,a){u(r,s,a),P(s,o)},p(r,a){a&1&&i!==(i=r[0].error.stack+"")&&S(o,i)},d(r){r&&p(s)}}}function D(t){let s,i=t[0].status+"",o,r,a,b=t[0].error.message+"",_,d,c,m,l=t[0].error.frame&&N(t),n=t[0].error.stack&&y(t);return{c(){s=v("h1"),o=k(i),r=h(),a=v("pre"),_=k(b),d=h(),l&&l.c(),c=h(),n&&n.c(),m=q()},l(e){s=g(e,"H1",{});var f=E(s);o=$(f,i),f.forEach(p),r=R(e),a=g(e,"PRE",{});var j=E(a);_=$(j,b),j.forEach(p),d=R(e),l&&l.l(e),c=R(e),n&&n.l(e),m=q()},m(e,f){u(e,s,f),P(s,o),u(e,r,f),u(e,a,f),P(a,_),u(e,d,f),l&&l.m(e,f),u(e,c,f),n&&n.m(e,f),u(e,m,f)},p(e,[f]){f&1&&i!==(i=e[0].status+"")&&S(o,i),f&1&&b!==(b=e[0].error.message+"")&&S(_,b),e[0].error.frame?l?l.p(e,f):(l=N(e),l.c(),l.m(c.parentNode,c)):l&&(l.d(1),l=null),e[0].error.stack?n?n.p(e,f):(n=y(e),n.c(),n.m(m.parentNode,m)):n&&(n.d(1),n=null)},i:w,o:w,d(e){e&&p(s),e&&p(r),e&&p(a),e&&p(d),l&&l.d(e),e&&p(c),n&&n.d(e),e&&p(m)}}}function I(t,s,i){let o;return G(t,z,r=>i(0,o=r)),[o]}class L extends A{constructor(s){super(),C(this,s,I,D,F,{})}}export{L as default};
diff --git a/spaces/huggingface-projects/stable-diffusion-multiplayer/frontend/src/lib/liveblocks/useErrorListener.ts b/spaces/huggingface-projects/stable-diffusion-multiplayer/frontend/src/lib/liveblocks/useErrorListener.ts
deleted file mode 100644
index 3bbba01c1a95744407135657ab399085054278ff..0000000000000000000000000000000000000000
--- a/spaces/huggingface-projects/stable-diffusion-multiplayer/frontend/src/lib/liveblocks/useErrorListener.ts
+++ /dev/null
@@ -1,14 +0,0 @@
-
-import { onDestroy } from "svelte";
-import { useRoom } from "./useRoom";
-
-
-export function useErrorListener(callback: (err: Error) => void): void {
-  const room = useRoom();
-
-  const unsubscribe = room.events.error.subscribe((e: Error) => callback(e))
-
-  onDestroy(() => {
-    unsubscribe();
-  });
-}
\ No newline at end of file
diff --git a/spaces/huggingface/data-measurements-tool/data_measurements/zipf.py b/spaces/huggingface/data-measurements-tool/data_measurements/zipf.py
deleted file mode 100644
index 843ee00254f90eb86e10974d5c4019e696246d14..0000000000000000000000000000000000000000
--- a/spaces/huggingface/data-measurements-tool/data_measurements/zipf.py
+++ /dev/null
@@ -1,247 +0,0 @@
-# Copyright 2021 The HuggingFace Team. All rights reserved.
-#
-# Licensed under the Apache License, Version 2.0 (the "License");
-# you may not use this file except in compliance with the License.
-# You may obtain a copy of the License at
-#
-#     http://www.apache.org/licenses/LICENSE-2.0
-#
-# Unless required by applicable law or agreed to in writing, software
-# distributed under the License is distributed on an "AS IS" BASIS,
-# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
-# See the License for the specific language governing permissions and
-# limitations under the License.
-
-import logging
-from pathlib import Path
-
-import numpy as np
-import pandas as pd
-import powerlaw
-import streamlit as st
-from scipy.stats import ks_2samp
-from scipy.stats import zipf as zipf_lib
-
-from .dataset_utils import CNT, PROP
-
-# treating inf values as NaN as well
-
-pd.set_option("use_inf_as_na", True)
-
-logs = logging.getLogger(__name__)
-logs.setLevel(logging.INFO)
-logs.propagate = False
-
-if not logs.handlers:
-
-    Path("./log_files").mkdir(exist_ok=True)
-
-    # Logging info to log file
-    file = logging.FileHandler("./log_files/zipf.log")
-    fileformat = logging.Formatter("%(asctime)s:%(message)s")
-    file.setLevel(logging.INFO)
-    file.setFormatter(fileformat)
-
-    # Logging debug messages to stream
-    stream = logging.StreamHandler()
-    streamformat = logging.Formatter("[data_measurements_tool] %(message)s")
-    stream.setLevel(logging.WARNING)
-    stream.setFormatter(streamformat)
-
-    logs.addHandler(file)
-    logs.addHandler(stream)
-
-
-class Zipf:
-    def __init__(self, vocab_counts_df=pd.DataFrame()):
-        self.vocab_counts_df = vocab_counts_df
-        self.alpha = None
-        self.xmin = None
-        self.xmax = None
-        self.fit = None
-        self.ranked_words = {}
-        self.uniq_counts = []
-        self.uniq_ranks = []
-        self.uniq_fit_counts = None
-        self.term_df = None
-        self.pvalue = None
-        self.ks_test = None
-        self.distance = None
-        self.fit = None
-        self.predicted_zipf_counts = None
-        if not self.vocab_counts_df.empty:
-            logs.info("Fitting based on input vocab counts.")
-            self.calc_fit(vocab_counts_df)
-            logs.info("Getting predicted counts.")
-            self.predicted_zipf_counts = self.calc_zipf_counts(vocab_counts_df)
-
-    def load(self, zipf_dict):
-        self.set_xmin(zipf_dict["xmin"])
-        self.set_xmax(zipf_dict["xmax"])
-        self.set_alpha(zipf_dict["alpha"])
-        self.set_ks_distance(zipf_dict["ks_distance"])
-        self.set_p(zipf_dict["p-value"])
-        self.set_unique_ranks(zipf_dict["uniq_ranks"])
-        self.set_unique_counts(zipf_dict["uniq_counts"])
-
-    def calc_fit(self, vocab_counts_df):
-        """
-        Uses the powerlaw package to fit the observed frequencies to a zipfian distribution.
-        We use the KS-distance to fit, as that seems more appropriate that MLE.
-        :param vocab_counts_df:
-        :return:
-        """
-        self.vocab_counts_df = vocab_counts_df
-        # TODO: These proportions may have already been calculated.
-        vocab_counts_df[PROP] = vocab_counts_df[CNT] / float(sum(vocab_counts_df[CNT]))
-        rank_column = vocab_counts_df[CNT].rank(
-            method="dense", numeric_only=True, ascending=False
-        )
-        vocab_counts_df["rank"] = rank_column.astype("int64")
-        observed_counts = vocab_counts_df[CNT].values
-        # Note another method for determining alpha might be defined by
-        # (Newman, 2005): alpha = 1 + n * sum(ln( xi / xmin )) ^ -1
-        self.fit = powerlaw.Fit(observed_counts, fit_method="KS", discrete=True)
-        # This should probably be a pmf (not pdf); using discrete=True above.
-        # original_data=False uses only the fitted data (within xmin and xmax).
-        # pdf_bin_edges: The portion of the data within the bin.
-        # observed_pdf: The probability density function (normalized histogram)
-        # of the data.
-        pdf_bin_edges, observed_pdf = self.fit.pdf(original_data=False)
-        # See the 'Distribution' class described here for info:
-        # https://pythonhosted.org/powerlaw/#powerlaw.Fit.pdf
-        theoretical_distro = self.fit.power_law
-        # The probability density function (normalized histogram) of the
-        # theoretical distribution.
-        predicted_pdf = theoretical_distro.pdf()
-        # !!!! CRITICAL VALUE FOR ZIPF !!!!
-        self.alpha = theoretical_distro.alpha
-        # Exclusive xmin: The optimal xmin *beyond which* the scaling regime of
-        # the power law fits best.
-        self.xmin = theoretical_distro.xmin
-        self.xmax = theoretical_distro.xmax
-        self.distance = theoretical_distro.KS()
-        self.ks_test = ks_2samp(observed_pdf, predicted_pdf)
-        self.pvalue = self.ks_test[1]
-        logs.info("KS test:")
-        logs.info(self.ks_test)
-
-    def set_xmax(self, xmax):
-        """
-        xmax is usually None, so we add some handling to set it as the
-        maximum rank in the dataset.
-        :param xmax:
-        :return:
-        """
-        if xmax:
-            self.xmax = int(xmax)
-        elif self.uniq_counts:
-            self.xmax = int(len(self.uniq_counts))
-        elif self.uniq_ranks:
-            self.xmax = int(len(self.uniq_ranks))
-
-    def get_xmax(self):
-        """
-        :return:
-        """
-        if not self.xmax:
-            self.set_xmax(self.xmax)
-        return self.xmax
-
-    def set_p(self, p):
-        self.p = int(p)
-
-    def get_p(self):
-        return int(self.p)
-
-    def set_xmin(self, xmin):
-        self.xmin = xmin
-
-    def get_xmin(self):
-        if self.xmin:
-            return int(self.xmin)
-        return self.xmin
-
-    def set_alpha(self, alpha):
-        self.alpha = float(alpha)
-
-    def get_alpha(self):
-        return float(self.alpha)
-
-    def set_ks_distance(self, distance):
-        self.distance = float(distance)
-
-    def get_ks_distance(self):
-        return self.distance
-
-    def calc_zipf_counts(self, vocab_counts_df):
-        """
-        The fit is based on an optimal xmin (minimum rank)
-        Let's use this to make count estimates for the zipf fit,
-        by multiplying the fitted pmf value by the sum of counts above xmin.
-        :return: array of count values following the fitted pmf.
-        """
-        # TODO: Limit from above xmin to below xmax, not just above xmin.
-        counts = vocab_counts_df[CNT]
-        self.uniq_counts = list(pd.unique(counts))
-        self.uniq_ranks = list(np.arange(1, len(self.uniq_counts) + 1))
-        logs.info(self.uniq_counts)
-        logs.info(self.xmin)
-        logs.info(self.xmax)
-        # Makes sure they are ints if not None
-        xmin = self.get_xmin()
-        xmax = self.get_xmax()
-        self.uniq_fit_counts = self.uniq_counts[xmin + 1 : xmax]
-        pmf_mass = float(sum(self.uniq_fit_counts))
-        zipf_counts = np.array(
-            [self.estimate_count(rank, pmf_mass) for rank in self.uniq_ranks]
-        )
-        return zipf_counts
-
-    def estimate_count(self, rank, pmf_mass):
-        return int(round(zipf_lib.pmf(rank, self.alpha) * pmf_mass))
-
-    def set_unique_ranks(self, ranks):
-        self.uniq_ranks = ranks
-
-    def get_unique_ranks(self):
-        return self.uniq_ranks
-
-    def get_unique_fit_counts(self):
-        return self.uniq_fit_counts
-
-    def set_unique_counts(self, counts):
-        self.uniq_counts = counts
-
-    def get_unique_counts(self):
-        return self.uniq_counts
-
-    def set_axes(self, unique_counts, unique_ranks):
-        self.uniq_counts = unique_counts
-        self.uniq_ranks = unique_ranks
-
-    # TODO: Incorporate this function (not currently using)
-    def fit_others(self, fit):
-        st.markdown(
-            "_Checking log likelihood ratio to see if the data is better explained by other well-behaved distributions..._"
-        )
-        # The first value returned from distribution_compare is the log likelihood ratio
-        better_distro = False
-        trunc = fit.distribution_compare("power_law", "truncated_power_law")
-        if trunc[0] < 0:
-            st.markdown("Seems a truncated power law is a better fit.")
-            better_distro = True
-
-        lognormal = fit.distribution_compare("power_law", "lognormal")
-        if lognormal[0] < 0:
-            st.markdown("Seems a lognormal distribution is a better fit.")
-            st.markdown("But don't panic -- that happens sometimes with language.")
-            better_distro = True
-
-        exponential = fit.distribution_compare("power_law", "exponential")
-        if exponential[0] < 0:
-            st.markdown("Seems an exponential distribution is a better fit. Panic.")
-            better_distro = True
-
-        if not better_distro:
-            st.markdown("\nSeems your data is best fit by a power law. Celebrate!!")
diff --git a/spaces/huggingface/datasets-tagging/tagging_app.py b/spaces/huggingface/datasets-tagging/tagging_app.py
deleted file mode 100644
index 780bdcf13bb461ffea9431ccdacb72e2c6cab19b..0000000000000000000000000000000000000000
--- a/spaces/huggingface/datasets-tagging/tagging_app.py
+++ /dev/null
@@ -1,416 +0,0 @@
-import json
-import logging
-from pathlib import Path
-from typing import Callable, Dict, List, Tuple
-
-import langcodes as lc
-import streamlit as st
-import yaml
-from datasets.utils.metadata import (
-    DatasetMetadata,
-    known_creators,
-    known_licenses,
-    known_multilingualities,
-    known_size_categories,
-    known_task_ids,
-)
-
-from apputils import new_state
-
-st.set_page_config(
-    page_title="HF Dataset Tagging App",
-    page_icon="https://huggingface.co/front/assets/huggingface_logo.svg",
-    layout="wide",
-    initial_sidebar_state="auto",
-)
-
-# XXX: restyling errors as streamlit does not respect whitespaces on `st.error` and doesn't scroll horizontally, which
-#   generally makes things easier when reading error reports
-st.markdown(
-    """
-<style>
-    div[role=alert] { overflow-x: scroll}
-    div.stAlert p { white-space: pre }
-</style>
-""",
-    unsafe_allow_html=True,
-)
-
-########################
-## Helper functions
-########################
-
-
-def load_ds_datas() -> Dict[str, Dict[str, Dict]]:
-    metada_exports = sorted(
-        [f for f in Path.cwd().iterdir() if f.name.startswith("metadata_")],
-        key=lambda f: f.lstat().st_mtime,
-        reverse=True,
-    )
-    if len(metada_exports) == 0:
-        raise ValueError("need to run ./build_metada_file.py at least once")
-    with metada_exports[0].open() as fi:
-        logging.info(f"loaded {metada_exports[0]}")
-        return json.load(fi)
-
-
-def split_known(vals: List[str], okset: List[str]) -> Tuple[List[str], List[str]]:
-    if vals is None:
-        return [], []
-    return [v for v in vals if v in okset], [v for v in vals if v not in okset]
-
-
-def multiselect(
-    w: st.delta_generator.DeltaGenerator,
-    title: str,
-    markdown: str,
-    values: List[str],
-    valid_set: List[str],
-    format_func: Callable = str,
-):
-    valid_values, invalid_values = split_known(values, valid_set)
-    w.markdown(f"#### {title}")
-    if len(invalid_values) > 0:
-        w.markdown("Found the following invalid values:")
-        w.error(invalid_values)
-    return w.multiselect(markdown, valid_set, default=valid_values, format_func=format_func, key=title)
-
-
-def validate_yaml(w: st.delta_generator.DeltaGenerator, yamlblock: str):
-    try:
-        DatasetMetadata.from_yaml_string(yamlblock)
-        if "pretty_name: " not in yamlblock or "pretty_name: ''" in yamlblock:
-            raise ValueError("Please specify a non-empty Dataset name.")
-        w.markdown("✅ This is a valid tagset! 🤗")
-    except Exception as e:
-        w.markdown("❌ This is an invalid tagset, here are the errors in it:")
-        w.error(e)
-
-
-def map_num_examples_to_size_category(n: int) -> str:
-    if n < 0:
-        size_cat = "unknown"
-    elif n < 1000:
-        size_cat = "n<1K"
-    elif n < 10000:
-        size_cat = "1K<n<10K"
-    elif n < 100000:
-        size_cat = "10K<n<100K"
-    elif n < 1000000:
-        size_cat = "100K<n<1M"
-    elif n < 10000000:
-        size_cat = "1M<n<10M"
-    elif n < 100000000:
-        size_cat = "10M<n<100M"
-    elif n < 1000000000:
-        size_cat = "100M<n<1B"
-    elif n < 10000000000:
-        size_cat = "1B<n<10B"
-    elif n < 100000000000:
-        size_cat = "10B<n<100B"
-    elif n < 1000000000000:
-        size_cat = "100B<n<1T"
-    else:
-        size_cat = "n>1T"
-    return size_cat
-
-
-def is_state_empty(state: Dict[str, List]) -> bool:
-    return sum(len(v) if v is not None else 0 for v in state.values()) == 0
-
-
-state = new_state()
-datasets_md = load_ds_datas()
-dataset_ids = list(datasets_md.keys())
-dataset_id_to_metadata = {name: mds["metadata"] for name, mds in datasets_md.items()}
-dataset_id_to_infos = {name: mds["infos"] for name, mds in datasets_md.items()}
-
-
-########################
-## Dataset selection
-########################
-
-
-st.sidebar.markdown(
-    """
-# HuggingFace Dataset Tagger
-
-This app aims to make it easier to add structured tags to the datasets present in the library.
-
-"""
-)
-
-
-queryparams = st.experimental_get_query_params()
-preload = queryparams.get("preload_dataset", list())
-preloaded_id = None
-initial_state = None
-initial_infos, initial_info_cfg = None, None
-dataset_selector_index = 0
-
-if len(preload) == 1 and preload[0] in dataset_ids:
-    preloaded_id, *_ = preload
-    initial_state = dataset_id_to_metadata.get(preloaded_id)
-    initial_infos = dataset_id_to_infos.get(preloaded_id)
-    initial_info_cfg = next(iter(initial_infos)) if initial_infos is not None else None  # pick first available config
-    state = initial_state or new_state()
-    dataset_selector_index = dataset_ids.index(preloaded_id)
-
-preloaded_id = st.sidebar.selectbox(
-    label="Choose dataset to load tag set from", options=dataset_ids, index=dataset_selector_index
-)
-
-leftbtn, rightbtn = st.sidebar.columns(2)
-if leftbtn.button("pre-load"):
-    initial_state = dataset_id_to_metadata[preloaded_id]
-    initial_infos = dataset_id_to_infos[preloaded_id]
-    initial_info_cfg = next(iter(initial_infos))  # pick first available config
-    state = initial_state or new_state()
-    st.experimental_set_query_params(preload_dataset=preloaded_id)
-if not is_state_empty(state):
-    if rightbtn.button("reset"):
-        state = new_state()
-        initial_state = None
-        preloaded_id = None
-        initial_infos = None
-        st.experimental_set_query_params()
-
-if preloaded_id is not None and initial_state is not None:
-    st.sidebar.markdown(
-        f"""
----
-The current base tagset is [`{preloaded_id}`](https://huggingface.co/datasets/{preloaded_id})
-"""
-    )
-    validate_yaml(st.sidebar, yaml.dump(initial_state))
-    st.sidebar.markdown(
-        f"""
-Here is the matching yaml block:
-
-```yaml
-{yaml.dump(initial_state)}
-```
-"""
-    )
-
-
-leftcol, _, rightcol = st.columns([12, 1, 12])
-
-#
-# DATASET NAME
-#
-leftcol.markdown("### Dataset name")
-state["pretty_name"] = leftcol.text_area(
-    "Pick a nice descriptive name for the dataset",
-)
-
-
-
-#
-# TASKS
-#
-leftcol.markdown("### Supported tasks")
-state["task_categories"] = multiselect(
-    leftcol,
-    "Task category",
-    "What categories of task does the dataset support?",
-    values=state["task_categories"],
-    valid_set=sorted(list(known_task_ids.keys())),
-)
-task_specifics = []
-for task_category in state["task_categories"]:
-    specs = multiselect(
-        leftcol,
-        f"Specific _{task_category}_ tasks",
-        f"What specific tasks does the dataset support?",
-        values=[ts for ts in (state["task_ids"] or []) if ts in known_task_ids[task_category].get("subtasks", [])],
-        valid_set=known_task_ids[task_category].get("subtasks", []),
-    )
-    if "other" in specs:
-        other_task = leftcol.text_input(
-            "You selected 'other' task. Please enter a short hyphen-separated description for the task:",
-            value="my-task-description",
-        )
-        leftcol.write(f"Registering {task_category}-other-{other_task} task")
-        specs[specs.index("other")] = f"{task_category}-other-{other_task}"
-    task_specifics += specs
-state["task_ids"] = task_specifics
-
-
-#
-# LANGUAGES
-#
-leftcol.markdown("### Languages")
-state["multilinguality"] = multiselect(
-    leftcol,
-    "Monolingual?",
-    "Does the dataset contain more than one language?",
-    values=state["multilinguality"],
-    valid_set=list(known_multilingualities.keys()),
-    format_func=lambda m: f"{m} : {known_multilingualities[m]}",
-)
-
-if "other" in state["multilinguality"]:
-    other_multilinguality = leftcol.text_input(
-        "You selected 'other' type of multilinguality. Please enter a short hyphen-separated description:",
-        value="my-multilinguality",
-    )
-    leftcol.write(f"Registering other-{other_multilinguality} multilinguality")
-    state["multilinguality"][state["multilinguality"].index("other")] = f"other-{other_multilinguality}"
-
-valid_values, invalid_values = list(), list()
-for langtag in state["language"]:
-    try:
-        lc.get(langtag)
-        valid_values.append(langtag)
-    except:
-        invalid_values.append(langtag)
-leftcol.markdown("#### Languages")
-if len(invalid_values) > 0:
-    leftcol.markdown("Found the following invalid values:")
-    leftcol.error(invalid_values)
-
-langtags = leftcol.text_area(
-    "What languages are represented in the dataset? expected format is BCP47 tags separated for ';' e.g. 'en;fr'",
-    value=";".join(valid_values),
-)
-state["language"] = langtags.strip().split(";") if langtags.strip() != "" else []
-
-
-#
-# DATASET CREATORS & ORIGINS
-#
-leftcol.markdown("### Dataset creators")
-state["language_creators"] = multiselect(
-    leftcol,
-    "Data origin",
-    "Where does the text in the dataset come from?",
-    values=state["language_creators"],
-    valid_set=known_creators["language"],
-)
-state["annotations_creators"] = multiselect(
-    leftcol,
-    "Annotations origin",
-    "Where do the annotations in the dataset come from?",
-    values=state["annotations_creators"],
-    valid_set=known_creators["annotations"],
-)
-
-
-#
-# LICENSE
-#
-state["license"] = multiselect(
-    leftcol,
-    "License",
-    "What license(s) is the dataset under?",
-    valid_set=list(known_licenses.keys()),
-    values=state["license"],
-    format_func=lambda l: f"{l} : {known_licenses[l]}",
-)
-
-
-#
-# LINK TO SUPPORTED DATASETS
-#
-pre_select_ext_a = []
-if "original" in state["source_datasets"]:
-    pre_select_ext_a += ["original"]
-if any([p.startswith("extended") for p in state["source_datasets"]]):
-    pre_select_ext_a += ["extended"]
-state["source_datasets"] = multiselect(
-    leftcol,
-    "Relations to existing work",
-    "Does the dataset contain original data and/or was it extended from other datasets?",
-    values=pre_select_ext_a,
-    valid_set=["original", "extended"],
-)
-
-if "extended" in state["source_datasets"]:
-    pre_select_ext_b = [p.split("|")[1] for p in state["source_datasets"] if p.startswith("extended|")]
-    extended_sources = multiselect(
-        leftcol,
-        "Linked datasets",
-        "Which other datasets does this one use data from?",
-        values=pre_select_ext_b,
-        valid_set=dataset_ids + ["other"],
-    )
-    # flush placeholder
-    state["source_datasets"].remove("extended")
-    state["source_datasets"] += [f"extended|{src}" for src in extended_sources]
-
-
-#
-# SIZE CATEGORY
-#
-leftcol.markdown("### Size category")
-logging.info(initial_infos[initial_info_cfg]["splits"] if initial_infos is not None else 0)
-initial_num_examples = (
-    sum([dct.get("num_examples", 0) for _split, dct in initial_infos[initial_info_cfg].get("splits", dict()).items()])
-    if initial_infos is not None
-    else -1
-)
-if initial_num_examples >= 0:
-    initial_size_categories = [map_num_examples_to_size_category(initial_num_examples)]
-else:
-    initial_size_categories = []
-current_size_cats = multiselect(
-    leftcol,
-    f"Size category",
-    f"How many samples are there in the dataset?",
-    values=initial_size_categories,
-    valid_set=known_size_categories,
-)
-if initial_size_categories:
-    leftcol.markdown(f"Computed size category from automatically generated dataset info to: `{initial_size_categories}`")
-prev_size_cats = state.get("size_categories") or []
-ok, nonok = split_known(prev_size_cats, known_size_categories)
-if len(nonok) > 0:
-    leftcol.markdown(f"**Found bad codes in existing tagset**:\n{nonok}")
-state["size_categories"] = current_size_cats
-
-
-#
-# ADDITIONAL TAGS
-#
-leftcol.markdown("### Tags")
-tags_text_area = leftcol.text_area(
-    "What are the additional keywords one can use to find this dataset ? "
-    "expected format is a list of keywords separated by ';' "
-    "e.g. 'bio;research papers' or 'newspapers;1800-1900'"
-)
-state["tags"] = [tag.strip() for tag in tags_text_area.strip(";").split(";")] if tags_text_area.strip(" ;") else []
-
-
-########################
-## Show results
-########################
-
-rightcol.markdown(
-    f"""
-### Finalized tag set
-
-"""
-)
-if is_state_empty(state):
-    rightcol.markdown("❌ This is an invalid tagset: it's empty!")
-else:
-    validate_yaml(rightcol, yaml.dump(state))
-
-
-rightcol.markdown(
-    f"""
-
-```yaml
-{yaml.dump(state)}
-```
----
-#### Arbitrary yaml validator
-
-This is a standalone tool, it is useful to check for errors on an existing tagset or modifying directly the text rather than the UI on the left.
-""",
-)
-
-yamlblock = rightcol.text_area("Input your yaml here")
-if yamlblock.strip() != "":
-    validate_yaml(rightcol, yamlblock)
diff --git a/spaces/huggingface/transformers-stats/app.py b/spaces/huggingface/transformers-stats/app.py
deleted file mode 100644
index 3e14e91c528316e6bababebdc00f4020b02f52d1..0000000000000000000000000000000000000000
--- a/spaces/huggingface/transformers-stats/app.py
+++ /dev/null
@@ -1,221 +0,0 @@
-from huggingface_hub import HfApi
-import pandas as pd
-import os
-import streamlit as st
-import altair as alt
-import numpy as np
-import datetime
-from huggingface_hub import Repository
-
-from transformers.models.auto.configuration_auto import CONFIG_MAPPING_NAMES
-from transformers.models.auto.modeling_auto import (
-    MODEL_FOR_CTC_MAPPING_NAMES,
-    MODEL_FOR_AUDIO_CLASSIFICATION_MAPPING_NAMES,
-    MODEL_FOR_AUDIO_FRAME_CLASSIFICATION_MAPPING_NAMES,
-    MODEL_FOR_AUDIO_XVECTOR_MAPPING_NAMES,
-    MODEL_FOR_SPEECH_SEQ_2_SEQ_MAPPING_NAMES,
-    MODEL_FOR_VISION_2_SEQ_MAPPING_NAMES,
-    MODEL_FOR_INSTANCE_SEGMENTATION_MAPPING_NAMES,
-    MODEL_FOR_SEMANTIC_SEGMENTATION_MAPPING_NAMES,
-    MODEL_FOR_IMAGE_CLASSIFICATION_MAPPING_NAMES,
-    MODEL_FOR_CAUSAL_IMAGE_MODELING_MAPPING_NAMES,
-    MODEL_FOR_MASKED_IMAGE_MODELING_MAPPING_NAMES,
-    MODEL_FOR_TABLE_QUESTION_ANSWERING_MAPPING_NAMES,
-    MODEL_FOR_VISUAL_QUESTION_ANSWERING_MAPPING_NAMES,
-    MODEL_FOR_DOCUMENT_QUESTION_ANSWERING_MAPPING_NAMES,
-    MODEL_FOR_BACKBONE_MAPPING_NAMES,
-    MODEL_FOR_ZERO_SHOT_IMAGE_CLASSIFICATION_MAPPING_NAMES,
-)
-
-audio_models = list(MODEL_FOR_CTC_MAPPING_NAMES.keys()) + list(MODEL_FOR_AUDIO_CLASSIFICATION_MAPPING_NAMES.keys()) + \
-               list(MODEL_FOR_SPEECH_SEQ_2_SEQ_MAPPING_NAMES.keys()) + list(MODEL_FOR_AUDIO_FRAME_CLASSIFICATION_MAPPING_NAMES.keys()) + \
-               list(MODEL_FOR_AUDIO_XVECTOR_MAPPING_NAMES.keys())
-
-vision_models = list(MODEL_FOR_VISION_2_SEQ_MAPPING_NAMES.keys()) + list(MODEL_FOR_INSTANCE_SEGMENTATION_MAPPING_NAMES.keys()) + \
-                list(MODEL_FOR_SEMANTIC_SEGMENTATION_MAPPING_NAMES.keys()) + list(MODEL_FOR_IMAGE_CLASSIFICATION_MAPPING_NAMES.keys()) + \
-                list(MODEL_FOR_CAUSAL_IMAGE_MODELING_MAPPING_NAMES.keys()) + list(MODEL_FOR_MASKED_IMAGE_MODELING_MAPPING_NAMES.keys()) + \
-                list(MODEL_FOR_TABLE_QUESTION_ANSWERING_MAPPING_NAMES.keys()) + list(MODEL_FOR_VISUAL_QUESTION_ANSWERING_MAPPING_NAMES.keys()) + \
-                list(MODEL_FOR_DOCUMENT_QUESTION_ANSWERING_MAPPING_NAMES.keys()) + list(MODEL_FOR_BACKBONE_MAPPING_NAMES.keys()) + \
-                list(MODEL_FOR_ZERO_SHOT_IMAGE_CLASSIFICATION_MAPPING_NAMES.keys())
-
-today = datetime.date.today()
-year, week, _ = today.isocalendar()
-
-DATASET_REPO_URL = (
-    "https://huggingface.co/datasets/huggingface/transformers-stats-space-data"
-)
-
-DATA_FILENAME = f"data_{week}_{year}.csv"
-DATA_FILE = os.path.join("data", DATA_FILENAME)
-
-HF_TOKEN = os.environ.get("HF_TOKEN")
-
-print("is none?", HF_TOKEN is None)
-
-
-def retrieve_model_stats():
-    hf_api = HfApi()
-    all_stats = {}
-    total_downloads = 0
-
-    for model_name in list(CONFIG_MAPPING_NAMES.keys()):
-        if model_name in audio_models:
-            modality = "audio"
-        elif model_name in vision_models:
-            modality = "vision"
-        else:
-            modality = "text"
-
-        model_stats = {
-            "num_downloads": 0,
-            "%_of_all_downloads": 0,
-            "num_models": 0,
-            "download_per_model": 0,
-            "modality": modality,
-        }
-        models = list(hf_api.list_models(filter=model_name))
-
-        model_stats["num_models"] = len(models)
-        model_stats["num_downloads"] = sum(
-            [m.downloads for m in models if hasattr(m, "downloads")]
-        )
-        if len(models) > 0:
-            model_stats["download_per_model"] = int(
-                model_stats["num_downloads"] / len(models)
-            )
-        else:
-            model_stats["download_per_model"] = model_stats["num_downloads"]
-
-        total_downloads += model_stats["num_downloads"]
-
-        # save in overall dict
-        all_stats[model_name] = model_stats
-
-    for model_name in list(CONFIG_MAPPING_NAMES.keys()):
-        all_stats[model_name]["%_of_all_downloads"] = (
-            round(all_stats[model_name]["num_downloads"] / total_downloads, 5) * 100
-        )  # noqa: E501
-        downloads = all_stats[model_name]["num_downloads"]
-        all_stats[model_name]["num_downloads"] = f"{downloads:,}"
-
-    sorted_results = dict(
-        reversed(sorted(all_stats.items(), key=lambda d: d[1]["%_of_all_downloads"]))
-    )
-    dataframe = pd.DataFrame.from_dict(sorted_results, orient="index")
-
-    # give header to model names
-    result = "model_names" + dataframe.to_csv()
-    return result
-
-
-repo = Repository(local_dir="data", clone_from=DATASET_REPO_URL, use_auth_token=HF_TOKEN)
-
-if not os.path.isfile(DATA_FILE):
-    st.title("You are the first this week!!! Please wait until the new data is generated and written")
-    result = retrieve_model_stats()
-
-    if not os.path.isfile(DATA_FILE):
-        with open(DATA_FILE, "w") as f:
-            f.write(result)
-
-        commit_url = repo.push_to_hub()
-        print(commit_url)
-
-with open(DATA_FILE, "r") as f:
-    dataframe = pd.read_csv(DATA_FILE)
-
-int_downloads = np.array(
-    [int(x.replace(",", "")) for x in dataframe["num_downloads"].values]
-)
-
-st.title(f"Stats for year {year} and week {week}")
-
-# print top 20 downloads
-source = pd.DataFrame(
-    {
-        "Number of total downloads": int_downloads[:20],
-        "Model architecture name": dataframe["model_names"].values[:20],
-    }
-)
-bar_chart = (
-    alt.Chart(source)
-    .mark_bar()
-    .encode(
-        y="Number of total downloads",
-        x=alt.X("Model architecture name", sort=None),
-    )
-)
-st.title("Top 20 downloads last 30 days")
-st.altair_chart(bar_chart, use_container_width=True)
-
-# print bottom 20 downloads
-source = pd.DataFrame(
-    {
-        "Number of total downloads": int_downloads[-20:],
-        "Model architecture name": dataframe["model_names"].values[-20:],
-    }
-)
-bar_chart = (
-    alt.Chart(source)
-    .mark_bar()
-    .encode(
-        y="Number of total downloads",
-        x=alt.X("Model architecture name", sort=None),
-    )
-)
-st.title("Bottom 20 downloads last 30 days")
-st.altair_chart(bar_chart, use_container_width=True)
-
-# print vision
-df_vision = dataframe[dataframe["modality"] == "vision"]
-vision_int_downloads = np.array(
-    [int(x.replace(",", "")) for x in df_vision["num_downloads"].values]
-)
-source = pd.DataFrame(
-    {
-        "Number of total downloads": vision_int_downloads,
-        "Model architecture name": df_vision["model_names"].values,
-    }
-)
-bar_chart = (
-    alt.Chart(source)
-    .mark_bar()
-    .encode(
-        y="Number of total downloads",
-        x=alt.X("Model architecture name", sort=None),
-    )
-)
-st.title("Vision downloads last 30 days")
-st.altair_chart(bar_chart, use_container_width=True)
-
-# print audio
-df_audio = dataframe[dataframe["modality"] == "audio"]
-audio_int_downloads = np.array(
-    [int(x.replace(",", "")) for x in df_audio["num_downloads"].values]
-)
-source = pd.DataFrame(
-    {
-        "Number of total downloads": audio_int_downloads,
-        "Model architecture name": df_audio["model_names"].values,
-    }
-)
-bar_chart = (
-    alt.Chart(source)
-    .mark_bar()
-    .encode(
-        y="Number of total downloads",
-        x=alt.X("Model architecture name", sort=None),
-    )
-)
-st.title("Audio downloads last 30 days")
-st.altair_chart(bar_chart, use_container_width=True)
-
-# print all stats
-st.title("All stats last 30 days")
-st.table(dataframe)
-
-st.title("Vision stats last 30 days")
-st.table(dataframe[dataframe["modality"] == "vision"].drop("modality", axis=1))
-
-st.title("Audio stats last 30 days")
-st.table(dataframe[dataframe["modality"] == "audio"].drop("modality", axis=1))
diff --git a/spaces/iamironman4279/SadTalker/src/face3d/models/arcface_torch/configs/ms1mv3_r50.py b/spaces/iamironman4279/SadTalker/src/face3d/models/arcface_torch/configs/ms1mv3_r50.py
deleted file mode 100644
index 08ba55dbbea6df0afffddbb3d1ed173efad99604..0000000000000000000000000000000000000000
--- a/spaces/iamironman4279/SadTalker/src/face3d/models/arcface_torch/configs/ms1mv3_r50.py
+++ /dev/null
@@ -1,26 +0,0 @@
-from easydict import EasyDict as edict
-
-# make training faster
-# our RAM is 256G
-# mount -t tmpfs -o size=140G  tmpfs /train_tmp
-
-config = edict()
-config.loss = "arcface"
-config.network = "r50"
-config.resume = False
-config.output = None
-config.embedding_size = 512
-config.sample_rate = 1.0
-config.fp16 = True
-config.momentum = 0.9
-config.weight_decay = 5e-4
-config.batch_size = 128
-config.lr = 0.1  # batch size is 512
-
-config.rec = "/train_tmp/ms1m-retinaface-t1"
-config.num_classes = 93431
-config.num_image = 5179510
-config.num_epoch = 25
-config.warmup_epoch = -1
-config.decay_epoch = [10, 16, 22]
-config.val_targets = ["lfw", "cfp_fp", "agedb_30"]
diff --git a/spaces/iccv23-diffusers-demo/stable-diffusion-image-variations/app.py b/spaces/iccv23-diffusers-demo/stable-diffusion-image-variations/app.py
deleted file mode 100644
index f352741bc458ee5b7523c10687c2e670429e1dc9..0000000000000000000000000000000000000000
--- a/spaces/iccv23-diffusers-demo/stable-diffusion-image-variations/app.py
+++ /dev/null
@@ -1,105 +0,0 @@
-import gradio as gr
-import torch
-from PIL import Image
-from torchvision import transforms
-
-from diffusers import StableDiffusionImageVariationPipeline
-
-def main(
-    input_im,
-    scale=3.0,
-    n_samples=4,
-    steps=25,
-    seed=0,
-    ):
-    generator = torch.Generator(device=device).manual_seed(int(seed))
-
-    tform = transforms.Compose([
-    transforms.ToTensor(),
-    transforms.Resize(
-        (224, 224),
-        interpolation=transforms.InterpolationMode.BICUBIC,
-        antialias=False,
-        ),
-        transforms.Normalize(
-          [0.48145466, 0.4578275, 0.40821073],
-          [0.26862954, 0.26130258, 0.27577711]),
-    ])
-    inp = tform(input_im).to(device)
-        
-    images_list = pipe(
-        inp.tile(n_samples, 1, 1, 1),
-        guidance_scale=scale,
-        num_inference_steps=steps,
-        generator=generator,
-        )
-
-    images = []
-    for i, image in enumerate(images_list["images"]):
-        if(images_list["nsfw_content_detected"][i]):
-            safe_image = Image.open(r"unsafe.png")
-            images.append(safe_image)
-        else:
-            images.append(image)
-    return images
-
-
-description = \
-"""
-__Now using Image Variations v2!__
-
-Generate variations on an input image using a fine-tuned version of Stable Diffision.
-Trained by [Justin Pinkney](https://www.justinpinkney.com) ([@Buntworthy](https://twitter.com/Buntworthy)) at [Lambda](https://lambdalabs.com/)
-
-This version has been ported to 🤗 Diffusers library, see more details on how to use this version in the [Lambda Diffusers repo](https://github.com/LambdaLabsML/lambda-diffusers).
-For the original training code see [this repo](https://github.com/justinpinkney/stable-diffusion).
-
-![](https://raw.githubusercontent.com/justinpinkney/stable-diffusion/main/assets/im-vars-thin.jpg)
-
-"""
-
-article = \
-"""
-## How does this work?
-
-The normal Stable Diffusion model is trained to be conditioned on text input. This version has had the original text encoder (from CLIP) removed, and replaced with
-the CLIP _image_ encoder instead. So instead of generating images based a text input, images are generated to match CLIP's embedding of the image.
-This creates images which have the same rough style and content, but different details, in particular the composition is generally quite different.
-This is a totally different approach to the img2img script of the original Stable Diffusion and gives very different results.
-
-The model was fine tuned on the [LAION aethetics v2 6+ dataset](https://laion.ai/blog/laion-aesthetics/) to accept the new conditioning.
-Training was done on 8xA100 GPUs on [Lambda GPU Cloud](https://lambdalabs.com/service/gpu-cloud).
-More details are on the [model card](https://huggingface.co/lambdalabs/sd-image-variations-diffusers).
-"""
-
-device = "cuda" if torch.cuda.is_available() else "cpu"
-pipe = StableDiffusionImageVariationPipeline.from_pretrained(
-    "lambdalabs/sd-image-variations-diffusers",
-    )
-pipe = pipe.to(device)
-
-inputs = [
-    gr.Image(),
-    gr.Slider(0, 25, value=3, step=1, label="Guidance scale"),
-    gr.Slider(1, 4, value=1, step=1, label="Number images"),
-    gr.Slider(5, 50, value=25, step=5, label="Steps"),
-    gr.Number(0, label="Seed", precision=0)
-]
-output = gr.Gallery(label="Generated variations")
-output.style(grid=2)
-
-examples = [
-    ["examples/vermeer.jpg", 3, 1, 25, 0],
-    ["examples/matisse.jpg", 3, 1, 25, 0],
-]
-
-demo = gr.Interface(
-    fn=main,
-    title="Stable Diffusion Image Variations",
-    description=description,
-    article=article,
-    inputs=inputs,
-    outputs=output,
-    examples=examples,
-    )
-demo.launch()
diff --git a/spaces/innat/Google-MediaPipe/facemesh.py b/spaces/innat/Google-MediaPipe/facemesh.py
deleted file mode 100644
index 6de3fbe048ac66ffa26fff631e3c15d18a9a0cfa..0000000000000000000000000000000000000000
--- a/spaces/innat/Google-MediaPipe/facemesh.py
+++ /dev/null
@@ -1,46 +0,0 @@
-
-import mediapipe as mp
-from utils import read_n_resize
-
-def mp_face_mesh_fn(image, min_detect_conf=0.5):
-    mp_drawing = mp.solutions.drawing_utils
-    mp_drawing_styles = mp.solutions.drawing_styles
-    mp_face_mesh = mp.solutions.face_mesh
-
-    with mp_face_mesh.FaceMesh(
-        static_image_mode=True,
-        max_num_faces=1,
-        refine_landmarks=True,
-        min_detection_confidence=min_detect_conf
-    ) as face_mesh:
-        resized_image = read_n_resize(image, read=False)
-        results = face_mesh.process(resized_image)
-
-        annotated_image = resized_image.copy()
-        for face_landmarks in results.multi_face_landmarks:
-            mp_drawing.draw_landmarks(
-                image=annotated_image,
-                landmark_list=face_landmarks,
-                connections=mp_face_mesh.FACEMESH_TESSELATION,
-                landmark_drawing_spec=None,
-                connection_drawing_spec=mp_drawing_styles
-                .get_default_face_mesh_tesselation_style()
-            )
-            mp_drawing.draw_landmarks(
-                image=annotated_image,
-                landmark_list=face_landmarks,
-                connections=mp_face_mesh.FACEMESH_CONTOURS,
-                landmark_drawing_spec=None,
-                connection_drawing_spec=mp_drawing_styles
-                .get_default_face_mesh_contours_style()
-            )
-            mp_drawing.draw_landmarks(
-                image=annotated_image,
-                landmark_list=face_landmarks,
-                connections=mp_face_mesh.FACEMESH_IRISES,
-                landmark_drawing_spec=None,
-                connection_drawing_spec=mp_drawing_styles
-                .get_default_face_mesh_iris_connections_style()
-            )
-        return annotated_image
-
diff --git a/spaces/inplisQlawa/anything-midjourney-v4-1/A73 Piano Station Full Version Free LINK Download.md b/spaces/inplisQlawa/anything-midjourney-v4-1/A73 Piano Station Full Version Free LINK Download.md
deleted file mode 100644
index c767f0ba12ae9c1f0e3fb4585cee7220357e34ef..0000000000000000000000000000000000000000
--- a/spaces/inplisQlawa/anything-midjourney-v4-1/A73 Piano Station Full Version Free LINK Download.md	
+++ /dev/null
@@ -1,6 +0,0 @@
-<h2>a73 piano station full version free download</h2><br /><p><b><b>Download File</b> &#9913; <a href="https://urlin.us/2uExLx">https://urlin.us/2uExLx</a></b></p><br /><br />
-
-October 25, 2021 - Download A73 Piano Station 1.4 from our website for free. The most popular versions among software users are 1.4, 1.2 and 1.1. Download the A73 Piano Station 1.4 Beta software from our website. The most popular versions among users are 1.4, 1.2 and 1.1. A73 Piano Station is software. Download the software only on a computer used for the purposes for which it was released. The software belongs to the Games category. The file size of the software package is 14.7 MB. It was designed for Windows/Mac. 8a78ff9644<br />
-<br />
-<br />
-<p></p>
diff --git a/spaces/inplisQlawa/anything-midjourney-v4-1/Funbag Fantasy 2 Free Download PC Game.md b/spaces/inplisQlawa/anything-midjourney-v4-1/Funbag Fantasy 2 Free Download PC Game.md
deleted file mode 100644
index 3e83adec38a1d86027b2576aebc17673d103df9a..0000000000000000000000000000000000000000
--- a/spaces/inplisQlawa/anything-midjourney-v4-1/Funbag Fantasy 2 Free Download PC Game.md	
+++ /dev/null
@@ -1,7 +0,0 @@
-
-<p>the game takes place on a world called “funbag”, where girls are more free and open-minded than boys. their quests are to fulfil a wish in order to make their life better. the game is set in a fantasy world where girls rule over boys. the game is a satire of the classic rpg and it draws inspiration from such game series as world of warcraft, monster hunter, and the legend of zelda.</p>
-<p>this game requires one or more of the following to play:</p>
-<h2>Funbag Fantasy 2 Free Download PC Game</h2><br /><p><b><b>DOWNLOAD</b> &gt;&gt;&gt;&gt;&gt; <a href="https://urlin.us/2uEyyt">https://urlin.us/2uEyyt</a></b></p><br /><br /> <ul> <li>operating system, which is windows xp, vista, 7, 8, 8.1 or 10</li> <li>processor, which is 1 ghz or faster</li> <li>ram, which is 2 gb or more</li> <li>sd card, which is 2 gb or more</li> <li>stick or controller</li> </ul>
-<p>funbag fantasy 2 free download pc game full version for windows. <br /><br />release date: jul 9, 2017<br />genre: fantasy<br />developer: telltale games<br />players: 1<br /><br />download funbag fantasy 2 for pc laptop in bluestacks, for android mobiles in bluestacks, for windows laptop in bluestacks, for mac laptop in bluestacks, for linux laptop in bluestacks, for ios mobiles in codes, for iphone in iubstacks, for ipad in iubstacks, for android tablets in iubstacks, for windows tablet in iubstacks, for mac book in iubstacks, for linux desktop in iubstacks, for routers & set-top-boxes in iubstacks, for amazon fire tv sticks in iubstacks, for amazon fire tv in iubstacks, for google chromecast in iubstacks, for web browser in iubstacks, for bluestacks in iubstacks, for windows in iubstacks, for mac in iubstacks, for linux in iubstacks, for xbox one in iubstacks, for playstation 4 in iubstacks, for ios in iubstacks, for android in iubstacks, for routers & set-top-boxes in iubstacks, for amazon fire tv sticks in iubstacks, for amazon fire tv in iubstacks, for google chromecast in iubstacks, for web browser in iubstacks, for bluestacks in iubstacks.</p> 899543212b<br />
-<br />
-<br />
\ No newline at end of file
diff --git a/spaces/inreVtussa/clothingai/Examples/Bonecraft Save Game 100 Complete Hit FREE.md b/spaces/inreVtussa/clothingai/Examples/Bonecraft Save Game 100 Complete Hit FREE.md
deleted file mode 100644
index f5105ae11f54335c009621374ad879c6672762e2..0000000000000000000000000000000000000000
--- a/spaces/inreVtussa/clothingai/Examples/Bonecraft Save Game 100 Complete Hit FREE.md	
+++ /dev/null
@@ -1,6 +0,0 @@
-<h2>bonecraft save game 100 complete hit</h2><br /><p><b><b>Download File</b> &middot;&middot;&middot;&middot;&middot; <a href="https://tiurll.com/2uCmjt">https://tiurll.com/2uCmjt</a></b></p><br /><br />
-<br />
- 3cee63e6c2<br />
-<br />
-<br />
-<p></p>
diff --git a/spaces/jackli888/stable-diffusion-webui/modules/textual_inversion/dataset.py b/spaces/jackli888/stable-diffusion-webui/modules/textual_inversion/dataset.py
deleted file mode 100644
index 093efcd4fc70602a802a82bc50457d0a5d08b5e2..0000000000000000000000000000000000000000
--- a/spaces/jackli888/stable-diffusion-webui/modules/textual_inversion/dataset.py
+++ /dev/null
@@ -1,246 +0,0 @@
-import os
-import numpy as np
-import PIL
-import torch
-from PIL import Image
-from torch.utils.data import Dataset, DataLoader, Sampler
-from torchvision import transforms
-from collections import defaultdict
-from random import shuffle, choices
-
-import random
-import tqdm
-from modules import devices, shared
-import re
-
-from ldm.modules.distributions.distributions import DiagonalGaussianDistribution
-
-re_numbers_at_start = re.compile(r"^[-\d]+\s*")
-
-
-class DatasetEntry:
-    def __init__(self, filename=None, filename_text=None, latent_dist=None, latent_sample=None, cond=None, cond_text=None, pixel_values=None, weight=None):
-        self.filename = filename
-        self.filename_text = filename_text
-        self.weight = weight
-        self.latent_dist = latent_dist
-        self.latent_sample = latent_sample
-        self.cond = cond
-        self.cond_text = cond_text
-        self.pixel_values = pixel_values
-
-
-class PersonalizedBase(Dataset):
-    def __init__(self, data_root, width, height, repeats, flip_p=0.5, placeholder_token="*", model=None, cond_model=None, device=None, template_file=None, include_cond=False, batch_size=1, gradient_step=1, shuffle_tags=False, tag_drop_out=0, latent_sampling_method='once', varsize=False, use_weight=False):
-        re_word = re.compile(shared.opts.dataset_filename_word_regex) if len(shared.opts.dataset_filename_word_regex) > 0 else None
-
-        self.placeholder_token = placeholder_token
-
-        self.flip = transforms.RandomHorizontalFlip(p=flip_p)
-
-        self.dataset = []
-
-        with open(template_file, "r") as file:
-            lines = [x.strip() for x in file.readlines()]
-
-        self.lines = lines
-
-        assert data_root, 'dataset directory not specified'
-        assert os.path.isdir(data_root), "Dataset directory doesn't exist"
-        assert os.listdir(data_root), "Dataset directory is empty"
-
-        self.image_paths = [os.path.join(data_root, file_path) for file_path in os.listdir(data_root)]
-
-        self.shuffle_tags = shuffle_tags
-        self.tag_drop_out = tag_drop_out
-        groups = defaultdict(list)
-
-        print("Preparing dataset...")
-        for path in tqdm.tqdm(self.image_paths):
-            alpha_channel = None
-            if shared.state.interrupted:
-                raise Exception("interrupted")
-            try:
-                image = Image.open(path)
-                #Currently does not work for single color transparency
-                #We would need to read image.info['transparency'] for that
-                if use_weight and 'A' in image.getbands():
-                    alpha_channel = image.getchannel('A')
-                image = image.convert('RGB')
-                if not varsize:
-                    image = image.resize((width, height), PIL.Image.BICUBIC)
-            except Exception:
-                continue
-
-            text_filename = os.path.splitext(path)[0] + ".txt"
-            filename = os.path.basename(path)
-
-            if os.path.exists(text_filename):
-                with open(text_filename, "r", encoding="utf8") as file:
-                    filename_text = file.read()
-            else:
-                filename_text = os.path.splitext(filename)[0]
-                filename_text = re.sub(re_numbers_at_start, '', filename_text)
-                if re_word:
-                    tokens = re_word.findall(filename_text)
-                    filename_text = (shared.opts.dataset_filename_join_string or "").join(tokens)
-
-            npimage = np.array(image).astype(np.uint8)
-            npimage = (npimage / 127.5 - 1.0).astype(np.float32)
-
-            torchdata = torch.from_numpy(npimage).permute(2, 0, 1).to(device=device, dtype=torch.float32)
-            latent_sample = None
-
-            with devices.autocast():
-                latent_dist = model.encode_first_stage(torchdata.unsqueeze(dim=0))
-
-            #Perform latent sampling, even for random sampling.
-            #We need the sample dimensions for the weights
-            if latent_sampling_method == "deterministic":
-                if isinstance(latent_dist, DiagonalGaussianDistribution):
-                    # Works only for DiagonalGaussianDistribution
-                    latent_dist.std = 0
-                else:
-                    latent_sampling_method = "once"
-            latent_sample = model.get_first_stage_encoding(latent_dist).squeeze().to(devices.cpu)
-
-            if use_weight and alpha_channel is not None:
-                channels, *latent_size = latent_sample.shape
-                weight_img = alpha_channel.resize(latent_size)
-                npweight = np.array(weight_img).astype(np.float32)
-                #Repeat for every channel in the latent sample
-                weight = torch.tensor([npweight] * channels).reshape([channels] + latent_size)
-                #Normalize the weight to a minimum of 0 and a mean of 1, that way the loss will be comparable to default.
-                weight -= weight.min()
-                weight /= weight.mean()
-            elif use_weight:
-                #If an image does not have a alpha channel, add a ones weight map anyway so we can stack it later
-                weight = torch.ones(latent_sample.shape)
-            else:
-                weight = None
-            
-            if latent_sampling_method == "random":
-                entry = DatasetEntry(filename=path, filename_text=filename_text, latent_dist=latent_dist, weight=weight)
-            else:
-                entry = DatasetEntry(filename=path, filename_text=filename_text, latent_sample=latent_sample, weight=weight)
-
-            if not (self.tag_drop_out != 0 or self.shuffle_tags):
-                entry.cond_text = self.create_text(filename_text)
-
-            if include_cond and not (self.tag_drop_out != 0 or self.shuffle_tags):
-                with devices.autocast():
-                    entry.cond = cond_model([entry.cond_text]).to(devices.cpu).squeeze(0)
-            groups[image.size].append(len(self.dataset))
-            self.dataset.append(entry)
-            del torchdata
-            del latent_dist
-            del latent_sample
-            del weight
-
-        self.length = len(self.dataset)
-        self.groups = list(groups.values())
-        assert self.length > 0, "No images have been found in the dataset."
-        self.batch_size = min(batch_size, self.length)
-        self.gradient_step = min(gradient_step, self.length // self.batch_size)
-        self.latent_sampling_method = latent_sampling_method
-
-        if len(groups) > 1:
-            print("Buckets:")
-            for (w, h), ids in sorted(groups.items(), key=lambda x: x[0]):
-                print(f"  {w}x{h}: {len(ids)}")
-            print()
-
-    def create_text(self, filename_text):
-        text = random.choice(self.lines)
-        tags = filename_text.split(',')
-        if self.tag_drop_out != 0:
-            tags = [t for t in tags if random.random() > self.tag_drop_out]
-        if self.shuffle_tags:
-            random.shuffle(tags)
-        text = text.replace("[filewords]", ','.join(tags))
-        text = text.replace("[name]", self.placeholder_token)
-        return text
-
-    def __len__(self):
-        return self.length
-
-    def __getitem__(self, i):
-        entry = self.dataset[i]
-        if self.tag_drop_out != 0 or self.shuffle_tags:
-            entry.cond_text = self.create_text(entry.filename_text)
-        if self.latent_sampling_method == "random":
-            entry.latent_sample = shared.sd_model.get_first_stage_encoding(entry.latent_dist).to(devices.cpu)
-        return entry
-
-
-class GroupedBatchSampler(Sampler):
-    def __init__(self, data_source: PersonalizedBase, batch_size: int):
-        super().__init__(data_source)
-
-        n = len(data_source)
-        self.groups = data_source.groups
-        self.len = n_batch = n // batch_size
-        expected = [len(g) / n * n_batch * batch_size for g in data_source.groups]
-        self.base = [int(e) // batch_size for e in expected]
-        self.n_rand_batches = nrb = n_batch - sum(self.base)
-        self.probs = [e%batch_size/nrb/batch_size if nrb>0 else 0 for e in expected]
-        self.batch_size = batch_size
-
-    def __len__(self):
-        return self.len
-
-    def __iter__(self):
-        b = self.batch_size
-
-        for g in self.groups:
-            shuffle(g)
-
-        batches = []
-        for g in self.groups:
-            batches.extend(g[i*b:(i+1)*b] for i in range(len(g) // b))
-        for _ in range(self.n_rand_batches):
-            rand_group = choices(self.groups, self.probs)[0]
-            batches.append(choices(rand_group, k=b))
-
-        shuffle(batches)
-
-        yield from batches
-
-
-class PersonalizedDataLoader(DataLoader):
-    def __init__(self, dataset, latent_sampling_method="once", batch_size=1, pin_memory=False):
-        super(PersonalizedDataLoader, self).__init__(dataset, batch_sampler=GroupedBatchSampler(dataset, batch_size), pin_memory=pin_memory)
-        if latent_sampling_method == "random":
-            self.collate_fn = collate_wrapper_random
-        else:
-            self.collate_fn = collate_wrapper
-
-
-class BatchLoader:
-    def __init__(self, data):
-        self.cond_text = [entry.cond_text for entry in data]
-        self.cond = [entry.cond for entry in data]
-        self.latent_sample = torch.stack([entry.latent_sample for entry in data]).squeeze(1)
-        if all(entry.weight is not None for entry in data):
-            self.weight = torch.stack([entry.weight for entry in data]).squeeze(1)
-        else:
-            self.weight = None
-        #self.emb_index = [entry.emb_index for entry in data]
-        #print(self.latent_sample.device)
-
-    def pin_memory(self):
-        self.latent_sample = self.latent_sample.pin_memory()
-        return self
-
-def collate_wrapper(batch):
-    return BatchLoader(batch)
-
-class BatchLoaderRandom(BatchLoader):
-    def __init__(self, data):
-        super().__init__(data)
-
-    def pin_memory(self):
-        return self
-
-def collate_wrapper_random(batch):
-    return BatchLoaderRandom(batch)
\ No newline at end of file
diff --git a/spaces/jhwen/bingo/src/lib/hooks/use-enter-submit.tsx b/spaces/jhwen/bingo/src/lib/hooks/use-enter-submit.tsx
deleted file mode 100644
index d66b2d3253baff164235d4ca791aae6d84721835..0000000000000000000000000000000000000000
--- a/spaces/jhwen/bingo/src/lib/hooks/use-enter-submit.tsx
+++ /dev/null
@@ -1,23 +0,0 @@
-import { useRef, type RefObject } from 'react'
-
-export function useEnterSubmit(): {
-  formRef: RefObject<HTMLFormElement>
-  onKeyDown: (event: React.KeyboardEvent<HTMLTextAreaElement>) => void
-} {
-  const formRef = useRef<HTMLFormElement>(null)
-
-  const handleKeyDown = (
-    event: React.KeyboardEvent<HTMLTextAreaElement>
-  ): void => {
-    if (
-      event.key === 'Enter' &&
-      !event.shiftKey &&
-      !event.nativeEvent.isComposing
-    ) {
-      formRef.current?.requestSubmit()
-      event.preventDefault()
-    }
-  }
-
-  return { formRef, onKeyDown: handleKeyDown }
-}
diff --git a/spaces/jie1/succ1/file/Merge_Dlsc.py b/spaces/jie1/succ1/file/Merge_Dlsc.py
deleted file mode 100644
index a6b7a81318a54ff4ac442be37592a3dbe9e88df9..0000000000000000000000000000000000000000
--- a/spaces/jie1/succ1/file/Merge_Dlsc.py
+++ /dev/null
@@ -1,38 +0,0 @@
-import re
-from tname import *
-from Rfile import *
-
-
-def Merge_Dlsc(sc_file, dl_file):
-    scontents = j_reads(sc_file.name)
-    scores = []
-
-    # 读取并保存第一个scores值
-    content = re.match('.*score=(\d.\d+?),', scontents[0])
-    score = content.group(1)
-    scores.append(float(score))
-
-    # 保存剩下的scores值
-    for i in range(2, len(scontents)):
-        if i % 2 == 0:
-            # 使用正则表达式
-            content = re.match('.*score=(\d.\d+?),', scontents[i])
-            score = content.group(1)
-            scores.append(float(score))
-
-    dcontents = j_reads(dl_file.name)
-    dcontents[0] = dcontents[0].strip() + "\t" + "scores value" + "\n"
-
-    name = Name()
-    name = name + r"kcat_scores.tsv"  # 结果文件名称
-    # 第一行与其它行格式不一样，单独写入
-    with open(name, "a") as f:
-        f.write(dcontents[0])
-
-    # 写入剩下的行
-    for i in range(1, len(dcontents)):
-        dcontents[i] = dcontents[i].strip() + "\t" + str(scores[i - 1]) + "\n"
-        with open(name, "a") as f:
-            f.write(dcontents[i])
-
-    return name
diff --git a/spaces/jinlinyi/PerspectiveFields/app.py b/spaces/jinlinyi/PerspectiveFields/app.py
deleted file mode 100644
index f501182d2fcbcd138a216346d7fd2960ca5951db..0000000000000000000000000000000000000000
--- a/spaces/jinlinyi/PerspectiveFields/app.py
+++ /dev/null
@@ -1,224 +0,0 @@
-
-import os
-os.system(f"pip install -U openmim")
-os.system(f"mim install mmcv")
-os.system(f"pip install git+https://github.com/jinlinyi/PerspectiveFields.git@dev#egg=perspective2d")
-
-
-import gradio as gr
-import cv2
-import copy
-import torch
-from PIL import Image, ImageDraw
-from glob import glob
-import numpy as np
-import os.path as osp
-from detectron2.config import get_cfg
-from detectron2.data.detection_utils import read_image
-from perspective2d.utils.predictor import VisualizationDemo
-import perspective2d.modeling  # noqa
-from perspective2d.config import get_perspective2d_cfg_defaults
-from perspective2d.utils import draw_from_r_p_f_cx_cy
-from datetime import datetime
-
-
-
-
-title = "Perspective Fields Demo"
-
-description = """
-<p style="text-align: center">
-    <a href="https://jinlinyi.github.io/PerspectiveFields/" target="_blank">Project Page</a> | 
-    <a href="https://arxiv.org/abs/2212.03239" target="_blank">Paper</a> | 
-    <a href="https://github.com/jinlinyi/PerspectiveFields" target="_blank">Code</a> | 
-    <a href="https://www.youtube.com/watch?v=sN5B_ZvMva8&themeRefresh=1" target="_blank">Video</a>
-</p>
-<h2>Gradio Demo</h2>
-<p>Try our Gradio demo for Perspective Fields for single image camera calibration. You can click on one of the provided examples or upload your own image.</p>
-<h3>Available Models:</h3>
-<ol>
-    <li><span style="color:red;">[NEW!!!]</span><strong>Paramnet-360Cities-edina:</strong> Our latest model trained on <a href="https://www.360cities.net/">360cities</a> and <a href="https://github.com/tien-d/EgoDepthNormal/tree/main#egocentric-depth-on-everyday-indoor-activities-edina-dataset">EDINA</a> dataset.</li>
-    <li><strong>PersNet-360Cities:</strong> PerspectiveNet trained on the 360Cities dataset. This model predicts perspective fields and is designed to be robust and generalize well to both indoor and outdoor images.</li>
-    <li><strong>PersNet_Paramnet-GSV-uncentered:</strong> A combination of PerspectiveNet and ParamNet trained on the Google Street View (GSV) dataset. This model predicts camera Roll, Pitch, and Field of View (FoV), as well as the Principal Point location.</li>
-    <li><strong>PersNet_Paramnet-GSV-centered:</strong> PerspectiveNet+ParamNet trained on the GSV dataset. This model assumes the principal point is at the center of the image and predicts camera Roll, Pitch, and FoV.</li>
-</ol>
-"""
-
-
-article = """
-<p style='text-align: center'><a href='https://arxiv.org/abs/2212.03239' target='_blank'>Perspective Fields for Single Image Camera Calibrations</a> | <a href='https://github.com/jinlinyi/PerspectiveFields' target='_blank'>Github Repo</a></p>
-"""
-
-
-
-
-def setup_cfg(args):
-    cfgs = []
-    configs = args['config_file'].split('#')
-    weights_id = args['opts'].index('MODEL.WEIGHTS') + 1
-    weights = args['opts'][weights_id].split('#')
-    for i, conf in enumerate(configs):
-        if len(conf) != 0:
-            tmp_opts = copy.deepcopy(args['opts'])
-            tmp_opts[weights_id] = weights[i]
-            cfg = get_cfg()
-            get_perspective2d_cfg_defaults(cfg)
-            cfg.merge_from_file(conf)
-            cfg.merge_from_list(tmp_opts)
-            cfg.freeze()
-            cfgs.append(cfg)
-    return cfgs
-
-def resize_fix_aspect_ratio(img, field, target_width=None, target_height=None):
-    height = img.shape[0]
-    width = img.shape[1]
-    if target_height is None:
-        factor = target_width / width
-    elif target_width is None:
-        factor = target_height / height
-    else:
-        factor = max(target_width / width, target_height / height)
-    if factor == target_width / width:
-        target_height = int(height * factor)
-    else:
-        target_width = int(width * factor)
-        
-    img = cv2.resize(img, (target_width, target_height))
-    for key in field:
-        if key not in ['up', 'lati']:
-            continue
-        tmp = field[key].numpy()
-        transpose = len(tmp.shape) == 3
-        if transpose:
-            tmp = tmp.transpose(1,2,0)
-        tmp = cv2.resize(tmp, (target_width, target_height))
-        if transpose:
-            tmp = tmp.transpose(2,0,1)
-        field[key] = torch.tensor(tmp)
-    return img, field
-
-
-def inference(img, model_type):
-    img_h = img.shape[0]
-    if model_type is None:
-        return None, ""
-    perspective_cfg_list = setup_cfg(model_zoo[model_type])
-    demo = VisualizationDemo(cfg_list=perspective_cfg_list)
-
-    # img = read_image(image_path, format="BGR")
-    img = img[..., ::-1] # rgb->bgr
-    pred = demo.run_on_image(img)
-    field = {
-        'up': pred['pred_gravity_original'].cpu().detach(),
-        'lati': pred['pred_latitude_original'].cpu().detach(),
-    }
-    img, field = resize_fix_aspect_ratio(img, field, 640)
-    if not model_zoo[model_type]['param']:
-        pred_vis = demo.draw(
-            image=img,
-            latimap=field['lati'],
-            gravity=field['up'],
-            latimap_format=pred['pred_latitude_original_mode'],
-        ).get_image()
-        param = "Not Implemented"
-    else:
-        if 'pred_general_vfov' not in pred.keys():
-            pred['pred_general_vfov'] = pred['pred_vfov']
-        if 'pred_rel_cx' not in pred.keys():
-            pred['pred_rel_cx'] = torch.FloatTensor([0])
-        if 'pred_rel_cy' not in pred.keys():
-            pred['pred_rel_cy'] = torch.FloatTensor([0])
-            
-        r_p_f_rad = np.radians(
-            [
-                pred['pred_roll'].cpu().item(),
-                pred['pred_pitch'].cpu().item(),
-                pred['pred_general_vfov'].cpu().item(),
-            ]
-        )
-        cx_cy = [
-            pred['pred_rel_cx'].cpu().item(),
-            pred['pred_rel_cy'].cpu().item(),
-        ]
-        param = f"roll {pred['pred_roll'].cpu().item() :.2f}\npitch {pred['pred_pitch'].cpu().item() :.2f}\nvertical fov {pred['pred_general_vfov'].cpu().item() :.2f}\nfocal_length {pred['pred_rel_focal'].cpu().item()*img_h :.2f}\n"
-        param += f"principal point {pred['pred_rel_cx'].cpu().item() :.2f} {pred['pred_rel_cy'].cpu().item() :.2f}"
-        pred_vis = draw_from_r_p_f_cx_cy(
-            img[:,:,::-1], 
-            *r_p_f_rad,
-            *cx_cy,
-            'rad',
-            up_color=(0,1,0),
-        )
-    print(f"""time {datetime.now().strftime("%H:%M:%S")}
-    img.shape {img.shape}
-    model_type {model_type}
-    param {param}
-    """
-    )
-    return Image.fromarray(pred_vis), param
-
-examples = []
-for img_name in glob('assets/imgs/*.*g'):
-    examples.append([img_name])
-print(examples)
-
-device = 'cuda' if torch.cuda.is_available() else 'cpu'
-model_zoo = {
-
-    'NEW:Paramnet-360Cities-edina-centered': {
-        'weights': ['https://www.dropbox.com/s/z2dja70bgy007su/paramnet_360cities_edina_rpf.pth'],
-        'opts': ['MODEL.WEIGHTS', 'models/paramnet_360cities_edina_rpf.pth', 'MODEL.DEVICE', device,],
-        'config_file': 'models/paramnet_360cities_edina_rpf.yaml',
-        'param': True,
-    },
-
-   'NEW:Paramnet-360Cities-edina-uncentered': {
-        'weights': ['https://www.dropbox.com/s/nt29e1pi83mm1va/paramnet_360cities_edina_rpfpp.pth'],
-        'opts': ['MODEL.WEIGHTS', 'models/paramnet_360cities_edina_rpfpp.pth', 'MODEL.DEVICE', device,],
-        'config_file': 'models/paramnet_360cities_edina_rpfpp.yaml',
-        'param': True,
-    },
-
-    'PersNet-360Cities': {
-        'weights': ['https://www.dropbox.com/s/czqrepqe7x70b7y/cvpr2023.pth'],
-        'opts': ['MODEL.WEIGHTS', 'models/cvpr2023.pth', 'MODEL.DEVICE', device,],
-        'config_file': 'models/cvpr2023.yaml',
-        'param': False,
-    },
-    'PersNet_Paramnet-GSV-uncentered': {
-        'weights': ['https://www.dropbox.com/s/ufdadxigewakzlz/paramnet_gsv_rpfpp.pth'],
-        'opts': ['MODEL.WEIGHTS', 'models/paramnet_gsv_rpfpp.pth', 'MODEL.DEVICE', device,],
-        'config_file': 'models/paramnet_gsv_rpfpp.yaml',
-        'param': True,
-    },
-    # trained on GSV dataset, predicts Perspective Fields + camera parameters (roll, pitch, fov), assuming centered principal point
-    'PersNet_Paramnet-GSV-centered': {
-        'weights': ['https://www.dropbox.com/s/g6xwbgnkggapyeu/paramnet_gsv_rpf.pth'],
-        'opts': ['MODEL.WEIGHTS', 'models/paramnet_gsv_rpf.pth', 'MODEL.DEVICE', device,],
-        'config_file': 'models/paramnet_gsv_rpf.yaml',
-        'param': True,
-    },
-}
-for model_id in model_zoo:
-    html = model_zoo[model_id]['weights'][0]
-    if not os.path.exists(os.path.join('models', html.split('/')[-1])):
-        os.system(f"wget -P models/ {html}")
-
-info = """Select model\n"""
-gr.Interface(
-    fn=inference,
-    inputs=[
-        "image", 
-        gr.Radio(
-            list(model_zoo.keys()), 
-            value=list(sorted(model_zoo.keys()))[0], 
-            label="Model", 
-            info=info,
-        ),
-    ],
-    outputs=[gr.Image(label='Perspective Fields'), gr.Textbox(label='Pred Camera Parameters')],
-    title=title,
-    description=description,
-    article=article,
-    examples=examples,
-).launch()
\ No newline at end of file
diff --git a/spaces/joaopereirajp/livvieChatBot/venv/lib/python3.9/site-packages/dns/rdtypes/ANY/SSHFP.py b/spaces/joaopereirajp/livvieChatBot/venv/lib/python3.9/site-packages/dns/rdtypes/ANY/SSHFP.py
deleted file mode 100644
index 67805452d6b7e17cf40dcc792130972f1b2b98b2..0000000000000000000000000000000000000000
--- a/spaces/joaopereirajp/livvieChatBot/venv/lib/python3.9/site-packages/dns/rdtypes/ANY/SSHFP.py
+++ /dev/null
@@ -1,69 +0,0 @@
-# Copyright (C) Dnspython Contributors, see LICENSE for text of ISC license
-
-# Copyright (C) 2005-2007, 2009-2011 Nominum, Inc.
-#
-# Permission to use, copy, modify, and distribute this software and its
-# documentation for any purpose with or without fee is hereby granted,
-# provided that the above copyright notice and this permission notice
-# appear in all copies.
-#
-# THE SOFTWARE IS PROVIDED "AS IS" AND NOMINUM DISCLAIMS ALL WARRANTIES
-# WITH REGARD TO THIS SOFTWARE INCLUDING ALL IMPLIED WARRANTIES OF
-# MERCHANTABILITY AND FITNESS. IN NO EVENT SHALL NOMINUM BE LIABLE FOR
-# ANY SPECIAL, DIRECT, INDIRECT, OR CONSEQUENTIAL DAMAGES OR ANY DAMAGES
-# WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS, WHETHER IN AN
-# ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION, ARISING OUT
-# OF OR IN CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE.
-
-import binascii
-import struct
-
-import dns.immutable
-import dns.rdata
-import dns.rdatatype
-
-
-@dns.immutable.immutable
-class SSHFP(dns.rdata.Rdata):
-
-    """SSHFP record"""
-
-    # See RFC 4255
-
-    __slots__ = ["algorithm", "fp_type", "fingerprint"]
-
-    def __init__(self, rdclass, rdtype, algorithm, fp_type, fingerprint):
-        super().__init__(rdclass, rdtype)
-        self.algorithm = self._as_uint8(algorithm)
-        self.fp_type = self._as_uint8(fp_type)
-        self.fingerprint = self._as_bytes(fingerprint, True)
-
-    def to_text(self, origin=None, relativize=True, **kw):
-        kw = kw.copy()
-        chunksize = kw.pop("chunksize", 128)
-        return "%d %d %s" % (
-            self.algorithm,
-            self.fp_type,
-            dns.rdata._hexify(self.fingerprint, chunksize=chunksize, **kw),
-        )
-
-    @classmethod
-    def from_text(
-        cls, rdclass, rdtype, tok, origin=None, relativize=True, relativize_to=None
-    ):
-        algorithm = tok.get_uint8()
-        fp_type = tok.get_uint8()
-        fingerprint = tok.concatenate_remaining_identifiers().encode()
-        fingerprint = binascii.unhexlify(fingerprint)
-        return cls(rdclass, rdtype, algorithm, fp_type, fingerprint)
-
-    def _to_wire(self, file, compress=None, origin=None, canonicalize=False):
-        header = struct.pack("!BB", self.algorithm, self.fp_type)
-        file.write(header)
-        file.write(self.fingerprint)
-
-    @classmethod
-    def from_wire_parser(cls, rdclass, rdtype, parser, origin=None):
-        header = parser.get_struct("BB")
-        fingerprint = parser.get_remaining()
-        return cls(rdclass, rdtype, header[0], header[1], fingerprint)
diff --git a/spaces/joaopereirajp/livvieChatBot/venv/lib/python3.9/site-packages/fontTools/varLib/instancer/solver.py b/spaces/joaopereirajp/livvieChatBot/venv/lib/python3.9/site-packages/fontTools/varLib/instancer/solver.py
deleted file mode 100644
index c991fcdcfbdc2fb6ac4815fe94b0c4ecb92a3e2d..0000000000000000000000000000000000000000
--- a/spaces/joaopereirajp/livvieChatBot/venv/lib/python3.9/site-packages/fontTools/varLib/instancer/solver.py
+++ /dev/null
@@ -1,305 +0,0 @@
-from fontTools.varLib.models import supportScalar
-from fontTools.misc.fixedTools import MAX_F2DOT14
-from functools import lru_cache
-
-__all__ = ["rebaseTent"]
-
-EPSILON = 1 / (1 << 14)
-
-
-def _reverse_negate(v):
-    return (-v[2], -v[1], -v[0])
-
-
-def _solve(tent, axisLimit, negative=False):
-    axisMin, axisDef, axisMax, _distanceNegative, _distancePositive = axisLimit
-    lower, peak, upper = tent
-
-    # Mirror the problem such that axisDef <= peak
-    if axisDef > peak:
-        return [
-            (scalar, _reverse_negate(t) if t is not None else None)
-            for scalar, t in _solve(
-                _reverse_negate(tent),
-                axisLimit.reverse_negate(),
-                not negative,
-            )
-        ]
-    # axisDef <= peak
-
-    # case 1: The whole deltaset falls outside the new limit; we can drop it
-    #
-    #                                          peak
-    #  1.........................................o..........
-    #                                           / \
-    #                                          /   \
-    #                                         /     \
-    #                                        /       \
-    #  0---|-----------|----------|-------- o         o----1
-    #    axisMin     axisDef    axisMax   lower     upper
-    #
-    if axisMax <= lower and axisMax < peak:
-        return []  # No overlap
-
-    # case 2: Only the peak and outermost bound fall outside the new limit;
-    # we keep the deltaset, update peak and outermost bound and and scale deltas
-    # by the scalar value for the restricted axis at the new limit, and solve
-    # recursively.
-    #
-    #                                  |peak
-    #  1...............................|.o..........
-    #                                  |/ \
-    #                                  /   \
-    #                                 /|    \
-    #                                / |     \
-    #  0--------------------------- o  |      o----1
-    #                           lower  |      upper
-    #                                  |
-    #                                axisMax
-    #
-    # Convert to:
-    #
-    #  1............................................
-    #                                  |
-    #                                  o peak
-    #                                 /|
-    #                                /x|
-    #  0--------------------------- o  o upper ----1
-    #                           lower  |
-    #                                  |
-    #                                axisMax
-    if axisMax < peak:
-        mult = supportScalar({"tag": axisMax}, {"tag": tent})
-        tent = (lower, axisMax, axisMax)
-        return [(scalar * mult, t) for scalar, t in _solve(tent, axisLimit)]
-
-    # lower <= axisDef <= peak <= axisMax
-
-    gain = supportScalar({"tag": axisDef}, {"tag": tent})
-    out = [(gain, None)]
-
-    # First, the positive side
-
-    # outGain is the scalar of axisMax at the tent.
-    outGain = supportScalar({"tag": axisMax}, {"tag": tent})
-
-    # Case 3a: Gain is more than outGain. The tent down-slope crosses
-    # the axis into negative. We have to split it into multiples.
-    #
-    #                      | peak  |
-    #  1...................|.o.....|..............
-    #                      |/x\_   |
-    #  gain................+....+_.|..............
-    #                     /|    |y\|
-    #  ................../.|....|..+_......outGain
-    #                   /  |    |  | \
-    #  0---|-----------o   |    |  |  o----------1
-    #    axisMin    lower  |    |  |   upper
-    #                      |    |  |
-    #                axisDef    |  axisMax
-    #                           |
-    #                      crossing
-    if gain > outGain:
-        # Crossing point on the axis.
-        crossing = peak + (1 - gain) * (upper - peak)
-
-        loc = (axisDef, peak, crossing)
-        scalar = 1
-
-        # The part before the crossing point.
-        out.append((scalar - gain, loc))
-
-        # The part after the crossing point may use one or two tents,
-        # depending on whether upper is before axisMax or not, in one
-        # case we need to keep it down to eternity.
-
-        # Case 3a1, similar to case 1neg; just one tent needed, as in
-        # the drawing above.
-        if upper >= axisMax:
-            loc = (crossing, axisMax, axisMax)
-            scalar = outGain
-
-            out.append((scalar - gain, loc))
-
-        # Case 3a2: Similar to case 2neg; two tents needed, to keep
-        # down to eternity.
-        #
-        #                      | peak             |
-        #  1...................|.o................|...
-        #                      |/ \_              |
-        #  gain................+....+_............|...
-        #                     /|    | \xxxxxxxxxxy|
-        #                    / |    |  \_xxxxxyyyy|
-        #                   /  |    |    \xxyyyyyy|
-        #  0---|-----------o   |    |     o-------|--1
-        #    axisMin    lower  |    |      upper  |
-        #                      |    |             |
-        #                axisDef    |             axisMax
-        #                           |
-        #                      crossing
-        else:
-            # A tent's peak cannot fall on axis default. Nudge it.
-            if upper == axisDef:
-                upper += EPSILON
-
-            # Downslope.
-            loc1 = (crossing, upper, axisMax)
-            scalar1 = 0
-
-            # Eternity justify.
-            loc2 = (upper, axisMax, axisMax)
-            scalar2 = 0
-
-            out.append((scalar1 - gain, loc1))
-            out.append((scalar2 - gain, loc2))
-
-    else:
-        # Special-case if peak is at axisMax.
-        if axisMax == peak:
-            upper = peak
-
-        # Case 3:
-        # We keep delta as is and only scale the axis upper to achieve
-        # the desired new tent if feasible.
-        #
-        #                        peak
-        #  1.....................o....................
-        #                       / \_|
-        #  ..................../....+_.........outGain
-        #                     /     | \
-        #  gain..............+......|..+_.............
-        #                   /|      |  | \
-        #  0---|-----------o |      |  |  o----------1
-        #    axisMin    lower|      |  |   upper
-        #                    |      |  newUpper
-        #              axisDef      axisMax
-        #
-        newUpper = peak + (1 - gain) * (upper - peak)
-        assert axisMax <= newUpper  # Because outGain >= gain
-        if newUpper <= axisDef + (axisMax - axisDef) * 2:
-            upper = newUpper
-            if not negative and axisDef + (axisMax - axisDef) * MAX_F2DOT14 < upper:
-                # we clamp +2.0 to the max F2Dot14 (~1.99994) for convenience
-                upper = axisDef + (axisMax - axisDef) * MAX_F2DOT14
-                assert peak < upper
-
-            loc = (max(axisDef, lower), peak, upper)
-            scalar = 1
-
-            out.append((scalar - gain, loc))
-
-        # Case 4: New limit doesn't fit; we need to chop into two tents,
-        # because the shape of a triangle with part of one side cut off
-        # cannot be represented as a triangle itself.
-        #
-        #            |   peak |
-        #  1.........|......o.|....................
-        #  ..........|...../x\|.............outGain
-        #            |    |xxy|\_
-        #            |   /xxxy|  \_
-        #            |  |xxxxy|    \_
-        #            |  /xxxxy|      \_
-        #  0---|-----|-oxxxxxx|        o----------1
-        #    axisMin | lower  |        upper
-        #            |        |
-        #          axisDef  axisMax
-        #
-        else:
-            loc1 = (max(axisDef, lower), peak, axisMax)
-            scalar1 = 1
-
-            loc2 = (peak, axisMax, axisMax)
-            scalar2 = outGain
-
-            out.append((scalar1 - gain, loc1))
-            # Don't add a dirac delta!
-            if peak < axisMax:
-                out.append((scalar2 - gain, loc2))
-
-    # Now, the negative side
-
-    # Case 1neg: Lower extends beyond axisMin: we chop. Simple.
-    #
-    #                     |   |peak
-    #  1..................|...|.o.................
-    #                     |   |/ \
-    #  gain...............|...+...\...............
-    #                     |x_/|    \
-    #                     |/  |     \
-    #                   _/|   |      \
-    #  0---------------o  |   |       o----------1
-    #              lower  |   |       upper
-    #                     |   |
-    #               axisMin   axisDef
-    #
-    if lower <= axisMin:
-        loc = (axisMin, axisMin, axisDef)
-        scalar = supportScalar({"tag": axisMin}, {"tag": tent})
-
-        out.append((scalar - gain, loc))
-
-    # Case 2neg: Lower is betwen axisMin and axisDef: we add two
-    # tents to keep it down all the way to eternity.
-    #
-    #      |               |peak
-    #  1...|...............|.o.................
-    #      |               |/ \
-    #  gain|...............+...\...............
-    #      |yxxxxxxxxxxxxx/|    \
-    #      |yyyyyyxxxxxxx/ |     \
-    #      |yyyyyyyyyyyx/  |      \
-    #  0---|-----------o   |       o----------1
-    #    axisMin    lower  |       upper
-    #                      |
-    #                    axisDef
-    #
-    else:
-        # A tent's peak cannot fall on axis default. Nudge it.
-        if lower == axisDef:
-            lower -= EPSILON
-
-        # Downslope.
-        loc1 = (axisMin, lower, axisDef)
-        scalar1 = 0
-
-        # Eternity justify.
-        loc2 = (axisMin, axisMin, lower)
-        scalar2 = 0
-
-        out.append((scalar1 - gain, loc1))
-        out.append((scalar2 - gain, loc2))
-
-    return out
-
-
-@lru_cache(128)
-def rebaseTent(tent, axisLimit):
-    """Given a tuple (lower,peak,upper) "tent" and new axis limits
-    (axisMin,axisDefault,axisMax), solves how to represent the tent
-    under the new axis configuration.  All values are in normalized
-    -1,0,+1 coordinate system. Tent values can be outside this range.
-
-    Return value is a list of tuples. Each tuple is of the form
-    (scalar,tent), where scalar is a multipler to multiply any
-    delta-sets by, and tent is a new tent for that output delta-set.
-    If tent value is None, that is a special deltaset that should
-    be always-enabled (called "gain")."""
-
-    axisMin, axisDef, axisMax, _distanceNegative, _distancePositive = axisLimit
-    assert -1 <= axisMin <= axisDef <= axisMax <= +1
-
-    lower, peak, upper = tent
-    assert -2 <= lower <= peak <= upper <= +2
-
-    assert peak != 0
-
-    sols = _solve(tent, axisLimit)
-
-    n = lambda v: axisLimit.renormalizeValue(v)
-    sols = [
-        (scalar, (n(v[0]), n(v[1]), n(v[2])) if v is not None else None)
-        for scalar, v in sols
-        if scalar
-    ]
-
-    return sols
diff --git a/spaces/jpfearnworks/ai_agents/modules/knowledge_retrieval/domains/family_domain.py b/spaces/jpfearnworks/ai_agents/modules/knowledge_retrieval/domains/family_domain.py
deleted file mode 100644
index 6e446bcf35369c52fad82692c18020299284f075..0000000000000000000000000000000000000000
--- a/spaces/jpfearnworks/ai_agents/modules/knowledge_retrieval/domains/family_domain.py
+++ /dev/null
@@ -1,68 +0,0 @@
-from modules.base.llm_chain_config import LLMChainConfig
-from modules.knowledge_retrieval.destination_chain import DestinationChainStrategy
-from modules.knowledge_retrieval.base import KnowledgeDomain
-from loguru import logger
-from langchain import PromptTemplate, LLMChain
-from langchain.llms.openai import OpenAI
-from typing import Callable
-import pprint 
-
-class FamilyDomain(KnowledgeDomain):
-    """
-    FamilyDomain Class
-
-    Design:
-    This class is a specific implementation of the KnowledgeDomain class, providing an 
-    implementation for generating responses to family-related questions. Following the 
-    Single Responsibility Principle (SRP), its sole responsibility is to generate family-related responses.
-
-    Intended Implementation:
-    The generate_response method should generate useful responses to family-related questions. 
-    This might involve rule-based logic or a trained machine learning model, depending on the 
-    specifics of the problem domain.
-    """
-    def generate_response(self, question: str) -> str:
-        template_cot = """You are asked a family-related question and rather than simply guessing the right answer break down the solution into a series of steps
-        The question is {question}
-
-        Write out your step by step reasoning and after considering all of the facts and applying this reasoning write out your final answer
-        """
-        prompt = PromptTemplate(template=template_cot, input_variables=["question"])
-        llm_chain = LLMChain(prompt=prompt, llm=OpenAI(temperature=0.7, max_tokens=1500))  # assuming OpenAI is the LLM to be used
-        response_cot = llm_chain.run(question)
-        return response_cot
-
-
-class FamilyChain(DestinationChainStrategy):
-    """
-    FamilyChain Class
-
-    Design:
-    This class is a specific implementation of the ChainStrategy class.
-    It follows the Open/Closed Principle (OCP) because it extends the ChainStrategy class 
-    without modifying its behavior. It also adheres to the Dependency Inversion Principle (DIP) as it 
-    depends on the abstraction (FamilyDomain) rather than a concrete class.
-
-    Intended Implementation:
-    The FamilyChain class serves as a wrapper around a FamilyDomain instance. It implements the run 
-    method from the ChainStrategy class, which simply calls the generate_response method of the FamilyDomain.
-    As such, when the run method is called with a question as input, the FamilyChain class will return a 
-    response generated by the FamilyDomain.
-    """
-    def __init__(self, config: LLMChainConfig, display: Callable):
-        super().__init__(config=config, display=display, knowledge_domain=FamilyDomain(), usage=config.usage)
-        print("Creating Family Chain with config: ")
-        pprint.pprint(vars(config))
-
-    def run(self, question):
-        print('Using Family Chain of Thought')
-        self.display("Using 'Family Chain of Thought'")
-        response_cot = super().run(question)
-        return response_cot
-
-def get_family_chain_config(temperature: float = 0.7) -> LLMChainConfig:
-    usage = """
-    This problem is family-related and the solution may be obtained by focusing on generating a coherent series 
-    of reasoning steps that lead to the final answer. The problem is related to family plans, personal matters, family relations, and general non business related questions.
-    """
-    return LLMChainConfig(usage=usage, temperature=temperature)
diff --git a/spaces/juuxn/SimpleRVC/myutils.py b/spaces/juuxn/SimpleRVC/myutils.py
deleted file mode 100644
index c27b81862e7ad35c35f16aa5b7d71871d2e35d6b..0000000000000000000000000000000000000000
--- a/spaces/juuxn/SimpleRVC/myutils.py
+++ /dev/null
@@ -1,92 +0,0 @@
-import requests
-import os
-import ffmpeg
-import numpy as np
-import random
-import shutil
-import torchaudio
-from pydub import AudioSegment
-import tempfile
-
-class Audio:
-
-    audio_path = "./audios"
-
-    def __init__(self, name, url):
-        self._name = name
-        self._url = url
-
-        if not os.path.exists(Audio.audio_path):
-            os.mkdir(Audio.audio_path)
-
-    @property
-    def name(self):
-        return self._name
-
-    @name.setter
-    def name(self, name):
-        self._name = name
-
-    @property
-    def url(self):
-        return self._url
-
-    @url.setter
-    def url(self, url):
-        self._url = url
-
-    def __str__(self):
-        return f'Audio: {self._name} {self._url}'
-
-    @classmethod
-    def load_audio(cls, file, sr):
-        try:
-            file = file.strip(' "\n')  # Eliminar espacios y comillas del nombre del archivo
-            # Convertir a formato WAV si no lo está
-            if not file.endswith(".wav"):
-                file_formanted = f"{file}.wav"
-                if not os.path.isfile(file_formanted):
-                    (
-                        ffmpeg.input(file)
-                        .output(file_formanted, format="wav")
-                        .run(cmd=["ffmpeg", "-nostdin"], capture_stdout=True, capture_stderr=True)
-                    )
-            else:
-                file_formanted = file
-
-            # Cargar el archivo formateado y devolverlo como NumPy array
-            out, _ = (
-                ffmpeg.input(file_formanted)
-                .output("-", format="f32le", acodec="pcm_f32le", ac=1, ar=sr)
-                .run(cmd=["ffmpeg", "-nostdin"], capture_stdout=True, capture_stderr=True)
-            )
-
-            # Eliminar el archivo formateado
-            os.remove(file_formanted)    
-        except Exception as e:
-            raise RuntimeError(f"Failed to load audio: {e}")
-
-        return np.frombuffer(out, np.float32).flatten()
-
-    @classmethod
-    def dowload_from_url(self, url = None, output = "./audios/file.wav"):
-        """
-        Descarga un aduio desde una url
-        Args:
-            path: Folder where the audio will be downloaded
-        Returns:
-            return: the path of the downloaded audio
-        """
-        request = requests.get(url, allow_redirects=True)
-        open(output, 'wb').write(request.content)
-
-        return output
-
-
-def delete_files(paths):
-    for path in paths:
-        if os.path.exists(path):
-            if os.path.isdir(path):
-                shutil.rmtree(path, ignore_errors=True)
-            if os.path.isfile(path):
-                os.remove(path)
\ No newline at end of file
diff --git a/spaces/k1ngtai/MMS/vits/utils.py b/spaces/k1ngtai/MMS/vits/utils.py
deleted file mode 100644
index b445fb65836a0b97e46426300eea9a820179797a..0000000000000000000000000000000000000000
--- a/spaces/k1ngtai/MMS/vits/utils.py
+++ /dev/null
@@ -1,258 +0,0 @@
-import os
-import glob
-import sys
-import argparse
-import logging
-import json
-import subprocess
-import numpy as np
-from scipy.io.wavfile import read
-import torch
-
-MATPLOTLIB_FLAG = False
-
-logging.basicConfig(stream=sys.stdout, level=logging.DEBUG)
-logger = logging
-
-
-def load_checkpoint(checkpoint_path, model, optimizer=None):
-  assert os.path.isfile(checkpoint_path)
-  checkpoint_dict = torch.load(checkpoint_path, map_location='cpu')
-  iteration = checkpoint_dict['iteration']
-  learning_rate = checkpoint_dict['learning_rate']
-  if optimizer is not None:
-    optimizer.load_state_dict(checkpoint_dict['optimizer'])
-  saved_state_dict = checkpoint_dict['model']
-  if hasattr(model, 'module'):
-    state_dict = model.module.state_dict()
-  else:
-    state_dict = model.state_dict()
-  new_state_dict= {}
-  for k, v in state_dict.items():
-    try:
-      new_state_dict[k] = saved_state_dict[k]
-    except:
-      logger.info("%s is not in the checkpoint" % k)
-      new_state_dict[k] = v
-  if hasattr(model, 'module'):
-    model.module.load_state_dict(new_state_dict)
-  else:
-    model.load_state_dict(new_state_dict)
-  logger.info("Loaded checkpoint '{}' (iteration {})" .format(
-    checkpoint_path, iteration))
-  return model, optimizer, learning_rate, iteration
-
-
-def save_checkpoint(model, optimizer, learning_rate, iteration, checkpoint_path):
-  logger.info("Saving model and optimizer state at iteration {} to {}".format(
-    iteration, checkpoint_path))
-  if hasattr(model, 'module'):
-    state_dict = model.module.state_dict()
-  else:
-    state_dict = model.state_dict()
-  torch.save({'model': state_dict,
-              'iteration': iteration,
-              'optimizer': optimizer.state_dict(),
-              'learning_rate': learning_rate}, checkpoint_path)
-
-
-def summarize(writer, global_step, scalars={}, histograms={}, images={}, audios={}, audio_sampling_rate=22050):
-  for k, v in scalars.items():
-    writer.add_scalar(k, v, global_step)
-  for k, v in histograms.items():
-    writer.add_histogram(k, v, global_step)
-  for k, v in images.items():
-    writer.add_image(k, v, global_step, dataformats='HWC')
-  for k, v in audios.items():
-    writer.add_audio(k, v, global_step, audio_sampling_rate)
-
-
-def latest_checkpoint_path(dir_path, regex="G_*.pth"):
-  f_list = glob.glob(os.path.join(dir_path, regex))
-  f_list.sort(key=lambda f: int("".join(filter(str.isdigit, f))))
-  x = f_list[-1]
-  print(x)
-  return x
-
-
-def plot_spectrogram_to_numpy(spectrogram):
-  global MATPLOTLIB_FLAG
-  if not MATPLOTLIB_FLAG:
-    import matplotlib
-    matplotlib.use("Agg")
-    MATPLOTLIB_FLAG = True
-    mpl_logger = logging.getLogger('matplotlib')
-    mpl_logger.setLevel(logging.WARNING)
-  import matplotlib.pylab as plt
-  import numpy as np
-  
-  fig, ax = plt.subplots(figsize=(10,2))
-  im = ax.imshow(spectrogram, aspect="auto", origin="lower",
-                  interpolation='none')
-  plt.colorbar(im, ax=ax)
-  plt.xlabel("Frames")
-  plt.ylabel("Channels")
-  plt.tight_layout()
-
-  fig.canvas.draw()
-  data = np.fromstring(fig.canvas.tostring_rgb(), dtype=np.uint8, sep='')
-  data = data.reshape(fig.canvas.get_width_height()[::-1] + (3,))
-  plt.close()
-  return data
-
-
-def plot_alignment_to_numpy(alignment, info=None):
-  global MATPLOTLIB_FLAG
-  if not MATPLOTLIB_FLAG:
-    import matplotlib
-    matplotlib.use("Agg")
-    MATPLOTLIB_FLAG = True
-    mpl_logger = logging.getLogger('matplotlib')
-    mpl_logger.setLevel(logging.WARNING)
-  import matplotlib.pylab as plt
-  import numpy as np
-
-  fig, ax = plt.subplots(figsize=(6, 4))
-  im = ax.imshow(alignment.transpose(), aspect='auto', origin='lower',
-                  interpolation='none')
-  fig.colorbar(im, ax=ax)
-  xlabel = 'Decoder timestep'
-  if info is not None:
-      xlabel += '\n\n' + info
-  plt.xlabel(xlabel)
-  plt.ylabel('Encoder timestep')
-  plt.tight_layout()
-
-  fig.canvas.draw()
-  data = np.fromstring(fig.canvas.tostring_rgb(), dtype=np.uint8, sep='')
-  data = data.reshape(fig.canvas.get_width_height()[::-1] + (3,))
-  plt.close()
-  return data
-
-
-def load_wav_to_torch(full_path):
-  sampling_rate, data = read(full_path)
-  return torch.FloatTensor(data.astype(np.float32)), sampling_rate
-
-
-def load_filepaths_and_text(filename, split="|"):
-  with open(filename, encoding='utf-8') as f:
-    filepaths_and_text = [line.strip().split(split) for line in f]
-  return filepaths_and_text
-
-
-def get_hparams(init=True):
-  parser = argparse.ArgumentParser()
-  parser.add_argument('-c', '--config', type=str, default="./configs/base.json",
-                      help='JSON file for configuration')
-  parser.add_argument('-m', '--model', type=str, required=True,
-                      help='Model name')
-  
-  args = parser.parse_args()
-  model_dir = os.path.join("./logs", args.model)
-
-  if not os.path.exists(model_dir):
-    os.makedirs(model_dir)
-
-  config_path = args.config
-  config_save_path = os.path.join(model_dir, "config.json")
-  if init:
-    with open(config_path, "r") as f:
-      data = f.read()
-    with open(config_save_path, "w") as f:
-      f.write(data)
-  else:
-    with open(config_save_path, "r") as f:
-      data = f.read()
-  config = json.loads(data)
-  
-  hparams = HParams(**config)
-  hparams.model_dir = model_dir
-  return hparams
-
-
-def get_hparams_from_dir(model_dir):
-  config_save_path = os.path.join(model_dir, "config.json")
-  with open(config_save_path, "r") as f:
-    data = f.read()
-  config = json.loads(data)
-
-  hparams =HParams(**config)
-  hparams.model_dir = model_dir
-  return hparams
-
-
-def get_hparams_from_file(config_path):
-  with open(config_path, "r") as f:
-    data = f.read()
-  config = json.loads(data)
-
-  hparams =HParams(**config)
-  return hparams
-
-
-def check_git_hash(model_dir):
-  source_dir = os.path.dirname(os.path.realpath(__file__))
-  if not os.path.exists(os.path.join(source_dir, ".git")):
-    logger.warn("{} is not a git repository, therefore hash value comparison will be ignored.".format(
-      source_dir
-    ))
-    return
-
-  cur_hash = subprocess.getoutput("git rev-parse HEAD")
-
-  path = os.path.join(model_dir, "githash")
-  if os.path.exists(path):
-    saved_hash = open(path).read()
-    if saved_hash != cur_hash:
-      logger.warn("git hash values are different. {}(saved) != {}(current)".format(
-        saved_hash[:8], cur_hash[:8]))
-  else:
-    open(path, "w").write(cur_hash)
-
-
-def get_logger(model_dir, filename="train.log"):
-  global logger
-  logger = logging.getLogger(os.path.basename(model_dir))
-  logger.setLevel(logging.DEBUG)
-  
-  formatter = logging.Formatter("%(asctime)s\t%(name)s\t%(levelname)s\t%(message)s")
-  if not os.path.exists(model_dir):
-    os.makedirs(model_dir)
-  h = logging.FileHandler(os.path.join(model_dir, filename))
-  h.setLevel(logging.DEBUG)
-  h.setFormatter(formatter)
-  logger.addHandler(h)
-  return logger
-
-
-class HParams():
-  def __init__(self, **kwargs):
-    for k, v in kwargs.items():
-      if type(v) == dict:
-        v = HParams(**v)
-      self[k] = v
-    
-  def keys(self):
-    return self.__dict__.keys()
-
-  def items(self):
-    return self.__dict__.items()
-
-  def values(self):
-    return self.__dict__.values()
-
-  def __len__(self):
-    return len(self.__dict__)
-
-  def __getitem__(self, key):
-    return getattr(self, key)
-
-  def __setitem__(self, key, value):
-    return setattr(self, key, value)
-
-  def __contains__(self, key):
-    return key in self.__dict__
-
-  def __repr__(self):
-    return self.__dict__.__repr__()
diff --git a/spaces/kandysh/NER_Tagger/process_tags.py b/spaces/kandysh/NER_Tagger/process_tags.py
deleted file mode 100644
index ccc05790fc8a0f47772cd81914fd7f9ab68b8ef0..0000000000000000000000000000000000000000
--- a/spaces/kandysh/NER_Tagger/process_tags.py
+++ /dev/null
@@ -1,132 +0,0 @@
-import collections
-import functools
-import operator
-import numpy as np
-import pandas as pd
-import plotly.express as px
-import plotly.graph_objects as go
-from plotly.offline import iplot
-from spacy import displacy
-
-
-def no_of_tags(data):
-    tag_in_sent = {}
-    for tag in data["entity"]:
-        if tag != "":
-            if tag not in tag_in_sent:
-                tag_in_sent[tag] = 1
-            else:
-                tag_in_sent[tag] += 1
-    return tag_in_sent
-
-
-def list_ents(data_frame):
-    index = 0
-    ents_list = []
-    for word, ent in zip(data_frame['words'], data_frame['entity']):
-        if ent != "":
-            ent_dict = {"start": index, "end": index + len(word) + 1, "label": ent.upper()}
-            ents_list.append(ent_dict)
-        index = index + len(word) + 1
-    return ents_list
-
-
-def color_creator(color_data):
-    color_dict = {}
-    for ner in range(0, len(color_data), 2):
-        color_dict[color_data[ner]] = color_data[ner + 1]
-    return color_dict
-
-
-def options(data_frame):
-    option = {"ents": color_creator(data_frame).keys(), "colors": color_creator(data_frame)}
-    return option
-
-
-def tag_display(sent, tag_colors):
-    # for sent in df_list:
-    ex = {"text": ' '.join(sent['words']), "ents": list_ents(sent), "title": None}
-    displacy.render(ex, style="ent", manual=True, options=options(tag_colors["NER"]))
-
-
-def bubble_sentence(ls, tag_colors):
-    # for ls in data_frame:
-    tags_data = no_of_tags(ls)
-    tags_data = pd.DataFrame(tags_data.items(), columns=["Entities", "Counts"])
-    data = [
-        go.Scatter(x=tags_data["Entities"], y=tags_data["Counts"],
-                   mode='markers', marker=dict(color=list(color_creator(tag_colors["NER"]).values()),
-                                               size=tags_data["Counts"] * 40,
-                                               )
-                   )
-    ]
-    layout = go.Layout(title=f'Words :{ls.count(axis=0)["clean_words"]} Tags :{ls.count(axis=0)["clean_entity"]}',
-                       xaxis=dict(title='Tags'),
-                       yaxis=dict(title='Count'),
-                       hovermode="closest")
-    figure = go.Figure(data=data, layout=layout)
-    iplot(figure)
-
-
-def bubble_document(data_frame, tag_colors):
-    doc_list = []
-    for ls in data_frame:
-        doc_list.append(no_of_tags(ls))
-    doc_tags = dict(functools.reduce(operator.add, map(collections.Counter, doc_list)))
-    doc_data = pd.DataFrame(doc_tags.items(), columns=["Entities", "Counts"])
-    data = [
-        go.Scatter(x=doc_data["Entities"], y=doc_data["Counts"],
-                   mode='markers', marker=dict(color=list(color_creator(tag_colors["NER"]).values()),
-                                               size=doc_data["Counts"] * 15)
-                   )
-    ]
-    layout = go.Layout(title="Distribution of Tags in the Document", xaxis=dict(title='Tags'),
-                       yaxis=dict(title='Count'), hovermode="closest")
-    figure = go.Figure(data=data, layout=layout)
-    iplot(figure)
-
-
-def line_document(data_frame):
-    line_list = pd.DataFrame(columns=["sentence", "words", "tags", "words_to_tag"])
-    total_words, total_tags = 0, 0
-    for ls in data_frame:
-        line_list.loc[len(line_list) + 1] = [len(line_list) + 1, ls.count(axis=0)["clean_words"],
-                                             ls.count(axis=0)["clean_entity"],
-                                             f'{ls.count(axis=0)["clean_words"]} : {ls.count(axis=0)["clean_entity"]}']
-        total_tags += ls.count(axis=0)["clean_entity"]
-        total_words += ls.count(axis=0)["clean_words"]
-    line_list["words_tag"] = line_list["words"] / line_list["tags"]
-    fig = px.line(line_list, x="sentence", y="words_tag", markers=True, text="words_to_tag", template="plotly_dark",
-                  title=f'Total Words : {total_words} '
-                        f'Total Entities : {total_tags}', line_shape='vh')
-    # fig.show()
-    iplot(fig)
-
-
-def scatter_document(data_frame, tags_data):
-    fig_list = []
-    for sent, color in zip(data_frame, list(color_creator(tags_data["NER"]).values())):
-        tags_df = pd.DataFrame(tags_data["_ntags_"], columns=["entity"])
-        sent_tags_data = pd.DataFrame(no_of_tags(sent).items(), columns=["entity", "count"])
-        tags_df = pd.merge(left=tags_df, right=sent_tags_data, how="left", left_on=["entity"], right_on=["entity"])
-        tags_df["count"] = tags_df['count'].replace(np.NAN, '0', regex=True).astype(int)
-        data = [
-            go.Scatter(x=tags_df["entity"], y=tags_df["count"],
-                       mode='markers', marker=dict(color=color,
-                                                   size=tags_df["count"] * 25,
-                                                   )
-                       )
-        ]
-        layout = go.Layout(title=' '.join(sent["words"]), xaxis=dict(title='Tags'),
-                           yaxis=dict(title='Count'),
-                           hovermode="closest",
-                           template="plotly_dark")
-        figure = go.Figure(data=data, layout=layout)
-        fig_list.append(figure)
-    layout = go.Layout(title="Document Tag Distribution", xaxis=dict(title='Tags'),
-                       yaxis=dict(title='Count'),
-                       hovermode="closest",
-                       template="plotly_dark")
-    fig = go.Figure(data=sum((fig.data for fig in fig_list), ()), layout=layout)
-    # iplot(fig)
-    return fig
diff --git a/spaces/kelothu/gradiolangchainbotopenai/app.py b/spaces/kelothu/gradiolangchainbotopenai/app.py
deleted file mode 100644
index a362dcc7d0ddd1eee86961f1bc3db6d894fbd3d5..0000000000000000000000000000000000000000
--- a/spaces/kelothu/gradiolangchainbotopenai/app.py
+++ /dev/null
@@ -1,34 +0,0 @@
-import os
-import gradio as gr
-from langchain.chat_models import ChatOpenAI
-from langchain import LLMChain, PromptTemplate
-from langchain.memory import ConversationBufferMemory
-
-OPENAI_API_KEY=os.getenv('OPENAI_API_KEY')
-
-template = """You are a helpful assistant to answer all user queries.
-{chat_history}
-User: {user_message}
-Chatbot:"""
-
-prompt = PromptTemplate(
-    input_variables=["chat_history", "user_message"], template=template
-)
-
-memory = ConversationBufferMemory(memory_key="chat_history")
-
-llm_chain = LLMChain(
-    llm=ChatOpenAI(temperature='0.5', model_name="gpt-3.5-turbo"),
-    prompt=prompt,
-    verbose=True,
-    memory=memory,
-)
-
-def get_text_response(user_message,history):
-    response = llm_chain.predict(user_message = user_message)
-    return response
-
-demo = gr.ChatInterface(get_text_response)
-
-if __name__ == "__main__":
-    demo.launch() #To create a public link, set `share=True` in `launch()`. To enable errors and logs, set `debug=True` in `launch()`.
diff --git a/spaces/keras-dreambooth/dreambooth-bored-ape/README.md b/spaces/keras-dreambooth/dreambooth-bored-ape/README.md
deleted file mode 100644
index 2f73f2f21cbbbf35e63e33164ffffc89b06148a6..0000000000000000000000000000000000000000
--- a/spaces/keras-dreambooth/dreambooth-bored-ape/README.md
+++ /dev/null
@@ -1,18 +0,0 @@
----
-title: Dreambooth Bored Ape
-emoji: 🐵
-colorFrom: red
-colorTo: pink
-sdk: gradio
-sdk_version: 3.23.0
-app_file: app.py
-pinned: false
-license: creativeml-openrail-m
-tags:
-  - keras-dreambooth
-  - scifi
----
-
-Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
-
----
diff --git a/spaces/keras-io/PointNet-Classification/app.py b/spaces/keras-io/PointNet-Classification/app.py
deleted file mode 100644
index 45cabd9f911b040f46b97e3fe1e123c5dbd15d71..0000000000000000000000000000000000000000
--- a/spaces/keras-io/PointNet-Classification/app.py
+++ /dev/null
@@ -1,114 +0,0 @@
-import math
-import numpy as np
-import pandas as pd
-
-import os
-import glob
-import trimesh
-import tensorflow as tf
-from tensorflow import keras
-from tensorflow.keras import layers
-from matplotlib import pyplot as plt
-
-import gradio as gr
-from huggingface_hub import from_pretrained_keras
-
-
-
-def conv_bn(x, filters):
-    x = layers.Conv1D(filters, kernel_size=1, padding="valid")(x)
-    x = layers.BatchNormalization(momentum=0.0)(x)
-    return layers.Activation("relu")(x)
-
-
-def dense_bn(x, filters):
-    x = layers.Dense(filters)(x)
-    x = layers.BatchNormalization(momentum=0.0)(x)
-    return layers.Activation("relu")(x)
-
-# @keras.utils.register_keras_serializable
-class OrthogonalRegularizer(keras.regularizers.Regularizer):
-    def __init__(self, num_features, l2reg=0.001, **kwarg):
-        super(OrthogonalRegularizer, self).__init__(**kwargs)
-        self.num_features = num_features
-        self.l2reg = l2reg
-        self.eye = tf.eye(num_features)
-
-    def __call__(self, x):
-        x = tf.reshape(x, (-1, self.num_features, self.num_features))
-        xxt = tf.tensordot(x, x, axes=(2, 2))
-        xxt = tf.reshape(xxt, (-1, self.num_features, self.num_features))
-        return tf.reduce_sum(self.l2reg * tf.square(xxt - self.eye))
-
-    def get_config(self):
-        return {'l2reg': float(self.l2reg)}
-
-def tnet(inputs, num_features):
-
-    # Initalise bias as the indentity matrix
-    bias = keras.initializers.Constant(np.eye(num_features).flatten())
-    reg = OrthogonalRegularizer(num_features)
-
-    x = conv_bn(inputs, 32)
-    x = conv_bn(x, 64)
-    x = conv_bn(x, 512)
-    x = layers.GlobalMaxPooling1D()(x)
-    x = dense_bn(x, 256)
-    x = dense_bn(x, 128)
-    x = layers.Dense(
-        num_features * num_features,
-        kernel_initializer="zeros",
-        bias_initializer=bias,
-        activity_regularizer=reg,
-    )(x)
-    feat_T = layers.Reshape((num_features, num_features))(x)
-    # Apply affine transformation to input features
-    return layers.Dot(axes=(2, 1))([inputs, feat_T])
-
-EXAMPLES_PATH = 'examples'
-model = from_pretrained_keras('keras-io/PointNet')
-
-CLASS_MAP = {0: 'chair',
- 1: 'sofa',
- 2: 'desk',
- 3: 'bed',
- 4: 'dresser',
- 5: 'night_stand',
- 6: 'toilet',
- 7: 'bathtub',
- 8: 'monitor',
- 9: 'table'}
-
-def infer(img_path):
-    mesh = trimesh.load(img_path.name)
-    points = mesh.sample(2048)
-    points = np.expand_dims(np.asarray(points), axis=0)
-
-    # run test data through model
-    preds = model.predict(points)
-    preds = tf.math.argmax(preds, -1)
-
-    # plot points with predicted class and label
-    fig = plt.figure(figsize=(4, 6))
-    ax = fig.add_subplot(2, 1, 1, projection="3d")
-    ax.scatter(points[0, :, 0], points[0, :, 1], points[0, :, 2])
-    ax.set_title(f"This is {CLASS_MAP[preds[0].numpy()]}")
-    ax.set_axis_off()
-    # plt.imshow(image)
-    return plt.gcf()
-
-# get the inputs
-inputs = gr.File(type = 'file')
-
-# the app outputs two segmented images
-output = gr.Plot()
-
-
-# it's good practice to pass examples, description and a title to guide users
-title = 'PointNet Classification and Segmentation'
-description = 'Classify images using point cloud Segmentation'
-article = "Author: <a href=\"https://huggingface.co/geninhu\">Nhu Hoang</a>. "
-examples = [f'{EXAMPLES_PATH}/{f}' for f in os.listdir(EXAMPLES_PATH)]
-
-gr.Interface(infer, inputs, output, examples= examples, allow_flagging='never', cache_examples=False,
-             title=title, description=description, article=article, live=False).launch(enable_queue=False, debug=True, inbrowser=False)
diff --git a/spaces/keremberke/construction-safety-object-detection/README.md b/spaces/keremberke/construction-safety-object-detection/README.md
deleted file mode 100644
index e26673c3c6de21657113e0dc4b7296b7738b1b14..0000000000000000000000000000000000000000
--- a/spaces/keremberke/construction-safety-object-detection/README.md
+++ /dev/null
@@ -1,12 +0,0 @@
----
-title: Construction Safety Object Detection
-emoji: 🎮
-colorFrom: red
-colorTo: gray
-sdk: gradio
-sdk_version: 3.15.0
-app_file: app.py
-pinned: false
----
-
-Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
diff --git a/spaces/kira4424/Tacotron-zero-short-voice-clone/vocoder_preprocess.py b/spaces/kira4424/Tacotron-zero-short-voice-clone/vocoder_preprocess.py
deleted file mode 100644
index 95f9e5a0f80edc566cfb31bb77736a1c58573d47..0000000000000000000000000000000000000000
--- a/spaces/kira4424/Tacotron-zero-short-voice-clone/vocoder_preprocess.py
+++ /dev/null
@@ -1,59 +0,0 @@
-from synthesizer.synthesize import run_synthesis
-from synthesizer.hparams import hparams
-from utils.argutils import print_args
-import argparse
-import os
-
-
-if __name__ == "__main__":
-    class MyFormatter(argparse.ArgumentDefaultsHelpFormatter, argparse.RawDescriptionHelpFormatter):
-        pass
-    
-    parser = argparse.ArgumentParser(
-        description="Creates ground-truth aligned (GTA) spectrograms from the vocoder.",
-        formatter_class=MyFormatter
-    )
-    parser.add_argument("datasets_root", type=str, help=\
-        "Path to the directory containing your SV2TTS directory. If you specify both --in_dir and "
-        "--out_dir, this argument won't be used.")
-    parser.add_argument("-m", "--model_dir", type=str, 
-                        default="synthesizer/saved_models/mandarin/", help=\
-        "Path to the pretrained model directory.")
-    parser.add_argument("-i", "--in_dir", type=str, default=argparse.SUPPRESS, help= \
-        "Path to the synthesizer directory that contains the mel spectrograms, the wavs and the "
-        "embeds. Defaults to  <datasets_root>/SV2TTS/synthesizer/.")
-    parser.add_argument("-o", "--out_dir", type=str, default=argparse.SUPPRESS, help= \
-        "Path to the output vocoder directory that will contain the ground truth aligned mel "
-        "spectrograms. Defaults to <datasets_root>/SV2TTS/vocoder/.")
-    parser.add_argument("--hparams", default="",
-                        help="Hyperparameter overrides as a comma-separated list of name=value "
-                             "pairs")
-    parser.add_argument("--no_trim", action="store_true", help=\
-        "Preprocess audio without trimming silences (not recommended).")
-    parser.add_argument("--cpu", action="store_true", help=\
-        "If True, processing is done on CPU, even when a GPU is available.")
-    args = parser.parse_args()
-    print_args(args, parser)
-    modified_hp = hparams.parse(args.hparams)
-    
-    if not hasattr(args, "in_dir"):
-        args.in_dir = os.path.join(args.datasets_root, "SV2TTS", "synthesizer")
-    if not hasattr(args, "out_dir"):
-        args.out_dir = os.path.join(args.datasets_root, "SV2TTS", "vocoder")
-
-    if args.cpu:
-        # Hide GPUs from Pytorch to force CPU processing
-        os.environ["CUDA_VISIBLE_DEVICES"] = ""
-    
-    # Verify webrtcvad is available
-    if not args.no_trim:
-        try:
-            import webrtcvad
-        except:
-            raise ModuleNotFoundError("Package 'webrtcvad' not found. This package enables "
-                "noise removal and is recommended. Please install and try again. If installation fails, "
-                "use --no_trim to disable this error message.")
-    del args.no_trim
-
-    run_synthesis(args.in_dir, args.out_dir, args.model_dir, modified_hp)
-
diff --git a/spaces/koajoel/PolyFormer/data/base_dataset.py b/spaces/koajoel/PolyFormer/data/base_dataset.py
deleted file mode 100644
index a2e5897991faa40ba09117edd4ba1a5da16bf416..0000000000000000000000000000000000000000
--- a/spaces/koajoel/PolyFormer/data/base_dataset.py
+++ /dev/null
@@ -1,84 +0,0 @@
-# ------------------------------------------------------------------------
-# Modified from OFA (https://github.com/OFA-Sys/OFA)
-# Copyright 2022 The OFA-Sys Team. 
-# All rights reserved.
-# This source code is licensed under the Apache 2.0 license 
-# found in the LICENSE file in the root directory.
-# ------------------------------------------------------------------------
-# Modifications Copyright Amazon.com, Inc. or its affiliates. All Rights Reserved.
-# SPDX-License-Identifier: Apache-2.0
-
-import logging
-import re
-import torch.utils.data
-from fairseq.data import FairseqDataset
-
-logger = logging.getLogger(__name__)
-
-
-class BaseDataset(FairseqDataset):
-    def __init__(self, split, dataset, bpe, src_dict, tgt_dict):
-        self.split = split
-        self.dataset = dataset
-        self.bpe = bpe
-        self.src_dict = src_dict
-        self.tgt_dict = tgt_dict
-
-        self.bos = src_dict.bos()
-        self.eos = src_dict.eos()
-        self.pad = src_dict.pad()
-        self.bos_item = torch.LongTensor([self.bos])
-        self.eos_item = torch.LongTensor([self.eos])
-
-    def __len__(self):
-        return len(self.dataset)
-
-    def encode_text(self, text, length=None, append_bos=False, append_eos=False, use_bpe=True):
-        s = self.tgt_dict.encode_line(
-            line=self.bpe.encode(text) if use_bpe else text,
-            add_if_not_exist=False,
-            append_eos=False
-        ).long()
-        if length is not None:
-            s = s[:length]
-        if append_bos:
-            s = torch.cat([self.bos_item, s])
-        if append_eos:
-            s = torch.cat([s, self.eos_item])
-        return s
-
-    def pre_question(self, question, max_ques_words):
-        question = question.lower().lstrip(",.!?*#:;~").replace('-', ' ').replace('/', ' ')
-
-        question = re.sub(
-            r"\s{2,}",
-            ' ',
-            question,
-        )
-        question = question.rstrip('\n')
-        question = question.strip(' ')
-
-        # truncate question
-        question_words = question.split(' ')
-        if len(question_words) > max_ques_words:
-            question = ' '.join(question_words[:max_ques_words])
-
-        return question
-
-    def pre_caption(self, caption, max_words):
-        caption = caption.lower().lstrip(",.!?*#:;~").replace('-', ' ').replace('/', ' ').replace('<person>', 'person')
-
-        caption = re.sub(
-            r"\s{2,}",
-            ' ',
-            caption,
-        )
-        caption = caption.rstrip('\n')
-        caption = caption.strip(' ')
-
-        # truncate caption
-        caption_words = caption.split(' ')
-        if len(caption_words) > max_words:
-            caption = ' '.join(caption_words[:max_words])
-
-        return caption
diff --git a/spaces/koajoel/PolyFormer/fairseq/examples/m2m_100/process_data/remove_too_much_punc.py b/spaces/koajoel/PolyFormer/fairseq/examples/m2m_100/process_data/remove_too_much_punc.py
deleted file mode 100644
index 6c280de2403daffab477ac88e2008a68b9e61ff0..0000000000000000000000000000000000000000
--- a/spaces/koajoel/PolyFormer/fairseq/examples/m2m_100/process_data/remove_too_much_punc.py
+++ /dev/null
@@ -1,36 +0,0 @@
-import gzip
-import argparse
-from string import punctuation
-
-def len_no_punc(s, punc):
-    return len([ch for ch in s if ch in punc])
-
-def filter_overpunc(len_npunc, len_sen):
-    return len_npunc < 0.5*len_sen
-
-def main(args):
-    punc = punctuation + "—|–"
-    print('Processing file {}'.format(args.input))
-    with gzip.open(args.input, 'rt', encoding=args.encoding) as tsv:
-        with open(args.bitext + '.' + args.src_lang, 'wt', encoding=args.encoding) as fsrc:
-            with open(args.bitext + '.' + args.tgt_lang, 'wt', encoding=args.encoding) as ftgt:
-                line = tsv.readline()
-                fields = line.split('\t')
-
-                src, tgt = fields[1], fields[2]
-
-                nchar_npunc_src = len_no_punc(src, punc)
-                nchar_npunc_tgt = len_no_punc(tgt, punc)
-
-                if filter_overpunc(nchar_npunc_src, len(src)) and filter_overpunc(nchar_npunc_tgt, len(tgt)):
-                    fsrc.write(src.strip() + '\n')
-                    ftgt.write(tgt.strip() + '\n')
-
-if __name__ == '__main__':
-    parser = argparse.ArgumentParser()
-    parser.add_argument("--input", required=True, type=str)
-    parser.add_argument('--encoding', default='utf-8', help='character encoding for input/output')
-    parser.add_argument('--bitext', type=str, required=True, help='language direction')
-    parser.add_argument('--src-lang', type=str, required=True, help='Source language')
-    parser.add_argument('--tgt-lang', type=str, required=True, help='Target language')
-    main(parser.parse_args())
diff --git a/spaces/konverner/deep-voice-cloning/src/deep_voice_cloning/transcriber/model.py b/spaces/konverner/deep-voice-cloning/src/deep_voice_cloning/transcriber/model.py
deleted file mode 100644
index 436c166149a994b173ca1178e8f8a7f461c9cb12..0000000000000000000000000000000000000000
--- a/spaces/konverner/deep-voice-cloning/src/deep_voice_cloning/transcriber/model.py
+++ /dev/null
@@ -1,22 +0,0 @@
-import os
-import json
-
-import numpy as np
-import torch
-from transformers import Wav2Vec2Processor, Wav2Vec2ForCTC
-
-
-class TranscriberModel:
-    def __init__(self, lang: str = 'en'):
-        with open(os.path.join(os.path.dirname(__file__), 'config.json')) as f:
-            config = json.load(f)
-        self.processor = Wav2Vec2Processor.from_pretrained(config['language_model_names'][lang])
-        self.model = Wav2Vec2ForCTC.from_pretrained(config['language_model_names'][lang])
-        self.device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
-
-    def forward(self, speech_array: np.array, sampling_rate: int = 16000) -> str:
-        model_input = self.processor(speech_array, sampling_rate=sampling_rate, return_tensors="pt", padding=True)
-        with torch.no_grad():
-            logits = self.model(model_input.input_values, attention_mask=model_input.attention_mask).logits
-            predicted_ids = torch.argmax(logits, dim=-1)
-        return self.processor.batch_decode(predicted_ids)
diff --git a/spaces/kukuhtw/VToonify/vtoonify/model/stylegan/dataset.py b/spaces/kukuhtw/VToonify/vtoonify/model/stylegan/dataset.py
deleted file mode 100644
index 7713ea2f8bc94d202d2dfbe830af3cb96b1e803d..0000000000000000000000000000000000000000
--- a/spaces/kukuhtw/VToonify/vtoonify/model/stylegan/dataset.py
+++ /dev/null
@@ -1,40 +0,0 @@
-from io import BytesIO
-
-import lmdb
-from PIL import Image
-from torch.utils.data import Dataset
-
-
-class MultiResolutionDataset(Dataset):
-    def __init__(self, path, transform, resolution=256):
-        self.env = lmdb.open(
-            path,
-            max_readers=32,
-            readonly=True,
-            lock=False,
-            readahead=False,
-            meminit=False,
-        )
-
-        if not self.env:
-            raise IOError('Cannot open lmdb dataset', path)
-
-        with self.env.begin(write=False) as txn:
-            self.length = int(txn.get('length'.encode('utf-8')).decode('utf-8'))
-
-        self.resolution = resolution
-        self.transform = transform
-
-    def __len__(self):
-        return self.length
-
-    def __getitem__(self, index):
-        with self.env.begin(write=False) as txn:
-            key = f'{self.resolution}-{str(index).zfill(5)}'.encode('utf-8')
-            img_bytes = txn.get(key)
-
-        buffer = BytesIO(img_bytes)
-        img = Image.open(buffer)
-        img = self.transform(img)
-
-        return img
diff --git a/spaces/ky2k/Toxicity_Classifier_POC/.venv/lib/python3.9/site-packages/PIL/ImageMath.py b/spaces/ky2k/Toxicity_Classifier_POC/.venv/lib/python3.9/site-packages/PIL/ImageMath.py
deleted file mode 100644
index ac7d36b698c2ec9839d8a771734c9f730f701534..0000000000000000000000000000000000000000
--- a/spaces/ky2k/Toxicity_Classifier_POC/.venv/lib/python3.9/site-packages/PIL/ImageMath.py
+++ /dev/null
@@ -1,263 +0,0 @@
-#
-# The Python Imaging Library
-# $Id$
-#
-# a simple math add-on for the Python Imaging Library
-#
-# History:
-# 1999-02-15 fl   Original PIL Plus release
-# 2005-05-05 fl   Simplified and cleaned up for PIL 1.1.6
-# 2005-09-12 fl   Fixed int() and float() for Python 2.4.1
-#
-# Copyright (c) 1999-2005 by Secret Labs AB
-# Copyright (c) 2005 by Fredrik Lundh
-#
-# See the README file for information on usage and redistribution.
-#
-
-import builtins
-
-from . import Image, _imagingmath
-
-
-def _isconstant(v):
-    return isinstance(v, (int, float))
-
-
-class _Operand:
-    """Wraps an image operand, providing standard operators"""
-
-    def __init__(self, im):
-        self.im = im
-
-    def __fixup(self, im1):
-        # convert image to suitable mode
-        if isinstance(im1, _Operand):
-            # argument was an image.
-            if im1.im.mode in ("1", "L"):
-                return im1.im.convert("I")
-            elif im1.im.mode in ("I", "F"):
-                return im1.im
-            else:
-                msg = f"unsupported mode: {im1.im.mode}"
-                raise ValueError(msg)
-        else:
-            # argument was a constant
-            if _isconstant(im1) and self.im.mode in ("1", "L", "I"):
-                return Image.new("I", self.im.size, im1)
-            else:
-                return Image.new("F", self.im.size, im1)
-
-    def apply(self, op, im1, im2=None, mode=None):
-        im1 = self.__fixup(im1)
-        if im2 is None:
-            # unary operation
-            out = Image.new(mode or im1.mode, im1.size, None)
-            im1.load()
-            try:
-                op = getattr(_imagingmath, op + "_" + im1.mode)
-            except AttributeError as e:
-                msg = f"bad operand type for '{op}'"
-                raise TypeError(msg) from e
-            _imagingmath.unop(op, out.im.id, im1.im.id)
-        else:
-            # binary operation
-            im2 = self.__fixup(im2)
-            if im1.mode != im2.mode:
-                # convert both arguments to floating point
-                if im1.mode != "F":
-                    im1 = im1.convert("F")
-                if im2.mode != "F":
-                    im2 = im2.convert("F")
-            if im1.size != im2.size:
-                # crop both arguments to a common size
-                size = (min(im1.size[0], im2.size[0]), min(im1.size[1], im2.size[1]))
-                if im1.size != size:
-                    im1 = im1.crop((0, 0) + size)
-                if im2.size != size:
-                    im2 = im2.crop((0, 0) + size)
-            out = Image.new(mode or im1.mode, im1.size, None)
-            im1.load()
-            im2.load()
-            try:
-                op = getattr(_imagingmath, op + "_" + im1.mode)
-            except AttributeError as e:
-                msg = f"bad operand type for '{op}'"
-                raise TypeError(msg) from e
-            _imagingmath.binop(op, out.im.id, im1.im.id, im2.im.id)
-        return _Operand(out)
-
-    # unary operators
-    def __bool__(self):
-        # an image is "true" if it contains at least one non-zero pixel
-        return self.im.getbbox() is not None
-
-    def __abs__(self):
-        return self.apply("abs", self)
-
-    def __pos__(self):
-        return self
-
-    def __neg__(self):
-        return self.apply("neg", self)
-
-    # binary operators
-    def __add__(self, other):
-        return self.apply("add", self, other)
-
-    def __radd__(self, other):
-        return self.apply("add", other, self)
-
-    def __sub__(self, other):
-        return self.apply("sub", self, other)
-
-    def __rsub__(self, other):
-        return self.apply("sub", other, self)
-
-    def __mul__(self, other):
-        return self.apply("mul", self, other)
-
-    def __rmul__(self, other):
-        return self.apply("mul", other, self)
-
-    def __truediv__(self, other):
-        return self.apply("div", self, other)
-
-    def __rtruediv__(self, other):
-        return self.apply("div", other, self)
-
-    def __mod__(self, other):
-        return self.apply("mod", self, other)
-
-    def __rmod__(self, other):
-        return self.apply("mod", other, self)
-
-    def __pow__(self, other):
-        return self.apply("pow", self, other)
-
-    def __rpow__(self, other):
-        return self.apply("pow", other, self)
-
-    # bitwise
-    def __invert__(self):
-        return self.apply("invert", self)
-
-    def __and__(self, other):
-        return self.apply("and", self, other)
-
-    def __rand__(self, other):
-        return self.apply("and", other, self)
-
-    def __or__(self, other):
-        return self.apply("or", self, other)
-
-    def __ror__(self, other):
-        return self.apply("or", other, self)
-
-    def __xor__(self, other):
-        return self.apply("xor", self, other)
-
-    def __rxor__(self, other):
-        return self.apply("xor", other, self)
-
-    def __lshift__(self, other):
-        return self.apply("lshift", self, other)
-
-    def __rshift__(self, other):
-        return self.apply("rshift", self, other)
-
-    # logical
-    def __eq__(self, other):
-        return self.apply("eq", self, other)
-
-    def __ne__(self, other):
-        return self.apply("ne", self, other)
-
-    def __lt__(self, other):
-        return self.apply("lt", self, other)
-
-    def __le__(self, other):
-        return self.apply("le", self, other)
-
-    def __gt__(self, other):
-        return self.apply("gt", self, other)
-
-    def __ge__(self, other):
-        return self.apply("ge", self, other)
-
-
-# conversions
-def imagemath_int(self):
-    return _Operand(self.im.convert("I"))
-
-
-def imagemath_float(self):
-    return _Operand(self.im.convert("F"))
-
-
-# logical
-def imagemath_equal(self, other):
-    return self.apply("eq", self, other, mode="I")
-
-
-def imagemath_notequal(self, other):
-    return self.apply("ne", self, other, mode="I")
-
-
-def imagemath_min(self, other):
-    return self.apply("min", self, other)
-
-
-def imagemath_max(self, other):
-    return self.apply("max", self, other)
-
-
-def imagemath_convert(self, mode):
-    return _Operand(self.im.convert(mode))
-
-
-ops = {}
-for k, v in list(globals().items()):
-    if k[:10] == "imagemath_":
-        ops[k[10:]] = v
-
-
-def eval(expression, _dict={}, **kw):
-    """
-    Evaluates an image expression.
-
-    :param expression: A string containing a Python-style expression.
-    :param options: Values to add to the evaluation context.  You
-                    can either use a dictionary, or one or more keyword
-                    arguments.
-    :return: The evaluated expression. This is usually an image object, but can
-             also be an integer, a floating point value, or a pixel tuple,
-             depending on the expression.
-    """
-
-    # build execution namespace
-    args = ops.copy()
-    args.update(_dict)
-    args.update(kw)
-    for k, v in list(args.items()):
-        if hasattr(v, "im"):
-            args[k] = _Operand(v)
-
-    compiled_code = compile(expression, "<string>", "eval")
-
-    def scan(code):
-        for const in code.co_consts:
-            if type(const) == type(compiled_code):
-                scan(const)
-
-        for name in code.co_names:
-            if name not in args and name != "abs":
-                msg = f"'{name}' not allowed"
-                raise ValueError(msg)
-
-    scan(compiled_code)
-    out = builtins.eval(expression, {"__builtins": {"abs": abs}}, args)
-    try:
-        return out.im
-    except AttributeError:
-        return out
diff --git a/spaces/ky2k/Toxicity_Classifier_POC/.venv/lib/python3.9/site-packages/fastapi/concurrency.py b/spaces/ky2k/Toxicity_Classifier_POC/.venv/lib/python3.9/site-packages/fastapi/concurrency.py
deleted file mode 100644
index 31b878d5df8a5d1c9687a8fdbf2f377e844d7f48..0000000000000000000000000000000000000000
--- a/spaces/ky2k/Toxicity_Classifier_POC/.venv/lib/python3.9/site-packages/fastapi/concurrency.py
+++ /dev/null
@@ -1,40 +0,0 @@
-from contextlib import AsyncExitStack as AsyncExitStack  # noqa
-from contextlib import asynccontextmanager as asynccontextmanager
-from typing import AsyncGenerator, ContextManager, TypeVar
-
-import anyio
-from anyio import CapacityLimiter
-from starlette.concurrency import iterate_in_threadpool as iterate_in_threadpool  # noqa
-from starlette.concurrency import run_in_threadpool as run_in_threadpool  # noqa
-from starlette.concurrency import (  # noqa
-    run_until_first_complete as run_until_first_complete,
-)
-
-_T = TypeVar("_T")
-
-
-@asynccontextmanager
-async def contextmanager_in_threadpool(
-    cm: ContextManager[_T],
-) -> AsyncGenerator[_T, None]:
-    # blocking __exit__ from running waiting on a free thread
-    # can create race conditions/deadlocks if the context manager itself
-    # has it's own internal pool (e.g. a database connection pool)
-    # to avoid this we let __exit__ run without a capacity limit
-    # since we're creating a new limiter for each call, any non-zero limit
-    # works (1 is arbitrary)
-    exit_limiter = CapacityLimiter(1)
-    try:
-        yield await run_in_threadpool(cm.__enter__)
-    except Exception as e:
-        ok = bool(
-            await anyio.to_thread.run_sync(
-                cm.__exit__, type(e), e, None, limiter=exit_limiter
-            )
-        )
-        if not ok:
-            raise e
-    else:
-        await anyio.to_thread.run_sync(
-            cm.__exit__, None, None, None, limiter=exit_limiter
-        )
diff --git a/spaces/ky2k/Toxicity_Classifier_POC/.venv/lib/python3.9/site-packages/fontTools/merge/unicode.py b/spaces/ky2k/Toxicity_Classifier_POC/.venv/lib/python3.9/site-packages/fontTools/merge/unicode.py
deleted file mode 100644
index 65ae6c49295ec25ce6e473e9a81e8a191c912d7f..0000000000000000000000000000000000000000
--- a/spaces/ky2k/Toxicity_Classifier_POC/.venv/lib/python3.9/site-packages/fontTools/merge/unicode.py
+++ /dev/null
@@ -1,78 +0,0 @@
-# Copyright 2021 Behdad Esfahbod. All Rights Reserved.
-
-
-def is_Default_Ignorable(u):
-    # http://www.unicode.org/reports/tr44/#Default_Ignorable_Code_Point
-    #
-    # TODO Move me to unicodedata module and autogenerate.
-    #
-    # Unicode 14.0:
-    # $ grep '; Default_Ignorable_Code_Point ' DerivedCoreProperties.txt | sed 's/;.*#/#/'
-    # 00AD          # Cf       SOFT HYPHEN
-    # 034F          # Mn       COMBINING GRAPHEME JOINER
-    # 061C          # Cf       ARABIC LETTER MARK
-    # 115F..1160    # Lo   [2] HANGUL CHOSEONG FILLER..HANGUL JUNGSEONG FILLER
-    # 17B4..17B5    # Mn   [2] KHMER VOWEL INHERENT AQ..KHMER VOWEL INHERENT AA
-    # 180B..180D    # Mn   [3] MONGOLIAN FREE VARIATION SELECTOR ONE..MONGOLIAN FREE VARIATION SELECTOR THREE
-    # 180E          # Cf       MONGOLIAN VOWEL SEPARATOR
-    # 180F          # Mn       MONGOLIAN FREE VARIATION SELECTOR FOUR
-    # 200B..200F    # Cf   [5] ZERO WIDTH SPACE..RIGHT-TO-LEFT MARK
-    # 202A..202E    # Cf   [5] LEFT-TO-RIGHT EMBEDDING..RIGHT-TO-LEFT OVERRIDE
-    # 2060..2064    # Cf   [5] WORD JOINER..INVISIBLE PLUS
-    # 2065          # Cn       <reserved-2065>
-    # 2066..206F    # Cf  [10] LEFT-TO-RIGHT ISOLATE..NOMINAL DIGIT SHAPES
-    # 3164          # Lo       HANGUL FILLER
-    # FE00..FE0F    # Mn  [16] VARIATION SELECTOR-1..VARIATION SELECTOR-16
-    # FEFF          # Cf       ZERO WIDTH NO-BREAK SPACE
-    # FFA0          # Lo       HALFWIDTH HANGUL FILLER
-    # FFF0..FFF8    # Cn   [9] <reserved-FFF0>..<reserved-FFF8>
-    # 1BCA0..1BCA3  # Cf   [4] SHORTHAND FORMAT LETTER OVERLAP..SHORTHAND FORMAT UP STEP
-    # 1D173..1D17A  # Cf   [8] MUSICAL SYMBOL BEGIN BEAM..MUSICAL SYMBOL END PHRASE
-    # E0000         # Cn       <reserved-E0000>
-    # E0001         # Cf       LANGUAGE TAG
-    # E0002..E001F  # Cn  [30] <reserved-E0002>..<reserved-E001F>
-    # E0020..E007F  # Cf  [96] TAG SPACE..CANCEL TAG
-    # E0080..E00FF  # Cn [128] <reserved-E0080>..<reserved-E00FF>
-    # E0100..E01EF  # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256
-    # E01F0..E0FFF  # Cn [3600] <reserved-E01F0>..<reserved-E0FFF>
-    return (
-        u == 0x00AD
-        or u == 0x034F  # Cf       SOFT HYPHEN
-        or u == 0x061C  # Mn       COMBINING GRAPHEME JOINER
-        or 0x115F <= u <= 0x1160  # Cf       ARABIC LETTER MARK
-        or 0x17B4  # Lo   [2] HANGUL CHOSEONG FILLER..HANGUL JUNGSEONG FILLER
-        <= u
-        <= 0x17B5
-        or 0x180B  # Mn   [2] KHMER VOWEL INHERENT AQ..KHMER VOWEL INHERENT AA
-        <= u
-        <= 0x180D
-        or u  # Mn   [3] MONGOLIAN FREE VARIATION SELECTOR ONE..MONGOLIAN FREE VARIATION SELECTOR THREE
-        == 0x180E
-        or u == 0x180F  # Cf       MONGOLIAN VOWEL SEPARATOR
-        or 0x200B <= u <= 0x200F  # Mn       MONGOLIAN FREE VARIATION SELECTOR FOUR
-        or 0x202A <= u <= 0x202E  # Cf   [5] ZERO WIDTH SPACE..RIGHT-TO-LEFT MARK
-        or 0x2060  # Cf   [5] LEFT-TO-RIGHT EMBEDDING..RIGHT-TO-LEFT OVERRIDE
-        <= u
-        <= 0x2064
-        or u == 0x2065  # Cf   [5] WORD JOINER..INVISIBLE PLUS
-        or 0x2066 <= u <= 0x206F  # Cn       <reserved-2065>
-        or u == 0x3164  # Cf  [10] LEFT-TO-RIGHT ISOLATE..NOMINAL DIGIT SHAPES
-        or 0xFE00 <= u <= 0xFE0F  # Lo       HANGUL FILLER
-        or u == 0xFEFF  # Mn  [16] VARIATION SELECTOR-1..VARIATION SELECTOR-16
-        or u == 0xFFA0  # Cf       ZERO WIDTH NO-BREAK SPACE
-        or 0xFFF0 <= u <= 0xFFF8  # Lo       HALFWIDTH HANGUL FILLER
-        or 0x1BCA0 <= u <= 0x1BCA3  # Cn   [9] <reserved-FFF0>..<reserved-FFF8>
-        or 0x1D173  # Cf   [4] SHORTHAND FORMAT LETTER OVERLAP..SHORTHAND FORMAT UP STEP
-        <= u
-        <= 0x1D17A
-        or u == 0xE0000  # Cf   [8] MUSICAL SYMBOL BEGIN BEAM..MUSICAL SYMBOL END PHRASE
-        or u == 0xE0001  # Cn       <reserved-E0000>
-        or 0xE0002 <= u <= 0xE001F  # Cf       LANGUAGE TAG
-        or 0xE0020 <= u <= 0xE007F  # Cn  [30] <reserved-E0002>..<reserved-E001F>
-        or 0xE0080 <= u <= 0xE00FF  # Cf  [96] TAG SPACE..CANCEL TAG
-        or 0xE0100 <= u <= 0xE01EF  # Cn [128] <reserved-E0080>..<reserved-E00FF>
-        or 0xE01F0  # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256
-        <= u
-        <= 0xE0FFF
-        or False  # Cn [3600] <reserved-E01F0>..<reserved-E0FFF>
-    )
diff --git a/spaces/ky2k/Toxicity_Classifier_POC/.venv/lib/python3.9/site-packages/matplotlib/testing/jpl_units/Epoch.py b/spaces/ky2k/Toxicity_Classifier_POC/.venv/lib/python3.9/site-packages/matplotlib/testing/jpl_units/Epoch.py
deleted file mode 100644
index 3808663056e7687f742e56d0392486ae287d5a58..0000000000000000000000000000000000000000
--- a/spaces/ky2k/Toxicity_Classifier_POC/.venv/lib/python3.9/site-packages/matplotlib/testing/jpl_units/Epoch.py
+++ /dev/null
@@ -1,211 +0,0 @@
-"""Epoch module."""
-
-import functools
-import operator
-import math
-import datetime as DT
-
-from matplotlib import _api
-from matplotlib.dates import date2num
-
-
-class Epoch:
-    # Frame conversion offsets in seconds
-    # t(TO) = t(FROM) + allowed[ FROM ][ TO ]
-    allowed = {
-        "ET": {
-            "UTC": +64.1839,
-            },
-        "UTC": {
-            "ET": -64.1839,
-            },
-        }
-
-    def __init__(self, frame, sec=None, jd=None, daynum=None, dt=None):
-        """
-        Create a new Epoch object.
-
-        Build an epoch 1 of 2 ways:
-
-        Using seconds past a Julian date:
-        #   Epoch('ET', sec=1e8, jd=2451545)
-
-        or using a matplotlib day number
-        #   Epoch('ET', daynum=730119.5)
-
-        = ERROR CONDITIONS
-        - If the input units are not in the allowed list, an error is thrown.
-
-        = INPUT VARIABLES
-        - frame     The frame of the epoch.  Must be 'ET' or 'UTC'
-        - sec        The number of seconds past the input JD.
-        - jd         The Julian date of the epoch.
-        - daynum    The matplotlib day number of the epoch.
-        - dt         A python datetime instance.
-        """
-        if ((sec is None and jd is not None) or
-                (sec is not None and jd is None) or
-                (daynum is not None and
-                 (sec is not None or jd is not None)) or
-                (daynum is None and dt is None and
-                 (sec is None or jd is None)) or
-                (daynum is not None and dt is not None) or
-                (dt is not None and (sec is not None or jd is not None)) or
-                ((dt is not None) and not isinstance(dt, DT.datetime))):
-            raise ValueError(
-                "Invalid inputs.  Must enter sec and jd together, "
-                "daynum by itself, or dt (must be a python datetime).\n"
-                "Sec = %s\n"
-                "JD  = %s\n"
-                "dnum= %s\n"
-                "dt  = %s" % (sec, jd, daynum, dt))
-
-        _api.check_in_list(self.allowed, frame=frame)
-        self._frame = frame
-
-        if dt is not None:
-            daynum = date2num(dt)
-
-        if daynum is not None:
-            # 1-JAN-0001 in JD = 1721425.5
-            jd = float(daynum) + 1721425.5
-            self._jd = math.floor(jd)
-            self._seconds = (jd - self._jd) * 86400.0
-
-        else:
-            self._seconds = float(sec)
-            self._jd = float(jd)
-
-            # Resolve seconds down to [ 0, 86400)
-            deltaDays = math.floor(self._seconds / 86400)
-            self._jd += deltaDays
-            self._seconds -= deltaDays * 86400.0
-
-    def convert(self, frame):
-        if self._frame == frame:
-            return self
-
-        offset = self.allowed[self._frame][frame]
-
-        return Epoch(frame, self._seconds + offset, self._jd)
-
-    def frame(self):
-        return self._frame
-
-    def julianDate(self, frame):
-        t = self
-        if frame != self._frame:
-            t = self.convert(frame)
-
-        return t._jd + t._seconds / 86400.0
-
-    def secondsPast(self, frame, jd):
-        t = self
-        if frame != self._frame:
-            t = self.convert(frame)
-
-        delta = t._jd - jd
-        return t._seconds + delta * 86400
-
-    def _cmp(self, op, rhs):
-        """Compare Epochs *self* and *rhs* using operator *op*."""
-        t = self
-        if self._frame != rhs._frame:
-            t = self.convert(rhs._frame)
-        if t._jd != rhs._jd:
-            return op(t._jd, rhs._jd)
-        return op(t._seconds, rhs._seconds)
-
-    __eq__ = functools.partialmethod(_cmp, operator.eq)
-    __ne__ = functools.partialmethod(_cmp, operator.ne)
-    __lt__ = functools.partialmethod(_cmp, operator.lt)
-    __le__ = functools.partialmethod(_cmp, operator.le)
-    __gt__ = functools.partialmethod(_cmp, operator.gt)
-    __ge__ = functools.partialmethod(_cmp, operator.ge)
-
-    def __add__(self, rhs):
-        """
-        Add a duration to an Epoch.
-
-        = INPUT VARIABLES
-        - rhs     The Epoch to subtract.
-
-        = RETURN VALUE
-        - Returns the difference of ourselves and the input Epoch.
-        """
-        t = self
-        if self._frame != rhs.frame():
-            t = self.convert(rhs._frame)
-
-        sec = t._seconds + rhs.seconds()
-
-        return Epoch(t._frame, sec, t._jd)
-
-    def __sub__(self, rhs):
-        """
-        Subtract two Epoch's or a Duration from an Epoch.
-
-        Valid:
-        Duration = Epoch - Epoch
-        Epoch = Epoch - Duration
-
-        = INPUT VARIABLES
-        - rhs     The Epoch to subtract.
-
-        = RETURN VALUE
-        - Returns either the duration between to Epoch's or the a new
-          Epoch that is the result of subtracting a duration from an epoch.
-        """
-        # Delay-load due to circular dependencies.
-        import matplotlib.testing.jpl_units as U
-
-        # Handle Epoch - Duration
-        if isinstance(rhs, U.Duration):
-            return self + -rhs
-
-        t = self
-        if self._frame != rhs._frame:
-            t = self.convert(rhs._frame)
-
-        days = t._jd - rhs._jd
-        sec = t._seconds - rhs._seconds
-
-        return U.Duration(rhs._frame, days*86400 + sec)
-
-    def __str__(self):
-        """Print the Epoch."""
-        return "%22.15e %s" % (self.julianDate(self._frame), self._frame)
-
-    def __repr__(self):
-        """Print the Epoch."""
-        return str(self)
-
-    @staticmethod
-    def range(start, stop, step):
-        """
-        Generate a range of Epoch objects.
-
-        Similar to the Python range() method.  Returns the range [
-        start, stop) at the requested step.  Each element will be a
-        Epoch object.
-
-        = INPUT VARIABLES
-        - start     The starting value of the range.
-        - stop      The stop value of the range.
-        - step      Step to use.
-
-        = RETURN VALUE
-        - Returns a list containing the requested Epoch values.
-        """
-        elems = []
-
-        i = 0
-        while True:
-            d = start + i * step
-            if d >= stop:
-                break
-
-            elems.append(d)
-            i += 1
-
-        return elems
diff --git a/spaces/leilevy/bingo/src/components/ui/voice/index.tsx b/spaces/leilevy/bingo/src/components/ui/voice/index.tsx
deleted file mode 100644
index 4adcb632226bfced8b97092782811edf08b56569..0000000000000000000000000000000000000000
--- a/spaces/leilevy/bingo/src/components/ui/voice/index.tsx
+++ /dev/null
@@ -1,28 +0,0 @@
-import './index.scss'
-
-export interface VoiceProps extends CSSPropertyRule {
-  num?: number;
-  duration?: number;
-}
-export default function Voice({ duration = 400, num = 7, ...others }) {
-  return (
-    <div className="voice-button" { ...others }>
-      {Array.from({ length: num }).map((_, index) => {
-        const randomDuration = Math.random() * 100 + duration
-        const initialDelay = Math.random() * 2 * duration
-        const initialScale = Math.sin((index + 1) * Math.PI / num)
-        return (
-          <div
-            className="voice-button-item"
-            key={index}
-            style={{
-              animationDelay: initialDelay + 'ms',
-              animationDuration: randomDuration + 'ms',
-              transform: `scale(${initialScale})`
-            }}
-          />
-        )
-      })}
-    </div>
-  )
-}
diff --git a/spaces/lianzhou/stable-diffusion-webui/app.py b/spaces/lianzhou/stable-diffusion-webui/app.py
deleted file mode 100644
index 445e8a8fbbebbaf7e36db563f63773d7a927e454..0000000000000000000000000000000000000000
--- a/spaces/lianzhou/stable-diffusion-webui/app.py
+++ /dev/null
@@ -1,72 +0,0 @@
-import os
-from subprocess import getoutput
-
-gpu_info = getoutput('nvidia-smi')
-if("A10G" in gpu_info):
-    os.system(f"pip install -q https://github.com/camenduru/stable-diffusion-webui-colab/releases/download/0.0.15/xformers-0.0.15.dev0+4c06c79.d20221205-cp38-cp38-linux_x86_64.whl")
-elif("T4" in gpu_info):
-    os.system(f"pip install -q https://github.com/camenduru/stable-diffusion-webui-colab/releases/download/0.0.15/xformers-0.0.15.dev0+1515f77.d20221130-cp38-cp38-linux_x86_64.whl")
-
-os.system(f"git clone https://github.com/camenduru/stable-diffusion-webui /home/user/app/stable-diffusion-webui")
-os.chdir("/home/user/app/stable-diffusion-webui")
-
-os.system(f"wget -q https://github.com/camenduru/webui/raw/main/env_patch.py -O /home/user/app/env_patch.py")
-os.system(f"sed -i -e '/import image_from_url_text/r /home/user/app/env_patch.py' /home/user/app/stable-diffusion-webui/modules/ui.py")
-os.system(f"sed -i -e '/(modelmerger_interface, \"Checkpoint Merger\", \"modelmerger\"),/d' /home/user/app/stable-diffusion-webui/modules/ui.py")
-os.system(f"sed -i -e '/(train_interface, \"Train\", \"ti\"),/d' /home/user/app/stable-diffusion-webui/modules/ui.py")
-os.system(f"sed -i -e '/extensions_interface, \"Extensions\", \"extensions\"/d' /home/user/app/stable-diffusion-webui/modules/ui.py")
-os.system(f"sed -i -e '/settings_interface, \"Settings\", \"settings\"/d' /home/user/app/stable-diffusion-webui/modules/ui.py")
-os.system(f'''sed -i -e "s/document.getElementsByTagName('gradio-app')\[0\].shadowRoot/!!document.getElementsByTagName('gradio-app')[0].shadowRoot ? document.getElementsByTagName('gradio-app')[0].shadowRoot : document/g" /home/user/app/stable-diffusion-webui/script.js''')
-os.system(f"sed -i -e 's/                show_progress=False,/                show_progress=True,/g' /home/user/app/stable-diffusion-webui/modules/ui.py")
-os.system(f"sed -i -e 's/shared.demo.launch/shared.demo.queue().launch/g' /home/user/app/stable-diffusion-webui/webui.py")
-os.system(f"sed -i -e 's/ outputs=\[/queue=False, &/g' /home/user/app/stable-diffusion-webui/modules/ui.py")
-os.system(f"sed -i -e 's/               queue=False,  /                /g' /home/user/app/stable-diffusion-webui/modules/ui.py")
-
-# ----------------------------Please duplicate this space and delete this block if you don't want to see the extra header----------------------------
-os.system(f"wget -q https://github.com/camenduru/webui/raw/main/header_patch.py -O /home/user/app/header_patch.py")
-os.system(f"sed -i -e '/demo:/r /home/user/app/header_patch.py' /home/user/app/stable-diffusion-webui/modules/ui.py")
-# ---------------------------------------------------------------------------------------------------------------------------------------------------
-
-if "IS_SHARED_UI" in os.environ:
-    os.system(f"rm -rfv /home/user/app/stable-diffusion-webui/scripts/")
-    
-    os.system(f"wget -q https://github.com/camenduru/webui/raw/main/shared-config.json -O /home/user/app/shared-config.json")
-    os.system(f"wget -q https://github.com/camenduru/webui/raw/main/shared-ui-config.json -O /home/user/app/shared-ui-config.json")
-
-    os.system(f"wget -q {os.getenv('MODEL_LINK')} -O /home/user/app/stable-diffusion-webui/models/Stable-diffusion/{os.getenv('MODEL_NAME')}")
-    os.system(f"wget -q {os.getenv('VAE_LINK')} -O /home/user/app/stable-diffusion-webui/models/Stable-diffusion/{os.getenv('VAE_NAME')}")
-    os.system(f"wget -q {os.getenv('YAML_LINK')} -O /home/user/app/stable-diffusion-webui/models/Stable-diffusion/{os.getenv('YAML_NAME')}")
-    
-    os.system(f"python launch.py --force-enable-xformers --disable-console-progressbars --enable-console-prompts --ui-config-file /home/user/app/shared-ui-config.json --ui-settings-file /home/user/app/shared-config.json --cors-allow-origins huggingface.co,hf.space --no-progressbar-hiding")
-else:
-    # Please duplicate this space and delete # character in front of the custom script you want to use or add here more custom scripts with same structure os.system(f"wget -q https://CUSTOM_SCRIPT_URL -O /home/user/app/stable-diffusion-webui/scripts/CUSTOM_SCRIPT_NAME.py")
-    os.system(f"wget -q https://gist.github.com/camenduru/9ec5f8141db9902e375967e93250860f/raw/d0bcf01786f20107c329c03f8968584ee67be12a/run_n_times.py -O /home/user/app/stable-diffusion-webui/scripts/run_n_times.py")
-    
-    # Please duplicate this space and delete # character in front of the extension you want to use or add here more extensions with same structure os.system(f"git clone https://EXTENSION_GIT_URL /home/user/app/stable-diffusion-webui/extensions/EXTENSION_NAME")
-    #os.system(f"git clone https://github.com/camenduru/stable-diffusion-webui-artists-to-study /home/user/app/stable-diffusion-webui/extensions/stable-diffusion-webui-artists-to-study")
-    os.system(f"git clone https://github.com/yfszzx/stable-diffusion-webui-images-browser /home/user/app/stable-diffusion-webui/extensions/stable-diffusion-webui-images-browser")
-    os.system(f"git clone https://github.com/deforum-art/deforum-for-automatic1111-webui /home/user/app/stable-diffusion-webui/extensions/deforum-for-automatic1111-webui")
-    
-    # Please duplicate this space and delete # character in front of the model you want to use or add here more ckpts with same structure os.system(f"wget -q https://CKPT_URL -O /home/user/app/stable-diffusion-webui/models/Stable-diffusion/CKPT_NAME.ckpt")
-    #os.system(f"wget -q https://huggingface.co/nitrosocke/Arcane-Diffusion/resolve/main/arcane-diffusion-v3.ckpt -O /home/user/app/stable-diffusion-webui/models/Stable-diffusion/arcane-diffusion-v3.ckpt")
-    #os.system(f"wget -q https://huggingface.co/DGSpitzer/Cyberpunk-Anime-Diffusion/resolve/main/Cyberpunk-Anime-Diffusion.ckpt -O /home/user/app/stable-diffusion-webui/models/Stable-diffusion/Cyberpunk-Anime-Diffusion.ckpt")
-    #os.system(f"wget -q https://huggingface.co/prompthero/midjourney-v4-diffusion/resolve/main/mdjrny-v4.ckpt -O /home/user/app/stable-diffusion-webui/models/Stable-diffusion/mdjrny-v4.ckpt")
-    #os.system(f"wget -q https://huggingface.co/nitrosocke/mo-di-diffusion/resolve/main/moDi-v1-pruned.ckpt -O /home/user/app/stable-diffusion-webui/models/Stable-diffusion/moDi-v1-pruned.ckpt")
-    #os.system(f"wget -q https://huggingface.co/Fictiverse/Stable_Diffusion_PaperCut_Model/resolve/main/PaperCut_v1.ckpt -O /home/user/app/stable-diffusion-webui/models/Stable-diffusion/PaperCut_v1.ckpt")
-    #os.system(f"wget -q https://huggingface.co/lilpotat/sa/resolve/main/samdoesarts_style.ckpt -O /home/user/app/stable-diffusion-webui/models/Stable-diffusion/samdoesarts_style.ckpt")
-    #os.system(f"wget -q https://huggingface.co/hakurei/waifu-diffusion-v1-3/resolve/main/wd-v1-3-float32.ckpt -O /home/user/app/stable-diffusion-webui/models/Stable-diffusion/wd-v1-3-float32.ckpt")
-    #os.system(f"wget -q https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt -O /home/user/app/stable-diffusion-webui/models/Stable-diffusion/sd-v1-4.ckpt")
-    #os.system(f"wget -q https://huggingface.co/runwayml/stable-diffusion-v1-5/resolve/main/v1-5-pruned-emaonly.ckpt -O /home/user/app/stable-diffusion-webui/models/Stable-diffusion/v1-5-pruned-emaonly.ckpt")
-    #os.system(f"wget -q https://huggingface.co/runwayml/stable-diffusion-inpainting/resolve/main/sd-v1-5-inpainting.ckpt -O /home/user/app/stable-diffusion-webui/models/Stable-diffusion/sd-v1-5-inpainting.ckpt")
-    
-    #os.system(f"wget -q https://huggingface.co/Linaqruf/anything-v3.0/resolve/main/Anything-V3.0-pruned.ckpt -O /home/user/app/stable-diffusion-webui/models/Stable-diffusion/Anything-V3.0-pruned.ckpt")
-    #os.system(f"wget -q https://huggingface.co/Linaqruf/anything-v3.0/resolve/main/Anything-V3.0.vae.pt -O /home/user/app/stable-diffusion-webui/models/Stable-diffusion/Anything-V3.0-pruned.vae.pt")
-    
-    #os.system(f"wget -q https://huggingface.co/stabilityai/stable-diffusion-2/resolve/main/768-v-ema.ckpt -O /home/user/app/stable-diffusion-webui/models/Stable-diffusion/768-v-ema.ckpt")
-    #os.system(f"wget -q https://raw.githubusercontent.com/Stability-AI/stablediffusion/main/configs/stable-diffusion/v2-inference-v.yaml -O /home/user/app/stable-diffusion-webui/models/Stable-diffusion/768-v-ema.yaml")
-    os.system(f"wget -q https://r2.kamiya-b.me/dreambooth_lib/akakura-sn.ckpt -O /home/user/app/stable-diffusion-webui/models/Stable-diffusion/akakura-sn.ckpt")
-    os.system(f"wget -q https://huggingface.co/stabilityai/stable-diffusion-2-1/resolve/main/v2-1_768-ema-pruned.ckpt -O /home/user/app/stable-diffusion-webui/models/Stable-diffusion/v2-1_768-ema-pruned.ckpt")
-    os.system(f"wget -q https://raw.githubusercontent.com/Stability-AI/stablediffusion/main/configs/stable-diffusion/v2-inference-v.yaml -O /home/user/app/stable-diffusion-webui/models/Stable-diffusion/v2-1_768-ema-pruned.yaml")
-
-    os.system(f"python launch.py --force-enable-xformers --ui-config-file /home/user/app/ui-config.json --ui-settings-file /home/user/app/config.json --disable-console-progressbars --enable-console-prompts --cors-allow-origins huggingface.co,hf.space --no-progressbar-hiding --api --skip-torch-cuda-test")
-    
\ No newline at end of file
diff --git a/spaces/limcheekin/zephyr-7B-beta-GGUF/main.py b/spaces/limcheekin/zephyr-7B-beta-GGUF/main.py
deleted file mode 100644
index 873db8e1ff392b80472cdf6faf6c153b16487e28..0000000000000000000000000000000000000000
--- a/spaces/limcheekin/zephyr-7B-beta-GGUF/main.py
+++ /dev/null
@@ -1,30 +0,0 @@
-from llama_cpp.server.app import create_app, Settings
-from fastapi.responses import HTMLResponse
-from fastapi.middleware.gzip import GZipMiddleware
-import os
-
-app = create_app(
-    Settings(
-        n_threads=2,  # set to number of cpu cores
-        model="model/gguf-model.bin",
-        embedding=True
-    )
-)
-
-app.add_middleware(GZipMiddleware, minimum_size=1000)
-
-# Read the content of index.html once and store it in memory
-with open("index.html", "r") as f:
-    content = f.read()
-
-
-@app.get("/", response_class=HTMLResponse)
-async def read_items():
-    return content
-
-if __name__ == "__main__":
-    import uvicorn
-    uvicorn.run(app,
-                host=os.environ["HOST"],
-                port=int(os.environ["PORT"])
-                )
diff --git a/spaces/lincquiQcaudo/Top-20-Diffusion/Dental Clinic Software Crack TOP Sites.md b/spaces/lincquiQcaudo/Top-20-Diffusion/Dental Clinic Software Crack TOP Sites.md
deleted file mode 100644
index f694cd8d7e54f82d018f7acabc4eda40a1cd1caa..0000000000000000000000000000000000000000
--- a/spaces/lincquiQcaudo/Top-20-Diffusion/Dental Clinic Software Crack TOP Sites.md	
+++ /dev/null
@@ -1,6 +0,0 @@
-<h2>dental clinic software crack sites</h2><br /><p><b><b>DOWNLOAD</b> &#9999; &#9999; &#9999; <a href="https://bytlly.com/2uGvNP">https://bytlly.com/2uGvNP</a></b></p><br /><br />
-<br />
- 4fefd39f24<br />
-<br />
-<br />
-<p></p>
diff --git a/spaces/lincquiQcaudo/Top-20-Diffusion/HD Online Player (Waris Shah Gurdas Maan Full Movie Do) BEST.md b/spaces/lincquiQcaudo/Top-20-Diffusion/HD Online Player (Waris Shah Gurdas Maan Full Movie Do) BEST.md
deleted file mode 100644
index 38d12484a212e2bd37dfa1815e5cebf6d9064054..0000000000000000000000000000000000000000
--- a/spaces/lincquiQcaudo/Top-20-Diffusion/HD Online Player (Waris Shah Gurdas Maan Full Movie Do) BEST.md	
+++ /dev/null
@@ -1,7 +0,0 @@
-<h2>HD Online Player (Waris Shah Gurdas Maan Full Movie Do)</h2><br /><p><b><b>Download File</b> &#128504; <a href="https://bytlly.com/2uGx3X">https://bytlly.com/2uGx3X</a></b></p><br /><br />
-
-Watch the latest Punjabi dubbed Hindi film Waris Shah: Ishk Daa Waaris (2006). Starring: Gurdas Maan, Juhi. Waits Shah Full HD Movie. ➥➥➥➥➥➥➥➥➥➥➥➥➥➥➥➥➥➥➥➥➥➥➥➥➥
-Waris Shah: Ishk Daa Vaaris is an Indian feature film directed by Ishan Sharmila. This is a story about a boy, Waris Shah, who was fascinated and in love with a girl named Sunama. One day he met a girl named Ishk Daa Vaaris, who became everything to him. But she left him in an instant, as she fell in love with another. And then Waris Shah turned to his friend who worked in the police and with his help he got on the trail of Sunama 8a78ff9644<br />
-<br />
-<br />
-<p></p>
diff --git a/spaces/ll0z0y/bingoa/Dockerfile b/spaces/ll0z0y/bingoa/Dockerfile
deleted file mode 100644
index c677b05b75f7e4b2beee8c97fb47957a0861a83e..0000000000000000000000000000000000000000
--- a/spaces/ll0z0y/bingoa/Dockerfile
+++ /dev/null
@@ -1,7 +0,0 @@
-FROM weaigc/bingo:latest
-
-ARG DEBIAN_FRONTEND=noninteractive
-
-ENV BING_HEADER ""
-
-CMD npm start
diff --git a/spaces/llmonitor/benchmarks/app/api/confirm/route.js b/spaces/llmonitor/benchmarks/app/api/confirm/route.js
deleted file mode 100644
index 3e8856d7378fb9e1634f08b0eba48d19f63b0c94..0000000000000000000000000000000000000000
--- a/spaces/llmonitor/benchmarks/app/api/confirm/route.js
+++ /dev/null
@@ -1,30 +0,0 @@
-import jwt from "jsonwebtoken"
-import db from "@/utils/db"
-
-export async function GET(request) {
-  const searchParams = request.nextUrl.searchParams
-  const token = searchParams.get("token")
-
-  console.log("token", token)
-
-  const { userId } = jwt.verify(token, process.env.JWT_SECRET)
-
-  const [userObj] =
-    await db`UPDATE users SET confirmed = true WHERE id = ${userId} RETURNING *`
-
-  const longLivedToken = jwt.sign(
-    {
-      userId: userObj.id,
-      exp: Math.floor(Date.now() / 1000) + 60 * 60 * 24 * 30, // 1 month
-    },
-    process.env.JWT_SECRET
-  )
-
-  return new Response(null, {
-    status: 302,
-    headers: {
-      "Set-Cookie": `token=${longLivedToken}; path=/; HttpOnly`,
-      Location: `/prompts`,
-    },
-  })
-}
diff --git a/spaces/lulmer/paraphraser_ai/app.py b/spaces/lulmer/paraphraser_ai/app.py
deleted file mode 100644
index 6e23ca16a9ef3ee4f48dc89bcfb491d78992cdb1..0000000000000000000000000000000000000000
--- a/spaces/lulmer/paraphraser_ai/app.py
+++ /dev/null
@@ -1,38 +0,0 @@
-import os
-import streamlit as st
-from backend.data_augmenter import BackTranslatorAugmenter
-from footer import footer
-os.environ['NO_PROXY'] = '127.0.0.1'
-st.set_page_config(layout="wide", page_title="Paraphraser.AI", page_icon="🤖✍️")
-st.title('Paraphraser.AI 🤖✍️')
-st.header("An intelligent sentence paraphraser")
-st.markdown('''This is a demo of a system that can rewrite some given paragraphs with slight differences.''')
-
-model_selection = st.sidebar.selectbox(
-    'Select a paraphraser:',
-    ['Vladimir 🧑🏼','Maria 👩🏽','Jacques 👨'],
-)
-
-input_text = st.text_area('Please type the text to paraphrase')
-
-
-
-class DummyAugmenter:
-    def __init__(self, in_lang="en", out_lang="ru") -> None:
-        pass
-    def back_translate(self,text):
-        return "La marche des vertueux est seumée d'obstacles"
-
-
-if model_selection == 'Vladimir 🧑🏼':
-    model = BackTranslatorAugmenter(in_lang="en", out_lang="ru")
-if model_selection == 'Maria 👩🏽':
-    model = BackTranslatorAugmenter(in_lang="en", out_lang="es")
-if model_selection == 'Jacques 👨':
-    model = BackTranslatorAugmenter(in_lang="en", out_lang="fr")
-
-if input_text:
-    st.header(f"Paraphrased text :")
-    st.write("".join(model.back_translate(input_text)))
-
-footer()
\ No newline at end of file
diff --git a/spaces/ma-xu/LIVE/compute_distance.h b/spaces/ma-xu/LIVE/compute_distance.h
deleted file mode 100644
index c125641a9d720bd16be1428e205bd6c07c726bc5..0000000000000000000000000000000000000000
--- a/spaces/ma-xu/LIVE/compute_distance.h
+++ /dev/null
@@ -1,949 +0,0 @@
-#pragma once
-
-#include "diffvg.h"
-#include "edge_query.h"
-#include "scene.h"
-#include "shape.h"
-#include "solve.h"
-#include "vector.h"
-
-#include <cassert>
-
-struct ClosestPointPathInfo {
-    int base_point_id;
-    int point_id;
-    float t_root;
-};
-
-DEVICE
-inline
-bool closest_point(const Circle &circle, const Vector2f &pt,
-                   Vector2f *result) {
-    *result = circle.center + circle.radius * normalize(pt - circle.center);
-    return false;
-}
-
-DEVICE
-inline
-bool closest_point(const Path &path, const BVHNode *bvh_nodes, const Vector2f &pt, float max_radius,
-                   ClosestPointPathInfo *path_info,
-                   Vector2f *result) {
-    auto min_dist = max_radius;
-    auto ret_pt = Vector2f{0, 0};
-    auto found = false;
-    auto num_segments = path.num_base_points;
-    constexpr auto max_bvh_size = 128;
-    int bvh_stack[max_bvh_size];
-    auto stack_size = 0;
-    bvh_stack[stack_size++] = 2 * num_segments - 2;
-    while (stack_size > 0) {
-        const BVHNode &node = bvh_nodes[bvh_stack[--stack_size]];
-        if (node.child1 < 0) {
-            // leaf
-            auto base_point_id = node.child0;
-            auto point_id = - node.child1 - 1;
-            assert(base_point_id < num_segments);
-            assert(point_id < path.num_points);
-            auto dist = 0.f;
-            auto closest_pt = Vector2f{0, 0};
-            auto t_root = 0.f;
-            if (path.num_control_points[base_point_id] == 0) {
-                // Straight line
-                auto i0 = point_id;
-                auto i1 = (point_id + 1) % path.num_points;
-                auto p0 = Vector2f{path.points[2 * i0], path.points[2 * i0 + 1]};
-                auto p1 = Vector2f{path.points[2 * i1], path.points[2 * i1 + 1]};
-                // project pt to line
-                auto t = dot(pt - p0, p1 - p0) / dot(p1 - p0, p1 - p0);
-                if (t < 0) {
-                    dist = distance(p0, pt);
-                    closest_pt = p0;
-                    t_root = 0;
-                } else if (t > 1) {
-                    dist = distance(p1, pt);
-                    closest_pt = p1;
-                    t_root = 1;
-                } else {
-                    dist = distance(p0 + t * (p1 - p0), pt);
-                    closest_pt = p0 + t * (p1 - p0);
-                    t_root = t;
-                }
-            } else if (path.num_control_points[base_point_id] == 1) {
-                // Quadratic Bezier curve
-                auto i0 = point_id;
-                auto i1 = point_id + 1;
-                auto i2 = (point_id + 2) % path.num_points;
-                auto p0 = Vector2f{path.points[2 * i0], path.points[2 * i0 + 1]};
-                auto p1 = Vector2f{path.points[2 * i1], path.points[2 * i1 + 1]};
-                auto p2 = Vector2f{path.points[2 * i2], path.points[2 * i2 + 1]};
-                if (path.use_distance_approx) {
-                    closest_pt = quadratic_closest_pt_approx(p0, p1, p2, pt, &t_root);
-                    dist = distance(closest_pt, pt);
-                } else {
-                    auto eval = [&](float t) -> Vector2f {
-                        auto tt = 1 - t;
-                        return (tt*tt)*p0 + (2*tt*t)*p1 + (t*t)*p2;
-                    };
-                    auto pt0 = eval(0);
-                    auto pt1 = eval(1);
-                    auto dist0 = distance(pt0, pt);
-                    auto dist1 = distance(pt1, pt);
-                    {
-                        dist = dist0;
-                        closest_pt = pt0;
-                        t_root = 0;
-                    }
-                    if (dist1 < dist) {
-                        dist = dist1;
-                        closest_pt = pt1;
-                        t_root = 1;
-                    }
-                    // The curve is (1-t)^2p0 + 2(1-t)tp1 + t^2p2
-                    // = (p0-2p1+p2)t^2+(-2p0+2p1)t+p0 = q
-                    // Want to solve (q - pt) dot q' = 0
-                    // q' = (p0-2p1+p2)t + (-p0+p1)
-                    // Expanding (p0-2p1+p2)^2 t^3 +
-                    //           3(p0-2p1+p2)(-p0+p1) t^2 +
-                    //           (2(-p0+p1)^2+(p0-2p1+p2)(p0-pt))t +
-                    //           (-p0+p1)(p0-pt) = 0
-                    auto A = sum((p0-2*p1+p2)*(p0-2*p1+p2));
-                    auto B = sum(3*(p0-2*p1+p2)*(-p0+p1));
-                    auto C = sum(2*(-p0+p1)*(-p0+p1)+(p0-2*p1+p2)*(p0-pt));
-                    auto D = sum((-p0+p1)*(p0-pt));
-                    float t[3];
-                    int num_sol = solve_cubic(A, B, C, D, t);
-                    for (int j = 0; j < num_sol; j++) {
-                        if (t[j] >= 0 && t[j] <= 1) {
-                            auto p = eval(t[j]);
-                            auto distp = distance(p, pt);
-                            if (distp < dist) {
-                                dist = distp;
-                                closest_pt = p;
-                                t_root = t[j];
-                            }
-                        }
-                    }
-                }
-            } else if (path.num_control_points[base_point_id] == 2) {
-                // Cubic Bezier curve
-                auto i0 = point_id;
-                auto i1 = point_id + 1;
-                auto i2 = point_id + 2;
-                auto i3 = (point_id + 3) % path.num_points;
-                auto p0 = Vector2f{path.points[2 * i0], path.points[2 * i0 + 1]};
-                auto p1 = Vector2f{path.points[2 * i1], path.points[2 * i1 + 1]};
-                auto p2 = Vector2f{path.points[2 * i2], path.points[2 * i2 + 1]};
-                auto p3 = Vector2f{path.points[2 * i3], path.points[2 * i3 + 1]};
-                auto eval = [&](float t) -> Vector2f {
-                    auto tt = 1 - t;
-                    return (tt*tt*tt)*p0 + (3*tt*tt*t)*p1 + (3*tt*t*t)*p2 + (t*t*t)*p3;
-                };
-                auto pt0 = eval(0);
-                auto pt1 = eval(1);
-                auto dist0 = distance(pt0, pt);
-                auto dist1 = distance(pt1, pt);
-                {
-                    dist = dist0;
-                    closest_pt = pt0;
-                    t_root = 0;
-                }
-                if (dist1 < dist) {
-                    dist = dist1;
-                    closest_pt = pt1;
-                    t_root = 1;
-                }
-                // The curve is (1 - t)^3 p0 + 3 * (1 - t)^2 t p1 + 3 * (1 - t) t^2 p2 + t^3 p3
-                // = (-p0+3p1-3p2+p3) t^3 + (3p0-6p1+3p2) t^2 + (-3p0+3p1) t + p0
-                // Want to solve (q - pt) dot q' = 0
-                // q' = 3*(-p0+3p1-3p2+p3)t^2 + 2*(3p0-6p1+3p2)t + (-3p0+3p1)
-                // Expanding 
-                // 3*(-p0+3p1-3p2+p3)^2 t^5
-                // 5*(-p0+3p1-3p2+p3)(3p0-6p1+3p2) t^4
-                // 4*(-p0+3p1-3p2+p3)(-3p0+3p1) + 2*(3p0-6p1+3p2)^2 t^3
-                // 3*(3p0-6p1+3p2)(-3p0+3p1) + 3*(-p0+3p1-3p2+p3)(p0-pt) t^2
-                // (-3p0+3p1)^2+2(p0-pt)(3p0-6p1+3p2) t
-                // (p0-pt)(-3p0+3p1)
-                double A = 3*sum((-p0+3*p1-3*p2+p3)*(-p0+3*p1-3*p2+p3));
-                double B = 5*sum((-p0+3*p1-3*p2+p3)*(3*p0-6*p1+3*p2));
-                double C = 4*sum((-p0+3*p1-3*p2+p3)*(-3*p0+3*p1)) + 2*sum((3*p0-6*p1+3*p2)*(3*p0-6*p1+3*p2));
-                double D = 3*(sum((3*p0-6*p1+3*p2)*(-3*p0+3*p1)) + sum((-p0+3*p1-3*p2+p3)*(p0-pt)));
-                double E = sum((-3*p0+3*p1)*(-3*p0+3*p1)) + 2*sum((p0-pt)*(3*p0-6*p1+3*p2));
-                double F = sum((p0-pt)*(-3*p0+3*p1));
-                // normalize the polynomial
-                B /= A;
-                C /= A;
-                D /= A;
-                E /= A;
-                F /= A;
-                // Isolator Polynomials:
-                // https://citeseerx.ist.psu.edu/viewdoc/download?doi=10.1.1.133.2233&rep=rep1&type=pdf
-                //                                       x/5 + B/25
-                //                                    /-----------------------------------------------------
-                // 5x^4 + 4B x^3 + 3C x^2 + 2D x + E /   x^5 +    B x^4 +       C x^3 +      D x^2 +      E x + F
-                //                                       x^5 + 4B/5 x^4 +    3C/5 x^3 +   2D/5 x^2 +    E/5 x
-                //                                      ----------------------------------------------------
-                //                                              B/5 x^4 +    2C/5 x^3 +   3D/5 x^2 +   4E/5 x + F
-                //                                              B/5 x^4 + 4B^2/25 x^3 + 3BC/25 x^2 + 2BD/25 x + BE/25
-                //                                      ----------------------------------------------------
-                //                                     (2C/5 - 4B^2/25)x^3 + (3D/5-3BC/25)x^2 + (4E/5-2BD/25) + (F-BE/25)
-                auto p1A = ((2 / 5.f) * C - (4 / 25.f) * B * B);
-                auto p1B = ((3 / 5.f) * D - (3 / 25.f) * B * C);
-                auto p1C = ((4 / 5.f) * E - (2 / 25.f) * B * D);
-                auto p1D = F - B * E / 25.f;
-                // auto q1A = 1 / 5.f;
-                // auto q1B = B / 25.f;
-                // x/5 + B/25 = 0
-                // x = -B/5
-                auto q_root = -B/5.f;
-                double p_roots[3];
-                int num_sol = solve_cubic(p1A, p1B, p1C, p1D, p_roots);
-                float intervals[4];
-                if (q_root >= 0 && q_root <= 1) {
-                    intervals[0] = q_root;
-                }
-                for (int j = 0; j < num_sol; j++) {
-                    intervals[j + 1] = p_roots[j];
-                }
-                auto num_intervals = 1 + num_sol;
-                // sort intervals
-                for (int j = 1; j < num_intervals; j++) {
-                    for (int k = j; k > 0 && intervals[k - 1] > intervals[k]; k--) {
-                        auto tmp = intervals[k];
-                        intervals[k] = intervals[k - 1];
-                        intervals[k - 1] = tmp;
-                    }
-                }
-                auto eval_polynomial = [&] (double t) {
-                    return t*t*t*t*t+
-                           B*t*t*t*t+
-                           C*t*t*t+
-                           D*t*t+
-                           E*t+
-                           F;
-                };
-                auto eval_polynomial_deriv = [&] (double t) {
-                    return 5*t*t*t*t+
-                           4*B*t*t*t+
-                           3*C*t*t+
-                           2*D*t+
-                           E;
-                };
-                auto lower_bound = 0.f;
-                for (int j = 0; j < num_intervals + 1; j++) {
-                    if (j < num_intervals && intervals[j] < 0.f) {
-                        continue;
-                    }
-                    auto upper_bound = j < num_intervals ?
-                        min(intervals[j], 1.f) : 1.f;
-                    auto lb = lower_bound;
-                    auto ub = upper_bound;
-                    auto lb_eval = eval_polynomial(lb);
-                    auto ub_eval = eval_polynomial(ub);
-                    if (lb_eval * ub_eval > 0) {
-                        // Doesn't have root
-                        continue;
-                    }
-                    if (lb_eval > ub_eval) {
-                        swap_(lb, ub);
-                    }
-                    auto t = 0.5f * (lb + ub);
-                    auto num_iter = 20;
-                    for (int it = 0; it < num_iter; it++) {
-                        if (!(t >= lb && t <= ub)) {
-                            t = 0.5f * (lb + ub);
-                        }
-                        auto value = eval_polynomial(t);
-                        if (fabs(value) < 1e-5f || it == num_iter - 1) {
-                            break;
-                        }
-                        // The derivative may not be entirely accurate,
-                        // but the bisection is going to handle this
-                        if (value > 0.f) {
-                            ub = t;
-                        } else {
-                            lb = t;
-                        }
-                        auto derivative = eval_polynomial_deriv(t);
-                        t -= value / derivative;
-                    }
-                    auto p = eval(t);
-                    auto distp = distance(p, pt);
-                    if (distp < dist) {
-                        dist = distp;
-                        closest_pt = p;
-                        t_root = t;
-                    }
-                    if (upper_bound >= 1.f) {
-                        break;
-                    }
-                    lower_bound = upper_bound;
-                }
-            } else {
-                assert(false);
-            }
-            if (dist < min_dist) {
-                min_dist = dist;
-                ret_pt = closest_pt;
-                path_info->base_point_id = base_point_id;
-                path_info->point_id = point_id;
-                path_info->t_root = t_root;
-                found = true;
-            }
-        } else {
-            assert(node.child0 >= 0 && node.child1 >= 0);
-            const AABB &b0 = bvh_nodes[node.child0].box;
-            if (within_distance(b0, pt, min_dist)) {
-                bvh_stack[stack_size++] = node.child0;
-            }
-            const AABB &b1 = bvh_nodes[node.child1].box;
-            if (within_distance(b1, pt, min_dist)) {
-                bvh_stack[stack_size++] = node.child1;
-            }
-            assert(stack_size <= max_bvh_size);
-        }
-    }
-    if (found) {
-        assert(path_info->base_point_id < num_segments);
-    }
-    *result = ret_pt;
-    return found;
-}
-
-DEVICE
-inline
-bool closest_point(const Rect &rect, const Vector2f &pt,
-                   Vector2f *result) {
-    auto min_dist = 0.f;
-    auto closest_pt = Vector2f{0, 0};
-    auto update = [&](const Vector2f &p0, const Vector2f &p1, bool first) {
-        // project pt to line
-        auto t = dot(pt - p0, p1 - p0) / dot(p1 - p0, p1 - p0);
-        if (t < 0) {
-            auto d = distance(p0, pt);
-            if (first || d < min_dist) {
-                min_dist = d;
-                closest_pt = p0;
-            }
-        } else if (t > 1) {
-            auto d = distance(p1, pt);
-            if (first || d < min_dist) {
-                min_dist = d;
-                closest_pt = p1;
-            }
-        } else {
-            auto p = p0 + t * (p1 - p0);
-            auto d = distance(p, pt);
-            if (first || d < min_dist) {
-                min_dist = d;
-                closest_pt = p0;
-            }
-        }
-    };
-    auto left_top = rect.p_min;
-    auto right_top = Vector2f{rect.p_max.x, rect.p_min.y};
-    auto left_bottom = Vector2f{rect.p_min.x, rect.p_max.y};
-    auto right_bottom = rect.p_max;
-    update(left_top, left_bottom, true);
-    update(left_top, right_top, false);
-    update(right_top, right_bottom, false);
-    update(left_bottom, right_bottom, false);
-    *result = closest_pt;
-    return true;
-}
-
-DEVICE
-inline
-bool closest_point(const Shape &shape, const BVHNode *bvh_nodes, const Vector2f &pt, float max_radius,
-                   ClosestPointPathInfo *path_info,
-                   Vector2f *result) {
-    switch (shape.type) {
-        case ShapeType::Circle:
-            return closest_point(*(const Circle *)shape.ptr, pt, result);
-        case ShapeType::Ellipse:
-            // https://www.geometrictools.com/Documentation/DistancePointEllipseEllipsoid.pdf
-            assert(false);
-            return false;
-        case ShapeType::Path:
-            return closest_point(*(const Path *)shape.ptr, bvh_nodes, pt, max_radius, path_info, result);
-        case ShapeType::Rect:
-            return closest_point(*(const Rect *)shape.ptr, pt, result);
-    }
-    assert(false);
-    return false;
-}
-
-DEVICE
-inline
-bool compute_distance(const SceneData &scene,
-                      int shape_group_id,
-                      const Vector2f &pt,
-                      float max_radius,
-                      int *min_shape_id,
-                      Vector2f *closest_pt_,
-                      ClosestPointPathInfo *path_info,
-                      float *result) {
-    const ShapeGroup &shape_group = scene.shape_groups[shape_group_id];
-    // pt is in canvas space, transform it to shape's local space
-    auto local_pt = xform_pt(shape_group.canvas_to_shape, pt);
-
-    constexpr auto max_bvh_stack_size = 64;
-    int bvh_stack[max_bvh_stack_size];
-    auto stack_size = 0;
-    bvh_stack[stack_size++] = 2 * shape_group.num_shapes - 2;
-    const auto &bvh_nodes = scene.shape_groups_bvh_nodes[shape_group_id];
-
-    auto min_dist = max_radius;
-    auto found = false;
-
-    while (stack_size > 0) {
-        const BVHNode &node = bvh_nodes[bvh_stack[--stack_size]];
-        if (node.child1 < 0) {
-            // leaf
-            auto shape_id = node.child0;
-            const auto &shape = scene.shapes[shape_id];
-            ClosestPointPathInfo local_path_info{-1, -1};
-            auto local_closest_pt = Vector2f{0, 0};
-            if (closest_point(shape, scene.path_bvhs[shape_id], local_pt, max_radius, &local_path_info, &local_closest_pt)) {
-                auto closest_pt = xform_pt(shape_group.shape_to_canvas, local_closest_pt);
-                auto dist = distance(closest_pt, pt);
-                if (!found || dist < min_dist) {
-                    found = true;
-                    min_dist = dist;
-                    if (min_shape_id != nullptr) {
-                        *min_shape_id = shape_id;
-                    }
-                    if (closest_pt_ != nullptr) {
-                        *closest_pt_ = closest_pt;
-                    }
-                    if (path_info != nullptr) {
-                        *path_info = local_path_info;
-                    }
-                }
-            }
-        } else {
-            assert(node.child0 >= 0 && node.child1 >= 0);
-            const AABB &b0 = bvh_nodes[node.child0].box;
-            if (inside(b0, local_pt, max_radius)) {
-                bvh_stack[stack_size++] = node.child0;
-            }
-            const AABB &b1 = bvh_nodes[node.child1].box;
-            if (inside(b1, local_pt, max_radius)) {
-                bvh_stack[stack_size++] = node.child1;
-            }
-            assert(stack_size <= max_bvh_stack_size);
-        }
-    }
-
-    *result = min_dist;
-    return found;
-}
-
-
-DEVICE
-inline
-void d_closest_point(const Circle &circle,
-                     const Vector2f &pt,
-                     const Vector2f &d_closest_pt,
-                     Circle &d_circle,
-                     Vector2f &d_pt) {
-    // return circle.center + circle.radius * normalize(pt - circle.center);
-    auto d_center = d_closest_pt *
-        (1 + d_normalize(pt - circle.center, circle.radius * d_closest_pt));
-    atomic_add(&d_circle.center.x, d_center);
-    atomic_add(&d_circle.radius, dot(d_closest_pt, normalize(pt - circle.center)));
-}
-
-DEVICE
-inline
-void d_closest_point(const Path &path,
-                     const Vector2f &pt,
-                     const Vector2f &d_closest_pt,
-                     const ClosestPointPathInfo &path_info,
-                     Path &d_path,
-                     Vector2f &d_pt) {
-    auto base_point_id = path_info.base_point_id;
-    auto point_id = path_info.point_id;
-    auto min_t_root = path_info.t_root;
-    
-    if (path.num_control_points[base_point_id] == 0) {
-        // Straight line
-        auto i0 = point_id;
-        auto i1 = (point_id + 1) % path.num_points;
-        auto p0 = Vector2f{path.points[2 * i0], path.points[2 * i0 + 1]};
-        auto p1 = Vector2f{path.points[2 * i1], path.points[2 * i1 + 1]};
-        // project pt to line
-        auto t = dot(pt - p0, p1 - p0) / dot(p1 - p0, p1 - p0);
-        auto d_p0 = Vector2f{0, 0};
-        auto d_p1 = Vector2f{0, 0};
-        if (t < 0) {
-            d_p0 += d_closest_pt;
-        } else if (t > 1) {
-            d_p1 += d_closest_pt;
-        } else {
-            auto d_p = d_closest_pt;
-            // p = p0 + t * (p1 - p0)
-            d_p0 += d_p * (1 - t);
-            d_p1 += d_p * t;
-        }
-        atomic_add(d_path.points + 2 * i0, d_p0);
-        atomic_add(d_path.points + 2 * i1, d_p1);
-    } else if (path.num_control_points[base_point_id] == 1) {
-        // Quadratic Bezier curve
-        auto i0 = point_id;
-        auto i1 = point_id + 1;
-        auto i2 = (point_id + 2) % path.num_points;
-        auto p0 = Vector2f{path.points[2 * i0], path.points[2 * i0 + 1]};
-        auto p1 = Vector2f{path.points[2 * i1], path.points[2 * i1 + 1]};
-        auto p2 = Vector2f{path.points[2 * i2], path.points[2 * i2 + 1]};
-        // auto eval = [&](float t) -> Vector2f {
-        //     auto tt = 1 - t;
-        //     return (tt*tt)*p0 + (2*tt*t)*p1 + (t*t)*p2;
-        // };
-        // auto dist0 = distance(eval(0), pt);
-        // auto dist1 = distance(eval(1), pt);
-        auto d_p0 = Vector2f{0, 0};
-        auto d_p1 = Vector2f{0, 0};
-        auto d_p2 = Vector2f{0, 0};
-        auto t = min_t_root;
-        if (t == 0) {
-            d_p0 += d_closest_pt;
-        } else if (t == 1) {
-            d_p2 += d_closest_pt;
-        } else {
-            // The curve is (1-t)^2p0 + 2(1-t)tp1 + t^2p2
-            // = (p0-2p1+p2)t^2+(-2p0+2p1)t+p0 = q
-            // Want to solve (q - pt) dot q' = 0
-            // q' = (p0-2p1+p2)t + (-p0+p1)
-            // Expanding (p0-2p1+p2)^2 t^3 +
-            //           3(p0-2p1+p2)(-p0+p1) t^2 +
-            //           (2(-p0+p1)^2+(p0-2p1+p2)(p0-pt))t +
-            //           (-p0+p1)(p0-pt) = 0
-            auto A = sum((p0-2*p1+p2)*(p0-2*p1+p2));
-            auto B = sum(3*(p0-2*p1+p2)*(-p0+p1));
-            auto C = sum(2*(-p0+p1)*(-p0+p1)+(p0-2*p1+p2)*(p0-pt));
-            // auto D = sum((-p0+p1)*(p0-pt));
-            auto d_p = d_closest_pt;
-            // p = eval(t)
-            auto tt = 1 - t;
-            // (tt*tt)*p0 + (2*tt*t)*p1 + (t*t)*p2
-            auto d_tt = 2 * tt * dot(d_p, p0) + 2 * t * dot(d_p, p1);
-            auto d_t = -d_tt + 2 * tt * dot(d_p, p1) + 2 * t * dot(d_p, p2);
-            auto d_p0 = d_p * tt * tt;
-            auto d_p1 = 2 * d_p * tt * t;
-            auto d_p2 = d_p * t * t;
-            // implicit function theorem: dt/dA = -1/(p'(t)) * dp/dA
-            auto poly_deriv_t = 3 * A * t * t + 2 * B * t + C;
-            if (fabs(poly_deriv_t) > 1e-6f) {
-                auto d_A = - (d_t / poly_deriv_t) * t * t * t;
-                auto d_B = - (d_t / poly_deriv_t) * t * t;
-                auto d_C = - (d_t / poly_deriv_t) * t;
-                auto d_D = - (d_t / poly_deriv_t);
-                // A = sum((p0-2*p1+p2)*(p0-2*p1+p2))
-                // B = sum(3*(p0-2*p1+p2)*(-p0+p1))
-                // C = sum(2*(-p0+p1)*(-p0+p1)+(p0-2*p1+p2)*(p0-pt))
-                // D = sum((-p0+p1)*(p0-pt))
-                d_p0 += 2*d_A*(p0-2*p1+p2)+
-                        3*d_B*((-p0+p1)-(p0-2*p1+p2))+
-                        2*d_C*(-2*(-p0+p1))+
-                          d_C*((p0-pt)+(p0-2*p1+p2))+
-                        2*d_D*(-(p0-pt)+(-p0+p1));
-                d_p1 += (-2)*2*d_A*(p0-2*p1+p2)+
-                        3*d_B*(-2*(-p0+p1)+(p0-2*p1+p2))+
-                        2*d_C*(2*(-p0+p1))+
-                          d_C*((-2)*(p0-pt))+
-                        d_D*(p0-pt);
-                d_p2 += 2*d_A*(p0-2*p1+p2)+
-                        3*d_B*(-p0+p1)+
-                        d_C*(p0-pt);
-                d_pt += d_C*(-(p0-2*p1+p2))+
-                        d_D*(-(-p0+p1));
-            }
-        }
-        atomic_add(d_path.points + 2 * i0, d_p0);
-        atomic_add(d_path.points + 2 * i1, d_p1);
-        atomic_add(d_path.points + 2 * i2, d_p2);
-    } else if (path.num_control_points[base_point_id] == 2) {
-        // Cubic Bezier curve
-        auto i0 = point_id;
-        auto i1 = point_id + 1;
-        auto i2 = point_id + 2;
-        auto i3 = (point_id + 3) % path.num_points;
-        auto p0 = Vector2f{path.points[2 * i0], path.points[2 * i0 + 1]};
-        auto p1 = Vector2f{path.points[2 * i1], path.points[2 * i1 + 1]};
-        auto p2 = Vector2f{path.points[2 * i2], path.points[2 * i2 + 1]};
-        auto p3 = Vector2f{path.points[2 * i3], path.points[2 * i3 + 1]};
-        // auto eval = [&](float t) -> Vector2f {
-        //     auto tt = 1 - t;
-        //     return (tt*tt*tt)*p0 + (3*tt*tt*t)*p1 + (3*tt*t*t)*p2 + (t*t*t)*p3;
-        // };
-        auto d_p0 = Vector2f{0, 0};
-        auto d_p1 = Vector2f{0, 0};
-        auto d_p2 = Vector2f{0, 0};
-        auto d_p3 = Vector2f{0, 0};
-        auto t = min_t_root;
-        if (t == 0) {
-            // closest_pt = p0
-            d_p0 += d_closest_pt;
-        } else if (t == 1) {
-            // closest_pt = p1
-            d_p3 += d_closest_pt;
-        } else {
-            // The curve is (1 - t)^3 p0 + 3 * (1 - t)^2 t p1 + 3 * (1 - t) t^2 p2 + t^3 p3
-            // = (-p0+3p1-3p2+p3) t^3 + (3p0-6p1+3p2) t^2 + (-3p0+3p1) t + p0
-            // Want to solve (q - pt) dot q' = 0
-            // q' = 3*(-p0+3p1-3p2+p3)t^2 + 2*(3p0-6p1+3p2)t + (-3p0+3p1)
-            // Expanding 
-            // 3*(-p0+3p1-3p2+p3)^2 t^5
-            // 5*(-p0+3p1-3p2+p3)(3p0-6p1+3p2) t^4
-            // 4*(-p0+3p1-3p2+p3)(-3p0+3p1) + 2*(3p0-6p1+3p2)^2 t^3
-            // 3*(3p0-6p1+3p2)(-3p0+3p1) + 3*(-p0+3p1-3p2+p3)(p0-pt) t^2
-            // (-3p0+3p1)^2+2(p0-pt)(3p0-6p1+3p2) t
-            // (p0-pt)(-3p0+3p1)
-            double A = 3*sum((-p0+3*p1-3*p2+p3)*(-p0+3*p1-3*p2+p3));
-            double B = 5*sum((-p0+3*p1-3*p2+p3)*(3*p0-6*p1+3*p2));
-            double C = 4*sum((-p0+3*p1-3*p2+p3)*(-3*p0+3*p1)) + 2*sum((3*p0-6*p1+3*p2)*(3*p0-6*p1+3*p2));
-            double D = 3*(sum((3*p0-6*p1+3*p2)*(-3*p0+3*p1)) + sum((-p0+3*p1-3*p2+p3)*(p0-pt)));
-            double E = sum((-3*p0+3*p1)*(-3*p0+3*p1)) + 2*sum((p0-pt)*(3*p0-6*p1+3*p2));
-            double F = sum((p0-pt)*(-3*p0+3*p1));
-            B /= A;
-            C /= A;
-            D /= A;
-            E /= A;
-            F /= A;
-            // auto eval_polynomial = [&] (double t) {
-            //     return t*t*t*t*t+
-            //            B*t*t*t*t+
-            //            C*t*t*t+
-            //            D*t*t+
-            //            E*t+
-            //            F;
-            // };
-            auto eval_polynomial_deriv = [&] (double t) {
-                return 5*t*t*t*t+
-                       4*B*t*t*t+
-                       3*C*t*t+
-                       2*D*t+
-                       E;
-            };
-
-            // auto p = eval(t);
-            auto d_p = d_closest_pt;
-            // (tt*tt*tt)*p0 + (3*tt*tt*t)*p1 + (3*tt*t*t)*p2 + (t*t*t)*p3
-            auto tt = 1 - t;
-            auto d_tt = 3 * tt * tt * dot(d_p, p0) +
-                        6 * tt * t * dot(d_p, p1) +
-                        3 * t * t * dot(d_p, p2);
-            auto d_t = -d_tt +
-                       3 * tt * tt * dot(d_p, p1) +
-                       6 * tt * t * dot(d_p, p2) +
-                       3 * t * t * dot(d_p, p3);
-            d_p0 += d_p * (tt * tt * tt);
-            d_p1 += d_p * (3 * tt * tt * t);
-            d_p2 += d_p * (3 * tt * t * t);
-            d_p3 += d_p * (t * t * t);
-            // implicit function theorem: dt/dA = -1/(p'(t)) * dp/dA
-            auto poly_deriv_t = eval_polynomial_deriv(t);
-            if (fabs(poly_deriv_t) > 1e-10f) {
-                auto d_B = -(d_t / poly_deriv_t) * t * t * t * t;
-                auto d_C = -(d_t / poly_deriv_t) * t * t * t;
-                auto d_D = -(d_t / poly_deriv_t) * t * t;
-                auto d_E = -(d_t / poly_deriv_t) * t;
-                auto d_F = -(d_t / poly_deriv_t);
-                // B = B' / A
-                // C = C' / A
-                // D = D' / A
-                // E = E' / A
-                // F = F' / A
-                auto d_A = -d_B * B / A
-                           -d_C * C / A
-                           -d_D * D / A
-                           -d_E * E / A
-                           -d_F * F / A;
-                d_B /= A;
-                d_C /= A;
-                d_D /= A;
-                d_E /= A;
-                d_F /= A;
-                {
-                    double A = 3*sum((-p0+3*p1-3*p2+p3)*(-p0+3*p1-3*p2+p3)) + 1e-3;
-                    double B = 5*sum((-p0+3*p1-3*p2+p3)*(3*p0-6*p1+3*p2));
-                    double C = 4*sum((-p0+3*p1-3*p2+p3)*(-3*p0+3*p1)) + 2*sum((3*p0-6*p1+3*p2)*(3*p0-6*p1+3*p2));
-                    double D = 3*(sum((3*p0-6*p1+3*p2)*(-3*p0+3*p1)) + sum((-p0+3*p1-3*p2+p3)*(p0-pt)));
-                    double E = sum((-3*p0+3*p1)*(-3*p0+3*p1)) + 2*sum((p0-pt)*(3*p0-6*p1+3*p2));
-                    double F = sum((p0-pt)*(-3*p0+3*p1));
-                    B /= A;
-                    C /= A;
-                    D /= A;
-                    E /= A;
-                    F /= A;
-                    auto eval_polynomial = [&] (double t) {
-                        return t*t*t*t*t+
-                               B*t*t*t*t+
-                               C*t*t*t+
-                               D*t*t+
-                               E*t+
-                               F;
-                    };
-                    auto eval_polynomial_deriv = [&] (double t) {
-                        return 5*t*t*t*t+
-                               4*B*t*t*t+
-                               3*C*t*t+
-                               2*D*t+
-                               E;
-                    };
-                    auto lb = t - 1e-2f;
-                    auto ub = t + 1e-2f;
-                    auto lb_eval = eval_polynomial(lb);
-                    auto ub_eval = eval_polynomial(ub);
-                    if (lb_eval > ub_eval) {
-                        swap_(lb, ub);
-                    }
-                    auto t_ = 0.5f * (lb + ub);
-                    auto num_iter = 20;
-                    for (int it = 0; it < num_iter; it++) {
-                        if (!(t_ >= lb && t_ <= ub)) {
-                            t_ = 0.5f * (lb + ub);
-                        }
-                        auto value = eval_polynomial(t_);
-                        if (fabs(value) < 1e-5f || it == num_iter - 1) {
-                            break;
-                        }
-                        // The derivative may not be entirely accurate,
-                        // but the bisection is going to handle this
-                        if (value > 0.f) {
-                            ub = t_;
-                        } else {
-                            lb = t_;
-                        }
-                        auto derivative = eval_polynomial_deriv(t);
-                        t_ -= value / derivative;
-                    }
-                }
-                // A = 3*sum((-p0+3*p1-3*p2+p3)*(-p0+3*p1-3*p2+p3))
-                d_p0 += d_A * 3 * (-1) * 2 * (-p0+3*p1-3*p2+p3);
-                d_p1 += d_A * 3 *   3  * 2 * (-p0+3*p1-3*p2+p3);
-                d_p2 += d_A * 3 * (-3) * 2 * (-p0+3*p1-3*p2+p3);
-                d_p3 += d_A * 3 *   1  * 2 * (-p0+3*p1-3*p2+p3);
-                // B = 5*sum((-p0+3*p1-3*p2+p3)*(3*p0-6*p1+3*p2))
-                d_p0 += d_B * 5 * ((-1) * (3*p0-6*p1+3*p2) + 3 * (-p0+3*p1-3*p2+p3));
-                d_p1 += d_B * 5 * (3 * (3*p0-6*p1+3*p2) + (-6) * (-p0+3*p1-3*p2+p3));
-                d_p2 += d_B * 5 * ((-3) * (3*p0-6*p1+3*p2) + 3 * (-p0+3*p1-3*p2+p3));
-                d_p3 += d_B * 5 * (3*p0-6*p1+3*p2);
-                // C = 4*sum((-p0+3*p1-3*p2+p3)*(-3*p0+3*p1)) + 2*sum((3*p0-6*p1+3*p2)*(3*p0-6*p1+3*p2))
-                d_p0 += d_C * 4 * ((-1) * (-3*p0+3*p1) + (-3) * (-p0+3*p1-3*p2+p3)) +
-                        d_C * 2 * (3 * 2 * (3*p0-6*p1+3*p2));
-                d_p1 += d_C * 4 * (3 * (-3*p0+3*p1) + 3 * (-p0+3*p1-3*p2+p3)) +
-                        d_C * 2 * ((-6) * 2 * (3*p0-6*p1+3*p2));
-                d_p2 += d_C * 4 * ((-3) * (-3*p0+3*p1)) +
-                        d_C * 2 * (3 * 2 * (3*p0-6*p1+3*p2));
-                d_p3 += d_C * 4 * (-3*p0+3*p1);
-                // D = 3*(sum((3*p0-6*p1+3*p2)*(-3*p0+3*p1)) + sum((-p0+3*p1-3*p2+p3)*(p0-pt)))
-                d_p0 += d_D * 3 * (3 * (-3*p0+3*p1) + (-3) * (3*p0-6*p1+3*p2)) +
-                        d_D * 3 * ((-1) * (p0-pt) + 1 * (-p0+3*p1-3*p2+p3));
-                d_p1 += d_D * 3 * ((-6) * (-3*p0+3*p1) + (3) * (3*p0-6*p1+3*p2)) +
-                        d_D * 3 * (3 * (p0-pt));
-                d_p2 += d_D * 3 * (3 * (-3*p0+3*p1)) +
-                        d_D * 3 * ((-3) * (p0-pt));
-                d_pt += d_D * 3 * ((-1) * (-p0+3*p1-3*p2+p3));
-                // E = sum((-3*p0+3*p1)*(-3*p0+3*p1)) + 2*sum((p0-pt)*(3*p0-6*p1+3*p2))
-                d_p0 += d_E * ((-3) * 2 * (-3*p0+3*p1)) +
-                        d_E * 2 * (1 * (3*p0-6*p1+3*p2) + 3 * (p0-pt));
-                d_p1 += d_E * (  3  * 2 * (-3*p0+3*p1)) +
-                        d_E * 2 * ((-6) * (p0-pt));
-                d_p2 += d_E * 2 * (  3  * (p0-pt));
-                d_pt += d_E * 2 * ((-1) * (3*p0-6*p1+3*p2));
-                // F = sum((p0-pt)*(-3*p0+3*p1))
-                d_p0 += d_F * (1 * (-3*p0+3*p1)) +
-                        d_F * ((-3) * (p0-pt));
-                d_p1 += d_F * (3 * (p0-pt));
-                d_pt += d_F * ((-1) * (-3*p0+3*p1));
-            }
-        }
-        atomic_add(d_path.points + 2 * i0, d_p0);
-        atomic_add(d_path.points + 2 * i1, d_p1);
-        atomic_add(d_path.points + 2 * i2, d_p2);
-        atomic_add(d_path.points + 2 * i3, d_p3);
-    } else {
-        assert(false);
-    }
-}
-
-DEVICE
-inline
-void d_closest_point(const Rect &rect,
-                     const Vector2f &pt,
-                     const Vector2f &d_closest_pt,
-                     Rect &d_rect,
-                     Vector2f &d_pt) {
-    auto dist = [&](const Vector2f &p0, const Vector2f &p1) -> float {
-        // project pt to line
-        auto t = dot(pt - p0, p1 - p0) / dot(p1 - p0, p1 - p0);
-        if (t < 0) {
-            return distance(p0, pt);
-        } else if (t > 1) {
-            return distance(p1, pt);
-        } else {
-            return distance(p0 + t * (p1 - p0), pt);
-        }
-        // return 0;
-    };
-    auto left_top = rect.p_min;
-    auto right_top = Vector2f{rect.p_max.x, rect.p_min.y};
-    auto left_bottom = Vector2f{rect.p_min.x, rect.p_max.y};
-    auto right_bottom = rect.p_max;
-    auto left_dist = dist(left_top, left_bottom);
-    auto top_dist = dist(left_top, right_top);
-    auto right_dist = dist(right_top, right_bottom);
-    auto bottom_dist = dist(left_bottom, right_bottom);
-    int min_id = 0;
-    auto min_dist = left_dist;
-    if (top_dist < min_dist) { min_dist = top_dist; min_id = 1; }
-    if (right_dist < min_dist) { min_dist = right_dist; min_id = 2; }
-    if (bottom_dist < min_dist) { min_dist = bottom_dist; min_id = 3; }
-
-    auto d_update = [&](const Vector2f &p0, const Vector2f &p1,
-                        const Vector2f &d_closest_pt,
-                        Vector2f &d_p0, Vector2f &d_p1) {
-        // project pt to line
-        auto t = dot(pt - p0, p1 - p0) / dot(p1 - p0, p1 - p0);
-        if (t < 0) {
-            d_p0 += d_closest_pt;
-        } else if (t > 1) {
-            d_p1 += d_closest_pt;
-        } else {
-            // p = p0 + t * (p1 - p0)
-            auto d_p = d_closest_pt;
-            d_p0 += d_p * (1 - t);
-            d_p1 += d_p * t;
-            auto d_t = sum(d_p * (p1 - p0));
-            // t = dot(pt - p0, p1 - p0) / dot(p1 - p0, p1 - p0)
-            auto d_numerator = d_t / dot(p1 - p0, p1 - p0);
-            auto d_denominator = d_t * (-t) / dot(p1 - p0, p1 - p0);
-            // numerator = dot(pt - p0, p1 - p0)
-            d_pt += (p1 - p0) * d_numerator;
-            d_p1 += (pt - p0) * d_numerator;
-            d_p0 += ((p0 - p1) + (p0 - pt)) * d_numerator;
-            // denominator = dot(p1 - p0, p1 - p0)
-            d_p1 += 2 * (p1 - p0) * d_denominator;
-            d_p0 += 2 * (p0 - p1) * d_denominator;
-        }
-    };
-    auto d_left_top = Vector2f{0, 0};
-    auto d_right_top = Vector2f{0, 0};
-    auto d_left_bottom = Vector2f{0, 0};
-    auto d_right_bottom = Vector2f{0, 0};
-    if (min_id == 0) {
-        d_update(left_top, left_bottom, d_closest_pt, d_left_top, d_left_bottom);
-    } else if (min_id == 1) {
-        d_update(left_top, right_top, d_closest_pt, d_left_top, d_right_top);
-    } else if (min_id == 2) {
-        d_update(right_top, right_bottom, d_closest_pt, d_right_top, d_right_bottom);
-    } else {
-        assert(min_id == 3);
-        d_update(left_bottom, right_bottom, d_closest_pt, d_left_bottom, d_right_bottom);
-    }
-    auto d_p_min = Vector2f{0, 0};
-    auto d_p_max = Vector2f{0, 0};
-    // left_top = rect.p_min
-    // right_top = Vector2f{rect.p_max.x, rect.p_min.y}
-    // left_bottom = Vector2f{rect.p_min.x, rect.p_max.y}
-    // right_bottom = rect.p_max
-    d_p_min += d_left_top;
-    d_p_max.x += d_right_top.x;
-    d_p_min.y += d_right_top.y;
-    d_p_min.x += d_left_bottom.x;
-    d_p_max.y += d_left_bottom.y;
-    d_p_max += d_right_bottom;
-    atomic_add(d_rect.p_min, d_p_min);
-    atomic_add(d_rect.p_max, d_p_max);
-}
-
-DEVICE
-inline
-void d_closest_point(const Shape &shape,
-                     const Vector2f &pt,
-                     const Vector2f &d_closest_pt,
-                     const ClosestPointPathInfo &path_info,
-                     Shape &d_shape,
-                     Vector2f &d_pt) {
-    switch (shape.type) {
-        case ShapeType::Circle:
-            d_closest_point(*(const Circle *)shape.ptr,
-                            pt,
-                            d_closest_pt,
-                            *(Circle *)d_shape.ptr,
-                            d_pt);
-            break;
-        case ShapeType::Ellipse:
-            // https://www.geometrictools.com/Documentation/DistancePointEllipseEllipsoid.pdf
-            assert(false);
-            break;
-        case ShapeType::Path:
-            d_closest_point(*(const Path *)shape.ptr,
-                            pt,
-                            d_closest_pt,
-                            path_info,
-                            *(Path *)d_shape.ptr,
-                            d_pt);
-            break;
-        case ShapeType::Rect:
-            d_closest_point(*(const Rect *)shape.ptr,
-                            pt,
-                            d_closest_pt,
-                            *(Rect *)d_shape.ptr,
-                            d_pt);
-            break;
-    }
-}
-
-DEVICE
-inline
-void d_compute_distance(const Matrix3x3f &canvas_to_shape,
-                        const Matrix3x3f &shape_to_canvas,
-                        const Shape &shape,
-                        const Vector2f &pt,
-                        const Vector2f &closest_pt,
-                        const ClosestPointPathInfo &path_info,
-                        float d_dist,
-                        Matrix3x3f &d_shape_to_canvas,
-                        Shape &d_shape,
-                        float *d_translation) {
-    if (distance_squared(pt, closest_pt) < 1e-10f) {
-        // The derivative at distance=0 is undefined
-        return;
-    }
-    assert(isfinite(d_dist));
-    // pt is in canvas space, transform it to shape's local space
-    auto local_pt = xform_pt(canvas_to_shape, pt);
-    auto local_closest_pt = xform_pt(canvas_to_shape, closest_pt);
-    // auto local_closest_pt = closest_point(shape, local_pt);
-    // auto closest_pt = xform_pt(shape_group.shape_to_canvas, local_closest_pt);
-    // auto dist = distance(closest_pt, pt);
-    auto d_pt = Vector2f{0, 0};
-    auto d_closest_pt = Vector2f{0, 0};
-    d_distance(closest_pt, pt, d_dist, d_closest_pt, d_pt);
-    assert(isfinite(d_pt));
-    assert(isfinite(d_closest_pt));
-    // auto closest_pt = xform_pt(shape_group.shape_to_canvas, local_closest_pt);
-    auto d_local_closest_pt = Vector2f{0, 0};
-    auto d_shape_to_canvas_ = Matrix3x3f();
-    d_xform_pt(shape_to_canvas, local_closest_pt, d_closest_pt,
-               d_shape_to_canvas_, d_local_closest_pt);
-    assert(isfinite(d_local_closest_pt));
-    auto d_local_pt = Vector2f{0, 0};
-    d_closest_point(shape, local_pt, d_local_closest_pt, path_info, d_shape, d_local_pt);
-    assert(isfinite(d_local_pt));
-    auto d_canvas_to_shape = Matrix3x3f();
-    d_xform_pt(canvas_to_shape,
-               pt,
-               d_local_pt,
-               d_canvas_to_shape,
-               d_pt);
-    // http://jack.valmadre.net/notes/2016/09/04/back-prop-differentials/#back-propagation-using-differentials
-    auto tc2s = transpose(canvas_to_shape);
-    d_shape_to_canvas_ += -tc2s * d_canvas_to_shape * tc2s;
-    atomic_add(&d_shape_to_canvas(0, 0), d_shape_to_canvas_);
-    if (d_translation != nullptr) {
-        atomic_add(d_translation, -d_pt);
-    }
-}
diff --git a/spaces/ma-xu/LIVE/thrust/thrust/mr/allocator.h b/spaces/ma-xu/LIVE/thrust/thrust/mr/allocator.h
deleted file mode 100644
index 4c6c3288601fcacce058fc2ae7f654d334a33827..0000000000000000000000000000000000000000
--- a/spaces/ma-xu/LIVE/thrust/thrust/mr/allocator.h
+++ /dev/null
@@ -1,250 +0,0 @@
-/*
- *  Copyright 2018 NVIDIA Corporation
- *
- *  Licensed under the Apache License, Version 2.0 (the "License");
- *  you may not use this file except in compliance with the License.
- *  You may obtain a copy of the License at
- *
- *      http://www.apache.org/licenses/LICENSE-2.0
- *
- *  Unless required by applicable law or agreed to in writing, software
- *  distributed under the License is distributed on an "AS IS" BASIS,
- *  WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
- *  See the License for the specific language governing permissions and
- *  limitations under the License.
- */
-
-/*! \file allocator.h
- *  \brief Allocator types usable with NPA-based memory resources.
- */
-
-#pragma once
-
-#include <limits>
-
-#include <thrust/detail/config/exec_check_disable.h>
-#include <thrust/detail/type_traits/pointer_traits.h>
-
-#include <thrust/mr/detail/config.h>
-#include <thrust/mr/validator.h>
-#include <thrust/mr/polymorphic_adaptor.h>
-
-namespace thrust
-{
-namespace mr
-{
-
-/*! \addtogroup memory_management Memory Management
- *  \addtogroup memory_management_classes Memory Management Classes
- *  \ingroup memory_management
- *  \{
- */
-
-/*! An \p mr::allocator is a template that fulfills the C++ requirements for Allocators,
- *  allowing to use the NPA-based memory resources where an Allocator is required. Unlike
- *  memory resources, but like other allocators, \p mr::allocator is typed and bound to
- *  allocate object of a specific type, however it can be freely rebound to other types.
- *
- *  \tparam T the type that will be allocated by this allocator.
- *  \tparam MR the upstream memory resource to use for memory allocation. Must derive from
- *      \p thrust::mr::memory_resource and must be \p final (in C++11 and beyond).
- */
-template<typename T, class MR>
-class allocator : private validator<MR>
-{
-public:
-    /*! The pointer to void type of this allocator. */
-    typedef typename MR::pointer void_pointer;
-
-    /*! The value type allocated by this allocator. Equivalent to \p T. */
-    typedef T value_type;
-    /*! The pointer type allocated by this allocator. Equivaled to the pointer type of \p MR rebound to \p T. */
-    typedef typename thrust::detail::pointer_traits<void_pointer>::template rebind<T>::other pointer;
-    /*! The pointer to const type. Equivalent to a pointer type of \p MR reboud to <tt>const T</tt>. */
-    typedef typename thrust::detail::pointer_traits<void_pointer>::template rebind<const T>::other const_pointer;
-    /*! The reference to the type allocated by this allocator. Supports smart references. */
-    typedef typename thrust::detail::pointer_traits<pointer>::reference reference;
-    /*! The const reference to the type allocated by this allocator. Supports smart references. */
-    typedef typename thrust::detail::pointer_traits<const_pointer>::reference const_reference;
-    /*! The size type of this allocator. Always \p std::size_t. */
-    typedef std::size_t size_type;
-    /*! The difference type between pointers allocated by this allocator. */
-    typedef typename thrust::detail::pointer_traits<pointer>::difference_type difference_type;
-
-    /*! Specifies that the allocator shall be propagated on container copy assignment. */
-    typedef detail::true_type propagate_on_container_copy_assignment;
-    /*! Specifies that the allocator shall be propagated on container move assignment. */
-    typedef detail::true_type propagate_on_container_move_assignment;
-    /*! Specifies that the allocator shall be propagated on container swap. */
-    typedef detail::true_type propagate_on_container_swap;
-
-    /*! The \p rebind metafunction provides the type of an \p allocator instantiated with another type.
-     *
-     *  \tparam U the other type to use for instantiation.
-     */
-    template<typename U>
-    struct rebind
-    {
-        /*! The typedef \p other gives the type of the rebound \p allocator.
-         */
-        typedef allocator<U, MR> other;
-    };
-
-    /*! Calculates the maximum number of elements allocated by this allocator.
-     *
-     *  \returns the maximum value of \p std::size_t, divided by the size of \p T.
-     */
-    __thrust_exec_check_disable__
-    __host__ __device__
-    size_type max_size() const
-    {
-        return std::numeric_limits<size_type>::max() / sizeof(T);
-    }
-
-    /*! Constructor.
-     *
-     *  \param resource the resource to be used to allocate raw memory.
-     */
-    __host__ __device__
-    allocator(MR * resource) : mem_res(resource)
-    {
-    }
-
-    /*! Copy constructor. Copies the resource pointer. */
-    template<typename U>
-    __host__ __device__
-    allocator(const allocator<U, MR> & other) : mem_res(other.resource())
-    {
-    }
-
-    /*! Allocates objects of type \p T.
-     *
-     *  \param n number of elements to allocate
-     *  \returns a pointer to the newly allocated storage.
-     */
-    THRUST_NODISCARD
-    __host__
-    pointer allocate(size_type n)
-    {
-        return static_cast<pointer>(mem_res->do_allocate(n * sizeof(T), THRUST_ALIGNOF(T)));
-    }
-
-    /*! Deallocates objects of type \p T.
-     *
-     *  \param p pointer returned by a previous call to \p allocate
-     *  \param n number of elements, passed as an argument to the \p allocate call that produced \p p
-     */
-    __host__
-    void deallocate(pointer p, size_type n)
-    {
-        return mem_res->do_deallocate(p, n * sizeof(T), THRUST_ALIGNOF(T));
-    }
-
-    /*! Extracts the memory resource used by this allocator.
-     *
-     *  \returns the memory resource used by this allocator.
-     */
-    __host__ __device__
-    MR * resource() const
-    {
-        return mem_res;
-    }
-
-private:
-    MR * mem_res;
-};
-
-/*! Compares the allocators for equality by comparing the underlying memory resources. */
-template<typename T, typename MR>
-__host__ __device__
-bool operator==(const allocator<T, MR> & lhs, const allocator<T, MR> & rhs) THRUST_NOEXCEPT
-{
-    return *lhs.resource() == *rhs.resource();
-}
-
-/*! Compares the allocators for inequality by comparing the underlying memory resources. */
-template<typename T, typename MR>
-__host__ __device__
-bool operator!=(const allocator<T, MR> & lhs, const allocator<T, MR> & rhs) THRUST_NOEXCEPT
-{
-    return !(lhs == rhs);
-}
-
-#if THRUST_CPP_DIALECT >= 2011
-
-template<typename T, typename Pointer>
-using polymorphic_allocator = allocator<T, polymorphic_adaptor_resource<Pointer> >;
-
-#else // C++11
-
-template<typename T, typename Pointer>
-class polymorphic_allocator : public allocator<T, polymorphic_adaptor_resource<Pointer> >
-{
-    typedef allocator<T, polymorphic_adaptor_resource<Pointer> > base;
-
-public:
-    /*! Initializes the base class with the parameter \p resource.
-     */
-    polymorphic_allocator(polymorphic_adaptor_resource<Pointer>  * resource) : base(resource)
-    {
-    }
-};
-
-#endif // C++11
-
-/*! A helper allocator class that uses global instances of a given upstream memory resource. Requires the memory resource
- *      to be default constructible.
- *
- *  \tparam T the type that will be allocated by this allocator.
- *  \tparam Upstream the upstream memory resource to use for memory allocation. Must derive from
- *      \p thrust::mr::memory_resource and must be \p final (in C++11 and beyond).
- */
-template<typename T, typename Upstream>
-class stateless_resource_allocator : public thrust::mr::allocator<T, Upstream>
-{
-    typedef thrust::mr::allocator<T, Upstream> base;
-
-public:
-    /*! The \p rebind metafunction provides the type of an \p stateless_resource_allocator instantiated with another type.
-     *
-     *  \tparam U the other type to use for instantiation.
-     */
-    template<typename U>
-    struct rebind
-    {
-        /*! The typedef \p other gives the type of the rebound \p stateless_resource_allocator.
-         */
-        typedef stateless_resource_allocator<U, Upstream> other;
-    };
-
-    /*! Default constructor. Uses \p get_global_resource to get the global instance of \p Upstream and initializes the
-     *      \p allocator base subobject with that resource.
-     */
-    __host__
-    stateless_resource_allocator() : base(get_global_resource<Upstream>())
-    {
-    }
-
-    /*! Copy constructor. Copies the memory resource pointer. */
-    __host__ __device__
-    stateless_resource_allocator(const stateless_resource_allocator & other)
-        : base(other) {}
-
-    /*! Conversion constructor from an allocator of a different type. Copies the memory resource pointer. */
-    template<typename U>
-    __host__ __device__
-    stateless_resource_allocator(const stateless_resource_allocator<U, Upstream> & other)
-        : base(other) {}
-
-#if THRUST_CPP_DIALECT >= 2011
-    stateless_resource_allocator & operator=(const stateless_resource_allocator &) = default;
-#endif
-
-    /*! Destructor. */
-    __host__ __device__
-    ~stateless_resource_allocator() {}
-};
-
-} // end mr
-} // end thrust
-
diff --git a/spaces/ma-xu/LIVE/thrust/thrust/system/cpp/detail/sequence.h b/spaces/ma-xu/LIVE/thrust/thrust/system/cpp/detail/sequence.h
deleted file mode 100644
index c6ae90664ad9538e73febfde86c334011de417c8..0000000000000000000000000000000000000000
--- a/spaces/ma-xu/LIVE/thrust/thrust/system/cpp/detail/sequence.h
+++ /dev/null
@@ -1,22 +0,0 @@
-/*
- *  Copyright 2008-2013 NVIDIA Corporation
- *
- *  Licensed under the Apache License, Version 2.0 (the "License");
- *  you may not use this file except in compliance with the License.
- *  You may obtain a copy of the License at
- *
- *      http://www.apache.org/licenses/LICENSE-2.0
- *
- *  Unless required by applicable law or agreed to in writing, software
- *  distributed under the License is distributed on an "AS IS" BASIS,
- *  WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
- *  See the License for the specific language governing permissions and
- *  limitations under the License.
- */
-
-#pragma once
-
-#include <thrust/detail/config.h>
-
-// this system has no special version of this algorithm 
-
diff --git a/spaces/ma-xu/LIVE/thrust/thrust/system/cuda/detail/sort.h b/spaces/ma-xu/LIVE/thrust/thrust/system/cuda/detail/sort.h
deleted file mode 100644
index 0711c224fe4241402ad0b3283cbb7cd87600f8f8..0000000000000000000000000000000000000000
--- a/spaces/ma-xu/LIVE/thrust/thrust/system/cuda/detail/sort.h
+++ /dev/null
@@ -1,1748 +0,0 @@
-/******************************************************************************
- * Copyright (c) 2016, NVIDIA CORPORATION.  All rights reserved.
- *
- * Redistribution and use in source and binary forms, with or without
- * modification, are permitted provided that the following conditions are met:
- *     * Redistributions of source code must retain the above copyright
- *       notice, this list of conditions and the following disclaimer.
- *     * Redistributions in binary form must reproduce the above copyright
- *       notice, this list of conditions and the following disclaimer in the
- *       documentation and/or other materials provided with the distribution.
- *     * Neither the name of the NVIDIA CORPORATION nor the
- *       names of its contributors may be used to endorse or promote products
- *       derived from this software without specific prior written permission.
- *
- * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
- * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
- * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
- * ARE DISCLAIMED. IN NO EVENT SHALL NVIDIA CORPORATION BE LIABLE FOR ANY
- * DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES
- * (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
- * LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND
- * ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
- * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
- * SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
- *
- ******************************************************************************/
-#pragma once
-
-#if THRUST_DEVICE_COMPILER == THRUST_DEVICE_COMPILER_NVCC
-#include <thrust/detail/cstdint.h>
-#include <thrust/detail/temporary_array.h>
-#include <thrust/system/cuda/detail/util.h>
-#include <thrust/system/cuda/config.h>
-#include <thrust/system/cuda/detail/core/agent_launcher.h>
-#include <thrust/system/cuda/detail/core/util.h>
-#include <cub/device/device_radix_sort.cuh>
-
-#include <thrust/system/cuda/detail/execution_policy.h>
-#include <thrust/system/cuda/detail/par_to_seq.h>
-#include <thrust/detail/trivial_sequence.h>
-#include <thrust/detail/integer_math.h>
-#include <thrust/extrema.h>
-#include <thrust/sort.h>
-#include <thrust/distance.h>
-#include <thrust/sequence.h>
-#include <thrust/detail/alignment.h>
-#include <thrust/type_traits/is_contiguous_iterator.h>
-
-namespace thrust
-{
-namespace cuda_cub {
-
-namespace __merge_sort {
-
-  template <class KeysIt1,
-            class KeysIt2,
-            class Size,
-            class BinaryPred>
-  THRUST_DEVICE_FUNCTION Size
-  merge_path(KeysIt1    keys1,
-             KeysIt2    keys2,
-             Size       keys1_count,
-             Size       keys2_count,
-             Size       diag,
-             BinaryPred binary_pred)
-  {
-    typedef typename iterator_traits<KeysIt1>::value_type key1_type;
-    typedef typename iterator_traits<KeysIt2>::value_type key2_type;
-
-    Size keys1_begin = thrust::max<Size>(0, diag - keys2_count);
-    Size keys1_end   = thrust::min<Size>(diag, keys1_count);
-
-    while (keys1_begin < keys1_end)
-    {
-      Size      mid  = (keys1_begin + keys1_end) >> 1;
-      key1_type key1 = keys1[mid];
-      key2_type key2 = keys2[diag - 1 - mid];
-      bool      pred = binary_pred(key2, key1);
-      if (pred)
-      {
-        keys1_end = mid;
-      }
-      else
-      {
-        keys1_begin = mid + 1;
-      }
-    }
-    return keys1_begin;
-  }
-
-  template <class It, class T2, class CompareOp, int ITEMS_PER_THREAD>
-  THRUST_DEVICE_FUNCTION void
-  serial_merge(It  keys_shared,
-               int keys1_beg,
-               int keys2_beg,
-               int keys1_count,
-               int keys2_count,
-               T2 (&output)[ITEMS_PER_THREAD],
-               int (&indices)[ITEMS_PER_THREAD],
-               CompareOp compare_op)
-  {
-    int keys1_end = keys1_beg + keys1_count;
-    int keys2_end = keys2_beg + keys2_count;
-
-    typedef typename iterator_value<It>::type key_type;
-
-    key_type key1 = keys_shared[keys1_beg];
-    key_type key2 = keys_shared[keys2_beg];
-
-
-#pragma unroll
-    for (int ITEM = 0; ITEM < ITEMS_PER_THREAD; ++ITEM)
-    {
-      bool p = (keys2_beg < keys2_end) &&
-               ((keys1_beg >= keys1_end) ||
-                compare_op(key2,key1));
-
-      output[ITEM]  = p ? key2 : key1;
-      indices[ITEM] = p ? keys2_beg++ : keys1_beg++;
-
-      if (p)
-      {
-        key2 = keys_shared[keys2_beg];
-      }
-      else
-      {
-        key1 = keys_shared[keys1_beg];
-      }
-    }
-  }
-
-  template <int                      _BLOCK_THREADS,
-            int                      _ITEMS_PER_THREAD = 1,
-            cub::BlockLoadAlgorithm  _LOAD_ALGORITHM   = cub::BLOCK_LOAD_DIRECT,
-            cub::CacheLoadModifier   _LOAD_MODIFIER    = cub::LOAD_LDG,
-            cub::BlockStoreAlgorithm _STORE_ALGORITHM  = cub::BLOCK_STORE_DIRECT>
-  struct PtxPolicy
-  {
-    enum
-    {
-      BLOCK_THREADS      = _BLOCK_THREADS,
-      ITEMS_PER_THREAD   = _ITEMS_PER_THREAD,
-      ITEMS_PER_TILE     = _BLOCK_THREADS * _ITEMS_PER_THREAD,
-    };
-
-    static const cub::BlockLoadAlgorithm  LOAD_ALGORITHM  = _LOAD_ALGORITHM;
-    static const cub::CacheLoadModifier   LOAD_MODIFIER   = _LOAD_MODIFIER;
-    static const cub::BlockStoreAlgorithm STORE_ALGORITHM = _STORE_ALGORITHM;
-  }; // PtxPolicy
-
-
-  template<class Arch, class T>
-  struct Tuning;
-
-  template<class T>
-  struct Tuning<sm35,T>
-  {
-    const static int INPUT_SIZE = sizeof(T);
-
-    enum
-    {
-      NOMINAL_4B_ITEMS_PER_THREAD = 11,
-      ITEMS_PER_THREAD            = CUB_MIN(NOMINAL_4B_ITEMS_PER_THREAD, CUB_MAX(1, (NOMINAL_4B_ITEMS_PER_THREAD * 4 / sizeof(T)))),
-    };
-
-    typedef PtxPolicy<256,
-                      ITEMS_PER_THREAD,
-                      cub::BLOCK_LOAD_WARP_TRANSPOSE,
-                      cub::LOAD_LDG,
-                      cub::BLOCK_STORE_WARP_TRANSPOSE>
-        type;
-  };
-
-  template<class T>
-  struct Tuning<sm52,T>
-  {
-    const static int INPUT_SIZE = sizeof(T);
-
-    enum
-    {
-      NOMINAL_4B_ITEMS_PER_THREAD = 15,
-      ITEMS_PER_THREAD            = CUB_MIN(NOMINAL_4B_ITEMS_PER_THREAD, CUB_MAX(1, (NOMINAL_4B_ITEMS_PER_THREAD * 4 / sizeof(T)))),
-    };
-
-    typedef PtxPolicy<512,
-                      ITEMS_PER_THREAD,
-                      cub::BLOCK_LOAD_WARP_TRANSPOSE,
-                      cub::LOAD_LDG,
-                      cub::BLOCK_STORE_WARP_TRANSPOSE>
-        type;
-  };
-
-  template<class T>
-  struct Tuning<sm60,T>
-  {
-    const static int INPUT_SIZE = sizeof(T);
-
-    enum
-    {
-      NOMINAL_4B_ITEMS_PER_THREAD = 17,
-      ITEMS_PER_THREAD            = CUB_MIN(NOMINAL_4B_ITEMS_PER_THREAD, CUB_MAX(1, (NOMINAL_4B_ITEMS_PER_THREAD * 4 / sizeof(T)))),
-    };
-
-    typedef PtxPolicy<256,
-                      ITEMS_PER_THREAD,
-                      cub::BLOCK_LOAD_WARP_TRANSPOSE,
-                      cub::LOAD_DEFAULT,
-                      cub::BLOCK_STORE_WARP_TRANSPOSE>
-        type;
-  };
-
-  template<class T>
-  struct Tuning<sm30,T>
-  {
-    enum
-    {
-      NOMINAL_4B_ITEMS_PER_THREAD = 7,
-      ITEMS_PER_THREAD            = CUB_MIN(NOMINAL_4B_ITEMS_PER_THREAD, CUB_MAX(1, (NOMINAL_4B_ITEMS_PER_THREAD * 4 / sizeof(T)))),
-    };
-
-    typedef PtxPolicy<128,
-                      ITEMS_PER_THREAD,
-                      cub::BLOCK_LOAD_WARP_TRANSPOSE,
-                      cub::LOAD_DEFAULT,
-                      cub::BLOCK_STORE_WARP_TRANSPOSE>
-        type;
-  };
-
-  template <class KeysIt,
-            class ItemsIt,
-            class Size,
-            class CompareOp,
-            class SORT_ITEMS,
-            class STABLE>
-  struct BlockSortAgent
-  {
-    typedef typename iterator_traits<KeysIt>::value_type key_type;
-    typedef typename iterator_traits<ItemsIt>::value_type item_type;
-
-    template <class Arch>
-    struct PtxPlan : Tuning<Arch, key_type>::type
-    {
-      typedef Tuning<Arch,key_type> tuning;
-
-      typedef typename core::LoadIterator<PtxPlan, KeysIt>::type  KeysLoadIt;
-      typedef typename core::LoadIterator<PtxPlan, ItemsIt>::type ItemsLoadIt;
-
-      typedef typename core::BlockLoad<PtxPlan, KeysLoadIt>::type  BlockLoadKeys;
-      typedef typename core::BlockLoad<PtxPlan, ItemsLoadIt>::type BlockLoadItems;
-
-      typedef typename core::BlockStore<PtxPlan, KeysIt>::type     BlockStoreKeysIt;
-      typedef typename core::BlockStore<PtxPlan, ItemsIt>::type    BlockStoreItemsIt;
-      typedef typename core::BlockStore<PtxPlan, key_type*>::type  BlockStoreKeysRaw;
-      typedef typename core::BlockStore<PtxPlan, item_type*>::type BlockStoreItemsRaw;
-
-      union TempStorage
-      {
-        typename BlockLoadKeys::TempStorage   load_keys;
-        typename BlockLoadItems::TempStorage  load_items;
-        typename BlockStoreKeysIt::TempStorage  store_keys_it;
-        typename BlockStoreItemsIt::TempStorage store_items_it;
-        typename BlockStoreKeysRaw::TempStorage  store_keys_raw;
-        typename BlockStoreItemsRaw::TempStorage store_items_raw;
-
-        core::uninitialized_array<key_type, PtxPlan::ITEMS_PER_TILE + 1>  keys_shared;
-        core::uninitialized_array<item_type, PtxPlan::ITEMS_PER_TILE + 1> items_shared;
-      };    // union TempStorage
-    };      // struct PtxPlan
-
-    typedef typename core::specialize_plan_msvc10_war<PtxPlan>::type::type ptx_plan;
-
-    typedef typename ptx_plan::KeysLoadIt         KeysLoadIt;
-    typedef typename ptx_plan::ItemsLoadIt        ItemsLoadIt;
-    typedef typename ptx_plan::BlockLoadKeys      BlockLoadKeys;
-    typedef typename ptx_plan::BlockLoadItems     BlockLoadItems;
-    typedef typename ptx_plan::BlockStoreKeysIt   BlockStoreKeysIt;
-    typedef typename ptx_plan::BlockStoreItemsIt  BlockStoreItemsIt;
-    typedef typename ptx_plan::BlockStoreKeysRaw  BlockStoreKeysRaw;
-    typedef typename ptx_plan::BlockStoreItemsRaw BlockStoreItemsRaw;
-    typedef typename ptx_plan::TempStorage        TempStorage;
-
-    enum
-    {
-      ITEMS_PER_THREAD = ptx_plan::ITEMS_PER_THREAD,
-      BLOCK_THREADS    = ptx_plan::BLOCK_THREADS,
-      ITEMS_PER_TILE   = ptx_plan::ITEMS_PER_TILE
-    };
-
-    struct impl
-    {
-      //---------------------------------------------------------------------
-      // Per thread data
-      //---------------------------------------------------------------------
-
-      bool         ping;
-      TempStorage& storage;
-      KeysLoadIt   keys_in;
-      ItemsLoadIt  items_in;
-      Size         keys_count;
-      KeysIt       keys_out_it;
-      ItemsIt      items_out_it;
-      key_type*    keys_out_raw;
-      item_type*   items_out_raw;
-      CompareOp    compare_op;
-
-      //---------------------------------------------------------------------
-      // Serial stable sort network
-      //---------------------------------------------------------------------
-
-      THRUST_DEVICE_FUNCTION
-      void stable_odd_even_sort(key_type (&keys)[ITEMS_PER_THREAD],
-                                item_type (&items)[ITEMS_PER_THREAD])
-      {
-#pragma unroll
-        for (int I = 0; I < ITEMS_PER_THREAD; ++I)
-        {
-#pragma unroll
-          for (int J = 1 & I; J < ITEMS_PER_THREAD - 1; J += 2)
-          {
-            if (compare_op(keys[J + 1], keys[J]))
-            {
-              using thrust::swap;
-              swap(keys[J], keys[J + 1]);
-              if (SORT_ITEMS::value)
-              {
-                swap(items[J], items[J + 1]);
-              }
-            }
-          }    // inner loop
-        }      // outer loop
-      }
-
-      //---------------------------------------------------------------------
-      // Parallel thread block merge sort
-      //---------------------------------------------------------------------
-
-      THRUST_DEVICE_FUNCTION void
-      block_mergesort(int tid,
-                      int count,
-                      key_type (&keys_loc)[ITEMS_PER_THREAD],
-                      item_type (&items_loc)[ITEMS_PER_THREAD])
-      {
-        using core::uninitialized_array;
-        using core::sync_threadblock;
-
-        // stable sort items in a single thread
-        //
-        stable_odd_even_sort(keys_loc,items_loc);
-
-        // each thread has  sorted keys_loc
-        // merge sort keys_loc in shared memory
-        //
-#pragma unroll
-        for (int coop = 2; coop <= BLOCK_THREADS; coop *= 2)
-        {
-          sync_threadblock();
-
-          // store keys in shmem
-          //
-#pragma unroll
-          for (int ITEM = 0; ITEM < ITEMS_PER_THREAD; ++ITEM)
-          {
-            int idx                  = ITEMS_PER_THREAD * threadIdx.x + ITEM;
-            storage.keys_shared[idx] = keys_loc[ITEM];
-          }
-
-          sync_threadblock();
-
-          int  indices[ITEMS_PER_THREAD];
-
-          int list  = ~(coop - 1) & tid;
-          int start = ITEMS_PER_THREAD * list;
-          int size  = ITEMS_PER_THREAD * (coop >> 1);
-
-          int diag = min(count,
-                         ITEMS_PER_THREAD * ((coop - 1) & tid));
-
-          int keys1_beg = min(count, start);
-          int keys1_end = min(count, keys1_beg + size);
-          int keys2_beg = keys1_end;
-          int keys2_end = min(count, keys2_beg + size);
-
-          int keys1_count = keys1_end - keys1_beg;
-          int keys2_count = keys2_end - keys2_beg;
-
-          int partition_diag = merge_path(&storage.keys_shared[keys1_beg],
-                                          &storage.keys_shared[keys2_beg],
-                                          keys1_count,
-                                          keys2_count,
-                                          diag,
-                                          compare_op);
-
-          int keys1_beg_loc   = keys1_beg + partition_diag;
-          int keys1_end_loc   = keys1_end;
-          int keys2_beg_loc   = keys2_beg + diag - partition_diag;
-          int keys2_end_loc   = keys2_end;
-          int keys1_count_loc = keys1_end_loc - keys1_beg_loc;
-          int keys2_count_loc = keys2_end_loc - keys2_beg_loc;
-          serial_merge(&storage.keys_shared[0],
-                       keys1_beg_loc,
-                       keys2_beg_loc,
-                       keys1_count_loc,
-                       keys2_count_loc,
-                       keys_loc,
-                       indices,
-                       compare_op);
-
-
-          if (SORT_ITEMS::value)
-          {
-            sync_threadblock();
-
-            // store keys in shmem
-            //
-#pragma unroll
-            for (int ITEM = 0; ITEM < ITEMS_PER_THREAD; ++ITEM)
-            {
-              int idx                   = ITEMS_PER_THREAD * threadIdx.x + ITEM;
-              storage.items_shared[idx] = items_loc[ITEM];
-            }
-
-            sync_threadblock();
-
-            // gather items from shmem
-            //
-#pragma unroll
-            for (int ITEM = 0; ITEM < ITEMS_PER_THREAD; ++ITEM)
-            {
-              items_loc[ITEM] = storage.items_shared[indices[ITEM]];
-            }
-          }
-        }
-      }    // func block_merge_sort
-
-      //---------------------------------------------------------------------
-      // Tile processing
-      //---------------------------------------------------------------------
-
-      template <bool IS_LAST_TILE>
-      THRUST_DEVICE_FUNCTION void
-      consume_tile(int  tid,
-                   Size /*tile_idx*/,
-                   Size tile_base,
-                   int  num_remaining)
-      {
-        using core::uninitialized_array;
-        using core::sync_threadblock;
-
-        item_type items_loc[ITEMS_PER_THREAD];
-        if (SORT_ITEMS::value)
-        {
-          BlockLoadItems(storage.load_items)
-              .Load(items_in + tile_base,
-                    items_loc,
-                    num_remaining,
-                    *(items_in + tile_base));
-
-          sync_threadblock();
-        }
-
-        key_type keys_loc[ITEMS_PER_THREAD];
-        if (IS_LAST_TILE)
-        {
-          BlockLoadKeys(storage.load_keys)
-              .Load(keys_in + tile_base,
-                    keys_loc,
-                    num_remaining,
-                    *(keys_in + tile_base));
-        }
-        else
-        {
-          BlockLoadKeys(storage.load_keys)
-              .Load(keys_in + tile_base, keys_loc);
-        }
-
-        if (IS_LAST_TILE)
-        {
-          // if last tile, find valid max_key
-          // and fill the remainig keys with it
-          //
-          key_type max_key = keys_loc[0];
-#pragma unroll
-          for (int ITEM = 1; ITEM < ITEMS_PER_THREAD; ++ITEM)
-          {
-            if (ITEMS_PER_THREAD * tid + ITEM < num_remaining)
-            {
-              max_key = compare_op(max_key, keys_loc[ITEM])
-                            ? keys_loc[ITEM]
-                            : max_key;
-            }
-            else
-            {
-              keys_loc[ITEM] = max_key;
-            }
-          }
-        }
-
-        sync_threadblock();
-
-        if (IS_LAST_TILE)
-        {
-          block_mergesort(tid,
-                          num_remaining,
-                          keys_loc,
-                          items_loc);
-        }
-        else
-        {
-          block_mergesort(tid,
-                          ITEMS_PER_TILE,
-                          keys_loc,
-                          items_loc);
-        }
-
-        sync_threadblock();
-
-        if (ping)
-        {
-          if (IS_LAST_TILE)
-          {
-            BlockStoreKeysIt(storage.store_keys_it)
-                .Store(keys_out_it + tile_base, keys_loc, num_remaining);
-          }
-          else
-          {
-            BlockStoreKeysIt(storage.store_keys_it)
-                .Store(keys_out_it + tile_base, keys_loc);
-          }
-
-          if (SORT_ITEMS::value)
-          {
-            sync_threadblock();
-
-            BlockStoreItemsIt(storage.store_items_it)
-                .Store(items_out_it + tile_base, items_loc, num_remaining);
-          }
-        }
-        else
-        {
-          if (IS_LAST_TILE)
-          {
-            BlockStoreKeysRaw(storage.store_keys_raw)
-                .Store(keys_out_raw + tile_base, keys_loc, num_remaining);
-          }
-          else
-          {
-            BlockStoreKeysRaw(storage.store_keys_raw)
-                .Store(keys_out_raw + tile_base, keys_loc);
-          }
-
-          if (SORT_ITEMS::value)
-          {
-            sync_threadblock();
-
-            BlockStoreItemsRaw(storage.store_items_raw)
-                .Store(items_out_raw + tile_base, items_loc, num_remaining);
-          }
-        }
-      }
-
-      //---------------------------------------------------------------------
-      // Constructor
-      //---------------------------------------------------------------------
-
-      THRUST_DEVICE_FUNCTION
-      impl(bool         ping_,
-           TempStorage& storage_,
-           KeysLoadIt   keys_in_,
-           ItemsLoadIt  items_in_,
-           Size         keys_count_,
-           KeysIt       keys_out_it_,
-           ItemsIt      items_out_it_,
-           key_type*    keys_out_raw_,
-           item_type*   items_out_raw_,
-           CompareOp    compare_op_)
-          : ping(ping_),
-            storage(storage_),
-            keys_in(keys_in_),
-            items_in(items_in_),
-            keys_count(keys_count_),
-            keys_out_it(keys_out_it_),
-            items_out_it(items_out_it_),
-            keys_out_raw(keys_out_raw_),
-            items_out_raw(items_out_raw_),
-            compare_op(compare_op_)
-      {
-        int  tid           = threadIdx.x;
-        Size tile_idx      = blockIdx.x;
-        Size num_tiles     = gridDim.x;
-        Size tile_base     = tile_idx * ITEMS_PER_TILE;
-        int  items_in_tile = min<int>(keys_count - tile_base, ITEMS_PER_TILE);
-        if (tile_idx < num_tiles - 1)
-        {
-          consume_tile<false>(tid, tile_idx, tile_base, ITEMS_PER_TILE);
-        }
-        else
-        {
-          consume_tile<true>(tid, tile_idx, tile_base, items_in_tile);
-        }
-      }
-    };    // struct impl
-
-    //---------------------------------------------------------------------
-    // Agent entry point
-    //---------------------------------------------------------------------
-
-    THRUST_AGENT_ENTRY(bool       ping,
-                       KeysIt     keys_inout,
-                       ItemsIt    items_inout,
-                       Size       keys_count,
-                       key_type*  keys_out,
-                       item_type* items_out,
-                       CompareOp  compare_op,
-                       char*      shmem)
-    {
-      TempStorage& storage = *reinterpret_cast<TempStorage*>(shmem);
-
-      impl(ping,
-           storage,
-           core::make_load_iterator(ptx_plan(), keys_inout),
-           core::make_load_iterator(ptx_plan(), items_inout),
-           keys_count,
-           keys_inout,
-           items_inout,
-           keys_out,
-           items_out,
-           compare_op);
-    }
-  };    // struct BlockSortAgent
-
-  template <class KeysIt,
-            class Size,
-            class CompareOp>
-  struct PartitionAgent
-  {
-    typedef typename iterator_traits<KeysIt>::value_type key_type;
-    template<class Arch>
-    struct PtxPlan : PtxPolicy<256> {};
-
-    typedef core::specialize_plan<PtxPlan> ptx_plan;
-
-    //---------------------------------------------------------------------
-    // Agent entry point
-    //---------------------------------------------------------------------
-
-    THRUST_AGENT_ENTRY(bool      ping,
-                       KeysIt    keys_ping,
-                       key_type* keys_pong,
-                       Size      keys_count,
-                       Size      num_partitions,
-                       Size*     merge_partitions,
-                       CompareOp compare_op,
-                       Size      coop,
-                       int       items_per_tile,
-                       char*     /*shmem*/)
-    {
-      Size partition_idx = blockDim.x * blockIdx.x + threadIdx.x;
-      if (partition_idx < num_partitions)
-      {
-        Size list  = ~(coop - 1) & partition_idx;
-        Size start = items_per_tile * list;
-        Size size  = items_per_tile * (coop >> 1);
-
-        Size keys1_beg = min(keys_count, start);
-        Size keys1_end = min(keys_count, start + size);
-        Size keys2_beg = keys1_end;
-        Size keys2_end = min(keys_count, keys2_beg + size);
-
-
-        Size partition_at = min(keys2_end - keys1_beg,
-                                items_per_tile * ((coop - 1) & partition_idx));
-
-        Size partition_diag = ping ? merge_path(keys_ping + keys1_beg,
-                                                keys_ping + keys2_beg,
-                                                keys1_end - keys1_beg,
-                                                keys2_end - keys2_beg,
-                                                partition_at,
-                                                compare_op)
-                                   : merge_path(keys_pong + keys1_beg,
-                                                keys_pong + keys2_beg,
-                                                keys1_end - keys1_beg,
-                                                keys2_end - keys2_beg,
-                                                partition_at,
-                                                compare_op);
-
-
-        merge_partitions[partition_idx] = keys1_beg + partition_diag;
-      }
-    }
-  };    // struct PartitionAgent
-
-  template <class KeysIt,
-            class ItemsIt,
-            class Size,
-            class CompareOp,
-            class MERGE_ITEMS>
-  struct MergeAgent
-  {
-    typedef typename iterator_traits<KeysIt>::value_type  key_type;
-    typedef typename iterator_traits<ItemsIt>::value_type item_type;
-
-    typedef KeysIt     KeysOutputPongIt;
-    typedef ItemsIt    ItemsOutputPongIt;
-    typedef key_type*  KeysOutputPingIt;
-    typedef item_type* ItemsOutputPingIt;
-
-    template<class Arch>
-    struct PtxPlan : Tuning<Arch,key_type>::type
-    {
-      typedef Tuning<Arch,key_type> tuning;
-
-      typedef typename core::LoadIterator<PtxPlan, KeysIt>::type     KeysLoadPingIt;
-      typedef typename core::LoadIterator<PtxPlan, ItemsIt>::type    ItemsLoadPingIt;
-      typedef typename core::LoadIterator<PtxPlan, key_type*>::type  KeysLoadPongIt;
-      typedef typename core::LoadIterator<PtxPlan, item_type*>::type ItemsLoadPongIt;
-
-      typedef typename core::BlockLoad<PtxPlan, KeysLoadPingIt>::type  BlockLoadKeysPing;
-      typedef typename core::BlockLoad<PtxPlan, ItemsLoadPingIt>::type BlockLoadItemsPing;
-      typedef typename core::BlockLoad<PtxPlan, KeysLoadPongIt>::type  BlockLoadKeysPong;
-      typedef typename core::BlockLoad<PtxPlan, ItemsLoadPongIt>::type BlockLoadItemsPong;
-
-      typedef typename core::BlockStore<PtxPlan, KeysOutputPongIt>::type  BlockStoreKeysPong;
-      typedef typename core::BlockStore<PtxPlan, ItemsOutputPongIt>::type BlockStoreItemsPong;
-      typedef typename core::BlockStore<PtxPlan, KeysOutputPingIt>::type  BlockStoreKeysPing;
-      typedef typename core::BlockStore<PtxPlan, ItemsOutputPingIt>::type BlockStoreItemsPing;
-
-      // gather required temporary storage in a union
-      //
-      union TempStorage
-      {
-        typename BlockLoadKeysPing::TempStorage  load_keys_ping;
-        typename BlockLoadItemsPing::TempStorage load_items_ping;
-        typename BlockLoadKeysPong::TempStorage  load_keys_pong;
-        typename BlockLoadItemsPong::TempStorage load_items_pong;
-
-        typename BlockStoreKeysPing::TempStorage  store_keys_ping;
-        typename BlockStoreItemsPing::TempStorage store_items_ping;
-        typename BlockStoreKeysPong::TempStorage  store_keys_pong;
-        typename BlockStoreItemsPong::TempStorage store_items_pong;
-
-        core::uninitialized_array<key_type, PtxPlan::ITEMS_PER_TILE + 1>  keys_shared;
-        core::uninitialized_array<item_type, PtxPlan::ITEMS_PER_TILE + 1> items_shared;
-      };    // union TempStorage
-    };    // struct PtxPlan
-
-    typedef typename core::specialize_plan_msvc10_war<PtxPlan>::type::type ptx_plan;
-
-    typedef typename ptx_plan::KeysLoadPingIt  KeysLoadPingIt;
-    typedef typename ptx_plan::ItemsLoadPingIt ItemsLoadPingIt;
-    typedef typename ptx_plan::KeysLoadPongIt  KeysLoadPongIt;
-    typedef typename ptx_plan::ItemsLoadPongIt ItemsLoadPongIt;
-
-    typedef typename ptx_plan::BlockLoadKeysPing  BlockLoadKeysPing;
-    typedef typename ptx_plan::BlockLoadItemsPing BlockLoadItemsPing;
-    typedef typename ptx_plan::BlockLoadKeysPong  BlockLoadKeysPong;
-    typedef typename ptx_plan::BlockLoadItemsPong BlockLoadItemsPong;
-
-    typedef typename ptx_plan::BlockStoreKeysPing  BlockStoreKeysPing;
-    typedef typename ptx_plan::BlockStoreItemsPing BlockStoreItemsPing;
-    typedef typename ptx_plan::BlockStoreKeysPong  BlockStoreKeysPong;
-    typedef typename ptx_plan::BlockStoreItemsPong BlockStoreItemsPong;
-
-    typedef typename ptx_plan::TempStorage     TempStorage;
-
-    enum
-    {
-      ITEMS_PER_THREAD = ptx_plan::ITEMS_PER_THREAD,
-      BLOCK_THREADS    = ptx_plan::BLOCK_THREADS,
-      ITEMS_PER_TILE   = ptx_plan::ITEMS_PER_TILE
-    };
-
-    struct impl
-    {
-      //---------------------------------------------------------------------
-      // Per thread data
-      //---------------------------------------------------------------------
-
-      bool            ping;
-      TempStorage&    storage;
-
-      KeysLoadPingIt  keys_in_ping;
-      ItemsLoadPingIt items_in_ping;
-      KeysLoadPongIt  keys_in_pong;
-      ItemsLoadPongIt items_in_pong;
-
-      Size            keys_count;
-
-      KeysOutputPongIt  keys_out_pong;
-      ItemsOutputPongIt items_out_pong;
-      KeysOutputPingIt  keys_out_ping;
-      ItemsOutputPingIt items_out_ping;
-
-      CompareOp       compare_op;
-      Size*           merge_partitions;
-      Size            coop;
-
-      //---------------------------------------------------------------------
-      // Utility functions
-      //---------------------------------------------------------------------
-
-      template <bool IS_FULL_TILE, class T, class It1, class It2>
-      THRUST_DEVICE_FUNCTION void
-      gmem_to_reg(T (&output)[ITEMS_PER_THREAD],
-                  It1 input1,
-                  It2 input2,
-                  int count1,
-                  int count2)
-      {
-        if (IS_FULL_TILE)
-        {
-#pragma unroll
-          for (int ITEM = 0; ITEM < ITEMS_PER_THREAD; ++ITEM)
-          {
-            int idx = BLOCK_THREADS * ITEM + threadIdx.x;
-            output[ITEM] = (idx < count1) ? input1[idx] : input2[idx - count1];
-          }
-        }
-        else
-        {
-#pragma unroll
-          for (int ITEM = 0; ITEM < ITEMS_PER_THREAD; ++ITEM)
-          {
-            int idx = BLOCK_THREADS * ITEM + threadIdx.x;
-            if (idx < count1 + count2)
-            {
-              output[ITEM] = (idx < count1) ? input1[idx] : input2[idx - count1];
-            }
-          }
-        }
-      }
-
-      template <class T, class It>
-      THRUST_DEVICE_FUNCTION void
-      reg_to_shared(It output,
-                    T (&input)[ITEMS_PER_THREAD])
-      {
-#pragma unroll
-        for (int ITEM = 0; ITEM < ITEMS_PER_THREAD; ++ITEM)
-        {
-          int idx = BLOCK_THREADS * ITEM + threadIdx.x;
-          output[idx] = input[ITEM];
-        }
-      }
-
-      //---------------------------------------------------------------------
-      // Tile processing
-      //---------------------------------------------------------------------
-
-      template <bool IS_FULL_TILE>
-      THRUST_DEVICE_FUNCTION void
-      consume_tile(int  tid,
-                   Size tile_idx,
-                   Size tile_base,
-                   int  count)
-      {
-        using core::sync_threadblock;
-        using core::uninitialized_array;
-
-        Size partition_beg = merge_partitions[tile_idx + 0];
-        Size partition_end = merge_partitions[tile_idx + 1];
-
-        Size list = ~(coop - 1) & tile_idx;
-        Size start = ITEMS_PER_TILE * list;
-        Size size  = ITEMS_PER_TILE * (coop >> 1);
-
-        Size diag   = ITEMS_PER_TILE * tile_idx - start;
-
-        Size keys1_beg = partition_beg;
-        Size keys1_end = partition_end;
-        Size keys2_beg = min<Size>(keys_count, 2 * start + size + diag - partition_beg);
-        Size keys2_end = min<Size>(keys_count, 2 * start + size + diag + ITEMS_PER_TILE - partition_end);
-
-        if (coop - 1 == ((coop - 1) & tile_idx))
-        {
-          keys1_end = min(keys_count, start + size);
-          keys2_end = min(keys_count, start + size * 2);
-        }
-
-        // number of keys per tile
-        //
-        int num_keys1 = static_cast<int>(keys1_end - keys1_beg);
-        int num_keys2 = static_cast<int>(keys2_end - keys2_beg);
-
-        // load keys1 & keys2
-        key_type keys_loc[ITEMS_PER_THREAD];
-        if (ping)
-        {
-          gmem_to_reg<IS_FULL_TILE>(keys_loc,
-                                    keys_in_ping + keys1_beg,
-                                    keys_in_ping + keys2_beg,
-                                    num_keys1,
-                                    num_keys2);
-        }
-        else
-        {
-          gmem_to_reg<IS_FULL_TILE>(keys_loc,
-                                    keys_in_pong + keys1_beg,
-                                    keys_in_pong + keys2_beg,
-                                    num_keys1,
-                                    num_keys2);
-        }
-        reg_to_shared(&storage.keys_shared[0], keys_loc);
-
-        // preload items into registers already
-        //
-        item_type items_loc[ITEMS_PER_THREAD];
-        if (MERGE_ITEMS::value)
-        {
-          if (ping)
-          {
-            gmem_to_reg<IS_FULL_TILE>(items_loc,
-                                      items_in_ping + keys1_beg,
-                                      items_in_ping + keys2_beg,
-                                      num_keys1,
-                                      num_keys2);
-          }
-          else
-          {
-            gmem_to_reg<IS_FULL_TILE>(items_loc,
-                                      items_in_pong + keys1_beg,
-                                      items_in_pong + keys2_beg,
-                                      num_keys1,
-                                      num_keys2);
-          }
-        }
-
-        sync_threadblock();
-
-        // use binary search in shared memory
-        // to find merge path for each of thread
-        // we can use int type here, because the number of
-        // items in shared memory is limited
-        //
-        int diag0_loc = min<Size>(num_keys1 + num_keys2,
-                                  ITEMS_PER_THREAD * tid);
-
-        int keys1_beg_loc = merge_path(&storage.keys_shared[0],
-                                       &storage.keys_shared[num_keys1],
-                                       num_keys1,
-                                       num_keys2,
-                                       diag0_loc,
-                                       compare_op);
-        int keys1_end_loc = num_keys1;
-        int keys2_beg_loc = diag0_loc - keys1_beg_loc;
-        int keys2_end_loc = num_keys2;
-
-        int num_keys1_loc = keys1_end_loc - keys1_beg_loc;
-        int num_keys2_loc = keys2_end_loc - keys2_beg_loc;
-
-        // perform serial merge
-        //
-        int indices[ITEMS_PER_THREAD];
-
-        serial_merge(&storage.keys_shared[0],
-                     keys1_beg_loc,
-                     keys2_beg_loc + num_keys1,
-                     num_keys1_loc,
-                     num_keys2_loc,
-                     keys_loc,
-                     indices,
-                     compare_op);
-
-        sync_threadblock();
-
-        // write keys
-        //
-        if (ping)
-        {
-          if (IS_FULL_TILE)
-          {
-            BlockStoreKeysPing(storage.store_keys_ping)
-                .Store(keys_out_ping + tile_base, keys_loc);
-          }
-          else
-          {
-            BlockStoreKeysPing(storage.store_keys_ping)
-                .Store(keys_out_ping + tile_base, keys_loc, num_keys1 + num_keys2);
-          }
-        }
-        else
-        {
-          if (IS_FULL_TILE)
-          {
-            BlockStoreKeysPong(storage.store_keys_pong)
-                .Store(keys_out_pong + tile_base, keys_loc);
-          }
-          else
-          {
-            BlockStoreKeysPong(storage.store_keys_pong)
-                .Store(keys_out_pong + tile_base, keys_loc, num_keys1 + num_keys2);
-          }
-        }
-
-        // if items are provided, merge them
-        if (MERGE_ITEMS::value)
-        {
-          sync_threadblock();
-
-          reg_to_shared(&storage.items_shared[0], items_loc);
-
-          sync_threadblock();
-
-          // gather items from shared mem
-          //
-#pragma unroll
-          for (int ITEM = 0; ITEM < ITEMS_PER_THREAD; ++ITEM)
-          {
-            items_loc[ITEM] = storage.items_shared[indices[ITEM]];
-          }
-
-          sync_threadblock();
-
-          // write from reg to gmem
-          //
-          if (ping)
-          {
-            if (IS_FULL_TILE)
-            {
-              BlockStoreItemsPing(storage.store_items_ping)
-                  .Store(items_out_ping + tile_base, items_loc);
-            }
-            else
-            {
-              BlockStoreItemsPing(storage.store_items_ping)
-                  .Store(items_out_ping + tile_base, items_loc, count);
-            }
-          }
-          else
-          {
-            if (IS_FULL_TILE)
-            {
-              BlockStoreItemsPong(storage.store_items_pong)
-                  .Store(items_out_pong + tile_base, items_loc);
-            }
-            else
-            {
-              BlockStoreItemsPong(storage.store_items_pong)
-                  .Store(items_out_pong + tile_base, items_loc, count);
-            }
-          }
-        }
-      }
-
-      //---------------------------------------------------------------------
-      // Constructor
-      //---------------------------------------------------------------------
-
-      THRUST_DEVICE_FUNCTION
-      impl(bool              ping_,
-           TempStorage&      storage_,
-           KeysLoadPingIt    keys_in_ping_,
-           ItemsLoadPingIt   items_in_ping_,
-           KeysLoadPongIt    keys_in_pong_,
-           ItemsLoadPongIt   items_in_pong_,
-           Size              keys_count_,
-           KeysOutputPingIt  keys_out_ping_,
-           ItemsOutputPingIt items_out_ping_,
-           KeysOutputPongIt  keys_out_pong_,
-           ItemsOutputPongIt items_out_pong_,
-           CompareOp         compare_op_,
-           Size*             merge_partitions_,
-           Size              coop_)
-          : ping(ping_),
-            storage(storage_),
-            keys_in_ping(keys_in_ping_),
-            items_in_ping(items_in_ping_),
-            keys_in_pong(keys_in_pong_),
-            items_in_pong(items_in_pong_),
-            keys_count(keys_count_),
-            keys_out_pong(keys_out_pong_),
-            items_out_pong(items_out_pong_),
-            keys_out_ping(keys_out_ping_),
-            items_out_ping(items_out_ping_),
-            compare_op(compare_op_),
-            merge_partitions(merge_partitions_),
-            coop(coop_)
-      {
-        // XXX with 8.5 chaging type to Size (or long long) results in error!
-        int  tile_idx      = blockIdx.x;
-        Size num_tiles     = gridDim.x;
-        Size tile_base     = Size(tile_idx) * ITEMS_PER_TILE;
-        int tid           = threadIdx.x;
-        int items_in_tile = static_cast<int>(min((Size)ITEMS_PER_TILE,
-                                                 keys_count - tile_base));
-        if (tile_idx < num_tiles - 1)
-        {
-          consume_tile<true>(tid,
-                             tile_idx,
-                             tile_base,
-                             ITEMS_PER_TILE);
-        }
-        else
-        {
-          consume_tile<false>(tid,
-                              tile_idx,
-                              tile_base,
-                              items_in_tile);
-        }
-      }
-    };    // struct impl
-
-    //---------------------------------------------------------------------
-    // Agent entry point
-    //---------------------------------------------------------------------
-
-    THRUST_AGENT_ENTRY(bool       ping,
-                       KeysIt     keys_ping,
-                       ItemsIt    items_ping,
-                       Size       keys_count,
-                       key_type*  keys_pong,
-                       item_type* items_pong,
-                       CompareOp  compare_op,
-                       Size*      merge_partitions,
-                       Size       coop,
-                       char*      shmem)
-    {
-      TempStorage& storage = *reinterpret_cast<TempStorage*>(shmem);
-
-      impl(ping,
-           storage,
-           core::make_load_iterator(ptx_plan(), keys_ping),
-           core::make_load_iterator(ptx_plan(), items_ping),
-           core::make_load_iterator(ptx_plan(), keys_pong),
-           core::make_load_iterator(ptx_plan(), items_pong),
-           keys_count,
-           keys_pong,
-           items_pong,
-           keys_ping,
-           items_ping,
-           compare_op,
-           merge_partitions,
-           coop);
-    }
-  };    // struct MergeAgent;
-
-  /////////////////////////
-
-  template <class SORT_ITEMS,
-            class STABLE,
-            class KeysIt,
-            class ItemsIt,
-            class Size,
-            class CompareOp>
-  THRUST_RUNTIME_FUNCTION cudaError_t
-  doit_step(void*        d_temp_storage,
-            size_t&      temp_storage_bytes,
-            KeysIt       keys,
-            ItemsIt      items,
-            Size         keys_count,
-            CompareOp    compare_op,
-            cudaStream_t stream,
-            bool         debug_sync)
-  {
-    using core::AgentPlan;
-    using core::get_agent_plan;
-
-    typedef typename iterator_traits<KeysIt>::value_type  key_type;
-    typedef typename iterator_traits<ItemsIt>::value_type item_type;
-
-    typedef core::AgentLauncher<
-        BlockSortAgent<KeysIt,
-                       ItemsIt,
-                       Size,
-                       CompareOp,
-                       SORT_ITEMS,
-                       STABLE> >
-        block_sort_agent;
-
-    typedef core::AgentLauncher<PartitionAgent<KeysIt, Size, CompareOp> >
-        partition_agent;
-
-    typedef core::AgentLauncher<
-        MergeAgent<KeysIt,
-                   ItemsIt,
-                   Size,
-                   CompareOp,
-                   SORT_ITEMS> >
-        merge_agent;
-
-    cudaError_t status = cudaSuccess;
-
-    if (keys_count == 0)
-      return status;
-
-    typename core::get_plan<partition_agent>::type partition_plan =
-        partition_agent::get_plan();
-
-    typename core::get_plan<merge_agent>::type merge_plan =
-        merge_agent::get_plan(stream);
-
-    AgentPlan block_sort_plan = merge_plan;
-
-    int tile_size = merge_plan.items_per_tile;
-    Size num_tiles = (keys_count + tile_size - 1) / tile_size;
-
-    size_t temp_storage1 = (1 + num_tiles) * sizeof(Size);
-    size_t temp_storage2 = keys_count * sizeof(key_type);
-    size_t temp_storage3 = keys_count * sizeof(item_type) * SORT_ITEMS::value;
-    size_t temp_storage4 = core::vshmem_size(max(block_sort_plan.shared_memory_size,
-                                                 merge_plan.shared_memory_size),
-                                             num_tiles);
-
-    void*  allocations[4]      = {NULL, NULL, NULL, NULL};
-    size_t allocation_sizes[4] = {temp_storage1, temp_storage2, temp_storage3, temp_storage4};
-
-    status = core::alias_storage(d_temp_storage,
-                                 temp_storage_bytes,
-                                 allocations,
-                                 allocation_sizes);
-    CUDA_CUB_RET_IF_FAIL(status);
-
-    if (d_temp_storage == NULL)
-    {
-      return status;
-    };
-
-    int num_passes = static_cast<int>(thrust::detail::log2_ri(num_tiles));
-    bool ping = !(1 & num_passes);
-
-    Size*      merge_partitions = (Size*)allocations[0];
-    key_type*  keys_buffer      = (key_type*)allocations[1];
-    item_type* items_buffer     = (item_type*)allocations[2];
-
-    char* vshmem_ptr = temp_storage4 > 0 ? (char*)allocations[3] : NULL;
-
-
-    block_sort_agent(block_sort_plan, keys_count, stream, vshmem_ptr, "block_sort_agent", debug_sync)
-        .launch(ping, keys, items, keys_count, keys_buffer, items_buffer, compare_op);
-    CUDA_CUB_RET_IF_FAIL(cudaPeekAtLastError());
-
-    size_t num_partitions = num_tiles + 1;
-
-    partition_agent pa(partition_plan, num_partitions, stream, "partition_agent", debug_sync);
-    merge_agent     ma(merge_plan, keys_count, stream, vshmem_ptr, "merge_agent", debug_sync);
-
-    for (int pass = 0; pass < num_passes; ++pass, ping = !ping)
-    {
-      Size coop = Size(2) << pass;
-
-      pa.launch(ping,
-                keys,
-                keys_buffer,
-                keys_count,
-                num_partitions,
-                merge_partitions,
-                compare_op,
-                coop,
-                merge_plan.items_per_tile);
-      CUDA_CUB_RET_IF_FAIL(cudaPeekAtLastError());
-
-
-      ma.launch(ping,
-                keys,
-                items,
-                keys_count,
-                keys_buffer,
-                items_buffer,
-                compare_op,
-                merge_partitions,
-                coop);
-      CUDA_CUB_RET_IF_FAIL(cudaPeekAtLastError());
-    }
-
-    return status;
-  }
-
-  template <typename SORT_ITEMS,
-            typename STABLE,
-            typename Derived,
-            typename KeysIt,
-            typename ItemsIt,
-            typename CompareOp>
-  THRUST_RUNTIME_FUNCTION
-  void merge_sort(execution_policy<Derived>& policy,
-                  KeysIt                     keys_first,
-                  KeysIt                     keys_last,
-                  ItemsIt                    items_first,
-                  CompareOp                  compare_op)
-
-  {
-    typedef typename iterator_traits<KeysIt>::difference_type size_type;
-
-    size_type count = static_cast<size_type>(thrust::distance(keys_first, keys_last));
-
-    size_t       storage_size = 0;
-    cudaStream_t stream       = cuda_cub::stream(policy);
-    bool         debug_sync   = THRUST_DEBUG_SYNC_FLAG;
-
-    cudaError_t status;
-    status = doit_step<SORT_ITEMS, STABLE>(NULL,
-                                           storage_size,
-                                           keys_first,
-                                           items_first,
-                                           count,
-                                           compare_op,
-                                           stream,
-                                           debug_sync);
-    cuda_cub::throw_on_error(status, "merge_sort: failed on 1st step");
-
-    // Allocate temporary storage.
-    thrust::detail::temporary_array<thrust::detail::uint8_t, Derived>
-      tmp(policy, storage_size);
-    void *ptr = static_cast<void*>(tmp.data().get());
-
-    status = doit_step<SORT_ITEMS, STABLE>(ptr,
-                                           storage_size,
-                                           keys_first,
-                                           items_first,
-                                           count,
-                                           compare_op,
-                                           stream,
-                                           debug_sync);
-    cuda_cub::throw_on_error(status, "merge_sort: failed on 2nd step");
-
-    status = cuda_cub::synchronize(policy);
-    cuda_cub::throw_on_error(status, "merge_sort: failed to synchronize");
-  }
-}    // namespace __merge_sort
-
-namespace __radix_sort {
-
-  template <class SORT_ITEMS, class Comparator>
-  struct dispatch;
-
-  // sort keys in ascending order
-  template <class K>
-  struct dispatch<thrust::detail::false_type, thrust::less<K> >
-  {
-    template <class Key, class Item, class Size>
-    THRUST_RUNTIME_FUNCTION static cudaError_t
-    doit(void*                    d_temp_storage,
-         size_t&                  temp_storage_bytes,
-         cub::DoubleBuffer<Key>&  keys_buffer,
-         cub::DoubleBuffer<Item>& /*items_buffer*/,
-         Size                     count,
-         cudaStream_t             stream,
-         bool                     debug_sync)
-    {
-      return cub::DeviceRadixSort::SortKeys(d_temp_storage,
-                                            temp_storage_bytes,
-                                            keys_buffer,
-                                            static_cast<int>(count),
-                                            0,
-                                            static_cast<int>(sizeof(Key) * 8),
-                                            stream,
-                                            debug_sync);
-    }
-  }; // struct dispatch -- sort keys in ascending order;
-
-  // sort keys in descending order
-  template <class K>
-  struct dispatch<thrust::detail::false_type, thrust::greater<K> >
-  {
-    template <class Key, class Item, class Size>
-    THRUST_RUNTIME_FUNCTION static cudaError_t
-    doit(void*                    d_temp_storage,
-         size_t&                  temp_storage_bytes,
-         cub::DoubleBuffer<Key>&  keys_buffer,
-         cub::DoubleBuffer<Item>& /*items_buffer*/,
-         Size                     count,
-         cudaStream_t             stream,
-         bool                     debug_sync)
-    {
-      return cub::DeviceRadixSort::SortKeysDescending(d_temp_storage,
-                                                      temp_storage_bytes,
-                                                      keys_buffer,
-                                                      static_cast<int>(count),
-                                                      0,
-                                                      static_cast<int>(sizeof(Key) * 8),
-                                                      stream,
-                                                      debug_sync);
-    }
-  }; // struct dispatch -- sort keys in descending order;
-
-  // sort pairs in ascending order
-  template <class K>
-  struct dispatch<thrust::detail::true_type, thrust::less<K> >
-  {
-    template <class Key, class Item, class Size>
-    THRUST_RUNTIME_FUNCTION static cudaError_t
-    doit(void*                    d_temp_storage,
-         size_t&                  temp_storage_bytes,
-         cub::DoubleBuffer<Key>&  keys_buffer,
-         cub::DoubleBuffer<Item>& items_buffer,
-         Size                     count,
-         cudaStream_t             stream,
-         bool                     debug_sync)
-    {
-      return cub::DeviceRadixSort::SortPairs(d_temp_storage,
-                                             temp_storage_bytes,
-                                             keys_buffer,
-                                             items_buffer,
-                                             static_cast<int>(count),
-                                             0,
-                                             static_cast<int>(sizeof(Key) * 8),
-                                             stream,
-                                             debug_sync);
-    }
-  }; // struct dispatch -- sort pairs in ascending order;
-
-  // sort pairs in descending order
-  template <class K>
-  struct dispatch<thrust::detail::true_type, thrust::greater<K> >
-  {
-    template <class Key, class Item, class Size>
-    THRUST_RUNTIME_FUNCTION static cudaError_t
-    doit(void*                    d_temp_storage,
-         size_t&                  temp_storage_bytes,
-         cub::DoubleBuffer<Key>&  keys_buffer,
-         cub::DoubleBuffer<Item>& items_buffer,
-         Size                     count,
-         cudaStream_t             stream,
-         bool                     debug_sync)
-    {
-      return cub::DeviceRadixSort::SortPairsDescending(d_temp_storage,
-                                                       temp_storage_bytes,
-                                                       keys_buffer,
-                                                       items_buffer,
-                                                       static_cast<int>(count),
-                                                       0,
-                                                       static_cast<int>(sizeof(Key) * 8),
-                                                       stream,
-                                                       debug_sync);
-    }
-  }; // struct dispatch -- sort pairs in descending order;
-
-  template <typename SORT_ITEMS,
-            typename Derived,
-            typename Key,
-            typename Item,
-            typename Size,
-            typename CompareOp>
-  THRUST_RUNTIME_FUNCTION
-  void radix_sort(execution_policy<Derived>& policy,
-                  Key*                       keys,
-                  Item*                      items,
-                  Size                       count,
-                  CompareOp)
-  {
-    size_t       temp_storage_bytes = 0;
-    cudaStream_t stream             = cuda_cub::stream(policy);
-    bool         debug_sync         = THRUST_DEBUG_SYNC_FLAG;
-
-    cub::DoubleBuffer<Key>  keys_buffer(keys, NULL);
-    cub::DoubleBuffer<Item> items_buffer(items, NULL);
-
-    Size keys_count = count;
-    Size items_count = SORT_ITEMS::value ? count : 0;
-
-    cudaError_t status;
-
-    status = dispatch<SORT_ITEMS, CompareOp>::doit(NULL,
-                                                   temp_storage_bytes,
-                                                   keys_buffer,
-                                                   items_buffer,
-                                                   keys_count,
-                                                   stream,
-                                                   debug_sync);
-    cuda_cub::throw_on_error(status, "radix_sort: failed on 1st step");
-
-    size_t keys_temp_storage  = core::align_to(sizeof(Key) * keys_count, 128);
-    size_t items_temp_storage = core::align_to(sizeof(Item) * items_count, 128);
-
-    size_t storage_size = keys_temp_storage
-                        + items_temp_storage
-                        + temp_storage_bytes;
-
-    // Allocate temporary storage.
-    thrust::detail::temporary_array<thrust::detail::uint8_t, Derived>
-      tmp(policy, storage_size);
-
-    keys_buffer.d_buffers[1]  = thrust::detail::aligned_reinterpret_cast<Key*>(
-      tmp.data().get()
-    );
-    items_buffer.d_buffers[1] = thrust::detail::aligned_reinterpret_cast<Item*>(
-      tmp.data().get() + keys_temp_storage
-    );
-    void *ptr = static_cast<void*>(
-      tmp.data().get() + keys_temp_storage + items_temp_storage
-    );
-
-    status = dispatch<SORT_ITEMS, CompareOp>::doit(ptr,
-                                                   temp_storage_bytes,
-                                                   keys_buffer,
-                                                   items_buffer,
-                                                   keys_count,
-                                                   stream,
-                                                   debug_sync);
-    cuda_cub::throw_on_error(status, "radix_sort: failed on 2nd step");
-
-    if (keys_buffer.selector != 0)
-    {
-      Key* temp_ptr = reinterpret_cast<Key*>(keys_buffer.d_buffers[1]);
-      cuda_cub::copy_n(policy, temp_ptr, keys_count, keys);
-    }
-    if (SORT_ITEMS::value && items_buffer.selector != 0)
-    {
-      Item* temp_ptr = reinterpret_cast<Item*>(items_buffer.d_buffers[1]);
-      cuda_cub::copy_n(policy, temp_ptr, items_count, items);
-    }
-  }
-}    // __radix_sort
-
-//---------------------------------------------------------------------
-// Smart sort picks at compile-time whether to dispatch radix or merge sort
-//---------------------------------------------------------------------
-
-namespace __smart_sort {
-
-  template <class Key, class CompareOp>
-  struct can_use_primitive_sort
-      : thrust::detail::and_<
-            thrust::detail::is_arithmetic<Key>,
-            thrust::detail::or_<
-                thrust::detail::is_same<CompareOp, thrust::less<Key> >,
-                thrust::detail::is_same<CompareOp, thrust::greater<Key> > > > {};
-
-  template <class Iterator, class CompareOp>
-  struct enable_if_primitive_sort
-      : thrust::detail::enable_if<
-            can_use_primitive_sort<typename iterator_value<Iterator>::type,
-                                   CompareOp>::value> {};
-
-  template <class Iterator, class CompareOp>
-  struct enable_if_comparison_sort
-      : thrust::detail::disable_if<
-            can_use_primitive_sort<typename iterator_value<Iterator>::type,
-                                   CompareOp>::value> {};
-
-
-  template <class SORT_ITEMS,
-            class STABLE,
-            class Policy,
-            class KeysIt,
-            class ItemsIt,
-            class CompareOp>
-  THRUST_RUNTIME_FUNCTION typename enable_if_comparison_sort<KeysIt, CompareOp>::type
-  smart_sort(Policy&   policy,
-             KeysIt    keys_first,
-             KeysIt    keys_last,
-             ItemsIt   items_first,
-             CompareOp compare_op)
-  {
-    __merge_sort::merge_sort<SORT_ITEMS, STABLE>(policy,
-                                                 keys_first,
-                                                 keys_last,
-                                                 items_first,
-                                                 compare_op);
-
-  }
-
-  template <class SORT_ITEMS,
-            class STABLE,
-            class Policy,
-            class KeysIt,
-            class ItemsIt,
-            class CompareOp>
-  THRUST_RUNTIME_FUNCTION typename enable_if_primitive_sort<KeysIt, CompareOp>::type
-  smart_sort(execution_policy<Policy>& policy,
-             KeysIt                    keys_first,
-             KeysIt                    keys_last,
-             ItemsIt                   items_first,
-             CompareOp                 compare_op)
-  {
-    // ensure sequences have trivial iterators
-    thrust::detail::trivial_sequence<KeysIt, Policy>
-        keys(policy, keys_first, keys_last);
-
-    if (SORT_ITEMS::value)
-    {
-      thrust::detail::trivial_sequence<ItemsIt, Policy>
-          values(policy, items_first, items_first + (keys_last - keys_first));
-
-      __radix_sort::radix_sort<SORT_ITEMS>(
-          policy,
-          thrust::raw_pointer_cast(&*keys.begin()),
-          thrust::raw_pointer_cast(&*values.begin()),
-          keys_last - keys_first,
-          compare_op);
-
-      if (!is_contiguous_iterator<ItemsIt>::value)
-      {
-        cuda_cub::copy(policy, values.begin(), values.end(), items_first);
-      }
-    }
-    else
-    {
-      __radix_sort::radix_sort<SORT_ITEMS>(
-          policy,
-          thrust::raw_pointer_cast(&*keys.begin()),
-          thrust::raw_pointer_cast(&*keys.begin()),
-          keys_last - keys_first,
-          compare_op);
-    }
-
-    // copy results back, if necessary
-    if (!is_contiguous_iterator<KeysIt>::value)
-    {
-      cuda_cub::copy(policy, keys.begin(), keys.end(), keys_first);
-    }
-  }
-}    // namespace __smart_sort
-
-
-//-------------------------
-// Thrust API entry points
-//-------------------------
-
-
-__thrust_exec_check_disable__
-template <class Derived, class ItemsIt, class CompareOp>
-void __host__ __device__
-sort(execution_policy<Derived>& policy,
-     ItemsIt                    first,
-     ItemsIt                    last,
-     CompareOp                  compare_op)
-{
-  if (__THRUST_HAS_CUDART__)
-  {
-    typedef typename thrust::iterator_value<ItemsIt>::type item_type;
-    __smart_sort::smart_sort<thrust::detail::false_type, thrust::detail::false_type>(
-        policy, first, last, (item_type*)NULL, compare_op);
-  }
-  else
-  {
-#if !__THRUST_HAS_CUDART__
-    thrust::sort(cvt_to_seq(derived_cast(policy)), first, last, compare_op);
-#endif
-  }
-}
-
-__thrust_exec_check_disable__
-template <class Derived, class ItemsIt, class CompareOp>
-void __host__ __device__
-stable_sort(execution_policy<Derived>& policy,
-            ItemsIt                    first,
-            ItemsIt                    last,
-            CompareOp                  compare_op)
-{
-  if (__THRUST_HAS_CUDART__)
-  {
-    typedef typename thrust::iterator_value<ItemsIt>::type item_type;
-    __smart_sort::smart_sort<thrust::detail::false_type, thrust::detail::true_type>(
-        policy, first, last, (item_type*)NULL, compare_op);
-  }
-  else
-  {
-#if !__THRUST_HAS_CUDART__
-    thrust::stable_sort(cvt_to_seq(derived_cast(policy)), first, last, compare_op);
-#endif
-  }
-}
-
-__thrust_exec_check_disable__
-template <class Derived, class KeysIt, class ValuesIt, class CompareOp>
-void __host__ __device__
-sort_by_key(execution_policy<Derived>& policy,
-            KeysIt                     keys_first,
-            KeysIt                     keys_last,
-            ValuesIt                   values,
-            CompareOp                  compare_op)
-{
-  if (__THRUST_HAS_CUDART__)
-  {
-    __smart_sort::smart_sort<thrust::detail::true_type, thrust::detail::false_type>(
-        policy, keys_first, keys_last, values, compare_op);
-  }
-  else
-  {
-#if !__THRUST_HAS_CUDART__
-    thrust::sort_by_key(
-        cvt_to_seq(derived_cast(policy)), keys_first, keys_last, values, compare_op);
-#endif
-  }
-}
-
-__thrust_exec_check_disable__
-template <class Derived,
-          class KeysIt,
-          class ValuesIt,
-          class CompareOp>
-void __host__ __device__
-stable_sort_by_key(execution_policy<Derived> &policy,
-            KeysIt                     keys_first,
-            KeysIt                     keys_last,
-            ValuesIt                   values,
-            CompareOp                  compare_op)
-{
-  if (__THRUST_HAS_CUDART__)
-  {
-    __smart_sort::smart_sort<thrust::detail::true_type, thrust::detail::true_type>(
-        policy, keys_first, keys_last, values, compare_op);
-  }
-  else
-  {
-#if !__THRUST_HAS_CUDART__
-    thrust::stable_sort_by_key(
-        cvt_to_seq(derived_cast(policy)), keys_first, keys_last, values, compare_op);
-#endif
-  }
-}
-
-// API with default comparator
-
-template <class Derived, class ItemsIt>
-void __host__ __device__
-sort(execution_policy<Derived>& policy,
-     ItemsIt                    first,
-     ItemsIt                    last)
-{
-  typedef typename thrust::iterator_value<ItemsIt>::type item_type;
-  cuda_cub::sort(policy, first, last, less<item_type>());
-}
-
-template <class Derived, class ItemsIt>
-void __host__ __device__
-stable_sort(execution_policy<Derived>& policy,
-            ItemsIt                    first,
-            ItemsIt                    last)
-{
-  typedef typename thrust::iterator_value<ItemsIt>::type item_type;
-  cuda_cub::stable_sort(policy, first, last, less<item_type>());
-}
-
-template <class Derived, class KeysIt, class ValuesIt>
-void __host__ __device__
-sort_by_key(execution_policy<Derived>& policy,
-            KeysIt                     keys_first,
-            KeysIt                     keys_last,
-            ValuesIt                   values)
-{
-  typedef typename thrust::iterator_value<KeysIt>::type key_type;
-  cuda_cub::sort_by_key(policy, keys_first, keys_last, values, less<key_type>());
-}
-
-template <class Derived, class KeysIt, class ValuesIt>
-void __host__ __device__
-stable_sort_by_key(
-    execution_policy<Derived>& policy, KeysIt keys_first, KeysIt keys_last, ValuesIt values)
-{
-  typedef typename thrust::iterator_value<KeysIt>::type key_type;
-  cuda_cub::stable_sort_by_key(policy, keys_first, keys_last, values, less<key_type>());
-}
-
-
-}    // namespace cuda_cub
-} // end namespace thrust
-#endif
diff --git a/spaces/mabzak/Youtube-Comment-Sentimen-Analisis/app.py b/spaces/mabzak/Youtube-Comment-Sentimen-Analisis/app.py
deleted file mode 100644
index 4d5de15c9679717ecf087dce24537fb383d7ec09..0000000000000000000000000000000000000000
--- a/spaces/mabzak/Youtube-Comment-Sentimen-Analisis/app.py
+++ /dev/null
@@ -1,122 +0,0 @@
-from tqdm import tqdm
-from itertools import islice
-from youtube_comment_downloader import *
-from transformers import AutoTokenizer, AutoModelForSequenceClassification, pipeline
-
-import matplotlib.pyplot as plt
-import csv
-import streamlit as st
-import pandas as pd
-import base64
-
- 
-# Inisialisasi model dan tokenizer
-pretrained= "mdhugol/indonesia-bert-sentiment-classification"
-model = AutoModelForSequenceClassification.from_pretrained(pretrained)
-tokenizer = AutoTokenizer.from_pretrained(pretrained)
-sentiment_analysis = pipeline("sentiment-analysis", model=model, tokenizer=tokenizer)
-label_index = {'LABEL_0': 'positive', 'LABEL_1': 'neutral', 'LABEL_2': 'negative'}
-
-st.title("Indonesia Youtube Comment Sentiment Analysis")
-st.write("Program ini akan menganalisis komentar dalam sebuah video di youtube menggunakan sentiment analysis, tidak termasuk komentar dalam komentar dan khusus untuk komentar bahasa indonesia")
-st.markdown("<p style='font-size:small;'><a href='https://github.com/Mabzak-Knight/Indonesia_Youtube_Comment_Sentiment_Analysis' target='_blank'>Github</a></p>", unsafe_allow_html=True)
-    
-# Input URL video
-video_url = st.text_input("Masukkan URL video YouTube:")
-
-# Input jumlah komentar yang ingin diambil
-num_comments = st.number_input("Jumlah komentar yang ingin diambil:", min_value=1, value=10)
-
-# Fungsi untuk analisis sentimen
-def analisis_sentimen(text):
-    result = sentiment_analysis(text)
-    label = label_index[result[0]['label']]
-    score = result[0]['score'] * 100
-    return label, score
-
-if st.button("Mulai Analisis"):
-    #Memulai Download Komentar
-    st.info("Memulai Download Komentar....")
-    # Inisialisasi YoutubeCommentDownloader
-    downloader = YoutubeCommentDownloader()
-
-    # Mendapatkan komentar
-    comments = downloader.get_comments_from_url(video_url, sort_by=SORT_BY_POPULAR)
-
-    # Membuka file CSV untuk menulis
-    with open('comments.csv', mode='w', encoding='utf-8', newline='') as file:
-        # Membuat objek writer
-        writer = csv.DictWriter(file, fieldnames=['cid', 'text', 'time', 'author', 'channel', 'votes', 'photo', 'heart', 'reply'])
-        
-        # Menulis header
-        writer.writeheader()
-        
-        # Menulis data komentar
-        for comment in tqdm(islice(comments, num_comments)):
-            # Menghapus kolom 'time_parsed' dari komentar
-            comment.pop('time_parsed', None)
-            writer.writerow(comment)
-
-    st.success(f"Komentar berhasil diunduh dan disimpan dalam file 'comments.csv'")
-    
-    # Membaca data dari file CSV
-    comments_df = pd.read_csv('comments.csv')
-    
-    #analisis sentimen
-    st.info("Memulai analisis sentimen, Proses mungkin lama....")
-
-    # List untuk menyimpan hasil analisis sentimen
-    scores = []
-    labels = []
-    # hasil_analisis = []
-
-    # Membaca data dari file CSV
-    with open('comments.csv', mode='r', encoding='utf-8') as file:
-        reader = csv.DictReader(file)
-        for row in tqdm(reader):
-            comment_text = row['text']
-             # Bagi teks menjadi bagian-bagian dengan panjang maksimum 512 token
-            parts = [comment_text[i:i+512] for i in range(0, len(comment_text), 512)]
-            for part in parts:
-                # Analisis sentimen
-                result = sentiment_analysis(part)
-                label = label_index[result[0]['label']]            
-                score = result[0]['score'] * 100
-                labels.append(label)
-                scores.append(score)
-                # hasil_analisis.append((comment_text, label, score))
-                
-    # Menampilkan hasil analisis sentimen
-    st.subheader("Hasil Analisis Sentimen")
-    # st.write(hasil_analisis)
-
-    # Menampilkan histogram
-    # labels, scores = zip(*[(label, score) for _, label, score in hasil_analisis])
-    plt.hist(labels, bins=30, color='blue', alpha=0.7, edgecolor='black')
-    plt.xlabel('Skor Sentimen')
-    plt.ylabel('Jumlah Komentar')
-    plt.title('Distribusi Sentimen Komentar')
-    st.pyplot(plt)
-
-    # Menghitung jumlah dan persentase
-    jumlah_positif = labels.count('positive')
-    jumlah_negatif = labels.count('negative')
-    jumlah_netral = labels.count('neutral')
-    total_komentar = len(labels)
-    persentase_positif = (jumlah_positif / total_komentar) * 100
-    persentase_negatif = (jumlah_negatif / total_komentar) * 100
-    persentase_netral = (jumlah_netral / total_komentar) * 100
-
-    st.write(f"Total Komentar: {total_komentar}")
-    st.write(f"Persentase Komentar Positif: {persentase_positif:.2f}% / {jumlah_positif} Komentar")
-    st.write(f"Persentase Komentar Negatif: {persentase_negatif:.2f}% / {jumlah_negatif} Komentar")
-    st.write(f"Persentase Komentar Netral: {persentase_netral:.2f}% / {jumlah_netral} Komentar")
-    
-    st.markdown("<p style='font-size:small;'>Komentar yang lebih panjang dari 512 karakter akan dibagi menjadi dua, sehingga total komentar mungkin lebih dari yang Anda ambil.</p>", unsafe_allow_html=True)
-    
-    # Menampilkan tabel dengan menggunakan st.table()
-    # st.subheader("Data Komentar")
-    # st.table(comments_df)
-    
-   
-
diff --git a/spaces/manhkhanhUIT/Image_Restoration_Colorization/Global/detection_models/Synchronized-BatchNorm-PyTorch/sync_batchnorm/__init__.py b/spaces/manhkhanhUIT/Image_Restoration_Colorization/Global/detection_models/Synchronized-BatchNorm-PyTorch/sync_batchnorm/__init__.py
deleted file mode 100644
index 6d9b36c74b1808b56ded68cf080a689db7e0ee4e..0000000000000000000000000000000000000000
--- a/spaces/manhkhanhUIT/Image_Restoration_Colorization/Global/detection_models/Synchronized-BatchNorm-PyTorch/sync_batchnorm/__init__.py
+++ /dev/null
@@ -1,14 +0,0 @@
-# -*- coding: utf-8 -*-
-# File   : __init__.py
-# Author : Jiayuan Mao
-# Email  : maojiayuan@gmail.com
-# Date   : 27/01/2018
-#
-# This file is part of Synchronized-BatchNorm-PyTorch.
-# https://github.com/vacancy/Synchronized-BatchNorm-PyTorch
-# Distributed under MIT License.
-
-from .batchnorm import set_sbn_eps_mode
-from .batchnorm import SynchronizedBatchNorm1d, SynchronizedBatchNorm2d, SynchronizedBatchNorm3d
-from .batchnorm import patch_sync_batchnorm, convert_model
-from .replicate import DataParallelWithCallback, patch_replication_callback
diff --git a/spaces/matthoffner/starchat-ui/components/Chat/PromptList.tsx b/spaces/matthoffner/starchat-ui/components/Chat/PromptList.tsx
deleted file mode 100644
index 3e5ad100b11223736446b4187e600fd97f193ac7..0000000000000000000000000000000000000000
--- a/spaces/matthoffner/starchat-ui/components/Chat/PromptList.tsx
+++ /dev/null
@@ -1,45 +0,0 @@
-import { FC, MutableRefObject } from 'react';
-
-import { Prompt } from '@/types/prompt';
-
-interface Props {
-  prompts: Prompt[];
-  activePromptIndex: number;
-  onSelect: () => void;
-  onMouseOver: (index: number) => void;
-  promptListRef: MutableRefObject<HTMLUListElement | null>;
-}
-
-export const PromptList: FC<Props> = ({
-  prompts,
-  activePromptIndex,
-  onSelect,
-  onMouseOver,
-  promptListRef,
-}) => {
-  return (
-    <ul
-      ref={promptListRef}
-      className="z-10 max-h-52 w-full overflow-scroll rounded border border-black/10 bg-white shadow-[0_0_10px_rgba(0,0,0,0.10)] dark:border-neutral-500 dark:bg-[#343541] dark:text-white dark:shadow-[0_0_15px_rgba(0,0,0,0.10)]"
-    >
-      {prompts.map((prompt, index) => (
-        <li
-          key={prompt.id}
-          className={`${
-            index === activePromptIndex
-              ? 'bg-gray-200 dark:bg-[#202123] dark:text-black'
-              : ''
-          } cursor-pointer px-3 py-2 text-sm text-black dark:text-white`}
-          onClick={(e) => {
-            e.preventDefault();
-            e.stopPropagation();
-            onSelect();
-          }}
-          onMouseEnter={() => onMouseOver(index)}
-        >
-          {prompt.name}
-        </li>
-      ))}
-    </ul>
-  );
-};
diff --git a/spaces/merve/data-leak/public/anonymization/make-estimates.js b/spaces/merve/data-leak/public/anonymization/make-estimates.js
deleted file mode 100644
index 46ed3feaf1acaccf35153c3ebaf5b60094b21daf..0000000000000000000000000000000000000000
--- a/spaces/merve/data-leak/public/anonymization/make-estimates.js
+++ /dev/null
@@ -1,227 +0,0 @@
-window.makeEstimates = function(){ 
-  var estimateScale = d3.scaleLinear()
-    .domain([.5 - .15, .5 + .15]).range([0, c.width])
-    .interpolate(d3.interpolateRound)
-
-  var jitterHeight = 90
-  var rs = 4 // rect size
-
-  var estimates = students[0].coinVals.map(d => ({val: .5, pctHead: .25, x: c.width/2, y: c.height - jitterHeight/2}))
-  var simulation = d3.forceSimulation(estimates)
-    .force('collide', d3.forceCollide(rs).strength(.1))
-    .stop()
-
-  function updateEstimates(){
-    var selectedStudents = students.all.slice(0, sliders.population)
-    
-    selectedStudents[0].coinVals.map((_, i) => {
-      estimates[i].pctHead = d3.mean(selectedStudents, d => (d.coinVals[i] < sliders.headsProb) || d.plagerized)
-
-      estimates[i].val = (1 - estimates[i].pctHead)/(1 - sliders.headsProb)
-    })
-    updateSimulation(60)
-  }  
-  updateEstimates()
-
-  function updateSimulation(ticks=80, yStrength=.005){
-    var variance = d3.variance(estimates, d => d.val)
-    var xStength = variance < .0005 ? .3 : .1
-
-    estimates.forEach(d => d.targetX = estimateScale(d.val))
-
-    simulation
-      .force('x', d3.forceX(d => d.targetX).strength(xStength))
-      .force('y', d3.forceY(c.height - jitterHeight/2).strength(yStrength))
-      .alpha(1)
-      // .alphaDecay(1 - Math.pow(0.001, 1/ticks))
-
-    for (var i = 0; i < ticks; ++i) simulation.tick()
-
-    estimates.forEach(d => {
-      d.x = Math.round(d.x)
-      d.y = Math.round(d.y)
-    })
-  }
-  updateSimulation(80, 1)
-  updateSimulation(80, .005)
-
-
-  // Set up DOM 
-  var histogramSel = c.svg.append('g').translate([0, -25])
-  var axisSel = histogramSel.append('g.axis.state.init-hidden')
-  var histogramAxis = axisSel.append('g')
-
-  var numTicks = 6
-  var xAxis = d3.axisTop(estimateScale).ticks(numTicks).tickFormat(d3.format('.0%')).tickSize(100)
-
-  histogramAxis.call(xAxis).translate([.5, c.height + 5])
-  middleTick = histogramAxis.selectAll('g').filter((d, i) => i === 3)
-  middleTick.select('text').classed('bold', 1)
-  middleTick.select('line').st({stroke: '#000'})
-  
-  histogramAxis.append('text.bold')
-    .text('actual non-plagiarism rate')
-    .translate([c.width/2, 11])
-    .st({fontSize: '10px'})
-
-  var containerSel = histogramSel.append('g#histogram').translate([0.5, .5])
-
-
-  // Selection overlay to highlight individual estimates.
-  var selectSize = rs*2 + 2
-  var selectColor = '#007276'
-  var rectFill = '#007276'
-
-  var activeSel = histogramSel.append('g.active.init-hidden.axis')
-    .st({pointerEvents: 'none'})
-
-  activeSel.append('rect')
-    .at({width: selectSize, height: selectSize, stroke: selectColor, fill: 'none', strokeWidth: 3})
-    .translate([-selectSize/2, -selectSize/2])
-
-  var activeTextHighlight = activeSel.append('rect')
-    .at({x: -32, width: 32*2, height: 18, y: -25, fill: 'rgba(255,255,255,.6)', rx: 10, ry: 10, xfill: 'red'})
-
-  var activeTextSel = activeSel.append('text.est-text.bold')
-    .text('34%')
-    .at({textAnchor: 'middle', textAnchor: 'middle', y: '-1em'})
-    .st({fill: selectColor})
-
-  var activePathSel = activeSel.append('path')
-    .st({stroke: selectColor, strokeWidth: 3})
-
-
-  // Update highlight DOM with current highlight
-  var curDrawData = {pctHead: .25, val: .5, x: c.width/2, y: c.height - jitterHeight/2}
-  function setActive(active, dur=0){
-    if (active !== estimates.active){
-      estimates.forEach(d => {
-        d.active = d == active
-        d.fy = d.active ? d.y : null
-      })
-      estimates.active = active
-    }
-
-    students.updateHeadsPos()
-
-
-    sel.flipCircle
-      .transition().duration(0).delay(d => d.i*5*(dur > 0 ? 1 : 0))
-      .at({transform: d => slides && slides.curSlide && slides.curSlide.showFlipCircle && d.coinVals[active.index] < sliders.headsProb ? 
-        'scale(1)' : 'scale(.1)'})
-
-
-    flipCoinTimer.stop()
-    if (dur){
-      var objI = d3.interpolateObject(curDrawData, active)
-
-      flipCoinTimer = d3.timer(ms => {
-        var t = d3.easeCubicInOut(d3.clamp(0, ms/dur, 1))
-        drawData(objI(t))
-        if (t == 1) flipCoinTimer.stop()
-      })
-    } else{
-      drawData(active)
-    }
-    
-    function drawData({pctHead, val, x, y}){
-      activeSel.translate([x + rs/2, y + rs/2])
-      activeTextSel.text('est. ' + d3.format('.1%')(val))
-      activePathSel.at({d: `M ${selectSize/2*Math.sign(c.width/2 - x)} -1 H ${c.width/2 - x}`})
-
-      var error = Math.abs(val - .5)
-      var fmt = d3.format(".1%")
-      var pop = sliders.population
-      d3.select('.rand-text')
-        // .html(`${fmt(1 - pctHead)} of students said they had never plagerized. Since about half the students flipped heads and automatically reported plagerizism, we double that to <span class='highlight square blue-box box'>estimate ${fmt(val)}</span> of students haven't plagerized—${error > .1 ? '' : error > .07 ? 'a little ' : 'not '}far from the actual rate of ${fmt(.5)}`)
-        // .html(`${Math.round((1 - pctHead)*pop)} of ${pop} students said they had never plagiarized. Since about half the students flipped heads and automatically reported plagiarism, we double that rate to <span class='highlight square blue-box box'>estimate ${fmt(val)}</span> of students haven't plagiarized—${error > .4 ? '' : error > .07 ? 'a little ' : 'not '}far from the actual rate of ${fmt(.5)}`)
-        .html(`Here, ${fmt(1 - pctHead)} students said they had never plagiarized. Doubling that, we <span class='highlight square blue-box box'>estimate ${fmt(val)}</span> of students haven't plagiarized—${error > .1 ? 'quite ' : error > .07 ? 'a little ' : 'not '}far from the actual rate of ${fmt(.5)}`)
-
-      curDrawData = {pctHead, val, x, y}
-    }
-  }
-  window.flipCoinTimer = d3.timer(d => d)
-
-
-
-  var estimateSel = containerSel.appendMany('rect.estimate', estimates)
-    .at({width: rs, height: rs, stroke: '#fff', fill: rectFill, strokeWidth: .5})
-    .st({fill: rectFill})
-    .translate([rs/2, rs/2])
-    .on('mouseover', (d, i) => {
-      if (window.slides.curSlide.showHistogram) {
-        setActive(d)
-      }
-    })
-
-  function setSelectorOpacity(textOpacity, strokeOpacity) {
-    activeTextSel.st({opacity: textOpacity})
-    activeSel.st({opacity: strokeOpacity})
-    activePathSel.st({opacity: strokeOpacity})
-  }
-
-  function render(transition=false){
-    estimateSel.translate(d => [d.x, d.y])
-    setActive(estimates.active)
-
-    if (transition){
-      if (window.flipAllCoinsTimer) window.flipAllCoinsTimer.stop()
-      window.flipAllCoinsTimer = d3.timer(ms => {
-        var t = d3.easeExpIn(d3.clamp(0, ms/5000, 1), 20)
-        if (flipAllCoinsTimer.forceEnd) t = 1
-        
-        if (t > .028) {
-          setSelectorOpacity(textOpacity=0, strokeOpacity=0.7)
-        }
-
-        var index = Math.floor((estimates.length - 2)*t) + 1
-        estimateSel.classed('active', (d, i) => i <= index)
-
-        setActive(estimates[index])
-        // flipCoinsSel.text('Flip coins ' + d3.format('03')(index < 100 ? index : index + 1) + ' times')
-        flipCoinsSel.text('Flip coins 200 times')
-
-        if (t == 1) {
-          flipAllCoinsTimer.stop()
-          setSelectorOpacity(textOpacity=1, strokeOpacity=1)
-        }
-      })
-    } else {
-      setSelectorOpacity(textOpacity=1, strokeOpacity=1)
-      flipCoinsSel
-    }   
-  }
-  window.flipAllCoinsTimer = d3.timer(d => d)
-
-
-  var flipCoinsSel = d3.select('.flip-coins').on('click', () => {
-    students.all.forEach(student => {
-      student.coinVals = student.coinVals.map(j => Math.random())
-    })
-
-    updateEstimates()
-    render(true)
-  })
-
-  d3.select('.flip-coins-once').on('click', flipCoin)
-  function flipCoin(){
-    active = estimates[0]
-
-    students.all.forEach(student => {
-      student.coinVals = student.coinVals.map(j => Math.random())
-    })
-
-    active.fy = active.y = c.height - jitterHeight/2
-    updateEstimates()
-
-    estimateSel.translate(d => [d.x, d.y])
-    estimates.active = null
-    setActive(active, 1000)
-  }
-
-  Object.assign(estimates, {updateEstimates, setActive, render, flipCoin, axisSel, containerSel, estimateSel, activeSel})
-
-  return estimates
-} 
-    
-if (window.init) window.init()
\ No newline at end of file
diff --git a/spaces/merve/data-leak/source/third_party/simple-statistics.min.js b/spaces/merve/data-leak/source/third_party/simple-statistics.min.js
deleted file mode 100644
index 9191046b7dc959d771a904875817c2b9c26ff0e5..0000000000000000000000000000000000000000
--- a/spaces/merve/data-leak/source/third_party/simple-statistics.min.js
+++ /dev/null
@@ -1,3 +0,0 @@
-// https://github.com/simple-statistics/simple-statistics Copyright (c) 2014, Tom MacWright
-
-!function(t,r){"object"==typeof exports&&"undefined"!=typeof module?r(exports):"function"==typeof define&&define.amd?define(["exports"],r):r(t.ss={})}(this,function(t){"use strict";function r(t){if(0===t.length)return 0;for(var r,n=t[0],e=0,a=1;a<t.length;a++)r=n+t[a],Math.abs(n)>=Math.abs(t[a])?e+=n-r+t[a]:e+=t[a]-r+n,n=r;return n+e}function g(t){if(0===t.length)throw new Error("mean requires at least one data point");return r(t)/t.length}function n(t,r){var n,e,a=g(t),o=0;if(2===r)for(e=0;e<t.length;e++)o+=(n=t[e]-a)*n;else for(e=0;e<t.length;e++)o+=Math.pow(t[e]-a,r);return o}function e(t){if(0===t.length)throw new Error("variance requires at least one data point");return n(t,2)/t.length}function a(t){if(1===t.length)return 0;var r=e(t);return Math.sqrt(r)}function o(t){if(0===t.length)throw new Error("mode requires at least one data point");if(1===t.length)return t[0];for(var r=t[0],n=NaN,e=0,a=1,o=1;o<t.length+1;o++)t[o]!==r?(e<a&&(e=a,n=r),a=1,r=t[o]):a++;return n}function f(t){return t.slice().sort(function(t,r){return t-r})}function u(t){if(0===t.length)throw new Error("min requires at least one data point");for(var r=t[0],n=1;n<t.length;n++)t[n]<r&&(r=t[n]);return r}function h(t){if(0===t.length)throw new Error("max requires at least one data point");for(var r=t[0],n=1;n<t.length;n++)t[n]>r&&(r=t[n]);return r}function i(t,r){var n=t.length*r;if(0===t.length)throw new Error("quantile requires at least one data point.");if(r<0||1<r)throw new Error("quantiles must be between 0 and 1");return 1===r?t[t.length-1]:0===r?t[0]:n%1!=0?t[Math.ceil(n)-1]:t.length%2==0?(t[n-1]+t[n])/2:t[n]}function c(t,r,n,e){for(n=n||0,e=e||t.length-1;n<e;){if(600<e-n){var a=e-n+1,o=r-n+1,i=Math.log(a),u=.5*Math.exp(2*i/3),h=.5*Math.sqrt(i*u*(a-u)/a);o-a/2<0&&(h*=-1),c(t,r,Math.max(n,Math.floor(r-o*u/a+h)),Math.min(e,Math.floor(r+(a-o)*u/a+h)))}var f=t[r],s=n,l=e;for(p(t,n,r),t[e]>f&&p(t,n,e);s<l;){for(p(t,s,l),s++,l--;t[s]<f;)s++;for(;t[l]>f;)l--}t[n]===f?p(t,n,l):p(t,++l,e),l<=r&&(n=l+1),r<=l&&(e=l-1)}}function p(t,r,n){var e=t[r];t[r]=t[n],t[n]=e}function s(t,r){var n=t.slice();if(Array.isArray(r)){!function(t,r){for(var n=[0],e=0;e<r.length;e++)n.push(w(t.length,r[e]));n.push(t.length-1),n.sort(v);var a=[0,n.length-1];for(;a.length;){var o=Math.ceil(a.pop()),i=Math.floor(a.pop());if(!(o-i<=1)){var u=Math.floor((i+o)/2);l(t,n[u],n[i],n[o]),a.push(i,u,u,o)}}}(n,r);for(var e=[],a=0;a<r.length;a++)e[a]=i(n,r[a]);return e}return l(n,w(n.length,r),0,n.length-1),i(n,r)}function l(t,r,n,e){r%1==0?c(t,r,n,e):(c(t,r=Math.floor(r),n,e),c(t,r+1,r+1,e))}function v(t,r){return t-r}function w(t,r){var n=t*r;return 1===r?t-1:0===r?0:n%1!=0?Math.ceil(n)-1:t%2==0?n-.5:n}function M(t,r){if(r<t[0])return 0;if(r>t[t.length-1])return 1;var n=function(t,r){var n=0,e=0,a=t.length;for(;e<a;)r<=t[n=e+a>>>1]?a=n:e=-~n;return e}(t,r);if(t[n]!==r)return n/t.length;n++;var e=function(t,r){var n=0,e=0,a=t.length;for(;e<a;)r>=t[n=e+a>>>1]?e=-~n:a=n;return e}(t,r);if(e===n)return n/t.length;var a=e-n+1;return a*(e+n)/2/a/t.length}function m(t){var r=s(t,.75),n=s(t,.25);if("number"==typeof r&&"number"==typeof n)return r-n}function d(t){return+s(t,.5)}function b(t){for(var r=d(t),n=[],e=0;e<t.length;e++)n.push(Math.abs(t[e]-r));return d(n)}function q(t,r){r=r||Math.random;for(var n,e,a=t.length;0<a;)e=Math.floor(r()*a--),n=t[a],t[a]=t[e],t[e]=n;return t}function E(t,r){return q(t.slice().slice(),r)}function y(t){for(var r,n=0,e=0;e<t.length;e++)0!==e&&t[e]===r||(r=t[e],n++);return n}function S(t,r){for(var n=[],e=0;e<t;e++){for(var a=[],o=0;o<r;o++)a.push(0);n.push(a)}return n}function x(t,r,n,e){var a;if(0<t){var o=(n[r]-n[t-1])/(r-t+1);a=e[r]-e[t-1]-(r-t+1)*o*o}else a=e[r]-n[r]*n[r]/(r+1);return a<0?0:a}function P(t,r,n,e,a,o,i){if(!(r<t)){var u=Math.floor((t+r)/2);e[n][u]=e[n-1][u-1],a[n][u]=u;var h=n;n<t&&(h=Math.max(h,a[n][t-1]||0)),h=Math.max(h,a[n-1][u]||0);var f,s,l,c=u-1;r<e.length-1&&(c=Math.min(c,a[n][r+1]||0));for(var g=c;h<=g&&!((f=x(g,u,o,i))+e[n-1][h-1]>=e[n][u]);--g)(s=x(h,u,o,i)+e[n-1][h-1])<e[n][u]&&(e[n][u]=s,a[n][u]=h),h++,(l=f+e[n-1][g-1])<e[n][u]&&(e[n][u]=l,a[n][u]=g);P(t,u-1,n,e,a,o,i),P(u+1,r,n,e,a,o,i)}}function k(t,r){if(t.length!==r.length)throw new Error("sampleCovariance requires samples with equal lengths");if(t.length<2)throw new Error("sampleCovariance requires at least two data points in each sample");for(var n=g(t),e=g(r),a=0,o=0;o<t.length;o++)a+=(t[o]-n)*(r[o]-e);return a/(t.length-1)}function I(t){if(t.length<2)throw new Error("sampleVariance requires at least two data points");return n(t,2)/(t.length-1)}function D(t){var r=I(t);return Math.sqrt(r)}function C(t,r,n,e){return(t*r+n*e)/(r+e)}function T(t){if(0===t.length)throw new Error("rootMeanSquare requires at least one data point");for(var r=0,n=0;n<t.length;n++)r+=Math.pow(t[n],2);return Math.sqrt(r/t.length)}function _(){this.totalCount=0,this.data={}}function F(){this.weights=[],this.bias=0}_.prototype.train=function(t,r){for(var n in this.data[r]||(this.data[r]={}),t){var e=t[n];void 0===this.data[r][n]&&(this.data[r][n]={}),void 0===this.data[r][n][e]&&(this.data[r][n][e]=0),this.data[r][n][e]++}this.totalCount++},_.prototype.score=function(t){var r,n={};for(var e in t){var a=t[e];for(r in this.data)n[r]={},this.data[r][e]?n[r][e+"_"+a]=(this.data[r][e][a]||0)/this.totalCount:n[r][e+"_"+a]=0}var o={};for(r in n)for(var i in o[r]=0,n[r])o[r]+=n[r][i];return o},F.prototype.predict=function(t){if(t.length!==this.weights.length)return null;for(var r=0,n=0;n<this.weights.length;n++)r+=this.weights[n]*t[n];return 0<(r+=this.bias)?1:0},F.prototype.train=function(t,r){if(0!==r&&1!==r)return null;t.length!==this.weights.length&&(this.weights=t,this.bias=1);var n=this.predict(t);if(n!==r){for(var e=r-n,a=0;a<this.weights.length;a++)this.weights[a]+=e*t[a];this.bias+=e}return this};var N=1e-4;function R(t){if(t<0)throw new Error("factorial requires a non-negative value");if(Math.floor(t)!==t)throw new Error("factorial requires an integer input");for(var r=1,n=2;n<=t;n++)r*=n;return r}var A=[.9999999999999971,57.15623566586292,-59.59796035547549,14.136097974741746,-.4919138160976202,3399464998481189e-20,4652362892704858e-20,-9837447530487956e-20,.0001580887032249125,-.00021026444172410488,.00021743961811521265,-.0001643181065367639,8441822398385275e-20,-26190838401581408e-21,36899182659531625e-22],z=Math.log(Math.sqrt(2*Math.PI));var V={1:{.995:0,.99:0,.975:0,.95:0,.9:.02,.5:.45,.1:2.71,.05:3.84,.025:5.02,.01:6.63,.005:7.88},2:{.995:.01,.99:.02,.975:.05,.95:.1,.9:.21,.5:1.39,.1:4.61,.05:5.99,.025:7.38,.01:9.21,.005:10.6},3:{.995:.07,.99:.11,.975:.22,.95:.35,.9:.58,.5:2.37,.1:6.25,.05:7.81,.025:9.35,.01:11.34,.005:12.84},4:{.995:.21,.99:.3,.975:.48,.95:.71,.9:1.06,.5:3.36,.1:7.78,.05:9.49,.025:11.14,.01:13.28,.005:14.86},5:{.995:.41,.99:.55,.975:.83,.95:1.15,.9:1.61,.5:4.35,.1:9.24,.05:11.07,.025:12.83,.01:15.09,.005:16.75},6:{.995:.68,.99:.87,.975:1.24,.95:1.64,.9:2.2,.5:5.35,.1:10.65,.05:12.59,.025:14.45,.01:16.81,.005:18.55},7:{.995:.99,.99:1.25,.975:1.69,.95:2.17,.9:2.83,.5:6.35,.1:12.02,.05:14.07,.025:16.01,.01:18.48,.005:20.28},8:{.995:1.34,.99:1.65,.975:2.18,.95:2.73,.9:3.49,.5:7.34,.1:13.36,.05:15.51,.025:17.53,.01:20.09,.005:21.96},9:{.995:1.73,.99:2.09,.975:2.7,.95:3.33,.9:4.17,.5:8.34,.1:14.68,.05:16.92,.025:19.02,.01:21.67,.005:23.59},10:{.995:2.16,.99:2.56,.975:3.25,.95:3.94,.9:4.87,.5:9.34,.1:15.99,.05:18.31,.025:20.48,.01:23.21,.005:25.19},11:{.995:2.6,.99:3.05,.975:3.82,.95:4.57,.9:5.58,.5:10.34,.1:17.28,.05:19.68,.025:21.92,.01:24.72,.005:26.76},12:{.995:3.07,.99:3.57,.975:4.4,.95:5.23,.9:6.3,.5:11.34,.1:18.55,.05:21.03,.025:23.34,.01:26.22,.005:28.3},13:{.995:3.57,.99:4.11,.975:5.01,.95:5.89,.9:7.04,.5:12.34,.1:19.81,.05:22.36,.025:24.74,.01:27.69,.005:29.82},14:{.995:4.07,.99:4.66,.975:5.63,.95:6.57,.9:7.79,.5:13.34,.1:21.06,.05:23.68,.025:26.12,.01:29.14,.005:31.32},15:{.995:4.6,.99:5.23,.975:6.27,.95:7.26,.9:8.55,.5:14.34,.1:22.31,.05:25,.025:27.49,.01:30.58,.005:32.8},16:{.995:5.14,.99:5.81,.975:6.91,.95:7.96,.9:9.31,.5:15.34,.1:23.54,.05:26.3,.025:28.85,.01:32,.005:34.27},17:{.995:5.7,.99:6.41,.975:7.56,.95:8.67,.9:10.09,.5:16.34,.1:24.77,.05:27.59,.025:30.19,.01:33.41,.005:35.72},18:{.995:6.26,.99:7.01,.975:8.23,.95:9.39,.9:10.87,.5:17.34,.1:25.99,.05:28.87,.025:31.53,.01:34.81,.005:37.16},19:{.995:6.84,.99:7.63,.975:8.91,.95:10.12,.9:11.65,.5:18.34,.1:27.2,.05:30.14,.025:32.85,.01:36.19,.005:38.58},20:{.995:7.43,.99:8.26,.975:9.59,.95:10.85,.9:12.44,.5:19.34,.1:28.41,.05:31.41,.025:34.17,.01:37.57,.005:40},21:{.995:8.03,.99:8.9,.975:10.28,.95:11.59,.9:13.24,.5:20.34,.1:29.62,.05:32.67,.025:35.48,.01:38.93,.005:41.4},22:{.995:8.64,.99:9.54,.975:10.98,.95:12.34,.9:14.04,.5:21.34,.1:30.81,.05:33.92,.025:36.78,.01:40.29,.005:42.8},23:{.995:9.26,.99:10.2,.975:11.69,.95:13.09,.9:14.85,.5:22.34,.1:32.01,.05:35.17,.025:38.08,.01:41.64,.005:44.18},24:{.995:9.89,.99:10.86,.975:12.4,.95:13.85,.9:15.66,.5:23.34,.1:33.2,.05:36.42,.025:39.36,.01:42.98,.005:45.56},25:{.995:10.52,.99:11.52,.975:13.12,.95:14.61,.9:16.47,.5:24.34,.1:34.28,.05:37.65,.025:40.65,.01:44.31,.005:46.93},26:{.995:11.16,.99:12.2,.975:13.84,.95:15.38,.9:17.29,.5:25.34,.1:35.56,.05:38.89,.025:41.92,.01:45.64,.005:48.29},27:{.995:11.81,.99:12.88,.975:14.57,.95:16.15,.9:18.11,.5:26.34,.1:36.74,.05:40.11,.025:43.19,.01:46.96,.005:49.65},28:{.995:12.46,.99:13.57,.975:15.31,.95:16.93,.9:18.94,.5:27.34,.1:37.92,.05:41.34,.025:44.46,.01:48.28,.005:50.99},29:{.995:13.12,.99:14.26,.975:16.05,.95:17.71,.9:19.77,.5:28.34,.1:39.09,.05:42.56,.025:45.72,.01:49.59,.005:52.34},30:{.995:13.79,.99:14.95,.975:16.79,.95:18.49,.9:20.6,.5:29.34,.1:40.26,.05:43.77,.025:46.98,.01:50.89,.005:53.67},40:{.995:20.71,.99:22.16,.975:24.43,.95:26.51,.9:29.05,.5:39.34,.1:51.81,.05:55.76,.025:59.34,.01:63.69,.005:66.77},50:{.995:27.99,.99:29.71,.975:32.36,.95:34.76,.9:37.69,.5:49.33,.1:63.17,.05:67.5,.025:71.42,.01:76.15,.005:79.49},60:{.995:35.53,.99:37.48,.975:40.48,.95:43.19,.9:46.46,.5:59.33,.1:74.4,.05:79.08,.025:83.3,.01:88.38,.005:91.95},70:{.995:43.28,.99:45.44,.975:48.76,.95:51.74,.9:55.33,.5:69.33,.1:85.53,.05:90.53,.025:95.02,.01:100.42,.005:104.22},80:{.995:51.17,.99:53.54,.975:57.15,.95:60.39,.9:64.28,.5:79.33,.1:96.58,.05:101.88,.025:106.63,.01:112.33,.005:116.32},90:{.995:59.2,.99:61.75,.975:65.65,.95:69.13,.9:73.29,.5:89.33,.1:107.57,.05:113.14,.025:118.14,.01:124.12,.005:128.3},100:{.995:67.33,.99:70.06,.975:74.22,.95:77.93,.9:82.36,.5:99.33,.1:118.5,.05:124.34,.025:129.56,.01:135.81,.005:140.17}};var j=Math.sqrt(2*Math.PI),B={gaussian:function(t){return Math.exp(-.5*t*t)/j}},K={nrd:function(t){var r=D(t),n=m(t);return"number"==typeof n&&(r=Math.min(r,n/1.34)),1.06*r*Math.pow(t.length,-.2)}};function O(e,t,r){var a,o;if(void 0===t)a=B.gaussian;else if("string"==typeof t){if(!B[t])throw new Error('Unknown kernel "'+t+'"');a=B[t]}else a=t;if(void 0===r)o=K.nrd(e);else if("string"==typeof r){if(!K[r])throw new Error('Unknown bandwidth method "'+r+'"');o=K[r](e)}else o=r;return function(t){var r=0,n=0;for(r=0;r<e.length;r++)n+=a((t-e[r])/o);return n/o/e.length}}var U=Math.sqrt(2*Math.PI);function G(t){for(var r=t,n=t,e=1;e<15;e++)r+=n*=t*t/(2*e+1);return Math.round(1e4*(.5+r/U*Math.exp(-t*t/2)))/1e4}for(var H=[],L=0;L<=3.09;L+=.01)H.push(G(L));function W(t){var r=1/(1+.5*Math.abs(t)),n=r*Math.exp(-Math.pow(t,2)-1.26551223+1.00002368*r+.37409196*Math.pow(r,2)+.09678418*Math.pow(r,3)-.18628806*Math.pow(r,4)+.27886807*Math.pow(r,5)-1.13520398*Math.pow(r,6)+1.48851587*Math.pow(r,7)-.82215223*Math.pow(r,8)+.17087277*Math.pow(r,9));return 0<=t?1-n:n-1}function J(t){var r=8*(Math.PI-3)/(3*Math.PI*(4-Math.PI)),n=Math.sqrt(Math.sqrt(Math.pow(2/(Math.PI*r)+Math.log(1-t*t)/2,2)-Math.log(1-t*t)/r)-(2/(Math.PI*r)+Math.log(1-t*t)/2));return 0<=t?n:-n}function Q(t){if("number"==typeof t)return t<0?-1:0===t?0:1;throw new TypeError("not a number")}t.linearRegression=function(t){var r,n,e=t.length;if(1===e)n=t[r=0][1];else{for(var a,o,i,u=0,h=0,f=0,s=0,l=0;l<e;l++)u+=o=(a=t[l])[0],h+=i=a[1],f+=o*o,s+=o*i;n=h/e-(r=(e*s-u*h)/(e*f-u*u))*u/e}return{m:r,b:n}},t.linearRegressionLine=function(r){return function(t){return r.b+r.m*t}},t.standardDeviation=a,t.rSquared=function(t,r){if(t.length<2)return 1;for(var n,e=0,a=0;a<t.length;a++)e+=t[a][1];n=e/t.length;for(var o=0,i=0;i<t.length;i++)o+=Math.pow(n-t[i][1],2);for(var u=0,h=0;h<t.length;h++)u+=Math.pow(t[h][1]-r(t[h][0]),2);return 1-u/o},t.mode=function(t){return o(f(t))},t.modeFast=function(t){for(var r,n=new Map,e=0,a=0;a<t.length;a++){var o=n.get(t[a]);void 0===o?o=1:o++,e<o&&(r=t[a],e=o),n.set(t[a],o)}if(0===e)throw new Error("mode requires at last one data point");return r},t.modeSorted=o,t.min=u,t.max=h,t.extent=function(t){if(0===t.length)throw new Error("extent requires at least one data point");for(var r=t[0],n=t[0],e=1;e<t.length;e++)t[e]>n&&(n=t[e]),t[e]<r&&(r=t[e]);return[r,n]},t.minSorted=function(t){return t[0]},t.maxSorted=function(t){return t[t.length-1]},t.extentSorted=function(t){return[t[0],t[t.length-1]]},t.sum=r,t.sumSimple=function(t){for(var r=0,n=0;n<t.length;n++)r+=t[n];return r},t.product=function(t){for(var r=1,n=0;n<t.length;n++)r*=t[n];return r},t.quantile=s,t.quantileSorted=i,t.quantileRank=function(t,r){return M(f(t),r)},t.quantileRankSorted=M,t.interquartileRange=m,t.iqr=m,t.medianAbsoluteDeviation=b,t.mad=b,t.chunk=function(t,r){var n=[];if(r<1)throw new Error("chunk size must be a positive number");if(Math.floor(r)!==r)throw new Error("chunk size must be an integer");for(var e=0;e<t.length;e+=r)n.push(t.slice(e,e+r));return n},t.sampleWithReplacement=function(t,r,n){if(0===t.length)return[];n=n||Math.random;for(var e=t.length,a=[],o=0;o<r;o++){var i=Math.floor(n()*e);a.push(t[i])}return a},t.shuffle=E,t.shuffleInPlace=q,t.sample=function(t,r,n){return E(t,n).slice(0,r)},t.ckmeans=function(t,r){if(r>t.length)throw new Error("cannot generate more classes than there are data values");var n=f(t);if(1===y(n))return[n];var e=S(r,n.length),a=S(r,n.length);!function(t,r,n){for(var e,a=r[0].length,o=t[Math.floor(a/2)],i=[],u=[],h=0;h<a;++h)e=t[h]-o,0===h?(i.push(e),u.push(e*e)):(i.push(i[h-1]+e),u.push(u[h-1]+e*e)),r[0][h]=x(0,h,i,u),n[0][h]=0;for(var f=1;f<r.length;++f)P(f<r.length-1?f:a-1,a-1,f,r,n,i,u)}(n,e,a);for(var o=[],i=a[0].length-1,u=a.length-1;0<=u;u--){var h=a[u][i];o[u]=n.slice(h,i+1),0<u&&(i=h-1)}return o},t.uniqueCountSorted=y,t.sumNthPowerDeviations=n,t.equalIntervalBreaks=function(t,r){if(t.length<2)return t;for(var n=u(t),e=h(t),a=[n],o=(e-n)/r,i=1;i<r;i++)a.push(a[0]+o*i);return a.push(e),a},t.sampleCovariance=k,t.sampleCorrelation=function(t,r){return k(t,r)/D(t)/D(r)},t.sampleVariance=I,t.sampleStandardDeviation=D,t.sampleSkewness=function(t){if(t.length<3)throw new Error("sampleSkewness requires at least three data points");for(var r,n=g(t),e=0,a=0,o=0;o<t.length;o++)e+=(r=t[o]-n)*r,a+=r*r*r;var i=t.length-1,u=Math.sqrt(e/i),h=t.length;return h*a/((h-1)*(h-2)*Math.pow(u,3))},t.sampleKurtosis=function(t){var r=t.length;if(r<4)throw new Error("sampleKurtosis requires at least four data points");for(var n,e=g(t),a=0,o=0,i=0;i<r;i++)a+=(n=t[i]-e)*n,o+=n*n*n*n;return(r-1)/((r-2)*(r-3))*(r*(r+1)*o/(a*a)-3*(r-1))},t.permutationsHeap=function(t){for(var r=new Array(t.length),n=[t.slice()],e=0;e<t.length;e++)r[e]=0;for(e=0;e<t.length;)if(r[e]<e){var a=0;e%2!=0&&(a=r[e]);var o=t[a];t[a]=t[e],t[e]=o,n.push(t.slice()),r[e]++,e=0}else r[e]=0,e++;return n},t.combinations=function t(r,n){var e,a,o,i,u=[];for(e=0;e<r.length;e++)if(1===n)u.push([r[e]]);else for(o=t(r.slice(e+1,r.length),n-1),a=0;a<o.length;a++)(i=o[a]).unshift(r[e]),u.push(i);return u},t.combinationsReplacement=function t(r,n){for(var e=[],a=0;a<r.length;a++)if(1===n)e.push([r[a]]);else for(var o=t(r.slice(a,r.length),n-1),i=0;i<o.length;i++)e.push([r[a]].concat(o[i]));return e},t.addToMean=function(t,r,n){return t+(n-t)/(r+1)},t.combineMeans=C,t.combineVariances=function(t,r,n,e,a,o){var i=C(r,n,a,o);return(n*(t+Math.pow(r-i,2))+o*(e+Math.pow(a-i,2)))/(n+o)},t.geometricMean=function(t){if(0===t.length)throw new Error("geometricMean requires at least one data point");for(var r=1,n=0;n<t.length;n++){if(t[n]<=0)throw new Error("geometricMean requires only positive numbers as input");r*=t[n]}return Math.pow(r,1/t.length)},t.harmonicMean=function(t){if(0===t.length)throw new Error("harmonicMean requires at least one data point");for(var r=0,n=0;n<t.length;n++){if(t[n]<=0)throw new Error("harmonicMean requires only positive numbers as input");r+=1/t[n]}return t.length/r},t.average=g,t.mean=g,t.median=d,t.medianSorted=function(t){return i(t,.5)},t.subtractFromMean=function(t,r,n){return(t*r-n)/(r-1)},t.rootMeanSquare=T,t.rms=T,t.variance=e,t.tTest=function(t,r){return(g(t)-r)/(a(t)/Math.sqrt(t.length))},t.tTestTwoSample=function(t,r,n){var e=t.length,a=r.length;if(!e||!a)return null;n||(n=0);var o=g(t),i=g(r),u=I(t),h=I(r);if("number"==typeof o&&"number"==typeof i&&"number"==typeof u&&"number"==typeof h){var f=((e-1)*u+(a-1)*h)/(e+a-2);return(o-i-n)/Math.sqrt(f*(1/e+1/a))}},t.BayesianClassifier=_,t.bayesian=_,t.PerceptronModel=F,t.perceptron=F,t.epsilon=N,t.factorial=R,t.gamma=function t(r){if("number"==typeof(n=r)&&isFinite(n)&&Math.floor(n)===n)return r<=0?NaN:R(r-1);var n;if(--r<0)return Math.PI/(Math.sin(Math.PI*-r)*t(-r));var e=r+.25;return Math.pow(r/Math.E,r)*Math.sqrt(2*Math.PI*(r+1/6))*(1+1/144/Math.pow(e,2)-1/12960/Math.pow(e,3)-257/207360/Math.pow(e,4)-52/2612736/Math.pow(e,5)+5741173/9405849600/Math.pow(e,6)+37529/18811699200/Math.pow(e,7))},t.gammaln=function(t){if(t<=0)return 1/0;t--;for(var r=A[0],n=1;n<15;n++)r+=A[n]/(t+n);var e=5.2421875+t;return z+Math.log(r)-e+(t+.5)*Math.log(e)},t.bernoulliDistribution=function(t){if(t<0||1<t)throw new Error("bernoulliDistribution requires probability to be between 0 and 1 inclusive");return[1-t,t]},t.binomialDistribution=function(t,r){if(!(r<0||1<r||t<=0||t%1!=0)){for(var n=0,e=0,a=[],o=1;a[n]=o*Math.pow(r,n)*Math.pow(1-r,t-n),e+=a[n],o=o*(t-++n+1)/n,e<1-N;);return a}},t.poissonDistribution=function(t){if(!(t<=0)){for(var r=0,n=0,e=[],a=1;e[r]=Math.exp(-t)*Math.pow(t,r)/a,n+=e[r],a*=++r,n<1-N;);return e}},t.chiSquaredDistributionTable=V,t.chiSquaredGoodnessOfFit=function(t,r,n){for(var e,a,o=0,i=r(g(t)),u=[],h=[],f=0;f<t.length;f++)void 0===u[t[f]]&&(u[t[f]]=0),u[t[f]]++;for(f=0;f<u.length;f++)void 0===u[f]&&(u[f]=0);for(a in i)a in u&&(h[+a]=i[a]*t.length);for(a=h.length-1;0<=a;a--)h[a]<3&&(h[a-1]+=h[a],h.pop(),u[a-1]+=u[a],u.pop());for(a=0;a<u.length;a++)o+=Math.pow(u[a]-h[a],2)/h[a];return e=u.length-1-1,V[e][n]<o},t.kernelDensityEstimation=O,t.kde=O,t.zScore=function(t,r,n){return(t-r)/n},t.cumulativeStdNormalProbability=function(t){var r=Math.abs(t),n=Math.min(Math.round(100*r),H.length-1);return 0<=t?H[n]:+(1-H[n]).toFixed(4)},t.standardNormalTable=H,t.errorFunction=W,t.erf=W,t.inverseErrorFunction=J,t.probit=function(t){return 0===t?t=N:1<=t&&(t=1-N),Math.sqrt(2)*J(2*t-1)},t.permutationTest=function(t,r,n,e){if(void 0===e&&(e=1e4),void 0===n&&(n="two_side"),"two_side"!==n&&"greater"!==n&&"less"!==n)throw new Error("`alternative` must be either 'two_side', 'greater', or 'less'");for(var a=g(t)-g(r),o=new Array(e),i=t.concat(r),u=Math.floor(i.length/2),h=0;h<e;h++){q(i);var f=i.slice(0,u),s=i.slice(u,i.length),l=g(f)-g(s);o[h]=l}var c=0;if("two_side"===n)for(h=0;h<=e;h++)Math.abs(o[h])>=Math.abs(a)&&(c+=1);else if("greater"===n)for(h=0;h<=e;h++)o[h]>=a&&(c+=1);else for(h=0;h<=e;h++)o[h]<=a&&(c+=1);return c/e},t.bisect=function(t,r,n,e,a){if("function"!=typeof t)throw new TypeError("func must be a function");for(var o=0;o<e;o++){var i=(r+n)/2;if(0===t(i)||Math.abs((n-r)/2)<a)return i;Q(t(i))===Q(t(r))?r=i:n=i}throw new Error("maximum number of iterations exceeded")},t.quickselect=c,t.sign=Q,t.numericSort=f,Object.defineProperty(t,"__esModule",{value:!0})});
diff --git a/spaces/merve/uncertainty-calibration/source/third_party/mobilenet@1.0.0.js b/spaces/merve/uncertainty-calibration/source/third_party/mobilenet@1.0.0.js
deleted file mode 100644
index d50ffe68663e1aabfc07faec02e8a3cb41b5dfe5..0000000000000000000000000000000000000000
--- a/spaces/merve/uncertainty-calibration/source/third_party/mobilenet@1.0.0.js
+++ /dev/null
@@ -1,2 +0,0 @@
-// @tensorflow/tfjs-models Copyright 2019 Google
-!function(e,a){"object"==typeof exports&&"undefined"!=typeof module?a(exports,require("@tensorflow/tfjs")):"function"==typeof define&&define.amd?define(["exports","@tensorflow/tfjs"],a):a((e=e||self).mobilenet={},e.tf)}(this,function(e,a){"use strict";function r(e,a,r,o){return new(r||(r=Promise))(function(i,t){function n(e){try{l(o.next(e))}catch(e){t(e)}}function s(e){try{l(o.throw(e))}catch(e){t(e)}}function l(e){e.done?i(e.value):new r(function(a){a(e.value)}).then(n,s)}l((o=o.apply(e,a||[])).next())})}function o(e,a){var r,o,i,t,n={label:0,sent:function(){if(1&i[0])throw i[1];return i[1]},trys:[],ops:[]};return t={next:s(0),throw:s(1),return:s(2)},"function"==typeof Symbol&&(t[Symbol.iterator]=function(){return this}),t;function s(t){return function(s){return function(t){if(r)throw new TypeError("Generator is already executing.");for(;n;)try{if(r=1,o&&(i=2&t[0]?o.return:t[0]?o.throw||((i=o.return)&&i.call(o),0):o.next)&&!(i=i.call(o,t[1])).done)return i;switch(o=0,i&&(t=[2&t[0],i.value]),t[0]){case 0:case 1:i=t;break;case 4:return n.label++,{value:t[1],done:!1};case 5:n.label++,o=t[1],t=[0];continue;case 7:t=n.ops.pop(),n.trys.pop();continue;default:if(!(i=(i=n.trys).length>0&&i[i.length-1])&&(6===t[0]||2===t[0])){n=0;continue}if(3===t[0]&&(!i||t[1]>i[0]&&t[1]<i[3])){n.label=t[1];break}if(6===t[0]&&n.label<i[1]){n.label=i[1],i=t;break}if(i&&n.label<i[2]){n.label=i[2],n.ops.push(t);break}i[2]&&n.ops.pop(),n.trys.pop();continue}t=a.call(e,n)}catch(e){t=[6,e],o=0}finally{r=i=0}if(5&t[0])throw t[1];return{value:t[0]?t[1]:void 0,done:!0}}([t,s])}}}var i={0:"tench, Tinca tinca",1:"goldfish, Carassius auratus",2:"great white shark, white shark, man-eater, man-eating shark, Carcharodon carcharias",3:"tiger shark, Galeocerdo cuvieri",4:"hammerhead, hammerhead shark",5:"electric ray, crampfish, numbfish, torpedo",6:"stingray",7:"cock",8:"hen",9:"ostrich, Struthio camelus",10:"brambling, Fringilla montifringilla",11:"goldfinch, Carduelis carduelis",12:"house finch, linnet, Carpodacus mexicanus",13:"junco, snowbird",14:"indigo bunting, indigo finch, indigo bird, Passerina cyanea",15:"robin, American robin, Turdus migratorius",16:"bulbul",17:"jay",18:"magpie",19:"chickadee",20:"water ouzel, dipper",21:"kite",22:"bald eagle, American eagle, Haliaeetus leucocephalus",23:"vulture",24:"great grey owl, great gray owl, Strix nebulosa",25:"European fire salamander, Salamandra salamandra",26:"common newt, Triturus vulgaris",27:"eft",28:"spotted salamander, Ambystoma maculatum",29:"axolotl, mud puppy, Ambystoma mexicanum",30:"bullfrog, Rana catesbeiana",31:"tree frog, tree-frog",32:"tailed frog, bell toad, ribbed toad, tailed toad, Ascaphus trui",33:"loggerhead, loggerhead turtle, Caretta caretta",34:"leatherback turtle, leatherback, leathery turtle, Dermochelys coriacea",35:"mud turtle",36:"terrapin",37:"box turtle, box tortoise",38:"banded gecko",39:"common iguana, iguana, Iguana iguana",40:"American chameleon, anole, Anolis carolinensis",41:"whiptail, whiptail lizard",42:"agama",43:"frilled lizard, Chlamydosaurus kingi",44:"alligator lizard",45:"Gila monster, Heloderma suspectum",46:"green lizard, Lacerta viridis",47:"African chameleon, Chamaeleo chamaeleon",48:"Komodo dragon, Komodo lizard, dragon lizard, giant lizard, Varanus komodoensis",49:"African crocodile, Nile crocodile, Crocodylus niloticus",50:"American alligator, Alligator mississipiensis",51:"triceratops",52:"thunder snake, worm snake, Carphophis amoenus",53:"ringneck snake, ring-necked snake, ring snake",54:"hognose snake, puff adder, sand viper",55:"green snake, grass snake",56:"king snake, kingsnake",57:"garter snake, grass snake",58:"water snake",59:"vine snake",60:"night snake, Hypsiglena torquata",61:"boa constrictor, Constrictor constrictor",62:"rock python, rock snake, Python sebae",63:"Indian cobra, Naja naja",64:"green mamba",65:"sea snake",66:"horned viper, cerastes, sand viper, horned asp, Cerastes cornutus",67:"diamondback, diamondback rattlesnake, Crotalus adamanteus",68:"sidewinder, horned rattlesnake, Crotalus cerastes",69:"trilobite",70:"harvestman, daddy longlegs, Phalangium opilio",71:"scorpion",72:"black and gold garden spider, Argiope aurantia",73:"barn spider, Araneus cavaticus",74:"garden spider, Aranea diademata",75:"black widow, Latrodectus mactans",76:"tarantula",77:"wolf spider, hunting spider",78:"tick",79:"centipede",80:"black grouse",81:"ptarmigan",82:"ruffed grouse, partridge, Bonasa umbellus",83:"prairie chicken, prairie grouse, prairie fowl",84:"peacock",85:"quail",86:"partridge",87:"African grey, African gray, Psittacus erithacus",88:"macaw",89:"sulphur-crested cockatoo, Kakatoe galerita, Cacatua galerita",90:"lorikeet",91:"coucal",92:"bee eater",93:"hornbill",94:"hummingbird",95:"jacamar",96:"toucan",97:"drake",98:"red-breasted merganser, Mergus serrator",99:"goose",100:"black swan, Cygnus atratus",101:"tusker",102:"echidna, spiny anteater, anteater",103:"platypus, duckbill, duckbilled platypus, duck-billed platypus, Ornithorhynchus anatinus",104:"wallaby, brush kangaroo",105:"koala, koala bear, kangaroo bear, native bear, Phascolarctos cinereus",106:"wombat",107:"jelly fish",108:"sea anemone, anemone",109:"brain coral",110:"flatworm, platyhelminth",111:"nematode, nematode worm, roundworm",112:"conch",113:"snail",114:"slug",115:"sea slug, nudibranch",116:"chiton, coat-of-mail shell, sea cradle, polyplacophore",117:"chambered nautilus, pearly nautilus, nautilus",118:"Dungeness crab, Cancer magister",119:"rock crab, Cancer irroratus",120:"fiddler crab",121:"king crab, Alaska crab, Alaskan king crab, Alaska king crab, Paralithodes camtschatica",122:"American lobster, Northern lobster, Maine lobster, Homarus americanus",123:"spiny lobster, langouste, rock lobster, crawfish, crayfish, sea crawfish",124:"crayfish, crawfish, crawdad, crawdaddy",125:"hermit crab",126:"isopod",127:"white stork, Ciconia ciconia",128:"black stork, Ciconia nigra",129:"spoonbill",130:"flamingo",131:"little blue heron, Egretta caerulea",132:"American egret, great white heron, Egretta albus",133:"bittern",134:"crane",135:"limpkin, Aramus pictus",136:"European gallinule, Porphyrio porphyrio",137:"American coot, marsh hen, mud hen, water hen, Fulica americana",138:"bustard",139:"ruddy turnstone, Arenaria interpres",140:"red-backed sandpiper, dunlin, Erolia alpina",141:"redshank, Tringa totanus",142:"dowitcher",143:"oystercatcher, oyster catcher",144:"pelican",145:"king penguin, Aptenodytes patagonica",146:"albatross, mollymawk",147:"grey whale, gray whale, devilfish, Eschrichtius gibbosus, Eschrichtius robustus",148:"killer whale, killer, orca, grampus, sea wolf, Orcinus orca",149:"dugong, Dugong dugon",150:"sea lion",151:"Chihuahua",152:"Japanese spaniel",153:"Maltese dog, Maltese terrier, Maltese",154:"Pekinese, Pekingese, Peke",155:"Shih-Tzu",156:"Blenheim spaniel",157:"papillon",158:"toy terrier",159:"Rhodesian ridgeback",160:"Afghan hound, Afghan",161:"basset, basset hound",162:"beagle",163:"bloodhound, sleuthhound",164:"bluetick",165:"black-and-tan coonhound",166:"Walker hound, Walker foxhound",167:"English foxhound",168:"redbone",169:"borzoi, Russian wolfhound",170:"Irish wolfhound",171:"Italian greyhound",172:"whippet",173:"Ibizan hound, Ibizan Podenco",174:"Norwegian elkhound, elkhound",175:"otterhound, otter hound",176:"Saluki, gazelle hound",177:"Scottish deerhound, deerhound",178:"Weimaraner",179:"Staffordshire bullterrier, Staffordshire bull terrier",180:"American Staffordshire terrier, Staffordshire terrier, American pit bull terrier, pit bull terrier",181:"Bedlington terrier",182:"Border terrier",183:"Kerry blue terrier",184:"Irish terrier",185:"Norfolk terrier",186:"Norwich terrier",187:"Yorkshire terrier",188:"wire-haired fox terrier",189:"Lakeland terrier",190:"Sealyham terrier, Sealyham",191:"Airedale, Airedale terrier",192:"cairn, cairn terrier",193:"Australian terrier",194:"Dandie Dinmont, Dandie Dinmont terrier",195:"Boston bull, Boston terrier",196:"miniature schnauzer",197:"giant schnauzer",198:"standard schnauzer",199:"Scotch terrier, Scottish terrier, Scottie",200:"Tibetan terrier, chrysanthemum dog",201:"silky terrier, Sydney silky",202:"soft-coated wheaten terrier",203:"West Highland white terrier",204:"Lhasa, Lhasa apso",205:"flat-coated retriever",206:"curly-coated retriever",207:"golden retriever",208:"Labrador retriever",209:"Chesapeake Bay retriever",210:"German short-haired pointer",211:"vizsla, Hungarian pointer",212:"English setter",213:"Irish setter, red setter",214:"Gordon setter",215:"Brittany spaniel",216:"clumber, clumber spaniel",217:"English springer, English springer spaniel",218:"Welsh springer spaniel",219:"cocker spaniel, English cocker spaniel, cocker",220:"Sussex spaniel",221:"Irish water spaniel",222:"kuvasz",223:"schipperke",224:"groenendael",225:"malinois",226:"briard",227:"kelpie",228:"komondor",229:"Old English sheepdog, bobtail",230:"Shetland sheepdog, Shetland sheep dog, Shetland",231:"collie",232:"Border collie",233:"Bouvier des Flandres, Bouviers des Flandres",234:"Rottweiler",235:"German shepherd, German shepherd dog, German police dog, alsatian",236:"Doberman, Doberman pinscher",237:"miniature pinscher",238:"Greater Swiss Mountain dog",239:"Bernese mountain dog",240:"Appenzeller",241:"EntleBucher",242:"boxer",243:"bull mastiff",244:"Tibetan mastiff",245:"French bulldog",246:"Great Dane",247:"Saint Bernard, St Bernard",248:"Eskimo dog, husky",249:"malamute, malemute, Alaskan malamute",250:"Siberian husky",251:"dalmatian, coach dog, carriage dog",252:"affenpinscher, monkey pinscher, monkey dog",253:"basenji",254:"pug, pug-dog",255:"Leonberg",256:"Newfoundland, Newfoundland dog",257:"Great Pyrenees",258:"Samoyed, Samoyede",259:"Pomeranian",260:"chow, chow chow",261:"keeshond",262:"Brabancon griffon",263:"Pembroke, Pembroke Welsh corgi",264:"Cardigan, Cardigan Welsh corgi",265:"toy poodle",266:"miniature poodle",267:"standard poodle",268:"Mexican hairless",269:"timber wolf, grey wolf, gray wolf, Canis lupus",270:"white wolf, Arctic wolf, Canis lupus tundrarum",271:"red wolf, maned wolf, Canis rufus, Canis niger",272:"coyote, prairie wolf, brush wolf, Canis latrans",273:"dingo, warrigal, warragal, Canis dingo",274:"dhole, Cuon alpinus",275:"African hunting dog, hyena dog, Cape hunting dog, Lycaon pictus",276:"hyena, hyaena",277:"red fox, Vulpes vulpes",278:"kit fox, Vulpes macrotis",279:"Arctic fox, white fox, Alopex lagopus",280:"grey fox, gray fox, Urocyon cinereoargenteus",281:"tabby, tabby cat",282:"tiger cat",283:"Persian cat",284:"Siamese cat, Siamese",285:"Egyptian cat",286:"cougar, puma, catamount, mountain lion, painter, panther, Felis concolor",287:"lynx, catamount",288:"leopard, Panthera pardus",289:"snow leopard, ounce, Panthera uncia",290:"jaguar, panther, Panthera onca, Felis onca",291:"lion, king of beasts, Panthera leo",292:"tiger, Panthera tigris",293:"cheetah, chetah, Acinonyx jubatus",294:"brown bear, bruin, Ursus arctos",295:"American black bear, black bear, Ursus americanus, Euarctos americanus",296:"ice bear, polar bear, Ursus Maritimus, Thalarctos maritimus",297:"sloth bear, Melursus ursinus, Ursus ursinus",298:"mongoose",299:"meerkat, mierkat",300:"tiger beetle",301:"ladybug, ladybeetle, lady beetle, ladybird, ladybird beetle",302:"ground beetle, carabid beetle",303:"long-horned beetle, longicorn, longicorn beetle",304:"leaf beetle, chrysomelid",305:"dung beetle",306:"rhinoceros beetle",307:"weevil",308:"fly",309:"bee",310:"ant, emmet, pismire",311:"grasshopper, hopper",312:"cricket",313:"walking stick, walkingstick, stick insect",314:"cockroach, roach",315:"mantis, mantid",316:"cicada, cicala",317:"leafhopper",318:"lacewing, lacewing fly",319:"dragonfly, darning needle, devil's darning needle, sewing needle, snake feeder, snake doctor, mosquito hawk, skeeter hawk",320:"damselfly",321:"admiral",322:"ringlet, ringlet butterfly",323:"monarch, monarch butterfly, milkweed butterfly, Danaus plexippus",324:"cabbage butterfly",325:"sulphur butterfly, sulfur butterfly",326:"lycaenid, lycaenid butterfly",327:"starfish, sea star",328:"sea urchin",329:"sea cucumber, holothurian",330:"wood rabbit, cottontail, cottontail rabbit",331:"hare",332:"Angora, Angora rabbit",333:"hamster",334:"porcupine, hedgehog",335:"fox squirrel, eastern fox squirrel, Sciurus niger",336:"marmot",337:"beaver",338:"guinea pig, Cavia cobaya",339:"sorrel",340:"zebra",341:"hog, pig, grunter, squealer, Sus scrofa",342:"wild boar, boar, Sus scrofa",343:"warthog",344:"hippopotamus, hippo, river horse, Hippopotamus amphibius",345:"ox",346:"water buffalo, water ox, Asiatic buffalo, Bubalus bubalis",347:"bison",348:"ram, tup",349:"bighorn, bighorn sheep, cimarron, Rocky Mountain bighorn, Rocky Mountain sheep, Ovis canadensis",350:"ibex, Capra ibex",351:"hartebeest",352:"impala, Aepyceros melampus",353:"gazelle",354:"Arabian camel, dromedary, Camelus dromedarius",355:"llama",356:"weasel",357:"mink",358:"polecat, fitch, foulmart, foumart, Mustela putorius",359:"black-footed ferret, ferret, Mustela nigripes",360:"otter",361:"skunk, polecat, wood pussy",362:"badger",363:"armadillo",364:"three-toed sloth, ai, Bradypus tridactylus",365:"orangutan, orang, orangutang, Pongo pygmaeus",366:"gorilla, Gorilla gorilla",367:"chimpanzee, chimp, Pan troglodytes",368:"gibbon, Hylobates lar",369:"siamang, Hylobates syndactylus, Symphalangus syndactylus",370:"guenon, guenon monkey",371:"patas, hussar monkey, Erythrocebus patas",372:"baboon",373:"macaque",374:"langur",375:"colobus, colobus monkey",376:"proboscis monkey, Nasalis larvatus",377:"marmoset",378:"capuchin, ringtail, Cebus capucinus",379:"howler monkey, howler",380:"titi, titi monkey",381:"spider monkey, Ateles geoffroyi",382:"squirrel monkey, Saimiri sciureus",383:"Madagascar cat, ring-tailed lemur, Lemur catta",384:"indri, indris, Indri indri, Indri brevicaudatus",385:"Indian elephant, Elephas maximus",386:"African elephant, Loxodonta africana",387:"lesser panda, red panda, panda, bear cat, cat bear, Ailurus fulgens",388:"giant panda, panda, panda bear, coon bear, Ailuropoda melanoleuca",389:"barracouta, snoek",390:"eel",391:"coho, cohoe, coho salmon, blue jack, silver salmon, Oncorhynchus kisutch",392:"rock beauty, Holocanthus tricolor",393:"anemone fish",394:"sturgeon",395:"gar, garfish, garpike, billfish, Lepisosteus osseus",396:"lionfish",397:"puffer, pufferfish, blowfish, globefish",398:"abacus",399:"abaya",400:"academic gown, academic robe, judge's robe",401:"accordion, piano accordion, squeeze box",402:"acoustic guitar",403:"aircraft carrier, carrier, flattop, attack aircraft carrier",404:"airliner",405:"airship, dirigible",406:"altar",407:"ambulance",408:"amphibian, amphibious vehicle",409:"analog clock",410:"apiary, bee house",411:"apron",412:"ashcan, trash can, garbage can, wastebin, ash bin, ash-bin, ashbin, dustbin, trash barrel, trash bin",413:"assault rifle, assault gun",414:"backpack, back pack, knapsack, packsack, rucksack, haversack",415:"bakery, bakeshop, bakehouse",416:"balance beam, beam",417:"balloon",418:"ballpoint, ballpoint pen, ballpen, Biro",419:"Band Aid",420:"banjo",421:"bannister, banister, balustrade, balusters, handrail",422:"barbell",423:"barber chair",424:"barbershop",425:"barn",426:"barometer",427:"barrel, cask",428:"barrow, garden cart, lawn cart, wheelbarrow",429:"baseball",430:"basketball",431:"bassinet",432:"bassoon",433:"bathing cap, swimming cap",434:"bath towel",435:"bathtub, bathing tub, bath, tub",436:"beach wagon, station wagon, wagon, estate car, beach waggon, station waggon, waggon",437:"beacon, lighthouse, beacon light, pharos",438:"beaker",439:"bearskin, busby, shako",440:"beer bottle",441:"beer glass",442:"bell cote, bell cot",443:"bib",444:"bicycle-built-for-two, tandem bicycle, tandem",445:"bikini, two-piece",446:"binder, ring-binder",447:"binoculars, field glasses, opera glasses",448:"birdhouse",449:"boathouse",450:"bobsled, bobsleigh, bob",451:"bolo tie, bolo, bola tie, bola",452:"bonnet, poke bonnet",453:"bookcase",454:"bookshop, bookstore, bookstall",455:"bottlecap",456:"bow",457:"bow tie, bow-tie, bowtie",458:"brass, memorial tablet, plaque",459:"brassiere, bra, bandeau",460:"breakwater, groin, groyne, mole, bulwark, seawall, jetty",461:"breastplate, aegis, egis",462:"broom",463:"bucket, pail",464:"buckle",465:"bulletproof vest",466:"bullet train, bullet",467:"butcher shop, meat market",468:"cab, hack, taxi, taxicab",469:"caldron, cauldron",470:"candle, taper, wax light",471:"cannon",472:"canoe",473:"can opener, tin opener",474:"cardigan",475:"car mirror",476:"carousel, carrousel, merry-go-round, roundabout, whirligig",477:"carpenter's kit, tool kit",478:"carton",479:"car wheel",480:"cash machine, cash dispenser, automated teller machine, automatic teller machine, automated teller, automatic teller, ATM",481:"cassette",482:"cassette player",483:"castle",484:"catamaran",485:"CD player",486:"cello, violoncello",487:"cellular telephone, cellular phone, cellphone, cell, mobile phone",488:"chain",489:"chainlink fence",490:"chain mail, ring mail, mail, chain armor, chain armour, ring armor, ring armour",491:"chain saw, chainsaw",492:"chest",493:"chiffonier, commode",494:"chime, bell, gong",495:"china cabinet, china closet",496:"Christmas stocking",497:"church, church building",498:"cinema, movie theater, movie theatre, movie house, picture palace",499:"cleaver, meat cleaver, chopper",500:"cliff dwelling",501:"cloak",502:"clog, geta, patten, sabot",503:"cocktail shaker",504:"coffee mug",505:"coffeepot",506:"coil, spiral, volute, whorl, helix",507:"combination lock",508:"computer keyboard, keypad",509:"confectionery, confectionary, candy store",510:"container ship, containership, container vessel",511:"convertible",512:"corkscrew, bottle screw",513:"cornet, horn, trumpet, trump",514:"cowboy boot",515:"cowboy hat, ten-gallon hat",516:"cradle",517:"crane",518:"crash helmet",519:"crate",520:"crib, cot",521:"Crock Pot",522:"croquet ball",523:"crutch",524:"cuirass",525:"dam, dike, dyke",526:"desk",527:"desktop computer",528:"dial telephone, dial phone",529:"diaper, nappy, napkin",530:"digital clock",531:"digital watch",532:"dining table, board",533:"dishrag, dishcloth",534:"dishwasher, dish washer, dishwashing machine",535:"disk brake, disc brake",536:"dock, dockage, docking facility",537:"dogsled, dog sled, dog sleigh",538:"dome",539:"doormat, welcome mat",540:"drilling platform, offshore rig",541:"drum, membranophone, tympan",542:"drumstick",543:"dumbbell",544:"Dutch oven",545:"electric fan, blower",546:"electric guitar",547:"electric locomotive",548:"entertainment center",549:"envelope",550:"espresso maker",551:"face powder",552:"feather boa, boa",553:"file, file cabinet, filing cabinet",554:"fireboat",555:"fire engine, fire truck",556:"fire screen, fireguard",557:"flagpole, flagstaff",558:"flute, transverse flute",559:"folding chair",560:"football helmet",561:"forklift",562:"fountain",563:"fountain pen",564:"four-poster",565:"freight car",566:"French horn, horn",567:"frying pan, frypan, skillet",568:"fur coat",569:"garbage truck, dustcart",570:"gasmask, respirator, gas helmet",571:"gas pump, gasoline pump, petrol pump, island dispenser",572:"goblet",573:"go-kart",574:"golf ball",575:"golfcart, golf cart",576:"gondola",577:"gong, tam-tam",578:"gown",579:"grand piano, grand",580:"greenhouse, nursery, glasshouse",581:"grille, radiator grille",582:"grocery store, grocery, food market, market",583:"guillotine",584:"hair slide",585:"hair spray",586:"half track",587:"hammer",588:"hamper",589:"hand blower, blow dryer, blow drier, hair dryer, hair drier",590:"hand-held computer, hand-held microcomputer",591:"handkerchief, hankie, hanky, hankey",592:"hard disc, hard disk, fixed disk",593:"harmonica, mouth organ, harp, mouth harp",594:"harp",595:"harvester, reaper",596:"hatchet",597:"holster",598:"home theater, home theatre",599:"honeycomb",600:"hook, claw",601:"hoopskirt, crinoline",602:"horizontal bar, high bar",603:"horse cart, horse-cart",604:"hourglass",605:"iPod",606:"iron, smoothing iron",607:"jack-o'-lantern",608:"jean, blue jean, denim",609:"jeep, landrover",610:"jersey, T-shirt, tee shirt",611:"jigsaw puzzle",612:"jinrikisha, ricksha, rickshaw",613:"joystick",614:"kimono",615:"knee pad",616:"knot",617:"lab coat, laboratory coat",618:"ladle",619:"lampshade, lamp shade",620:"laptop, laptop computer",621:"lawn mower, mower",622:"lens cap, lens cover",623:"letter opener, paper knife, paperknife",624:"library",625:"lifeboat",626:"lighter, light, igniter, ignitor",627:"limousine, limo",628:"liner, ocean liner",629:"lipstick, lip rouge",630:"Loafer",631:"lotion",632:"loudspeaker, speaker, speaker unit, loudspeaker system, speaker system",633:"loupe, jeweler's loupe",634:"lumbermill, sawmill",635:"magnetic compass",636:"mailbag, postbag",637:"mailbox, letter box",638:"maillot",639:"maillot, tank suit",640:"manhole cover",641:"maraca",642:"marimba, xylophone",643:"mask",644:"matchstick",645:"maypole",646:"maze, labyrinth",647:"measuring cup",648:"medicine chest, medicine cabinet",649:"megalith, megalithic structure",650:"microphone, mike",651:"microwave, microwave oven",652:"military uniform",653:"milk can",654:"minibus",655:"miniskirt, mini",656:"minivan",657:"missile",658:"mitten",659:"mixing bowl",660:"mobile home, manufactured home",661:"Model T",662:"modem",663:"monastery",664:"monitor",665:"moped",666:"mortar",667:"mortarboard",668:"mosque",669:"mosquito net",670:"motor scooter, scooter",671:"mountain bike, all-terrain bike, off-roader",672:"mountain tent",673:"mouse, computer mouse",674:"mousetrap",675:"moving van",676:"muzzle",677:"nail",678:"neck brace",679:"necklace",680:"nipple",681:"notebook, notebook computer",682:"obelisk",683:"oboe, hautboy, hautbois",684:"ocarina, sweet potato",685:"odometer, hodometer, mileometer, milometer",686:"oil filter",687:"organ, pipe organ",688:"oscilloscope, scope, cathode-ray oscilloscope, CRO",689:"overskirt",690:"oxcart",691:"oxygen mask",692:"packet",693:"paddle, boat paddle",694:"paddlewheel, paddle wheel",695:"padlock",696:"paintbrush",697:"pajama, pyjama, pj's, jammies",698:"palace",699:"panpipe, pandean pipe, syrinx",700:"paper towel",701:"parachute, chute",702:"parallel bars, bars",703:"park bench",704:"parking meter",705:"passenger car, coach, carriage",706:"patio, terrace",707:"pay-phone, pay-station",708:"pedestal, plinth, footstall",709:"pencil box, pencil case",710:"pencil sharpener",711:"perfume, essence",712:"Petri dish",713:"photocopier",714:"pick, plectrum, plectron",715:"pickelhaube",716:"picket fence, paling",717:"pickup, pickup truck",718:"pier",719:"piggy bank, penny bank",720:"pill bottle",721:"pillow",722:"ping-pong ball",723:"pinwheel",724:"pirate, pirate ship",725:"pitcher, ewer",726:"plane, carpenter's plane, woodworking plane",727:"planetarium",728:"plastic bag",729:"plate rack",730:"plow, plough",731:"plunger, plumber's helper",732:"Polaroid camera, Polaroid Land camera",733:"pole",734:"police van, police wagon, paddy wagon, patrol wagon, wagon, black Maria",735:"poncho",736:"pool table, billiard table, snooker table",737:"pop bottle, soda bottle",738:"pot, flowerpot",739:"potter's wheel",740:"power drill",741:"prayer rug, prayer mat",742:"printer",743:"prison, prison house",744:"projectile, missile",745:"projector",746:"puck, hockey puck",747:"punching bag, punch bag, punching ball, punchball",748:"purse",749:"quill, quill pen",750:"quilt, comforter, comfort, puff",751:"racer, race car, racing car",752:"racket, racquet",753:"radiator",754:"radio, wireless",755:"radio telescope, radio reflector",756:"rain barrel",757:"recreational vehicle, RV, R.V.",758:"reel",759:"reflex camera",760:"refrigerator, icebox",761:"remote control, remote",762:"restaurant, eating house, eating place, eatery",763:"revolver, six-gun, six-shooter",764:"rifle",765:"rocking chair, rocker",766:"rotisserie",767:"rubber eraser, rubber, pencil eraser",768:"rugby ball",769:"rule, ruler",770:"running shoe",771:"safe",772:"safety pin",773:"saltshaker, salt shaker",774:"sandal",775:"sarong",776:"sax, saxophone",777:"scabbard",778:"scale, weighing machine",779:"school bus",780:"schooner",781:"scoreboard",782:"screen, CRT screen",783:"screw",784:"screwdriver",785:"seat belt, seatbelt",786:"sewing machine",787:"shield, buckler",788:"shoe shop, shoe-shop, shoe store",789:"shoji",790:"shopping basket",791:"shopping cart",792:"shovel",793:"shower cap",794:"shower curtain",795:"ski",796:"ski mask",797:"sleeping bag",798:"slide rule, slipstick",799:"sliding door",800:"slot, one-armed bandit",801:"snorkel",802:"snowmobile",803:"snowplow, snowplough",804:"soap dispenser",805:"soccer ball",806:"sock",807:"solar dish, solar collector, solar furnace",808:"sombrero",809:"soup bowl",810:"space bar",811:"space heater",812:"space shuttle",813:"spatula",814:"speedboat",815:"spider web, spider's web",816:"spindle",817:"sports car, sport car",818:"spotlight, spot",819:"stage",820:"steam locomotive",821:"steel arch bridge",822:"steel drum",823:"stethoscope",824:"stole",825:"stone wall",826:"stopwatch, stop watch",827:"stove",828:"strainer",829:"streetcar, tram, tramcar, trolley, trolley car",830:"stretcher",831:"studio couch, day bed",832:"stupa, tope",833:"submarine, pigboat, sub, U-boat",834:"suit, suit of clothes",835:"sundial",836:"sunglass",837:"sunglasses, dark glasses, shades",838:"sunscreen, sunblock, sun blocker",839:"suspension bridge",840:"swab, swob, mop",841:"sweatshirt",842:"swimming trunks, bathing trunks",843:"swing",844:"switch, electric switch, electrical switch",845:"syringe",846:"table lamp",847:"tank, army tank, armored combat vehicle, armoured combat vehicle",848:"tape player",849:"teapot",850:"teddy, teddy bear",851:"television, television system",852:"tennis ball",853:"thatch, thatched roof",854:"theater curtain, theatre curtain",855:"thimble",856:"thresher, thrasher, threshing machine",857:"throne",858:"tile roof",859:"toaster",860:"tobacco shop, tobacconist shop, tobacconist",861:"toilet seat",862:"torch",863:"totem pole",864:"tow truck, tow car, wrecker",865:"toyshop",866:"tractor",867:"trailer truck, tractor trailer, trucking rig, rig, articulated lorry, semi",868:"tray",869:"trench coat",870:"tricycle, trike, velocipede",871:"trimaran",872:"tripod",873:"triumphal arch",874:"trolleybus, trolley coach, trackless trolley",875:"trombone",876:"tub, vat",877:"turnstile",878:"typewriter keyboard",879:"umbrella",880:"unicycle, monocycle",881:"upright, upright piano",882:"vacuum, vacuum cleaner",883:"vase",884:"vault",885:"velvet",886:"vending machine",887:"vestment",888:"viaduct",889:"violin, fiddle",890:"volleyball",891:"waffle iron",892:"wall clock",893:"wallet, billfold, notecase, pocketbook",894:"wardrobe, closet, press",895:"warplane, military plane",896:"washbasin, handbasin, washbowl, lavabo, wash-hand basin",897:"washer, automatic washer, washing machine",898:"water bottle",899:"water jug",900:"water tower",901:"whiskey jug",902:"whistle",903:"wig",904:"window screen",905:"window shade",906:"Windsor tie",907:"wine bottle",908:"wing",909:"wok",910:"wooden spoon",911:"wool, woolen, woollen",912:"worm fence, snake fence, snake-rail fence, Virginia fence",913:"wreck",914:"yawl",915:"yurt",916:"web site, website, internet site, site",917:"comic book",918:"crossword puzzle, crossword",919:"street sign",920:"traffic light, traffic signal, stoplight",921:"book jacket, dust cover, dust jacket, dust wrapper",922:"menu",923:"plate",924:"guacamole",925:"consomme",926:"hot pot, hotpot",927:"trifle",928:"ice cream, icecream",929:"ice lolly, lolly, lollipop, popsicle",930:"French loaf",931:"bagel, beigel",932:"pretzel",933:"cheeseburger",934:"hotdog, hot dog, red hot",935:"mashed potato",936:"head cabbage",937:"broccoli",938:"cauliflower",939:"zucchini, courgette",940:"spaghetti squash",941:"acorn squash",942:"butternut squash",943:"cucumber, cuke",944:"artichoke, globe artichoke",945:"bell pepper",946:"cardoon",947:"mushroom",948:"Granny Smith",949:"strawberry",950:"orange",951:"lemon",952:"fig",953:"pineapple, ananas",954:"banana",955:"jackfruit, jak, jack",956:"custard apple",957:"pomegranate",958:"hay",959:"carbonara",960:"chocolate sauce, chocolate syrup",961:"dough",962:"meat loaf, meatloaf",963:"pizza, pizza pie",964:"potpie",965:"burrito",966:"red wine",967:"espresso",968:"cup",969:"eggnog",970:"alp",971:"bubble",972:"cliff, drop, drop-off",973:"coral reef",974:"geyser",975:"lakeside, lakeshore",976:"promontory, headland, head, foreland",977:"sandbar, sand bar",978:"seashore, coast, seacoast, sea-coast",979:"valley, vale",980:"volcano",981:"ballplayer, baseball player",982:"groom, bridegroom",983:"scuba diver",984:"rapeseed",985:"daisy",986:"yellow lady's slipper, yellow lady-slipper, Cypripedium calceolus, Cypripedium parviflorum",987:"corn",988:"acorn",989:"hip, rose hip, rosehip",990:"buckeye, horse chestnut, conker",991:"coral fungus",992:"agaric",993:"gyromitra",994:"stinkhorn, carrion fungus",995:"earthstar",996:"hen-of-the-woods, hen of the woods, Polyporus frondosus, Grifola frondosa",997:"bolete",998:"ear, spike, capitulum",999:"toilet tissue, toilet paper, bathroom tissue"},t={"1.00":"module_apply_default/MobilenetV1/Logits/global_pool","2.00":"module_apply_default/MobilenetV2/Logits/AvgPool"},n={"1.00":{.25:"https://tfhub.dev/google/imagenet/mobilenet_v1_025_224/classification/1","0.50":"https://tfhub.dev/google/imagenet/mobilenet_v1_050_224/classification/1",.75:"https://tfhub.dev/google/imagenet/mobilenet_v1_075_224/classification/1","1.00":"https://tfhub.dev/google/imagenet/mobilenet_v1_100_224/classification/1"},"2.00":{"0.50":"https://tfhub.dev/google/imagenet/mobilenet_v2_050_224/classification/2",.75:"https://tfhub.dev/google/imagenet/mobilenet_v2_075_224/classification/2","1.00":"https://tfhub.dev/google/imagenet/mobilenet_v2_100_224/classification/2"}};var s=function(){function e(e,r){this.version=e,this.alpha=r,this.normalizationOffset=a.scalar(127.5)}return e.prototype.load=function(){return r(this,void 0,void 0,function(){var e,r,i,t=this;return o(this,function(o){switch(o.label){case 0:return e=n[this.version][this.alpha],r=this,[4,a.loadGraphModel(e,{fromTFHub:!0})];case 1:return r.model=o.sent(),[4,(i=a.tidy(function(){return t.model.predict(a.zeros([1,224,224,3]))})).data()];case 2:return o.sent(),i.dispose(),[2]}})})},e.prototype.infer=function(e,r){var o=this;return void 0===r&&(r=!1),a.tidy(function(){e instanceof a.Tensor||(e=a.browser.fromPixels(e));var i=e.toFloat().sub(o.normalizationOffset).div(o.normalizationOffset),n=i;if(224!==e.shape[0]||224!==e.shape[1]){n=a.image.resizeBilinear(i,[224,224],!0)}var s,l=n.reshape([-1,224,224,3]);if(r){var c=t[o.version];s=o.model.execute(l,c).squeeze([1,2])}else{s=o.model.predict(l).slice([0,1],[-1,1e3])}return s})},e.prototype.classify=function(e,a){return void 0===a&&(a=3),r(this,void 0,void 0,function(){var t,n;return o(this,function(s){switch(s.label){case 0:return[4,function(e,a){return r(this,void 0,void 0,function(){var r,t,n,s,l,c,u;return o(this,function(o){switch(o.label){case 0:return[4,(r=e.softmax()).data()];case 1:for(t=o.sent(),r.dispose(),n=[],u=0;u<t.length;u++)n.push({value:t[u],index:u});for(n.sort(function(e,a){return a.value-e.value}),s=new Float32Array(a),l=new Int32Array(a),u=0;u<a;u++)s[u]=n[u].value,l[u]=n[u].index;for(c=[],u=0;u<l.length;u++)c.push({className:i[l[u]],probability:s[u]});return[2,c]}})})}(t=this.infer(e),a)];case 1:return n=s.sent(),t.dispose(),[2,n]}})})},e}();e.load=function(e,i){return void 0===e&&(e=1),void 0===i&&(i=1),r(this,void 0,void 0,function(){var r,t,l;return o(this,function(o){switch(o.label){case 0:if(null==a)throw new Error("Cannot find TensorFlow.js. If you are using a <script> tag, please also include @tensorflow/tfjs on the page before using this model.");if(r=e.toFixed(2),t=i.toFixed(2),!(r in n))throw new Error("Invalid version of MobileNet. Valid versions are: "+Object.keys(n));if(!(t in n[r]))throw new Error("MobileNet constructed with invalid alpha "+i+". Valid multipliers for this version are: "+Object.keys(n[r])+".");return[4,(l=new s(r,t)).load()];case 1:return o.sent(),[2,l]}})})},e.MobileNet=s,Object.defineProperty(e,"__esModule",{value:!0})});
\ No newline at end of file
diff --git a/spaces/metricspace/OcTra/df_local/utils.py b/spaces/metricspace/OcTra/df_local/utils.py
deleted file mode 100644
index 3eb33922dea93a54af8d797bb6ae57f57daecf05..0000000000000000000000000000000000000000
--- a/spaces/metricspace/OcTra/df_local/utils.py
+++ /dev/null
@@ -1,230 +0,0 @@
-import collections
-import math
-import os
-import random
-import subprocess
-from socket import gethostname
-from typing import Any, Dict, Set, Tuple, Union
-
-import numpy as np
-import torch
-from loguru import logger
-from torch import Tensor
-#from torch._six import string_classes
-from torch.autograd import Function
-from torch.types import Number
-
-from df_local.config import config
-from df_local.model import ModelParams
-
-try:
-    from torchaudio.functional import resample as ta_resample
-except ImportError:
-    from torchaudio.compliance.kaldi import resample_waveform as ta_resample  # type: ignore
-
-
-def get_resample_params(method: str) -> Dict[str, Any]:
-    params = {
-        "sinc_fast": {"resampling_method": "sinc_interpolation", "lowpass_filter_width": 16},
-        "sinc_best": {"resampling_method": "sinc_interpolation", "lowpass_filter_width": 64},
-        "kaiser_fast": {
-            "resampling_method": "kaiser_window",
-            "lowpass_filter_width": 16,
-            "rolloff": 0.85,
-            "beta": 8.555504641634386,
-        },
-        "kaiser_best": {
-            "resampling_method": "kaiser_window",
-            "lowpass_filter_width": 16,
-            "rolloff": 0.9475937167399596,
-            "beta": 14.769656459379492,
-        },
-    }
-    assert method in params.keys(), f"method must be one of {list(params.keys())}"
-    return params[method]
-
-
-def resample(audio: Tensor, orig_sr: int, new_sr: int, method="sinc_fast"):
-    params = get_resample_params(method)
-    return ta_resample(audio, orig_sr, new_sr, **params)
-
-
-def get_device():
-    s = config("DEVICE", default="", section="train")
-    if s == "":
-        if torch.cuda.is_available():
-            DEVICE = torch.device("cuda:0")
-        else:
-            DEVICE = torch.device("cpu")
-    else:
-        DEVICE = torch.device(s)
-    return DEVICE
-
-
-def as_complex(x: Tensor):
-    if torch.is_complex(x):
-        return x
-    if x.shape[-1] != 2:
-        raise ValueError(f"Last dimension need to be of length 2 (re + im), but got {x.shape}")
-    if x.stride(-1) != 1:
-        x = x.contiguous()
-    return torch.view_as_complex(x)
-
-
-def as_real(x: Tensor):
-    if torch.is_complex(x):
-        return torch.view_as_real(x)
-    return x
-
-
-class angle_re_im(Function):
-    """Similar to torch.angle but robustify the gradient for zero magnitude."""
-
-    @staticmethod
-    def forward(ctx, re: Tensor, im: Tensor):
-        ctx.save_for_backward(re, im)
-        return torch.atan2(im, re)
-
-    @staticmethod
-    def backward(ctx, grad: Tensor) -> Tuple[Tensor, Tensor]:
-        re, im = ctx.saved_tensors
-        grad_inv = grad / (re.square() + im.square()).clamp_min_(1e-10)
-        return -im * grad_inv, re * grad_inv
-
-
-class angle(Function):
-    """Similar to torch.angle but robustify the gradient for zero magnitude."""
-
-    @staticmethod
-    def forward(ctx, x: Tensor):
-        ctx.save_for_backward(x)
-        return torch.atan2(x.imag, x.real)
-
-    @staticmethod
-    def backward(ctx, grad: Tensor):
-        (x,) = ctx.saved_tensors
-        grad_inv = grad / (x.real.square() + x.imag.square()).clamp_min_(1e-10)
-        return torch.view_as_complex(torch.stack((-x.imag * grad_inv, x.real * grad_inv), dim=-1))
-
-
-def check_finite_module(obj, name="Module", _raise=True) -> Set[str]:
-    out: Set[str] = set()
-    if isinstance(obj, torch.nn.Module):
-        for name, child in obj.named_children():
-            out = out | check_finite_module(child, name)
-        for name, param in obj.named_parameters():
-            out = out | check_finite_module(param, name)
-        for name, buf in obj.named_buffers():
-            out = out | check_finite_module(buf, name)
-    if _raise and len(out) > 0:
-        raise ValueError(f"{name} not finite during checkpoint writing including: {out}")
-    return out
-
-
-def make_np(x: Union[Tensor, np.ndarray, Number]) -> np.ndarray:
-    """Transforms Tensor to numpy.
-    Args:
-      x: An instance of torch tensor or caffe blob name
-
-    Returns:
-        numpy.array: Numpy array
-    """
-    if isinstance(x, np.ndarray):
-        return x
-    if np.isscalar(x):
-        return np.array([x])
-    if isinstance(x, Tensor):
-        return x.detach().cpu().numpy()
-    raise NotImplementedError(
-        "Got {}, but numpy array, scalar, or torch tensor are expected.".format(type(x))
-    )
-
-
-def get_norm_alpha(log: bool = True) -> float:
-    p = ModelParams()
-    a_ = _calculate_norm_alpha(sr=p.sr, hop_size=p.hop_size, tau=p.norm_tau)
-    precision = 3
-    a = 1.0
-    while a >= 1.0:
-        a = round(a_, precision)
-        precision += 1
-    if log:
-        logger.info(f"Running with normalization window alpha = '{a}'")
-    return a
-
-
-def _calculate_norm_alpha(sr: int, hop_size: int, tau: float):
-    """Exponential decay factor alpha for a given tau (decay window size [s])."""
-    dt = hop_size / sr
-    return math.exp(-dt / tau)
-
-
-def check_manual_seed(seed: int = None):
-    """If manual seed is not specified, choose a random one and communicate it to the user."""
-    seed = seed or random.randint(1, 10000)
-    np.random.seed(seed)
-    random.seed(seed)
-    torch.manual_seed(seed)
-    return seed
-
-
-def get_git_root():
-    git_local_dir = os.path.dirname(os.path.abspath(__file__))
-    args = ["git", "-C", git_local_dir, "rev-parse", "--show-toplevel"]
-    return subprocess.check_output(args).strip().decode()
-
-
-def get_commit_hash():
-    """Returns the current git commit."""
-    try:
-        git_dir = get_git_root()
-        args = ["git", "-C", git_dir, "rev-parse", "--short", "--verify", "HEAD"]
-        commit = subprocess.check_output(args).strip().decode()
-    except subprocess.CalledProcessError:
-        # probably not in git repo
-        commit = None
-    return commit
-
-
-def get_host() -> str:
-    return gethostname()
-
-
-def get_branch_name():
-    try:
-        git_dir = os.path.dirname(os.path.abspath(__file__))
-        args = ["git", "-C", git_dir, "rev-parse", "--abbrev-ref", "HEAD"]
-        branch = subprocess.check_output(args).strip().decode()
-    except subprocess.CalledProcessError:
-        # probably not in git repo
-        branch = None
-    return branch
-
-
-# from pytorch/ignite:
-def apply_to_tensor(input_, func):
-    """Apply a function on a tensor or mapping, or sequence of tensors."""
-    if isinstance(input_, torch.nn.Module):
-        return [apply_to_tensor(c, func) for c in input_.children()]
-    elif isinstance(input_, torch.nn.Parameter):
-        return func(input_.data)
-    elif isinstance(input_, Tensor):
-        return func(input_)
-    elif isinstance(input_, str):
-        return input_
-    elif isinstance(input_, collections.Mapping):
-        return {k: apply_to_tensor(sample, func) for k, sample in input_.items()}
-    elif isinstance(input_, collections.Iterable):
-        return [apply_to_tensor(sample, func) for sample in input_]
-    elif input_ is None:
-        return input_
-    else:
-        return input_
-
-
-def detach_hidden(hidden: Any) -> Any:
-    """Cut backpropagation graph.
-    Auxillary function to cut the backpropagation graph by detaching the hidden
-    vector.
-    """
-    return apply_to_tensor(hidden, Tensor.detach)
diff --git a/spaces/mikkoar/marco/src/lib/isomorphic/index.ts b/spaces/mikkoar/marco/src/lib/isomorphic/index.ts
deleted file mode 100644
index 738dc92f74079ab762d584fb7422a8c8c3b61547..0000000000000000000000000000000000000000
--- a/spaces/mikkoar/marco/src/lib/isomorphic/index.ts
+++ /dev/null
@@ -1,17 +0,0 @@
-'use client'
-
-import Default from './browser'
-
-let exportsModel: any = {}
-
-if (process.browser) {
-  Object.assign(exportsModel, require('./browser').default)
-} else {
-  Object.assign(exportsModel, require('./node').default)
-}
-
-export default exportsModel! as typeof Default
-
-export const fetch: typeof Default.fetch = exportsModel!.fetch
-export const WebSocket: typeof Default.WebSocket = exportsModel!.WebSocket
-export const debug: typeof Default.debug = exportsModel!.debug
diff --git a/spaces/milyiyo/reimagine-it/captioning/__init__.py b/spaces/milyiyo/reimagine-it/captioning/__init__.py
deleted file mode 100644
index e69de29bb2d1d6434b8b29ae775ad8c2e48c5391..0000000000000000000000000000000000000000
diff --git a/spaces/mingyuan/ReMoDiffuse/mogen/models/transformers/actor.py b/spaces/mingyuan/ReMoDiffuse/mogen/models/transformers/actor.py
deleted file mode 100644
index dee5a05cf5d460901ed0cddca04a9b9701cd89c4..0000000000000000000000000000000000000000
--- a/spaces/mingyuan/ReMoDiffuse/mogen/models/transformers/actor.py
+++ /dev/null
@@ -1,189 +0,0 @@
-from cv2 import norm
-import torch
-from torch import layer_norm, nn
-from mmcv.runner import BaseModule
-import numpy as np
-
-from ..builder import SUBMODULES
-from .position_encoding import SinusoidalPositionalEncoding, LearnedPositionalEncoding
-import math
-
-
-@SUBMODULES.register_module()
-class ACTOREncoder(BaseModule):
-    def __init__(self,
-                 max_seq_len=16,
-                 njoints=None,
-                 nfeats=None,
-                 input_feats=None,
-                 latent_dim=256,
-                 output_dim=256,
-                 condition_dim=None,
-                 num_heads=4,
-                 ff_size=1024,
-                 num_layers=8,
-                 activation='gelu',
-                 dropout=0.1,
-                 use_condition=False,
-                 num_class=None,
-                 use_final_proj=False,
-                 output_var=False,
-                 pos_embedding='sinusoidal',
-                 init_cfg=None):
-        super().__init__(init_cfg=init_cfg)
-        self.njoints = njoints
-        self.nfeats = nfeats
-        if input_feats is None:
-            assert self.njoints is not None and self.nfeats is not None
-            self.input_feats = njoints * nfeats
-        else:
-            self.input_feats = input_feats
-        self.max_seq_len = max_seq_len
-        self.latent_dim = latent_dim
-        self.condition_dim = condition_dim
-        self.use_condition = use_condition
-        self.num_class = num_class
-        self.use_final_proj = use_final_proj
-        self.output_var = output_var
-        self.skelEmbedding = nn.Linear(self.input_feats, self.latent_dim)
-        if self.use_condition:
-            if num_class is None:
-                self.mu_layer = build_MLP(self.condition_dim, self.latent_dim)
-                if self.output_var:
-                    self.sigma_layer = build_MLP(self.condition_dim, self.latent_dim)
-            else:
-                self.mu_layer = nn.Parameter(torch.randn(num_class, self.latent_dim))
-                if self.output_var:
-                    self.sigma_layer = nn.Parameter(torch.randn(num_class, self.latent_dim))
-        else:
-            if self.output_var:
-                self.query = nn.Parameter(torch.randn(2, self.latent_dim))
-            else:
-                self.query = nn.Parameter(torch.randn(1, self.latent_dim))
-        if pos_embedding == 'sinusoidal':
-            self.pos_encoder = SinusoidalPositionalEncoding(latent_dim, dropout)
-        else:
-            self.pos_encoder = LearnedPositionalEncoding(latent_dim, dropout, max_len=max_seq_len + 2)
-        seqTransEncoderLayer = nn.TransformerEncoderLayer(
-            d_model=self.latent_dim,
-            nhead=num_heads,
-            dim_feedforward=ff_size,
-            dropout=dropout,
-            activation=activation)
-        self.seqTransEncoder = nn.TransformerEncoder(
-            seqTransEncoderLayer,
-            num_layers=num_layers)
-
-    def forward(self, motion, motion_mask=None, condition=None):
-        B, T = motion.shape[:2]
-        motion = motion.view(B, T, -1)
-        feature = self.skelEmbedding(motion)
-        if self.use_condition:
-            if self.output_var:
-                if self.num_class is None:
-                    sigma_query = self.sigma_layer(condition).view(B, 1, -1)
-                else:
-                    sigma_query = self.sigma_layer[condition.long()].view(B, 1, -1)
-                feature = torch.cat((sigma_query, feature), dim=1)
-            if self.num_class is None:
-                mu_query = self.mu_layer(condition).view(B, 1, -1)
-            else:
-                mu_query = self.mu_layer[condition.long()].view(B, 1, -1)
-            feature = torch.cat((mu_query, feature), dim=1)  
-        else:
-            query = self.query.view(1, -1, self.latent_dim).repeat(B, 1, 1)
-            feature = torch.cat((query, feature), dim=1)
-        if self.output_var:
-            motion_mask = torch.cat((torch.zeros(B, 2).to(motion.device), 1 - motion_mask), dim=1).bool()
-        else:
-            motion_mask = torch.cat((torch.zeros(B, 1).to(motion.device), 1 - motion_mask), dim=1).bool()
-        feature = feature.permute(1, 0, 2).contiguous()
-        feature = self.pos_encoder(feature)
-        feature = self.seqTransEncoder(feature, src_key_padding_mask=motion_mask)
-        if self.use_final_proj:
-            mu = self.final_mu(feature[0])
-            if self.output_var:
-                sigma = self.final_sigma(feature[1])
-                return mu, sigma
-            return mu
-        else:
-            if self.output_var:
-                return feature[0], feature[1]
-            else:
-                return feature[0]
-
-
-@SUBMODULES.register_module()
-class ACTORDecoder(BaseModule):
-
-    def __init__(self,
-                 max_seq_len=16,
-                 njoints=None,
-                 nfeats=None,
-                 input_feats=None,
-                 input_dim=256,
-                 latent_dim=256,
-                 condition_dim=None,
-                 num_heads=4,
-                 ff_size=1024,
-                 num_layers=8,
-                 activation='gelu',
-                 dropout=0.1,
-                 use_condition=False,
-                 num_class=None,
-                 pos_embedding='sinusoidal',
-                 init_cfg=None):
-        super().__init__(init_cfg=init_cfg)
-        if input_dim != latent_dim:
-            self.linear = nn.Linear(input_dim, latent_dim)
-        else:
-            self.linear = nn.Identity()
-        self.njoints = njoints
-        self.nfeats = nfeats
-        if input_feats is None:
-            assert self.njoints is not None and self.nfeats is not None
-            self.input_feats = njoints * nfeats
-        else:
-            self.input_feats = input_feats
-        self.max_seq_len = max_seq_len
-        self.input_dim = input_dim
-        self.latent_dim = latent_dim
-        self.condition_dim = condition_dim
-        self.use_condition = use_condition
-        self.num_class = num_class
-        if self.use_condition:
-            if num_class is None:
-                self.condition_bias = build_MLP(condition_dim, latent_dim)
-            else:
-                self.condition_bias = nn.Parameter(torch.randn(num_class, latent_dim))
-        if pos_embedding == 'sinusoidal':
-            self.pos_encoder = SinusoidalPositionalEncoding(latent_dim, dropout)
-        else:
-            self.pos_encoder = LearnedPositionalEncoding(latent_dim, dropout, max_len=max_seq_len)
-        seqTransDecoderLayer = nn.TransformerDecoderLayer(
-            d_model=self.latent_dim,
-            nhead=num_heads,
-            dim_feedforward=ff_size,
-            dropout=dropout,
-            activation=activation)
-        self.seqTransDecoder = nn.TransformerDecoder(
-            seqTransDecoderLayer,
-            num_layers=num_layers)
-
-        self.final = nn.Linear(self.latent_dim, self.input_feats)
-
-    def forward(self, input, motion_mask=None, condition=None):
-        B = input.shape[0]
-        T = self.max_seq_len
-        input = self.linear(input)
-        if self.use_condition:
-            if self.num_class is None:
-                condition = self.condition_bias(condition)
-            else:
-                condition = self.condition_bias[condition.long()].squeeze(1)
-            input = input + condition
-        query = self.pos_encoder.pe[:T, :].view(T, 1, -1).repeat(1, B, 1)
-        input = input.view(1, B, -1)
-        feature = self.seqTransDecoder(tgt=query, memory=input, tgt_key_padding_mask=(1 - motion_mask).bool())
-        pose = self.final(feature).permute(1, 0, 2).contiguous()
-        return pose
diff --git a/spaces/mohsayed/arabic_text_detection/app.py b/spaces/mohsayed/arabic_text_detection/app.py
deleted file mode 100644
index 8740249a57ecbd8b4924a5de9ab49c8393f35103..0000000000000000000000000000000000000000
--- a/spaces/mohsayed/arabic_text_detection/app.py
+++ /dev/null
@@ -1,221 +0,0 @@
-import json
-import requests
-import streamlit as st
-import pandas as pd
-import numpy as np
-from urllib.request import urlretrieve ,urlopen
-import os
-import torch
-from distutils.dir_util import copy_tree
-import tempfile
-import zipfile
-import subprocess
-import mmcv
-from mmcv import Config
-import sys
-from shapely.geometry import Polygon 
-
-
-import shutil
-import ssl
-
-import urllib.request
-from pathlib import Path
-
-import cv2
-from PIL import Image
-##########
-@st.cache(allow_output_mutation=True)
-def loading_resources():
-  dl_url = os.environ['dl_url']
-  if 'utils2.py' not in os.listdir('./'):
-    urlretrieve(dl_url, 'appdata.zip')
-    with zipfile.ZipFile("appdata.zip","r") as zip_ref:
-      zip_ref.extractall("./")
-loading_resources()
-
-import utilss
-from utils2 import *
-if 'model_inference' not in sys.modules:
-  from mmocr.apis import init_detector ,model_inference
-else:
-  model_inference = sys.modules['model_inference']
-  init_detector = sys.modules['init_detector']
-
-########## utils
-def draw_conts(im,conts,fcolor,stroke):
-  opacity = .3
-  im =im.copy()
-  # fcolor =fcolor if fcolor else get_random_color()
-  frontmm = np.full_like(im,fcolor,np.uint8)
-  mask = np.zeros_like(im)
-  for cont in conts:
-    cv2.drawContours(mask, [cont], -1, color=[int(opacity*255)]*3, thickness=cv2.FILLED)
-  mask = cv2.cvtColor(mask, cv2.COLOR_BGR2GRAY)
-  rgba = np.dstack((frontmm, mask))
-  im = utilss.overlay_image_alpha(im,rgba)
-  # drawline
-  cv2.drawContours(im, conts, -1, color=fcolor, thickness=stroke)
-  return im
-def image_resize(image, width = None, height = None, inter = cv2.INTER_AREA):
-    dim = None
-    (h, w) = image.shape[:2]
-    if width is None and height is None:
-        return image
-
-    if width is None:
-        r = height / float(h)
-        dim = (int(w * r), height)
-    else:
-        r = width / float(w)
-        dim = (width, int(h * r))
-    resized = cv2.resize(image, dim, interpolation = inter)
-    return resized
-def download_file(url, local_filename):
-    with requests.get(url, stream=True) as r:
-        with open(local_filename, 'wb') as f:
-            shutil.copyfileobj(r.raw, f)
-
-    return local_filename
-def load_and_preprocess_img(img_path, bbox=None):
-  img = Image.open(img_path).convert('RGB')
-  img = np.array(img).astype(np.uint8)
-  return img
-
-
-# @st.cache()
-def predictim(im , model):
-  if 'model_inference' not in sys.modules:
-    # if not model_inference:
-    from mmocr.apis import model_inference
-  result = model_inference(model,im )
-  # result[]
-  return result
-  # return result
-# minfer=None
-# minit=None
-@st.cache(allow_output_mutation=True)
-def loading_model():
-  # global minfer
-  # global minit
-  
-  from mmdet.apis import set_random_seed
-  set_random_seed(0, deterministic=False)
-  cfg = Config.fromfile('./cfgsn.py')
-  # checkpoint = "./200s.pth"
-  checkpoint = "./100s.pth"
-  model1 = init_detector(cfg, checkpoint, device="cpu")
-  # if model1.cfg.data.test['type'] == 'ConcatDataset':
-  #   model1.cfg.data.test.pipeline = model1.cfg.data.test['datasets'][0].pipeline
-  return model1
-model = loading_model()
-
-
-
-def main():
-  st.sidebar.info('Images are deleted instantly')
-  form0 =st.sidebar.form("my_form0")
-
-  f = form0.file_uploader("Upload an Image", type=['png', 'jpg', 'jpeg', 'tiff', 'gif'])
-  btnpredicrupload = form0.form_submit_button("PREDICT")
-
-
-  # st.sidebar.write(" ------ ")
-  form =st.sidebar.form("my_form")
-  photos = ['1.jpg','2.jpg','3.jpg','4.jpg','5.jpg','6.jpg',]
-  option = form.selectbox('Or choose a sample image', photos)
-  submitted = form.form_submit_button("PREDICT")
-
-  st.sidebar.write(" ------ ")
-  st.sidebar.info('Options')
-  extra_postprocess = st.sidebar.checkbox('perform extra postprocessing',value=True)
-  fcolor = st.sidebar.selectbox('boundary color', ['red','green','blue'],index =0)
-  fstroke = st.sidebar.selectbox('boundary thickness', ['1','2','3'] ,index=0 )
-  # do_thresh_box = st.sidebar.checkbox('adaptive threshold')
-
-  if btnpredicrupload and f is not None:
-    tfile = tempfile.NamedTemporaryFile(delete=True)
-    tfile.write(f.read())
-    imgpath=tfile.name
-    run_app(imgpath ,fcolor,extra_post=extra_postprocess,fstroke=fstroke)
-  if submitted:
-    st.empty()
-    directory ='./imgs/'
-    pic = os.path.join(directory, option)
-    imgpath=directory+option
-    run_app(imgpath ,fcolor,extra_post=extra_postprocess,fstroke=fstroke)
-  # inp = st.text_input('t2','')
-  # if st.button('run'):
-  #   subprocess.run(inp.split(' '))
-
-
-# def run_app(imgpath,do_thresh,fcolor):
-def run_app(imgpath,fcolor,**kwargs):
-  d0 =dict(red=[255,0,0] ,green=[0,255,0] ,blue=[0,0,255]  )
-  fcolor = d0[fcolor]
-  # st.sidebar.write(imgpath)
-  # r = np.random.randint(1e3,1e7)
-  tfile = tempfile.NamedTemporaryFile(delete=True,suffix='.jpg')
-  dst = tfile.name
-  # tfile = open()
-  img = load_and_preprocess_img(imgpath)
-  # img = utilss.resize_with_pad(img,800,800)
-  # if do_thresh:
-  #   gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
-  #   threshim = cv2.adaptiveThreshold(gray, 255, cv2.ADAPTIVE_THRESH_GAUSSIAN_C,cv2.THRESH_BINARY, 51, 20)
-  #   img= cv2.cvtColor(threshim, cv2.COLOR_GRAY2RGB)
-  
-  cv2.imwrite(dst,cv2.cvtColor(img, cv2.COLOR_BGR2RGB))
-  # imgo = image_resize(img , width = 640)
-  st.write('input:')
-  st.image(img, caption = "Selected Input" , width =640)
-
-  # if st.button('predict2'):
-  
-  # try:
-  # except: print('errr--------------')
-  ''
-  ##################
-  preds,img_metas,downsample_ratio =  model_inference(model,dst )
-  ff= fixer(img,preds,img_metas,downsample_ratio)
-  polys= ff.polysfin3
-  if kwargs['extra_post']:
-    try:
-      polys =find_polys4(ff) 
-    except:
-      print('error polys4')
-      polys= ff.polysfin3
-  
-
-  # with open('./0.json','r') as f:
-  #   res = json.load(f)
-  ################
-  mm = draw_conts(img,[poly2cont(p) for p in polys],fcolor,stroke=int(kwargs['fstroke']))
-  ## mm=image_resize(mm, width = 640)
-  #######
-  # mm=preds[1]*preds[0]
-  # mm=cv2.cvtColor(mm, cv2.COLOR_GRAY2RGB)
-  st.image(mm,caption='output image' , width = 640)
-  # del polys
-  del ff
-  del mm 
-  del preds
-  del polys
-  del img
-  del img_metas
-  # os.remove(dst)
-  # x = predictim(img,model)
-  # st.write(x)
-
-main()
-
-
-
-
-
-
-
-
-
-
-  
\ No newline at end of file
diff --git a/spaces/mrneuralnet/P-PD/local_detector.py b/spaces/mrneuralnet/P-PD/local_detector.py
deleted file mode 100644
index 9409dffffd079719397336f948ee384cdbc359bb..0000000000000000000000000000000000000000
--- a/spaces/mrneuralnet/P-PD/local_detector.py
+++ /dev/null
@@ -1,88 +0,0 @@
-import argparse
-import os
-import sys
-import numpy as np
-import torch
-import torchvision.transforms as transforms
-from PIL import Image
-
-from networks.drn_seg import DRNSeg
-from utils.tools import *
-from utils.visualize import *
-
-
-if __name__ == '__main__':
-    parser = argparse.ArgumentParser()
-    parser.add_argument(
-        "--input_path", required=True, help="the model input")
-    parser.add_argument(
-        "--dest_folder", required=True, help="folder to store the results")
-    parser.add_argument(
-        "--model_path", required=True, help="path to the drn model")
-    parser.add_argument(
-        "--gpu_id", default='0', help="the id of the gpu to run model on")
-    parser.add_argument(
-        "--no_crop",
-        action="store_true",
-        help="do not use a face detector, instead run on the full input image")
-    args = parser.parse_args()
-
-    img_path = args.input_path
-    dest_folder = args.dest_folder
-    model_path = args.model_path
-    gpu_id = args.gpu_id
-
-    # Loading the model
-    if torch.cuda.is_available():
-        device = 'cuda:{}'.format(gpu_id)
-    else:
-        device = 'cpu'
-
-    model = DRNSeg(2)
-    state_dict = torch.load(model_path, map_location=device)
-    model.load_state_dict(state_dict['model'])
-    model.to(device)
-    model.eval()
-
-    # Data preprocessing
-    tf = transforms.Compose([
-        transforms.ToTensor(),
-        transforms.Normalize(
-            mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225])
-    ])
-
-    im_w, im_h = Image.open(img_path).size
-    if args.no_crop:
-        face = Image.open(img_path).convert('RGB')
-    else:
-        faces = face_detection(img_path, verbose=False)
-        if len(faces) == 0:
-            print("no face detected by dlib, exiting")
-            sys.exit()
-        face, box = faces[0]
-    face = resize_shorter_side(face, 400)[0]
-    face_tens = tf(face).to(device)
-
-    # Warping field prediction
-    with torch.no_grad():
-        flow = model(face_tens.unsqueeze(0))[0].cpu().numpy()
-        flow = np.transpose(flow, (1, 2, 0))
-        h, w, _ = flow.shape
-
-    # Undoing the warps
-    modified = face.resize((w, h), Image.BICUBIC)
-    modified_np = np.asarray(modified)
-    reverse_np = warp(modified_np, flow)
-    reverse = Image.fromarray(reverse_np)
-
-    # Saving the results
-    modified.save(
-        os.path.join(dest_folder, 'cropped_input.jpg'),
-        quality=90)
-    reverse.save(
-        os.path.join(dest_folder, 'warped.jpg'),
-        quality=90)
-    flow_magn = np.sqrt(flow[:, :, 0]**2 + flow[:, :, 1]**2)
-    save_heatmap_cv(
-        modified_np, flow_magn,
-        os.path.join(dest_folder, 'heatmap.jpg'))
diff --git a/spaces/msarmi9/multi30k/models.py b/spaces/msarmi9/multi30k/models.py
deleted file mode 100644
index 0392f7ea9d8c3b0b7d216afbc64ef00178557343..0000000000000000000000000000000000000000
--- a/spaces/msarmi9/multi30k/models.py
+++ /dev/null
@@ -1,162 +0,0 @@
-from typing import *
-
-import torch
-import torch.nn as nn
-
-from attention import Attention
-from attention import ConcatScore
-
-Tensor = torch.Tensor
-
-
-class Encoder(nn.Module):
-    """Single layer recurrent bidirectional encoder."""""
-
-    def __init__(self, vocab_size: int, hidden_dim: int, pad_idx: int):
-        super().__init__()
-        self.embedding = nn.Sequential(
-            OrderedDict(
-                embedding=nn.Embedding(vocab_size, hidden_dim, padding_idx=pad_idx),
-                dropout=nn.Dropout(p=0.33),
-            )
-        )
-        self.gru = nn.GRU(hidden_dim, hidden_dim, batch_first=True, bidirectional=True)
-        self.fc = nn.Linear(2*hidden_dim, hidden_dim)
-        self.initialize_parameters()
-
-    def forward(self, input: Tensor) -> Tuple[Tensor, Tensor]:
-        """Encode a sequence of tokens as a sequence of hidden states."""""
-        B, T = input.shape
-        embedded = self.embedding(input)                     # (B, T, D)
-        output, hidden = self.gru(embedded)                  # (B, T, 2*D), (2, B, D)
-        hidden = torch.cat((hidden[0], hidden[1]), dim=-1)   # (B, 2*D)
-        hidden = torch.tanh(self.fc(hidden))                 # (B, D)
-        return output, hidden.unsqueeze(0)                   # (B, T, 2*D), (1, B, D)
-
-    @torch.no_grad()
-    def initialize_parameters(self):
-        """Initialize linear weights uniformly, recurrent weights orthogonally, and bias to zero."""""
-        for name, parameters in self.named_parameters():
-            if "embedding" in name:
-                nn.init.xavier_uniform_(parameters)
-            elif "weight_ih" in name:
-                w_ir, w_iz, w_in = torch.chunk(parameters, chunks=3, dim=0)
-                nn.init.xavier_uniform_(w_ir)
-                nn.init.xavier_uniform_(w_iz)
-                nn.init.xavier_uniform_(w_in)
-            elif "weight_hh" in name:
-                w_hr, w_hz, w_hn = torch.chunk(parameters, chunks=3, dim=0)
-                nn.init.orthogonal_(w_hr)
-                nn.init.orthogonal_(w_hz)
-                nn.init.orthogonal_(w_hn)
-            elif "weight" in name:
-                nn.init.xavier_uniform_(parameters)
-            elif "bias" in name:
-                nn.init.zeros_(parameters)
-
-
-class Decoder(nn.Module):
-    """Single layer recurrent decoder."""""
-
-    def __init__(self, vocab_size: int, hidden_dim: int, pad_idx: int, temperature: float = 1.0):
-        super().__init__()
-        self.embedding = nn.Sequential(
-            OrderedDict(
-                embedding=nn.Embedding(vocab_size, hidden_dim, padding_idx=pad_idx),
-                dropout=nn.Dropout(p=0.33),
-            )
-        )
-        self.attention = Attention(ConcatScore(hidden_dim), nn.Dropout(p=0.1))
-        self.gru = nn.GRU(3*hidden_dim, hidden_dim, batch_first=True)
-        self.fc = nn.Sequential(
-            OrderedDict(
-                fc1=nn.Linear(4*hidden_dim, hidden_dim),
-                layer_norm=nn.LayerNorm(hidden_dim),
-                gelu=nn.GELU(),
-                fc2=nn.Linear(hidden_dim, vocab_size, bias=False),
-            )
-        )
-        self.fc.fc2.weight = self.embedding.embedding.weight
-        self.temperature = temperature
-        self.initialize_parameters()
-
-    def forward(self, input: Tensor, hidden: Tensor, encoder_output: Tensor, source_mask: Tensor = None) -> Tuple[Tensor, Tensor, Tensor]:
-        """Predict the next token given an input token. Returns unnormalized predictions over the vocabulary."""""
-        B, = input.shape                                                                           # L=1
-        embedded = self.embedding(input.view(B, 1))                                                # (B, 1, D)
-        context, weights = self.attention(hidden.view(B, 1, -1), encoder_output, source_mask)      # (B, 1, 2*D), (B, 1, T)
-        output, hidden = self.gru(torch.cat((embedded, context), dim=-1), hidden)                  # (B, 1, D), (1, B, D)
-        predictions = self.fc(torch.cat((embedded, context, output), dim=-1)) / self.temperature   # (B, 1, V)
-        return predictions.view(B, -1), hidden, weights.view(B, -1)                                # (B, V), (1, B, D), (B, T)
-
-
-    @torch.no_grad()
-    def initialize_parameters(self):
-        """Initialize linear weights uniformly, recurrent weights orthogonally, and bias to zero."""""
-        for name, parameters in self.named_parameters():
-            if "norm" in name:
-                continue
-            elif "embedding" in name:
-                nn.init.xavier_uniform_(parameters)
-            elif "weight_ih" in name:
-                w_ir, w_iz, w_in = torch.chunk(parameters, chunks=3, dim=0)
-                nn.init.xavier_uniform_(w_ir)
-                nn.init.xavier_uniform_(w_iz)
-                nn.init.xavier_uniform_(w_in)
-            elif "weight_hh" in name:
-                w_hr, w_hz, w_hn = torch.chunk(parameters, chunks=3, dim=0)
-                nn.init.orthogonal_(w_hr)
-                nn.init.orthogonal_(w_hz)
-                nn.init.orthogonal_(w_hn)
-            elif "weight" in name:
-                nn.init.xavier_uniform_(parameters)
-            elif "bias" in name:
-                nn.init.zeros_(parameters)
-
-
-class Seq2Seq(nn.Module):
-    """Seq2seq with attention."""""
-
-    def __init__(self, vocab_size: int, hidden_dim: int, bos_idx: int, eos_idx: int, pad_idx: int, teacher_forcing: float = 0.5, temperature: float = 1.0):
-        super().__init__()
-        self.encoder = Encoder(vocab_size, hidden_dim, pad_idx)
-        self.decoder = Decoder(vocab_size, hidden_dim, pad_idx, temperature=temperature)
-        self.bos_idx = bos_idx
-        self.eos_idx = eos_idx
-        self.pad_idx = pad_idx
-        self.teacher_forcing = teacher_forcing
-
-    def forward(self, source: Tensor, target: Tensor) -> Tensor:
-        """Forward pass at training time. Returns unnormalized predictions over the vocabulary."""""
-        (B, T), (B, L) = source.shape, target.shape
-        encoder_output, hidden = self.encoder(source)                          # (B, T, D), (1, B, D)
-        decoder_input = torch.full((B,), self.bos_idx, device=source.device)   # (B,)
-        source_mask = source == self.pad_idx                                   # (B, 1, T)
-
-        output = []
-        for i in range(L):
-            predictions, hidden, _ = self.decoder(decoder_input, hidden, encoder_output, source_mask)   # (B, V), (1, B, D)
-            output.append(predictions)
-            if self.training and random.random() < self.teacher_forcing:
-                decoder_input = target[:,i]                                    # (B,)
-            else:
-                decoder_input = predictions.argmax(dim=1)                      # (B,)
-        return torch.stack(output, dim=1)                                      # (B, L, V)
-
-    @torch.inference_mode()
-    def decode(self, source: Tensor, max_decode_length: int) -> Tuple[Tensor, Tensor]:
-        """Decode a single sequence at inference time.  Returns output sequence and attention weights."""""
-        B, (T,) = 1, source.shape
-        encoder_output, hidden = self.encoder(source.view(B, T))               # (B, T, D), (B, 1, D)
-        decoder_input = torch.full((B,), self.bos_idx, device=source.device)   # (B,)
-
-        output, attention = [], []
-        for i in range(max_decode_length):
-            predictions, hidden, weights = self.decoder(decoder_input, hidden, encoder_output)   # (B, V), (1, B, D), (B, T)
-            output.append(predictions.argmax(dim=-1))                          # (B,)
-            attention.append(weights)                                          # (B, T)
-            if output[i] == self.eos_idx:
-                break
-            else:
-                decoder_input = output[i]                                      # (B,)
-        return torch.cat(output, dim=0), torch.cat(attention, dim=0)           # (L,), (L, T)
diff --git a/spaces/mshukor/UnIVAL/fairseq/examples/m2m_100/install_dependecies.sh b/spaces/mshukor/UnIVAL/fairseq/examples/m2m_100/install_dependecies.sh
deleted file mode 100644
index 82a1054745264a56fbec4a8eb593884f8a42bd08..0000000000000000000000000000000000000000
--- a/spaces/mshukor/UnIVAL/fairseq/examples/m2m_100/install_dependecies.sh
+++ /dev/null
@@ -1,78 +0,0 @@
-#!/usr/bin/env bash
-# Copyright (c) Facebook, Inc. and its affiliates.
-#
-# This source code is licensed under the MIT license found in the
-# LICENSE file in the root directory of this source tree.
-
-
-CWD=`pwd`
-INSTALL_PATH=$CWD/tokenizers/thirdparty
-
-MOSES=$INSTALL_PATH/mosesdecoder
-if [ ! -d $MOSES ]; then
-    echo 'Cloning Moses github repository (for tokenization scripts)...'
-    git clone https://github.com/moses-smt/mosesdecoder.git $MOSES
-    cd $MOSES
-    # To deal with differences in handling ' vs "
-    git checkout 03578921cc1a03402
-    cd -
-fi
-
-WMT16_SCRIPTS=$INSTALL_PATH/wmt16-scripts
-if [ ! -d $WMT16_SCRIPTS ]; then
-    echo 'Cloning Romanian tokenization scripts'
-    git clone https://github.com/rsennrich/wmt16-scripts.git $WMT16_SCRIPTS
-fi
-
-KYTEA=$INSTALL_PATH/kytea
-if [ ! -f $KYTEA/bin/kytea ]; then
-    git clone https://github.com/neubig/kytea.git $KYTEA
-    cd $KYTEA
-    autoreconf -i
-    ./configure --prefix=`pwd`
-    make
-    make install
-    cd ..
-fi
-
-export MECAB=$INSTALL_PATH/mecab-0.996-ko-0.9.2
-if [ ! -f $MECAB/bin/mecab ]; then
-    cd $INSTALL_PATH
-    curl -LO https://bitbucket.org/eunjeon/mecab-ko/downloads/mecab-0.996-ko-0.9.2.tar.gz
-    tar zxfv mecab-0.996-ko-0.9.2.tar.gz
-    cd mecab-0.996-ko-0.9.2/
-    ./configure --prefix=`pwd`
-    make
-    make install
-
-    cd ..
-    curl -LO https://bitbucket.org/eunjeon/mecab-ko-dic/downloads/mecab-ko-dic-2.1.1-20180720.tar.gz
-    tar zxfv mecab-ko-dic-2.1.1-20180720.tar.gz
-    cd mecab-ko-dic-2.1.1-20180720/
-    ./autogen.sh
-    ./configure --prefix=`pwd` --with-dicdir=$MECAB/lib/mecab/dic/mecab-ko-dic --with-mecab-config=$MECAB/bin/mecab-config
-    make
-    sh -c 'echo "dicdir=$MECAB/lib/mecab/dic/mecab-ko-dic" > $MECAB/etc/mecabrc'
-    make install
-    cd $CWD
-fi
-
-INDIC_RESOURCES_PATH=$INSTALL_PATH/indic_nlp_resources
-if [ ! -d $INDIC_RESOURCES_PATH ]; then
-    echo 'Cloning indic_nlp_resources'
-    git clone https://github.com/anoopkunchukuttan/indic_nlp_resources.git $INDIC_RESOURCES_PATH
-fi
-
-
-if [ ! -f $INSTALL_PATH/seg_my.py ]; then
-    cd $INSTALL_PATH
-    wget http://lotus.kuee.kyoto-u.ac.jp/WAT/my-en-data/wat2020.my-en.zip
-    unzip wat2020.my-en.zip
-    # switch to python3
-    cat wat2020.my-en/myseg.py  |sed 's/^sys.std/###sys.std/g' | sed 's/### sys/sys/g' | sed 's/unichr/chr/g' > seg_my.py
-    cd $CWD
-fi
-
-
-pip install pythainlp sacrebleu indic-nlp-library
-
diff --git a/spaces/mshukor/UnIVAL/fairseq/fairseq/tasks/multilingual_masked_lm.py b/spaces/mshukor/UnIVAL/fairseq/fairseq/tasks/multilingual_masked_lm.py
deleted file mode 100644
index 9e6ce4b8a2f77ed889a6e1451321a8e3ac21dc67..0000000000000000000000000000000000000000
--- a/spaces/mshukor/UnIVAL/fairseq/fairseq/tasks/multilingual_masked_lm.py
+++ /dev/null
@@ -1,338 +0,0 @@
-# Copyright (c) Facebook, Inc. and its affiliates.
-#
-# This source code is licensed under the MIT license found in the
-# LICENSE file in the root directory of this source tree.
-
-import logging
-import os
-
-import numpy as np
-import torch
-from fairseq import utils
-from fairseq.data import (
-    ConcatDataset,
-    Dictionary,
-    IdDataset,
-    MaskTokensDataset,
-    NestedDictionaryDataset,
-    NumelDataset,
-    NumSamplesDataset,
-    PadDataset,
-    PrependTokenDataset,
-    RawLabelDataset,
-    ResamplingDataset,
-    SortDataset,
-    TokenBlockDataset,
-    data_utils,
-    encoders,
-)
-from fairseq.tasks import LegacyFairseqTask, register_task
-
-
-logger = logging.getLogger(__name__)
-
-
-@register_task("multilingual_masked_lm")
-class MultiLingualMaskedLMTask(LegacyFairseqTask):
-    """Task for training masked language models (e.g., BERT, RoBERTa)."""
-
-    @staticmethod
-    def add_args(parser):
-        """Add task-specific arguments to the parser."""
-        parser.add_argument(
-            "data",
-            help="colon separated path to data directories list, \
-                            will be iterated upon during epochs in round-robin manner",
-        )
-        parser.add_argument(
-            "--sample-break-mode",
-            default="complete",
-            choices=["none", "complete", "complete_doc", "eos"],
-            help='If omitted or "none", fills each sample with tokens-per-sample '
-            'tokens. If set to "complete", splits samples only at the end '
-            "of sentence, but may include multiple sentences per sample. "
-            '"complete_doc" is similar but respects doc boundaries. '
-            'If set to "eos", includes only one sentence per sample.',
-        )
-        parser.add_argument(
-            "--tokens-per-sample",
-            default=512,
-            type=int,
-            help="max number of total tokens over all segments "
-            "per sample for BERT dataset",
-        )
-        parser.add_argument(
-            "--mask-prob",
-            default=0.15,
-            type=float,
-            help="probability of replacing a token with mask",
-        )
-        parser.add_argument(
-            "--leave-unmasked-prob",
-            default=0.1,
-            type=float,
-            help="probability that a masked token is unmasked",
-        )
-        parser.add_argument(
-            "--random-token-prob",
-            default=0.1,
-            type=float,
-            help="probability of replacing a token with a random token",
-        )
-        parser.add_argument(
-            "--freq-weighted-replacement",
-            action="store_true",
-            help="sample random replacement words based on word frequencies",
-        )
-        parser.add_argument(
-            "--mask-whole-words",
-            default=False,
-            action="store_true",
-            help="mask whole words; you may also want to set --bpe",
-        )
-        parser.add_argument(
-            "--multilang-sampling-alpha",
-            type=float,
-            default=1.0,
-            help="smoothing alpha for sample rations across multiple datasets",
-        )
-
-    def __init__(self, args, dictionary):
-        super().__init__(args)
-        self.dictionary = dictionary
-        self.seed = args.seed
-
-        # add mask token
-        self.mask_idx = dictionary.add_symbol("<mask>")
-
-    @classmethod
-    def setup_task(cls, args, **kwargs):
-        paths = utils.split_paths(args.data)
-        assert len(paths) > 0
-        dictionary = Dictionary.load(os.path.join(paths[0], "dict.txt"))
-        logger.info("dictionary: {} types".format(len(dictionary)))
-        return cls(args, dictionary)
-
-    def _get_whole_word_mask(self):
-        # create masked input and targets
-        if self.args.mask_whole_words:
-            bpe = encoders.build_bpe(self.args)
-            if bpe is not None:
-
-                def is_beginning_of_word(i):
-                    if i < self.source_dictionary.nspecial:
-                        # special elements are always considered beginnings
-                        return True
-                    tok = self.source_dictionary[i]
-                    if tok.startswith("madeupword"):
-                        return True
-                    try:
-                        return bpe.is_beginning_of_word(tok)
-                    except ValueError:
-                        return True
-
-                mask_whole_words = torch.ByteTensor(
-                    list(map(is_beginning_of_word, range(len(self.source_dictionary))))
-                )
-        else:
-            mask_whole_words = None
-        return mask_whole_words
-
-    def _get_sample_prob(self, dataset_lens):
-        """
-        Get smoothed sampling porbability by languages. This helps low resource
-        languages by upsampling them.
-        """
-        prob = dataset_lens / dataset_lens.sum()
-        smoothed_prob = prob ** self.args.multilang_sampling_alpha
-        smoothed_prob = smoothed_prob / smoothed_prob.sum()
-        return smoothed_prob
-
-    def load_dataset(self, split, epoch=1, combine=False, **kwargs):
-        """Load a given dataset split.
-
-        Args:
-            split (str): name of the split (e.g., train, valid, test)
-        """
-        paths = utils.split_paths(self.args.data)
-        assert len(paths) > 0
-        data_path = paths[(epoch - 1) % len(paths)]
-
-        languages = sorted(
-            name
-            for name in os.listdir(data_path)
-            if os.path.isdir(os.path.join(data_path, name))
-        )
-
-        logger.info("Training on {0} languages: {1}".format(len(languages), languages))
-        logger.info(
-            "Language to id mapping: ", {lang: id for id, lang in enumerate(languages)}
-        )
-
-        mask_whole_words = self._get_whole_word_mask()
-        lang_datasets = []
-        for lang_id, language in enumerate(languages):
-            split_path = os.path.join(data_path, language, split)
-
-            dataset = data_utils.load_indexed_dataset(
-                split_path,
-                self.source_dictionary,
-                self.args.dataset_impl,
-                combine=combine,
-            )
-            if dataset is None:
-                raise FileNotFoundError(
-                    "Dataset not found: {} ({})".format(split, split_path)
-                )
-
-            # create continuous blocks of tokens
-            dataset = TokenBlockDataset(
-                dataset,
-                dataset.sizes,
-                self.args.tokens_per_sample - 1,  # one less for <s>
-                pad=self.source_dictionary.pad(),
-                eos=self.source_dictionary.eos(),
-                break_mode=self.args.sample_break_mode,
-            )
-            logger.info("loaded {} blocks from: {}".format(len(dataset), split_path))
-
-            # prepend beginning-of-sentence token (<s>, equiv. to [CLS] in BERT)
-            dataset = PrependTokenDataset(dataset, self.source_dictionary.bos())
-
-            src_dataset, tgt_dataset = MaskTokensDataset.apply_mask(
-                dataset,
-                self.source_dictionary,
-                pad_idx=self.source_dictionary.pad(),
-                mask_idx=self.mask_idx,
-                seed=self.args.seed,
-                mask_prob=self.args.mask_prob,
-                leave_unmasked_prob=self.args.leave_unmasked_prob,
-                random_token_prob=self.args.random_token_prob,
-                freq_weighted_replacement=self.args.freq_weighted_replacement,
-                mask_whole_words=mask_whole_words,
-            )
-
-            lang_dataset = NestedDictionaryDataset(
-                {
-                    "net_input": {
-                        "src_tokens": PadDataset(
-                            src_dataset,
-                            pad_idx=self.source_dictionary.pad(),
-                            left_pad=False,
-                        ),
-                        "src_lengths": NumelDataset(src_dataset, reduce=False),
-                    },
-                    "target": PadDataset(
-                        tgt_dataset,
-                        pad_idx=self.source_dictionary.pad(),
-                        left_pad=False,
-                    ),
-                    "nsentences": NumSamplesDataset(),
-                    "ntokens": NumelDataset(src_dataset, reduce=True),
-                    "lang_id": RawLabelDataset([lang_id] * src_dataset.sizes.shape[0]),
-                },
-                sizes=[src_dataset.sizes],
-            )
-            lang_datasets.append(lang_dataset)
-
-        dataset_lengths = np.array(
-            [len(d) for d in lang_datasets],
-            dtype=float,
-        )
-        logger.info(
-            "loaded total {} blocks for all languages".format(
-                dataset_lengths.sum(),
-            )
-        )
-        if split == self.args.train_subset:
-            # For train subset, additionally up or down sample languages.
-            sample_probs = self._get_sample_prob(dataset_lengths)
-            logger.info(
-                "Sample probability by language: ",
-                {
-                    lang: "{0:.4f}".format(sample_probs[id])
-                    for id, lang in enumerate(languages)
-                },
-            )
-            size_ratio = (sample_probs * dataset_lengths.sum()) / dataset_lengths
-            logger.info(
-                "Up/Down Sampling ratio by language: ",
-                {
-                    lang: "{0:.2f}".format(size_ratio[id])
-                    for id, lang in enumerate(languages)
-                },
-            )
-
-            resampled_lang_datasets = [
-                ResamplingDataset(
-                    lang_datasets[i],
-                    size_ratio=size_ratio[i],
-                    seed=self.args.seed,
-                    epoch=epoch,
-                    replace=size_ratio[i] >= 1.0,
-                )
-                for i, d in enumerate(lang_datasets)
-            ]
-            dataset = ConcatDataset(resampled_lang_datasets)
-        else:
-            dataset = ConcatDataset(lang_datasets)
-            lang_splits = [split]
-            for lang_id, lang_dataset in enumerate(lang_datasets):
-                split_name = split + "_" + languages[lang_id]
-                lang_splits.append(split_name)
-                self.datasets[split_name] = lang_dataset
-
-            # [TODO]: This is hacky for now to print validation ppl for each
-            # language individually. Maybe need task API changes to allow it
-            # in more generic ways.
-            if split in self.args.valid_subset:
-                self.args.valid_subset = self.args.valid_subset.replace(
-                    split, ",".join(lang_splits)
-                )
-
-        with data_utils.numpy_seed(self.args.seed + epoch):
-            shuffle = np.random.permutation(len(dataset))
-
-        self.datasets[split] = SortDataset(
-            dataset,
-            sort_order=[
-                shuffle,
-                dataset.sizes,
-            ],
-        )
-
-    def build_dataset_for_inference(self, src_tokens, src_lengths, sort=True):
-        src_dataset = PadDataset(
-            TokenBlockDataset(
-                src_tokens,
-                src_lengths,
-                self.args.tokens_per_sample - 1,  # one less for <s>
-                pad=self.source_dictionary.pad(),
-                eos=self.source_dictionary.eos(),
-                break_mode="eos",
-            ),
-            pad_idx=self.source_dictionary.pad(),
-            left_pad=False,
-        )
-        src_dataset = PrependTokenDataset(src_dataset, self.source_dictionary.bos())
-        src_dataset = NestedDictionaryDataset(
-            {
-                "id": IdDataset(),
-                "net_input": {
-                    "src_tokens": src_dataset,
-                    "src_lengths": NumelDataset(src_dataset, reduce=False),
-                },
-            },
-            sizes=src_lengths,
-        )
-        if sort:
-            src_dataset = SortDataset(src_dataset, sort_order=[src_lengths])
-        return src_dataset
-
-    @property
-    def source_dictionary(self):
-        return self.dictionary
-
-    @property
-    def target_dictionary(self):
-        return self.dictionary
diff --git a/spaces/mshukor/UnIVAL/run_scripts/caption/scaling_best/audio/clotho/unival_audio_caption_clotho.sh b/spaces/mshukor/UnIVAL/run_scripts/caption/scaling_best/audio/clotho/unival_audio_caption_clotho.sh
deleted file mode 100644
index 8d810fc4b43346e0754653b336d1239bca8a494c..0000000000000000000000000000000000000000
--- a/spaces/mshukor/UnIVAL/run_scripts/caption/scaling_best/audio/clotho/unival_audio_caption_clotho.sh
+++ /dev/null
@@ -1,217 +0,0 @@
-
-
-# Number of GPUs per GPU worker
-export GPUS_PER_NODE=8
-# Number of GPU workers, for single-worker training, please set to 1
-export NUM_NODES=$SLURM_NNODES
-# The ip address of the rank-0 worker, for single-worker training, please set to localhost
-master_addr=$(scontrol show hostnames "$SLURM_JOB_NODELIST" | head -n 1)
-export MASTER_ADDR=$master_addr
-
-# The port for communication
-export MASTER_PORT=12350
-# The rank of this worker, should be in {0, ..., WORKER_CNT-1}, for single-worker training, please set to 0
-export RANK=$SLURM_NODEID
-
-echo "MASTER_ADDR: $MASTER_ADDR"
-echo "RANK :$RANK"
-echo "NUM_NODES :$NUM_NODES"
-echo "GPUS_PER_NODE :$GPUS_PER_NODE"
-
-export MIOPEN_USER_DB_PATH=/lus/home/NAT/gda2204/mshukor/.config/miopen_${MASTER_ADDR}_${SLURM_PROCID}/
-
-echo "MIOPEN_USER_DB_PATH :$MIOPEN_USER_DB_PATH"
-
-num_workers=0
-
-
-exp_name=unival_audio_caption_clotho
-
-
-ofa_dir=/lus/home/NAT/gda2204/mshukor/code/unival
-base_data_dir=/lus/scratch/NAT/gda2204/SHARED/data
-base_log_dir=/work/NAT/gda2204/mshukor/logs
-
-save_base_log_dir=/lus/scratch/NAT/gda2204/SHARED/logs
-save_dir=${save_base_log_dir}/ofa/checkpoints/caption/${exp_name}
-
-log_dir=${save_dir}
-
-mkdir -p $log_dir $save_dir
-
-bpe_dir=${ofa_dir}/utils/BPE
-user_dir=${ofa_dir}/ofa_module
-
-
-
-image_dir=${base_data_dir}
-
-
-data_dir=${base_data_dir}/ofa/audio_data/caption_data
-# data=${data_dir}/clotho_development.tsv,${data_dir}/clotho_evaluation.tsv
-
-data=${data_dir}/clotho_development_1.tsv,${data_dir}/clotho_development_2.tsv,${data_dir}/clotho_development_3.tsv,${data_dir}/clotho_development_4.tsv,${data_dir}/clotho_development_5.tsv,${data_dir}/clotho_development_6.tsv,${data_dir}/clotho_development_7.tsv,${data_dir}/clotho_development_8.tsv,${data_dir}/clotho_development_9.tsv,${data_dir}/clotho_development_10.tsv,${data_dir}/clotho_evaluation.tsv
-
-eval_cider_cached=${data_dir}/cider_cached_tokens/clotho-evaluation-words.p
-
-restore_file=${base_log_dir}/ofa/checkpoints/pretrain/unival_s2_hs/checkpoint1.pt
-
-
-
-selected_cols=0,4,2
-
-task=audio_caption
-arch=unival_base
-pretrained_model=  
-
-
-criterion=adjust_label_smoothed_encouraging_loss
-label_smoothing=0.1
-lr=5e-5
-max_epoch=25
-warmup_ratio=0.06
-batch_size=16
-update_freq=1
-resnet_drop_path_rate=0.0
-encoder_drop_path_rate=0.1
-decoder_drop_path_rate=0.1
-dropout=0.1
-attention_dropout=0.0
-max_src_length=80
-max_tgt_length=20
-num_bins=1000
-# patch_image_size=480
-drop_worst_ratio=0.2
-
-
-
-
-###
-image_encoder_name=timm_resnet #vit_base_patch16_224 144
-patch_image_size=384
-resnet_type=resnet101
-
-resnet_model_path=${base_log_dir}/pretrained_models/resnet101_a1h-36d3f2aa.pth
-
-# video
-video_encoder_name=all_resnext101 # 49 
-patch_frame_size=224
-video_model_path=${base_log_dir}/pretrained_models/3dcnn/resnext-101-kinetics.pth #${base_log_dir}/pretrained_models/TimeSformer_divST_8x32_224_K600.pyth
-num_frames=8
-
-# audio 
-audio_encoder_name=pann_cnn14
-audio_model_path=${base_log_dir}/pretrained_models/Cnn14_mAP_0.431.pth 
-mel_bins=64
-hop_size=200 # 155 tok
-
-
-
-save_interval=1
-validate_interval_updates=2000
-save_interval_updates=0
-
-validate_interval=1
-
-sample_patch_num='--sample-patch-num=784' # ''
-
-eval_args='--eval-args={"beam":5,"unnormalized":true,"temperature":1.0,"stop_on_max_len":true}'
-
-
-drop_worst_ratio=0.05 # modified from 0.2 for el
-log_end=0.75  # for el
-drop_best_ratio=0.05
-drop_best_after=6000
-drop_worst_after=6000
-
-echo "max_epoch "${max_epoch}
-for warmup_ratio in {0.06,}; do
-  echo "warmup_ratio "${warmup_ratio}
-  for drop_worst_after in {6000,}; do
-    echo "drop_worst_after "${drop_worst_after}
-
-    log_file=${log_dir}/${max_epoch}"_"${warmup_ratio}"_"${drop_worst_after}".log"
-    save_path=${save_dir}/${max_epoch}"_"${warmup_ratio}"_"${drop_worst_after}
-    mkdir -p $save_path
-
-    python3 -m torch.distributed.launch \
-        --nnodes=${NUM_NODES} \
-        --nproc_per_node=${GPUS_PER_NODE} \
-        --master_port=${MASTER_PORT} \
-        --node_rank=${RANK} \
-        --master_addr=${MASTER_ADDR} \
-        --use_env ${ofa_dir}/train.py \
-        $data \
-        --selected-cols=${selected_cols} \
-        --bpe-dir=${bpe_dir} \
-        --user-dir=${user_dir} \
-        --restore-file=${restore_file} \
-        --save-dir=${save_path} \
-        --task=${task} \
-        --arch=${arch} \
-        --criterion=${criterion} \
-        --label-smoothing=${label_smoothing} \
-        --batch-size=${batch_size} \
-        --update-freq=${update_freq} \
-        --encoder-normalize-before \
-        --decoder-normalize-before \
-        --share-decoder-input-output-embed \
-        --share-all-embeddings \
-        --layernorm-embedding \
-        --patch-layernorm-embedding \
-        --code-layernorm-embedding \
-        --resnet-drop-path-rate=${resnet_drop_path_rate} \
-        --encoder-drop-path-rate=${encoder_drop_path_rate} \
-        --decoder-drop-path-rate=${decoder_drop_path_rate} \
-        --dropout=${dropout} \
-        --attention-dropout=${attention_dropout} \
-        --weight-decay=0.01 --optimizer=adam --adam-betas="(0.9,0.999)" --adam-eps=1e-08 --clip-norm=1.0 \
-        --lr-scheduler=polynomial_decay --lr=${lr} \
-        --max-epoch=${max_epoch} --warmup-ratio=${warmup_ratio} \
-        --log-format=simple --log-interval=10 \
-        --fixed-validation-seed=7 \
-        --no-epoch-checkpoints --keep-best-checkpoints=1 \
-        --save-interval=${save_interval} --validate-interval=${validate_interval} \
-        --save-interval-updates=${save_interval_updates} --validate-interval-updates=${validate_interval_updates} \
-        --eval-cider \
-        --eval-cider-cached-tokens=${eval_cider_cached} \
-        --eval-args='{"beam":5,"max_len_b":16,"no_repeat_ngram_size":3}' \
-        --best-checkpoint-metric=cider --maximize-best-checkpoint-metric \
-        --max-src-length=${max_src_length} \
-        --max-tgt-length=${max_tgt_length} \
-        --find-unused-parameters \
-        --freeze-encoder-embedding \
-        --freeze-decoder-embedding \
-        --add-type-embedding \
-        --scale-attn \
-        --scale-fc \
-        --scale-heads \
-        --disable-entangle \
-        --num-bins=${num_bins} \
-        --patch-image-size=${patch_image_size} \
-        --drop-worst-ratio=${drop_worst_ratio} \
-        --drop-worst-after=${drop_worst_after} \
-        --fp16-scale-window=512 \
-        --fp16 \
-        --num-workers=0 \
-        --image-dir=${image_dir} \
-        --video-model-path=${video_model_path} \
-        --patch-frame-size=${patch_frame_size} \
-        ${sample_patch_num} \
-        ${eval_args} \
-        --num-frames=${num_frames} \
-        --resnet-type=${resnet_type} \
-        --resnet-model-path=${resnet_model_path} \
-        --audio-encoder-name=${audio_encoder_name} \
-        --audio-model-path=${audio_model_path} \
-        --mel-bins=${mel_bins} \
-        --hop-size=${hop_size} \
-        --reset-dataloader --reset-meters --reset-optimizer \
-        --image-encoder-name=${image_encoder_name} \
-        --video-encoder-name=${video_encoder_name} \
-        --save-on-cuda \
-        --log-end ${log_end} --drop-best-ratio ${drop_best_ratio} --drop-best-after ${drop_best_after} \
-        --strict 
-
-  done
-done
diff --git a/spaces/nakamura196/yolov5-kunshujo/ultralytics/yolov5/utils/flask_rest_api/README.md b/spaces/nakamura196/yolov5-kunshujo/ultralytics/yolov5/utils/flask_rest_api/README.md
deleted file mode 100644
index a726acbd92043458311dd949cc09c0195cd35400..0000000000000000000000000000000000000000
--- a/spaces/nakamura196/yolov5-kunshujo/ultralytics/yolov5/utils/flask_rest_api/README.md
+++ /dev/null
@@ -1,73 +0,0 @@
-# Flask REST API
-
-[REST](https://en.wikipedia.org/wiki/Representational_state_transfer) [API](https://en.wikipedia.org/wiki/API)s are
-commonly used to expose Machine Learning (ML)  models to other services. This folder contains an example REST API
-created using Flask to expose the YOLOv5s model from [PyTorch Hub](https://pytorch.org/hub/ultralytics_yolov5/).
-
-## Requirements
-
-[Flask](https://palletsprojects.com/p/flask/) is required. Install with:
-
-```shell
-$ pip install Flask
-```
-
-## Run
-
-After Flask installation run:
-
-```shell
-$ python3 restapi.py --port 5000
-```
-
-Then use [curl](https://curl.se/) to perform a request:
-
-```shell
-$ curl -X POST -F image=@zidane.jpg 'http://localhost:5000/v1/object-detection/yolov5s'
-```
-
-The model inference results are returned as a JSON response:
-
-```json
-[
-  {
-    "class": 0,
-    "confidence": 0.8900438547,
-    "height": 0.9318675399,
-    "name": "person",
-    "width": 0.3264600933,
-    "xcenter": 0.7438579798,
-    "ycenter": 0.5207948685
-  },
-  {
-    "class": 0,
-    "confidence": 0.8440024257,
-    "height": 0.7155083418,
-    "name": "person",
-    "width": 0.6546785235,
-    "xcenter": 0.427829951,
-    "ycenter": 0.6334488392
-  },
-  {
-    "class": 27,
-    "confidence": 0.3771208823,
-    "height": 0.3902671337,
-    "name": "tie",
-    "width": 0.0696444362,
-    "xcenter": 0.3675483763,
-    "ycenter": 0.7991207838
-  },
-  {
-    "class": 27,
-    "confidence": 0.3527112305,
-    "height": 0.1540903747,
-    "name": "tie",
-    "width": 0.0336618312,
-    "xcenter": 0.7814827561,
-    "ycenter": 0.5065554976
-  }
-]
-```
-
-An example python script to perform inference using [requests](https://docs.python-requests.org/en/master/) is given
-in `example_request.py`
diff --git a/spaces/netiMophi/DreamlikeArt-Diffusion-1.0/Atomic Mail Sender 8 Crack.md b/spaces/netiMophi/DreamlikeArt-Diffusion-1.0/Atomic Mail Sender 8 Crack.md
deleted file mode 100644
index 0999d3f00492b6b6f5f3d71e6e397d17ee1ee680..0000000000000000000000000000000000000000
--- a/spaces/netiMophi/DreamlikeArt-Diffusion-1.0/Atomic Mail Sender 8 Crack.md	
+++ /dev/null
@@ -1,28 +0,0 @@
-<br />
-<h1>How to Use Atomic Mail Sender 8 Crack to Boost Your Email Marketing Campaigns</h1>
-<p>Email marketing is one of the most effective ways to reach your target audience, promote your products or services, and generate leads or sales. However, email marketing can also be challenging, especially if you don't have the right tools to create, send, and track your campaigns.</p>
-<h2>atomic mail sender 8 crack</h2><br /><p><b><b>Download File</b> >>> <a href="https://urlcod.com/2uIc4N">https://urlcod.com/2uIc4N</a></b></p><br /><br />
-<p>That's why many email marketers look for a reliable and affordable email marketing software platform that can help them with their email marketing goals. One of the most popular options is Atomic Mail Sender, a powerful bulk email sender that allows you to create and send personalized emails to thousands of recipients in minutes.</p>
-<p>Atomic Mail Sender has many features that make it stand out among other email marketing software platforms, such as:</p>
-<ul>
-<li>A flexible SMTP server that lets you bypass your ISP's server and send messages directly to recipients' inboxes.</li>
-<li>A built-in email tracker that lets you monitor the performance of your campaigns, such as open rates, click rates, bounce rates, and unsubscribe rates.</li>
-<li>A user-friendly interface that lets you design your emails using templates or a drag and drop editor.</li>
-<li>A powerful email verifier that lets you check the validity of your email addresses and remove invalid or inactive ones.</li>
-<li>A spam checker that lets you test your emails for spam filters and avoid getting blacklisted.</li>
-</ul>
-<p>However, Atomic Mail Sender is not a free software. You need to purchase a license to use it for your email marketing campaigns. The price of Atomic Mail Sender depends on the number of licenses you need, ranging from $79.85 for one license to $299.85 for five licenses.</p>
-<p>But what if you don't have the budget to buy Atomic Mail Sender? Is there a way to use it for free?</p>
-<p>The answer is yes, but it comes with a risk. Some people claim that they have found a way to use Atomic Mail Sender 8 crack, which is a modified version of the software that bypasses the license verification process and lets you use it without paying anything.</p>
-<p>However, using Atomic Mail Sender 8 crack is not recommended for several reasons:</p>
-<p></p>
-<ul>
-<li>It is illegal. Using cracked software is a violation of the intellectual property rights of the software developers. You could face legal consequences if you are caught using Atomic Mail Sender 8 crack.</li>
-<li>It is unsafe. Cracked software often contains malware or viruses that can harm your computer or compromise your data. You could lose your files, expose your personal information, or damage your system if you download or install Atomic Mail Sender 8 crack.</li>
-<li>It is unreliable. Cracked software often has bugs or errors that can affect the functionality or performance of the software. You could experience crashes, freezes, or glitches when using Atomic Mail Sender 8 crack. You could also miss out on the updates or support that the official version of Atomic Mail Sender provides.</li>
-</ul>
-<p>Therefore, it is better to avoid using Atomic Mail Sender 8 crack and instead invest in the official version of Atomic Mail Sender. You will get more benefits and value from using a legitimate and trustworthy email marketing software platform than risking your reputation and security by using a cracked one.</p>
-<p>If you want to learn more about Atomic Mail Sender and how it can help you with your email marketing campaigns, you can visit their official website at <a href="https://www.atompark.com/downloads/bulk-email-sender/">https://www.atompark.com/downloads/bulk-email-sender/</a>. You can also download a free trial version of Atomic Mail Sender and test its features before buying a license.</p>
-<p>Email marketing doesn't have to be hard or expensive. With Atomic Mail Sender, you can create and send professional and personalized emails to your audience in minutes and boost your email marketing results.</p> cec2833e83<br />
-<br />
-<br />
\ No newline at end of file
diff --git a/spaces/netiMophi/DreamlikeArt-Diffusion-1.0/Download __FULL__ Software Transformasi Koordinat Bakosurtanal.md b/spaces/netiMophi/DreamlikeArt-Diffusion-1.0/Download __FULL__ Software Transformasi Koordinat Bakosurtanal.md
deleted file mode 100644
index 176bf53a1dc3fdbee901a8f83a194e58c7fb8b0a..0000000000000000000000000000000000000000
--- a/spaces/netiMophi/DreamlikeArt-Diffusion-1.0/Download __FULL__ Software Transformasi Koordinat Bakosurtanal.md	
+++ /dev/null
@@ -1,44 +0,0 @@
-
-<h1>How to Download and Use Software for Coordinate Transformation from BAKOSURTANAL</h1>
-<p>BAKOSURTANAL (now BIG - Geospatial Information Agency) is an Indonesian government agency that provides geospatial information and services. One of the software tools that they offer is a coordinate transformation software that can convert between different coordinate systems, such as Geographical Coordinate System (GCS), UTM, and TM3. This software can be useful for geospatial data processing and mapping purposes.</p>
-<h2>download software transformasi koordinat bakosurtanal</h2><br /><p><b><b>DOWNLOAD</b> - <a href="https://urlcod.com/2uIaWm">https://urlcod.com/2uIaWm</a></b></p><br /><br />
-<p>In this article, we will show you how to download and use this software for coordinate transformation. We will also provide some examples of how to convert coordinates from one system to another using this software.</p>
-<h2>How to Download the Software</h2>
-<p>The software is called Transkoord and it is available for free download from the BAKOSURTANAL website. You can access the download link here[^1^] [^3^]. The file size is about 2 MB and it is a compressed file in RAR format. You will need a program like WinRAR or 7-Zip to extract the file.</p>
-<p>After extracting the file, you will see a folder called Transkoord with several files inside. The main executable file is TransKoord.exe. You do not need to install the software, just run it as administrator by right-clicking on it and choosing Run as administrator.</p>
-<p></p>
-<h2>How to Use the Software</h2>
-<p>The software has three modes of operation: interactive, extractive, and projection. In interactive mode, you can convert coordinates one by one by entering the input values and choosing the output system. In extractive mode, you can convert coordinates in bulk by using a text file as input and output. In projection mode, you can convert coordinates in DXF format (AutoCAD) by using a separate window.</p>
-<p>We will explain each mode in more detail below.</p>
-<h3>Interactive Mode</h3>
-<p>In interactive mode, you can see a main window with several tabs and buttons. The tabs are for choosing the input and output coordinate systems, such as GCS, UTM, or TM3. The buttons are for performing the conversion or clearing the input/output fields.</p>
-<p>To use this mode, follow these steps:</p>
-<ol>
-<li>Select the input tab and enter the name of the point (optional) and the input coordinates. You can also choose the datum (such as WGS84) from the drop-down menu.</li>
-<li>Select the output tab and choose the output coordinate system.</li>
-<li>Click on the button that corresponds to the conversion direction (such as GCS >> UTM) to perform the conversion. The output coordinates will be displayed on the output tab.</li>
-<li>You can clear the input/output fields by clicking on Clear Input or Clear Output buttons.</li>
-</ol>
-<p>For example, if you want to convert from GCS to UTM, you can enter the following values:</p>
-<table border="1">
-<tr><td>Name</td><td>1</td></tr>
-<tr><td>Latitude</td><td>-6.1754</td></tr>
-<tr><td>Longitude</td><td>106.8272</td></tr>
-<tr><td>Datum</td><td>WGS84</td></tr>
-</table>
-<p>Then, select UTM as the output system and click on GCS >> UTM button. The output values will be:</p>
-<table border="1">
-<tr><td>Name</td><td>1</td></tr>
-<tr><td>Easting</td><td>700264.64</td></tr>
-<tr><td>Northing</td><td>9316319.94</td></tr>
-<tr><td>Zone</td><td>48M</td></tr>
-<tr><td>Datum</td><td>WGS84</td></tr>
-</table>
-
-<h3>Extractive Mode</h3>
-<p>In extractive mode, you can use a text file as input and output for coordinate conversion. The text file must have a specific format that is compatible with the software. You can see an example of the format in the folder Transkoord\Contoh File TXT\Contoh Format Standar.txt.</p>
-<p>The format consists of four lines for each point:</p>
-<ul>
-<li>The first line is the name of the point</p> 7196e7f11a<br />
-<br />
-<br />
\ No newline at end of file
diff --git a/spaces/nickmuchi/fintweet-GPT-Search/variables.py b/spaces/nickmuchi/fintweet-GPT-Search/variables.py
deleted file mode 100644
index b752c0fd061dc02ba89e643aabe303a7501ed772..0000000000000000000000000000000000000000
--- a/spaces/nickmuchi/fintweet-GPT-Search/variables.py
+++ /dev/null
@@ -1,154 +0,0 @@
-##Variables
-
-import os
-import streamlit as st
-import pathlib
-
-from langchain.embeddings import HuggingFaceEmbeddings,HuggingFaceInstructEmbeddings
-from langchain.vectorstores import FAISS
-from langchain.memory import ConversationBufferMemory
-from langchain.chat_models.openai import ChatOpenAI
-from langchain.callbacks.base import CallbackManager
-from langchain.callbacks.streaming_stdout import StreamingStdOutCallbackHandler
-from langchain import VectorDBQA
-import pandas as pd
-
-from langchain.chat_models import ChatOpenAI
-from langchain.prompts.chat import (
-    ChatPromptTemplate,
-    SystemMessagePromptTemplate,
-    AIMessagePromptTemplate,
-    HumanMessagePromptTemplate,
-)
-from langchain.schema import (
-    AIMessage,
-    HumanMessage,
-    SystemMessage
-)
-
-from optimum.onnxruntime import ORTModelForSequenceClassification
-from transformers import pipeline, AutoTokenizer
-from optimum.pipelines import pipeline
-import tweepy
-import pandas as pd
-import numpy as np
-import plotly_express as px
-import plotly.graph_objects as go
-from datetime import datetime as dt
-from st_aggrid import GridOptionsBuilder, AgGrid, GridUpdateMode, DataReturnMode
-from datasets import Dataset
-from huggingface_hub import Repository
-
-@st.experimental_singleton(suppress_st_warning=True)
-def load_models():
-    '''load sentimant and topic clssification models'''
-    sent_pipe = pipeline(task,model=sent_model_id, tokenizer=sent_model_id)
-    topic_pipe = pipeline(task, model=topic_model_id, tokenizer=topic_model_id)
-    
-    return sent_pipe, topic_pipe
-
-@st.cache(allow_output_mutation=True, suppress_st_warning=True)
-def process_tweets(df,df_users):
-    '''process tweets into a dataframe'''
-    
-    df['author'] = df['author'].astype(np.int64)
-    
-    df_merged = df.merge(df_users, on='author')
-
-    tweet_list = df_merged['tweet'].tolist()
-    
-    sentiment, topic = pd.DataFrame(sentiment_classifier(tweet_list)), pd.DataFrame(topic_classifier(tweet_list))
-    
-    sentiment.rename(columns={'score':'sentiment_confidence','label':'sentiment'}, inplace=True)
-    
-    topic.rename(columns={'score':'topic_confidence','label':'topic'}, inplace=True)
-    
-    df_group = pd.concat([df_merged,sentiment,topic],axis=1)
-
-    df_group[['sentiment_confidence','topic_confidence']] = df_group[['sentiment_confidence','topic_confidence']].round(2).mul(100)
-
-    df_tweets = df_group[['creation_time','username','tweet','sentiment','topic','sentiment_confidence','topic_confidence']]
-
-    df_tweets = df_tweets.sort_values(by=['creation_time'],ascending=False)
-
-    return df_tweets
-
-@st.experimental_singleton(suppress_st_warning=True)
-def create_vectorstore(texts,model,username,topic,creation_time):
-    '''Create FAISS vectorstore'''
-
-    if model == "hkunlp/instructor-large":
-        emb = HuggingFaceInstructEmbeddings(model_name=model,
-                                            query_instruction='Represent the Financial question for retrieving supporting documents: ',
-                                            embed_instruction='Represent the Financial document for retrieval: ')
-        
-    elif model == "sentence-transformers/all-mpnet-base-v2":
-        emb = HuggingFaceEmbeddings(model_name=model)
-
-    docsearch = FAISS.from_texts(texts, emb,
-                                metadatas=[{"source": user,"topic":top,"extraction_time":tme} for user,top,tme in zip(username,topic,creation_time)])
-
-    return docsearch
-
-    
-@st.experimental_singleton(suppress_st_warning=True)
-def embed_tweets(query,_prompt,_docsearch):
-    '''Process file with latest tweets'''
-
-    streaming_llm = ChatOpenAI(streaming=True, callback_manager=CallbackManager([StreamingStdOutCallbackHandler()]), verbose=True, temperature=0)
-    chain_type_kwargs = {"prompt": _prompt}
-    chain = VectorDBQA.from_chain_type(
-    ChatOpenAI(temperature=0), 
-    chain_type="stuff", 
-    vectorstore=_docsearch,
-    chain_type_kwargs=chain_type_kwargs,
-    return_source_documents=True,
-    k=5
-    )
-
-    result = chain({"query": query})
-
-    return result
-
-CONFIG = {
-    "bearer_token": os.environ.get("bearer_token")
-              }
-
-sent_model_id = 'nickmuchi/optimum-finbert-tone-finetuned-fintwitter-classification'
-topic_model_id = 'nickmuchi/optimum-finbert-tone-finetuned-finance-topic-classification'
-task = 'text-classification'
-
-sentiments = {"0": "Bearish", "1": "Bullish", "2": "Neutral"}
-
-topics = {
-    "0": "Analyst Update",
-    "1": "Fed | Central Banks",
-    "2": "Company | Product News",
-    "3": "Treasuries | Corporate Debt",
-    "4": "Dividend",
-    "5": "Earnings",
-    "6": "Energy | Oil",
-    "7": "Financials",
-    "8": "Currencies",
-    "9": "General News | Opinion",
-    "10": "Gold | Metals | Materials",
-    "11": "IPO",
-    "12": "Legal | Regulation",
-    "13": "M&A | Investments",
-    "14": "Macro",
-    "15": "Markets",
-    "16": "Politics",
-    "17": "Personnel Change",
-    "18": "Stock Commentary",
-    "19": "Stock Movement",
-}
-
-sentiment_classifier, topic_classifier = load_models()
-
-def convert_user_names(user_name: list):
-    '''convert user_names to tweepy format'''
-    users = []
-    for user in user_name:
-        users.append(f"from:{user}")
-    
-    return " OR ".join(users)
\ No newline at end of file
diff --git a/spaces/niew/vits-uma-genshin-honka/text/symbols.py b/spaces/niew/vits-uma-genshin-honka/text/symbols.py
deleted file mode 100644
index edfbd24247be8c757275ce80b9ec27a0ffa808f3..0000000000000000000000000000000000000000
--- a/spaces/niew/vits-uma-genshin-honka/text/symbols.py
+++ /dev/null
@@ -1,39 +0,0 @@
-'''
-Defines the set of symbols used in text input to the model.
-'''
-
-'''# japanese_cleaners
-_pad        = '_'
-_punctuation = ',.!?-'
-_letters = 'AEINOQUabdefghijkmnoprstuvwyzʃʧ↓↑ '
-'''
-
-'''# japanese_cleaners2
-_pad        = '_'
-_punctuation = ',.!?-~…'
-_letters = 'AEINOQUabdefghijkmnoprstuvwyzʃʧʦ↓↑ '
-'''
-
-'''# korean_cleaners
-_pad        = '_'
-_punctuation = ',.!?…~'
-_letters = 'ㄱㄴㄷㄹㅁㅂㅅㅇㅈㅊㅋㅌㅍㅎㄲㄸㅃㅆㅉㅏㅓㅗㅜㅡㅣㅐㅔ '
-'''
-
-'''# chinese_cleaners
-_pad        = '_'
-_punctuation = '，。！？—…'
-_letters = 'ㄅㄆㄇㄈㄉㄊㄋㄌㄍㄎㄏㄐㄑㄒㄓㄔㄕㄖㄗㄘㄙㄚㄛㄜㄝㄞㄟㄠㄡㄢㄣㄤㄥㄦㄧㄨㄩˉˊˇˋ˙ '
-'''
-
-# zh_ja_mixture_cleaners
-_pad        = '_'
-_punctuation = ',.!?-~…'
-_letters = 'AEINOQUabdefghijklmnoprstuvwyzʃʧʦɯɹəɥ⁼ʰ`→↓↑ '
-
-
-# Export all symbols:
-symbols = [_pad] + list(_punctuation) + list(_letters)
-
-# Special symbol ids
-SPACE_ID = symbols.index(" ")
\ No newline at end of file
diff --git a/spaces/nomic-ai/squad_v2/style.css b/spaces/nomic-ai/squad_v2/style.css
deleted file mode 100644
index 114adf441e9032febb46bc056b2a8bb651075f0d..0000000000000000000000000000000000000000
--- a/spaces/nomic-ai/squad_v2/style.css
+++ /dev/null
@@ -1,28 +0,0 @@
-body {
-	padding: 2rem;
-	font-family: -apple-system, BlinkMacSystemFont, "Arial", sans-serif;
-}
-
-h1 {
-	font-size: 16px;
-	margin-top: 0;
-}
-
-p {
-	color: rgb(107, 114, 128);
-	font-size: 15px;
-	margin-bottom: 10px;
-	margin-top: 5px;
-}
-
-.card {
-	max-width: 620px;
-	margin: 0 auto;
-	padding: 16px;
-	border: 1px solid lightgray;
-	border-radius: 16px;
-}
-
-.card p:last-child {
-	margin-bottom: 0;
-}
diff --git a/spaces/nomnomnonono/Sound-Effect-Search/app.py b/spaces/nomnomnonono/Sound-Effect-Search/app.py
deleted file mode 100644
index aab4ccd734e213c5cd0268f26a42649ac08ebdd2..0000000000000000000000000000000000000000
--- a/spaces/nomnomnonono/Sound-Effect-Search/app.py
+++ /dev/null
@@ -1,40 +0,0 @@
-import gradio as gr
-from src.search import Search
-
-search = Search("config.yaml")
-
-with gr.Blocks() as demo:
-    gr.Markdown("Search Sound Effect using this demo.")
-    with gr.TabItem("Search from Audio File"):
-        with gr.Row():
-            with gr.Column(scale=1):
-                text_input = gr.Textbox(value="太鼓", label="SE Title")
-                audio_input = gr.Audio(source="upload")
-                ratio = gr.Slider(minimum=0, maximum=1, value=1, label="Weight Parameter. 1 means 'use only text'. 0 means 'use only audio'.")
-                topk = gr.Dropdown(
-                    [5, 10, 20, 30, 40, 50], value="20", label="Top K"
-                )
-                button = gr.Button("Search")
-            with gr.Column(scale=2):
-                output = gr.Dataframe()
-    with gr.TabItem("Search from Microphone"):
-        with gr.Row():
-            with gr.Column(scale=1):
-                mic_text_input = gr.Textbox(value="太鼓", label="SE Title")
-                mic_audio_input = gr.Audio(source="microphone")
-                mic_ratio = gr.Slider(minimum=0, maximum=1, value=1, label="Weight Parameter. 1 means 'use only text'. 0 means 'use only audio'.")
-                mic_topk = gr.Dropdown(
-                    [5, 10, 20, 30, 40, 50], value="20", label="Top K"
-                )
-                mic_button = gr.Button("Search")
-            with gr.Column(scale=2):
-                mic_output = gr.Dataframe()
-
-    button.click(
-        search.search, inputs=[text_input, audio_input, ratio, topk], outputs=output
-    )
-    mic_button.click(
-        search.search, inputs=[mic_text_input, mic_audio_input, mic_ratio, mic_topk], outputs=mic_output
-    )
-
-demo.launch()
diff --git a/spaces/nsarrazin/agents-js-oasst/src/routes/generate/+server.ts b/spaces/nsarrazin/agents-js-oasst/src/routes/generate/+server.ts
deleted file mode 100644
index 40ba3e1e3922aaaac1bb4fb630748efe93811c86..0000000000000000000000000000000000000000
--- a/spaces/nsarrazin/agents-js-oasst/src/routes/generate/+server.ts
+++ /dev/null
@@ -1,40 +0,0 @@
-import { error, json } from "@sveltejs/kit";
-import {
-  defaultTools,
-  HfAgent,
-  LLMFromEndpoint,
-  LLMFromHub,
-} from "@huggingface/agents";
-import { HF_ACCESS_TOKEN, HF_ENDPOINT } from "$env/static/private";
-
-export async function POST({ request }) {
-  const r = await request.json();
-  const { prompt, tools: selectedTools, filetypes } = r;
-  const tools = defaultTools.filter((el) => selectedTools.includes(el.name));
-
-  let agent;
-  if (HF_ENDPOINT !== "") {
-    agent = new HfAgent(
-      HF_ACCESS_TOKEN,
-      LLMFromEndpoint(HF_ACCESS_TOKEN, HF_ENDPOINT),
-      tools
-    );
-  } else {
-    agent = new HfAgent(HF_ACCESS_TOKEN, LLMFromHub(HF_ACCESS_TOKEN), tools);
-  }
-
-  const files = filetypes
-    ? filetypes.map((el: string) => ({
-        type: el,
-      }))
-    : undefined;
-
-  let code = "";
-  try {
-    code = await agent.generateCode(prompt, files);
-  } catch (e) {
-    throw error(500, e as Error);
-  }
-
-  return json(code);
-}
diff --git a/spaces/omdenatopekachapter/left_ejection_fraction/welcome.py b/spaces/omdenatopekachapter/left_ejection_fraction/welcome.py
deleted file mode 100644
index cdfcea8d2dd882406385719b230cec10c0da3d1b..0000000000000000000000000000000000000000
--- a/spaces/omdenatopekachapter/left_ejection_fraction/welcome.py
+++ /dev/null
@@ -1,104 +0,0 @@
-import streamlit as st
-import pandas as pd
-
-
-
-
-def welcome_page():
-
-
-
-
-  #st.set_page_config(page_title='Welcome', layout='wide')
-
-  st.markdown(
-      """
-      <style>
-          .block-container.css-18e3th9.egzxvld2 {
-          padding-top: 0;
-          }
-          header.css-vg37xl.e8zbici2 {
-          background: none;
-          }
-          span.css-10trblm.e16nr0p30 {
-          color: #4477BB;
-          }
-          .css-1dp5vir.e8zbici1 {
-          background-image: linear-gradient(
-          90deg, rgb(130 166 192), rgb(74 189 130)
-          );
-          }
-          .css-tw2vp1.e1tzin5v0 {
-          gap: 10px;
-          }
-          h1#topeka-chapter {
-          padding: 0;
-          }
-          h1#liverpool-chapter span.css-10trblm.e16nr0p30 {
-          border-bottom: none;
-          font-variant: inherit;
-          }
-          label.css-cgyhhy.effi0qh3, span.css-10trblm.e16nr0p30 {
-          font-weight: bold;
-          font-variant-caps: small-caps;
-          border-bottom: 3px solid #4477BB;
-          }
-          div[data-testid="stSidebarNav"] li div a {
-          margin-left: 1rem;
-          padding: 1rem;
-          width: 300px;
-          border-radius: 0.5rem;
-          }
-          div[data-testid="stSidebarNav"] li div::focus-visible {
-          background-color: rgba(151, 166, 195, 0.15);
-          }
-          svg.e1fb0mya1.css-fblp2m.ex0cdmw0 {
-          width: 2rem;
-          height: 2rem;
-          }
-
-      </style>
-      """, unsafe_allow_html=True
-  )
-
-  st.markdown(
-  """
-  <style>
-  body, h1, h2, h3, h4, h5, h6, p, span, label {
-  font-family: 'Lilita One', cursive;
-  }
-  </style>
-  """, unsafe_allow_html=True
-  )
-
-  col1, col2 = st.columns((1, 5))   
-  with col1:
-      #st.image("https://raw.githubusercontent.com/explainable-ai/lvef_assessment_app/main/resources/Omdena-Logo.png?raw=true")
-      #st.image("https://github.com/explainable-ai/lvef_assessment_app/blob/9ea978de07fd1c27f19d9ebcb1af404f85cde6a6/resources/Favicon.png?raw=true")
-      logo_url = "https://github.com/explainable-ai/lvef_assessment_app/blob/9ea978de07fd1c27f19d9ebcb1af404f85cde6a6/resources/Favicon.png?raw=true"
-
-      st.image(logo_url, width=100)
-  with col2:
-      st.write('# Omdena Topeka Chapter')
-
-  st.markdown('# Project Overview')
-  st.markdown(""" The AI model developed in this project aims to automate the measurement of left ventricular ejection fraction (LVEF) during echocardiography. Manual measurement of LVEF is currently time-consuming and prone to variability, which can lead to inaccurate diagnoses and treatment plans. By automating this process, the workload of healthcare professionals can be reduced, and patient outcomes can be improved by enabling more precise diagnoses and personalized treatment plans.
-
-  The resulting solution is an example of how AI can be integrated into clinical practice, which can lead to more widespread adoption of echocardiography for precision medicine. This can have significant benefits for patients, as echocardiography is a non-invasive and relatively low-cost imaging technique that can provide valuable information about the heart's structure and function. By improving the accuracy and efficiency of echocardiography, the AI model can help to make this technique more accessible and widely used, ultimately improving patient outcomes.""")
-
-
-  st.markdown('## Video: What is Ejection Fraction?')
-  col1, col2 = st.columns((1, 1))
-  with col1:
-      st.video("https://www.youtube.com/watch?v=lGfNjFFbrco")
-  with col2:
-      st.markdown('### Project Focus')
-      st.markdown("""The project’s primary purpose is to accurately predict LVEF measurement.""")
-      st.markdown("""* Develop and train an accurate AI model using the EchoNet-Dynamic dataset to predict LVEF measurement during echocardiography.""")
-      st.markdown("""* Optimize the AI model to minimize error and variability in LVEF measurement predictions, using supervised and unsupervised learning techniques.""")
-      st.markdown("""* Develop a user-friendly interface to integrate the AI model""")
-      st.markdown('### Two-Stream Model')
-      st.markdown("""A two-stream model is a deep learning model used to analyze echocardiogram videos by processing spatial and temporal information in parallel. It consists of two parallel neural networks that analyze each frame and motion between consecutive frames to capture cardiac dynamics. The model can automate diagnosis of various cardiac conditions with high accuracy.""")
-      st.markdown('### Volume Tracing Detection Model')
-      st.markdown("""The Volume Tracing Detection Model is a deep learning model that uses keypoint detection techniques to identify the volume within the left ventricle (LV) of the heart as a set of grid lines. The model is trained on the EchoNet-Dynamic dataset, which already contains tracings for the end-systolic (ES) and end-diastolic (ED) frames. The LV volume calculated at both phases is used to calculate the ejection fraction """)
-
diff --git a/spaces/omlab/vlchecklist_demo/models/vilt/datasets/__init__.py b/spaces/omlab/vlchecklist_demo/models/vilt/datasets/__init__.py
deleted file mode 100644
index 95ec6a37a1b0b310537f3c56dc7f3c405979736e..0000000000000000000000000000000000000000
--- a/spaces/omlab/vlchecklist_demo/models/vilt/datasets/__init__.py
+++ /dev/null
@@ -1,7 +0,0 @@
-from .vg_caption_dataset import VisualGenomeCaptionDataset
-from .coco_caption_karpathy_dataset import CocoCaptionKarpathyDataset
-from .f30k_caption_karpathy_dataset import F30KCaptionKarpathyDataset
-from .conceptual_caption_dataset import ConceptualCaptionDataset
-from .sbu_caption_dataset import SBUCaptionDataset
-from .vqav2_dataset import VQAv2Dataset
-from .nlvr2_dataset import NLVR2Dataset
diff --git a/spaces/osanseviero/esmfold/app.py b/spaces/osanseviero/esmfold/app.py
deleted file mode 100644
index 725dc398f262d987265cf4065ab58926376654e6..0000000000000000000000000000000000000000
--- a/spaces/osanseviero/esmfold/app.py
+++ /dev/null
@@ -1,163 +0,0 @@
-import gradio as gr
-import os
-import requests
-
-
-DEFAULT_SEQ = "MGSSHHHHHHSSGLVPRGSHMRGPNPTAASLEASAGPFTVRSFTVSRPSGYGAGTVYYPTNAGGTVGAIAIVPGYTARQSSIKWWGPRLASHGFVVITIDTNSTLDQPSSRSSQQMAALRQVASLNGTSSSPIYGKVDTARMGVMGWSMGGGGSLISAANNPSLKAAAPQAPWDSSTNFSSVTVPTLIFACENDSIAPVNSSALPIYDSMSRNAKQFLEINGGSHSCANSGNSNQALIGKKGVAWMKRFMDNDTRYSTFACENPNSTRVSDFRTANCSLEDPAANKARKEAELAAATAEQ"
-
-
-def read_mol(molpath):
-    with open(molpath, "r") as fp:
-        lines = fp.readlines()
-    mol = ""
-    for l in lines:
-        mol += l
-    return mol
-
-
-def molecule(input_pdb):
-    mol = read_mol(input_pdb)
-
-    x = (
-        """<!DOCTYPE html>
-        <html>
-        <head>    
-    <meta http-equiv="content-type" content="text/html; charset=UTF-8" />
-    <style>
-    body{
-        font-family:sans-serif
-    }
-    .mol-container {
-    width: 100%;
-    height: 380px;
-    position: relative;
-    }
-    .mol-container select{
-        background-image:None;
-    }
-    </style>
-    <script src="https://3Dmol.csb.pitt.edu/build/3Dmol-min.js"></script>
-    </head>
-    <body style="overflow: hidden;">  
-    <div id="container" class="mol-container"></div>
-  
-            <script>
-               let pdb = `"""
-        + mol
-        + """`  
-      
-             $(document).ready(function () {
-                let element = $("#container");
-                let config = { backgroundColor: "white" };
-                let viewer = $3Dmol.createViewer(element, config);
-                let colorAlpha = function (atom) {
-                    if (atom.b < 0.5) {
-                        return "OrangeRed";
-                    } else if (atom.b < 0.7) {
-                        return "Gold";
-                    } else if (atom.b < 0.9) {
-                        return "MediumTurquoise";
-                    } else {
-                        return "Blue";
-                    }
-                };
-                
-                viewer.addModel(pdb, "pdb");
-                // set plddt coloring
-                viewer.getModel(0).setStyle({cartoon: { colorfunc: colorAlpha }});
-                // display pLDDT tooltips when hovering over atoms
-                viewer.getModel(0).setHoverable({}, true,
-                        function (atom, viewer, event, container) {
-                            if (!atom.label) {
-                                atom.label = viewer.addLabel(atom.resn + atom.resi + " pLDDT=" + atom.b, { position: atom, backgroundColor: "mintcream", fontColor: "black" });
-                            }
-                        },
-                        function (atom, viewer) {
-                            if (atom.label) {
-                                viewer.removeLabel(atom.label);
-                                delete atom.label;
-                            }
-                        }
-                    );
-                viewer.zoomTo();
-                viewer.render();
-                viewer.zoom(1.2, 2000);
-              })
-        </script>
-        </body></html>"""
-    )
-
-    return f"""<iframe style="width: 100%; height: 380px" name="result" allow="midi; geolocation; microphone; camera; 
-    display-capture; encrypted-media;" sandbox="allow-modals allow-forms 
-    allow-scripts allow-same-origin allow-popups 
-    allow-top-navigation-by-user-activation allow-downloads" allowfullscreen="" 
-    allowpaymentrequest="" frameborder="0" srcdoc='{x}'></iframe>"""
-
-import tempfile
-
-
-def update(sequence=DEFAULT_SEQ):
-    headers = {
-        'Content-Type': 'application/x-www-form-urlencoded',
-    }
-
-    response = requests.post('https://api.esmatlas.com/foldSequence/v1/pdb/', headers=headers, data=sequence)
-    name = sequence[:3] + sequence[-3:] 
-    pdb_string = response.content.decode('utf-8')
-    
-    tmp = tempfile.NamedTemporaryFile()
-    with open(tmp.name, "w") as f:
-        f.write(pdb_string)
-    print("File name", tmp.name)
-    return molecule(tmp.name)
-
-
-def suggest(option):
-   if option == "Plastic degradation protein":
-     suggestion = "MGSSHHHHHHSSGLVPRGSHMRGPNPTAASLEASAGPFTVRSFTVSRPSGYGAGTVYYPTNAGGTVGAIAIVPGYTARQSSIKWWGPRLASHGFVVITIDTNSTLDQPSSRSSQQMAALRQVASLNGTSSSPIYGKVDTARMGVMGWSMGGGGSLISAANNPSLKAAAPQAPWDSSTNFSSVTVPTLIFACENDSIAPVNSSALPIYDSMSRNAKQFLEINGGSHSCANSGNSNQALIGKKGVAWMKRFMDNDTRYSTFACENPNSTRVSDFRTANCSLEDPAANKARKEAELAAATAEQ"
-   elif option == "Antifreeze protein":
-     suggestion = "QCTGGADCTSCTGACTGCGNCPNAVTCTNSQHCVKANTCTGSTDCNTAQTCTNSKDCFEANTCTDSTNCYKATACTNSSGCPGH"
-   elif option == "AI Generated protein":
-     suggestion = "MSGMKKLYEYTVTTLDEFLEKLKEFILNTSKDKIYKLTITNPKLIKDIGKAIAKAAEIADVDPKEIEEMIKAVEENELTKLVITIEQTDDKYVIKVELENEDGLVHSFEIYFKNKEEMEKFLELLEKLISKLSGS"
-   elif option == "7-bladed propeller fold":
-     suggestion = "VKLAGNSSLCPINGWAVYSKDNSIRIGSKGDVFVIREPFISCSHLECRTFFLTQGALLNDKHSNGTVKDRSPHRTLMSCPVGEAPSPYNSRFESVAWSASACHDGTSWLTIGISGPDNGAVAVLKYNGIITDTIKSWRNNILRTQESECACVNGSCFTVMTDGPSNGQASYKIFKMEKGKVVKSVELDAPNYHYEECSCYPNAGEITCVCRDNWHGSNRPWVSFNQNLEYQIGYICSGVFGDNPRPNDGTGSCGPVSSNGAYGVKGFSFKYGNGVWIGRTKSTNSRSGFEMIWDPNGWTETDSSFSVKQDIVAITDWSGYSGSFVQHPELTGLDCIRPCFWVELIRGRPKESTIWTSGSSISFCGVNSDTVGWSWPDGAELPFTIDK"
-   else:
-     suggestion = ""
-   return suggestion
-
-
-demo = gr.Blocks()
-
-
-with demo:
-    gr.HTML("""<div style="text-align: center; max-width: 700px; margin: 0 auto;">
-              <div
-              style="
-                  display: inline-flex;
-                  align-items: center;
-                  gap: 0.8rem;
-                  font-size: 1.75rem;
-              "
-              >
-              <h1 style="font-weight: 900; margin-bottom: 7px; margin-top: 5px;">
-                   ESMFold Protein Folding demo
-              </h1>
-              </div>
-              <p style="margin-bottom: 10px; font-size: 94%">
-                  You can input a single protein sequence and you get the predicted protein structure
-              </p>
-          </div>""")
-    name = gr.Dropdown(label="Choose a Sample Protein", value="Plastic degradation protein", choices=["Antifreeze protein", "Plastic degradation protein",  "AI Generated protein", "7-bladed propeller fold", "custom"])
-    with gr.Row():
-        inp = gr.Textbox(label="Protein sequence", lines=3, value=DEFAULT_SEQ, placeholder="Write your protein sequence here...")
-        btn = gr.Button("🔬 Predict Structure ").style(full_width=False)
-    mol = gr.HTML(update)    
-    #download = gr.File(label="Download file")
-    btn.click(fn=update, inputs=inp, outputs=mol)
-    
-    name.change(fn=suggest, inputs=name, outputs=inp)
-    name.change(fn=lambda :"", inputs=None, outputs=mol)
-    inp.change(fn=update, inputs=inp, outputs=mol)
-    
-    gr.Markdown("A demo of [ESM](https://esmatlas.com/about) by Meta using the API. You can also use ESM in Hugging Face `transformers` as shown [here](https://github.com/huggingface/notebooks/blob/ab81a52182acf691e6743a50bc47bd1c1622086f/examples/protein_folding.ipynb), which is supported since [v4.24](https://github.com/huggingface/transformers/releases/tag/v4.24.0).")
-demo.launch(debug=True)
\ No newline at end of file
diff --git a/spaces/osanseviero/shiny/README.md b/spaces/osanseviero/shiny/README.md
deleted file mode 100644
index 27d6f17f998d29be91f30068f5c0f3922c134019..0000000000000000000000000000000000000000
--- a/spaces/osanseviero/shiny/README.md
+++ /dev/null
@@ -1,12 +0,0 @@
----
-title: Shiny
-emoji: 💻
-colorFrom: green
-colorTo: gray
-sdk: gradio
-sdk_version: 3.1.1
-app_file: app.py
-pinned: false
----
-
-Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
diff --git a/spaces/patrickvonplaten/vq-vs-stable-diffusion/app.py b/spaces/patrickvonplaten/vq-vs-stable-diffusion/app.py
deleted file mode 100644
index 1c00bce91ec7d89b81c7200a5e42e01fea43a0e5..0000000000000000000000000000000000000000
--- a/spaces/patrickvonplaten/vq-vs-stable-diffusion/app.py
+++ /dev/null
@@ -1,47 +0,0 @@
-import os
-import gradio as gr
-import torch
-from diffusers import DiffusionPipeline
-
-print(f"Is CUDA available: {torch.cuda.is_available()}")
-
-if torch.cuda.is_available():
-    print(f"CUDA device: {torch.cuda.get_device_name(torch.cuda.current_device())}")
-    pipe_sd = DiffusionPipeline.from_pretrained("runwayml/stable-diffusion-v1-5", torch_dtype=torch.float16, revision="fp16", use_auth_token=os.getenv("HUGGING_FACE_HUB_TOKEN")).to("cuda")
-    pipe_vq = DiffusionPipeline.from_pretrained("microsoft/vq-diffusion-ithq", torch_dtype=torch.float16).to("cuda")
-else:
-    pipe_sd = DiffusionPipeline.from_pretrained("runwayml/stable-diffusion-v1-5", use_auth_token=os.getenv("HUGGING_FACE_HUB_TOKEN"))
-    pipe_vq = DiffusionPipeline.from_pretrained("microsoft/vq-diffusion-ithq")
-
-examples = [
-  ["A sketch of a palm tree."],
-  ["A teddy bear playing in the pool."],
-  ["A simple wedding cake with lego bride and groom topper and cake pops."],
-  ["A realistic tree using a mixture of different colored pencils."],
-  ["Muscular Santa Claus."],
-  ["A man with a pineapple head."],
-  ["Pebble tower standing on the left on the sea beach."],
-]
-
-title = "VQ Diffusion vs. Stable Diffusion 1-5"
-description = "This demo compares [VQ-Diffusion-ITHQ](https://huggingface.co/microsoft/vq-diffusion-ithq) and [Stable-Diffusion-v1-5](https://huggingface.co/runwayml/stable-diffusion-v1-5) for text to image generation."
-
-
-def inference(text):
-    output_sd = pipe_sd(text).images[0]
-    output_vq_diffusion = pipe_vq(text, truncation_rate=1.0).images[0]
-    return [output_vq_diffusion, output_sd]
-
-
-io = gr.Interface(
-  inference,
-  gr.Textbox(lines=3),
-  outputs=[
-    gr.Image(type="pil", label="VQ-Diffusion"),
-    gr.Image(type="pil", label="Stable Diffusion"),
-  ],
-  title=title,
-  description=description,
-  examples=examples
-)
-io.launch()
diff --git a/spaces/pknez/face-swap-docker/mynewshinyroop/Lib/site-packages/pip/__pip-runner__.py b/spaces/pknez/face-swap-docker/mynewshinyroop/Lib/site-packages/pip/__pip-runner__.py
deleted file mode 100644
index 49a148a097e9cc06c165571e0bffaf7cae17dc5b..0000000000000000000000000000000000000000
--- a/spaces/pknez/face-swap-docker/mynewshinyroop/Lib/site-packages/pip/__pip-runner__.py
+++ /dev/null
@@ -1,50 +0,0 @@
-"""Execute exactly this copy of pip, within a different environment.
-
-This file is named as it is, to ensure that this module can't be imported via
-an import statement.
-"""
-
-# /!\ This version compatibility check section must be Python 2 compatible. /!\
-
-import sys
-
-# Copied from setup.py
-PYTHON_REQUIRES = (3, 7)
-
-
-def version_str(version):  # type: ignore
-    return ".".join(str(v) for v in version)
-
-
-if sys.version_info[:2] < PYTHON_REQUIRES:
-    raise SystemExit(
-        "This version of pip does not support python {} (requires >={}).".format(
-            version_str(sys.version_info[:2]), version_str(PYTHON_REQUIRES)
-        )
-    )
-
-# From here on, we can use Python 3 features, but the syntax must remain
-# Python 2 compatible.
-
-import runpy  # noqa: E402
-from importlib.machinery import PathFinder  # noqa: E402
-from os.path import dirname  # noqa: E402
-
-PIP_SOURCES_ROOT = dirname(dirname(__file__))
-
-
-class PipImportRedirectingFinder:
-    @classmethod
-    def find_spec(self, fullname, path=None, target=None):  # type: ignore
-        if fullname != "pip":
-            return None
-
-        spec = PathFinder.find_spec(fullname, [PIP_SOURCES_ROOT], target)
-        assert spec, (PIP_SOURCES_ROOT, fullname)
-        return spec
-
-
-sys.meta_path.insert(0, PipImportRedirectingFinder())
-
-assert __name__ == "__main__", "Cannot run __pip-runner__.py as a non-main module"
-runpy.run_module("pip", run_name="__main__", alter_sys=True)
diff --git a/spaces/pknez/face-swap-docker/mynewshinyroop/Lib/site-packages/wheel/cli/__init__.py b/spaces/pknez/face-swap-docker/mynewshinyroop/Lib/site-packages/wheel/cli/__init__.py
deleted file mode 100644
index c09f839546b0bd9e44d602e127c41b085085d262..0000000000000000000000000000000000000000
--- a/spaces/pknez/face-swap-docker/mynewshinyroop/Lib/site-packages/wheel/cli/__init__.py
+++ /dev/null
@@ -1,155 +0,0 @@
-"""
-Wheel command-line utility.
-"""
-
-from __future__ import annotations
-
-import argparse
-import os
-import sys
-from argparse import ArgumentTypeError
-
-
-class WheelError(Exception):
-    pass
-
-
-def unpack_f(args):
-    from .unpack import unpack
-
-    unpack(args.wheelfile, args.dest)
-
-
-def pack_f(args):
-    from .pack import pack
-
-    pack(args.directory, args.dest_dir, args.build_number)
-
-
-def convert_f(args):
-    from .convert import convert
-
-    convert(args.files, args.dest_dir, args.verbose)
-
-
-def tags_f(args):
-    from .tags import tags
-
-    names = (
-        tags(
-            wheel,
-            args.python_tag,
-            args.abi_tag,
-            args.platform_tag,
-            args.build,
-            args.remove,
-        )
-        for wheel in args.wheel
-    )
-
-    for name in names:
-        print(name)
-
-
-def version_f(args):
-    from .. import __version__
-
-    print("wheel %s" % __version__)
-
-
-def parse_build_tag(build_tag: str) -> str:
-    if not build_tag[0].isdigit():
-        raise ArgumentTypeError("build tag must begin with a digit")
-    elif "-" in build_tag:
-        raise ArgumentTypeError("invalid character ('-') in build tag")
-
-    return build_tag
-
-
-TAGS_HELP = """\
-Make a new wheel with given tags. Any tags unspecified will remain the same.
-Starting the tags with a "+" will append to the existing tags. Starting with a
-"-" will remove a tag (use --option=-TAG syntax). Multiple tags can be
-separated by ".". The original file will remain unless --remove is given.  The
-output filename(s) will be displayed on stdout for further processing.
-"""
-
-
-def parser():
-    p = argparse.ArgumentParser()
-    s = p.add_subparsers(help="commands")
-
-    unpack_parser = s.add_parser("unpack", help="Unpack wheel")
-    unpack_parser.add_argument(
-        "--dest", "-d", help="Destination directory", default="."
-    )
-    unpack_parser.add_argument("wheelfile", help="Wheel file")
-    unpack_parser.set_defaults(func=unpack_f)
-
-    repack_parser = s.add_parser("pack", help="Repack wheel")
-    repack_parser.add_argument("directory", help="Root directory of the unpacked wheel")
-    repack_parser.add_argument(
-        "--dest-dir",
-        "-d",
-        default=os.path.curdir,
-        help="Directory to store the wheel (default %(default)s)",
-    )
-    repack_parser.add_argument(
-        "--build-number", help="Build tag to use in the wheel name"
-    )
-    repack_parser.set_defaults(func=pack_f)
-
-    convert_parser = s.add_parser("convert", help="Convert egg or wininst to wheel")
-    convert_parser.add_argument("files", nargs="*", help="Files to convert")
-    convert_parser.add_argument(
-        "--dest-dir",
-        "-d",
-        default=os.path.curdir,
-        help="Directory to store wheels (default %(default)s)",
-    )
-    convert_parser.add_argument("--verbose", "-v", action="store_true")
-    convert_parser.set_defaults(func=convert_f)
-
-    tags_parser = s.add_parser(
-        "tags", help="Add or replace the tags on a wheel", description=TAGS_HELP
-    )
-    tags_parser.add_argument("wheel", nargs="*", help="Existing wheel(s) to retag")
-    tags_parser.add_argument(
-        "--remove",
-        action="store_true",
-        help="Remove the original files, keeping only the renamed ones",
-    )
-    tags_parser.add_argument(
-        "--python-tag", metavar="TAG", help="Specify an interpreter tag(s)"
-    )
-    tags_parser.add_argument("--abi-tag", metavar="TAG", help="Specify an ABI tag(s)")
-    tags_parser.add_argument(
-        "--platform-tag", metavar="TAG", help="Specify a platform tag(s)"
-    )
-    tags_parser.add_argument(
-        "--build", type=parse_build_tag, metavar="BUILD", help="Specify a build tag"
-    )
-    tags_parser.set_defaults(func=tags_f)
-
-    version_parser = s.add_parser("version", help="Print version and exit")
-    version_parser.set_defaults(func=version_f)
-
-    help_parser = s.add_parser("help", help="Show this help")
-    help_parser.set_defaults(func=lambda args: p.print_help())
-
-    return p
-
-
-def main():
-    p = parser()
-    args = p.parse_args()
-    if not hasattr(args, "func"):
-        p.print_help()
-    else:
-        try:
-            args.func(args)
-            return 0
-        except WheelError as e:
-            print(e, file=sys.stderr)
-
-    return 1
diff --git a/spaces/pragyachik/togethercomputer-RedPajama-INCITE-Chat-3B-v1/app.py b/spaces/pragyachik/togethercomputer-RedPajama-INCITE-Chat-3B-v1/app.py
deleted file mode 100644
index 91667f3eaa06e8062337a945e15d009e26950326..0000000000000000000000000000000000000000
--- a/spaces/pragyachik/togethercomputer-RedPajama-INCITE-Chat-3B-v1/app.py
+++ /dev/null
@@ -1,3 +0,0 @@
-import gradio as gr
-
-gr.Interface.load("models/togethercomputer/RedPajama-INCITE-Chat-3B-v1").launch()
\ No newline at end of file
diff --git a/spaces/prerna9811/Chord/portaudio/test/patest_longsine.c b/spaces/prerna9811/Chord/portaudio/test/patest_longsine.c
deleted file mode 100644
index f439030e77454ef7502ca0a9335e8e16122a3c28..0000000000000000000000000000000000000000
--- a/spaces/prerna9811/Chord/portaudio/test/patest_longsine.c
+++ /dev/null
@@ -1,151 +0,0 @@
-/** @file patest_longsine.c
-    @ingroup test_src
-    @brief Play a sine wave until ENTER hit.
-    @author Phil Burk  http://www.softsynth.com
-*/
-/*
- * $Id$
- *
- * This program uses the PortAudio Portable Audio Library.
- * For more information see: http://www.portaudio.com
- * Copyright (c) 1999-2000 Ross Bencina and Phil Burk
- *
- * Permission is hereby granted, free of charge, to any person obtaining
- * a copy of this software and associated documentation files
- * (the "Software"), to deal in the Software without restriction,
- * including without limitation the rights to use, copy, modify, merge,
- * publish, distribute, sublicense, and/or sell copies of the Software,
- * and to permit persons to whom the Software is furnished to do so,
- * subject to the following conditions:
- *
- * The above copyright notice and this permission notice shall be
- * included in all copies or substantial portions of the Software.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
- * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
- * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.
- * IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR
- * ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF
- * CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION
- * WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.
- */
-
-/*
- * The text above constitutes the entire PortAudio license; however,
- * the PortAudio community also makes the following non-binding requests:
- *
- * Any person wishing to distribute modifications to the Software is
- * requested to send the modifications to the original developer so that
- * they can be incorporated into the canonical version. It is also
- * requested that these non-binding requests be included along with the
- * license above.
- */
-
-#include <stdio.h>
-#include <math.h>
-
-#include "portaudio.h"
-
-#define SAMPLE_RATE   (44100)
-
-#ifndef M_PI
-#define M_PI  (3.14159265)
-#endif
-
-#define TABLE_SIZE   (200)
-typedef struct
-{
-    float sine[TABLE_SIZE];
-    int left_phase;
-    int right_phase;
-}
-paTestData;
-
-/* This routine will be called by the PortAudio engine when audio is needed.
-** It may called at interrupt level on some machines so don't do anything
-** that could mess up the system like calling malloc() or free().
-*/
-static int patestCallback(const void*                     inputBuffer,
-                          void*                           outputBuffer,
-                          unsigned long                   framesPerBuffer,
-                          const PaStreamCallbackTimeInfo* timeInfo,
-                          PaStreamCallbackFlags           statusFlags,
-                          void*                           userData)
-{
-    paTestData *data = (paTestData*)userData;
-    float *out = (float*)outputBuffer;
-    unsigned int i;
-    (void) inputBuffer; /* Prevent unused argument warning. */
-    for( i=0; i<framesPerBuffer; i++ )
-    {
-        *out++ = data->sine[data->left_phase];  /* left */
-        *out++ = data->sine[data->right_phase];  /* right */
-        data->left_phase += 1;
-        if( data->left_phase >= TABLE_SIZE ) data->left_phase -= TABLE_SIZE;
-        data->right_phase += 3; /* higher pitch so we can distinguish left and right. */
-        if( data->right_phase >= TABLE_SIZE ) data->right_phase -= TABLE_SIZE;
-    }
-    return 0;
-}
-
-/*******************************************************************/
-int main(void);
-int main(void)
-{
-    PaStreamParameters outputParameters;
-    PaStream *stream;
-    PaError err;
-    paTestData data;
-    int i;
-    printf("PortAudio Test: output sine wave.\n");
-
-    /* initialise sinusoidal wavetable */
-    for( i=0; i<TABLE_SIZE; i++ )
-    {
-        data.sine[i] = (float) sin( ((double)i/(double)TABLE_SIZE) * M_PI * 2. );
-    }
-    data.left_phase = data.right_phase = 0;
-
-    err = Pa_Initialize();
-    if( err != paNoError ) goto error;
-
-    outputParameters.device = Pa_GetDefaultOutputDevice(); /* default output device */
-    if (outputParameters.device == paNoDevice) {
-        fprintf(stderr,"Error: No default output device.\n");
-        goto error;
-    }
-    outputParameters.channelCount = 2;                     /* stereo output */
-    outputParameters.sampleFormat = paFloat32;             /* 32 bit floating point output */
-    outputParameters.suggestedLatency = Pa_GetDeviceInfo( outputParameters.device )->defaultLowOutputLatency;
-    outputParameters.hostApiSpecificStreamInfo = NULL;
-
-    err = Pa_OpenStream( &stream,
-                         NULL,              /* No input. */
-                         &outputParameters, /* As above. */
-                         SAMPLE_RATE,
-                         256,               /* Frames per buffer. */
-                         paClipOff,         /* No out of range samples expected. */
-                         patestCallback,
-                         &data );
-    if( err != paNoError ) goto error;
-
-    err = Pa_StartStream( stream );
-    if( err != paNoError ) goto error;
-
-    printf("Hit ENTER to stop program.\n");
-    getchar();
-
-    err = Pa_CloseStream( stream );
-    if( err != paNoError ) goto error;
-    Pa_Terminate();
-
-    printf("Test finished.\n");
-    return err;
-
-error:
-    Pa_Terminate();
-    fprintf( stderr, "An error occurred while using the portaudio stream\n" );
-    fprintf( stderr, "Error number: %d\n", err );
-    fprintf( stderr, "Error message: %s\n", Pa_GetErrorText( err ) );
-    return err;
-}
diff --git a/spaces/profayle/TerrapinTalk/myenv/lib/python3.9/site-packages/altair/vegalite/v5/schema/core.py b/spaces/profayle/TerrapinTalk/myenv/lib/python3.9/site-packages/altair/vegalite/v5/schema/core.py
deleted file mode 100644
index 3d12e085872ee00fe7fb0e8a9d02fe18a30997c6..0000000000000000000000000000000000000000
--- a/spaces/profayle/TerrapinTalk/myenv/lib/python3.9/site-packages/altair/vegalite/v5/schema/core.py
+++ /dev/null
@@ -1,21985 +0,0 @@
-# The contents of this file are automatically written by
-# tools/generate_schema_wrapper.py. Do not modify directly.
-
-from altair.utils.schemapi import SchemaBase, Undefined, UndefinedType, _subclasses
-
-import pkgutil
-import json
-
-def load_schema():
-    """Load the json schema associated with this module's functions"""
-    return json.loads(pkgutil.get_data(__name__, 'vega-lite-schema.json').decode('utf-8'))
-
-
-class VegaLiteSchema(SchemaBase):
-    _rootschema = load_schema()
-    @classmethod
-    def _default_wrapper_classes(cls):
-        return _subclasses(VegaLiteSchema)
-
-
-class Root(VegaLiteSchema):
-    """Root schema wrapper
-
-    anyOf(:class:`TopLevelUnitSpec`, :class:`TopLevelFacetSpec`, :class:`TopLevelLayerSpec`,
-    :class:`TopLevelRepeatSpec`, :class:`TopLevelConcatSpec`, :class:`TopLevelVConcatSpec`,
-    :class:`TopLevelHConcatSpec`)
-    A Vega-Lite top-level specification. This is the root class for all Vega-Lite
-    specifications. (The json schema is generated from this type.)
-    """
-    _schema = VegaLiteSchema._rootschema
-
-    def __init__(self, *args, **kwds):
-        super(Root, self).__init__(*args, **kwds)
-
-
-class Aggregate(VegaLiteSchema):
-    """Aggregate schema wrapper
-
-    anyOf(:class:`NonArgAggregateOp`, :class:`ArgmaxDef`, :class:`ArgminDef`)
-    """
-    _schema = {'$ref': '#/definitions/Aggregate'}
-
-    def __init__(self, *args, **kwds):
-        super(Aggregate, self).__init__(*args, **kwds)
-
-
-class AggregateOp(VegaLiteSchema):
-    """AggregateOp schema wrapper
-
-    enum('argmax', 'argmin', 'average', 'count', 'distinct', 'max', 'mean', 'median', 'min',
-    'missing', 'product', 'q1', 'q3', 'ci0', 'ci1', 'stderr', 'stdev', 'stdevp', 'sum', 'valid',
-    'values', 'variance', 'variancep')
-    """
-    _schema = {'$ref': '#/definitions/AggregateOp'}
-
-    def __init__(self, *args):
-        super(AggregateOp, self).__init__(*args)
-
-
-class AggregatedFieldDef(VegaLiteSchema):
-    """AggregatedFieldDef schema wrapper
-
-    Mapping(required=[op, as])
-
-    Parameters
-    ----------
-
-    op : :class:`AggregateOp`
-        The aggregation operation to apply to the fields (e.g., ``"sum"``, ``"average"``, or
-        ``"count"`` ). See the `full list of supported aggregation operations
-        <https://vega.github.io/vega-lite/docs/aggregate.html#ops>`__ for more information.
-    field : :class:`FieldName`
-        The data field for which to compute aggregate function. This is required for all
-        aggregation operations except ``"count"``.
-    as : :class:`FieldName`
-        The output field names to use for each aggregated field.
-    """
-    _schema = {'$ref': '#/definitions/AggregatedFieldDef'}
-
-    def __init__(self, op=Undefined, field=Undefined, **kwds):
-        super(AggregatedFieldDef, self).__init__(op=op, field=field, **kwds)
-
-
-class Align(VegaLiteSchema):
-    """Align schema wrapper
-
-    enum('left', 'center', 'right')
-    """
-    _schema = {'$ref': '#/definitions/Align'}
-
-    def __init__(self, *args):
-        super(Align, self).__init__(*args)
-
-
-class AnyMark(VegaLiteSchema):
-    """AnyMark schema wrapper
-
-    anyOf(:class:`CompositeMark`, :class:`CompositeMarkDef`, :class:`Mark`, :class:`MarkDef`)
-    """
-    _schema = {'$ref': '#/definitions/AnyMark'}
-
-    def __init__(self, *args, **kwds):
-        super(AnyMark, self).__init__(*args, **kwds)
-
-
-class AnyMarkConfig(VegaLiteSchema):
-    """AnyMarkConfig schema wrapper
-
-    anyOf(:class:`MarkConfig`, :class:`AreaConfig`, :class:`BarConfig`, :class:`RectConfig`,
-    :class:`LineConfig`, :class:`TickConfig`)
-    """
-    _schema = {'$ref': '#/definitions/AnyMarkConfig'}
-
-    def __init__(self, *args, **kwds):
-        super(AnyMarkConfig, self).__init__(*args, **kwds)
-
-
-class AreaConfig(AnyMarkConfig):
-    """AreaConfig schema wrapper
-
-    Mapping(required=[])
-
-    Parameters
-    ----------
-
-    align : anyOf(:class:`Align`, :class:`ExprRef`)
-        The horizontal alignment of the text or ranged marks (area, bar, image, rect, rule).
-        One of ``"left"``, ``"right"``, ``"center"``.
-
-        **Note:** Expression reference is *not* supported for range marks.
-    angle : anyOf(float, :class:`ExprRef`)
-        The rotation angle of the text, in degrees.
-    aria : anyOf(boolean, :class:`ExprRef`)
-        A boolean flag indicating if `ARIA attributes
-        <https://developer.mozilla.org/en-US/docs/Web/Accessibility/ARIA>`__ should be
-        included (SVG output only). If ``false``, the "aria-hidden" attribute will be set on
-        the output SVG element, removing the mark item from the ARIA accessibility tree.
-    ariaRole : anyOf(string, :class:`ExprRef`)
-        Sets the type of user interface element of the mark item for `ARIA accessibility
-        <https://developer.mozilla.org/en-US/docs/Web/Accessibility/ARIA>`__ (SVG output
-        only). If specified, this property determines the "role" attribute. Warning: this
-        property is experimental and may be changed in the future.
-    ariaRoleDescription : anyOf(string, :class:`ExprRef`)
-        A human-readable, author-localized description for the role of the mark item for
-        `ARIA accessibility
-        <https://developer.mozilla.org/en-US/docs/Web/Accessibility/ARIA>`__ (SVG output
-        only). If specified, this property determines the "aria-roledescription" attribute.
-        Warning: this property is experimental and may be changed in the future.
-    aspect : anyOf(boolean, :class:`ExprRef`)
-        Whether to keep aspect ratio of image marks.
-    baseline : anyOf(:class:`TextBaseline`, :class:`ExprRef`)
-        For text marks, the vertical text baseline. One of ``"alphabetic"`` (default),
-        ``"top"``, ``"middle"``, ``"bottom"``, ``"line-top"``, ``"line-bottom"``, or an
-        expression reference that provides one of the valid values. The ``"line-top"`` and
-        ``"line-bottom"`` values operate similarly to ``"top"`` and ``"bottom"``, but are
-        calculated relative to the ``lineHeight`` rather than ``fontSize`` alone.
-
-        For range marks, the vertical alignment of the marks. One of ``"top"``,
-        ``"middle"``, ``"bottom"``.
-
-        **Note:** Expression reference is *not* supported for range marks.
-    blend : anyOf(:class:`Blend`, :class:`ExprRef`)
-        The color blend mode for drawing an item on its current background. Any valid `CSS
-        mix-blend-mode <https://developer.mozilla.org/en-US/docs/Web/CSS/mix-blend-mode>`__
-        value can be used.
-
-        __Default value:__ ``"source-over"``
-    color : anyOf(:class:`Color`, :class:`Gradient`, :class:`ExprRef`)
-        Default color.
-
-        **Default value:** :raw-html:`<span style="color: #4682b4;">&#9632;</span>`
-        ``"#4682b4"``
-
-        **Note:**
-
-
-        * This property cannot be used in a `style config
-          <https://vega.github.io/vega-lite/docs/mark.html#style-config>`__.
-        * The ``fill`` and ``stroke`` properties have higher precedence than ``color`` and
-          will override ``color``.
-    cornerRadius : anyOf(float, :class:`ExprRef`)
-        The radius in pixels of rounded rectangles or arcs' corners.
-
-        **Default value:** ``0``
-    cornerRadiusBottomLeft : anyOf(float, :class:`ExprRef`)
-        The radius in pixels of rounded rectangles' bottom left corner.
-
-        **Default value:** ``0``
-    cornerRadiusBottomRight : anyOf(float, :class:`ExprRef`)
-        The radius in pixels of rounded rectangles' bottom right corner.
-
-        **Default value:** ``0``
-    cornerRadiusTopLeft : anyOf(float, :class:`ExprRef`)
-        The radius in pixels of rounded rectangles' top right corner.
-
-        **Default value:** ``0``
-    cornerRadiusTopRight : anyOf(float, :class:`ExprRef`)
-        The radius in pixels of rounded rectangles' top left corner.
-
-        **Default value:** ``0``
-    cursor : anyOf(:class:`Cursor`, :class:`ExprRef`)
-        The mouse cursor used over the mark. Any valid `CSS cursor type
-        <https://developer.mozilla.org/en-US/docs/Web/CSS/cursor#Values>`__ can be used.
-    description : anyOf(string, :class:`ExprRef`)
-        A text description of the mark item for `ARIA accessibility
-        <https://developer.mozilla.org/en-US/docs/Web/Accessibility/ARIA>`__ (SVG output
-        only). If specified, this property determines the `"aria-label" attribute
-        <https://developer.mozilla.org/en-US/docs/Web/Accessibility/ARIA/ARIA_Techniques/Using_the_aria-label_attribute>`__.
-    dir : anyOf(:class:`TextDirection`, :class:`ExprRef`)
-        The direction of the text. One of ``"ltr"`` (left-to-right) or ``"rtl"``
-        (right-to-left). This property determines on which side is truncated in response to
-        the limit parameter.
-
-        **Default value:** ``"ltr"``
-    dx : anyOf(float, :class:`ExprRef`)
-        The horizontal offset, in pixels, between the text label and its anchor point. The
-        offset is applied after rotation by the *angle* property.
-    dy : anyOf(float, :class:`ExprRef`)
-        The vertical offset, in pixels, between the text label and its anchor point. The
-        offset is applied after rotation by the *angle* property.
-    ellipsis : anyOf(string, :class:`ExprRef`)
-        The ellipsis string for text truncated in response to the limit parameter.
-
-        **Default value:** ``"…"``
-    endAngle : anyOf(float, :class:`ExprRef`)
-        The end angle in radians for arc marks. A value of ``0`` indicates up (north),
-        increasing values proceed clockwise.
-    fill : anyOf(:class:`Color`, :class:`Gradient`, None, :class:`ExprRef`)
-        Default fill color. This property has higher precedence than ``config.color``. Set
-        to ``null`` to remove fill.
-
-        **Default value:** (None)
-    fillOpacity : anyOf(float, :class:`ExprRef`)
-        The fill opacity (value between [0,1]).
-
-        **Default value:** ``1``
-    filled : boolean
-        Whether the mark's color should be used as fill color instead of stroke color.
-
-        **Default value:** ``false`` for all ``point``, ``line``, and ``rule`` marks as well
-        as ``geoshape`` marks for `graticule
-        <https://vega.github.io/vega-lite/docs/data.html#graticule>`__ data sources;
-        otherwise, ``true``.
-
-        **Note:** This property cannot be used in a `style config
-        <https://vega.github.io/vega-lite/docs/mark.html#style-config>`__.
-    font : anyOf(string, :class:`ExprRef`)
-        The typeface to set the text in (e.g., ``"Helvetica Neue"`` ).
-    fontSize : anyOf(float, :class:`ExprRef`)
-        The font size, in pixels.
-
-        **Default value:** ``11``
-    fontStyle : anyOf(:class:`FontStyle`, :class:`ExprRef`)
-        The font style (e.g., ``"italic"`` ).
-    fontWeight : anyOf(:class:`FontWeight`, :class:`ExprRef`)
-        The font weight. This can be either a string (e.g ``"bold"``, ``"normal"`` ) or a
-        number ( ``100``, ``200``, ``300``, ..., ``900`` where ``"normal"`` = ``400`` and
-        ``"bold"`` = ``700`` ).
-    height : anyOf(float, :class:`ExprRef`)
-        Height of the marks.
-    href : anyOf(:class:`URI`, :class:`ExprRef`)
-        A URL to load upon mouse click. If defined, the mark acts as a hyperlink.
-    innerRadius : anyOf(float, :class:`ExprRef`)
-        The inner radius in pixels of arc marks. ``innerRadius`` is an alias for
-        ``radius2``.
-
-        **Default value:** ``0``
-    interpolate : anyOf(:class:`Interpolate`, :class:`ExprRef`)
-        The line interpolation method to use for line and area marks. One of the following:
-
-
-        * ``"linear"`` : piecewise linear segments, as in a polyline.
-        * ``"linear-closed"`` : close the linear segments to form a polygon.
-        * ``"step"`` : alternate between horizontal and vertical segments, as in a step
-          function.
-        * ``"step-before"`` : alternate between vertical and horizontal segments, as in a
-          step function.
-        * ``"step-after"`` : alternate between horizontal and vertical segments, as in a
-          step function.
-        * ``"basis"`` : a B-spline, with control point duplication on the ends.
-        * ``"basis-open"`` : an open B-spline; may not intersect the start or end.
-        * ``"basis-closed"`` : a closed B-spline, as in a loop.
-        * ``"cardinal"`` : a Cardinal spline, with control point duplication on the ends.
-        * ``"cardinal-open"`` : an open Cardinal spline; may not intersect the start or end,
-          but will intersect other control points.
-        * ``"cardinal-closed"`` : a closed Cardinal spline, as in a loop.
-        * ``"bundle"`` : equivalent to basis, except the tension parameter is used to
-          straighten the spline.
-        * ``"monotone"`` : cubic interpolation that preserves monotonicity in y.
-    invalid : enum('filter', None)
-        Defines how Vega-Lite should handle marks for invalid values ( ``null`` and ``NaN``
-        ).
-
-
-        * If set to ``"filter"`` (default), all data items with null values will be skipped
-          (for line, trail, and area marks) or filtered (for other marks).
-        * If ``null``, all data items are included. In this case, invalid values will be
-          interpreted as zeroes.
-    limit : anyOf(float, :class:`ExprRef`)
-        The maximum length of the text mark in pixels. The text value will be automatically
-        truncated if the rendered size exceeds the limit.
-
-        **Default value:** ``0`` -- indicating no limit
-    line : anyOf(boolean, :class:`OverlayMarkDef`)
-        A flag for overlaying line on top of area marks, or an object defining the
-        properties of the overlayed lines.
-
-
-        If this value is an empty object ( ``{}`` ) or ``true``, lines with default
-        properties will be used.
-
-        If this value is ``false``, no lines would be automatically added to area marks.
-
-        **Default value:** ``false``.
-    lineBreak : anyOf(string, :class:`ExprRef`)
-        A delimiter, such as a newline character, upon which to break text strings into
-        multiple lines. This property is ignored if the text is array-valued.
-    lineHeight : anyOf(float, :class:`ExprRef`)
-        The line height in pixels (the spacing between subsequent lines of text) for
-        multi-line text marks.
-    opacity : anyOf(float, :class:`ExprRef`)
-        The overall opacity (value between [0,1]).
-
-        **Default value:** ``0.7`` for non-aggregate plots with ``point``, ``tick``,
-        ``circle``, or ``square`` marks or layered ``bar`` charts and ``1`` otherwise.
-    order : anyOf(None, boolean)
-        For line and trail marks, this ``order`` property can be set to ``null`` or
-        ``false`` to make the lines use the original order in the data sources.
-    orient : :class:`Orientation`
-        The orientation of a non-stacked bar, tick, area, and line charts. The value is
-        either horizontal (default) or vertical.
-
-
-        * For bar, rule and tick, this determines whether the size of the bar and tick
-          should be applied to x or y dimension.
-        * For area, this property determines the orient property of the Vega output.
-        * For line and trail marks, this property determines the sort order of the points in
-          the line if ``config.sortLineBy`` is not specified. For stacked charts, this is
-          always determined by the orientation of the stack; therefore explicitly specified
-          value will be ignored.
-    outerRadius : anyOf(float, :class:`ExprRef`)
-        The outer radius in pixels of arc marks. ``outerRadius`` is an alias for ``radius``.
-
-        **Default value:** ``0``
-    padAngle : anyOf(float, :class:`ExprRef`)
-        The angular padding applied to sides of the arc, in radians.
-    point : anyOf(boolean, :class:`OverlayMarkDef`, string)
-        A flag for overlaying points on top of line or area marks, or an object defining the
-        properties of the overlayed points.
-
-
-        If this property is ``"transparent"``, transparent points will be used (for
-        enhancing tooltips and selections).
-
-        If this property is an empty object ( ``{}`` ) or ``true``, filled points with
-        default properties will be used.
-
-        If this property is ``false``, no points would be automatically added to line or
-        area marks.
-
-        **Default value:** ``false``.
-    radius : anyOf(float, :class:`ExprRef`)
-        For arc mark, the primary (outer) radius in pixels.
-
-        For text marks, polar coordinate radial offset, in pixels, of the text from the
-        origin determined by the ``x`` and ``y`` properties.
-
-        **Default value:** ``min(plot_width, plot_height)/2``
-    radius2 : anyOf(float, :class:`ExprRef`)
-        The secondary (inner) radius in pixels of arc marks.
-
-        **Default value:** ``0``
-    shape : anyOf(anyOf(:class:`SymbolShape`, string), :class:`ExprRef`)
-        Shape of the point marks. Supported values include:
-
-
-        * plotting shapes: ``"circle"``, ``"square"``, ``"cross"``, ``"diamond"``,
-          ``"triangle-up"``, ``"triangle-down"``, ``"triangle-right"``, or
-          ``"triangle-left"``.
-        * the line symbol ``"stroke"``
-        * centered directional shapes ``"arrow"``, ``"wedge"``, or ``"triangle"``
-        * a custom `SVG path string
-          <https://developer.mozilla.org/en-US/docs/Web/SVG/Tutorial/Paths>`__ (For correct
-          sizing, custom shape paths should be defined within a square bounding box with
-          coordinates ranging from -1 to 1 along both the x and y dimensions.)
-
-        **Default value:** ``"circle"``
-    size : anyOf(float, :class:`ExprRef`)
-        Default size for marks.
-
-
-        * For ``point`` / ``circle`` / ``square``, this represents the pixel area of the
-          marks. Note that this value sets the area of the symbol; the side lengths will
-          increase with the square root of this value.
-        * For ``bar``, this represents the band size of the bar, in pixels.
-        * For ``text``, this represents the font size, in pixels.
-
-        **Default value:**
-
-
-        * ``30`` for point, circle, square marks; width/height's ``step``
-        * ``2`` for bar marks with discrete dimensions;
-        * ``5`` for bar marks with continuous dimensions;
-        * ``11`` for text marks.
-    smooth : anyOf(boolean, :class:`ExprRef`)
-        A boolean flag (default true) indicating if the image should be smoothed when
-        resized. If false, individual pixels should be scaled directly rather than
-        interpolated with smoothing. For SVG rendering, this option may not work in some
-        browsers due to lack of standardization.
-    startAngle : anyOf(float, :class:`ExprRef`)
-        The start angle in radians for arc marks. A value of ``0`` indicates up (north),
-        increasing values proceed clockwise.
-    stroke : anyOf(:class:`Color`, :class:`Gradient`, None, :class:`ExprRef`)
-        Default stroke color. This property has higher precedence than ``config.color``. Set
-        to ``null`` to remove stroke.
-
-        **Default value:** (None)
-    strokeCap : anyOf(:class:`StrokeCap`, :class:`ExprRef`)
-        The stroke cap for line ending style. One of ``"butt"``, ``"round"``, or
-        ``"square"``.
-
-        **Default value:** ``"butt"``
-    strokeDash : anyOf(List(float), :class:`ExprRef`)
-        An array of alternating stroke, space lengths for creating dashed or dotted lines.
-    strokeDashOffset : anyOf(float, :class:`ExprRef`)
-        The offset (in pixels) into which to begin drawing with the stroke dash array.
-    strokeJoin : anyOf(:class:`StrokeJoin`, :class:`ExprRef`)
-        The stroke line join method. One of ``"miter"``, ``"round"`` or ``"bevel"``.
-
-        **Default value:** ``"miter"``
-    strokeMiterLimit : anyOf(float, :class:`ExprRef`)
-        The miter limit at which to bevel a line join.
-    strokeOffset : anyOf(float, :class:`ExprRef`)
-        The offset in pixels at which to draw the group stroke and fill. If unspecified, the
-        default behavior is to dynamically offset stroked groups such that 1 pixel stroke
-        widths align with the pixel grid.
-    strokeOpacity : anyOf(float, :class:`ExprRef`)
-        The stroke opacity (value between [0,1]).
-
-        **Default value:** ``1``
-    strokeWidth : anyOf(float, :class:`ExprRef`)
-        The stroke width, in pixels.
-    tension : anyOf(float, :class:`ExprRef`)
-        Depending on the interpolation type, sets the tension parameter (for line and area
-        marks).
-    text : anyOf(:class:`Text`, :class:`ExprRef`)
-        Placeholder text if the ``text`` channel is not specified
-    theta : anyOf(float, :class:`ExprRef`)
-        For arc marks, the arc length in radians if theta2 is not specified, otherwise the
-        start arc angle. (A value of 0 indicates up or “north”, increasing values proceed
-        clockwise.)
-
-        For text marks, polar coordinate angle in radians.
-    theta2 : anyOf(float, :class:`ExprRef`)
-        The end angle of arc marks in radians. A value of 0 indicates up or “north”,
-        increasing values proceed clockwise.
-    timeUnitBandPosition : float
-        Default relative band position for a time unit. If set to ``0``, the marks will be
-        positioned at the beginning of the time unit band step. If set to ``0.5``, the marks
-        will be positioned in the middle of the time unit band step.
-    timeUnitBandSize : float
-        Default relative band size for a time unit. If set to ``1``, the bandwidth of the
-        marks will be equal to the time unit band step. If set to ``0.5``, bandwidth of the
-        marks will be half of the time unit band step.
-    tooltip : anyOf(float, string, boolean, :class:`TooltipContent`, :class:`ExprRef`, None)
-        The tooltip text string to show upon mouse hover or an object defining which fields
-        should the tooltip be derived from.
-
-
-        * If ``tooltip`` is ``true`` or ``{"content": "encoding"}``, then all fields from
-          ``encoding`` will be used.
-        * If ``tooltip`` is ``{"content": "data"}``, then all fields that appear in the
-          highlighted data point will be used.
-        * If set to ``null`` or ``false``, then no tooltip will be used.
-
-        See the `tooltip <https://vega.github.io/vega-lite/docs/tooltip.html>`__
-        documentation for a detailed discussion about tooltip  in Vega-Lite.
-
-        **Default value:** ``null``
-    url : anyOf(:class:`URI`, :class:`ExprRef`)
-        The URL of the image file for image marks.
-    width : anyOf(float, :class:`ExprRef`)
-        Width of the marks.
-    x : anyOf(float, string, :class:`ExprRef`)
-        X coordinates of the marks, or width of horizontal ``"bar"`` and ``"area"`` without
-        specified ``x2`` or ``width``.
-
-        The ``value`` of this channel can be a number or a string ``"width"`` for the width
-        of the plot.
-    x2 : anyOf(float, string, :class:`ExprRef`)
-        X2 coordinates for ranged ``"area"``, ``"bar"``, ``"rect"``, and  ``"rule"``.
-
-        The ``value`` of this channel can be a number or a string ``"width"`` for the width
-        of the plot.
-    y : anyOf(float, string, :class:`ExprRef`)
-        Y coordinates of the marks, or height of vertical ``"bar"`` and ``"area"`` without
-        specified ``y2`` or ``height``.
-
-        The ``value`` of this channel can be a number or a string ``"height"`` for the
-        height of the plot.
-    y2 : anyOf(float, string, :class:`ExprRef`)
-        Y2 coordinates for ranged ``"area"``, ``"bar"``, ``"rect"``, and  ``"rule"``.
-
-        The ``value`` of this channel can be a number or a string ``"height"`` for the
-        height of the plot.
-    """
-    _schema = {'$ref': '#/definitions/AreaConfig'}
-
-    def __init__(self, align=Undefined, angle=Undefined, aria=Undefined, ariaRole=Undefined,
-                 ariaRoleDescription=Undefined, aspect=Undefined, baseline=Undefined, blend=Undefined,
-                 color=Undefined, cornerRadius=Undefined, cornerRadiusBottomLeft=Undefined,
-                 cornerRadiusBottomRight=Undefined, cornerRadiusTopLeft=Undefined,
-                 cornerRadiusTopRight=Undefined, cursor=Undefined, description=Undefined, dir=Undefined,
-                 dx=Undefined, dy=Undefined, ellipsis=Undefined, endAngle=Undefined, fill=Undefined,
-                 fillOpacity=Undefined, filled=Undefined, font=Undefined, fontSize=Undefined,
-                 fontStyle=Undefined, fontWeight=Undefined, height=Undefined, href=Undefined,
-                 innerRadius=Undefined, interpolate=Undefined, invalid=Undefined, limit=Undefined,
-                 line=Undefined, lineBreak=Undefined, lineHeight=Undefined, opacity=Undefined,
-                 order=Undefined, orient=Undefined, outerRadius=Undefined, padAngle=Undefined,
-                 point=Undefined, radius=Undefined, radius2=Undefined, shape=Undefined, size=Undefined,
-                 smooth=Undefined, startAngle=Undefined, stroke=Undefined, strokeCap=Undefined,
-                 strokeDash=Undefined, strokeDashOffset=Undefined, strokeJoin=Undefined,
-                 strokeMiterLimit=Undefined, strokeOffset=Undefined, strokeOpacity=Undefined,
-                 strokeWidth=Undefined, tension=Undefined, text=Undefined, theta=Undefined,
-                 theta2=Undefined, timeUnitBandPosition=Undefined, timeUnitBandSize=Undefined,
-                 tooltip=Undefined, url=Undefined, width=Undefined, x=Undefined, x2=Undefined,
-                 y=Undefined, y2=Undefined, **kwds):
-        super(AreaConfig, self).__init__(align=align, angle=angle, aria=aria, ariaRole=ariaRole,
-                                         ariaRoleDescription=ariaRoleDescription, aspect=aspect,
-                                         baseline=baseline, blend=blend, color=color,
-                                         cornerRadius=cornerRadius,
-                                         cornerRadiusBottomLeft=cornerRadiusBottomLeft,
-                                         cornerRadiusBottomRight=cornerRadiusBottomRight,
-                                         cornerRadiusTopLeft=cornerRadiusTopLeft,
-                                         cornerRadiusTopRight=cornerRadiusTopRight, cursor=cursor,
-                                         description=description, dir=dir, dx=dx, dy=dy,
-                                         ellipsis=ellipsis, endAngle=endAngle, fill=fill,
-                                         fillOpacity=fillOpacity, filled=filled, font=font,
-                                         fontSize=fontSize, fontStyle=fontStyle, fontWeight=fontWeight,
-                                         height=height, href=href, innerRadius=innerRadius,
-                                         interpolate=interpolate, invalid=invalid, limit=limit,
-                                         line=line, lineBreak=lineBreak, lineHeight=lineHeight,
-                                         opacity=opacity, order=order, orient=orient,
-                                         outerRadius=outerRadius, padAngle=padAngle, point=point,
-                                         radius=radius, radius2=radius2, shape=shape, size=size,
-                                         smooth=smooth, startAngle=startAngle, stroke=stroke,
-                                         strokeCap=strokeCap, strokeDash=strokeDash,
-                                         strokeDashOffset=strokeDashOffset, strokeJoin=strokeJoin,
-                                         strokeMiterLimit=strokeMiterLimit, strokeOffset=strokeOffset,
-                                         strokeOpacity=strokeOpacity, strokeWidth=strokeWidth,
-                                         tension=tension, text=text, theta=theta, theta2=theta2,
-                                         timeUnitBandPosition=timeUnitBandPosition,
-                                         timeUnitBandSize=timeUnitBandSize, tooltip=tooltip, url=url,
-                                         width=width, x=x, x2=x2, y=y, y2=y2, **kwds)
-
-
-class ArgmaxDef(Aggregate):
-    """ArgmaxDef schema wrapper
-
-    Mapping(required=[argmax])
-
-    Parameters
-    ----------
-
-    argmax : :class:`FieldName`
-
-    """
-    _schema = {'$ref': '#/definitions/ArgmaxDef'}
-
-    def __init__(self, argmax=Undefined, **kwds):
-        super(ArgmaxDef, self).__init__(argmax=argmax, **kwds)
-
-
-class ArgminDef(Aggregate):
-    """ArgminDef schema wrapper
-
-    Mapping(required=[argmin])
-
-    Parameters
-    ----------
-
-    argmin : :class:`FieldName`
-
-    """
-    _schema = {'$ref': '#/definitions/ArgminDef'}
-
-    def __init__(self, argmin=Undefined, **kwds):
-        super(ArgminDef, self).__init__(argmin=argmin, **kwds)
-
-
-class AutoSizeParams(VegaLiteSchema):
-    """AutoSizeParams schema wrapper
-
-    Mapping(required=[])
-
-    Parameters
-    ----------
-
-    contains : enum('content', 'padding')
-        Determines how size calculation should be performed, one of ``"content"`` or
-        ``"padding"``. The default setting ( ``"content"`` ) interprets the width and height
-        settings as the data rectangle (plotting) dimensions, to which padding is then
-        added. In contrast, the ``"padding"`` setting includes the padding within the view
-        size calculations, such that the width and height settings indicate the **total**
-        intended size of the view.
-
-        **Default value** : ``"content"``
-    resize : boolean
-        A boolean flag indicating if autosize layout should be re-calculated on every view
-        update.
-
-        **Default value** : ``false``
-    type : :class:`AutosizeType`
-        The sizing format type. One of ``"pad"``, ``"fit"``, ``"fit-x"``, ``"fit-y"``,  or
-        ``"none"``. See the `autosize type
-        <https://vega.github.io/vega-lite/docs/size.html#autosize>`__ documentation for
-        descriptions of each.
-
-        **Default value** : ``"pad"``
-    """
-    _schema = {'$ref': '#/definitions/AutoSizeParams'}
-
-    def __init__(self, contains=Undefined, resize=Undefined, type=Undefined, **kwds):
-        super(AutoSizeParams, self).__init__(contains=contains, resize=resize, type=type, **kwds)
-
-
-class AutosizeType(VegaLiteSchema):
-    """AutosizeType schema wrapper
-
-    enum('pad', 'none', 'fit', 'fit-x', 'fit-y')
-    """
-    _schema = {'$ref': '#/definitions/AutosizeType'}
-
-    def __init__(self, *args):
-        super(AutosizeType, self).__init__(*args)
-
-
-class Axis(VegaLiteSchema):
-    """Axis schema wrapper
-
-    Mapping(required=[])
-
-    Parameters
-    ----------
-
-    aria : anyOf(boolean, :class:`ExprRef`)
-        A boolean flag indicating if `ARIA attributes
-        <https://developer.mozilla.org/en-US/docs/Web/Accessibility/ARIA>`__ should be
-        included (SVG output only). If ``false``, the "aria-hidden" attribute will be set on
-        the output SVG group, removing the axis from the ARIA accessibility tree.
-
-        **Default value:** ``true``
-    bandPosition : anyOf(float, :class:`ExprRef`)
-        An interpolation fraction indicating where, for ``band`` scales, axis ticks should
-        be positioned. A value of ``0`` places ticks at the left edge of their bands. A
-        value of ``0.5`` places ticks in the middle of their bands.
-
-        **Default value:** ``0.5``
-    description : anyOf(string, :class:`ExprRef`)
-        A text description of this axis for `ARIA accessibility
-        <https://developer.mozilla.org/en-US/docs/Web/Accessibility/ARIA>`__ (SVG output
-        only). If the ``aria`` property is true, for SVG output the `"aria-label" attribute
-        <https://developer.mozilla.org/en-US/docs/Web/Accessibility/ARIA/ARIA_Techniques/Using_the_aria-label_attribute>`__
-        will be set to this description. If the description is unspecified it will be
-        automatically generated.
-    domain : boolean
-        A boolean flag indicating if the domain (the axis baseline) should be included as
-        part of the axis.
-
-        **Default value:** ``true``
-    domainCap : anyOf(:class:`StrokeCap`, :class:`ExprRef`)
-        The stroke cap for the domain line's ending style. One of ``"butt"``, ``"round"`` or
-        ``"square"``.
-
-        **Default value:** ``"butt"``
-    domainColor : anyOf(anyOf(None, :class:`Color`), :class:`ExprRef`)
-        Color of axis domain line.
-
-        **Default value:** ``"gray"``.
-    domainDash : anyOf(List(float), :class:`ExprRef`)
-        An array of alternating [stroke, space] lengths for dashed domain lines.
-    domainDashOffset : anyOf(float, :class:`ExprRef`)
-        The pixel offset at which to start drawing with the domain dash array.
-    domainOpacity : anyOf(float, :class:`ExprRef`)
-        Opacity of the axis domain line.
-    domainWidth : anyOf(float, :class:`ExprRef`)
-        Stroke width of axis domain line
-
-        **Default value:** ``1``
-    format : anyOf(string, :class:`Dict`)
-        When used with the default ``"number"`` and ``"time"`` format type, the text
-        formatting pattern for labels of guides (axes, legends, headers) and text marks.
-
-
-        * If the format type is ``"number"`` (e.g., for quantitative fields), this is D3's
-          `number format pattern <https://github.com/d3/d3-format#locale_format>`__.
-        * If the format type is ``"time"`` (e.g., for temporal fields), this is D3's `time
-          format pattern <https://github.com/d3/d3-time-format#locale_format>`__.
-
-        See the `format documentation <https://vega.github.io/vega-lite/docs/format.html>`__
-        for more examples.
-
-        When used with a `custom formatType
-        <https://vega.github.io/vega-lite/docs/config.html#custom-format-type>`__, this
-        value will be passed as ``format`` alongside ``datum.value`` to the registered
-        function.
-
-        **Default value:**  Derived from `numberFormat
-        <https://vega.github.io/vega-lite/docs/config.html#format>`__ config for number
-        format and from `timeFormat
-        <https://vega.github.io/vega-lite/docs/config.html#format>`__ config for time
-        format.
-    formatType : string
-        The format type for labels. One of ``"number"``, ``"time"``, or a `registered custom
-        format type
-        <https://vega.github.io/vega-lite/docs/config.html#custom-format-type>`__.
-
-        **Default value:**
-
-
-        * ``"time"`` for temporal fields and ordinal and nominal fields with ``timeUnit``.
-        * ``"number"`` for quantitative fields as well as ordinal and nominal fields without
-          ``timeUnit``.
-    grid : boolean
-        A boolean flag indicating if grid lines should be included as part of the axis
-
-        **Default value:** ``true`` for `continuous scales
-        <https://vega.github.io/vega-lite/docs/scale.html#continuous>`__ that are not
-        binned; otherwise, ``false``.
-    gridCap : anyOf(:class:`StrokeCap`, :class:`ExprRef`)
-        The stroke cap for grid lines' ending style. One of ``"butt"``, ``"round"`` or
-        ``"square"``.
-
-        **Default value:** ``"butt"``
-    gridColor : anyOf(anyOf(None, :class:`Color`), :class:`ExprRef`, :class:`ConditionalAxisColor`)
-        Color of gridlines.
-
-        **Default value:** ``"lightGray"``.
-    gridDash : anyOf(List(float), :class:`ExprRef`, :class:`ConditionalAxisNumberArray`)
-        An array of alternating [stroke, space] lengths for dashed grid lines.
-    gridDashOffset : anyOf(float, :class:`ExprRef`, :class:`ConditionalAxisNumber`)
-        The pixel offset at which to start drawing with the grid dash array.
-    gridOpacity : anyOf(float, :class:`ExprRef`, :class:`ConditionalAxisNumber`)
-        The stroke opacity of grid (value between [0,1])
-
-        **Default value:** ``1``
-    gridWidth : anyOf(float, :class:`ExprRef`, :class:`ConditionalAxisNumber`)
-        The grid width, in pixels.
-
-        **Default value:** ``1``
-    labelAlign : anyOf(:class:`Align`, :class:`ExprRef`, :class:`ConditionalAxisLabelAlign`)
-        Horizontal text alignment of axis tick labels, overriding the default setting for
-        the current axis orientation.
-    labelAngle : anyOf(float, :class:`ExprRef`)
-        The rotation angle of the axis labels.
-
-        **Default value:** ``-90`` for nominal and ordinal fields; ``0`` otherwise.
-    labelBaseline : anyOf(:class:`TextBaseline`, :class:`ExprRef`, :class:`ConditionalAxisLabelBaseline`)
-        Vertical text baseline of axis tick labels, overriding the default setting for the
-        current axis orientation. One of ``"alphabetic"`` (default), ``"top"``,
-        ``"middle"``, ``"bottom"``, ``"line-top"``, or ``"line-bottom"``. The ``"line-top"``
-        and ``"line-bottom"`` values operate similarly to ``"top"`` and ``"bottom"``, but
-        are calculated relative to the *lineHeight* rather than *fontSize* alone.
-    labelBound : anyOf(anyOf(float, boolean), :class:`ExprRef`)
-        Indicates if labels should be hidden if they exceed the axis range. If ``false``
-        (the default) no bounds overlap analysis is performed. If ``true``, labels will be
-        hidden if they exceed the axis range by more than 1 pixel. If this property is a
-        number, it specifies the pixel tolerance: the maximum amount by which a label
-        bounding box may exceed the axis range.
-
-        **Default value:** ``false``.
-    labelColor : anyOf(anyOf(None, :class:`Color`), :class:`ExprRef`, :class:`ConditionalAxisColor`)
-        The color of the tick label, can be in hex color code or regular color name.
-    labelExpr : string
-        `Vega expression <https://vega.github.io/vega/docs/expressions/>`__ for customizing
-        labels.
-
-        **Note:** The label text and value can be assessed via the ``label`` and ``value``
-        properties of the axis's backing ``datum`` object.
-    labelFlush : anyOf(boolean, float)
-        Indicates if the first and last axis labels should be aligned flush with the scale
-        range. Flush alignment for a horizontal axis will left-align the first label and
-        right-align the last label. For vertical axes, bottom and top text baselines are
-        applied instead. If this property is a number, it also indicates the number of
-        pixels by which to offset the first and last labels; for example, a value of 2 will
-        flush-align the first and last labels and also push them 2 pixels outward from the
-        center of the axis. The additional adjustment can sometimes help the labels better
-        visually group with corresponding axis ticks.
-
-        **Default value:** ``true`` for axis of a continuous x-scale. Otherwise, ``false``.
-    labelFlushOffset : anyOf(float, :class:`ExprRef`)
-        Indicates the number of pixels by which to offset flush-adjusted labels. For
-        example, a value of ``2`` will push flush-adjusted labels 2 pixels outward from the
-        center of the axis. Offsets can help the labels better visually group with
-        corresponding axis ticks.
-
-        **Default value:** ``0``.
-    labelFont : anyOf(string, :class:`ExprRef`, :class:`ConditionalAxisString`)
-        The font of the tick label.
-    labelFontSize : anyOf(float, :class:`ExprRef`, :class:`ConditionalAxisNumber`)
-        The font size of the label, in pixels.
-    labelFontStyle : anyOf(:class:`FontStyle`, :class:`ExprRef`, :class:`ConditionalAxisLabelFontStyle`)
-        Font style of the title.
-    labelFontWeight : anyOf(:class:`FontWeight`, :class:`ExprRef`, :class:`ConditionalAxisLabelFontWeight`)
-        Font weight of axis tick labels.
-    labelLimit : anyOf(float, :class:`ExprRef`)
-        Maximum allowed pixel width of axis tick labels.
-
-        **Default value:** ``180``
-    labelLineHeight : anyOf(float, :class:`ExprRef`)
-        Line height in pixels for multi-line label text or label text with ``"line-top"`` or
-        ``"line-bottom"`` baseline.
-    labelOffset : anyOf(float, :class:`ExprRef`, :class:`ConditionalAxisNumber`)
-        Position offset in pixels to apply to labels, in addition to tickOffset.
-
-        **Default value:** ``0``
-    labelOpacity : anyOf(float, :class:`ExprRef`, :class:`ConditionalAxisNumber`)
-        The opacity of the labels.
-    labelOverlap : anyOf(:class:`LabelOverlap`, :class:`ExprRef`)
-        The strategy to use for resolving overlap of axis labels. If ``false`` (the
-        default), no overlap reduction is attempted. If set to ``true`` or ``"parity"``, a
-        strategy of removing every other label is used (this works well for standard linear
-        axes). If set to ``"greedy"``, a linear scan of the labels is performed, removing
-        any labels that overlaps with the last visible label (this often works better for
-        log-scaled axes).
-
-        **Default value:** ``true`` for non-nominal fields with non-log scales; ``"greedy"``
-        for log scales; otherwise ``false``.
-    labelPadding : anyOf(float, :class:`ExprRef`, :class:`ConditionalAxisNumber`)
-        The padding in pixels between labels and ticks.
-
-        **Default value:** ``2``
-    labelSeparation : anyOf(float, :class:`ExprRef`)
-        The minimum separation that must be between label bounding boxes for them to be
-        considered non-overlapping (default ``0`` ). This property is ignored if
-        *labelOverlap* resolution is not enabled.
-    labels : boolean
-        A boolean flag indicating if labels should be included as part of the axis.
-
-        **Default value:** ``true``.
-    maxExtent : anyOf(float, :class:`ExprRef`)
-        The maximum extent in pixels that axis ticks and labels should use. This determines
-        a maximum offset value for axis titles.
-
-        **Default value:** ``undefined``.
-    minExtent : anyOf(float, :class:`ExprRef`)
-        The minimum extent in pixels that axis ticks and labels should use. This determines
-        a minimum offset value for axis titles.
-
-        **Default value:** ``30`` for y-axis; ``undefined`` for x-axis.
-    offset : anyOf(float, :class:`ExprRef`)
-        The offset, in pixels, by which to displace the axis from the edge of the enclosing
-        group or data rectangle.
-
-        **Default value:** derived from the `axis config
-        <https://vega.github.io/vega-lite/docs/config.html#facet-scale-config>`__ 's
-        ``offset`` ( ``0`` by default)
-    orient : anyOf(:class:`AxisOrient`, :class:`ExprRef`)
-        The orientation of the axis. One of ``"top"``, ``"bottom"``, ``"left"`` or
-        ``"right"``. The orientation can be used to further specialize the axis type (e.g.,
-        a y-axis oriented towards the right edge of the chart).
-
-        **Default value:** ``"bottom"`` for x-axes and ``"left"`` for y-axes.
-    position : anyOf(float, :class:`ExprRef`)
-        The anchor position of the axis in pixels. For x-axes with top or bottom
-        orientation, this sets the axis group x coordinate. For y-axes with left or right
-        orientation, this sets the axis group y coordinate.
-
-        **Default value** : ``0``
-    style : anyOf(string, List(string))
-        A string or array of strings indicating the name of custom styles to apply to the
-        axis. A style is a named collection of axis property defined within the `style
-        configuration <https://vega.github.io/vega-lite/docs/mark.html#style-config>`__. If
-        style is an array, later styles will override earlier styles.
-
-        **Default value:** (none) **Note:** Any specified style will augment the default
-        style. For example, an x-axis mark with ``"style": "foo"`` will use ``config.axisX``
-        and ``config.style.foo`` (the specified style ``"foo"`` has higher precedence).
-    tickBand : anyOf(enum('center', 'extent'), :class:`ExprRef`)
-        For band scales, indicates if ticks and grid lines should be placed at the
-        ``"center"`` of a band (default) or at the band ``"extent"`` s to indicate intervals
-    tickCap : anyOf(:class:`StrokeCap`, :class:`ExprRef`)
-        The stroke cap for the tick lines' ending style. One of ``"butt"``, ``"round"`` or
-        ``"square"``.
-
-        **Default value:** ``"butt"``
-    tickColor : anyOf(anyOf(None, :class:`Color`), :class:`ExprRef`, :class:`ConditionalAxisColor`)
-        The color of the axis's tick.
-
-        **Default value:** ``"gray"``
-    tickCount : anyOf(float, :class:`TimeInterval`, :class:`TimeIntervalStep`, :class:`ExprRef`)
-        A desired number of ticks, for axes visualizing quantitative scales. The resulting
-        number may be different so that values are "nice" (multiples of 2, 5, 10) and lie
-        within the underlying scale's range.
-
-        For scales of type ``"time"`` or ``"utc"``, the tick count can instead be a time
-        interval specifier. Legal string values are ``"millisecond"``, ``"second"``,
-        ``"minute"``, ``"hour"``, ``"day"``, ``"week"``, ``"month"``, and ``"year"``.
-        Alternatively, an object-valued interval specifier of the form ``{"interval":
-        "month", "step": 3}`` includes a desired number of interval steps. Here, ticks are
-        generated for each quarter (Jan, Apr, Jul, Oct) boundary.
-
-        **Default value** : Determine using a formula ``ceil(width/40)`` for x and
-        ``ceil(height/40)`` for y.
-    tickDash : anyOf(List(float), :class:`ExprRef`, :class:`ConditionalAxisNumberArray`)
-        An array of alternating [stroke, space] lengths for dashed tick mark lines.
-    tickDashOffset : anyOf(float, :class:`ExprRef`, :class:`ConditionalAxisNumber`)
-        The pixel offset at which to start drawing with the tick mark dash array.
-    tickExtra : boolean
-        Boolean flag indicating if an extra axis tick should be added for the initial
-        position of the axis. This flag is useful for styling axes for ``band`` scales such
-        that ticks are placed on band boundaries rather in the middle of a band. Use in
-        conjunction with ``"bandPosition": 1`` and an axis ``"padding"`` value of ``0``.
-    tickMinStep : anyOf(float, :class:`ExprRef`)
-        The minimum desired step between axis ticks, in terms of scale domain values. For
-        example, a value of ``1`` indicates that ticks should not be less than 1 unit apart.
-        If ``tickMinStep`` is specified, the ``tickCount`` value will be adjusted, if
-        necessary, to enforce the minimum step value.
-    tickOffset : anyOf(float, :class:`ExprRef`)
-        Position offset in pixels to apply to ticks, labels, and gridlines.
-    tickOpacity : anyOf(float, :class:`ExprRef`, :class:`ConditionalAxisNumber`)
-        Opacity of the ticks.
-    tickRound : boolean
-        Boolean flag indicating if pixel position values should be rounded to the nearest
-        integer.
-
-        **Default value:** ``true``
-    tickSize : anyOf(float, :class:`ExprRef`, :class:`ConditionalAxisNumber`)
-        The size in pixels of axis ticks.
-
-        **Default value:** ``5``
-    tickWidth : anyOf(float, :class:`ExprRef`, :class:`ConditionalAxisNumber`)
-        The width, in pixels, of ticks.
-
-        **Default value:** ``1``
-    ticks : boolean
-        Boolean value that determines whether the axis should include ticks.
-
-        **Default value:** ``true``
-    title : anyOf(:class:`Text`, None)
-        A title for the field. If ``null``, the title will be removed.
-
-        **Default value:**  derived from the field's name and transformation function (
-        ``aggregate``, ``bin`` and ``timeUnit`` ). If the field has an aggregate function,
-        the function is displayed as part of the title (e.g., ``"Sum of Profit"`` ). If the
-        field is binned or has a time unit applied, the applied function is shown in
-        parentheses (e.g., ``"Profit (binned)"``, ``"Transaction Date (year-month)"`` ).
-        Otherwise, the title is simply the field name.
-
-        **Notes** :
-
-        1) You can customize the default field title format by providing the `fieldTitle
-        <https://vega.github.io/vega-lite/docs/config.html#top-level-config>`__ property in
-        the `config <https://vega.github.io/vega-lite/docs/config.html>`__ or `fieldTitle
-        function via the compile function's options
-        <https://vega.github.io/vega-lite/usage/compile.html#field-title>`__.
-
-        2) If both field definition's ``title`` and axis, header, or legend ``title`` are
-        defined, axis/header/legend title will be used.
-    titleAlign : anyOf(:class:`Align`, :class:`ExprRef`)
-        Horizontal text alignment of axis titles.
-    titleAnchor : anyOf(:class:`TitleAnchor`, :class:`ExprRef`)
-        Text anchor position for placing axis titles.
-    titleAngle : anyOf(float, :class:`ExprRef`)
-        Angle in degrees of axis titles.
-    titleBaseline : anyOf(:class:`TextBaseline`, :class:`ExprRef`)
-        Vertical text baseline for axis titles. One of ``"alphabetic"`` (default),
-        ``"top"``, ``"middle"``, ``"bottom"``, ``"line-top"``, or ``"line-bottom"``. The
-        ``"line-top"`` and ``"line-bottom"`` values operate similarly to ``"top"`` and
-        ``"bottom"``, but are calculated relative to the *lineHeight* rather than *fontSize*
-        alone.
-    titleColor : anyOf(anyOf(None, :class:`Color`), :class:`ExprRef`)
-        Color of the title, can be in hex color code or regular color name.
-    titleFont : anyOf(string, :class:`ExprRef`)
-        Font of the title. (e.g., ``"Helvetica Neue"`` ).
-    titleFontSize : anyOf(float, :class:`ExprRef`)
-        Font size of the title.
-    titleFontStyle : anyOf(:class:`FontStyle`, :class:`ExprRef`)
-        Font style of the title.
-    titleFontWeight : anyOf(:class:`FontWeight`, :class:`ExprRef`)
-        Font weight of the title. This can be either a string (e.g ``"bold"``, ``"normal"``
-        ) or a number ( ``100``, ``200``, ``300``, ..., ``900`` where ``"normal"`` = ``400``
-        and ``"bold"`` = ``700`` ).
-    titleLimit : anyOf(float, :class:`ExprRef`)
-        Maximum allowed pixel width of axis titles.
-    titleLineHeight : anyOf(float, :class:`ExprRef`)
-        Line height in pixels for multi-line title text or title text with ``"line-top"`` or
-        ``"line-bottom"`` baseline.
-    titleOpacity : anyOf(float, :class:`ExprRef`)
-        Opacity of the axis title.
-    titlePadding : anyOf(float, :class:`ExprRef`)
-        The padding, in pixels, between title and axis.
-    titleX : anyOf(float, :class:`ExprRef`)
-        X-coordinate of the axis title relative to the axis group.
-    titleY : anyOf(float, :class:`ExprRef`)
-        Y-coordinate of the axis title relative to the axis group.
-    translate : anyOf(float, :class:`ExprRef`)
-        Coordinate space translation offset for axis layout. By default, axes are translated
-        by a 0.5 pixel offset for both the x and y coordinates in order to align stroked
-        lines with the pixel grid. However, for vector graphics output these pixel-specific
-        adjustments may be undesirable, in which case translate can be changed (for example,
-        to zero).
-
-        **Default value:** ``0.5``
-    values : anyOf(List(float), List(string), List(boolean), List(:class:`DateTime`), :class:`ExprRef`)
-        Explicitly set the visible axis tick values.
-    zindex : float
-        A non-negative integer indicating the z-index of the axis. If zindex is 0, axes
-        should be drawn behind all chart elements. To put them in front, set ``zindex`` to
-        ``1`` or more.
-
-        **Default value:** ``0`` (behind the marks).
-    """
-    _schema = {'$ref': '#/definitions/Axis'}
-
-    def __init__(self, aria=Undefined, bandPosition=Undefined, description=Undefined, domain=Undefined,
-                 domainCap=Undefined, domainColor=Undefined, domainDash=Undefined,
-                 domainDashOffset=Undefined, domainOpacity=Undefined, domainWidth=Undefined,
-                 format=Undefined, formatType=Undefined, grid=Undefined, gridCap=Undefined,
-                 gridColor=Undefined, gridDash=Undefined, gridDashOffset=Undefined,
-                 gridOpacity=Undefined, gridWidth=Undefined, labelAlign=Undefined, labelAngle=Undefined,
-                 labelBaseline=Undefined, labelBound=Undefined, labelColor=Undefined,
-                 labelExpr=Undefined, labelFlush=Undefined, labelFlushOffset=Undefined,
-                 labelFont=Undefined, labelFontSize=Undefined, labelFontStyle=Undefined,
-                 labelFontWeight=Undefined, labelLimit=Undefined, labelLineHeight=Undefined,
-                 labelOffset=Undefined, labelOpacity=Undefined, labelOverlap=Undefined,
-                 labelPadding=Undefined, labelSeparation=Undefined, labels=Undefined,
-                 maxExtent=Undefined, minExtent=Undefined, offset=Undefined, orient=Undefined,
-                 position=Undefined, style=Undefined, tickBand=Undefined, tickCap=Undefined,
-                 tickColor=Undefined, tickCount=Undefined, tickDash=Undefined, tickDashOffset=Undefined,
-                 tickExtra=Undefined, tickMinStep=Undefined, tickOffset=Undefined,
-                 tickOpacity=Undefined, tickRound=Undefined, tickSize=Undefined, tickWidth=Undefined,
-                 ticks=Undefined, title=Undefined, titleAlign=Undefined, titleAnchor=Undefined,
-                 titleAngle=Undefined, titleBaseline=Undefined, titleColor=Undefined,
-                 titleFont=Undefined, titleFontSize=Undefined, titleFontStyle=Undefined,
-                 titleFontWeight=Undefined, titleLimit=Undefined, titleLineHeight=Undefined,
-                 titleOpacity=Undefined, titlePadding=Undefined, titleX=Undefined, titleY=Undefined,
-                 translate=Undefined, values=Undefined, zindex=Undefined, **kwds):
-        super(Axis, self).__init__(aria=aria, bandPosition=bandPosition, description=description,
-                                   domain=domain, domainCap=domainCap, domainColor=domainColor,
-                                   domainDash=domainDash, domainDashOffset=domainDashOffset,
-                                   domainOpacity=domainOpacity, domainWidth=domainWidth, format=format,
-                                   formatType=formatType, grid=grid, gridCap=gridCap,
-                                   gridColor=gridColor, gridDash=gridDash,
-                                   gridDashOffset=gridDashOffset, gridOpacity=gridOpacity,
-                                   gridWidth=gridWidth, labelAlign=labelAlign, labelAngle=labelAngle,
-                                   labelBaseline=labelBaseline, labelBound=labelBound,
-                                   labelColor=labelColor, labelExpr=labelExpr, labelFlush=labelFlush,
-                                   labelFlushOffset=labelFlushOffset, labelFont=labelFont,
-                                   labelFontSize=labelFontSize, labelFontStyle=labelFontStyle,
-                                   labelFontWeight=labelFontWeight, labelLimit=labelLimit,
-                                   labelLineHeight=labelLineHeight, labelOffset=labelOffset,
-                                   labelOpacity=labelOpacity, labelOverlap=labelOverlap,
-                                   labelPadding=labelPadding, labelSeparation=labelSeparation,
-                                   labels=labels, maxExtent=maxExtent, minExtent=minExtent,
-                                   offset=offset, orient=orient, position=position, style=style,
-                                   tickBand=tickBand, tickCap=tickCap, tickColor=tickColor,
-                                   tickCount=tickCount, tickDash=tickDash,
-                                   tickDashOffset=tickDashOffset, tickExtra=tickExtra,
-                                   tickMinStep=tickMinStep, tickOffset=tickOffset,
-                                   tickOpacity=tickOpacity, tickRound=tickRound, tickSize=tickSize,
-                                   tickWidth=tickWidth, ticks=ticks, title=title, titleAlign=titleAlign,
-                                   titleAnchor=titleAnchor, titleAngle=titleAngle,
-                                   titleBaseline=titleBaseline, titleColor=titleColor,
-                                   titleFont=titleFont, titleFontSize=titleFontSize,
-                                   titleFontStyle=titleFontStyle, titleFontWeight=titleFontWeight,
-                                   titleLimit=titleLimit, titleLineHeight=titleLineHeight,
-                                   titleOpacity=titleOpacity, titlePadding=titlePadding, titleX=titleX,
-                                   titleY=titleY, translate=translate, values=values, zindex=zindex,
-                                   **kwds)
-
-
-class AxisConfig(VegaLiteSchema):
-    """AxisConfig schema wrapper
-
-    Mapping(required=[])
-
-    Parameters
-    ----------
-
-    aria : anyOf(boolean, :class:`ExprRef`)
-        A boolean flag indicating if `ARIA attributes
-        <https://developer.mozilla.org/en-US/docs/Web/Accessibility/ARIA>`__ should be
-        included (SVG output only). If ``false``, the "aria-hidden" attribute will be set on
-        the output SVG group, removing the axis from the ARIA accessibility tree.
-
-        **Default value:** ``true``
-    bandPosition : anyOf(float, :class:`ExprRef`)
-        An interpolation fraction indicating where, for ``band`` scales, axis ticks should
-        be positioned. A value of ``0`` places ticks at the left edge of their bands. A
-        value of ``0.5`` places ticks in the middle of their bands.
-
-        **Default value:** ``0.5``
-    description : anyOf(string, :class:`ExprRef`)
-        A text description of this axis for `ARIA accessibility
-        <https://developer.mozilla.org/en-US/docs/Web/Accessibility/ARIA>`__ (SVG output
-        only). If the ``aria`` property is true, for SVG output the `"aria-label" attribute
-        <https://developer.mozilla.org/en-US/docs/Web/Accessibility/ARIA/ARIA_Techniques/Using_the_aria-label_attribute>`__
-        will be set to this description. If the description is unspecified it will be
-        automatically generated.
-    disable : boolean
-        Disable axis by default.
-    domain : boolean
-        A boolean flag indicating if the domain (the axis baseline) should be included as
-        part of the axis.
-
-        **Default value:** ``true``
-    domainCap : anyOf(:class:`StrokeCap`, :class:`ExprRef`)
-        The stroke cap for the domain line's ending style. One of ``"butt"``, ``"round"`` or
-        ``"square"``.
-
-        **Default value:** ``"butt"``
-    domainColor : anyOf(anyOf(None, :class:`Color`), :class:`ExprRef`)
-        Color of axis domain line.
-
-        **Default value:** ``"gray"``.
-    domainDash : anyOf(List(float), :class:`ExprRef`)
-        An array of alternating [stroke, space] lengths for dashed domain lines.
-    domainDashOffset : anyOf(float, :class:`ExprRef`)
-        The pixel offset at which to start drawing with the domain dash array.
-    domainOpacity : anyOf(float, :class:`ExprRef`)
-        Opacity of the axis domain line.
-    domainWidth : anyOf(float, :class:`ExprRef`)
-        Stroke width of axis domain line
-
-        **Default value:** ``1``
-    format : anyOf(string, :class:`Dict`)
-        When used with the default ``"number"`` and ``"time"`` format type, the text
-        formatting pattern for labels of guides (axes, legends, headers) and text marks.
-
-
-        * If the format type is ``"number"`` (e.g., for quantitative fields), this is D3's
-          `number format pattern <https://github.com/d3/d3-format#locale_format>`__.
-        * If the format type is ``"time"`` (e.g., for temporal fields), this is D3's `time
-          format pattern <https://github.com/d3/d3-time-format#locale_format>`__.
-
-        See the `format documentation <https://vega.github.io/vega-lite/docs/format.html>`__
-        for more examples.
-
-        When used with a `custom formatType
-        <https://vega.github.io/vega-lite/docs/config.html#custom-format-type>`__, this
-        value will be passed as ``format`` alongside ``datum.value`` to the registered
-        function.
-
-        **Default value:**  Derived from `numberFormat
-        <https://vega.github.io/vega-lite/docs/config.html#format>`__ config for number
-        format and from `timeFormat
-        <https://vega.github.io/vega-lite/docs/config.html#format>`__ config for time
-        format.
-    formatType : string
-        The format type for labels. One of ``"number"``, ``"time"``, or a `registered custom
-        format type
-        <https://vega.github.io/vega-lite/docs/config.html#custom-format-type>`__.
-
-        **Default value:**
-
-
-        * ``"time"`` for temporal fields and ordinal and nominal fields with ``timeUnit``.
-        * ``"number"`` for quantitative fields as well as ordinal and nominal fields without
-          ``timeUnit``.
-    grid : boolean
-        A boolean flag indicating if grid lines should be included as part of the axis
-
-        **Default value:** ``true`` for `continuous scales
-        <https://vega.github.io/vega-lite/docs/scale.html#continuous>`__ that are not
-        binned; otherwise, ``false``.
-    gridCap : anyOf(:class:`StrokeCap`, :class:`ExprRef`)
-        The stroke cap for grid lines' ending style. One of ``"butt"``, ``"round"`` or
-        ``"square"``.
-
-        **Default value:** ``"butt"``
-    gridColor : anyOf(anyOf(None, :class:`Color`), :class:`ExprRef`, :class:`ConditionalAxisColor`)
-        Color of gridlines.
-
-        **Default value:** ``"lightGray"``.
-    gridDash : anyOf(List(float), :class:`ExprRef`, :class:`ConditionalAxisNumberArray`)
-        An array of alternating [stroke, space] lengths for dashed grid lines.
-    gridDashOffset : anyOf(float, :class:`ExprRef`, :class:`ConditionalAxisNumber`)
-        The pixel offset at which to start drawing with the grid dash array.
-    gridOpacity : anyOf(float, :class:`ExprRef`, :class:`ConditionalAxisNumber`)
-        The stroke opacity of grid (value between [0,1])
-
-        **Default value:** ``1``
-    gridWidth : anyOf(float, :class:`ExprRef`, :class:`ConditionalAxisNumber`)
-        The grid width, in pixels.
-
-        **Default value:** ``1``
-    labelAlign : anyOf(:class:`Align`, :class:`ExprRef`, :class:`ConditionalAxisLabelAlign`)
-        Horizontal text alignment of axis tick labels, overriding the default setting for
-        the current axis orientation.
-    labelAngle : anyOf(float, :class:`ExprRef`)
-        The rotation angle of the axis labels.
-
-        **Default value:** ``-90`` for nominal and ordinal fields; ``0`` otherwise.
-    labelBaseline : anyOf(:class:`TextBaseline`, :class:`ExprRef`, :class:`ConditionalAxisLabelBaseline`)
-        Vertical text baseline of axis tick labels, overriding the default setting for the
-        current axis orientation. One of ``"alphabetic"`` (default), ``"top"``,
-        ``"middle"``, ``"bottom"``, ``"line-top"``, or ``"line-bottom"``. The ``"line-top"``
-        and ``"line-bottom"`` values operate similarly to ``"top"`` and ``"bottom"``, but
-        are calculated relative to the *lineHeight* rather than *fontSize* alone.
-    labelBound : anyOf(anyOf(float, boolean), :class:`ExprRef`)
-        Indicates if labels should be hidden if they exceed the axis range. If ``false``
-        (the default) no bounds overlap analysis is performed. If ``true``, labels will be
-        hidden if they exceed the axis range by more than 1 pixel. If this property is a
-        number, it specifies the pixel tolerance: the maximum amount by which a label
-        bounding box may exceed the axis range.
-
-        **Default value:** ``false``.
-    labelColor : anyOf(anyOf(None, :class:`Color`), :class:`ExprRef`, :class:`ConditionalAxisColor`)
-        The color of the tick label, can be in hex color code or regular color name.
-    labelExpr : string
-        `Vega expression <https://vega.github.io/vega/docs/expressions/>`__ for customizing
-        labels.
-
-        **Note:** The label text and value can be assessed via the ``label`` and ``value``
-        properties of the axis's backing ``datum`` object.
-    labelFlush : anyOf(boolean, float)
-        Indicates if the first and last axis labels should be aligned flush with the scale
-        range. Flush alignment for a horizontal axis will left-align the first label and
-        right-align the last label. For vertical axes, bottom and top text baselines are
-        applied instead. If this property is a number, it also indicates the number of
-        pixels by which to offset the first and last labels; for example, a value of 2 will
-        flush-align the first and last labels and also push them 2 pixels outward from the
-        center of the axis. The additional adjustment can sometimes help the labels better
-        visually group with corresponding axis ticks.
-
-        **Default value:** ``true`` for axis of a continuous x-scale. Otherwise, ``false``.
-    labelFlushOffset : anyOf(float, :class:`ExprRef`)
-        Indicates the number of pixels by which to offset flush-adjusted labels. For
-        example, a value of ``2`` will push flush-adjusted labels 2 pixels outward from the
-        center of the axis. Offsets can help the labels better visually group with
-        corresponding axis ticks.
-
-        **Default value:** ``0``.
-    labelFont : anyOf(string, :class:`ExprRef`, :class:`ConditionalAxisString`)
-        The font of the tick label.
-    labelFontSize : anyOf(float, :class:`ExprRef`, :class:`ConditionalAxisNumber`)
-        The font size of the label, in pixels.
-    labelFontStyle : anyOf(:class:`FontStyle`, :class:`ExprRef`, :class:`ConditionalAxisLabelFontStyle`)
-        Font style of the title.
-    labelFontWeight : anyOf(:class:`FontWeight`, :class:`ExprRef`, :class:`ConditionalAxisLabelFontWeight`)
-        Font weight of axis tick labels.
-    labelLimit : anyOf(float, :class:`ExprRef`)
-        Maximum allowed pixel width of axis tick labels.
-
-        **Default value:** ``180``
-    labelLineHeight : anyOf(float, :class:`ExprRef`)
-        Line height in pixels for multi-line label text or label text with ``"line-top"`` or
-        ``"line-bottom"`` baseline.
-    labelOffset : anyOf(float, :class:`ExprRef`, :class:`ConditionalAxisNumber`)
-        Position offset in pixels to apply to labels, in addition to tickOffset.
-
-        **Default value:** ``0``
-    labelOpacity : anyOf(float, :class:`ExprRef`, :class:`ConditionalAxisNumber`)
-        The opacity of the labels.
-    labelOverlap : anyOf(:class:`LabelOverlap`, :class:`ExprRef`)
-        The strategy to use for resolving overlap of axis labels. If ``false`` (the
-        default), no overlap reduction is attempted. If set to ``true`` or ``"parity"``, a
-        strategy of removing every other label is used (this works well for standard linear
-        axes). If set to ``"greedy"``, a linear scan of the labels is performed, removing
-        any labels that overlaps with the last visible label (this often works better for
-        log-scaled axes).
-
-        **Default value:** ``true`` for non-nominal fields with non-log scales; ``"greedy"``
-        for log scales; otherwise ``false``.
-    labelPadding : anyOf(float, :class:`ExprRef`, :class:`ConditionalAxisNumber`)
-        The padding in pixels between labels and ticks.
-
-        **Default value:** ``2``
-    labelSeparation : anyOf(float, :class:`ExprRef`)
-        The minimum separation that must be between label bounding boxes for them to be
-        considered non-overlapping (default ``0`` ). This property is ignored if
-        *labelOverlap* resolution is not enabled.
-    labels : boolean
-        A boolean flag indicating if labels should be included as part of the axis.
-
-        **Default value:** ``true``.
-    maxExtent : anyOf(float, :class:`ExprRef`)
-        The maximum extent in pixels that axis ticks and labels should use. This determines
-        a maximum offset value for axis titles.
-
-        **Default value:** ``undefined``.
-    minExtent : anyOf(float, :class:`ExprRef`)
-        The minimum extent in pixels that axis ticks and labels should use. This determines
-        a minimum offset value for axis titles.
-
-        **Default value:** ``30`` for y-axis; ``undefined`` for x-axis.
-    offset : anyOf(float, :class:`ExprRef`)
-        The offset, in pixels, by which to displace the axis from the edge of the enclosing
-        group or data rectangle.
-
-        **Default value:** derived from the `axis config
-        <https://vega.github.io/vega-lite/docs/config.html#facet-scale-config>`__ 's
-        ``offset`` ( ``0`` by default)
-    orient : anyOf(:class:`AxisOrient`, :class:`ExprRef`)
-        The orientation of the axis. One of ``"top"``, ``"bottom"``, ``"left"`` or
-        ``"right"``. The orientation can be used to further specialize the axis type (e.g.,
-        a y-axis oriented towards the right edge of the chart).
-
-        **Default value:** ``"bottom"`` for x-axes and ``"left"`` for y-axes.
-    position : anyOf(float, :class:`ExprRef`)
-        The anchor position of the axis in pixels. For x-axes with top or bottom
-        orientation, this sets the axis group x coordinate. For y-axes with left or right
-        orientation, this sets the axis group y coordinate.
-
-        **Default value** : ``0``
-    style : anyOf(string, List(string))
-        A string or array of strings indicating the name of custom styles to apply to the
-        axis. A style is a named collection of axis property defined within the `style
-        configuration <https://vega.github.io/vega-lite/docs/mark.html#style-config>`__. If
-        style is an array, later styles will override earlier styles.
-
-        **Default value:** (none) **Note:** Any specified style will augment the default
-        style. For example, an x-axis mark with ``"style": "foo"`` will use ``config.axisX``
-        and ``config.style.foo`` (the specified style ``"foo"`` has higher precedence).
-    tickBand : anyOf(enum('center', 'extent'), :class:`ExprRef`)
-        For band scales, indicates if ticks and grid lines should be placed at the
-        ``"center"`` of a band (default) or at the band ``"extent"`` s to indicate intervals
-    tickCap : anyOf(:class:`StrokeCap`, :class:`ExprRef`)
-        The stroke cap for the tick lines' ending style. One of ``"butt"``, ``"round"`` or
-        ``"square"``.
-
-        **Default value:** ``"butt"``
-    tickColor : anyOf(anyOf(None, :class:`Color`), :class:`ExprRef`, :class:`ConditionalAxisColor`)
-        The color of the axis's tick.
-
-        **Default value:** ``"gray"``
-    tickCount : anyOf(float, :class:`TimeInterval`, :class:`TimeIntervalStep`, :class:`ExprRef`)
-        A desired number of ticks, for axes visualizing quantitative scales. The resulting
-        number may be different so that values are "nice" (multiples of 2, 5, 10) and lie
-        within the underlying scale's range.
-
-        For scales of type ``"time"`` or ``"utc"``, the tick count can instead be a time
-        interval specifier. Legal string values are ``"millisecond"``, ``"second"``,
-        ``"minute"``, ``"hour"``, ``"day"``, ``"week"``, ``"month"``, and ``"year"``.
-        Alternatively, an object-valued interval specifier of the form ``{"interval":
-        "month", "step": 3}`` includes a desired number of interval steps. Here, ticks are
-        generated for each quarter (Jan, Apr, Jul, Oct) boundary.
-
-        **Default value** : Determine using a formula ``ceil(width/40)`` for x and
-        ``ceil(height/40)`` for y.
-    tickDash : anyOf(List(float), :class:`ExprRef`, :class:`ConditionalAxisNumberArray`)
-        An array of alternating [stroke, space] lengths for dashed tick mark lines.
-    tickDashOffset : anyOf(float, :class:`ExprRef`, :class:`ConditionalAxisNumber`)
-        The pixel offset at which to start drawing with the tick mark dash array.
-    tickExtra : boolean
-        Boolean flag indicating if an extra axis tick should be added for the initial
-        position of the axis. This flag is useful for styling axes for ``band`` scales such
-        that ticks are placed on band boundaries rather in the middle of a band. Use in
-        conjunction with ``"bandPosition": 1`` and an axis ``"padding"`` value of ``0``.
-    tickMinStep : anyOf(float, :class:`ExprRef`)
-        The minimum desired step between axis ticks, in terms of scale domain values. For
-        example, a value of ``1`` indicates that ticks should not be less than 1 unit apart.
-        If ``tickMinStep`` is specified, the ``tickCount`` value will be adjusted, if
-        necessary, to enforce the minimum step value.
-    tickOffset : anyOf(float, :class:`ExprRef`)
-        Position offset in pixels to apply to ticks, labels, and gridlines.
-    tickOpacity : anyOf(float, :class:`ExprRef`, :class:`ConditionalAxisNumber`)
-        Opacity of the ticks.
-    tickRound : boolean
-        Boolean flag indicating if pixel position values should be rounded to the nearest
-        integer.
-
-        **Default value:** ``true``
-    tickSize : anyOf(float, :class:`ExprRef`, :class:`ConditionalAxisNumber`)
-        The size in pixels of axis ticks.
-
-        **Default value:** ``5``
-    tickWidth : anyOf(float, :class:`ExprRef`, :class:`ConditionalAxisNumber`)
-        The width, in pixels, of ticks.
-
-        **Default value:** ``1``
-    ticks : boolean
-        Boolean value that determines whether the axis should include ticks.
-
-        **Default value:** ``true``
-    title : anyOf(:class:`Text`, None)
-        A title for the field. If ``null``, the title will be removed.
-
-        **Default value:**  derived from the field's name and transformation function (
-        ``aggregate``, ``bin`` and ``timeUnit`` ). If the field has an aggregate function,
-        the function is displayed as part of the title (e.g., ``"Sum of Profit"`` ). If the
-        field is binned or has a time unit applied, the applied function is shown in
-        parentheses (e.g., ``"Profit (binned)"``, ``"Transaction Date (year-month)"`` ).
-        Otherwise, the title is simply the field name.
-
-        **Notes** :
-
-        1) You can customize the default field title format by providing the `fieldTitle
-        <https://vega.github.io/vega-lite/docs/config.html#top-level-config>`__ property in
-        the `config <https://vega.github.io/vega-lite/docs/config.html>`__ or `fieldTitle
-        function via the compile function's options
-        <https://vega.github.io/vega-lite/usage/compile.html#field-title>`__.
-
-        2) If both field definition's ``title`` and axis, header, or legend ``title`` are
-        defined, axis/header/legend title will be used.
-    titleAlign : anyOf(:class:`Align`, :class:`ExprRef`)
-        Horizontal text alignment of axis titles.
-    titleAnchor : anyOf(:class:`TitleAnchor`, :class:`ExprRef`)
-        Text anchor position for placing axis titles.
-    titleAngle : anyOf(float, :class:`ExprRef`)
-        Angle in degrees of axis titles.
-    titleBaseline : anyOf(:class:`TextBaseline`, :class:`ExprRef`)
-        Vertical text baseline for axis titles. One of ``"alphabetic"`` (default),
-        ``"top"``, ``"middle"``, ``"bottom"``, ``"line-top"``, or ``"line-bottom"``. The
-        ``"line-top"`` and ``"line-bottom"`` values operate similarly to ``"top"`` and
-        ``"bottom"``, but are calculated relative to the *lineHeight* rather than *fontSize*
-        alone.
-    titleColor : anyOf(anyOf(None, :class:`Color`), :class:`ExprRef`)
-        Color of the title, can be in hex color code or regular color name.
-    titleFont : anyOf(string, :class:`ExprRef`)
-        Font of the title. (e.g., ``"Helvetica Neue"`` ).
-    titleFontSize : anyOf(float, :class:`ExprRef`)
-        Font size of the title.
-    titleFontStyle : anyOf(:class:`FontStyle`, :class:`ExprRef`)
-        Font style of the title.
-    titleFontWeight : anyOf(:class:`FontWeight`, :class:`ExprRef`)
-        Font weight of the title. This can be either a string (e.g ``"bold"``, ``"normal"``
-        ) or a number ( ``100``, ``200``, ``300``, ..., ``900`` where ``"normal"`` = ``400``
-        and ``"bold"`` = ``700`` ).
-    titleLimit : anyOf(float, :class:`ExprRef`)
-        Maximum allowed pixel width of axis titles.
-    titleLineHeight : anyOf(float, :class:`ExprRef`)
-        Line height in pixels for multi-line title text or title text with ``"line-top"`` or
-        ``"line-bottom"`` baseline.
-    titleOpacity : anyOf(float, :class:`ExprRef`)
-        Opacity of the axis title.
-    titlePadding : anyOf(float, :class:`ExprRef`)
-        The padding, in pixels, between title and axis.
-    titleX : anyOf(float, :class:`ExprRef`)
-        X-coordinate of the axis title relative to the axis group.
-    titleY : anyOf(float, :class:`ExprRef`)
-        Y-coordinate of the axis title relative to the axis group.
-    translate : anyOf(float, :class:`ExprRef`)
-        Coordinate space translation offset for axis layout. By default, axes are translated
-        by a 0.5 pixel offset for both the x and y coordinates in order to align stroked
-        lines with the pixel grid. However, for vector graphics output these pixel-specific
-        adjustments may be undesirable, in which case translate can be changed (for example,
-        to zero).
-
-        **Default value:** ``0.5``
-    values : anyOf(List(float), List(string), List(boolean), List(:class:`DateTime`), :class:`ExprRef`)
-        Explicitly set the visible axis tick values.
-    zindex : float
-        A non-negative integer indicating the z-index of the axis. If zindex is 0, axes
-        should be drawn behind all chart elements. To put them in front, set ``zindex`` to
-        ``1`` or more.
-
-        **Default value:** ``0`` (behind the marks).
-    """
-    _schema = {'$ref': '#/definitions/AxisConfig'}
-
-    def __init__(self, aria=Undefined, bandPosition=Undefined, description=Undefined, disable=Undefined,
-                 domain=Undefined, domainCap=Undefined, domainColor=Undefined, domainDash=Undefined,
-                 domainDashOffset=Undefined, domainOpacity=Undefined, domainWidth=Undefined,
-                 format=Undefined, formatType=Undefined, grid=Undefined, gridCap=Undefined,
-                 gridColor=Undefined, gridDash=Undefined, gridDashOffset=Undefined,
-                 gridOpacity=Undefined, gridWidth=Undefined, labelAlign=Undefined, labelAngle=Undefined,
-                 labelBaseline=Undefined, labelBound=Undefined, labelColor=Undefined,
-                 labelExpr=Undefined, labelFlush=Undefined, labelFlushOffset=Undefined,
-                 labelFont=Undefined, labelFontSize=Undefined, labelFontStyle=Undefined,
-                 labelFontWeight=Undefined, labelLimit=Undefined, labelLineHeight=Undefined,
-                 labelOffset=Undefined, labelOpacity=Undefined, labelOverlap=Undefined,
-                 labelPadding=Undefined, labelSeparation=Undefined, labels=Undefined,
-                 maxExtent=Undefined, minExtent=Undefined, offset=Undefined, orient=Undefined,
-                 position=Undefined, style=Undefined, tickBand=Undefined, tickCap=Undefined,
-                 tickColor=Undefined, tickCount=Undefined, tickDash=Undefined, tickDashOffset=Undefined,
-                 tickExtra=Undefined, tickMinStep=Undefined, tickOffset=Undefined,
-                 tickOpacity=Undefined, tickRound=Undefined, tickSize=Undefined, tickWidth=Undefined,
-                 ticks=Undefined, title=Undefined, titleAlign=Undefined, titleAnchor=Undefined,
-                 titleAngle=Undefined, titleBaseline=Undefined, titleColor=Undefined,
-                 titleFont=Undefined, titleFontSize=Undefined, titleFontStyle=Undefined,
-                 titleFontWeight=Undefined, titleLimit=Undefined, titleLineHeight=Undefined,
-                 titleOpacity=Undefined, titlePadding=Undefined, titleX=Undefined, titleY=Undefined,
-                 translate=Undefined, values=Undefined, zindex=Undefined, **kwds):
-        super(AxisConfig, self).__init__(aria=aria, bandPosition=bandPosition, description=description,
-                                         disable=disable, domain=domain, domainCap=domainCap,
-                                         domainColor=domainColor, domainDash=domainDash,
-                                         domainDashOffset=domainDashOffset, domainOpacity=domainOpacity,
-                                         domainWidth=domainWidth, format=format, formatType=formatType,
-                                         grid=grid, gridCap=gridCap, gridColor=gridColor,
-                                         gridDash=gridDash, gridDashOffset=gridDashOffset,
-                                         gridOpacity=gridOpacity, gridWidth=gridWidth,
-                                         labelAlign=labelAlign, labelAngle=labelAngle,
-                                         labelBaseline=labelBaseline, labelBound=labelBound,
-                                         labelColor=labelColor, labelExpr=labelExpr,
-                                         labelFlush=labelFlush, labelFlushOffset=labelFlushOffset,
-                                         labelFont=labelFont, labelFontSize=labelFontSize,
-                                         labelFontStyle=labelFontStyle, labelFontWeight=labelFontWeight,
-                                         labelLimit=labelLimit, labelLineHeight=labelLineHeight,
-                                         labelOffset=labelOffset, labelOpacity=labelOpacity,
-                                         labelOverlap=labelOverlap, labelPadding=labelPadding,
-                                         labelSeparation=labelSeparation, labels=labels,
-                                         maxExtent=maxExtent, minExtent=minExtent, offset=offset,
-                                         orient=orient, position=position, style=style,
-                                         tickBand=tickBand, tickCap=tickCap, tickColor=tickColor,
-                                         tickCount=tickCount, tickDash=tickDash,
-                                         tickDashOffset=tickDashOffset, tickExtra=tickExtra,
-                                         tickMinStep=tickMinStep, tickOffset=tickOffset,
-                                         tickOpacity=tickOpacity, tickRound=tickRound,
-                                         tickSize=tickSize, tickWidth=tickWidth, ticks=ticks,
-                                         title=title, titleAlign=titleAlign, titleAnchor=titleAnchor,
-                                         titleAngle=titleAngle, titleBaseline=titleBaseline,
-                                         titleColor=titleColor, titleFont=titleFont,
-                                         titleFontSize=titleFontSize, titleFontStyle=titleFontStyle,
-                                         titleFontWeight=titleFontWeight, titleLimit=titleLimit,
-                                         titleLineHeight=titleLineHeight, titleOpacity=titleOpacity,
-                                         titlePadding=titlePadding, titleX=titleX, titleY=titleY,
-                                         translate=translate, values=values, zindex=zindex, **kwds)
-
-
-class AxisOrient(VegaLiteSchema):
-    """AxisOrient schema wrapper
-
-    enum('top', 'bottom', 'left', 'right')
-    """
-    _schema = {'$ref': '#/definitions/AxisOrient'}
-
-    def __init__(self, *args):
-        super(AxisOrient, self).__init__(*args)
-
-
-class AxisResolveMap(VegaLiteSchema):
-    """AxisResolveMap schema wrapper
-
-    Mapping(required=[])
-
-    Parameters
-    ----------
-
-    x : :class:`ResolveMode`
-
-    y : :class:`ResolveMode`
-
-    """
-    _schema = {'$ref': '#/definitions/AxisResolveMap'}
-
-    def __init__(self, x=Undefined, y=Undefined, **kwds):
-        super(AxisResolveMap, self).__init__(x=x, y=y, **kwds)
-
-
-class BBox(VegaLiteSchema):
-    """BBox schema wrapper
-
-    anyOf(List(float), List(float))
-    Bounding box https://tools.ietf.org/html/rfc7946#section-5
-    """
-    _schema = {'$ref': '#/definitions/BBox'}
-
-    def __init__(self, *args, **kwds):
-        super(BBox, self).__init__(*args, **kwds)
-
-
-class BarConfig(AnyMarkConfig):
-    """BarConfig schema wrapper
-
-    Mapping(required=[])
-
-    Parameters
-    ----------
-
-    align : anyOf(:class:`Align`, :class:`ExprRef`)
-        The horizontal alignment of the text or ranged marks (area, bar, image, rect, rule).
-        One of ``"left"``, ``"right"``, ``"center"``.
-
-        **Note:** Expression reference is *not* supported for range marks.
-    angle : anyOf(float, :class:`ExprRef`)
-        The rotation angle of the text, in degrees.
-    aria : anyOf(boolean, :class:`ExprRef`)
-        A boolean flag indicating if `ARIA attributes
-        <https://developer.mozilla.org/en-US/docs/Web/Accessibility/ARIA>`__ should be
-        included (SVG output only). If ``false``, the "aria-hidden" attribute will be set on
-        the output SVG element, removing the mark item from the ARIA accessibility tree.
-    ariaRole : anyOf(string, :class:`ExprRef`)
-        Sets the type of user interface element of the mark item for `ARIA accessibility
-        <https://developer.mozilla.org/en-US/docs/Web/Accessibility/ARIA>`__ (SVG output
-        only). If specified, this property determines the "role" attribute. Warning: this
-        property is experimental and may be changed in the future.
-    ariaRoleDescription : anyOf(string, :class:`ExprRef`)
-        A human-readable, author-localized description for the role of the mark item for
-        `ARIA accessibility
-        <https://developer.mozilla.org/en-US/docs/Web/Accessibility/ARIA>`__ (SVG output
-        only). If specified, this property determines the "aria-roledescription" attribute.
-        Warning: this property is experimental and may be changed in the future.
-    aspect : anyOf(boolean, :class:`ExprRef`)
-        Whether to keep aspect ratio of image marks.
-    baseline : anyOf(:class:`TextBaseline`, :class:`ExprRef`)
-        For text marks, the vertical text baseline. One of ``"alphabetic"`` (default),
-        ``"top"``, ``"middle"``, ``"bottom"``, ``"line-top"``, ``"line-bottom"``, or an
-        expression reference that provides one of the valid values. The ``"line-top"`` and
-        ``"line-bottom"`` values operate similarly to ``"top"`` and ``"bottom"``, but are
-        calculated relative to the ``lineHeight`` rather than ``fontSize`` alone.
-
-        For range marks, the vertical alignment of the marks. One of ``"top"``,
-        ``"middle"``, ``"bottom"``.
-
-        **Note:** Expression reference is *not* supported for range marks.
-    binSpacing : float
-        Offset between bars for binned field. The ideal value for this is either 0
-        (preferred by statisticians) or 1 (Vega-Lite default, D3 example style).
-
-        **Default value:** ``1``
-    blend : anyOf(:class:`Blend`, :class:`ExprRef`)
-        The color blend mode for drawing an item on its current background. Any valid `CSS
-        mix-blend-mode <https://developer.mozilla.org/en-US/docs/Web/CSS/mix-blend-mode>`__
-        value can be used.
-
-        __Default value:__ ``"source-over"``
-    color : anyOf(:class:`Color`, :class:`Gradient`, :class:`ExprRef`)
-        Default color.
-
-        **Default value:** :raw-html:`<span style="color: #4682b4;">&#9632;</span>`
-        ``"#4682b4"``
-
-        **Note:**
-
-
-        * This property cannot be used in a `style config
-          <https://vega.github.io/vega-lite/docs/mark.html#style-config>`__.
-        * The ``fill`` and ``stroke`` properties have higher precedence than ``color`` and
-          will override ``color``.
-    continuousBandSize : float
-        The default size of the bars on continuous scales.
-
-        **Default value:** ``5``
-    cornerRadius : anyOf(float, :class:`ExprRef`)
-        The radius in pixels of rounded rectangles or arcs' corners.
-
-        **Default value:** ``0``
-    cornerRadiusBottomLeft : anyOf(float, :class:`ExprRef`)
-        The radius in pixels of rounded rectangles' bottom left corner.
-
-        **Default value:** ``0``
-    cornerRadiusBottomRight : anyOf(float, :class:`ExprRef`)
-        The radius in pixels of rounded rectangles' bottom right corner.
-
-        **Default value:** ``0``
-    cornerRadiusEnd : anyOf(float, :class:`ExprRef`)
-        For vertical bars, top-left and top-right corner radius.
-
-        For horizontal bars, top-right and bottom-right corner radius.
-    cornerRadiusTopLeft : anyOf(float, :class:`ExprRef`)
-        The radius in pixels of rounded rectangles' top right corner.
-
-        **Default value:** ``0``
-    cornerRadiusTopRight : anyOf(float, :class:`ExprRef`)
-        The radius in pixels of rounded rectangles' top left corner.
-
-        **Default value:** ``0``
-    cursor : anyOf(:class:`Cursor`, :class:`ExprRef`)
-        The mouse cursor used over the mark. Any valid `CSS cursor type
-        <https://developer.mozilla.org/en-US/docs/Web/CSS/cursor#Values>`__ can be used.
-    description : anyOf(string, :class:`ExprRef`)
-        A text description of the mark item for `ARIA accessibility
-        <https://developer.mozilla.org/en-US/docs/Web/Accessibility/ARIA>`__ (SVG output
-        only). If specified, this property determines the `"aria-label" attribute
-        <https://developer.mozilla.org/en-US/docs/Web/Accessibility/ARIA/ARIA_Techniques/Using_the_aria-label_attribute>`__.
-    dir : anyOf(:class:`TextDirection`, :class:`ExprRef`)
-        The direction of the text. One of ``"ltr"`` (left-to-right) or ``"rtl"``
-        (right-to-left). This property determines on which side is truncated in response to
-        the limit parameter.
-
-        **Default value:** ``"ltr"``
-    discreteBandSize : anyOf(float, :class:`RelativeBandSize`)
-        The default size of the bars with discrete dimensions. If unspecified, the default
-        size is  ``step-2``, which provides 2 pixel offset between bars.
-    dx : anyOf(float, :class:`ExprRef`)
-        The horizontal offset, in pixels, between the text label and its anchor point. The
-        offset is applied after rotation by the *angle* property.
-    dy : anyOf(float, :class:`ExprRef`)
-        The vertical offset, in pixels, between the text label and its anchor point. The
-        offset is applied after rotation by the *angle* property.
-    ellipsis : anyOf(string, :class:`ExprRef`)
-        The ellipsis string for text truncated in response to the limit parameter.
-
-        **Default value:** ``"…"``
-    endAngle : anyOf(float, :class:`ExprRef`)
-        The end angle in radians for arc marks. A value of ``0`` indicates up (north),
-        increasing values proceed clockwise.
-    fill : anyOf(:class:`Color`, :class:`Gradient`, None, :class:`ExprRef`)
-        Default fill color. This property has higher precedence than ``config.color``. Set
-        to ``null`` to remove fill.
-
-        **Default value:** (None)
-    fillOpacity : anyOf(float, :class:`ExprRef`)
-        The fill opacity (value between [0,1]).
-
-        **Default value:** ``1``
-    filled : boolean
-        Whether the mark's color should be used as fill color instead of stroke color.
-
-        **Default value:** ``false`` for all ``point``, ``line``, and ``rule`` marks as well
-        as ``geoshape`` marks for `graticule
-        <https://vega.github.io/vega-lite/docs/data.html#graticule>`__ data sources;
-        otherwise, ``true``.
-
-        **Note:** This property cannot be used in a `style config
-        <https://vega.github.io/vega-lite/docs/mark.html#style-config>`__.
-    font : anyOf(string, :class:`ExprRef`)
-        The typeface to set the text in (e.g., ``"Helvetica Neue"`` ).
-    fontSize : anyOf(float, :class:`ExprRef`)
-        The font size, in pixels.
-
-        **Default value:** ``11``
-    fontStyle : anyOf(:class:`FontStyle`, :class:`ExprRef`)
-        The font style (e.g., ``"italic"`` ).
-    fontWeight : anyOf(:class:`FontWeight`, :class:`ExprRef`)
-        The font weight. This can be either a string (e.g ``"bold"``, ``"normal"`` ) or a
-        number ( ``100``, ``200``, ``300``, ..., ``900`` where ``"normal"`` = ``400`` and
-        ``"bold"`` = ``700`` ).
-    height : anyOf(float, :class:`ExprRef`)
-        Height of the marks.
-    href : anyOf(:class:`URI`, :class:`ExprRef`)
-        A URL to load upon mouse click. If defined, the mark acts as a hyperlink.
-    innerRadius : anyOf(float, :class:`ExprRef`)
-        The inner radius in pixels of arc marks. ``innerRadius`` is an alias for
-        ``radius2``.
-
-        **Default value:** ``0``
-    interpolate : anyOf(:class:`Interpolate`, :class:`ExprRef`)
-        The line interpolation method to use for line and area marks. One of the following:
-
-
-        * ``"linear"`` : piecewise linear segments, as in a polyline.
-        * ``"linear-closed"`` : close the linear segments to form a polygon.
-        * ``"step"`` : alternate between horizontal and vertical segments, as in a step
-          function.
-        * ``"step-before"`` : alternate between vertical and horizontal segments, as in a
-          step function.
-        * ``"step-after"`` : alternate between horizontal and vertical segments, as in a
-          step function.
-        * ``"basis"`` : a B-spline, with control point duplication on the ends.
-        * ``"basis-open"`` : an open B-spline; may not intersect the start or end.
-        * ``"basis-closed"`` : a closed B-spline, as in a loop.
-        * ``"cardinal"`` : a Cardinal spline, with control point duplication on the ends.
-        * ``"cardinal-open"`` : an open Cardinal spline; may not intersect the start or end,
-          but will intersect other control points.
-        * ``"cardinal-closed"`` : a closed Cardinal spline, as in a loop.
-        * ``"bundle"`` : equivalent to basis, except the tension parameter is used to
-          straighten the spline.
-        * ``"monotone"`` : cubic interpolation that preserves monotonicity in y.
-    invalid : enum('filter', None)
-        Defines how Vega-Lite should handle marks for invalid values ( ``null`` and ``NaN``
-        ).
-
-
-        * If set to ``"filter"`` (default), all data items with null values will be skipped
-          (for line, trail, and area marks) or filtered (for other marks).
-        * If ``null``, all data items are included. In this case, invalid values will be
-          interpreted as zeroes.
-    limit : anyOf(float, :class:`ExprRef`)
-        The maximum length of the text mark in pixels. The text value will be automatically
-        truncated if the rendered size exceeds the limit.
-
-        **Default value:** ``0`` -- indicating no limit
-    lineBreak : anyOf(string, :class:`ExprRef`)
-        A delimiter, such as a newline character, upon which to break text strings into
-        multiple lines. This property is ignored if the text is array-valued.
-    lineHeight : anyOf(float, :class:`ExprRef`)
-        The line height in pixels (the spacing between subsequent lines of text) for
-        multi-line text marks.
-    minBandSize : anyOf(float, :class:`ExprRef`)
-        The minimum band size for bar and rectangle marks. **Default value:** ``0.25``
-    opacity : anyOf(float, :class:`ExprRef`)
-        The overall opacity (value between [0,1]).
-
-        **Default value:** ``0.7`` for non-aggregate plots with ``point``, ``tick``,
-        ``circle``, or ``square`` marks or layered ``bar`` charts and ``1`` otherwise.
-    order : anyOf(None, boolean)
-        For line and trail marks, this ``order`` property can be set to ``null`` or
-        ``false`` to make the lines use the original order in the data sources.
-    orient : :class:`Orientation`
-        The orientation of a non-stacked bar, tick, area, and line charts. The value is
-        either horizontal (default) or vertical.
-
-
-        * For bar, rule and tick, this determines whether the size of the bar and tick
-          should be applied to x or y dimension.
-        * For area, this property determines the orient property of the Vega output.
-        * For line and trail marks, this property determines the sort order of the points in
-          the line if ``config.sortLineBy`` is not specified. For stacked charts, this is
-          always determined by the orientation of the stack; therefore explicitly specified
-          value will be ignored.
-    outerRadius : anyOf(float, :class:`ExprRef`)
-        The outer radius in pixels of arc marks. ``outerRadius`` is an alias for ``radius``.
-
-        **Default value:** ``0``
-    padAngle : anyOf(float, :class:`ExprRef`)
-        The angular padding applied to sides of the arc, in radians.
-    radius : anyOf(float, :class:`ExprRef`)
-        For arc mark, the primary (outer) radius in pixels.
-
-        For text marks, polar coordinate radial offset, in pixels, of the text from the
-        origin determined by the ``x`` and ``y`` properties.
-
-        **Default value:** ``min(plot_width, plot_height)/2``
-    radius2 : anyOf(float, :class:`ExprRef`)
-        The secondary (inner) radius in pixels of arc marks.
-
-        **Default value:** ``0``
-    shape : anyOf(anyOf(:class:`SymbolShape`, string), :class:`ExprRef`)
-        Shape of the point marks. Supported values include:
-
-
-        * plotting shapes: ``"circle"``, ``"square"``, ``"cross"``, ``"diamond"``,
-          ``"triangle-up"``, ``"triangle-down"``, ``"triangle-right"``, or
-          ``"triangle-left"``.
-        * the line symbol ``"stroke"``
-        * centered directional shapes ``"arrow"``, ``"wedge"``, or ``"triangle"``
-        * a custom `SVG path string
-          <https://developer.mozilla.org/en-US/docs/Web/SVG/Tutorial/Paths>`__ (For correct
-          sizing, custom shape paths should be defined within a square bounding box with
-          coordinates ranging from -1 to 1 along both the x and y dimensions.)
-
-        **Default value:** ``"circle"``
-    size : anyOf(float, :class:`ExprRef`)
-        Default size for marks.
-
-
-        * For ``point`` / ``circle`` / ``square``, this represents the pixel area of the
-          marks. Note that this value sets the area of the symbol; the side lengths will
-          increase with the square root of this value.
-        * For ``bar``, this represents the band size of the bar, in pixels.
-        * For ``text``, this represents the font size, in pixels.
-
-        **Default value:**
-
-
-        * ``30`` for point, circle, square marks; width/height's ``step``
-        * ``2`` for bar marks with discrete dimensions;
-        * ``5`` for bar marks with continuous dimensions;
-        * ``11`` for text marks.
-    smooth : anyOf(boolean, :class:`ExprRef`)
-        A boolean flag (default true) indicating if the image should be smoothed when
-        resized. If false, individual pixels should be scaled directly rather than
-        interpolated with smoothing. For SVG rendering, this option may not work in some
-        browsers due to lack of standardization.
-    startAngle : anyOf(float, :class:`ExprRef`)
-        The start angle in radians for arc marks. A value of ``0`` indicates up (north),
-        increasing values proceed clockwise.
-    stroke : anyOf(:class:`Color`, :class:`Gradient`, None, :class:`ExprRef`)
-        Default stroke color. This property has higher precedence than ``config.color``. Set
-        to ``null`` to remove stroke.
-
-        **Default value:** (None)
-    strokeCap : anyOf(:class:`StrokeCap`, :class:`ExprRef`)
-        The stroke cap for line ending style. One of ``"butt"``, ``"round"``, or
-        ``"square"``.
-
-        **Default value:** ``"butt"``
-    strokeDash : anyOf(List(float), :class:`ExprRef`)
-        An array of alternating stroke, space lengths for creating dashed or dotted lines.
-    strokeDashOffset : anyOf(float, :class:`ExprRef`)
-        The offset (in pixels) into which to begin drawing with the stroke dash array.
-    strokeJoin : anyOf(:class:`StrokeJoin`, :class:`ExprRef`)
-        The stroke line join method. One of ``"miter"``, ``"round"`` or ``"bevel"``.
-
-        **Default value:** ``"miter"``
-    strokeMiterLimit : anyOf(float, :class:`ExprRef`)
-        The miter limit at which to bevel a line join.
-    strokeOffset : anyOf(float, :class:`ExprRef`)
-        The offset in pixels at which to draw the group stroke and fill. If unspecified, the
-        default behavior is to dynamically offset stroked groups such that 1 pixel stroke
-        widths align with the pixel grid.
-    strokeOpacity : anyOf(float, :class:`ExprRef`)
-        The stroke opacity (value between [0,1]).
-
-        **Default value:** ``1``
-    strokeWidth : anyOf(float, :class:`ExprRef`)
-        The stroke width, in pixels.
-    tension : anyOf(float, :class:`ExprRef`)
-        Depending on the interpolation type, sets the tension parameter (for line and area
-        marks).
-    text : anyOf(:class:`Text`, :class:`ExprRef`)
-        Placeholder text if the ``text`` channel is not specified
-    theta : anyOf(float, :class:`ExprRef`)
-        For arc marks, the arc length in radians if theta2 is not specified, otherwise the
-        start arc angle. (A value of 0 indicates up or “north”, increasing values proceed
-        clockwise.)
-
-        For text marks, polar coordinate angle in radians.
-    theta2 : anyOf(float, :class:`ExprRef`)
-        The end angle of arc marks in radians. A value of 0 indicates up or “north”,
-        increasing values proceed clockwise.
-    timeUnitBandPosition : float
-        Default relative band position for a time unit. If set to ``0``, the marks will be
-        positioned at the beginning of the time unit band step. If set to ``0.5``, the marks
-        will be positioned in the middle of the time unit band step.
-    timeUnitBandSize : float
-        Default relative band size for a time unit. If set to ``1``, the bandwidth of the
-        marks will be equal to the time unit band step. If set to ``0.5``, bandwidth of the
-        marks will be half of the time unit band step.
-    tooltip : anyOf(float, string, boolean, :class:`TooltipContent`, :class:`ExprRef`, None)
-        The tooltip text string to show upon mouse hover or an object defining which fields
-        should the tooltip be derived from.
-
-
-        * If ``tooltip`` is ``true`` or ``{"content": "encoding"}``, then all fields from
-          ``encoding`` will be used.
-        * If ``tooltip`` is ``{"content": "data"}``, then all fields that appear in the
-          highlighted data point will be used.
-        * If set to ``null`` or ``false``, then no tooltip will be used.
-
-        See the `tooltip <https://vega.github.io/vega-lite/docs/tooltip.html>`__
-        documentation for a detailed discussion about tooltip  in Vega-Lite.
-
-        **Default value:** ``null``
-    url : anyOf(:class:`URI`, :class:`ExprRef`)
-        The URL of the image file for image marks.
-    width : anyOf(float, :class:`ExprRef`)
-        Width of the marks.
-    x : anyOf(float, string, :class:`ExprRef`)
-        X coordinates of the marks, or width of horizontal ``"bar"`` and ``"area"`` without
-        specified ``x2`` or ``width``.
-
-        The ``value`` of this channel can be a number or a string ``"width"`` for the width
-        of the plot.
-    x2 : anyOf(float, string, :class:`ExprRef`)
-        X2 coordinates for ranged ``"area"``, ``"bar"``, ``"rect"``, and  ``"rule"``.
-
-        The ``value`` of this channel can be a number or a string ``"width"`` for the width
-        of the plot.
-    y : anyOf(float, string, :class:`ExprRef`)
-        Y coordinates of the marks, or height of vertical ``"bar"`` and ``"area"`` without
-        specified ``y2`` or ``height``.
-
-        The ``value`` of this channel can be a number or a string ``"height"`` for the
-        height of the plot.
-    y2 : anyOf(float, string, :class:`ExprRef`)
-        Y2 coordinates for ranged ``"area"``, ``"bar"``, ``"rect"``, and  ``"rule"``.
-
-        The ``value`` of this channel can be a number or a string ``"height"`` for the
-        height of the plot.
-    """
-    _schema = {'$ref': '#/definitions/BarConfig'}
-
-    def __init__(self, align=Undefined, angle=Undefined, aria=Undefined, ariaRole=Undefined,
-                 ariaRoleDescription=Undefined, aspect=Undefined, baseline=Undefined,
-                 binSpacing=Undefined, blend=Undefined, color=Undefined, continuousBandSize=Undefined,
-                 cornerRadius=Undefined, cornerRadiusBottomLeft=Undefined,
-                 cornerRadiusBottomRight=Undefined, cornerRadiusEnd=Undefined,
-                 cornerRadiusTopLeft=Undefined, cornerRadiusTopRight=Undefined, cursor=Undefined,
-                 description=Undefined, dir=Undefined, discreteBandSize=Undefined, dx=Undefined,
-                 dy=Undefined, ellipsis=Undefined, endAngle=Undefined, fill=Undefined,
-                 fillOpacity=Undefined, filled=Undefined, font=Undefined, fontSize=Undefined,
-                 fontStyle=Undefined, fontWeight=Undefined, height=Undefined, href=Undefined,
-                 innerRadius=Undefined, interpolate=Undefined, invalid=Undefined, limit=Undefined,
-                 lineBreak=Undefined, lineHeight=Undefined, minBandSize=Undefined, opacity=Undefined,
-                 order=Undefined, orient=Undefined, outerRadius=Undefined, padAngle=Undefined,
-                 radius=Undefined, radius2=Undefined, shape=Undefined, size=Undefined, smooth=Undefined,
-                 startAngle=Undefined, stroke=Undefined, strokeCap=Undefined, strokeDash=Undefined,
-                 strokeDashOffset=Undefined, strokeJoin=Undefined, strokeMiterLimit=Undefined,
-                 strokeOffset=Undefined, strokeOpacity=Undefined, strokeWidth=Undefined,
-                 tension=Undefined, text=Undefined, theta=Undefined, theta2=Undefined,
-                 timeUnitBandPosition=Undefined, timeUnitBandSize=Undefined, tooltip=Undefined,
-                 url=Undefined, width=Undefined, x=Undefined, x2=Undefined, y=Undefined, y2=Undefined,
-                 **kwds):
-        super(BarConfig, self).__init__(align=align, angle=angle, aria=aria, ariaRole=ariaRole,
-                                        ariaRoleDescription=ariaRoleDescription, aspect=aspect,
-                                        baseline=baseline, binSpacing=binSpacing, blend=blend,
-                                        color=color, continuousBandSize=continuousBandSize,
-                                        cornerRadius=cornerRadius,
-                                        cornerRadiusBottomLeft=cornerRadiusBottomLeft,
-                                        cornerRadiusBottomRight=cornerRadiusBottomRight,
-                                        cornerRadiusEnd=cornerRadiusEnd,
-                                        cornerRadiusTopLeft=cornerRadiusTopLeft,
-                                        cornerRadiusTopRight=cornerRadiusTopRight, cursor=cursor,
-                                        description=description, dir=dir,
-                                        discreteBandSize=discreteBandSize, dx=dx, dy=dy,
-                                        ellipsis=ellipsis, endAngle=endAngle, fill=fill,
-                                        fillOpacity=fillOpacity, filled=filled, font=font,
-                                        fontSize=fontSize, fontStyle=fontStyle, fontWeight=fontWeight,
-                                        height=height, href=href, innerRadius=innerRadius,
-                                        interpolate=interpolate, invalid=invalid, limit=limit,
-                                        lineBreak=lineBreak, lineHeight=lineHeight,
-                                        minBandSize=minBandSize, opacity=opacity, order=order,
-                                        orient=orient, outerRadius=outerRadius, padAngle=padAngle,
-                                        radius=radius, radius2=radius2, shape=shape, size=size,
-                                        smooth=smooth, startAngle=startAngle, stroke=stroke,
-                                        strokeCap=strokeCap, strokeDash=strokeDash,
-                                        strokeDashOffset=strokeDashOffset, strokeJoin=strokeJoin,
-                                        strokeMiterLimit=strokeMiterLimit, strokeOffset=strokeOffset,
-                                        strokeOpacity=strokeOpacity, strokeWidth=strokeWidth,
-                                        tension=tension, text=text, theta=theta, theta2=theta2,
-                                        timeUnitBandPosition=timeUnitBandPosition,
-                                        timeUnitBandSize=timeUnitBandSize, tooltip=tooltip, url=url,
-                                        width=width, x=x, x2=x2, y=y, y2=y2, **kwds)
-
-
-class BaseTitleNoValueRefs(VegaLiteSchema):
-    """BaseTitleNoValueRefs schema wrapper
-
-    Mapping(required=[])
-
-    Parameters
-    ----------
-
-    align : :class:`Align`
-        Horizontal text alignment for title text. One of ``"left"``, ``"center"``, or
-        ``"right"``.
-    anchor : anyOf(:class:`TitleAnchor`, :class:`ExprRef`)
-        The anchor position for placing the title and subtitle text. One of ``"start"``,
-        ``"middle"``, or ``"end"``. For example, with an orientation of top these anchor
-        positions map to a left-, center-, or right-aligned title.
-    angle : anyOf(float, :class:`ExprRef`)
-        Angle in degrees of title and subtitle text.
-    aria : anyOf(boolean, :class:`ExprRef`)
-        A boolean flag indicating if `ARIA attributes
-        <https://developer.mozilla.org/en-US/docs/Web/Accessibility/ARIA>`__ should be
-        included (SVG output only). If ``false``, the "aria-hidden" attribute will be set on
-        the output SVG group, removing the title from the ARIA accessibility tree.
-
-        **Default value:** ``true``
-    baseline : :class:`TextBaseline`
-        Vertical text baseline for title and subtitle text. One of ``"alphabetic"``
-        (default), ``"top"``, ``"middle"``, ``"bottom"``, ``"line-top"``, or
-        ``"line-bottom"``. The ``"line-top"`` and ``"line-bottom"`` values operate similarly
-        to ``"top"`` and ``"bottom"``, but are calculated relative to the *lineHeight*
-        rather than *fontSize* alone.
-    color : anyOf(anyOf(None, :class:`Color`), :class:`ExprRef`)
-        Text color for title text.
-    dx : anyOf(float, :class:`ExprRef`)
-        Delta offset for title and subtitle text x-coordinate.
-    dy : anyOf(float, :class:`ExprRef`)
-        Delta offset for title and subtitle text y-coordinate.
-    font : anyOf(string, :class:`ExprRef`)
-        Font name for title text.
-    fontSize : anyOf(float, :class:`ExprRef`)
-        Font size in pixels for title text.
-    fontStyle : anyOf(:class:`FontStyle`, :class:`ExprRef`)
-        Font style for title text.
-    fontWeight : anyOf(:class:`FontWeight`, :class:`ExprRef`)
-        Font weight for title text. This can be either a string (e.g ``"bold"``,
-        ``"normal"`` ) or a number ( ``100``, ``200``, ``300``, ..., ``900`` where
-        ``"normal"`` = ``400`` and ``"bold"`` = ``700`` ).
-    frame : anyOf(anyOf(:class:`TitleFrame`, string), :class:`ExprRef`)
-        The reference frame for the anchor position, one of ``"bounds"`` (to anchor relative
-        to the full bounding box) or ``"group"`` (to anchor relative to the group width or
-        height).
-    limit : anyOf(float, :class:`ExprRef`)
-        The maximum allowed length in pixels of title and subtitle text.
-    lineHeight : anyOf(float, :class:`ExprRef`)
-        Line height in pixels for multi-line title text or title text with ``"line-top"`` or
-        ``"line-bottom"`` baseline.
-    offset : anyOf(float, :class:`ExprRef`)
-        The orthogonal offset in pixels by which to displace the title group from its
-        position along the edge of the chart.
-    orient : anyOf(:class:`TitleOrient`, :class:`ExprRef`)
-        Default title orientation ( ``"top"``, ``"bottom"``, ``"left"``, or ``"right"`` )
-    subtitleColor : anyOf(anyOf(None, :class:`Color`), :class:`ExprRef`)
-        Text color for subtitle text.
-    subtitleFont : anyOf(string, :class:`ExprRef`)
-        Font name for subtitle text.
-    subtitleFontSize : anyOf(float, :class:`ExprRef`)
-        Font size in pixels for subtitle text.
-    subtitleFontStyle : anyOf(:class:`FontStyle`, :class:`ExprRef`)
-        Font style for subtitle text.
-    subtitleFontWeight : anyOf(:class:`FontWeight`, :class:`ExprRef`)
-        Font weight for subtitle text. This can be either a string (e.g ``"bold"``,
-        ``"normal"`` ) or a number ( ``100``, ``200``, ``300``, ..., ``900`` where
-        ``"normal"`` = ``400`` and ``"bold"`` = ``700`` ).
-    subtitleLineHeight : anyOf(float, :class:`ExprRef`)
-        Line height in pixels for multi-line subtitle text.
-    subtitlePadding : anyOf(float, :class:`ExprRef`)
-        The padding in pixels between title and subtitle text.
-    zindex : anyOf(float, :class:`ExprRef`)
-        The integer z-index indicating the layering of the title group relative to other
-        axis, mark, and legend groups.
-
-        **Default value:** ``0``.
-    """
-    _schema = {'$ref': '#/definitions/BaseTitleNoValueRefs'}
-
-    def __init__(self, align=Undefined, anchor=Undefined, angle=Undefined, aria=Undefined,
-                 baseline=Undefined, color=Undefined, dx=Undefined, dy=Undefined, font=Undefined,
-                 fontSize=Undefined, fontStyle=Undefined, fontWeight=Undefined, frame=Undefined,
-                 limit=Undefined, lineHeight=Undefined, offset=Undefined, orient=Undefined,
-                 subtitleColor=Undefined, subtitleFont=Undefined, subtitleFontSize=Undefined,
-                 subtitleFontStyle=Undefined, subtitleFontWeight=Undefined,
-                 subtitleLineHeight=Undefined, subtitlePadding=Undefined, zindex=Undefined, **kwds):
-        super(BaseTitleNoValueRefs, self).__init__(align=align, anchor=anchor, angle=angle, aria=aria,
-                                                   baseline=baseline, color=color, dx=dx, dy=dy,
-                                                   font=font, fontSize=fontSize, fontStyle=fontStyle,
-                                                   fontWeight=fontWeight, frame=frame, limit=limit,
-                                                   lineHeight=lineHeight, offset=offset, orient=orient,
-                                                   subtitleColor=subtitleColor,
-                                                   subtitleFont=subtitleFont,
-                                                   subtitleFontSize=subtitleFontSize,
-                                                   subtitleFontStyle=subtitleFontStyle,
-                                                   subtitleFontWeight=subtitleFontWeight,
-                                                   subtitleLineHeight=subtitleLineHeight,
-                                                   subtitlePadding=subtitlePadding, zindex=zindex,
-                                                   **kwds)
-
-
-class BinExtent(VegaLiteSchema):
-    """BinExtent schema wrapper
-
-    anyOf(List(float), :class:`ParameterExtent`)
-    """
-    _schema = {'$ref': '#/definitions/BinExtent'}
-
-    def __init__(self, *args, **kwds):
-        super(BinExtent, self).__init__(*args, **kwds)
-
-
-class BinParams(VegaLiteSchema):
-    """BinParams schema wrapper
-
-    Mapping(required=[])
-    Binning properties or boolean flag for determining whether to bin data or not.
-
-    Parameters
-    ----------
-
-    anchor : float
-        A value in the binned domain at which to anchor the bins, shifting the bin
-        boundaries if necessary to ensure that a boundary aligns with the anchor value.
-
-        **Default value:** the minimum bin extent value
-    base : float
-        The number base to use for automatic bin determination (default is base 10).
-
-        **Default value:** ``10``
-    binned : boolean
-        When set to ``true``, Vega-Lite treats the input data as already binned.
-    divide : List(float)
-        Scale factors indicating allowable subdivisions. The default value is [5, 2], which
-        indicates that for base 10 numbers (the default base), the method may consider
-        dividing bin sizes by 5 and/or 2. For example, for an initial step size of 10, the
-        method can check if bin sizes of 2 (= 10/5), 5 (= 10/2), or 1 (= 10/(5*2)) might
-        also satisfy the given constraints.
-
-        **Default value:** ``[5, 2]``
-    extent : :class:`BinExtent`
-        A two-element ( ``[min, max]`` ) array indicating the range of desired bin values.
-    maxbins : float
-        Maximum number of bins.
-
-        **Default value:** ``6`` for ``row``, ``column`` and ``shape`` channels; ``10`` for
-        other channels
-    minstep : float
-        A minimum allowable step size (particularly useful for integer values).
-    nice : boolean
-        If true, attempts to make the bin boundaries use human-friendly boundaries, such as
-        multiples of ten.
-
-        **Default value:** ``true``
-    step : float
-        An exact step size to use between bins.
-
-        **Note:** If provided, options such as maxbins will be ignored.
-    steps : List(float)
-        An array of allowable step sizes to choose from.
-    """
-    _schema = {'$ref': '#/definitions/BinParams'}
-
-    def __init__(self, anchor=Undefined, base=Undefined, binned=Undefined, divide=Undefined,
-                 extent=Undefined, maxbins=Undefined, minstep=Undefined, nice=Undefined, step=Undefined,
-                 steps=Undefined, **kwds):
-        super(BinParams, self).__init__(anchor=anchor, base=base, binned=binned, divide=divide,
-                                        extent=extent, maxbins=maxbins, minstep=minstep, nice=nice,
-                                        step=step, steps=steps, **kwds)
-
-
-class Binding(VegaLiteSchema):
-    """Binding schema wrapper
-
-    anyOf(:class:`BindCheckbox`, :class:`BindRadioSelect`, :class:`BindRange`,
-    :class:`BindInput`, :class:`BindDirect`)
-    """
-    _schema = {'$ref': '#/definitions/Binding'}
-
-    def __init__(self, *args, **kwds):
-        super(Binding, self).__init__(*args, **kwds)
-
-
-class BindCheckbox(Binding):
-    """BindCheckbox schema wrapper
-
-    Mapping(required=[input])
-
-    Parameters
-    ----------
-
-    input : string
-
-    debounce : float
-        If defined, delays event handling until the specified milliseconds have elapsed
-        since the last event was fired.
-    element : :class:`Element`
-        An optional CSS selector string indicating the parent element to which the input
-        element should be added. By default, all input elements are added within the parent
-        container of the Vega view.
-    name : string
-        By default, the signal name is used to label input elements. This ``name`` property
-        can be used instead to specify a custom label for the bound signal.
-    """
-    _schema = {'$ref': '#/definitions/BindCheckbox'}
-
-    def __init__(self, input=Undefined, debounce=Undefined, element=Undefined, name=Undefined, **kwds):
-        super(BindCheckbox, self).__init__(input=input, debounce=debounce, element=element, name=name,
-                                           **kwds)
-
-
-class BindDirect(Binding):
-    """BindDirect schema wrapper
-
-    Mapping(required=[element])
-
-    Parameters
-    ----------
-
-    element : anyOf(:class:`Element`, Mapping(required=[]))
-        An input element that exposes a *value* property and supports the `EventTarget
-        <https://developer.mozilla.org/en-US/docs/Web/API/EventTarget>`__ interface, or a
-        CSS selector string to such an element. When the element updates and dispatches an
-        event, the *value* property will be used as the new, bound signal value. When the
-        signal updates independent of the element, the *value* property will be set to the
-        signal value and a new event will be dispatched on the element.
-    debounce : float
-        If defined, delays event handling until the specified milliseconds have elapsed
-        since the last event was fired.
-    event : string
-        The event (default ``"input"`` ) to listen for to track changes on the external
-        element.
-    """
-    _schema = {'$ref': '#/definitions/BindDirect'}
-
-    def __init__(self, element=Undefined, debounce=Undefined, event=Undefined, **kwds):
-        super(BindDirect, self).__init__(element=element, debounce=debounce, event=event, **kwds)
-
-
-class BindInput(Binding):
-    """BindInput schema wrapper
-
-    Mapping(required=[])
-
-    Parameters
-    ----------
-
-    autocomplete : string
-        A hint for form autofill. See the `HTML autocomplete attribute
-        <https://developer.mozilla.org/en-US/docs/Web/HTML/Attributes/autocomplete>`__ for
-        additional information.
-    debounce : float
-        If defined, delays event handling until the specified milliseconds have elapsed
-        since the last event was fired.
-    element : :class:`Element`
-        An optional CSS selector string indicating the parent element to which the input
-        element should be added. By default, all input elements are added within the parent
-        container of the Vega view.
-    input : string
-        The type of input element to use. The valid values are ``"checkbox"``, ``"radio"``,
-        ``"range"``, ``"select"``, and any other legal `HTML form input type
-        <https://developer.mozilla.org/en-US/docs/Web/HTML/Element/input>`__.
-    name : string
-        By default, the signal name is used to label input elements. This ``name`` property
-        can be used instead to specify a custom label for the bound signal.
-    placeholder : string
-        Text that appears in the form control when it has no value set.
-    """
-    _schema = {'$ref': '#/definitions/BindInput'}
-
-    def __init__(self, autocomplete=Undefined, debounce=Undefined, element=Undefined, input=Undefined,
-                 name=Undefined, placeholder=Undefined, **kwds):
-        super(BindInput, self).__init__(autocomplete=autocomplete, debounce=debounce, element=element,
-                                        input=input, name=name, placeholder=placeholder, **kwds)
-
-
-class BindRadioSelect(Binding):
-    """BindRadioSelect schema wrapper
-
-    Mapping(required=[input, options])
-
-    Parameters
-    ----------
-
-    input : enum('radio', 'select')
-
-    options : List(Any)
-        An array of options to select from.
-    debounce : float
-        If defined, delays event handling until the specified milliseconds have elapsed
-        since the last event was fired.
-    element : :class:`Element`
-        An optional CSS selector string indicating the parent element to which the input
-        element should be added. By default, all input elements are added within the parent
-        container of the Vega view.
-    labels : List(string)
-        An array of label strings to represent the ``options`` values. If unspecified, the
-        ``options`` value will be coerced to a string and used as the label.
-    name : string
-        By default, the signal name is used to label input elements. This ``name`` property
-        can be used instead to specify a custom label for the bound signal.
-    """
-    _schema = {'$ref': '#/definitions/BindRadioSelect'}
-
-    def __init__(self, input=Undefined, options=Undefined, debounce=Undefined, element=Undefined,
-                 labels=Undefined, name=Undefined, **kwds):
-        super(BindRadioSelect, self).__init__(input=input, options=options, debounce=debounce,
-                                              element=element, labels=labels, name=name, **kwds)
-
-
-class BindRange(Binding):
-    """BindRange schema wrapper
-
-    Mapping(required=[input])
-
-    Parameters
-    ----------
-
-    input : string
-
-    debounce : float
-        If defined, delays event handling until the specified milliseconds have elapsed
-        since the last event was fired.
-    element : :class:`Element`
-        An optional CSS selector string indicating the parent element to which the input
-        element should be added. By default, all input elements are added within the parent
-        container of the Vega view.
-    max : float
-        Sets the maximum slider value. Defaults to the larger of the signal value and
-        ``100``.
-    min : float
-        Sets the minimum slider value. Defaults to the smaller of the signal value and
-        ``0``.
-    name : string
-        By default, the signal name is used to label input elements. This ``name`` property
-        can be used instead to specify a custom label for the bound signal.
-    step : float
-        Sets the minimum slider increment. If undefined, the step size will be automatically
-        determined based on the ``min`` and ``max`` values.
-    """
-    _schema = {'$ref': '#/definitions/BindRange'}
-
-    def __init__(self, input=Undefined, debounce=Undefined, element=Undefined, max=Undefined,
-                 min=Undefined, name=Undefined, step=Undefined, **kwds):
-        super(BindRange, self).__init__(input=input, debounce=debounce, element=element, max=max,
-                                        min=min, name=name, step=step, **kwds)
-
-
-class BinnedTimeUnit(VegaLiteSchema):
-    """BinnedTimeUnit schema wrapper
-
-    anyOf(enum('binnedyear', 'binnedyearquarter', 'binnedyearquartermonth', 'binnedyearmonth',
-    'binnedyearmonthdate', 'binnedyearmonthdatehours', 'binnedyearmonthdatehoursminutes',
-    'binnedyearmonthdatehoursminutesseconds', 'binnedyearweek', 'binnedyearweekday',
-    'binnedyearweekdayhours', 'binnedyearweekdayhoursminutes',
-    'binnedyearweekdayhoursminutesseconds', 'binnedyeardayofyear'), enum('binnedutcyear',
-    'binnedutcyearquarter', 'binnedutcyearquartermonth', 'binnedutcyearmonth',
-    'binnedutcyearmonthdate', 'binnedutcyearmonthdatehours',
-    'binnedutcyearmonthdatehoursminutes', 'binnedutcyearmonthdatehoursminutesseconds',
-    'binnedutcyearweek', 'binnedutcyearweekday', 'binnedutcyearweekdayhours',
-    'binnedutcyearweekdayhoursminutes', 'binnedutcyearweekdayhoursminutesseconds',
-    'binnedutcyeardayofyear'))
-    """
-    _schema = {'$ref': '#/definitions/BinnedTimeUnit'}
-
-    def __init__(self, *args, **kwds):
-        super(BinnedTimeUnit, self).__init__(*args, **kwds)
-
-
-class Blend(VegaLiteSchema):
-    """Blend schema wrapper
-
-    enum(None, 'multiply', 'screen', 'overlay', 'darken', 'lighten', 'color-dodge',
-    'color-burn', 'hard-light', 'soft-light', 'difference', 'exclusion', 'hue', 'saturation',
-    'color', 'luminosity')
-    """
-    _schema = {'$ref': '#/definitions/Blend'}
-
-    def __init__(self, *args):
-        super(Blend, self).__init__(*args)
-
-
-class BoxPlotConfig(VegaLiteSchema):
-    """BoxPlotConfig schema wrapper
-
-    Mapping(required=[])
-
-    Parameters
-    ----------
-
-    box : anyOf(boolean, :class:`AnyMarkConfig`)
-
-    extent : anyOf(string, float)
-        The extent of the whiskers. Available options include:
-
-
-        * ``"min-max"`` : min and max are the lower and upper whiskers respectively.
-        * A number representing multiple of the interquartile range. This number will be
-          multiplied by the IQR to determine whisker boundary, which spans from the smallest
-          data to the largest data within the range *[Q1 - k * IQR, Q3 + k * IQR]* where
-          *Q1* and *Q3* are the first and third quartiles while *IQR* is the interquartile
-          range ( *Q3-Q1* ).
-
-        **Default value:** ``1.5``.
-    median : anyOf(boolean, :class:`AnyMarkConfig`)
-
-    outliers : anyOf(boolean, :class:`AnyMarkConfig`)
-
-    rule : anyOf(boolean, :class:`AnyMarkConfig`)
-
-    size : float
-        Size of the box and median tick of a box plot
-    ticks : anyOf(boolean, :class:`AnyMarkConfig`)
-
-    """
-    _schema = {'$ref': '#/definitions/BoxPlotConfig'}
-
-    def __init__(self, box=Undefined, extent=Undefined, median=Undefined, outliers=Undefined,
-                 rule=Undefined, size=Undefined, ticks=Undefined, **kwds):
-        super(BoxPlotConfig, self).__init__(box=box, extent=extent, median=median, outliers=outliers,
-                                            rule=rule, size=size, ticks=ticks, **kwds)
-
-
-class BrushConfig(VegaLiteSchema):
-    """BrushConfig schema wrapper
-
-    Mapping(required=[])
-
-    Parameters
-    ----------
-
-    cursor : :class:`Cursor`
-        The mouse cursor used over the interval mark. Any valid `CSS cursor type
-        <https://developer.mozilla.org/en-US/docs/Web/CSS/cursor#Values>`__ can be used.
-    fill : :class:`Color`
-        The fill color of the interval mark.
-
-        **Default value:** ``"#333333"``
-    fillOpacity : float
-        The fill opacity of the interval mark (a value between ``0`` and ``1`` ).
-
-        **Default value:** ``0.125``
-    stroke : :class:`Color`
-        The stroke color of the interval mark.
-
-        **Default value:** ``"#ffffff"``
-    strokeDash : List(float)
-        An array of alternating stroke and space lengths, for creating dashed or dotted
-        lines.
-    strokeDashOffset : float
-        The offset (in pixels) with which to begin drawing the stroke dash array.
-    strokeOpacity : float
-        The stroke opacity of the interval mark (a value between ``0`` and ``1`` ).
-    strokeWidth : float
-        The stroke width of the interval mark.
-    """
-    _schema = {'$ref': '#/definitions/BrushConfig'}
-
-    def __init__(self, cursor=Undefined, fill=Undefined, fillOpacity=Undefined, stroke=Undefined,
-                 strokeDash=Undefined, strokeDashOffset=Undefined, strokeOpacity=Undefined,
-                 strokeWidth=Undefined, **kwds):
-        super(BrushConfig, self).__init__(cursor=cursor, fill=fill, fillOpacity=fillOpacity,
-                                          stroke=stroke, strokeDash=strokeDash,
-                                          strokeDashOffset=strokeDashOffset,
-                                          strokeOpacity=strokeOpacity, strokeWidth=strokeWidth, **kwds)
-
-
-class Color(VegaLiteSchema):
-    """Color schema wrapper
-
-    anyOf(:class:`ColorName`, :class:`HexColor`, string)
-    """
-    _schema = {'$ref': '#/definitions/Color'}
-
-    def __init__(self, *args, **kwds):
-        super(Color, self).__init__(*args, **kwds)
-
-
-class ColorDef(VegaLiteSchema):
-    """ColorDef schema wrapper
-
-    anyOf(:class:`FieldOrDatumDefWithConditionMarkPropFieldDefGradientstringnull`,
-    :class:`FieldOrDatumDefWithConditionDatumDefGradientstringnull`,
-    :class:`ValueDefWithConditionMarkPropFieldOrDatumDefGradientstringnull`)
-    """
-    _schema = {'$ref': '#/definitions/ColorDef'}
-
-    def __init__(self, *args, **kwds):
-        super(ColorDef, self).__init__(*args, **kwds)
-
-
-class ColorName(Color):
-    """ColorName schema wrapper
-
-    enum('black', 'silver', 'gray', 'white', 'maroon', 'red', 'purple', 'fuchsia', 'green',
-    'lime', 'olive', 'yellow', 'navy', 'blue', 'teal', 'aqua', 'orange', 'aliceblue',
-    'antiquewhite', 'aquamarine', 'azure', 'beige', 'bisque', 'blanchedalmond', 'blueviolet',
-    'brown', 'burlywood', 'cadetblue', 'chartreuse', 'chocolate', 'coral', 'cornflowerblue',
-    'cornsilk', 'crimson', 'cyan', 'darkblue', 'darkcyan', 'darkgoldenrod', 'darkgray',
-    'darkgreen', 'darkgrey', 'darkkhaki', 'darkmagenta', 'darkolivegreen', 'darkorange',
-    'darkorchid', 'darkred', 'darksalmon', 'darkseagreen', 'darkslateblue', 'darkslategray',
-    'darkslategrey', 'darkturquoise', 'darkviolet', 'deeppink', 'deepskyblue', 'dimgray',
-    'dimgrey', 'dodgerblue', 'firebrick', 'floralwhite', 'forestgreen', 'gainsboro',
-    'ghostwhite', 'gold', 'goldenrod', 'greenyellow', 'grey', 'honeydew', 'hotpink',
-    'indianred', 'indigo', 'ivory', 'khaki', 'lavender', 'lavenderblush', 'lawngreen',
-    'lemonchiffon', 'lightblue', 'lightcoral', 'lightcyan', 'lightgoldenrodyellow', 'lightgray',
-    'lightgreen', 'lightgrey', 'lightpink', 'lightsalmon', 'lightseagreen', 'lightskyblue',
-    'lightslategray', 'lightslategrey', 'lightsteelblue', 'lightyellow', 'limegreen', 'linen',
-    'magenta', 'mediumaquamarine', 'mediumblue', 'mediumorchid', 'mediumpurple',
-    'mediumseagreen', 'mediumslateblue', 'mediumspringgreen', 'mediumturquoise',
-    'mediumvioletred', 'midnightblue', 'mintcream', 'mistyrose', 'moccasin', 'navajowhite',
-    'oldlace', 'olivedrab', 'orangered', 'orchid', 'palegoldenrod', 'palegreen',
-    'paleturquoise', 'palevioletred', 'papayawhip', 'peachpuff', 'peru', 'pink', 'plum',
-    'powderblue', 'rosybrown', 'royalblue', 'saddlebrown', 'salmon', 'sandybrown', 'seagreen',
-    'seashell', 'sienna', 'skyblue', 'slateblue', 'slategray', 'slategrey', 'snow',
-    'springgreen', 'steelblue', 'tan', 'thistle', 'tomato', 'turquoise', 'violet', 'wheat',
-    'whitesmoke', 'yellowgreen', 'rebeccapurple')
-    """
-    _schema = {'$ref': '#/definitions/ColorName'}
-
-    def __init__(self, *args):
-        super(ColorName, self).__init__(*args)
-
-
-class ColorScheme(VegaLiteSchema):
-    """ColorScheme schema wrapper
-
-    anyOf(:class:`Categorical`, :class:`SequentialSingleHue`, :class:`SequentialMultiHue`,
-    :class:`Diverging`, :class:`Cyclical`)
-    """
-    _schema = {'$ref': '#/definitions/ColorScheme'}
-
-    def __init__(self, *args, **kwds):
-        super(ColorScheme, self).__init__(*args, **kwds)
-
-
-class Categorical(ColorScheme):
-    """Categorical schema wrapper
-
-    enum('accent', 'category10', 'category20', 'category20b', 'category20c', 'dark2', 'paired',
-    'pastel1', 'pastel2', 'set1', 'set2', 'set3', 'tableau10', 'tableau20')
-    """
-    _schema = {'$ref': '#/definitions/Categorical'}
-
-    def __init__(self, *args):
-        super(Categorical, self).__init__(*args)
-
-
-class CompositeMark(AnyMark):
-    """CompositeMark schema wrapper
-
-    anyOf(:class:`BoxPlot`, :class:`ErrorBar`, :class:`ErrorBand`)
-    """
-    _schema = {'$ref': '#/definitions/CompositeMark'}
-
-    def __init__(self, *args, **kwds):
-        super(CompositeMark, self).__init__(*args, **kwds)
-
-
-class BoxPlot(CompositeMark):
-    """BoxPlot schema wrapper
-
-    string
-    """
-    _schema = {'$ref': '#/definitions/BoxPlot'}
-
-    def __init__(self, *args):
-        super(BoxPlot, self).__init__(*args)
-
-
-class CompositeMarkDef(AnyMark):
-    """CompositeMarkDef schema wrapper
-
-    anyOf(:class:`BoxPlotDef`, :class:`ErrorBarDef`, :class:`ErrorBandDef`)
-    """
-    _schema = {'$ref': '#/definitions/CompositeMarkDef'}
-
-    def __init__(self, *args, **kwds):
-        super(CompositeMarkDef, self).__init__(*args, **kwds)
-
-
-class BoxPlotDef(CompositeMarkDef):
-    """BoxPlotDef schema wrapper
-
-    Mapping(required=[type])
-
-    Parameters
-    ----------
-
-    type : :class:`BoxPlot`
-        The mark type. This could a primitive mark type (one of ``"bar"``, ``"circle"``,
-        ``"square"``, ``"tick"``, ``"line"``, ``"area"``, ``"point"``, ``"geoshape"``,
-        ``"rule"``, and ``"text"`` ) or a composite mark type ( ``"boxplot"``,
-        ``"errorband"``, ``"errorbar"`` ).
-    box : anyOf(boolean, :class:`AnyMarkConfig`)
-
-    clip : boolean
-        Whether a composite mark be clipped to the enclosing group’s width and height.
-    color : anyOf(:class:`Color`, :class:`Gradient`, :class:`ExprRef`)
-        Default color.
-
-        **Default value:** :raw-html:`<span style="color: #4682b4;">&#9632;</span>`
-        ``"#4682b4"``
-
-        **Note:**
-
-
-        * This property cannot be used in a `style config
-          <https://vega.github.io/vega-lite/docs/mark.html#style-config>`__.
-        * The ``fill`` and ``stroke`` properties have higher precedence than ``color`` and
-          will override ``color``.
-    extent : anyOf(string, float)
-        The extent of the whiskers. Available options include:
-
-
-        * ``"min-max"`` : min and max are the lower and upper whiskers respectively.
-        * A number representing multiple of the interquartile range. This number will be
-          multiplied by the IQR to determine whisker boundary, which spans from the smallest
-          data to the largest data within the range *[Q1 - k * IQR, Q3 + k * IQR]* where
-          *Q1* and *Q3* are the first and third quartiles while *IQR* is the interquartile
-          range ( *Q3-Q1* ).
-
-        **Default value:** ``1.5``.
-    invalid : enum('filter', None)
-        Defines how Vega-Lite should handle marks for invalid values ( ``null`` and ``NaN``
-        ).
-
-
-        * If set to ``"filter"`` (default), all data items with null values will be skipped
-          (for line, trail, and area marks) or filtered (for other marks).
-        * If ``null``, all data items are included. In this case, invalid values will be
-          interpreted as zeroes.
-    median : anyOf(boolean, :class:`AnyMarkConfig`)
-
-    opacity : float
-        The opacity (value between [0,1]) of the mark.
-    orient : :class:`Orientation`
-        Orientation of the box plot. This is normally automatically determined based on
-        types of fields on x and y channels. However, an explicit ``orient`` be specified
-        when the orientation is ambiguous.
-
-        **Default value:** ``"vertical"``.
-    outliers : anyOf(boolean, :class:`AnyMarkConfig`)
-
-    rule : anyOf(boolean, :class:`AnyMarkConfig`)
-
-    size : float
-        Size of the box and median tick of a box plot
-    ticks : anyOf(boolean, :class:`AnyMarkConfig`)
-
-    """
-    _schema = {'$ref': '#/definitions/BoxPlotDef'}
-
-    def __init__(self, type=Undefined, box=Undefined, clip=Undefined, color=Undefined, extent=Undefined,
-                 invalid=Undefined, median=Undefined, opacity=Undefined, orient=Undefined,
-                 outliers=Undefined, rule=Undefined, size=Undefined, ticks=Undefined, **kwds):
-        super(BoxPlotDef, self).__init__(type=type, box=box, clip=clip, color=color, extent=extent,
-                                         invalid=invalid, median=median, opacity=opacity, orient=orient,
-                                         outliers=outliers, rule=rule, size=size, ticks=ticks, **kwds)
-
-
-class CompositionConfig(VegaLiteSchema):
-    """CompositionConfig schema wrapper
-
-    Mapping(required=[])
-
-    Parameters
-    ----------
-
-    columns : float
-        The number of columns to include in the view composition layout.
-
-        **Default value** : ``undefined`` -- An infinite number of columns (a single row)
-        will be assumed. This is equivalent to ``hconcat`` (for ``concat`` ) and to using
-        the ``column`` channel (for ``facet`` and ``repeat`` ).
-
-        **Note** :
-
-        1) This property is only for:
-
-
-        * the general (wrappable) ``concat`` operator (not ``hconcat`` / ``vconcat`` )
-        * the ``facet`` and ``repeat`` operator with one field/repetition definition
-          (without row/column nesting)
-
-        2) Setting the ``columns`` to ``1`` is equivalent to ``vconcat`` (for ``concat`` )
-        and to using the ``row`` channel (for ``facet`` and ``repeat`` ).
-    spacing : float
-        The default spacing in pixels between composed sub-views.
-
-        **Default value** : ``20``
-    """
-    _schema = {'$ref': '#/definitions/CompositionConfig'}
-
-    def __init__(self, columns=Undefined, spacing=Undefined, **kwds):
-        super(CompositionConfig, self).__init__(columns=columns, spacing=spacing, **kwds)
-
-
-class ConditionalAxisColor(VegaLiteSchema):
-    """ConditionalAxisColor schema wrapper
-
-    anyOf(Mapping(required=[condition, value]), Mapping(required=[condition, expr]))
-    """
-    _schema = {'$ref': '#/definitions/ConditionalAxisColor'}
-
-    def __init__(self, *args, **kwds):
-        super(ConditionalAxisColor, self).__init__(*args, **kwds)
-
-
-class ConditionalAxisLabelAlign(VegaLiteSchema):
-    """ConditionalAxisLabelAlign schema wrapper
-
-    anyOf(Mapping(required=[condition, value]), Mapping(required=[condition, expr]))
-    """
-    _schema = {'$ref': '#/definitions/ConditionalAxisLabelAlign'}
-
-    def __init__(self, *args, **kwds):
-        super(ConditionalAxisLabelAlign, self).__init__(*args, **kwds)
-
-
-class ConditionalAxisLabelBaseline(VegaLiteSchema):
-    """ConditionalAxisLabelBaseline schema wrapper
-
-    anyOf(Mapping(required=[condition, value]), Mapping(required=[condition, expr]))
-    """
-    _schema = {'$ref': '#/definitions/ConditionalAxisLabelBaseline'}
-
-    def __init__(self, *args, **kwds):
-        super(ConditionalAxisLabelBaseline, self).__init__(*args, **kwds)
-
-
-class ConditionalAxisLabelFontStyle(VegaLiteSchema):
-    """ConditionalAxisLabelFontStyle schema wrapper
-
-    anyOf(Mapping(required=[condition, value]), Mapping(required=[condition, expr]))
-    """
-    _schema = {'$ref': '#/definitions/ConditionalAxisLabelFontStyle'}
-
-    def __init__(self, *args, **kwds):
-        super(ConditionalAxisLabelFontStyle, self).__init__(*args, **kwds)
-
-
-class ConditionalAxisLabelFontWeight(VegaLiteSchema):
-    """ConditionalAxisLabelFontWeight schema wrapper
-
-    anyOf(Mapping(required=[condition, value]), Mapping(required=[condition, expr]))
-    """
-    _schema = {'$ref': '#/definitions/ConditionalAxisLabelFontWeight'}
-
-    def __init__(self, *args, **kwds):
-        super(ConditionalAxisLabelFontWeight, self).__init__(*args, **kwds)
-
-
-class ConditionalAxisNumber(VegaLiteSchema):
-    """ConditionalAxisNumber schema wrapper
-
-    anyOf(Mapping(required=[condition, value]), Mapping(required=[condition, expr]))
-    """
-    _schema = {'$ref': '#/definitions/ConditionalAxisNumber'}
-
-    def __init__(self, *args, **kwds):
-        super(ConditionalAxisNumber, self).__init__(*args, **kwds)
-
-
-class ConditionalAxisNumberArray(VegaLiteSchema):
-    """ConditionalAxisNumberArray schema wrapper
-
-    anyOf(Mapping(required=[condition, value]), Mapping(required=[condition, expr]))
-    """
-    _schema = {'$ref': '#/definitions/ConditionalAxisNumberArray'}
-
-    def __init__(self, *args, **kwds):
-        super(ConditionalAxisNumberArray, self).__init__(*args, **kwds)
-
-
-class ConditionalAxisPropertyAlignnull(VegaLiteSchema):
-    """ConditionalAxisPropertyAlignnull schema wrapper
-
-    anyOf(Mapping(required=[condition, value]), Mapping(required=[condition, expr]))
-    """
-    _schema = {'$ref': '#/definitions/ConditionalAxisProperty<(Align|null)>'}
-
-    def __init__(self, *args, **kwds):
-        super(ConditionalAxisPropertyAlignnull, self).__init__(*args, **kwds)
-
-
-class ConditionalAxisPropertyColornull(VegaLiteSchema):
-    """ConditionalAxisPropertyColornull schema wrapper
-
-    anyOf(Mapping(required=[condition, value]), Mapping(required=[condition, expr]))
-    """
-    _schema = {'$ref': '#/definitions/ConditionalAxisProperty<(Color|null)>'}
-
-    def __init__(self, *args, **kwds):
-        super(ConditionalAxisPropertyColornull, self).__init__(*args, **kwds)
-
-
-class ConditionalAxisPropertyFontStylenull(VegaLiteSchema):
-    """ConditionalAxisPropertyFontStylenull schema wrapper
-
-    anyOf(Mapping(required=[condition, value]), Mapping(required=[condition, expr]))
-    """
-    _schema = {'$ref': '#/definitions/ConditionalAxisProperty<(FontStyle|null)>'}
-
-    def __init__(self, *args, **kwds):
-        super(ConditionalAxisPropertyFontStylenull, self).__init__(*args, **kwds)
-
-
-class ConditionalAxisPropertyFontWeightnull(VegaLiteSchema):
-    """ConditionalAxisPropertyFontWeightnull schema wrapper
-
-    anyOf(Mapping(required=[condition, value]), Mapping(required=[condition, expr]))
-    """
-    _schema = {'$ref': '#/definitions/ConditionalAxisProperty<(FontWeight|null)>'}
-
-    def __init__(self, *args, **kwds):
-        super(ConditionalAxisPropertyFontWeightnull, self).__init__(*args, **kwds)
-
-
-class ConditionalAxisPropertyTextBaselinenull(VegaLiteSchema):
-    """ConditionalAxisPropertyTextBaselinenull schema wrapper
-
-    anyOf(Mapping(required=[condition, value]), Mapping(required=[condition, expr]))
-    """
-    _schema = {'$ref': '#/definitions/ConditionalAxisProperty<(TextBaseline|null)>'}
-
-    def __init__(self, *args, **kwds):
-        super(ConditionalAxisPropertyTextBaselinenull, self).__init__(*args, **kwds)
-
-
-class ConditionalAxisPropertynumberArraynull(VegaLiteSchema):
-    """ConditionalAxisPropertynumberArraynull schema wrapper
-
-    anyOf(Mapping(required=[condition, value]), Mapping(required=[condition, expr]))
-    """
-    _schema = {'$ref': '#/definitions/ConditionalAxisProperty<(number[]|null)>'}
-
-    def __init__(self, *args, **kwds):
-        super(ConditionalAxisPropertynumberArraynull, self).__init__(*args, **kwds)
-
-
-class ConditionalAxisPropertynumbernull(VegaLiteSchema):
-    """ConditionalAxisPropertynumbernull schema wrapper
-
-    anyOf(Mapping(required=[condition, value]), Mapping(required=[condition, expr]))
-    """
-    _schema = {'$ref': '#/definitions/ConditionalAxisProperty<(number|null)>'}
-
-    def __init__(self, *args, **kwds):
-        super(ConditionalAxisPropertynumbernull, self).__init__(*args, **kwds)
-
-
-class ConditionalAxisPropertystringnull(VegaLiteSchema):
-    """ConditionalAxisPropertystringnull schema wrapper
-
-    anyOf(Mapping(required=[condition, value]), Mapping(required=[condition, expr]))
-    """
-    _schema = {'$ref': '#/definitions/ConditionalAxisProperty<(string|null)>'}
-
-    def __init__(self, *args, **kwds):
-        super(ConditionalAxisPropertystringnull, self).__init__(*args, **kwds)
-
-
-class ConditionalAxisString(VegaLiteSchema):
-    """ConditionalAxisString schema wrapper
-
-    anyOf(Mapping(required=[condition, value]), Mapping(required=[condition, expr]))
-    """
-    _schema = {'$ref': '#/definitions/ConditionalAxisString'}
-
-    def __init__(self, *args, **kwds):
-        super(ConditionalAxisString, self).__init__(*args, **kwds)
-
-
-class ConditionalMarkPropFieldOrDatumDef(VegaLiteSchema):
-    """ConditionalMarkPropFieldOrDatumDef schema wrapper
-
-    anyOf(:class:`ConditionalPredicateMarkPropFieldOrDatumDef`,
-    :class:`ConditionalParameterMarkPropFieldOrDatumDef`)
-    """
-    _schema = {'$ref': '#/definitions/ConditionalMarkPropFieldOrDatumDef'}
-
-    def __init__(self, *args, **kwds):
-        super(ConditionalMarkPropFieldOrDatumDef, self).__init__(*args, **kwds)
-
-
-class ConditionalMarkPropFieldOrDatumDefTypeForShape(VegaLiteSchema):
-    """ConditionalMarkPropFieldOrDatumDefTypeForShape schema wrapper
-
-    anyOf(:class:`ConditionalPredicateMarkPropFieldOrDatumDefTypeForShape`,
-    :class:`ConditionalParameterMarkPropFieldOrDatumDefTypeForShape`)
-    """
-    _schema = {'$ref': '#/definitions/ConditionalMarkPropFieldOrDatumDef<TypeForShape>'}
-
-    def __init__(self, *args, **kwds):
-        super(ConditionalMarkPropFieldOrDatumDefTypeForShape, self).__init__(*args, **kwds)
-
-
-class ConditionalParameterMarkPropFieldOrDatumDef(ConditionalMarkPropFieldOrDatumDef):
-    """ConditionalParameterMarkPropFieldOrDatumDef schema wrapper
-
-    anyOf(Mapping(required=[param]), Mapping(required=[param]))
-    """
-    _schema = {'$ref': '#/definitions/ConditionalParameter<MarkPropFieldOrDatumDef>'}
-
-    def __init__(self, *args, **kwds):
-        super(ConditionalParameterMarkPropFieldOrDatumDef, self).__init__(*args, **kwds)
-
-
-class ConditionalParameterMarkPropFieldOrDatumDefTypeForShape(ConditionalMarkPropFieldOrDatumDefTypeForShape):
-    """ConditionalParameterMarkPropFieldOrDatumDefTypeForShape schema wrapper
-
-    anyOf(Mapping(required=[param]), Mapping(required=[param]))
-    """
-    _schema = {'$ref': '#/definitions/ConditionalParameter<MarkPropFieldOrDatumDef<TypeForShape>>'}
-
-    def __init__(self, *args, **kwds):
-        super(ConditionalParameterMarkPropFieldOrDatumDefTypeForShape, self).__init__(*args, **kwds)
-
-
-class ConditionalPredicateMarkPropFieldOrDatumDef(ConditionalMarkPropFieldOrDatumDef):
-    """ConditionalPredicateMarkPropFieldOrDatumDef schema wrapper
-
-    anyOf(Mapping(required=[test]), Mapping(required=[test]))
-    """
-    _schema = {'$ref': '#/definitions/ConditionalPredicate<MarkPropFieldOrDatumDef>'}
-
-    def __init__(self, *args, **kwds):
-        super(ConditionalPredicateMarkPropFieldOrDatumDef, self).__init__(*args, **kwds)
-
-
-class ConditionalPredicateMarkPropFieldOrDatumDefTypeForShape(ConditionalMarkPropFieldOrDatumDefTypeForShape):
-    """ConditionalPredicateMarkPropFieldOrDatumDefTypeForShape schema wrapper
-
-    anyOf(Mapping(required=[test]), Mapping(required=[test]))
-    """
-    _schema = {'$ref': '#/definitions/ConditionalPredicate<MarkPropFieldOrDatumDef<TypeForShape>>'}
-
-    def __init__(self, *args, **kwds):
-        super(ConditionalPredicateMarkPropFieldOrDatumDefTypeForShape, self).__init__(*args, **kwds)
-
-
-class ConditionalPredicateValueDefAlignnullExprRef(VegaLiteSchema):
-    """ConditionalPredicateValueDefAlignnullExprRef schema wrapper
-
-    anyOf(Mapping(required=[test, value]), Mapping(required=[expr, test]))
-    """
-    _schema = {'$ref': '#/definitions/ConditionalPredicate<(ValueDef<(Align|null)>|ExprRef)>'}
-
-    def __init__(self, *args, **kwds):
-        super(ConditionalPredicateValueDefAlignnullExprRef, self).__init__(*args, **kwds)
-
-
-class ConditionalPredicateValueDefColornullExprRef(VegaLiteSchema):
-    """ConditionalPredicateValueDefColornullExprRef schema wrapper
-
-    anyOf(Mapping(required=[test, value]), Mapping(required=[expr, test]))
-    """
-    _schema = {'$ref': '#/definitions/ConditionalPredicate<(ValueDef<(Color|null)>|ExprRef)>'}
-
-    def __init__(self, *args, **kwds):
-        super(ConditionalPredicateValueDefColornullExprRef, self).__init__(*args, **kwds)
-
-
-class ConditionalPredicateValueDefFontStylenullExprRef(VegaLiteSchema):
-    """ConditionalPredicateValueDefFontStylenullExprRef schema wrapper
-
-    anyOf(Mapping(required=[test, value]), Mapping(required=[expr, test]))
-    """
-    _schema = {'$ref': '#/definitions/ConditionalPredicate<(ValueDef<(FontStyle|null)>|ExprRef)>'}
-
-    def __init__(self, *args, **kwds):
-        super(ConditionalPredicateValueDefFontStylenullExprRef, self).__init__(*args, **kwds)
-
-
-class ConditionalPredicateValueDefFontWeightnullExprRef(VegaLiteSchema):
-    """ConditionalPredicateValueDefFontWeightnullExprRef schema wrapper
-
-    anyOf(Mapping(required=[test, value]), Mapping(required=[expr, test]))
-    """
-    _schema = {'$ref': '#/definitions/ConditionalPredicate<(ValueDef<(FontWeight|null)>|ExprRef)>'}
-
-    def __init__(self, *args, **kwds):
-        super(ConditionalPredicateValueDefFontWeightnullExprRef, self).__init__(*args, **kwds)
-
-
-class ConditionalPredicateValueDefTextBaselinenullExprRef(VegaLiteSchema):
-    """ConditionalPredicateValueDefTextBaselinenullExprRef schema wrapper
-
-    anyOf(Mapping(required=[test, value]), Mapping(required=[expr, test]))
-    """
-    _schema = {'$ref': '#/definitions/ConditionalPredicate<(ValueDef<(TextBaseline|null)>|ExprRef)>'}
-
-    def __init__(self, *args, **kwds):
-        super(ConditionalPredicateValueDefTextBaselinenullExprRef, self).__init__(*args, **kwds)
-
-
-class ConditionalPredicateValueDefnumberArraynullExprRef(VegaLiteSchema):
-    """ConditionalPredicateValueDefnumberArraynullExprRef schema wrapper
-
-    anyOf(Mapping(required=[test, value]), Mapping(required=[expr, test]))
-    """
-    _schema = {'$ref': '#/definitions/ConditionalPredicate<(ValueDef<(number[]|null)>|ExprRef)>'}
-
-    def __init__(self, *args, **kwds):
-        super(ConditionalPredicateValueDefnumberArraynullExprRef, self).__init__(*args, **kwds)
-
-
-class ConditionalPredicateValueDefnumbernullExprRef(VegaLiteSchema):
-    """ConditionalPredicateValueDefnumbernullExprRef schema wrapper
-
-    anyOf(Mapping(required=[test, value]), Mapping(required=[expr, test]))
-    """
-    _schema = {'$ref': '#/definitions/ConditionalPredicate<(ValueDef<(number|null)>|ExprRef)>'}
-
-    def __init__(self, *args, **kwds):
-        super(ConditionalPredicateValueDefnumbernullExprRef, self).__init__(*args, **kwds)
-
-
-class ConditionalStringFieldDef(VegaLiteSchema):
-    """ConditionalStringFieldDef schema wrapper
-
-    anyOf(:class:`ConditionalPredicateStringFieldDef`,
-    :class:`ConditionalParameterStringFieldDef`)
-    """
-    _schema = {'$ref': '#/definitions/ConditionalStringFieldDef'}
-
-    def __init__(self, *args, **kwds):
-        super(ConditionalStringFieldDef, self).__init__(*args, **kwds)
-
-
-class ConditionalParameterStringFieldDef(ConditionalStringFieldDef):
-    """ConditionalParameterStringFieldDef schema wrapper
-
-    Mapping(required=[param])
-
-    Parameters
-    ----------
-
-    param : :class:`ParameterName`
-        Filter using a parameter name.
-    aggregate : :class:`Aggregate`
-        Aggregation function for the field (e.g., ``"mean"``, ``"sum"``, ``"median"``,
-        ``"min"``, ``"max"``, ``"count"`` ).
-
-        **Default value:** ``undefined`` (None)
-
-        **See also:** `aggregate <https://vega.github.io/vega-lite/docs/aggregate.html>`__
-        documentation.
-    bandPosition : float
-        Relative position on a band of a stacked, binned, time unit, or band scale. For
-        example, the marks will be positioned at the beginning of the band if set to ``0``,
-        and at the middle of the band if set to ``0.5``.
-    bin : anyOf(boolean, :class:`BinParams`, string, None)
-        A flag for binning a ``quantitative`` field, `an object defining binning parameters
-        <https://vega.github.io/vega-lite/docs/bin.html#bin-parameters>`__, or indicating
-        that the data for ``x`` or ``y`` channel are binned before they are imported into
-        Vega-Lite ( ``"binned"`` ).
-
-
-        If ``true``, default `binning parameters
-        <https://vega.github.io/vega-lite/docs/bin.html#bin-parameters>`__ will be applied.
-
-        If ``"binned"``, this indicates that the data for the ``x`` (or ``y`` ) channel are
-        already binned. You can map the bin-start field to ``x`` (or ``y`` ) and the bin-end
-        field to ``x2`` (or ``y2`` ). The scale and axis will be formatted similar to
-        binning in Vega-Lite.  To adjust the axis ticks based on the bin step, you can also
-        set the axis's `tickMinStep
-        <https://vega.github.io/vega-lite/docs/axis.html#ticks>`__ property.
-
-        **Default value:** ``false``
-
-        **See also:** `bin <https://vega.github.io/vega-lite/docs/bin.html>`__
-        documentation.
-    empty : boolean
-        For selection parameters, the predicate of empty selections returns true by default.
-        Override this behavior, by setting this property ``empty: false``.
-    field : :class:`Field`
-        **Required.** A string defining the name of the field from which to pull a data
-        value or an object defining iterated values from the `repeat
-        <https://vega.github.io/vega-lite/docs/repeat.html>`__ operator.
-
-        **See also:** `field <https://vega.github.io/vega-lite/docs/field.html>`__
-        documentation.
-
-        **Notes:** 1)  Dots ( ``.`` ) and brackets ( ``[`` and ``]`` ) can be used to access
-        nested objects (e.g., ``"field": "foo.bar"`` and ``"field": "foo['bar']"`` ). If
-        field names contain dots or brackets but are not nested, you can use ``\\`` to
-        escape dots and brackets (e.g., ``"a\\.b"`` and ``"a\\[0\\]"`` ). See more details
-        about escaping in the `field documentation
-        <https://vega.github.io/vega-lite/docs/field.html>`__. 2) ``field`` is not required
-        if ``aggregate`` is ``count``.
-    format : anyOf(string, :class:`Dict`)
-        When used with the default ``"number"`` and ``"time"`` format type, the text
-        formatting pattern for labels of guides (axes, legends, headers) and text marks.
-
-
-        * If the format type is ``"number"`` (e.g., for quantitative fields), this is D3's
-          `number format pattern <https://github.com/d3/d3-format#locale_format>`__.
-        * If the format type is ``"time"`` (e.g., for temporal fields), this is D3's `time
-          format pattern <https://github.com/d3/d3-time-format#locale_format>`__.
-
-        See the `format documentation <https://vega.github.io/vega-lite/docs/format.html>`__
-        for more examples.
-
-        When used with a `custom formatType
-        <https://vega.github.io/vega-lite/docs/config.html#custom-format-type>`__, this
-        value will be passed as ``format`` alongside ``datum.value`` to the registered
-        function.
-
-        **Default value:**  Derived from `numberFormat
-        <https://vega.github.io/vega-lite/docs/config.html#format>`__ config for number
-        format and from `timeFormat
-        <https://vega.github.io/vega-lite/docs/config.html#format>`__ config for time
-        format.
-    formatType : string
-        The format type for labels. One of ``"number"``, ``"time"``, or a `registered custom
-        format type
-        <https://vega.github.io/vega-lite/docs/config.html#custom-format-type>`__.
-
-        **Default value:**
-
-
-        * ``"time"`` for temporal fields and ordinal and nominal fields with ``timeUnit``.
-        * ``"number"`` for quantitative fields as well as ordinal and nominal fields without
-          ``timeUnit``.
-    timeUnit : anyOf(:class:`TimeUnit`, :class:`BinnedTimeUnit`, :class:`TimeUnitParams`)
-        Time unit (e.g., ``year``, ``yearmonth``, ``month``, ``hours`` ) for a temporal
-        field. or `a temporal field that gets casted as ordinal
-        <https://vega.github.io/vega-lite/docs/type.html#cast>`__.
-
-        **Default value:** ``undefined`` (None)
-
-        **See also:** `timeUnit <https://vega.github.io/vega-lite/docs/timeunit.html>`__
-        documentation.
-    title : anyOf(:class:`Text`, None)
-        A title for the field. If ``null``, the title will be removed.
-
-        **Default value:**  derived from the field's name and transformation function (
-        ``aggregate``, ``bin`` and ``timeUnit`` ). If the field has an aggregate function,
-        the function is displayed as part of the title (e.g., ``"Sum of Profit"`` ). If the
-        field is binned or has a time unit applied, the applied function is shown in
-        parentheses (e.g., ``"Profit (binned)"``, ``"Transaction Date (year-month)"`` ).
-        Otherwise, the title is simply the field name.
-
-        **Notes** :
-
-        1) You can customize the default field title format by providing the `fieldTitle
-        <https://vega.github.io/vega-lite/docs/config.html#top-level-config>`__ property in
-        the `config <https://vega.github.io/vega-lite/docs/config.html>`__ or `fieldTitle
-        function via the compile function's options
-        <https://vega.github.io/vega-lite/usage/compile.html#field-title>`__.
-
-        2) If both field definition's ``title`` and axis, header, or legend ``title`` are
-        defined, axis/header/legend title will be used.
-    type : :class:`StandardType`
-        The type of measurement ( ``"quantitative"``, ``"temporal"``, ``"ordinal"``, or
-        ``"nominal"`` ) for the encoded field or constant value ( ``datum`` ). It can also
-        be a ``"geojson"`` type for encoding `'geoshape'
-        <https://vega.github.io/vega-lite/docs/geoshape.html>`__.
-
-        Vega-Lite automatically infers data types in many cases as discussed below. However,
-        type is required for a field if: (1) the field is not nominal and the field encoding
-        has no specified ``aggregate`` (except ``argmin`` and ``argmax`` ), ``bin``, scale
-        type, custom ``sort`` order, nor ``timeUnit`` or (2) if you wish to use an ordinal
-        scale for a field with ``bin`` or ``timeUnit``.
-
-        **Default value:**
-
-        1) For a data ``field``, ``"nominal"`` is the default data type unless the field
-        encoding has ``aggregate``, ``channel``, ``bin``, scale type, ``sort``, or
-        ``timeUnit`` that satisfies the following criteria:
-
-
-        * ``"quantitative"`` is the default type if (1) the encoded field contains ``bin``
-          or ``aggregate`` except ``"argmin"`` and ``"argmax"``, (2) the encoding channel is
-          ``latitude`` or ``longitude`` channel or (3) if the specified scale type is `a
-          quantitative scale <https://vega.github.io/vega-lite/docs/scale.html#type>`__.
-        * ``"temporal"`` is the default type if (1) the encoded field contains ``timeUnit``
-          or (2) the specified scale type is a time or utc scale
-        * ``"ordinal"`` is the default type if (1) the encoded field contains a `custom sort
-          order
-          <https://vega.github.io/vega-lite/docs/sort.html#specifying-custom-sort-order>`__,
-          (2) the specified scale type is an ordinal/point/band scale, or (3) the encoding
-          channel is ``order``.
-
-        2) For a constant value in data domain ( ``datum`` ):
-
-
-        * ``"quantitative"`` if the datum is a number
-        * ``"nominal"`` if the datum is a string
-        * ``"temporal"`` if the datum is `a date time object
-          <https://vega.github.io/vega-lite/docs/datetime.html>`__
-
-        **Note:**
-
-
-        * Data ``type`` describes the semantics of the data rather than the primitive data
-          types (number, string, etc.). The same primitive data type can have different
-          types of measurement. For example, numeric data can represent quantitative,
-          ordinal, or nominal data.
-        * Data values for a temporal field can be either a date-time string (e.g.,
-          ``"2015-03-07 12:32:17"``, ``"17:01"``, ``"2015-03-16"``. ``"2015"`` ) or a
-          timestamp number (e.g., ``1552199579097`` ).
-        * When using with `bin <https://vega.github.io/vega-lite/docs/bin.html>`__, the
-          ``type`` property can be either ``"quantitative"`` (for using a linear bin scale)
-          or `"ordinal" (for using an ordinal bin scale)
-          <https://vega.github.io/vega-lite/docs/type.html#cast-bin>`__.
-        * When using with `timeUnit
-          <https://vega.github.io/vega-lite/docs/timeunit.html>`__, the ``type`` property
-          can be either ``"temporal"`` (default, for using a temporal scale) or `"ordinal"
-          (for using an ordinal scale)
-          <https://vega.github.io/vega-lite/docs/type.html#cast-bin>`__.
-        * When using with `aggregate
-          <https://vega.github.io/vega-lite/docs/aggregate.html>`__, the ``type`` property
-          refers to the post-aggregation data type. For example, we can calculate count
-          ``distinct`` of a categorical field ``"cat"`` using ``{"aggregate": "distinct",
-          "field": "cat"}``. The ``"type"`` of the aggregate output is ``"quantitative"``.
-        * Secondary channels (e.g., ``x2``, ``y2``, ``xError``, ``yError`` ) do not have
-          ``type`` as they must have exactly the same type as their primary channels (e.g.,
-          ``x``, ``y`` ).
-
-        **See also:** `type <https://vega.github.io/vega-lite/docs/type.html>`__
-        documentation.
-    """
-    _schema = {'$ref': '#/definitions/ConditionalParameter<StringFieldDef>'}
-
-    def __init__(self, param=Undefined, aggregate=Undefined, bandPosition=Undefined, bin=Undefined,
-                 empty=Undefined, field=Undefined, format=Undefined, formatType=Undefined,
-                 timeUnit=Undefined, title=Undefined, type=Undefined, **kwds):
-        super(ConditionalParameterStringFieldDef, self).__init__(param=param, aggregate=aggregate,
-                                                                 bandPosition=bandPosition, bin=bin,
-                                                                 empty=empty, field=field,
-                                                                 format=format, formatType=formatType,
-                                                                 timeUnit=timeUnit, title=title,
-                                                                 type=type, **kwds)
-
-
-class ConditionalPredicateStringFieldDef(ConditionalStringFieldDef):
-    """ConditionalPredicateStringFieldDef schema wrapper
-
-    Mapping(required=[test])
-
-    Parameters
-    ----------
-
-    test : :class:`PredicateComposition`
-        Predicate for triggering the condition
-    aggregate : :class:`Aggregate`
-        Aggregation function for the field (e.g., ``"mean"``, ``"sum"``, ``"median"``,
-        ``"min"``, ``"max"``, ``"count"`` ).
-
-        **Default value:** ``undefined`` (None)
-
-        **See also:** `aggregate <https://vega.github.io/vega-lite/docs/aggregate.html>`__
-        documentation.
-    bandPosition : float
-        Relative position on a band of a stacked, binned, time unit, or band scale. For
-        example, the marks will be positioned at the beginning of the band if set to ``0``,
-        and at the middle of the band if set to ``0.5``.
-    bin : anyOf(boolean, :class:`BinParams`, string, None)
-        A flag for binning a ``quantitative`` field, `an object defining binning parameters
-        <https://vega.github.io/vega-lite/docs/bin.html#bin-parameters>`__, or indicating
-        that the data for ``x`` or ``y`` channel are binned before they are imported into
-        Vega-Lite ( ``"binned"`` ).
-
-
-        If ``true``, default `binning parameters
-        <https://vega.github.io/vega-lite/docs/bin.html#bin-parameters>`__ will be applied.
-
-        If ``"binned"``, this indicates that the data for the ``x`` (or ``y`` ) channel are
-        already binned. You can map the bin-start field to ``x`` (or ``y`` ) and the bin-end
-        field to ``x2`` (or ``y2`` ). The scale and axis will be formatted similar to
-        binning in Vega-Lite.  To adjust the axis ticks based on the bin step, you can also
-        set the axis's `tickMinStep
-        <https://vega.github.io/vega-lite/docs/axis.html#ticks>`__ property.
-
-        **Default value:** ``false``
-
-        **See also:** `bin <https://vega.github.io/vega-lite/docs/bin.html>`__
-        documentation.
-    field : :class:`Field`
-        **Required.** A string defining the name of the field from which to pull a data
-        value or an object defining iterated values from the `repeat
-        <https://vega.github.io/vega-lite/docs/repeat.html>`__ operator.
-
-        **See also:** `field <https://vega.github.io/vega-lite/docs/field.html>`__
-        documentation.
-
-        **Notes:** 1)  Dots ( ``.`` ) and brackets ( ``[`` and ``]`` ) can be used to access
-        nested objects (e.g., ``"field": "foo.bar"`` and ``"field": "foo['bar']"`` ). If
-        field names contain dots or brackets but are not nested, you can use ``\\`` to
-        escape dots and brackets (e.g., ``"a\\.b"`` and ``"a\\[0\\]"`` ). See more details
-        about escaping in the `field documentation
-        <https://vega.github.io/vega-lite/docs/field.html>`__. 2) ``field`` is not required
-        if ``aggregate`` is ``count``.
-    format : anyOf(string, :class:`Dict`)
-        When used with the default ``"number"`` and ``"time"`` format type, the text
-        formatting pattern for labels of guides (axes, legends, headers) and text marks.
-
-
-        * If the format type is ``"number"`` (e.g., for quantitative fields), this is D3's
-          `number format pattern <https://github.com/d3/d3-format#locale_format>`__.
-        * If the format type is ``"time"`` (e.g., for temporal fields), this is D3's `time
-          format pattern <https://github.com/d3/d3-time-format#locale_format>`__.
-
-        See the `format documentation <https://vega.github.io/vega-lite/docs/format.html>`__
-        for more examples.
-
-        When used with a `custom formatType
-        <https://vega.github.io/vega-lite/docs/config.html#custom-format-type>`__, this
-        value will be passed as ``format`` alongside ``datum.value`` to the registered
-        function.
-
-        **Default value:**  Derived from `numberFormat
-        <https://vega.github.io/vega-lite/docs/config.html#format>`__ config for number
-        format and from `timeFormat
-        <https://vega.github.io/vega-lite/docs/config.html#format>`__ config for time
-        format.
-    formatType : string
-        The format type for labels. One of ``"number"``, ``"time"``, or a `registered custom
-        format type
-        <https://vega.github.io/vega-lite/docs/config.html#custom-format-type>`__.
-
-        **Default value:**
-
-
-        * ``"time"`` for temporal fields and ordinal and nominal fields with ``timeUnit``.
-        * ``"number"`` for quantitative fields as well as ordinal and nominal fields without
-          ``timeUnit``.
-    timeUnit : anyOf(:class:`TimeUnit`, :class:`BinnedTimeUnit`, :class:`TimeUnitParams`)
-        Time unit (e.g., ``year``, ``yearmonth``, ``month``, ``hours`` ) for a temporal
-        field. or `a temporal field that gets casted as ordinal
-        <https://vega.github.io/vega-lite/docs/type.html#cast>`__.
-
-        **Default value:** ``undefined`` (None)
-
-        **See also:** `timeUnit <https://vega.github.io/vega-lite/docs/timeunit.html>`__
-        documentation.
-    title : anyOf(:class:`Text`, None)
-        A title for the field. If ``null``, the title will be removed.
-
-        **Default value:**  derived from the field's name and transformation function (
-        ``aggregate``, ``bin`` and ``timeUnit`` ). If the field has an aggregate function,
-        the function is displayed as part of the title (e.g., ``"Sum of Profit"`` ). If the
-        field is binned or has a time unit applied, the applied function is shown in
-        parentheses (e.g., ``"Profit (binned)"``, ``"Transaction Date (year-month)"`` ).
-        Otherwise, the title is simply the field name.
-
-        **Notes** :
-
-        1) You can customize the default field title format by providing the `fieldTitle
-        <https://vega.github.io/vega-lite/docs/config.html#top-level-config>`__ property in
-        the `config <https://vega.github.io/vega-lite/docs/config.html>`__ or `fieldTitle
-        function via the compile function's options
-        <https://vega.github.io/vega-lite/usage/compile.html#field-title>`__.
-
-        2) If both field definition's ``title`` and axis, header, or legend ``title`` are
-        defined, axis/header/legend title will be used.
-    type : :class:`StandardType`
-        The type of measurement ( ``"quantitative"``, ``"temporal"``, ``"ordinal"``, or
-        ``"nominal"`` ) for the encoded field or constant value ( ``datum`` ). It can also
-        be a ``"geojson"`` type for encoding `'geoshape'
-        <https://vega.github.io/vega-lite/docs/geoshape.html>`__.
-
-        Vega-Lite automatically infers data types in many cases as discussed below. However,
-        type is required for a field if: (1) the field is not nominal and the field encoding
-        has no specified ``aggregate`` (except ``argmin`` and ``argmax`` ), ``bin``, scale
-        type, custom ``sort`` order, nor ``timeUnit`` or (2) if you wish to use an ordinal
-        scale for a field with ``bin`` or ``timeUnit``.
-
-        **Default value:**
-
-        1) For a data ``field``, ``"nominal"`` is the default data type unless the field
-        encoding has ``aggregate``, ``channel``, ``bin``, scale type, ``sort``, or
-        ``timeUnit`` that satisfies the following criteria:
-
-
-        * ``"quantitative"`` is the default type if (1) the encoded field contains ``bin``
-          or ``aggregate`` except ``"argmin"`` and ``"argmax"``, (2) the encoding channel is
-          ``latitude`` or ``longitude`` channel or (3) if the specified scale type is `a
-          quantitative scale <https://vega.github.io/vega-lite/docs/scale.html#type>`__.
-        * ``"temporal"`` is the default type if (1) the encoded field contains ``timeUnit``
-          or (2) the specified scale type is a time or utc scale
-        * ``"ordinal"`` is the default type if (1) the encoded field contains a `custom sort
-          order
-          <https://vega.github.io/vega-lite/docs/sort.html#specifying-custom-sort-order>`__,
-          (2) the specified scale type is an ordinal/point/band scale, or (3) the encoding
-          channel is ``order``.
-
-        2) For a constant value in data domain ( ``datum`` ):
-
-
-        * ``"quantitative"`` if the datum is a number
-        * ``"nominal"`` if the datum is a string
-        * ``"temporal"`` if the datum is `a date time object
-          <https://vega.github.io/vega-lite/docs/datetime.html>`__
-
-        **Note:**
-
-
-        * Data ``type`` describes the semantics of the data rather than the primitive data
-          types (number, string, etc.). The same primitive data type can have different
-          types of measurement. For example, numeric data can represent quantitative,
-          ordinal, or nominal data.
-        * Data values for a temporal field can be either a date-time string (e.g.,
-          ``"2015-03-07 12:32:17"``, ``"17:01"``, ``"2015-03-16"``. ``"2015"`` ) or a
-          timestamp number (e.g., ``1552199579097`` ).
-        * When using with `bin <https://vega.github.io/vega-lite/docs/bin.html>`__, the
-          ``type`` property can be either ``"quantitative"`` (for using a linear bin scale)
-          or `"ordinal" (for using an ordinal bin scale)
-          <https://vega.github.io/vega-lite/docs/type.html#cast-bin>`__.
-        * When using with `timeUnit
-          <https://vega.github.io/vega-lite/docs/timeunit.html>`__, the ``type`` property
-          can be either ``"temporal"`` (default, for using a temporal scale) or `"ordinal"
-          (for using an ordinal scale)
-          <https://vega.github.io/vega-lite/docs/type.html#cast-bin>`__.
-        * When using with `aggregate
-          <https://vega.github.io/vega-lite/docs/aggregate.html>`__, the ``type`` property
-          refers to the post-aggregation data type. For example, we can calculate count
-          ``distinct`` of a categorical field ``"cat"`` using ``{"aggregate": "distinct",
-          "field": "cat"}``. The ``"type"`` of the aggregate output is ``"quantitative"``.
-        * Secondary channels (e.g., ``x2``, ``y2``, ``xError``, ``yError`` ) do not have
-          ``type`` as they must have exactly the same type as their primary channels (e.g.,
-          ``x``, ``y`` ).
-
-        **See also:** `type <https://vega.github.io/vega-lite/docs/type.html>`__
-        documentation.
-    """
-    _schema = {'$ref': '#/definitions/ConditionalPredicate<StringFieldDef>'}
-
-    def __init__(self, test=Undefined, aggregate=Undefined, bandPosition=Undefined, bin=Undefined,
-                 field=Undefined, format=Undefined, formatType=Undefined, timeUnit=Undefined,
-                 title=Undefined, type=Undefined, **kwds):
-        super(ConditionalPredicateStringFieldDef, self).__init__(test=test, aggregate=aggregate,
-                                                                 bandPosition=bandPosition, bin=bin,
-                                                                 field=field, format=format,
-                                                                 formatType=formatType,
-                                                                 timeUnit=timeUnit, title=title,
-                                                                 type=type, **kwds)
-
-
-class ConditionalValueDefGradientstringnullExprRef(VegaLiteSchema):
-    """ConditionalValueDefGradientstringnullExprRef schema wrapper
-
-    anyOf(:class:`ConditionalPredicateValueDefGradientstringnullExprRef`,
-    :class:`ConditionalParameterValueDefGradientstringnullExprRef`)
-    """
-    _schema = {'$ref': '#/definitions/ConditionalValueDef<(Gradient|string|null|ExprRef)>'}
-
-    def __init__(self, *args, **kwds):
-        super(ConditionalValueDefGradientstringnullExprRef, self).__init__(*args, **kwds)
-
-
-class ConditionalParameterValueDefGradientstringnullExprRef(ConditionalValueDefGradientstringnullExprRef):
-    """ConditionalParameterValueDefGradientstringnullExprRef schema wrapper
-
-    Mapping(required=[param, value])
-
-    Parameters
-    ----------
-
-    param : :class:`ParameterName`
-        Filter using a parameter name.
-    value : anyOf(:class:`Gradient`, string, None, :class:`ExprRef`)
-        A constant value in visual domain (e.g., ``"red"`` / ``"#0099ff"`` / `gradient
-        definition <https://vega.github.io/vega-lite/docs/types.html#gradient>`__ for color,
-        values between ``0`` to ``1`` for opacity).
-    empty : boolean
-        For selection parameters, the predicate of empty selections returns true by default.
-        Override this behavior, by setting this property ``empty: false``.
-    """
-    _schema = {'$ref': '#/definitions/ConditionalParameter<ValueDef<(Gradient|string|null|ExprRef)>>'}
-
-    def __init__(self, param=Undefined, value=Undefined, empty=Undefined, **kwds):
-        super(ConditionalParameterValueDefGradientstringnullExprRef, self).__init__(param=param,
-                                                                                    value=value,
-                                                                                    empty=empty, **kwds)
-
-
-class ConditionalPredicateValueDefGradientstringnullExprRef(ConditionalValueDefGradientstringnullExprRef):
-    """ConditionalPredicateValueDefGradientstringnullExprRef schema wrapper
-
-    Mapping(required=[test, value])
-
-    Parameters
-    ----------
-
-    test : :class:`PredicateComposition`
-        Predicate for triggering the condition
-    value : anyOf(:class:`Gradient`, string, None, :class:`ExprRef`)
-        A constant value in visual domain (e.g., ``"red"`` / ``"#0099ff"`` / `gradient
-        definition <https://vega.github.io/vega-lite/docs/types.html#gradient>`__ for color,
-        values between ``0`` to ``1`` for opacity).
-    """
-    _schema = {'$ref': '#/definitions/ConditionalPredicate<ValueDef<(Gradient|string|null|ExprRef)>>'}
-
-    def __init__(self, test=Undefined, value=Undefined, **kwds):
-        super(ConditionalPredicateValueDefGradientstringnullExprRef, self).__init__(test=test,
-                                                                                    value=value, **kwds)
-
-
-class ConditionalValueDefTextExprRef(VegaLiteSchema):
-    """ConditionalValueDefTextExprRef schema wrapper
-
-    anyOf(:class:`ConditionalPredicateValueDefTextExprRef`,
-    :class:`ConditionalParameterValueDefTextExprRef`)
-    """
-    _schema = {'$ref': '#/definitions/ConditionalValueDef<(Text|ExprRef)>'}
-
-    def __init__(self, *args, **kwds):
-        super(ConditionalValueDefTextExprRef, self).__init__(*args, **kwds)
-
-
-class ConditionalParameterValueDefTextExprRef(ConditionalValueDefTextExprRef):
-    """ConditionalParameterValueDefTextExprRef schema wrapper
-
-    Mapping(required=[param, value])
-
-    Parameters
-    ----------
-
-    param : :class:`ParameterName`
-        Filter using a parameter name.
-    value : anyOf(:class:`Text`, :class:`ExprRef`)
-        A constant value in visual domain (e.g., ``"red"`` / ``"#0099ff"`` / `gradient
-        definition <https://vega.github.io/vega-lite/docs/types.html#gradient>`__ for color,
-        values between ``0`` to ``1`` for opacity).
-    empty : boolean
-        For selection parameters, the predicate of empty selections returns true by default.
-        Override this behavior, by setting this property ``empty: false``.
-    """
-    _schema = {'$ref': '#/definitions/ConditionalParameter<ValueDef<(Text|ExprRef)>>'}
-
-    def __init__(self, param=Undefined, value=Undefined, empty=Undefined, **kwds):
-        super(ConditionalParameterValueDefTextExprRef, self).__init__(param=param, value=value,
-                                                                      empty=empty, **kwds)
-
-
-class ConditionalPredicateValueDefTextExprRef(ConditionalValueDefTextExprRef):
-    """ConditionalPredicateValueDefTextExprRef schema wrapper
-
-    Mapping(required=[test, value])
-
-    Parameters
-    ----------
-
-    test : :class:`PredicateComposition`
-        Predicate for triggering the condition
-    value : anyOf(:class:`Text`, :class:`ExprRef`)
-        A constant value in visual domain (e.g., ``"red"`` / ``"#0099ff"`` / `gradient
-        definition <https://vega.github.io/vega-lite/docs/types.html#gradient>`__ for color,
-        values between ``0`` to ``1`` for opacity).
-    """
-    _schema = {'$ref': '#/definitions/ConditionalPredicate<ValueDef<(Text|ExprRef)>>'}
-
-    def __init__(self, test=Undefined, value=Undefined, **kwds):
-        super(ConditionalPredicateValueDefTextExprRef, self).__init__(test=test, value=value, **kwds)
-
-
-class ConditionalValueDefnumber(VegaLiteSchema):
-    """ConditionalValueDefnumber schema wrapper
-
-    anyOf(:class:`ConditionalPredicateValueDefnumber`,
-    :class:`ConditionalParameterValueDefnumber`)
-    """
-    _schema = {'$ref': '#/definitions/ConditionalValueDef<number>'}
-
-    def __init__(self, *args, **kwds):
-        super(ConditionalValueDefnumber, self).__init__(*args, **kwds)
-
-
-class ConditionalParameterValueDefnumber(ConditionalValueDefnumber):
-    """ConditionalParameterValueDefnumber schema wrapper
-
-    Mapping(required=[param, value])
-
-    Parameters
-    ----------
-
-    param : :class:`ParameterName`
-        Filter using a parameter name.
-    value : float
-        A constant value in visual domain (e.g., ``"red"`` / ``"#0099ff"`` / `gradient
-        definition <https://vega.github.io/vega-lite/docs/types.html#gradient>`__ for color,
-        values between ``0`` to ``1`` for opacity).
-    empty : boolean
-        For selection parameters, the predicate of empty selections returns true by default.
-        Override this behavior, by setting this property ``empty: false``.
-    """
-    _schema = {'$ref': '#/definitions/ConditionalParameter<ValueDef<number>>'}
-
-    def __init__(self, param=Undefined, value=Undefined, empty=Undefined, **kwds):
-        super(ConditionalParameterValueDefnumber, self).__init__(param=param, value=value, empty=empty,
-                                                                 **kwds)
-
-
-class ConditionalPredicateValueDefnumber(ConditionalValueDefnumber):
-    """ConditionalPredicateValueDefnumber schema wrapper
-
-    Mapping(required=[test, value])
-
-    Parameters
-    ----------
-
-    test : :class:`PredicateComposition`
-        Predicate for triggering the condition
-    value : float
-        A constant value in visual domain (e.g., ``"red"`` / ``"#0099ff"`` / `gradient
-        definition <https://vega.github.io/vega-lite/docs/types.html#gradient>`__ for color,
-        values between ``0`` to ``1`` for opacity).
-    """
-    _schema = {'$ref': '#/definitions/ConditionalPredicate<ValueDef<number>>'}
-
-    def __init__(self, test=Undefined, value=Undefined, **kwds):
-        super(ConditionalPredicateValueDefnumber, self).__init__(test=test, value=value, **kwds)
-
-
-class ConditionalValueDefnumberArrayExprRef(VegaLiteSchema):
-    """ConditionalValueDefnumberArrayExprRef schema wrapper
-
-    anyOf(:class:`ConditionalPredicateValueDefnumberArrayExprRef`,
-    :class:`ConditionalParameterValueDefnumberArrayExprRef`)
-    """
-    _schema = {'$ref': '#/definitions/ConditionalValueDef<(number[]|ExprRef)>'}
-
-    def __init__(self, *args, **kwds):
-        super(ConditionalValueDefnumberArrayExprRef, self).__init__(*args, **kwds)
-
-
-class ConditionalParameterValueDefnumberArrayExprRef(ConditionalValueDefnumberArrayExprRef):
-    """ConditionalParameterValueDefnumberArrayExprRef schema wrapper
-
-    Mapping(required=[param, value])
-
-    Parameters
-    ----------
-
-    param : :class:`ParameterName`
-        Filter using a parameter name.
-    value : anyOf(List(float), :class:`ExprRef`)
-        A constant value in visual domain (e.g., ``"red"`` / ``"#0099ff"`` / `gradient
-        definition <https://vega.github.io/vega-lite/docs/types.html#gradient>`__ for color,
-        values between ``0`` to ``1`` for opacity).
-    empty : boolean
-        For selection parameters, the predicate of empty selections returns true by default.
-        Override this behavior, by setting this property ``empty: false``.
-    """
-    _schema = {'$ref': '#/definitions/ConditionalParameter<ValueDef<(number[]|ExprRef)>>'}
-
-    def __init__(self, param=Undefined, value=Undefined, empty=Undefined, **kwds):
-        super(ConditionalParameterValueDefnumberArrayExprRef, self).__init__(param=param, value=value,
-                                                                             empty=empty, **kwds)
-
-
-class ConditionalPredicateValueDefnumberArrayExprRef(ConditionalValueDefnumberArrayExprRef):
-    """ConditionalPredicateValueDefnumberArrayExprRef schema wrapper
-
-    Mapping(required=[test, value])
-
-    Parameters
-    ----------
-
-    test : :class:`PredicateComposition`
-        Predicate for triggering the condition
-    value : anyOf(List(float), :class:`ExprRef`)
-        A constant value in visual domain (e.g., ``"red"`` / ``"#0099ff"`` / `gradient
-        definition <https://vega.github.io/vega-lite/docs/types.html#gradient>`__ for color,
-        values between ``0`` to ``1`` for opacity).
-    """
-    _schema = {'$ref': '#/definitions/ConditionalPredicate<ValueDef<(number[]|ExprRef)>>'}
-
-    def __init__(self, test=Undefined, value=Undefined, **kwds):
-        super(ConditionalPredicateValueDefnumberArrayExprRef, self).__init__(test=test, value=value,
-                                                                             **kwds)
-
-
-class ConditionalValueDefnumberExprRef(VegaLiteSchema):
-    """ConditionalValueDefnumberExprRef schema wrapper
-
-    anyOf(:class:`ConditionalPredicateValueDefnumberExprRef`,
-    :class:`ConditionalParameterValueDefnumberExprRef`)
-    """
-    _schema = {'$ref': '#/definitions/ConditionalValueDef<(number|ExprRef)>'}
-
-    def __init__(self, *args, **kwds):
-        super(ConditionalValueDefnumberExprRef, self).__init__(*args, **kwds)
-
-
-class ConditionalParameterValueDefnumberExprRef(ConditionalValueDefnumberExprRef):
-    """ConditionalParameterValueDefnumberExprRef schema wrapper
-
-    Mapping(required=[param, value])
-
-    Parameters
-    ----------
-
-    param : :class:`ParameterName`
-        Filter using a parameter name.
-    value : anyOf(float, :class:`ExprRef`)
-        A constant value in visual domain (e.g., ``"red"`` / ``"#0099ff"`` / `gradient
-        definition <https://vega.github.io/vega-lite/docs/types.html#gradient>`__ for color,
-        values between ``0`` to ``1`` for opacity).
-    empty : boolean
-        For selection parameters, the predicate of empty selections returns true by default.
-        Override this behavior, by setting this property ``empty: false``.
-    """
-    _schema = {'$ref': '#/definitions/ConditionalParameter<ValueDef<(number|ExprRef)>>'}
-
-    def __init__(self, param=Undefined, value=Undefined, empty=Undefined, **kwds):
-        super(ConditionalParameterValueDefnumberExprRef, self).__init__(param=param, value=value,
-                                                                        empty=empty, **kwds)
-
-
-class ConditionalPredicateValueDefnumberExprRef(ConditionalValueDefnumberExprRef):
-    """ConditionalPredicateValueDefnumberExprRef schema wrapper
-
-    Mapping(required=[test, value])
-
-    Parameters
-    ----------
-
-    test : :class:`PredicateComposition`
-        Predicate for triggering the condition
-    value : anyOf(float, :class:`ExprRef`)
-        A constant value in visual domain (e.g., ``"red"`` / ``"#0099ff"`` / `gradient
-        definition <https://vega.github.io/vega-lite/docs/types.html#gradient>`__ for color,
-        values between ``0`` to ``1`` for opacity).
-    """
-    _schema = {'$ref': '#/definitions/ConditionalPredicate<ValueDef<(number|ExprRef)>>'}
-
-    def __init__(self, test=Undefined, value=Undefined, **kwds):
-        super(ConditionalPredicateValueDefnumberExprRef, self).__init__(test=test, value=value, **kwds)
-
-
-class ConditionalValueDefstringExprRef(VegaLiteSchema):
-    """ConditionalValueDefstringExprRef schema wrapper
-
-    anyOf(:class:`ConditionalPredicateValueDefstringExprRef`,
-    :class:`ConditionalParameterValueDefstringExprRef`)
-    """
-    _schema = {'$ref': '#/definitions/ConditionalValueDef<(string|ExprRef)>'}
-
-    def __init__(self, *args, **kwds):
-        super(ConditionalValueDefstringExprRef, self).__init__(*args, **kwds)
-
-
-class ConditionalParameterValueDefstringExprRef(ConditionalValueDefstringExprRef):
-    """ConditionalParameterValueDefstringExprRef schema wrapper
-
-    Mapping(required=[param, value])
-
-    Parameters
-    ----------
-
-    param : :class:`ParameterName`
-        Filter using a parameter name.
-    value : anyOf(string, :class:`ExprRef`)
-        A constant value in visual domain (e.g., ``"red"`` / ``"#0099ff"`` / `gradient
-        definition <https://vega.github.io/vega-lite/docs/types.html#gradient>`__ for color,
-        values between ``0`` to ``1`` for opacity).
-    empty : boolean
-        For selection parameters, the predicate of empty selections returns true by default.
-        Override this behavior, by setting this property ``empty: false``.
-    """
-    _schema = {'$ref': '#/definitions/ConditionalParameter<ValueDef<(string|ExprRef)>>'}
-
-    def __init__(self, param=Undefined, value=Undefined, empty=Undefined, **kwds):
-        super(ConditionalParameterValueDefstringExprRef, self).__init__(param=param, value=value,
-                                                                        empty=empty, **kwds)
-
-
-class ConditionalPredicateValueDefstringExprRef(ConditionalValueDefstringExprRef):
-    """ConditionalPredicateValueDefstringExprRef schema wrapper
-
-    Mapping(required=[test, value])
-
-    Parameters
-    ----------
-
-    test : :class:`PredicateComposition`
-        Predicate for triggering the condition
-    value : anyOf(string, :class:`ExprRef`)
-        A constant value in visual domain (e.g., ``"red"`` / ``"#0099ff"`` / `gradient
-        definition <https://vega.github.io/vega-lite/docs/types.html#gradient>`__ for color,
-        values between ``0`` to ``1`` for opacity).
-    """
-    _schema = {'$ref': '#/definitions/ConditionalPredicate<ValueDef<(string|ExprRef)>>'}
-
-    def __init__(self, test=Undefined, value=Undefined, **kwds):
-        super(ConditionalPredicateValueDefstringExprRef, self).__init__(test=test, value=value, **kwds)
-
-
-class ConditionalValueDefstringnullExprRef(VegaLiteSchema):
-    """ConditionalValueDefstringnullExprRef schema wrapper
-
-    anyOf(:class:`ConditionalPredicateValueDefstringnullExprRef`,
-    :class:`ConditionalParameterValueDefstringnullExprRef`)
-    """
-    _schema = {'$ref': '#/definitions/ConditionalValueDef<(string|null|ExprRef)>'}
-
-    def __init__(self, *args, **kwds):
-        super(ConditionalValueDefstringnullExprRef, self).__init__(*args, **kwds)
-
-
-class ConditionalParameterValueDefstringnullExprRef(ConditionalValueDefstringnullExprRef):
-    """ConditionalParameterValueDefstringnullExprRef schema wrapper
-
-    Mapping(required=[param, value])
-
-    Parameters
-    ----------
-
-    param : :class:`ParameterName`
-        Filter using a parameter name.
-    value : anyOf(string, None, :class:`ExprRef`)
-        A constant value in visual domain (e.g., ``"red"`` / ``"#0099ff"`` / `gradient
-        definition <https://vega.github.io/vega-lite/docs/types.html#gradient>`__ for color,
-        values between ``0`` to ``1`` for opacity).
-    empty : boolean
-        For selection parameters, the predicate of empty selections returns true by default.
-        Override this behavior, by setting this property ``empty: false``.
-    """
-    _schema = {'$ref': '#/definitions/ConditionalParameter<ValueDef<(string|null|ExprRef)>>'}
-
-    def __init__(self, param=Undefined, value=Undefined, empty=Undefined, **kwds):
-        super(ConditionalParameterValueDefstringnullExprRef, self).__init__(param=param, value=value,
-                                                                            empty=empty, **kwds)
-
-
-class ConditionalPredicateValueDefstringnullExprRef(ConditionalValueDefstringnullExprRef):
-    """ConditionalPredicateValueDefstringnullExprRef schema wrapper
-
-    Mapping(required=[test, value])
-
-    Parameters
-    ----------
-
-    test : :class:`PredicateComposition`
-        Predicate for triggering the condition
-    value : anyOf(string, None, :class:`ExprRef`)
-        A constant value in visual domain (e.g., ``"red"`` / ``"#0099ff"`` / `gradient
-        definition <https://vega.github.io/vega-lite/docs/types.html#gradient>`__ for color,
-        values between ``0`` to ``1`` for opacity).
-    """
-    _schema = {'$ref': '#/definitions/ConditionalPredicate<ValueDef<(string|null|ExprRef)>>'}
-
-    def __init__(self, test=Undefined, value=Undefined, **kwds):
-        super(ConditionalPredicateValueDefstringnullExprRef, self).__init__(test=test, value=value,
-                                                                            **kwds)
-
-
-class Config(VegaLiteSchema):
-    """Config schema wrapper
-
-    Mapping(required=[])
-
-    Parameters
-    ----------
-
-    arc : :class:`RectConfig`
-        Arc-specific Config
-    area : :class:`AreaConfig`
-        Area-Specific Config
-    aria : boolean
-        A boolean flag indicating if ARIA default attributes should be included for marks
-        and guides (SVG output only). If false, the ``"aria-hidden"`` attribute will be set
-        for all guides, removing them from the ARIA accessibility tree and Vega-Lite will
-        not generate default descriptions for marks.
-
-        **Default value:** ``true``.
-    autosize : anyOf(:class:`AutosizeType`, :class:`AutoSizeParams`)
-        How the visualization size should be determined. If a string, should be one of
-        ``"pad"``, ``"fit"`` or ``"none"``. Object values can additionally specify
-        parameters for content sizing and automatic resizing.
-
-        **Default value** : ``pad``
-    axis : :class:`AxisConfig`
-        Axis configuration, which determines default properties for all ``x`` and ``y``
-        `axes <https://vega.github.io/vega-lite/docs/axis.html>`__. For a full list of axis
-        configuration options, please see the `corresponding section of the axis
-        documentation <https://vega.github.io/vega-lite/docs/axis.html#config>`__.
-    axisBand : :class:`AxisConfig`
-        Config for axes with "band" scales.
-    axisBottom : :class:`AxisConfig`
-        Config for x-axis along the bottom edge of the chart.
-    axisDiscrete : :class:`AxisConfig`
-        Config for axes with "point" or "band" scales.
-    axisLeft : :class:`AxisConfig`
-        Config for y-axis along the left edge of the chart.
-    axisPoint : :class:`AxisConfig`
-        Config for axes with "point" scales.
-    axisQuantitative : :class:`AxisConfig`
-        Config for quantitative axes.
-    axisRight : :class:`AxisConfig`
-        Config for y-axis along the right edge of the chart.
-    axisTemporal : :class:`AxisConfig`
-        Config for temporal axes.
-    axisTop : :class:`AxisConfig`
-        Config for x-axis along the top edge of the chart.
-    axisX : :class:`AxisConfig`
-        X-axis specific config.
-    axisXBand : :class:`AxisConfig`
-        Config for x-axes with "band" scales.
-    axisXDiscrete : :class:`AxisConfig`
-        Config for x-axes with "point" or "band" scales.
-    axisXPoint : :class:`AxisConfig`
-        Config for x-axes with "point" scales.
-    axisXQuantitative : :class:`AxisConfig`
-        Config for x-quantitative axes.
-    axisXTemporal : :class:`AxisConfig`
-        Config for x-temporal axes.
-    axisY : :class:`AxisConfig`
-        Y-axis specific config.
-    axisYBand : :class:`AxisConfig`
-        Config for y-axes with "band" scales.
-    axisYDiscrete : :class:`AxisConfig`
-        Config for y-axes with "point" or "band" scales.
-    axisYPoint : :class:`AxisConfig`
-        Config for y-axes with "point" scales.
-    axisYQuantitative : :class:`AxisConfig`
-        Config for y-quantitative axes.
-    axisYTemporal : :class:`AxisConfig`
-        Config for y-temporal axes.
-    background : anyOf(:class:`Color`, :class:`ExprRef`)
-        CSS color property to use as the background of the entire view.
-
-        **Default value:** ``"white"``
-    bar : :class:`BarConfig`
-        Bar-Specific Config
-    boxplot : :class:`BoxPlotConfig`
-        Box Config
-    circle : :class:`MarkConfig`
-        Circle-Specific Config
-    concat : :class:`CompositionConfig`
-        Default configuration for all concatenation and repeat view composition operators (
-        ``concat``, ``hconcat``, ``vconcat``, and ``repeat`` )
-    countTitle : string
-        Default axis and legend title for count fields.
-
-        **Default value:** ``'Count of Records``.
-    customFormatTypes : boolean
-        Allow the ``formatType`` property for text marks and guides to accept a custom
-        formatter function `registered as a Vega expression
-        <https://vega.github.io/vega-lite/usage/compile.html#format-type>`__.
-    errorband : :class:`ErrorBandConfig`
-        ErrorBand Config
-    errorbar : :class:`ErrorBarConfig`
-        ErrorBar Config
-    facet : :class:`CompositionConfig`
-        Default configuration for the ``facet`` view composition operator
-    fieldTitle : enum('verbal', 'functional', 'plain')
-        Defines how Vega-Lite generates title for fields. There are three possible styles:
-
-
-        * ``"verbal"`` (Default) - displays function in a verbal style (e.g., "Sum of
-          field", "Year-month of date", "field (binned)").
-        * ``"function"`` - displays function using parentheses and capitalized texts (e.g.,
-          "SUM(field)", "YEARMONTH(date)", "BIN(field)").
-        * ``"plain"`` - displays only the field name without functions (e.g., "field",
-          "date", "field").
-    font : string
-        Default font for all text marks, titles, and labels.
-    geoshape : :class:`MarkConfig`
-        Geoshape-Specific Config
-    header : :class:`HeaderConfig`
-        Header configuration, which determines default properties for all `headers
-        <https://vega.github.io/vega-lite/docs/header.html>`__.
-
-        For a full list of header configuration options, please see the `corresponding
-        section of in the header documentation
-        <https://vega.github.io/vega-lite/docs/header.html#config>`__.
-    headerColumn : :class:`HeaderConfig`
-        Header configuration, which determines default properties for column `headers
-        <https://vega.github.io/vega-lite/docs/header.html>`__.
-
-        For a full list of header configuration options, please see the `corresponding
-        section of in the header documentation
-        <https://vega.github.io/vega-lite/docs/header.html#config>`__.
-    headerFacet : :class:`HeaderConfig`
-        Header configuration, which determines default properties for non-row/column facet
-        `headers <https://vega.github.io/vega-lite/docs/header.html>`__.
-
-        For a full list of header configuration options, please see the `corresponding
-        section of in the header documentation
-        <https://vega.github.io/vega-lite/docs/header.html#config>`__.
-    headerRow : :class:`HeaderConfig`
-        Header configuration, which determines default properties for row `headers
-        <https://vega.github.io/vega-lite/docs/header.html>`__.
-
-        For a full list of header configuration options, please see the `corresponding
-        section of in the header documentation
-        <https://vega.github.io/vega-lite/docs/header.html#config>`__.
-    image : :class:`RectConfig`
-        Image-specific Config
-    legend : :class:`LegendConfig`
-        Legend configuration, which determines default properties for all `legends
-        <https://vega.github.io/vega-lite/docs/legend.html>`__. For a full list of legend
-        configuration options, please see the `corresponding section of in the legend
-        documentation <https://vega.github.io/vega-lite/docs/legend.html#config>`__.
-    line : :class:`LineConfig`
-        Line-Specific Config
-    lineBreak : anyOf(string, :class:`ExprRef`)
-        A delimiter, such as a newline character, upon which to break text strings into
-        multiple lines. This property provides a global default for text marks, which is
-        overridden by mark or style config settings, and by the lineBreak mark encoding
-        channel. If signal-valued, either string or regular expression (regexp) values are
-        valid.
-    locale : :class:`Locale`
-        Locale definitions for string parsing and formatting of number and date values. The
-        locale object should contain ``number`` and/or ``time`` properties with `locale
-        definitions <https://vega.github.io/vega/docs/api/locale/>`__. Locale definitions
-        provided in the config block may be overridden by the View constructor locale
-        option.
-    mark : :class:`MarkConfig`
-        Mark Config
-    normalizedNumberFormat : string
-        If normalizedNumberFormatType is not specified, D3 number format for axis labels,
-        text marks, and tooltips of normalized stacked fields (fields with ``stack:
-        "normalize"`` ). For example ``"s"`` for SI units. Use `D3's number format pattern
-        <https://github.com/d3/d3-format#locale_format>`__.
-
-        If ``config.normalizedNumberFormatType`` is specified and
-        ``config.customFormatTypes`` is ``true``, this value will be passed as ``format``
-        alongside ``datum.value`` to the ``config.numberFormatType`` function. **Default
-        value:** ``%``
-    normalizedNumberFormatType : string
-        `Custom format type
-        <https://vega.github.io/vega-lite/docs/config.html#custom-format-type>`__ for
-        ``config.normalizedNumberFormat``.
-
-        **Default value:** ``undefined`` -- This is equilvalent to call D3-format, which is
-        exposed as `format in Vega-Expression
-        <https://vega.github.io/vega/docs/expressions/#format>`__. **Note:** You must also
-        set ``customFormatTypes`` to ``true`` to use this feature.
-    numberFormat : string
-        If numberFormatType is not specified, D3 number format for guide labels, text marks,
-        and tooltips of non-normalized fields (fields *without* ``stack: "normalize"`` ).
-        For example ``"s"`` for SI units. Use `D3's number format pattern
-        <https://github.com/d3/d3-format#locale_format>`__.
-
-        If ``config.numberFormatType`` is specified and ``config.customFormatTypes`` is
-        ``true``, this value will be passed as ``format`` alongside ``datum.value`` to the
-        ``config.numberFormatType`` function.
-    numberFormatType : string
-        `Custom format type
-        <https://vega.github.io/vega-lite/docs/config.html#custom-format-type>`__ for
-        ``config.numberFormat``.
-
-        **Default value:** ``undefined`` -- This is equilvalent to call D3-format, which is
-        exposed as `format in Vega-Expression
-        <https://vega.github.io/vega/docs/expressions/#format>`__. **Note:** You must also
-        set ``customFormatTypes`` to ``true`` to use this feature.
-    padding : anyOf(:class:`Padding`, :class:`ExprRef`)
-        The default visualization padding, in pixels, from the edge of the visualization
-        canvas to the data rectangle. If a number, specifies padding for all sides. If an
-        object, the value should have the format ``{"left": 5, "top": 5, "right": 5,
-        "bottom": 5}`` to specify padding for each side of the visualization.
-
-        **Default value** : ``5``
-    params : List(:class:`TopLevelParameter`)
-        Dynamic variables or selections that parameterize a visualization.
-    point : :class:`MarkConfig`
-        Point-Specific Config
-    projection : :class:`ProjectionConfig`
-        Projection configuration, which determines default properties for all `projections
-        <https://vega.github.io/vega-lite/docs/projection.html>`__. For a full list of
-        projection configuration options, please see the `corresponding section of the
-        projection documentation
-        <https://vega.github.io/vega-lite/docs/projection.html#config>`__.
-    range : :class:`RangeConfig`
-        An object hash that defines default range arrays or schemes for using with scales.
-        For a full list of scale range configuration options, please see the `corresponding
-        section of the scale documentation
-        <https://vega.github.io/vega-lite/docs/scale.html#config>`__.
-    rect : :class:`RectConfig`
-        Rect-Specific Config
-    rule : :class:`MarkConfig`
-        Rule-Specific Config
-    scale : :class:`ScaleConfig`
-        Scale configuration determines default properties for all `scales
-        <https://vega.github.io/vega-lite/docs/scale.html>`__. For a full list of scale
-        configuration options, please see the `corresponding section of the scale
-        documentation <https://vega.github.io/vega-lite/docs/scale.html#config>`__.
-    selection : :class:`SelectionConfig`
-        An object hash for defining default properties for each type of selections.
-    square : :class:`MarkConfig`
-        Square-Specific Config
-    style : :class:`StyleConfigIndex`
-        An object hash that defines key-value mappings to determine default properties for
-        marks with a given `style
-        <https://vega.github.io/vega-lite/docs/mark.html#mark-def>`__. The keys represent
-        styles names; the values have to be valid `mark configuration objects
-        <https://vega.github.io/vega-lite/docs/mark.html#config>`__.
-    text : :class:`MarkConfig`
-        Text-Specific Config
-    tick : :class:`TickConfig`
-        Tick-Specific Config
-    timeFormat : string
-        Default time format for raw time values (without time units) in text marks, legend
-        labels and header labels.
-
-        **Default value:** ``"%b %d, %Y"`` **Note:** Axes automatically determine the format
-        for each label automatically so this config does not affect axes.
-    timeFormatType : string
-        `Custom format type
-        <https://vega.github.io/vega-lite/docs/config.html#custom-format-type>`__ for
-        ``config.timeFormat``.
-
-        **Default value:** ``undefined`` -- This is equilvalent to call D3-time-format,
-        which is exposed as `timeFormat in Vega-Expression
-        <https://vega.github.io/vega/docs/expressions/#timeFormat>`__. **Note:** You must
-        also set ``customFormatTypes`` to ``true`` and there must *not* be a ``timeUnit``
-        defined to use this feature.
-    title : :class:`TitleConfig`
-        Title configuration, which determines default properties for all `titles
-        <https://vega.github.io/vega-lite/docs/title.html>`__. For a full list of title
-        configuration options, please see the `corresponding section of the title
-        documentation <https://vega.github.io/vega-lite/docs/title.html#config>`__.
-    tooltipFormat : :class:`FormatConfig`
-        Define `custom format configuration
-        <https://vega.github.io/vega-lite/docs/config.html#format>`__ for tooltips. If
-        unspecified, default format config will be applied.
-    trail : :class:`LineConfig`
-        Trail-Specific Config
-    view : :class:`ViewConfig`
-        Default properties for `single view plots
-        <https://vega.github.io/vega-lite/docs/spec.html#single>`__.
-    """
-    _schema = {'$ref': '#/definitions/Config'}
-
-    def __init__(self, arc=Undefined, area=Undefined, aria=Undefined, autosize=Undefined,
-                 axis=Undefined, axisBand=Undefined, axisBottom=Undefined, axisDiscrete=Undefined,
-                 axisLeft=Undefined, axisPoint=Undefined, axisQuantitative=Undefined,
-                 axisRight=Undefined, axisTemporal=Undefined, axisTop=Undefined, axisX=Undefined,
-                 axisXBand=Undefined, axisXDiscrete=Undefined, axisXPoint=Undefined,
-                 axisXQuantitative=Undefined, axisXTemporal=Undefined, axisY=Undefined,
-                 axisYBand=Undefined, axisYDiscrete=Undefined, axisYPoint=Undefined,
-                 axisYQuantitative=Undefined, axisYTemporal=Undefined, background=Undefined,
-                 bar=Undefined, boxplot=Undefined, circle=Undefined, concat=Undefined,
-                 countTitle=Undefined, customFormatTypes=Undefined, errorband=Undefined,
-                 errorbar=Undefined, facet=Undefined, fieldTitle=Undefined, font=Undefined,
-                 geoshape=Undefined, header=Undefined, headerColumn=Undefined, headerFacet=Undefined,
-                 headerRow=Undefined, image=Undefined, legend=Undefined, line=Undefined,
-                 lineBreak=Undefined, locale=Undefined, mark=Undefined,
-                 normalizedNumberFormat=Undefined, normalizedNumberFormatType=Undefined,
-                 numberFormat=Undefined, numberFormatType=Undefined, padding=Undefined,
-                 params=Undefined, point=Undefined, projection=Undefined, range=Undefined,
-                 rect=Undefined, rule=Undefined, scale=Undefined, selection=Undefined, square=Undefined,
-                 style=Undefined, text=Undefined, tick=Undefined, timeFormat=Undefined,
-                 timeFormatType=Undefined, title=Undefined, tooltipFormat=Undefined, trail=Undefined,
-                 view=Undefined, **kwds):
-        super(Config, self).__init__(arc=arc, area=area, aria=aria, autosize=autosize, axis=axis,
-                                     axisBand=axisBand, axisBottom=axisBottom,
-                                     axisDiscrete=axisDiscrete, axisLeft=axisLeft, axisPoint=axisPoint,
-                                     axisQuantitative=axisQuantitative, axisRight=axisRight,
-                                     axisTemporal=axisTemporal, axisTop=axisTop, axisX=axisX,
-                                     axisXBand=axisXBand, axisXDiscrete=axisXDiscrete,
-                                     axisXPoint=axisXPoint, axisXQuantitative=axisXQuantitative,
-                                     axisXTemporal=axisXTemporal, axisY=axisY, axisYBand=axisYBand,
-                                     axisYDiscrete=axisYDiscrete, axisYPoint=axisYPoint,
-                                     axisYQuantitative=axisYQuantitative, axisYTemporal=axisYTemporal,
-                                     background=background, bar=bar, boxplot=boxplot, circle=circle,
-                                     concat=concat, countTitle=countTitle,
-                                     customFormatTypes=customFormatTypes, errorband=errorband,
-                                     errorbar=errorbar, facet=facet, fieldTitle=fieldTitle, font=font,
-                                     geoshape=geoshape, header=header, headerColumn=headerColumn,
-                                     headerFacet=headerFacet, headerRow=headerRow, image=image,
-                                     legend=legend, line=line, lineBreak=lineBreak, locale=locale,
-                                     mark=mark, normalizedNumberFormat=normalizedNumberFormat,
-                                     normalizedNumberFormatType=normalizedNumberFormatType,
-                                     numberFormat=numberFormat, numberFormatType=numberFormatType,
-                                     padding=padding, params=params, point=point, projection=projection,
-                                     range=range, rect=rect, rule=rule, scale=scale,
-                                     selection=selection, square=square, style=style, text=text,
-                                     tick=tick, timeFormat=timeFormat, timeFormatType=timeFormatType,
-                                     title=title, tooltipFormat=tooltipFormat, trail=trail, view=view,
-                                     **kwds)
-
-
-class Cursor(VegaLiteSchema):
-    """Cursor schema wrapper
-
-    enum('auto', 'default', 'none', 'context-menu', 'help', 'pointer', 'progress', 'wait',
-    'cell', 'crosshair', 'text', 'vertical-text', 'alias', 'copy', 'move', 'no-drop',
-    'not-allowed', 'e-resize', 'n-resize', 'ne-resize', 'nw-resize', 's-resize', 'se-resize',
-    'sw-resize', 'w-resize', 'ew-resize', 'ns-resize', 'nesw-resize', 'nwse-resize',
-    'col-resize', 'row-resize', 'all-scroll', 'zoom-in', 'zoom-out', 'grab', 'grabbing')
-    """
-    _schema = {'$ref': '#/definitions/Cursor'}
-
-    def __init__(self, *args):
-        super(Cursor, self).__init__(*args)
-
-
-class Cyclical(ColorScheme):
-    """Cyclical schema wrapper
-
-    enum('rainbow', 'sinebow')
-    """
-    _schema = {'$ref': '#/definitions/Cyclical'}
-
-    def __init__(self, *args):
-        super(Cyclical, self).__init__(*args)
-
-
-class Data(VegaLiteSchema):
-    """Data schema wrapper
-
-    anyOf(:class:`DataSource`, :class:`Generator`)
-    """
-    _schema = {'$ref': '#/definitions/Data'}
-
-    def __init__(self, *args, **kwds):
-        super(Data, self).__init__(*args, **kwds)
-
-
-class DataFormat(VegaLiteSchema):
-    """DataFormat schema wrapper
-
-    anyOf(:class:`CsvDataFormat`, :class:`DsvDataFormat`, :class:`JsonDataFormat`,
-    :class:`TopoDataFormat`)
-    """
-    _schema = {'$ref': '#/definitions/DataFormat'}
-
-    def __init__(self, *args, **kwds):
-        super(DataFormat, self).__init__(*args, **kwds)
-
-
-class CsvDataFormat(DataFormat):
-    """CsvDataFormat schema wrapper
-
-    Mapping(required=[])
-
-    Parameters
-    ----------
-
-    parse : anyOf(:class:`Parse`, None)
-        If set to ``null``, disable type inference based on the spec and only use type
-        inference based on the data. Alternatively, a parsing directive object can be
-        provided for explicit data types. Each property of the object corresponds to a field
-        name, and the value to the desired data type (one of ``"number"``, ``"boolean"``,
-        ``"date"``, or null (do not parse the field)). For example, ``"parse":
-        {"modified_on": "date"}`` parses the ``modified_on`` field in each input record a
-        Date value.
-
-        For ``"date"``, we parse data based using JavaScript's `Date.parse()
-        <https://developer.mozilla.org/en-US/docs/Web/JavaScript/Reference/Global_Objects/Date/parse>`__.
-        For Specific date formats can be provided (e.g., ``{foo: "date:'%m%d%Y'"}`` ), using
-        the `d3-time-format syntax <https://github.com/d3/d3-time-format#locale_format>`__.
-        UTC date format parsing is supported similarly (e.g., ``{foo: "utc:'%m%d%Y'"}`` ).
-        See more about `UTC time
-        <https://vega.github.io/vega-lite/docs/timeunit.html#utc>`__
-    type : enum('csv', 'tsv')
-        Type of input data: ``"json"``, ``"csv"``, ``"tsv"``, ``"dsv"``.
-
-        **Default value:**  The default format type is determined by the extension of the
-        file URL. If no extension is detected, ``"json"`` will be used by default.
-    """
-    _schema = {'$ref': '#/definitions/CsvDataFormat'}
-
-    def __init__(self, parse=Undefined, type=Undefined, **kwds):
-        super(CsvDataFormat, self).__init__(parse=parse, type=type, **kwds)
-
-
-class DataSource(Data):
-    """DataSource schema wrapper
-
-    anyOf(:class:`UrlData`, :class:`InlineData`, :class:`NamedData`)
-    """
-    _schema = {'$ref': '#/definitions/DataSource'}
-
-    def __init__(self, *args, **kwds):
-        super(DataSource, self).__init__(*args, **kwds)
-
-
-class Datasets(VegaLiteSchema):
-    """Datasets schema wrapper
-
-    Mapping(required=[])
-    """
-    _schema = {'$ref': '#/definitions/Datasets'}
-
-    def __init__(self, **kwds):
-        super(Datasets, self).__init__(**kwds)
-
-
-class Day(VegaLiteSchema):
-    """Day schema wrapper
-
-    float
-    """
-    _schema = {'$ref': '#/definitions/Day'}
-
-    def __init__(self, *args):
-        super(Day, self).__init__(*args)
-
-
-class Dict(VegaLiteSchema):
-    """Dict schema wrapper
-
-    Mapping(required=[])
-    """
-    _schema = {'$ref': '#/definitions/Dict'}
-
-    def __init__(self, **kwds):
-        super(Dict, self).__init__(**kwds)
-
-
-class DictInlineDataset(VegaLiteSchema):
-    """DictInlineDataset schema wrapper
-
-    Mapping(required=[])
-    """
-    _schema = {'$ref': '#/definitions/Dict<InlineDataset>'}
-
-    def __init__(self, **kwds):
-        super(DictInlineDataset, self).__init__(**kwds)
-
-
-class DictSelectionInit(VegaLiteSchema):
-    """DictSelectionInit schema wrapper
-
-    Mapping(required=[])
-    """
-    _schema = {'$ref': '#/definitions/Dict<SelectionInit>'}
-
-    def __init__(self, **kwds):
-        super(DictSelectionInit, self).__init__(**kwds)
-
-
-class DictSelectionInitInterval(VegaLiteSchema):
-    """DictSelectionInitInterval schema wrapper
-
-    Mapping(required=[])
-    """
-    _schema = {'$ref': '#/definitions/Dict<SelectionInitInterval>'}
-
-    def __init__(self, **kwds):
-        super(DictSelectionInitInterval, self).__init__(**kwds)
-
-
-class Diverging(ColorScheme):
-    """Diverging schema wrapper
-
-    enum('blueorange', 'blueorange-3', 'blueorange-4', 'blueorange-5', 'blueorange-6',
-    'blueorange-7', 'blueorange-8', 'blueorange-9', 'blueorange-10', 'blueorange-11',
-    'brownbluegreen', 'brownbluegreen-3', 'brownbluegreen-4', 'brownbluegreen-5',
-    'brownbluegreen-6', 'brownbluegreen-7', 'brownbluegreen-8', 'brownbluegreen-9',
-    'brownbluegreen-10', 'brownbluegreen-11', 'purplegreen', 'purplegreen-3', 'purplegreen-4',
-    'purplegreen-5', 'purplegreen-6', 'purplegreen-7', 'purplegreen-8', 'purplegreen-9',
-    'purplegreen-10', 'purplegreen-11', 'pinkyellowgreen', 'pinkyellowgreen-3',
-    'pinkyellowgreen-4', 'pinkyellowgreen-5', 'pinkyellowgreen-6', 'pinkyellowgreen-7',
-    'pinkyellowgreen-8', 'pinkyellowgreen-9', 'pinkyellowgreen-10', 'pinkyellowgreen-11',
-    'purpleorange', 'purpleorange-3', 'purpleorange-4', 'purpleorange-5', 'purpleorange-6',
-    'purpleorange-7', 'purpleorange-8', 'purpleorange-9', 'purpleorange-10', 'purpleorange-11',
-    'redblue', 'redblue-3', 'redblue-4', 'redblue-5', 'redblue-6', 'redblue-7', 'redblue-8',
-    'redblue-9', 'redblue-10', 'redblue-11', 'redgrey', 'redgrey-3', 'redgrey-4', 'redgrey-5',
-    'redgrey-6', 'redgrey-7', 'redgrey-8', 'redgrey-9', 'redgrey-10', 'redgrey-11',
-    'redyellowblue', 'redyellowblue-3', 'redyellowblue-4', 'redyellowblue-5', 'redyellowblue-6',
-    'redyellowblue-7', 'redyellowblue-8', 'redyellowblue-9', 'redyellowblue-10',
-    'redyellowblue-11', 'redyellowgreen', 'redyellowgreen-3', 'redyellowgreen-4',
-    'redyellowgreen-5', 'redyellowgreen-6', 'redyellowgreen-7', 'redyellowgreen-8',
-    'redyellowgreen-9', 'redyellowgreen-10', 'redyellowgreen-11', 'spectral', 'spectral-3',
-    'spectral-4', 'spectral-5', 'spectral-6', 'spectral-7', 'spectral-8', 'spectral-9',
-    'spectral-10', 'spectral-11')
-    """
-    _schema = {'$ref': '#/definitions/Diverging'}
-
-    def __init__(self, *args):
-        super(Diverging, self).__init__(*args)
-
-
-class DomainUnionWith(VegaLiteSchema):
-    """DomainUnionWith schema wrapper
-
-    Mapping(required=[unionWith])
-
-    Parameters
-    ----------
-
-    unionWith : anyOf(List(float), List(string), List(boolean), List(:class:`DateTime`))
-        Customized domain values to be union with the field's values or explicitly defined
-        domain. Should be an array of valid scale domain values.
-    """
-    _schema = {'$ref': '#/definitions/DomainUnionWith'}
-
-    def __init__(self, unionWith=Undefined, **kwds):
-        super(DomainUnionWith, self).__init__(unionWith=unionWith, **kwds)
-
-
-class DsvDataFormat(DataFormat):
-    """DsvDataFormat schema wrapper
-
-    Mapping(required=[delimiter])
-
-    Parameters
-    ----------
-
-    delimiter : string
-        The delimiter between records. The delimiter must be a single character (i.e., a
-        single 16-bit code unit); so, ASCII delimiters are fine, but emoji delimiters are
-        not.
-    parse : anyOf(:class:`Parse`, None)
-        If set to ``null``, disable type inference based on the spec and only use type
-        inference based on the data. Alternatively, a parsing directive object can be
-        provided for explicit data types. Each property of the object corresponds to a field
-        name, and the value to the desired data type (one of ``"number"``, ``"boolean"``,
-        ``"date"``, or null (do not parse the field)). For example, ``"parse":
-        {"modified_on": "date"}`` parses the ``modified_on`` field in each input record a
-        Date value.
-
-        For ``"date"``, we parse data based using JavaScript's `Date.parse()
-        <https://developer.mozilla.org/en-US/docs/Web/JavaScript/Reference/Global_Objects/Date/parse>`__.
-        For Specific date formats can be provided (e.g., ``{foo: "date:'%m%d%Y'"}`` ), using
-        the `d3-time-format syntax <https://github.com/d3/d3-time-format#locale_format>`__.
-        UTC date format parsing is supported similarly (e.g., ``{foo: "utc:'%m%d%Y'"}`` ).
-        See more about `UTC time
-        <https://vega.github.io/vega-lite/docs/timeunit.html#utc>`__
-    type : string
-        Type of input data: ``"json"``, ``"csv"``, ``"tsv"``, ``"dsv"``.
-
-        **Default value:**  The default format type is determined by the extension of the
-        file URL. If no extension is detected, ``"json"`` will be used by default.
-    """
-    _schema = {'$ref': '#/definitions/DsvDataFormat'}
-
-    def __init__(self, delimiter=Undefined, parse=Undefined, type=Undefined, **kwds):
-        super(DsvDataFormat, self).__init__(delimiter=delimiter, parse=parse, type=type, **kwds)
-
-
-class Element(VegaLiteSchema):
-    """Element schema wrapper
-
-    string
-    """
-    _schema = {'$ref': '#/definitions/Element'}
-
-    def __init__(self, *args):
-        super(Element, self).__init__(*args)
-
-
-class Encoding(VegaLiteSchema):
-    """Encoding schema wrapper
-
-    Mapping(required=[])
-
-    Parameters
-    ----------
-
-    angle : :class:`NumericMarkPropDef`
-        Rotation angle of point and text marks.
-    color : :class:`ColorDef`
-        Color of the marks – either fill or stroke color based on  the ``filled`` property
-        of mark definition. By default, ``color`` represents fill color for ``"area"``,
-        ``"bar"``, ``"tick"``, ``"text"``, ``"trail"``, ``"circle"``, and ``"square"`` /
-        stroke color for ``"line"`` and ``"point"``.
-
-        **Default value:** If undefined, the default color depends on `mark config
-        <https://vega.github.io/vega-lite/docs/config.html#mark-config>`__ 's ``color``
-        property.
-
-        *Note:* 1) For fine-grained control over both fill and stroke colors of the marks,
-        please use the ``fill`` and ``stroke`` channels. The ``fill`` or ``stroke``
-        encodings have higher precedence than ``color``, thus may override the ``color``
-        encoding if conflicting encodings are specified. 2) See the scale documentation for
-        more information about customizing `color scheme
-        <https://vega.github.io/vega-lite/docs/scale.html#scheme>`__.
-    description : anyOf(:class:`StringFieldDefWithCondition`, :class:`StringValueDefWithCondition`)
-        A text description of this mark for ARIA accessibility (SVG output only). For SVG
-        output the ``"aria-label"`` attribute will be set to this description.
-    detail : anyOf(:class:`FieldDefWithoutScale`, List(:class:`FieldDefWithoutScale`))
-        Additional levels of detail for grouping data in aggregate views and in line, trail,
-        and area marks without mapping data to a specific visual channel.
-    fill : :class:`ColorDef`
-        Fill color of the marks. **Default value:** If undefined, the default color depends
-        on `mark config <https://vega.github.io/vega-lite/docs/config.html#mark-config>`__
-        's ``color`` property.
-
-        *Note:* The ``fill`` encoding has higher precedence than ``color``, thus may
-        override the ``color`` encoding if conflicting encodings are specified.
-    fillOpacity : :class:`NumericMarkPropDef`
-        Fill opacity of the marks.
-
-        **Default value:** If undefined, the default opacity depends on `mark config
-        <https://vega.github.io/vega-lite/docs/config.html#mark-config>`__ 's
-        ``fillOpacity`` property.
-    href : anyOf(:class:`StringFieldDefWithCondition`, :class:`StringValueDefWithCondition`)
-        A URL to load upon mouse click.
-    key : :class:`FieldDefWithoutScale`
-        A data field to use as a unique key for data binding. When a visualization’s data is
-        updated, the key value will be used to match data elements to existing mark
-        instances. Use a key channel to enable object constancy for transitions over dynamic
-        data.
-    latitude : :class:`LatLongDef`
-        Latitude position of geographically projected marks.
-    latitude2 : :class:`Position2Def`
-        Latitude-2 position for geographically projected ranged ``"area"``, ``"bar"``,
-        ``"rect"``, and  ``"rule"``.
-    longitude : :class:`LatLongDef`
-        Longitude position of geographically projected marks.
-    longitude2 : :class:`Position2Def`
-        Longitude-2 position for geographically projected ranged ``"area"``, ``"bar"``,
-        ``"rect"``, and  ``"rule"``.
-    opacity : :class:`NumericMarkPropDef`
-        Opacity of the marks.
-
-        **Default value:** If undefined, the default opacity depends on `mark config
-        <https://vega.github.io/vega-lite/docs/config.html#mark-config>`__ 's ``opacity``
-        property.
-    order : anyOf(:class:`OrderFieldDef`, List(:class:`OrderFieldDef`), :class:`OrderValueDef`, :class:`OrderOnlyDef`)
-        Order of the marks.
-
-
-        * For stacked marks, this ``order`` channel encodes `stack order
-          <https://vega.github.io/vega-lite/docs/stack.html#order>`__.
-        * For line and trail marks, this ``order`` channel encodes order of data points in
-          the lines. This can be useful for creating `a connected scatterplot
-          <https://vega.github.io/vega-lite/examples/connected_scatterplot.html>`__. Setting
-          ``order`` to ``{"value": null}`` makes the line marks use the original order in
-          the data sources.
-        * Otherwise, this ``order`` channel encodes layer order of the marks.
-
-        **Note** : In aggregate plots, ``order`` field should be ``aggregate`` d to avoid
-        creating additional aggregation grouping.
-    radius : :class:`PolarDef`
-        The outer radius in pixels of arc marks.
-    radius2 : :class:`Position2Def`
-        The inner radius in pixels of arc marks.
-    shape : :class:`ShapeDef`
-        Shape of the mark.
-
-
-        #.
-        For ``point`` marks the supported values include:   - plotting shapes: ``"circle"``,
-        ``"square"``, ``"cross"``, ``"diamond"``, ``"triangle-up"``, ``"triangle-down"``,
-        ``"triangle-right"``, or ``"triangle-left"``.   - the line symbol ``"stroke"``   -
-        centered directional shapes ``"arrow"``, ``"wedge"``, or ``"triangle"``   - a custom
-        `SVG path string
-        <https://developer.mozilla.org/en-US/docs/Web/SVG/Tutorial/Paths>`__ (For correct
-        sizing, custom shape paths should be defined within a square bounding box with
-        coordinates ranging from -1 to 1 along both the x and y dimensions.)
-
-        #.
-        For ``geoshape`` marks it should be a field definition of the geojson data
-
-        **Default value:** If undefined, the default shape depends on `mark config
-        <https://vega.github.io/vega-lite/docs/config.html#point-config>`__ 's ``shape``
-        property. ( ``"circle"`` if unset.)
-    size : :class:`NumericMarkPropDef`
-        Size of the mark.
-
-
-        * For ``"point"``, ``"square"`` and ``"circle"``, – the symbol size, or pixel area
-          of the mark.
-        * For ``"bar"`` and ``"tick"`` – the bar and tick's size.
-        * For ``"text"`` – the text's font size.
-        * Size is unsupported for ``"line"``, ``"area"``, and ``"rect"``. (Use ``"trail"``
-          instead of line with varying size)
-    stroke : :class:`ColorDef`
-        Stroke color of the marks. **Default value:** If undefined, the default color
-        depends on `mark config
-        <https://vega.github.io/vega-lite/docs/config.html#mark-config>`__ 's ``color``
-        property.
-
-        *Note:* The ``stroke`` encoding has higher precedence than ``color``, thus may
-        override the ``color`` encoding if conflicting encodings are specified.
-    strokeDash : :class:`NumericArrayMarkPropDef`
-        Stroke dash of the marks.
-
-        **Default value:** ``[1,0]`` (No dash).
-    strokeOpacity : :class:`NumericMarkPropDef`
-        Stroke opacity of the marks.
-
-        **Default value:** If undefined, the default opacity depends on `mark config
-        <https://vega.github.io/vega-lite/docs/config.html#mark-config>`__ 's
-        ``strokeOpacity`` property.
-    strokeWidth : :class:`NumericMarkPropDef`
-        Stroke width of the marks.
-
-        **Default value:** If undefined, the default stroke width depends on `mark config
-        <https://vega.github.io/vega-lite/docs/config.html#mark-config>`__ 's
-        ``strokeWidth`` property.
-    text : :class:`TextDef`
-        Text of the ``text`` mark.
-    theta : :class:`PolarDef`
-        For arc marks, the arc length in radians if theta2 is not specified, otherwise the
-        start arc angle. (A value of 0 indicates up or “north”, increasing values proceed
-        clockwise.)
-
-        For text marks, polar coordinate angle in radians.
-    theta2 : :class:`Position2Def`
-        The end angle of arc marks in radians. A value of 0 indicates up or “north”,
-        increasing values proceed clockwise.
-    tooltip : anyOf(:class:`StringFieldDefWithCondition`, :class:`StringValueDefWithCondition`, List(:class:`StringFieldDef`), None)
-        The tooltip text to show upon mouse hover. Specifying ``tooltip`` encoding overrides
-        `the tooltip property in the mark definition
-        <https://vega.github.io/vega-lite/docs/mark.html#mark-def>`__.
-
-        See the `tooltip <https://vega.github.io/vega-lite/docs/tooltip.html>`__
-        documentation for a detailed discussion about tooltip in Vega-Lite.
-    url : anyOf(:class:`StringFieldDefWithCondition`, :class:`StringValueDefWithCondition`)
-        The URL of an image mark.
-    x : :class:`PositionDef`
-        X coordinates of the marks, or width of horizontal ``"bar"`` and ``"area"`` without
-        specified ``x2`` or ``width``.
-
-        The ``value`` of this channel can be a number or a string ``"width"`` for the width
-        of the plot.
-    x2 : :class:`Position2Def`
-        X2 coordinates for ranged ``"area"``, ``"bar"``, ``"rect"``, and  ``"rule"``.
-
-        The ``value`` of this channel can be a number or a string ``"width"`` for the width
-        of the plot.
-    xError : anyOf(:class:`SecondaryFieldDef`, :class:`ValueDefnumber`)
-        Error value of x coordinates for error specified ``"errorbar"`` and ``"errorband"``.
-    xError2 : anyOf(:class:`SecondaryFieldDef`, :class:`ValueDefnumber`)
-        Secondary error value of x coordinates for error specified ``"errorbar"`` and
-        ``"errorband"``.
-    xOffset : :class:`OffsetDef`
-        Offset of x-position of the marks
-    y : :class:`PositionDef`
-        Y coordinates of the marks, or height of vertical ``"bar"`` and ``"area"`` without
-        specified ``y2`` or ``height``.
-
-        The ``value`` of this channel can be a number or a string ``"height"`` for the
-        height of the plot.
-    y2 : :class:`Position2Def`
-        Y2 coordinates for ranged ``"area"``, ``"bar"``, ``"rect"``, and  ``"rule"``.
-
-        The ``value`` of this channel can be a number or a string ``"height"`` for the
-        height of the plot.
-    yError : anyOf(:class:`SecondaryFieldDef`, :class:`ValueDefnumber`)
-        Error value of y coordinates for error specified ``"errorbar"`` and ``"errorband"``.
-    yError2 : anyOf(:class:`SecondaryFieldDef`, :class:`ValueDefnumber`)
-        Secondary error value of y coordinates for error specified ``"errorbar"`` and
-        ``"errorband"``.
-    yOffset : :class:`OffsetDef`
-        Offset of y-position of the marks
-    """
-    _schema = {'$ref': '#/definitions/Encoding'}
-
-    def __init__(self, angle=Undefined, color=Undefined, description=Undefined, detail=Undefined,
-                 fill=Undefined, fillOpacity=Undefined, href=Undefined, key=Undefined,
-                 latitude=Undefined, latitude2=Undefined, longitude=Undefined, longitude2=Undefined,
-                 opacity=Undefined, order=Undefined, radius=Undefined, radius2=Undefined,
-                 shape=Undefined, size=Undefined, stroke=Undefined, strokeDash=Undefined,
-                 strokeOpacity=Undefined, strokeWidth=Undefined, text=Undefined, theta=Undefined,
-                 theta2=Undefined, tooltip=Undefined, url=Undefined, x=Undefined, x2=Undefined,
-                 xError=Undefined, xError2=Undefined, xOffset=Undefined, y=Undefined, y2=Undefined,
-                 yError=Undefined, yError2=Undefined, yOffset=Undefined, **kwds):
-        super(Encoding, self).__init__(angle=angle, color=color, description=description, detail=detail,
-                                       fill=fill, fillOpacity=fillOpacity, href=href, key=key,
-                                       latitude=latitude, latitude2=latitude2, longitude=longitude,
-                                       longitude2=longitude2, opacity=opacity, order=order,
-                                       radius=radius, radius2=radius2, shape=shape, size=size,
-                                       stroke=stroke, strokeDash=strokeDash,
-                                       strokeOpacity=strokeOpacity, strokeWidth=strokeWidth, text=text,
-                                       theta=theta, theta2=theta2, tooltip=tooltip, url=url, x=x, x2=x2,
-                                       xError=xError, xError2=xError2, xOffset=xOffset, y=y, y2=y2,
-                                       yError=yError, yError2=yError2, yOffset=yOffset, **kwds)
-
-
-class ErrorBand(CompositeMark):
-    """ErrorBand schema wrapper
-
-    string
-    """
-    _schema = {'$ref': '#/definitions/ErrorBand'}
-
-    def __init__(self, *args):
-        super(ErrorBand, self).__init__(*args)
-
-
-class ErrorBandConfig(VegaLiteSchema):
-    """ErrorBandConfig schema wrapper
-
-    Mapping(required=[])
-
-    Parameters
-    ----------
-
-    band : anyOf(boolean, :class:`AnyMarkConfig`)
-
-    borders : anyOf(boolean, :class:`AnyMarkConfig`)
-
-    extent : :class:`ErrorBarExtent`
-        The extent of the band. Available options include:
-
-
-        * ``"ci"`` : Extend the band to the confidence interval of the mean.
-        * ``"stderr"`` : The size of band are set to the value of standard error, extending
-          from the mean.
-        * ``"stdev"`` : The size of band are set to the value of standard deviation,
-          extending from the mean.
-        * ``"iqr"`` : Extend the band to the q1 and q3.
-
-        **Default value:** ``"stderr"``.
-    interpolate : :class:`Interpolate`
-        The line interpolation method for the error band. One of the following:
-
-
-        * ``"linear"`` : piecewise linear segments, as in a polyline.
-        * ``"linear-closed"`` : close the linear segments to form a polygon.
-        * ``"step"`` : a piecewise constant function (a step function) consisting of
-          alternating horizontal and vertical lines. The y-value changes at the midpoint of
-          each pair of adjacent x-values.
-        * ``"step-before"`` : a piecewise constant function (a step function) consisting of
-          alternating horizontal and vertical lines. The y-value changes before the x-value.
-        * ``"step-after"`` : a piecewise constant function (a step function) consisting of
-          alternating horizontal and vertical lines. The y-value changes after the x-value.
-        * ``"basis"`` : a B-spline, with control point duplication on the ends.
-        * ``"basis-open"`` : an open B-spline; may not intersect the start or end.
-        * ``"basis-closed"`` : a closed B-spline, as in a loop.
-        * ``"cardinal"`` : a Cardinal spline, with control point duplication on the ends.
-        * ``"cardinal-open"`` : an open Cardinal spline; may not intersect the start or end,
-          but will intersect other control points.
-        * ``"cardinal-closed"`` : a closed Cardinal spline, as in a loop.
-        * ``"bundle"`` : equivalent to basis, except the tension parameter is used to
-          straighten the spline.
-        * ``"monotone"`` : cubic interpolation that preserves monotonicity in y.
-    tension : float
-        The tension parameter for the interpolation type of the error band.
-    """
-    _schema = {'$ref': '#/definitions/ErrorBandConfig'}
-
-    def __init__(self, band=Undefined, borders=Undefined, extent=Undefined, interpolate=Undefined,
-                 tension=Undefined, **kwds):
-        super(ErrorBandConfig, self).__init__(band=band, borders=borders, extent=extent,
-                                              interpolate=interpolate, tension=tension, **kwds)
-
-
-class ErrorBandDef(CompositeMarkDef):
-    """ErrorBandDef schema wrapper
-
-    Mapping(required=[type])
-
-    Parameters
-    ----------
-
-    type : :class:`ErrorBand`
-        The mark type. This could a primitive mark type (one of ``"bar"``, ``"circle"``,
-        ``"square"``, ``"tick"``, ``"line"``, ``"area"``, ``"point"``, ``"geoshape"``,
-        ``"rule"``, and ``"text"`` ) or a composite mark type ( ``"boxplot"``,
-        ``"errorband"``, ``"errorbar"`` ).
-    band : anyOf(boolean, :class:`AnyMarkConfig`)
-
-    borders : anyOf(boolean, :class:`AnyMarkConfig`)
-
-    clip : boolean
-        Whether a composite mark be clipped to the enclosing group’s width and height.
-    color : anyOf(:class:`Color`, :class:`Gradient`, :class:`ExprRef`)
-        Default color.
-
-        **Default value:** :raw-html:`<span style="color: #4682b4;">&#9632;</span>`
-        ``"#4682b4"``
-
-        **Note:**
-
-
-        * This property cannot be used in a `style config
-          <https://vega.github.io/vega-lite/docs/mark.html#style-config>`__.
-        * The ``fill`` and ``stroke`` properties have higher precedence than ``color`` and
-          will override ``color``.
-    extent : :class:`ErrorBarExtent`
-        The extent of the band. Available options include:
-
-
-        * ``"ci"`` : Extend the band to the confidence interval of the mean.
-        * ``"stderr"`` : The size of band are set to the value of standard error, extending
-          from the mean.
-        * ``"stdev"`` : The size of band are set to the value of standard deviation,
-          extending from the mean.
-        * ``"iqr"`` : Extend the band to the q1 and q3.
-
-        **Default value:** ``"stderr"``.
-    interpolate : :class:`Interpolate`
-        The line interpolation method for the error band. One of the following:
-
-
-        * ``"linear"`` : piecewise linear segments, as in a polyline.
-        * ``"linear-closed"`` : close the linear segments to form a polygon.
-        * ``"step"`` : a piecewise constant function (a step function) consisting of
-          alternating horizontal and vertical lines. The y-value changes at the midpoint of
-          each pair of adjacent x-values.
-        * ``"step-before"`` : a piecewise constant function (a step function) consisting of
-          alternating horizontal and vertical lines. The y-value changes before the x-value.
-        * ``"step-after"`` : a piecewise constant function (a step function) consisting of
-          alternating horizontal and vertical lines. The y-value changes after the x-value.
-        * ``"basis"`` : a B-spline, with control point duplication on the ends.
-        * ``"basis-open"`` : an open B-spline; may not intersect the start or end.
-        * ``"basis-closed"`` : a closed B-spline, as in a loop.
-        * ``"cardinal"`` : a Cardinal spline, with control point duplication on the ends.
-        * ``"cardinal-open"`` : an open Cardinal spline; may not intersect the start or end,
-          but will intersect other control points.
-        * ``"cardinal-closed"`` : a closed Cardinal spline, as in a loop.
-        * ``"bundle"`` : equivalent to basis, except the tension parameter is used to
-          straighten the spline.
-        * ``"monotone"`` : cubic interpolation that preserves monotonicity in y.
-    opacity : float
-        The opacity (value between [0,1]) of the mark.
-    orient : :class:`Orientation`
-        Orientation of the error band. This is normally automatically determined, but can be
-        specified when the orientation is ambiguous and cannot be automatically determined.
-    tension : float
-        The tension parameter for the interpolation type of the error band.
-    """
-    _schema = {'$ref': '#/definitions/ErrorBandDef'}
-
-    def __init__(self, type=Undefined, band=Undefined, borders=Undefined, clip=Undefined,
-                 color=Undefined, extent=Undefined, interpolate=Undefined, opacity=Undefined,
-                 orient=Undefined, tension=Undefined, **kwds):
-        super(ErrorBandDef, self).__init__(type=type, band=band, borders=borders, clip=clip,
-                                           color=color, extent=extent, interpolate=interpolate,
-                                           opacity=opacity, orient=orient, tension=tension, **kwds)
-
-
-class ErrorBar(CompositeMark):
-    """ErrorBar schema wrapper
-
-    string
-    """
-    _schema = {'$ref': '#/definitions/ErrorBar'}
-
-    def __init__(self, *args):
-        super(ErrorBar, self).__init__(*args)
-
-
-class ErrorBarConfig(VegaLiteSchema):
-    """ErrorBarConfig schema wrapper
-
-    Mapping(required=[])
-
-    Parameters
-    ----------
-
-    extent : :class:`ErrorBarExtent`
-        The extent of the rule. Available options include:
-
-
-        * ``"ci"`` : Extend the rule to the confidence interval of the mean.
-        * ``"stderr"`` : The size of rule are set to the value of standard error, extending
-          from the mean.
-        * ``"stdev"`` : The size of rule are set to the value of standard deviation,
-          extending from the mean.
-        * ``"iqr"`` : Extend the rule to the q1 and q3.
-
-        **Default value:** ``"stderr"``.
-    rule : anyOf(boolean, :class:`AnyMarkConfig`)
-
-    size : float
-        Size of the ticks of an error bar
-    thickness : float
-        Thickness of the ticks and the bar of an error bar
-    ticks : anyOf(boolean, :class:`AnyMarkConfig`)
-
-    """
-    _schema = {'$ref': '#/definitions/ErrorBarConfig'}
-
-    def __init__(self, extent=Undefined, rule=Undefined, size=Undefined, thickness=Undefined,
-                 ticks=Undefined, **kwds):
-        super(ErrorBarConfig, self).__init__(extent=extent, rule=rule, size=size, thickness=thickness,
-                                             ticks=ticks, **kwds)
-
-
-class ErrorBarDef(CompositeMarkDef):
-    """ErrorBarDef schema wrapper
-
-    Mapping(required=[type])
-
-    Parameters
-    ----------
-
-    type : :class:`ErrorBar`
-        The mark type. This could a primitive mark type (one of ``"bar"``, ``"circle"``,
-        ``"square"``, ``"tick"``, ``"line"``, ``"area"``, ``"point"``, ``"geoshape"``,
-        ``"rule"``, and ``"text"`` ) or a composite mark type ( ``"boxplot"``,
-        ``"errorband"``, ``"errorbar"`` ).
-    clip : boolean
-        Whether a composite mark be clipped to the enclosing group’s width and height.
-    color : anyOf(:class:`Color`, :class:`Gradient`, :class:`ExprRef`)
-        Default color.
-
-        **Default value:** :raw-html:`<span style="color: #4682b4;">&#9632;</span>`
-        ``"#4682b4"``
-
-        **Note:**
-
-
-        * This property cannot be used in a `style config
-          <https://vega.github.io/vega-lite/docs/mark.html#style-config>`__.
-        * The ``fill`` and ``stroke`` properties have higher precedence than ``color`` and
-          will override ``color``.
-    extent : :class:`ErrorBarExtent`
-        The extent of the rule. Available options include:
-
-
-        * ``"ci"`` : Extend the rule to the confidence interval of the mean.
-        * ``"stderr"`` : The size of rule are set to the value of standard error, extending
-          from the mean.
-        * ``"stdev"`` : The size of rule are set to the value of standard deviation,
-          extending from the mean.
-        * ``"iqr"`` : Extend the rule to the q1 and q3.
-
-        **Default value:** ``"stderr"``.
-    opacity : float
-        The opacity (value between [0,1]) of the mark.
-    orient : :class:`Orientation`
-        Orientation of the error bar. This is normally automatically determined, but can be
-        specified when the orientation is ambiguous and cannot be automatically determined.
-    rule : anyOf(boolean, :class:`AnyMarkConfig`)
-
-    size : float
-        Size of the ticks of an error bar
-    thickness : float
-        Thickness of the ticks and the bar of an error bar
-    ticks : anyOf(boolean, :class:`AnyMarkConfig`)
-
-    """
-    _schema = {'$ref': '#/definitions/ErrorBarDef'}
-
-    def __init__(self, type=Undefined, clip=Undefined, color=Undefined, extent=Undefined,
-                 opacity=Undefined, orient=Undefined, rule=Undefined, size=Undefined,
-                 thickness=Undefined, ticks=Undefined, **kwds):
-        super(ErrorBarDef, self).__init__(type=type, clip=clip, color=color, extent=extent,
-                                          opacity=opacity, orient=orient, rule=rule, size=size,
-                                          thickness=thickness, ticks=ticks, **kwds)
-
-
-class ErrorBarExtent(VegaLiteSchema):
-    """ErrorBarExtent schema wrapper
-
-    enum('ci', 'iqr', 'stderr', 'stdev')
-    """
-    _schema = {'$ref': '#/definitions/ErrorBarExtent'}
-
-    def __init__(self, *args):
-        super(ErrorBarExtent, self).__init__(*args)
-
-
-class Expr(VegaLiteSchema):
-    """Expr schema wrapper
-
-    string
-    """
-    _schema = {'$ref': '#/definitions/Expr'}
-
-    def __init__(self, *args):
-        super(Expr, self).__init__(*args)
-
-
-class ExprRef(VegaLiteSchema):
-    """ExprRef schema wrapper
-
-    Mapping(required=[expr])
-
-    Parameters
-    ----------
-
-    expr : string
-        Vega expression (which can refer to Vega-Lite parameters).
-    """
-    _schema = {'$ref': '#/definitions/ExprRef'}
-
-    def __init__(self, expr=Undefined, **kwds):
-        super(ExprRef, self).__init__(expr=expr, **kwds)
-
-
-class FacetEncodingFieldDef(VegaLiteSchema):
-    """FacetEncodingFieldDef schema wrapper
-
-    Mapping(required=[])
-
-    Parameters
-    ----------
-
-    aggregate : :class:`Aggregate`
-        Aggregation function for the field (e.g., ``"mean"``, ``"sum"``, ``"median"``,
-        ``"min"``, ``"max"``, ``"count"`` ).
-
-        **Default value:** ``undefined`` (None)
-
-        **See also:** `aggregate <https://vega.github.io/vega-lite/docs/aggregate.html>`__
-        documentation.
-    align : anyOf(:class:`LayoutAlign`, :class:`RowColLayoutAlign`)
-        The alignment to apply to grid rows and columns. The supported string values are
-        ``"all"``, ``"each"``, and ``"none"``.
-
-
-        * For ``"none"``, a flow layout will be used, in which adjacent subviews are simply
-          placed one after the other.
-        * For ``"each"``, subviews will be aligned into a clean grid structure, but each row
-          or column may be of variable size.
-        * For ``"all"``, subviews will be aligned and each row or column will be sized
-          identically based on the maximum observed size. String values for this property
-          will be applied to both grid rows and columns.
-
-        Alternatively, an object value of the form ``{"row": string, "column": string}`` can
-        be used to supply different alignments for rows and columns.
-
-        **Default value:** ``"all"``.
-    bandPosition : float
-        Relative position on a band of a stacked, binned, time unit, or band scale. For
-        example, the marks will be positioned at the beginning of the band if set to ``0``,
-        and at the middle of the band if set to ``0.5``.
-    bin : anyOf(boolean, :class:`BinParams`, None)
-        A flag for binning a ``quantitative`` field, `an object defining binning parameters
-        <https://vega.github.io/vega-lite/docs/bin.html#bin-parameters>`__, or indicating
-        that the data for ``x`` or ``y`` channel are binned before they are imported into
-        Vega-Lite ( ``"binned"`` ).
-
-
-        If ``true``, default `binning parameters
-        <https://vega.github.io/vega-lite/docs/bin.html#bin-parameters>`__ will be applied.
-
-        If ``"binned"``, this indicates that the data for the ``x`` (or ``y`` ) channel are
-        already binned. You can map the bin-start field to ``x`` (or ``y`` ) and the bin-end
-        field to ``x2`` (or ``y2`` ). The scale and axis will be formatted similar to
-        binning in Vega-Lite.  To adjust the axis ticks based on the bin step, you can also
-        set the axis's `tickMinStep
-        <https://vega.github.io/vega-lite/docs/axis.html#ticks>`__ property.
-
-        **Default value:** ``false``
-
-        **See also:** `bin <https://vega.github.io/vega-lite/docs/bin.html>`__
-        documentation.
-    bounds : enum('full', 'flush')
-        The bounds calculation method to use for determining the extent of a sub-plot. One
-        of ``full`` (the default) or ``flush``.
-
-
-        * If set to ``full``, the entire calculated bounds (including axes, title, and
-          legend) will be used.
-        * If set to ``flush``, only the specified width and height values for the sub-view
-          will be used. The ``flush`` setting can be useful when attempting to place
-          sub-plots without axes or legends into a uniform grid structure.
-
-        **Default value:** ``"full"``
-    center : anyOf(boolean, :class:`RowColboolean`)
-        Boolean flag indicating if subviews should be centered relative to their respective
-        rows or columns.
-
-        An object value of the form ``{"row": boolean, "column": boolean}`` can be used to
-        supply different centering values for rows and columns.
-
-        **Default value:** ``false``
-    columns : float
-        The number of columns to include in the view composition layout.
-
-        **Default value** : ``undefined`` -- An infinite number of columns (a single row)
-        will be assumed. This is equivalent to ``hconcat`` (for ``concat`` ) and to using
-        the ``column`` channel (for ``facet`` and ``repeat`` ).
-
-        **Note** :
-
-        1) This property is only for:
-
-
-        * the general (wrappable) ``concat`` operator (not ``hconcat`` / ``vconcat`` )
-        * the ``facet`` and ``repeat`` operator with one field/repetition definition
-          (without row/column nesting)
-
-        2) Setting the ``columns`` to ``1`` is equivalent to ``vconcat`` (for ``concat`` )
-        and to using the ``row`` channel (for ``facet`` and ``repeat`` ).
-    field : :class:`Field`
-        **Required.** A string defining the name of the field from which to pull a data
-        value or an object defining iterated values from the `repeat
-        <https://vega.github.io/vega-lite/docs/repeat.html>`__ operator.
-
-        **See also:** `field <https://vega.github.io/vega-lite/docs/field.html>`__
-        documentation.
-
-        **Notes:** 1)  Dots ( ``.`` ) and brackets ( ``[`` and ``]`` ) can be used to access
-        nested objects (e.g., ``"field": "foo.bar"`` and ``"field": "foo['bar']"`` ). If
-        field names contain dots or brackets but are not nested, you can use ``\\`` to
-        escape dots and brackets (e.g., ``"a\\.b"`` and ``"a\\[0\\]"`` ). See more details
-        about escaping in the `field documentation
-        <https://vega.github.io/vega-lite/docs/field.html>`__. 2) ``field`` is not required
-        if ``aggregate`` is ``count``.
-    header : anyOf(:class:`Header`, None)
-        An object defining properties of a facet's header.
-    sort : anyOf(:class:`SortArray`, :class:`SortOrder`, :class:`EncodingSortField`, None)
-        Sort order for the encoded field.
-
-        For continuous fields (quantitative or temporal), ``sort`` can be either
-        ``"ascending"`` or ``"descending"``.
-
-        For discrete fields, ``sort`` can be one of the following:
-
-
-        * ``"ascending"`` or ``"descending"`` -- for sorting by the values' natural order in
-          JavaScript.
-        * `A sort field definition
-          <https://vega.github.io/vega-lite/docs/sort.html#sort-field>`__ for sorting by
-          another field.
-        * `An array specifying the field values in preferred order
-          <https://vega.github.io/vega-lite/docs/sort.html#sort-array>`__. In this case, the
-          sort order will obey the values in the array, followed by any unspecified values
-          in their original order. For discrete time field, values in the sort array can be
-          `date-time definition objects
-          <https://vega.github.io/vega-lite/docs/datetime.html>`__. In addition, for time
-          units ``"month"`` and ``"day"``, the values can be the month or day names (case
-          insensitive) or their 3-letter initials (e.g., ``"Mon"``, ``"Tue"`` ).
-        * ``null`` indicating no sort.
-
-        **Default value:** ``"ascending"``
-
-        **Note:** ``null`` is not supported for ``row`` and ``column``.
-    spacing : anyOf(float, :class:`RowColnumber`)
-        The spacing in pixels between sub-views of the composition operator. An object of
-        the form ``{"row": number, "column": number}`` can be used to set different spacing
-        values for rows and columns.
-
-        **Default value** : Depends on ``"spacing"`` property of `the view composition
-        configuration <https://vega.github.io/vega-lite/docs/config.html#view-config>`__ (
-        ``20`` by default)
-    timeUnit : anyOf(:class:`TimeUnit`, :class:`BinnedTimeUnit`, :class:`TimeUnitParams`)
-        Time unit (e.g., ``year``, ``yearmonth``, ``month``, ``hours`` ) for a temporal
-        field. or `a temporal field that gets casted as ordinal
-        <https://vega.github.io/vega-lite/docs/type.html#cast>`__.
-
-        **Default value:** ``undefined`` (None)
-
-        **See also:** `timeUnit <https://vega.github.io/vega-lite/docs/timeunit.html>`__
-        documentation.
-    title : anyOf(:class:`Text`, None)
-        A title for the field. If ``null``, the title will be removed.
-
-        **Default value:**  derived from the field's name and transformation function (
-        ``aggregate``, ``bin`` and ``timeUnit`` ). If the field has an aggregate function,
-        the function is displayed as part of the title (e.g., ``"Sum of Profit"`` ). If the
-        field is binned or has a time unit applied, the applied function is shown in
-        parentheses (e.g., ``"Profit (binned)"``, ``"Transaction Date (year-month)"`` ).
-        Otherwise, the title is simply the field name.
-
-        **Notes** :
-
-        1) You can customize the default field title format by providing the `fieldTitle
-        <https://vega.github.io/vega-lite/docs/config.html#top-level-config>`__ property in
-        the `config <https://vega.github.io/vega-lite/docs/config.html>`__ or `fieldTitle
-        function via the compile function's options
-        <https://vega.github.io/vega-lite/usage/compile.html#field-title>`__.
-
-        2) If both field definition's ``title`` and axis, header, or legend ``title`` are
-        defined, axis/header/legend title will be used.
-    type : :class:`StandardType`
-        The type of measurement ( ``"quantitative"``, ``"temporal"``, ``"ordinal"``, or
-        ``"nominal"`` ) for the encoded field or constant value ( ``datum`` ). It can also
-        be a ``"geojson"`` type for encoding `'geoshape'
-        <https://vega.github.io/vega-lite/docs/geoshape.html>`__.
-
-        Vega-Lite automatically infers data types in many cases as discussed below. However,
-        type is required for a field if: (1) the field is not nominal and the field encoding
-        has no specified ``aggregate`` (except ``argmin`` and ``argmax`` ), ``bin``, scale
-        type, custom ``sort`` order, nor ``timeUnit`` or (2) if you wish to use an ordinal
-        scale for a field with ``bin`` or ``timeUnit``.
-
-        **Default value:**
-
-        1) For a data ``field``, ``"nominal"`` is the default data type unless the field
-        encoding has ``aggregate``, ``channel``, ``bin``, scale type, ``sort``, or
-        ``timeUnit`` that satisfies the following criteria:
-
-
-        * ``"quantitative"`` is the default type if (1) the encoded field contains ``bin``
-          or ``aggregate`` except ``"argmin"`` and ``"argmax"``, (2) the encoding channel is
-          ``latitude`` or ``longitude`` channel or (3) if the specified scale type is `a
-          quantitative scale <https://vega.github.io/vega-lite/docs/scale.html#type>`__.
-        * ``"temporal"`` is the default type if (1) the encoded field contains ``timeUnit``
-          or (2) the specified scale type is a time or utc scale
-        * ``"ordinal"`` is the default type if (1) the encoded field contains a `custom sort
-          order
-          <https://vega.github.io/vega-lite/docs/sort.html#specifying-custom-sort-order>`__,
-          (2) the specified scale type is an ordinal/point/band scale, or (3) the encoding
-          channel is ``order``.
-
-        2) For a constant value in data domain ( ``datum`` ):
-
-
-        * ``"quantitative"`` if the datum is a number
-        * ``"nominal"`` if the datum is a string
-        * ``"temporal"`` if the datum is `a date time object
-          <https://vega.github.io/vega-lite/docs/datetime.html>`__
-
-        **Note:**
-
-
-        * Data ``type`` describes the semantics of the data rather than the primitive data
-          types (number, string, etc.). The same primitive data type can have different
-          types of measurement. For example, numeric data can represent quantitative,
-          ordinal, or nominal data.
-        * Data values for a temporal field can be either a date-time string (e.g.,
-          ``"2015-03-07 12:32:17"``, ``"17:01"``, ``"2015-03-16"``. ``"2015"`` ) or a
-          timestamp number (e.g., ``1552199579097`` ).
-        * When using with `bin <https://vega.github.io/vega-lite/docs/bin.html>`__, the
-          ``type`` property can be either ``"quantitative"`` (for using a linear bin scale)
-          or `"ordinal" (for using an ordinal bin scale)
-          <https://vega.github.io/vega-lite/docs/type.html#cast-bin>`__.
-        * When using with `timeUnit
-          <https://vega.github.io/vega-lite/docs/timeunit.html>`__, the ``type`` property
-          can be either ``"temporal"`` (default, for using a temporal scale) or `"ordinal"
-          (for using an ordinal scale)
-          <https://vega.github.io/vega-lite/docs/type.html#cast-bin>`__.
-        * When using with `aggregate
-          <https://vega.github.io/vega-lite/docs/aggregate.html>`__, the ``type`` property
-          refers to the post-aggregation data type. For example, we can calculate count
-          ``distinct`` of a categorical field ``"cat"`` using ``{"aggregate": "distinct",
-          "field": "cat"}``. The ``"type"`` of the aggregate output is ``"quantitative"``.
-        * Secondary channels (e.g., ``x2``, ``y2``, ``xError``, ``yError`` ) do not have
-          ``type`` as they must have exactly the same type as their primary channels (e.g.,
-          ``x``, ``y`` ).
-
-        **See also:** `type <https://vega.github.io/vega-lite/docs/type.html>`__
-        documentation.
-    """
-    _schema = {'$ref': '#/definitions/FacetEncodingFieldDef'}
-
-    def __init__(self, aggregate=Undefined, align=Undefined, bandPosition=Undefined, bin=Undefined,
-                 bounds=Undefined, center=Undefined, columns=Undefined, field=Undefined,
-                 header=Undefined, sort=Undefined, spacing=Undefined, timeUnit=Undefined,
-                 title=Undefined, type=Undefined, **kwds):
-        super(FacetEncodingFieldDef, self).__init__(aggregate=aggregate, align=align,
-                                                    bandPosition=bandPosition, bin=bin, bounds=bounds,
-                                                    center=center, columns=columns, field=field,
-                                                    header=header, sort=sort, spacing=spacing,
-                                                    timeUnit=timeUnit, title=title, type=type, **kwds)
-
-
-class FacetFieldDef(VegaLiteSchema):
-    """FacetFieldDef schema wrapper
-
-    Mapping(required=[])
-
-    Parameters
-    ----------
-
-    aggregate : :class:`Aggregate`
-        Aggregation function for the field (e.g., ``"mean"``, ``"sum"``, ``"median"``,
-        ``"min"``, ``"max"``, ``"count"`` ).
-
-        **Default value:** ``undefined`` (None)
-
-        **See also:** `aggregate <https://vega.github.io/vega-lite/docs/aggregate.html>`__
-        documentation.
-    bandPosition : float
-        Relative position on a band of a stacked, binned, time unit, or band scale. For
-        example, the marks will be positioned at the beginning of the band if set to ``0``,
-        and at the middle of the band if set to ``0.5``.
-    bin : anyOf(boolean, :class:`BinParams`, None)
-        A flag for binning a ``quantitative`` field, `an object defining binning parameters
-        <https://vega.github.io/vega-lite/docs/bin.html#bin-parameters>`__, or indicating
-        that the data for ``x`` or ``y`` channel are binned before they are imported into
-        Vega-Lite ( ``"binned"`` ).
-
-
-        If ``true``, default `binning parameters
-        <https://vega.github.io/vega-lite/docs/bin.html#bin-parameters>`__ will be applied.
-
-        If ``"binned"``, this indicates that the data for the ``x`` (or ``y`` ) channel are
-        already binned. You can map the bin-start field to ``x`` (or ``y`` ) and the bin-end
-        field to ``x2`` (or ``y2`` ). The scale and axis will be formatted similar to
-        binning in Vega-Lite.  To adjust the axis ticks based on the bin step, you can also
-        set the axis's `tickMinStep
-        <https://vega.github.io/vega-lite/docs/axis.html#ticks>`__ property.
-
-        **Default value:** ``false``
-
-        **See also:** `bin <https://vega.github.io/vega-lite/docs/bin.html>`__
-        documentation.
-    field : :class:`Field`
-        **Required.** A string defining the name of the field from which to pull a data
-        value or an object defining iterated values from the `repeat
-        <https://vega.github.io/vega-lite/docs/repeat.html>`__ operator.
-
-        **See also:** `field <https://vega.github.io/vega-lite/docs/field.html>`__
-        documentation.
-
-        **Notes:** 1)  Dots ( ``.`` ) and brackets ( ``[`` and ``]`` ) can be used to access
-        nested objects (e.g., ``"field": "foo.bar"`` and ``"field": "foo['bar']"`` ). If
-        field names contain dots or brackets but are not nested, you can use ``\\`` to
-        escape dots and brackets (e.g., ``"a\\.b"`` and ``"a\\[0\\]"`` ). See more details
-        about escaping in the `field documentation
-        <https://vega.github.io/vega-lite/docs/field.html>`__. 2) ``field`` is not required
-        if ``aggregate`` is ``count``.
-    header : anyOf(:class:`Header`, None)
-        An object defining properties of a facet's header.
-    sort : anyOf(:class:`SortArray`, :class:`SortOrder`, :class:`EncodingSortField`, None)
-        Sort order for the encoded field.
-
-        For continuous fields (quantitative or temporal), ``sort`` can be either
-        ``"ascending"`` or ``"descending"``.
-
-        For discrete fields, ``sort`` can be one of the following:
-
-
-        * ``"ascending"`` or ``"descending"`` -- for sorting by the values' natural order in
-          JavaScript.
-        * `A sort field definition
-          <https://vega.github.io/vega-lite/docs/sort.html#sort-field>`__ for sorting by
-          another field.
-        * `An array specifying the field values in preferred order
-          <https://vega.github.io/vega-lite/docs/sort.html#sort-array>`__. In this case, the
-          sort order will obey the values in the array, followed by any unspecified values
-          in their original order. For discrete time field, values in the sort array can be
-          `date-time definition objects
-          <https://vega.github.io/vega-lite/docs/datetime.html>`__. In addition, for time
-          units ``"month"`` and ``"day"``, the values can be the month or day names (case
-          insensitive) or their 3-letter initials (e.g., ``"Mon"``, ``"Tue"`` ).
-        * ``null`` indicating no sort.
-
-        **Default value:** ``"ascending"``
-
-        **Note:** ``null`` is not supported for ``row`` and ``column``.
-    timeUnit : anyOf(:class:`TimeUnit`, :class:`BinnedTimeUnit`, :class:`TimeUnitParams`)
-        Time unit (e.g., ``year``, ``yearmonth``, ``month``, ``hours`` ) for a temporal
-        field. or `a temporal field that gets casted as ordinal
-        <https://vega.github.io/vega-lite/docs/type.html#cast>`__.
-
-        **Default value:** ``undefined`` (None)
-
-        **See also:** `timeUnit <https://vega.github.io/vega-lite/docs/timeunit.html>`__
-        documentation.
-    title : anyOf(:class:`Text`, None)
-        A title for the field. If ``null``, the title will be removed.
-
-        **Default value:**  derived from the field's name and transformation function (
-        ``aggregate``, ``bin`` and ``timeUnit`` ). If the field has an aggregate function,
-        the function is displayed as part of the title (e.g., ``"Sum of Profit"`` ). If the
-        field is binned or has a time unit applied, the applied function is shown in
-        parentheses (e.g., ``"Profit (binned)"``, ``"Transaction Date (year-month)"`` ).
-        Otherwise, the title is simply the field name.
-
-        **Notes** :
-
-        1) You can customize the default field title format by providing the `fieldTitle
-        <https://vega.github.io/vega-lite/docs/config.html#top-level-config>`__ property in
-        the `config <https://vega.github.io/vega-lite/docs/config.html>`__ or `fieldTitle
-        function via the compile function's options
-        <https://vega.github.io/vega-lite/usage/compile.html#field-title>`__.
-
-        2) If both field definition's ``title`` and axis, header, or legend ``title`` are
-        defined, axis/header/legend title will be used.
-    type : :class:`StandardType`
-        The type of measurement ( ``"quantitative"``, ``"temporal"``, ``"ordinal"``, or
-        ``"nominal"`` ) for the encoded field or constant value ( ``datum`` ). It can also
-        be a ``"geojson"`` type for encoding `'geoshape'
-        <https://vega.github.io/vega-lite/docs/geoshape.html>`__.
-
-        Vega-Lite automatically infers data types in many cases as discussed below. However,
-        type is required for a field if: (1) the field is not nominal and the field encoding
-        has no specified ``aggregate`` (except ``argmin`` and ``argmax`` ), ``bin``, scale
-        type, custom ``sort`` order, nor ``timeUnit`` or (2) if you wish to use an ordinal
-        scale for a field with ``bin`` or ``timeUnit``.
-
-        **Default value:**
-
-        1) For a data ``field``, ``"nominal"`` is the default data type unless the field
-        encoding has ``aggregate``, ``channel``, ``bin``, scale type, ``sort``, or
-        ``timeUnit`` that satisfies the following criteria:
-
-
-        * ``"quantitative"`` is the default type if (1) the encoded field contains ``bin``
-          or ``aggregate`` except ``"argmin"`` and ``"argmax"``, (2) the encoding channel is
-          ``latitude`` or ``longitude`` channel or (3) if the specified scale type is `a
-          quantitative scale <https://vega.github.io/vega-lite/docs/scale.html#type>`__.
-        * ``"temporal"`` is the default type if (1) the encoded field contains ``timeUnit``
-          or (2) the specified scale type is a time or utc scale
-        * ``"ordinal"`` is the default type if (1) the encoded field contains a `custom sort
-          order
-          <https://vega.github.io/vega-lite/docs/sort.html#specifying-custom-sort-order>`__,
-          (2) the specified scale type is an ordinal/point/band scale, or (3) the encoding
-          channel is ``order``.
-
-        2) For a constant value in data domain ( ``datum`` ):
-
-
-        * ``"quantitative"`` if the datum is a number
-        * ``"nominal"`` if the datum is a string
-        * ``"temporal"`` if the datum is `a date time object
-          <https://vega.github.io/vega-lite/docs/datetime.html>`__
-
-        **Note:**
-
-
-        * Data ``type`` describes the semantics of the data rather than the primitive data
-          types (number, string, etc.). The same primitive data type can have different
-          types of measurement. For example, numeric data can represent quantitative,
-          ordinal, or nominal data.
-        * Data values for a temporal field can be either a date-time string (e.g.,
-          ``"2015-03-07 12:32:17"``, ``"17:01"``, ``"2015-03-16"``. ``"2015"`` ) or a
-          timestamp number (e.g., ``1552199579097`` ).
-        * When using with `bin <https://vega.github.io/vega-lite/docs/bin.html>`__, the
-          ``type`` property can be either ``"quantitative"`` (for using a linear bin scale)
-          or `"ordinal" (for using an ordinal bin scale)
-          <https://vega.github.io/vega-lite/docs/type.html#cast-bin>`__.
-        * When using with `timeUnit
-          <https://vega.github.io/vega-lite/docs/timeunit.html>`__, the ``type`` property
-          can be either ``"temporal"`` (default, for using a temporal scale) or `"ordinal"
-          (for using an ordinal scale)
-          <https://vega.github.io/vega-lite/docs/type.html#cast-bin>`__.
-        * When using with `aggregate
-          <https://vega.github.io/vega-lite/docs/aggregate.html>`__, the ``type`` property
-          refers to the post-aggregation data type. For example, we can calculate count
-          ``distinct`` of a categorical field ``"cat"`` using ``{"aggregate": "distinct",
-          "field": "cat"}``. The ``"type"`` of the aggregate output is ``"quantitative"``.
-        * Secondary channels (e.g., ``x2``, ``y2``, ``xError``, ``yError`` ) do not have
-          ``type`` as they must have exactly the same type as their primary channels (e.g.,
-          ``x``, ``y`` ).
-
-        **See also:** `type <https://vega.github.io/vega-lite/docs/type.html>`__
-        documentation.
-    """
-    _schema = {'$ref': '#/definitions/FacetFieldDef'}
-
-    def __init__(self, aggregate=Undefined, bandPosition=Undefined, bin=Undefined, field=Undefined,
-                 header=Undefined, sort=Undefined, timeUnit=Undefined, title=Undefined, type=Undefined,
-                 **kwds):
-        super(FacetFieldDef, self).__init__(aggregate=aggregate, bandPosition=bandPosition, bin=bin,
-                                            field=field, header=header, sort=sort, timeUnit=timeUnit,
-                                            title=title, type=type, **kwds)
-
-
-class FacetMapping(VegaLiteSchema):
-    """FacetMapping schema wrapper
-
-    Mapping(required=[])
-
-    Parameters
-    ----------
-
-    column : :class:`FacetFieldDef`
-        A field definition for the horizontal facet of trellis plots.
-    row : :class:`FacetFieldDef`
-        A field definition for the vertical facet of trellis plots.
-    """
-    _schema = {'$ref': '#/definitions/FacetMapping'}
-
-    def __init__(self, column=Undefined, row=Undefined, **kwds):
-        super(FacetMapping, self).__init__(column=column, row=row, **kwds)
-
-
-class FacetedEncoding(VegaLiteSchema):
-    """FacetedEncoding schema wrapper
-
-    Mapping(required=[])
-
-    Parameters
-    ----------
-
-    angle : :class:`NumericMarkPropDef`
-        Rotation angle of point and text marks.
-    color : :class:`ColorDef`
-        Color of the marks – either fill or stroke color based on  the ``filled`` property
-        of mark definition. By default, ``color`` represents fill color for ``"area"``,
-        ``"bar"``, ``"tick"``, ``"text"``, ``"trail"``, ``"circle"``, and ``"square"`` /
-        stroke color for ``"line"`` and ``"point"``.
-
-        **Default value:** If undefined, the default color depends on `mark config
-        <https://vega.github.io/vega-lite/docs/config.html#mark-config>`__ 's ``color``
-        property.
-
-        *Note:* 1) For fine-grained control over both fill and stroke colors of the marks,
-        please use the ``fill`` and ``stroke`` channels. The ``fill`` or ``stroke``
-        encodings have higher precedence than ``color``, thus may override the ``color``
-        encoding if conflicting encodings are specified. 2) See the scale documentation for
-        more information about customizing `color scheme
-        <https://vega.github.io/vega-lite/docs/scale.html#scheme>`__.
-    column : :class:`RowColumnEncodingFieldDef`
-        A field definition for the horizontal facet of trellis plots.
-    description : anyOf(:class:`StringFieldDefWithCondition`, :class:`StringValueDefWithCondition`)
-        A text description of this mark for ARIA accessibility (SVG output only). For SVG
-        output the ``"aria-label"`` attribute will be set to this description.
-    detail : anyOf(:class:`FieldDefWithoutScale`, List(:class:`FieldDefWithoutScale`))
-        Additional levels of detail for grouping data in aggregate views and in line, trail,
-        and area marks without mapping data to a specific visual channel.
-    facet : :class:`FacetEncodingFieldDef`
-        A field definition for the (flexible) facet of trellis plots.
-
-        If either ``row`` or ``column`` is specified, this channel will be ignored.
-    fill : :class:`ColorDef`
-        Fill color of the marks. **Default value:** If undefined, the default color depends
-        on `mark config <https://vega.github.io/vega-lite/docs/config.html#mark-config>`__
-        's ``color`` property.
-
-        *Note:* The ``fill`` encoding has higher precedence than ``color``, thus may
-        override the ``color`` encoding if conflicting encodings are specified.
-    fillOpacity : :class:`NumericMarkPropDef`
-        Fill opacity of the marks.
-
-        **Default value:** If undefined, the default opacity depends on `mark config
-        <https://vega.github.io/vega-lite/docs/config.html#mark-config>`__ 's
-        ``fillOpacity`` property.
-    href : anyOf(:class:`StringFieldDefWithCondition`, :class:`StringValueDefWithCondition`)
-        A URL to load upon mouse click.
-    key : :class:`FieldDefWithoutScale`
-        A data field to use as a unique key for data binding. When a visualization’s data is
-        updated, the key value will be used to match data elements to existing mark
-        instances. Use a key channel to enable object constancy for transitions over dynamic
-        data.
-    latitude : :class:`LatLongDef`
-        Latitude position of geographically projected marks.
-    latitude2 : :class:`Position2Def`
-        Latitude-2 position for geographically projected ranged ``"area"``, ``"bar"``,
-        ``"rect"``, and  ``"rule"``.
-    longitude : :class:`LatLongDef`
-        Longitude position of geographically projected marks.
-    longitude2 : :class:`Position2Def`
-        Longitude-2 position for geographically projected ranged ``"area"``, ``"bar"``,
-        ``"rect"``, and  ``"rule"``.
-    opacity : :class:`NumericMarkPropDef`
-        Opacity of the marks.
-
-        **Default value:** If undefined, the default opacity depends on `mark config
-        <https://vega.github.io/vega-lite/docs/config.html#mark-config>`__ 's ``opacity``
-        property.
-    order : anyOf(:class:`OrderFieldDef`, List(:class:`OrderFieldDef`), :class:`OrderValueDef`, :class:`OrderOnlyDef`)
-        Order of the marks.
-
-
-        * For stacked marks, this ``order`` channel encodes `stack order
-          <https://vega.github.io/vega-lite/docs/stack.html#order>`__.
-        * For line and trail marks, this ``order`` channel encodes order of data points in
-          the lines. This can be useful for creating `a connected scatterplot
-          <https://vega.github.io/vega-lite/examples/connected_scatterplot.html>`__. Setting
-          ``order`` to ``{"value": null}`` makes the line marks use the original order in
-          the data sources.
-        * Otherwise, this ``order`` channel encodes layer order of the marks.
-
-        **Note** : In aggregate plots, ``order`` field should be ``aggregate`` d to avoid
-        creating additional aggregation grouping.
-    radius : :class:`PolarDef`
-        The outer radius in pixels of arc marks.
-    radius2 : :class:`Position2Def`
-        The inner radius in pixels of arc marks.
-    row : :class:`RowColumnEncodingFieldDef`
-        A field definition for the vertical facet of trellis plots.
-    shape : :class:`ShapeDef`
-        Shape of the mark.
-
-
-        #.
-        For ``point`` marks the supported values include:   - plotting shapes: ``"circle"``,
-        ``"square"``, ``"cross"``, ``"diamond"``, ``"triangle-up"``, ``"triangle-down"``,
-        ``"triangle-right"``, or ``"triangle-left"``.   - the line symbol ``"stroke"``   -
-        centered directional shapes ``"arrow"``, ``"wedge"``, or ``"triangle"``   - a custom
-        `SVG path string
-        <https://developer.mozilla.org/en-US/docs/Web/SVG/Tutorial/Paths>`__ (For correct
-        sizing, custom shape paths should be defined within a square bounding box with
-        coordinates ranging from -1 to 1 along both the x and y dimensions.)
-
-        #.
-        For ``geoshape`` marks it should be a field definition of the geojson data
-
-        **Default value:** If undefined, the default shape depends on `mark config
-        <https://vega.github.io/vega-lite/docs/config.html#point-config>`__ 's ``shape``
-        property. ( ``"circle"`` if unset.)
-    size : :class:`NumericMarkPropDef`
-        Size of the mark.
-
-
-        * For ``"point"``, ``"square"`` and ``"circle"``, – the symbol size, or pixel area
-          of the mark.
-        * For ``"bar"`` and ``"tick"`` – the bar and tick's size.
-        * For ``"text"`` – the text's font size.
-        * Size is unsupported for ``"line"``, ``"area"``, and ``"rect"``. (Use ``"trail"``
-          instead of line with varying size)
-    stroke : :class:`ColorDef`
-        Stroke color of the marks. **Default value:** If undefined, the default color
-        depends on `mark config
-        <https://vega.github.io/vega-lite/docs/config.html#mark-config>`__ 's ``color``
-        property.
-
-        *Note:* The ``stroke`` encoding has higher precedence than ``color``, thus may
-        override the ``color`` encoding if conflicting encodings are specified.
-    strokeDash : :class:`NumericArrayMarkPropDef`
-        Stroke dash of the marks.
-
-        **Default value:** ``[1,0]`` (No dash).
-    strokeOpacity : :class:`NumericMarkPropDef`
-        Stroke opacity of the marks.
-
-        **Default value:** If undefined, the default opacity depends on `mark config
-        <https://vega.github.io/vega-lite/docs/config.html#mark-config>`__ 's
-        ``strokeOpacity`` property.
-    strokeWidth : :class:`NumericMarkPropDef`
-        Stroke width of the marks.
-
-        **Default value:** If undefined, the default stroke width depends on `mark config
-        <https://vega.github.io/vega-lite/docs/config.html#mark-config>`__ 's
-        ``strokeWidth`` property.
-    text : :class:`TextDef`
-        Text of the ``text`` mark.
-    theta : :class:`PolarDef`
-        For arc marks, the arc length in radians if theta2 is not specified, otherwise the
-        start arc angle. (A value of 0 indicates up or “north”, increasing values proceed
-        clockwise.)
-
-        For text marks, polar coordinate angle in radians.
-    theta2 : :class:`Position2Def`
-        The end angle of arc marks in radians. A value of 0 indicates up or “north”,
-        increasing values proceed clockwise.
-    tooltip : anyOf(:class:`StringFieldDefWithCondition`, :class:`StringValueDefWithCondition`, List(:class:`StringFieldDef`), None)
-        The tooltip text to show upon mouse hover. Specifying ``tooltip`` encoding overrides
-        `the tooltip property in the mark definition
-        <https://vega.github.io/vega-lite/docs/mark.html#mark-def>`__.
-
-        See the `tooltip <https://vega.github.io/vega-lite/docs/tooltip.html>`__
-        documentation for a detailed discussion about tooltip in Vega-Lite.
-    url : anyOf(:class:`StringFieldDefWithCondition`, :class:`StringValueDefWithCondition`)
-        The URL of an image mark.
-    x : :class:`PositionDef`
-        X coordinates of the marks, or width of horizontal ``"bar"`` and ``"area"`` without
-        specified ``x2`` or ``width``.
-
-        The ``value`` of this channel can be a number or a string ``"width"`` for the width
-        of the plot.
-    x2 : :class:`Position2Def`
-        X2 coordinates for ranged ``"area"``, ``"bar"``, ``"rect"``, and  ``"rule"``.
-
-        The ``value`` of this channel can be a number or a string ``"width"`` for the width
-        of the plot.
-    xError : anyOf(:class:`SecondaryFieldDef`, :class:`ValueDefnumber`)
-        Error value of x coordinates for error specified ``"errorbar"`` and ``"errorband"``.
-    xError2 : anyOf(:class:`SecondaryFieldDef`, :class:`ValueDefnumber`)
-        Secondary error value of x coordinates for error specified ``"errorbar"`` and
-        ``"errorband"``.
-    xOffset : :class:`OffsetDef`
-        Offset of x-position of the marks
-    y : :class:`PositionDef`
-        Y coordinates of the marks, or height of vertical ``"bar"`` and ``"area"`` without
-        specified ``y2`` or ``height``.
-
-        The ``value`` of this channel can be a number or a string ``"height"`` for the
-        height of the plot.
-    y2 : :class:`Position2Def`
-        Y2 coordinates for ranged ``"area"``, ``"bar"``, ``"rect"``, and  ``"rule"``.
-
-        The ``value`` of this channel can be a number or a string ``"height"`` for the
-        height of the plot.
-    yError : anyOf(:class:`SecondaryFieldDef`, :class:`ValueDefnumber`)
-        Error value of y coordinates for error specified ``"errorbar"`` and ``"errorband"``.
-    yError2 : anyOf(:class:`SecondaryFieldDef`, :class:`ValueDefnumber`)
-        Secondary error value of y coordinates for error specified ``"errorbar"`` and
-        ``"errorband"``.
-    yOffset : :class:`OffsetDef`
-        Offset of y-position of the marks
-    """
-    _schema = {'$ref': '#/definitions/FacetedEncoding'}
-
-    def __init__(self, angle=Undefined, color=Undefined, column=Undefined, description=Undefined,
-                 detail=Undefined, facet=Undefined, fill=Undefined, fillOpacity=Undefined,
-                 href=Undefined, key=Undefined, latitude=Undefined, latitude2=Undefined,
-                 longitude=Undefined, longitude2=Undefined, opacity=Undefined, order=Undefined,
-                 radius=Undefined, radius2=Undefined, row=Undefined, shape=Undefined, size=Undefined,
-                 stroke=Undefined, strokeDash=Undefined, strokeOpacity=Undefined, strokeWidth=Undefined,
-                 text=Undefined, theta=Undefined, theta2=Undefined, tooltip=Undefined, url=Undefined,
-                 x=Undefined, x2=Undefined, xError=Undefined, xError2=Undefined, xOffset=Undefined,
-                 y=Undefined, y2=Undefined, yError=Undefined, yError2=Undefined, yOffset=Undefined,
-                 **kwds):
-        super(FacetedEncoding, self).__init__(angle=angle, color=color, column=column,
-                                              description=description, detail=detail, facet=facet,
-                                              fill=fill, fillOpacity=fillOpacity, href=href, key=key,
-                                              latitude=latitude, latitude2=latitude2,
-                                              longitude=longitude, longitude2=longitude2,
-                                              opacity=opacity, order=order, radius=radius,
-                                              radius2=radius2, row=row, shape=shape, size=size,
-                                              stroke=stroke, strokeDash=strokeDash,
-                                              strokeOpacity=strokeOpacity, strokeWidth=strokeWidth,
-                                              text=text, theta=theta, theta2=theta2, tooltip=tooltip,
-                                              url=url, x=x, x2=x2, xError=xError, xError2=xError2,
-                                              xOffset=xOffset, y=y, y2=y2, yError=yError,
-                                              yError2=yError2, yOffset=yOffset, **kwds)
-
-
-class Feature(VegaLiteSchema):
-    """Feature schema wrapper
-
-    Mapping(required=[geometry, properties, type])
-    A feature object which contains a geometry and associated properties.
-    https://tools.ietf.org/html/rfc7946#section-3.2
-
-    Parameters
-    ----------
-
-    geometry : :class:`Geometry`
-        The feature's geometry
-    properties : :class:`GeoJsonProperties`
-        Properties associated with this feature.
-    type : string
-        Specifies the type of GeoJSON object.
-    bbox : :class:`BBox`
-        Bounding box of the coordinate range of the object's Geometries, Features, or
-        Feature Collections. https://tools.ietf.org/html/rfc7946#section-5
-    id : anyOf(string, float)
-        A value that uniquely identifies this feature in a
-        https://tools.ietf.org/html/rfc7946#section-3.2.
-    """
-    _schema = {'$ref': '#/definitions/Feature'}
-
-    def __init__(self, geometry=Undefined, properties=Undefined, type=Undefined, bbox=Undefined,
-                 id=Undefined, **kwds):
-        super(Feature, self).__init__(geometry=geometry, properties=properties, type=type, bbox=bbox,
-                                      id=id, **kwds)
-
-
-class FeatureCollection(VegaLiteSchema):
-    """FeatureCollection schema wrapper
-
-    Mapping(required=[features, type])
-    A collection of feature objects.  https://tools.ietf.org/html/rfc7946#section-3.3
-
-    Parameters
-    ----------
-
-    features : List(:class:`FeatureGeometryGeoJsonProperties`)
-
-    type : string
-        Specifies the type of GeoJSON object.
-    bbox : :class:`BBox`
-        Bounding box of the coordinate range of the object's Geometries, Features, or
-        Feature Collections. https://tools.ietf.org/html/rfc7946#section-5
-    """
-    _schema = {'$ref': '#/definitions/FeatureCollection'}
-
-    def __init__(self, features=Undefined, type=Undefined, bbox=Undefined, **kwds):
-        super(FeatureCollection, self).__init__(features=features, type=type, bbox=bbox, **kwds)
-
-
-class FeatureGeometryGeoJsonProperties(VegaLiteSchema):
-    """FeatureGeometryGeoJsonProperties schema wrapper
-
-    Mapping(required=[geometry, properties, type])
-    A feature object which contains a geometry and associated properties.
-    https://tools.ietf.org/html/rfc7946#section-3.2
-
-    Parameters
-    ----------
-
-    geometry : :class:`Geometry`
-        The feature's geometry
-    properties : :class:`GeoJsonProperties`
-        Properties associated with this feature.
-    type : string
-        Specifies the type of GeoJSON object.
-    bbox : :class:`BBox`
-        Bounding box of the coordinate range of the object's Geometries, Features, or
-        Feature Collections. https://tools.ietf.org/html/rfc7946#section-5
-    id : anyOf(string, float)
-        A value that uniquely identifies this feature in a
-        https://tools.ietf.org/html/rfc7946#section-3.2.
-    """
-    _schema = {'$ref': '#/definitions/Feature<Geometry,GeoJsonProperties>'}
-
-    def __init__(self, geometry=Undefined, properties=Undefined, type=Undefined, bbox=Undefined,
-                 id=Undefined, **kwds):
-        super(FeatureGeometryGeoJsonProperties, self).__init__(geometry=geometry, properties=properties,
-                                                               type=type, bbox=bbox, id=id, **kwds)
-
-
-class Field(VegaLiteSchema):
-    """Field schema wrapper
-
-    anyOf(:class:`FieldName`, :class:`RepeatRef`)
-    """
-    _schema = {'$ref': '#/definitions/Field'}
-
-    def __init__(self, *args, **kwds):
-        super(Field, self).__init__(*args, **kwds)
-
-
-class FieldDefWithoutScale(VegaLiteSchema):
-    """FieldDefWithoutScale schema wrapper
-
-    Mapping(required=[])
-    Definition object for a data field, its type and transformation of an encoding channel.
-
-    Parameters
-    ----------
-
-    aggregate : :class:`Aggregate`
-        Aggregation function for the field (e.g., ``"mean"``, ``"sum"``, ``"median"``,
-        ``"min"``, ``"max"``, ``"count"`` ).
-
-        **Default value:** ``undefined`` (None)
-
-        **See also:** `aggregate <https://vega.github.io/vega-lite/docs/aggregate.html>`__
-        documentation.
-    bandPosition : float
-        Relative position on a band of a stacked, binned, time unit, or band scale. For
-        example, the marks will be positioned at the beginning of the band if set to ``0``,
-        and at the middle of the band if set to ``0.5``.
-    bin : anyOf(boolean, :class:`BinParams`, string, None)
-        A flag for binning a ``quantitative`` field, `an object defining binning parameters
-        <https://vega.github.io/vega-lite/docs/bin.html#bin-parameters>`__, or indicating
-        that the data for ``x`` or ``y`` channel are binned before they are imported into
-        Vega-Lite ( ``"binned"`` ).
-
-
-        If ``true``, default `binning parameters
-        <https://vega.github.io/vega-lite/docs/bin.html#bin-parameters>`__ will be applied.
-
-        If ``"binned"``, this indicates that the data for the ``x`` (or ``y`` ) channel are
-        already binned. You can map the bin-start field to ``x`` (or ``y`` ) and the bin-end
-        field to ``x2`` (or ``y2`` ). The scale and axis will be formatted similar to
-        binning in Vega-Lite.  To adjust the axis ticks based on the bin step, you can also
-        set the axis's `tickMinStep
-        <https://vega.github.io/vega-lite/docs/axis.html#ticks>`__ property.
-
-        **Default value:** ``false``
-
-        **See also:** `bin <https://vega.github.io/vega-lite/docs/bin.html>`__
-        documentation.
-    field : :class:`Field`
-        **Required.** A string defining the name of the field from which to pull a data
-        value or an object defining iterated values from the `repeat
-        <https://vega.github.io/vega-lite/docs/repeat.html>`__ operator.
-
-        **See also:** `field <https://vega.github.io/vega-lite/docs/field.html>`__
-        documentation.
-
-        **Notes:** 1)  Dots ( ``.`` ) and brackets ( ``[`` and ``]`` ) can be used to access
-        nested objects (e.g., ``"field": "foo.bar"`` and ``"field": "foo['bar']"`` ). If
-        field names contain dots or brackets but are not nested, you can use ``\\`` to
-        escape dots and brackets (e.g., ``"a\\.b"`` and ``"a\\[0\\]"`` ). See more details
-        about escaping in the `field documentation
-        <https://vega.github.io/vega-lite/docs/field.html>`__. 2) ``field`` is not required
-        if ``aggregate`` is ``count``.
-    timeUnit : anyOf(:class:`TimeUnit`, :class:`BinnedTimeUnit`, :class:`TimeUnitParams`)
-        Time unit (e.g., ``year``, ``yearmonth``, ``month``, ``hours`` ) for a temporal
-        field. or `a temporal field that gets casted as ordinal
-        <https://vega.github.io/vega-lite/docs/type.html#cast>`__.
-
-        **Default value:** ``undefined`` (None)
-
-        **See also:** `timeUnit <https://vega.github.io/vega-lite/docs/timeunit.html>`__
-        documentation.
-    title : anyOf(:class:`Text`, None)
-        A title for the field. If ``null``, the title will be removed.
-
-        **Default value:**  derived from the field's name and transformation function (
-        ``aggregate``, ``bin`` and ``timeUnit`` ). If the field has an aggregate function,
-        the function is displayed as part of the title (e.g., ``"Sum of Profit"`` ). If the
-        field is binned or has a time unit applied, the applied function is shown in
-        parentheses (e.g., ``"Profit (binned)"``, ``"Transaction Date (year-month)"`` ).
-        Otherwise, the title is simply the field name.
-
-        **Notes** :
-
-        1) You can customize the default field title format by providing the `fieldTitle
-        <https://vega.github.io/vega-lite/docs/config.html#top-level-config>`__ property in
-        the `config <https://vega.github.io/vega-lite/docs/config.html>`__ or `fieldTitle
-        function via the compile function's options
-        <https://vega.github.io/vega-lite/usage/compile.html#field-title>`__.
-
-        2) If both field definition's ``title`` and axis, header, or legend ``title`` are
-        defined, axis/header/legend title will be used.
-    type : :class:`StandardType`
-        The type of measurement ( ``"quantitative"``, ``"temporal"``, ``"ordinal"``, or
-        ``"nominal"`` ) for the encoded field or constant value ( ``datum`` ). It can also
-        be a ``"geojson"`` type for encoding `'geoshape'
-        <https://vega.github.io/vega-lite/docs/geoshape.html>`__.
-
-        Vega-Lite automatically infers data types in many cases as discussed below. However,
-        type is required for a field if: (1) the field is not nominal and the field encoding
-        has no specified ``aggregate`` (except ``argmin`` and ``argmax`` ), ``bin``, scale
-        type, custom ``sort`` order, nor ``timeUnit`` or (2) if you wish to use an ordinal
-        scale for a field with ``bin`` or ``timeUnit``.
-
-        **Default value:**
-
-        1) For a data ``field``, ``"nominal"`` is the default data type unless the field
-        encoding has ``aggregate``, ``channel``, ``bin``, scale type, ``sort``, or
-        ``timeUnit`` that satisfies the following criteria:
-
-
-        * ``"quantitative"`` is the default type if (1) the encoded field contains ``bin``
-          or ``aggregate`` except ``"argmin"`` and ``"argmax"``, (2) the encoding channel is
-          ``latitude`` or ``longitude`` channel or (3) if the specified scale type is `a
-          quantitative scale <https://vega.github.io/vega-lite/docs/scale.html#type>`__.
-        * ``"temporal"`` is the default type if (1) the encoded field contains ``timeUnit``
-          or (2) the specified scale type is a time or utc scale
-        * ``"ordinal"`` is the default type if (1) the encoded field contains a `custom sort
-          order
-          <https://vega.github.io/vega-lite/docs/sort.html#specifying-custom-sort-order>`__,
-          (2) the specified scale type is an ordinal/point/band scale, or (3) the encoding
-          channel is ``order``.
-
-        2) For a constant value in data domain ( ``datum`` ):
-
-
-        * ``"quantitative"`` if the datum is a number
-        * ``"nominal"`` if the datum is a string
-        * ``"temporal"`` if the datum is `a date time object
-          <https://vega.github.io/vega-lite/docs/datetime.html>`__
-
-        **Note:**
-
-
-        * Data ``type`` describes the semantics of the data rather than the primitive data
-          types (number, string, etc.). The same primitive data type can have different
-          types of measurement. For example, numeric data can represent quantitative,
-          ordinal, or nominal data.
-        * Data values for a temporal field can be either a date-time string (e.g.,
-          ``"2015-03-07 12:32:17"``, ``"17:01"``, ``"2015-03-16"``. ``"2015"`` ) or a
-          timestamp number (e.g., ``1552199579097`` ).
-        * When using with `bin <https://vega.github.io/vega-lite/docs/bin.html>`__, the
-          ``type`` property can be either ``"quantitative"`` (for using a linear bin scale)
-          or `"ordinal" (for using an ordinal bin scale)
-          <https://vega.github.io/vega-lite/docs/type.html#cast-bin>`__.
-        * When using with `timeUnit
-          <https://vega.github.io/vega-lite/docs/timeunit.html>`__, the ``type`` property
-          can be either ``"temporal"`` (default, for using a temporal scale) or `"ordinal"
-          (for using an ordinal scale)
-          <https://vega.github.io/vega-lite/docs/type.html#cast-bin>`__.
-        * When using with `aggregate
-          <https://vega.github.io/vega-lite/docs/aggregate.html>`__, the ``type`` property
-          refers to the post-aggregation data type. For example, we can calculate count
-          ``distinct`` of a categorical field ``"cat"`` using ``{"aggregate": "distinct",
-          "field": "cat"}``. The ``"type"`` of the aggregate output is ``"quantitative"``.
-        * Secondary channels (e.g., ``x2``, ``y2``, ``xError``, ``yError`` ) do not have
-          ``type`` as they must have exactly the same type as their primary channels (e.g.,
-          ``x``, ``y`` ).
-
-        **See also:** `type <https://vega.github.io/vega-lite/docs/type.html>`__
-        documentation.
-    """
-    _schema = {'$ref': '#/definitions/FieldDefWithoutScale'}
-
-    def __init__(self, aggregate=Undefined, bandPosition=Undefined, bin=Undefined, field=Undefined,
-                 timeUnit=Undefined, title=Undefined, type=Undefined, **kwds):
-        super(FieldDefWithoutScale, self).__init__(aggregate=aggregate, bandPosition=bandPosition,
-                                                   bin=bin, field=field, timeUnit=timeUnit, title=title,
-                                                   type=type, **kwds)
-
-
-class FieldName(Field):
-    """FieldName schema wrapper
-
-    string
-    """
-    _schema = {'$ref': '#/definitions/FieldName'}
-
-    def __init__(self, *args):
-        super(FieldName, self).__init__(*args)
-
-
-class FieldOrDatumDefWithConditionStringFieldDefstring(VegaLiteSchema):
-    """FieldOrDatumDefWithConditionStringFieldDefstring schema wrapper
-
-    Mapping(required=[])
-
-    Parameters
-    ----------
-
-    aggregate : :class:`Aggregate`
-        Aggregation function for the field (e.g., ``"mean"``, ``"sum"``, ``"median"``,
-        ``"min"``, ``"max"``, ``"count"`` ).
-
-        **Default value:** ``undefined`` (None)
-
-        **See also:** `aggregate <https://vega.github.io/vega-lite/docs/aggregate.html>`__
-        documentation.
-    bandPosition : float
-        Relative position on a band of a stacked, binned, time unit, or band scale. For
-        example, the marks will be positioned at the beginning of the band if set to ``0``,
-        and at the middle of the band if set to ``0.5``.
-    bin : anyOf(boolean, :class:`BinParams`, string, None)
-        A flag for binning a ``quantitative`` field, `an object defining binning parameters
-        <https://vega.github.io/vega-lite/docs/bin.html#bin-parameters>`__, or indicating
-        that the data for ``x`` or ``y`` channel are binned before they are imported into
-        Vega-Lite ( ``"binned"`` ).
-
-
-        If ``true``, default `binning parameters
-        <https://vega.github.io/vega-lite/docs/bin.html#bin-parameters>`__ will be applied.
-
-        If ``"binned"``, this indicates that the data for the ``x`` (or ``y`` ) channel are
-        already binned. You can map the bin-start field to ``x`` (or ``y`` ) and the bin-end
-        field to ``x2`` (or ``y2`` ). The scale and axis will be formatted similar to
-        binning in Vega-Lite.  To adjust the axis ticks based on the bin step, you can also
-        set the axis's `tickMinStep
-        <https://vega.github.io/vega-lite/docs/axis.html#ticks>`__ property.
-
-        **Default value:** ``false``
-
-        **See also:** `bin <https://vega.github.io/vega-lite/docs/bin.html>`__
-        documentation.
-    condition : anyOf(:class:`ConditionalValueDefstringExprRef`, List(:class:`ConditionalValueDefstringExprRef`))
-        One or more value definition(s) with `a parameter or a test predicate
-        <https://vega.github.io/vega-lite/docs/condition.html>`__.
-
-        **Note:** A field definition's ``condition`` property can only contain `conditional
-        value definitions <https://vega.github.io/vega-lite/docs/condition.html#value>`__
-        since Vega-Lite only allows at most one encoded field per encoding channel.
-    field : :class:`Field`
-        **Required.** A string defining the name of the field from which to pull a data
-        value or an object defining iterated values from the `repeat
-        <https://vega.github.io/vega-lite/docs/repeat.html>`__ operator.
-
-        **See also:** `field <https://vega.github.io/vega-lite/docs/field.html>`__
-        documentation.
-
-        **Notes:** 1)  Dots ( ``.`` ) and brackets ( ``[`` and ``]`` ) can be used to access
-        nested objects (e.g., ``"field": "foo.bar"`` and ``"field": "foo['bar']"`` ). If
-        field names contain dots or brackets but are not nested, you can use ``\\`` to
-        escape dots and brackets (e.g., ``"a\\.b"`` and ``"a\\[0\\]"`` ). See more details
-        about escaping in the `field documentation
-        <https://vega.github.io/vega-lite/docs/field.html>`__. 2) ``field`` is not required
-        if ``aggregate`` is ``count``.
-    format : anyOf(string, :class:`Dict`)
-        When used with the default ``"number"`` and ``"time"`` format type, the text
-        formatting pattern for labels of guides (axes, legends, headers) and text marks.
-
-
-        * If the format type is ``"number"`` (e.g., for quantitative fields), this is D3's
-          `number format pattern <https://github.com/d3/d3-format#locale_format>`__.
-        * If the format type is ``"time"`` (e.g., for temporal fields), this is D3's `time
-          format pattern <https://github.com/d3/d3-time-format#locale_format>`__.
-
-        See the `format documentation <https://vega.github.io/vega-lite/docs/format.html>`__
-        for more examples.
-
-        When used with a `custom formatType
-        <https://vega.github.io/vega-lite/docs/config.html#custom-format-type>`__, this
-        value will be passed as ``format`` alongside ``datum.value`` to the registered
-        function.
-
-        **Default value:**  Derived from `numberFormat
-        <https://vega.github.io/vega-lite/docs/config.html#format>`__ config for number
-        format and from `timeFormat
-        <https://vega.github.io/vega-lite/docs/config.html#format>`__ config for time
-        format.
-    formatType : string
-        The format type for labels. One of ``"number"``, ``"time"``, or a `registered custom
-        format type
-        <https://vega.github.io/vega-lite/docs/config.html#custom-format-type>`__.
-
-        **Default value:**
-
-
-        * ``"time"`` for temporal fields and ordinal and nominal fields with ``timeUnit``.
-        * ``"number"`` for quantitative fields as well as ordinal and nominal fields without
-          ``timeUnit``.
-    timeUnit : anyOf(:class:`TimeUnit`, :class:`BinnedTimeUnit`, :class:`TimeUnitParams`)
-        Time unit (e.g., ``year``, ``yearmonth``, ``month``, ``hours`` ) for a temporal
-        field. or `a temporal field that gets casted as ordinal
-        <https://vega.github.io/vega-lite/docs/type.html#cast>`__.
-
-        **Default value:** ``undefined`` (None)
-
-        **See also:** `timeUnit <https://vega.github.io/vega-lite/docs/timeunit.html>`__
-        documentation.
-    title : anyOf(:class:`Text`, None)
-        A title for the field. If ``null``, the title will be removed.
-
-        **Default value:**  derived from the field's name and transformation function (
-        ``aggregate``, ``bin`` and ``timeUnit`` ). If the field has an aggregate function,
-        the function is displayed as part of the title (e.g., ``"Sum of Profit"`` ). If the
-        field is binned or has a time unit applied, the applied function is shown in
-        parentheses (e.g., ``"Profit (binned)"``, ``"Transaction Date (year-month)"`` ).
-        Otherwise, the title is simply the field name.
-
-        **Notes** :
-
-        1) You can customize the default field title format by providing the `fieldTitle
-        <https://vega.github.io/vega-lite/docs/config.html#top-level-config>`__ property in
-        the `config <https://vega.github.io/vega-lite/docs/config.html>`__ or `fieldTitle
-        function via the compile function's options
-        <https://vega.github.io/vega-lite/usage/compile.html#field-title>`__.
-
-        2) If both field definition's ``title`` and axis, header, or legend ``title`` are
-        defined, axis/header/legend title will be used.
-    type : :class:`StandardType`
-        The type of measurement ( ``"quantitative"``, ``"temporal"``, ``"ordinal"``, or
-        ``"nominal"`` ) for the encoded field or constant value ( ``datum`` ). It can also
-        be a ``"geojson"`` type for encoding `'geoshape'
-        <https://vega.github.io/vega-lite/docs/geoshape.html>`__.
-
-        Vega-Lite automatically infers data types in many cases as discussed below. However,
-        type is required for a field if: (1) the field is not nominal and the field encoding
-        has no specified ``aggregate`` (except ``argmin`` and ``argmax`` ), ``bin``, scale
-        type, custom ``sort`` order, nor ``timeUnit`` or (2) if you wish to use an ordinal
-        scale for a field with ``bin`` or ``timeUnit``.
-
-        **Default value:**
-
-        1) For a data ``field``, ``"nominal"`` is the default data type unless the field
-        encoding has ``aggregate``, ``channel``, ``bin``, scale type, ``sort``, or
-        ``timeUnit`` that satisfies the following criteria:
-
-
-        * ``"quantitative"`` is the default type if (1) the encoded field contains ``bin``
-          or ``aggregate`` except ``"argmin"`` and ``"argmax"``, (2) the encoding channel is
-          ``latitude`` or ``longitude`` channel or (3) if the specified scale type is `a
-          quantitative scale <https://vega.github.io/vega-lite/docs/scale.html#type>`__.
-        * ``"temporal"`` is the default type if (1) the encoded field contains ``timeUnit``
-          or (2) the specified scale type is a time or utc scale
-        * ``"ordinal"`` is the default type if (1) the encoded field contains a `custom sort
-          order
-          <https://vega.github.io/vega-lite/docs/sort.html#specifying-custom-sort-order>`__,
-          (2) the specified scale type is an ordinal/point/band scale, or (3) the encoding
-          channel is ``order``.
-
-        2) For a constant value in data domain ( ``datum`` ):
-
-
-        * ``"quantitative"`` if the datum is a number
-        * ``"nominal"`` if the datum is a string
-        * ``"temporal"`` if the datum is `a date time object
-          <https://vega.github.io/vega-lite/docs/datetime.html>`__
-
-        **Note:**
-
-
-        * Data ``type`` describes the semantics of the data rather than the primitive data
-          types (number, string, etc.). The same primitive data type can have different
-          types of measurement. For example, numeric data can represent quantitative,
-          ordinal, or nominal data.
-        * Data values for a temporal field can be either a date-time string (e.g.,
-          ``"2015-03-07 12:32:17"``, ``"17:01"``, ``"2015-03-16"``. ``"2015"`` ) or a
-          timestamp number (e.g., ``1552199579097`` ).
-        * When using with `bin <https://vega.github.io/vega-lite/docs/bin.html>`__, the
-          ``type`` property can be either ``"quantitative"`` (for using a linear bin scale)
-          or `"ordinal" (for using an ordinal bin scale)
-          <https://vega.github.io/vega-lite/docs/type.html#cast-bin>`__.
-        * When using with `timeUnit
-          <https://vega.github.io/vega-lite/docs/timeunit.html>`__, the ``type`` property
-          can be either ``"temporal"`` (default, for using a temporal scale) or `"ordinal"
-          (for using an ordinal scale)
-          <https://vega.github.io/vega-lite/docs/type.html#cast-bin>`__.
-        * When using with `aggregate
-          <https://vega.github.io/vega-lite/docs/aggregate.html>`__, the ``type`` property
-          refers to the post-aggregation data type. For example, we can calculate count
-          ``distinct`` of a categorical field ``"cat"`` using ``{"aggregate": "distinct",
-          "field": "cat"}``. The ``"type"`` of the aggregate output is ``"quantitative"``.
-        * Secondary channels (e.g., ``x2``, ``y2``, ``xError``, ``yError`` ) do not have
-          ``type`` as they must have exactly the same type as their primary channels (e.g.,
-          ``x``, ``y`` ).
-
-        **See also:** `type <https://vega.github.io/vega-lite/docs/type.html>`__
-        documentation.
-    """
-    _schema = {'$ref': '#/definitions/FieldOrDatumDefWithCondition<StringFieldDef,string>'}
-
-    def __init__(self, aggregate=Undefined, bandPosition=Undefined, bin=Undefined, condition=Undefined,
-                 field=Undefined, format=Undefined, formatType=Undefined, timeUnit=Undefined,
-                 title=Undefined, type=Undefined, **kwds):
-        super(FieldOrDatumDefWithConditionStringFieldDefstring, self).__init__(aggregate=aggregate,
-                                                                               bandPosition=bandPosition,
-                                                                               bin=bin,
-                                                                               condition=condition,
-                                                                               field=field,
-                                                                               format=format,
-                                                                               formatType=formatType,
-                                                                               timeUnit=timeUnit,
-                                                                               title=title, type=type,
-                                                                               **kwds)
-
-
-class FieldRange(VegaLiteSchema):
-    """FieldRange schema wrapper
-
-    Mapping(required=[field])
-
-    Parameters
-    ----------
-
-    field : string
-
-    """
-    _schema = {'$ref': '#/definitions/FieldRange'}
-
-    def __init__(self, field=Undefined, **kwds):
-        super(FieldRange, self).__init__(field=field, **kwds)
-
-
-class Fit(VegaLiteSchema):
-    """Fit schema wrapper
-
-    anyOf(:class:`GeoJsonFeature`, :class:`GeoJsonFeatureCollection`,
-    List(:class:`GeoJsonFeature`))
-    """
-    _schema = {'$ref': '#/definitions/Fit'}
-
-    def __init__(self, *args, **kwds):
-        super(Fit, self).__init__(*args, **kwds)
-
-
-class FontStyle(VegaLiteSchema):
-    """FontStyle schema wrapper
-
-    string
-    """
-    _schema = {'$ref': '#/definitions/FontStyle'}
-
-    def __init__(self, *args):
-        super(FontStyle, self).__init__(*args)
-
-
-class FontWeight(VegaLiteSchema):
-    """FontWeight schema wrapper
-
-    enum('normal', 'bold', 'lighter', 'bolder', 100, 200, 300, 400, 500, 600, 700, 800, 900)
-    """
-    _schema = {'$ref': '#/definitions/FontWeight'}
-
-    def __init__(self, *args):
-        super(FontWeight, self).__init__(*args)
-
-
-class FormatConfig(VegaLiteSchema):
-    """FormatConfig schema wrapper
-
-    Mapping(required=[])
-
-    Parameters
-    ----------
-
-    normalizedNumberFormat : string
-        If normalizedNumberFormatType is not specified, D3 number format for axis labels,
-        text marks, and tooltips of normalized stacked fields (fields with ``stack:
-        "normalize"`` ). For example ``"s"`` for SI units. Use `D3's number format pattern
-        <https://github.com/d3/d3-format#locale_format>`__.
-
-        If ``config.normalizedNumberFormatType`` is specified and
-        ``config.customFormatTypes`` is ``true``, this value will be passed as ``format``
-        alongside ``datum.value`` to the ``config.numberFormatType`` function. **Default
-        value:** ``%``
-    normalizedNumberFormatType : string
-        `Custom format type
-        <https://vega.github.io/vega-lite/docs/config.html#custom-format-type>`__ for
-        ``config.normalizedNumberFormat``.
-
-        **Default value:** ``undefined`` -- This is equilvalent to call D3-format, which is
-        exposed as `format in Vega-Expression
-        <https://vega.github.io/vega/docs/expressions/#format>`__. **Note:** You must also
-        set ``customFormatTypes`` to ``true`` to use this feature.
-    numberFormat : string
-        If numberFormatType is not specified, D3 number format for guide labels, text marks,
-        and tooltips of non-normalized fields (fields *without* ``stack: "normalize"`` ).
-        For example ``"s"`` for SI units. Use `D3's number format pattern
-        <https://github.com/d3/d3-format#locale_format>`__.
-
-        If ``config.numberFormatType`` is specified and ``config.customFormatTypes`` is
-        ``true``, this value will be passed as ``format`` alongside ``datum.value`` to the
-        ``config.numberFormatType`` function.
-    numberFormatType : string
-        `Custom format type
-        <https://vega.github.io/vega-lite/docs/config.html#custom-format-type>`__ for
-        ``config.numberFormat``.
-
-        **Default value:** ``undefined`` -- This is equilvalent to call D3-format, which is
-        exposed as `format in Vega-Expression
-        <https://vega.github.io/vega/docs/expressions/#format>`__. **Note:** You must also
-        set ``customFormatTypes`` to ``true`` to use this feature.
-    timeFormat : string
-        Default time format for raw time values (without time units) in text marks, legend
-        labels and header labels.
-
-        **Default value:** ``"%b %d, %Y"`` **Note:** Axes automatically determine the format
-        for each label automatically so this config does not affect axes.
-    timeFormatType : string
-        `Custom format type
-        <https://vega.github.io/vega-lite/docs/config.html#custom-format-type>`__ for
-        ``config.timeFormat``.
-
-        **Default value:** ``undefined`` -- This is equilvalent to call D3-time-format,
-        which is exposed as `timeFormat in Vega-Expression
-        <https://vega.github.io/vega/docs/expressions/#timeFormat>`__. **Note:** You must
-        also set ``customFormatTypes`` to ``true`` and there must *not* be a ``timeUnit``
-        defined to use this feature.
-    """
-    _schema = {'$ref': '#/definitions/FormatConfig'}
-
-    def __init__(self, normalizedNumberFormat=Undefined, normalizedNumberFormatType=Undefined,
-                 numberFormat=Undefined, numberFormatType=Undefined, timeFormat=Undefined,
-                 timeFormatType=Undefined, **kwds):
-        super(FormatConfig, self).__init__(normalizedNumberFormat=normalizedNumberFormat,
-                                           normalizedNumberFormatType=normalizedNumberFormatType,
-                                           numberFormat=numberFormat, numberFormatType=numberFormatType,
-                                           timeFormat=timeFormat, timeFormatType=timeFormatType, **kwds)
-
-
-class Generator(Data):
-    """Generator schema wrapper
-
-    anyOf(:class:`SequenceGenerator`, :class:`SphereGenerator`, :class:`GraticuleGenerator`)
-    """
-    _schema = {'$ref': '#/definitions/Generator'}
-
-    def __init__(self, *args, **kwds):
-        super(Generator, self).__init__(*args, **kwds)
-
-
-class GenericUnitSpecEncodingAnyMark(VegaLiteSchema):
-    """GenericUnitSpecEncodingAnyMark schema wrapper
-
-    Mapping(required=[mark])
-    Base interface for a unit (single-view) specification.
-
-    Parameters
-    ----------
-
-    mark : :class:`AnyMark`
-        A string describing the mark type (one of ``"bar"``, ``"circle"``, ``"square"``,
-        ``"tick"``, ``"line"``, ``"area"``, ``"point"``, ``"rule"``, ``"geoshape"``, and
-        ``"text"`` ) or a `mark definition object
-        <https://vega.github.io/vega-lite/docs/mark.html#mark-def>`__.
-    data : anyOf(:class:`Data`, None)
-        An object describing the data source. Set to ``null`` to ignore the parent's data
-        source. If no data is set, it is derived from the parent.
-    description : string
-        Description of this mark for commenting purpose.
-    encoding : :class:`Encoding`
-        A key-value mapping between encoding channels and definition of fields.
-    name : string
-        Name of the visualization for later reference.
-    params : List(:class:`SelectionParameter`)
-        An array of parameters that may either be simple variables, or more complex
-        selections that map user input to data queries.
-    projection : :class:`Projection`
-        An object defining properties of geographic projection, which will be applied to
-        ``shape`` path for ``"geoshape"`` marks and to ``latitude`` and ``"longitude"``
-        channels for other marks.
-    title : anyOf(:class:`Text`, :class:`TitleParams`)
-        Title for the plot.
-    transform : List(:class:`Transform`)
-        An array of data transformations such as filter and new field calculation.
-    """
-    _schema = {'$ref': '#/definitions/GenericUnitSpec<Encoding,AnyMark>'}
-
-    def __init__(self, mark=Undefined, data=Undefined, description=Undefined, encoding=Undefined,
-                 name=Undefined, params=Undefined, projection=Undefined, title=Undefined,
-                 transform=Undefined, **kwds):
-        super(GenericUnitSpecEncodingAnyMark, self).__init__(mark=mark, data=data,
-                                                             description=description, encoding=encoding,
-                                                             name=name, params=params,
-                                                             projection=projection, title=title,
-                                                             transform=transform, **kwds)
-
-
-class GeoJsonFeature(Fit):
-    """GeoJsonFeature schema wrapper
-
-    Mapping(required=[geometry, properties, type])
-    A feature object which contains a geometry and associated properties.
-    https://tools.ietf.org/html/rfc7946#section-3.2
-
-    Parameters
-    ----------
-
-    geometry : :class:`Geometry`
-        The feature's geometry
-    properties : :class:`GeoJsonProperties`
-        Properties associated with this feature.
-    type : string
-        Specifies the type of GeoJSON object.
-    bbox : :class:`BBox`
-        Bounding box of the coordinate range of the object's Geometries, Features, or
-        Feature Collections. https://tools.ietf.org/html/rfc7946#section-5
-    id : anyOf(string, float)
-        A value that uniquely identifies this feature in a
-        https://tools.ietf.org/html/rfc7946#section-3.2.
-    """
-    _schema = {'$ref': '#/definitions/GeoJsonFeature'}
-
-    def __init__(self, geometry=Undefined, properties=Undefined, type=Undefined, bbox=Undefined,
-                 id=Undefined, **kwds):
-        super(GeoJsonFeature, self).__init__(geometry=geometry, properties=properties, type=type,
-                                             bbox=bbox, id=id, **kwds)
-
-
-class GeoJsonFeatureCollection(Fit):
-    """GeoJsonFeatureCollection schema wrapper
-
-    Mapping(required=[features, type])
-    A collection of feature objects.  https://tools.ietf.org/html/rfc7946#section-3.3
-
-    Parameters
-    ----------
-
-    features : List(:class:`FeatureGeometryGeoJsonProperties`)
-
-    type : string
-        Specifies the type of GeoJSON object.
-    bbox : :class:`BBox`
-        Bounding box of the coordinate range of the object's Geometries, Features, or
-        Feature Collections. https://tools.ietf.org/html/rfc7946#section-5
-    """
-    _schema = {'$ref': '#/definitions/GeoJsonFeatureCollection'}
-
-    def __init__(self, features=Undefined, type=Undefined, bbox=Undefined, **kwds):
-        super(GeoJsonFeatureCollection, self).__init__(features=features, type=type, bbox=bbox, **kwds)
-
-
-class GeoJsonProperties(VegaLiteSchema):
-    """GeoJsonProperties schema wrapper
-
-    anyOf(Mapping(required=[]), None)
-    """
-    _schema = {'$ref': '#/definitions/GeoJsonProperties'}
-
-    def __init__(self, *args, **kwds):
-        super(GeoJsonProperties, self).__init__(*args, **kwds)
-
-
-class Geometry(VegaLiteSchema):
-    """Geometry schema wrapper
-
-    anyOf(:class:`Point`, :class:`MultiPoint`, :class:`LineString`, :class:`MultiLineString`,
-    :class:`Polygon`, :class:`MultiPolygon`, :class:`GeometryCollection`)
-    Union of geometry objects. https://tools.ietf.org/html/rfc7946#section-3
-    """
-    _schema = {'$ref': '#/definitions/Geometry'}
-
-    def __init__(self, *args, **kwds):
-        super(Geometry, self).__init__(*args, **kwds)
-
-
-class GeometryCollection(Geometry):
-    """GeometryCollection schema wrapper
-
-    Mapping(required=[geometries, type])
-    Geometry Collection https://tools.ietf.org/html/rfc7946#section-3.1.8
-
-    Parameters
-    ----------
-
-    geometries : List(:class:`Geometry`)
-
-    type : string
-        Specifies the type of GeoJSON object.
-    bbox : :class:`BBox`
-        Bounding box of the coordinate range of the object's Geometries, Features, or
-        Feature Collections. https://tools.ietf.org/html/rfc7946#section-5
-    """
-    _schema = {'$ref': '#/definitions/GeometryCollection'}
-
-    def __init__(self, geometries=Undefined, type=Undefined, bbox=Undefined, **kwds):
-        super(GeometryCollection, self).__init__(geometries=geometries, type=type, bbox=bbox, **kwds)
-
-
-class Gradient(VegaLiteSchema):
-    """Gradient schema wrapper
-
-    anyOf(:class:`LinearGradient`, :class:`RadialGradient`)
-    """
-    _schema = {'$ref': '#/definitions/Gradient'}
-
-    def __init__(self, *args, **kwds):
-        super(Gradient, self).__init__(*args, **kwds)
-
-
-class GradientStop(VegaLiteSchema):
-    """GradientStop schema wrapper
-
-    Mapping(required=[offset, color])
-
-    Parameters
-    ----------
-
-    color : :class:`Color`
-        The color value at this point in the gradient.
-    offset : float
-        The offset fraction for the color stop, indicating its position within the gradient.
-    """
-    _schema = {'$ref': '#/definitions/GradientStop'}
-
-    def __init__(self, color=Undefined, offset=Undefined, **kwds):
-        super(GradientStop, self).__init__(color=color, offset=offset, **kwds)
-
-
-class GraticuleGenerator(Generator):
-    """GraticuleGenerator schema wrapper
-
-    Mapping(required=[graticule])
-
-    Parameters
-    ----------
-
-    graticule : anyOf(boolean, :class:`GraticuleParams`)
-        Generate graticule GeoJSON data for geographic reference lines.
-    name : string
-        Provide a placeholder name and bind data at runtime.
-    """
-    _schema = {'$ref': '#/definitions/GraticuleGenerator'}
-
-    def __init__(self, graticule=Undefined, name=Undefined, **kwds):
-        super(GraticuleGenerator, self).__init__(graticule=graticule, name=name, **kwds)
-
-
-class GraticuleParams(VegaLiteSchema):
-    """GraticuleParams schema wrapper
-
-    Mapping(required=[])
-
-    Parameters
-    ----------
-
-    extent : :class:`Vector2Vector2number`
-        Sets both the major and minor extents to the same values.
-    extentMajor : :class:`Vector2Vector2number`
-        The major extent of the graticule as a two-element array of coordinates.
-    extentMinor : :class:`Vector2Vector2number`
-        The minor extent of the graticule as a two-element array of coordinates.
-    precision : float
-        The precision of the graticule in degrees.
-
-        **Default value:** ``2.5``
-    step : :class:`Vector2number`
-        Sets both the major and minor step angles to the same values.
-    stepMajor : :class:`Vector2number`
-        The major step angles of the graticule.
-
-        **Default value:** ``[90, 360]``
-    stepMinor : :class:`Vector2number`
-        The minor step angles of the graticule.
-
-        **Default value:** ``[10, 10]``
-    """
-    _schema = {'$ref': '#/definitions/GraticuleParams'}
-
-    def __init__(self, extent=Undefined, extentMajor=Undefined, extentMinor=Undefined,
-                 precision=Undefined, step=Undefined, stepMajor=Undefined, stepMinor=Undefined, **kwds):
-        super(GraticuleParams, self).__init__(extent=extent, extentMajor=extentMajor,
-                                              extentMinor=extentMinor, precision=precision, step=step,
-                                              stepMajor=stepMajor, stepMinor=stepMinor, **kwds)
-
-
-class Header(VegaLiteSchema):
-    """Header schema wrapper
-
-    Mapping(required=[])
-    Headers of row / column channels for faceted plots.
-
-    Parameters
-    ----------
-
-    format : anyOf(string, :class:`Dict`)
-        When used with the default ``"number"`` and ``"time"`` format type, the text
-        formatting pattern for labels of guides (axes, legends, headers) and text marks.
-
-
-        * If the format type is ``"number"`` (e.g., for quantitative fields), this is D3's
-          `number format pattern <https://github.com/d3/d3-format#locale_format>`__.
-        * If the format type is ``"time"`` (e.g., for temporal fields), this is D3's `time
-          format pattern <https://github.com/d3/d3-time-format#locale_format>`__.
-
-        See the `format documentation <https://vega.github.io/vega-lite/docs/format.html>`__
-        for more examples.
-
-        When used with a `custom formatType
-        <https://vega.github.io/vega-lite/docs/config.html#custom-format-type>`__, this
-        value will be passed as ``format`` alongside ``datum.value`` to the registered
-        function.
-
-        **Default value:**  Derived from `numberFormat
-        <https://vega.github.io/vega-lite/docs/config.html#format>`__ config for number
-        format and from `timeFormat
-        <https://vega.github.io/vega-lite/docs/config.html#format>`__ config for time
-        format.
-    formatType : string
-        The format type for labels. One of ``"number"``, ``"time"``, or a `registered custom
-        format type
-        <https://vega.github.io/vega-lite/docs/config.html#custom-format-type>`__.
-
-        **Default value:**
-
-
-        * ``"time"`` for temporal fields and ordinal and nominal fields with ``timeUnit``.
-        * ``"number"`` for quantitative fields as well as ordinal and nominal fields without
-          ``timeUnit``.
-    labelAlign : anyOf(:class:`Align`, :class:`ExprRef`)
-        Horizontal text alignment of header labels. One of ``"left"``, ``"center"``, or
-        ``"right"``.
-    labelAnchor : :class:`TitleAnchor`
-        The anchor position for placing the labels. One of ``"start"``, ``"middle"``, or
-        ``"end"``. For example, with a label orientation of top these anchor positions map
-        to a left-, center-, or right-aligned label.
-    labelAngle : float
-        The rotation angle of the header labels.
-
-        **Default value:** ``0`` for column header, ``-90`` for row header.
-    labelBaseline : anyOf(:class:`TextBaseline`, :class:`ExprRef`)
-        The vertical text baseline for the header labels. One of ``"alphabetic"`` (default),
-        ``"top"``, ``"middle"``, ``"bottom"``, ``"line-top"``, or ``"line-bottom"``. The
-        ``"line-top"`` and ``"line-bottom"`` values operate similarly to ``"top"`` and
-        ``"bottom"``, but are calculated relative to the ``titleLineHeight`` rather than
-        ``titleFontSize`` alone.
-    labelColor : anyOf(:class:`Color`, :class:`ExprRef`)
-        The color of the header label, can be in hex color code or regular color name.
-    labelExpr : string
-        `Vega expression <https://vega.github.io/vega/docs/expressions/>`__ for customizing
-        labels.
-
-        **Note:** The label text and value can be assessed via the ``label`` and ``value``
-        properties of the header's backing ``datum`` object.
-    labelFont : anyOf(string, :class:`ExprRef`)
-        The font of the header label.
-    labelFontSize : anyOf(float, :class:`ExprRef`)
-        The font size of the header label, in pixels.
-    labelFontStyle : anyOf(:class:`FontStyle`, :class:`ExprRef`)
-        The font style of the header label.
-    labelFontWeight : anyOf(:class:`FontWeight`, :class:`ExprRef`)
-        The font weight of the header label.
-    labelLimit : anyOf(float, :class:`ExprRef`)
-        The maximum length of the header label in pixels. The text value will be
-        automatically truncated if the rendered size exceeds the limit.
-
-        **Default value:** ``0``, indicating no limit
-    labelLineHeight : anyOf(float, :class:`ExprRef`)
-        Line height in pixels for multi-line header labels or title text with ``"line-top"``
-        or ``"line-bottom"`` baseline.
-    labelOrient : :class:`Orient`
-        The orientation of the header label. One of ``"top"``, ``"bottom"``, ``"left"`` or
-        ``"right"``.
-    labelPadding : anyOf(float, :class:`ExprRef`)
-        The padding, in pixel, between facet header's label and the plot.
-
-        **Default value:** ``10``
-    labels : boolean
-        A boolean flag indicating if labels should be included as part of the header.
-
-        **Default value:** ``true``.
-    orient : :class:`Orient`
-        Shortcut for setting both labelOrient and titleOrient.
-    title : anyOf(:class:`Text`, None)
-        A title for the field. If ``null``, the title will be removed.
-
-        **Default value:**  derived from the field's name and transformation function (
-        ``aggregate``, ``bin`` and ``timeUnit`` ). If the field has an aggregate function,
-        the function is displayed as part of the title (e.g., ``"Sum of Profit"`` ). If the
-        field is binned or has a time unit applied, the applied function is shown in
-        parentheses (e.g., ``"Profit (binned)"``, ``"Transaction Date (year-month)"`` ).
-        Otherwise, the title is simply the field name.
-
-        **Notes** :
-
-        1) You can customize the default field title format by providing the `fieldTitle
-        <https://vega.github.io/vega-lite/docs/config.html#top-level-config>`__ property in
-        the `config <https://vega.github.io/vega-lite/docs/config.html>`__ or `fieldTitle
-        function via the compile function's options
-        <https://vega.github.io/vega-lite/usage/compile.html#field-title>`__.
-
-        2) If both field definition's ``title`` and axis, header, or legend ``title`` are
-        defined, axis/header/legend title will be used.
-    titleAlign : anyOf(:class:`Align`, :class:`ExprRef`)
-        Horizontal text alignment (to the anchor) of header titles.
-    titleAnchor : :class:`TitleAnchor`
-        The anchor position for placing the title. One of ``"start"``, ``"middle"``, or
-        ``"end"``. For example, with an orientation of top these anchor positions map to a
-        left-, center-, or right-aligned title.
-    titleAngle : float
-        The rotation angle of the header title.
-
-        **Default value:** ``0``.
-    titleBaseline : anyOf(:class:`TextBaseline`, :class:`ExprRef`)
-        The vertical text baseline for the header title. One of ``"alphabetic"`` (default),
-        ``"top"``, ``"middle"``, ``"bottom"``, ``"line-top"``, or ``"line-bottom"``. The
-        ``"line-top"`` and ``"line-bottom"`` values operate similarly to ``"top"`` and
-        ``"bottom"``, but are calculated relative to the ``titleLineHeight`` rather than
-        ``titleFontSize`` alone.
-
-        **Default value:** ``"middle"``
-    titleColor : anyOf(:class:`Color`, :class:`ExprRef`)
-        Color of the header title, can be in hex color code or regular color name.
-    titleFont : anyOf(string, :class:`ExprRef`)
-        Font of the header title. (e.g., ``"Helvetica Neue"`` ).
-    titleFontSize : anyOf(float, :class:`ExprRef`)
-        Font size of the header title.
-    titleFontStyle : anyOf(:class:`FontStyle`, :class:`ExprRef`)
-        The font style of the header title.
-    titleFontWeight : anyOf(:class:`FontWeight`, :class:`ExprRef`)
-        Font weight of the header title. This can be either a string (e.g ``"bold"``,
-        ``"normal"`` ) or a number ( ``100``, ``200``, ``300``, ..., ``900`` where
-        ``"normal"`` = ``400`` and ``"bold"`` = ``700`` ).
-    titleLimit : anyOf(float, :class:`ExprRef`)
-        The maximum length of the header title in pixels. The text value will be
-        automatically truncated if the rendered size exceeds the limit.
-
-        **Default value:** ``0``, indicating no limit
-    titleLineHeight : anyOf(float, :class:`ExprRef`)
-        Line height in pixels for multi-line header title text or title text with
-        ``"line-top"`` or ``"line-bottom"`` baseline.
-    titleOrient : :class:`Orient`
-        The orientation of the header title. One of ``"top"``, ``"bottom"``, ``"left"`` or
-        ``"right"``.
-    titlePadding : anyOf(float, :class:`ExprRef`)
-        The padding, in pixel, between facet header's title and the label.
-
-        **Default value:** ``10``
-    """
-    _schema = {'$ref': '#/definitions/Header'}
-
-    def __init__(self, format=Undefined, formatType=Undefined, labelAlign=Undefined,
-                 labelAnchor=Undefined, labelAngle=Undefined, labelBaseline=Undefined,
-                 labelColor=Undefined, labelExpr=Undefined, labelFont=Undefined,
-                 labelFontSize=Undefined, labelFontStyle=Undefined, labelFontWeight=Undefined,
-                 labelLimit=Undefined, labelLineHeight=Undefined, labelOrient=Undefined,
-                 labelPadding=Undefined, labels=Undefined, orient=Undefined, title=Undefined,
-                 titleAlign=Undefined, titleAnchor=Undefined, titleAngle=Undefined,
-                 titleBaseline=Undefined, titleColor=Undefined, titleFont=Undefined,
-                 titleFontSize=Undefined, titleFontStyle=Undefined, titleFontWeight=Undefined,
-                 titleLimit=Undefined, titleLineHeight=Undefined, titleOrient=Undefined,
-                 titlePadding=Undefined, **kwds):
-        super(Header, self).__init__(format=format, formatType=formatType, labelAlign=labelAlign,
-                                     labelAnchor=labelAnchor, labelAngle=labelAngle,
-                                     labelBaseline=labelBaseline, labelColor=labelColor,
-                                     labelExpr=labelExpr, labelFont=labelFont,
-                                     labelFontSize=labelFontSize, labelFontStyle=labelFontStyle,
-                                     labelFontWeight=labelFontWeight, labelLimit=labelLimit,
-                                     labelLineHeight=labelLineHeight, labelOrient=labelOrient,
-                                     labelPadding=labelPadding, labels=labels, orient=orient,
-                                     title=title, titleAlign=titleAlign, titleAnchor=titleAnchor,
-                                     titleAngle=titleAngle, titleBaseline=titleBaseline,
-                                     titleColor=titleColor, titleFont=titleFont,
-                                     titleFontSize=titleFontSize, titleFontStyle=titleFontStyle,
-                                     titleFontWeight=titleFontWeight, titleLimit=titleLimit,
-                                     titleLineHeight=titleLineHeight, titleOrient=titleOrient,
-                                     titlePadding=titlePadding, **kwds)
-
-
-class HeaderConfig(VegaLiteSchema):
-    """HeaderConfig schema wrapper
-
-    Mapping(required=[])
-
-    Parameters
-    ----------
-
-    format : anyOf(string, :class:`Dict`)
-        When used with the default ``"number"`` and ``"time"`` format type, the text
-        formatting pattern for labels of guides (axes, legends, headers) and text marks.
-
-
-        * If the format type is ``"number"`` (e.g., for quantitative fields), this is D3's
-          `number format pattern <https://github.com/d3/d3-format#locale_format>`__.
-        * If the format type is ``"time"`` (e.g., for temporal fields), this is D3's `time
-          format pattern <https://github.com/d3/d3-time-format#locale_format>`__.
-
-        See the `format documentation <https://vega.github.io/vega-lite/docs/format.html>`__
-        for more examples.
-
-        When used with a `custom formatType
-        <https://vega.github.io/vega-lite/docs/config.html#custom-format-type>`__, this
-        value will be passed as ``format`` alongside ``datum.value`` to the registered
-        function.
-
-        **Default value:**  Derived from `numberFormat
-        <https://vega.github.io/vega-lite/docs/config.html#format>`__ config for number
-        format and from `timeFormat
-        <https://vega.github.io/vega-lite/docs/config.html#format>`__ config for time
-        format.
-    formatType : string
-        The format type for labels. One of ``"number"``, ``"time"``, or a `registered custom
-        format type
-        <https://vega.github.io/vega-lite/docs/config.html#custom-format-type>`__.
-
-        **Default value:**
-
-
-        * ``"time"`` for temporal fields and ordinal and nominal fields with ``timeUnit``.
-        * ``"number"`` for quantitative fields as well as ordinal and nominal fields without
-          ``timeUnit``.
-    labelAlign : anyOf(:class:`Align`, :class:`ExprRef`)
-        Horizontal text alignment of header labels. One of ``"left"``, ``"center"``, or
-        ``"right"``.
-    labelAnchor : :class:`TitleAnchor`
-        The anchor position for placing the labels. One of ``"start"``, ``"middle"``, or
-        ``"end"``. For example, with a label orientation of top these anchor positions map
-        to a left-, center-, or right-aligned label.
-    labelAngle : float
-        The rotation angle of the header labels.
-
-        **Default value:** ``0`` for column header, ``-90`` for row header.
-    labelBaseline : anyOf(:class:`TextBaseline`, :class:`ExprRef`)
-        The vertical text baseline for the header labels. One of ``"alphabetic"`` (default),
-        ``"top"``, ``"middle"``, ``"bottom"``, ``"line-top"``, or ``"line-bottom"``. The
-        ``"line-top"`` and ``"line-bottom"`` values operate similarly to ``"top"`` and
-        ``"bottom"``, but are calculated relative to the ``titleLineHeight`` rather than
-        ``titleFontSize`` alone.
-    labelColor : anyOf(:class:`Color`, :class:`ExprRef`)
-        The color of the header label, can be in hex color code or regular color name.
-    labelExpr : string
-        `Vega expression <https://vega.github.io/vega/docs/expressions/>`__ for customizing
-        labels.
-
-        **Note:** The label text and value can be assessed via the ``label`` and ``value``
-        properties of the header's backing ``datum`` object.
-    labelFont : anyOf(string, :class:`ExprRef`)
-        The font of the header label.
-    labelFontSize : anyOf(float, :class:`ExprRef`)
-        The font size of the header label, in pixels.
-    labelFontStyle : anyOf(:class:`FontStyle`, :class:`ExprRef`)
-        The font style of the header label.
-    labelFontWeight : anyOf(:class:`FontWeight`, :class:`ExprRef`)
-        The font weight of the header label.
-    labelLimit : anyOf(float, :class:`ExprRef`)
-        The maximum length of the header label in pixels. The text value will be
-        automatically truncated if the rendered size exceeds the limit.
-
-        **Default value:** ``0``, indicating no limit
-    labelLineHeight : anyOf(float, :class:`ExprRef`)
-        Line height in pixels for multi-line header labels or title text with ``"line-top"``
-        or ``"line-bottom"`` baseline.
-    labelOrient : :class:`Orient`
-        The orientation of the header label. One of ``"top"``, ``"bottom"``, ``"left"`` or
-        ``"right"``.
-    labelPadding : anyOf(float, :class:`ExprRef`)
-        The padding, in pixel, between facet header's label and the plot.
-
-        **Default value:** ``10``
-    labels : boolean
-        A boolean flag indicating if labels should be included as part of the header.
-
-        **Default value:** ``true``.
-    orient : :class:`Orient`
-        Shortcut for setting both labelOrient and titleOrient.
-    title : None
-        Set to null to disable title for the axis, legend, or header.
-    titleAlign : anyOf(:class:`Align`, :class:`ExprRef`)
-        Horizontal text alignment (to the anchor) of header titles.
-    titleAnchor : :class:`TitleAnchor`
-        The anchor position for placing the title. One of ``"start"``, ``"middle"``, or
-        ``"end"``. For example, with an orientation of top these anchor positions map to a
-        left-, center-, or right-aligned title.
-    titleAngle : float
-        The rotation angle of the header title.
-
-        **Default value:** ``0``.
-    titleBaseline : anyOf(:class:`TextBaseline`, :class:`ExprRef`)
-        The vertical text baseline for the header title. One of ``"alphabetic"`` (default),
-        ``"top"``, ``"middle"``, ``"bottom"``, ``"line-top"``, or ``"line-bottom"``. The
-        ``"line-top"`` and ``"line-bottom"`` values operate similarly to ``"top"`` and
-        ``"bottom"``, but are calculated relative to the ``titleLineHeight`` rather than
-        ``titleFontSize`` alone.
-
-        **Default value:** ``"middle"``
-    titleColor : anyOf(:class:`Color`, :class:`ExprRef`)
-        Color of the header title, can be in hex color code or regular color name.
-    titleFont : anyOf(string, :class:`ExprRef`)
-        Font of the header title. (e.g., ``"Helvetica Neue"`` ).
-    titleFontSize : anyOf(float, :class:`ExprRef`)
-        Font size of the header title.
-    titleFontStyle : anyOf(:class:`FontStyle`, :class:`ExprRef`)
-        The font style of the header title.
-    titleFontWeight : anyOf(:class:`FontWeight`, :class:`ExprRef`)
-        Font weight of the header title. This can be either a string (e.g ``"bold"``,
-        ``"normal"`` ) or a number ( ``100``, ``200``, ``300``, ..., ``900`` where
-        ``"normal"`` = ``400`` and ``"bold"`` = ``700`` ).
-    titleLimit : anyOf(float, :class:`ExprRef`)
-        The maximum length of the header title in pixels. The text value will be
-        automatically truncated if the rendered size exceeds the limit.
-
-        **Default value:** ``0``, indicating no limit
-    titleLineHeight : anyOf(float, :class:`ExprRef`)
-        Line height in pixels for multi-line header title text or title text with
-        ``"line-top"`` or ``"line-bottom"`` baseline.
-    titleOrient : :class:`Orient`
-        The orientation of the header title. One of ``"top"``, ``"bottom"``, ``"left"`` or
-        ``"right"``.
-    titlePadding : anyOf(float, :class:`ExprRef`)
-        The padding, in pixel, between facet header's title and the label.
-
-        **Default value:** ``10``
-    """
-    _schema = {'$ref': '#/definitions/HeaderConfig'}
-
-    def __init__(self, format=Undefined, formatType=Undefined, labelAlign=Undefined,
-                 labelAnchor=Undefined, labelAngle=Undefined, labelBaseline=Undefined,
-                 labelColor=Undefined, labelExpr=Undefined, labelFont=Undefined,
-                 labelFontSize=Undefined, labelFontStyle=Undefined, labelFontWeight=Undefined,
-                 labelLimit=Undefined, labelLineHeight=Undefined, labelOrient=Undefined,
-                 labelPadding=Undefined, labels=Undefined, orient=Undefined, title=Undefined,
-                 titleAlign=Undefined, titleAnchor=Undefined, titleAngle=Undefined,
-                 titleBaseline=Undefined, titleColor=Undefined, titleFont=Undefined,
-                 titleFontSize=Undefined, titleFontStyle=Undefined, titleFontWeight=Undefined,
-                 titleLimit=Undefined, titleLineHeight=Undefined, titleOrient=Undefined,
-                 titlePadding=Undefined, **kwds):
-        super(HeaderConfig, self).__init__(format=format, formatType=formatType, labelAlign=labelAlign,
-                                           labelAnchor=labelAnchor, labelAngle=labelAngle,
-                                           labelBaseline=labelBaseline, labelColor=labelColor,
-                                           labelExpr=labelExpr, labelFont=labelFont,
-                                           labelFontSize=labelFontSize, labelFontStyle=labelFontStyle,
-                                           labelFontWeight=labelFontWeight, labelLimit=labelLimit,
-                                           labelLineHeight=labelLineHeight, labelOrient=labelOrient,
-                                           labelPadding=labelPadding, labels=labels, orient=orient,
-                                           title=title, titleAlign=titleAlign, titleAnchor=titleAnchor,
-                                           titleAngle=titleAngle, titleBaseline=titleBaseline,
-                                           titleColor=titleColor, titleFont=titleFont,
-                                           titleFontSize=titleFontSize, titleFontStyle=titleFontStyle,
-                                           titleFontWeight=titleFontWeight, titleLimit=titleLimit,
-                                           titleLineHeight=titleLineHeight, titleOrient=titleOrient,
-                                           titlePadding=titlePadding, **kwds)
-
-
-class HexColor(Color):
-    """HexColor schema wrapper
-
-    string
-    """
-    _schema = {'$ref': '#/definitions/HexColor'}
-
-    def __init__(self, *args):
-        super(HexColor, self).__init__(*args)
-
-
-class ImputeMethod(VegaLiteSchema):
-    """ImputeMethod schema wrapper
-
-    enum('value', 'median', 'max', 'min', 'mean')
-    """
-    _schema = {'$ref': '#/definitions/ImputeMethod'}
-
-    def __init__(self, *args):
-        super(ImputeMethod, self).__init__(*args)
-
-
-class ImputeParams(VegaLiteSchema):
-    """ImputeParams schema wrapper
-
-    Mapping(required=[])
-
-    Parameters
-    ----------
-
-    frame : List(anyOf(None, float))
-        A frame specification as a two-element array used to control the window over which
-        the specified method is applied. The array entries should either be a number
-        indicating the offset from the current data object, or null to indicate unbounded
-        rows preceding or following the current data object. For example, the value ``[-5,
-        5]`` indicates that the window should include five objects preceding and five
-        objects following the current object.
-
-        **Default value:** :  ``[null, null]`` indicating that the window includes all
-        objects.
-    keyvals : anyOf(List(Any), :class:`ImputeSequence`)
-        Defines the key values that should be considered for imputation. An array of key
-        values or an object defining a `number sequence
-        <https://vega.github.io/vega-lite/docs/impute.html#sequence-def>`__.
-
-        If provided, this will be used in addition to the key values observed within the
-        input data. If not provided, the values will be derived from all unique values of
-        the ``key`` field. For ``impute`` in ``encoding``, the key field is the x-field if
-        the y-field is imputed, or vice versa.
-
-        If there is no impute grouping, this property *must* be specified.
-    method : :class:`ImputeMethod`
-        The imputation method to use for the field value of imputed data objects. One of
-        ``"value"``, ``"mean"``, ``"median"``, ``"max"`` or ``"min"``.
-
-        **Default value:**  ``"value"``
-    value : Any
-        The field value to use when the imputation ``method`` is ``"value"``.
-    """
-    _schema = {'$ref': '#/definitions/ImputeParams'}
-
-    def __init__(self, frame=Undefined, keyvals=Undefined, method=Undefined, value=Undefined, **kwds):
-        super(ImputeParams, self).__init__(frame=frame, keyvals=keyvals, method=method, value=value,
-                                           **kwds)
-
-
-class ImputeSequence(VegaLiteSchema):
-    """ImputeSequence schema wrapper
-
-    Mapping(required=[stop])
-
-    Parameters
-    ----------
-
-    stop : float
-        The ending value(exclusive) of the sequence.
-    start : float
-        The starting value of the sequence. **Default value:** ``0``
-    step : float
-        The step value between sequence entries. **Default value:** ``1`` or ``-1`` if
-        ``stop < start``
-    """
-    _schema = {'$ref': '#/definitions/ImputeSequence'}
-
-    def __init__(self, stop=Undefined, start=Undefined, step=Undefined, **kwds):
-        super(ImputeSequence, self).__init__(stop=stop, start=start, step=step, **kwds)
-
-
-class InlineData(DataSource):
-    """InlineData schema wrapper
-
-    Mapping(required=[values])
-
-    Parameters
-    ----------
-
-    values : :class:`InlineDataset`
-        The full data set, included inline. This can be an array of objects or primitive
-        values, an object, or a string. Arrays of primitive values are ingested as objects
-        with a ``data`` property. Strings are parsed according to the specified format type.
-    format : :class:`DataFormat`
-        An object that specifies the format for parsing the data.
-    name : string
-        Provide a placeholder name and bind data at runtime.
-    """
-    _schema = {'$ref': '#/definitions/InlineData'}
-
-    def __init__(self, values=Undefined, format=Undefined, name=Undefined, **kwds):
-        super(InlineData, self).__init__(values=values, format=format, name=name, **kwds)
-
-
-class InlineDataset(VegaLiteSchema):
-    """InlineDataset schema wrapper
-
-    anyOf(List(float), List(string), List(boolean), List(Mapping(required=[])), string,
-    Mapping(required=[]))
-    """
-    _schema = {'$ref': '#/definitions/InlineDataset'}
-
-    def __init__(self, *args, **kwds):
-        super(InlineDataset, self).__init__(*args, **kwds)
-
-
-class Interpolate(VegaLiteSchema):
-    """Interpolate schema wrapper
-
-    enum('basis', 'basis-open', 'basis-closed', 'bundle', 'cardinal', 'cardinal-open',
-    'cardinal-closed', 'catmull-rom', 'linear', 'linear-closed', 'monotone', 'natural', 'step',
-    'step-before', 'step-after')
-    """
-    _schema = {'$ref': '#/definitions/Interpolate'}
-
-    def __init__(self, *args):
-        super(Interpolate, self).__init__(*args)
-
-
-class IntervalSelectionConfig(VegaLiteSchema):
-    """IntervalSelectionConfig schema wrapper
-
-    Mapping(required=[type])
-
-    Parameters
-    ----------
-
-    type : string
-        Determines the default event processing and data query for the selection. Vega-Lite
-        currently supports two selection types:
-
-
-        * ``"point"`` -- to select multiple discrete data values; the first value is
-          selected on ``click`` and additional values toggled on shift-click.
-        * ``"interval"`` -- to select a continuous range of data values on ``drag``.
-    clear : anyOf(:class:`Stream`, string, boolean)
-        Clears the selection, emptying it of all values. This property can be a `Event
-        Stream <https://vega.github.io/vega/docs/event-streams/>`__ or ``false`` to disable
-        clear.
-
-        **Default value:** ``dblclick``.
-
-        **See also:** `clear examples
-        <https://vega.github.io/vega-lite/docs/selection.html#clear>`__ in the
-        documentation.
-    encodings : List(:class:`SingleDefUnitChannel`)
-        An array of encoding channels. The corresponding data field values must match for a
-        data tuple to fall within the selection.
-
-        **See also:** The `projection with encodings and fields section
-        <https://vega.github.io/vega-lite/docs/selection.html#project>`__ in the
-        documentation.
-    fields : List(:class:`FieldName`)
-        An array of field names whose values must match for a data tuple to fall within the
-        selection.
-
-        **See also:** The `projection with encodings and fields section
-        <https://vega.github.io/vega-lite/docs/selection.html#project>`__ in the
-        documentation.
-    mark : :class:`BrushConfig`
-        An interval selection also adds a rectangle mark to depict the extents of the
-        interval. The ``mark`` property can be used to customize the appearance of the mark.
-
-        **See also:** `mark examples
-        <https://vega.github.io/vega-lite/docs/selection.html#mark>`__ in the documentation.
-    on : anyOf(:class:`Stream`, string)
-        A `Vega event stream <https://vega.github.io/vega/docs/event-streams/>`__ (object or
-        selector) that triggers the selection. For interval selections, the event stream
-        must specify a `start and end
-        <https://vega.github.io/vega/docs/event-streams/#between-filters>`__.
-
-        **See also:** `on examples
-        <https://vega.github.io/vega-lite/docs/selection.html#on>`__ in the documentation.
-    resolve : :class:`SelectionResolution`
-        With layered and multi-view displays, a strategy that determines how selections'
-        data queries are resolved when applied in a filter transform, conditional encoding
-        rule, or scale domain.
-
-        One of:
-
-
-        * ``"global"`` -- only one brush exists for the entire SPLOM. When the user begins
-          to drag, any previous brushes are cleared, and a new one is constructed.
-        * ``"union"`` -- each cell contains its own brush, and points are highlighted if
-          they lie within *any* of these individual brushes.
-        * ``"intersect"`` -- each cell contains its own brush, and points are highlighted
-          only if they fall within *all* of these individual brushes.
-
-        **Default value:** ``global``.
-
-        **See also:** `resolve examples
-        <https://vega.github.io/vega-lite/docs/selection.html#resolve>`__ in the
-        documentation.
-    translate : anyOf(string, boolean)
-        When truthy, allows a user to interactively move an interval selection
-        back-and-forth. Can be ``true``, ``false`` (to disable panning), or a `Vega event
-        stream definition <https://vega.github.io/vega/docs/event-streams/>`__ which must
-        include a start and end event to trigger continuous panning. Discrete panning (e.g.,
-        pressing the left/right arrow keys) will be supported in future versions.
-
-        **Default value:** ``true``, which corresponds to ``[mousedown, window:mouseup] >
-        window:mousemove!``. This default allows users to clicks and drags within an
-        interval selection to reposition it.
-
-        **See also:** `translate examples
-        <https://vega.github.io/vega-lite/docs/selection.html#translate>`__ in the
-        documentation.
-    zoom : anyOf(string, boolean)
-        When truthy, allows a user to interactively resize an interval selection. Can be
-        ``true``, ``false`` (to disable zooming), or a `Vega event stream definition
-        <https://vega.github.io/vega/docs/event-streams/>`__. Currently, only ``wheel``
-        events are supported, but custom event streams can still be used to specify filters,
-        debouncing, and throttling. Future versions will expand the set of events that can
-        trigger this transformation.
-
-        **Default value:** ``true``, which corresponds to ``wheel!``. This default allows
-        users to use the mouse wheel to resize an interval selection.
-
-        **See also:** `zoom examples
-        <https://vega.github.io/vega-lite/docs/selection.html#zoom>`__ in the documentation.
-    """
-    _schema = {'$ref': '#/definitions/IntervalSelectionConfig'}
-
-    def __init__(self, type=Undefined, clear=Undefined, encodings=Undefined, fields=Undefined,
-                 mark=Undefined, on=Undefined, resolve=Undefined, translate=Undefined, zoom=Undefined,
-                 **kwds):
-        super(IntervalSelectionConfig, self).__init__(type=type, clear=clear, encodings=encodings,
-                                                      fields=fields, mark=mark, on=on, resolve=resolve,
-                                                      translate=translate, zoom=zoom, **kwds)
-
-
-class IntervalSelectionConfigWithoutType(VegaLiteSchema):
-    """IntervalSelectionConfigWithoutType schema wrapper
-
-    Mapping(required=[])
-
-    Parameters
-    ----------
-
-    clear : anyOf(:class:`Stream`, string, boolean)
-        Clears the selection, emptying it of all values. This property can be a `Event
-        Stream <https://vega.github.io/vega/docs/event-streams/>`__ or ``false`` to disable
-        clear.
-
-        **Default value:** ``dblclick``.
-
-        **See also:** `clear examples
-        <https://vega.github.io/vega-lite/docs/selection.html#clear>`__ in the
-        documentation.
-    encodings : List(:class:`SingleDefUnitChannel`)
-        An array of encoding channels. The corresponding data field values must match for a
-        data tuple to fall within the selection.
-
-        **See also:** The `projection with encodings and fields section
-        <https://vega.github.io/vega-lite/docs/selection.html#project>`__ in the
-        documentation.
-    fields : List(:class:`FieldName`)
-        An array of field names whose values must match for a data tuple to fall within the
-        selection.
-
-        **See also:** The `projection with encodings and fields section
-        <https://vega.github.io/vega-lite/docs/selection.html#project>`__ in the
-        documentation.
-    mark : :class:`BrushConfig`
-        An interval selection also adds a rectangle mark to depict the extents of the
-        interval. The ``mark`` property can be used to customize the appearance of the mark.
-
-        **See also:** `mark examples
-        <https://vega.github.io/vega-lite/docs/selection.html#mark>`__ in the documentation.
-    on : anyOf(:class:`Stream`, string)
-        A `Vega event stream <https://vega.github.io/vega/docs/event-streams/>`__ (object or
-        selector) that triggers the selection. For interval selections, the event stream
-        must specify a `start and end
-        <https://vega.github.io/vega/docs/event-streams/#between-filters>`__.
-
-        **See also:** `on examples
-        <https://vega.github.io/vega-lite/docs/selection.html#on>`__ in the documentation.
-    resolve : :class:`SelectionResolution`
-        With layered and multi-view displays, a strategy that determines how selections'
-        data queries are resolved when applied in a filter transform, conditional encoding
-        rule, or scale domain.
-
-        One of:
-
-
-        * ``"global"`` -- only one brush exists for the entire SPLOM. When the user begins
-          to drag, any previous brushes are cleared, and a new one is constructed.
-        * ``"union"`` -- each cell contains its own brush, and points are highlighted if
-          they lie within *any* of these individual brushes.
-        * ``"intersect"`` -- each cell contains its own brush, and points are highlighted
-          only if they fall within *all* of these individual brushes.
-
-        **Default value:** ``global``.
-
-        **See also:** `resolve examples
-        <https://vega.github.io/vega-lite/docs/selection.html#resolve>`__ in the
-        documentation.
-    translate : anyOf(string, boolean)
-        When truthy, allows a user to interactively move an interval selection
-        back-and-forth. Can be ``true``, ``false`` (to disable panning), or a `Vega event
-        stream definition <https://vega.github.io/vega/docs/event-streams/>`__ which must
-        include a start and end event to trigger continuous panning. Discrete panning (e.g.,
-        pressing the left/right arrow keys) will be supported in future versions.
-
-        **Default value:** ``true``, which corresponds to ``[mousedown, window:mouseup] >
-        window:mousemove!``. This default allows users to clicks and drags within an
-        interval selection to reposition it.
-
-        **See also:** `translate examples
-        <https://vega.github.io/vega-lite/docs/selection.html#translate>`__ in the
-        documentation.
-    zoom : anyOf(string, boolean)
-        When truthy, allows a user to interactively resize an interval selection. Can be
-        ``true``, ``false`` (to disable zooming), or a `Vega event stream definition
-        <https://vega.github.io/vega/docs/event-streams/>`__. Currently, only ``wheel``
-        events are supported, but custom event streams can still be used to specify filters,
-        debouncing, and throttling. Future versions will expand the set of events that can
-        trigger this transformation.
-
-        **Default value:** ``true``, which corresponds to ``wheel!``. This default allows
-        users to use the mouse wheel to resize an interval selection.
-
-        **See also:** `zoom examples
-        <https://vega.github.io/vega-lite/docs/selection.html#zoom>`__ in the documentation.
-    """
-    _schema = {'$ref': '#/definitions/IntervalSelectionConfigWithoutType'}
-
-    def __init__(self, clear=Undefined, encodings=Undefined, fields=Undefined, mark=Undefined,
-                 on=Undefined, resolve=Undefined, translate=Undefined, zoom=Undefined, **kwds):
-        super(IntervalSelectionConfigWithoutType, self).__init__(clear=clear, encodings=encodings,
-                                                                 fields=fields, mark=mark, on=on,
-                                                                 resolve=resolve, translate=translate,
-                                                                 zoom=zoom, **kwds)
-
-
-class JoinAggregateFieldDef(VegaLiteSchema):
-    """JoinAggregateFieldDef schema wrapper
-
-    Mapping(required=[op, as])
-
-    Parameters
-    ----------
-
-    op : :class:`AggregateOp`
-        The aggregation operation to apply (e.g., ``"sum"``, ``"average"`` or ``"count"`` ).
-        See the list of all supported operations `here
-        <https://vega.github.io/vega-lite/docs/aggregate.html#ops>`__.
-    field : :class:`FieldName`
-        The data field for which to compute the aggregate function. This can be omitted for
-        functions that do not operate over a field such as ``"count"``.
-    as : :class:`FieldName`
-        The output name for the join aggregate operation.
-    """
-    _schema = {'$ref': '#/definitions/JoinAggregateFieldDef'}
-
-    def __init__(self, op=Undefined, field=Undefined, **kwds):
-        super(JoinAggregateFieldDef, self).__init__(op=op, field=field, **kwds)
-
-
-class JsonDataFormat(DataFormat):
-    """JsonDataFormat schema wrapper
-
-    Mapping(required=[])
-
-    Parameters
-    ----------
-
-    parse : anyOf(:class:`Parse`, None)
-        If set to ``null``, disable type inference based on the spec and only use type
-        inference based on the data. Alternatively, a parsing directive object can be
-        provided for explicit data types. Each property of the object corresponds to a field
-        name, and the value to the desired data type (one of ``"number"``, ``"boolean"``,
-        ``"date"``, or null (do not parse the field)). For example, ``"parse":
-        {"modified_on": "date"}`` parses the ``modified_on`` field in each input record a
-        Date value.
-
-        For ``"date"``, we parse data based using JavaScript's `Date.parse()
-        <https://developer.mozilla.org/en-US/docs/Web/JavaScript/Reference/Global_Objects/Date/parse>`__.
-        For Specific date formats can be provided (e.g., ``{foo: "date:'%m%d%Y'"}`` ), using
-        the `d3-time-format syntax <https://github.com/d3/d3-time-format#locale_format>`__.
-        UTC date format parsing is supported similarly (e.g., ``{foo: "utc:'%m%d%Y'"}`` ).
-        See more about `UTC time
-        <https://vega.github.io/vega-lite/docs/timeunit.html#utc>`__
-    property : string
-        The JSON property containing the desired data. This parameter can be used when the
-        loaded JSON file may have surrounding structure or meta-data. For example
-        ``"property": "values.features"`` is equivalent to retrieving
-        ``json.values.features`` from the loaded JSON object.
-    type : string
-        Type of input data: ``"json"``, ``"csv"``, ``"tsv"``, ``"dsv"``.
-
-        **Default value:**  The default format type is determined by the extension of the
-        file URL. If no extension is detected, ``"json"`` will be used by default.
-    """
-    _schema = {'$ref': '#/definitions/JsonDataFormat'}
-
-    def __init__(self, parse=Undefined, property=Undefined, type=Undefined, **kwds):
-        super(JsonDataFormat, self).__init__(parse=parse, property=property, type=type, **kwds)
-
-
-class LabelOverlap(VegaLiteSchema):
-    """LabelOverlap schema wrapper
-
-    anyOf(boolean, string, string)
-    """
-    _schema = {'$ref': '#/definitions/LabelOverlap'}
-
-    def __init__(self, *args, **kwds):
-        super(LabelOverlap, self).__init__(*args, **kwds)
-
-
-class LatLongDef(VegaLiteSchema):
-    """LatLongDef schema wrapper
-
-    anyOf(:class:`LatLongFieldDef`, :class:`DatumDef`)
-    """
-    _schema = {'$ref': '#/definitions/LatLongDef'}
-
-    def __init__(self, *args, **kwds):
-        super(LatLongDef, self).__init__(*args, **kwds)
-
-
-class LatLongFieldDef(LatLongDef):
-    """LatLongFieldDef schema wrapper
-
-    Mapping(required=[])
-
-    Parameters
-    ----------
-
-    aggregate : :class:`Aggregate`
-        Aggregation function for the field (e.g., ``"mean"``, ``"sum"``, ``"median"``,
-        ``"min"``, ``"max"``, ``"count"`` ).
-
-        **Default value:** ``undefined`` (None)
-
-        **See also:** `aggregate <https://vega.github.io/vega-lite/docs/aggregate.html>`__
-        documentation.
-    bandPosition : float
-        Relative position on a band of a stacked, binned, time unit, or band scale. For
-        example, the marks will be positioned at the beginning of the band if set to ``0``,
-        and at the middle of the band if set to ``0.5``.
-    bin : None
-        A flag for binning a ``quantitative`` field, `an object defining binning parameters
-        <https://vega.github.io/vega-lite/docs/bin.html#bin-parameters>`__, or indicating
-        that the data for ``x`` or ``y`` channel are binned before they are imported into
-        Vega-Lite ( ``"binned"`` ).
-
-
-        If ``true``, default `binning parameters
-        <https://vega.github.io/vega-lite/docs/bin.html#bin-parameters>`__ will be applied.
-
-        If ``"binned"``, this indicates that the data for the ``x`` (or ``y`` ) channel are
-        already binned. You can map the bin-start field to ``x`` (or ``y`` ) and the bin-end
-        field to ``x2`` (or ``y2`` ). The scale and axis will be formatted similar to
-        binning in Vega-Lite.  To adjust the axis ticks based on the bin step, you can also
-        set the axis's `tickMinStep
-        <https://vega.github.io/vega-lite/docs/axis.html#ticks>`__ property.
-
-        **Default value:** ``false``
-
-        **See also:** `bin <https://vega.github.io/vega-lite/docs/bin.html>`__
-        documentation.
-    field : :class:`Field`
-        **Required.** A string defining the name of the field from which to pull a data
-        value or an object defining iterated values from the `repeat
-        <https://vega.github.io/vega-lite/docs/repeat.html>`__ operator.
-
-        **See also:** `field <https://vega.github.io/vega-lite/docs/field.html>`__
-        documentation.
-
-        **Notes:** 1)  Dots ( ``.`` ) and brackets ( ``[`` and ``]`` ) can be used to access
-        nested objects (e.g., ``"field": "foo.bar"`` and ``"field": "foo['bar']"`` ). If
-        field names contain dots or brackets but are not nested, you can use ``\\`` to
-        escape dots and brackets (e.g., ``"a\\.b"`` and ``"a\\[0\\]"`` ). See more details
-        about escaping in the `field documentation
-        <https://vega.github.io/vega-lite/docs/field.html>`__. 2) ``field`` is not required
-        if ``aggregate`` is ``count``.
-    timeUnit : anyOf(:class:`TimeUnit`, :class:`BinnedTimeUnit`, :class:`TimeUnitParams`)
-        Time unit (e.g., ``year``, ``yearmonth``, ``month``, ``hours`` ) for a temporal
-        field. or `a temporal field that gets casted as ordinal
-        <https://vega.github.io/vega-lite/docs/type.html#cast>`__.
-
-        **Default value:** ``undefined`` (None)
-
-        **See also:** `timeUnit <https://vega.github.io/vega-lite/docs/timeunit.html>`__
-        documentation.
-    title : anyOf(:class:`Text`, None)
-        A title for the field. If ``null``, the title will be removed.
-
-        **Default value:**  derived from the field's name and transformation function (
-        ``aggregate``, ``bin`` and ``timeUnit`` ). If the field has an aggregate function,
-        the function is displayed as part of the title (e.g., ``"Sum of Profit"`` ). If the
-        field is binned or has a time unit applied, the applied function is shown in
-        parentheses (e.g., ``"Profit (binned)"``, ``"Transaction Date (year-month)"`` ).
-        Otherwise, the title is simply the field name.
-
-        **Notes** :
-
-        1) You can customize the default field title format by providing the `fieldTitle
-        <https://vega.github.io/vega-lite/docs/config.html#top-level-config>`__ property in
-        the `config <https://vega.github.io/vega-lite/docs/config.html>`__ or `fieldTitle
-        function via the compile function's options
-        <https://vega.github.io/vega-lite/usage/compile.html#field-title>`__.
-
-        2) If both field definition's ``title`` and axis, header, or legend ``title`` are
-        defined, axis/header/legend title will be used.
-    type : string
-        The type of measurement ( ``"quantitative"``, ``"temporal"``, ``"ordinal"``, or
-        ``"nominal"`` ) for the encoded field or constant value ( ``datum`` ). It can also
-        be a ``"geojson"`` type for encoding `'geoshape'
-        <https://vega.github.io/vega-lite/docs/geoshape.html>`__.
-
-        Vega-Lite automatically infers data types in many cases as discussed below. However,
-        type is required for a field if: (1) the field is not nominal and the field encoding
-        has no specified ``aggregate`` (except ``argmin`` and ``argmax`` ), ``bin``, scale
-        type, custom ``sort`` order, nor ``timeUnit`` or (2) if you wish to use an ordinal
-        scale for a field with ``bin`` or ``timeUnit``.
-
-        **Default value:**
-
-        1) For a data ``field``, ``"nominal"`` is the default data type unless the field
-        encoding has ``aggregate``, ``channel``, ``bin``, scale type, ``sort``, or
-        ``timeUnit`` that satisfies the following criteria:
-
-
-        * ``"quantitative"`` is the default type if (1) the encoded field contains ``bin``
-          or ``aggregate`` except ``"argmin"`` and ``"argmax"``, (2) the encoding channel is
-          ``latitude`` or ``longitude`` channel or (3) if the specified scale type is `a
-          quantitative scale <https://vega.github.io/vega-lite/docs/scale.html#type>`__.
-        * ``"temporal"`` is the default type if (1) the encoded field contains ``timeUnit``
-          or (2) the specified scale type is a time or utc scale
-        * ``"ordinal"`` is the default type if (1) the encoded field contains a `custom sort
-          order
-          <https://vega.github.io/vega-lite/docs/sort.html#specifying-custom-sort-order>`__,
-          (2) the specified scale type is an ordinal/point/band scale, or (3) the encoding
-          channel is ``order``.
-
-        2) For a constant value in data domain ( ``datum`` ):
-
-
-        * ``"quantitative"`` if the datum is a number
-        * ``"nominal"`` if the datum is a string
-        * ``"temporal"`` if the datum is `a date time object
-          <https://vega.github.io/vega-lite/docs/datetime.html>`__
-
-        **Note:**
-
-
-        * Data ``type`` describes the semantics of the data rather than the primitive data
-          types (number, string, etc.). The same primitive data type can have different
-          types of measurement. For example, numeric data can represent quantitative,
-          ordinal, or nominal data.
-        * Data values for a temporal field can be either a date-time string (e.g.,
-          ``"2015-03-07 12:32:17"``, ``"17:01"``, ``"2015-03-16"``. ``"2015"`` ) or a
-          timestamp number (e.g., ``1552199579097`` ).
-        * When using with `bin <https://vega.github.io/vega-lite/docs/bin.html>`__, the
-          ``type`` property can be either ``"quantitative"`` (for using a linear bin scale)
-          or `"ordinal" (for using an ordinal bin scale)
-          <https://vega.github.io/vega-lite/docs/type.html#cast-bin>`__.
-        * When using with `timeUnit
-          <https://vega.github.io/vega-lite/docs/timeunit.html>`__, the ``type`` property
-          can be either ``"temporal"`` (default, for using a temporal scale) or `"ordinal"
-          (for using an ordinal scale)
-          <https://vega.github.io/vega-lite/docs/type.html#cast-bin>`__.
-        * When using with `aggregate
-          <https://vega.github.io/vega-lite/docs/aggregate.html>`__, the ``type`` property
-          refers to the post-aggregation data type. For example, we can calculate count
-          ``distinct`` of a categorical field ``"cat"`` using ``{"aggregate": "distinct",
-          "field": "cat"}``. The ``"type"`` of the aggregate output is ``"quantitative"``.
-        * Secondary channels (e.g., ``x2``, ``y2``, ``xError``, ``yError`` ) do not have
-          ``type`` as they must have exactly the same type as their primary channels (e.g.,
-          ``x``, ``y`` ).
-
-        **See also:** `type <https://vega.github.io/vega-lite/docs/type.html>`__
-        documentation.
-    """
-    _schema = {'$ref': '#/definitions/LatLongFieldDef'}
-
-    def __init__(self, aggregate=Undefined, bandPosition=Undefined, bin=Undefined, field=Undefined,
-                 timeUnit=Undefined, title=Undefined, type=Undefined, **kwds):
-        super(LatLongFieldDef, self).__init__(aggregate=aggregate, bandPosition=bandPosition, bin=bin,
-                                              field=field, timeUnit=timeUnit, title=title, type=type,
-                                              **kwds)
-
-
-class LayerRepeatMapping(VegaLiteSchema):
-    """LayerRepeatMapping schema wrapper
-
-    Mapping(required=[layer])
-
-    Parameters
-    ----------
-
-    layer : List(string)
-        An array of fields to be repeated as layers.
-    column : List(string)
-        An array of fields to be repeated horizontally.
-    row : List(string)
-        An array of fields to be repeated vertically.
-    """
-    _schema = {'$ref': '#/definitions/LayerRepeatMapping'}
-
-    def __init__(self, layer=Undefined, column=Undefined, row=Undefined, **kwds):
-        super(LayerRepeatMapping, self).__init__(layer=layer, column=column, row=row, **kwds)
-
-
-class LayoutAlign(VegaLiteSchema):
-    """LayoutAlign schema wrapper
-
-    enum('all', 'each', 'none')
-    """
-    _schema = {'$ref': '#/definitions/LayoutAlign'}
-
-    def __init__(self, *args):
-        super(LayoutAlign, self).__init__(*args)
-
-
-class Legend(VegaLiteSchema):
-    """Legend schema wrapper
-
-    Mapping(required=[])
-    Properties of a legend or boolean flag for determining whether to show it.
-
-    Parameters
-    ----------
-
-    aria : anyOf(boolean, :class:`ExprRef`)
-        A boolean flag indicating if `ARIA attributes
-        <https://developer.mozilla.org/en-US/docs/Web/Accessibility/ARIA>`__ should be
-        included (SVG output only). If ``false``, the "aria-hidden" attribute will be set on
-        the output SVG group, removing the legend from the ARIA accessibility tree.
-
-        **Default value:** ``true``
-    clipHeight : anyOf(float, :class:`ExprRef`)
-        The height in pixels to clip symbol legend entries and limit their size.
-    columnPadding : anyOf(float, :class:`ExprRef`)
-        The horizontal padding in pixels between symbol legend entries.
-
-        **Default value:** ``10``.
-    columns : anyOf(float, :class:`ExprRef`)
-        The number of columns in which to arrange symbol legend entries. A value of ``0`` or
-        lower indicates a single row with one column per entry.
-    cornerRadius : anyOf(float, :class:`ExprRef`)
-        Corner radius for the full legend.
-    description : anyOf(string, :class:`ExprRef`)
-        A text description of this legend for `ARIA accessibility
-        <https://developer.mozilla.org/en-US/docs/Web/Accessibility/ARIA>`__ (SVG output
-        only). If the ``aria`` property is true, for SVG output the `"aria-label" attribute
-        <https://developer.mozilla.org/en-US/docs/Web/Accessibility/ARIA/ARIA_Techniques/Using_the_aria-label_attribute>`__
-        will be set to this description. If the description is unspecified it will be
-        automatically generated.
-    direction : :class:`Orientation`
-        The direction of the legend, one of ``"vertical"`` or ``"horizontal"``.
-
-        **Default value:**
-
-
-        * For top-/bottom- ``orient`` ed legends, ``"horizontal"``
-        * For left-/right- ``orient`` ed legends, ``"vertical"``
-        * For top/bottom-left/right- ``orient`` ed legends, ``"horizontal"`` for gradient
-          legends and ``"vertical"`` for symbol legends.
-    fillColor : anyOf(anyOf(None, :class:`Color`), :class:`ExprRef`)
-        Background fill color for the full legend.
-    format : anyOf(string, :class:`Dict`)
-        When used with the default ``"number"`` and ``"time"`` format type, the text
-        formatting pattern for labels of guides (axes, legends, headers) and text marks.
-
-
-        * If the format type is ``"number"`` (e.g., for quantitative fields), this is D3's
-          `number format pattern <https://github.com/d3/d3-format#locale_format>`__.
-        * If the format type is ``"time"`` (e.g., for temporal fields), this is D3's `time
-          format pattern <https://github.com/d3/d3-time-format#locale_format>`__.
-
-        See the `format documentation <https://vega.github.io/vega-lite/docs/format.html>`__
-        for more examples.
-
-        When used with a `custom formatType
-        <https://vega.github.io/vega-lite/docs/config.html#custom-format-type>`__, this
-        value will be passed as ``format`` alongside ``datum.value`` to the registered
-        function.
-
-        **Default value:**  Derived from `numberFormat
-        <https://vega.github.io/vega-lite/docs/config.html#format>`__ config for number
-        format and from `timeFormat
-        <https://vega.github.io/vega-lite/docs/config.html#format>`__ config for time
-        format.
-    formatType : string
-        The format type for labels. One of ``"number"``, ``"time"``, or a `registered custom
-        format type
-        <https://vega.github.io/vega-lite/docs/config.html#custom-format-type>`__.
-
-        **Default value:**
-
-
-        * ``"time"`` for temporal fields and ordinal and nominal fields with ``timeUnit``.
-        * ``"number"`` for quantitative fields as well as ordinal and nominal fields without
-          ``timeUnit``.
-    gradientLength : anyOf(float, :class:`ExprRef`)
-        The length in pixels of the primary axis of a color gradient. This value corresponds
-        to the height of a vertical gradient or the width of a horizontal gradient.
-
-        **Default value:** ``200``.
-    gradientOpacity : anyOf(float, :class:`ExprRef`)
-        Opacity of the color gradient.
-    gradientStrokeColor : anyOf(anyOf(None, :class:`Color`), :class:`ExprRef`)
-        The color of the gradient stroke, can be in hex color code or regular color name.
-
-        **Default value:** ``"lightGray"``.
-    gradientStrokeWidth : anyOf(float, :class:`ExprRef`)
-        The width of the gradient stroke, in pixels.
-
-        **Default value:** ``0``.
-    gradientThickness : anyOf(float, :class:`ExprRef`)
-        The thickness in pixels of the color gradient. This value corresponds to the width
-        of a vertical gradient or the height of a horizontal gradient.
-
-        **Default value:** ``16``.
-    gridAlign : anyOf(:class:`LayoutAlign`, :class:`ExprRef`)
-        The alignment to apply to symbol legends rows and columns. The supported string
-        values are ``"all"``, ``"each"`` (the default), and ``none``. For more information,
-        see the `grid layout documentation <https://vega.github.io/vega/docs/layout>`__.
-
-        **Default value:** ``"each"``.
-    labelAlign : anyOf(:class:`Align`, :class:`ExprRef`)
-        The alignment of the legend label, can be left, center, or right.
-    labelBaseline : anyOf(:class:`TextBaseline`, :class:`ExprRef`)
-        The position of the baseline of legend label, can be ``"top"``, ``"middle"``,
-        ``"bottom"``, or ``"alphabetic"``.
-
-        **Default value:** ``"middle"``.
-    labelColor : anyOf(anyOf(None, :class:`Color`), :class:`ExprRef`)
-        The color of the legend label, can be in hex color code or regular color name.
-    labelExpr : string
-        `Vega expression <https://vega.github.io/vega/docs/expressions/>`__ for customizing
-        labels.
-
-        **Note:** The label text and value can be assessed via the ``label`` and ``value``
-        properties of the legend's backing ``datum`` object.
-    labelFont : anyOf(string, :class:`ExprRef`)
-        The font of the legend label.
-    labelFontSize : anyOf(float, :class:`ExprRef`)
-        The font size of legend label.
-
-        **Default value:** ``10``.
-    labelFontStyle : anyOf(:class:`FontStyle`, :class:`ExprRef`)
-        The font style of legend label.
-    labelFontWeight : anyOf(:class:`FontWeight`, :class:`ExprRef`)
-        The font weight of legend label.
-    labelLimit : anyOf(float, :class:`ExprRef`)
-        Maximum allowed pixel width of legend tick labels.
-
-        **Default value:** ``160``.
-    labelOffset : anyOf(float, :class:`ExprRef`)
-        The offset of the legend label.
-
-        **Default value:** ``4``.
-    labelOpacity : anyOf(float, :class:`ExprRef`)
-        Opacity of labels.
-    labelOverlap : anyOf(:class:`LabelOverlap`, :class:`ExprRef`)
-        The strategy to use for resolving overlap of labels in gradient legends. If
-        ``false``, no overlap reduction is attempted. If set to ``true`` (default) or
-        ``"parity"``, a strategy of removing every other label is used. If set to
-        ``"greedy"``, a linear scan of the labels is performed, removing any label that
-        overlaps with the last visible label (this often works better for log-scaled axes).
-
-        **Default value:** ``true``.
-    labelPadding : anyOf(float, :class:`ExprRef`)
-        Padding in pixels between the legend and legend labels.
-    labelSeparation : anyOf(float, :class:`ExprRef`)
-        The minimum separation that must be between label bounding boxes for them to be
-        considered non-overlapping (default ``0`` ). This property is ignored if
-        *labelOverlap* resolution is not enabled.
-    legendX : anyOf(float, :class:`ExprRef`)
-        Custom x-position for legend with orient "none".
-    legendY : anyOf(float, :class:`ExprRef`)
-        Custom y-position for legend with orient "none".
-    offset : anyOf(float, :class:`ExprRef`)
-        The offset in pixels by which to displace the legend from the data rectangle and
-        axes.
-
-        **Default value:** ``18``.
-    orient : :class:`LegendOrient`
-        The orientation of the legend, which determines how the legend is positioned within
-        the scene. One of ``"left"``, ``"right"``, ``"top"``, ``"bottom"``, ``"top-left"``,
-        ``"top-right"``, ``"bottom-left"``, ``"bottom-right"``, ``"none"``.
-
-        **Default value:** ``"right"``
-    padding : anyOf(float, :class:`ExprRef`)
-        The padding between the border and content of the legend group.
-
-        **Default value:** ``0``.
-    rowPadding : anyOf(float, :class:`ExprRef`)
-        The vertical padding in pixels between symbol legend entries.
-
-        **Default value:** ``2``.
-    strokeColor : anyOf(anyOf(None, :class:`Color`), :class:`ExprRef`)
-        Border stroke color for the full legend.
-    symbolDash : anyOf(List(float), :class:`ExprRef`)
-        An array of alternating [stroke, space] lengths for dashed symbol strokes.
-    symbolDashOffset : anyOf(float, :class:`ExprRef`)
-        The pixel offset at which to start drawing with the symbol stroke dash array.
-    symbolFillColor : anyOf(anyOf(None, :class:`Color`), :class:`ExprRef`)
-        The color of the legend symbol,
-    symbolLimit : anyOf(float, :class:`ExprRef`)
-        The maximum number of allowed entries for a symbol legend. Additional entries will
-        be dropped.
-    symbolOffset : anyOf(float, :class:`ExprRef`)
-        Horizontal pixel offset for legend symbols.
-
-        **Default value:** ``0``.
-    symbolOpacity : anyOf(float, :class:`ExprRef`)
-        Opacity of the legend symbols.
-    symbolSize : anyOf(float, :class:`ExprRef`)
-        The size of the legend symbol, in pixels.
-
-        **Default value:** ``100``.
-    symbolStrokeColor : anyOf(anyOf(None, :class:`Color`), :class:`ExprRef`)
-        Stroke color for legend symbols.
-    symbolStrokeWidth : anyOf(float, :class:`ExprRef`)
-        The width of the symbol's stroke.
-
-        **Default value:** ``1.5``.
-    symbolType : anyOf(:class:`SymbolShape`, :class:`ExprRef`)
-        The symbol shape. One of the plotting shapes ``circle`` (default), ``square``,
-        ``cross``, ``diamond``, ``triangle-up``, ``triangle-down``, ``triangle-right``, or
-        ``triangle-left``, the line symbol ``stroke``, or one of the centered directional
-        shapes ``arrow``, ``wedge``, or ``triangle``. Alternatively, a custom `SVG path
-        string <https://developer.mozilla.org/en-US/docs/Web/SVG/Tutorial/Paths>`__ can be
-        provided. For correct sizing, custom shape paths should be defined within a square
-        bounding box with coordinates ranging from -1 to 1 along both the x and y
-        dimensions.
-
-        **Default value:** ``"circle"``.
-    tickCount : anyOf(:class:`TickCount`, :class:`ExprRef`)
-        The desired number of tick values for quantitative legends.
-    tickMinStep : anyOf(float, :class:`ExprRef`)
-        The minimum desired step between legend ticks, in terms of scale domain values. For
-        example, a value of ``1`` indicates that ticks should not be less than 1 unit apart.
-        If ``tickMinStep`` is specified, the ``tickCount`` value will be adjusted, if
-        necessary, to enforce the minimum step value.
-
-        **Default value** : ``undefined``
-    title : anyOf(:class:`Text`, None)
-        A title for the field. If ``null``, the title will be removed.
-
-        **Default value:**  derived from the field's name and transformation function (
-        ``aggregate``, ``bin`` and ``timeUnit`` ). If the field has an aggregate function,
-        the function is displayed as part of the title (e.g., ``"Sum of Profit"`` ). If the
-        field is binned or has a time unit applied, the applied function is shown in
-        parentheses (e.g., ``"Profit (binned)"``, ``"Transaction Date (year-month)"`` ).
-        Otherwise, the title is simply the field name.
-
-        **Notes** :
-
-        1) You can customize the default field title format by providing the `fieldTitle
-        <https://vega.github.io/vega-lite/docs/config.html#top-level-config>`__ property in
-        the `config <https://vega.github.io/vega-lite/docs/config.html>`__ or `fieldTitle
-        function via the compile function's options
-        <https://vega.github.io/vega-lite/usage/compile.html#field-title>`__.
-
-        2) If both field definition's ``title`` and axis, header, or legend ``title`` are
-        defined, axis/header/legend title will be used.
-    titleAlign : anyOf(:class:`Align`, :class:`ExprRef`)
-        Horizontal text alignment for legend titles.
-
-        **Default value:** ``"left"``.
-    titleAnchor : anyOf(:class:`TitleAnchor`, :class:`ExprRef`)
-        Text anchor position for placing legend titles.
-    titleBaseline : anyOf(:class:`TextBaseline`, :class:`ExprRef`)
-        Vertical text baseline for legend titles.  One of ``"alphabetic"`` (default),
-        ``"top"``, ``"middle"``, ``"bottom"``, ``"line-top"``, or ``"line-bottom"``. The
-        ``"line-top"`` and ``"line-bottom"`` values operate similarly to ``"top"`` and
-        ``"bottom"``, but are calculated relative to the *lineHeight* rather than *fontSize*
-        alone.
-
-        **Default value:** ``"top"``.
-    titleColor : anyOf(anyOf(None, :class:`Color`), :class:`ExprRef`)
-        The color of the legend title, can be in hex color code or regular color name.
-    titleFont : anyOf(string, :class:`ExprRef`)
-        The font of the legend title.
-    titleFontSize : anyOf(float, :class:`ExprRef`)
-        The font size of the legend title.
-    titleFontStyle : anyOf(:class:`FontStyle`, :class:`ExprRef`)
-        The font style of the legend title.
-    titleFontWeight : anyOf(:class:`FontWeight`, :class:`ExprRef`)
-        The font weight of the legend title. This can be either a string (e.g ``"bold"``,
-        ``"normal"`` ) or a number ( ``100``, ``200``, ``300``, ..., ``900`` where
-        ``"normal"`` = ``400`` and ``"bold"`` = ``700`` ).
-    titleLimit : anyOf(float, :class:`ExprRef`)
-        Maximum allowed pixel width of legend titles.
-
-        **Default value:** ``180``.
-    titleLineHeight : anyOf(float, :class:`ExprRef`)
-        Line height in pixels for multi-line title text or title text with ``"line-top"`` or
-        ``"line-bottom"`` baseline.
-    titleOpacity : anyOf(float, :class:`ExprRef`)
-        Opacity of the legend title.
-    titleOrient : anyOf(:class:`Orient`, :class:`ExprRef`)
-        Orientation of the legend title.
-    titlePadding : anyOf(float, :class:`ExprRef`)
-        The padding, in pixels, between title and legend.
-
-        **Default value:** ``5``.
-    type : enum('symbol', 'gradient')
-        The type of the legend. Use ``"symbol"`` to create a discrete legend and
-        ``"gradient"`` for a continuous color gradient.
-
-        **Default value:** ``"gradient"`` for non-binned quantitative fields and temporal
-        fields; ``"symbol"`` otherwise.
-    values : anyOf(List(float), List(string), List(boolean), List(:class:`DateTime`), :class:`ExprRef`)
-        Explicitly set the visible legend values.
-    zindex : float
-        A non-negative integer indicating the z-index of the legend. If zindex is 0, legend
-        should be drawn behind all chart elements. To put them in front, use zindex = 1.
-    """
-    _schema = {'$ref': '#/definitions/Legend'}
-
-    def __init__(self, aria=Undefined, clipHeight=Undefined, columnPadding=Undefined, columns=Undefined,
-                 cornerRadius=Undefined, description=Undefined, direction=Undefined,
-                 fillColor=Undefined, format=Undefined, formatType=Undefined, gradientLength=Undefined,
-                 gradientOpacity=Undefined, gradientStrokeColor=Undefined,
-                 gradientStrokeWidth=Undefined, gradientThickness=Undefined, gridAlign=Undefined,
-                 labelAlign=Undefined, labelBaseline=Undefined, labelColor=Undefined,
-                 labelExpr=Undefined, labelFont=Undefined, labelFontSize=Undefined,
-                 labelFontStyle=Undefined, labelFontWeight=Undefined, labelLimit=Undefined,
-                 labelOffset=Undefined, labelOpacity=Undefined, labelOverlap=Undefined,
-                 labelPadding=Undefined, labelSeparation=Undefined, legendX=Undefined,
-                 legendY=Undefined, offset=Undefined, orient=Undefined, padding=Undefined,
-                 rowPadding=Undefined, strokeColor=Undefined, symbolDash=Undefined,
-                 symbolDashOffset=Undefined, symbolFillColor=Undefined, symbolLimit=Undefined,
-                 symbolOffset=Undefined, symbolOpacity=Undefined, symbolSize=Undefined,
-                 symbolStrokeColor=Undefined, symbolStrokeWidth=Undefined, symbolType=Undefined,
-                 tickCount=Undefined, tickMinStep=Undefined, title=Undefined, titleAlign=Undefined,
-                 titleAnchor=Undefined, titleBaseline=Undefined, titleColor=Undefined,
-                 titleFont=Undefined, titleFontSize=Undefined, titleFontStyle=Undefined,
-                 titleFontWeight=Undefined, titleLimit=Undefined, titleLineHeight=Undefined,
-                 titleOpacity=Undefined, titleOrient=Undefined, titlePadding=Undefined, type=Undefined,
-                 values=Undefined, zindex=Undefined, **kwds):
-        super(Legend, self).__init__(aria=aria, clipHeight=clipHeight, columnPadding=columnPadding,
-                                     columns=columns, cornerRadius=cornerRadius,
-                                     description=description, direction=direction, fillColor=fillColor,
-                                     format=format, formatType=formatType,
-                                     gradientLength=gradientLength, gradientOpacity=gradientOpacity,
-                                     gradientStrokeColor=gradientStrokeColor,
-                                     gradientStrokeWidth=gradientStrokeWidth,
-                                     gradientThickness=gradientThickness, gridAlign=gridAlign,
-                                     labelAlign=labelAlign, labelBaseline=labelBaseline,
-                                     labelColor=labelColor, labelExpr=labelExpr, labelFont=labelFont,
-                                     labelFontSize=labelFontSize, labelFontStyle=labelFontStyle,
-                                     labelFontWeight=labelFontWeight, labelLimit=labelLimit,
-                                     labelOffset=labelOffset, labelOpacity=labelOpacity,
-                                     labelOverlap=labelOverlap, labelPadding=labelPadding,
-                                     labelSeparation=labelSeparation, legendX=legendX, legendY=legendY,
-                                     offset=offset, orient=orient, padding=padding,
-                                     rowPadding=rowPadding, strokeColor=strokeColor,
-                                     symbolDash=symbolDash, symbolDashOffset=symbolDashOffset,
-                                     symbolFillColor=symbolFillColor, symbolLimit=symbolLimit,
-                                     symbolOffset=symbolOffset, symbolOpacity=symbolOpacity,
-                                     symbolSize=symbolSize, symbolStrokeColor=symbolStrokeColor,
-                                     symbolStrokeWidth=symbolStrokeWidth, symbolType=symbolType,
-                                     tickCount=tickCount, tickMinStep=tickMinStep, title=title,
-                                     titleAlign=titleAlign, titleAnchor=titleAnchor,
-                                     titleBaseline=titleBaseline, titleColor=titleColor,
-                                     titleFont=titleFont, titleFontSize=titleFontSize,
-                                     titleFontStyle=titleFontStyle, titleFontWeight=titleFontWeight,
-                                     titleLimit=titleLimit, titleLineHeight=titleLineHeight,
-                                     titleOpacity=titleOpacity, titleOrient=titleOrient,
-                                     titlePadding=titlePadding, type=type, values=values, zindex=zindex,
-                                     **kwds)
-
-
-class LegendBinding(VegaLiteSchema):
-    """LegendBinding schema wrapper
-
-    anyOf(string, :class:`LegendStreamBinding`)
-    """
-    _schema = {'$ref': '#/definitions/LegendBinding'}
-
-    def __init__(self, *args, **kwds):
-        super(LegendBinding, self).__init__(*args, **kwds)
-
-
-class LegendConfig(VegaLiteSchema):
-    """LegendConfig schema wrapper
-
-    Mapping(required=[])
-
-    Parameters
-    ----------
-
-    aria : anyOf(boolean, :class:`ExprRef`)
-        A boolean flag indicating if `ARIA attributes
-        <https://developer.mozilla.org/en-US/docs/Web/Accessibility/ARIA>`__ should be
-        included (SVG output only). If ``false``, the "aria-hidden" attribute will be set on
-        the output SVG group, removing the legend from the ARIA accessibility tree.
-
-        **Default value:** ``true``
-    clipHeight : anyOf(float, :class:`ExprRef`)
-        The height in pixels to clip symbol legend entries and limit their size.
-    columnPadding : anyOf(float, :class:`ExprRef`)
-        The horizontal padding in pixels between symbol legend entries.
-
-        **Default value:** ``10``.
-    columns : anyOf(float, :class:`ExprRef`)
-        The number of columns in which to arrange symbol legend entries. A value of ``0`` or
-        lower indicates a single row with one column per entry.
-    cornerRadius : anyOf(float, :class:`ExprRef`)
-        Corner radius for the full legend.
-    description : anyOf(string, :class:`ExprRef`)
-        A text description of this legend for `ARIA accessibility
-        <https://developer.mozilla.org/en-US/docs/Web/Accessibility/ARIA>`__ (SVG output
-        only). If the ``aria`` property is true, for SVG output the `"aria-label" attribute
-        <https://developer.mozilla.org/en-US/docs/Web/Accessibility/ARIA/ARIA_Techniques/Using_the_aria-label_attribute>`__
-        will be set to this description. If the description is unspecified it will be
-        automatically generated.
-    direction : :class:`Orientation`
-        The direction of the legend, one of ``"vertical"`` or ``"horizontal"``.
-
-        **Default value:**
-
-
-        * For top-/bottom- ``orient`` ed legends, ``"horizontal"``
-        * For left-/right- ``orient`` ed legends, ``"vertical"``
-        * For top/bottom-left/right- ``orient`` ed legends, ``"horizontal"`` for gradient
-          legends and ``"vertical"`` for symbol legends.
-    disable : boolean
-        Disable legend by default
-    fillColor : anyOf(anyOf(None, :class:`Color`), :class:`ExprRef`)
-        Background fill color for the full legend.
-    gradientDirection : anyOf(:class:`Orientation`, :class:`ExprRef`)
-        The default direction ( ``"horizontal"`` or ``"vertical"`` ) for gradient legends.
-
-        **Default value:** ``"vertical"``.
-    gradientHorizontalMaxLength : float
-        Max legend length for a horizontal gradient when ``config.legend.gradientLength`` is
-        undefined.
-
-        **Default value:** ``200``
-    gradientHorizontalMinLength : float
-        Min legend length for a horizontal gradient when ``config.legend.gradientLength`` is
-        undefined.
-
-        **Default value:** ``100``
-    gradientLabelLimit : anyOf(float, :class:`ExprRef`)
-        The maximum allowed length in pixels of color ramp gradient labels.
-    gradientLabelOffset : anyOf(float, :class:`ExprRef`)
-        Vertical offset in pixels for color ramp gradient labels.
-
-        **Default value:** ``2``.
-    gradientLength : anyOf(float, :class:`ExprRef`)
-        The length in pixels of the primary axis of a color gradient. This value corresponds
-        to the height of a vertical gradient or the width of a horizontal gradient.
-
-        **Default value:** ``200``.
-    gradientOpacity : anyOf(float, :class:`ExprRef`)
-        Opacity of the color gradient.
-    gradientStrokeColor : anyOf(anyOf(None, :class:`Color`), :class:`ExprRef`)
-        The color of the gradient stroke, can be in hex color code or regular color name.
-
-        **Default value:** ``"lightGray"``.
-    gradientStrokeWidth : anyOf(float, :class:`ExprRef`)
-        The width of the gradient stroke, in pixels.
-
-        **Default value:** ``0``.
-    gradientThickness : anyOf(float, :class:`ExprRef`)
-        The thickness in pixels of the color gradient. This value corresponds to the width
-        of a vertical gradient or the height of a horizontal gradient.
-
-        **Default value:** ``16``.
-    gradientVerticalMaxLength : float
-        Max legend length for a vertical gradient when ``config.legend.gradientLength`` is
-        undefined.
-
-        **Default value:** ``200``
-    gradientVerticalMinLength : float
-        Min legend length for a vertical gradient when ``config.legend.gradientLength`` is
-        undefined.
-
-        **Default value:** ``100``
-    gridAlign : anyOf(:class:`LayoutAlign`, :class:`ExprRef`)
-        The alignment to apply to symbol legends rows and columns. The supported string
-        values are ``"all"``, ``"each"`` (the default), and ``none``. For more information,
-        see the `grid layout documentation <https://vega.github.io/vega/docs/layout>`__.
-
-        **Default value:** ``"each"``.
-    labelAlign : anyOf(:class:`Align`, :class:`ExprRef`)
-        The alignment of the legend label, can be left, center, or right.
-    labelBaseline : anyOf(:class:`TextBaseline`, :class:`ExprRef`)
-        The position of the baseline of legend label, can be ``"top"``, ``"middle"``,
-        ``"bottom"``, or ``"alphabetic"``.
-
-        **Default value:** ``"middle"``.
-    labelColor : anyOf(anyOf(None, :class:`Color`), :class:`ExprRef`)
-        The color of the legend label, can be in hex color code or regular color name.
-    labelFont : anyOf(string, :class:`ExprRef`)
-        The font of the legend label.
-    labelFontSize : anyOf(float, :class:`ExprRef`)
-        The font size of legend label.
-
-        **Default value:** ``10``.
-    labelFontStyle : anyOf(:class:`FontStyle`, :class:`ExprRef`)
-        The font style of legend label.
-    labelFontWeight : anyOf(:class:`FontWeight`, :class:`ExprRef`)
-        The font weight of legend label.
-    labelLimit : anyOf(float, :class:`ExprRef`)
-        Maximum allowed pixel width of legend tick labels.
-
-        **Default value:** ``160``.
-    labelOffset : anyOf(float, :class:`ExprRef`)
-        The offset of the legend label.
-
-        **Default value:** ``4``.
-    labelOpacity : anyOf(float, :class:`ExprRef`)
-        Opacity of labels.
-    labelOverlap : anyOf(:class:`LabelOverlap`, :class:`ExprRef`)
-        The strategy to use for resolving overlap of labels in gradient legends. If
-        ``false``, no overlap reduction is attempted. If set to ``true`` or ``"parity"``, a
-        strategy of removing every other label is used. If set to ``"greedy"``, a linear
-        scan of the labels is performed, removing any label that overlaps with the last
-        visible label (this often works better for log-scaled axes).
-
-        **Default value:** ``"greedy"`` for ``log scales otherwise`` true`.
-    labelPadding : anyOf(float, :class:`ExprRef`)
-        Padding in pixels between the legend and legend labels.
-    labelSeparation : anyOf(float, :class:`ExprRef`)
-        The minimum separation that must be between label bounding boxes for them to be
-        considered non-overlapping (default ``0`` ). This property is ignored if
-        *labelOverlap* resolution is not enabled.
-    layout : :class:`ExprRef`
-
-    legendX : anyOf(float, :class:`ExprRef`)
-        Custom x-position for legend with orient "none".
-    legendY : anyOf(float, :class:`ExprRef`)
-        Custom y-position for legend with orient "none".
-    offset : anyOf(float, :class:`ExprRef`)
-        The offset in pixels by which to displace the legend from the data rectangle and
-        axes.
-
-        **Default value:** ``18``.
-    orient : :class:`LegendOrient`
-        The orientation of the legend, which determines how the legend is positioned within
-        the scene. One of ``"left"``, ``"right"``, ``"top"``, ``"bottom"``, ``"top-left"``,
-        ``"top-right"``, ``"bottom-left"``, ``"bottom-right"``, ``"none"``.
-
-        **Default value:** ``"right"``
-    padding : anyOf(float, :class:`ExprRef`)
-        The padding between the border and content of the legend group.
-
-        **Default value:** ``0``.
-    rowPadding : anyOf(float, :class:`ExprRef`)
-        The vertical padding in pixels between symbol legend entries.
-
-        **Default value:** ``2``.
-    strokeColor : anyOf(anyOf(None, :class:`Color`), :class:`ExprRef`)
-        Border stroke color for the full legend.
-    strokeDash : anyOf(List(float), :class:`ExprRef`)
-        Border stroke dash pattern for the full legend.
-    strokeWidth : anyOf(float, :class:`ExprRef`)
-        Border stroke width for the full legend.
-    symbolBaseFillColor : anyOf(anyOf(None, :class:`Color`), :class:`ExprRef`)
-        Default fill color for legend symbols. Only applied if there is no ``"fill"`` scale
-        color encoding for the legend.
-
-        **Default value:** ``"transparent"``.
-    symbolBaseStrokeColor : anyOf(anyOf(None, :class:`Color`), :class:`ExprRef`)
-        Default stroke color for legend symbols. Only applied if there is no ``"fill"``
-        scale color encoding for the legend.
-
-        **Default value:** ``"gray"``.
-    symbolDash : anyOf(List(float), :class:`ExprRef`)
-        An array of alternating [stroke, space] lengths for dashed symbol strokes.
-    symbolDashOffset : anyOf(float, :class:`ExprRef`)
-        The pixel offset at which to start drawing with the symbol stroke dash array.
-    symbolDirection : anyOf(:class:`Orientation`, :class:`ExprRef`)
-        The default direction ( ``"horizontal"`` or ``"vertical"`` ) for symbol legends.
-
-        **Default value:** ``"vertical"``.
-    symbolFillColor : anyOf(anyOf(None, :class:`Color`), :class:`ExprRef`)
-        The color of the legend symbol,
-    symbolLimit : anyOf(float, :class:`ExprRef`)
-        The maximum number of allowed entries for a symbol legend. Additional entries will
-        be dropped.
-    symbolOffset : anyOf(float, :class:`ExprRef`)
-        Horizontal pixel offset for legend symbols.
-
-        **Default value:** ``0``.
-    symbolOpacity : anyOf(float, :class:`ExprRef`)
-        Opacity of the legend symbols.
-    symbolSize : anyOf(float, :class:`ExprRef`)
-        The size of the legend symbol, in pixels.
-
-        **Default value:** ``100``.
-    symbolStrokeColor : anyOf(anyOf(None, :class:`Color`), :class:`ExprRef`)
-        Stroke color for legend symbols.
-    symbolStrokeWidth : anyOf(float, :class:`ExprRef`)
-        The width of the symbol's stroke.
-
-        **Default value:** ``1.5``.
-    symbolType : anyOf(:class:`SymbolShape`, :class:`ExprRef`)
-        The symbol shape. One of the plotting shapes ``circle`` (default), ``square``,
-        ``cross``, ``diamond``, ``triangle-up``, ``triangle-down``, ``triangle-right``, or
-        ``triangle-left``, the line symbol ``stroke``, or one of the centered directional
-        shapes ``arrow``, ``wedge``, or ``triangle``. Alternatively, a custom `SVG path
-        string <https://developer.mozilla.org/en-US/docs/Web/SVG/Tutorial/Paths>`__ can be
-        provided. For correct sizing, custom shape paths should be defined within a square
-        bounding box with coordinates ranging from -1 to 1 along both the x and y
-        dimensions.
-
-        **Default value:** ``"circle"``.
-    tickCount : anyOf(:class:`TickCount`, :class:`ExprRef`)
-        The desired number of tick values for quantitative legends.
-    title : None
-        Set to null to disable title for the axis, legend, or header.
-    titleAlign : anyOf(:class:`Align`, :class:`ExprRef`)
-        Horizontal text alignment for legend titles.
-
-        **Default value:** ``"left"``.
-    titleAnchor : anyOf(:class:`TitleAnchor`, :class:`ExprRef`)
-        Text anchor position for placing legend titles.
-    titleBaseline : anyOf(:class:`TextBaseline`, :class:`ExprRef`)
-        Vertical text baseline for legend titles.  One of ``"alphabetic"`` (default),
-        ``"top"``, ``"middle"``, ``"bottom"``, ``"line-top"``, or ``"line-bottom"``. The
-        ``"line-top"`` and ``"line-bottom"`` values operate similarly to ``"top"`` and
-        ``"bottom"``, but are calculated relative to the *lineHeight* rather than *fontSize*
-        alone.
-
-        **Default value:** ``"top"``.
-    titleColor : anyOf(anyOf(None, :class:`Color`), :class:`ExprRef`)
-        The color of the legend title, can be in hex color code or regular color name.
-    titleFont : anyOf(string, :class:`ExprRef`)
-        The font of the legend title.
-    titleFontSize : anyOf(float, :class:`ExprRef`)
-        The font size of the legend title.
-    titleFontStyle : anyOf(:class:`FontStyle`, :class:`ExprRef`)
-        The font style of the legend title.
-    titleFontWeight : anyOf(:class:`FontWeight`, :class:`ExprRef`)
-        The font weight of the legend title. This can be either a string (e.g ``"bold"``,
-        ``"normal"`` ) or a number ( ``100``, ``200``, ``300``, ..., ``900`` where
-        ``"normal"`` = ``400`` and ``"bold"`` = ``700`` ).
-    titleLimit : anyOf(float, :class:`ExprRef`)
-        Maximum allowed pixel width of legend titles.
-
-        **Default value:** ``180``.
-    titleLineHeight : anyOf(float, :class:`ExprRef`)
-        Line height in pixels for multi-line title text or title text with ``"line-top"`` or
-        ``"line-bottom"`` baseline.
-    titleOpacity : anyOf(float, :class:`ExprRef`)
-        Opacity of the legend title.
-    titleOrient : anyOf(:class:`Orient`, :class:`ExprRef`)
-        Orientation of the legend title.
-    titlePadding : anyOf(float, :class:`ExprRef`)
-        The padding, in pixels, between title and legend.
-
-        **Default value:** ``5``.
-    unselectedOpacity : float
-        The opacity of unselected legend entries.
-
-        **Default value:** 0.35.
-    zindex : anyOf(float, :class:`ExprRef`)
-        The integer z-index indicating the layering of the legend group relative to other
-        axis, mark, and legend groups.
-    """
-    _schema = {'$ref': '#/definitions/LegendConfig'}
-
-    def __init__(self, aria=Undefined, clipHeight=Undefined, columnPadding=Undefined, columns=Undefined,
-                 cornerRadius=Undefined, description=Undefined, direction=Undefined, disable=Undefined,
-                 fillColor=Undefined, gradientDirection=Undefined,
-                 gradientHorizontalMaxLength=Undefined, gradientHorizontalMinLength=Undefined,
-                 gradientLabelLimit=Undefined, gradientLabelOffset=Undefined, gradientLength=Undefined,
-                 gradientOpacity=Undefined, gradientStrokeColor=Undefined,
-                 gradientStrokeWidth=Undefined, gradientThickness=Undefined,
-                 gradientVerticalMaxLength=Undefined, gradientVerticalMinLength=Undefined,
-                 gridAlign=Undefined, labelAlign=Undefined, labelBaseline=Undefined,
-                 labelColor=Undefined, labelFont=Undefined, labelFontSize=Undefined,
-                 labelFontStyle=Undefined, labelFontWeight=Undefined, labelLimit=Undefined,
-                 labelOffset=Undefined, labelOpacity=Undefined, labelOverlap=Undefined,
-                 labelPadding=Undefined, labelSeparation=Undefined, layout=Undefined, legendX=Undefined,
-                 legendY=Undefined, offset=Undefined, orient=Undefined, padding=Undefined,
-                 rowPadding=Undefined, strokeColor=Undefined, strokeDash=Undefined,
-                 strokeWidth=Undefined, symbolBaseFillColor=Undefined, symbolBaseStrokeColor=Undefined,
-                 symbolDash=Undefined, symbolDashOffset=Undefined, symbolDirection=Undefined,
-                 symbolFillColor=Undefined, symbolLimit=Undefined, symbolOffset=Undefined,
-                 symbolOpacity=Undefined, symbolSize=Undefined, symbolStrokeColor=Undefined,
-                 symbolStrokeWidth=Undefined, symbolType=Undefined, tickCount=Undefined,
-                 title=Undefined, titleAlign=Undefined, titleAnchor=Undefined, titleBaseline=Undefined,
-                 titleColor=Undefined, titleFont=Undefined, titleFontSize=Undefined,
-                 titleFontStyle=Undefined, titleFontWeight=Undefined, titleLimit=Undefined,
-                 titleLineHeight=Undefined, titleOpacity=Undefined, titleOrient=Undefined,
-                 titlePadding=Undefined, unselectedOpacity=Undefined, zindex=Undefined, **kwds):
-        super(LegendConfig, self).__init__(aria=aria, clipHeight=clipHeight,
-                                           columnPadding=columnPadding, columns=columns,
-                                           cornerRadius=cornerRadius, description=description,
-                                           direction=direction, disable=disable, fillColor=fillColor,
-                                           gradientDirection=gradientDirection,
-                                           gradientHorizontalMaxLength=gradientHorizontalMaxLength,
-                                           gradientHorizontalMinLength=gradientHorizontalMinLength,
-                                           gradientLabelLimit=gradientLabelLimit,
-                                           gradientLabelOffset=gradientLabelOffset,
-                                           gradientLength=gradientLength,
-                                           gradientOpacity=gradientOpacity,
-                                           gradientStrokeColor=gradientStrokeColor,
-                                           gradientStrokeWidth=gradientStrokeWidth,
-                                           gradientThickness=gradientThickness,
-                                           gradientVerticalMaxLength=gradientVerticalMaxLength,
-                                           gradientVerticalMinLength=gradientVerticalMinLength,
-                                           gridAlign=gridAlign, labelAlign=labelAlign,
-                                           labelBaseline=labelBaseline, labelColor=labelColor,
-                                           labelFont=labelFont, labelFontSize=labelFontSize,
-                                           labelFontStyle=labelFontStyle,
-                                           labelFontWeight=labelFontWeight, labelLimit=labelLimit,
-                                           labelOffset=labelOffset, labelOpacity=labelOpacity,
-                                           labelOverlap=labelOverlap, labelPadding=labelPadding,
-                                           labelSeparation=labelSeparation, layout=layout,
-                                           legendX=legendX, legendY=legendY, offset=offset,
-                                           orient=orient, padding=padding, rowPadding=rowPadding,
-                                           strokeColor=strokeColor, strokeDash=strokeDash,
-                                           strokeWidth=strokeWidth,
-                                           symbolBaseFillColor=symbolBaseFillColor,
-                                           symbolBaseStrokeColor=symbolBaseStrokeColor,
-                                           symbolDash=symbolDash, symbolDashOffset=symbolDashOffset,
-                                           symbolDirection=symbolDirection,
-                                           symbolFillColor=symbolFillColor, symbolLimit=symbolLimit,
-                                           symbolOffset=symbolOffset, symbolOpacity=symbolOpacity,
-                                           symbolSize=symbolSize, symbolStrokeColor=symbolStrokeColor,
-                                           symbolStrokeWidth=symbolStrokeWidth, symbolType=symbolType,
-                                           tickCount=tickCount, title=title, titleAlign=titleAlign,
-                                           titleAnchor=titleAnchor, titleBaseline=titleBaseline,
-                                           titleColor=titleColor, titleFont=titleFont,
-                                           titleFontSize=titleFontSize, titleFontStyle=titleFontStyle,
-                                           titleFontWeight=titleFontWeight, titleLimit=titleLimit,
-                                           titleLineHeight=titleLineHeight, titleOpacity=titleOpacity,
-                                           titleOrient=titleOrient, titlePadding=titlePadding,
-                                           unselectedOpacity=unselectedOpacity, zindex=zindex, **kwds)
-
-
-class LegendOrient(VegaLiteSchema):
-    """LegendOrient schema wrapper
-
-    enum('none', 'left', 'right', 'top', 'bottom', 'top-left', 'top-right', 'bottom-left',
-    'bottom-right')
-    """
-    _schema = {'$ref': '#/definitions/LegendOrient'}
-
-    def __init__(self, *args):
-        super(LegendOrient, self).__init__(*args)
-
-
-class LegendResolveMap(VegaLiteSchema):
-    """LegendResolveMap schema wrapper
-
-    Mapping(required=[])
-
-    Parameters
-    ----------
-
-    angle : :class:`ResolveMode`
-
-    color : :class:`ResolveMode`
-
-    fill : :class:`ResolveMode`
-
-    fillOpacity : :class:`ResolveMode`
-
-    opacity : :class:`ResolveMode`
-
-    shape : :class:`ResolveMode`
-
-    size : :class:`ResolveMode`
-
-    stroke : :class:`ResolveMode`
-
-    strokeDash : :class:`ResolveMode`
-
-    strokeOpacity : :class:`ResolveMode`
-
-    strokeWidth : :class:`ResolveMode`
-
-    """
-    _schema = {'$ref': '#/definitions/LegendResolveMap'}
-
-    def __init__(self, angle=Undefined, color=Undefined, fill=Undefined, fillOpacity=Undefined,
-                 opacity=Undefined, shape=Undefined, size=Undefined, stroke=Undefined,
-                 strokeDash=Undefined, strokeOpacity=Undefined, strokeWidth=Undefined, **kwds):
-        super(LegendResolveMap, self).__init__(angle=angle, color=color, fill=fill,
-                                               fillOpacity=fillOpacity, opacity=opacity, shape=shape,
-                                               size=size, stroke=stroke, strokeDash=strokeDash,
-                                               strokeOpacity=strokeOpacity, strokeWidth=strokeWidth,
-                                               **kwds)
-
-
-class LegendStreamBinding(LegendBinding):
-    """LegendStreamBinding schema wrapper
-
-    Mapping(required=[legend])
-
-    Parameters
-    ----------
-
-    legend : anyOf(string, :class:`Stream`)
-
-    """
-    _schema = {'$ref': '#/definitions/LegendStreamBinding'}
-
-    def __init__(self, legend=Undefined, **kwds):
-        super(LegendStreamBinding, self).__init__(legend=legend, **kwds)
-
-
-class LineConfig(AnyMarkConfig):
-    """LineConfig schema wrapper
-
-    Mapping(required=[])
-
-    Parameters
-    ----------
-
-    align : anyOf(:class:`Align`, :class:`ExprRef`)
-        The horizontal alignment of the text or ranged marks (area, bar, image, rect, rule).
-        One of ``"left"``, ``"right"``, ``"center"``.
-
-        **Note:** Expression reference is *not* supported for range marks.
-    angle : anyOf(float, :class:`ExprRef`)
-        The rotation angle of the text, in degrees.
-    aria : anyOf(boolean, :class:`ExprRef`)
-        A boolean flag indicating if `ARIA attributes
-        <https://developer.mozilla.org/en-US/docs/Web/Accessibility/ARIA>`__ should be
-        included (SVG output only). If ``false``, the "aria-hidden" attribute will be set on
-        the output SVG element, removing the mark item from the ARIA accessibility tree.
-    ariaRole : anyOf(string, :class:`ExprRef`)
-        Sets the type of user interface element of the mark item for `ARIA accessibility
-        <https://developer.mozilla.org/en-US/docs/Web/Accessibility/ARIA>`__ (SVG output
-        only). If specified, this property determines the "role" attribute. Warning: this
-        property is experimental and may be changed in the future.
-    ariaRoleDescription : anyOf(string, :class:`ExprRef`)
-        A human-readable, author-localized description for the role of the mark item for
-        `ARIA accessibility
-        <https://developer.mozilla.org/en-US/docs/Web/Accessibility/ARIA>`__ (SVG output
-        only). If specified, this property determines the "aria-roledescription" attribute.
-        Warning: this property is experimental and may be changed in the future.
-    aspect : anyOf(boolean, :class:`ExprRef`)
-        Whether to keep aspect ratio of image marks.
-    baseline : anyOf(:class:`TextBaseline`, :class:`ExprRef`)
-        For text marks, the vertical text baseline. One of ``"alphabetic"`` (default),
-        ``"top"``, ``"middle"``, ``"bottom"``, ``"line-top"``, ``"line-bottom"``, or an
-        expression reference that provides one of the valid values. The ``"line-top"`` and
-        ``"line-bottom"`` values operate similarly to ``"top"`` and ``"bottom"``, but are
-        calculated relative to the ``lineHeight`` rather than ``fontSize`` alone.
-
-        For range marks, the vertical alignment of the marks. One of ``"top"``,
-        ``"middle"``, ``"bottom"``.
-
-        **Note:** Expression reference is *not* supported for range marks.
-    blend : anyOf(:class:`Blend`, :class:`ExprRef`)
-        The color blend mode for drawing an item on its current background. Any valid `CSS
-        mix-blend-mode <https://developer.mozilla.org/en-US/docs/Web/CSS/mix-blend-mode>`__
-        value can be used.
-
-        __Default value:__ ``"source-over"``
-    color : anyOf(:class:`Color`, :class:`Gradient`, :class:`ExprRef`)
-        Default color.
-
-        **Default value:** :raw-html:`<span style="color: #4682b4;">&#9632;</span>`
-        ``"#4682b4"``
-
-        **Note:**
-
-
-        * This property cannot be used in a `style config
-          <https://vega.github.io/vega-lite/docs/mark.html#style-config>`__.
-        * The ``fill`` and ``stroke`` properties have higher precedence than ``color`` and
-          will override ``color``.
-    cornerRadius : anyOf(float, :class:`ExprRef`)
-        The radius in pixels of rounded rectangles or arcs' corners.
-
-        **Default value:** ``0``
-    cornerRadiusBottomLeft : anyOf(float, :class:`ExprRef`)
-        The radius in pixels of rounded rectangles' bottom left corner.
-
-        **Default value:** ``0``
-    cornerRadiusBottomRight : anyOf(float, :class:`ExprRef`)
-        The radius in pixels of rounded rectangles' bottom right corner.
-
-        **Default value:** ``0``
-    cornerRadiusTopLeft : anyOf(float, :class:`ExprRef`)
-        The radius in pixels of rounded rectangles' top right corner.
-
-        **Default value:** ``0``
-    cornerRadiusTopRight : anyOf(float, :class:`ExprRef`)
-        The radius in pixels of rounded rectangles' top left corner.
-
-        **Default value:** ``0``
-    cursor : anyOf(:class:`Cursor`, :class:`ExprRef`)
-        The mouse cursor used over the mark. Any valid `CSS cursor type
-        <https://developer.mozilla.org/en-US/docs/Web/CSS/cursor#Values>`__ can be used.
-    description : anyOf(string, :class:`ExprRef`)
-        A text description of the mark item for `ARIA accessibility
-        <https://developer.mozilla.org/en-US/docs/Web/Accessibility/ARIA>`__ (SVG output
-        only). If specified, this property determines the `"aria-label" attribute
-        <https://developer.mozilla.org/en-US/docs/Web/Accessibility/ARIA/ARIA_Techniques/Using_the_aria-label_attribute>`__.
-    dir : anyOf(:class:`TextDirection`, :class:`ExprRef`)
-        The direction of the text. One of ``"ltr"`` (left-to-right) or ``"rtl"``
-        (right-to-left). This property determines on which side is truncated in response to
-        the limit parameter.
-
-        **Default value:** ``"ltr"``
-    dx : anyOf(float, :class:`ExprRef`)
-        The horizontal offset, in pixels, between the text label and its anchor point. The
-        offset is applied after rotation by the *angle* property.
-    dy : anyOf(float, :class:`ExprRef`)
-        The vertical offset, in pixels, between the text label and its anchor point. The
-        offset is applied after rotation by the *angle* property.
-    ellipsis : anyOf(string, :class:`ExprRef`)
-        The ellipsis string for text truncated in response to the limit parameter.
-
-        **Default value:** ``"…"``
-    endAngle : anyOf(float, :class:`ExprRef`)
-        The end angle in radians for arc marks. A value of ``0`` indicates up (north),
-        increasing values proceed clockwise.
-    fill : anyOf(:class:`Color`, :class:`Gradient`, None, :class:`ExprRef`)
-        Default fill color. This property has higher precedence than ``config.color``. Set
-        to ``null`` to remove fill.
-
-        **Default value:** (None)
-    fillOpacity : anyOf(float, :class:`ExprRef`)
-        The fill opacity (value between [0,1]).
-
-        **Default value:** ``1``
-    filled : boolean
-        Whether the mark's color should be used as fill color instead of stroke color.
-
-        **Default value:** ``false`` for all ``point``, ``line``, and ``rule`` marks as well
-        as ``geoshape`` marks for `graticule
-        <https://vega.github.io/vega-lite/docs/data.html#graticule>`__ data sources;
-        otherwise, ``true``.
-
-        **Note:** This property cannot be used in a `style config
-        <https://vega.github.io/vega-lite/docs/mark.html#style-config>`__.
-    font : anyOf(string, :class:`ExprRef`)
-        The typeface to set the text in (e.g., ``"Helvetica Neue"`` ).
-    fontSize : anyOf(float, :class:`ExprRef`)
-        The font size, in pixels.
-
-        **Default value:** ``11``
-    fontStyle : anyOf(:class:`FontStyle`, :class:`ExprRef`)
-        The font style (e.g., ``"italic"`` ).
-    fontWeight : anyOf(:class:`FontWeight`, :class:`ExprRef`)
-        The font weight. This can be either a string (e.g ``"bold"``, ``"normal"`` ) or a
-        number ( ``100``, ``200``, ``300``, ..., ``900`` where ``"normal"`` = ``400`` and
-        ``"bold"`` = ``700`` ).
-    height : anyOf(float, :class:`ExprRef`)
-        Height of the marks.
-    href : anyOf(:class:`URI`, :class:`ExprRef`)
-        A URL to load upon mouse click. If defined, the mark acts as a hyperlink.
-    innerRadius : anyOf(float, :class:`ExprRef`)
-        The inner radius in pixels of arc marks. ``innerRadius`` is an alias for
-        ``radius2``.
-
-        **Default value:** ``0``
-    interpolate : anyOf(:class:`Interpolate`, :class:`ExprRef`)
-        The line interpolation method to use for line and area marks. One of the following:
-
-
-        * ``"linear"`` : piecewise linear segments, as in a polyline.
-        * ``"linear-closed"`` : close the linear segments to form a polygon.
-        * ``"step"`` : alternate between horizontal and vertical segments, as in a step
-          function.
-        * ``"step-before"`` : alternate between vertical and horizontal segments, as in a
-          step function.
-        * ``"step-after"`` : alternate between horizontal and vertical segments, as in a
-          step function.
-        * ``"basis"`` : a B-spline, with control point duplication on the ends.
-        * ``"basis-open"`` : an open B-spline; may not intersect the start or end.
-        * ``"basis-closed"`` : a closed B-spline, as in a loop.
-        * ``"cardinal"`` : a Cardinal spline, with control point duplication on the ends.
-        * ``"cardinal-open"`` : an open Cardinal spline; may not intersect the start or end,
-          but will intersect other control points.
-        * ``"cardinal-closed"`` : a closed Cardinal spline, as in a loop.
-        * ``"bundle"`` : equivalent to basis, except the tension parameter is used to
-          straighten the spline.
-        * ``"monotone"`` : cubic interpolation that preserves monotonicity in y.
-    invalid : enum('filter', None)
-        Defines how Vega-Lite should handle marks for invalid values ( ``null`` and ``NaN``
-        ).
-
-
-        * If set to ``"filter"`` (default), all data items with null values will be skipped
-          (for line, trail, and area marks) or filtered (for other marks).
-        * If ``null``, all data items are included. In this case, invalid values will be
-          interpreted as zeroes.
-    limit : anyOf(float, :class:`ExprRef`)
-        The maximum length of the text mark in pixels. The text value will be automatically
-        truncated if the rendered size exceeds the limit.
-
-        **Default value:** ``0`` -- indicating no limit
-    lineBreak : anyOf(string, :class:`ExprRef`)
-        A delimiter, such as a newline character, upon which to break text strings into
-        multiple lines. This property is ignored if the text is array-valued.
-    lineHeight : anyOf(float, :class:`ExprRef`)
-        The line height in pixels (the spacing between subsequent lines of text) for
-        multi-line text marks.
-    opacity : anyOf(float, :class:`ExprRef`)
-        The overall opacity (value between [0,1]).
-
-        **Default value:** ``0.7`` for non-aggregate plots with ``point``, ``tick``,
-        ``circle``, or ``square`` marks or layered ``bar`` charts and ``1`` otherwise.
-    order : anyOf(None, boolean)
-        For line and trail marks, this ``order`` property can be set to ``null`` or
-        ``false`` to make the lines use the original order in the data sources.
-    orient : :class:`Orientation`
-        The orientation of a non-stacked bar, tick, area, and line charts. The value is
-        either horizontal (default) or vertical.
-
-
-        * For bar, rule and tick, this determines whether the size of the bar and tick
-          should be applied to x or y dimension.
-        * For area, this property determines the orient property of the Vega output.
-        * For line and trail marks, this property determines the sort order of the points in
-          the line if ``config.sortLineBy`` is not specified. For stacked charts, this is
-          always determined by the orientation of the stack; therefore explicitly specified
-          value will be ignored.
-    outerRadius : anyOf(float, :class:`ExprRef`)
-        The outer radius in pixels of arc marks. ``outerRadius`` is an alias for ``radius``.
-
-        **Default value:** ``0``
-    padAngle : anyOf(float, :class:`ExprRef`)
-        The angular padding applied to sides of the arc, in radians.
-    point : anyOf(boolean, :class:`OverlayMarkDef`, string)
-        A flag for overlaying points on top of line or area marks, or an object defining the
-        properties of the overlayed points.
-
-
-        If this property is ``"transparent"``, transparent points will be used (for
-        enhancing tooltips and selections).
-
-        If this property is an empty object ( ``{}`` ) or ``true``, filled points with
-        default properties will be used.
-
-        If this property is ``false``, no points would be automatically added to line or
-        area marks.
-
-        **Default value:** ``false``.
-    radius : anyOf(float, :class:`ExprRef`)
-        For arc mark, the primary (outer) radius in pixels.
-
-        For text marks, polar coordinate radial offset, in pixels, of the text from the
-        origin determined by the ``x`` and ``y`` properties.
-
-        **Default value:** ``min(plot_width, plot_height)/2``
-    radius2 : anyOf(float, :class:`ExprRef`)
-        The secondary (inner) radius in pixels of arc marks.
-
-        **Default value:** ``0``
-    shape : anyOf(anyOf(:class:`SymbolShape`, string), :class:`ExprRef`)
-        Shape of the point marks. Supported values include:
-
-
-        * plotting shapes: ``"circle"``, ``"square"``, ``"cross"``, ``"diamond"``,
-          ``"triangle-up"``, ``"triangle-down"``, ``"triangle-right"``, or
-          ``"triangle-left"``.
-        * the line symbol ``"stroke"``
-        * centered directional shapes ``"arrow"``, ``"wedge"``, or ``"triangle"``
-        * a custom `SVG path string
-          <https://developer.mozilla.org/en-US/docs/Web/SVG/Tutorial/Paths>`__ (For correct
-          sizing, custom shape paths should be defined within a square bounding box with
-          coordinates ranging from -1 to 1 along both the x and y dimensions.)
-
-        **Default value:** ``"circle"``
-    size : anyOf(float, :class:`ExprRef`)
-        Default size for marks.
-
-
-        * For ``point`` / ``circle`` / ``square``, this represents the pixel area of the
-          marks. Note that this value sets the area of the symbol; the side lengths will
-          increase with the square root of this value.
-        * For ``bar``, this represents the band size of the bar, in pixels.
-        * For ``text``, this represents the font size, in pixels.
-
-        **Default value:**
-
-
-        * ``30`` for point, circle, square marks; width/height's ``step``
-        * ``2`` for bar marks with discrete dimensions;
-        * ``5`` for bar marks with continuous dimensions;
-        * ``11`` for text marks.
-    smooth : anyOf(boolean, :class:`ExprRef`)
-        A boolean flag (default true) indicating if the image should be smoothed when
-        resized. If false, individual pixels should be scaled directly rather than
-        interpolated with smoothing. For SVG rendering, this option may not work in some
-        browsers due to lack of standardization.
-    startAngle : anyOf(float, :class:`ExprRef`)
-        The start angle in radians for arc marks. A value of ``0`` indicates up (north),
-        increasing values proceed clockwise.
-    stroke : anyOf(:class:`Color`, :class:`Gradient`, None, :class:`ExprRef`)
-        Default stroke color. This property has higher precedence than ``config.color``. Set
-        to ``null`` to remove stroke.
-
-        **Default value:** (None)
-    strokeCap : anyOf(:class:`StrokeCap`, :class:`ExprRef`)
-        The stroke cap for line ending style. One of ``"butt"``, ``"round"``, or
-        ``"square"``.
-
-        **Default value:** ``"butt"``
-    strokeDash : anyOf(List(float), :class:`ExprRef`)
-        An array of alternating stroke, space lengths for creating dashed or dotted lines.
-    strokeDashOffset : anyOf(float, :class:`ExprRef`)
-        The offset (in pixels) into which to begin drawing with the stroke dash array.
-    strokeJoin : anyOf(:class:`StrokeJoin`, :class:`ExprRef`)
-        The stroke line join method. One of ``"miter"``, ``"round"`` or ``"bevel"``.
-
-        **Default value:** ``"miter"``
-    strokeMiterLimit : anyOf(float, :class:`ExprRef`)
-        The miter limit at which to bevel a line join.
-    strokeOffset : anyOf(float, :class:`ExprRef`)
-        The offset in pixels at which to draw the group stroke and fill. If unspecified, the
-        default behavior is to dynamically offset stroked groups such that 1 pixel stroke
-        widths align with the pixel grid.
-    strokeOpacity : anyOf(float, :class:`ExprRef`)
-        The stroke opacity (value between [0,1]).
-
-        **Default value:** ``1``
-    strokeWidth : anyOf(float, :class:`ExprRef`)
-        The stroke width, in pixels.
-    tension : anyOf(float, :class:`ExprRef`)
-        Depending on the interpolation type, sets the tension parameter (for line and area
-        marks).
-    text : anyOf(:class:`Text`, :class:`ExprRef`)
-        Placeholder text if the ``text`` channel is not specified
-    theta : anyOf(float, :class:`ExprRef`)
-        For arc marks, the arc length in radians if theta2 is not specified, otherwise the
-        start arc angle. (A value of 0 indicates up or “north”, increasing values proceed
-        clockwise.)
-
-        For text marks, polar coordinate angle in radians.
-    theta2 : anyOf(float, :class:`ExprRef`)
-        The end angle of arc marks in radians. A value of 0 indicates up or “north”,
-        increasing values proceed clockwise.
-    timeUnitBandPosition : float
-        Default relative band position for a time unit. If set to ``0``, the marks will be
-        positioned at the beginning of the time unit band step. If set to ``0.5``, the marks
-        will be positioned in the middle of the time unit band step.
-    timeUnitBandSize : float
-        Default relative band size for a time unit. If set to ``1``, the bandwidth of the
-        marks will be equal to the time unit band step. If set to ``0.5``, bandwidth of the
-        marks will be half of the time unit band step.
-    tooltip : anyOf(float, string, boolean, :class:`TooltipContent`, :class:`ExprRef`, None)
-        The tooltip text string to show upon mouse hover or an object defining which fields
-        should the tooltip be derived from.
-
-
-        * If ``tooltip`` is ``true`` or ``{"content": "encoding"}``, then all fields from
-          ``encoding`` will be used.
-        * If ``tooltip`` is ``{"content": "data"}``, then all fields that appear in the
-          highlighted data point will be used.
-        * If set to ``null`` or ``false``, then no tooltip will be used.
-
-        See the `tooltip <https://vega.github.io/vega-lite/docs/tooltip.html>`__
-        documentation for a detailed discussion about tooltip  in Vega-Lite.
-
-        **Default value:** ``null``
-    url : anyOf(:class:`URI`, :class:`ExprRef`)
-        The URL of the image file for image marks.
-    width : anyOf(float, :class:`ExprRef`)
-        Width of the marks.
-    x : anyOf(float, string, :class:`ExprRef`)
-        X coordinates of the marks, or width of horizontal ``"bar"`` and ``"area"`` without
-        specified ``x2`` or ``width``.
-
-        The ``value`` of this channel can be a number or a string ``"width"`` for the width
-        of the plot.
-    x2 : anyOf(float, string, :class:`ExprRef`)
-        X2 coordinates for ranged ``"area"``, ``"bar"``, ``"rect"``, and  ``"rule"``.
-
-        The ``value`` of this channel can be a number or a string ``"width"`` for the width
-        of the plot.
-    y : anyOf(float, string, :class:`ExprRef`)
-        Y coordinates of the marks, or height of vertical ``"bar"`` and ``"area"`` without
-        specified ``y2`` or ``height``.
-
-        The ``value`` of this channel can be a number or a string ``"height"`` for the
-        height of the plot.
-    y2 : anyOf(float, string, :class:`ExprRef`)
-        Y2 coordinates for ranged ``"area"``, ``"bar"``, ``"rect"``, and  ``"rule"``.
-
-        The ``value`` of this channel can be a number or a string ``"height"`` for the
-        height of the plot.
-    """
-    _schema = {'$ref': '#/definitions/LineConfig'}
-
-    def __init__(self, align=Undefined, angle=Undefined, aria=Undefined, ariaRole=Undefined,
-                 ariaRoleDescription=Undefined, aspect=Undefined, baseline=Undefined, blend=Undefined,
-                 color=Undefined, cornerRadius=Undefined, cornerRadiusBottomLeft=Undefined,
-                 cornerRadiusBottomRight=Undefined, cornerRadiusTopLeft=Undefined,
-                 cornerRadiusTopRight=Undefined, cursor=Undefined, description=Undefined, dir=Undefined,
-                 dx=Undefined, dy=Undefined, ellipsis=Undefined, endAngle=Undefined, fill=Undefined,
-                 fillOpacity=Undefined, filled=Undefined, font=Undefined, fontSize=Undefined,
-                 fontStyle=Undefined, fontWeight=Undefined, height=Undefined, href=Undefined,
-                 innerRadius=Undefined, interpolate=Undefined, invalid=Undefined, limit=Undefined,
-                 lineBreak=Undefined, lineHeight=Undefined, opacity=Undefined, order=Undefined,
-                 orient=Undefined, outerRadius=Undefined, padAngle=Undefined, point=Undefined,
-                 radius=Undefined, radius2=Undefined, shape=Undefined, size=Undefined, smooth=Undefined,
-                 startAngle=Undefined, stroke=Undefined, strokeCap=Undefined, strokeDash=Undefined,
-                 strokeDashOffset=Undefined, strokeJoin=Undefined, strokeMiterLimit=Undefined,
-                 strokeOffset=Undefined, strokeOpacity=Undefined, strokeWidth=Undefined,
-                 tension=Undefined, text=Undefined, theta=Undefined, theta2=Undefined,
-                 timeUnitBandPosition=Undefined, timeUnitBandSize=Undefined, tooltip=Undefined,
-                 url=Undefined, width=Undefined, x=Undefined, x2=Undefined, y=Undefined, y2=Undefined,
-                 **kwds):
-        super(LineConfig, self).__init__(align=align, angle=angle, aria=aria, ariaRole=ariaRole,
-                                         ariaRoleDescription=ariaRoleDescription, aspect=aspect,
-                                         baseline=baseline, blend=blend, color=color,
-                                         cornerRadius=cornerRadius,
-                                         cornerRadiusBottomLeft=cornerRadiusBottomLeft,
-                                         cornerRadiusBottomRight=cornerRadiusBottomRight,
-                                         cornerRadiusTopLeft=cornerRadiusTopLeft,
-                                         cornerRadiusTopRight=cornerRadiusTopRight, cursor=cursor,
-                                         description=description, dir=dir, dx=dx, dy=dy,
-                                         ellipsis=ellipsis, endAngle=endAngle, fill=fill,
-                                         fillOpacity=fillOpacity, filled=filled, font=font,
-                                         fontSize=fontSize, fontStyle=fontStyle, fontWeight=fontWeight,
-                                         height=height, href=href, innerRadius=innerRadius,
-                                         interpolate=interpolate, invalid=invalid, limit=limit,
-                                         lineBreak=lineBreak, lineHeight=lineHeight, opacity=opacity,
-                                         order=order, orient=orient, outerRadius=outerRadius,
-                                         padAngle=padAngle, point=point, radius=radius, radius2=radius2,
-                                         shape=shape, size=size, smooth=smooth, startAngle=startAngle,
-                                         stroke=stroke, strokeCap=strokeCap, strokeDash=strokeDash,
-                                         strokeDashOffset=strokeDashOffset, strokeJoin=strokeJoin,
-                                         strokeMiterLimit=strokeMiterLimit, strokeOffset=strokeOffset,
-                                         strokeOpacity=strokeOpacity, strokeWidth=strokeWidth,
-                                         tension=tension, text=text, theta=theta, theta2=theta2,
-                                         timeUnitBandPosition=timeUnitBandPosition,
-                                         timeUnitBandSize=timeUnitBandSize, tooltip=tooltip, url=url,
-                                         width=width, x=x, x2=x2, y=y, y2=y2, **kwds)
-
-
-class LineString(Geometry):
-    """LineString schema wrapper
-
-    Mapping(required=[coordinates, type])
-    LineString geometry object. https://tools.ietf.org/html/rfc7946#section-3.1.4
-
-    Parameters
-    ----------
-
-    coordinates : List(:class:`Position`)
-
-    type : string
-        Specifies the type of GeoJSON object.
-    bbox : :class:`BBox`
-        Bounding box of the coordinate range of the object's Geometries, Features, or
-        Feature Collections. https://tools.ietf.org/html/rfc7946#section-5
-    """
-    _schema = {'$ref': '#/definitions/LineString'}
-
-    def __init__(self, coordinates=Undefined, type=Undefined, bbox=Undefined, **kwds):
-        super(LineString, self).__init__(coordinates=coordinates, type=type, bbox=bbox, **kwds)
-
-
-class LinearGradient(Gradient):
-    """LinearGradient schema wrapper
-
-    Mapping(required=[gradient, stops])
-
-    Parameters
-    ----------
-
-    gradient : string
-        The type of gradient. Use ``"linear"`` for a linear gradient.
-    stops : List(:class:`GradientStop`)
-        An array of gradient stops defining the gradient color sequence.
-    id : string
-
-    x1 : float
-        The starting x-coordinate, in normalized [0, 1] coordinates, of the linear gradient.
-
-        **Default value:** ``0``
-    x2 : float
-        The ending x-coordinate, in normalized [0, 1] coordinates, of the linear gradient.
-
-        **Default value:** ``1``
-    y1 : float
-        The starting y-coordinate, in normalized [0, 1] coordinates, of the linear gradient.
-
-        **Default value:** ``0``
-    y2 : float
-        The ending y-coordinate, in normalized [0, 1] coordinates, of the linear gradient.
-
-        **Default value:** ``0``
-    """
-    _schema = {'$ref': '#/definitions/LinearGradient'}
-
-    def __init__(self, gradient=Undefined, stops=Undefined, id=Undefined, x1=Undefined, x2=Undefined,
-                 y1=Undefined, y2=Undefined, **kwds):
-        super(LinearGradient, self).__init__(gradient=gradient, stops=stops, id=id, x1=x1, x2=x2, y1=y1,
-                                             y2=y2, **kwds)
-
-
-class Locale(VegaLiteSchema):
-    """Locale schema wrapper
-
-    Mapping(required=[])
-
-    Parameters
-    ----------
-
-    number : :class:`NumberLocale`
-        Locale definition for formatting numbers.
-    time : :class:`TimeLocale`
-        Locale definition for formatting dates and times.
-    """
-    _schema = {'$ref': '#/definitions/Locale'}
-
-    def __init__(self, number=Undefined, time=Undefined, **kwds):
-        super(Locale, self).__init__(number=number, time=time, **kwds)
-
-
-class LookupData(VegaLiteSchema):
-    """LookupData schema wrapper
-
-    Mapping(required=[data, key])
-
-    Parameters
-    ----------
-
-    data : :class:`Data`
-        Secondary data source to lookup in.
-    key : :class:`FieldName`
-        Key in data to lookup.
-    fields : List(:class:`FieldName`)
-        Fields in foreign data or selection to lookup. If not specified, the entire object
-        is queried.
-    """
-    _schema = {'$ref': '#/definitions/LookupData'}
-
-    def __init__(self, data=Undefined, key=Undefined, fields=Undefined, **kwds):
-        super(LookupData, self).__init__(data=data, key=key, fields=fields, **kwds)
-
-
-class LookupSelection(VegaLiteSchema):
-    """LookupSelection schema wrapper
-
-    Mapping(required=[key, param])
-
-    Parameters
-    ----------
-
-    key : :class:`FieldName`
-        Key in data to lookup.
-    param : :class:`ParameterName`
-        Selection parameter name to look up.
-    fields : List(:class:`FieldName`)
-        Fields in foreign data or selection to lookup. If not specified, the entire object
-        is queried.
-    """
-    _schema = {'$ref': '#/definitions/LookupSelection'}
-
-    def __init__(self, key=Undefined, param=Undefined, fields=Undefined, **kwds):
-        super(LookupSelection, self).__init__(key=key, param=param, fields=fields, **kwds)
-
-
-class Mark(AnyMark):
-    """Mark schema wrapper
-
-    enum('arc', 'area', 'bar', 'image', 'line', 'point', 'rect', 'rule', 'text', 'tick',
-    'trail', 'circle', 'square', 'geoshape')
-    All types of primitive marks.
-    """
-    _schema = {'$ref': '#/definitions/Mark'}
-
-    def __init__(self, *args):
-        super(Mark, self).__init__(*args)
-
-
-class MarkConfig(AnyMarkConfig):
-    """MarkConfig schema wrapper
-
-    Mapping(required=[])
-
-    Parameters
-    ----------
-
-    align : anyOf(:class:`Align`, :class:`ExprRef`)
-        The horizontal alignment of the text or ranged marks (area, bar, image, rect, rule).
-        One of ``"left"``, ``"right"``, ``"center"``.
-
-        **Note:** Expression reference is *not* supported for range marks.
-    angle : anyOf(float, :class:`ExprRef`)
-        The rotation angle of the text, in degrees.
-    aria : anyOf(boolean, :class:`ExprRef`)
-        A boolean flag indicating if `ARIA attributes
-        <https://developer.mozilla.org/en-US/docs/Web/Accessibility/ARIA>`__ should be
-        included (SVG output only). If ``false``, the "aria-hidden" attribute will be set on
-        the output SVG element, removing the mark item from the ARIA accessibility tree.
-    ariaRole : anyOf(string, :class:`ExprRef`)
-        Sets the type of user interface element of the mark item for `ARIA accessibility
-        <https://developer.mozilla.org/en-US/docs/Web/Accessibility/ARIA>`__ (SVG output
-        only). If specified, this property determines the "role" attribute. Warning: this
-        property is experimental and may be changed in the future.
-    ariaRoleDescription : anyOf(string, :class:`ExprRef`)
-        A human-readable, author-localized description for the role of the mark item for
-        `ARIA accessibility
-        <https://developer.mozilla.org/en-US/docs/Web/Accessibility/ARIA>`__ (SVG output
-        only). If specified, this property determines the "aria-roledescription" attribute.
-        Warning: this property is experimental and may be changed in the future.
-    aspect : anyOf(boolean, :class:`ExprRef`)
-        Whether to keep aspect ratio of image marks.
-    baseline : anyOf(:class:`TextBaseline`, :class:`ExprRef`)
-        For text marks, the vertical text baseline. One of ``"alphabetic"`` (default),
-        ``"top"``, ``"middle"``, ``"bottom"``, ``"line-top"``, ``"line-bottom"``, or an
-        expression reference that provides one of the valid values. The ``"line-top"`` and
-        ``"line-bottom"`` values operate similarly to ``"top"`` and ``"bottom"``, but are
-        calculated relative to the ``lineHeight`` rather than ``fontSize`` alone.
-
-        For range marks, the vertical alignment of the marks. One of ``"top"``,
-        ``"middle"``, ``"bottom"``.
-
-        **Note:** Expression reference is *not* supported for range marks.
-    blend : anyOf(:class:`Blend`, :class:`ExprRef`)
-        The color blend mode for drawing an item on its current background. Any valid `CSS
-        mix-blend-mode <https://developer.mozilla.org/en-US/docs/Web/CSS/mix-blend-mode>`__
-        value can be used.
-
-        __Default value:__ ``"source-over"``
-    color : anyOf(:class:`Color`, :class:`Gradient`, :class:`ExprRef`)
-        Default color.
-
-        **Default value:** :raw-html:`<span style="color: #4682b4;">&#9632;</span>`
-        ``"#4682b4"``
-
-        **Note:**
-
-
-        * This property cannot be used in a `style config
-          <https://vega.github.io/vega-lite/docs/mark.html#style-config>`__.
-        * The ``fill`` and ``stroke`` properties have higher precedence than ``color`` and
-          will override ``color``.
-    cornerRadius : anyOf(float, :class:`ExprRef`)
-        The radius in pixels of rounded rectangles or arcs' corners.
-
-        **Default value:** ``0``
-    cornerRadiusBottomLeft : anyOf(float, :class:`ExprRef`)
-        The radius in pixels of rounded rectangles' bottom left corner.
-
-        **Default value:** ``0``
-    cornerRadiusBottomRight : anyOf(float, :class:`ExprRef`)
-        The radius in pixels of rounded rectangles' bottom right corner.
-
-        **Default value:** ``0``
-    cornerRadiusTopLeft : anyOf(float, :class:`ExprRef`)
-        The radius in pixels of rounded rectangles' top right corner.
-
-        **Default value:** ``0``
-    cornerRadiusTopRight : anyOf(float, :class:`ExprRef`)
-        The radius in pixels of rounded rectangles' top left corner.
-
-        **Default value:** ``0``
-    cursor : anyOf(:class:`Cursor`, :class:`ExprRef`)
-        The mouse cursor used over the mark. Any valid `CSS cursor type
-        <https://developer.mozilla.org/en-US/docs/Web/CSS/cursor#Values>`__ can be used.
-    description : anyOf(string, :class:`ExprRef`)
-        A text description of the mark item for `ARIA accessibility
-        <https://developer.mozilla.org/en-US/docs/Web/Accessibility/ARIA>`__ (SVG output
-        only). If specified, this property determines the `"aria-label" attribute
-        <https://developer.mozilla.org/en-US/docs/Web/Accessibility/ARIA/ARIA_Techniques/Using_the_aria-label_attribute>`__.
-    dir : anyOf(:class:`TextDirection`, :class:`ExprRef`)
-        The direction of the text. One of ``"ltr"`` (left-to-right) or ``"rtl"``
-        (right-to-left). This property determines on which side is truncated in response to
-        the limit parameter.
-
-        **Default value:** ``"ltr"``
-    dx : anyOf(float, :class:`ExprRef`)
-        The horizontal offset, in pixels, between the text label and its anchor point. The
-        offset is applied after rotation by the *angle* property.
-    dy : anyOf(float, :class:`ExprRef`)
-        The vertical offset, in pixels, between the text label and its anchor point. The
-        offset is applied after rotation by the *angle* property.
-    ellipsis : anyOf(string, :class:`ExprRef`)
-        The ellipsis string for text truncated in response to the limit parameter.
-
-        **Default value:** ``"…"``
-    endAngle : anyOf(float, :class:`ExprRef`)
-        The end angle in radians for arc marks. A value of ``0`` indicates up (north),
-        increasing values proceed clockwise.
-    fill : anyOf(:class:`Color`, :class:`Gradient`, None, :class:`ExprRef`)
-        Default fill color. This property has higher precedence than ``config.color``. Set
-        to ``null`` to remove fill.
-
-        **Default value:** (None)
-    fillOpacity : anyOf(float, :class:`ExprRef`)
-        The fill opacity (value between [0,1]).
-
-        **Default value:** ``1``
-    filled : boolean
-        Whether the mark's color should be used as fill color instead of stroke color.
-
-        **Default value:** ``false`` for all ``point``, ``line``, and ``rule`` marks as well
-        as ``geoshape`` marks for `graticule
-        <https://vega.github.io/vega-lite/docs/data.html#graticule>`__ data sources;
-        otherwise, ``true``.
-
-        **Note:** This property cannot be used in a `style config
-        <https://vega.github.io/vega-lite/docs/mark.html#style-config>`__.
-    font : anyOf(string, :class:`ExprRef`)
-        The typeface to set the text in (e.g., ``"Helvetica Neue"`` ).
-    fontSize : anyOf(float, :class:`ExprRef`)
-        The font size, in pixels.
-
-        **Default value:** ``11``
-    fontStyle : anyOf(:class:`FontStyle`, :class:`ExprRef`)
-        The font style (e.g., ``"italic"`` ).
-    fontWeight : anyOf(:class:`FontWeight`, :class:`ExprRef`)
-        The font weight. This can be either a string (e.g ``"bold"``, ``"normal"`` ) or a
-        number ( ``100``, ``200``, ``300``, ..., ``900`` where ``"normal"`` = ``400`` and
-        ``"bold"`` = ``700`` ).
-    height : anyOf(float, :class:`ExprRef`)
-        Height of the marks.
-    href : anyOf(:class:`URI`, :class:`ExprRef`)
-        A URL to load upon mouse click. If defined, the mark acts as a hyperlink.
-    innerRadius : anyOf(float, :class:`ExprRef`)
-        The inner radius in pixels of arc marks. ``innerRadius`` is an alias for
-        ``radius2``.
-
-        **Default value:** ``0``
-    interpolate : anyOf(:class:`Interpolate`, :class:`ExprRef`)
-        The line interpolation method to use for line and area marks. One of the following:
-
-
-        * ``"linear"`` : piecewise linear segments, as in a polyline.
-        * ``"linear-closed"`` : close the linear segments to form a polygon.
-        * ``"step"`` : alternate between horizontal and vertical segments, as in a step
-          function.
-        * ``"step-before"`` : alternate between vertical and horizontal segments, as in a
-          step function.
-        * ``"step-after"`` : alternate between horizontal and vertical segments, as in a
-          step function.
-        * ``"basis"`` : a B-spline, with control point duplication on the ends.
-        * ``"basis-open"`` : an open B-spline; may not intersect the start or end.
-        * ``"basis-closed"`` : a closed B-spline, as in a loop.
-        * ``"cardinal"`` : a Cardinal spline, with control point duplication on the ends.
-        * ``"cardinal-open"`` : an open Cardinal spline; may not intersect the start or end,
-          but will intersect other control points.
-        * ``"cardinal-closed"`` : a closed Cardinal spline, as in a loop.
-        * ``"bundle"`` : equivalent to basis, except the tension parameter is used to
-          straighten the spline.
-        * ``"monotone"`` : cubic interpolation that preserves monotonicity in y.
-    invalid : enum('filter', None)
-        Defines how Vega-Lite should handle marks for invalid values ( ``null`` and ``NaN``
-        ).
-
-
-        * If set to ``"filter"`` (default), all data items with null values will be skipped
-          (for line, trail, and area marks) or filtered (for other marks).
-        * If ``null``, all data items are included. In this case, invalid values will be
-          interpreted as zeroes.
-    limit : anyOf(float, :class:`ExprRef`)
-        The maximum length of the text mark in pixels. The text value will be automatically
-        truncated if the rendered size exceeds the limit.
-
-        **Default value:** ``0`` -- indicating no limit
-    lineBreak : anyOf(string, :class:`ExprRef`)
-        A delimiter, such as a newline character, upon which to break text strings into
-        multiple lines. This property is ignored if the text is array-valued.
-    lineHeight : anyOf(float, :class:`ExprRef`)
-        The line height in pixels (the spacing between subsequent lines of text) for
-        multi-line text marks.
-    opacity : anyOf(float, :class:`ExprRef`)
-        The overall opacity (value between [0,1]).
-
-        **Default value:** ``0.7`` for non-aggregate plots with ``point``, ``tick``,
-        ``circle``, or ``square`` marks or layered ``bar`` charts and ``1`` otherwise.
-    order : anyOf(None, boolean)
-        For line and trail marks, this ``order`` property can be set to ``null`` or
-        ``false`` to make the lines use the original order in the data sources.
-    orient : :class:`Orientation`
-        The orientation of a non-stacked bar, tick, area, and line charts. The value is
-        either horizontal (default) or vertical.
-
-
-        * For bar, rule and tick, this determines whether the size of the bar and tick
-          should be applied to x or y dimension.
-        * For area, this property determines the orient property of the Vega output.
-        * For line and trail marks, this property determines the sort order of the points in
-          the line if ``config.sortLineBy`` is not specified. For stacked charts, this is
-          always determined by the orientation of the stack; therefore explicitly specified
-          value will be ignored.
-    outerRadius : anyOf(float, :class:`ExprRef`)
-        The outer radius in pixels of arc marks. ``outerRadius`` is an alias for ``radius``.
-
-        **Default value:** ``0``
-    padAngle : anyOf(float, :class:`ExprRef`)
-        The angular padding applied to sides of the arc, in radians.
-    radius : anyOf(float, :class:`ExprRef`)
-        For arc mark, the primary (outer) radius in pixels.
-
-        For text marks, polar coordinate radial offset, in pixels, of the text from the
-        origin determined by the ``x`` and ``y`` properties.
-
-        **Default value:** ``min(plot_width, plot_height)/2``
-    radius2 : anyOf(float, :class:`ExprRef`)
-        The secondary (inner) radius in pixels of arc marks.
-
-        **Default value:** ``0``
-    shape : anyOf(anyOf(:class:`SymbolShape`, string), :class:`ExprRef`)
-        Shape of the point marks. Supported values include:
-
-
-        * plotting shapes: ``"circle"``, ``"square"``, ``"cross"``, ``"diamond"``,
-          ``"triangle-up"``, ``"triangle-down"``, ``"triangle-right"``, or
-          ``"triangle-left"``.
-        * the line symbol ``"stroke"``
-        * centered directional shapes ``"arrow"``, ``"wedge"``, or ``"triangle"``
-        * a custom `SVG path string
-          <https://developer.mozilla.org/en-US/docs/Web/SVG/Tutorial/Paths>`__ (For correct
-          sizing, custom shape paths should be defined within a square bounding box with
-          coordinates ranging from -1 to 1 along both the x and y dimensions.)
-
-        **Default value:** ``"circle"``
-    size : anyOf(float, :class:`ExprRef`)
-        Default size for marks.
-
-
-        * For ``point`` / ``circle`` / ``square``, this represents the pixel area of the
-          marks. Note that this value sets the area of the symbol; the side lengths will
-          increase with the square root of this value.
-        * For ``bar``, this represents the band size of the bar, in pixels.
-        * For ``text``, this represents the font size, in pixels.
-
-        **Default value:**
-
-
-        * ``30`` for point, circle, square marks; width/height's ``step``
-        * ``2`` for bar marks with discrete dimensions;
-        * ``5`` for bar marks with continuous dimensions;
-        * ``11`` for text marks.
-    smooth : anyOf(boolean, :class:`ExprRef`)
-        A boolean flag (default true) indicating if the image should be smoothed when
-        resized. If false, individual pixels should be scaled directly rather than
-        interpolated with smoothing. For SVG rendering, this option may not work in some
-        browsers due to lack of standardization.
-    startAngle : anyOf(float, :class:`ExprRef`)
-        The start angle in radians for arc marks. A value of ``0`` indicates up (north),
-        increasing values proceed clockwise.
-    stroke : anyOf(:class:`Color`, :class:`Gradient`, None, :class:`ExprRef`)
-        Default stroke color. This property has higher precedence than ``config.color``. Set
-        to ``null`` to remove stroke.
-
-        **Default value:** (None)
-    strokeCap : anyOf(:class:`StrokeCap`, :class:`ExprRef`)
-        The stroke cap for line ending style. One of ``"butt"``, ``"round"``, or
-        ``"square"``.
-
-        **Default value:** ``"butt"``
-    strokeDash : anyOf(List(float), :class:`ExprRef`)
-        An array of alternating stroke, space lengths for creating dashed or dotted lines.
-    strokeDashOffset : anyOf(float, :class:`ExprRef`)
-        The offset (in pixels) into which to begin drawing with the stroke dash array.
-    strokeJoin : anyOf(:class:`StrokeJoin`, :class:`ExprRef`)
-        The stroke line join method. One of ``"miter"``, ``"round"`` or ``"bevel"``.
-
-        **Default value:** ``"miter"``
-    strokeMiterLimit : anyOf(float, :class:`ExprRef`)
-        The miter limit at which to bevel a line join.
-    strokeOffset : anyOf(float, :class:`ExprRef`)
-        The offset in pixels at which to draw the group stroke and fill. If unspecified, the
-        default behavior is to dynamically offset stroked groups such that 1 pixel stroke
-        widths align with the pixel grid.
-    strokeOpacity : anyOf(float, :class:`ExprRef`)
-        The stroke opacity (value between [0,1]).
-
-        **Default value:** ``1``
-    strokeWidth : anyOf(float, :class:`ExprRef`)
-        The stroke width, in pixels.
-    tension : anyOf(float, :class:`ExprRef`)
-        Depending on the interpolation type, sets the tension parameter (for line and area
-        marks).
-    text : anyOf(:class:`Text`, :class:`ExprRef`)
-        Placeholder text if the ``text`` channel is not specified
-    theta : anyOf(float, :class:`ExprRef`)
-        For arc marks, the arc length in radians if theta2 is not specified, otherwise the
-        start arc angle. (A value of 0 indicates up or “north”, increasing values proceed
-        clockwise.)
-
-        For text marks, polar coordinate angle in radians.
-    theta2 : anyOf(float, :class:`ExprRef`)
-        The end angle of arc marks in radians. A value of 0 indicates up or “north”,
-        increasing values proceed clockwise.
-    timeUnitBandPosition : float
-        Default relative band position for a time unit. If set to ``0``, the marks will be
-        positioned at the beginning of the time unit band step. If set to ``0.5``, the marks
-        will be positioned in the middle of the time unit band step.
-    timeUnitBandSize : float
-        Default relative band size for a time unit. If set to ``1``, the bandwidth of the
-        marks will be equal to the time unit band step. If set to ``0.5``, bandwidth of the
-        marks will be half of the time unit band step.
-    tooltip : anyOf(float, string, boolean, :class:`TooltipContent`, :class:`ExprRef`, None)
-        The tooltip text string to show upon mouse hover or an object defining which fields
-        should the tooltip be derived from.
-
-
-        * If ``tooltip`` is ``true`` or ``{"content": "encoding"}``, then all fields from
-          ``encoding`` will be used.
-        * If ``tooltip`` is ``{"content": "data"}``, then all fields that appear in the
-          highlighted data point will be used.
-        * If set to ``null`` or ``false``, then no tooltip will be used.
-
-        See the `tooltip <https://vega.github.io/vega-lite/docs/tooltip.html>`__
-        documentation for a detailed discussion about tooltip  in Vega-Lite.
-
-        **Default value:** ``null``
-    url : anyOf(:class:`URI`, :class:`ExprRef`)
-        The URL of the image file for image marks.
-    width : anyOf(float, :class:`ExprRef`)
-        Width of the marks.
-    x : anyOf(float, string, :class:`ExprRef`)
-        X coordinates of the marks, or width of horizontal ``"bar"`` and ``"area"`` without
-        specified ``x2`` or ``width``.
-
-        The ``value`` of this channel can be a number or a string ``"width"`` for the width
-        of the plot.
-    x2 : anyOf(float, string, :class:`ExprRef`)
-        X2 coordinates for ranged ``"area"``, ``"bar"``, ``"rect"``, and  ``"rule"``.
-
-        The ``value`` of this channel can be a number or a string ``"width"`` for the width
-        of the plot.
-    y : anyOf(float, string, :class:`ExprRef`)
-        Y coordinates of the marks, or height of vertical ``"bar"`` and ``"area"`` without
-        specified ``y2`` or ``height``.
-
-        The ``value`` of this channel can be a number or a string ``"height"`` for the
-        height of the plot.
-    y2 : anyOf(float, string, :class:`ExprRef`)
-        Y2 coordinates for ranged ``"area"``, ``"bar"``, ``"rect"``, and  ``"rule"``.
-
-        The ``value`` of this channel can be a number or a string ``"height"`` for the
-        height of the plot.
-    """
-    _schema = {'$ref': '#/definitions/MarkConfig'}
-
-    def __init__(self, align=Undefined, angle=Undefined, aria=Undefined, ariaRole=Undefined,
-                 ariaRoleDescription=Undefined, aspect=Undefined, baseline=Undefined, blend=Undefined,
-                 color=Undefined, cornerRadius=Undefined, cornerRadiusBottomLeft=Undefined,
-                 cornerRadiusBottomRight=Undefined, cornerRadiusTopLeft=Undefined,
-                 cornerRadiusTopRight=Undefined, cursor=Undefined, description=Undefined, dir=Undefined,
-                 dx=Undefined, dy=Undefined, ellipsis=Undefined, endAngle=Undefined, fill=Undefined,
-                 fillOpacity=Undefined, filled=Undefined, font=Undefined, fontSize=Undefined,
-                 fontStyle=Undefined, fontWeight=Undefined, height=Undefined, href=Undefined,
-                 innerRadius=Undefined, interpolate=Undefined, invalid=Undefined, limit=Undefined,
-                 lineBreak=Undefined, lineHeight=Undefined, opacity=Undefined, order=Undefined,
-                 orient=Undefined, outerRadius=Undefined, padAngle=Undefined, radius=Undefined,
-                 radius2=Undefined, shape=Undefined, size=Undefined, smooth=Undefined,
-                 startAngle=Undefined, stroke=Undefined, strokeCap=Undefined, strokeDash=Undefined,
-                 strokeDashOffset=Undefined, strokeJoin=Undefined, strokeMiterLimit=Undefined,
-                 strokeOffset=Undefined, strokeOpacity=Undefined, strokeWidth=Undefined,
-                 tension=Undefined, text=Undefined, theta=Undefined, theta2=Undefined,
-                 timeUnitBandPosition=Undefined, timeUnitBandSize=Undefined, tooltip=Undefined,
-                 url=Undefined, width=Undefined, x=Undefined, x2=Undefined, y=Undefined, y2=Undefined,
-                 **kwds):
-        super(MarkConfig, self).__init__(align=align, angle=angle, aria=aria, ariaRole=ariaRole,
-                                         ariaRoleDescription=ariaRoleDescription, aspect=aspect,
-                                         baseline=baseline, blend=blend, color=color,
-                                         cornerRadius=cornerRadius,
-                                         cornerRadiusBottomLeft=cornerRadiusBottomLeft,
-                                         cornerRadiusBottomRight=cornerRadiusBottomRight,
-                                         cornerRadiusTopLeft=cornerRadiusTopLeft,
-                                         cornerRadiusTopRight=cornerRadiusTopRight, cursor=cursor,
-                                         description=description, dir=dir, dx=dx, dy=dy,
-                                         ellipsis=ellipsis, endAngle=endAngle, fill=fill,
-                                         fillOpacity=fillOpacity, filled=filled, font=font,
-                                         fontSize=fontSize, fontStyle=fontStyle, fontWeight=fontWeight,
-                                         height=height, href=href, innerRadius=innerRadius,
-                                         interpolate=interpolate, invalid=invalid, limit=limit,
-                                         lineBreak=lineBreak, lineHeight=lineHeight, opacity=opacity,
-                                         order=order, orient=orient, outerRadius=outerRadius,
-                                         padAngle=padAngle, radius=radius, radius2=radius2, shape=shape,
-                                         size=size, smooth=smooth, startAngle=startAngle, stroke=stroke,
-                                         strokeCap=strokeCap, strokeDash=strokeDash,
-                                         strokeDashOffset=strokeDashOffset, strokeJoin=strokeJoin,
-                                         strokeMiterLimit=strokeMiterLimit, strokeOffset=strokeOffset,
-                                         strokeOpacity=strokeOpacity, strokeWidth=strokeWidth,
-                                         tension=tension, text=text, theta=theta, theta2=theta2,
-                                         timeUnitBandPosition=timeUnitBandPosition,
-                                         timeUnitBandSize=timeUnitBandSize, tooltip=tooltip, url=url,
-                                         width=width, x=x, x2=x2, y=y, y2=y2, **kwds)
-
-
-class MarkDef(AnyMark):
-    """MarkDef schema wrapper
-
-    Mapping(required=[type])
-
-    Parameters
-    ----------
-
-    type : :class:`Mark`
-        The mark type. This could a primitive mark type (one of ``"bar"``, ``"circle"``,
-        ``"square"``, ``"tick"``, ``"line"``, ``"area"``, ``"point"``, ``"geoshape"``,
-        ``"rule"``, and ``"text"`` ) or a composite mark type ( ``"boxplot"``,
-        ``"errorband"``, ``"errorbar"`` ).
-    align : anyOf(:class:`Align`, :class:`ExprRef`)
-        The horizontal alignment of the text or ranged marks (area, bar, image, rect, rule).
-        One of ``"left"``, ``"right"``, ``"center"``.
-
-        **Note:** Expression reference is *not* supported for range marks.
-    angle : anyOf(float, :class:`ExprRef`)
-        The rotation angle of the text, in degrees.
-    aria : anyOf(boolean, :class:`ExprRef`)
-        A boolean flag indicating if `ARIA attributes
-        <https://developer.mozilla.org/en-US/docs/Web/Accessibility/ARIA>`__ should be
-        included (SVG output only). If ``false``, the "aria-hidden" attribute will be set on
-        the output SVG element, removing the mark item from the ARIA accessibility tree.
-    ariaRole : anyOf(string, :class:`ExprRef`)
-        Sets the type of user interface element of the mark item for `ARIA accessibility
-        <https://developer.mozilla.org/en-US/docs/Web/Accessibility/ARIA>`__ (SVG output
-        only). If specified, this property determines the "role" attribute. Warning: this
-        property is experimental and may be changed in the future.
-    ariaRoleDescription : anyOf(string, :class:`ExprRef`)
-        A human-readable, author-localized description for the role of the mark item for
-        `ARIA accessibility
-        <https://developer.mozilla.org/en-US/docs/Web/Accessibility/ARIA>`__ (SVG output
-        only). If specified, this property determines the "aria-roledescription" attribute.
-        Warning: this property is experimental and may be changed in the future.
-    aspect : anyOf(boolean, :class:`ExprRef`)
-        Whether to keep aspect ratio of image marks.
-    bandSize : float
-        The width of the ticks.
-
-        **Default value:**  3/4 of step (width step for horizontal ticks and height step for
-        vertical ticks).
-    baseline : anyOf(:class:`TextBaseline`, :class:`ExprRef`)
-        For text marks, the vertical text baseline. One of ``"alphabetic"`` (default),
-        ``"top"``, ``"middle"``, ``"bottom"``, ``"line-top"``, ``"line-bottom"``, or an
-        expression reference that provides one of the valid values. The ``"line-top"`` and
-        ``"line-bottom"`` values operate similarly to ``"top"`` and ``"bottom"``, but are
-        calculated relative to the ``lineHeight`` rather than ``fontSize`` alone.
-
-        For range marks, the vertical alignment of the marks. One of ``"top"``,
-        ``"middle"``, ``"bottom"``.
-
-        **Note:** Expression reference is *not* supported for range marks.
-    binSpacing : float
-        Offset between bars for binned field. The ideal value for this is either 0
-        (preferred by statisticians) or 1 (Vega-Lite default, D3 example style).
-
-        **Default value:** ``1``
-    blend : anyOf(:class:`Blend`, :class:`ExprRef`)
-        The color blend mode for drawing an item on its current background. Any valid `CSS
-        mix-blend-mode <https://developer.mozilla.org/en-US/docs/Web/CSS/mix-blend-mode>`__
-        value can be used.
-
-        __Default value:__ ``"source-over"``
-    clip : boolean
-        Whether a mark be clipped to the enclosing group’s width and height.
-    color : anyOf(:class:`Color`, :class:`Gradient`, :class:`ExprRef`)
-        Default color.
-
-        **Default value:** :raw-html:`<span style="color: #4682b4;">&#9632;</span>`
-        ``"#4682b4"``
-
-        **Note:**
-
-
-        * This property cannot be used in a `style config
-          <https://vega.github.io/vega-lite/docs/mark.html#style-config>`__.
-        * The ``fill`` and ``stroke`` properties have higher precedence than ``color`` and
-          will override ``color``.
-    continuousBandSize : float
-        The default size of the bars on continuous scales.
-
-        **Default value:** ``5``
-    cornerRadius : anyOf(float, :class:`ExprRef`)
-        The radius in pixels of rounded rectangles or arcs' corners.
-
-        **Default value:** ``0``
-    cornerRadiusBottomLeft : anyOf(float, :class:`ExprRef`)
-        The radius in pixels of rounded rectangles' bottom left corner.
-
-        **Default value:** ``0``
-    cornerRadiusBottomRight : anyOf(float, :class:`ExprRef`)
-        The radius in pixels of rounded rectangles' bottom right corner.
-
-        **Default value:** ``0``
-    cornerRadiusEnd : anyOf(float, :class:`ExprRef`)
-        For vertical bars, top-left and top-right corner radius.
-
-        For horizontal bars, top-right and bottom-right corner radius.
-    cornerRadiusTopLeft : anyOf(float, :class:`ExprRef`)
-        The radius in pixels of rounded rectangles' top right corner.
-
-        **Default value:** ``0``
-    cornerRadiusTopRight : anyOf(float, :class:`ExprRef`)
-        The radius in pixels of rounded rectangles' top left corner.
-
-        **Default value:** ``0``
-    cursor : anyOf(:class:`Cursor`, :class:`ExprRef`)
-        The mouse cursor used over the mark. Any valid `CSS cursor type
-        <https://developer.mozilla.org/en-US/docs/Web/CSS/cursor#Values>`__ can be used.
-    description : anyOf(string, :class:`ExprRef`)
-        A text description of the mark item for `ARIA accessibility
-        <https://developer.mozilla.org/en-US/docs/Web/Accessibility/ARIA>`__ (SVG output
-        only). If specified, this property determines the `"aria-label" attribute
-        <https://developer.mozilla.org/en-US/docs/Web/Accessibility/ARIA/ARIA_Techniques/Using_the_aria-label_attribute>`__.
-    dir : anyOf(:class:`TextDirection`, :class:`ExprRef`)
-        The direction of the text. One of ``"ltr"`` (left-to-right) or ``"rtl"``
-        (right-to-left). This property determines on which side is truncated in response to
-        the limit parameter.
-
-        **Default value:** ``"ltr"``
-    discreteBandSize : anyOf(float, :class:`RelativeBandSize`)
-        The default size of the bars with discrete dimensions. If unspecified, the default
-        size is  ``step-2``, which provides 2 pixel offset between bars.
-    dx : anyOf(float, :class:`ExprRef`)
-        The horizontal offset, in pixels, between the text label and its anchor point. The
-        offset is applied after rotation by the *angle* property.
-    dy : anyOf(float, :class:`ExprRef`)
-        The vertical offset, in pixels, between the text label and its anchor point. The
-        offset is applied after rotation by the *angle* property.
-    ellipsis : anyOf(string, :class:`ExprRef`)
-        The ellipsis string for text truncated in response to the limit parameter.
-
-        **Default value:** ``"…"``
-    fill : anyOf(:class:`Color`, :class:`Gradient`, None, :class:`ExprRef`)
-        Default fill color. This property has higher precedence than ``config.color``. Set
-        to ``null`` to remove fill.
-
-        **Default value:** (None)
-    fillOpacity : anyOf(float, :class:`ExprRef`)
-        The fill opacity (value between [0,1]).
-
-        **Default value:** ``1``
-    filled : boolean
-        Whether the mark's color should be used as fill color instead of stroke color.
-
-        **Default value:** ``false`` for all ``point``, ``line``, and ``rule`` marks as well
-        as ``geoshape`` marks for `graticule
-        <https://vega.github.io/vega-lite/docs/data.html#graticule>`__ data sources;
-        otherwise, ``true``.
-
-        **Note:** This property cannot be used in a `style config
-        <https://vega.github.io/vega-lite/docs/mark.html#style-config>`__.
-    font : anyOf(string, :class:`ExprRef`)
-        The typeface to set the text in (e.g., ``"Helvetica Neue"`` ).
-    fontSize : anyOf(float, :class:`ExprRef`)
-        The font size, in pixels.
-
-        **Default value:** ``11``
-    fontStyle : anyOf(:class:`FontStyle`, :class:`ExprRef`)
-        The font style (e.g., ``"italic"`` ).
-    fontWeight : anyOf(:class:`FontWeight`, :class:`ExprRef`)
-        The font weight. This can be either a string (e.g ``"bold"``, ``"normal"`` ) or a
-        number ( ``100``, ``200``, ``300``, ..., ``900`` where ``"normal"`` = ``400`` and
-        ``"bold"`` = ``700`` ).
-    height : anyOf(float, :class:`ExprRef`, :class:`RelativeBandSize`)
-        Height of the marks.  One of:
-
-
-        A number representing a fixed pixel height.
-
-        A relative band size definition.  For example, ``{band: 0.5}`` represents half of
-        the band
-    href : anyOf(:class:`URI`, :class:`ExprRef`)
-        A URL to load upon mouse click. If defined, the mark acts as a hyperlink.
-    innerRadius : anyOf(float, :class:`ExprRef`)
-        The inner radius in pixels of arc marks. ``innerRadius`` is an alias for
-        ``radius2``.
-
-        **Default value:** ``0``
-    interpolate : anyOf(:class:`Interpolate`, :class:`ExprRef`)
-        The line interpolation method to use for line and area marks. One of the following:
-
-
-        * ``"linear"`` : piecewise linear segments, as in a polyline.
-        * ``"linear-closed"`` : close the linear segments to form a polygon.
-        * ``"step"`` : alternate between horizontal and vertical segments, as in a step
-          function.
-        * ``"step-before"`` : alternate between vertical and horizontal segments, as in a
-          step function.
-        * ``"step-after"`` : alternate between horizontal and vertical segments, as in a
-          step function.
-        * ``"basis"`` : a B-spline, with control point duplication on the ends.
-        * ``"basis-open"`` : an open B-spline; may not intersect the start or end.
-        * ``"basis-closed"`` : a closed B-spline, as in a loop.
-        * ``"cardinal"`` : a Cardinal spline, with control point duplication on the ends.
-        * ``"cardinal-open"`` : an open Cardinal spline; may not intersect the start or end,
-          but will intersect other control points.
-        * ``"cardinal-closed"`` : a closed Cardinal spline, as in a loop.
-        * ``"bundle"`` : equivalent to basis, except the tension parameter is used to
-          straighten the spline.
-        * ``"monotone"`` : cubic interpolation that preserves monotonicity in y.
-    invalid : enum('filter', None)
-        Defines how Vega-Lite should handle marks for invalid values ( ``null`` and ``NaN``
-        ).
-
-
-        * If set to ``"filter"`` (default), all data items with null values will be skipped
-          (for line, trail, and area marks) or filtered (for other marks).
-        * If ``null``, all data items are included. In this case, invalid values will be
-          interpreted as zeroes.
-    limit : anyOf(float, :class:`ExprRef`)
-        The maximum length of the text mark in pixels. The text value will be automatically
-        truncated if the rendered size exceeds the limit.
-
-        **Default value:** ``0`` -- indicating no limit
-    line : anyOf(boolean, :class:`OverlayMarkDef`)
-        A flag for overlaying line on top of area marks, or an object defining the
-        properties of the overlayed lines.
-
-
-        If this value is an empty object ( ``{}`` ) or ``true``, lines with default
-        properties will be used.
-
-        If this value is ``false``, no lines would be automatically added to area marks.
-
-        **Default value:** ``false``.
-    lineBreak : anyOf(string, :class:`ExprRef`)
-        A delimiter, such as a newline character, upon which to break text strings into
-        multiple lines. This property is ignored if the text is array-valued.
-    lineHeight : anyOf(float, :class:`ExprRef`)
-        The line height in pixels (the spacing between subsequent lines of text) for
-        multi-line text marks.
-    minBandSize : anyOf(float, :class:`ExprRef`)
-        The minimum band size for bar and rectangle marks. **Default value:** ``0.25``
-    opacity : anyOf(float, :class:`ExprRef`)
-        The overall opacity (value between [0,1]).
-
-        **Default value:** ``0.7`` for non-aggregate plots with ``point``, ``tick``,
-        ``circle``, or ``square`` marks or layered ``bar`` charts and ``1`` otherwise.
-    order : anyOf(None, boolean)
-        For line and trail marks, this ``order`` property can be set to ``null`` or
-        ``false`` to make the lines use the original order in the data sources.
-    orient : :class:`Orientation`
-        The orientation of a non-stacked bar, tick, area, and line charts. The value is
-        either horizontal (default) or vertical.
-
-
-        * For bar, rule and tick, this determines whether the size of the bar and tick
-          should be applied to x or y dimension.
-        * For area, this property determines the orient property of the Vega output.
-        * For line and trail marks, this property determines the sort order of the points in
-          the line if ``config.sortLineBy`` is not specified. For stacked charts, this is
-          always determined by the orientation of the stack; therefore explicitly specified
-          value will be ignored.
-    outerRadius : anyOf(float, :class:`ExprRef`)
-        The outer radius in pixels of arc marks. ``outerRadius`` is an alias for ``radius``.
-
-        **Default value:** ``0``
-    padAngle : anyOf(float, :class:`ExprRef`)
-        The angular padding applied to sides of the arc, in radians.
-    point : anyOf(boolean, :class:`OverlayMarkDef`, string)
-        A flag for overlaying points on top of line or area marks, or an object defining the
-        properties of the overlayed points.
-
-
-        If this property is ``"transparent"``, transparent points will be used (for
-        enhancing tooltips and selections).
-
-        If this property is an empty object ( ``{}`` ) or ``true``, filled points with
-        default properties will be used.
-
-        If this property is ``false``, no points would be automatically added to line or
-        area marks.
-
-        **Default value:** ``false``.
-    radius : anyOf(float, :class:`ExprRef`)
-        For arc mark, the primary (outer) radius in pixels.
-
-        For text marks, polar coordinate radial offset, in pixels, of the text from the
-        origin determined by the ``x`` and ``y`` properties.
-
-        **Default value:** ``min(plot_width, plot_height)/2``
-    radius2 : anyOf(float, :class:`ExprRef`)
-        The secondary (inner) radius in pixels of arc marks.
-
-        **Default value:** ``0``
-    radius2Offset : anyOf(float, :class:`ExprRef`)
-        Offset for radius2.
-    radiusOffset : anyOf(float, :class:`ExprRef`)
-        Offset for radius.
-    shape : anyOf(anyOf(:class:`SymbolShape`, string), :class:`ExprRef`)
-        Shape of the point marks. Supported values include:
-
-
-        * plotting shapes: ``"circle"``, ``"square"``, ``"cross"``, ``"diamond"``,
-          ``"triangle-up"``, ``"triangle-down"``, ``"triangle-right"``, or
-          ``"triangle-left"``.
-        * the line symbol ``"stroke"``
-        * centered directional shapes ``"arrow"``, ``"wedge"``, or ``"triangle"``
-        * a custom `SVG path string
-          <https://developer.mozilla.org/en-US/docs/Web/SVG/Tutorial/Paths>`__ (For correct
-          sizing, custom shape paths should be defined within a square bounding box with
-          coordinates ranging from -1 to 1 along both the x and y dimensions.)
-
-        **Default value:** ``"circle"``
-    size : anyOf(float, :class:`ExprRef`)
-        Default size for marks.
-
-
-        * For ``point`` / ``circle`` / ``square``, this represents the pixel area of the
-          marks. Note that this value sets the area of the symbol; the side lengths will
-          increase with the square root of this value.
-        * For ``bar``, this represents the band size of the bar, in pixels.
-        * For ``text``, this represents the font size, in pixels.
-
-        **Default value:**
-
-
-        * ``30`` for point, circle, square marks; width/height's ``step``
-        * ``2`` for bar marks with discrete dimensions;
-        * ``5`` for bar marks with continuous dimensions;
-        * ``11`` for text marks.
-    smooth : anyOf(boolean, :class:`ExprRef`)
-        A boolean flag (default true) indicating if the image should be smoothed when
-        resized. If false, individual pixels should be scaled directly rather than
-        interpolated with smoothing. For SVG rendering, this option may not work in some
-        browsers due to lack of standardization.
-    stroke : anyOf(:class:`Color`, :class:`Gradient`, None, :class:`ExprRef`)
-        Default stroke color. This property has higher precedence than ``config.color``. Set
-        to ``null`` to remove stroke.
-
-        **Default value:** (None)
-    strokeCap : anyOf(:class:`StrokeCap`, :class:`ExprRef`)
-        The stroke cap for line ending style. One of ``"butt"``, ``"round"``, or
-        ``"square"``.
-
-        **Default value:** ``"butt"``
-    strokeDash : anyOf(List(float), :class:`ExprRef`)
-        An array of alternating stroke, space lengths for creating dashed or dotted lines.
-    strokeDashOffset : anyOf(float, :class:`ExprRef`)
-        The offset (in pixels) into which to begin drawing with the stroke dash array.
-    strokeJoin : anyOf(:class:`StrokeJoin`, :class:`ExprRef`)
-        The stroke line join method. One of ``"miter"``, ``"round"`` or ``"bevel"``.
-
-        **Default value:** ``"miter"``
-    strokeMiterLimit : anyOf(float, :class:`ExprRef`)
-        The miter limit at which to bevel a line join.
-    strokeOffset : anyOf(float, :class:`ExprRef`)
-        The offset in pixels at which to draw the group stroke and fill. If unspecified, the
-        default behavior is to dynamically offset stroked groups such that 1 pixel stroke
-        widths align with the pixel grid.
-    strokeOpacity : anyOf(float, :class:`ExprRef`)
-        The stroke opacity (value between [0,1]).
-
-        **Default value:** ``1``
-    strokeWidth : anyOf(float, :class:`ExprRef`)
-        The stroke width, in pixels.
-    style : anyOf(string, List(string))
-        A string or array of strings indicating the name of custom styles to apply to the
-        mark. A style is a named collection of mark property defaults defined within the
-        `style configuration
-        <https://vega.github.io/vega-lite/docs/mark.html#style-config>`__. If style is an
-        array, later styles will override earlier styles. Any `mark properties
-        <https://vega.github.io/vega-lite/docs/encoding.html#mark-prop>`__ explicitly
-        defined within the ``encoding`` will override a style default.
-
-        **Default value:** The mark's name. For example, a bar mark will have style
-        ``"bar"`` by default. **Note:** Any specified style will augment the default style.
-        For example, a bar mark with ``"style": "foo"`` will receive from
-        ``config.style.bar`` and ``config.style.foo`` (the specified style ``"foo"`` has
-        higher precedence).
-    tension : anyOf(float, :class:`ExprRef`)
-        Depending on the interpolation type, sets the tension parameter (for line and area
-        marks).
-    text : anyOf(:class:`Text`, :class:`ExprRef`)
-        Placeholder text if the ``text`` channel is not specified
-    theta : anyOf(float, :class:`ExprRef`)
-        For arc marks, the arc length in radians if theta2 is not specified, otherwise the
-        start arc angle. (A value of 0 indicates up or “north”, increasing values proceed
-        clockwise.)
-
-        For text marks, polar coordinate angle in radians.
-    theta2 : anyOf(float, :class:`ExprRef`)
-        The end angle of arc marks in radians. A value of 0 indicates up or “north”,
-        increasing values proceed clockwise.
-    theta2Offset : anyOf(float, :class:`ExprRef`)
-        Offset for theta2.
-    thetaOffset : anyOf(float, :class:`ExprRef`)
-        Offset for theta.
-    thickness : float
-        Thickness of the tick mark.
-
-        **Default value:**  ``1``
-    timeUnitBandPosition : float
-        Default relative band position for a time unit. If set to ``0``, the marks will be
-        positioned at the beginning of the time unit band step. If set to ``0.5``, the marks
-        will be positioned in the middle of the time unit band step.
-    timeUnitBandSize : float
-        Default relative band size for a time unit. If set to ``1``, the bandwidth of the
-        marks will be equal to the time unit band step. If set to ``0.5``, bandwidth of the
-        marks will be half of the time unit band step.
-    tooltip : anyOf(float, string, boolean, :class:`TooltipContent`, :class:`ExprRef`, None)
-        The tooltip text string to show upon mouse hover or an object defining which fields
-        should the tooltip be derived from.
-
-
-        * If ``tooltip`` is ``true`` or ``{"content": "encoding"}``, then all fields from
-          ``encoding`` will be used.
-        * If ``tooltip`` is ``{"content": "data"}``, then all fields that appear in the
-          highlighted data point will be used.
-        * If set to ``null`` or ``false``, then no tooltip will be used.
-
-        See the `tooltip <https://vega.github.io/vega-lite/docs/tooltip.html>`__
-        documentation for a detailed discussion about tooltip  in Vega-Lite.
-
-        **Default value:** ``null``
-    url : anyOf(:class:`URI`, :class:`ExprRef`)
-        The URL of the image file for image marks.
-    width : anyOf(float, :class:`ExprRef`, :class:`RelativeBandSize`)
-        Width of the marks.  One of:
-
-
-        A number representing a fixed pixel width.
-
-        A relative band size definition.  For example, ``{band: 0.5}`` represents half of
-        the band.
-    x : anyOf(float, string, :class:`ExprRef`)
-        X coordinates of the marks, or width of horizontal ``"bar"`` and ``"area"`` without
-        specified ``x2`` or ``width``.
-
-        The ``value`` of this channel can be a number or a string ``"width"`` for the width
-        of the plot.
-    x2 : anyOf(float, string, :class:`ExprRef`)
-        X2 coordinates for ranged ``"area"``, ``"bar"``, ``"rect"``, and  ``"rule"``.
-
-        The ``value`` of this channel can be a number or a string ``"width"`` for the width
-        of the plot.
-    x2Offset : anyOf(float, :class:`ExprRef`)
-        Offset for x2-position.
-    xOffset : anyOf(float, :class:`ExprRef`)
-        Offset for x-position.
-    y : anyOf(float, string, :class:`ExprRef`)
-        Y coordinates of the marks, or height of vertical ``"bar"`` and ``"area"`` without
-        specified ``y2`` or ``height``.
-
-        The ``value`` of this channel can be a number or a string ``"height"`` for the
-        height of the plot.
-    y2 : anyOf(float, string, :class:`ExprRef`)
-        Y2 coordinates for ranged ``"area"``, ``"bar"``, ``"rect"``, and  ``"rule"``.
-
-        The ``value`` of this channel can be a number or a string ``"height"`` for the
-        height of the plot.
-    y2Offset : anyOf(float, :class:`ExprRef`)
-        Offset for y2-position.
-    yOffset : anyOf(float, :class:`ExprRef`)
-        Offset for y-position.
-    """
-    _schema = {'$ref': '#/definitions/MarkDef'}
-
-    def __init__(self, type=Undefined, align=Undefined, angle=Undefined, aria=Undefined,
-                 ariaRole=Undefined, ariaRoleDescription=Undefined, aspect=Undefined,
-                 bandSize=Undefined, baseline=Undefined, binSpacing=Undefined, blend=Undefined,
-                 clip=Undefined, color=Undefined, continuousBandSize=Undefined, cornerRadius=Undefined,
-                 cornerRadiusBottomLeft=Undefined, cornerRadiusBottomRight=Undefined,
-                 cornerRadiusEnd=Undefined, cornerRadiusTopLeft=Undefined,
-                 cornerRadiusTopRight=Undefined, cursor=Undefined, description=Undefined, dir=Undefined,
-                 discreteBandSize=Undefined, dx=Undefined, dy=Undefined, ellipsis=Undefined,
-                 fill=Undefined, fillOpacity=Undefined, filled=Undefined, font=Undefined,
-                 fontSize=Undefined, fontStyle=Undefined, fontWeight=Undefined, height=Undefined,
-                 href=Undefined, innerRadius=Undefined, interpolate=Undefined, invalid=Undefined,
-                 limit=Undefined, line=Undefined, lineBreak=Undefined, lineHeight=Undefined,
-                 minBandSize=Undefined, opacity=Undefined, order=Undefined, orient=Undefined,
-                 outerRadius=Undefined, padAngle=Undefined, point=Undefined, radius=Undefined,
-                 radius2=Undefined, radius2Offset=Undefined, radiusOffset=Undefined, shape=Undefined,
-                 size=Undefined, smooth=Undefined, stroke=Undefined, strokeCap=Undefined,
-                 strokeDash=Undefined, strokeDashOffset=Undefined, strokeJoin=Undefined,
-                 strokeMiterLimit=Undefined, strokeOffset=Undefined, strokeOpacity=Undefined,
-                 strokeWidth=Undefined, style=Undefined, tension=Undefined, text=Undefined,
-                 theta=Undefined, theta2=Undefined, theta2Offset=Undefined, thetaOffset=Undefined,
-                 thickness=Undefined, timeUnitBandPosition=Undefined, timeUnitBandSize=Undefined,
-                 tooltip=Undefined, url=Undefined, width=Undefined, x=Undefined, x2=Undefined,
-                 x2Offset=Undefined, xOffset=Undefined, y=Undefined, y2=Undefined, y2Offset=Undefined,
-                 yOffset=Undefined, **kwds):
-        super(MarkDef, self).__init__(type=type, align=align, angle=angle, aria=aria, ariaRole=ariaRole,
-                                      ariaRoleDescription=ariaRoleDescription, aspect=aspect,
-                                      bandSize=bandSize, baseline=baseline, binSpacing=binSpacing,
-                                      blend=blend, clip=clip, color=color,
-                                      continuousBandSize=continuousBandSize, cornerRadius=cornerRadius,
-                                      cornerRadiusBottomLeft=cornerRadiusBottomLeft,
-                                      cornerRadiusBottomRight=cornerRadiusBottomRight,
-                                      cornerRadiusEnd=cornerRadiusEnd,
-                                      cornerRadiusTopLeft=cornerRadiusTopLeft,
-                                      cornerRadiusTopRight=cornerRadiusTopRight, cursor=cursor,
-                                      description=description, dir=dir,
-                                      discreteBandSize=discreteBandSize, dx=dx, dy=dy,
-                                      ellipsis=ellipsis, fill=fill, fillOpacity=fillOpacity,
-                                      filled=filled, font=font, fontSize=fontSize, fontStyle=fontStyle,
-                                      fontWeight=fontWeight, height=height, href=href,
-                                      innerRadius=innerRadius, interpolate=interpolate, invalid=invalid,
-                                      limit=limit, line=line, lineBreak=lineBreak,
-                                      lineHeight=lineHeight, minBandSize=minBandSize, opacity=opacity,
-                                      order=order, orient=orient, outerRadius=outerRadius,
-                                      padAngle=padAngle, point=point, radius=radius, radius2=radius2,
-                                      radius2Offset=radius2Offset, radiusOffset=radiusOffset,
-                                      shape=shape, size=size, smooth=smooth, stroke=stroke,
-                                      strokeCap=strokeCap, strokeDash=strokeDash,
-                                      strokeDashOffset=strokeDashOffset, strokeJoin=strokeJoin,
-                                      strokeMiterLimit=strokeMiterLimit, strokeOffset=strokeOffset,
-                                      strokeOpacity=strokeOpacity, strokeWidth=strokeWidth, style=style,
-                                      tension=tension, text=text, theta=theta, theta2=theta2,
-                                      theta2Offset=theta2Offset, thetaOffset=thetaOffset,
-                                      thickness=thickness, timeUnitBandPosition=timeUnitBandPosition,
-                                      timeUnitBandSize=timeUnitBandSize, tooltip=tooltip, url=url,
-                                      width=width, x=x, x2=x2, x2Offset=x2Offset, xOffset=xOffset, y=y,
-                                      y2=y2, y2Offset=y2Offset, yOffset=yOffset, **kwds)
-
-
-class MarkPropDefGradientstringnull(VegaLiteSchema):
-    """MarkPropDefGradientstringnull schema wrapper
-
-    anyOf(:class:`FieldOrDatumDefWithConditionMarkPropFieldDefGradientstringnull`,
-    :class:`FieldOrDatumDefWithConditionDatumDefGradientstringnull`,
-    :class:`ValueDefWithConditionMarkPropFieldOrDatumDefGradientstringnull`)
-    """
-    _schema = {'$ref': '#/definitions/MarkPropDef<(Gradient|string|null)>'}
-
-    def __init__(self, *args, **kwds):
-        super(MarkPropDefGradientstringnull, self).__init__(*args, **kwds)
-
-
-class FieldOrDatumDefWithConditionDatumDefGradientstringnull(ColorDef, MarkPropDefGradientstringnull):
-    """FieldOrDatumDefWithConditionDatumDefGradientstringnull schema wrapper
-
-    Mapping(required=[])
-
-    Parameters
-    ----------
-
-    bandPosition : float
-        Relative position on a band of a stacked, binned, time unit, or band scale. For
-        example, the marks will be positioned at the beginning of the band if set to ``0``,
-        and at the middle of the band if set to ``0.5``.
-    condition : anyOf(:class:`ConditionalValueDefGradientstringnullExprRef`, List(:class:`ConditionalValueDefGradientstringnullExprRef`))
-        One or more value definition(s) with `a parameter or a test predicate
-        <https://vega.github.io/vega-lite/docs/condition.html>`__.
-
-        **Note:** A field definition's ``condition`` property can only contain `conditional
-        value definitions <https://vega.github.io/vega-lite/docs/condition.html#value>`__
-        since Vega-Lite only allows at most one encoded field per encoding channel.
-    datum : anyOf(:class:`PrimitiveValue`, :class:`DateTime`, :class:`ExprRef`, :class:`RepeatRef`)
-        A constant value in data domain.
-    title : anyOf(:class:`Text`, None)
-        A title for the field. If ``null``, the title will be removed.
-
-        **Default value:**  derived from the field's name and transformation function (
-        ``aggregate``, ``bin`` and ``timeUnit`` ). If the field has an aggregate function,
-        the function is displayed as part of the title (e.g., ``"Sum of Profit"`` ). If the
-        field is binned or has a time unit applied, the applied function is shown in
-        parentheses (e.g., ``"Profit (binned)"``, ``"Transaction Date (year-month)"`` ).
-        Otherwise, the title is simply the field name.
-
-        **Notes** :
-
-        1) You can customize the default field title format by providing the `fieldTitle
-        <https://vega.github.io/vega-lite/docs/config.html#top-level-config>`__ property in
-        the `config <https://vega.github.io/vega-lite/docs/config.html>`__ or `fieldTitle
-        function via the compile function's options
-        <https://vega.github.io/vega-lite/usage/compile.html#field-title>`__.
-
-        2) If both field definition's ``title`` and axis, header, or legend ``title`` are
-        defined, axis/header/legend title will be used.
-    type : :class:`Type`
-        The type of measurement ( ``"quantitative"``, ``"temporal"``, ``"ordinal"``, or
-        ``"nominal"`` ) for the encoded field or constant value ( ``datum`` ). It can also
-        be a ``"geojson"`` type for encoding `'geoshape'
-        <https://vega.github.io/vega-lite/docs/geoshape.html>`__.
-
-        Vega-Lite automatically infers data types in many cases as discussed below. However,
-        type is required for a field if: (1) the field is not nominal and the field encoding
-        has no specified ``aggregate`` (except ``argmin`` and ``argmax`` ), ``bin``, scale
-        type, custom ``sort`` order, nor ``timeUnit`` or (2) if you wish to use an ordinal
-        scale for a field with ``bin`` or ``timeUnit``.
-
-        **Default value:**
-
-        1) For a data ``field``, ``"nominal"`` is the default data type unless the field
-        encoding has ``aggregate``, ``channel``, ``bin``, scale type, ``sort``, or
-        ``timeUnit`` that satisfies the following criteria:
-
-
-        * ``"quantitative"`` is the default type if (1) the encoded field contains ``bin``
-          or ``aggregate`` except ``"argmin"`` and ``"argmax"``, (2) the encoding channel is
-          ``latitude`` or ``longitude`` channel or (3) if the specified scale type is `a
-          quantitative scale <https://vega.github.io/vega-lite/docs/scale.html#type>`__.
-        * ``"temporal"`` is the default type if (1) the encoded field contains ``timeUnit``
-          or (2) the specified scale type is a time or utc scale
-        * ``"ordinal"`` is the default type if (1) the encoded field contains a `custom sort
-          order
-          <https://vega.github.io/vega-lite/docs/sort.html#specifying-custom-sort-order>`__,
-          (2) the specified scale type is an ordinal/point/band scale, or (3) the encoding
-          channel is ``order``.
-
-        2) For a constant value in data domain ( ``datum`` ):
-
-
-        * ``"quantitative"`` if the datum is a number
-        * ``"nominal"`` if the datum is a string
-        * ``"temporal"`` if the datum is `a date time object
-          <https://vega.github.io/vega-lite/docs/datetime.html>`__
-
-        **Note:**
-
-
-        * Data ``type`` describes the semantics of the data rather than the primitive data
-          types (number, string, etc.). The same primitive data type can have different
-          types of measurement. For example, numeric data can represent quantitative,
-          ordinal, or nominal data.
-        * Data values for a temporal field can be either a date-time string (e.g.,
-          ``"2015-03-07 12:32:17"``, ``"17:01"``, ``"2015-03-16"``. ``"2015"`` ) or a
-          timestamp number (e.g., ``1552199579097`` ).
-        * When using with `bin <https://vega.github.io/vega-lite/docs/bin.html>`__, the
-          ``type`` property can be either ``"quantitative"`` (for using a linear bin scale)
-          or `"ordinal" (for using an ordinal bin scale)
-          <https://vega.github.io/vega-lite/docs/type.html#cast-bin>`__.
-        * When using with `timeUnit
-          <https://vega.github.io/vega-lite/docs/timeunit.html>`__, the ``type`` property
-          can be either ``"temporal"`` (default, for using a temporal scale) or `"ordinal"
-          (for using an ordinal scale)
-          <https://vega.github.io/vega-lite/docs/type.html#cast-bin>`__.
-        * When using with `aggregate
-          <https://vega.github.io/vega-lite/docs/aggregate.html>`__, the ``type`` property
-          refers to the post-aggregation data type. For example, we can calculate count
-          ``distinct`` of a categorical field ``"cat"`` using ``{"aggregate": "distinct",
-          "field": "cat"}``. The ``"type"`` of the aggregate output is ``"quantitative"``.
-        * Secondary channels (e.g., ``x2``, ``y2``, ``xError``, ``yError`` ) do not have
-          ``type`` as they must have exactly the same type as their primary channels (e.g.,
-          ``x``, ``y`` ).
-
-        **See also:** `type <https://vega.github.io/vega-lite/docs/type.html>`__
-        documentation.
-    """
-    _schema = {'$ref': '#/definitions/FieldOrDatumDefWithCondition<DatumDef,(Gradient|string|null)>'}
-
-    def __init__(self, bandPosition=Undefined, condition=Undefined, datum=Undefined, title=Undefined,
-                 type=Undefined, **kwds):
-        super(FieldOrDatumDefWithConditionDatumDefGradientstringnull, self).__init__(bandPosition=bandPosition,
-                                                                                     condition=condition,
-                                                                                     datum=datum,
-                                                                                     title=title,
-                                                                                     type=type, **kwds)
-
-
-class FieldOrDatumDefWithConditionMarkPropFieldDefGradientstringnull(ColorDef, MarkPropDefGradientstringnull):
-    """FieldOrDatumDefWithConditionMarkPropFieldDefGradientstringnull schema wrapper
-
-    Mapping(required=[])
-
-    Parameters
-    ----------
-
-    aggregate : :class:`Aggregate`
-        Aggregation function for the field (e.g., ``"mean"``, ``"sum"``, ``"median"``,
-        ``"min"``, ``"max"``, ``"count"`` ).
-
-        **Default value:** ``undefined`` (None)
-
-        **See also:** `aggregate <https://vega.github.io/vega-lite/docs/aggregate.html>`__
-        documentation.
-    bandPosition : float
-        Relative position on a band of a stacked, binned, time unit, or band scale. For
-        example, the marks will be positioned at the beginning of the band if set to ``0``,
-        and at the middle of the band if set to ``0.5``.
-    bin : anyOf(boolean, :class:`BinParams`, None)
-        A flag for binning a ``quantitative`` field, `an object defining binning parameters
-        <https://vega.github.io/vega-lite/docs/bin.html#bin-parameters>`__, or indicating
-        that the data for ``x`` or ``y`` channel are binned before they are imported into
-        Vega-Lite ( ``"binned"`` ).
-
-
-        If ``true``, default `binning parameters
-        <https://vega.github.io/vega-lite/docs/bin.html#bin-parameters>`__ will be applied.
-
-        If ``"binned"``, this indicates that the data for the ``x`` (or ``y`` ) channel are
-        already binned. You can map the bin-start field to ``x`` (or ``y`` ) and the bin-end
-        field to ``x2`` (or ``y2`` ). The scale and axis will be formatted similar to
-        binning in Vega-Lite.  To adjust the axis ticks based on the bin step, you can also
-        set the axis's `tickMinStep
-        <https://vega.github.io/vega-lite/docs/axis.html#ticks>`__ property.
-
-        **Default value:** ``false``
-
-        **See also:** `bin <https://vega.github.io/vega-lite/docs/bin.html>`__
-        documentation.
-    condition : anyOf(:class:`ConditionalValueDefGradientstringnullExprRef`, List(:class:`ConditionalValueDefGradientstringnullExprRef`))
-        One or more value definition(s) with `a parameter or a test predicate
-        <https://vega.github.io/vega-lite/docs/condition.html>`__.
-
-        **Note:** A field definition's ``condition`` property can only contain `conditional
-        value definitions <https://vega.github.io/vega-lite/docs/condition.html#value>`__
-        since Vega-Lite only allows at most one encoded field per encoding channel.
-    field : :class:`Field`
-        **Required.** A string defining the name of the field from which to pull a data
-        value or an object defining iterated values from the `repeat
-        <https://vega.github.io/vega-lite/docs/repeat.html>`__ operator.
-
-        **See also:** `field <https://vega.github.io/vega-lite/docs/field.html>`__
-        documentation.
-
-        **Notes:** 1)  Dots ( ``.`` ) and brackets ( ``[`` and ``]`` ) can be used to access
-        nested objects (e.g., ``"field": "foo.bar"`` and ``"field": "foo['bar']"`` ). If
-        field names contain dots or brackets but are not nested, you can use ``\\`` to
-        escape dots and brackets (e.g., ``"a\\.b"`` and ``"a\\[0\\]"`` ). See more details
-        about escaping in the `field documentation
-        <https://vega.github.io/vega-lite/docs/field.html>`__. 2) ``field`` is not required
-        if ``aggregate`` is ``count``.
-    legend : anyOf(:class:`Legend`, None)
-        An object defining properties of the legend. If ``null``, the legend for the
-        encoding channel will be removed.
-
-        **Default value:** If undefined, default `legend properties
-        <https://vega.github.io/vega-lite/docs/legend.html>`__ are applied.
-
-        **See also:** `legend <https://vega.github.io/vega-lite/docs/legend.html>`__
-        documentation.
-    scale : anyOf(:class:`Scale`, None)
-        An object defining properties of the channel's scale, which is the function that
-        transforms values in the data domain (numbers, dates, strings, etc) to visual values
-        (pixels, colors, sizes) of the encoding channels.
-
-        If ``null``, the scale will be `disabled and the data value will be directly encoded
-        <https://vega.github.io/vega-lite/docs/scale.html#disable>`__.
-
-        **Default value:** If undefined, default `scale properties
-        <https://vega.github.io/vega-lite/docs/scale.html>`__ are applied.
-
-        **See also:** `scale <https://vega.github.io/vega-lite/docs/scale.html>`__
-        documentation.
-    sort : :class:`Sort`
-        Sort order for the encoded field.
-
-        For continuous fields (quantitative or temporal), ``sort`` can be either
-        ``"ascending"`` or ``"descending"``.
-
-        For discrete fields, ``sort`` can be one of the following:
-
-
-        * ``"ascending"`` or ``"descending"`` -- for sorting by the values' natural order in
-          JavaScript.
-        * `A string indicating an encoding channel name to sort by
-          <https://vega.github.io/vega-lite/docs/sort.html#sort-by-encoding>`__ (e.g.,
-          ``"x"`` or ``"y"`` ) with an optional minus prefix for descending sort (e.g.,
-          ``"-x"`` to sort by x-field, descending). This channel string is short-form of `a
-          sort-by-encoding definition
-          <https://vega.github.io/vega-lite/docs/sort.html#sort-by-encoding>`__. For
-          example, ``"sort": "-x"`` is equivalent to ``"sort": {"encoding": "x", "order":
-          "descending"}``.
-        * `A sort field definition
-          <https://vega.github.io/vega-lite/docs/sort.html#sort-field>`__ for sorting by
-          another field.
-        * `An array specifying the field values in preferred order
-          <https://vega.github.io/vega-lite/docs/sort.html#sort-array>`__. In this case, the
-          sort order will obey the values in the array, followed by any unspecified values
-          in their original order. For discrete time field, values in the sort array can be
-          `date-time definition objects
-          <https://vega.github.io/vega-lite/docs/datetime.html>`__. In addition, for time
-          units ``"month"`` and ``"day"``, the values can be the month or day names (case
-          insensitive) or their 3-letter initials (e.g., ``"Mon"``, ``"Tue"`` ).
-        * ``null`` indicating no sort.
-
-        **Default value:** ``"ascending"``
-
-        **Note:** ``null`` and sorting by another channel is not supported for ``row`` and
-        ``column``.
-
-        **See also:** `sort <https://vega.github.io/vega-lite/docs/sort.html>`__
-        documentation.
-    timeUnit : anyOf(:class:`TimeUnit`, :class:`BinnedTimeUnit`, :class:`TimeUnitParams`)
-        Time unit (e.g., ``year``, ``yearmonth``, ``month``, ``hours`` ) for a temporal
-        field. or `a temporal field that gets casted as ordinal
-        <https://vega.github.io/vega-lite/docs/type.html#cast>`__.
-
-        **Default value:** ``undefined`` (None)
-
-        **See also:** `timeUnit <https://vega.github.io/vega-lite/docs/timeunit.html>`__
-        documentation.
-    title : anyOf(:class:`Text`, None)
-        A title for the field. If ``null``, the title will be removed.
-
-        **Default value:**  derived from the field's name and transformation function (
-        ``aggregate``, ``bin`` and ``timeUnit`` ). If the field has an aggregate function,
-        the function is displayed as part of the title (e.g., ``"Sum of Profit"`` ). If the
-        field is binned or has a time unit applied, the applied function is shown in
-        parentheses (e.g., ``"Profit (binned)"``, ``"Transaction Date (year-month)"`` ).
-        Otherwise, the title is simply the field name.
-
-        **Notes** :
-
-        1) You can customize the default field title format by providing the `fieldTitle
-        <https://vega.github.io/vega-lite/docs/config.html#top-level-config>`__ property in
-        the `config <https://vega.github.io/vega-lite/docs/config.html>`__ or `fieldTitle
-        function via the compile function's options
-        <https://vega.github.io/vega-lite/usage/compile.html#field-title>`__.
-
-        2) If both field definition's ``title`` and axis, header, or legend ``title`` are
-        defined, axis/header/legend title will be used.
-    type : :class:`StandardType`
-        The type of measurement ( ``"quantitative"``, ``"temporal"``, ``"ordinal"``, or
-        ``"nominal"`` ) for the encoded field or constant value ( ``datum`` ). It can also
-        be a ``"geojson"`` type for encoding `'geoshape'
-        <https://vega.github.io/vega-lite/docs/geoshape.html>`__.
-
-        Vega-Lite automatically infers data types in many cases as discussed below. However,
-        type is required for a field if: (1) the field is not nominal and the field encoding
-        has no specified ``aggregate`` (except ``argmin`` and ``argmax`` ), ``bin``, scale
-        type, custom ``sort`` order, nor ``timeUnit`` or (2) if you wish to use an ordinal
-        scale for a field with ``bin`` or ``timeUnit``.
-
-        **Default value:**
-
-        1) For a data ``field``, ``"nominal"`` is the default data type unless the field
-        encoding has ``aggregate``, ``channel``, ``bin``, scale type, ``sort``, or
-        ``timeUnit`` that satisfies the following criteria:
-
-
-        * ``"quantitative"`` is the default type if (1) the encoded field contains ``bin``
-          or ``aggregate`` except ``"argmin"`` and ``"argmax"``, (2) the encoding channel is
-          ``latitude`` or ``longitude`` channel or (3) if the specified scale type is `a
-          quantitative scale <https://vega.github.io/vega-lite/docs/scale.html#type>`__.
-        * ``"temporal"`` is the default type if (1) the encoded field contains ``timeUnit``
-          or (2) the specified scale type is a time or utc scale
-        * ``"ordinal"`` is the default type if (1) the encoded field contains a `custom sort
-          order
-          <https://vega.github.io/vega-lite/docs/sort.html#specifying-custom-sort-order>`__,
-          (2) the specified scale type is an ordinal/point/band scale, or (3) the encoding
-          channel is ``order``.
-
-        2) For a constant value in data domain ( ``datum`` ):
-
-
-        * ``"quantitative"`` if the datum is a number
-        * ``"nominal"`` if the datum is a string
-        * ``"temporal"`` if the datum is `a date time object
-          <https://vega.github.io/vega-lite/docs/datetime.html>`__
-
-        **Note:**
-
-
-        * Data ``type`` describes the semantics of the data rather than the primitive data
-          types (number, string, etc.). The same primitive data type can have different
-          types of measurement. For example, numeric data can represent quantitative,
-          ordinal, or nominal data.
-        * Data values for a temporal field can be either a date-time string (e.g.,
-          ``"2015-03-07 12:32:17"``, ``"17:01"``, ``"2015-03-16"``. ``"2015"`` ) or a
-          timestamp number (e.g., ``1552199579097`` ).
-        * When using with `bin <https://vega.github.io/vega-lite/docs/bin.html>`__, the
-          ``type`` property can be either ``"quantitative"`` (for using a linear bin scale)
-          or `"ordinal" (for using an ordinal bin scale)
-          <https://vega.github.io/vega-lite/docs/type.html#cast-bin>`__.
-        * When using with `timeUnit
-          <https://vega.github.io/vega-lite/docs/timeunit.html>`__, the ``type`` property
-          can be either ``"temporal"`` (default, for using a temporal scale) or `"ordinal"
-          (for using an ordinal scale)
-          <https://vega.github.io/vega-lite/docs/type.html#cast-bin>`__.
-        * When using with `aggregate
-          <https://vega.github.io/vega-lite/docs/aggregate.html>`__, the ``type`` property
-          refers to the post-aggregation data type. For example, we can calculate count
-          ``distinct`` of a categorical field ``"cat"`` using ``{"aggregate": "distinct",
-          "field": "cat"}``. The ``"type"`` of the aggregate output is ``"quantitative"``.
-        * Secondary channels (e.g., ``x2``, ``y2``, ``xError``, ``yError`` ) do not have
-          ``type`` as they must have exactly the same type as their primary channels (e.g.,
-          ``x``, ``y`` ).
-
-        **See also:** `type <https://vega.github.io/vega-lite/docs/type.html>`__
-        documentation.
-    """
-    _schema = {'$ref': '#/definitions/FieldOrDatumDefWithCondition<MarkPropFieldDef,(Gradient|string|null)>'}
-
-    def __init__(self, aggregate=Undefined, bandPosition=Undefined, bin=Undefined, condition=Undefined,
-                 field=Undefined, legend=Undefined, scale=Undefined, sort=Undefined, timeUnit=Undefined,
-                 title=Undefined, type=Undefined, **kwds):
-        super(FieldOrDatumDefWithConditionMarkPropFieldDefGradientstringnull, self).__init__(aggregate=aggregate,
-                                                                                             bandPosition=bandPosition,
-                                                                                             bin=bin,
-                                                                                             condition=condition,
-                                                                                             field=field,
-                                                                                             legend=legend,
-                                                                                             scale=scale,
-                                                                                             sort=sort,
-                                                                                             timeUnit=timeUnit,
-                                                                                             title=title,
-                                                                                             type=type,
-                                                                                             **kwds)
-
-
-class MarkPropDefnumber(VegaLiteSchema):
-    """MarkPropDefnumber schema wrapper
-
-    anyOf(:class:`FieldOrDatumDefWithConditionMarkPropFieldDefnumber`,
-    :class:`FieldOrDatumDefWithConditionDatumDefnumber`,
-    :class:`ValueDefWithConditionMarkPropFieldOrDatumDefnumber`)
-    """
-    _schema = {'$ref': '#/definitions/MarkPropDef<number>'}
-
-    def __init__(self, *args, **kwds):
-        super(MarkPropDefnumber, self).__init__(*args, **kwds)
-
-
-class MarkPropDefnumberArray(VegaLiteSchema):
-    """MarkPropDefnumberArray schema wrapper
-
-    anyOf(:class:`FieldOrDatumDefWithConditionMarkPropFieldDefnumberArray`,
-    :class:`FieldOrDatumDefWithConditionDatumDefnumberArray`,
-    :class:`ValueDefWithConditionMarkPropFieldOrDatumDefnumberArray`)
-    """
-    _schema = {'$ref': '#/definitions/MarkPropDef<number[]>'}
-
-    def __init__(self, *args, **kwds):
-        super(MarkPropDefnumberArray, self).__init__(*args, **kwds)
-
-
-class MarkPropDefstringnullTypeForShape(VegaLiteSchema):
-    """MarkPropDefstringnullTypeForShape schema wrapper
-
-    anyOf(:class:`FieldOrDatumDefWithConditionMarkPropFieldDefTypeForShapestringnull`,
-    :class:`FieldOrDatumDefWithConditionDatumDefstringnull`,
-    :class:`ValueDefWithConditionMarkPropFieldOrDatumDefTypeForShapestringnull`)
-    """
-    _schema = {'$ref': '#/definitions/MarkPropDef<(string|null),TypeForShape>'}
-
-    def __init__(self, *args, **kwds):
-        super(MarkPropDefstringnullTypeForShape, self).__init__(*args, **kwds)
-
-
-class MarkType(VegaLiteSchema):
-    """MarkType schema wrapper
-
-    enum('arc', 'area', 'image', 'group', 'line', 'path', 'rect', 'rule', 'shape', 'symbol',
-    'text', 'trail')
-    """
-    _schema = {'$ref': '#/definitions/MarkType'}
-
-    def __init__(self, *args):
-        super(MarkType, self).__init__(*args)
-
-
-class Month(VegaLiteSchema):
-    """Month schema wrapper
-
-    float
-    """
-    _schema = {'$ref': '#/definitions/Month'}
-
-    def __init__(self, *args):
-        super(Month, self).__init__(*args)
-
-
-class MultiLineString(Geometry):
-    """MultiLineString schema wrapper
-
-    Mapping(required=[coordinates, type])
-    MultiLineString geometry object. https://tools.ietf.org/html/rfc7946#section-3.1.5
-
-    Parameters
-    ----------
-
-    coordinates : List(List(:class:`Position`))
-
-    type : string
-        Specifies the type of GeoJSON object.
-    bbox : :class:`BBox`
-        Bounding box of the coordinate range of the object's Geometries, Features, or
-        Feature Collections. https://tools.ietf.org/html/rfc7946#section-5
-    """
-    _schema = {'$ref': '#/definitions/MultiLineString'}
-
-    def __init__(self, coordinates=Undefined, type=Undefined, bbox=Undefined, **kwds):
-        super(MultiLineString, self).__init__(coordinates=coordinates, type=type, bbox=bbox, **kwds)
-
-
-class MultiPoint(Geometry):
-    """MultiPoint schema wrapper
-
-    Mapping(required=[coordinates, type])
-    MultiPoint geometry object.  https://tools.ietf.org/html/rfc7946#section-3.1.3
-
-    Parameters
-    ----------
-
-    coordinates : List(:class:`Position`)
-
-    type : string
-        Specifies the type of GeoJSON object.
-    bbox : :class:`BBox`
-        Bounding box of the coordinate range of the object's Geometries, Features, or
-        Feature Collections. https://tools.ietf.org/html/rfc7946#section-5
-    """
-    _schema = {'$ref': '#/definitions/MultiPoint'}
-
-    def __init__(self, coordinates=Undefined, type=Undefined, bbox=Undefined, **kwds):
-        super(MultiPoint, self).__init__(coordinates=coordinates, type=type, bbox=bbox, **kwds)
-
-
-class MultiPolygon(Geometry):
-    """MultiPolygon schema wrapper
-
-    Mapping(required=[coordinates, type])
-    MultiPolygon geometry object. https://tools.ietf.org/html/rfc7946#section-3.1.7
-
-    Parameters
-    ----------
-
-    coordinates : List(List(List(:class:`Position`)))
-
-    type : string
-        Specifies the type of GeoJSON object.
-    bbox : :class:`BBox`
-        Bounding box of the coordinate range of the object's Geometries, Features, or
-        Feature Collections. https://tools.ietf.org/html/rfc7946#section-5
-    """
-    _schema = {'$ref': '#/definitions/MultiPolygon'}
-
-    def __init__(self, coordinates=Undefined, type=Undefined, bbox=Undefined, **kwds):
-        super(MultiPolygon, self).__init__(coordinates=coordinates, type=type, bbox=bbox, **kwds)
-
-
-class NamedData(DataSource):
-    """NamedData schema wrapper
-
-    Mapping(required=[name])
-
-    Parameters
-    ----------
-
-    name : string
-        Provide a placeholder name and bind data at runtime.
-
-        New data may change the layout but Vega does not always resize the chart. To update
-        the layout when the data updates, set `autosize
-        <https://vega.github.io/vega-lite/docs/size.html#autosize>`__ or explicitly use
-        `view.resize <https://vega.github.io/vega/docs/api/view/#view_resize>`__.
-    format : :class:`DataFormat`
-        An object that specifies the format for parsing the data.
-    """
-    _schema = {'$ref': '#/definitions/NamedData'}
-
-    def __init__(self, name=Undefined, format=Undefined, **kwds):
-        super(NamedData, self).__init__(name=name, format=format, **kwds)
-
-
-class NonArgAggregateOp(Aggregate):
-    """NonArgAggregateOp schema wrapper
-
-    enum('average', 'count', 'distinct', 'max', 'mean', 'median', 'min', 'missing', 'product',
-    'q1', 'q3', 'ci0', 'ci1', 'stderr', 'stdev', 'stdevp', 'sum', 'valid', 'values', 'variance',
-    'variancep')
-    """
-    _schema = {'$ref': '#/definitions/NonArgAggregateOp'}
-
-    def __init__(self, *args):
-        super(NonArgAggregateOp, self).__init__(*args)
-
-
-class NonNormalizedSpec(VegaLiteSchema):
-    """NonNormalizedSpec schema wrapper
-
-    anyOf(:class:`FacetedUnitSpec`, :class:`LayerSpec`, :class:`RepeatSpec`, :class:`FacetSpec`,
-    :class:`ConcatSpecGenericSpec`, :class:`VConcatSpecGenericSpec`,
-    :class:`HConcatSpecGenericSpec`)
-    Any specification in Vega-Lite.
-    """
-    _schema = {'$ref': '#/definitions/NonNormalizedSpec'}
-
-    def __init__(self, *args, **kwds):
-        super(NonNormalizedSpec, self).__init__(*args, **kwds)
-
-
-class NumberLocale(VegaLiteSchema):
-    """NumberLocale schema wrapper
-
-    Mapping(required=[decimal, thousands, grouping, currency])
-    Locale definition for formatting numbers.
-
-    Parameters
-    ----------
-
-    currency : :class:`Vector2string`
-        The currency prefix and suffix (e.g., ["$", ""]).
-    decimal : string
-        The decimal point (e.g., ".").
-    grouping : List(float)
-        The array of group sizes (e.g., [3]), cycled as needed.
-    thousands : string
-        The group separator (e.g., ",").
-    minus : string
-        The minus sign (defaults to hyphen-minus, "-").
-    nan : string
-        The not-a-number value (defaults to "NaN").
-    numerals : :class:`Vector10string`
-        An array of ten strings to replace the numerals 0-9.
-    percent : string
-        The percent sign (defaults to "%").
-    """
-    _schema = {'$ref': '#/definitions/NumberLocale'}
-
-    def __init__(self, currency=Undefined, decimal=Undefined, grouping=Undefined, thousands=Undefined,
-                 minus=Undefined, nan=Undefined, numerals=Undefined, percent=Undefined, **kwds):
-        super(NumberLocale, self).__init__(currency=currency, decimal=decimal, grouping=grouping,
-                                           thousands=thousands, minus=minus, nan=nan, numerals=numerals,
-                                           percent=percent, **kwds)
-
-
-class NumericArrayMarkPropDef(VegaLiteSchema):
-    """NumericArrayMarkPropDef schema wrapper
-
-    anyOf(:class:`FieldOrDatumDefWithConditionMarkPropFieldDefnumberArray`,
-    :class:`FieldOrDatumDefWithConditionDatumDefnumberArray`,
-    :class:`ValueDefWithConditionMarkPropFieldOrDatumDefnumberArray`)
-    """
-    _schema = {'$ref': '#/definitions/NumericArrayMarkPropDef'}
-
-    def __init__(self, *args, **kwds):
-        super(NumericArrayMarkPropDef, self).__init__(*args, **kwds)
-
-
-class FieldOrDatumDefWithConditionDatumDefnumberArray(MarkPropDefnumberArray, NumericArrayMarkPropDef):
-    """FieldOrDatumDefWithConditionDatumDefnumberArray schema wrapper
-
-    Mapping(required=[])
-
-    Parameters
-    ----------
-
-    bandPosition : float
-        Relative position on a band of a stacked, binned, time unit, or band scale. For
-        example, the marks will be positioned at the beginning of the band if set to ``0``,
-        and at the middle of the band if set to ``0.5``.
-    condition : anyOf(:class:`ConditionalValueDefnumberArrayExprRef`, List(:class:`ConditionalValueDefnumberArrayExprRef`))
-        One or more value definition(s) with `a parameter or a test predicate
-        <https://vega.github.io/vega-lite/docs/condition.html>`__.
-
-        **Note:** A field definition's ``condition`` property can only contain `conditional
-        value definitions <https://vega.github.io/vega-lite/docs/condition.html#value>`__
-        since Vega-Lite only allows at most one encoded field per encoding channel.
-    datum : anyOf(:class:`PrimitiveValue`, :class:`DateTime`, :class:`ExprRef`, :class:`RepeatRef`)
-        A constant value in data domain.
-    title : anyOf(:class:`Text`, None)
-        A title for the field. If ``null``, the title will be removed.
-
-        **Default value:**  derived from the field's name and transformation function (
-        ``aggregate``, ``bin`` and ``timeUnit`` ). If the field has an aggregate function,
-        the function is displayed as part of the title (e.g., ``"Sum of Profit"`` ). If the
-        field is binned or has a time unit applied, the applied function is shown in
-        parentheses (e.g., ``"Profit (binned)"``, ``"Transaction Date (year-month)"`` ).
-        Otherwise, the title is simply the field name.
-
-        **Notes** :
-
-        1) You can customize the default field title format by providing the `fieldTitle
-        <https://vega.github.io/vega-lite/docs/config.html#top-level-config>`__ property in
-        the `config <https://vega.github.io/vega-lite/docs/config.html>`__ or `fieldTitle
-        function via the compile function's options
-        <https://vega.github.io/vega-lite/usage/compile.html#field-title>`__.
-
-        2) If both field definition's ``title`` and axis, header, or legend ``title`` are
-        defined, axis/header/legend title will be used.
-    type : :class:`Type`
-        The type of measurement ( ``"quantitative"``, ``"temporal"``, ``"ordinal"``, or
-        ``"nominal"`` ) for the encoded field or constant value ( ``datum`` ). It can also
-        be a ``"geojson"`` type for encoding `'geoshape'
-        <https://vega.github.io/vega-lite/docs/geoshape.html>`__.
-
-        Vega-Lite automatically infers data types in many cases as discussed below. However,
-        type is required for a field if: (1) the field is not nominal and the field encoding
-        has no specified ``aggregate`` (except ``argmin`` and ``argmax`` ), ``bin``, scale
-        type, custom ``sort`` order, nor ``timeUnit`` or (2) if you wish to use an ordinal
-        scale for a field with ``bin`` or ``timeUnit``.
-
-        **Default value:**
-
-        1) For a data ``field``, ``"nominal"`` is the default data type unless the field
-        encoding has ``aggregate``, ``channel``, ``bin``, scale type, ``sort``, or
-        ``timeUnit`` that satisfies the following criteria:
-
-
-        * ``"quantitative"`` is the default type if (1) the encoded field contains ``bin``
-          or ``aggregate`` except ``"argmin"`` and ``"argmax"``, (2) the encoding channel is
-          ``latitude`` or ``longitude`` channel or (3) if the specified scale type is `a
-          quantitative scale <https://vega.github.io/vega-lite/docs/scale.html#type>`__.
-        * ``"temporal"`` is the default type if (1) the encoded field contains ``timeUnit``
-          or (2) the specified scale type is a time or utc scale
-        * ``"ordinal"`` is the default type if (1) the encoded field contains a `custom sort
-          order
-          <https://vega.github.io/vega-lite/docs/sort.html#specifying-custom-sort-order>`__,
-          (2) the specified scale type is an ordinal/point/band scale, or (3) the encoding
-          channel is ``order``.
-
-        2) For a constant value in data domain ( ``datum`` ):
-
-
-        * ``"quantitative"`` if the datum is a number
-        * ``"nominal"`` if the datum is a string
-        * ``"temporal"`` if the datum is `a date time object
-          <https://vega.github.io/vega-lite/docs/datetime.html>`__
-
-        **Note:**
-
-
-        * Data ``type`` describes the semantics of the data rather than the primitive data
-          types (number, string, etc.). The same primitive data type can have different
-          types of measurement. For example, numeric data can represent quantitative,
-          ordinal, or nominal data.
-        * Data values for a temporal field can be either a date-time string (e.g.,
-          ``"2015-03-07 12:32:17"``, ``"17:01"``, ``"2015-03-16"``. ``"2015"`` ) or a
-          timestamp number (e.g., ``1552199579097`` ).
-        * When using with `bin <https://vega.github.io/vega-lite/docs/bin.html>`__, the
-          ``type`` property can be either ``"quantitative"`` (for using a linear bin scale)
-          or `"ordinal" (for using an ordinal bin scale)
-          <https://vega.github.io/vega-lite/docs/type.html#cast-bin>`__.
-        * When using with `timeUnit
-          <https://vega.github.io/vega-lite/docs/timeunit.html>`__, the ``type`` property
-          can be either ``"temporal"`` (default, for using a temporal scale) or `"ordinal"
-          (for using an ordinal scale)
-          <https://vega.github.io/vega-lite/docs/type.html#cast-bin>`__.
-        * When using with `aggregate
-          <https://vega.github.io/vega-lite/docs/aggregate.html>`__, the ``type`` property
-          refers to the post-aggregation data type. For example, we can calculate count
-          ``distinct`` of a categorical field ``"cat"`` using ``{"aggregate": "distinct",
-          "field": "cat"}``. The ``"type"`` of the aggregate output is ``"quantitative"``.
-        * Secondary channels (e.g., ``x2``, ``y2``, ``xError``, ``yError`` ) do not have
-          ``type`` as they must have exactly the same type as their primary channels (e.g.,
-          ``x``, ``y`` ).
-
-        **See also:** `type <https://vega.github.io/vega-lite/docs/type.html>`__
-        documentation.
-    """
-    _schema = {'$ref': '#/definitions/FieldOrDatumDefWithCondition<DatumDef,number[]>'}
-
-    def __init__(self, bandPosition=Undefined, condition=Undefined, datum=Undefined, title=Undefined,
-                 type=Undefined, **kwds):
-        super(FieldOrDatumDefWithConditionDatumDefnumberArray, self).__init__(bandPosition=bandPosition,
-                                                                              condition=condition,
-                                                                              datum=datum, title=title,
-                                                                              type=type, **kwds)
-
-
-class FieldOrDatumDefWithConditionMarkPropFieldDefnumberArray(MarkPropDefnumberArray, NumericArrayMarkPropDef):
-    """FieldOrDatumDefWithConditionMarkPropFieldDefnumberArray schema wrapper
-
-    Mapping(required=[])
-
-    Parameters
-    ----------
-
-    aggregate : :class:`Aggregate`
-        Aggregation function for the field (e.g., ``"mean"``, ``"sum"``, ``"median"``,
-        ``"min"``, ``"max"``, ``"count"`` ).
-
-        **Default value:** ``undefined`` (None)
-
-        **See also:** `aggregate <https://vega.github.io/vega-lite/docs/aggregate.html>`__
-        documentation.
-    bandPosition : float
-        Relative position on a band of a stacked, binned, time unit, or band scale. For
-        example, the marks will be positioned at the beginning of the band if set to ``0``,
-        and at the middle of the band if set to ``0.5``.
-    bin : anyOf(boolean, :class:`BinParams`, None)
-        A flag for binning a ``quantitative`` field, `an object defining binning parameters
-        <https://vega.github.io/vega-lite/docs/bin.html#bin-parameters>`__, or indicating
-        that the data for ``x`` or ``y`` channel are binned before they are imported into
-        Vega-Lite ( ``"binned"`` ).
-
-
-        If ``true``, default `binning parameters
-        <https://vega.github.io/vega-lite/docs/bin.html#bin-parameters>`__ will be applied.
-
-        If ``"binned"``, this indicates that the data for the ``x`` (or ``y`` ) channel are
-        already binned. You can map the bin-start field to ``x`` (or ``y`` ) and the bin-end
-        field to ``x2`` (or ``y2`` ). The scale and axis will be formatted similar to
-        binning in Vega-Lite.  To adjust the axis ticks based on the bin step, you can also
-        set the axis's `tickMinStep
-        <https://vega.github.io/vega-lite/docs/axis.html#ticks>`__ property.
-
-        **Default value:** ``false``
-
-        **See also:** `bin <https://vega.github.io/vega-lite/docs/bin.html>`__
-        documentation.
-    condition : anyOf(:class:`ConditionalValueDefnumberArrayExprRef`, List(:class:`ConditionalValueDefnumberArrayExprRef`))
-        One or more value definition(s) with `a parameter or a test predicate
-        <https://vega.github.io/vega-lite/docs/condition.html>`__.
-
-        **Note:** A field definition's ``condition`` property can only contain `conditional
-        value definitions <https://vega.github.io/vega-lite/docs/condition.html#value>`__
-        since Vega-Lite only allows at most one encoded field per encoding channel.
-    field : :class:`Field`
-        **Required.** A string defining the name of the field from which to pull a data
-        value or an object defining iterated values from the `repeat
-        <https://vega.github.io/vega-lite/docs/repeat.html>`__ operator.
-
-        **See also:** `field <https://vega.github.io/vega-lite/docs/field.html>`__
-        documentation.
-
-        **Notes:** 1)  Dots ( ``.`` ) and brackets ( ``[`` and ``]`` ) can be used to access
-        nested objects (e.g., ``"field": "foo.bar"`` and ``"field": "foo['bar']"`` ). If
-        field names contain dots or brackets but are not nested, you can use ``\\`` to
-        escape dots and brackets (e.g., ``"a\\.b"`` and ``"a\\[0\\]"`` ). See more details
-        about escaping in the `field documentation
-        <https://vega.github.io/vega-lite/docs/field.html>`__. 2) ``field`` is not required
-        if ``aggregate`` is ``count``.
-    legend : anyOf(:class:`Legend`, None)
-        An object defining properties of the legend. If ``null``, the legend for the
-        encoding channel will be removed.
-
-        **Default value:** If undefined, default `legend properties
-        <https://vega.github.io/vega-lite/docs/legend.html>`__ are applied.
-
-        **See also:** `legend <https://vega.github.io/vega-lite/docs/legend.html>`__
-        documentation.
-    scale : anyOf(:class:`Scale`, None)
-        An object defining properties of the channel's scale, which is the function that
-        transforms values in the data domain (numbers, dates, strings, etc) to visual values
-        (pixels, colors, sizes) of the encoding channels.
-
-        If ``null``, the scale will be `disabled and the data value will be directly encoded
-        <https://vega.github.io/vega-lite/docs/scale.html#disable>`__.
-
-        **Default value:** If undefined, default `scale properties
-        <https://vega.github.io/vega-lite/docs/scale.html>`__ are applied.
-
-        **See also:** `scale <https://vega.github.io/vega-lite/docs/scale.html>`__
-        documentation.
-    sort : :class:`Sort`
-        Sort order for the encoded field.
-
-        For continuous fields (quantitative or temporal), ``sort`` can be either
-        ``"ascending"`` or ``"descending"``.
-
-        For discrete fields, ``sort`` can be one of the following:
-
-
-        * ``"ascending"`` or ``"descending"`` -- for sorting by the values' natural order in
-          JavaScript.
-        * `A string indicating an encoding channel name to sort by
-          <https://vega.github.io/vega-lite/docs/sort.html#sort-by-encoding>`__ (e.g.,
-          ``"x"`` or ``"y"`` ) with an optional minus prefix for descending sort (e.g.,
-          ``"-x"`` to sort by x-field, descending). This channel string is short-form of `a
-          sort-by-encoding definition
-          <https://vega.github.io/vega-lite/docs/sort.html#sort-by-encoding>`__. For
-          example, ``"sort": "-x"`` is equivalent to ``"sort": {"encoding": "x", "order":
-          "descending"}``.
-        * `A sort field definition
-          <https://vega.github.io/vega-lite/docs/sort.html#sort-field>`__ for sorting by
-          another field.
-        * `An array specifying the field values in preferred order
-          <https://vega.github.io/vega-lite/docs/sort.html#sort-array>`__. In this case, the
-          sort order will obey the values in the array, followed by any unspecified values
-          in their original order. For discrete time field, values in the sort array can be
-          `date-time definition objects
-          <https://vega.github.io/vega-lite/docs/datetime.html>`__. In addition, for time
-          units ``"month"`` and ``"day"``, the values can be the month or day names (case
-          insensitive) or their 3-letter initials (e.g., ``"Mon"``, ``"Tue"`` ).
-        * ``null`` indicating no sort.
-
-        **Default value:** ``"ascending"``
-
-        **Note:** ``null`` and sorting by another channel is not supported for ``row`` and
-        ``column``.
-
-        **See also:** `sort <https://vega.github.io/vega-lite/docs/sort.html>`__
-        documentation.
-    timeUnit : anyOf(:class:`TimeUnit`, :class:`BinnedTimeUnit`, :class:`TimeUnitParams`)
-        Time unit (e.g., ``year``, ``yearmonth``, ``month``, ``hours`` ) for a temporal
-        field. or `a temporal field that gets casted as ordinal
-        <https://vega.github.io/vega-lite/docs/type.html#cast>`__.
-
-        **Default value:** ``undefined`` (None)
-
-        **See also:** `timeUnit <https://vega.github.io/vega-lite/docs/timeunit.html>`__
-        documentation.
-    title : anyOf(:class:`Text`, None)
-        A title for the field. If ``null``, the title will be removed.
-
-        **Default value:**  derived from the field's name and transformation function (
-        ``aggregate``, ``bin`` and ``timeUnit`` ). If the field has an aggregate function,
-        the function is displayed as part of the title (e.g., ``"Sum of Profit"`` ). If the
-        field is binned or has a time unit applied, the applied function is shown in
-        parentheses (e.g., ``"Profit (binned)"``, ``"Transaction Date (year-month)"`` ).
-        Otherwise, the title is simply the field name.
-
-        **Notes** :
-
-        1) You can customize the default field title format by providing the `fieldTitle
-        <https://vega.github.io/vega-lite/docs/config.html#top-level-config>`__ property in
-        the `config <https://vega.github.io/vega-lite/docs/config.html>`__ or `fieldTitle
-        function via the compile function's options
-        <https://vega.github.io/vega-lite/usage/compile.html#field-title>`__.
-
-        2) If both field definition's ``title`` and axis, header, or legend ``title`` are
-        defined, axis/header/legend title will be used.
-    type : :class:`StandardType`
-        The type of measurement ( ``"quantitative"``, ``"temporal"``, ``"ordinal"``, or
-        ``"nominal"`` ) for the encoded field or constant value ( ``datum`` ). It can also
-        be a ``"geojson"`` type for encoding `'geoshape'
-        <https://vega.github.io/vega-lite/docs/geoshape.html>`__.
-
-        Vega-Lite automatically infers data types in many cases as discussed below. However,
-        type is required for a field if: (1) the field is not nominal and the field encoding
-        has no specified ``aggregate`` (except ``argmin`` and ``argmax`` ), ``bin``, scale
-        type, custom ``sort`` order, nor ``timeUnit`` or (2) if you wish to use an ordinal
-        scale for a field with ``bin`` or ``timeUnit``.
-
-        **Default value:**
-
-        1) For a data ``field``, ``"nominal"`` is the default data type unless the field
-        encoding has ``aggregate``, ``channel``, ``bin``, scale type, ``sort``, or
-        ``timeUnit`` that satisfies the following criteria:
-
-
-        * ``"quantitative"`` is the default type if (1) the encoded field contains ``bin``
-          or ``aggregate`` except ``"argmin"`` and ``"argmax"``, (2) the encoding channel is
-          ``latitude`` or ``longitude`` channel or (3) if the specified scale type is `a
-          quantitative scale <https://vega.github.io/vega-lite/docs/scale.html#type>`__.
-        * ``"temporal"`` is the default type if (1) the encoded field contains ``timeUnit``
-          or (2) the specified scale type is a time or utc scale
-        * ``"ordinal"`` is the default type if (1) the encoded field contains a `custom sort
-          order
-          <https://vega.github.io/vega-lite/docs/sort.html#specifying-custom-sort-order>`__,
-          (2) the specified scale type is an ordinal/point/band scale, or (3) the encoding
-          channel is ``order``.
-
-        2) For a constant value in data domain ( ``datum`` ):
-
-
-        * ``"quantitative"`` if the datum is a number
-        * ``"nominal"`` if the datum is a string
-        * ``"temporal"`` if the datum is `a date time object
-          <https://vega.github.io/vega-lite/docs/datetime.html>`__
-
-        **Note:**
-
-
-        * Data ``type`` describes the semantics of the data rather than the primitive data
-          types (number, string, etc.). The same primitive data type can have different
-          types of measurement. For example, numeric data can represent quantitative,
-          ordinal, or nominal data.
-        * Data values for a temporal field can be either a date-time string (e.g.,
-          ``"2015-03-07 12:32:17"``, ``"17:01"``, ``"2015-03-16"``. ``"2015"`` ) or a
-          timestamp number (e.g., ``1552199579097`` ).
-        * When using with `bin <https://vega.github.io/vega-lite/docs/bin.html>`__, the
-          ``type`` property can be either ``"quantitative"`` (for using a linear bin scale)
-          or `"ordinal" (for using an ordinal bin scale)
-          <https://vega.github.io/vega-lite/docs/type.html#cast-bin>`__.
-        * When using with `timeUnit
-          <https://vega.github.io/vega-lite/docs/timeunit.html>`__, the ``type`` property
-          can be either ``"temporal"`` (default, for using a temporal scale) or `"ordinal"
-          (for using an ordinal scale)
-          <https://vega.github.io/vega-lite/docs/type.html#cast-bin>`__.
-        * When using with `aggregate
-          <https://vega.github.io/vega-lite/docs/aggregate.html>`__, the ``type`` property
-          refers to the post-aggregation data type. For example, we can calculate count
-          ``distinct`` of a categorical field ``"cat"`` using ``{"aggregate": "distinct",
-          "field": "cat"}``. The ``"type"`` of the aggregate output is ``"quantitative"``.
-        * Secondary channels (e.g., ``x2``, ``y2``, ``xError``, ``yError`` ) do not have
-          ``type`` as they must have exactly the same type as their primary channels (e.g.,
-          ``x``, ``y`` ).
-
-        **See also:** `type <https://vega.github.io/vega-lite/docs/type.html>`__
-        documentation.
-    """
-    _schema = {'$ref': '#/definitions/FieldOrDatumDefWithCondition<MarkPropFieldDef,number[]>'}
-
-    def __init__(self, aggregate=Undefined, bandPosition=Undefined, bin=Undefined, condition=Undefined,
-                 field=Undefined, legend=Undefined, scale=Undefined, sort=Undefined, timeUnit=Undefined,
-                 title=Undefined, type=Undefined, **kwds):
-        super(FieldOrDatumDefWithConditionMarkPropFieldDefnumberArray, self).__init__(aggregate=aggregate,
-                                                                                      bandPosition=bandPosition,
-                                                                                      bin=bin,
-                                                                                      condition=condition,
-                                                                                      field=field,
-                                                                                      legend=legend,
-                                                                                      scale=scale,
-                                                                                      sort=sort,
-                                                                                      timeUnit=timeUnit,
-                                                                                      title=title,
-                                                                                      type=type, **kwds)
-
-
-class NumericMarkPropDef(VegaLiteSchema):
-    """NumericMarkPropDef schema wrapper
-
-    anyOf(:class:`FieldOrDatumDefWithConditionMarkPropFieldDefnumber`,
-    :class:`FieldOrDatumDefWithConditionDatumDefnumber`,
-    :class:`ValueDefWithConditionMarkPropFieldOrDatumDefnumber`)
-    """
-    _schema = {'$ref': '#/definitions/NumericMarkPropDef'}
-
-    def __init__(self, *args, **kwds):
-        super(NumericMarkPropDef, self).__init__(*args, **kwds)
-
-
-class FieldOrDatumDefWithConditionDatumDefnumber(MarkPropDefnumber, NumericMarkPropDef):
-    """FieldOrDatumDefWithConditionDatumDefnumber schema wrapper
-
-    Mapping(required=[])
-
-    Parameters
-    ----------
-
-    bandPosition : float
-        Relative position on a band of a stacked, binned, time unit, or band scale. For
-        example, the marks will be positioned at the beginning of the band if set to ``0``,
-        and at the middle of the band if set to ``0.5``.
-    condition : anyOf(:class:`ConditionalValueDefnumberExprRef`, List(:class:`ConditionalValueDefnumberExprRef`))
-        One or more value definition(s) with `a parameter or a test predicate
-        <https://vega.github.io/vega-lite/docs/condition.html>`__.
-
-        **Note:** A field definition's ``condition`` property can only contain `conditional
-        value definitions <https://vega.github.io/vega-lite/docs/condition.html#value>`__
-        since Vega-Lite only allows at most one encoded field per encoding channel.
-    datum : anyOf(:class:`PrimitiveValue`, :class:`DateTime`, :class:`ExprRef`, :class:`RepeatRef`)
-        A constant value in data domain.
-    title : anyOf(:class:`Text`, None)
-        A title for the field. If ``null``, the title will be removed.
-
-        **Default value:**  derived from the field's name and transformation function (
-        ``aggregate``, ``bin`` and ``timeUnit`` ). If the field has an aggregate function,
-        the function is displayed as part of the title (e.g., ``"Sum of Profit"`` ). If the
-        field is binned or has a time unit applied, the applied function is shown in
-        parentheses (e.g., ``"Profit (binned)"``, ``"Transaction Date (year-month)"`` ).
-        Otherwise, the title is simply the field name.
-
-        **Notes** :
-
-        1) You can customize the default field title format by providing the `fieldTitle
-        <https://vega.github.io/vega-lite/docs/config.html#top-level-config>`__ property in
-        the `config <https://vega.github.io/vega-lite/docs/config.html>`__ or `fieldTitle
-        function via the compile function's options
-        <https://vega.github.io/vega-lite/usage/compile.html#field-title>`__.
-
-        2) If both field definition's ``title`` and axis, header, or legend ``title`` are
-        defined, axis/header/legend title will be used.
-    type : :class:`Type`
-        The type of measurement ( ``"quantitative"``, ``"temporal"``, ``"ordinal"``, or
-        ``"nominal"`` ) for the encoded field or constant value ( ``datum`` ). It can also
-        be a ``"geojson"`` type for encoding `'geoshape'
-        <https://vega.github.io/vega-lite/docs/geoshape.html>`__.
-
-        Vega-Lite automatically infers data types in many cases as discussed below. However,
-        type is required for a field if: (1) the field is not nominal and the field encoding
-        has no specified ``aggregate`` (except ``argmin`` and ``argmax`` ), ``bin``, scale
-        type, custom ``sort`` order, nor ``timeUnit`` or (2) if you wish to use an ordinal
-        scale for a field with ``bin`` or ``timeUnit``.
-
-        **Default value:**
-
-        1) For a data ``field``, ``"nominal"`` is the default data type unless the field
-        encoding has ``aggregate``, ``channel``, ``bin``, scale type, ``sort``, or
-        ``timeUnit`` that satisfies the following criteria:
-
-
-        * ``"quantitative"`` is the default type if (1) the encoded field contains ``bin``
-          or ``aggregate`` except ``"argmin"`` and ``"argmax"``, (2) the encoding channel is
-          ``latitude`` or ``longitude`` channel or (3) if the specified scale type is `a
-          quantitative scale <https://vega.github.io/vega-lite/docs/scale.html#type>`__.
-        * ``"temporal"`` is the default type if (1) the encoded field contains ``timeUnit``
-          or (2) the specified scale type is a time or utc scale
-        * ``"ordinal"`` is the default type if (1) the encoded field contains a `custom sort
-          order
-          <https://vega.github.io/vega-lite/docs/sort.html#specifying-custom-sort-order>`__,
-          (2) the specified scale type is an ordinal/point/band scale, or (3) the encoding
-          channel is ``order``.
-
-        2) For a constant value in data domain ( ``datum`` ):
-
-
-        * ``"quantitative"`` if the datum is a number
-        * ``"nominal"`` if the datum is a string
-        * ``"temporal"`` if the datum is `a date time object
-          <https://vega.github.io/vega-lite/docs/datetime.html>`__
-
-        **Note:**
-
-
-        * Data ``type`` describes the semantics of the data rather than the primitive data
-          types (number, string, etc.). The same primitive data type can have different
-          types of measurement. For example, numeric data can represent quantitative,
-          ordinal, or nominal data.
-        * Data values for a temporal field can be either a date-time string (e.g.,
-          ``"2015-03-07 12:32:17"``, ``"17:01"``, ``"2015-03-16"``. ``"2015"`` ) or a
-          timestamp number (e.g., ``1552199579097`` ).
-        * When using with `bin <https://vega.github.io/vega-lite/docs/bin.html>`__, the
-          ``type`` property can be either ``"quantitative"`` (for using a linear bin scale)
-          or `"ordinal" (for using an ordinal bin scale)
-          <https://vega.github.io/vega-lite/docs/type.html#cast-bin>`__.
-        * When using with `timeUnit
-          <https://vega.github.io/vega-lite/docs/timeunit.html>`__, the ``type`` property
-          can be either ``"temporal"`` (default, for using a temporal scale) or `"ordinal"
-          (for using an ordinal scale)
-          <https://vega.github.io/vega-lite/docs/type.html#cast-bin>`__.
-        * When using with `aggregate
-          <https://vega.github.io/vega-lite/docs/aggregate.html>`__, the ``type`` property
-          refers to the post-aggregation data type. For example, we can calculate count
-          ``distinct`` of a categorical field ``"cat"`` using ``{"aggregate": "distinct",
-          "field": "cat"}``. The ``"type"`` of the aggregate output is ``"quantitative"``.
-        * Secondary channels (e.g., ``x2``, ``y2``, ``xError``, ``yError`` ) do not have
-          ``type`` as they must have exactly the same type as their primary channels (e.g.,
-          ``x``, ``y`` ).
-
-        **See also:** `type <https://vega.github.io/vega-lite/docs/type.html>`__
-        documentation.
-    """
-    _schema = {'$ref': '#/definitions/FieldOrDatumDefWithCondition<DatumDef,number>'}
-
-    def __init__(self, bandPosition=Undefined, condition=Undefined, datum=Undefined, title=Undefined,
-                 type=Undefined, **kwds):
-        super(FieldOrDatumDefWithConditionDatumDefnumber, self).__init__(bandPosition=bandPosition,
-                                                                         condition=condition,
-                                                                         datum=datum, title=title,
-                                                                         type=type, **kwds)
-
-
-class FieldOrDatumDefWithConditionMarkPropFieldDefnumber(MarkPropDefnumber, NumericMarkPropDef):
-    """FieldOrDatumDefWithConditionMarkPropFieldDefnumber schema wrapper
-
-    Mapping(required=[])
-
-    Parameters
-    ----------
-
-    aggregate : :class:`Aggregate`
-        Aggregation function for the field (e.g., ``"mean"``, ``"sum"``, ``"median"``,
-        ``"min"``, ``"max"``, ``"count"`` ).
-
-        **Default value:** ``undefined`` (None)
-
-        **See also:** `aggregate <https://vega.github.io/vega-lite/docs/aggregate.html>`__
-        documentation.
-    bandPosition : float
-        Relative position on a band of a stacked, binned, time unit, or band scale. For
-        example, the marks will be positioned at the beginning of the band if set to ``0``,
-        and at the middle of the band if set to ``0.5``.
-    bin : anyOf(boolean, :class:`BinParams`, None)
-        A flag for binning a ``quantitative`` field, `an object defining binning parameters
-        <https://vega.github.io/vega-lite/docs/bin.html#bin-parameters>`__, or indicating
-        that the data for ``x`` or ``y`` channel are binned before they are imported into
-        Vega-Lite ( ``"binned"`` ).
-
-
-        If ``true``, default `binning parameters
-        <https://vega.github.io/vega-lite/docs/bin.html#bin-parameters>`__ will be applied.
-
-        If ``"binned"``, this indicates that the data for the ``x`` (or ``y`` ) channel are
-        already binned. You can map the bin-start field to ``x`` (or ``y`` ) and the bin-end
-        field to ``x2`` (or ``y2`` ). The scale and axis will be formatted similar to
-        binning in Vega-Lite.  To adjust the axis ticks based on the bin step, you can also
-        set the axis's `tickMinStep
-        <https://vega.github.io/vega-lite/docs/axis.html#ticks>`__ property.
-
-        **Default value:** ``false``
-
-        **See also:** `bin <https://vega.github.io/vega-lite/docs/bin.html>`__
-        documentation.
-    condition : anyOf(:class:`ConditionalValueDefnumberExprRef`, List(:class:`ConditionalValueDefnumberExprRef`))
-        One or more value definition(s) with `a parameter or a test predicate
-        <https://vega.github.io/vega-lite/docs/condition.html>`__.
-
-        **Note:** A field definition's ``condition`` property can only contain `conditional
-        value definitions <https://vega.github.io/vega-lite/docs/condition.html#value>`__
-        since Vega-Lite only allows at most one encoded field per encoding channel.
-    field : :class:`Field`
-        **Required.** A string defining the name of the field from which to pull a data
-        value or an object defining iterated values from the `repeat
-        <https://vega.github.io/vega-lite/docs/repeat.html>`__ operator.
-
-        **See also:** `field <https://vega.github.io/vega-lite/docs/field.html>`__
-        documentation.
-
-        **Notes:** 1)  Dots ( ``.`` ) and brackets ( ``[`` and ``]`` ) can be used to access
-        nested objects (e.g., ``"field": "foo.bar"`` and ``"field": "foo['bar']"`` ). If
-        field names contain dots or brackets but are not nested, you can use ``\\`` to
-        escape dots and brackets (e.g., ``"a\\.b"`` and ``"a\\[0\\]"`` ). See more details
-        about escaping in the `field documentation
-        <https://vega.github.io/vega-lite/docs/field.html>`__. 2) ``field`` is not required
-        if ``aggregate`` is ``count``.
-    legend : anyOf(:class:`Legend`, None)
-        An object defining properties of the legend. If ``null``, the legend for the
-        encoding channel will be removed.
-
-        **Default value:** If undefined, default `legend properties
-        <https://vega.github.io/vega-lite/docs/legend.html>`__ are applied.
-
-        **See also:** `legend <https://vega.github.io/vega-lite/docs/legend.html>`__
-        documentation.
-    scale : anyOf(:class:`Scale`, None)
-        An object defining properties of the channel's scale, which is the function that
-        transforms values in the data domain (numbers, dates, strings, etc) to visual values
-        (pixels, colors, sizes) of the encoding channels.
-
-        If ``null``, the scale will be `disabled and the data value will be directly encoded
-        <https://vega.github.io/vega-lite/docs/scale.html#disable>`__.
-
-        **Default value:** If undefined, default `scale properties
-        <https://vega.github.io/vega-lite/docs/scale.html>`__ are applied.
-
-        **See also:** `scale <https://vega.github.io/vega-lite/docs/scale.html>`__
-        documentation.
-    sort : :class:`Sort`
-        Sort order for the encoded field.
-
-        For continuous fields (quantitative or temporal), ``sort`` can be either
-        ``"ascending"`` or ``"descending"``.
-
-        For discrete fields, ``sort`` can be one of the following:
-
-
-        * ``"ascending"`` or ``"descending"`` -- for sorting by the values' natural order in
-          JavaScript.
-        * `A string indicating an encoding channel name to sort by
-          <https://vega.github.io/vega-lite/docs/sort.html#sort-by-encoding>`__ (e.g.,
-          ``"x"`` or ``"y"`` ) with an optional minus prefix for descending sort (e.g.,
-          ``"-x"`` to sort by x-field, descending). This channel string is short-form of `a
-          sort-by-encoding definition
-          <https://vega.github.io/vega-lite/docs/sort.html#sort-by-encoding>`__. For
-          example, ``"sort": "-x"`` is equivalent to ``"sort": {"encoding": "x", "order":
-          "descending"}``.
-        * `A sort field definition
-          <https://vega.github.io/vega-lite/docs/sort.html#sort-field>`__ for sorting by
-          another field.
-        * `An array specifying the field values in preferred order
-          <https://vega.github.io/vega-lite/docs/sort.html#sort-array>`__. In this case, the
-          sort order will obey the values in the array, followed by any unspecified values
-          in their original order. For discrete time field, values in the sort array can be
-          `date-time definition objects
-          <https://vega.github.io/vega-lite/docs/datetime.html>`__. In addition, for time
-          units ``"month"`` and ``"day"``, the values can be the month or day names (case
-          insensitive) or their 3-letter initials (e.g., ``"Mon"``, ``"Tue"`` ).
-        * ``null`` indicating no sort.
-
-        **Default value:** ``"ascending"``
-
-        **Note:** ``null`` and sorting by another channel is not supported for ``row`` and
-        ``column``.
-
-        **See also:** `sort <https://vega.github.io/vega-lite/docs/sort.html>`__
-        documentation.
-    timeUnit : anyOf(:class:`TimeUnit`, :class:`BinnedTimeUnit`, :class:`TimeUnitParams`)
-        Time unit (e.g., ``year``, ``yearmonth``, ``month``, ``hours`` ) for a temporal
-        field. or `a temporal field that gets casted as ordinal
-        <https://vega.github.io/vega-lite/docs/type.html#cast>`__.
-
-        **Default value:** ``undefined`` (None)
-
-        **See also:** `timeUnit <https://vega.github.io/vega-lite/docs/timeunit.html>`__
-        documentation.
-    title : anyOf(:class:`Text`, None)
-        A title for the field. If ``null``, the title will be removed.
-
-        **Default value:**  derived from the field's name and transformation function (
-        ``aggregate``, ``bin`` and ``timeUnit`` ). If the field has an aggregate function,
-        the function is displayed as part of the title (e.g., ``"Sum of Profit"`` ). If the
-        field is binned or has a time unit applied, the applied function is shown in
-        parentheses (e.g., ``"Profit (binned)"``, ``"Transaction Date (year-month)"`` ).
-        Otherwise, the title is simply the field name.
-
-        **Notes** :
-
-        1) You can customize the default field title format by providing the `fieldTitle
-        <https://vega.github.io/vega-lite/docs/config.html#top-level-config>`__ property in
-        the `config <https://vega.github.io/vega-lite/docs/config.html>`__ or `fieldTitle
-        function via the compile function's options
-        <https://vega.github.io/vega-lite/usage/compile.html#field-title>`__.
-
-        2) If both field definition's ``title`` and axis, header, or legend ``title`` are
-        defined, axis/header/legend title will be used.
-    type : :class:`StandardType`
-        The type of measurement ( ``"quantitative"``, ``"temporal"``, ``"ordinal"``, or
-        ``"nominal"`` ) for the encoded field or constant value ( ``datum`` ). It can also
-        be a ``"geojson"`` type for encoding `'geoshape'
-        <https://vega.github.io/vega-lite/docs/geoshape.html>`__.
-
-        Vega-Lite automatically infers data types in many cases as discussed below. However,
-        type is required for a field if: (1) the field is not nominal and the field encoding
-        has no specified ``aggregate`` (except ``argmin`` and ``argmax`` ), ``bin``, scale
-        type, custom ``sort`` order, nor ``timeUnit`` or (2) if you wish to use an ordinal
-        scale for a field with ``bin`` or ``timeUnit``.
-
-        **Default value:**
-
-        1) For a data ``field``, ``"nominal"`` is the default data type unless the field
-        encoding has ``aggregate``, ``channel``, ``bin``, scale type, ``sort``, or
-        ``timeUnit`` that satisfies the following criteria:
-
-
-        * ``"quantitative"`` is the default type if (1) the encoded field contains ``bin``
-          or ``aggregate`` except ``"argmin"`` and ``"argmax"``, (2) the encoding channel is
-          ``latitude`` or ``longitude`` channel or (3) if the specified scale type is `a
-          quantitative scale <https://vega.github.io/vega-lite/docs/scale.html#type>`__.
-        * ``"temporal"`` is the default type if (1) the encoded field contains ``timeUnit``
-          or (2) the specified scale type is a time or utc scale
-        * ``"ordinal"`` is the default type if (1) the encoded field contains a `custom sort
-          order
-          <https://vega.github.io/vega-lite/docs/sort.html#specifying-custom-sort-order>`__,
-          (2) the specified scale type is an ordinal/point/band scale, or (3) the encoding
-          channel is ``order``.
-
-        2) For a constant value in data domain ( ``datum`` ):
-
-
-        * ``"quantitative"`` if the datum is a number
-        * ``"nominal"`` if the datum is a string
-        * ``"temporal"`` if the datum is `a date time object
-          <https://vega.github.io/vega-lite/docs/datetime.html>`__
-
-        **Note:**
-
-
-        * Data ``type`` describes the semantics of the data rather than the primitive data
-          types (number, string, etc.). The same primitive data type can have different
-          types of measurement. For example, numeric data can represent quantitative,
-          ordinal, or nominal data.
-        * Data values for a temporal field can be either a date-time string (e.g.,
-          ``"2015-03-07 12:32:17"``, ``"17:01"``, ``"2015-03-16"``. ``"2015"`` ) or a
-          timestamp number (e.g., ``1552199579097`` ).
-        * When using with `bin <https://vega.github.io/vega-lite/docs/bin.html>`__, the
-          ``type`` property can be either ``"quantitative"`` (for using a linear bin scale)
-          or `"ordinal" (for using an ordinal bin scale)
-          <https://vega.github.io/vega-lite/docs/type.html#cast-bin>`__.
-        * When using with `timeUnit
-          <https://vega.github.io/vega-lite/docs/timeunit.html>`__, the ``type`` property
-          can be either ``"temporal"`` (default, for using a temporal scale) or `"ordinal"
-          (for using an ordinal scale)
-          <https://vega.github.io/vega-lite/docs/type.html#cast-bin>`__.
-        * When using with `aggregate
-          <https://vega.github.io/vega-lite/docs/aggregate.html>`__, the ``type`` property
-          refers to the post-aggregation data type. For example, we can calculate count
-          ``distinct`` of a categorical field ``"cat"`` using ``{"aggregate": "distinct",
-          "field": "cat"}``. The ``"type"`` of the aggregate output is ``"quantitative"``.
-        * Secondary channels (e.g., ``x2``, ``y2``, ``xError``, ``yError`` ) do not have
-          ``type`` as they must have exactly the same type as their primary channels (e.g.,
-          ``x``, ``y`` ).
-
-        **See also:** `type <https://vega.github.io/vega-lite/docs/type.html>`__
-        documentation.
-    """
-    _schema = {'$ref': '#/definitions/FieldOrDatumDefWithCondition<MarkPropFieldDef,number>'}
-
-    def __init__(self, aggregate=Undefined, bandPosition=Undefined, bin=Undefined, condition=Undefined,
-                 field=Undefined, legend=Undefined, scale=Undefined, sort=Undefined, timeUnit=Undefined,
-                 title=Undefined, type=Undefined, **kwds):
-        super(FieldOrDatumDefWithConditionMarkPropFieldDefnumber, self).__init__(aggregate=aggregate,
-                                                                                 bandPosition=bandPosition,
-                                                                                 bin=bin,
-                                                                                 condition=condition,
-                                                                                 field=field,
-                                                                                 legend=legend,
-                                                                                 scale=scale, sort=sort,
-                                                                                 timeUnit=timeUnit,
-                                                                                 title=title, type=type,
-                                                                                 **kwds)
-
-
-class OffsetDef(VegaLiteSchema):
-    """OffsetDef schema wrapper
-
-    anyOf(:class:`ScaleFieldDef`, :class:`ScaleDatumDef`, :class:`ValueDefnumber`)
-    """
-    _schema = {'$ref': '#/definitions/OffsetDef'}
-
-    def __init__(self, *args, **kwds):
-        super(OffsetDef, self).__init__(*args, **kwds)
-
-
-class OrderFieldDef(VegaLiteSchema):
-    """OrderFieldDef schema wrapper
-
-    Mapping(required=[])
-
-    Parameters
-    ----------
-
-    aggregate : :class:`Aggregate`
-        Aggregation function for the field (e.g., ``"mean"``, ``"sum"``, ``"median"``,
-        ``"min"``, ``"max"``, ``"count"`` ).
-
-        **Default value:** ``undefined`` (None)
-
-        **See also:** `aggregate <https://vega.github.io/vega-lite/docs/aggregate.html>`__
-        documentation.
-    bandPosition : float
-        Relative position on a band of a stacked, binned, time unit, or band scale. For
-        example, the marks will be positioned at the beginning of the band if set to ``0``,
-        and at the middle of the band if set to ``0.5``.
-    bin : anyOf(boolean, :class:`BinParams`, string, None)
-        A flag for binning a ``quantitative`` field, `an object defining binning parameters
-        <https://vega.github.io/vega-lite/docs/bin.html#bin-parameters>`__, or indicating
-        that the data for ``x`` or ``y`` channel are binned before they are imported into
-        Vega-Lite ( ``"binned"`` ).
-
-
-        If ``true``, default `binning parameters
-        <https://vega.github.io/vega-lite/docs/bin.html#bin-parameters>`__ will be applied.
-
-        If ``"binned"``, this indicates that the data for the ``x`` (or ``y`` ) channel are
-        already binned. You can map the bin-start field to ``x`` (or ``y`` ) and the bin-end
-        field to ``x2`` (or ``y2`` ). The scale and axis will be formatted similar to
-        binning in Vega-Lite.  To adjust the axis ticks based on the bin step, you can also
-        set the axis's `tickMinStep
-        <https://vega.github.io/vega-lite/docs/axis.html#ticks>`__ property.
-
-        **Default value:** ``false``
-
-        **See also:** `bin <https://vega.github.io/vega-lite/docs/bin.html>`__
-        documentation.
-    field : :class:`Field`
-        **Required.** A string defining the name of the field from which to pull a data
-        value or an object defining iterated values from the `repeat
-        <https://vega.github.io/vega-lite/docs/repeat.html>`__ operator.
-
-        **See also:** `field <https://vega.github.io/vega-lite/docs/field.html>`__
-        documentation.
-
-        **Notes:** 1)  Dots ( ``.`` ) and brackets ( ``[`` and ``]`` ) can be used to access
-        nested objects (e.g., ``"field": "foo.bar"`` and ``"field": "foo['bar']"`` ). If
-        field names contain dots or brackets but are not nested, you can use ``\\`` to
-        escape dots and brackets (e.g., ``"a\\.b"`` and ``"a\\[0\\]"`` ). See more details
-        about escaping in the `field documentation
-        <https://vega.github.io/vega-lite/docs/field.html>`__. 2) ``field`` is not required
-        if ``aggregate`` is ``count``.
-    sort : :class:`SortOrder`
-        The sort order. One of ``"ascending"`` (default) or ``"descending"``.
-    timeUnit : anyOf(:class:`TimeUnit`, :class:`BinnedTimeUnit`, :class:`TimeUnitParams`)
-        Time unit (e.g., ``year``, ``yearmonth``, ``month``, ``hours`` ) for a temporal
-        field. or `a temporal field that gets casted as ordinal
-        <https://vega.github.io/vega-lite/docs/type.html#cast>`__.
-
-        **Default value:** ``undefined`` (None)
-
-        **See also:** `timeUnit <https://vega.github.io/vega-lite/docs/timeunit.html>`__
-        documentation.
-    title : anyOf(:class:`Text`, None)
-        A title for the field. If ``null``, the title will be removed.
-
-        **Default value:**  derived from the field's name and transformation function (
-        ``aggregate``, ``bin`` and ``timeUnit`` ). If the field has an aggregate function,
-        the function is displayed as part of the title (e.g., ``"Sum of Profit"`` ). If the
-        field is binned or has a time unit applied, the applied function is shown in
-        parentheses (e.g., ``"Profit (binned)"``, ``"Transaction Date (year-month)"`` ).
-        Otherwise, the title is simply the field name.
-
-        **Notes** :
-
-        1) You can customize the default field title format by providing the `fieldTitle
-        <https://vega.github.io/vega-lite/docs/config.html#top-level-config>`__ property in
-        the `config <https://vega.github.io/vega-lite/docs/config.html>`__ or `fieldTitle
-        function via the compile function's options
-        <https://vega.github.io/vega-lite/usage/compile.html#field-title>`__.
-
-        2) If both field definition's ``title`` and axis, header, or legend ``title`` are
-        defined, axis/header/legend title will be used.
-    type : :class:`StandardType`
-        The type of measurement ( ``"quantitative"``, ``"temporal"``, ``"ordinal"``, or
-        ``"nominal"`` ) for the encoded field or constant value ( ``datum`` ). It can also
-        be a ``"geojson"`` type for encoding `'geoshape'
-        <https://vega.github.io/vega-lite/docs/geoshape.html>`__.
-
-        Vega-Lite automatically infers data types in many cases as discussed below. However,
-        type is required for a field if: (1) the field is not nominal and the field encoding
-        has no specified ``aggregate`` (except ``argmin`` and ``argmax`` ), ``bin``, scale
-        type, custom ``sort`` order, nor ``timeUnit`` or (2) if you wish to use an ordinal
-        scale for a field with ``bin`` or ``timeUnit``.
-
-        **Default value:**
-
-        1) For a data ``field``, ``"nominal"`` is the default data type unless the field
-        encoding has ``aggregate``, ``channel``, ``bin``, scale type, ``sort``, or
-        ``timeUnit`` that satisfies the following criteria:
-
-
-        * ``"quantitative"`` is the default type if (1) the encoded field contains ``bin``
-          or ``aggregate`` except ``"argmin"`` and ``"argmax"``, (2) the encoding channel is
-          ``latitude`` or ``longitude`` channel or (3) if the specified scale type is `a
-          quantitative scale <https://vega.github.io/vega-lite/docs/scale.html#type>`__.
-        * ``"temporal"`` is the default type if (1) the encoded field contains ``timeUnit``
-          or (2) the specified scale type is a time or utc scale
-        * ``"ordinal"`` is the default type if (1) the encoded field contains a `custom sort
-          order
-          <https://vega.github.io/vega-lite/docs/sort.html#specifying-custom-sort-order>`__,
-          (2) the specified scale type is an ordinal/point/band scale, or (3) the encoding
-          channel is ``order``.
-
-        2) For a constant value in data domain ( ``datum`` ):
-
-
-        * ``"quantitative"`` if the datum is a number
-        * ``"nominal"`` if the datum is a string
-        * ``"temporal"`` if the datum is `a date time object
-          <https://vega.github.io/vega-lite/docs/datetime.html>`__
-
-        **Note:**
-
-
-        * Data ``type`` describes the semantics of the data rather than the primitive data
-          types (number, string, etc.). The same primitive data type can have different
-          types of measurement. For example, numeric data can represent quantitative,
-          ordinal, or nominal data.
-        * Data values for a temporal field can be either a date-time string (e.g.,
-          ``"2015-03-07 12:32:17"``, ``"17:01"``, ``"2015-03-16"``. ``"2015"`` ) or a
-          timestamp number (e.g., ``1552199579097`` ).
-        * When using with `bin <https://vega.github.io/vega-lite/docs/bin.html>`__, the
-          ``type`` property can be either ``"quantitative"`` (for using a linear bin scale)
-          or `"ordinal" (for using an ordinal bin scale)
-          <https://vega.github.io/vega-lite/docs/type.html#cast-bin>`__.
-        * When using with `timeUnit
-          <https://vega.github.io/vega-lite/docs/timeunit.html>`__, the ``type`` property
-          can be either ``"temporal"`` (default, for using a temporal scale) or `"ordinal"
-          (for using an ordinal scale)
-          <https://vega.github.io/vega-lite/docs/type.html#cast-bin>`__.
-        * When using with `aggregate
-          <https://vega.github.io/vega-lite/docs/aggregate.html>`__, the ``type`` property
-          refers to the post-aggregation data type. For example, we can calculate count
-          ``distinct`` of a categorical field ``"cat"`` using ``{"aggregate": "distinct",
-          "field": "cat"}``. The ``"type"`` of the aggregate output is ``"quantitative"``.
-        * Secondary channels (e.g., ``x2``, ``y2``, ``xError``, ``yError`` ) do not have
-          ``type`` as they must have exactly the same type as their primary channels (e.g.,
-          ``x``, ``y`` ).
-
-        **See also:** `type <https://vega.github.io/vega-lite/docs/type.html>`__
-        documentation.
-    """
-    _schema = {'$ref': '#/definitions/OrderFieldDef'}
-
-    def __init__(self, aggregate=Undefined, bandPosition=Undefined, bin=Undefined, field=Undefined,
-                 sort=Undefined, timeUnit=Undefined, title=Undefined, type=Undefined, **kwds):
-        super(OrderFieldDef, self).__init__(aggregate=aggregate, bandPosition=bandPosition, bin=bin,
-                                            field=field, sort=sort, timeUnit=timeUnit, title=title,
-                                            type=type, **kwds)
-
-
-class OrderOnlyDef(VegaLiteSchema):
-    """OrderOnlyDef schema wrapper
-
-    Mapping(required=[])
-
-    Parameters
-    ----------
-
-    sort : :class:`SortOrder`
-        The sort order. One of ``"ascending"`` (default) or ``"descending"``.
-    """
-    _schema = {'$ref': '#/definitions/OrderOnlyDef'}
-
-    def __init__(self, sort=Undefined, **kwds):
-        super(OrderOnlyDef, self).__init__(sort=sort, **kwds)
-
-
-class OrderValueDef(VegaLiteSchema):
-    """OrderValueDef schema wrapper
-
-    Mapping(required=[value])
-
-    Parameters
-    ----------
-
-    value : anyOf(float, :class:`ExprRef`)
-        A constant value in visual domain (e.g., ``"red"`` / ``"#0099ff"`` / `gradient
-        definition <https://vega.github.io/vega-lite/docs/types.html#gradient>`__ for color,
-        values between ``0`` to ``1`` for opacity).
-    condition : anyOf(:class:`ConditionalValueDefnumber`, List(:class:`ConditionalValueDefnumber`))
-        One or more value definition(s) with `a parameter or a test predicate
-        <https://vega.github.io/vega-lite/docs/condition.html>`__.
-
-        **Note:** A field definition's ``condition`` property can only contain `conditional
-        value definitions <https://vega.github.io/vega-lite/docs/condition.html#value>`__
-        since Vega-Lite only allows at most one encoded field per encoding channel.
-    """
-    _schema = {'$ref': '#/definitions/OrderValueDef'}
-
-    def __init__(self, value=Undefined, condition=Undefined, **kwds):
-        super(OrderValueDef, self).__init__(value=value, condition=condition, **kwds)
-
-
-class Orient(VegaLiteSchema):
-    """Orient schema wrapper
-
-    enum('left', 'right', 'top', 'bottom')
-    """
-    _schema = {'$ref': '#/definitions/Orient'}
-
-    def __init__(self, *args):
-        super(Orient, self).__init__(*args)
-
-
-class Orientation(VegaLiteSchema):
-    """Orientation schema wrapper
-
-    enum('horizontal', 'vertical')
-    """
-    _schema = {'$ref': '#/definitions/Orientation'}
-
-    def __init__(self, *args):
-        super(Orientation, self).__init__(*args)
-
-
-class OverlayMarkDef(VegaLiteSchema):
-    """OverlayMarkDef schema wrapper
-
-    Mapping(required=[])
-
-    Parameters
-    ----------
-
-    align : anyOf(:class:`Align`, :class:`ExprRef`)
-        The horizontal alignment of the text or ranged marks (area, bar, image, rect, rule).
-        One of ``"left"``, ``"right"``, ``"center"``.
-
-        **Note:** Expression reference is *not* supported for range marks.
-    angle : anyOf(float, :class:`ExprRef`)
-        The rotation angle of the text, in degrees.
-    aria : anyOf(boolean, :class:`ExprRef`)
-        A boolean flag indicating if `ARIA attributes
-        <https://developer.mozilla.org/en-US/docs/Web/Accessibility/ARIA>`__ should be
-        included (SVG output only). If ``false``, the "aria-hidden" attribute will be set on
-        the output SVG element, removing the mark item from the ARIA accessibility tree.
-    ariaRole : anyOf(string, :class:`ExprRef`)
-        Sets the type of user interface element of the mark item for `ARIA accessibility
-        <https://developer.mozilla.org/en-US/docs/Web/Accessibility/ARIA>`__ (SVG output
-        only). If specified, this property determines the "role" attribute. Warning: this
-        property is experimental and may be changed in the future.
-    ariaRoleDescription : anyOf(string, :class:`ExprRef`)
-        A human-readable, author-localized description for the role of the mark item for
-        `ARIA accessibility
-        <https://developer.mozilla.org/en-US/docs/Web/Accessibility/ARIA>`__ (SVG output
-        only). If specified, this property determines the "aria-roledescription" attribute.
-        Warning: this property is experimental and may be changed in the future.
-    aspect : anyOf(boolean, :class:`ExprRef`)
-        Whether to keep aspect ratio of image marks.
-    baseline : anyOf(:class:`TextBaseline`, :class:`ExprRef`)
-        For text marks, the vertical text baseline. One of ``"alphabetic"`` (default),
-        ``"top"``, ``"middle"``, ``"bottom"``, ``"line-top"``, ``"line-bottom"``, or an
-        expression reference that provides one of the valid values. The ``"line-top"`` and
-        ``"line-bottom"`` values operate similarly to ``"top"`` and ``"bottom"``, but are
-        calculated relative to the ``lineHeight`` rather than ``fontSize`` alone.
-
-        For range marks, the vertical alignment of the marks. One of ``"top"``,
-        ``"middle"``, ``"bottom"``.
-
-        **Note:** Expression reference is *not* supported for range marks.
-    blend : anyOf(:class:`Blend`, :class:`ExprRef`)
-        The color blend mode for drawing an item on its current background. Any valid `CSS
-        mix-blend-mode <https://developer.mozilla.org/en-US/docs/Web/CSS/mix-blend-mode>`__
-        value can be used.
-
-        __Default value:__ ``"source-over"``
-    clip : boolean
-        Whether a mark be clipped to the enclosing group’s width and height.
-    color : anyOf(:class:`Color`, :class:`Gradient`, :class:`ExprRef`)
-        Default color.
-
-        **Default value:** :raw-html:`<span style="color: #4682b4;">&#9632;</span>`
-        ``"#4682b4"``
-
-        **Note:**
-
-
-        * This property cannot be used in a `style config
-          <https://vega.github.io/vega-lite/docs/mark.html#style-config>`__.
-        * The ``fill`` and ``stroke`` properties have higher precedence than ``color`` and
-          will override ``color``.
-    cornerRadius : anyOf(float, :class:`ExprRef`)
-        The radius in pixels of rounded rectangles or arcs' corners.
-
-        **Default value:** ``0``
-    cornerRadiusBottomLeft : anyOf(float, :class:`ExprRef`)
-        The radius in pixels of rounded rectangles' bottom left corner.
-
-        **Default value:** ``0``
-    cornerRadiusBottomRight : anyOf(float, :class:`ExprRef`)
-        The radius in pixels of rounded rectangles' bottom right corner.
-
-        **Default value:** ``0``
-    cornerRadiusTopLeft : anyOf(float, :class:`ExprRef`)
-        The radius in pixels of rounded rectangles' top right corner.
-
-        **Default value:** ``0``
-    cornerRadiusTopRight : anyOf(float, :class:`ExprRef`)
-        The radius in pixels of rounded rectangles' top left corner.
-
-        **Default value:** ``0``
-    cursor : anyOf(:class:`Cursor`, :class:`ExprRef`)
-        The mouse cursor used over the mark. Any valid `CSS cursor type
-        <https://developer.mozilla.org/en-US/docs/Web/CSS/cursor#Values>`__ can be used.
-    description : anyOf(string, :class:`ExprRef`)
-        A text description of the mark item for `ARIA accessibility
-        <https://developer.mozilla.org/en-US/docs/Web/Accessibility/ARIA>`__ (SVG output
-        only). If specified, this property determines the `"aria-label" attribute
-        <https://developer.mozilla.org/en-US/docs/Web/Accessibility/ARIA/ARIA_Techniques/Using_the_aria-label_attribute>`__.
-    dir : anyOf(:class:`TextDirection`, :class:`ExprRef`)
-        The direction of the text. One of ``"ltr"`` (left-to-right) or ``"rtl"``
-        (right-to-left). This property determines on which side is truncated in response to
-        the limit parameter.
-
-        **Default value:** ``"ltr"``
-    dx : anyOf(float, :class:`ExprRef`)
-        The horizontal offset, in pixels, between the text label and its anchor point. The
-        offset is applied after rotation by the *angle* property.
-    dy : anyOf(float, :class:`ExprRef`)
-        The vertical offset, in pixels, between the text label and its anchor point. The
-        offset is applied after rotation by the *angle* property.
-    ellipsis : anyOf(string, :class:`ExprRef`)
-        The ellipsis string for text truncated in response to the limit parameter.
-
-        **Default value:** ``"…"``
-    endAngle : anyOf(float, :class:`ExprRef`)
-        The end angle in radians for arc marks. A value of ``0`` indicates up (north),
-        increasing values proceed clockwise.
-    fill : anyOf(:class:`Color`, :class:`Gradient`, None, :class:`ExprRef`)
-        Default fill color. This property has higher precedence than ``config.color``. Set
-        to ``null`` to remove fill.
-
-        **Default value:** (None)
-    fillOpacity : anyOf(float, :class:`ExprRef`)
-        The fill opacity (value between [0,1]).
-
-        **Default value:** ``1``
-    filled : boolean
-        Whether the mark's color should be used as fill color instead of stroke color.
-
-        **Default value:** ``false`` for all ``point``, ``line``, and ``rule`` marks as well
-        as ``geoshape`` marks for `graticule
-        <https://vega.github.io/vega-lite/docs/data.html#graticule>`__ data sources;
-        otherwise, ``true``.
-
-        **Note:** This property cannot be used in a `style config
-        <https://vega.github.io/vega-lite/docs/mark.html#style-config>`__.
-    font : anyOf(string, :class:`ExprRef`)
-        The typeface to set the text in (e.g., ``"Helvetica Neue"`` ).
-    fontSize : anyOf(float, :class:`ExprRef`)
-        The font size, in pixels.
-
-        **Default value:** ``11``
-    fontStyle : anyOf(:class:`FontStyle`, :class:`ExprRef`)
-        The font style (e.g., ``"italic"`` ).
-    fontWeight : anyOf(:class:`FontWeight`, :class:`ExprRef`)
-        The font weight. This can be either a string (e.g ``"bold"``, ``"normal"`` ) or a
-        number ( ``100``, ``200``, ``300``, ..., ``900`` where ``"normal"`` = ``400`` and
-        ``"bold"`` = ``700`` ).
-    height : anyOf(float, :class:`ExprRef`)
-        Height of the marks.
-    href : anyOf(:class:`URI`, :class:`ExprRef`)
-        A URL to load upon mouse click. If defined, the mark acts as a hyperlink.
-    innerRadius : anyOf(float, :class:`ExprRef`)
-        The inner radius in pixels of arc marks. ``innerRadius`` is an alias for
-        ``radius2``.
-
-        **Default value:** ``0``
-    interpolate : anyOf(:class:`Interpolate`, :class:`ExprRef`)
-        The line interpolation method to use for line and area marks. One of the following:
-
-
-        * ``"linear"`` : piecewise linear segments, as in a polyline.
-        * ``"linear-closed"`` : close the linear segments to form a polygon.
-        * ``"step"`` : alternate between horizontal and vertical segments, as in a step
-          function.
-        * ``"step-before"`` : alternate between vertical and horizontal segments, as in a
-          step function.
-        * ``"step-after"`` : alternate between horizontal and vertical segments, as in a
-          step function.
-        * ``"basis"`` : a B-spline, with control point duplication on the ends.
-        * ``"basis-open"`` : an open B-spline; may not intersect the start or end.
-        * ``"basis-closed"`` : a closed B-spline, as in a loop.
-        * ``"cardinal"`` : a Cardinal spline, with control point duplication on the ends.
-        * ``"cardinal-open"`` : an open Cardinal spline; may not intersect the start or end,
-          but will intersect other control points.
-        * ``"cardinal-closed"`` : a closed Cardinal spline, as in a loop.
-        * ``"bundle"`` : equivalent to basis, except the tension parameter is used to
-          straighten the spline.
-        * ``"monotone"`` : cubic interpolation that preserves monotonicity in y.
-    invalid : enum('filter', None)
-        Defines how Vega-Lite should handle marks for invalid values ( ``null`` and ``NaN``
-        ).
-
-
-        * If set to ``"filter"`` (default), all data items with null values will be skipped
-          (for line, trail, and area marks) or filtered (for other marks).
-        * If ``null``, all data items are included. In this case, invalid values will be
-          interpreted as zeroes.
-    limit : anyOf(float, :class:`ExprRef`)
-        The maximum length of the text mark in pixels. The text value will be automatically
-        truncated if the rendered size exceeds the limit.
-
-        **Default value:** ``0`` -- indicating no limit
-    lineBreak : anyOf(string, :class:`ExprRef`)
-        A delimiter, such as a newline character, upon which to break text strings into
-        multiple lines. This property is ignored if the text is array-valued.
-    lineHeight : anyOf(float, :class:`ExprRef`)
-        The line height in pixels (the spacing between subsequent lines of text) for
-        multi-line text marks.
-    opacity : anyOf(float, :class:`ExprRef`)
-        The overall opacity (value between [0,1]).
-
-        **Default value:** ``0.7`` for non-aggregate plots with ``point``, ``tick``,
-        ``circle``, or ``square`` marks or layered ``bar`` charts and ``1`` otherwise.
-    order : anyOf(None, boolean)
-        For line and trail marks, this ``order`` property can be set to ``null`` or
-        ``false`` to make the lines use the original order in the data sources.
-    orient : :class:`Orientation`
-        The orientation of a non-stacked bar, tick, area, and line charts. The value is
-        either horizontal (default) or vertical.
-
-
-        * For bar, rule and tick, this determines whether the size of the bar and tick
-          should be applied to x or y dimension.
-        * For area, this property determines the orient property of the Vega output.
-        * For line and trail marks, this property determines the sort order of the points in
-          the line if ``config.sortLineBy`` is not specified. For stacked charts, this is
-          always determined by the orientation of the stack; therefore explicitly specified
-          value will be ignored.
-    outerRadius : anyOf(float, :class:`ExprRef`)
-        The outer radius in pixels of arc marks. ``outerRadius`` is an alias for ``radius``.
-
-        **Default value:** ``0``
-    padAngle : anyOf(float, :class:`ExprRef`)
-        The angular padding applied to sides of the arc, in radians.
-    radius : anyOf(float, :class:`ExprRef`)
-        For arc mark, the primary (outer) radius in pixels.
-
-        For text marks, polar coordinate radial offset, in pixels, of the text from the
-        origin determined by the ``x`` and ``y`` properties.
-
-        **Default value:** ``min(plot_width, plot_height)/2``
-    radius2 : anyOf(float, :class:`ExprRef`)
-        The secondary (inner) radius in pixels of arc marks.
-
-        **Default value:** ``0``
-    radius2Offset : anyOf(float, :class:`ExprRef`)
-        Offset for radius2.
-    radiusOffset : anyOf(float, :class:`ExprRef`)
-        Offset for radius.
-    shape : anyOf(anyOf(:class:`SymbolShape`, string), :class:`ExprRef`)
-        Shape of the point marks. Supported values include:
-
-
-        * plotting shapes: ``"circle"``, ``"square"``, ``"cross"``, ``"diamond"``,
-          ``"triangle-up"``, ``"triangle-down"``, ``"triangle-right"``, or
-          ``"triangle-left"``.
-        * the line symbol ``"stroke"``
-        * centered directional shapes ``"arrow"``, ``"wedge"``, or ``"triangle"``
-        * a custom `SVG path string
-          <https://developer.mozilla.org/en-US/docs/Web/SVG/Tutorial/Paths>`__ (For correct
-          sizing, custom shape paths should be defined within a square bounding box with
-          coordinates ranging from -1 to 1 along both the x and y dimensions.)
-
-        **Default value:** ``"circle"``
-    size : anyOf(float, :class:`ExprRef`)
-        Default size for marks.
-
-
-        * For ``point`` / ``circle`` / ``square``, this represents the pixel area of the
-          marks. Note that this value sets the area of the symbol; the side lengths will
-          increase with the square root of this value.
-        * For ``bar``, this represents the band size of the bar, in pixels.
-        * For ``text``, this represents the font size, in pixels.
-
-        **Default value:**
-
-
-        * ``30`` for point, circle, square marks; width/height's ``step``
-        * ``2`` for bar marks with discrete dimensions;
-        * ``5`` for bar marks with continuous dimensions;
-        * ``11`` for text marks.
-    smooth : anyOf(boolean, :class:`ExprRef`)
-        A boolean flag (default true) indicating if the image should be smoothed when
-        resized. If false, individual pixels should be scaled directly rather than
-        interpolated with smoothing. For SVG rendering, this option may not work in some
-        browsers due to lack of standardization.
-    startAngle : anyOf(float, :class:`ExprRef`)
-        The start angle in radians for arc marks. A value of ``0`` indicates up (north),
-        increasing values proceed clockwise.
-    stroke : anyOf(:class:`Color`, :class:`Gradient`, None, :class:`ExprRef`)
-        Default stroke color. This property has higher precedence than ``config.color``. Set
-        to ``null`` to remove stroke.
-
-        **Default value:** (None)
-    strokeCap : anyOf(:class:`StrokeCap`, :class:`ExprRef`)
-        The stroke cap for line ending style. One of ``"butt"``, ``"round"``, or
-        ``"square"``.
-
-        **Default value:** ``"butt"``
-    strokeDash : anyOf(List(float), :class:`ExprRef`)
-        An array of alternating stroke, space lengths for creating dashed or dotted lines.
-    strokeDashOffset : anyOf(float, :class:`ExprRef`)
-        The offset (in pixels) into which to begin drawing with the stroke dash array.
-    strokeJoin : anyOf(:class:`StrokeJoin`, :class:`ExprRef`)
-        The stroke line join method. One of ``"miter"``, ``"round"`` or ``"bevel"``.
-
-        **Default value:** ``"miter"``
-    strokeMiterLimit : anyOf(float, :class:`ExprRef`)
-        The miter limit at which to bevel a line join.
-    strokeOffset : anyOf(float, :class:`ExprRef`)
-        The offset in pixels at which to draw the group stroke and fill. If unspecified, the
-        default behavior is to dynamically offset stroked groups such that 1 pixel stroke
-        widths align with the pixel grid.
-    strokeOpacity : anyOf(float, :class:`ExprRef`)
-        The stroke opacity (value between [0,1]).
-
-        **Default value:** ``1``
-    strokeWidth : anyOf(float, :class:`ExprRef`)
-        The stroke width, in pixels.
-    style : anyOf(string, List(string))
-        A string or array of strings indicating the name of custom styles to apply to the
-        mark. A style is a named collection of mark property defaults defined within the
-        `style configuration
-        <https://vega.github.io/vega-lite/docs/mark.html#style-config>`__. If style is an
-        array, later styles will override earlier styles. Any `mark properties
-        <https://vega.github.io/vega-lite/docs/encoding.html#mark-prop>`__ explicitly
-        defined within the ``encoding`` will override a style default.
-
-        **Default value:** The mark's name. For example, a bar mark will have style
-        ``"bar"`` by default. **Note:** Any specified style will augment the default style.
-        For example, a bar mark with ``"style": "foo"`` will receive from
-        ``config.style.bar`` and ``config.style.foo`` (the specified style ``"foo"`` has
-        higher precedence).
-    tension : anyOf(float, :class:`ExprRef`)
-        Depending on the interpolation type, sets the tension parameter (for line and area
-        marks).
-    text : anyOf(:class:`Text`, :class:`ExprRef`)
-        Placeholder text if the ``text`` channel is not specified
-    theta : anyOf(float, :class:`ExprRef`)
-        For arc marks, the arc length in radians if theta2 is not specified, otherwise the
-        start arc angle. (A value of 0 indicates up or “north”, increasing values proceed
-        clockwise.)
-
-        For text marks, polar coordinate angle in radians.
-    theta2 : anyOf(float, :class:`ExprRef`)
-        The end angle of arc marks in radians. A value of 0 indicates up or “north”,
-        increasing values proceed clockwise.
-    theta2Offset : anyOf(float, :class:`ExprRef`)
-        Offset for theta2.
-    thetaOffset : anyOf(float, :class:`ExprRef`)
-        Offset for theta.
-    timeUnitBandPosition : float
-        Default relative band position for a time unit. If set to ``0``, the marks will be
-        positioned at the beginning of the time unit band step. If set to ``0.5``, the marks
-        will be positioned in the middle of the time unit band step.
-    timeUnitBandSize : float
-        Default relative band size for a time unit. If set to ``1``, the bandwidth of the
-        marks will be equal to the time unit band step. If set to ``0.5``, bandwidth of the
-        marks will be half of the time unit band step.
-    tooltip : anyOf(float, string, boolean, :class:`TooltipContent`, :class:`ExprRef`, None)
-        The tooltip text string to show upon mouse hover or an object defining which fields
-        should the tooltip be derived from.
-
-
-        * If ``tooltip`` is ``true`` or ``{"content": "encoding"}``, then all fields from
-          ``encoding`` will be used.
-        * If ``tooltip`` is ``{"content": "data"}``, then all fields that appear in the
-          highlighted data point will be used.
-        * If set to ``null`` or ``false``, then no tooltip will be used.
-
-        See the `tooltip <https://vega.github.io/vega-lite/docs/tooltip.html>`__
-        documentation for a detailed discussion about tooltip  in Vega-Lite.
-
-        **Default value:** ``null``
-    url : anyOf(:class:`URI`, :class:`ExprRef`)
-        The URL of the image file for image marks.
-    width : anyOf(float, :class:`ExprRef`)
-        Width of the marks.
-    x : anyOf(float, string, :class:`ExprRef`)
-        X coordinates of the marks, or width of horizontal ``"bar"`` and ``"area"`` without
-        specified ``x2`` or ``width``.
-
-        The ``value`` of this channel can be a number or a string ``"width"`` for the width
-        of the plot.
-    x2 : anyOf(float, string, :class:`ExprRef`)
-        X2 coordinates for ranged ``"area"``, ``"bar"``, ``"rect"``, and  ``"rule"``.
-
-        The ``value`` of this channel can be a number or a string ``"width"`` for the width
-        of the plot.
-    x2Offset : anyOf(float, :class:`ExprRef`)
-        Offset for x2-position.
-    xOffset : anyOf(float, :class:`ExprRef`)
-        Offset for x-position.
-    y : anyOf(float, string, :class:`ExprRef`)
-        Y coordinates of the marks, or height of vertical ``"bar"`` and ``"area"`` without
-        specified ``y2`` or ``height``.
-
-        The ``value`` of this channel can be a number or a string ``"height"`` for the
-        height of the plot.
-    y2 : anyOf(float, string, :class:`ExprRef`)
-        Y2 coordinates for ranged ``"area"``, ``"bar"``, ``"rect"``, and  ``"rule"``.
-
-        The ``value`` of this channel can be a number or a string ``"height"`` for the
-        height of the plot.
-    y2Offset : anyOf(float, :class:`ExprRef`)
-        Offset for y2-position.
-    yOffset : anyOf(float, :class:`ExprRef`)
-        Offset for y-position.
-    """
-    _schema = {'$ref': '#/definitions/OverlayMarkDef'}
-
-    def __init__(self, align=Undefined, angle=Undefined, aria=Undefined, ariaRole=Undefined,
-                 ariaRoleDescription=Undefined, aspect=Undefined, baseline=Undefined, blend=Undefined,
-                 clip=Undefined, color=Undefined, cornerRadius=Undefined,
-                 cornerRadiusBottomLeft=Undefined, cornerRadiusBottomRight=Undefined,
-                 cornerRadiusTopLeft=Undefined, cornerRadiusTopRight=Undefined, cursor=Undefined,
-                 description=Undefined, dir=Undefined, dx=Undefined, dy=Undefined, ellipsis=Undefined,
-                 endAngle=Undefined, fill=Undefined, fillOpacity=Undefined, filled=Undefined,
-                 font=Undefined, fontSize=Undefined, fontStyle=Undefined, fontWeight=Undefined,
-                 height=Undefined, href=Undefined, innerRadius=Undefined, interpolate=Undefined,
-                 invalid=Undefined, limit=Undefined, lineBreak=Undefined, lineHeight=Undefined,
-                 opacity=Undefined, order=Undefined, orient=Undefined, outerRadius=Undefined,
-                 padAngle=Undefined, radius=Undefined, radius2=Undefined, radius2Offset=Undefined,
-                 radiusOffset=Undefined, shape=Undefined, size=Undefined, smooth=Undefined,
-                 startAngle=Undefined, stroke=Undefined, strokeCap=Undefined, strokeDash=Undefined,
-                 strokeDashOffset=Undefined, strokeJoin=Undefined, strokeMiterLimit=Undefined,
-                 strokeOffset=Undefined, strokeOpacity=Undefined, strokeWidth=Undefined,
-                 style=Undefined, tension=Undefined, text=Undefined, theta=Undefined, theta2=Undefined,
-                 theta2Offset=Undefined, thetaOffset=Undefined, timeUnitBandPosition=Undefined,
-                 timeUnitBandSize=Undefined, tooltip=Undefined, url=Undefined, width=Undefined,
-                 x=Undefined, x2=Undefined, x2Offset=Undefined, xOffset=Undefined, y=Undefined,
-                 y2=Undefined, y2Offset=Undefined, yOffset=Undefined, **kwds):
-        super(OverlayMarkDef, self).__init__(align=align, angle=angle, aria=aria, ariaRole=ariaRole,
-                                             ariaRoleDescription=ariaRoleDescription, aspect=aspect,
-                                             baseline=baseline, blend=blend, clip=clip, color=color,
-                                             cornerRadius=cornerRadius,
-                                             cornerRadiusBottomLeft=cornerRadiusBottomLeft,
-                                             cornerRadiusBottomRight=cornerRadiusBottomRight,
-                                             cornerRadiusTopLeft=cornerRadiusTopLeft,
-                                             cornerRadiusTopRight=cornerRadiusTopRight, cursor=cursor,
-                                             description=description, dir=dir, dx=dx, dy=dy,
-                                             ellipsis=ellipsis, endAngle=endAngle, fill=fill,
-                                             fillOpacity=fillOpacity, filled=filled, font=font,
-                                             fontSize=fontSize, fontStyle=fontStyle,
-                                             fontWeight=fontWeight, height=height, href=href,
-                                             innerRadius=innerRadius, interpolate=interpolate,
-                                             invalid=invalid, limit=limit, lineBreak=lineBreak,
-                                             lineHeight=lineHeight, opacity=opacity, order=order,
-                                             orient=orient, outerRadius=outerRadius, padAngle=padAngle,
-                                             radius=radius, radius2=radius2,
-                                             radius2Offset=radius2Offset, radiusOffset=radiusOffset,
-                                             shape=shape, size=size, smooth=smooth,
-                                             startAngle=startAngle, stroke=stroke, strokeCap=strokeCap,
-                                             strokeDash=strokeDash, strokeDashOffset=strokeDashOffset,
-                                             strokeJoin=strokeJoin, strokeMiterLimit=strokeMiterLimit,
-                                             strokeOffset=strokeOffset, strokeOpacity=strokeOpacity,
-                                             strokeWidth=strokeWidth, style=style, tension=tension,
-                                             text=text, theta=theta, theta2=theta2,
-                                             theta2Offset=theta2Offset, thetaOffset=thetaOffset,
-                                             timeUnitBandPosition=timeUnitBandPosition,
-                                             timeUnitBandSize=timeUnitBandSize, tooltip=tooltip,
-                                             url=url, width=width, x=x, x2=x2, x2Offset=x2Offset,
-                                             xOffset=xOffset, y=y, y2=y2, y2Offset=y2Offset,
-                                             yOffset=yOffset, **kwds)
-
-
-class Padding(VegaLiteSchema):
-    """Padding schema wrapper
-
-    anyOf(float, Mapping(required=[]))
-    """
-    _schema = {'$ref': '#/definitions/Padding'}
-
-    def __init__(self, *args, **kwds):
-        super(Padding, self).__init__(*args, **kwds)
-
-
-class ParameterExtent(BinExtent):
-    """ParameterExtent schema wrapper
-
-    anyOf(Mapping(required=[param]), Mapping(required=[param]))
-    """
-    _schema = {'$ref': '#/definitions/ParameterExtent'}
-
-    def __init__(self, *args, **kwds):
-        super(ParameterExtent, self).__init__(*args, **kwds)
-
-
-class ParameterName(VegaLiteSchema):
-    """ParameterName schema wrapper
-
-    string
-    """
-    _schema = {'$ref': '#/definitions/ParameterName'}
-
-    def __init__(self, *args):
-        super(ParameterName, self).__init__(*args)
-
-
-class Parse(VegaLiteSchema):
-    """Parse schema wrapper
-
-    Mapping(required=[])
-    """
-    _schema = {'$ref': '#/definitions/Parse'}
-
-    def __init__(self, **kwds):
-        super(Parse, self).__init__(**kwds)
-
-
-class ParseValue(VegaLiteSchema):
-    """ParseValue schema wrapper
-
-    anyOf(None, string, string, string, string, string)
-    """
-    _schema = {'$ref': '#/definitions/ParseValue'}
-
-    def __init__(self, *args, **kwds):
-        super(ParseValue, self).__init__(*args, **kwds)
-
-
-class Point(Geometry):
-    """Point schema wrapper
-
-    Mapping(required=[coordinates, type])
-    Point geometry object. https://tools.ietf.org/html/rfc7946#section-3.1.2
-
-    Parameters
-    ----------
-
-    coordinates : :class:`Position`
-        A Position is an array of coordinates.
-        https://tools.ietf.org/html/rfc7946#section-3.1.1 Array should contain between two
-        and three elements. The previous GeoJSON specification allowed more elements (e.g.,
-        which could be used to represent M values), but the current specification only
-        allows X, Y, and (optionally) Z to be defined.
-    type : string
-        Specifies the type of GeoJSON object.
-    bbox : :class:`BBox`
-        Bounding box of the coordinate range of the object's Geometries, Features, or
-        Feature Collections. https://tools.ietf.org/html/rfc7946#section-5
-    """
-    _schema = {'$ref': '#/definitions/Point'}
-
-    def __init__(self, coordinates=Undefined, type=Undefined, bbox=Undefined, **kwds):
-        super(Point, self).__init__(coordinates=coordinates, type=type, bbox=bbox, **kwds)
-
-
-class PointSelectionConfig(VegaLiteSchema):
-    """PointSelectionConfig schema wrapper
-
-    Mapping(required=[type])
-
-    Parameters
-    ----------
-
-    type : string
-        Determines the default event processing and data query for the selection. Vega-Lite
-        currently supports two selection types:
-
-
-        * ``"point"`` -- to select multiple discrete data values; the first value is
-          selected on ``click`` and additional values toggled on shift-click.
-        * ``"interval"`` -- to select a continuous range of data values on ``drag``.
-    clear : anyOf(:class:`Stream`, string, boolean)
-        Clears the selection, emptying it of all values. This property can be a `Event
-        Stream <https://vega.github.io/vega/docs/event-streams/>`__ or ``false`` to disable
-        clear.
-
-        **Default value:** ``dblclick``.
-
-        **See also:** `clear examples
-        <https://vega.github.io/vega-lite/docs/selection.html#clear>`__ in the
-        documentation.
-    encodings : List(:class:`SingleDefUnitChannel`)
-        An array of encoding channels. The corresponding data field values must match for a
-        data tuple to fall within the selection.
-
-        **See also:** The `projection with encodings and fields section
-        <https://vega.github.io/vega-lite/docs/selection.html#project>`__ in the
-        documentation.
-    fields : List(:class:`FieldName`)
-        An array of field names whose values must match for a data tuple to fall within the
-        selection.
-
-        **See also:** The `projection with encodings and fields section
-        <https://vega.github.io/vega-lite/docs/selection.html#project>`__ in the
-        documentation.
-    nearest : boolean
-        When true, an invisible voronoi diagram is computed to accelerate discrete
-        selection. The data value *nearest* the mouse cursor is added to the selection.
-
-        **Default value:** ``false``, which means that data values must be interacted with
-        directly (e.g., clicked on) to be added to the selection.
-
-        **See also:** `nearest examples
-        <https://vega.github.io/vega-lite/docs/selection.html#nearest>`__ documentation.
-    on : anyOf(:class:`Stream`, string)
-        A `Vega event stream <https://vega.github.io/vega/docs/event-streams/>`__ (object or
-        selector) that triggers the selection. For interval selections, the event stream
-        must specify a `start and end
-        <https://vega.github.io/vega/docs/event-streams/#between-filters>`__.
-
-        **See also:** `on examples
-        <https://vega.github.io/vega-lite/docs/selection.html#on>`__ in the documentation.
-    resolve : :class:`SelectionResolution`
-        With layered and multi-view displays, a strategy that determines how selections'
-        data queries are resolved when applied in a filter transform, conditional encoding
-        rule, or scale domain.
-
-        One of:
-
-
-        * ``"global"`` -- only one brush exists for the entire SPLOM. When the user begins
-          to drag, any previous brushes are cleared, and a new one is constructed.
-        * ``"union"`` -- each cell contains its own brush, and points are highlighted if
-          they lie within *any* of these individual brushes.
-        * ``"intersect"`` -- each cell contains its own brush, and points are highlighted
-          only if they fall within *all* of these individual brushes.
-
-        **Default value:** ``global``.
-
-        **See also:** `resolve examples
-        <https://vega.github.io/vega-lite/docs/selection.html#resolve>`__ in the
-        documentation.
-    toggle : anyOf(string, boolean)
-        Controls whether data values should be toggled (inserted or removed from a point
-        selection) or only ever inserted into point selections.
-
-        One of:
-
-
-        * ``true`` -- the default behavior, which corresponds to ``"event.shiftKey"``.  As a
-          result, data values are toggled when the user interacts with the shift-key
-          pressed.
-        * ``false`` -- disables toggling behaviour; the selection will only ever contain a
-          single data value corresponding to the most recent interaction.
-        * A `Vega expression <https://vega.github.io/vega/docs/expressions/>`__ which is
-          re-evaluated as the user interacts. If the expression evaluates to ``true``, the
-          data value is toggled into or out of the point selection. If the expression
-          evaluates to ``false``, the point selection is first cleared, and the data value
-          is then inserted. For example, setting the value to the Vega expression ``"true"``
-          will toggle data values without the user pressing the shift-key.
-
-        **Default value:** ``true``
-
-        **See also:** `toggle examples
-        <https://vega.github.io/vega-lite/docs/selection.html#toggle>`__ in the
-        documentation.
-    """
-    _schema = {'$ref': '#/definitions/PointSelectionConfig'}
-
-    def __init__(self, type=Undefined, clear=Undefined, encodings=Undefined, fields=Undefined,
-                 nearest=Undefined, on=Undefined, resolve=Undefined, toggle=Undefined, **kwds):
-        super(PointSelectionConfig, self).__init__(type=type, clear=clear, encodings=encodings,
-                                                   fields=fields, nearest=nearest, on=on,
-                                                   resolve=resolve, toggle=toggle, **kwds)
-
-
-class PointSelectionConfigWithoutType(VegaLiteSchema):
-    """PointSelectionConfigWithoutType schema wrapper
-
-    Mapping(required=[])
-
-    Parameters
-    ----------
-
-    clear : anyOf(:class:`Stream`, string, boolean)
-        Clears the selection, emptying it of all values. This property can be a `Event
-        Stream <https://vega.github.io/vega/docs/event-streams/>`__ or ``false`` to disable
-        clear.
-
-        **Default value:** ``dblclick``.
-
-        **See also:** `clear examples
-        <https://vega.github.io/vega-lite/docs/selection.html#clear>`__ in the
-        documentation.
-    encodings : List(:class:`SingleDefUnitChannel`)
-        An array of encoding channels. The corresponding data field values must match for a
-        data tuple to fall within the selection.
-
-        **See also:** The `projection with encodings and fields section
-        <https://vega.github.io/vega-lite/docs/selection.html#project>`__ in the
-        documentation.
-    fields : List(:class:`FieldName`)
-        An array of field names whose values must match for a data tuple to fall within the
-        selection.
-
-        **See also:** The `projection with encodings and fields section
-        <https://vega.github.io/vega-lite/docs/selection.html#project>`__ in the
-        documentation.
-    nearest : boolean
-        When true, an invisible voronoi diagram is computed to accelerate discrete
-        selection. The data value *nearest* the mouse cursor is added to the selection.
-
-        **Default value:** ``false``, which means that data values must be interacted with
-        directly (e.g., clicked on) to be added to the selection.
-
-        **See also:** `nearest examples
-        <https://vega.github.io/vega-lite/docs/selection.html#nearest>`__ documentation.
-    on : anyOf(:class:`Stream`, string)
-        A `Vega event stream <https://vega.github.io/vega/docs/event-streams/>`__ (object or
-        selector) that triggers the selection. For interval selections, the event stream
-        must specify a `start and end
-        <https://vega.github.io/vega/docs/event-streams/#between-filters>`__.
-
-        **See also:** `on examples
-        <https://vega.github.io/vega-lite/docs/selection.html#on>`__ in the documentation.
-    resolve : :class:`SelectionResolution`
-        With layered and multi-view displays, a strategy that determines how selections'
-        data queries are resolved when applied in a filter transform, conditional encoding
-        rule, or scale domain.
-
-        One of:
-
-
-        * ``"global"`` -- only one brush exists for the entire SPLOM. When the user begins
-          to drag, any previous brushes are cleared, and a new one is constructed.
-        * ``"union"`` -- each cell contains its own brush, and points are highlighted if
-          they lie within *any* of these individual brushes.
-        * ``"intersect"`` -- each cell contains its own brush, and points are highlighted
-          only if they fall within *all* of these individual brushes.
-
-        **Default value:** ``global``.
-
-        **See also:** `resolve examples
-        <https://vega.github.io/vega-lite/docs/selection.html#resolve>`__ in the
-        documentation.
-    toggle : anyOf(string, boolean)
-        Controls whether data values should be toggled (inserted or removed from a point
-        selection) or only ever inserted into point selections.
-
-        One of:
-
-
-        * ``true`` -- the default behavior, which corresponds to ``"event.shiftKey"``.  As a
-          result, data values are toggled when the user interacts with the shift-key
-          pressed.
-        * ``false`` -- disables toggling behaviour; the selection will only ever contain a
-          single data value corresponding to the most recent interaction.
-        * A `Vega expression <https://vega.github.io/vega/docs/expressions/>`__ which is
-          re-evaluated as the user interacts. If the expression evaluates to ``true``, the
-          data value is toggled into or out of the point selection. If the expression
-          evaluates to ``false``, the point selection is first cleared, and the data value
-          is then inserted. For example, setting the value to the Vega expression ``"true"``
-          will toggle data values without the user pressing the shift-key.
-
-        **Default value:** ``true``
-
-        **See also:** `toggle examples
-        <https://vega.github.io/vega-lite/docs/selection.html#toggle>`__ in the
-        documentation.
-    """
-    _schema = {'$ref': '#/definitions/PointSelectionConfigWithoutType'}
-
-    def __init__(self, clear=Undefined, encodings=Undefined, fields=Undefined, nearest=Undefined,
-                 on=Undefined, resolve=Undefined, toggle=Undefined, **kwds):
-        super(PointSelectionConfigWithoutType, self).__init__(clear=clear, encodings=encodings,
-                                                              fields=fields, nearest=nearest, on=on,
-                                                              resolve=resolve, toggle=toggle, **kwds)
-
-
-class PolarDef(VegaLiteSchema):
-    """PolarDef schema wrapper
-
-    anyOf(:class:`PositionFieldDefBase`, :class:`PositionDatumDefBase`,
-    :class:`PositionValueDef`)
-    """
-    _schema = {'$ref': '#/definitions/PolarDef'}
-
-    def __init__(self, *args, **kwds):
-        super(PolarDef, self).__init__(*args, **kwds)
-
-
-class Polygon(Geometry):
-    """Polygon schema wrapper
-
-    Mapping(required=[coordinates, type])
-    Polygon geometry object. https://tools.ietf.org/html/rfc7946#section-3.1.6
-
-    Parameters
-    ----------
-
-    coordinates : List(List(:class:`Position`))
-
-    type : string
-        Specifies the type of GeoJSON object.
-    bbox : :class:`BBox`
-        Bounding box of the coordinate range of the object's Geometries, Features, or
-        Feature Collections. https://tools.ietf.org/html/rfc7946#section-5
-    """
-    _schema = {'$ref': '#/definitions/Polygon'}
-
-    def __init__(self, coordinates=Undefined, type=Undefined, bbox=Undefined, **kwds):
-        super(Polygon, self).__init__(coordinates=coordinates, type=type, bbox=bbox, **kwds)
-
-
-class Position(VegaLiteSchema):
-    """Position schema wrapper
-
-    List(float)
-    A Position is an array of coordinates. https://tools.ietf.org/html/rfc7946#section-3.1.1
-    Array should contain between two and three elements. The previous GeoJSON specification
-    allowed more elements (e.g., which could be used to represent M values), but the current
-    specification only allows X, Y, and (optionally) Z to be defined.
-    """
-    _schema = {'$ref': '#/definitions/Position'}
-
-    def __init__(self, *args):
-        super(Position, self).__init__(*args)
-
-
-class Position2Def(VegaLiteSchema):
-    """Position2Def schema wrapper
-
-    anyOf(:class:`SecondaryFieldDef`, :class:`DatumDef`, :class:`PositionValueDef`)
-    """
-    _schema = {'$ref': '#/definitions/Position2Def'}
-
-    def __init__(self, *args, **kwds):
-        super(Position2Def, self).__init__(*args, **kwds)
-
-
-class DatumDef(LatLongDef, Position2Def):
-    """DatumDef schema wrapper
-
-    Mapping(required=[])
-
-    Parameters
-    ----------
-
-    bandPosition : float
-        Relative position on a band of a stacked, binned, time unit, or band scale. For
-        example, the marks will be positioned at the beginning of the band if set to ``0``,
-        and at the middle of the band if set to ``0.5``.
-    datum : anyOf(:class:`PrimitiveValue`, :class:`DateTime`, :class:`ExprRef`, :class:`RepeatRef`)
-        A constant value in data domain.
-    title : anyOf(:class:`Text`, None)
-        A title for the field. If ``null``, the title will be removed.
-
-        **Default value:**  derived from the field's name and transformation function (
-        ``aggregate``, ``bin`` and ``timeUnit`` ). If the field has an aggregate function,
-        the function is displayed as part of the title (e.g., ``"Sum of Profit"`` ). If the
-        field is binned or has a time unit applied, the applied function is shown in
-        parentheses (e.g., ``"Profit (binned)"``, ``"Transaction Date (year-month)"`` ).
-        Otherwise, the title is simply the field name.
-
-        **Notes** :
-
-        1) You can customize the default field title format by providing the `fieldTitle
-        <https://vega.github.io/vega-lite/docs/config.html#top-level-config>`__ property in
-        the `config <https://vega.github.io/vega-lite/docs/config.html>`__ or `fieldTitle
-        function via the compile function's options
-        <https://vega.github.io/vega-lite/usage/compile.html#field-title>`__.
-
-        2) If both field definition's ``title`` and axis, header, or legend ``title`` are
-        defined, axis/header/legend title will be used.
-    type : :class:`Type`
-        The type of measurement ( ``"quantitative"``, ``"temporal"``, ``"ordinal"``, or
-        ``"nominal"`` ) for the encoded field or constant value ( ``datum`` ). It can also
-        be a ``"geojson"`` type for encoding `'geoshape'
-        <https://vega.github.io/vega-lite/docs/geoshape.html>`__.
-
-        Vega-Lite automatically infers data types in many cases as discussed below. However,
-        type is required for a field if: (1) the field is not nominal and the field encoding
-        has no specified ``aggregate`` (except ``argmin`` and ``argmax`` ), ``bin``, scale
-        type, custom ``sort`` order, nor ``timeUnit`` or (2) if you wish to use an ordinal
-        scale for a field with ``bin`` or ``timeUnit``.
-
-        **Default value:**
-
-        1) For a data ``field``, ``"nominal"`` is the default data type unless the field
-        encoding has ``aggregate``, ``channel``, ``bin``, scale type, ``sort``, or
-        ``timeUnit`` that satisfies the following criteria:
-
-
-        * ``"quantitative"`` is the default type if (1) the encoded field contains ``bin``
-          or ``aggregate`` except ``"argmin"`` and ``"argmax"``, (2) the encoding channel is
-          ``latitude`` or ``longitude`` channel or (3) if the specified scale type is `a
-          quantitative scale <https://vega.github.io/vega-lite/docs/scale.html#type>`__.
-        * ``"temporal"`` is the default type if (1) the encoded field contains ``timeUnit``
-          or (2) the specified scale type is a time or utc scale
-        * ``"ordinal"`` is the default type if (1) the encoded field contains a `custom sort
-          order
-          <https://vega.github.io/vega-lite/docs/sort.html#specifying-custom-sort-order>`__,
-          (2) the specified scale type is an ordinal/point/band scale, or (3) the encoding
-          channel is ``order``.
-
-        2) For a constant value in data domain ( ``datum`` ):
-
-
-        * ``"quantitative"`` if the datum is a number
-        * ``"nominal"`` if the datum is a string
-        * ``"temporal"`` if the datum is `a date time object
-          <https://vega.github.io/vega-lite/docs/datetime.html>`__
-
-        **Note:**
-
-
-        * Data ``type`` describes the semantics of the data rather than the primitive data
-          types (number, string, etc.). The same primitive data type can have different
-          types of measurement. For example, numeric data can represent quantitative,
-          ordinal, or nominal data.
-        * Data values for a temporal field can be either a date-time string (e.g.,
-          ``"2015-03-07 12:32:17"``, ``"17:01"``, ``"2015-03-16"``. ``"2015"`` ) or a
-          timestamp number (e.g., ``1552199579097`` ).
-        * When using with `bin <https://vega.github.io/vega-lite/docs/bin.html>`__, the
-          ``type`` property can be either ``"quantitative"`` (for using a linear bin scale)
-          or `"ordinal" (for using an ordinal bin scale)
-          <https://vega.github.io/vega-lite/docs/type.html#cast-bin>`__.
-        * When using with `timeUnit
-          <https://vega.github.io/vega-lite/docs/timeunit.html>`__, the ``type`` property
-          can be either ``"temporal"`` (default, for using a temporal scale) or `"ordinal"
-          (for using an ordinal scale)
-          <https://vega.github.io/vega-lite/docs/type.html#cast-bin>`__.
-        * When using with `aggregate
-          <https://vega.github.io/vega-lite/docs/aggregate.html>`__, the ``type`` property
-          refers to the post-aggregation data type. For example, we can calculate count
-          ``distinct`` of a categorical field ``"cat"`` using ``{"aggregate": "distinct",
-          "field": "cat"}``. The ``"type"`` of the aggregate output is ``"quantitative"``.
-        * Secondary channels (e.g., ``x2``, ``y2``, ``xError``, ``yError`` ) do not have
-          ``type`` as they must have exactly the same type as their primary channels (e.g.,
-          ``x``, ``y`` ).
-
-        **See also:** `type <https://vega.github.io/vega-lite/docs/type.html>`__
-        documentation.
-    """
-    _schema = {'$ref': '#/definitions/DatumDef'}
-
-    def __init__(self, bandPosition=Undefined, datum=Undefined, title=Undefined, type=Undefined, **kwds):
-        super(DatumDef, self).__init__(bandPosition=bandPosition, datum=datum, title=title, type=type,
-                                       **kwds)
-
-
-class PositionDatumDefBase(PolarDef):
-    """PositionDatumDefBase schema wrapper
-
-    Mapping(required=[])
-
-    Parameters
-    ----------
-
-    bandPosition : float
-        Relative position on a band of a stacked, binned, time unit, or band scale. For
-        example, the marks will be positioned at the beginning of the band if set to ``0``,
-        and at the middle of the band if set to ``0.5``.
-    datum : anyOf(:class:`PrimitiveValue`, :class:`DateTime`, :class:`ExprRef`, :class:`RepeatRef`)
-        A constant value in data domain.
-    scale : anyOf(:class:`Scale`, None)
-        An object defining properties of the channel's scale, which is the function that
-        transforms values in the data domain (numbers, dates, strings, etc) to visual values
-        (pixels, colors, sizes) of the encoding channels.
-
-        If ``null``, the scale will be `disabled and the data value will be directly encoded
-        <https://vega.github.io/vega-lite/docs/scale.html#disable>`__.
-
-        **Default value:** If undefined, default `scale properties
-        <https://vega.github.io/vega-lite/docs/scale.html>`__ are applied.
-
-        **See also:** `scale <https://vega.github.io/vega-lite/docs/scale.html>`__
-        documentation.
-    stack : anyOf(:class:`StackOffset`, None, boolean)
-        Type of stacking offset if the field should be stacked. ``stack`` is only applicable
-        for ``x``, ``y``, ``theta``, and ``radius`` channels with continuous domains. For
-        example, ``stack`` of ``y`` can be used to customize stacking for a vertical bar
-        chart.
-
-        ``stack`` can be one of the following values:
-
-
-        * ``"zero"`` or `true`: stacking with baseline offset at zero value of the scale
-          (for creating typical stacked
-          [bar](https://vega.github.io/vega-lite/docs/stack.html#bar) and `area
-          <https://vega.github.io/vega-lite/docs/stack.html#area>`__ chart).
-        * ``"normalize"`` - stacking with normalized domain (for creating `normalized
-          stacked bar and area charts
-          <https://vega.github.io/vega-lite/docs/stack.html#normalized>`__ and pie charts
-          `with percentage tooltip
-          <https://vega.github.io/vega-lite/docs/arc.html#tooltip>`__ ). :raw-html:`<br/>`
-        * ``"center"`` - stacking with center baseline (for `streamgraph
-          <https://vega.github.io/vega-lite/docs/stack.html#streamgraph>`__ ).
-        * ``null`` or ``false`` - No-stacking. This will produce layered `bar
-          <https://vega.github.io/vega-lite/docs/stack.html#layered-bar-chart>`__ and area
-          chart.
-
-        **Default value:** ``zero`` for plots with all of the following conditions are true:
-        (1) the mark is ``bar``, ``area``, or ``arc`` ; (2) the stacked measure channel (x
-        or y) has a linear scale; (3) At least one of non-position channels mapped to an
-        unaggregated field that is different from x and y. Otherwise, ``null`` by default.
-
-        **See also:** `stack <https://vega.github.io/vega-lite/docs/stack.html>`__
-        documentation.
-    title : anyOf(:class:`Text`, None)
-        A title for the field. If ``null``, the title will be removed.
-
-        **Default value:**  derived from the field's name and transformation function (
-        ``aggregate``, ``bin`` and ``timeUnit`` ). If the field has an aggregate function,
-        the function is displayed as part of the title (e.g., ``"Sum of Profit"`` ). If the
-        field is binned or has a time unit applied, the applied function is shown in
-        parentheses (e.g., ``"Profit (binned)"``, ``"Transaction Date (year-month)"`` ).
-        Otherwise, the title is simply the field name.
-
-        **Notes** :
-
-        1) You can customize the default field title format by providing the `fieldTitle
-        <https://vega.github.io/vega-lite/docs/config.html#top-level-config>`__ property in
-        the `config <https://vega.github.io/vega-lite/docs/config.html>`__ or `fieldTitle
-        function via the compile function's options
-        <https://vega.github.io/vega-lite/usage/compile.html#field-title>`__.
-
-        2) If both field definition's ``title`` and axis, header, or legend ``title`` are
-        defined, axis/header/legend title will be used.
-    type : :class:`Type`
-        The type of measurement ( ``"quantitative"``, ``"temporal"``, ``"ordinal"``, or
-        ``"nominal"`` ) for the encoded field or constant value ( ``datum`` ). It can also
-        be a ``"geojson"`` type for encoding `'geoshape'
-        <https://vega.github.io/vega-lite/docs/geoshape.html>`__.
-
-        Vega-Lite automatically infers data types in many cases as discussed below. However,
-        type is required for a field if: (1) the field is not nominal and the field encoding
-        has no specified ``aggregate`` (except ``argmin`` and ``argmax`` ), ``bin``, scale
-        type, custom ``sort`` order, nor ``timeUnit`` or (2) if you wish to use an ordinal
-        scale for a field with ``bin`` or ``timeUnit``.
-
-        **Default value:**
-
-        1) For a data ``field``, ``"nominal"`` is the default data type unless the field
-        encoding has ``aggregate``, ``channel``, ``bin``, scale type, ``sort``, or
-        ``timeUnit`` that satisfies the following criteria:
-
-
-        * ``"quantitative"`` is the default type if (1) the encoded field contains ``bin``
-          or ``aggregate`` except ``"argmin"`` and ``"argmax"``, (2) the encoding channel is
-          ``latitude`` or ``longitude`` channel or (3) if the specified scale type is `a
-          quantitative scale <https://vega.github.io/vega-lite/docs/scale.html#type>`__.
-        * ``"temporal"`` is the default type if (1) the encoded field contains ``timeUnit``
-          or (2) the specified scale type is a time or utc scale
-        * ``"ordinal"`` is the default type if (1) the encoded field contains a `custom sort
-          order
-          <https://vega.github.io/vega-lite/docs/sort.html#specifying-custom-sort-order>`__,
-          (2) the specified scale type is an ordinal/point/band scale, or (3) the encoding
-          channel is ``order``.
-
-        2) For a constant value in data domain ( ``datum`` ):
-
-
-        * ``"quantitative"`` if the datum is a number
-        * ``"nominal"`` if the datum is a string
-        * ``"temporal"`` if the datum is `a date time object
-          <https://vega.github.io/vega-lite/docs/datetime.html>`__
-
-        **Note:**
-
-
-        * Data ``type`` describes the semantics of the data rather than the primitive data
-          types (number, string, etc.). The same primitive data type can have different
-          types of measurement. For example, numeric data can represent quantitative,
-          ordinal, or nominal data.
-        * Data values for a temporal field can be either a date-time string (e.g.,
-          ``"2015-03-07 12:32:17"``, ``"17:01"``, ``"2015-03-16"``. ``"2015"`` ) or a
-          timestamp number (e.g., ``1552199579097`` ).
-        * When using with `bin <https://vega.github.io/vega-lite/docs/bin.html>`__, the
-          ``type`` property can be either ``"quantitative"`` (for using a linear bin scale)
-          or `"ordinal" (for using an ordinal bin scale)
-          <https://vega.github.io/vega-lite/docs/type.html#cast-bin>`__.
-        * When using with `timeUnit
-          <https://vega.github.io/vega-lite/docs/timeunit.html>`__, the ``type`` property
-          can be either ``"temporal"`` (default, for using a temporal scale) or `"ordinal"
-          (for using an ordinal scale)
-          <https://vega.github.io/vega-lite/docs/type.html#cast-bin>`__.
-        * When using with `aggregate
-          <https://vega.github.io/vega-lite/docs/aggregate.html>`__, the ``type`` property
-          refers to the post-aggregation data type. For example, we can calculate count
-          ``distinct`` of a categorical field ``"cat"`` using ``{"aggregate": "distinct",
-          "field": "cat"}``. The ``"type"`` of the aggregate output is ``"quantitative"``.
-        * Secondary channels (e.g., ``x2``, ``y2``, ``xError``, ``yError`` ) do not have
-          ``type`` as they must have exactly the same type as their primary channels (e.g.,
-          ``x``, ``y`` ).
-
-        **See also:** `type <https://vega.github.io/vega-lite/docs/type.html>`__
-        documentation.
-    """
-    _schema = {'$ref': '#/definitions/PositionDatumDefBase'}
-
-    def __init__(self, bandPosition=Undefined, datum=Undefined, scale=Undefined, stack=Undefined,
-                 title=Undefined, type=Undefined, **kwds):
-        super(PositionDatumDefBase, self).__init__(bandPosition=bandPosition, datum=datum, scale=scale,
-                                                   stack=stack, title=title, type=type, **kwds)
-
-
-class PositionDef(VegaLiteSchema):
-    """PositionDef schema wrapper
-
-    anyOf(:class:`PositionFieldDef`, :class:`PositionDatumDef`, :class:`PositionValueDef`)
-    """
-    _schema = {'$ref': '#/definitions/PositionDef'}
-
-    def __init__(self, *args, **kwds):
-        super(PositionDef, self).__init__(*args, **kwds)
-
-
-class PositionDatumDef(PositionDef):
-    """PositionDatumDef schema wrapper
-
-    Mapping(required=[])
-
-    Parameters
-    ----------
-
-    axis : anyOf(:class:`Axis`, None)
-        An object defining properties of axis's gridlines, ticks and labels. If ``null``,
-        the axis for the encoding channel will be removed.
-
-        **Default value:** If undefined, default `axis properties
-        <https://vega.github.io/vega-lite/docs/axis.html>`__ are applied.
-
-        **See also:** `axis <https://vega.github.io/vega-lite/docs/axis.html>`__
-        documentation.
-    bandPosition : float
-        Relative position on a band of a stacked, binned, time unit, or band scale. For
-        example, the marks will be positioned at the beginning of the band if set to ``0``,
-        and at the middle of the band if set to ``0.5``.
-    datum : anyOf(:class:`PrimitiveValue`, :class:`DateTime`, :class:`ExprRef`, :class:`RepeatRef`)
-        A constant value in data domain.
-    impute : anyOf(:class:`ImputeParams`, None)
-        An object defining the properties of the Impute Operation to be applied. The field
-        value of the other positional channel is taken as ``key`` of the ``Impute``
-        Operation. The field of the ``color`` channel if specified is used as ``groupby`` of
-        the ``Impute`` Operation.
-
-        **See also:** `impute <https://vega.github.io/vega-lite/docs/impute.html>`__
-        documentation.
-    scale : anyOf(:class:`Scale`, None)
-        An object defining properties of the channel's scale, which is the function that
-        transforms values in the data domain (numbers, dates, strings, etc) to visual values
-        (pixels, colors, sizes) of the encoding channels.
-
-        If ``null``, the scale will be `disabled and the data value will be directly encoded
-        <https://vega.github.io/vega-lite/docs/scale.html#disable>`__.
-
-        **Default value:** If undefined, default `scale properties
-        <https://vega.github.io/vega-lite/docs/scale.html>`__ are applied.
-
-        **See also:** `scale <https://vega.github.io/vega-lite/docs/scale.html>`__
-        documentation.
-    stack : anyOf(:class:`StackOffset`, None, boolean)
-        Type of stacking offset if the field should be stacked. ``stack`` is only applicable
-        for ``x``, ``y``, ``theta``, and ``radius`` channels with continuous domains. For
-        example, ``stack`` of ``y`` can be used to customize stacking for a vertical bar
-        chart.
-
-        ``stack`` can be one of the following values:
-
-
-        * ``"zero"`` or `true`: stacking with baseline offset at zero value of the scale
-          (for creating typical stacked
-          [bar](https://vega.github.io/vega-lite/docs/stack.html#bar) and `area
-          <https://vega.github.io/vega-lite/docs/stack.html#area>`__ chart).
-        * ``"normalize"`` - stacking with normalized domain (for creating `normalized
-          stacked bar and area charts
-          <https://vega.github.io/vega-lite/docs/stack.html#normalized>`__ and pie charts
-          `with percentage tooltip
-          <https://vega.github.io/vega-lite/docs/arc.html#tooltip>`__ ). :raw-html:`<br/>`
-        * ``"center"`` - stacking with center baseline (for `streamgraph
-          <https://vega.github.io/vega-lite/docs/stack.html#streamgraph>`__ ).
-        * ``null`` or ``false`` - No-stacking. This will produce layered `bar
-          <https://vega.github.io/vega-lite/docs/stack.html#layered-bar-chart>`__ and area
-          chart.
-
-        **Default value:** ``zero`` for plots with all of the following conditions are true:
-        (1) the mark is ``bar``, ``area``, or ``arc`` ; (2) the stacked measure channel (x
-        or y) has a linear scale; (3) At least one of non-position channels mapped to an
-        unaggregated field that is different from x and y. Otherwise, ``null`` by default.
-
-        **See also:** `stack <https://vega.github.io/vega-lite/docs/stack.html>`__
-        documentation.
-    title : anyOf(:class:`Text`, None)
-        A title for the field. If ``null``, the title will be removed.
-
-        **Default value:**  derived from the field's name and transformation function (
-        ``aggregate``, ``bin`` and ``timeUnit`` ). If the field has an aggregate function,
-        the function is displayed as part of the title (e.g., ``"Sum of Profit"`` ). If the
-        field is binned or has a time unit applied, the applied function is shown in
-        parentheses (e.g., ``"Profit (binned)"``, ``"Transaction Date (year-month)"`` ).
-        Otherwise, the title is simply the field name.
-
-        **Notes** :
-
-        1) You can customize the default field title format by providing the `fieldTitle
-        <https://vega.github.io/vega-lite/docs/config.html#top-level-config>`__ property in
-        the `config <https://vega.github.io/vega-lite/docs/config.html>`__ or `fieldTitle
-        function via the compile function's options
-        <https://vega.github.io/vega-lite/usage/compile.html#field-title>`__.
-
-        2) If both field definition's ``title`` and axis, header, or legend ``title`` are
-        defined, axis/header/legend title will be used.
-    type : :class:`Type`
-        The type of measurement ( ``"quantitative"``, ``"temporal"``, ``"ordinal"``, or
-        ``"nominal"`` ) for the encoded field or constant value ( ``datum`` ). It can also
-        be a ``"geojson"`` type for encoding `'geoshape'
-        <https://vega.github.io/vega-lite/docs/geoshape.html>`__.
-
-        Vega-Lite automatically infers data types in many cases as discussed below. However,
-        type is required for a field if: (1) the field is not nominal and the field encoding
-        has no specified ``aggregate`` (except ``argmin`` and ``argmax`` ), ``bin``, scale
-        type, custom ``sort`` order, nor ``timeUnit`` or (2) if you wish to use an ordinal
-        scale for a field with ``bin`` or ``timeUnit``.
-
-        **Default value:**
-
-        1) For a data ``field``, ``"nominal"`` is the default data type unless the field
-        encoding has ``aggregate``, ``channel``, ``bin``, scale type, ``sort``, or
-        ``timeUnit`` that satisfies the following criteria:
-
-
-        * ``"quantitative"`` is the default type if (1) the encoded field contains ``bin``
-          or ``aggregate`` except ``"argmin"`` and ``"argmax"``, (2) the encoding channel is
-          ``latitude`` or ``longitude`` channel or (3) if the specified scale type is `a
-          quantitative scale <https://vega.github.io/vega-lite/docs/scale.html#type>`__.
-        * ``"temporal"`` is the default type if (1) the encoded field contains ``timeUnit``
-          or (2) the specified scale type is a time or utc scale
-        * ``"ordinal"`` is the default type if (1) the encoded field contains a `custom sort
-          order
-          <https://vega.github.io/vega-lite/docs/sort.html#specifying-custom-sort-order>`__,
-          (2) the specified scale type is an ordinal/point/band scale, or (3) the encoding
-          channel is ``order``.
-
-        2) For a constant value in data domain ( ``datum`` ):
-
-
-        * ``"quantitative"`` if the datum is a number
-        * ``"nominal"`` if the datum is a string
-        * ``"temporal"`` if the datum is `a date time object
-          <https://vega.github.io/vega-lite/docs/datetime.html>`__
-
-        **Note:**
-
-
-        * Data ``type`` describes the semantics of the data rather than the primitive data
-          types (number, string, etc.). The same primitive data type can have different
-          types of measurement. For example, numeric data can represent quantitative,
-          ordinal, or nominal data.
-        * Data values for a temporal field can be either a date-time string (e.g.,
-          ``"2015-03-07 12:32:17"``, ``"17:01"``, ``"2015-03-16"``. ``"2015"`` ) or a
-          timestamp number (e.g., ``1552199579097`` ).
-        * When using with `bin <https://vega.github.io/vega-lite/docs/bin.html>`__, the
-          ``type`` property can be either ``"quantitative"`` (for using a linear bin scale)
-          or `"ordinal" (for using an ordinal bin scale)
-          <https://vega.github.io/vega-lite/docs/type.html#cast-bin>`__.
-        * When using with `timeUnit
-          <https://vega.github.io/vega-lite/docs/timeunit.html>`__, the ``type`` property
-          can be either ``"temporal"`` (default, for using a temporal scale) or `"ordinal"
-          (for using an ordinal scale)
-          <https://vega.github.io/vega-lite/docs/type.html#cast-bin>`__.
-        * When using with `aggregate
-          <https://vega.github.io/vega-lite/docs/aggregate.html>`__, the ``type`` property
-          refers to the post-aggregation data type. For example, we can calculate count
-          ``distinct`` of a categorical field ``"cat"`` using ``{"aggregate": "distinct",
-          "field": "cat"}``. The ``"type"`` of the aggregate output is ``"quantitative"``.
-        * Secondary channels (e.g., ``x2``, ``y2``, ``xError``, ``yError`` ) do not have
-          ``type`` as they must have exactly the same type as their primary channels (e.g.,
-          ``x``, ``y`` ).
-
-        **See also:** `type <https://vega.github.io/vega-lite/docs/type.html>`__
-        documentation.
-    """
-    _schema = {'$ref': '#/definitions/PositionDatumDef'}
-
-    def __init__(self, axis=Undefined, bandPosition=Undefined, datum=Undefined, impute=Undefined,
-                 scale=Undefined, stack=Undefined, title=Undefined, type=Undefined, **kwds):
-        super(PositionDatumDef, self).__init__(axis=axis, bandPosition=bandPosition, datum=datum,
-                                               impute=impute, scale=scale, stack=stack, title=title,
-                                               type=type, **kwds)
-
-
-class PositionFieldDef(PositionDef):
-    """PositionFieldDef schema wrapper
-
-    Mapping(required=[])
-
-    Parameters
-    ----------
-
-    aggregate : :class:`Aggregate`
-        Aggregation function for the field (e.g., ``"mean"``, ``"sum"``, ``"median"``,
-        ``"min"``, ``"max"``, ``"count"`` ).
-
-        **Default value:** ``undefined`` (None)
-
-        **See also:** `aggregate <https://vega.github.io/vega-lite/docs/aggregate.html>`__
-        documentation.
-    axis : anyOf(:class:`Axis`, None)
-        An object defining properties of axis's gridlines, ticks and labels. If ``null``,
-        the axis for the encoding channel will be removed.
-
-        **Default value:** If undefined, default `axis properties
-        <https://vega.github.io/vega-lite/docs/axis.html>`__ are applied.
-
-        **See also:** `axis <https://vega.github.io/vega-lite/docs/axis.html>`__
-        documentation.
-    bandPosition : float
-        Relative position on a band of a stacked, binned, time unit, or band scale. For
-        example, the marks will be positioned at the beginning of the band if set to ``0``,
-        and at the middle of the band if set to ``0.5``.
-    bin : anyOf(boolean, :class:`BinParams`, string, None)
-        A flag for binning a ``quantitative`` field, `an object defining binning parameters
-        <https://vega.github.io/vega-lite/docs/bin.html#bin-parameters>`__, or indicating
-        that the data for ``x`` or ``y`` channel are binned before they are imported into
-        Vega-Lite ( ``"binned"`` ).
-
-
-        If ``true``, default `binning parameters
-        <https://vega.github.io/vega-lite/docs/bin.html#bin-parameters>`__ will be applied.
-
-        If ``"binned"``, this indicates that the data for the ``x`` (or ``y`` ) channel are
-        already binned. You can map the bin-start field to ``x`` (or ``y`` ) and the bin-end
-        field to ``x2`` (or ``y2`` ). The scale and axis will be formatted similar to
-        binning in Vega-Lite.  To adjust the axis ticks based on the bin step, you can also
-        set the axis's `tickMinStep
-        <https://vega.github.io/vega-lite/docs/axis.html#ticks>`__ property.
-
-        **Default value:** ``false``
-
-        **See also:** `bin <https://vega.github.io/vega-lite/docs/bin.html>`__
-        documentation.
-    field : :class:`Field`
-        **Required.** A string defining the name of the field from which to pull a data
-        value or an object defining iterated values from the `repeat
-        <https://vega.github.io/vega-lite/docs/repeat.html>`__ operator.
-
-        **See also:** `field <https://vega.github.io/vega-lite/docs/field.html>`__
-        documentation.
-
-        **Notes:** 1)  Dots ( ``.`` ) and brackets ( ``[`` and ``]`` ) can be used to access
-        nested objects (e.g., ``"field": "foo.bar"`` and ``"field": "foo['bar']"`` ). If
-        field names contain dots or brackets but are not nested, you can use ``\\`` to
-        escape dots and brackets (e.g., ``"a\\.b"`` and ``"a\\[0\\]"`` ). See more details
-        about escaping in the `field documentation
-        <https://vega.github.io/vega-lite/docs/field.html>`__. 2) ``field`` is not required
-        if ``aggregate`` is ``count``.
-    impute : anyOf(:class:`ImputeParams`, None)
-        An object defining the properties of the Impute Operation to be applied. The field
-        value of the other positional channel is taken as ``key`` of the ``Impute``
-        Operation. The field of the ``color`` channel if specified is used as ``groupby`` of
-        the ``Impute`` Operation.
-
-        **See also:** `impute <https://vega.github.io/vega-lite/docs/impute.html>`__
-        documentation.
-    scale : anyOf(:class:`Scale`, None)
-        An object defining properties of the channel's scale, which is the function that
-        transforms values in the data domain (numbers, dates, strings, etc) to visual values
-        (pixels, colors, sizes) of the encoding channels.
-
-        If ``null``, the scale will be `disabled and the data value will be directly encoded
-        <https://vega.github.io/vega-lite/docs/scale.html#disable>`__.
-
-        **Default value:** If undefined, default `scale properties
-        <https://vega.github.io/vega-lite/docs/scale.html>`__ are applied.
-
-        **See also:** `scale <https://vega.github.io/vega-lite/docs/scale.html>`__
-        documentation.
-    sort : :class:`Sort`
-        Sort order for the encoded field.
-
-        For continuous fields (quantitative or temporal), ``sort`` can be either
-        ``"ascending"`` or ``"descending"``.
-
-        For discrete fields, ``sort`` can be one of the following:
-
-
-        * ``"ascending"`` or ``"descending"`` -- for sorting by the values' natural order in
-          JavaScript.
-        * `A string indicating an encoding channel name to sort by
-          <https://vega.github.io/vega-lite/docs/sort.html#sort-by-encoding>`__ (e.g.,
-          ``"x"`` or ``"y"`` ) with an optional minus prefix for descending sort (e.g.,
-          ``"-x"`` to sort by x-field, descending). This channel string is short-form of `a
-          sort-by-encoding definition
-          <https://vega.github.io/vega-lite/docs/sort.html#sort-by-encoding>`__. For
-          example, ``"sort": "-x"`` is equivalent to ``"sort": {"encoding": "x", "order":
-          "descending"}``.
-        * `A sort field definition
-          <https://vega.github.io/vega-lite/docs/sort.html#sort-field>`__ for sorting by
-          another field.
-        * `An array specifying the field values in preferred order
-          <https://vega.github.io/vega-lite/docs/sort.html#sort-array>`__. In this case, the
-          sort order will obey the values in the array, followed by any unspecified values
-          in their original order. For discrete time field, values in the sort array can be
-          `date-time definition objects
-          <https://vega.github.io/vega-lite/docs/datetime.html>`__. In addition, for time
-          units ``"month"`` and ``"day"``, the values can be the month or day names (case
-          insensitive) or their 3-letter initials (e.g., ``"Mon"``, ``"Tue"`` ).
-        * ``null`` indicating no sort.
-
-        **Default value:** ``"ascending"``
-
-        **Note:** ``null`` and sorting by another channel is not supported for ``row`` and
-        ``column``.
-
-        **See also:** `sort <https://vega.github.io/vega-lite/docs/sort.html>`__
-        documentation.
-    stack : anyOf(:class:`StackOffset`, None, boolean)
-        Type of stacking offset if the field should be stacked. ``stack`` is only applicable
-        for ``x``, ``y``, ``theta``, and ``radius`` channels with continuous domains. For
-        example, ``stack`` of ``y`` can be used to customize stacking for a vertical bar
-        chart.
-
-        ``stack`` can be one of the following values:
-
-
-        * ``"zero"`` or `true`: stacking with baseline offset at zero value of the scale
-          (for creating typical stacked
-          [bar](https://vega.github.io/vega-lite/docs/stack.html#bar) and `area
-          <https://vega.github.io/vega-lite/docs/stack.html#area>`__ chart).
-        * ``"normalize"`` - stacking with normalized domain (for creating `normalized
-          stacked bar and area charts
-          <https://vega.github.io/vega-lite/docs/stack.html#normalized>`__ and pie charts
-          `with percentage tooltip
-          <https://vega.github.io/vega-lite/docs/arc.html#tooltip>`__ ). :raw-html:`<br/>`
-        * ``"center"`` - stacking with center baseline (for `streamgraph
-          <https://vega.github.io/vega-lite/docs/stack.html#streamgraph>`__ ).
-        * ``null`` or ``false`` - No-stacking. This will produce layered `bar
-          <https://vega.github.io/vega-lite/docs/stack.html#layered-bar-chart>`__ and area
-          chart.
-
-        **Default value:** ``zero`` for plots with all of the following conditions are true:
-        (1) the mark is ``bar``, ``area``, or ``arc`` ; (2) the stacked measure channel (x
-        or y) has a linear scale; (3) At least one of non-position channels mapped to an
-        unaggregated field that is different from x and y. Otherwise, ``null`` by default.
-
-        **See also:** `stack <https://vega.github.io/vega-lite/docs/stack.html>`__
-        documentation.
-    timeUnit : anyOf(:class:`TimeUnit`, :class:`BinnedTimeUnit`, :class:`TimeUnitParams`)
-        Time unit (e.g., ``year``, ``yearmonth``, ``month``, ``hours`` ) for a temporal
-        field. or `a temporal field that gets casted as ordinal
-        <https://vega.github.io/vega-lite/docs/type.html#cast>`__.
-
-        **Default value:** ``undefined`` (None)
-
-        **See also:** `timeUnit <https://vega.github.io/vega-lite/docs/timeunit.html>`__
-        documentation.
-    title : anyOf(:class:`Text`, None)
-        A title for the field. If ``null``, the title will be removed.
-
-        **Default value:**  derived from the field's name and transformation function (
-        ``aggregate``, ``bin`` and ``timeUnit`` ). If the field has an aggregate function,
-        the function is displayed as part of the title (e.g., ``"Sum of Profit"`` ). If the
-        field is binned or has a time unit applied, the applied function is shown in
-        parentheses (e.g., ``"Profit (binned)"``, ``"Transaction Date (year-month)"`` ).
-        Otherwise, the title is simply the field name.
-
-        **Notes** :
-
-        1) You can customize the default field title format by providing the `fieldTitle
-        <https://vega.github.io/vega-lite/docs/config.html#top-level-config>`__ property in
-        the `config <https://vega.github.io/vega-lite/docs/config.html>`__ or `fieldTitle
-        function via the compile function's options
-        <https://vega.github.io/vega-lite/usage/compile.html#field-title>`__.
-
-        2) If both field definition's ``title`` and axis, header, or legend ``title`` are
-        defined, axis/header/legend title will be used.
-    type : :class:`StandardType`
-        The type of measurement ( ``"quantitative"``, ``"temporal"``, ``"ordinal"``, or
-        ``"nominal"`` ) for the encoded field or constant value ( ``datum`` ). It can also
-        be a ``"geojson"`` type for encoding `'geoshape'
-        <https://vega.github.io/vega-lite/docs/geoshape.html>`__.
-
-        Vega-Lite automatically infers data types in many cases as discussed below. However,
-        type is required for a field if: (1) the field is not nominal and the field encoding
-        has no specified ``aggregate`` (except ``argmin`` and ``argmax`` ), ``bin``, scale
-        type, custom ``sort`` order, nor ``timeUnit`` or (2) if you wish to use an ordinal
-        scale for a field with ``bin`` or ``timeUnit``.
-
-        **Default value:**
-
-        1) For a data ``field``, ``"nominal"`` is the default data type unless the field
-        encoding has ``aggregate``, ``channel``, ``bin``, scale type, ``sort``, or
-        ``timeUnit`` that satisfies the following criteria:
-
-
-        * ``"quantitative"`` is the default type if (1) the encoded field contains ``bin``
-          or ``aggregate`` except ``"argmin"`` and ``"argmax"``, (2) the encoding channel is
-          ``latitude`` or ``longitude`` channel or (3) if the specified scale type is `a
-          quantitative scale <https://vega.github.io/vega-lite/docs/scale.html#type>`__.
-        * ``"temporal"`` is the default type if (1) the encoded field contains ``timeUnit``
-          or (2) the specified scale type is a time or utc scale
-        * ``"ordinal"`` is the default type if (1) the encoded field contains a `custom sort
-          order
-          <https://vega.github.io/vega-lite/docs/sort.html#specifying-custom-sort-order>`__,
-          (2) the specified scale type is an ordinal/point/band scale, or (3) the encoding
-          channel is ``order``.
-
-        2) For a constant value in data domain ( ``datum`` ):
-
-
-        * ``"quantitative"`` if the datum is a number
-        * ``"nominal"`` if the datum is a string
-        * ``"temporal"`` if the datum is `a date time object
-          <https://vega.github.io/vega-lite/docs/datetime.html>`__
-
-        **Note:**
-
-
-        * Data ``type`` describes the semantics of the data rather than the primitive data
-          types (number, string, etc.). The same primitive data type can have different
-          types of measurement. For example, numeric data can represent quantitative,
-          ordinal, or nominal data.
-        * Data values for a temporal field can be either a date-time string (e.g.,
-          ``"2015-03-07 12:32:17"``, ``"17:01"``, ``"2015-03-16"``. ``"2015"`` ) or a
-          timestamp number (e.g., ``1552199579097`` ).
-        * When using with `bin <https://vega.github.io/vega-lite/docs/bin.html>`__, the
-          ``type`` property can be either ``"quantitative"`` (for using a linear bin scale)
-          or `"ordinal" (for using an ordinal bin scale)
-          <https://vega.github.io/vega-lite/docs/type.html#cast-bin>`__.
-        * When using with `timeUnit
-          <https://vega.github.io/vega-lite/docs/timeunit.html>`__, the ``type`` property
-          can be either ``"temporal"`` (default, for using a temporal scale) or `"ordinal"
-          (for using an ordinal scale)
-          <https://vega.github.io/vega-lite/docs/type.html#cast-bin>`__.
-        * When using with `aggregate
-          <https://vega.github.io/vega-lite/docs/aggregate.html>`__, the ``type`` property
-          refers to the post-aggregation data type. For example, we can calculate count
-          ``distinct`` of a categorical field ``"cat"`` using ``{"aggregate": "distinct",
-          "field": "cat"}``. The ``"type"`` of the aggregate output is ``"quantitative"``.
-        * Secondary channels (e.g., ``x2``, ``y2``, ``xError``, ``yError`` ) do not have
-          ``type`` as they must have exactly the same type as their primary channels (e.g.,
-          ``x``, ``y`` ).
-
-        **See also:** `type <https://vega.github.io/vega-lite/docs/type.html>`__
-        documentation.
-    """
-    _schema = {'$ref': '#/definitions/PositionFieldDef'}
-
-    def __init__(self, aggregate=Undefined, axis=Undefined, bandPosition=Undefined, bin=Undefined,
-                 field=Undefined, impute=Undefined, scale=Undefined, sort=Undefined, stack=Undefined,
-                 timeUnit=Undefined, title=Undefined, type=Undefined, **kwds):
-        super(PositionFieldDef, self).__init__(aggregate=aggregate, axis=axis,
-                                               bandPosition=bandPosition, bin=bin, field=field,
-                                               impute=impute, scale=scale, sort=sort, stack=stack,
-                                               timeUnit=timeUnit, title=title, type=type, **kwds)
-
-
-class PositionFieldDefBase(PolarDef):
-    """PositionFieldDefBase schema wrapper
-
-    Mapping(required=[])
-
-    Parameters
-    ----------
-
-    aggregate : :class:`Aggregate`
-        Aggregation function for the field (e.g., ``"mean"``, ``"sum"``, ``"median"``,
-        ``"min"``, ``"max"``, ``"count"`` ).
-
-        **Default value:** ``undefined`` (None)
-
-        **See also:** `aggregate <https://vega.github.io/vega-lite/docs/aggregate.html>`__
-        documentation.
-    bandPosition : float
-        Relative position on a band of a stacked, binned, time unit, or band scale. For
-        example, the marks will be positioned at the beginning of the band if set to ``0``,
-        and at the middle of the band if set to ``0.5``.
-    bin : anyOf(boolean, :class:`BinParams`, string, None)
-        A flag for binning a ``quantitative`` field, `an object defining binning parameters
-        <https://vega.github.io/vega-lite/docs/bin.html#bin-parameters>`__, or indicating
-        that the data for ``x`` or ``y`` channel are binned before they are imported into
-        Vega-Lite ( ``"binned"`` ).
-
-
-        If ``true``, default `binning parameters
-        <https://vega.github.io/vega-lite/docs/bin.html#bin-parameters>`__ will be applied.
-
-        If ``"binned"``, this indicates that the data for the ``x`` (or ``y`` ) channel are
-        already binned. You can map the bin-start field to ``x`` (or ``y`` ) and the bin-end
-        field to ``x2`` (or ``y2`` ). The scale and axis will be formatted similar to
-        binning in Vega-Lite.  To adjust the axis ticks based on the bin step, you can also
-        set the axis's `tickMinStep
-        <https://vega.github.io/vega-lite/docs/axis.html#ticks>`__ property.
-
-        **Default value:** ``false``
-
-        **See also:** `bin <https://vega.github.io/vega-lite/docs/bin.html>`__
-        documentation.
-    field : :class:`Field`
-        **Required.** A string defining the name of the field from which to pull a data
-        value or an object defining iterated values from the `repeat
-        <https://vega.github.io/vega-lite/docs/repeat.html>`__ operator.
-
-        **See also:** `field <https://vega.github.io/vega-lite/docs/field.html>`__
-        documentation.
-
-        **Notes:** 1)  Dots ( ``.`` ) and brackets ( ``[`` and ``]`` ) can be used to access
-        nested objects (e.g., ``"field": "foo.bar"`` and ``"field": "foo['bar']"`` ). If
-        field names contain dots or brackets but are not nested, you can use ``\\`` to
-        escape dots and brackets (e.g., ``"a\\.b"`` and ``"a\\[0\\]"`` ). See more details
-        about escaping in the `field documentation
-        <https://vega.github.io/vega-lite/docs/field.html>`__. 2) ``field`` is not required
-        if ``aggregate`` is ``count``.
-    scale : anyOf(:class:`Scale`, None)
-        An object defining properties of the channel's scale, which is the function that
-        transforms values in the data domain (numbers, dates, strings, etc) to visual values
-        (pixels, colors, sizes) of the encoding channels.
-
-        If ``null``, the scale will be `disabled and the data value will be directly encoded
-        <https://vega.github.io/vega-lite/docs/scale.html#disable>`__.
-
-        **Default value:** If undefined, default `scale properties
-        <https://vega.github.io/vega-lite/docs/scale.html>`__ are applied.
-
-        **See also:** `scale <https://vega.github.io/vega-lite/docs/scale.html>`__
-        documentation.
-    sort : :class:`Sort`
-        Sort order for the encoded field.
-
-        For continuous fields (quantitative or temporal), ``sort`` can be either
-        ``"ascending"`` or ``"descending"``.
-
-        For discrete fields, ``sort`` can be one of the following:
-
-
-        * ``"ascending"`` or ``"descending"`` -- for sorting by the values' natural order in
-          JavaScript.
-        * `A string indicating an encoding channel name to sort by
-          <https://vega.github.io/vega-lite/docs/sort.html#sort-by-encoding>`__ (e.g.,
-          ``"x"`` or ``"y"`` ) with an optional minus prefix for descending sort (e.g.,
-          ``"-x"`` to sort by x-field, descending). This channel string is short-form of `a
-          sort-by-encoding definition
-          <https://vega.github.io/vega-lite/docs/sort.html#sort-by-encoding>`__. For
-          example, ``"sort": "-x"`` is equivalent to ``"sort": {"encoding": "x", "order":
-          "descending"}``.
-        * `A sort field definition
-          <https://vega.github.io/vega-lite/docs/sort.html#sort-field>`__ for sorting by
-          another field.
-        * `An array specifying the field values in preferred order
-          <https://vega.github.io/vega-lite/docs/sort.html#sort-array>`__. In this case, the
-          sort order will obey the values in the array, followed by any unspecified values
-          in their original order. For discrete time field, values in the sort array can be
-          `date-time definition objects
-          <https://vega.github.io/vega-lite/docs/datetime.html>`__. In addition, for time
-          units ``"month"`` and ``"day"``, the values can be the month or day names (case
-          insensitive) or their 3-letter initials (e.g., ``"Mon"``, ``"Tue"`` ).
-        * ``null`` indicating no sort.
-
-        **Default value:** ``"ascending"``
-
-        **Note:** ``null`` and sorting by another channel is not supported for ``row`` and
-        ``column``.
-
-        **See also:** `sort <https://vega.github.io/vega-lite/docs/sort.html>`__
-        documentation.
-    stack : anyOf(:class:`StackOffset`, None, boolean)
-        Type of stacking offset if the field should be stacked. ``stack`` is only applicable
-        for ``x``, ``y``, ``theta``, and ``radius`` channels with continuous domains. For
-        example, ``stack`` of ``y`` can be used to customize stacking for a vertical bar
-        chart.
-
-        ``stack`` can be one of the following values:
-
-
-        * ``"zero"`` or `true`: stacking with baseline offset at zero value of the scale
-          (for creating typical stacked
-          [bar](https://vega.github.io/vega-lite/docs/stack.html#bar) and `area
-          <https://vega.github.io/vega-lite/docs/stack.html#area>`__ chart).
-        * ``"normalize"`` - stacking with normalized domain (for creating `normalized
-          stacked bar and area charts
-          <https://vega.github.io/vega-lite/docs/stack.html#normalized>`__ and pie charts
-          `with percentage tooltip
-          <https://vega.github.io/vega-lite/docs/arc.html#tooltip>`__ ). :raw-html:`<br/>`
-        * ``"center"`` - stacking with center baseline (for `streamgraph
-          <https://vega.github.io/vega-lite/docs/stack.html#streamgraph>`__ ).
-        * ``null`` or ``false`` - No-stacking. This will produce layered `bar
-          <https://vega.github.io/vega-lite/docs/stack.html#layered-bar-chart>`__ and area
-          chart.
-
-        **Default value:** ``zero`` for plots with all of the following conditions are true:
-        (1) the mark is ``bar``, ``area``, or ``arc`` ; (2) the stacked measure channel (x
-        or y) has a linear scale; (3) At least one of non-position channels mapped to an
-        unaggregated field that is different from x and y. Otherwise, ``null`` by default.
-
-        **See also:** `stack <https://vega.github.io/vega-lite/docs/stack.html>`__
-        documentation.
-    timeUnit : anyOf(:class:`TimeUnit`, :class:`BinnedTimeUnit`, :class:`TimeUnitParams`)
-        Time unit (e.g., ``year``, ``yearmonth``, ``month``, ``hours`` ) for a temporal
-        field. or `a temporal field that gets casted as ordinal
-        <https://vega.github.io/vega-lite/docs/type.html#cast>`__.
-
-        **Default value:** ``undefined`` (None)
-
-        **See also:** `timeUnit <https://vega.github.io/vega-lite/docs/timeunit.html>`__
-        documentation.
-    title : anyOf(:class:`Text`, None)
-        A title for the field. If ``null``, the title will be removed.
-
-        **Default value:**  derived from the field's name and transformation function (
-        ``aggregate``, ``bin`` and ``timeUnit`` ). If the field has an aggregate function,
-        the function is displayed as part of the title (e.g., ``"Sum of Profit"`` ). If the
-        field is binned or has a time unit applied, the applied function is shown in
-        parentheses (e.g., ``"Profit (binned)"``, ``"Transaction Date (year-month)"`` ).
-        Otherwise, the title is simply the field name.
-
-        **Notes** :
-
-        1) You can customize the default field title format by providing the `fieldTitle
-        <https://vega.github.io/vega-lite/docs/config.html#top-level-config>`__ property in
-        the `config <https://vega.github.io/vega-lite/docs/config.html>`__ or `fieldTitle
-        function via the compile function's options
-        <https://vega.github.io/vega-lite/usage/compile.html#field-title>`__.
-
-        2) If both field definition's ``title`` and axis, header, or legend ``title`` are
-        defined, axis/header/legend title will be used.
-    type : :class:`StandardType`
-        The type of measurement ( ``"quantitative"``, ``"temporal"``, ``"ordinal"``, or
-        ``"nominal"`` ) for the encoded field or constant value ( ``datum`` ). It can also
-        be a ``"geojson"`` type for encoding `'geoshape'
-        <https://vega.github.io/vega-lite/docs/geoshape.html>`__.
-
-        Vega-Lite automatically infers data types in many cases as discussed below. However,
-        type is required for a field if: (1) the field is not nominal and the field encoding
-        has no specified ``aggregate`` (except ``argmin`` and ``argmax`` ), ``bin``, scale
-        type, custom ``sort`` order, nor ``timeUnit`` or (2) if you wish to use an ordinal
-        scale for a field with ``bin`` or ``timeUnit``.
-
-        **Default value:**
-
-        1) For a data ``field``, ``"nominal"`` is the default data type unless the field
-        encoding has ``aggregate``, ``channel``, ``bin``, scale type, ``sort``, or
-        ``timeUnit`` that satisfies the following criteria:
-
-
-        * ``"quantitative"`` is the default type if (1) the encoded field contains ``bin``
-          or ``aggregate`` except ``"argmin"`` and ``"argmax"``, (2) the encoding channel is
-          ``latitude`` or ``longitude`` channel or (3) if the specified scale type is `a
-          quantitative scale <https://vega.github.io/vega-lite/docs/scale.html#type>`__.
-        * ``"temporal"`` is the default type if (1) the encoded field contains ``timeUnit``
-          or (2) the specified scale type is a time or utc scale
-        * ``"ordinal"`` is the default type if (1) the encoded field contains a `custom sort
-          order
-          <https://vega.github.io/vega-lite/docs/sort.html#specifying-custom-sort-order>`__,
-          (2) the specified scale type is an ordinal/point/band scale, or (3) the encoding
-          channel is ``order``.
-
-        2) For a constant value in data domain ( ``datum`` ):
-
-
-        * ``"quantitative"`` if the datum is a number
-        * ``"nominal"`` if the datum is a string
-        * ``"temporal"`` if the datum is `a date time object
-          <https://vega.github.io/vega-lite/docs/datetime.html>`__
-
-        **Note:**
-
-
-        * Data ``type`` describes the semantics of the data rather than the primitive data
-          types (number, string, etc.). The same primitive data type can have different
-          types of measurement. For example, numeric data can represent quantitative,
-          ordinal, or nominal data.
-        * Data values for a temporal field can be either a date-time string (e.g.,
-          ``"2015-03-07 12:32:17"``, ``"17:01"``, ``"2015-03-16"``. ``"2015"`` ) or a
-          timestamp number (e.g., ``1552199579097`` ).
-        * When using with `bin <https://vega.github.io/vega-lite/docs/bin.html>`__, the
-          ``type`` property can be either ``"quantitative"`` (for using a linear bin scale)
-          or `"ordinal" (for using an ordinal bin scale)
-          <https://vega.github.io/vega-lite/docs/type.html#cast-bin>`__.
-        * When using with `timeUnit
-          <https://vega.github.io/vega-lite/docs/timeunit.html>`__, the ``type`` property
-          can be either ``"temporal"`` (default, for using a temporal scale) or `"ordinal"
-          (for using an ordinal scale)
-          <https://vega.github.io/vega-lite/docs/type.html#cast-bin>`__.
-        * When using with `aggregate
-          <https://vega.github.io/vega-lite/docs/aggregate.html>`__, the ``type`` property
-          refers to the post-aggregation data type. For example, we can calculate count
-          ``distinct`` of a categorical field ``"cat"`` using ``{"aggregate": "distinct",
-          "field": "cat"}``. The ``"type"`` of the aggregate output is ``"quantitative"``.
-        * Secondary channels (e.g., ``x2``, ``y2``, ``xError``, ``yError`` ) do not have
-          ``type`` as they must have exactly the same type as their primary channels (e.g.,
-          ``x``, ``y`` ).
-
-        **See also:** `type <https://vega.github.io/vega-lite/docs/type.html>`__
-        documentation.
-    """
-    _schema = {'$ref': '#/definitions/PositionFieldDefBase'}
-
-    def __init__(self, aggregate=Undefined, bandPosition=Undefined, bin=Undefined, field=Undefined,
-                 scale=Undefined, sort=Undefined, stack=Undefined, timeUnit=Undefined, title=Undefined,
-                 type=Undefined, **kwds):
-        super(PositionFieldDefBase, self).__init__(aggregate=aggregate, bandPosition=bandPosition,
-                                                   bin=bin, field=field, scale=scale, sort=sort,
-                                                   stack=stack, timeUnit=timeUnit, title=title,
-                                                   type=type, **kwds)
-
-
-class PositionValueDef(PolarDef, Position2Def, PositionDef):
-    """PositionValueDef schema wrapper
-
-    Mapping(required=[value])
-    Definition object for a constant value (primitive value or gradient definition) of an
-    encoding channel.
-
-    Parameters
-    ----------
-
-    value : anyOf(float, string, string, :class:`ExprRef`)
-        A constant value in visual domain (e.g., ``"red"`` / ``"#0099ff"`` / `gradient
-        definition <https://vega.github.io/vega-lite/docs/types.html#gradient>`__ for color,
-        values between ``0`` to ``1`` for opacity).
-    """
-    _schema = {'$ref': '#/definitions/PositionValueDef'}
-
-    def __init__(self, value=Undefined, **kwds):
-        super(PositionValueDef, self).__init__(value=value, **kwds)
-
-
-class PredicateComposition(VegaLiteSchema):
-    """PredicateComposition schema wrapper
-
-    anyOf(:class:`LogicalNotPredicate`, :class:`LogicalAndPredicate`,
-    :class:`LogicalOrPredicate`, :class:`Predicate`)
-    """
-    _schema = {'$ref': '#/definitions/PredicateComposition'}
-
-    def __init__(self, *args, **kwds):
-        super(PredicateComposition, self).__init__(*args, **kwds)
-
-
-class LogicalAndPredicate(PredicateComposition):
-    """LogicalAndPredicate schema wrapper
-
-    Mapping(required=[and])
-
-    Parameters
-    ----------
-
-    and : List(:class:`PredicateComposition`)
-
-    """
-    _schema = {'$ref': '#/definitions/LogicalAnd<Predicate>'}
-
-    def __init__(self, **kwds):
-        super(LogicalAndPredicate, self).__init__(**kwds)
-
-
-class LogicalNotPredicate(PredicateComposition):
-    """LogicalNotPredicate schema wrapper
-
-    Mapping(required=[not])
-
-    Parameters
-    ----------
-
-    not : :class:`PredicateComposition`
-
-    """
-    _schema = {'$ref': '#/definitions/LogicalNot<Predicate>'}
-
-    def __init__(self, **kwds):
-        super(LogicalNotPredicate, self).__init__(**kwds)
-
-
-class LogicalOrPredicate(PredicateComposition):
-    """LogicalOrPredicate schema wrapper
-
-    Mapping(required=[or])
-
-    Parameters
-    ----------
-
-    or : List(:class:`PredicateComposition`)
-
-    """
-    _schema = {'$ref': '#/definitions/LogicalOr<Predicate>'}
-
-    def __init__(self, **kwds):
-        super(LogicalOrPredicate, self).__init__(**kwds)
-
-
-class Predicate(PredicateComposition):
-    """Predicate schema wrapper
-
-    anyOf(:class:`FieldEqualPredicate`, :class:`FieldRangePredicate`,
-    :class:`FieldOneOfPredicate`, :class:`FieldLTPredicate`, :class:`FieldGTPredicate`,
-    :class:`FieldLTEPredicate`, :class:`FieldGTEPredicate`, :class:`FieldValidPredicate`,
-    :class:`ParameterPredicate`, string)
-    """
-    _schema = {'$ref': '#/definitions/Predicate'}
-
-    def __init__(self, *args, **kwds):
-        super(Predicate, self).__init__(*args, **kwds)
-
-
-class FieldEqualPredicate(Predicate):
-    """FieldEqualPredicate schema wrapper
-
-    Mapping(required=[equal, field])
-
-    Parameters
-    ----------
-
-    equal : anyOf(string, float, boolean, :class:`DateTime`, :class:`ExprRef`)
-        The value that the field should be equal to.
-    field : :class:`FieldName`
-        Field to be tested.
-    timeUnit : anyOf(:class:`TimeUnit`, :class:`BinnedTimeUnit`, :class:`TimeUnitParams`)
-        Time unit for the field to be tested.
-    """
-    _schema = {'$ref': '#/definitions/FieldEqualPredicate'}
-
-    def __init__(self, equal=Undefined, field=Undefined, timeUnit=Undefined, **kwds):
-        super(FieldEqualPredicate, self).__init__(equal=equal, field=field, timeUnit=timeUnit, **kwds)
-
-
-class FieldGTEPredicate(Predicate):
-    """FieldGTEPredicate schema wrapper
-
-    Mapping(required=[field, gte])
-
-    Parameters
-    ----------
-
-    field : :class:`FieldName`
-        Field to be tested.
-    gte : anyOf(string, float, :class:`DateTime`, :class:`ExprRef`)
-        The value that the field should be greater than or equals to.
-    timeUnit : anyOf(:class:`TimeUnit`, :class:`BinnedTimeUnit`, :class:`TimeUnitParams`)
-        Time unit for the field to be tested.
-    """
-    _schema = {'$ref': '#/definitions/FieldGTEPredicate'}
-
-    def __init__(self, field=Undefined, gte=Undefined, timeUnit=Undefined, **kwds):
-        super(FieldGTEPredicate, self).__init__(field=field, gte=gte, timeUnit=timeUnit, **kwds)
-
-
-class FieldGTPredicate(Predicate):
-    """FieldGTPredicate schema wrapper
-
-    Mapping(required=[field, gt])
-
-    Parameters
-    ----------
-
-    field : :class:`FieldName`
-        Field to be tested.
-    gt : anyOf(string, float, :class:`DateTime`, :class:`ExprRef`)
-        The value that the field should be greater than.
-    timeUnit : anyOf(:class:`TimeUnit`, :class:`BinnedTimeUnit`, :class:`TimeUnitParams`)
-        Time unit for the field to be tested.
-    """
-    _schema = {'$ref': '#/definitions/FieldGTPredicate'}
-
-    def __init__(self, field=Undefined, gt=Undefined, timeUnit=Undefined, **kwds):
-        super(FieldGTPredicate, self).__init__(field=field, gt=gt, timeUnit=timeUnit, **kwds)
-
-
-class FieldLTEPredicate(Predicate):
-    """FieldLTEPredicate schema wrapper
-
-    Mapping(required=[field, lte])
-
-    Parameters
-    ----------
-
-    field : :class:`FieldName`
-        Field to be tested.
-    lte : anyOf(string, float, :class:`DateTime`, :class:`ExprRef`)
-        The value that the field should be less than or equals to.
-    timeUnit : anyOf(:class:`TimeUnit`, :class:`BinnedTimeUnit`, :class:`TimeUnitParams`)
-        Time unit for the field to be tested.
-    """
-    _schema = {'$ref': '#/definitions/FieldLTEPredicate'}
-
-    def __init__(self, field=Undefined, lte=Undefined, timeUnit=Undefined, **kwds):
-        super(FieldLTEPredicate, self).__init__(field=field, lte=lte, timeUnit=timeUnit, **kwds)
-
-
-class FieldLTPredicate(Predicate):
-    """FieldLTPredicate schema wrapper
-
-    Mapping(required=[field, lt])
-
-    Parameters
-    ----------
-
-    field : :class:`FieldName`
-        Field to be tested.
-    lt : anyOf(string, float, :class:`DateTime`, :class:`ExprRef`)
-        The value that the field should be less than.
-    timeUnit : anyOf(:class:`TimeUnit`, :class:`BinnedTimeUnit`, :class:`TimeUnitParams`)
-        Time unit for the field to be tested.
-    """
-    _schema = {'$ref': '#/definitions/FieldLTPredicate'}
-
-    def __init__(self, field=Undefined, lt=Undefined, timeUnit=Undefined, **kwds):
-        super(FieldLTPredicate, self).__init__(field=field, lt=lt, timeUnit=timeUnit, **kwds)
-
-
-class FieldOneOfPredicate(Predicate):
-    """FieldOneOfPredicate schema wrapper
-
-    Mapping(required=[field, oneOf])
-
-    Parameters
-    ----------
-
-    field : :class:`FieldName`
-        Field to be tested.
-    oneOf : anyOf(List(string), List(float), List(boolean), List(:class:`DateTime`))
-        A set of values that the ``field`` 's value should be a member of, for a data item
-        included in the filtered data.
-    timeUnit : anyOf(:class:`TimeUnit`, :class:`BinnedTimeUnit`, :class:`TimeUnitParams`)
-        Time unit for the field to be tested.
-    """
-    _schema = {'$ref': '#/definitions/FieldOneOfPredicate'}
-
-    def __init__(self, field=Undefined, oneOf=Undefined, timeUnit=Undefined, **kwds):
-        super(FieldOneOfPredicate, self).__init__(field=field, oneOf=oneOf, timeUnit=timeUnit, **kwds)
-
-
-class FieldRangePredicate(Predicate):
-    """FieldRangePredicate schema wrapper
-
-    Mapping(required=[field, range])
-
-    Parameters
-    ----------
-
-    field : :class:`FieldName`
-        Field to be tested.
-    range : anyOf(List(anyOf(float, :class:`DateTime`, None, :class:`ExprRef`)), :class:`ExprRef`)
-        An array of inclusive minimum and maximum values for a field value of a data item to
-        be included in the filtered data.
-    timeUnit : anyOf(:class:`TimeUnit`, :class:`BinnedTimeUnit`, :class:`TimeUnitParams`)
-        Time unit for the field to be tested.
-    """
-    _schema = {'$ref': '#/definitions/FieldRangePredicate'}
-
-    def __init__(self, field=Undefined, range=Undefined, timeUnit=Undefined, **kwds):
-        super(FieldRangePredicate, self).__init__(field=field, range=range, timeUnit=timeUnit, **kwds)
-
-
-class FieldValidPredicate(Predicate):
-    """FieldValidPredicate schema wrapper
-
-    Mapping(required=[field, valid])
-
-    Parameters
-    ----------
-
-    field : :class:`FieldName`
-        Field to be tested.
-    valid : boolean
-        If set to true the field's value has to be valid, meaning both not ``null`` and not
-        `NaN
-        <https://developer.mozilla.org/en-US/docs/Web/JavaScript/Reference/Global_Objects/NaN>`__.
-    timeUnit : anyOf(:class:`TimeUnit`, :class:`BinnedTimeUnit`, :class:`TimeUnitParams`)
-        Time unit for the field to be tested.
-    """
-    _schema = {'$ref': '#/definitions/FieldValidPredicate'}
-
-    def __init__(self, field=Undefined, valid=Undefined, timeUnit=Undefined, **kwds):
-        super(FieldValidPredicate, self).__init__(field=field, valid=valid, timeUnit=timeUnit, **kwds)
-
-
-class ParameterPredicate(Predicate):
-    """ParameterPredicate schema wrapper
-
-    Mapping(required=[param])
-
-    Parameters
-    ----------
-
-    param : :class:`ParameterName`
-        Filter using a parameter name.
-    empty : boolean
-        For selection parameters, the predicate of empty selections returns true by default.
-        Override this behavior, by setting this property ``empty: false``.
-    """
-    _schema = {'$ref': '#/definitions/ParameterPredicate'}
-
-    def __init__(self, param=Undefined, empty=Undefined, **kwds):
-        super(ParameterPredicate, self).__init__(param=param, empty=empty, **kwds)
-
-
-class Projection(VegaLiteSchema):
-    """Projection schema wrapper
-
-    Mapping(required=[])
-
-    Parameters
-    ----------
-
-    center : anyOf(:class:`Vector2number`, :class:`ExprRef`)
-        The projection's center, a two-element array of longitude and latitude in degrees.
-
-        **Default value:** ``[0, 0]``
-    clipAngle : anyOf(float, :class:`ExprRef`)
-        The projection's clipping circle radius to the specified angle in degrees. If
-        ``null``, switches to `antimeridian <http://bl.ocks.org/mbostock/3788999>`__ cutting
-        rather than small-circle clipping.
-    clipExtent : anyOf(:class:`Vector2Vector2number`, :class:`ExprRef`)
-        The projection's viewport clip extent to the specified bounds in pixels. The extent
-        bounds are specified as an array ``[[x0, y0], [x1, y1]]``, where ``x0`` is the
-        left-side of the viewport, ``y0`` is the top, ``x1`` is the right and ``y1`` is the
-        bottom. If ``null``, no viewport clipping is performed.
-    coefficient : anyOf(float, :class:`ExprRef`)
-        The coefficient parameter for the ``hammer`` projection.
-
-        **Default value:** ``2``
-    distance : anyOf(float, :class:`ExprRef`)
-        For the ``satellite`` projection, the distance from the center of the sphere to the
-        point of view, as a proportion of the sphere’s radius. The recommended maximum clip
-        angle for a given ``distance`` is acos(1 / distance) converted to degrees. If tilt
-        is also applied, then more conservative clipping may be necessary.
-
-        **Default value:** ``2.0``
-    extent : anyOf(:class:`Vector2Vector2number`, :class:`ExprRef`)
-
-    fit : anyOf(:class:`Fit`, List(:class:`Fit`), :class:`ExprRef`)
-
-    fraction : anyOf(float, :class:`ExprRef`)
-        The fraction parameter for the ``bottomley`` projection.
-
-        **Default value:** ``0.5``, corresponding to a sin(ψ) where ψ = π/6.
-    lobes : anyOf(float, :class:`ExprRef`)
-        The number of lobes in projections that support multi-lobe views: ``berghaus``,
-        ``gingery``, or ``healpix``. The default value varies based on the projection type.
-    parallel : anyOf(float, :class:`ExprRef`)
-        The parallel parameter for projections that support it: ``armadillo``, ``bonne``,
-        ``craig``, ``cylindricalEqualArea``, ``cylindricalStereographic``,
-        ``hammerRetroazimuthal``, ``loximuthal``, or ``rectangularPolyconic``. The default
-        value varies based on the projection type.
-    parallels : anyOf(List(float), :class:`ExprRef`)
-        For conic projections, the `two standard parallels
-        <https://en.wikipedia.org/wiki/Map_projection#Conic>`__ that define the map layout.
-        The default depends on the specific conic projection used.
-    pointRadius : anyOf(float, :class:`ExprRef`)
-        The default radius (in pixels) to use when drawing GeoJSON ``Point`` and
-        ``MultiPoint`` geometries. This parameter sets a constant default value. To modify
-        the point radius in response to data, see the corresponding parameter of the GeoPath
-        and GeoShape transforms.
-
-        **Default value:** ``4.5``
-    precision : anyOf(float, :class:`ExprRef`)
-        The threshold for the projection's `adaptive resampling
-        <http://bl.ocks.org/mbostock/3795544>`__ to the specified value in pixels. This
-        value corresponds to the `Douglas–Peucker distance
-        <http://en.wikipedia.org/wiki/Ramer%E2%80%93Douglas%E2%80%93Peucker_algorithm>`__.
-        If precision is not specified, returns the projection's current resampling precision
-        which defaults to ``√0.5 ≅ 0.70710…``.
-    radius : anyOf(float, :class:`ExprRef`)
-        The radius parameter for the ``airy`` or ``gingery`` projection. The default value
-        varies based on the projection type.
-    ratio : anyOf(float, :class:`ExprRef`)
-        The ratio parameter for the ``hill``, ``hufnagel``, or ``wagner`` projections. The
-        default value varies based on the projection type.
-    reflectX : anyOf(boolean, :class:`ExprRef`)
-        Sets whether or not the x-dimension is reflected (negated) in the output.
-    reflectY : anyOf(boolean, :class:`ExprRef`)
-        Sets whether or not the y-dimension is reflected (negated) in the output.
-    rotate : anyOf(anyOf(:class:`Vector2number`, :class:`Vector3number`), :class:`ExprRef`)
-        The projection's three-axis rotation to the specified angles, which must be a two-
-        or three-element array of numbers [ ``lambda``, ``phi``, ``gamma`` ] specifying the
-        rotation angles in degrees about each spherical axis. (These correspond to yaw,
-        pitch and roll.)
-
-        **Default value:** ``[0, 0, 0]``
-    scale : anyOf(float, :class:`ExprRef`)
-        The projection’s scale (zoom) factor, overriding automatic fitting. The default
-        scale is projection-specific. The scale factor corresponds linearly to the distance
-        between projected points; however, scale factor values are not equivalent across
-        projections.
-    size : anyOf(:class:`Vector2number`, :class:`ExprRef`)
-        Used in conjunction with fit, provides the width and height in pixels of the area to
-        which the projection should be automatically fit.
-    spacing : anyOf(float, :class:`ExprRef`)
-        The spacing parameter for the ``lagrange`` projection.
-
-        **Default value:** ``0.5``
-    tilt : anyOf(float, :class:`ExprRef`)
-        The tilt angle (in degrees) for the ``satellite`` projection.
-
-        **Default value:** ``0``.
-    translate : anyOf(:class:`Vector2number`, :class:`ExprRef`)
-        The projection’s translation offset as a two-element array ``[tx, ty]``.
-    type : anyOf(:class:`ProjectionType`, :class:`ExprRef`)
-        The cartographic projection to use. This value is case-insensitive, for example
-        ``"albers"`` and ``"Albers"`` indicate the same projection type. You can find all
-        valid projection types `in the documentation
-        <https://vega.github.io/vega-lite/docs/projection.html#projection-types>`__.
-
-        **Default value:** ``equalEarth``
-    """
-    _schema = {'$ref': '#/definitions/Projection'}
-
-    def __init__(self, center=Undefined, clipAngle=Undefined, clipExtent=Undefined,
-                 coefficient=Undefined, distance=Undefined, extent=Undefined, fit=Undefined,
-                 fraction=Undefined, lobes=Undefined, parallel=Undefined, parallels=Undefined,
-                 pointRadius=Undefined, precision=Undefined, radius=Undefined, ratio=Undefined,
-                 reflectX=Undefined, reflectY=Undefined, rotate=Undefined, scale=Undefined,
-                 size=Undefined, spacing=Undefined, tilt=Undefined, translate=Undefined, type=Undefined,
-                 **kwds):
-        super(Projection, self).__init__(center=center, clipAngle=clipAngle, clipExtent=clipExtent,
-                                         coefficient=coefficient, distance=distance, extent=extent,
-                                         fit=fit, fraction=fraction, lobes=lobes, parallel=parallel,
-                                         parallels=parallels, pointRadius=pointRadius,
-                                         precision=precision, radius=radius, ratio=ratio,
-                                         reflectX=reflectX, reflectY=reflectY, rotate=rotate,
-                                         scale=scale, size=size, spacing=spacing, tilt=tilt,
-                                         translate=translate, type=type, **kwds)
-
-
-class ProjectionConfig(VegaLiteSchema):
-    """ProjectionConfig schema wrapper
-
-    Mapping(required=[])
-
-    Parameters
-    ----------
-
-    center : anyOf(:class:`Vector2number`, :class:`ExprRef`)
-        The projection's center, a two-element array of longitude and latitude in degrees.
-
-        **Default value:** ``[0, 0]``
-    clipAngle : anyOf(float, :class:`ExprRef`)
-        The projection's clipping circle radius to the specified angle in degrees. If
-        ``null``, switches to `antimeridian <http://bl.ocks.org/mbostock/3788999>`__ cutting
-        rather than small-circle clipping.
-    clipExtent : anyOf(:class:`Vector2Vector2number`, :class:`ExprRef`)
-        The projection's viewport clip extent to the specified bounds in pixels. The extent
-        bounds are specified as an array ``[[x0, y0], [x1, y1]]``, where ``x0`` is the
-        left-side of the viewport, ``y0`` is the top, ``x1`` is the right and ``y1`` is the
-        bottom. If ``null``, no viewport clipping is performed.
-    coefficient : anyOf(float, :class:`ExprRef`)
-        The coefficient parameter for the ``hammer`` projection.
-
-        **Default value:** ``2``
-    distance : anyOf(float, :class:`ExprRef`)
-        For the ``satellite`` projection, the distance from the center of the sphere to the
-        point of view, as a proportion of the sphere’s radius. The recommended maximum clip
-        angle for a given ``distance`` is acos(1 / distance) converted to degrees. If tilt
-        is also applied, then more conservative clipping may be necessary.
-
-        **Default value:** ``2.0``
-    extent : anyOf(:class:`Vector2Vector2number`, :class:`ExprRef`)
-
-    fit : anyOf(:class:`Fit`, List(:class:`Fit`), :class:`ExprRef`)
-
-    fraction : anyOf(float, :class:`ExprRef`)
-        The fraction parameter for the ``bottomley`` projection.
-
-        **Default value:** ``0.5``, corresponding to a sin(ψ) where ψ = π/6.
-    lobes : anyOf(float, :class:`ExprRef`)
-        The number of lobes in projections that support multi-lobe views: ``berghaus``,
-        ``gingery``, or ``healpix``. The default value varies based on the projection type.
-    parallel : anyOf(float, :class:`ExprRef`)
-        The parallel parameter for projections that support it: ``armadillo``, ``bonne``,
-        ``craig``, ``cylindricalEqualArea``, ``cylindricalStereographic``,
-        ``hammerRetroazimuthal``, ``loximuthal``, or ``rectangularPolyconic``. The default
-        value varies based on the projection type.
-    parallels : anyOf(List(float), :class:`ExprRef`)
-        For conic projections, the `two standard parallels
-        <https://en.wikipedia.org/wiki/Map_projection#Conic>`__ that define the map layout.
-        The default depends on the specific conic projection used.
-    pointRadius : anyOf(float, :class:`ExprRef`)
-        The default radius (in pixels) to use when drawing GeoJSON ``Point`` and
-        ``MultiPoint`` geometries. This parameter sets a constant default value. To modify
-        the point radius in response to data, see the corresponding parameter of the GeoPath
-        and GeoShape transforms.
-
-        **Default value:** ``4.5``
-    precision : anyOf(float, :class:`ExprRef`)
-        The threshold for the projection's `adaptive resampling
-        <http://bl.ocks.org/mbostock/3795544>`__ to the specified value in pixels. This
-        value corresponds to the `Douglas–Peucker distance
-        <http://en.wikipedia.org/wiki/Ramer%E2%80%93Douglas%E2%80%93Peucker_algorithm>`__.
-        If precision is not specified, returns the projection's current resampling precision
-        which defaults to ``√0.5 ≅ 0.70710…``.
-    radius : anyOf(float, :class:`ExprRef`)
-        The radius parameter for the ``airy`` or ``gingery`` projection. The default value
-        varies based on the projection type.
-    ratio : anyOf(float, :class:`ExprRef`)
-        The ratio parameter for the ``hill``, ``hufnagel``, or ``wagner`` projections. The
-        default value varies based on the projection type.
-    reflectX : anyOf(boolean, :class:`ExprRef`)
-        Sets whether or not the x-dimension is reflected (negated) in the output.
-    reflectY : anyOf(boolean, :class:`ExprRef`)
-        Sets whether or not the y-dimension is reflected (negated) in the output.
-    rotate : anyOf(anyOf(:class:`Vector2number`, :class:`Vector3number`), :class:`ExprRef`)
-        The projection's three-axis rotation to the specified angles, which must be a two-
-        or three-element array of numbers [ ``lambda``, ``phi``, ``gamma`` ] specifying the
-        rotation angles in degrees about each spherical axis. (These correspond to yaw,
-        pitch and roll.)
-
-        **Default value:** ``[0, 0, 0]``
-    scale : anyOf(float, :class:`ExprRef`)
-        The projection’s scale (zoom) factor, overriding automatic fitting. The default
-        scale is projection-specific. The scale factor corresponds linearly to the distance
-        between projected points; however, scale factor values are not equivalent across
-        projections.
-    size : anyOf(:class:`Vector2number`, :class:`ExprRef`)
-        Used in conjunction with fit, provides the width and height in pixels of the area to
-        which the projection should be automatically fit.
-    spacing : anyOf(float, :class:`ExprRef`)
-        The spacing parameter for the ``lagrange`` projection.
-
-        **Default value:** ``0.5``
-    tilt : anyOf(float, :class:`ExprRef`)
-        The tilt angle (in degrees) for the ``satellite`` projection.
-
-        **Default value:** ``0``.
-    translate : anyOf(:class:`Vector2number`, :class:`ExprRef`)
-        The projection’s translation offset as a two-element array ``[tx, ty]``.
-    type : anyOf(:class:`ProjectionType`, :class:`ExprRef`)
-        The cartographic projection to use. This value is case-insensitive, for example
-        ``"albers"`` and ``"Albers"`` indicate the same projection type. You can find all
-        valid projection types `in the documentation
-        <https://vega.github.io/vega-lite/docs/projection.html#projection-types>`__.
-
-        **Default value:** ``equalEarth``
-    """
-    _schema = {'$ref': '#/definitions/ProjectionConfig'}
-
-    def __init__(self, center=Undefined, clipAngle=Undefined, clipExtent=Undefined,
-                 coefficient=Undefined, distance=Undefined, extent=Undefined, fit=Undefined,
-                 fraction=Undefined, lobes=Undefined, parallel=Undefined, parallels=Undefined,
-                 pointRadius=Undefined, precision=Undefined, radius=Undefined, ratio=Undefined,
-                 reflectX=Undefined, reflectY=Undefined, rotate=Undefined, scale=Undefined,
-                 size=Undefined, spacing=Undefined, tilt=Undefined, translate=Undefined, type=Undefined,
-                 **kwds):
-        super(ProjectionConfig, self).__init__(center=center, clipAngle=clipAngle,
-                                               clipExtent=clipExtent, coefficient=coefficient,
-                                               distance=distance, extent=extent, fit=fit,
-                                               fraction=fraction, lobes=lobes, parallel=parallel,
-                                               parallels=parallels, pointRadius=pointRadius,
-                                               precision=precision, radius=radius, ratio=ratio,
-                                               reflectX=reflectX, reflectY=reflectY, rotate=rotate,
-                                               scale=scale, size=size, spacing=spacing, tilt=tilt,
-                                               translate=translate, type=type, **kwds)
-
-
-class ProjectionType(VegaLiteSchema):
-    """ProjectionType schema wrapper
-
-    enum('albers', 'albersUsa', 'azimuthalEqualArea', 'azimuthalEquidistant', 'conicConformal',
-    'conicEqualArea', 'conicEquidistant', 'equalEarth', 'equirectangular', 'gnomonic',
-    'identity', 'mercator', 'naturalEarth1', 'orthographic', 'stereographic',
-    'transverseMercator')
-    """
-    _schema = {'$ref': '#/definitions/ProjectionType'}
-
-    def __init__(self, *args):
-        super(ProjectionType, self).__init__(*args)
-
-
-class RadialGradient(Gradient):
-    """RadialGradient schema wrapper
-
-    Mapping(required=[gradient, stops])
-
-    Parameters
-    ----------
-
-    gradient : string
-        The type of gradient. Use ``"radial"`` for a radial gradient.
-    stops : List(:class:`GradientStop`)
-        An array of gradient stops defining the gradient color sequence.
-    id : string
-
-    r1 : float
-        The radius length, in normalized [0, 1] coordinates, of the inner circle for the
-        gradient.
-
-        **Default value:** ``0``
-    r2 : float
-        The radius length, in normalized [0, 1] coordinates, of the outer circle for the
-        gradient.
-
-        **Default value:** ``0.5``
-    x1 : float
-        The x-coordinate, in normalized [0, 1] coordinates, for the center of the inner
-        circle for the gradient.
-
-        **Default value:** ``0.5``
-    x2 : float
-        The x-coordinate, in normalized [0, 1] coordinates, for the center of the outer
-        circle for the gradient.
-
-        **Default value:** ``0.5``
-    y1 : float
-        The y-coordinate, in normalized [0, 1] coordinates, for the center of the inner
-        circle for the gradient.
-
-        **Default value:** ``0.5``
-    y2 : float
-        The y-coordinate, in normalized [0, 1] coordinates, for the center of the outer
-        circle for the gradient.
-
-        **Default value:** ``0.5``
-    """
-    _schema = {'$ref': '#/definitions/RadialGradient'}
-
-    def __init__(self, gradient=Undefined, stops=Undefined, id=Undefined, r1=Undefined, r2=Undefined,
-                 x1=Undefined, x2=Undefined, y1=Undefined, y2=Undefined, **kwds):
-        super(RadialGradient, self).__init__(gradient=gradient, stops=stops, id=id, r1=r1, r2=r2, x1=x1,
-                                             x2=x2, y1=y1, y2=y2, **kwds)
-
-
-class RangeConfig(VegaLiteSchema):
-    """RangeConfig schema wrapper
-
-    Mapping(required=[])
-
-    Parameters
-    ----------
-
-    category : anyOf(:class:`RangeScheme`, List(:class:`Color`))
-        Default `color scheme <https://vega.github.io/vega/docs/schemes/>`__ for categorical
-        data.
-    diverging : anyOf(:class:`RangeScheme`, List(:class:`Color`))
-        Default `color scheme <https://vega.github.io/vega/docs/schemes/>`__ for diverging
-        quantitative ramps.
-    heatmap : anyOf(:class:`RangeScheme`, List(:class:`Color`))
-        Default `color scheme <https://vega.github.io/vega/docs/schemes/>`__ for
-        quantitative heatmaps.
-    ordinal : anyOf(:class:`RangeScheme`, List(:class:`Color`))
-        Default `color scheme <https://vega.github.io/vega/docs/schemes/>`__ for
-        rank-ordered data.
-    ramp : anyOf(:class:`RangeScheme`, List(:class:`Color`))
-        Default `color scheme <https://vega.github.io/vega/docs/schemes/>`__ for sequential
-        quantitative ramps.
-    symbol : List(:class:`SymbolShape`)
-        Array of `symbol <https://vega.github.io/vega/docs/marks/symbol/>`__ names or paths
-        for the default shape palette.
-    """
-    _schema = {'$ref': '#/definitions/RangeConfig'}
-
-    def __init__(self, category=Undefined, diverging=Undefined, heatmap=Undefined, ordinal=Undefined,
-                 ramp=Undefined, symbol=Undefined, **kwds):
-        super(RangeConfig, self).__init__(category=category, diverging=diverging, heatmap=heatmap,
-                                          ordinal=ordinal, ramp=ramp, symbol=symbol, **kwds)
-
-
-class RangeRawArray(VegaLiteSchema):
-    """RangeRawArray schema wrapper
-
-    List(float)
-    """
-    _schema = {'$ref': '#/definitions/RangeRawArray'}
-
-    def __init__(self, *args):
-        super(RangeRawArray, self).__init__(*args)
-
-
-class RangeScheme(VegaLiteSchema):
-    """RangeScheme schema wrapper
-
-    anyOf(:class:`RangeEnum`, :class:`RangeRaw`, Mapping(required=[scheme]))
-    """
-    _schema = {'$ref': '#/definitions/RangeScheme'}
-
-    def __init__(self, *args, **kwds):
-        super(RangeScheme, self).__init__(*args, **kwds)
-
-
-class RangeEnum(RangeScheme):
-    """RangeEnum schema wrapper
-
-    enum('width', 'height', 'symbol', 'category', 'ordinal', 'ramp', 'diverging', 'heatmap')
-    """
-    _schema = {'$ref': '#/definitions/RangeEnum'}
-
-    def __init__(self, *args):
-        super(RangeEnum, self).__init__(*args)
-
-
-class RangeRaw(RangeScheme):
-    """RangeRaw schema wrapper
-
-    List(anyOf(None, boolean, string, float, :class:`RangeRawArray`))
-    """
-    _schema = {'$ref': '#/definitions/RangeRaw'}
-
-    def __init__(self, *args):
-        super(RangeRaw, self).__init__(*args)
-
-
-class RectConfig(AnyMarkConfig):
-    """RectConfig schema wrapper
-
-    Mapping(required=[])
-
-    Parameters
-    ----------
-
-    align : anyOf(:class:`Align`, :class:`ExprRef`)
-        The horizontal alignment of the text or ranged marks (area, bar, image, rect, rule).
-        One of ``"left"``, ``"right"``, ``"center"``.
-
-        **Note:** Expression reference is *not* supported for range marks.
-    angle : anyOf(float, :class:`ExprRef`)
-        The rotation angle of the text, in degrees.
-    aria : anyOf(boolean, :class:`ExprRef`)
-        A boolean flag indicating if `ARIA attributes
-        <https://developer.mozilla.org/en-US/docs/Web/Accessibility/ARIA>`__ should be
-        included (SVG output only). If ``false``, the "aria-hidden" attribute will be set on
-        the output SVG element, removing the mark item from the ARIA accessibility tree.
-    ariaRole : anyOf(string, :class:`ExprRef`)
-        Sets the type of user interface element of the mark item for `ARIA accessibility
-        <https://developer.mozilla.org/en-US/docs/Web/Accessibility/ARIA>`__ (SVG output
-        only). If specified, this property determines the "role" attribute. Warning: this
-        property is experimental and may be changed in the future.
-    ariaRoleDescription : anyOf(string, :class:`ExprRef`)
-        A human-readable, author-localized description for the role of the mark item for
-        `ARIA accessibility
-        <https://developer.mozilla.org/en-US/docs/Web/Accessibility/ARIA>`__ (SVG output
-        only). If specified, this property determines the "aria-roledescription" attribute.
-        Warning: this property is experimental and may be changed in the future.
-    aspect : anyOf(boolean, :class:`ExprRef`)
-        Whether to keep aspect ratio of image marks.
-    baseline : anyOf(:class:`TextBaseline`, :class:`ExprRef`)
-        For text marks, the vertical text baseline. One of ``"alphabetic"`` (default),
-        ``"top"``, ``"middle"``, ``"bottom"``, ``"line-top"``, ``"line-bottom"``, or an
-        expression reference that provides one of the valid values. The ``"line-top"`` and
-        ``"line-bottom"`` values operate similarly to ``"top"`` and ``"bottom"``, but are
-        calculated relative to the ``lineHeight`` rather than ``fontSize`` alone.
-
-        For range marks, the vertical alignment of the marks. One of ``"top"``,
-        ``"middle"``, ``"bottom"``.
-
-        **Note:** Expression reference is *not* supported for range marks.
-    binSpacing : float
-        Offset between bars for binned field. The ideal value for this is either 0
-        (preferred by statisticians) or 1 (Vega-Lite default, D3 example style).
-
-        **Default value:** ``1``
-    blend : anyOf(:class:`Blend`, :class:`ExprRef`)
-        The color blend mode for drawing an item on its current background. Any valid `CSS
-        mix-blend-mode <https://developer.mozilla.org/en-US/docs/Web/CSS/mix-blend-mode>`__
-        value can be used.
-
-        __Default value:__ ``"source-over"``
-    color : anyOf(:class:`Color`, :class:`Gradient`, :class:`ExprRef`)
-        Default color.
-
-        **Default value:** :raw-html:`<span style="color: #4682b4;">&#9632;</span>`
-        ``"#4682b4"``
-
-        **Note:**
-
-
-        * This property cannot be used in a `style config
-          <https://vega.github.io/vega-lite/docs/mark.html#style-config>`__.
-        * The ``fill`` and ``stroke`` properties have higher precedence than ``color`` and
-          will override ``color``.
-    continuousBandSize : float
-        The default size of the bars on continuous scales.
-
-        **Default value:** ``5``
-    cornerRadius : anyOf(float, :class:`ExprRef`)
-        The radius in pixels of rounded rectangles or arcs' corners.
-
-        **Default value:** ``0``
-    cornerRadiusBottomLeft : anyOf(float, :class:`ExprRef`)
-        The radius in pixels of rounded rectangles' bottom left corner.
-
-        **Default value:** ``0``
-    cornerRadiusBottomRight : anyOf(float, :class:`ExprRef`)
-        The radius in pixels of rounded rectangles' bottom right corner.
-
-        **Default value:** ``0``
-    cornerRadiusTopLeft : anyOf(float, :class:`ExprRef`)
-        The radius in pixels of rounded rectangles' top right corner.
-
-        **Default value:** ``0``
-    cornerRadiusTopRight : anyOf(float, :class:`ExprRef`)
-        The radius in pixels of rounded rectangles' top left corner.
-
-        **Default value:** ``0``
-    cursor : anyOf(:class:`Cursor`, :class:`ExprRef`)
-        The mouse cursor used over the mark. Any valid `CSS cursor type
-        <https://developer.mozilla.org/en-US/docs/Web/CSS/cursor#Values>`__ can be used.
-    description : anyOf(string, :class:`ExprRef`)
-        A text description of the mark item for `ARIA accessibility
-        <https://developer.mozilla.org/en-US/docs/Web/Accessibility/ARIA>`__ (SVG output
-        only). If specified, this property determines the `"aria-label" attribute
-        <https://developer.mozilla.org/en-US/docs/Web/Accessibility/ARIA/ARIA_Techniques/Using_the_aria-label_attribute>`__.
-    dir : anyOf(:class:`TextDirection`, :class:`ExprRef`)
-        The direction of the text. One of ``"ltr"`` (left-to-right) or ``"rtl"``
-        (right-to-left). This property determines on which side is truncated in response to
-        the limit parameter.
-
-        **Default value:** ``"ltr"``
-    discreteBandSize : anyOf(float, :class:`RelativeBandSize`)
-        The default size of the bars with discrete dimensions. If unspecified, the default
-        size is  ``step-2``, which provides 2 pixel offset between bars.
-    dx : anyOf(float, :class:`ExprRef`)
-        The horizontal offset, in pixels, between the text label and its anchor point. The
-        offset is applied after rotation by the *angle* property.
-    dy : anyOf(float, :class:`ExprRef`)
-        The vertical offset, in pixels, between the text label and its anchor point. The
-        offset is applied after rotation by the *angle* property.
-    ellipsis : anyOf(string, :class:`ExprRef`)
-        The ellipsis string for text truncated in response to the limit parameter.
-
-        **Default value:** ``"…"``
-    endAngle : anyOf(float, :class:`ExprRef`)
-        The end angle in radians for arc marks. A value of ``0`` indicates up (north),
-        increasing values proceed clockwise.
-    fill : anyOf(:class:`Color`, :class:`Gradient`, None, :class:`ExprRef`)
-        Default fill color. This property has higher precedence than ``config.color``. Set
-        to ``null`` to remove fill.
-
-        **Default value:** (None)
-    fillOpacity : anyOf(float, :class:`ExprRef`)
-        The fill opacity (value between [0,1]).
-
-        **Default value:** ``1``
-    filled : boolean
-        Whether the mark's color should be used as fill color instead of stroke color.
-
-        **Default value:** ``false`` for all ``point``, ``line``, and ``rule`` marks as well
-        as ``geoshape`` marks for `graticule
-        <https://vega.github.io/vega-lite/docs/data.html#graticule>`__ data sources;
-        otherwise, ``true``.
-
-        **Note:** This property cannot be used in a `style config
-        <https://vega.github.io/vega-lite/docs/mark.html#style-config>`__.
-    font : anyOf(string, :class:`ExprRef`)
-        The typeface to set the text in (e.g., ``"Helvetica Neue"`` ).
-    fontSize : anyOf(float, :class:`ExprRef`)
-        The font size, in pixels.
-
-        **Default value:** ``11``
-    fontStyle : anyOf(:class:`FontStyle`, :class:`ExprRef`)
-        The font style (e.g., ``"italic"`` ).
-    fontWeight : anyOf(:class:`FontWeight`, :class:`ExprRef`)
-        The font weight. This can be either a string (e.g ``"bold"``, ``"normal"`` ) or a
-        number ( ``100``, ``200``, ``300``, ..., ``900`` where ``"normal"`` = ``400`` and
-        ``"bold"`` = ``700`` ).
-    height : anyOf(float, :class:`ExprRef`)
-        Height of the marks.
-    href : anyOf(:class:`URI`, :class:`ExprRef`)
-        A URL to load upon mouse click. If defined, the mark acts as a hyperlink.
-    innerRadius : anyOf(float, :class:`ExprRef`)
-        The inner radius in pixels of arc marks. ``innerRadius`` is an alias for
-        ``radius2``.
-
-        **Default value:** ``0``
-    interpolate : anyOf(:class:`Interpolate`, :class:`ExprRef`)
-        The line interpolation method to use for line and area marks. One of the following:
-
-
-        * ``"linear"`` : piecewise linear segments, as in a polyline.
-        * ``"linear-closed"`` : close the linear segments to form a polygon.
-        * ``"step"`` : alternate between horizontal and vertical segments, as in a step
-          function.
-        * ``"step-before"`` : alternate between vertical and horizontal segments, as in a
-          step function.
-        * ``"step-after"`` : alternate between horizontal and vertical segments, as in a
-          step function.
-        * ``"basis"`` : a B-spline, with control point duplication on the ends.
-        * ``"basis-open"`` : an open B-spline; may not intersect the start or end.
-        * ``"basis-closed"`` : a closed B-spline, as in a loop.
-        * ``"cardinal"`` : a Cardinal spline, with control point duplication on the ends.
-        * ``"cardinal-open"`` : an open Cardinal spline; may not intersect the start or end,
-          but will intersect other control points.
-        * ``"cardinal-closed"`` : a closed Cardinal spline, as in a loop.
-        * ``"bundle"`` : equivalent to basis, except the tension parameter is used to
-          straighten the spline.
-        * ``"monotone"`` : cubic interpolation that preserves monotonicity in y.
-    invalid : enum('filter', None)
-        Defines how Vega-Lite should handle marks for invalid values ( ``null`` and ``NaN``
-        ).
-
-
-        * If set to ``"filter"`` (default), all data items with null values will be skipped
-          (for line, trail, and area marks) or filtered (for other marks).
-        * If ``null``, all data items are included. In this case, invalid values will be
-          interpreted as zeroes.
-    limit : anyOf(float, :class:`ExprRef`)
-        The maximum length of the text mark in pixels. The text value will be automatically
-        truncated if the rendered size exceeds the limit.
-
-        **Default value:** ``0`` -- indicating no limit
-    lineBreak : anyOf(string, :class:`ExprRef`)
-        A delimiter, such as a newline character, upon which to break text strings into
-        multiple lines. This property is ignored if the text is array-valued.
-    lineHeight : anyOf(float, :class:`ExprRef`)
-        The line height in pixels (the spacing between subsequent lines of text) for
-        multi-line text marks.
-    minBandSize : anyOf(float, :class:`ExprRef`)
-        The minimum band size for bar and rectangle marks. **Default value:** ``0.25``
-    opacity : anyOf(float, :class:`ExprRef`)
-        The overall opacity (value between [0,1]).
-
-        **Default value:** ``0.7`` for non-aggregate plots with ``point``, ``tick``,
-        ``circle``, or ``square`` marks or layered ``bar`` charts and ``1`` otherwise.
-    order : anyOf(None, boolean)
-        For line and trail marks, this ``order`` property can be set to ``null`` or
-        ``false`` to make the lines use the original order in the data sources.
-    orient : :class:`Orientation`
-        The orientation of a non-stacked bar, tick, area, and line charts. The value is
-        either horizontal (default) or vertical.
-
-
-        * For bar, rule and tick, this determines whether the size of the bar and tick
-          should be applied to x or y dimension.
-        * For area, this property determines the orient property of the Vega output.
-        * For line and trail marks, this property determines the sort order of the points in
-          the line if ``config.sortLineBy`` is not specified. For stacked charts, this is
-          always determined by the orientation of the stack; therefore explicitly specified
-          value will be ignored.
-    outerRadius : anyOf(float, :class:`ExprRef`)
-        The outer radius in pixels of arc marks. ``outerRadius`` is an alias for ``radius``.
-
-        **Default value:** ``0``
-    padAngle : anyOf(float, :class:`ExprRef`)
-        The angular padding applied to sides of the arc, in radians.
-    radius : anyOf(float, :class:`ExprRef`)
-        For arc mark, the primary (outer) radius in pixels.
-
-        For text marks, polar coordinate radial offset, in pixels, of the text from the
-        origin determined by the ``x`` and ``y`` properties.
-
-        **Default value:** ``min(plot_width, plot_height)/2``
-    radius2 : anyOf(float, :class:`ExprRef`)
-        The secondary (inner) radius in pixels of arc marks.
-
-        **Default value:** ``0``
-    shape : anyOf(anyOf(:class:`SymbolShape`, string), :class:`ExprRef`)
-        Shape of the point marks. Supported values include:
-
-
-        * plotting shapes: ``"circle"``, ``"square"``, ``"cross"``, ``"diamond"``,
-          ``"triangle-up"``, ``"triangle-down"``, ``"triangle-right"``, or
-          ``"triangle-left"``.
-        * the line symbol ``"stroke"``
-        * centered directional shapes ``"arrow"``, ``"wedge"``, or ``"triangle"``
-        * a custom `SVG path string
-          <https://developer.mozilla.org/en-US/docs/Web/SVG/Tutorial/Paths>`__ (For correct
-          sizing, custom shape paths should be defined within a square bounding box with
-          coordinates ranging from -1 to 1 along both the x and y dimensions.)
-
-        **Default value:** ``"circle"``
-    size : anyOf(float, :class:`ExprRef`)
-        Default size for marks.
-
-
-        * For ``point`` / ``circle`` / ``square``, this represents the pixel area of the
-          marks. Note that this value sets the area of the symbol; the side lengths will
-          increase with the square root of this value.
-        * For ``bar``, this represents the band size of the bar, in pixels.
-        * For ``text``, this represents the font size, in pixels.
-
-        **Default value:**
-
-
-        * ``30`` for point, circle, square marks; width/height's ``step``
-        * ``2`` for bar marks with discrete dimensions;
-        * ``5`` for bar marks with continuous dimensions;
-        * ``11`` for text marks.
-    smooth : anyOf(boolean, :class:`ExprRef`)
-        A boolean flag (default true) indicating if the image should be smoothed when
-        resized. If false, individual pixels should be scaled directly rather than
-        interpolated with smoothing. For SVG rendering, this option may not work in some
-        browsers due to lack of standardization.
-    startAngle : anyOf(float, :class:`ExprRef`)
-        The start angle in radians for arc marks. A value of ``0`` indicates up (north),
-        increasing values proceed clockwise.
-    stroke : anyOf(:class:`Color`, :class:`Gradient`, None, :class:`ExprRef`)
-        Default stroke color. This property has higher precedence than ``config.color``. Set
-        to ``null`` to remove stroke.
-
-        **Default value:** (None)
-    strokeCap : anyOf(:class:`StrokeCap`, :class:`ExprRef`)
-        The stroke cap for line ending style. One of ``"butt"``, ``"round"``, or
-        ``"square"``.
-
-        **Default value:** ``"butt"``
-    strokeDash : anyOf(List(float), :class:`ExprRef`)
-        An array of alternating stroke, space lengths for creating dashed or dotted lines.
-    strokeDashOffset : anyOf(float, :class:`ExprRef`)
-        The offset (in pixels) into which to begin drawing with the stroke dash array.
-    strokeJoin : anyOf(:class:`StrokeJoin`, :class:`ExprRef`)
-        The stroke line join method. One of ``"miter"``, ``"round"`` or ``"bevel"``.
-
-        **Default value:** ``"miter"``
-    strokeMiterLimit : anyOf(float, :class:`ExprRef`)
-        The miter limit at which to bevel a line join.
-    strokeOffset : anyOf(float, :class:`ExprRef`)
-        The offset in pixels at which to draw the group stroke and fill. If unspecified, the
-        default behavior is to dynamically offset stroked groups such that 1 pixel stroke
-        widths align with the pixel grid.
-    strokeOpacity : anyOf(float, :class:`ExprRef`)
-        The stroke opacity (value between [0,1]).
-
-        **Default value:** ``1``
-    strokeWidth : anyOf(float, :class:`ExprRef`)
-        The stroke width, in pixels.
-    tension : anyOf(float, :class:`ExprRef`)
-        Depending on the interpolation type, sets the tension parameter (for line and area
-        marks).
-    text : anyOf(:class:`Text`, :class:`ExprRef`)
-        Placeholder text if the ``text`` channel is not specified
-    theta : anyOf(float, :class:`ExprRef`)
-        For arc marks, the arc length in radians if theta2 is not specified, otherwise the
-        start arc angle. (A value of 0 indicates up or “north”, increasing values proceed
-        clockwise.)
-
-        For text marks, polar coordinate angle in radians.
-    theta2 : anyOf(float, :class:`ExprRef`)
-        The end angle of arc marks in radians. A value of 0 indicates up or “north”,
-        increasing values proceed clockwise.
-    timeUnitBandPosition : float
-        Default relative band position for a time unit. If set to ``0``, the marks will be
-        positioned at the beginning of the time unit band step. If set to ``0.5``, the marks
-        will be positioned in the middle of the time unit band step.
-    timeUnitBandSize : float
-        Default relative band size for a time unit. If set to ``1``, the bandwidth of the
-        marks will be equal to the time unit band step. If set to ``0.5``, bandwidth of the
-        marks will be half of the time unit band step.
-    tooltip : anyOf(float, string, boolean, :class:`TooltipContent`, :class:`ExprRef`, None)
-        The tooltip text string to show upon mouse hover or an object defining which fields
-        should the tooltip be derived from.
-
-
-        * If ``tooltip`` is ``true`` or ``{"content": "encoding"}``, then all fields from
-          ``encoding`` will be used.
-        * If ``tooltip`` is ``{"content": "data"}``, then all fields that appear in the
-          highlighted data point will be used.
-        * If set to ``null`` or ``false``, then no tooltip will be used.
-
-        See the `tooltip <https://vega.github.io/vega-lite/docs/tooltip.html>`__
-        documentation for a detailed discussion about tooltip  in Vega-Lite.
-
-        **Default value:** ``null``
-    url : anyOf(:class:`URI`, :class:`ExprRef`)
-        The URL of the image file for image marks.
-    width : anyOf(float, :class:`ExprRef`)
-        Width of the marks.
-    x : anyOf(float, string, :class:`ExprRef`)
-        X coordinates of the marks, or width of horizontal ``"bar"`` and ``"area"`` without
-        specified ``x2`` or ``width``.
-
-        The ``value`` of this channel can be a number or a string ``"width"`` for the width
-        of the plot.
-    x2 : anyOf(float, string, :class:`ExprRef`)
-        X2 coordinates for ranged ``"area"``, ``"bar"``, ``"rect"``, and  ``"rule"``.
-
-        The ``value`` of this channel can be a number or a string ``"width"`` for the width
-        of the plot.
-    y : anyOf(float, string, :class:`ExprRef`)
-        Y coordinates of the marks, or height of vertical ``"bar"`` and ``"area"`` without
-        specified ``y2`` or ``height``.
-
-        The ``value`` of this channel can be a number or a string ``"height"`` for the
-        height of the plot.
-    y2 : anyOf(float, string, :class:`ExprRef`)
-        Y2 coordinates for ranged ``"area"``, ``"bar"``, ``"rect"``, and  ``"rule"``.
-
-        The ``value`` of this channel can be a number or a string ``"height"`` for the
-        height of the plot.
-    """
-    _schema = {'$ref': '#/definitions/RectConfig'}
-
-    def __init__(self, align=Undefined, angle=Undefined, aria=Undefined, ariaRole=Undefined,
-                 ariaRoleDescription=Undefined, aspect=Undefined, baseline=Undefined,
-                 binSpacing=Undefined, blend=Undefined, color=Undefined, continuousBandSize=Undefined,
-                 cornerRadius=Undefined, cornerRadiusBottomLeft=Undefined,
-                 cornerRadiusBottomRight=Undefined, cornerRadiusTopLeft=Undefined,
-                 cornerRadiusTopRight=Undefined, cursor=Undefined, description=Undefined, dir=Undefined,
-                 discreteBandSize=Undefined, dx=Undefined, dy=Undefined, ellipsis=Undefined,
-                 endAngle=Undefined, fill=Undefined, fillOpacity=Undefined, filled=Undefined,
-                 font=Undefined, fontSize=Undefined, fontStyle=Undefined, fontWeight=Undefined,
-                 height=Undefined, href=Undefined, innerRadius=Undefined, interpolate=Undefined,
-                 invalid=Undefined, limit=Undefined, lineBreak=Undefined, lineHeight=Undefined,
-                 minBandSize=Undefined, opacity=Undefined, order=Undefined, orient=Undefined,
-                 outerRadius=Undefined, padAngle=Undefined, radius=Undefined, radius2=Undefined,
-                 shape=Undefined, size=Undefined, smooth=Undefined, startAngle=Undefined,
-                 stroke=Undefined, strokeCap=Undefined, strokeDash=Undefined,
-                 strokeDashOffset=Undefined, strokeJoin=Undefined, strokeMiterLimit=Undefined,
-                 strokeOffset=Undefined, strokeOpacity=Undefined, strokeWidth=Undefined,
-                 tension=Undefined, text=Undefined, theta=Undefined, theta2=Undefined,
-                 timeUnitBandPosition=Undefined, timeUnitBandSize=Undefined, tooltip=Undefined,
-                 url=Undefined, width=Undefined, x=Undefined, x2=Undefined, y=Undefined, y2=Undefined,
-                 **kwds):
-        super(RectConfig, self).__init__(align=align, angle=angle, aria=aria, ariaRole=ariaRole,
-                                         ariaRoleDescription=ariaRoleDescription, aspect=aspect,
-                                         baseline=baseline, binSpacing=binSpacing, blend=blend,
-                                         color=color, continuousBandSize=continuousBandSize,
-                                         cornerRadius=cornerRadius,
-                                         cornerRadiusBottomLeft=cornerRadiusBottomLeft,
-                                         cornerRadiusBottomRight=cornerRadiusBottomRight,
-                                         cornerRadiusTopLeft=cornerRadiusTopLeft,
-                                         cornerRadiusTopRight=cornerRadiusTopRight, cursor=cursor,
-                                         description=description, dir=dir,
-                                         discreteBandSize=discreteBandSize, dx=dx, dy=dy,
-                                         ellipsis=ellipsis, endAngle=endAngle, fill=fill,
-                                         fillOpacity=fillOpacity, filled=filled, font=font,
-                                         fontSize=fontSize, fontStyle=fontStyle, fontWeight=fontWeight,
-                                         height=height, href=href, innerRadius=innerRadius,
-                                         interpolate=interpolate, invalid=invalid, limit=limit,
-                                         lineBreak=lineBreak, lineHeight=lineHeight,
-                                         minBandSize=minBandSize, opacity=opacity, order=order,
-                                         orient=orient, outerRadius=outerRadius, padAngle=padAngle,
-                                         radius=radius, radius2=radius2, shape=shape, size=size,
-                                         smooth=smooth, startAngle=startAngle, stroke=stroke,
-                                         strokeCap=strokeCap, strokeDash=strokeDash,
-                                         strokeDashOffset=strokeDashOffset, strokeJoin=strokeJoin,
-                                         strokeMiterLimit=strokeMiterLimit, strokeOffset=strokeOffset,
-                                         strokeOpacity=strokeOpacity, strokeWidth=strokeWidth,
-                                         tension=tension, text=text, theta=theta, theta2=theta2,
-                                         timeUnitBandPosition=timeUnitBandPosition,
-                                         timeUnitBandSize=timeUnitBandSize, tooltip=tooltip, url=url,
-                                         width=width, x=x, x2=x2, y=y, y2=y2, **kwds)
-
-
-class RelativeBandSize(VegaLiteSchema):
-    """RelativeBandSize schema wrapper
-
-    Mapping(required=[band])
-
-    Parameters
-    ----------
-
-    band : float
-        The relative band size.  For example ``0.5`` means half of the band scale's band
-        width.
-    """
-    _schema = {'$ref': '#/definitions/RelativeBandSize'}
-
-    def __init__(self, band=Undefined, **kwds):
-        super(RelativeBandSize, self).__init__(band=band, **kwds)
-
-
-class RepeatMapping(VegaLiteSchema):
-    """RepeatMapping schema wrapper
-
-    Mapping(required=[])
-
-    Parameters
-    ----------
-
-    column : List(string)
-        An array of fields to be repeated horizontally.
-    row : List(string)
-        An array of fields to be repeated vertically.
-    """
-    _schema = {'$ref': '#/definitions/RepeatMapping'}
-
-    def __init__(self, column=Undefined, row=Undefined, **kwds):
-        super(RepeatMapping, self).__init__(column=column, row=row, **kwds)
-
-
-class RepeatRef(Field):
-    """RepeatRef schema wrapper
-
-    Mapping(required=[repeat])
-    Reference to a repeated value.
-
-    Parameters
-    ----------
-
-    repeat : enum('row', 'column', 'repeat', 'layer')
-
-    """
-    _schema = {'$ref': '#/definitions/RepeatRef'}
-
-    def __init__(self, repeat=Undefined, **kwds):
-        super(RepeatRef, self).__init__(repeat=repeat, **kwds)
-
-
-class Resolve(VegaLiteSchema):
-    """Resolve schema wrapper
-
-    Mapping(required=[])
-    Defines how scales, axes, and legends from different specs should be combined. Resolve is a
-    mapping from ``scale``, ``axis``, and ``legend`` to a mapping from channels to resolutions.
-    Scales and guides can be resolved to be ``"independent"`` or ``"shared"``.
-
-    Parameters
-    ----------
-
-    axis : :class:`AxisResolveMap`
-
-    legend : :class:`LegendResolveMap`
-
-    scale : :class:`ScaleResolveMap`
-
-    """
-    _schema = {'$ref': '#/definitions/Resolve'}
-
-    def __init__(self, axis=Undefined, legend=Undefined, scale=Undefined, **kwds):
-        super(Resolve, self).__init__(axis=axis, legend=legend, scale=scale, **kwds)
-
-
-class ResolveMode(VegaLiteSchema):
-    """ResolveMode schema wrapper
-
-    enum('independent', 'shared')
-    """
-    _schema = {'$ref': '#/definitions/ResolveMode'}
-
-    def __init__(self, *args):
-        super(ResolveMode, self).__init__(*args)
-
-
-class RowColLayoutAlign(VegaLiteSchema):
-    """RowColLayoutAlign schema wrapper
-
-    Mapping(required=[])
-
-    Parameters
-    ----------
-
-    column : :class:`LayoutAlign`
-
-    row : :class:`LayoutAlign`
-
-    """
-    _schema = {'$ref': '#/definitions/RowCol<LayoutAlign>'}
-
-    def __init__(self, column=Undefined, row=Undefined, **kwds):
-        super(RowColLayoutAlign, self).__init__(column=column, row=row, **kwds)
-
-
-class RowColboolean(VegaLiteSchema):
-    """RowColboolean schema wrapper
-
-    Mapping(required=[])
-
-    Parameters
-    ----------
-
-    column : boolean
-
-    row : boolean
-
-    """
-    _schema = {'$ref': '#/definitions/RowCol<boolean>'}
-
-    def __init__(self, column=Undefined, row=Undefined, **kwds):
-        super(RowColboolean, self).__init__(column=column, row=row, **kwds)
-
-
-class RowColnumber(VegaLiteSchema):
-    """RowColnumber schema wrapper
-
-    Mapping(required=[])
-
-    Parameters
-    ----------
-
-    column : float
-
-    row : float
-
-    """
-    _schema = {'$ref': '#/definitions/RowCol<number>'}
-
-    def __init__(self, column=Undefined, row=Undefined, **kwds):
-        super(RowColnumber, self).__init__(column=column, row=row, **kwds)
-
-
-class RowColumnEncodingFieldDef(VegaLiteSchema):
-    """RowColumnEncodingFieldDef schema wrapper
-
-    Mapping(required=[])
-
-    Parameters
-    ----------
-
-    aggregate : :class:`Aggregate`
-        Aggregation function for the field (e.g., ``"mean"``, ``"sum"``, ``"median"``,
-        ``"min"``, ``"max"``, ``"count"`` ).
-
-        **Default value:** ``undefined`` (None)
-
-        **See also:** `aggregate <https://vega.github.io/vega-lite/docs/aggregate.html>`__
-        documentation.
-    align : :class:`LayoutAlign`
-        The alignment to apply to row/column facet's subplot. The supported string values
-        are ``"all"``, ``"each"``, and ``"none"``.
-
-
-        * For ``"none"``, a flow layout will be used, in which adjacent subviews are simply
-          placed one after the other.
-        * For ``"each"``, subviews will be aligned into a clean grid structure, but each row
-          or column may be of variable size.
-        * For ``"all"``, subviews will be aligned and each row or column will be sized
-          identically based on the maximum observed size. String values for this property
-          will be applied to both grid rows and columns.
-
-        **Default value:** ``"all"``.
-    bandPosition : float
-        Relative position on a band of a stacked, binned, time unit, or band scale. For
-        example, the marks will be positioned at the beginning of the band if set to ``0``,
-        and at the middle of the band if set to ``0.5``.
-    bin : anyOf(boolean, :class:`BinParams`, None)
-        A flag for binning a ``quantitative`` field, `an object defining binning parameters
-        <https://vega.github.io/vega-lite/docs/bin.html#bin-parameters>`__, or indicating
-        that the data for ``x`` or ``y`` channel are binned before they are imported into
-        Vega-Lite ( ``"binned"`` ).
-
-
-        If ``true``, default `binning parameters
-        <https://vega.github.io/vega-lite/docs/bin.html#bin-parameters>`__ will be applied.
-
-        If ``"binned"``, this indicates that the data for the ``x`` (or ``y`` ) channel are
-        already binned. You can map the bin-start field to ``x`` (or ``y`` ) and the bin-end
-        field to ``x2`` (or ``y2`` ). The scale and axis will be formatted similar to
-        binning in Vega-Lite.  To adjust the axis ticks based on the bin step, you can also
-        set the axis's `tickMinStep
-        <https://vega.github.io/vega-lite/docs/axis.html#ticks>`__ property.
-
-        **Default value:** ``false``
-
-        **See also:** `bin <https://vega.github.io/vega-lite/docs/bin.html>`__
-        documentation.
-    center : boolean
-        Boolean flag indicating if facet's subviews should be centered relative to their
-        respective rows or columns.
-
-        **Default value:** ``false``
-    field : :class:`Field`
-        **Required.** A string defining the name of the field from which to pull a data
-        value or an object defining iterated values from the `repeat
-        <https://vega.github.io/vega-lite/docs/repeat.html>`__ operator.
-
-        **See also:** `field <https://vega.github.io/vega-lite/docs/field.html>`__
-        documentation.
-
-        **Notes:** 1)  Dots ( ``.`` ) and brackets ( ``[`` and ``]`` ) can be used to access
-        nested objects (e.g., ``"field": "foo.bar"`` and ``"field": "foo['bar']"`` ). If
-        field names contain dots or brackets but are not nested, you can use ``\\`` to
-        escape dots and brackets (e.g., ``"a\\.b"`` and ``"a\\[0\\]"`` ). See more details
-        about escaping in the `field documentation
-        <https://vega.github.io/vega-lite/docs/field.html>`__. 2) ``field`` is not required
-        if ``aggregate`` is ``count``.
-    header : anyOf(:class:`Header`, None)
-        An object defining properties of a facet's header.
-    sort : anyOf(:class:`SortArray`, :class:`SortOrder`, :class:`EncodingSortField`, None)
-        Sort order for the encoded field.
-
-        For continuous fields (quantitative or temporal), ``sort`` can be either
-        ``"ascending"`` or ``"descending"``.
-
-        For discrete fields, ``sort`` can be one of the following:
-
-
-        * ``"ascending"`` or ``"descending"`` -- for sorting by the values' natural order in
-          JavaScript.
-        * `A sort field definition
-          <https://vega.github.io/vega-lite/docs/sort.html#sort-field>`__ for sorting by
-          another field.
-        * `An array specifying the field values in preferred order
-          <https://vega.github.io/vega-lite/docs/sort.html#sort-array>`__. In this case, the
-          sort order will obey the values in the array, followed by any unspecified values
-          in their original order. For discrete time field, values in the sort array can be
-          `date-time definition objects
-          <https://vega.github.io/vega-lite/docs/datetime.html>`__. In addition, for time
-          units ``"month"`` and ``"day"``, the values can be the month or day names (case
-          insensitive) or their 3-letter initials (e.g., ``"Mon"``, ``"Tue"`` ).
-        * ``null`` indicating no sort.
-
-        **Default value:** ``"ascending"``
-
-        **Note:** ``null`` is not supported for ``row`` and ``column``.
-    spacing : float
-        The spacing in pixels between facet's sub-views.
-
-        **Default value** : Depends on ``"spacing"`` property of `the view composition
-        configuration <https://vega.github.io/vega-lite/docs/config.html#view-config>`__ (
-        ``20`` by default)
-    timeUnit : anyOf(:class:`TimeUnit`, :class:`BinnedTimeUnit`, :class:`TimeUnitParams`)
-        Time unit (e.g., ``year``, ``yearmonth``, ``month``, ``hours`` ) for a temporal
-        field. or `a temporal field that gets casted as ordinal
-        <https://vega.github.io/vega-lite/docs/type.html#cast>`__.
-
-        **Default value:** ``undefined`` (None)
-
-        **See also:** `timeUnit <https://vega.github.io/vega-lite/docs/timeunit.html>`__
-        documentation.
-    title : anyOf(:class:`Text`, None)
-        A title for the field. If ``null``, the title will be removed.
-
-        **Default value:**  derived from the field's name and transformation function (
-        ``aggregate``, ``bin`` and ``timeUnit`` ). If the field has an aggregate function,
-        the function is displayed as part of the title (e.g., ``"Sum of Profit"`` ). If the
-        field is binned or has a time unit applied, the applied function is shown in
-        parentheses (e.g., ``"Profit (binned)"``, ``"Transaction Date (year-month)"`` ).
-        Otherwise, the title is simply the field name.
-
-        **Notes** :
-
-        1) You can customize the default field title format by providing the `fieldTitle
-        <https://vega.github.io/vega-lite/docs/config.html#top-level-config>`__ property in
-        the `config <https://vega.github.io/vega-lite/docs/config.html>`__ or `fieldTitle
-        function via the compile function's options
-        <https://vega.github.io/vega-lite/usage/compile.html#field-title>`__.
-
-        2) If both field definition's ``title`` and axis, header, or legend ``title`` are
-        defined, axis/header/legend title will be used.
-    type : :class:`StandardType`
-        The type of measurement ( ``"quantitative"``, ``"temporal"``, ``"ordinal"``, or
-        ``"nominal"`` ) for the encoded field or constant value ( ``datum`` ). It can also
-        be a ``"geojson"`` type for encoding `'geoshape'
-        <https://vega.github.io/vega-lite/docs/geoshape.html>`__.
-
-        Vega-Lite automatically infers data types in many cases as discussed below. However,
-        type is required for a field if: (1) the field is not nominal and the field encoding
-        has no specified ``aggregate`` (except ``argmin`` and ``argmax`` ), ``bin``, scale
-        type, custom ``sort`` order, nor ``timeUnit`` or (2) if you wish to use an ordinal
-        scale for a field with ``bin`` or ``timeUnit``.
-
-        **Default value:**
-
-        1) For a data ``field``, ``"nominal"`` is the default data type unless the field
-        encoding has ``aggregate``, ``channel``, ``bin``, scale type, ``sort``, or
-        ``timeUnit`` that satisfies the following criteria:
-
-
-        * ``"quantitative"`` is the default type if (1) the encoded field contains ``bin``
-          or ``aggregate`` except ``"argmin"`` and ``"argmax"``, (2) the encoding channel is
-          ``latitude`` or ``longitude`` channel or (3) if the specified scale type is `a
-          quantitative scale <https://vega.github.io/vega-lite/docs/scale.html#type>`__.
-        * ``"temporal"`` is the default type if (1) the encoded field contains ``timeUnit``
-          or (2) the specified scale type is a time or utc scale
-        * ``"ordinal"`` is the default type if (1) the encoded field contains a `custom sort
-          order
-          <https://vega.github.io/vega-lite/docs/sort.html#specifying-custom-sort-order>`__,
-          (2) the specified scale type is an ordinal/point/band scale, or (3) the encoding
-          channel is ``order``.
-
-        2) For a constant value in data domain ( ``datum`` ):
-
-
-        * ``"quantitative"`` if the datum is a number
-        * ``"nominal"`` if the datum is a string
-        * ``"temporal"`` if the datum is `a date time object
-          <https://vega.github.io/vega-lite/docs/datetime.html>`__
-
-        **Note:**
-
-
-        * Data ``type`` describes the semantics of the data rather than the primitive data
-          types (number, string, etc.). The same primitive data type can have different
-          types of measurement. For example, numeric data can represent quantitative,
-          ordinal, or nominal data.
-        * Data values for a temporal field can be either a date-time string (e.g.,
-          ``"2015-03-07 12:32:17"``, ``"17:01"``, ``"2015-03-16"``. ``"2015"`` ) or a
-          timestamp number (e.g., ``1552199579097`` ).
-        * When using with `bin <https://vega.github.io/vega-lite/docs/bin.html>`__, the
-          ``type`` property can be either ``"quantitative"`` (for using a linear bin scale)
-          or `"ordinal" (for using an ordinal bin scale)
-          <https://vega.github.io/vega-lite/docs/type.html#cast-bin>`__.
-        * When using with `timeUnit
-          <https://vega.github.io/vega-lite/docs/timeunit.html>`__, the ``type`` property
-          can be either ``"temporal"`` (default, for using a temporal scale) or `"ordinal"
-          (for using an ordinal scale)
-          <https://vega.github.io/vega-lite/docs/type.html#cast-bin>`__.
-        * When using with `aggregate
-          <https://vega.github.io/vega-lite/docs/aggregate.html>`__, the ``type`` property
-          refers to the post-aggregation data type. For example, we can calculate count
-          ``distinct`` of a categorical field ``"cat"`` using ``{"aggregate": "distinct",
-          "field": "cat"}``. The ``"type"`` of the aggregate output is ``"quantitative"``.
-        * Secondary channels (e.g., ``x2``, ``y2``, ``xError``, ``yError`` ) do not have
-          ``type`` as they must have exactly the same type as their primary channels (e.g.,
-          ``x``, ``y`` ).
-
-        **See also:** `type <https://vega.github.io/vega-lite/docs/type.html>`__
-        documentation.
-    """
-    _schema = {'$ref': '#/definitions/RowColumnEncodingFieldDef'}
-
-    def __init__(self, aggregate=Undefined, align=Undefined, bandPosition=Undefined, bin=Undefined,
-                 center=Undefined, field=Undefined, header=Undefined, sort=Undefined, spacing=Undefined,
-                 timeUnit=Undefined, title=Undefined, type=Undefined, **kwds):
-        super(RowColumnEncodingFieldDef, self).__init__(aggregate=aggregate, align=align,
-                                                        bandPosition=bandPosition, bin=bin,
-                                                        center=center, field=field, header=header,
-                                                        sort=sort, spacing=spacing, timeUnit=timeUnit,
-                                                        title=title, type=type, **kwds)
-
-
-class Scale(VegaLiteSchema):
-    """Scale schema wrapper
-
-    Mapping(required=[])
-
-    Parameters
-    ----------
-
-    align : anyOf(float, :class:`ExprRef`)
-        The alignment of the steps within the scale range.
-
-        This value must lie in the range ``[0,1]``. A value of ``0.5`` indicates that the
-        steps should be centered within the range. A value of ``0`` or ``1`` may be used to
-        shift the bands to one side, say to position them adjacent to an axis.
-
-        **Default value:** ``0.5``
-    base : anyOf(float, :class:`ExprRef`)
-        The logarithm base of the ``log`` scale (default ``10`` ).
-    bins : :class:`ScaleBins`
-        Bin boundaries can be provided to scales as either an explicit array of bin
-        boundaries or as a bin specification object. The legal values are:
-
-
-        * An `array <../types/#Array>`__ literal of bin boundary values. For example, ``[0,
-          5, 10, 15, 20]``. The array must include both starting and ending boundaries. The
-          previous example uses five values to indicate a total of four bin intervals:
-          [0-5), [5-10), [10-15), [15-20]. Array literals may include signal references as
-          elements.
-        * A `bin specification object
-          <https://vega.github.io/vega-lite/docs/scale.html#bins>`__ that indicates the bin
-          *step* size, and optionally the *start* and *stop* boundaries.
-        * An array of bin boundaries over the scale domain. If provided, axes and legends
-          will use the bin boundaries to inform the choice of tick marks and text labels.
-    clamp : anyOf(boolean, :class:`ExprRef`)
-        If ``true``, values that exceed the data domain are clamped to either the minimum or
-        maximum range value
-
-        **Default value:** derived from the `scale config
-        <https://vega.github.io/vega-lite/docs/config.html#scale-config>`__ 's ``clamp`` (
-        ``true`` by default).
-    constant : anyOf(float, :class:`ExprRef`)
-        A constant determining the slope of the symlog function around zero. Only used for
-        ``symlog`` scales.
-
-        **Default value:** ``1``
-    domain : anyOf(List(anyOf(None, string, float, boolean, :class:`DateTime`, :class:`ExprRef`)), string, :class:`ParameterExtent`, :class:`DomainUnionWith`, :class:`ExprRef`)
-        Customized domain values in the form of constant values or dynamic values driven by
-        a parameter.
-
-        1) Constant ``domain`` for *quantitative* fields can take one of the following
-        forms:
-
-
-        * A two-element array with minimum and maximum values. To create a diverging scale,
-          this two-element array can be combined with the ``domainMid`` property.
-        * An array with more than two entries, for `Piecewise quantitative scales
-          <https://vega.github.io/vega-lite/docs/scale.html#piecewise>`__.
-        * A string value ``"unaggregated"``, if the input field is aggregated, to indicate
-          that the domain should include the raw data values prior to the aggregation.
-
-        2) Constant ``domain`` for *temporal* fields can be a two-element array with minimum
-        and maximum values, in the form of either timestamps or the `DateTime definition
-        objects <https://vega.github.io/vega-lite/docs/types.html#datetime>`__.
-
-        3) Constant ``domain`` for *ordinal* and *nominal* fields can be an array that lists
-        valid input values.
-
-        4) To combine (union) specified constant domain with the field's values, ``domain``
-        can be an object with a ``unionWith`` property that specify constant domain to be
-        combined. For example, ``domain: {unionWith: [0, 100]}`` for a quantitative scale
-        means that the scale domain always includes ``[0, 100]``, but will include other
-        values in the fields beyond ``[0, 100]``.
-
-        5) Domain can also takes an object defining a field or encoding of a parameter that
-        `interactively determines
-        <https://vega.github.io/vega-lite/docs/selection.html#scale-domains>`__ the scale
-        domain.
-    domainMax : anyOf(float, :class:`DateTime`, :class:`ExprRef`)
-        Sets the maximum value in the scale domain, overriding the ``domain`` property. This
-        property is only intended for use with scales having continuous domains.
-    domainMid : anyOf(float, :class:`ExprRef`)
-        Inserts a single mid-point value into a two-element domain. The mid-point value must
-        lie between the domain minimum and maximum values. This property can be useful for
-        setting a midpoint for `diverging color scales
-        <https://vega.github.io/vega-lite/docs/scale.html#piecewise>`__. The domainMid
-        property is only intended for use with scales supporting continuous, piecewise
-        domains.
-    domainMin : anyOf(float, :class:`DateTime`, :class:`ExprRef`)
-        Sets the minimum value in the scale domain, overriding the domain property. This
-        property is only intended for use with scales having continuous domains.
-    domainRaw : :class:`ExprRef`
-        An expression for an array of raw values that, if non-null, directly overrides the
-        *domain* property. This is useful for supporting interactions such as panning or
-        zooming a scale. The scale may be initially determined using a data-driven domain,
-        then modified in response to user input by setting the rawDomain value.
-    exponent : anyOf(float, :class:`ExprRef`)
-        The exponent of the ``pow`` scale.
-    interpolate : anyOf(:class:`ScaleInterpolateEnum`, :class:`ExprRef`, :class:`ScaleInterpolateParams`)
-        The interpolation method for range values. By default, a general interpolator for
-        numbers, dates, strings and colors (in HCL space) is used. For color ranges, this
-        property allows interpolation in alternative color spaces. Legal values include
-        ``rgb``, ``hsl``, ``hsl-long``, ``lab``, ``hcl``, ``hcl-long``, ``cubehelix`` and
-        ``cubehelix-long`` ('-long' variants use longer paths in polar coordinate spaces).
-        If object-valued, this property accepts an object with a string-valued *type*
-        property and an optional numeric *gamma* property applicable to rgb and cubehelix
-        interpolators. For more, see the `d3-interpolate documentation
-        <https://github.com/d3/d3-interpolate>`__.
-
-
-        * **Default value:** ``hcl``
-    nice : anyOf(boolean, float, :class:`TimeInterval`, :class:`TimeIntervalStep`, :class:`ExprRef`)
-        Extending the domain so that it starts and ends on nice round values. This method
-        typically modifies the scale’s domain, and may only extend the bounds to the nearest
-        round value. Nicing is useful if the domain is computed from data and may be
-        irregular. For example, for a domain of *[0.201479…, 0.996679…]*, a nice domain
-        might be *[0.2, 1.0]*.
-
-        For quantitative scales such as linear, ``nice`` can be either a boolean flag or a
-        number. If ``nice`` is a number, it will represent a desired tick count. This allows
-        greater control over the step size used to extend the bounds, guaranteeing that the
-        returned ticks will exactly cover the domain.
-
-        For temporal fields with time and utc scales, the ``nice`` value can be a string
-        indicating the desired time interval. Legal values are ``"millisecond"``,
-        ``"second"``, ``"minute"``, ``"hour"``, ``"day"``, ``"week"``, ``"month"``, and
-        ``"year"``. Alternatively, ``time`` and ``utc`` scales can accept an object-valued
-        interval specifier of the form ``{"interval": "month", "step": 3}``, which includes
-        a desired number of interval steps. Here, the domain would snap to quarter (Jan,
-        Apr, Jul, Oct) boundaries.
-
-        **Default value:** ``true`` for unbinned *quantitative* fields without explicit
-        domain bounds; ``false`` otherwise.
-    padding : anyOf(float, :class:`ExprRef`)
-        For * `continuous <https://vega.github.io/vega-lite/docs/scale.html#continuous>`__ *
-        scales, expands the scale domain to accommodate the specified number of pixels on
-        each of the scale range. The scale range must represent pixels for this parameter to
-        function as intended. Padding adjustment is performed prior to all other
-        adjustments, including the effects of the  ``zero``,  ``nice``,  ``domainMin``, and
-        ``domainMax``  properties.
-
-        For * `band <https://vega.github.io/vega-lite/docs/scale.html#band>`__ * scales,
-        shortcut for setting ``paddingInner`` and ``paddingOuter`` to the same value.
-
-        For * `point <https://vega.github.io/vega-lite/docs/scale.html#point>`__ * scales,
-        alias for ``paddingOuter``.
-
-        **Default value:** For *continuous* scales, derived from the `scale config
-        <https://vega.github.io/vega-lite/docs/scale.html#config>`__ 's
-        ``continuousPadding``. For *band and point* scales, see ``paddingInner`` and
-        ``paddingOuter``. By default, Vega-Lite sets padding such that *width/height =
-        number of unique values * step*.
-    paddingInner : anyOf(float, :class:`ExprRef`)
-        The inner padding (spacing) within each band step of band scales, as a fraction of
-        the step size. This value must lie in the range [0,1].
-
-        For point scale, this property is invalid as point scales do not have internal band
-        widths (only step sizes between bands).
-
-        **Default value:** derived from the `scale config
-        <https://vega.github.io/vega-lite/docs/scale.html#config>`__ 's
-        ``bandPaddingInner``.
-    paddingOuter : anyOf(float, :class:`ExprRef`)
-        The outer padding (spacing) at the ends of the range of band and point scales, as a
-        fraction of the step size. This value must lie in the range [0,1].
-
-        **Default value:** derived from the `scale config
-        <https://vega.github.io/vega-lite/docs/scale.html#config>`__ 's ``bandPaddingOuter``
-        for band scales and ``pointPadding`` for point scales. By default, Vega-Lite sets
-        outer padding such that *width/height = number of unique values * step*.
-    range : anyOf(:class:`RangeEnum`, List(anyOf(float, string, List(float), :class:`ExprRef`)), :class:`FieldRange`)
-        The range of the scale. One of:
-
-
-        A string indicating a `pre-defined named scale range
-        <https://vega.github.io/vega-lite/docs/scale.html#range-config>`__ (e.g., example,
-        ``"symbol"``, or ``"diverging"`` ).
-
-        For `continuous scales
-        <https://vega.github.io/vega-lite/docs/scale.html#continuous>`__, two-element array
-        indicating  minimum and maximum values, or an array with more than two entries for
-        specifying a `piecewise scale
-        <https://vega.github.io/vega-lite/docs/scale.html#piecewise>`__.
-
-        For `discrete <https://vega.github.io/vega-lite/docs/scale.html#discrete>`__ and
-        `discretizing <https://vega.github.io/vega-lite/docs/scale.html#discretizing>`__
-        scales, an array of desired output values or an object with a ``field`` property
-        representing the range values.  For example, if a field ``color`` contains CSS color
-        names, we can set ``range`` to ``{field: "color"}``.
-
-        **Notes:**
-
-        1) For color scales you can also specify a color `scheme
-        <https://vega.github.io/vega-lite/docs/scale.html#scheme>`__ instead of ``range``.
-
-        2) Any directly specified ``range`` for ``x`` and ``y`` channels will be ignored.
-        Range can be customized via the view's corresponding `size
-        <https://vega.github.io/vega-lite/docs/size.html>`__ ( ``width`` and ``height`` ).
-    rangeMax : anyOf(float, string, :class:`ExprRef`)
-        Sets the maximum value in the scale range, overriding the ``range`` property or the
-        default range. This property is only intended for use with scales having continuous
-        ranges.
-    rangeMin : anyOf(float, string, :class:`ExprRef`)
-        Sets the minimum value in the scale range, overriding the ``range`` property or the
-        default range. This property is only intended for use with scales having continuous
-        ranges.
-    reverse : anyOf(boolean, :class:`ExprRef`)
-        If true, reverses the order of the scale range. **Default value:** ``false``.
-    round : anyOf(boolean, :class:`ExprRef`)
-        If ``true``, rounds numeric output values to integers. This can be helpful for
-        snapping to the pixel grid.
-
-        **Default value:** ``false``.
-    scheme : anyOf(:class:`ColorScheme`, :class:`SchemeParams`, :class:`ExprRef`)
-        A string indicating a color `scheme
-        <https://vega.github.io/vega-lite/docs/scale.html#scheme>`__ name (e.g.,
-        ``"category10"`` or ``"blues"`` ) or a `scheme parameter object
-        <https://vega.github.io/vega-lite/docs/scale.html#scheme-params>`__.
-
-        Discrete color schemes may be used with `discrete
-        <https://vega.github.io/vega-lite/docs/scale.html#discrete>`__ or `discretizing
-        <https://vega.github.io/vega-lite/docs/scale.html#discretizing>`__ scales.
-        Continuous color schemes are intended for use with color scales.
-
-        For the full list of supported schemes, please refer to the `Vega Scheme
-        <https://vega.github.io/vega/docs/schemes/#reference>`__ reference.
-    type : :class:`ScaleType`
-        The type of scale. Vega-Lite supports the following categories of scale types:
-
-        1) `Continuous Scales
-        <https://vega.github.io/vega-lite/docs/scale.html#continuous>`__ -- mapping
-        continuous domains to continuous output ranges ( `"linear"
-        <https://vega.github.io/vega-lite/docs/scale.html#linear>`__, `"pow"
-        <https://vega.github.io/vega-lite/docs/scale.html#pow>`__, `"sqrt"
-        <https://vega.github.io/vega-lite/docs/scale.html#sqrt>`__, `"symlog"
-        <https://vega.github.io/vega-lite/docs/scale.html#symlog>`__, `"log"
-        <https://vega.github.io/vega-lite/docs/scale.html#log>`__, `"time"
-        <https://vega.github.io/vega-lite/docs/scale.html#time>`__, `"utc"
-        <https://vega.github.io/vega-lite/docs/scale.html#utc>`__.
-
-        2) `Discrete Scales <https://vega.github.io/vega-lite/docs/scale.html#discrete>`__
-        -- mapping discrete domains to discrete ( `"ordinal"
-        <https://vega.github.io/vega-lite/docs/scale.html#ordinal>`__ ) or continuous (
-        `"band" <https://vega.github.io/vega-lite/docs/scale.html#band>`__ and `"point"
-        <https://vega.github.io/vega-lite/docs/scale.html#point>`__ ) output ranges.
-
-        3) `Discretizing Scales
-        <https://vega.github.io/vega-lite/docs/scale.html#discretizing>`__ -- mapping
-        continuous domains to discrete output ranges `"bin-ordinal"
-        <https://vega.github.io/vega-lite/docs/scale.html#bin-ordinal>`__, `"quantile"
-        <https://vega.github.io/vega-lite/docs/scale.html#quantile>`__, `"quantize"
-        <https://vega.github.io/vega-lite/docs/scale.html#quantize>`__ and `"threshold"
-        <https://vega.github.io/vega-lite/docs/scale.html#threshold>`__.
-
-        **Default value:** please see the `scale type table
-        <https://vega.github.io/vega-lite/docs/scale.html#type>`__.
-    zero : anyOf(boolean, :class:`ExprRef`)
-        If ``true``, ensures that a zero baseline value is included in the scale domain.
-
-        **Default value:** ``true`` for x and y channels if the quantitative field is not
-        binned and no custom ``domain`` is provided; ``false`` otherwise.
-
-        **Note:** Log, time, and utc scales do not support ``zero``.
-    """
-    _schema = {'$ref': '#/definitions/Scale'}
-
-    def __init__(self, align=Undefined, base=Undefined, bins=Undefined, clamp=Undefined,
-                 constant=Undefined, domain=Undefined, domainMax=Undefined, domainMid=Undefined,
-                 domainMin=Undefined, domainRaw=Undefined, exponent=Undefined, interpolate=Undefined,
-                 nice=Undefined, padding=Undefined, paddingInner=Undefined, paddingOuter=Undefined,
-                 range=Undefined, rangeMax=Undefined, rangeMin=Undefined, reverse=Undefined,
-                 round=Undefined, scheme=Undefined, type=Undefined, zero=Undefined, **kwds):
-        super(Scale, self).__init__(align=align, base=base, bins=bins, clamp=clamp, constant=constant,
-                                    domain=domain, domainMax=domainMax, domainMid=domainMid,
-                                    domainMin=domainMin, domainRaw=domainRaw, exponent=exponent,
-                                    interpolate=interpolate, nice=nice, padding=padding,
-                                    paddingInner=paddingInner, paddingOuter=paddingOuter, range=range,
-                                    rangeMax=rangeMax, rangeMin=rangeMin, reverse=reverse, round=round,
-                                    scheme=scheme, type=type, zero=zero, **kwds)
-
-
-class ScaleBins(VegaLiteSchema):
-    """ScaleBins schema wrapper
-
-    anyOf(List(float), :class:`ScaleBinParams`)
-    """
-    _schema = {'$ref': '#/definitions/ScaleBins'}
-
-    def __init__(self, *args, **kwds):
-        super(ScaleBins, self).__init__(*args, **kwds)
-
-
-class ScaleBinParams(ScaleBins):
-    """ScaleBinParams schema wrapper
-
-    Mapping(required=[step])
-
-    Parameters
-    ----------
-
-    step : float
-        The step size defining the bin interval width.
-    start : float
-        The starting (lowest-valued) bin boundary.
-
-        **Default value:** The lowest value of the scale domain will be used.
-    stop : float
-        The stopping (highest-valued) bin boundary.
-
-        **Default value:** The highest value of the scale domain will be used.
-    """
-    _schema = {'$ref': '#/definitions/ScaleBinParams'}
-
-    def __init__(self, step=Undefined, start=Undefined, stop=Undefined, **kwds):
-        super(ScaleBinParams, self).__init__(step=step, start=start, stop=stop, **kwds)
-
-
-class ScaleConfig(VegaLiteSchema):
-    """ScaleConfig schema wrapper
-
-    Mapping(required=[])
-
-    Parameters
-    ----------
-
-    bandPaddingInner : anyOf(float, :class:`ExprRef`)
-        Default inner padding for ``x`` and ``y`` band scales.
-
-        **Default value:**
-
-
-        * ``nestedOffsetPaddingInner`` for x/y scales with nested x/y offset scales.
-        * ``barBandPaddingInner`` for bar marks ( ``0.1`` by default)
-        * ``rectBandPaddingInner`` for rect and other marks ( ``0`` by default)
-    bandPaddingOuter : anyOf(float, :class:`ExprRef`)
-        Default outer padding for ``x`` and ``y`` band scales.
-
-        **Default value:** ``paddingInner/2`` (which makes *width/height = number of unique
-        values * step* )
-    bandWithNestedOffsetPaddingInner : anyOf(float, :class:`ExprRef`)
-        Default inner padding for ``x`` and ``y`` band scales with nested ``xOffset`` and
-        ``yOffset`` encoding.
-
-        **Default value:** ``0.2``
-    bandWithNestedOffsetPaddingOuter : anyOf(float, :class:`ExprRef`)
-        Default outer padding for ``x`` and ``y`` band scales with nested ``xOffset`` and
-        ``yOffset`` encoding.
-
-        **Default value:** ``0.2``
-    barBandPaddingInner : anyOf(float, :class:`ExprRef`)
-        Default inner padding for ``x`` and ``y`` band-ordinal scales of ``"bar"`` marks.
-
-        **Default value:** ``0.1``
-    clamp : anyOf(boolean, :class:`ExprRef`)
-        If true, values that exceed the data domain are clamped to either the minimum or
-        maximum range value
-    continuousPadding : anyOf(float, :class:`ExprRef`)
-        Default padding for continuous x/y scales.
-
-        **Default:** The bar width for continuous x-scale of a vertical bar and continuous
-        y-scale of a horizontal bar.; ``0`` otherwise.
-    maxBandSize : float
-        The default max value for mapping quantitative fields to bar's size/bandSize.
-
-        If undefined (default), we will use the axis's size (width or height) - 1.
-    maxFontSize : float
-        The default max value for mapping quantitative fields to text's size/fontSize.
-
-        **Default value:** ``40``
-    maxOpacity : float
-        Default max opacity for mapping a field to opacity.
-
-        **Default value:** ``0.8``
-    maxSize : float
-        Default max value for point size scale.
-    maxStrokeWidth : float
-        Default max strokeWidth for the scale of strokeWidth for rule and line marks and of
-        size for trail marks.
-
-        **Default value:** ``4``
-    minBandSize : float
-        The default min value for mapping quantitative fields to bar and tick's
-        size/bandSize scale with zero=false.
-
-        **Default value:** ``2``
-    minFontSize : float
-        The default min value for mapping quantitative fields to tick's size/fontSize scale
-        with zero=false
-
-        **Default value:** ``8``
-    minOpacity : float
-        Default minimum opacity for mapping a field to opacity.
-
-        **Default value:** ``0.3``
-    minSize : float
-        Default minimum value for point size scale with zero=false.
-
-        **Default value:** ``9``
-    minStrokeWidth : float
-        Default minimum strokeWidth for the scale of strokeWidth for rule and line marks and
-        of size for trail marks with zero=false.
-
-        **Default value:** ``1``
-    offsetBandPaddingInner : anyOf(float, :class:`ExprRef`)
-        Default padding inner for xOffset/yOffset's band scales.
-
-        **Default Value:** ``0``
-    offsetBandPaddingOuter : anyOf(float, :class:`ExprRef`)
-        Default padding outer for xOffset/yOffset's band scales.
-
-        **Default Value:** ``0``
-    pointPadding : anyOf(float, :class:`ExprRef`)
-        Default outer padding for ``x`` and ``y`` point-ordinal scales.
-
-        **Default value:** ``0.5`` (which makes *width/height = number of unique values *
-        step* )
-    quantileCount : float
-        Default range cardinality for `quantile
-        <https://vega.github.io/vega-lite/docs/scale.html#quantile>`__ scale.
-
-        **Default value:** ``4``
-    quantizeCount : float
-        Default range cardinality for `quantize
-        <https://vega.github.io/vega-lite/docs/scale.html#quantize>`__ scale.
-
-        **Default value:** ``4``
-    rectBandPaddingInner : anyOf(float, :class:`ExprRef`)
-        Default inner padding for ``x`` and ``y`` band-ordinal scales of ``"rect"`` marks.
-
-        **Default value:** ``0``
-    round : anyOf(boolean, :class:`ExprRef`)
-        If true, rounds numeric output values to integers. This can be helpful for snapping
-        to the pixel grid. (Only available for ``x``, ``y``, and ``size`` scales.)
-    useUnaggregatedDomain : boolean
-        Use the source data range before aggregation as scale domain instead of aggregated
-        data for aggregate axis.
-
-        This is equivalent to setting ``domain`` to ``"unaggregate"`` for aggregated
-        *quantitative* fields by default.
-
-        This property only works with aggregate functions that produce values within the raw
-        data domain ( ``"mean"``, ``"average"``, ``"median"``, ``"q1"``, ``"q3"``,
-        ``"min"``, ``"max"`` ). For other aggregations that produce values outside of the
-        raw data domain (e.g. ``"count"``, ``"sum"`` ), this property is ignored.
-
-        **Default value:** ``false``
-    xReverse : anyOf(boolean, :class:`ExprRef`)
-        Reverse x-scale by default (useful for right-to-left charts).
-    zero : boolean
-        Default ``scale.zero`` for `continuous
-        <https://vega.github.io/vega-lite/docs/scale.html#continuous>`__ scales except for
-        (1) x/y-scales of non-ranged bar or area charts and (2) size scales.
-
-        **Default value:** ``true``
-    """
-    _schema = {'$ref': '#/definitions/ScaleConfig'}
-
-    def __init__(self, bandPaddingInner=Undefined, bandPaddingOuter=Undefined,
-                 bandWithNestedOffsetPaddingInner=Undefined, bandWithNestedOffsetPaddingOuter=Undefined,
-                 barBandPaddingInner=Undefined, clamp=Undefined, continuousPadding=Undefined,
-                 maxBandSize=Undefined, maxFontSize=Undefined, maxOpacity=Undefined, maxSize=Undefined,
-                 maxStrokeWidth=Undefined, minBandSize=Undefined, minFontSize=Undefined,
-                 minOpacity=Undefined, minSize=Undefined, minStrokeWidth=Undefined,
-                 offsetBandPaddingInner=Undefined, offsetBandPaddingOuter=Undefined,
-                 pointPadding=Undefined, quantileCount=Undefined, quantizeCount=Undefined,
-                 rectBandPaddingInner=Undefined, round=Undefined, useUnaggregatedDomain=Undefined,
-                 xReverse=Undefined, zero=Undefined, **kwds):
-        super(ScaleConfig, self).__init__(bandPaddingInner=bandPaddingInner,
-                                          bandPaddingOuter=bandPaddingOuter,
-                                          bandWithNestedOffsetPaddingInner=bandWithNestedOffsetPaddingInner,
-                                          bandWithNestedOffsetPaddingOuter=bandWithNestedOffsetPaddingOuter,
-                                          barBandPaddingInner=barBandPaddingInner, clamp=clamp,
-                                          continuousPadding=continuousPadding, maxBandSize=maxBandSize,
-                                          maxFontSize=maxFontSize, maxOpacity=maxOpacity,
-                                          maxSize=maxSize, maxStrokeWidth=maxStrokeWidth,
-                                          minBandSize=minBandSize, minFontSize=minFontSize,
-                                          minOpacity=minOpacity, minSize=minSize,
-                                          minStrokeWidth=minStrokeWidth,
-                                          offsetBandPaddingInner=offsetBandPaddingInner,
-                                          offsetBandPaddingOuter=offsetBandPaddingOuter,
-                                          pointPadding=pointPadding, quantileCount=quantileCount,
-                                          quantizeCount=quantizeCount,
-                                          rectBandPaddingInner=rectBandPaddingInner, round=round,
-                                          useUnaggregatedDomain=useUnaggregatedDomain,
-                                          xReverse=xReverse, zero=zero, **kwds)
-
-
-class ScaleDatumDef(OffsetDef):
-    """ScaleDatumDef schema wrapper
-
-    Mapping(required=[])
-
-    Parameters
-    ----------
-
-    bandPosition : float
-        Relative position on a band of a stacked, binned, time unit, or band scale. For
-        example, the marks will be positioned at the beginning of the band if set to ``0``,
-        and at the middle of the band if set to ``0.5``.
-    datum : anyOf(:class:`PrimitiveValue`, :class:`DateTime`, :class:`ExprRef`, :class:`RepeatRef`)
-        A constant value in data domain.
-    scale : anyOf(:class:`Scale`, None)
-        An object defining properties of the channel's scale, which is the function that
-        transforms values in the data domain (numbers, dates, strings, etc) to visual values
-        (pixels, colors, sizes) of the encoding channels.
-
-        If ``null``, the scale will be `disabled and the data value will be directly encoded
-        <https://vega.github.io/vega-lite/docs/scale.html#disable>`__.
-
-        **Default value:** If undefined, default `scale properties
-        <https://vega.github.io/vega-lite/docs/scale.html>`__ are applied.
-
-        **See also:** `scale <https://vega.github.io/vega-lite/docs/scale.html>`__
-        documentation.
-    title : anyOf(:class:`Text`, None)
-        A title for the field. If ``null``, the title will be removed.
-
-        **Default value:**  derived from the field's name and transformation function (
-        ``aggregate``, ``bin`` and ``timeUnit`` ). If the field has an aggregate function,
-        the function is displayed as part of the title (e.g., ``"Sum of Profit"`` ). If the
-        field is binned or has a time unit applied, the applied function is shown in
-        parentheses (e.g., ``"Profit (binned)"``, ``"Transaction Date (year-month)"`` ).
-        Otherwise, the title is simply the field name.
-
-        **Notes** :
-
-        1) You can customize the default field title format by providing the `fieldTitle
-        <https://vega.github.io/vega-lite/docs/config.html#top-level-config>`__ property in
-        the `config <https://vega.github.io/vega-lite/docs/config.html>`__ or `fieldTitle
-        function via the compile function's options
-        <https://vega.github.io/vega-lite/usage/compile.html#field-title>`__.
-
-        2) If both field definition's ``title`` and axis, header, or legend ``title`` are
-        defined, axis/header/legend title will be used.
-    type : :class:`Type`
-        The type of measurement ( ``"quantitative"``, ``"temporal"``, ``"ordinal"``, or
-        ``"nominal"`` ) for the encoded field or constant value ( ``datum`` ). It can also
-        be a ``"geojson"`` type for encoding `'geoshape'
-        <https://vega.github.io/vega-lite/docs/geoshape.html>`__.
-
-        Vega-Lite automatically infers data types in many cases as discussed below. However,
-        type is required for a field if: (1) the field is not nominal and the field encoding
-        has no specified ``aggregate`` (except ``argmin`` and ``argmax`` ), ``bin``, scale
-        type, custom ``sort`` order, nor ``timeUnit`` or (2) if you wish to use an ordinal
-        scale for a field with ``bin`` or ``timeUnit``.
-
-        **Default value:**
-
-        1) For a data ``field``, ``"nominal"`` is the default data type unless the field
-        encoding has ``aggregate``, ``channel``, ``bin``, scale type, ``sort``, or
-        ``timeUnit`` that satisfies the following criteria:
-
-
-        * ``"quantitative"`` is the default type if (1) the encoded field contains ``bin``
-          or ``aggregate`` except ``"argmin"`` and ``"argmax"``, (2) the encoding channel is
-          ``latitude`` or ``longitude`` channel or (3) if the specified scale type is `a
-          quantitative scale <https://vega.github.io/vega-lite/docs/scale.html#type>`__.
-        * ``"temporal"`` is the default type if (1) the encoded field contains ``timeUnit``
-          or (2) the specified scale type is a time or utc scale
-        * ``"ordinal"`` is the default type if (1) the encoded field contains a `custom sort
-          order
-          <https://vega.github.io/vega-lite/docs/sort.html#specifying-custom-sort-order>`__,
-          (2) the specified scale type is an ordinal/point/band scale, or (3) the encoding
-          channel is ``order``.
-
-        2) For a constant value in data domain ( ``datum`` ):
-
-
-        * ``"quantitative"`` if the datum is a number
-        * ``"nominal"`` if the datum is a string
-        * ``"temporal"`` if the datum is `a date time object
-          <https://vega.github.io/vega-lite/docs/datetime.html>`__
-
-        **Note:**
-
-
-        * Data ``type`` describes the semantics of the data rather than the primitive data
-          types (number, string, etc.). The same primitive data type can have different
-          types of measurement. For example, numeric data can represent quantitative,
-          ordinal, or nominal data.
-        * Data values for a temporal field can be either a date-time string (e.g.,
-          ``"2015-03-07 12:32:17"``, ``"17:01"``, ``"2015-03-16"``. ``"2015"`` ) or a
-          timestamp number (e.g., ``1552199579097`` ).
-        * When using with `bin <https://vega.github.io/vega-lite/docs/bin.html>`__, the
-          ``type`` property can be either ``"quantitative"`` (for using a linear bin scale)
-          or `"ordinal" (for using an ordinal bin scale)
-          <https://vega.github.io/vega-lite/docs/type.html#cast-bin>`__.
-        * When using with `timeUnit
-          <https://vega.github.io/vega-lite/docs/timeunit.html>`__, the ``type`` property
-          can be either ``"temporal"`` (default, for using a temporal scale) or `"ordinal"
-          (for using an ordinal scale)
-          <https://vega.github.io/vega-lite/docs/type.html#cast-bin>`__.
-        * When using with `aggregate
-          <https://vega.github.io/vega-lite/docs/aggregate.html>`__, the ``type`` property
-          refers to the post-aggregation data type. For example, we can calculate count
-          ``distinct`` of a categorical field ``"cat"`` using ``{"aggregate": "distinct",
-          "field": "cat"}``. The ``"type"`` of the aggregate output is ``"quantitative"``.
-        * Secondary channels (e.g., ``x2``, ``y2``, ``xError``, ``yError`` ) do not have
-          ``type`` as they must have exactly the same type as their primary channels (e.g.,
-          ``x``, ``y`` ).
-
-        **See also:** `type <https://vega.github.io/vega-lite/docs/type.html>`__
-        documentation.
-    """
-    _schema = {'$ref': '#/definitions/ScaleDatumDef'}
-
-    def __init__(self, bandPosition=Undefined, datum=Undefined, scale=Undefined, title=Undefined,
-                 type=Undefined, **kwds):
-        super(ScaleDatumDef, self).__init__(bandPosition=bandPosition, datum=datum, scale=scale,
-                                            title=title, type=type, **kwds)
-
-
-class ScaleFieldDef(OffsetDef):
-    """ScaleFieldDef schema wrapper
-
-    Mapping(required=[])
-
-    Parameters
-    ----------
-
-    aggregate : :class:`Aggregate`
-        Aggregation function for the field (e.g., ``"mean"``, ``"sum"``, ``"median"``,
-        ``"min"``, ``"max"``, ``"count"`` ).
-
-        **Default value:** ``undefined`` (None)
-
-        **See also:** `aggregate <https://vega.github.io/vega-lite/docs/aggregate.html>`__
-        documentation.
-    bandPosition : float
-        Relative position on a band of a stacked, binned, time unit, or band scale. For
-        example, the marks will be positioned at the beginning of the band if set to ``0``,
-        and at the middle of the band if set to ``0.5``.
-    bin : anyOf(boolean, :class:`BinParams`, None)
-        A flag for binning a ``quantitative`` field, `an object defining binning parameters
-        <https://vega.github.io/vega-lite/docs/bin.html#bin-parameters>`__, or indicating
-        that the data for ``x`` or ``y`` channel are binned before they are imported into
-        Vega-Lite ( ``"binned"`` ).
-
-
-        If ``true``, default `binning parameters
-        <https://vega.github.io/vega-lite/docs/bin.html#bin-parameters>`__ will be applied.
-
-        If ``"binned"``, this indicates that the data for the ``x`` (or ``y`` ) channel are
-        already binned. You can map the bin-start field to ``x`` (or ``y`` ) and the bin-end
-        field to ``x2`` (or ``y2`` ). The scale and axis will be formatted similar to
-        binning in Vega-Lite.  To adjust the axis ticks based on the bin step, you can also
-        set the axis's `tickMinStep
-        <https://vega.github.io/vega-lite/docs/axis.html#ticks>`__ property.
-
-        **Default value:** ``false``
-
-        **See also:** `bin <https://vega.github.io/vega-lite/docs/bin.html>`__
-        documentation.
-    field : :class:`Field`
-        **Required.** A string defining the name of the field from which to pull a data
-        value or an object defining iterated values from the `repeat
-        <https://vega.github.io/vega-lite/docs/repeat.html>`__ operator.
-
-        **See also:** `field <https://vega.github.io/vega-lite/docs/field.html>`__
-        documentation.
-
-        **Notes:** 1)  Dots ( ``.`` ) and brackets ( ``[`` and ``]`` ) can be used to access
-        nested objects (e.g., ``"field": "foo.bar"`` and ``"field": "foo['bar']"`` ). If
-        field names contain dots or brackets but are not nested, you can use ``\\`` to
-        escape dots and brackets (e.g., ``"a\\.b"`` and ``"a\\[0\\]"`` ). See more details
-        about escaping in the `field documentation
-        <https://vega.github.io/vega-lite/docs/field.html>`__. 2) ``field`` is not required
-        if ``aggregate`` is ``count``.
-    scale : anyOf(:class:`Scale`, None)
-        An object defining properties of the channel's scale, which is the function that
-        transforms values in the data domain (numbers, dates, strings, etc) to visual values
-        (pixels, colors, sizes) of the encoding channels.
-
-        If ``null``, the scale will be `disabled and the data value will be directly encoded
-        <https://vega.github.io/vega-lite/docs/scale.html#disable>`__.
-
-        **Default value:** If undefined, default `scale properties
-        <https://vega.github.io/vega-lite/docs/scale.html>`__ are applied.
-
-        **See also:** `scale <https://vega.github.io/vega-lite/docs/scale.html>`__
-        documentation.
-    sort : :class:`Sort`
-        Sort order for the encoded field.
-
-        For continuous fields (quantitative or temporal), ``sort`` can be either
-        ``"ascending"`` or ``"descending"``.
-
-        For discrete fields, ``sort`` can be one of the following:
-
-
-        * ``"ascending"`` or ``"descending"`` -- for sorting by the values' natural order in
-          JavaScript.
-        * `A string indicating an encoding channel name to sort by
-          <https://vega.github.io/vega-lite/docs/sort.html#sort-by-encoding>`__ (e.g.,
-          ``"x"`` or ``"y"`` ) with an optional minus prefix for descending sort (e.g.,
-          ``"-x"`` to sort by x-field, descending). This channel string is short-form of `a
-          sort-by-encoding definition
-          <https://vega.github.io/vega-lite/docs/sort.html#sort-by-encoding>`__. For
-          example, ``"sort": "-x"`` is equivalent to ``"sort": {"encoding": "x", "order":
-          "descending"}``.
-        * `A sort field definition
-          <https://vega.github.io/vega-lite/docs/sort.html#sort-field>`__ for sorting by
-          another field.
-        * `An array specifying the field values in preferred order
-          <https://vega.github.io/vega-lite/docs/sort.html#sort-array>`__. In this case, the
-          sort order will obey the values in the array, followed by any unspecified values
-          in their original order. For discrete time field, values in the sort array can be
-          `date-time definition objects
-          <https://vega.github.io/vega-lite/docs/datetime.html>`__. In addition, for time
-          units ``"month"`` and ``"day"``, the values can be the month or day names (case
-          insensitive) or their 3-letter initials (e.g., ``"Mon"``, ``"Tue"`` ).
-        * ``null`` indicating no sort.
-
-        **Default value:** ``"ascending"``
-
-        **Note:** ``null`` and sorting by another channel is not supported for ``row`` and
-        ``column``.
-
-        **See also:** `sort <https://vega.github.io/vega-lite/docs/sort.html>`__
-        documentation.
-    timeUnit : anyOf(:class:`TimeUnit`, :class:`BinnedTimeUnit`, :class:`TimeUnitParams`)
-        Time unit (e.g., ``year``, ``yearmonth``, ``month``, ``hours`` ) for a temporal
-        field. or `a temporal field that gets casted as ordinal
-        <https://vega.github.io/vega-lite/docs/type.html#cast>`__.
-
-        **Default value:** ``undefined`` (None)
-
-        **See also:** `timeUnit <https://vega.github.io/vega-lite/docs/timeunit.html>`__
-        documentation.
-    title : anyOf(:class:`Text`, None)
-        A title for the field. If ``null``, the title will be removed.
-
-        **Default value:**  derived from the field's name and transformation function (
-        ``aggregate``, ``bin`` and ``timeUnit`` ). If the field has an aggregate function,
-        the function is displayed as part of the title (e.g., ``"Sum of Profit"`` ). If the
-        field is binned or has a time unit applied, the applied function is shown in
-        parentheses (e.g., ``"Profit (binned)"``, ``"Transaction Date (year-month)"`` ).
-        Otherwise, the title is simply the field name.
-
-        **Notes** :
-
-        1) You can customize the default field title format by providing the `fieldTitle
-        <https://vega.github.io/vega-lite/docs/config.html#top-level-config>`__ property in
-        the `config <https://vega.github.io/vega-lite/docs/config.html>`__ or `fieldTitle
-        function via the compile function's options
-        <https://vega.github.io/vega-lite/usage/compile.html#field-title>`__.
-
-        2) If both field definition's ``title`` and axis, header, or legend ``title`` are
-        defined, axis/header/legend title will be used.
-    type : :class:`StandardType`
-        The type of measurement ( ``"quantitative"``, ``"temporal"``, ``"ordinal"``, or
-        ``"nominal"`` ) for the encoded field or constant value ( ``datum`` ). It can also
-        be a ``"geojson"`` type for encoding `'geoshape'
-        <https://vega.github.io/vega-lite/docs/geoshape.html>`__.
-
-        Vega-Lite automatically infers data types in many cases as discussed below. However,
-        type is required for a field if: (1) the field is not nominal and the field encoding
-        has no specified ``aggregate`` (except ``argmin`` and ``argmax`` ), ``bin``, scale
-        type, custom ``sort`` order, nor ``timeUnit`` or (2) if you wish to use an ordinal
-        scale for a field with ``bin`` or ``timeUnit``.
-
-        **Default value:**
-
-        1) For a data ``field``, ``"nominal"`` is the default data type unless the field
-        encoding has ``aggregate``, ``channel``, ``bin``, scale type, ``sort``, or
-        ``timeUnit`` that satisfies the following criteria:
-
-
-        * ``"quantitative"`` is the default type if (1) the encoded field contains ``bin``
-          or ``aggregate`` except ``"argmin"`` and ``"argmax"``, (2) the encoding channel is
-          ``latitude`` or ``longitude`` channel or (3) if the specified scale type is `a
-          quantitative scale <https://vega.github.io/vega-lite/docs/scale.html#type>`__.
-        * ``"temporal"`` is the default type if (1) the encoded field contains ``timeUnit``
-          or (2) the specified scale type is a time or utc scale
-        * ``"ordinal"`` is the default type if (1) the encoded field contains a `custom sort
-          order
-          <https://vega.github.io/vega-lite/docs/sort.html#specifying-custom-sort-order>`__,
-          (2) the specified scale type is an ordinal/point/band scale, or (3) the encoding
-          channel is ``order``.
-
-        2) For a constant value in data domain ( ``datum`` ):
-
-
-        * ``"quantitative"`` if the datum is a number
-        * ``"nominal"`` if the datum is a string
-        * ``"temporal"`` if the datum is `a date time object
-          <https://vega.github.io/vega-lite/docs/datetime.html>`__
-
-        **Note:**
-
-
-        * Data ``type`` describes the semantics of the data rather than the primitive data
-          types (number, string, etc.). The same primitive data type can have different
-          types of measurement. For example, numeric data can represent quantitative,
-          ordinal, or nominal data.
-        * Data values for a temporal field can be either a date-time string (e.g.,
-          ``"2015-03-07 12:32:17"``, ``"17:01"``, ``"2015-03-16"``. ``"2015"`` ) or a
-          timestamp number (e.g., ``1552199579097`` ).
-        * When using with `bin <https://vega.github.io/vega-lite/docs/bin.html>`__, the
-          ``type`` property can be either ``"quantitative"`` (for using a linear bin scale)
-          or `"ordinal" (for using an ordinal bin scale)
-          <https://vega.github.io/vega-lite/docs/type.html#cast-bin>`__.
-        * When using with `timeUnit
-          <https://vega.github.io/vega-lite/docs/timeunit.html>`__, the ``type`` property
-          can be either ``"temporal"`` (default, for using a temporal scale) or `"ordinal"
-          (for using an ordinal scale)
-          <https://vega.github.io/vega-lite/docs/type.html#cast-bin>`__.
-        * When using with `aggregate
-          <https://vega.github.io/vega-lite/docs/aggregate.html>`__, the ``type`` property
-          refers to the post-aggregation data type. For example, we can calculate count
-          ``distinct`` of a categorical field ``"cat"`` using ``{"aggregate": "distinct",
-          "field": "cat"}``. The ``"type"`` of the aggregate output is ``"quantitative"``.
-        * Secondary channels (e.g., ``x2``, ``y2``, ``xError``, ``yError`` ) do not have
-          ``type`` as they must have exactly the same type as their primary channels (e.g.,
-          ``x``, ``y`` ).
-
-        **See also:** `type <https://vega.github.io/vega-lite/docs/type.html>`__
-        documentation.
-    """
-    _schema = {'$ref': '#/definitions/ScaleFieldDef'}
-
-    def __init__(self, aggregate=Undefined, bandPosition=Undefined, bin=Undefined, field=Undefined,
-                 scale=Undefined, sort=Undefined, timeUnit=Undefined, title=Undefined, type=Undefined,
-                 **kwds):
-        super(ScaleFieldDef, self).__init__(aggregate=aggregate, bandPosition=bandPosition, bin=bin,
-                                            field=field, scale=scale, sort=sort, timeUnit=timeUnit,
-                                            title=title, type=type, **kwds)
-
-
-class ScaleInterpolateEnum(VegaLiteSchema):
-    """ScaleInterpolateEnum schema wrapper
-
-    enum('rgb', 'lab', 'hcl', 'hsl', 'hsl-long', 'hcl-long', 'cubehelix', 'cubehelix-long')
-    """
-    _schema = {'$ref': '#/definitions/ScaleInterpolateEnum'}
-
-    def __init__(self, *args):
-        super(ScaleInterpolateEnum, self).__init__(*args)
-
-
-class ScaleInterpolateParams(VegaLiteSchema):
-    """ScaleInterpolateParams schema wrapper
-
-    Mapping(required=[type])
-
-    Parameters
-    ----------
-
-    type : enum('rgb', 'cubehelix', 'cubehelix-long')
-
-    gamma : float
-
-    """
-    _schema = {'$ref': '#/definitions/ScaleInterpolateParams'}
-
-    def __init__(self, type=Undefined, gamma=Undefined, **kwds):
-        super(ScaleInterpolateParams, self).__init__(type=type, gamma=gamma, **kwds)
-
-
-class ScaleResolveMap(VegaLiteSchema):
-    """ScaleResolveMap schema wrapper
-
-    Mapping(required=[])
-
-    Parameters
-    ----------
-
-    angle : :class:`ResolveMode`
-
-    color : :class:`ResolveMode`
-
-    fill : :class:`ResolveMode`
-
-    fillOpacity : :class:`ResolveMode`
-
-    opacity : :class:`ResolveMode`
-
-    radius : :class:`ResolveMode`
-
-    shape : :class:`ResolveMode`
-
-    size : :class:`ResolveMode`
-
-    stroke : :class:`ResolveMode`
-
-    strokeDash : :class:`ResolveMode`
-
-    strokeOpacity : :class:`ResolveMode`
-
-    strokeWidth : :class:`ResolveMode`
-
-    theta : :class:`ResolveMode`
-
-    x : :class:`ResolveMode`
-
-    xOffset : :class:`ResolveMode`
-
-    y : :class:`ResolveMode`
-
-    yOffset : :class:`ResolveMode`
-
-    """
-    _schema = {'$ref': '#/definitions/ScaleResolveMap'}
-
-    def __init__(self, angle=Undefined, color=Undefined, fill=Undefined, fillOpacity=Undefined,
-                 opacity=Undefined, radius=Undefined, shape=Undefined, size=Undefined, stroke=Undefined,
-                 strokeDash=Undefined, strokeOpacity=Undefined, strokeWidth=Undefined, theta=Undefined,
-                 x=Undefined, xOffset=Undefined, y=Undefined, yOffset=Undefined, **kwds):
-        super(ScaleResolveMap, self).__init__(angle=angle, color=color, fill=fill,
-                                              fillOpacity=fillOpacity, opacity=opacity, radius=radius,
-                                              shape=shape, size=size, stroke=stroke,
-                                              strokeDash=strokeDash, strokeOpacity=strokeOpacity,
-                                              strokeWidth=strokeWidth, theta=theta, x=x,
-                                              xOffset=xOffset, y=y, yOffset=yOffset, **kwds)
-
-
-class ScaleType(VegaLiteSchema):
-    """ScaleType schema wrapper
-
-    enum('linear', 'log', 'pow', 'sqrt', 'symlog', 'identity', 'sequential', 'time', 'utc',
-    'quantile', 'quantize', 'threshold', 'bin-ordinal', 'ordinal', 'point', 'band')
-    """
-    _schema = {'$ref': '#/definitions/ScaleType'}
-
-    def __init__(self, *args):
-        super(ScaleType, self).__init__(*args)
-
-
-class SchemeParams(VegaLiteSchema):
-    """SchemeParams schema wrapper
-
-    Mapping(required=[name])
-
-    Parameters
-    ----------
-
-    name : :class:`ColorScheme`
-        A color scheme name for ordinal scales (e.g., ``"category10"`` or ``"blues"`` ).
-
-        For the full list of supported schemes, please refer to the `Vega Scheme
-        <https://vega.github.io/vega/docs/schemes/#reference>`__ reference.
-    count : float
-        The number of colors to use in the scheme. This can be useful for scale types such
-        as ``"quantize"``, which use the length of the scale range to determine the number
-        of discrete bins for the scale domain.
-    extent : List(float)
-        The extent of the color range to use. For example ``[0.2, 1]`` will rescale the
-        color scheme such that color values in the range *[0, 0.2)* are excluded from the
-        scheme.
-    """
-    _schema = {'$ref': '#/definitions/SchemeParams'}
-
-    def __init__(self, name=Undefined, count=Undefined, extent=Undefined, **kwds):
-        super(SchemeParams, self).__init__(name=name, count=count, extent=extent, **kwds)
-
-
-class SecondaryFieldDef(Position2Def):
-    """SecondaryFieldDef schema wrapper
-
-    Mapping(required=[])
-    A field definition of a secondary channel that shares a scale with another primary channel.
-    For example, ``x2``, ``xError`` and ``xError2`` share the same scale with ``x``.
-
-    Parameters
-    ----------
-
-    aggregate : :class:`Aggregate`
-        Aggregation function for the field (e.g., ``"mean"``, ``"sum"``, ``"median"``,
-        ``"min"``, ``"max"``, ``"count"`` ).
-
-        **Default value:** ``undefined`` (None)
-
-        **See also:** `aggregate <https://vega.github.io/vega-lite/docs/aggregate.html>`__
-        documentation.
-    bandPosition : float
-        Relative position on a band of a stacked, binned, time unit, or band scale. For
-        example, the marks will be positioned at the beginning of the band if set to ``0``,
-        and at the middle of the band if set to ``0.5``.
-    bin : None
-        A flag for binning a ``quantitative`` field, `an object defining binning parameters
-        <https://vega.github.io/vega-lite/docs/bin.html#bin-parameters>`__, or indicating
-        that the data for ``x`` or ``y`` channel are binned before they are imported into
-        Vega-Lite ( ``"binned"`` ).
-
-
-        If ``true``, default `binning parameters
-        <https://vega.github.io/vega-lite/docs/bin.html#bin-parameters>`__ will be applied.
-
-        If ``"binned"``, this indicates that the data for the ``x`` (or ``y`` ) channel are
-        already binned. You can map the bin-start field to ``x`` (or ``y`` ) and the bin-end
-        field to ``x2`` (or ``y2`` ). The scale and axis will be formatted similar to
-        binning in Vega-Lite.  To adjust the axis ticks based on the bin step, you can also
-        set the axis's `tickMinStep
-        <https://vega.github.io/vega-lite/docs/axis.html#ticks>`__ property.
-
-        **Default value:** ``false``
-
-        **See also:** `bin <https://vega.github.io/vega-lite/docs/bin.html>`__
-        documentation.
-    field : :class:`Field`
-        **Required.** A string defining the name of the field from which to pull a data
-        value or an object defining iterated values from the `repeat
-        <https://vega.github.io/vega-lite/docs/repeat.html>`__ operator.
-
-        **See also:** `field <https://vega.github.io/vega-lite/docs/field.html>`__
-        documentation.
-
-        **Notes:** 1)  Dots ( ``.`` ) and brackets ( ``[`` and ``]`` ) can be used to access
-        nested objects (e.g., ``"field": "foo.bar"`` and ``"field": "foo['bar']"`` ). If
-        field names contain dots or brackets but are not nested, you can use ``\\`` to
-        escape dots and brackets (e.g., ``"a\\.b"`` and ``"a\\[0\\]"`` ). See more details
-        about escaping in the `field documentation
-        <https://vega.github.io/vega-lite/docs/field.html>`__. 2) ``field`` is not required
-        if ``aggregate`` is ``count``.
-    timeUnit : anyOf(:class:`TimeUnit`, :class:`BinnedTimeUnit`, :class:`TimeUnitParams`)
-        Time unit (e.g., ``year``, ``yearmonth``, ``month``, ``hours`` ) for a temporal
-        field. or `a temporal field that gets casted as ordinal
-        <https://vega.github.io/vega-lite/docs/type.html#cast>`__.
-
-        **Default value:** ``undefined`` (None)
-
-        **See also:** `timeUnit <https://vega.github.io/vega-lite/docs/timeunit.html>`__
-        documentation.
-    title : anyOf(:class:`Text`, None)
-        A title for the field. If ``null``, the title will be removed.
-
-        **Default value:**  derived from the field's name and transformation function (
-        ``aggregate``, ``bin`` and ``timeUnit`` ). If the field has an aggregate function,
-        the function is displayed as part of the title (e.g., ``"Sum of Profit"`` ). If the
-        field is binned or has a time unit applied, the applied function is shown in
-        parentheses (e.g., ``"Profit (binned)"``, ``"Transaction Date (year-month)"`` ).
-        Otherwise, the title is simply the field name.
-
-        **Notes** :
-
-        1) You can customize the default field title format by providing the `fieldTitle
-        <https://vega.github.io/vega-lite/docs/config.html#top-level-config>`__ property in
-        the `config <https://vega.github.io/vega-lite/docs/config.html>`__ or `fieldTitle
-        function via the compile function's options
-        <https://vega.github.io/vega-lite/usage/compile.html#field-title>`__.
-
-        2) If both field definition's ``title`` and axis, header, or legend ``title`` are
-        defined, axis/header/legend title will be used.
-    """
-    _schema = {'$ref': '#/definitions/SecondaryFieldDef'}
-
-    def __init__(self, aggregate=Undefined, bandPosition=Undefined, bin=Undefined, field=Undefined,
-                 timeUnit=Undefined, title=Undefined, **kwds):
-        super(SecondaryFieldDef, self).__init__(aggregate=aggregate, bandPosition=bandPosition, bin=bin,
-                                                field=field, timeUnit=timeUnit, title=title, **kwds)
-
-
-class SelectionConfig(VegaLiteSchema):
-    """SelectionConfig schema wrapper
-
-    Mapping(required=[])
-
-    Parameters
-    ----------
-
-    interval : :class:`IntervalSelectionConfigWithoutType`
-        The default definition for an `interval
-        <https://vega.github.io/vega-lite/docs/parameter.html#select>`__ selection. All
-        properties and transformations for an interval selection definition (except ``type``
-        ) may be specified here.
-
-        For instance, setting ``interval`` to ``{"translate": false}`` disables the ability
-        to move interval selections by default.
-    point : :class:`PointSelectionConfigWithoutType`
-        The default definition for a `point
-        <https://vega.github.io/vega-lite/docs/parameter.html#select>`__ selection. All
-        properties and transformations  for a point selection definition (except ``type`` )
-        may be specified here.
-
-        For instance, setting ``point`` to ``{"on": "dblclick"}`` populates point selections
-        on double-click by default.
-    """
-    _schema = {'$ref': '#/definitions/SelectionConfig'}
-
-    def __init__(self, interval=Undefined, point=Undefined, **kwds):
-        super(SelectionConfig, self).__init__(interval=interval, point=point, **kwds)
-
-
-class SelectionInit(VegaLiteSchema):
-    """SelectionInit schema wrapper
-
-    anyOf(:class:`PrimitiveValue`, :class:`DateTime`)
-    """
-    _schema = {'$ref': '#/definitions/SelectionInit'}
-
-    def __init__(self, *args, **kwds):
-        super(SelectionInit, self).__init__(*args, **kwds)
-
-
-class DateTime(SelectionInit):
-    """DateTime schema wrapper
-
-    Mapping(required=[])
-    Object for defining datetime in Vega-Lite Filter. If both month and quarter are provided,
-    month has higher precedence. ``day`` cannot be combined with other date. We accept string
-    for month and day names.
-
-    Parameters
-    ----------
-
-    date : float
-        Integer value representing the date (day of the month) from 1-31.
-    day : anyOf(:class:`Day`, string)
-        Value representing the day of a week. This can be one of: (1) integer value -- ``1``
-        represents Monday; (2) case-insensitive day name (e.g., ``"Monday"`` ); (3)
-        case-insensitive, 3-character short day name (e.g., ``"Mon"`` ).
-
-        **Warning:** A DateTime definition object with ``day`` ** should not be combined
-        with ``year``, ``quarter``, ``month``, or ``date``.
-    hours : float
-        Integer value representing the hour of a day from 0-23.
-    milliseconds : float
-        Integer value representing the millisecond segment of time.
-    minutes : float
-        Integer value representing the minute segment of time from 0-59.
-    month : anyOf(:class:`Month`, string)
-        One of: (1) integer value representing the month from ``1`` - ``12``. ``1``
-        represents January; (2) case-insensitive month name (e.g., ``"January"`` ); (3)
-        case-insensitive, 3-character short month name (e.g., ``"Jan"`` ).
-    quarter : float
-        Integer value representing the quarter of the year (from 1-4).
-    seconds : float
-        Integer value representing the second segment (0-59) of a time value
-    utc : boolean
-        A boolean flag indicating if date time is in utc time. If false, the date time is in
-        local time
-    year : float
-        Integer value representing the year.
-    """
-    _schema = {'$ref': '#/definitions/DateTime'}
-
-    def __init__(self, date=Undefined, day=Undefined, hours=Undefined, milliseconds=Undefined,
-                 minutes=Undefined, month=Undefined, quarter=Undefined, seconds=Undefined,
-                 utc=Undefined, year=Undefined, **kwds):
-        super(DateTime, self).__init__(date=date, day=day, hours=hours, milliseconds=milliseconds,
-                                       minutes=minutes, month=month, quarter=quarter, seconds=seconds,
-                                       utc=utc, year=year, **kwds)
-
-
-class PrimitiveValue(SelectionInit):
-    """PrimitiveValue schema wrapper
-
-    anyOf(float, string, boolean, None)
-    """
-    _schema = {'$ref': '#/definitions/PrimitiveValue'}
-
-    def __init__(self, *args):
-        super(PrimitiveValue, self).__init__(*args)
-
-
-class SelectionInitInterval(VegaLiteSchema):
-    """SelectionInitInterval schema wrapper
-
-    anyOf(:class:`Vector2boolean`, :class:`Vector2number`, :class:`Vector2string`,
-    :class:`Vector2DateTime`)
-    """
-    _schema = {'$ref': '#/definitions/SelectionInitInterval'}
-
-    def __init__(self, *args, **kwds):
-        super(SelectionInitInterval, self).__init__(*args, **kwds)
-
-
-class SelectionInitIntervalMapping(VegaLiteSchema):
-    """SelectionInitIntervalMapping schema wrapper
-
-    Mapping(required=[])
-    """
-    _schema = {'$ref': '#/definitions/SelectionInitIntervalMapping'}
-
-    def __init__(self, **kwds):
-        super(SelectionInitIntervalMapping, self).__init__(**kwds)
-
-
-class SelectionInitMapping(VegaLiteSchema):
-    """SelectionInitMapping schema wrapper
-
-    Mapping(required=[])
-    """
-    _schema = {'$ref': '#/definitions/SelectionInitMapping'}
-
-    def __init__(self, **kwds):
-        super(SelectionInitMapping, self).__init__(**kwds)
-
-
-class SelectionParameter(VegaLiteSchema):
-    """SelectionParameter schema wrapper
-
-    Mapping(required=[name, select])
-
-    Parameters
-    ----------
-
-    name : :class:`ParameterName`
-        Required. A unique name for the selection parameter. Selection names should be valid
-        JavaScript identifiers: they should contain only alphanumeric characters (or "$", or
-        "_") and may not start with a digit. Reserved keywords that may not be used as
-        parameter names are "datum", "event", "item", and "parent".
-    select : anyOf(:class:`SelectionType`, :class:`PointSelectionConfig`, :class:`IntervalSelectionConfig`)
-        Determines the default event processing and data query for the selection. Vega-Lite
-        currently supports two selection types:
-
-
-        * ``"point"`` -- to select multiple discrete data values; the first value is
-          selected on ``click`` and additional values toggled on shift-click.
-        * ``"interval"`` -- to select a continuous range of data values on ``drag``.
-    bind : anyOf(:class:`Binding`, Mapping(required=[]), :class:`LegendBinding`, string)
-        When set, a selection is populated by input elements (also known as dynamic query
-        widgets) or by interacting with the corresponding legend. Direct manipulation
-        interaction is disabled by default; to re-enable it, set the selection's `on
-        <https://vega.github.io/vega-lite/docs/selection.html#common-selection-properties>`__
-        property.
-
-        Legend bindings are restricted to selections that only specify a single field or
-        encoding.
-
-        Query widget binding takes the form of Vega's `input element binding definition
-        <https://vega.github.io/vega/docs/signals/#bind>`__ or can be a mapping between
-        projected field/encodings and binding definitions.
-
-        **See also:** `bind <https://vega.github.io/vega-lite/docs/bind.html>`__
-        documentation.
-    value : anyOf(:class:`SelectionInit`, List(:class:`SelectionInitMapping`), :class:`SelectionInitIntervalMapping`)
-        Initialize the selection with a mapping between `projected channels or field names
-        <https://vega.github.io/vega-lite/docs/selection.html#project>`__ and initial
-        values.
-
-        **See also:** `init <https://vega.github.io/vega-lite/docs/value.html>`__
-        documentation.
-    """
-    _schema = {'$ref': '#/definitions/SelectionParameter'}
-
-    def __init__(self, name=Undefined, select=Undefined, bind=Undefined, value=Undefined, **kwds):
-        super(SelectionParameter, self).__init__(name=name, select=select, bind=bind, value=value,
-                                                 **kwds)
-
-
-class SelectionResolution(VegaLiteSchema):
-    """SelectionResolution schema wrapper
-
-    enum('global', 'union', 'intersect')
-    """
-    _schema = {'$ref': '#/definitions/SelectionResolution'}
-
-    def __init__(self, *args):
-        super(SelectionResolution, self).__init__(*args)
-
-
-class SelectionType(VegaLiteSchema):
-    """SelectionType schema wrapper
-
-    enum('point', 'interval')
-    """
-    _schema = {'$ref': '#/definitions/SelectionType'}
-
-    def __init__(self, *args):
-        super(SelectionType, self).__init__(*args)
-
-
-class SequenceGenerator(Generator):
-    """SequenceGenerator schema wrapper
-
-    Mapping(required=[sequence])
-
-    Parameters
-    ----------
-
-    sequence : :class:`SequenceParams`
-        Generate a sequence of numbers.
-    name : string
-        Provide a placeholder name and bind data at runtime.
-    """
-    _schema = {'$ref': '#/definitions/SequenceGenerator'}
-
-    def __init__(self, sequence=Undefined, name=Undefined, **kwds):
-        super(SequenceGenerator, self).__init__(sequence=sequence, name=name, **kwds)
-
-
-class SequenceParams(VegaLiteSchema):
-    """SequenceParams schema wrapper
-
-    Mapping(required=[start, stop])
-
-    Parameters
-    ----------
-
-    start : float
-        The starting value of the sequence (inclusive).
-    stop : float
-        The ending value of the sequence (exclusive).
-    step : float
-        The step value between sequence entries.
-
-        **Default value:** ``1``
-    as : :class:`FieldName`
-        The name of the generated sequence field.
-
-        **Default value:** ``"data"``
-    """
-    _schema = {'$ref': '#/definitions/SequenceParams'}
-
-    def __init__(self, start=Undefined, stop=Undefined, step=Undefined, **kwds):
-        super(SequenceParams, self).__init__(start=start, stop=stop, step=step, **kwds)
-
-
-class SequentialMultiHue(ColorScheme):
-    """SequentialMultiHue schema wrapper
-
-    enum('turbo', 'viridis', 'inferno', 'magma', 'plasma', 'cividis', 'bluegreen',
-    'bluegreen-3', 'bluegreen-4', 'bluegreen-5', 'bluegreen-6', 'bluegreen-7', 'bluegreen-8',
-    'bluegreen-9', 'bluepurple', 'bluepurple-3', 'bluepurple-4', 'bluepurple-5', 'bluepurple-6',
-    'bluepurple-7', 'bluepurple-8', 'bluepurple-9', 'goldgreen', 'goldgreen-3', 'goldgreen-4',
-    'goldgreen-5', 'goldgreen-6', 'goldgreen-7', 'goldgreen-8', 'goldgreen-9', 'goldorange',
-    'goldorange-3', 'goldorange-4', 'goldorange-5', 'goldorange-6', 'goldorange-7',
-    'goldorange-8', 'goldorange-9', 'goldred', 'goldred-3', 'goldred-4', 'goldred-5',
-    'goldred-6', 'goldred-7', 'goldred-8', 'goldred-9', 'greenblue', 'greenblue-3',
-    'greenblue-4', 'greenblue-5', 'greenblue-6', 'greenblue-7', 'greenblue-8', 'greenblue-9',
-    'orangered', 'orangered-3', 'orangered-4', 'orangered-5', 'orangered-6', 'orangered-7',
-    'orangered-8', 'orangered-9', 'purplebluegreen', 'purplebluegreen-3', 'purplebluegreen-4',
-    'purplebluegreen-5', 'purplebluegreen-6', 'purplebluegreen-7', 'purplebluegreen-8',
-    'purplebluegreen-9', 'purpleblue', 'purpleblue-3', 'purpleblue-4', 'purpleblue-5',
-    'purpleblue-6', 'purpleblue-7', 'purpleblue-8', 'purpleblue-9', 'purplered', 'purplered-3',
-    'purplered-4', 'purplered-5', 'purplered-6', 'purplered-7', 'purplered-8', 'purplered-9',
-    'redpurple', 'redpurple-3', 'redpurple-4', 'redpurple-5', 'redpurple-6', 'redpurple-7',
-    'redpurple-8', 'redpurple-9', 'yellowgreenblue', 'yellowgreenblue-3', 'yellowgreenblue-4',
-    'yellowgreenblue-5', 'yellowgreenblue-6', 'yellowgreenblue-7', 'yellowgreenblue-8',
-    'yellowgreenblue-9', 'yellowgreen', 'yellowgreen-3', 'yellowgreen-4', 'yellowgreen-5',
-    'yellowgreen-6', 'yellowgreen-7', 'yellowgreen-8', 'yellowgreen-9', 'yelloworangebrown',
-    'yelloworangebrown-3', 'yelloworangebrown-4', 'yelloworangebrown-5', 'yelloworangebrown-6',
-    'yelloworangebrown-7', 'yelloworangebrown-8', 'yelloworangebrown-9', 'yelloworangered',
-    'yelloworangered-3', 'yelloworangered-4', 'yelloworangered-5', 'yelloworangered-6',
-    'yelloworangered-7', 'yelloworangered-8', 'yelloworangered-9', 'darkblue', 'darkblue-3',
-    'darkblue-4', 'darkblue-5', 'darkblue-6', 'darkblue-7', 'darkblue-8', 'darkblue-9',
-    'darkgold', 'darkgold-3', 'darkgold-4', 'darkgold-5', 'darkgold-6', 'darkgold-7',
-    'darkgold-8', 'darkgold-9', 'darkgreen', 'darkgreen-3', 'darkgreen-4', 'darkgreen-5',
-    'darkgreen-6', 'darkgreen-7', 'darkgreen-8', 'darkgreen-9', 'darkmulti', 'darkmulti-3',
-    'darkmulti-4', 'darkmulti-5', 'darkmulti-6', 'darkmulti-7', 'darkmulti-8', 'darkmulti-9',
-    'darkred', 'darkred-3', 'darkred-4', 'darkred-5', 'darkred-6', 'darkred-7', 'darkred-8',
-    'darkred-9', 'lightgreyred', 'lightgreyred-3', 'lightgreyred-4', 'lightgreyred-5',
-    'lightgreyred-6', 'lightgreyred-7', 'lightgreyred-8', 'lightgreyred-9', 'lightgreyteal',
-    'lightgreyteal-3', 'lightgreyteal-4', 'lightgreyteal-5', 'lightgreyteal-6',
-    'lightgreyteal-7', 'lightgreyteal-8', 'lightgreyteal-9', 'lightmulti', 'lightmulti-3',
-    'lightmulti-4', 'lightmulti-5', 'lightmulti-6', 'lightmulti-7', 'lightmulti-8',
-    'lightmulti-9', 'lightorange', 'lightorange-3', 'lightorange-4', 'lightorange-5',
-    'lightorange-6', 'lightorange-7', 'lightorange-8', 'lightorange-9', 'lighttealblue',
-    'lighttealblue-3', 'lighttealblue-4', 'lighttealblue-5', 'lighttealblue-6',
-    'lighttealblue-7', 'lighttealblue-8', 'lighttealblue-9')
-    """
-    _schema = {'$ref': '#/definitions/SequentialMultiHue'}
-
-    def __init__(self, *args):
-        super(SequentialMultiHue, self).__init__(*args)
-
-
-class SequentialSingleHue(ColorScheme):
-    """SequentialSingleHue schema wrapper
-
-    enum('blues', 'tealblues', 'teals', 'greens', 'browns', 'greys', 'purples', 'warmgreys',
-    'reds', 'oranges')
-    """
-    _schema = {'$ref': '#/definitions/SequentialSingleHue'}
-
-    def __init__(self, *args):
-        super(SequentialSingleHue, self).__init__(*args)
-
-
-class ShapeDef(VegaLiteSchema):
-    """ShapeDef schema wrapper
-
-    anyOf(:class:`FieldOrDatumDefWithConditionMarkPropFieldDefTypeForShapestringnull`,
-    :class:`FieldOrDatumDefWithConditionDatumDefstringnull`,
-    :class:`ValueDefWithConditionMarkPropFieldOrDatumDefTypeForShapestringnull`)
-    """
-    _schema = {'$ref': '#/definitions/ShapeDef'}
-
-    def __init__(self, *args, **kwds):
-        super(ShapeDef, self).__init__(*args, **kwds)
-
-
-class FieldOrDatumDefWithConditionDatumDefstringnull(MarkPropDefstringnullTypeForShape, ShapeDef):
-    """FieldOrDatumDefWithConditionDatumDefstringnull schema wrapper
-
-    Mapping(required=[])
-
-    Parameters
-    ----------
-
-    bandPosition : float
-        Relative position on a band of a stacked, binned, time unit, or band scale. For
-        example, the marks will be positioned at the beginning of the band if set to ``0``,
-        and at the middle of the band if set to ``0.5``.
-    condition : anyOf(:class:`ConditionalValueDefstringnullExprRef`, List(:class:`ConditionalValueDefstringnullExprRef`))
-        One or more value definition(s) with `a parameter or a test predicate
-        <https://vega.github.io/vega-lite/docs/condition.html>`__.
-
-        **Note:** A field definition's ``condition`` property can only contain `conditional
-        value definitions <https://vega.github.io/vega-lite/docs/condition.html#value>`__
-        since Vega-Lite only allows at most one encoded field per encoding channel.
-    datum : anyOf(:class:`PrimitiveValue`, :class:`DateTime`, :class:`ExprRef`, :class:`RepeatRef`)
-        A constant value in data domain.
-    title : anyOf(:class:`Text`, None)
-        A title for the field. If ``null``, the title will be removed.
-
-        **Default value:**  derived from the field's name and transformation function (
-        ``aggregate``, ``bin`` and ``timeUnit`` ). If the field has an aggregate function,
-        the function is displayed as part of the title (e.g., ``"Sum of Profit"`` ). If the
-        field is binned or has a time unit applied, the applied function is shown in
-        parentheses (e.g., ``"Profit (binned)"``, ``"Transaction Date (year-month)"`` ).
-        Otherwise, the title is simply the field name.
-
-        **Notes** :
-
-        1) You can customize the default field title format by providing the `fieldTitle
-        <https://vega.github.io/vega-lite/docs/config.html#top-level-config>`__ property in
-        the `config <https://vega.github.io/vega-lite/docs/config.html>`__ or `fieldTitle
-        function via the compile function's options
-        <https://vega.github.io/vega-lite/usage/compile.html#field-title>`__.
-
-        2) If both field definition's ``title`` and axis, header, or legend ``title`` are
-        defined, axis/header/legend title will be used.
-    type : :class:`Type`
-        The type of measurement ( ``"quantitative"``, ``"temporal"``, ``"ordinal"``, or
-        ``"nominal"`` ) for the encoded field or constant value ( ``datum`` ). It can also
-        be a ``"geojson"`` type for encoding `'geoshape'
-        <https://vega.github.io/vega-lite/docs/geoshape.html>`__.
-
-        Vega-Lite automatically infers data types in many cases as discussed below. However,
-        type is required for a field if: (1) the field is not nominal and the field encoding
-        has no specified ``aggregate`` (except ``argmin`` and ``argmax`` ), ``bin``, scale
-        type, custom ``sort`` order, nor ``timeUnit`` or (2) if you wish to use an ordinal
-        scale for a field with ``bin`` or ``timeUnit``.
-
-        **Default value:**
-
-        1) For a data ``field``, ``"nominal"`` is the default data type unless the field
-        encoding has ``aggregate``, ``channel``, ``bin``, scale type, ``sort``, or
-        ``timeUnit`` that satisfies the following criteria:
-
-
-        * ``"quantitative"`` is the default type if (1) the encoded field contains ``bin``
-          or ``aggregate`` except ``"argmin"`` and ``"argmax"``, (2) the encoding channel is
-          ``latitude`` or ``longitude`` channel or (3) if the specified scale type is `a
-          quantitative scale <https://vega.github.io/vega-lite/docs/scale.html#type>`__.
-        * ``"temporal"`` is the default type if (1) the encoded field contains ``timeUnit``
-          or (2) the specified scale type is a time or utc scale
-        * ``"ordinal"`` is the default type if (1) the encoded field contains a `custom sort
-          order
-          <https://vega.github.io/vega-lite/docs/sort.html#specifying-custom-sort-order>`__,
-          (2) the specified scale type is an ordinal/point/band scale, or (3) the encoding
-          channel is ``order``.
-
-        2) For a constant value in data domain ( ``datum`` ):
-
-
-        * ``"quantitative"`` if the datum is a number
-        * ``"nominal"`` if the datum is a string
-        * ``"temporal"`` if the datum is `a date time object
-          <https://vega.github.io/vega-lite/docs/datetime.html>`__
-
-        **Note:**
-
-
-        * Data ``type`` describes the semantics of the data rather than the primitive data
-          types (number, string, etc.). The same primitive data type can have different
-          types of measurement. For example, numeric data can represent quantitative,
-          ordinal, or nominal data.
-        * Data values for a temporal field can be either a date-time string (e.g.,
-          ``"2015-03-07 12:32:17"``, ``"17:01"``, ``"2015-03-16"``. ``"2015"`` ) or a
-          timestamp number (e.g., ``1552199579097`` ).
-        * When using with `bin <https://vega.github.io/vega-lite/docs/bin.html>`__, the
-          ``type`` property can be either ``"quantitative"`` (for using a linear bin scale)
-          or `"ordinal" (for using an ordinal bin scale)
-          <https://vega.github.io/vega-lite/docs/type.html#cast-bin>`__.
-        * When using with `timeUnit
-          <https://vega.github.io/vega-lite/docs/timeunit.html>`__, the ``type`` property
-          can be either ``"temporal"`` (default, for using a temporal scale) or `"ordinal"
-          (for using an ordinal scale)
-          <https://vega.github.io/vega-lite/docs/type.html#cast-bin>`__.
-        * When using with `aggregate
-          <https://vega.github.io/vega-lite/docs/aggregate.html>`__, the ``type`` property
-          refers to the post-aggregation data type. For example, we can calculate count
-          ``distinct`` of a categorical field ``"cat"`` using ``{"aggregate": "distinct",
-          "field": "cat"}``. The ``"type"`` of the aggregate output is ``"quantitative"``.
-        * Secondary channels (e.g., ``x2``, ``y2``, ``xError``, ``yError`` ) do not have
-          ``type`` as they must have exactly the same type as their primary channels (e.g.,
-          ``x``, ``y`` ).
-
-        **See also:** `type <https://vega.github.io/vega-lite/docs/type.html>`__
-        documentation.
-    """
-    _schema = {'$ref': '#/definitions/FieldOrDatumDefWithCondition<DatumDef,(string|null)>'}
-
-    def __init__(self, bandPosition=Undefined, condition=Undefined, datum=Undefined, title=Undefined,
-                 type=Undefined, **kwds):
-        super(FieldOrDatumDefWithConditionDatumDefstringnull, self).__init__(bandPosition=bandPosition,
-                                                                             condition=condition,
-                                                                             datum=datum, title=title,
-                                                                             type=type, **kwds)
-
-
-class FieldOrDatumDefWithConditionMarkPropFieldDefTypeForShapestringnull(MarkPropDefstringnullTypeForShape, ShapeDef):
-    """FieldOrDatumDefWithConditionMarkPropFieldDefTypeForShapestringnull schema wrapper
-
-    Mapping(required=[])
-
-    Parameters
-    ----------
-
-    aggregate : :class:`Aggregate`
-        Aggregation function for the field (e.g., ``"mean"``, ``"sum"``, ``"median"``,
-        ``"min"``, ``"max"``, ``"count"`` ).
-
-        **Default value:** ``undefined`` (None)
-
-        **See also:** `aggregate <https://vega.github.io/vega-lite/docs/aggregate.html>`__
-        documentation.
-    bandPosition : float
-        Relative position on a band of a stacked, binned, time unit, or band scale. For
-        example, the marks will be positioned at the beginning of the band if set to ``0``,
-        and at the middle of the band if set to ``0.5``.
-    bin : anyOf(boolean, :class:`BinParams`, None)
-        A flag for binning a ``quantitative`` field, `an object defining binning parameters
-        <https://vega.github.io/vega-lite/docs/bin.html#bin-parameters>`__, or indicating
-        that the data for ``x`` or ``y`` channel are binned before they are imported into
-        Vega-Lite ( ``"binned"`` ).
-
-
-        If ``true``, default `binning parameters
-        <https://vega.github.io/vega-lite/docs/bin.html#bin-parameters>`__ will be applied.
-
-        If ``"binned"``, this indicates that the data for the ``x`` (or ``y`` ) channel are
-        already binned. You can map the bin-start field to ``x`` (or ``y`` ) and the bin-end
-        field to ``x2`` (or ``y2`` ). The scale and axis will be formatted similar to
-        binning in Vega-Lite.  To adjust the axis ticks based on the bin step, you can also
-        set the axis's `tickMinStep
-        <https://vega.github.io/vega-lite/docs/axis.html#ticks>`__ property.
-
-        **Default value:** ``false``
-
-        **See also:** `bin <https://vega.github.io/vega-lite/docs/bin.html>`__
-        documentation.
-    condition : anyOf(:class:`ConditionalValueDefstringnullExprRef`, List(:class:`ConditionalValueDefstringnullExprRef`))
-        One or more value definition(s) with `a parameter or a test predicate
-        <https://vega.github.io/vega-lite/docs/condition.html>`__.
-
-        **Note:** A field definition's ``condition`` property can only contain `conditional
-        value definitions <https://vega.github.io/vega-lite/docs/condition.html#value>`__
-        since Vega-Lite only allows at most one encoded field per encoding channel.
-    field : :class:`Field`
-        **Required.** A string defining the name of the field from which to pull a data
-        value or an object defining iterated values from the `repeat
-        <https://vega.github.io/vega-lite/docs/repeat.html>`__ operator.
-
-        **See also:** `field <https://vega.github.io/vega-lite/docs/field.html>`__
-        documentation.
-
-        **Notes:** 1)  Dots ( ``.`` ) and brackets ( ``[`` and ``]`` ) can be used to access
-        nested objects (e.g., ``"field": "foo.bar"`` and ``"field": "foo['bar']"`` ). If
-        field names contain dots or brackets but are not nested, you can use ``\\`` to
-        escape dots and brackets (e.g., ``"a\\.b"`` and ``"a\\[0\\]"`` ). See more details
-        about escaping in the `field documentation
-        <https://vega.github.io/vega-lite/docs/field.html>`__. 2) ``field`` is not required
-        if ``aggregate`` is ``count``.
-    legend : anyOf(:class:`Legend`, None)
-        An object defining properties of the legend. If ``null``, the legend for the
-        encoding channel will be removed.
-
-        **Default value:** If undefined, default `legend properties
-        <https://vega.github.io/vega-lite/docs/legend.html>`__ are applied.
-
-        **See also:** `legend <https://vega.github.io/vega-lite/docs/legend.html>`__
-        documentation.
-    scale : anyOf(:class:`Scale`, None)
-        An object defining properties of the channel's scale, which is the function that
-        transforms values in the data domain (numbers, dates, strings, etc) to visual values
-        (pixels, colors, sizes) of the encoding channels.
-
-        If ``null``, the scale will be `disabled and the data value will be directly encoded
-        <https://vega.github.io/vega-lite/docs/scale.html#disable>`__.
-
-        **Default value:** If undefined, default `scale properties
-        <https://vega.github.io/vega-lite/docs/scale.html>`__ are applied.
-
-        **See also:** `scale <https://vega.github.io/vega-lite/docs/scale.html>`__
-        documentation.
-    sort : :class:`Sort`
-        Sort order for the encoded field.
-
-        For continuous fields (quantitative or temporal), ``sort`` can be either
-        ``"ascending"`` or ``"descending"``.
-
-        For discrete fields, ``sort`` can be one of the following:
-
-
-        * ``"ascending"`` or ``"descending"`` -- for sorting by the values' natural order in
-          JavaScript.
-        * `A string indicating an encoding channel name to sort by
-          <https://vega.github.io/vega-lite/docs/sort.html#sort-by-encoding>`__ (e.g.,
-          ``"x"`` or ``"y"`` ) with an optional minus prefix for descending sort (e.g.,
-          ``"-x"`` to sort by x-field, descending). This channel string is short-form of `a
-          sort-by-encoding definition
-          <https://vega.github.io/vega-lite/docs/sort.html#sort-by-encoding>`__. For
-          example, ``"sort": "-x"`` is equivalent to ``"sort": {"encoding": "x", "order":
-          "descending"}``.
-        * `A sort field definition
-          <https://vega.github.io/vega-lite/docs/sort.html#sort-field>`__ for sorting by
-          another field.
-        * `An array specifying the field values in preferred order
-          <https://vega.github.io/vega-lite/docs/sort.html#sort-array>`__. In this case, the
-          sort order will obey the values in the array, followed by any unspecified values
-          in their original order. For discrete time field, values in the sort array can be
-          `date-time definition objects
-          <https://vega.github.io/vega-lite/docs/datetime.html>`__. In addition, for time
-          units ``"month"`` and ``"day"``, the values can be the month or day names (case
-          insensitive) or their 3-letter initials (e.g., ``"Mon"``, ``"Tue"`` ).
-        * ``null`` indicating no sort.
-
-        **Default value:** ``"ascending"``
-
-        **Note:** ``null`` and sorting by another channel is not supported for ``row`` and
-        ``column``.
-
-        **See also:** `sort <https://vega.github.io/vega-lite/docs/sort.html>`__
-        documentation.
-    timeUnit : anyOf(:class:`TimeUnit`, :class:`BinnedTimeUnit`, :class:`TimeUnitParams`)
-        Time unit (e.g., ``year``, ``yearmonth``, ``month``, ``hours`` ) for a temporal
-        field. or `a temporal field that gets casted as ordinal
-        <https://vega.github.io/vega-lite/docs/type.html#cast>`__.
-
-        **Default value:** ``undefined`` (None)
-
-        **See also:** `timeUnit <https://vega.github.io/vega-lite/docs/timeunit.html>`__
-        documentation.
-    title : anyOf(:class:`Text`, None)
-        A title for the field. If ``null``, the title will be removed.
-
-        **Default value:**  derived from the field's name and transformation function (
-        ``aggregate``, ``bin`` and ``timeUnit`` ). If the field has an aggregate function,
-        the function is displayed as part of the title (e.g., ``"Sum of Profit"`` ). If the
-        field is binned or has a time unit applied, the applied function is shown in
-        parentheses (e.g., ``"Profit (binned)"``, ``"Transaction Date (year-month)"`` ).
-        Otherwise, the title is simply the field name.
-
-        **Notes** :
-
-        1) You can customize the default field title format by providing the `fieldTitle
-        <https://vega.github.io/vega-lite/docs/config.html#top-level-config>`__ property in
-        the `config <https://vega.github.io/vega-lite/docs/config.html>`__ or `fieldTitle
-        function via the compile function's options
-        <https://vega.github.io/vega-lite/usage/compile.html#field-title>`__.
-
-        2) If both field definition's ``title`` and axis, header, or legend ``title`` are
-        defined, axis/header/legend title will be used.
-    type : :class:`TypeForShape`
-        The type of measurement ( ``"quantitative"``, ``"temporal"``, ``"ordinal"``, or
-        ``"nominal"`` ) for the encoded field or constant value ( ``datum`` ). It can also
-        be a ``"geojson"`` type for encoding `'geoshape'
-        <https://vega.github.io/vega-lite/docs/geoshape.html>`__.
-
-        Vega-Lite automatically infers data types in many cases as discussed below. However,
-        type is required for a field if: (1) the field is not nominal and the field encoding
-        has no specified ``aggregate`` (except ``argmin`` and ``argmax`` ), ``bin``, scale
-        type, custom ``sort`` order, nor ``timeUnit`` or (2) if you wish to use an ordinal
-        scale for a field with ``bin`` or ``timeUnit``.
-
-        **Default value:**
-
-        1) For a data ``field``, ``"nominal"`` is the default data type unless the field
-        encoding has ``aggregate``, ``channel``, ``bin``, scale type, ``sort``, or
-        ``timeUnit`` that satisfies the following criteria:
-
-
-        * ``"quantitative"`` is the default type if (1) the encoded field contains ``bin``
-          or ``aggregate`` except ``"argmin"`` and ``"argmax"``, (2) the encoding channel is
-          ``latitude`` or ``longitude`` channel or (3) if the specified scale type is `a
-          quantitative scale <https://vega.github.io/vega-lite/docs/scale.html#type>`__.
-        * ``"temporal"`` is the default type if (1) the encoded field contains ``timeUnit``
-          or (2) the specified scale type is a time or utc scale
-        * ``"ordinal"`` is the default type if (1) the encoded field contains a `custom sort
-          order
-          <https://vega.github.io/vega-lite/docs/sort.html#specifying-custom-sort-order>`__,
-          (2) the specified scale type is an ordinal/point/band scale, or (3) the encoding
-          channel is ``order``.
-
-        2) For a constant value in data domain ( ``datum`` ):
-
-
-        * ``"quantitative"`` if the datum is a number
-        * ``"nominal"`` if the datum is a string
-        * ``"temporal"`` if the datum is `a date time object
-          <https://vega.github.io/vega-lite/docs/datetime.html>`__
-
-        **Note:**
-
-
-        * Data ``type`` describes the semantics of the data rather than the primitive data
-          types (number, string, etc.). The same primitive data type can have different
-          types of measurement. For example, numeric data can represent quantitative,
-          ordinal, or nominal data.
-        * Data values for a temporal field can be either a date-time string (e.g.,
-          ``"2015-03-07 12:32:17"``, ``"17:01"``, ``"2015-03-16"``. ``"2015"`` ) or a
-          timestamp number (e.g., ``1552199579097`` ).
-        * When using with `bin <https://vega.github.io/vega-lite/docs/bin.html>`__, the
-          ``type`` property can be either ``"quantitative"`` (for using a linear bin scale)
-          or `"ordinal" (for using an ordinal bin scale)
-          <https://vega.github.io/vega-lite/docs/type.html#cast-bin>`__.
-        * When using with `timeUnit
-          <https://vega.github.io/vega-lite/docs/timeunit.html>`__, the ``type`` property
-          can be either ``"temporal"`` (default, for using a temporal scale) or `"ordinal"
-          (for using an ordinal scale)
-          <https://vega.github.io/vega-lite/docs/type.html#cast-bin>`__.
-        * When using with `aggregate
-          <https://vega.github.io/vega-lite/docs/aggregate.html>`__, the ``type`` property
-          refers to the post-aggregation data type. For example, we can calculate count
-          ``distinct`` of a categorical field ``"cat"`` using ``{"aggregate": "distinct",
-          "field": "cat"}``. The ``"type"`` of the aggregate output is ``"quantitative"``.
-        * Secondary channels (e.g., ``x2``, ``y2``, ``xError``, ``yError`` ) do not have
-          ``type`` as they must have exactly the same type as their primary channels (e.g.,
-          ``x``, ``y`` ).
-
-        **See also:** `type <https://vega.github.io/vega-lite/docs/type.html>`__
-        documentation.
-    """
-    _schema = {'$ref': '#/definitions/FieldOrDatumDefWithCondition<MarkPropFieldDef<TypeForShape>,(string|null)>'}
-
-    def __init__(self, aggregate=Undefined, bandPosition=Undefined, bin=Undefined, condition=Undefined,
-                 field=Undefined, legend=Undefined, scale=Undefined, sort=Undefined, timeUnit=Undefined,
-                 title=Undefined, type=Undefined, **kwds):
-        super(FieldOrDatumDefWithConditionMarkPropFieldDefTypeForShapestringnull, self).__init__(aggregate=aggregate,
-                                                                                                 bandPosition=bandPosition,
-                                                                                                 bin=bin,
-                                                                                                 condition=condition,
-                                                                                                 field=field,
-                                                                                                 legend=legend,
-                                                                                                 scale=scale,
-                                                                                                 sort=sort,
-                                                                                                 timeUnit=timeUnit,
-                                                                                                 title=title,
-                                                                                                 type=type,
-                                                                                                 **kwds)
-
-
-class SharedEncoding(VegaLiteSchema):
-    """SharedEncoding schema wrapper
-
-    Mapping(required=[])
-
-    Parameters
-    ----------
-
-    angle : Mapping(required=[])
-
-    color : Mapping(required=[])
-
-    description : Mapping(required=[])
-
-    detail : anyOf(:class:`FieldDefWithoutScale`, List(:class:`FieldDefWithoutScale`))
-        Additional levels of detail for grouping data in aggregate views and in line, trail,
-        and area marks without mapping data to a specific visual channel.
-    fill : Mapping(required=[])
-
-    fillOpacity : Mapping(required=[])
-
-    href : Mapping(required=[])
-
-    key : Mapping(required=[])
-
-    latitude : Mapping(required=[])
-
-    latitude2 : Mapping(required=[])
-
-    longitude : Mapping(required=[])
-
-    longitude2 : Mapping(required=[])
-
-    opacity : Mapping(required=[])
-
-    order : anyOf(:class:`OrderFieldDef`, List(:class:`OrderFieldDef`), :class:`OrderValueDef`, :class:`OrderOnlyDef`)
-        Order of the marks.
-
-
-        * For stacked marks, this ``order`` channel encodes `stack order
-          <https://vega.github.io/vega-lite/docs/stack.html#order>`__.
-        * For line and trail marks, this ``order`` channel encodes order of data points in
-          the lines. This can be useful for creating `a connected scatterplot
-          <https://vega.github.io/vega-lite/examples/connected_scatterplot.html>`__. Setting
-          ``order`` to ``{"value": null}`` makes the line marks use the original order in
-          the data sources.
-        * Otherwise, this ``order`` channel encodes layer order of the marks.
-
-        **Note** : In aggregate plots, ``order`` field should be ``aggregate`` d to avoid
-        creating additional aggregation grouping.
-    radius : Mapping(required=[])
-
-    radius2 : Mapping(required=[])
-
-    shape : Mapping(required=[])
-
-    size : Mapping(required=[])
-
-    stroke : Mapping(required=[])
-
-    strokeDash : Mapping(required=[])
-
-    strokeOpacity : Mapping(required=[])
-
-    strokeWidth : Mapping(required=[])
-
-    text : Mapping(required=[])
-
-    theta : Mapping(required=[])
-
-    theta2 : Mapping(required=[])
-
-    tooltip : anyOf(:class:`StringFieldDefWithCondition`, :class:`StringValueDefWithCondition`, List(:class:`StringFieldDef`), None)
-        The tooltip text to show upon mouse hover. Specifying ``tooltip`` encoding overrides
-        `the tooltip property in the mark definition
-        <https://vega.github.io/vega-lite/docs/mark.html#mark-def>`__.
-
-        See the `tooltip <https://vega.github.io/vega-lite/docs/tooltip.html>`__
-        documentation for a detailed discussion about tooltip in Vega-Lite.
-    url : Mapping(required=[])
-
-    x : Mapping(required=[])
-
-    x2 : Mapping(required=[])
-
-    xError : Mapping(required=[])
-
-    xError2 : Mapping(required=[])
-
-    xOffset : Mapping(required=[])
-
-    y : Mapping(required=[])
-
-    y2 : Mapping(required=[])
-
-    yError : Mapping(required=[])
-
-    yError2 : Mapping(required=[])
-
-    yOffset : Mapping(required=[])
-
-    """
-    _schema = {'$ref': '#/definitions/SharedEncoding'}
-
-    def __init__(self, angle=Undefined, color=Undefined, description=Undefined, detail=Undefined,
-                 fill=Undefined, fillOpacity=Undefined, href=Undefined, key=Undefined,
-                 latitude=Undefined, latitude2=Undefined, longitude=Undefined, longitude2=Undefined,
-                 opacity=Undefined, order=Undefined, radius=Undefined, radius2=Undefined,
-                 shape=Undefined, size=Undefined, stroke=Undefined, strokeDash=Undefined,
-                 strokeOpacity=Undefined, strokeWidth=Undefined, text=Undefined, theta=Undefined,
-                 theta2=Undefined, tooltip=Undefined, url=Undefined, x=Undefined, x2=Undefined,
-                 xError=Undefined, xError2=Undefined, xOffset=Undefined, y=Undefined, y2=Undefined,
-                 yError=Undefined, yError2=Undefined, yOffset=Undefined, **kwds):
-        super(SharedEncoding, self).__init__(angle=angle, color=color, description=description,
-                                             detail=detail, fill=fill, fillOpacity=fillOpacity,
-                                             href=href, key=key, latitude=latitude, latitude2=latitude2,
-                                             longitude=longitude, longitude2=longitude2,
-                                             opacity=opacity, order=order, radius=radius,
-                                             radius2=radius2, shape=shape, size=size, stroke=stroke,
-                                             strokeDash=strokeDash, strokeOpacity=strokeOpacity,
-                                             strokeWidth=strokeWidth, text=text, theta=theta,
-                                             theta2=theta2, tooltip=tooltip, url=url, x=x, x2=x2,
-                                             xError=xError, xError2=xError2, xOffset=xOffset, y=y,
-                                             y2=y2, yError=yError, yError2=yError2, yOffset=yOffset,
-                                             **kwds)
-
-
-class SingleDefUnitChannel(VegaLiteSchema):
-    """SingleDefUnitChannel schema wrapper
-
-    enum('x', 'y', 'xOffset', 'yOffset', 'x2', 'y2', 'longitude', 'latitude', 'longitude2',
-    'latitude2', 'theta', 'theta2', 'radius', 'radius2', 'color', 'fill', 'stroke', 'opacity',
-    'fillOpacity', 'strokeOpacity', 'strokeWidth', 'strokeDash', 'size', 'angle', 'shape',
-    'key', 'text', 'href', 'url', 'description')
-    """
-    _schema = {'$ref': '#/definitions/SingleDefUnitChannel'}
-
-    def __init__(self, *args):
-        super(SingleDefUnitChannel, self).__init__(*args)
-
-
-class Sort(VegaLiteSchema):
-    """Sort schema wrapper
-
-    anyOf(:class:`SortArray`, :class:`AllSortString`, :class:`EncodingSortField`,
-    :class:`SortByEncoding`, None)
-    """
-    _schema = {'$ref': '#/definitions/Sort'}
-
-    def __init__(self, *args, **kwds):
-        super(Sort, self).__init__(*args, **kwds)
-
-
-class AllSortString(Sort):
-    """AllSortString schema wrapper
-
-    anyOf(:class:`SortOrder`, :class:`SortByChannel`, :class:`SortByChannelDesc`)
-    """
-    _schema = {'$ref': '#/definitions/AllSortString'}
-
-    def __init__(self, *args, **kwds):
-        super(AllSortString, self).__init__(*args, **kwds)
-
-
-class EncodingSortField(Sort):
-    """EncodingSortField schema wrapper
-
-    Mapping(required=[])
-    A sort definition for sorting a discrete scale in an encoding field definition.
-
-    Parameters
-    ----------
-
-    field : :class:`Field`
-        The data `field <https://vega.github.io/vega-lite/docs/field.html>`__ to sort by.
-
-        **Default value:** If unspecified, defaults to the field specified in the outer data
-        reference.
-    op : :class:`NonArgAggregateOp`
-        An `aggregate operation
-        <https://vega.github.io/vega-lite/docs/aggregate.html#ops>`__ to perform on the
-        field prior to sorting (e.g., ``"count"``, ``"mean"`` and ``"median"`` ). An
-        aggregation is required when there are multiple values of the sort field for each
-        encoded data field. The input data objects will be aggregated, grouped by the
-        encoded data field.
-
-        For a full list of operations, please see the documentation for `aggregate
-        <https://vega.github.io/vega-lite/docs/aggregate.html#ops>`__.
-
-        **Default value:** ``"sum"`` for stacked plots. Otherwise, ``"min"``.
-    order : anyOf(:class:`SortOrder`, None)
-        The sort order. One of ``"ascending"`` (default), ``"descending"``, or ``null`` (no
-        not sort).
-    """
-    _schema = {'$ref': '#/definitions/EncodingSortField'}
-
-    def __init__(self, field=Undefined, op=Undefined, order=Undefined, **kwds):
-        super(EncodingSortField, self).__init__(field=field, op=op, order=order, **kwds)
-
-
-class SortArray(Sort):
-    """SortArray schema wrapper
-
-    anyOf(List(float), List(string), List(boolean), List(:class:`DateTime`))
-    """
-    _schema = {'$ref': '#/definitions/SortArray'}
-
-    def __init__(self, *args, **kwds):
-        super(SortArray, self).__init__(*args, **kwds)
-
-
-class SortByChannel(AllSortString):
-    """SortByChannel schema wrapper
-
-    enum('x', 'y', 'color', 'fill', 'stroke', 'strokeWidth', 'size', 'shape', 'fillOpacity',
-    'strokeOpacity', 'opacity', 'text')
-    """
-    _schema = {'$ref': '#/definitions/SortByChannel'}
-
-    def __init__(self, *args):
-        super(SortByChannel, self).__init__(*args)
-
-
-class SortByChannelDesc(AllSortString):
-    """SortByChannelDesc schema wrapper
-
-    enum('-x', '-y', '-color', '-fill', '-stroke', '-strokeWidth', '-size', '-shape',
-    '-fillOpacity', '-strokeOpacity', '-opacity', '-text')
-    """
-    _schema = {'$ref': '#/definitions/SortByChannelDesc'}
-
-    def __init__(self, *args):
-        super(SortByChannelDesc, self).__init__(*args)
-
-
-class SortByEncoding(Sort):
-    """SortByEncoding schema wrapper
-
-    Mapping(required=[encoding])
-
-    Parameters
-    ----------
-
-    encoding : :class:`SortByChannel`
-        The `encoding channel
-        <https://vega.github.io/vega-lite/docs/encoding.html#channels>`__ to sort by (e.g.,
-        ``"x"``, ``"y"`` )
-    order : anyOf(:class:`SortOrder`, None)
-        The sort order. One of ``"ascending"`` (default), ``"descending"``, or ``null`` (no
-        not sort).
-    """
-    _schema = {'$ref': '#/definitions/SortByEncoding'}
-
-    def __init__(self, encoding=Undefined, order=Undefined, **kwds):
-        super(SortByEncoding, self).__init__(encoding=encoding, order=order, **kwds)
-
-
-class SortField(VegaLiteSchema):
-    """SortField schema wrapper
-
-    Mapping(required=[field])
-    A sort definition for transform
-
-    Parameters
-    ----------
-
-    field : :class:`FieldName`
-        The name of the field to sort.
-    order : anyOf(:class:`SortOrder`, None)
-        Whether to sort the field in ascending or descending order. One of ``"ascending"``
-        (default), ``"descending"``, or ``null`` (no not sort).
-    """
-    _schema = {'$ref': '#/definitions/SortField'}
-
-    def __init__(self, field=Undefined, order=Undefined, **kwds):
-        super(SortField, self).__init__(field=field, order=order, **kwds)
-
-
-class SortOrder(AllSortString):
-    """SortOrder schema wrapper
-
-    enum('ascending', 'descending')
-    """
-    _schema = {'$ref': '#/definitions/SortOrder'}
-
-    def __init__(self, *args):
-        super(SortOrder, self).__init__(*args)
-
-
-class Spec(VegaLiteSchema):
-    """Spec schema wrapper
-
-    anyOf(:class:`FacetedUnitSpec`, :class:`LayerSpec`, :class:`RepeatSpec`, :class:`FacetSpec`,
-    :class:`ConcatSpecGenericSpec`, :class:`VConcatSpecGenericSpec`,
-    :class:`HConcatSpecGenericSpec`)
-    Any specification in Vega-Lite.
-    """
-    _schema = {'$ref': '#/definitions/Spec'}
-
-    def __init__(self, *args, **kwds):
-        super(Spec, self).__init__(*args, **kwds)
-
-
-class ConcatSpecGenericSpec(Spec, NonNormalizedSpec):
-    """ConcatSpecGenericSpec schema wrapper
-
-    Mapping(required=[concat])
-    Base interface for a generalized concatenation specification.
-
-    Parameters
-    ----------
-
-    concat : List(:class:`Spec`)
-        A list of views to be concatenated.
-    align : anyOf(:class:`LayoutAlign`, :class:`RowColLayoutAlign`)
-        The alignment to apply to grid rows and columns. The supported string values are
-        ``"all"``, ``"each"``, and ``"none"``.
-
-
-        * For ``"none"``, a flow layout will be used, in which adjacent subviews are simply
-          placed one after the other.
-        * For ``"each"``, subviews will be aligned into a clean grid structure, but each row
-          or column may be of variable size.
-        * For ``"all"``, subviews will be aligned and each row or column will be sized
-          identically based on the maximum observed size. String values for this property
-          will be applied to both grid rows and columns.
-
-        Alternatively, an object value of the form ``{"row": string, "column": string}`` can
-        be used to supply different alignments for rows and columns.
-
-        **Default value:** ``"all"``.
-    bounds : enum('full', 'flush')
-        The bounds calculation method to use for determining the extent of a sub-plot. One
-        of ``full`` (the default) or ``flush``.
-
-
-        * If set to ``full``, the entire calculated bounds (including axes, title, and
-          legend) will be used.
-        * If set to ``flush``, only the specified width and height values for the sub-view
-          will be used. The ``flush`` setting can be useful when attempting to place
-          sub-plots without axes or legends into a uniform grid structure.
-
-        **Default value:** ``"full"``
-    center : anyOf(boolean, :class:`RowColboolean`)
-        Boolean flag indicating if subviews should be centered relative to their respective
-        rows or columns.
-
-        An object value of the form ``{"row": boolean, "column": boolean}`` can be used to
-        supply different centering values for rows and columns.
-
-        **Default value:** ``false``
-    columns : float
-        The number of columns to include in the view composition layout.
-
-        **Default value** : ``undefined`` -- An infinite number of columns (a single row)
-        will be assumed. This is equivalent to ``hconcat`` (for ``concat`` ) and to using
-        the ``column`` channel (for ``facet`` and ``repeat`` ).
-
-        **Note** :
-
-        1) This property is only for:
-
-
-        * the general (wrappable) ``concat`` operator (not ``hconcat`` / ``vconcat`` )
-        * the ``facet`` and ``repeat`` operator with one field/repetition definition
-          (without row/column nesting)
-
-        2) Setting the ``columns`` to ``1`` is equivalent to ``vconcat`` (for ``concat`` )
-        and to using the ``row`` channel (for ``facet`` and ``repeat`` ).
-    data : anyOf(:class:`Data`, None)
-        An object describing the data source. Set to ``null`` to ignore the parent's data
-        source. If no data is set, it is derived from the parent.
-    description : string
-        Description of this mark for commenting purpose.
-    name : string
-        Name of the visualization for later reference.
-    resolve : :class:`Resolve`
-        Scale, axis, and legend resolutions for view composition specifications.
-    spacing : anyOf(float, :class:`RowColnumber`)
-        The spacing in pixels between sub-views of the composition operator. An object of
-        the form ``{"row": number, "column": number}`` can be used to set different spacing
-        values for rows and columns.
-
-        **Default value** : Depends on ``"spacing"`` property of `the view composition
-        configuration <https://vega.github.io/vega-lite/docs/config.html#view-config>`__ (
-        ``20`` by default)
-    title : anyOf(:class:`Text`, :class:`TitleParams`)
-        Title for the plot.
-    transform : List(:class:`Transform`)
-        An array of data transformations such as filter and new field calculation.
-    """
-    _schema = {'$ref': '#/definitions/ConcatSpec<GenericSpec>'}
-
-    def __init__(self, concat=Undefined, align=Undefined, bounds=Undefined, center=Undefined,
-                 columns=Undefined, data=Undefined, description=Undefined, name=Undefined,
-                 resolve=Undefined, spacing=Undefined, title=Undefined, transform=Undefined, **kwds):
-        super(ConcatSpecGenericSpec, self).__init__(concat=concat, align=align, bounds=bounds,
-                                                    center=center, columns=columns, data=data,
-                                                    description=description, name=name, resolve=resolve,
-                                                    spacing=spacing, title=title, transform=transform,
-                                                    **kwds)
-
-
-class FacetSpec(Spec, NonNormalizedSpec):
-    """FacetSpec schema wrapper
-
-    Mapping(required=[facet, spec])
-    Base interface for a facet specification.
-
-    Parameters
-    ----------
-
-    facet : anyOf(:class:`FacetFieldDef`, :class:`FacetMapping`)
-        Definition for how to facet the data. One of: 1) `a field definition for faceting
-        the plot by one field
-        <https://vega.github.io/vega-lite/docs/facet.html#field-def>`__ 2) `An object that
-        maps row and column channels to their field definitions
-        <https://vega.github.io/vega-lite/docs/facet.html#mapping>`__
-    spec : anyOf(:class:`LayerSpec`, :class:`FacetedUnitSpec`)
-        A specification of the view that gets faceted.
-    align : anyOf(:class:`LayoutAlign`, :class:`RowColLayoutAlign`)
-        The alignment to apply to grid rows and columns. The supported string values are
-        ``"all"``, ``"each"``, and ``"none"``.
-
-
-        * For ``"none"``, a flow layout will be used, in which adjacent subviews are simply
-          placed one after the other.
-        * For ``"each"``, subviews will be aligned into a clean grid structure, but each row
-          or column may be of variable size.
-        * For ``"all"``, subviews will be aligned and each row or column will be sized
-          identically based on the maximum observed size. String values for this property
-          will be applied to both grid rows and columns.
-
-        Alternatively, an object value of the form ``{"row": string, "column": string}`` can
-        be used to supply different alignments for rows and columns.
-
-        **Default value:** ``"all"``.
-    bounds : enum('full', 'flush')
-        The bounds calculation method to use for determining the extent of a sub-plot. One
-        of ``full`` (the default) or ``flush``.
-
-
-        * If set to ``full``, the entire calculated bounds (including axes, title, and
-          legend) will be used.
-        * If set to ``flush``, only the specified width and height values for the sub-view
-          will be used. The ``flush`` setting can be useful when attempting to place
-          sub-plots without axes or legends into a uniform grid structure.
-
-        **Default value:** ``"full"``
-    center : anyOf(boolean, :class:`RowColboolean`)
-        Boolean flag indicating if subviews should be centered relative to their respective
-        rows or columns.
-
-        An object value of the form ``{"row": boolean, "column": boolean}`` can be used to
-        supply different centering values for rows and columns.
-
-        **Default value:** ``false``
-    columns : float
-        The number of columns to include in the view composition layout.
-
-        **Default value** : ``undefined`` -- An infinite number of columns (a single row)
-        will be assumed. This is equivalent to ``hconcat`` (for ``concat`` ) and to using
-        the ``column`` channel (for ``facet`` and ``repeat`` ).
-
-        **Note** :
-
-        1) This property is only for:
-
-
-        * the general (wrappable) ``concat`` operator (not ``hconcat`` / ``vconcat`` )
-        * the ``facet`` and ``repeat`` operator with one field/repetition definition
-          (without row/column nesting)
-
-        2) Setting the ``columns`` to ``1`` is equivalent to ``vconcat`` (for ``concat`` )
-        and to using the ``row`` channel (for ``facet`` and ``repeat`` ).
-    data : anyOf(:class:`Data`, None)
-        An object describing the data source. Set to ``null`` to ignore the parent's data
-        source. If no data is set, it is derived from the parent.
-    description : string
-        Description of this mark for commenting purpose.
-    name : string
-        Name of the visualization for later reference.
-    resolve : :class:`Resolve`
-        Scale, axis, and legend resolutions for view composition specifications.
-    spacing : anyOf(float, :class:`RowColnumber`)
-        The spacing in pixels between sub-views of the composition operator. An object of
-        the form ``{"row": number, "column": number}`` can be used to set different spacing
-        values for rows and columns.
-
-        **Default value** : Depends on ``"spacing"`` property of `the view composition
-        configuration <https://vega.github.io/vega-lite/docs/config.html#view-config>`__ (
-        ``20`` by default)
-    title : anyOf(:class:`Text`, :class:`TitleParams`)
-        Title for the plot.
-    transform : List(:class:`Transform`)
-        An array of data transformations such as filter and new field calculation.
-    """
-    _schema = {'$ref': '#/definitions/FacetSpec'}
-
-    def __init__(self, facet=Undefined, spec=Undefined, align=Undefined, bounds=Undefined,
-                 center=Undefined, columns=Undefined, data=Undefined, description=Undefined,
-                 name=Undefined, resolve=Undefined, spacing=Undefined, title=Undefined,
-                 transform=Undefined, **kwds):
-        super(FacetSpec, self).__init__(facet=facet, spec=spec, align=align, bounds=bounds,
-                                        center=center, columns=columns, data=data,
-                                        description=description, name=name, resolve=resolve,
-                                        spacing=spacing, title=title, transform=transform, **kwds)
-
-
-class FacetedUnitSpec(Spec, NonNormalizedSpec):
-    """FacetedUnitSpec schema wrapper
-
-    Mapping(required=[mark])
-    Unit spec that can have a composite mark and row or column channels (shorthand for a facet
-    spec).
-
-    Parameters
-    ----------
-
-    mark : :class:`AnyMark`
-        A string describing the mark type (one of ``"bar"``, ``"circle"``, ``"square"``,
-        ``"tick"``, ``"line"``, ``"area"``, ``"point"``, ``"rule"``, ``"geoshape"``, and
-        ``"text"`` ) or a `mark definition object
-        <https://vega.github.io/vega-lite/docs/mark.html#mark-def>`__.
-    align : anyOf(:class:`LayoutAlign`, :class:`RowColLayoutAlign`)
-        The alignment to apply to grid rows and columns. The supported string values are
-        ``"all"``, ``"each"``, and ``"none"``.
-
-
-        * For ``"none"``, a flow layout will be used, in which adjacent subviews are simply
-          placed one after the other.
-        * For ``"each"``, subviews will be aligned into a clean grid structure, but each row
-          or column may be of variable size.
-        * For ``"all"``, subviews will be aligned and each row or column will be sized
-          identically based on the maximum observed size. String values for this property
-          will be applied to both grid rows and columns.
-
-        Alternatively, an object value of the form ``{"row": string, "column": string}`` can
-        be used to supply different alignments for rows and columns.
-
-        **Default value:** ``"all"``.
-    bounds : enum('full', 'flush')
-        The bounds calculation method to use for determining the extent of a sub-plot. One
-        of ``full`` (the default) or ``flush``.
-
-
-        * If set to ``full``, the entire calculated bounds (including axes, title, and
-          legend) will be used.
-        * If set to ``flush``, only the specified width and height values for the sub-view
-          will be used. The ``flush`` setting can be useful when attempting to place
-          sub-plots without axes or legends into a uniform grid structure.
-
-        **Default value:** ``"full"``
-    center : anyOf(boolean, :class:`RowColboolean`)
-        Boolean flag indicating if subviews should be centered relative to their respective
-        rows or columns.
-
-        An object value of the form ``{"row": boolean, "column": boolean}`` can be used to
-        supply different centering values for rows and columns.
-
-        **Default value:** ``false``
-    data : anyOf(:class:`Data`, None)
-        An object describing the data source. Set to ``null`` to ignore the parent's data
-        source. If no data is set, it is derived from the parent.
-    description : string
-        Description of this mark for commenting purpose.
-    encoding : :class:`FacetedEncoding`
-        A key-value mapping between encoding channels and definition of fields.
-    height : anyOf(float, string, :class:`Step`)
-        The height of a visualization.
-
-
-        * For a plot with a continuous y-field, height should be a number.
-        * For a plot with either a discrete y-field or no y-field, height can be either a
-          number indicating a fixed height or an object in the form of ``{step: number}``
-          defining the height per discrete step. (No y-field is equivalent to having one
-          discrete step.)
-        * To enable responsive sizing on height, it should be set to ``"container"``.
-
-        **Default value:** Based on ``config.view.continuousHeight`` for a plot with a
-        continuous y-field and ``config.view.discreteHeight`` otherwise.
-
-        **Note:** For plots with `row and column channels
-        <https://vega.github.io/vega-lite/docs/encoding.html#facet>`__, this represents the
-        height of a single view and the ``"container"`` option cannot be used.
-
-        **See also:** `height <https://vega.github.io/vega-lite/docs/size.html>`__
-        documentation.
-    name : string
-        Name of the visualization for later reference.
-    params : List(:class:`SelectionParameter`)
-        An array of parameters that may either be simple variables, or more complex
-        selections that map user input to data queries.
-    projection : :class:`Projection`
-        An object defining properties of geographic projection, which will be applied to
-        ``shape`` path for ``"geoshape"`` marks and to ``latitude`` and ``"longitude"``
-        channels for other marks.
-    resolve : :class:`Resolve`
-        Scale, axis, and legend resolutions for view composition specifications.
-    spacing : anyOf(float, :class:`RowColnumber`)
-        The spacing in pixels between sub-views of the composition operator. An object of
-        the form ``{"row": number, "column": number}`` can be used to set different spacing
-        values for rows and columns.
-
-        **Default value** : Depends on ``"spacing"`` property of `the view composition
-        configuration <https://vega.github.io/vega-lite/docs/config.html#view-config>`__ (
-        ``20`` by default)
-    title : anyOf(:class:`Text`, :class:`TitleParams`)
-        Title for the plot.
-    transform : List(:class:`Transform`)
-        An array of data transformations such as filter and new field calculation.
-    view : :class:`ViewBackground`
-        An object defining the view background's fill and stroke.
-
-        **Default value:** none (transparent)
-    width : anyOf(float, string, :class:`Step`)
-        The width of a visualization.
-
-
-        * For a plot with a continuous x-field, width should be a number.
-        * For a plot with either a discrete x-field or no x-field, width can be either a
-          number indicating a fixed width or an object in the form of ``{step: number}``
-          defining the width per discrete step. (No x-field is equivalent to having one
-          discrete step.)
-        * To enable responsive sizing on width, it should be set to ``"container"``.
-
-        **Default value:** Based on ``config.view.continuousWidth`` for a plot with a
-        continuous x-field and ``config.view.discreteWidth`` otherwise.
-
-        **Note:** For plots with `row and column channels
-        <https://vega.github.io/vega-lite/docs/encoding.html#facet>`__, this represents the
-        width of a single view and the ``"container"`` option cannot be used.
-
-        **See also:** `width <https://vega.github.io/vega-lite/docs/size.html>`__
-        documentation.
-    """
-    _schema = {'$ref': '#/definitions/FacetedUnitSpec'}
-
-    def __init__(self, mark=Undefined, align=Undefined, bounds=Undefined, center=Undefined,
-                 data=Undefined, description=Undefined, encoding=Undefined, height=Undefined,
-                 name=Undefined, params=Undefined, projection=Undefined, resolve=Undefined,
-                 spacing=Undefined, title=Undefined, transform=Undefined, view=Undefined,
-                 width=Undefined, **kwds):
-        super(FacetedUnitSpec, self).__init__(mark=mark, align=align, bounds=bounds, center=center,
-                                              data=data, description=description, encoding=encoding,
-                                              height=height, name=name, params=params,
-                                              projection=projection, resolve=resolve, spacing=spacing,
-                                              title=title, transform=transform, view=view, width=width,
-                                              **kwds)
-
-
-class HConcatSpecGenericSpec(Spec, NonNormalizedSpec):
-    """HConcatSpecGenericSpec schema wrapper
-
-    Mapping(required=[hconcat])
-    Base interface for a horizontal concatenation specification.
-
-    Parameters
-    ----------
-
-    hconcat : List(:class:`Spec`)
-        A list of views to be concatenated and put into a row.
-    bounds : enum('full', 'flush')
-        The bounds calculation method to use for determining the extent of a sub-plot. One
-        of ``full`` (the default) or ``flush``.
-
-
-        * If set to ``full``, the entire calculated bounds (including axes, title, and
-          legend) will be used.
-        * If set to ``flush``, only the specified width and height values for the sub-view
-          will be used. The ``flush`` setting can be useful when attempting to place
-          sub-plots without axes or legends into a uniform grid structure.
-
-        **Default value:** ``"full"``
-    center : boolean
-        Boolean flag indicating if subviews should be centered relative to their respective
-        rows or columns.
-
-        **Default value:** ``false``
-    data : anyOf(:class:`Data`, None)
-        An object describing the data source. Set to ``null`` to ignore the parent's data
-        source. If no data is set, it is derived from the parent.
-    description : string
-        Description of this mark for commenting purpose.
-    name : string
-        Name of the visualization for later reference.
-    resolve : :class:`Resolve`
-        Scale, axis, and legend resolutions for view composition specifications.
-    spacing : float
-        The spacing in pixels between sub-views of the concat operator.
-
-        **Default value** : ``10``
-    title : anyOf(:class:`Text`, :class:`TitleParams`)
-        Title for the plot.
-    transform : List(:class:`Transform`)
-        An array of data transformations such as filter and new field calculation.
-    """
-    _schema = {'$ref': '#/definitions/HConcatSpec<GenericSpec>'}
-
-    def __init__(self, hconcat=Undefined, bounds=Undefined, center=Undefined, data=Undefined,
-                 description=Undefined, name=Undefined, resolve=Undefined, spacing=Undefined,
-                 title=Undefined, transform=Undefined, **kwds):
-        super(HConcatSpecGenericSpec, self).__init__(hconcat=hconcat, bounds=bounds, center=center,
-                                                     data=data, description=description, name=name,
-                                                     resolve=resolve, spacing=spacing, title=title,
-                                                     transform=transform, **kwds)
-
-
-class LayerSpec(Spec, NonNormalizedSpec):
-    """LayerSpec schema wrapper
-
-    Mapping(required=[layer])
-    A full layered plot specification, which may contains ``encoding`` and ``projection``
-    properties that will be applied to underlying unit (single-view) specifications.
-
-    Parameters
-    ----------
-
-    layer : List(anyOf(:class:`LayerSpec`, :class:`UnitSpec`))
-        Layer or single view specifications to be layered.
-
-        **Note** : Specifications inside ``layer`` cannot use ``row`` and ``column``
-        channels as layering facet specifications is not allowed. Instead, use the `facet
-        operator <https://vega.github.io/vega-lite/docs/facet.html>`__ and place a layer
-        inside a facet.
-    data : anyOf(:class:`Data`, None)
-        An object describing the data source. Set to ``null`` to ignore the parent's data
-        source. If no data is set, it is derived from the parent.
-    description : string
-        Description of this mark for commenting purpose.
-    encoding : :class:`SharedEncoding`
-        A shared key-value mapping between encoding channels and definition of fields in the
-        underlying layers.
-    height : anyOf(float, string, :class:`Step`)
-        The height of a visualization.
-
-
-        * For a plot with a continuous y-field, height should be a number.
-        * For a plot with either a discrete y-field or no y-field, height can be either a
-          number indicating a fixed height or an object in the form of ``{step: number}``
-          defining the height per discrete step. (No y-field is equivalent to having one
-          discrete step.)
-        * To enable responsive sizing on height, it should be set to ``"container"``.
-
-        **Default value:** Based on ``config.view.continuousHeight`` for a plot with a
-        continuous y-field and ``config.view.discreteHeight`` otherwise.
-
-        **Note:** For plots with `row and column channels
-        <https://vega.github.io/vega-lite/docs/encoding.html#facet>`__, this represents the
-        height of a single view and the ``"container"`` option cannot be used.
-
-        **See also:** `height <https://vega.github.io/vega-lite/docs/size.html>`__
-        documentation.
-    name : string
-        Name of the visualization for later reference.
-    projection : :class:`Projection`
-        An object defining properties of the geographic projection shared by underlying
-        layers.
-    resolve : :class:`Resolve`
-        Scale, axis, and legend resolutions for view composition specifications.
-    title : anyOf(:class:`Text`, :class:`TitleParams`)
-        Title for the plot.
-    transform : List(:class:`Transform`)
-        An array of data transformations such as filter and new field calculation.
-    view : :class:`ViewBackground`
-        An object defining the view background's fill and stroke.
-
-        **Default value:** none (transparent)
-    width : anyOf(float, string, :class:`Step`)
-        The width of a visualization.
-
-
-        * For a plot with a continuous x-field, width should be a number.
-        * For a plot with either a discrete x-field or no x-field, width can be either a
-          number indicating a fixed width or an object in the form of ``{step: number}``
-          defining the width per discrete step. (No x-field is equivalent to having one
-          discrete step.)
-        * To enable responsive sizing on width, it should be set to ``"container"``.
-
-        **Default value:** Based on ``config.view.continuousWidth`` for a plot with a
-        continuous x-field and ``config.view.discreteWidth`` otherwise.
-
-        **Note:** For plots with `row and column channels
-        <https://vega.github.io/vega-lite/docs/encoding.html#facet>`__, this represents the
-        width of a single view and the ``"container"`` option cannot be used.
-
-        **See also:** `width <https://vega.github.io/vega-lite/docs/size.html>`__
-        documentation.
-    """
-    _schema = {'$ref': '#/definitions/LayerSpec'}
-
-    def __init__(self, layer=Undefined, data=Undefined, description=Undefined, encoding=Undefined,
-                 height=Undefined, name=Undefined, projection=Undefined, resolve=Undefined,
-                 title=Undefined, transform=Undefined, view=Undefined, width=Undefined, **kwds):
-        super(LayerSpec, self).__init__(layer=layer, data=data, description=description,
-                                        encoding=encoding, height=height, name=name,
-                                        projection=projection, resolve=resolve, title=title,
-                                        transform=transform, view=view, width=width, **kwds)
-
-
-class RepeatSpec(Spec, NonNormalizedSpec):
-    """RepeatSpec schema wrapper
-
-    anyOf(:class:`NonLayerRepeatSpec`, :class:`LayerRepeatSpec`)
-    """
-    _schema = {'$ref': '#/definitions/RepeatSpec'}
-
-    def __init__(self, *args, **kwds):
-        super(RepeatSpec, self).__init__(*args, **kwds)
-
-
-class LayerRepeatSpec(RepeatSpec):
-    """LayerRepeatSpec schema wrapper
-
-    Mapping(required=[repeat, spec])
-
-    Parameters
-    ----------
-
-    repeat : :class:`LayerRepeatMapping`
-        Definition for fields to be repeated. One of: 1) An array of fields to be repeated.
-        If ``"repeat"`` is an array, the field can be referred to as ``{"repeat":
-        "repeat"}``. The repeated views are laid out in a wrapped row. You can set the
-        number of columns to control the wrapping. 2) An object that maps ``"row"`` and/or
-        ``"column"`` to the listed fields to be repeated along the particular orientations.
-        The objects ``{"repeat": "row"}`` and ``{"repeat": "column"}`` can be used to refer
-        to the repeated field respectively.
-    spec : anyOf(:class:`LayerSpec`, :class:`UnitSpecWithFrame`)
-        A specification of the view that gets repeated.
-    align : anyOf(:class:`LayoutAlign`, :class:`RowColLayoutAlign`)
-        The alignment to apply to grid rows and columns. The supported string values are
-        ``"all"``, ``"each"``, and ``"none"``.
-
-
-        * For ``"none"``, a flow layout will be used, in which adjacent subviews are simply
-          placed one after the other.
-        * For ``"each"``, subviews will be aligned into a clean grid structure, but each row
-          or column may be of variable size.
-        * For ``"all"``, subviews will be aligned and each row or column will be sized
-          identically based on the maximum observed size. String values for this property
-          will be applied to both grid rows and columns.
-
-        Alternatively, an object value of the form ``{"row": string, "column": string}`` can
-        be used to supply different alignments for rows and columns.
-
-        **Default value:** ``"all"``.
-    bounds : enum('full', 'flush')
-        The bounds calculation method to use for determining the extent of a sub-plot. One
-        of ``full`` (the default) or ``flush``.
-
-
-        * If set to ``full``, the entire calculated bounds (including axes, title, and
-          legend) will be used.
-        * If set to ``flush``, only the specified width and height values for the sub-view
-          will be used. The ``flush`` setting can be useful when attempting to place
-          sub-plots without axes or legends into a uniform grid structure.
-
-        **Default value:** ``"full"``
-    center : anyOf(boolean, :class:`RowColboolean`)
-        Boolean flag indicating if subviews should be centered relative to their respective
-        rows or columns.
-
-        An object value of the form ``{"row": boolean, "column": boolean}`` can be used to
-        supply different centering values for rows and columns.
-
-        **Default value:** ``false``
-    columns : float
-        The number of columns to include in the view composition layout.
-
-        **Default value** : ``undefined`` -- An infinite number of columns (a single row)
-        will be assumed. This is equivalent to ``hconcat`` (for ``concat`` ) and to using
-        the ``column`` channel (for ``facet`` and ``repeat`` ).
-
-        **Note** :
-
-        1) This property is only for:
-
-
-        * the general (wrappable) ``concat`` operator (not ``hconcat`` / ``vconcat`` )
-        * the ``facet`` and ``repeat`` operator with one field/repetition definition
-          (without row/column nesting)
-
-        2) Setting the ``columns`` to ``1`` is equivalent to ``vconcat`` (for ``concat`` )
-        and to using the ``row`` channel (for ``facet`` and ``repeat`` ).
-    data : anyOf(:class:`Data`, None)
-        An object describing the data source. Set to ``null`` to ignore the parent's data
-        source. If no data is set, it is derived from the parent.
-    description : string
-        Description of this mark for commenting purpose.
-    name : string
-        Name of the visualization for later reference.
-    resolve : :class:`Resolve`
-        Scale, axis, and legend resolutions for view composition specifications.
-    spacing : anyOf(float, :class:`RowColnumber`)
-        The spacing in pixels between sub-views of the composition operator. An object of
-        the form ``{"row": number, "column": number}`` can be used to set different spacing
-        values for rows and columns.
-
-        **Default value** : Depends on ``"spacing"`` property of `the view composition
-        configuration <https://vega.github.io/vega-lite/docs/config.html#view-config>`__ (
-        ``20`` by default)
-    title : anyOf(:class:`Text`, :class:`TitleParams`)
-        Title for the plot.
-    transform : List(:class:`Transform`)
-        An array of data transformations such as filter and new field calculation.
-    """
-    _schema = {'$ref': '#/definitions/LayerRepeatSpec'}
-
-    def __init__(self, repeat=Undefined, spec=Undefined, align=Undefined, bounds=Undefined,
-                 center=Undefined, columns=Undefined, data=Undefined, description=Undefined,
-                 name=Undefined, resolve=Undefined, spacing=Undefined, title=Undefined,
-                 transform=Undefined, **kwds):
-        super(LayerRepeatSpec, self).__init__(repeat=repeat, spec=spec, align=align, bounds=bounds,
-                                              center=center, columns=columns, data=data,
-                                              description=description, name=name, resolve=resolve,
-                                              spacing=spacing, title=title, transform=transform, **kwds)
-
-
-class NonLayerRepeatSpec(RepeatSpec):
-    """NonLayerRepeatSpec schema wrapper
-
-    Mapping(required=[repeat, spec])
-    Base interface for a repeat specification.
-
-    Parameters
-    ----------
-
-    repeat : anyOf(List(string), :class:`RepeatMapping`)
-        Definition for fields to be repeated. One of: 1) An array of fields to be repeated.
-        If ``"repeat"`` is an array, the field can be referred to as ``{"repeat":
-        "repeat"}``. The repeated views are laid out in a wrapped row. You can set the
-        number of columns to control the wrapping. 2) An object that maps ``"row"`` and/or
-        ``"column"`` to the listed fields to be repeated along the particular orientations.
-        The objects ``{"repeat": "row"}`` and ``{"repeat": "column"}`` can be used to refer
-        to the repeated field respectively.
-    spec : :class:`NonNormalizedSpec`
-        A specification of the view that gets repeated.
-    align : anyOf(:class:`LayoutAlign`, :class:`RowColLayoutAlign`)
-        The alignment to apply to grid rows and columns. The supported string values are
-        ``"all"``, ``"each"``, and ``"none"``.
-
-
-        * For ``"none"``, a flow layout will be used, in which adjacent subviews are simply
-          placed one after the other.
-        * For ``"each"``, subviews will be aligned into a clean grid structure, but each row
-          or column may be of variable size.
-        * For ``"all"``, subviews will be aligned and each row or column will be sized
-          identically based on the maximum observed size. String values for this property
-          will be applied to both grid rows and columns.
-
-        Alternatively, an object value of the form ``{"row": string, "column": string}`` can
-        be used to supply different alignments for rows and columns.
-
-        **Default value:** ``"all"``.
-    bounds : enum('full', 'flush')
-        The bounds calculation method to use for determining the extent of a sub-plot. One
-        of ``full`` (the default) or ``flush``.
-
-
-        * If set to ``full``, the entire calculated bounds (including axes, title, and
-          legend) will be used.
-        * If set to ``flush``, only the specified width and height values for the sub-view
-          will be used. The ``flush`` setting can be useful when attempting to place
-          sub-plots without axes or legends into a uniform grid structure.
-
-        **Default value:** ``"full"``
-    center : anyOf(boolean, :class:`RowColboolean`)
-        Boolean flag indicating if subviews should be centered relative to their respective
-        rows or columns.
-
-        An object value of the form ``{"row": boolean, "column": boolean}`` can be used to
-        supply different centering values for rows and columns.
-
-        **Default value:** ``false``
-    columns : float
-        The number of columns to include in the view composition layout.
-
-        **Default value** : ``undefined`` -- An infinite number of columns (a single row)
-        will be assumed. This is equivalent to ``hconcat`` (for ``concat`` ) and to using
-        the ``column`` channel (for ``facet`` and ``repeat`` ).
-
-        **Note** :
-
-        1) This property is only for:
-
-
-        * the general (wrappable) ``concat`` operator (not ``hconcat`` / ``vconcat`` )
-        * the ``facet`` and ``repeat`` operator with one field/repetition definition
-          (without row/column nesting)
-
-        2) Setting the ``columns`` to ``1`` is equivalent to ``vconcat`` (for ``concat`` )
-        and to using the ``row`` channel (for ``facet`` and ``repeat`` ).
-    data : anyOf(:class:`Data`, None)
-        An object describing the data source. Set to ``null`` to ignore the parent's data
-        source. If no data is set, it is derived from the parent.
-    description : string
-        Description of this mark for commenting purpose.
-    name : string
-        Name of the visualization for later reference.
-    resolve : :class:`Resolve`
-        Scale, axis, and legend resolutions for view composition specifications.
-    spacing : anyOf(float, :class:`RowColnumber`)
-        The spacing in pixels between sub-views of the composition operator. An object of
-        the form ``{"row": number, "column": number}`` can be used to set different spacing
-        values for rows and columns.
-
-        **Default value** : Depends on ``"spacing"`` property of `the view composition
-        configuration <https://vega.github.io/vega-lite/docs/config.html#view-config>`__ (
-        ``20`` by default)
-    title : anyOf(:class:`Text`, :class:`TitleParams`)
-        Title for the plot.
-    transform : List(:class:`Transform`)
-        An array of data transformations such as filter and new field calculation.
-    """
-    _schema = {'$ref': '#/definitions/NonLayerRepeatSpec'}
-
-    def __init__(self, repeat=Undefined, spec=Undefined, align=Undefined, bounds=Undefined,
-                 center=Undefined, columns=Undefined, data=Undefined, description=Undefined,
-                 name=Undefined, resolve=Undefined, spacing=Undefined, title=Undefined,
-                 transform=Undefined, **kwds):
-        super(NonLayerRepeatSpec, self).__init__(repeat=repeat, spec=spec, align=align, bounds=bounds,
-                                                 center=center, columns=columns, data=data,
-                                                 description=description, name=name, resolve=resolve,
-                                                 spacing=spacing, title=title, transform=transform,
-                                                 **kwds)
-
-
-class SphereGenerator(Generator):
-    """SphereGenerator schema wrapper
-
-    Mapping(required=[sphere])
-
-    Parameters
-    ----------
-
-    sphere : anyOf(boolean, Mapping(required=[]))
-        Generate sphere GeoJSON data for the full globe.
-    name : string
-        Provide a placeholder name and bind data at runtime.
-    """
-    _schema = {'$ref': '#/definitions/SphereGenerator'}
-
-    def __init__(self, sphere=Undefined, name=Undefined, **kwds):
-        super(SphereGenerator, self).__init__(sphere=sphere, name=name, **kwds)
-
-
-class StackOffset(VegaLiteSchema):
-    """StackOffset schema wrapper
-
-    enum('zero', 'center', 'normalize')
-    """
-    _schema = {'$ref': '#/definitions/StackOffset'}
-
-    def __init__(self, *args):
-        super(StackOffset, self).__init__(*args)
-
-
-class StandardType(VegaLiteSchema):
-    """StandardType schema wrapper
-
-    enum('quantitative', 'ordinal', 'temporal', 'nominal')
-    """
-    _schema = {'$ref': '#/definitions/StandardType'}
-
-    def __init__(self, *args):
-        super(StandardType, self).__init__(*args)
-
-
-class Step(VegaLiteSchema):
-    """Step schema wrapper
-
-    Mapping(required=[step])
-
-    Parameters
-    ----------
-
-    step : float
-        The size (width/height) per discrete step.
-    for : :class:`StepFor`
-        Whether to apply the step to position scale or offset scale when there are both
-        ``x`` and ``xOffset`` or both ``y`` and ``yOffset`` encodings.
-    """
-    _schema = {'$ref': '#/definitions/Step'}
-
-    def __init__(self, step=Undefined, **kwds):
-        super(Step, self).__init__(step=step, **kwds)
-
-
-class StepFor(VegaLiteSchema):
-    """StepFor schema wrapper
-
-    enum('position', 'offset')
-    """
-    _schema = {'$ref': '#/definitions/StepFor'}
-
-    def __init__(self, *args):
-        super(StepFor, self).__init__(*args)
-
-
-class Stream(VegaLiteSchema):
-    """Stream schema wrapper
-
-    anyOf(:class:`EventStream`, :class:`DerivedStream`, :class:`MergedStream`)
-    """
-    _schema = {'$ref': '#/definitions/Stream'}
-
-    def __init__(self, *args, **kwds):
-        super(Stream, self).__init__(*args, **kwds)
-
-
-class DerivedStream(Stream):
-    """DerivedStream schema wrapper
-
-    Mapping(required=[stream])
-
-    Parameters
-    ----------
-
-    stream : :class:`Stream`
-
-    between : List(:class:`Stream`)
-
-    consume : boolean
-
-    debounce : float
-
-    filter : anyOf(:class:`Expr`, List(:class:`Expr`))
-
-    markname : string
-
-    marktype : :class:`MarkType`
-
-    throttle : float
-
-    """
-    _schema = {'$ref': '#/definitions/DerivedStream'}
-
-    def __init__(self, stream=Undefined, between=Undefined, consume=Undefined, debounce=Undefined,
-                 filter=Undefined, markname=Undefined, marktype=Undefined, throttle=Undefined, **kwds):
-        super(DerivedStream, self).__init__(stream=stream, between=between, consume=consume,
-                                            debounce=debounce, filter=filter, markname=markname,
-                                            marktype=marktype, throttle=throttle, **kwds)
-
-
-class EventStream(Stream):
-    """EventStream schema wrapper
-
-    anyOf(Mapping(required=[type]), Mapping(required=[source, type]))
-    """
-    _schema = {'$ref': '#/definitions/EventStream'}
-
-    def __init__(self, *args, **kwds):
-        super(EventStream, self).__init__(*args, **kwds)
-
-
-class MergedStream(Stream):
-    """MergedStream schema wrapper
-
-    Mapping(required=[merge])
-
-    Parameters
-    ----------
-
-    merge : List(:class:`Stream`)
-
-    between : List(:class:`Stream`)
-
-    consume : boolean
-
-    debounce : float
-
-    filter : anyOf(:class:`Expr`, List(:class:`Expr`))
-
-    markname : string
-
-    marktype : :class:`MarkType`
-
-    throttle : float
-
-    """
-    _schema = {'$ref': '#/definitions/MergedStream'}
-
-    def __init__(self, merge=Undefined, between=Undefined, consume=Undefined, debounce=Undefined,
-                 filter=Undefined, markname=Undefined, marktype=Undefined, throttle=Undefined, **kwds):
-        super(MergedStream, self).__init__(merge=merge, between=between, consume=consume,
-                                           debounce=debounce, filter=filter, markname=markname,
-                                           marktype=marktype, throttle=throttle, **kwds)
-
-
-class StringFieldDef(VegaLiteSchema):
-    """StringFieldDef schema wrapper
-
-    Mapping(required=[])
-
-    Parameters
-    ----------
-
-    aggregate : :class:`Aggregate`
-        Aggregation function for the field (e.g., ``"mean"``, ``"sum"``, ``"median"``,
-        ``"min"``, ``"max"``, ``"count"`` ).
-
-        **Default value:** ``undefined`` (None)
-
-        **See also:** `aggregate <https://vega.github.io/vega-lite/docs/aggregate.html>`__
-        documentation.
-    bandPosition : float
-        Relative position on a band of a stacked, binned, time unit, or band scale. For
-        example, the marks will be positioned at the beginning of the band if set to ``0``,
-        and at the middle of the band if set to ``0.5``.
-    bin : anyOf(boolean, :class:`BinParams`, string, None)
-        A flag for binning a ``quantitative`` field, `an object defining binning parameters
-        <https://vega.github.io/vega-lite/docs/bin.html#bin-parameters>`__, or indicating
-        that the data for ``x`` or ``y`` channel are binned before they are imported into
-        Vega-Lite ( ``"binned"`` ).
-
-
-        If ``true``, default `binning parameters
-        <https://vega.github.io/vega-lite/docs/bin.html#bin-parameters>`__ will be applied.
-
-        If ``"binned"``, this indicates that the data for the ``x`` (or ``y`` ) channel are
-        already binned. You can map the bin-start field to ``x`` (or ``y`` ) and the bin-end
-        field to ``x2`` (or ``y2`` ). The scale and axis will be formatted similar to
-        binning in Vega-Lite.  To adjust the axis ticks based on the bin step, you can also
-        set the axis's `tickMinStep
-        <https://vega.github.io/vega-lite/docs/axis.html#ticks>`__ property.
-
-        **Default value:** ``false``
-
-        **See also:** `bin <https://vega.github.io/vega-lite/docs/bin.html>`__
-        documentation.
-    field : :class:`Field`
-        **Required.** A string defining the name of the field from which to pull a data
-        value or an object defining iterated values from the `repeat
-        <https://vega.github.io/vega-lite/docs/repeat.html>`__ operator.
-
-        **See also:** `field <https://vega.github.io/vega-lite/docs/field.html>`__
-        documentation.
-
-        **Notes:** 1)  Dots ( ``.`` ) and brackets ( ``[`` and ``]`` ) can be used to access
-        nested objects (e.g., ``"field": "foo.bar"`` and ``"field": "foo['bar']"`` ). If
-        field names contain dots or brackets but are not nested, you can use ``\\`` to
-        escape dots and brackets (e.g., ``"a\\.b"`` and ``"a\\[0\\]"`` ). See more details
-        about escaping in the `field documentation
-        <https://vega.github.io/vega-lite/docs/field.html>`__. 2) ``field`` is not required
-        if ``aggregate`` is ``count``.
-    format : anyOf(string, :class:`Dict`)
-        When used with the default ``"number"`` and ``"time"`` format type, the text
-        formatting pattern for labels of guides (axes, legends, headers) and text marks.
-
-
-        * If the format type is ``"number"`` (e.g., for quantitative fields), this is D3's
-          `number format pattern <https://github.com/d3/d3-format#locale_format>`__.
-        * If the format type is ``"time"`` (e.g., for temporal fields), this is D3's `time
-          format pattern <https://github.com/d3/d3-time-format#locale_format>`__.
-
-        See the `format documentation <https://vega.github.io/vega-lite/docs/format.html>`__
-        for more examples.
-
-        When used with a `custom formatType
-        <https://vega.github.io/vega-lite/docs/config.html#custom-format-type>`__, this
-        value will be passed as ``format`` alongside ``datum.value`` to the registered
-        function.
-
-        **Default value:**  Derived from `numberFormat
-        <https://vega.github.io/vega-lite/docs/config.html#format>`__ config for number
-        format and from `timeFormat
-        <https://vega.github.io/vega-lite/docs/config.html#format>`__ config for time
-        format.
-    formatType : string
-        The format type for labels. One of ``"number"``, ``"time"``, or a `registered custom
-        format type
-        <https://vega.github.io/vega-lite/docs/config.html#custom-format-type>`__.
-
-        **Default value:**
-
-
-        * ``"time"`` for temporal fields and ordinal and nominal fields with ``timeUnit``.
-        * ``"number"`` for quantitative fields as well as ordinal and nominal fields without
-          ``timeUnit``.
-    timeUnit : anyOf(:class:`TimeUnit`, :class:`BinnedTimeUnit`, :class:`TimeUnitParams`)
-        Time unit (e.g., ``year``, ``yearmonth``, ``month``, ``hours`` ) for a temporal
-        field. or `a temporal field that gets casted as ordinal
-        <https://vega.github.io/vega-lite/docs/type.html#cast>`__.
-
-        **Default value:** ``undefined`` (None)
-
-        **See also:** `timeUnit <https://vega.github.io/vega-lite/docs/timeunit.html>`__
-        documentation.
-    title : anyOf(:class:`Text`, None)
-        A title for the field. If ``null``, the title will be removed.
-
-        **Default value:**  derived from the field's name and transformation function (
-        ``aggregate``, ``bin`` and ``timeUnit`` ). If the field has an aggregate function,
-        the function is displayed as part of the title (e.g., ``"Sum of Profit"`` ). If the
-        field is binned or has a time unit applied, the applied function is shown in
-        parentheses (e.g., ``"Profit (binned)"``, ``"Transaction Date (year-month)"`` ).
-        Otherwise, the title is simply the field name.
-
-        **Notes** :
-
-        1) You can customize the default field title format by providing the `fieldTitle
-        <https://vega.github.io/vega-lite/docs/config.html#top-level-config>`__ property in
-        the `config <https://vega.github.io/vega-lite/docs/config.html>`__ or `fieldTitle
-        function via the compile function's options
-        <https://vega.github.io/vega-lite/usage/compile.html#field-title>`__.
-
-        2) If both field definition's ``title`` and axis, header, or legend ``title`` are
-        defined, axis/header/legend title will be used.
-    type : :class:`StandardType`
-        The type of measurement ( ``"quantitative"``, ``"temporal"``, ``"ordinal"``, or
-        ``"nominal"`` ) for the encoded field or constant value ( ``datum`` ). It can also
-        be a ``"geojson"`` type for encoding `'geoshape'
-        <https://vega.github.io/vega-lite/docs/geoshape.html>`__.
-
-        Vega-Lite automatically infers data types in many cases as discussed below. However,
-        type is required for a field if: (1) the field is not nominal and the field encoding
-        has no specified ``aggregate`` (except ``argmin`` and ``argmax`` ), ``bin``, scale
-        type, custom ``sort`` order, nor ``timeUnit`` or (2) if you wish to use an ordinal
-        scale for a field with ``bin`` or ``timeUnit``.
-
-        **Default value:**
-
-        1) For a data ``field``, ``"nominal"`` is the default data type unless the field
-        encoding has ``aggregate``, ``channel``, ``bin``, scale type, ``sort``, or
-        ``timeUnit`` that satisfies the following criteria:
-
-
-        * ``"quantitative"`` is the default type if (1) the encoded field contains ``bin``
-          or ``aggregate`` except ``"argmin"`` and ``"argmax"``, (2) the encoding channel is
-          ``latitude`` or ``longitude`` channel or (3) if the specified scale type is `a
-          quantitative scale <https://vega.github.io/vega-lite/docs/scale.html#type>`__.
-        * ``"temporal"`` is the default type if (1) the encoded field contains ``timeUnit``
-          or (2) the specified scale type is a time or utc scale
-        * ``"ordinal"`` is the default type if (1) the encoded field contains a `custom sort
-          order
-          <https://vega.github.io/vega-lite/docs/sort.html#specifying-custom-sort-order>`__,
-          (2) the specified scale type is an ordinal/point/band scale, or (3) the encoding
-          channel is ``order``.
-
-        2) For a constant value in data domain ( ``datum`` ):
-
-
-        * ``"quantitative"`` if the datum is a number
-        * ``"nominal"`` if the datum is a string
-        * ``"temporal"`` if the datum is `a date time object
-          <https://vega.github.io/vega-lite/docs/datetime.html>`__
-
-        **Note:**
-
-
-        * Data ``type`` describes the semantics of the data rather than the primitive data
-          types (number, string, etc.). The same primitive data type can have different
-          types of measurement. For example, numeric data can represent quantitative,
-          ordinal, or nominal data.
-        * Data values for a temporal field can be either a date-time string (e.g.,
-          ``"2015-03-07 12:32:17"``, ``"17:01"``, ``"2015-03-16"``. ``"2015"`` ) or a
-          timestamp number (e.g., ``1552199579097`` ).
-        * When using with `bin <https://vega.github.io/vega-lite/docs/bin.html>`__, the
-          ``type`` property can be either ``"quantitative"`` (for using a linear bin scale)
-          or `"ordinal" (for using an ordinal bin scale)
-          <https://vega.github.io/vega-lite/docs/type.html#cast-bin>`__.
-        * When using with `timeUnit
-          <https://vega.github.io/vega-lite/docs/timeunit.html>`__, the ``type`` property
-          can be either ``"temporal"`` (default, for using a temporal scale) or `"ordinal"
-          (for using an ordinal scale)
-          <https://vega.github.io/vega-lite/docs/type.html#cast-bin>`__.
-        * When using with `aggregate
-          <https://vega.github.io/vega-lite/docs/aggregate.html>`__, the ``type`` property
-          refers to the post-aggregation data type. For example, we can calculate count
-          ``distinct`` of a categorical field ``"cat"`` using ``{"aggregate": "distinct",
-          "field": "cat"}``. The ``"type"`` of the aggregate output is ``"quantitative"``.
-        * Secondary channels (e.g., ``x2``, ``y2``, ``xError``, ``yError`` ) do not have
-          ``type`` as they must have exactly the same type as their primary channels (e.g.,
-          ``x``, ``y`` ).
-
-        **See also:** `type <https://vega.github.io/vega-lite/docs/type.html>`__
-        documentation.
-    """
-    _schema = {'$ref': '#/definitions/StringFieldDef'}
-
-    def __init__(self, aggregate=Undefined, bandPosition=Undefined, bin=Undefined, field=Undefined,
-                 format=Undefined, formatType=Undefined, timeUnit=Undefined, title=Undefined,
-                 type=Undefined, **kwds):
-        super(StringFieldDef, self).__init__(aggregate=aggregate, bandPosition=bandPosition, bin=bin,
-                                             field=field, format=format, formatType=formatType,
-                                             timeUnit=timeUnit, title=title, type=type, **kwds)
-
-
-class StringFieldDefWithCondition(VegaLiteSchema):
-    """StringFieldDefWithCondition schema wrapper
-
-    Mapping(required=[])
-
-    Parameters
-    ----------
-
-    aggregate : :class:`Aggregate`
-        Aggregation function for the field (e.g., ``"mean"``, ``"sum"``, ``"median"``,
-        ``"min"``, ``"max"``, ``"count"`` ).
-
-        **Default value:** ``undefined`` (None)
-
-        **See also:** `aggregate <https://vega.github.io/vega-lite/docs/aggregate.html>`__
-        documentation.
-    bandPosition : float
-        Relative position on a band of a stacked, binned, time unit, or band scale. For
-        example, the marks will be positioned at the beginning of the band if set to ``0``,
-        and at the middle of the band if set to ``0.5``.
-    bin : anyOf(boolean, :class:`BinParams`, string, None)
-        A flag for binning a ``quantitative`` field, `an object defining binning parameters
-        <https://vega.github.io/vega-lite/docs/bin.html#bin-parameters>`__, or indicating
-        that the data for ``x`` or ``y`` channel are binned before they are imported into
-        Vega-Lite ( ``"binned"`` ).
-
-
-        If ``true``, default `binning parameters
-        <https://vega.github.io/vega-lite/docs/bin.html#bin-parameters>`__ will be applied.
-
-        If ``"binned"``, this indicates that the data for the ``x`` (or ``y`` ) channel are
-        already binned. You can map the bin-start field to ``x`` (or ``y`` ) and the bin-end
-        field to ``x2`` (or ``y2`` ). The scale and axis will be formatted similar to
-        binning in Vega-Lite.  To adjust the axis ticks based on the bin step, you can also
-        set the axis's `tickMinStep
-        <https://vega.github.io/vega-lite/docs/axis.html#ticks>`__ property.
-
-        **Default value:** ``false``
-
-        **See also:** `bin <https://vega.github.io/vega-lite/docs/bin.html>`__
-        documentation.
-    condition : anyOf(:class:`ConditionalValueDefstringExprRef`, List(:class:`ConditionalValueDefstringExprRef`))
-        One or more value definition(s) with `a parameter or a test predicate
-        <https://vega.github.io/vega-lite/docs/condition.html>`__.
-
-        **Note:** A field definition's ``condition`` property can only contain `conditional
-        value definitions <https://vega.github.io/vega-lite/docs/condition.html#value>`__
-        since Vega-Lite only allows at most one encoded field per encoding channel.
-    field : :class:`Field`
-        **Required.** A string defining the name of the field from which to pull a data
-        value or an object defining iterated values from the `repeat
-        <https://vega.github.io/vega-lite/docs/repeat.html>`__ operator.
-
-        **See also:** `field <https://vega.github.io/vega-lite/docs/field.html>`__
-        documentation.
-
-        **Notes:** 1)  Dots ( ``.`` ) and brackets ( ``[`` and ``]`` ) can be used to access
-        nested objects (e.g., ``"field": "foo.bar"`` and ``"field": "foo['bar']"`` ). If
-        field names contain dots or brackets but are not nested, you can use ``\\`` to
-        escape dots and brackets (e.g., ``"a\\.b"`` and ``"a\\[0\\]"`` ). See more details
-        about escaping in the `field documentation
-        <https://vega.github.io/vega-lite/docs/field.html>`__. 2) ``field`` is not required
-        if ``aggregate`` is ``count``.
-    format : anyOf(string, :class:`Dict`)
-        When used with the default ``"number"`` and ``"time"`` format type, the text
-        formatting pattern for labels of guides (axes, legends, headers) and text marks.
-
-
-        * If the format type is ``"number"`` (e.g., for quantitative fields), this is D3's
-          `number format pattern <https://github.com/d3/d3-format#locale_format>`__.
-        * If the format type is ``"time"`` (e.g., for temporal fields), this is D3's `time
-          format pattern <https://github.com/d3/d3-time-format#locale_format>`__.
-
-        See the `format documentation <https://vega.github.io/vega-lite/docs/format.html>`__
-        for more examples.
-
-        When used with a `custom formatType
-        <https://vega.github.io/vega-lite/docs/config.html#custom-format-type>`__, this
-        value will be passed as ``format`` alongside ``datum.value`` to the registered
-        function.
-
-        **Default value:**  Derived from `numberFormat
-        <https://vega.github.io/vega-lite/docs/config.html#format>`__ config for number
-        format and from `timeFormat
-        <https://vega.github.io/vega-lite/docs/config.html#format>`__ config for time
-        format.
-    formatType : string
-        The format type for labels. One of ``"number"``, ``"time"``, or a `registered custom
-        format type
-        <https://vega.github.io/vega-lite/docs/config.html#custom-format-type>`__.
-
-        **Default value:**
-
-
-        * ``"time"`` for temporal fields and ordinal and nominal fields with ``timeUnit``.
-        * ``"number"`` for quantitative fields as well as ordinal and nominal fields without
-          ``timeUnit``.
-    timeUnit : anyOf(:class:`TimeUnit`, :class:`BinnedTimeUnit`, :class:`TimeUnitParams`)
-        Time unit (e.g., ``year``, ``yearmonth``, ``month``, ``hours`` ) for a temporal
-        field. or `a temporal field that gets casted as ordinal
-        <https://vega.github.io/vega-lite/docs/type.html#cast>`__.
-
-        **Default value:** ``undefined`` (None)
-
-        **See also:** `timeUnit <https://vega.github.io/vega-lite/docs/timeunit.html>`__
-        documentation.
-    title : anyOf(:class:`Text`, None)
-        A title for the field. If ``null``, the title will be removed.
-
-        **Default value:**  derived from the field's name and transformation function (
-        ``aggregate``, ``bin`` and ``timeUnit`` ). If the field has an aggregate function,
-        the function is displayed as part of the title (e.g., ``"Sum of Profit"`` ). If the
-        field is binned or has a time unit applied, the applied function is shown in
-        parentheses (e.g., ``"Profit (binned)"``, ``"Transaction Date (year-month)"`` ).
-        Otherwise, the title is simply the field name.
-
-        **Notes** :
-
-        1) You can customize the default field title format by providing the `fieldTitle
-        <https://vega.github.io/vega-lite/docs/config.html#top-level-config>`__ property in
-        the `config <https://vega.github.io/vega-lite/docs/config.html>`__ or `fieldTitle
-        function via the compile function's options
-        <https://vega.github.io/vega-lite/usage/compile.html#field-title>`__.
-
-        2) If both field definition's ``title`` and axis, header, or legend ``title`` are
-        defined, axis/header/legend title will be used.
-    type : :class:`StandardType`
-        The type of measurement ( ``"quantitative"``, ``"temporal"``, ``"ordinal"``, or
-        ``"nominal"`` ) for the encoded field or constant value ( ``datum`` ). It can also
-        be a ``"geojson"`` type for encoding `'geoshape'
-        <https://vega.github.io/vega-lite/docs/geoshape.html>`__.
-
-        Vega-Lite automatically infers data types in many cases as discussed below. However,
-        type is required for a field if: (1) the field is not nominal and the field encoding
-        has no specified ``aggregate`` (except ``argmin`` and ``argmax`` ), ``bin``, scale
-        type, custom ``sort`` order, nor ``timeUnit`` or (2) if you wish to use an ordinal
-        scale for a field with ``bin`` or ``timeUnit``.
-
-        **Default value:**
-
-        1) For a data ``field``, ``"nominal"`` is the default data type unless the field
-        encoding has ``aggregate``, ``channel``, ``bin``, scale type, ``sort``, or
-        ``timeUnit`` that satisfies the following criteria:
-
-
-        * ``"quantitative"`` is the default type if (1) the encoded field contains ``bin``
-          or ``aggregate`` except ``"argmin"`` and ``"argmax"``, (2) the encoding channel is
-          ``latitude`` or ``longitude`` channel or (3) if the specified scale type is `a
-          quantitative scale <https://vega.github.io/vega-lite/docs/scale.html#type>`__.
-        * ``"temporal"`` is the default type if (1) the encoded field contains ``timeUnit``
-          or (2) the specified scale type is a time or utc scale
-        * ``"ordinal"`` is the default type if (1) the encoded field contains a `custom sort
-          order
-          <https://vega.github.io/vega-lite/docs/sort.html#specifying-custom-sort-order>`__,
-          (2) the specified scale type is an ordinal/point/band scale, or (3) the encoding
-          channel is ``order``.
-
-        2) For a constant value in data domain ( ``datum`` ):
-
-
-        * ``"quantitative"`` if the datum is a number
-        * ``"nominal"`` if the datum is a string
-        * ``"temporal"`` if the datum is `a date time object
-          <https://vega.github.io/vega-lite/docs/datetime.html>`__
-
-        **Note:**
-
-
-        * Data ``type`` describes the semantics of the data rather than the primitive data
-          types (number, string, etc.). The same primitive data type can have different
-          types of measurement. For example, numeric data can represent quantitative,
-          ordinal, or nominal data.
-        * Data values for a temporal field can be either a date-time string (e.g.,
-          ``"2015-03-07 12:32:17"``, ``"17:01"``, ``"2015-03-16"``. ``"2015"`` ) or a
-          timestamp number (e.g., ``1552199579097`` ).
-        * When using with `bin <https://vega.github.io/vega-lite/docs/bin.html>`__, the
-          ``type`` property can be either ``"quantitative"`` (for using a linear bin scale)
-          or `"ordinal" (for using an ordinal bin scale)
-          <https://vega.github.io/vega-lite/docs/type.html#cast-bin>`__.
-        * When using with `timeUnit
-          <https://vega.github.io/vega-lite/docs/timeunit.html>`__, the ``type`` property
-          can be either ``"temporal"`` (default, for using a temporal scale) or `"ordinal"
-          (for using an ordinal scale)
-          <https://vega.github.io/vega-lite/docs/type.html#cast-bin>`__.
-        * When using with `aggregate
-          <https://vega.github.io/vega-lite/docs/aggregate.html>`__, the ``type`` property
-          refers to the post-aggregation data type. For example, we can calculate count
-          ``distinct`` of a categorical field ``"cat"`` using ``{"aggregate": "distinct",
-          "field": "cat"}``. The ``"type"`` of the aggregate output is ``"quantitative"``.
-        * Secondary channels (e.g., ``x2``, ``y2``, ``xError``, ``yError`` ) do not have
-          ``type`` as they must have exactly the same type as their primary channels (e.g.,
-          ``x``, ``y`` ).
-
-        **See also:** `type <https://vega.github.io/vega-lite/docs/type.html>`__
-        documentation.
-    """
-    _schema = {'$ref': '#/definitions/StringFieldDefWithCondition'}
-
-    def __init__(self, aggregate=Undefined, bandPosition=Undefined, bin=Undefined, condition=Undefined,
-                 field=Undefined, format=Undefined, formatType=Undefined, timeUnit=Undefined,
-                 title=Undefined, type=Undefined, **kwds):
-        super(StringFieldDefWithCondition, self).__init__(aggregate=aggregate,
-                                                          bandPosition=bandPosition, bin=bin,
-                                                          condition=condition, field=field,
-                                                          format=format, formatType=formatType,
-                                                          timeUnit=timeUnit, title=title, type=type,
-                                                          **kwds)
-
-
-class StringValueDefWithCondition(VegaLiteSchema):
-    """StringValueDefWithCondition schema wrapper
-
-    Mapping(required=[])
-
-    Parameters
-    ----------
-
-    condition : anyOf(:class:`ConditionalMarkPropFieldOrDatumDef`, :class:`ConditionalValueDefstringnullExprRef`, List(:class:`ConditionalValueDefstringnullExprRef`))
-        A field definition or one or more value definition(s) with a parameter predicate.
-    value : anyOf(string, None, :class:`ExprRef`)
-        A constant value in visual domain (e.g., ``"red"`` / ``"#0099ff"`` / `gradient
-        definition <https://vega.github.io/vega-lite/docs/types.html#gradient>`__ for color,
-        values between ``0`` to ``1`` for opacity).
-    """
-    _schema = {'$ref': '#/definitions/StringValueDefWithCondition'}
-
-    def __init__(self, condition=Undefined, value=Undefined, **kwds):
-        super(StringValueDefWithCondition, self).__init__(condition=condition, value=value, **kwds)
-
-
-class StrokeCap(VegaLiteSchema):
-    """StrokeCap schema wrapper
-
-    enum('butt', 'round', 'square')
-    """
-    _schema = {'$ref': '#/definitions/StrokeCap'}
-
-    def __init__(self, *args):
-        super(StrokeCap, self).__init__(*args)
-
-
-class StrokeJoin(VegaLiteSchema):
-    """StrokeJoin schema wrapper
-
-    enum('miter', 'round', 'bevel')
-    """
-    _schema = {'$ref': '#/definitions/StrokeJoin'}
-
-    def __init__(self, *args):
-        super(StrokeJoin, self).__init__(*args)
-
-
-class StyleConfigIndex(VegaLiteSchema):
-    """StyleConfigIndex schema wrapper
-
-    Mapping(required=[])
-
-    Parameters
-    ----------
-
-    arc : :class:`RectConfig`
-        Arc-specific Config
-    area : :class:`AreaConfig`
-        Area-Specific Config
-    bar : :class:`BarConfig`
-        Bar-Specific Config
-    circle : :class:`MarkConfig`
-        Circle-Specific Config
-    geoshape : :class:`MarkConfig`
-        Geoshape-Specific Config
-    image : :class:`RectConfig`
-        Image-specific Config
-    line : :class:`LineConfig`
-        Line-Specific Config
-    mark : :class:`MarkConfig`
-        Mark Config
-    point : :class:`MarkConfig`
-        Point-Specific Config
-    rect : :class:`RectConfig`
-        Rect-Specific Config
-    rule : :class:`MarkConfig`
-        Rule-Specific Config
-    square : :class:`MarkConfig`
-        Square-Specific Config
-    text : :class:`MarkConfig`
-        Text-Specific Config
-    tick : :class:`TickConfig`
-        Tick-Specific Config
-    trail : :class:`LineConfig`
-        Trail-Specific Config
-    group-subtitle : :class:`MarkConfig`
-        Default style for chart subtitles
-    group-title : :class:`MarkConfig`
-        Default style for chart titles
-    guide-label : :class:`MarkConfig`
-        Default style for axis, legend, and header labels.
-    guide-title : :class:`MarkConfig`
-        Default style for axis, legend, and header titles.
-    """
-    _schema = {'$ref': '#/definitions/StyleConfigIndex'}
-
-    def __init__(self, arc=Undefined, area=Undefined, bar=Undefined, circle=Undefined,
-                 geoshape=Undefined, image=Undefined, line=Undefined, mark=Undefined, point=Undefined,
-                 rect=Undefined, rule=Undefined, square=Undefined, text=Undefined, tick=Undefined,
-                 trail=Undefined, **kwds):
-        super(StyleConfigIndex, self).__init__(arc=arc, area=area, bar=bar, circle=circle,
-                                               geoshape=geoshape, image=image, line=line, mark=mark,
-                                               point=point, rect=rect, rule=rule, square=square,
-                                               text=text, tick=tick, trail=trail, **kwds)
-
-
-class SymbolShape(VegaLiteSchema):
-    """SymbolShape schema wrapper
-
-    string
-    """
-    _schema = {'$ref': '#/definitions/SymbolShape'}
-
-    def __init__(self, *args):
-        super(SymbolShape, self).__init__(*args)
-
-
-class Text(VegaLiteSchema):
-    """Text schema wrapper
-
-    anyOf(string, List(string))
-    """
-    _schema = {'$ref': '#/definitions/Text'}
-
-    def __init__(self, *args, **kwds):
-        super(Text, self).__init__(*args, **kwds)
-
-
-class TextBaseline(VegaLiteSchema):
-    """TextBaseline schema wrapper
-
-    anyOf(string, :class:`Baseline`, string, string)
-    """
-    _schema = {'$ref': '#/definitions/TextBaseline'}
-
-    def __init__(self, *args, **kwds):
-        super(TextBaseline, self).__init__(*args, **kwds)
-
-
-class Baseline(TextBaseline):
-    """Baseline schema wrapper
-
-    enum('top', 'middle', 'bottom')
-    """
-    _schema = {'$ref': '#/definitions/Baseline'}
-
-    def __init__(self, *args):
-        super(Baseline, self).__init__(*args)
-
-
-class TextDef(VegaLiteSchema):
-    """TextDef schema wrapper
-
-    anyOf(:class:`FieldOrDatumDefWithConditionStringFieldDefText`,
-    :class:`FieldOrDatumDefWithConditionStringDatumDefText`,
-    :class:`ValueDefWithConditionStringFieldDefText`)
-    """
-    _schema = {'$ref': '#/definitions/TextDef'}
-
-    def __init__(self, *args, **kwds):
-        super(TextDef, self).__init__(*args, **kwds)
-
-
-class FieldOrDatumDefWithConditionStringDatumDefText(TextDef):
-    """FieldOrDatumDefWithConditionStringDatumDefText schema wrapper
-
-    Mapping(required=[])
-
-    Parameters
-    ----------
-
-    bandPosition : float
-        Relative position on a band of a stacked, binned, time unit, or band scale. For
-        example, the marks will be positioned at the beginning of the band if set to ``0``,
-        and at the middle of the band if set to ``0.5``.
-    condition : anyOf(:class:`ConditionalValueDefTextExprRef`, List(:class:`ConditionalValueDefTextExprRef`))
-        One or more value definition(s) with `a parameter or a test predicate
-        <https://vega.github.io/vega-lite/docs/condition.html>`__.
-
-        **Note:** A field definition's ``condition`` property can only contain `conditional
-        value definitions <https://vega.github.io/vega-lite/docs/condition.html#value>`__
-        since Vega-Lite only allows at most one encoded field per encoding channel.
-    datum : anyOf(:class:`PrimitiveValue`, :class:`DateTime`, :class:`ExprRef`, :class:`RepeatRef`)
-        A constant value in data domain.
-    format : anyOf(string, :class:`Dict`)
-        When used with the default ``"number"`` and ``"time"`` format type, the text
-        formatting pattern for labels of guides (axes, legends, headers) and text marks.
-
-
-        * If the format type is ``"number"`` (e.g., for quantitative fields), this is D3's
-          `number format pattern <https://github.com/d3/d3-format#locale_format>`__.
-        * If the format type is ``"time"`` (e.g., for temporal fields), this is D3's `time
-          format pattern <https://github.com/d3/d3-time-format#locale_format>`__.
-
-        See the `format documentation <https://vega.github.io/vega-lite/docs/format.html>`__
-        for more examples.
-
-        When used with a `custom formatType
-        <https://vega.github.io/vega-lite/docs/config.html#custom-format-type>`__, this
-        value will be passed as ``format`` alongside ``datum.value`` to the registered
-        function.
-
-        **Default value:**  Derived from `numberFormat
-        <https://vega.github.io/vega-lite/docs/config.html#format>`__ config for number
-        format and from `timeFormat
-        <https://vega.github.io/vega-lite/docs/config.html#format>`__ config for time
-        format.
-    formatType : string
-        The format type for labels. One of ``"number"``, ``"time"``, or a `registered custom
-        format type
-        <https://vega.github.io/vega-lite/docs/config.html#custom-format-type>`__.
-
-        **Default value:**
-
-
-        * ``"time"`` for temporal fields and ordinal and nominal fields with ``timeUnit``.
-        * ``"number"`` for quantitative fields as well as ordinal and nominal fields without
-          ``timeUnit``.
-    title : anyOf(:class:`Text`, None)
-        A title for the field. If ``null``, the title will be removed.
-
-        **Default value:**  derived from the field's name and transformation function (
-        ``aggregate``, ``bin`` and ``timeUnit`` ). If the field has an aggregate function,
-        the function is displayed as part of the title (e.g., ``"Sum of Profit"`` ). If the
-        field is binned or has a time unit applied, the applied function is shown in
-        parentheses (e.g., ``"Profit (binned)"``, ``"Transaction Date (year-month)"`` ).
-        Otherwise, the title is simply the field name.
-
-        **Notes** :
-
-        1) You can customize the default field title format by providing the `fieldTitle
-        <https://vega.github.io/vega-lite/docs/config.html#top-level-config>`__ property in
-        the `config <https://vega.github.io/vega-lite/docs/config.html>`__ or `fieldTitle
-        function via the compile function's options
-        <https://vega.github.io/vega-lite/usage/compile.html#field-title>`__.
-
-        2) If both field definition's ``title`` and axis, header, or legend ``title`` are
-        defined, axis/header/legend title will be used.
-    type : :class:`Type`
-        The type of measurement ( ``"quantitative"``, ``"temporal"``, ``"ordinal"``, or
-        ``"nominal"`` ) for the encoded field or constant value ( ``datum`` ). It can also
-        be a ``"geojson"`` type for encoding `'geoshape'
-        <https://vega.github.io/vega-lite/docs/geoshape.html>`__.
-
-        Vega-Lite automatically infers data types in many cases as discussed below. However,
-        type is required for a field if: (1) the field is not nominal and the field encoding
-        has no specified ``aggregate`` (except ``argmin`` and ``argmax`` ), ``bin``, scale
-        type, custom ``sort`` order, nor ``timeUnit`` or (2) if you wish to use an ordinal
-        scale for a field with ``bin`` or ``timeUnit``.
-
-        **Default value:**
-
-        1) For a data ``field``, ``"nominal"`` is the default data type unless the field
-        encoding has ``aggregate``, ``channel``, ``bin``, scale type, ``sort``, or
-        ``timeUnit`` that satisfies the following criteria:
-
-
-        * ``"quantitative"`` is the default type if (1) the encoded field contains ``bin``
-          or ``aggregate`` except ``"argmin"`` and ``"argmax"``, (2) the encoding channel is
-          ``latitude`` or ``longitude`` channel or (3) if the specified scale type is `a
-          quantitative scale <https://vega.github.io/vega-lite/docs/scale.html#type>`__.
-        * ``"temporal"`` is the default type if (1) the encoded field contains ``timeUnit``
-          or (2) the specified scale type is a time or utc scale
-        * ``"ordinal"`` is the default type if (1) the encoded field contains a `custom sort
-          order
-          <https://vega.github.io/vega-lite/docs/sort.html#specifying-custom-sort-order>`__,
-          (2) the specified scale type is an ordinal/point/band scale, or (3) the encoding
-          channel is ``order``.
-
-        2) For a constant value in data domain ( ``datum`` ):
-
-
-        * ``"quantitative"`` if the datum is a number
-        * ``"nominal"`` if the datum is a string
-        * ``"temporal"`` if the datum is `a date time object
-          <https://vega.github.io/vega-lite/docs/datetime.html>`__
-
-        **Note:**
-
-
-        * Data ``type`` describes the semantics of the data rather than the primitive data
-          types (number, string, etc.). The same primitive data type can have different
-          types of measurement. For example, numeric data can represent quantitative,
-          ordinal, or nominal data.
-        * Data values for a temporal field can be either a date-time string (e.g.,
-          ``"2015-03-07 12:32:17"``, ``"17:01"``, ``"2015-03-16"``. ``"2015"`` ) or a
-          timestamp number (e.g., ``1552199579097`` ).
-        * When using with `bin <https://vega.github.io/vega-lite/docs/bin.html>`__, the
-          ``type`` property can be either ``"quantitative"`` (for using a linear bin scale)
-          or `"ordinal" (for using an ordinal bin scale)
-          <https://vega.github.io/vega-lite/docs/type.html#cast-bin>`__.
-        * When using with `timeUnit
-          <https://vega.github.io/vega-lite/docs/timeunit.html>`__, the ``type`` property
-          can be either ``"temporal"`` (default, for using a temporal scale) or `"ordinal"
-          (for using an ordinal scale)
-          <https://vega.github.io/vega-lite/docs/type.html#cast-bin>`__.
-        * When using with `aggregate
-          <https://vega.github.io/vega-lite/docs/aggregate.html>`__, the ``type`` property
-          refers to the post-aggregation data type. For example, we can calculate count
-          ``distinct`` of a categorical field ``"cat"`` using ``{"aggregate": "distinct",
-          "field": "cat"}``. The ``"type"`` of the aggregate output is ``"quantitative"``.
-        * Secondary channels (e.g., ``x2``, ``y2``, ``xError``, ``yError`` ) do not have
-          ``type`` as they must have exactly the same type as their primary channels (e.g.,
-          ``x``, ``y`` ).
-
-        **See also:** `type <https://vega.github.io/vega-lite/docs/type.html>`__
-        documentation.
-    """
-    _schema = {'$ref': '#/definitions/FieldOrDatumDefWithCondition<StringDatumDef,Text>'}
-
-    def __init__(self, bandPosition=Undefined, condition=Undefined, datum=Undefined, format=Undefined,
-                 formatType=Undefined, title=Undefined, type=Undefined, **kwds):
-        super(FieldOrDatumDefWithConditionStringDatumDefText, self).__init__(bandPosition=bandPosition,
-                                                                             condition=condition,
-                                                                             datum=datum, format=format,
-                                                                             formatType=formatType,
-                                                                             title=title, type=type,
-                                                                             **kwds)
-
-
-class FieldOrDatumDefWithConditionStringFieldDefText(TextDef):
-    """FieldOrDatumDefWithConditionStringFieldDefText schema wrapper
-
-    Mapping(required=[])
-
-    Parameters
-    ----------
-
-    aggregate : :class:`Aggregate`
-        Aggregation function for the field (e.g., ``"mean"``, ``"sum"``, ``"median"``,
-        ``"min"``, ``"max"``, ``"count"`` ).
-
-        **Default value:** ``undefined`` (None)
-
-        **See also:** `aggregate <https://vega.github.io/vega-lite/docs/aggregate.html>`__
-        documentation.
-    bandPosition : float
-        Relative position on a band of a stacked, binned, time unit, or band scale. For
-        example, the marks will be positioned at the beginning of the band if set to ``0``,
-        and at the middle of the band if set to ``0.5``.
-    bin : anyOf(boolean, :class:`BinParams`, string, None)
-        A flag for binning a ``quantitative`` field, `an object defining binning parameters
-        <https://vega.github.io/vega-lite/docs/bin.html#bin-parameters>`__, or indicating
-        that the data for ``x`` or ``y`` channel are binned before they are imported into
-        Vega-Lite ( ``"binned"`` ).
-
-
-        If ``true``, default `binning parameters
-        <https://vega.github.io/vega-lite/docs/bin.html#bin-parameters>`__ will be applied.
-
-        If ``"binned"``, this indicates that the data for the ``x`` (or ``y`` ) channel are
-        already binned. You can map the bin-start field to ``x`` (or ``y`` ) and the bin-end
-        field to ``x2`` (or ``y2`` ). The scale and axis will be formatted similar to
-        binning in Vega-Lite.  To adjust the axis ticks based on the bin step, you can also
-        set the axis's `tickMinStep
-        <https://vega.github.io/vega-lite/docs/axis.html#ticks>`__ property.
-
-        **Default value:** ``false``
-
-        **See also:** `bin <https://vega.github.io/vega-lite/docs/bin.html>`__
-        documentation.
-    condition : anyOf(:class:`ConditionalValueDefTextExprRef`, List(:class:`ConditionalValueDefTextExprRef`))
-        One or more value definition(s) with `a parameter or a test predicate
-        <https://vega.github.io/vega-lite/docs/condition.html>`__.
-
-        **Note:** A field definition's ``condition`` property can only contain `conditional
-        value definitions <https://vega.github.io/vega-lite/docs/condition.html#value>`__
-        since Vega-Lite only allows at most one encoded field per encoding channel.
-    field : :class:`Field`
-        **Required.** A string defining the name of the field from which to pull a data
-        value or an object defining iterated values from the `repeat
-        <https://vega.github.io/vega-lite/docs/repeat.html>`__ operator.
-
-        **See also:** `field <https://vega.github.io/vega-lite/docs/field.html>`__
-        documentation.
-
-        **Notes:** 1)  Dots ( ``.`` ) and brackets ( ``[`` and ``]`` ) can be used to access
-        nested objects (e.g., ``"field": "foo.bar"`` and ``"field": "foo['bar']"`` ). If
-        field names contain dots or brackets but are not nested, you can use ``\\`` to
-        escape dots and brackets (e.g., ``"a\\.b"`` and ``"a\\[0\\]"`` ). See more details
-        about escaping in the `field documentation
-        <https://vega.github.io/vega-lite/docs/field.html>`__. 2) ``field`` is not required
-        if ``aggregate`` is ``count``.
-    format : anyOf(string, :class:`Dict`)
-        When used with the default ``"number"`` and ``"time"`` format type, the text
-        formatting pattern for labels of guides (axes, legends, headers) and text marks.
-
-
-        * If the format type is ``"number"`` (e.g., for quantitative fields), this is D3's
-          `number format pattern <https://github.com/d3/d3-format#locale_format>`__.
-        * If the format type is ``"time"`` (e.g., for temporal fields), this is D3's `time
-          format pattern <https://github.com/d3/d3-time-format#locale_format>`__.
-
-        See the `format documentation <https://vega.github.io/vega-lite/docs/format.html>`__
-        for more examples.
-
-        When used with a `custom formatType
-        <https://vega.github.io/vega-lite/docs/config.html#custom-format-type>`__, this
-        value will be passed as ``format`` alongside ``datum.value`` to the registered
-        function.
-
-        **Default value:**  Derived from `numberFormat
-        <https://vega.github.io/vega-lite/docs/config.html#format>`__ config for number
-        format and from `timeFormat
-        <https://vega.github.io/vega-lite/docs/config.html#format>`__ config for time
-        format.
-    formatType : string
-        The format type for labels. One of ``"number"``, ``"time"``, or a `registered custom
-        format type
-        <https://vega.github.io/vega-lite/docs/config.html#custom-format-type>`__.
-
-        **Default value:**
-
-
-        * ``"time"`` for temporal fields and ordinal and nominal fields with ``timeUnit``.
-        * ``"number"`` for quantitative fields as well as ordinal and nominal fields without
-          ``timeUnit``.
-    timeUnit : anyOf(:class:`TimeUnit`, :class:`BinnedTimeUnit`, :class:`TimeUnitParams`)
-        Time unit (e.g., ``year``, ``yearmonth``, ``month``, ``hours`` ) for a temporal
-        field. or `a temporal field that gets casted as ordinal
-        <https://vega.github.io/vega-lite/docs/type.html#cast>`__.
-
-        **Default value:** ``undefined`` (None)
-
-        **See also:** `timeUnit <https://vega.github.io/vega-lite/docs/timeunit.html>`__
-        documentation.
-    title : anyOf(:class:`Text`, None)
-        A title for the field. If ``null``, the title will be removed.
-
-        **Default value:**  derived from the field's name and transformation function (
-        ``aggregate``, ``bin`` and ``timeUnit`` ). If the field has an aggregate function,
-        the function is displayed as part of the title (e.g., ``"Sum of Profit"`` ). If the
-        field is binned or has a time unit applied, the applied function is shown in
-        parentheses (e.g., ``"Profit (binned)"``, ``"Transaction Date (year-month)"`` ).
-        Otherwise, the title is simply the field name.
-
-        **Notes** :
-
-        1) You can customize the default field title format by providing the `fieldTitle
-        <https://vega.github.io/vega-lite/docs/config.html#top-level-config>`__ property in
-        the `config <https://vega.github.io/vega-lite/docs/config.html>`__ or `fieldTitle
-        function via the compile function's options
-        <https://vega.github.io/vega-lite/usage/compile.html#field-title>`__.
-
-        2) If both field definition's ``title`` and axis, header, or legend ``title`` are
-        defined, axis/header/legend title will be used.
-    type : :class:`StandardType`
-        The type of measurement ( ``"quantitative"``, ``"temporal"``, ``"ordinal"``, or
-        ``"nominal"`` ) for the encoded field or constant value ( ``datum`` ). It can also
-        be a ``"geojson"`` type for encoding `'geoshape'
-        <https://vega.github.io/vega-lite/docs/geoshape.html>`__.
-
-        Vega-Lite automatically infers data types in many cases as discussed below. However,
-        type is required for a field if: (1) the field is not nominal and the field encoding
-        has no specified ``aggregate`` (except ``argmin`` and ``argmax`` ), ``bin``, scale
-        type, custom ``sort`` order, nor ``timeUnit`` or (2) if you wish to use an ordinal
-        scale for a field with ``bin`` or ``timeUnit``.
-
-        **Default value:**
-
-        1) For a data ``field``, ``"nominal"`` is the default data type unless the field
-        encoding has ``aggregate``, ``channel``, ``bin``, scale type, ``sort``, or
-        ``timeUnit`` that satisfies the following criteria:
-
-
-        * ``"quantitative"`` is the default type if (1) the encoded field contains ``bin``
-          or ``aggregate`` except ``"argmin"`` and ``"argmax"``, (2) the encoding channel is
-          ``latitude`` or ``longitude`` channel or (3) if the specified scale type is `a
-          quantitative scale <https://vega.github.io/vega-lite/docs/scale.html#type>`__.
-        * ``"temporal"`` is the default type if (1) the encoded field contains ``timeUnit``
-          or (2) the specified scale type is a time or utc scale
-        * ``"ordinal"`` is the default type if (1) the encoded field contains a `custom sort
-          order
-          <https://vega.github.io/vega-lite/docs/sort.html#specifying-custom-sort-order>`__,
-          (2) the specified scale type is an ordinal/point/band scale, or (3) the encoding
-          channel is ``order``.
-
-        2) For a constant value in data domain ( ``datum`` ):
-
-
-        * ``"quantitative"`` if the datum is a number
-        * ``"nominal"`` if the datum is a string
-        * ``"temporal"`` if the datum is `a date time object
-          <https://vega.github.io/vega-lite/docs/datetime.html>`__
-
-        **Note:**
-
-
-        * Data ``type`` describes the semantics of the data rather than the primitive data
-          types (number, string, etc.). The same primitive data type can have different
-          types of measurement. For example, numeric data can represent quantitative,
-          ordinal, or nominal data.
-        * Data values for a temporal field can be either a date-time string (e.g.,
-          ``"2015-03-07 12:32:17"``, ``"17:01"``, ``"2015-03-16"``. ``"2015"`` ) or a
-          timestamp number (e.g., ``1552199579097`` ).
-        * When using with `bin <https://vega.github.io/vega-lite/docs/bin.html>`__, the
-          ``type`` property can be either ``"quantitative"`` (for using a linear bin scale)
-          or `"ordinal" (for using an ordinal bin scale)
-          <https://vega.github.io/vega-lite/docs/type.html#cast-bin>`__.
-        * When using with `timeUnit
-          <https://vega.github.io/vega-lite/docs/timeunit.html>`__, the ``type`` property
-          can be either ``"temporal"`` (default, for using a temporal scale) or `"ordinal"
-          (for using an ordinal scale)
-          <https://vega.github.io/vega-lite/docs/type.html#cast-bin>`__.
-        * When using with `aggregate
-          <https://vega.github.io/vega-lite/docs/aggregate.html>`__, the ``type`` property
-          refers to the post-aggregation data type. For example, we can calculate count
-          ``distinct`` of a categorical field ``"cat"`` using ``{"aggregate": "distinct",
-          "field": "cat"}``. The ``"type"`` of the aggregate output is ``"quantitative"``.
-        * Secondary channels (e.g., ``x2``, ``y2``, ``xError``, ``yError`` ) do not have
-          ``type`` as they must have exactly the same type as their primary channels (e.g.,
-          ``x``, ``y`` ).
-
-        **See also:** `type <https://vega.github.io/vega-lite/docs/type.html>`__
-        documentation.
-    """
-    _schema = {'$ref': '#/definitions/FieldOrDatumDefWithCondition<StringFieldDef,Text>'}
-
-    def __init__(self, aggregate=Undefined, bandPosition=Undefined, bin=Undefined, condition=Undefined,
-                 field=Undefined, format=Undefined, formatType=Undefined, timeUnit=Undefined,
-                 title=Undefined, type=Undefined, **kwds):
-        super(FieldOrDatumDefWithConditionStringFieldDefText, self).__init__(aggregate=aggregate,
-                                                                             bandPosition=bandPosition,
-                                                                             bin=bin,
-                                                                             condition=condition,
-                                                                             field=field, format=format,
-                                                                             formatType=formatType,
-                                                                             timeUnit=timeUnit,
-                                                                             title=title, type=type,
-                                                                             **kwds)
-
-
-class TextDirection(VegaLiteSchema):
-    """TextDirection schema wrapper
-
-    enum('ltr', 'rtl')
-    """
-    _schema = {'$ref': '#/definitions/TextDirection'}
-
-    def __init__(self, *args):
-        super(TextDirection, self).__init__(*args)
-
-
-class TickConfig(AnyMarkConfig):
-    """TickConfig schema wrapper
-
-    Mapping(required=[])
-
-    Parameters
-    ----------
-
-    align : anyOf(:class:`Align`, :class:`ExprRef`)
-        The horizontal alignment of the text or ranged marks (area, bar, image, rect, rule).
-        One of ``"left"``, ``"right"``, ``"center"``.
-
-        **Note:** Expression reference is *not* supported for range marks.
-    angle : anyOf(float, :class:`ExprRef`)
-        The rotation angle of the text, in degrees.
-    aria : anyOf(boolean, :class:`ExprRef`)
-        A boolean flag indicating if `ARIA attributes
-        <https://developer.mozilla.org/en-US/docs/Web/Accessibility/ARIA>`__ should be
-        included (SVG output only). If ``false``, the "aria-hidden" attribute will be set on
-        the output SVG element, removing the mark item from the ARIA accessibility tree.
-    ariaRole : anyOf(string, :class:`ExprRef`)
-        Sets the type of user interface element of the mark item for `ARIA accessibility
-        <https://developer.mozilla.org/en-US/docs/Web/Accessibility/ARIA>`__ (SVG output
-        only). If specified, this property determines the "role" attribute. Warning: this
-        property is experimental and may be changed in the future.
-    ariaRoleDescription : anyOf(string, :class:`ExprRef`)
-        A human-readable, author-localized description for the role of the mark item for
-        `ARIA accessibility
-        <https://developer.mozilla.org/en-US/docs/Web/Accessibility/ARIA>`__ (SVG output
-        only). If specified, this property determines the "aria-roledescription" attribute.
-        Warning: this property is experimental and may be changed in the future.
-    aspect : anyOf(boolean, :class:`ExprRef`)
-        Whether to keep aspect ratio of image marks.
-    bandSize : float
-        The width of the ticks.
-
-        **Default value:**  3/4 of step (width step for horizontal ticks and height step for
-        vertical ticks).
-    baseline : anyOf(:class:`TextBaseline`, :class:`ExprRef`)
-        For text marks, the vertical text baseline. One of ``"alphabetic"`` (default),
-        ``"top"``, ``"middle"``, ``"bottom"``, ``"line-top"``, ``"line-bottom"``, or an
-        expression reference that provides one of the valid values. The ``"line-top"`` and
-        ``"line-bottom"`` values operate similarly to ``"top"`` and ``"bottom"``, but are
-        calculated relative to the ``lineHeight`` rather than ``fontSize`` alone.
-
-        For range marks, the vertical alignment of the marks. One of ``"top"``,
-        ``"middle"``, ``"bottom"``.
-
-        **Note:** Expression reference is *not* supported for range marks.
-    blend : anyOf(:class:`Blend`, :class:`ExprRef`)
-        The color blend mode for drawing an item on its current background. Any valid `CSS
-        mix-blend-mode <https://developer.mozilla.org/en-US/docs/Web/CSS/mix-blend-mode>`__
-        value can be used.
-
-        __Default value:__ ``"source-over"``
-    color : anyOf(:class:`Color`, :class:`Gradient`, :class:`ExprRef`)
-        Default color.
-
-        **Default value:** :raw-html:`<span style="color: #4682b4;">&#9632;</span>`
-        ``"#4682b4"``
-
-        **Note:**
-
-
-        * This property cannot be used in a `style config
-          <https://vega.github.io/vega-lite/docs/mark.html#style-config>`__.
-        * The ``fill`` and ``stroke`` properties have higher precedence than ``color`` and
-          will override ``color``.
-    cornerRadius : anyOf(float, :class:`ExprRef`)
-        The radius in pixels of rounded rectangles or arcs' corners.
-
-        **Default value:** ``0``
-    cornerRadiusBottomLeft : anyOf(float, :class:`ExprRef`)
-        The radius in pixels of rounded rectangles' bottom left corner.
-
-        **Default value:** ``0``
-    cornerRadiusBottomRight : anyOf(float, :class:`ExprRef`)
-        The radius in pixels of rounded rectangles' bottom right corner.
-
-        **Default value:** ``0``
-    cornerRadiusTopLeft : anyOf(float, :class:`ExprRef`)
-        The radius in pixels of rounded rectangles' top right corner.
-
-        **Default value:** ``0``
-    cornerRadiusTopRight : anyOf(float, :class:`ExprRef`)
-        The radius in pixels of rounded rectangles' top left corner.
-
-        **Default value:** ``0``
-    cursor : anyOf(:class:`Cursor`, :class:`ExprRef`)
-        The mouse cursor used over the mark. Any valid `CSS cursor type
-        <https://developer.mozilla.org/en-US/docs/Web/CSS/cursor#Values>`__ can be used.
-    description : anyOf(string, :class:`ExprRef`)
-        A text description of the mark item for `ARIA accessibility
-        <https://developer.mozilla.org/en-US/docs/Web/Accessibility/ARIA>`__ (SVG output
-        only). If specified, this property determines the `"aria-label" attribute
-        <https://developer.mozilla.org/en-US/docs/Web/Accessibility/ARIA/ARIA_Techniques/Using_the_aria-label_attribute>`__.
-    dir : anyOf(:class:`TextDirection`, :class:`ExprRef`)
-        The direction of the text. One of ``"ltr"`` (left-to-right) or ``"rtl"``
-        (right-to-left). This property determines on which side is truncated in response to
-        the limit parameter.
-
-        **Default value:** ``"ltr"``
-    dx : anyOf(float, :class:`ExprRef`)
-        The horizontal offset, in pixels, between the text label and its anchor point. The
-        offset is applied after rotation by the *angle* property.
-    dy : anyOf(float, :class:`ExprRef`)
-        The vertical offset, in pixels, between the text label and its anchor point. The
-        offset is applied after rotation by the *angle* property.
-    ellipsis : anyOf(string, :class:`ExprRef`)
-        The ellipsis string for text truncated in response to the limit parameter.
-
-        **Default value:** ``"…"``
-    endAngle : anyOf(float, :class:`ExprRef`)
-        The end angle in radians for arc marks. A value of ``0`` indicates up (north),
-        increasing values proceed clockwise.
-    fill : anyOf(:class:`Color`, :class:`Gradient`, None, :class:`ExprRef`)
-        Default fill color. This property has higher precedence than ``config.color``. Set
-        to ``null`` to remove fill.
-
-        **Default value:** (None)
-    fillOpacity : anyOf(float, :class:`ExprRef`)
-        The fill opacity (value between [0,1]).
-
-        **Default value:** ``1``
-    filled : boolean
-        Whether the mark's color should be used as fill color instead of stroke color.
-
-        **Default value:** ``false`` for all ``point``, ``line``, and ``rule`` marks as well
-        as ``geoshape`` marks for `graticule
-        <https://vega.github.io/vega-lite/docs/data.html#graticule>`__ data sources;
-        otherwise, ``true``.
-
-        **Note:** This property cannot be used in a `style config
-        <https://vega.github.io/vega-lite/docs/mark.html#style-config>`__.
-    font : anyOf(string, :class:`ExprRef`)
-        The typeface to set the text in (e.g., ``"Helvetica Neue"`` ).
-    fontSize : anyOf(float, :class:`ExprRef`)
-        The font size, in pixels.
-
-        **Default value:** ``11``
-    fontStyle : anyOf(:class:`FontStyle`, :class:`ExprRef`)
-        The font style (e.g., ``"italic"`` ).
-    fontWeight : anyOf(:class:`FontWeight`, :class:`ExprRef`)
-        The font weight. This can be either a string (e.g ``"bold"``, ``"normal"`` ) or a
-        number ( ``100``, ``200``, ``300``, ..., ``900`` where ``"normal"`` = ``400`` and
-        ``"bold"`` = ``700`` ).
-    height : anyOf(float, :class:`ExprRef`)
-        Height of the marks.
-    href : anyOf(:class:`URI`, :class:`ExprRef`)
-        A URL to load upon mouse click. If defined, the mark acts as a hyperlink.
-    innerRadius : anyOf(float, :class:`ExprRef`)
-        The inner radius in pixels of arc marks. ``innerRadius`` is an alias for
-        ``radius2``.
-
-        **Default value:** ``0``
-    interpolate : anyOf(:class:`Interpolate`, :class:`ExprRef`)
-        The line interpolation method to use for line and area marks. One of the following:
-
-
-        * ``"linear"`` : piecewise linear segments, as in a polyline.
-        * ``"linear-closed"`` : close the linear segments to form a polygon.
-        * ``"step"`` : alternate between horizontal and vertical segments, as in a step
-          function.
-        * ``"step-before"`` : alternate between vertical and horizontal segments, as in a
-          step function.
-        * ``"step-after"`` : alternate between horizontal and vertical segments, as in a
-          step function.
-        * ``"basis"`` : a B-spline, with control point duplication on the ends.
-        * ``"basis-open"`` : an open B-spline; may not intersect the start or end.
-        * ``"basis-closed"`` : a closed B-spline, as in a loop.
-        * ``"cardinal"`` : a Cardinal spline, with control point duplication on the ends.
-        * ``"cardinal-open"`` : an open Cardinal spline; may not intersect the start or end,
-          but will intersect other control points.
-        * ``"cardinal-closed"`` : a closed Cardinal spline, as in a loop.
-        * ``"bundle"`` : equivalent to basis, except the tension parameter is used to
-          straighten the spline.
-        * ``"monotone"`` : cubic interpolation that preserves monotonicity in y.
-    invalid : enum('filter', None)
-        Defines how Vega-Lite should handle marks for invalid values ( ``null`` and ``NaN``
-        ).
-
-
-        * If set to ``"filter"`` (default), all data items with null values will be skipped
-          (for line, trail, and area marks) or filtered (for other marks).
-        * If ``null``, all data items are included. In this case, invalid values will be
-          interpreted as zeroes.
-    limit : anyOf(float, :class:`ExprRef`)
-        The maximum length of the text mark in pixels. The text value will be automatically
-        truncated if the rendered size exceeds the limit.
-
-        **Default value:** ``0`` -- indicating no limit
-    lineBreak : anyOf(string, :class:`ExprRef`)
-        A delimiter, such as a newline character, upon which to break text strings into
-        multiple lines. This property is ignored if the text is array-valued.
-    lineHeight : anyOf(float, :class:`ExprRef`)
-        The line height in pixels (the spacing between subsequent lines of text) for
-        multi-line text marks.
-    opacity : anyOf(float, :class:`ExprRef`)
-        The overall opacity (value between [0,1]).
-
-        **Default value:** ``0.7`` for non-aggregate plots with ``point``, ``tick``,
-        ``circle``, or ``square`` marks or layered ``bar`` charts and ``1`` otherwise.
-    order : anyOf(None, boolean)
-        For line and trail marks, this ``order`` property can be set to ``null`` or
-        ``false`` to make the lines use the original order in the data sources.
-    orient : :class:`Orientation`
-        The orientation of a non-stacked bar, tick, area, and line charts. The value is
-        either horizontal (default) or vertical.
-
-
-        * For bar, rule and tick, this determines whether the size of the bar and tick
-          should be applied to x or y dimension.
-        * For area, this property determines the orient property of the Vega output.
-        * For line and trail marks, this property determines the sort order of the points in
-          the line if ``config.sortLineBy`` is not specified. For stacked charts, this is
-          always determined by the orientation of the stack; therefore explicitly specified
-          value will be ignored.
-    outerRadius : anyOf(float, :class:`ExprRef`)
-        The outer radius in pixels of arc marks. ``outerRadius`` is an alias for ``radius``.
-
-        **Default value:** ``0``
-    padAngle : anyOf(float, :class:`ExprRef`)
-        The angular padding applied to sides of the arc, in radians.
-    radius : anyOf(float, :class:`ExprRef`)
-        For arc mark, the primary (outer) radius in pixels.
-
-        For text marks, polar coordinate radial offset, in pixels, of the text from the
-        origin determined by the ``x`` and ``y`` properties.
-
-        **Default value:** ``min(plot_width, plot_height)/2``
-    radius2 : anyOf(float, :class:`ExprRef`)
-        The secondary (inner) radius in pixels of arc marks.
-
-        **Default value:** ``0``
-    shape : anyOf(anyOf(:class:`SymbolShape`, string), :class:`ExprRef`)
-        Shape of the point marks. Supported values include:
-
-
-        * plotting shapes: ``"circle"``, ``"square"``, ``"cross"``, ``"diamond"``,
-          ``"triangle-up"``, ``"triangle-down"``, ``"triangle-right"``, or
-          ``"triangle-left"``.
-        * the line symbol ``"stroke"``
-        * centered directional shapes ``"arrow"``, ``"wedge"``, or ``"triangle"``
-        * a custom `SVG path string
-          <https://developer.mozilla.org/en-US/docs/Web/SVG/Tutorial/Paths>`__ (For correct
-          sizing, custom shape paths should be defined within a square bounding box with
-          coordinates ranging from -1 to 1 along both the x and y dimensions.)
-
-        **Default value:** ``"circle"``
-    size : anyOf(float, :class:`ExprRef`)
-        Default size for marks.
-
-
-        * For ``point`` / ``circle`` / ``square``, this represents the pixel area of the
-          marks. Note that this value sets the area of the symbol; the side lengths will
-          increase with the square root of this value.
-        * For ``bar``, this represents the band size of the bar, in pixels.
-        * For ``text``, this represents the font size, in pixels.
-
-        **Default value:**
-
-
-        * ``30`` for point, circle, square marks; width/height's ``step``
-        * ``2`` for bar marks with discrete dimensions;
-        * ``5`` for bar marks with continuous dimensions;
-        * ``11`` for text marks.
-    smooth : anyOf(boolean, :class:`ExprRef`)
-        A boolean flag (default true) indicating if the image should be smoothed when
-        resized. If false, individual pixels should be scaled directly rather than
-        interpolated with smoothing. For SVG rendering, this option may not work in some
-        browsers due to lack of standardization.
-    startAngle : anyOf(float, :class:`ExprRef`)
-        The start angle in radians for arc marks. A value of ``0`` indicates up (north),
-        increasing values proceed clockwise.
-    stroke : anyOf(:class:`Color`, :class:`Gradient`, None, :class:`ExprRef`)
-        Default stroke color. This property has higher precedence than ``config.color``. Set
-        to ``null`` to remove stroke.
-
-        **Default value:** (None)
-    strokeCap : anyOf(:class:`StrokeCap`, :class:`ExprRef`)
-        The stroke cap for line ending style. One of ``"butt"``, ``"round"``, or
-        ``"square"``.
-
-        **Default value:** ``"butt"``
-    strokeDash : anyOf(List(float), :class:`ExprRef`)
-        An array of alternating stroke, space lengths for creating dashed or dotted lines.
-    strokeDashOffset : anyOf(float, :class:`ExprRef`)
-        The offset (in pixels) into which to begin drawing with the stroke dash array.
-    strokeJoin : anyOf(:class:`StrokeJoin`, :class:`ExprRef`)
-        The stroke line join method. One of ``"miter"``, ``"round"`` or ``"bevel"``.
-
-        **Default value:** ``"miter"``
-    strokeMiterLimit : anyOf(float, :class:`ExprRef`)
-        The miter limit at which to bevel a line join.
-    strokeOffset : anyOf(float, :class:`ExprRef`)
-        The offset in pixels at which to draw the group stroke and fill. If unspecified, the
-        default behavior is to dynamically offset stroked groups such that 1 pixel stroke
-        widths align with the pixel grid.
-    strokeOpacity : anyOf(float, :class:`ExprRef`)
-        The stroke opacity (value between [0,1]).
-
-        **Default value:** ``1``
-    strokeWidth : anyOf(float, :class:`ExprRef`)
-        The stroke width, in pixels.
-    tension : anyOf(float, :class:`ExprRef`)
-        Depending on the interpolation type, sets the tension parameter (for line and area
-        marks).
-    text : anyOf(:class:`Text`, :class:`ExprRef`)
-        Placeholder text if the ``text`` channel is not specified
-    theta : anyOf(float, :class:`ExprRef`)
-        For arc marks, the arc length in radians if theta2 is not specified, otherwise the
-        start arc angle. (A value of 0 indicates up or “north”, increasing values proceed
-        clockwise.)
-
-        For text marks, polar coordinate angle in radians.
-    theta2 : anyOf(float, :class:`ExprRef`)
-        The end angle of arc marks in radians. A value of 0 indicates up or “north”,
-        increasing values proceed clockwise.
-    thickness : float
-        Thickness of the tick mark.
-
-        **Default value:**  ``1``
-    timeUnitBandPosition : float
-        Default relative band position for a time unit. If set to ``0``, the marks will be
-        positioned at the beginning of the time unit band step. If set to ``0.5``, the marks
-        will be positioned in the middle of the time unit band step.
-    timeUnitBandSize : float
-        Default relative band size for a time unit. If set to ``1``, the bandwidth of the
-        marks will be equal to the time unit band step. If set to ``0.5``, bandwidth of the
-        marks will be half of the time unit band step.
-    tooltip : anyOf(float, string, boolean, :class:`TooltipContent`, :class:`ExprRef`, None)
-        The tooltip text string to show upon mouse hover or an object defining which fields
-        should the tooltip be derived from.
-
-
-        * If ``tooltip`` is ``true`` or ``{"content": "encoding"}``, then all fields from
-          ``encoding`` will be used.
-        * If ``tooltip`` is ``{"content": "data"}``, then all fields that appear in the
-          highlighted data point will be used.
-        * If set to ``null`` or ``false``, then no tooltip will be used.
-
-        See the `tooltip <https://vega.github.io/vega-lite/docs/tooltip.html>`__
-        documentation for a detailed discussion about tooltip  in Vega-Lite.
-
-        **Default value:** ``null``
-    url : anyOf(:class:`URI`, :class:`ExprRef`)
-        The URL of the image file for image marks.
-    width : anyOf(float, :class:`ExprRef`)
-        Width of the marks.
-    x : anyOf(float, string, :class:`ExprRef`)
-        X coordinates of the marks, or width of horizontal ``"bar"`` and ``"area"`` without
-        specified ``x2`` or ``width``.
-
-        The ``value`` of this channel can be a number or a string ``"width"`` for the width
-        of the plot.
-    x2 : anyOf(float, string, :class:`ExprRef`)
-        X2 coordinates for ranged ``"area"``, ``"bar"``, ``"rect"``, and  ``"rule"``.
-
-        The ``value`` of this channel can be a number or a string ``"width"`` for the width
-        of the plot.
-    y : anyOf(float, string, :class:`ExprRef`)
-        Y coordinates of the marks, or height of vertical ``"bar"`` and ``"area"`` without
-        specified ``y2`` or ``height``.
-
-        The ``value`` of this channel can be a number or a string ``"height"`` for the
-        height of the plot.
-    y2 : anyOf(float, string, :class:`ExprRef`)
-        Y2 coordinates for ranged ``"area"``, ``"bar"``, ``"rect"``, and  ``"rule"``.
-
-        The ``value`` of this channel can be a number or a string ``"height"`` for the
-        height of the plot.
-    """
-    _schema = {'$ref': '#/definitions/TickConfig'}
-
-    def __init__(self, align=Undefined, angle=Undefined, aria=Undefined, ariaRole=Undefined,
-                 ariaRoleDescription=Undefined, aspect=Undefined, bandSize=Undefined,
-                 baseline=Undefined, blend=Undefined, color=Undefined, cornerRadius=Undefined,
-                 cornerRadiusBottomLeft=Undefined, cornerRadiusBottomRight=Undefined,
-                 cornerRadiusTopLeft=Undefined, cornerRadiusTopRight=Undefined, cursor=Undefined,
-                 description=Undefined, dir=Undefined, dx=Undefined, dy=Undefined, ellipsis=Undefined,
-                 endAngle=Undefined, fill=Undefined, fillOpacity=Undefined, filled=Undefined,
-                 font=Undefined, fontSize=Undefined, fontStyle=Undefined, fontWeight=Undefined,
-                 height=Undefined, href=Undefined, innerRadius=Undefined, interpolate=Undefined,
-                 invalid=Undefined, limit=Undefined, lineBreak=Undefined, lineHeight=Undefined,
-                 opacity=Undefined, order=Undefined, orient=Undefined, outerRadius=Undefined,
-                 padAngle=Undefined, radius=Undefined, radius2=Undefined, shape=Undefined,
-                 size=Undefined, smooth=Undefined, startAngle=Undefined, stroke=Undefined,
-                 strokeCap=Undefined, strokeDash=Undefined, strokeDashOffset=Undefined,
-                 strokeJoin=Undefined, strokeMiterLimit=Undefined, strokeOffset=Undefined,
-                 strokeOpacity=Undefined, strokeWidth=Undefined, tension=Undefined, text=Undefined,
-                 theta=Undefined, theta2=Undefined, thickness=Undefined, timeUnitBandPosition=Undefined,
-                 timeUnitBandSize=Undefined, tooltip=Undefined, url=Undefined, width=Undefined,
-                 x=Undefined, x2=Undefined, y=Undefined, y2=Undefined, **kwds):
-        super(TickConfig, self).__init__(align=align, angle=angle, aria=aria, ariaRole=ariaRole,
-                                         ariaRoleDescription=ariaRoleDescription, aspect=aspect,
-                                         bandSize=bandSize, baseline=baseline, blend=blend, color=color,
-                                         cornerRadius=cornerRadius,
-                                         cornerRadiusBottomLeft=cornerRadiusBottomLeft,
-                                         cornerRadiusBottomRight=cornerRadiusBottomRight,
-                                         cornerRadiusTopLeft=cornerRadiusTopLeft,
-                                         cornerRadiusTopRight=cornerRadiusTopRight, cursor=cursor,
-                                         description=description, dir=dir, dx=dx, dy=dy,
-                                         ellipsis=ellipsis, endAngle=endAngle, fill=fill,
-                                         fillOpacity=fillOpacity, filled=filled, font=font,
-                                         fontSize=fontSize, fontStyle=fontStyle, fontWeight=fontWeight,
-                                         height=height, href=href, innerRadius=innerRadius,
-                                         interpolate=interpolate, invalid=invalid, limit=limit,
-                                         lineBreak=lineBreak, lineHeight=lineHeight, opacity=opacity,
-                                         order=order, orient=orient, outerRadius=outerRadius,
-                                         padAngle=padAngle, radius=radius, radius2=radius2, shape=shape,
-                                         size=size, smooth=smooth, startAngle=startAngle, stroke=stroke,
-                                         strokeCap=strokeCap, strokeDash=strokeDash,
-                                         strokeDashOffset=strokeDashOffset, strokeJoin=strokeJoin,
-                                         strokeMiterLimit=strokeMiterLimit, strokeOffset=strokeOffset,
-                                         strokeOpacity=strokeOpacity, strokeWidth=strokeWidth,
-                                         tension=tension, text=text, theta=theta, theta2=theta2,
-                                         thickness=thickness, timeUnitBandPosition=timeUnitBandPosition,
-                                         timeUnitBandSize=timeUnitBandSize, tooltip=tooltip, url=url,
-                                         width=width, x=x, x2=x2, y=y, y2=y2, **kwds)
-
-
-class TickCount(VegaLiteSchema):
-    """TickCount schema wrapper
-
-    anyOf(float, :class:`TimeInterval`, :class:`TimeIntervalStep`)
-    """
-    _schema = {'$ref': '#/definitions/TickCount'}
-
-    def __init__(self, *args, **kwds):
-        super(TickCount, self).__init__(*args, **kwds)
-
-
-class TimeInterval(TickCount):
-    """TimeInterval schema wrapper
-
-    enum('millisecond', 'second', 'minute', 'hour', 'day', 'week', 'month', 'year')
-    """
-    _schema = {'$ref': '#/definitions/TimeInterval'}
-
-    def __init__(self, *args):
-        super(TimeInterval, self).__init__(*args)
-
-
-class TimeIntervalStep(TickCount):
-    """TimeIntervalStep schema wrapper
-
-    Mapping(required=[interval, step])
-
-    Parameters
-    ----------
-
-    interval : :class:`TimeInterval`
-
-    step : float
-
-    """
-    _schema = {'$ref': '#/definitions/TimeIntervalStep'}
-
-    def __init__(self, interval=Undefined, step=Undefined, **kwds):
-        super(TimeIntervalStep, self).__init__(interval=interval, step=step, **kwds)
-
-
-class TimeLocale(VegaLiteSchema):
-    """TimeLocale schema wrapper
-
-    Mapping(required=[dateTime, date, time, periods, days, shortDays, months, shortMonths])
-    Locale definition for formatting dates and times.
-
-    Parameters
-    ----------
-
-    date : string
-        The date (%x) format specifier (e.g., "%m/%d/%Y").
-    dateTime : string
-        The date and time (%c) format specifier (e.g., "%a %b %e %X %Y").
-    days : :class:`Vector7string`
-        The full names of the weekdays, starting with Sunday.
-    months : :class:`Vector12string`
-        The full names of the months (starting with January).
-    periods : :class:`Vector2string`
-        The A.M. and P.M. equivalents (e.g., ["AM", "PM"]).
-    shortDays : :class:`Vector7string`
-        The abbreviated names of the weekdays, starting with Sunday.
-    shortMonths : :class:`Vector12string`
-        The abbreviated names of the months (starting with January).
-    time : string
-        The time (%X) format specifier (e.g., "%H:%M:%S").
-    """
-    _schema = {'$ref': '#/definitions/TimeLocale'}
-
-    def __init__(self, date=Undefined, dateTime=Undefined, days=Undefined, months=Undefined,
-                 periods=Undefined, shortDays=Undefined, shortMonths=Undefined, time=Undefined, **kwds):
-        super(TimeLocale, self).__init__(date=date, dateTime=dateTime, days=days, months=months,
-                                         periods=periods, shortDays=shortDays, shortMonths=shortMonths,
-                                         time=time, **kwds)
-
-
-class TimeUnit(VegaLiteSchema):
-    """TimeUnit schema wrapper
-
-    anyOf(:class:`SingleTimeUnit`, :class:`MultiTimeUnit`)
-    """
-    _schema = {'$ref': '#/definitions/TimeUnit'}
-
-    def __init__(self, *args, **kwds):
-        super(TimeUnit, self).__init__(*args, **kwds)
-
-
-class MultiTimeUnit(TimeUnit):
-    """MultiTimeUnit schema wrapper
-
-    anyOf(:class:`LocalMultiTimeUnit`, :class:`UtcMultiTimeUnit`)
-    """
-    _schema = {'$ref': '#/definitions/MultiTimeUnit'}
-
-    def __init__(self, *args, **kwds):
-        super(MultiTimeUnit, self).__init__(*args, **kwds)
-
-
-class LocalMultiTimeUnit(MultiTimeUnit):
-    """LocalMultiTimeUnit schema wrapper
-
-    enum('yearquarter', 'yearquartermonth', 'yearmonth', 'yearmonthdate', 'yearmonthdatehours',
-    'yearmonthdatehoursminutes', 'yearmonthdatehoursminutesseconds', 'yearweek', 'yearweekday',
-    'yearweekdayhours', 'yearweekdayhoursminutes', 'yearweekdayhoursminutesseconds',
-    'yeardayofyear', 'quartermonth', 'monthdate', 'monthdatehours', 'monthdatehoursminutes',
-    'monthdatehoursminutesseconds', 'weekday', 'weeksdayhours', 'weekdayhoursminutes',
-    'weekdayhoursminutesseconds', 'dayhours', 'dayhoursminutes', 'dayhoursminutesseconds',
-    'hoursminutes', 'hoursminutesseconds', 'minutesseconds', 'secondsmilliseconds')
-    """
-    _schema = {'$ref': '#/definitions/LocalMultiTimeUnit'}
-
-    def __init__(self, *args):
-        super(LocalMultiTimeUnit, self).__init__(*args)
-
-
-class SingleTimeUnit(TimeUnit):
-    """SingleTimeUnit schema wrapper
-
-    anyOf(:class:`LocalSingleTimeUnit`, :class:`UtcSingleTimeUnit`)
-    """
-    _schema = {'$ref': '#/definitions/SingleTimeUnit'}
-
-    def __init__(self, *args, **kwds):
-        super(SingleTimeUnit, self).__init__(*args, **kwds)
-
-
-class LocalSingleTimeUnit(SingleTimeUnit):
-    """LocalSingleTimeUnit schema wrapper
-
-    enum('year', 'quarter', 'month', 'week', 'day', 'dayofyear', 'date', 'hours', 'minutes',
-    'seconds', 'milliseconds')
-    """
-    _schema = {'$ref': '#/definitions/LocalSingleTimeUnit'}
-
-    def __init__(self, *args):
-        super(LocalSingleTimeUnit, self).__init__(*args)
-
-
-class TimeUnitParams(VegaLiteSchema):
-    """TimeUnitParams schema wrapper
-
-    Mapping(required=[])
-    Time Unit Params for encoding predicate, which can specified if the data is  already
-    "binned".
-
-    Parameters
-    ----------
-
-    binned : boolean
-        Whether the data has already been binned to this time unit. If true, Vega-Lite will
-        only format the data, marks, and guides, without applying the timeUnit transform to
-        re-bin the data again.
-    maxbins : float
-        If no ``unit`` is specified, maxbins is used to infer time units.
-    step : float
-        The number of steps between bins, in terms of the least significant unit provided.
-    unit : :class:`TimeUnit`
-        Defines how date-time values should be binned.
-    utc : boolean
-        True to use UTC timezone. Equivalent to using a ``utc`` prefixed ``TimeUnit``.
-    """
-    _schema = {'$ref': '#/definitions/TimeUnitParams'}
-
-    def __init__(self, binned=Undefined, maxbins=Undefined, step=Undefined, unit=Undefined,
-                 utc=Undefined, **kwds):
-        super(TimeUnitParams, self).__init__(binned=binned, maxbins=maxbins, step=step, unit=unit,
-                                             utc=utc, **kwds)
-
-
-class TimeUnitTransformParams(VegaLiteSchema):
-    """TimeUnitTransformParams schema wrapper
-
-    Mapping(required=[])
-
-    Parameters
-    ----------
-
-    maxbins : float
-        If no ``unit`` is specified, maxbins is used to infer time units.
-    step : float
-        The number of steps between bins, in terms of the least significant unit provided.
-    unit : :class:`TimeUnit`
-        Defines how date-time values should be binned.
-    utc : boolean
-        True to use UTC timezone. Equivalent to using a ``utc`` prefixed ``TimeUnit``.
-    """
-    _schema = {'$ref': '#/definitions/TimeUnitTransformParams'}
-
-    def __init__(self, maxbins=Undefined, step=Undefined, unit=Undefined, utc=Undefined, **kwds):
-        super(TimeUnitTransformParams, self).__init__(maxbins=maxbins, step=step, unit=unit, utc=utc,
-                                                      **kwds)
-
-
-class TitleAnchor(VegaLiteSchema):
-    """TitleAnchor schema wrapper
-
-    enum(None, 'start', 'middle', 'end')
-    """
-    _schema = {'$ref': '#/definitions/TitleAnchor'}
-
-    def __init__(self, *args):
-        super(TitleAnchor, self).__init__(*args)
-
-
-class TitleConfig(VegaLiteSchema):
-    """TitleConfig schema wrapper
-
-    Mapping(required=[])
-
-    Parameters
-    ----------
-
-    align : :class:`Align`
-        Horizontal text alignment for title text. One of ``"left"``, ``"center"``, or
-        ``"right"``.
-    anchor : anyOf(:class:`TitleAnchor`, :class:`ExprRef`)
-        The anchor position for placing the title and subtitle text. One of ``"start"``,
-        ``"middle"``, or ``"end"``. For example, with an orientation of top these anchor
-        positions map to a left-, center-, or right-aligned title.
-    angle : anyOf(float, :class:`ExprRef`)
-        Angle in degrees of title and subtitle text.
-    aria : anyOf(boolean, :class:`ExprRef`)
-        A boolean flag indicating if `ARIA attributes
-        <https://developer.mozilla.org/en-US/docs/Web/Accessibility/ARIA>`__ should be
-        included (SVG output only). If ``false``, the "aria-hidden" attribute will be set on
-        the output SVG group, removing the title from the ARIA accessibility tree.
-
-        **Default value:** ``true``
-    baseline : :class:`TextBaseline`
-        Vertical text baseline for title and subtitle text. One of ``"alphabetic"``
-        (default), ``"top"``, ``"middle"``, ``"bottom"``, ``"line-top"``, or
-        ``"line-bottom"``. The ``"line-top"`` and ``"line-bottom"`` values operate similarly
-        to ``"top"`` and ``"bottom"``, but are calculated relative to the *lineHeight*
-        rather than *fontSize* alone.
-    color : anyOf(anyOf(None, :class:`Color`), :class:`ExprRef`)
-        Text color for title text.
-    dx : anyOf(float, :class:`ExprRef`)
-        Delta offset for title and subtitle text x-coordinate.
-    dy : anyOf(float, :class:`ExprRef`)
-        Delta offset for title and subtitle text y-coordinate.
-    font : anyOf(string, :class:`ExprRef`)
-        Font name for title text.
-    fontSize : anyOf(float, :class:`ExprRef`)
-        Font size in pixels for title text.
-    fontStyle : anyOf(:class:`FontStyle`, :class:`ExprRef`)
-        Font style for title text.
-    fontWeight : anyOf(:class:`FontWeight`, :class:`ExprRef`)
-        Font weight for title text. This can be either a string (e.g ``"bold"``,
-        ``"normal"`` ) or a number ( ``100``, ``200``, ``300``, ..., ``900`` where
-        ``"normal"`` = ``400`` and ``"bold"`` = ``700`` ).
-    frame : anyOf(anyOf(:class:`TitleFrame`, string), :class:`ExprRef`)
-        The reference frame for the anchor position, one of ``"bounds"`` (to anchor relative
-        to the full bounding box) or ``"group"`` (to anchor relative to the group width or
-        height).
-    limit : anyOf(float, :class:`ExprRef`)
-        The maximum allowed length in pixels of title and subtitle text.
-    lineHeight : anyOf(float, :class:`ExprRef`)
-        Line height in pixels for multi-line title text or title text with ``"line-top"`` or
-        ``"line-bottom"`` baseline.
-    offset : anyOf(float, :class:`ExprRef`)
-        The orthogonal offset in pixels by which to displace the title group from its
-        position along the edge of the chart.
-    orient : anyOf(:class:`TitleOrient`, :class:`ExprRef`)
-        Default title orientation ( ``"top"``, ``"bottom"``, ``"left"``, or ``"right"`` )
-    subtitleColor : anyOf(anyOf(None, :class:`Color`), :class:`ExprRef`)
-        Text color for subtitle text.
-    subtitleFont : anyOf(string, :class:`ExprRef`)
-        Font name for subtitle text.
-    subtitleFontSize : anyOf(float, :class:`ExprRef`)
-        Font size in pixels for subtitle text.
-    subtitleFontStyle : anyOf(:class:`FontStyle`, :class:`ExprRef`)
-        Font style for subtitle text.
-    subtitleFontWeight : anyOf(:class:`FontWeight`, :class:`ExprRef`)
-        Font weight for subtitle text. This can be either a string (e.g ``"bold"``,
-        ``"normal"`` ) or a number ( ``100``, ``200``, ``300``, ..., ``900`` where
-        ``"normal"`` = ``400`` and ``"bold"`` = ``700`` ).
-    subtitleLineHeight : anyOf(float, :class:`ExprRef`)
-        Line height in pixels for multi-line subtitle text.
-    subtitlePadding : anyOf(float, :class:`ExprRef`)
-        The padding in pixels between title and subtitle text.
-    zindex : anyOf(float, :class:`ExprRef`)
-        The integer z-index indicating the layering of the title group relative to other
-        axis, mark, and legend groups.
-
-        **Default value:** ``0``.
-    """
-    _schema = {'$ref': '#/definitions/TitleConfig'}
-
-    def __init__(self, align=Undefined, anchor=Undefined, angle=Undefined, aria=Undefined,
-                 baseline=Undefined, color=Undefined, dx=Undefined, dy=Undefined, font=Undefined,
-                 fontSize=Undefined, fontStyle=Undefined, fontWeight=Undefined, frame=Undefined,
-                 limit=Undefined, lineHeight=Undefined, offset=Undefined, orient=Undefined,
-                 subtitleColor=Undefined, subtitleFont=Undefined, subtitleFontSize=Undefined,
-                 subtitleFontStyle=Undefined, subtitleFontWeight=Undefined,
-                 subtitleLineHeight=Undefined, subtitlePadding=Undefined, zindex=Undefined, **kwds):
-        super(TitleConfig, self).__init__(align=align, anchor=anchor, angle=angle, aria=aria,
-                                          baseline=baseline, color=color, dx=dx, dy=dy, font=font,
-                                          fontSize=fontSize, fontStyle=fontStyle, fontWeight=fontWeight,
-                                          frame=frame, limit=limit, lineHeight=lineHeight,
-                                          offset=offset, orient=orient, subtitleColor=subtitleColor,
-                                          subtitleFont=subtitleFont, subtitleFontSize=subtitleFontSize,
-                                          subtitleFontStyle=subtitleFontStyle,
-                                          subtitleFontWeight=subtitleFontWeight,
-                                          subtitleLineHeight=subtitleLineHeight,
-                                          subtitlePadding=subtitlePadding, zindex=zindex, **kwds)
-
-
-class TitleFrame(VegaLiteSchema):
-    """TitleFrame schema wrapper
-
-    enum('bounds', 'group')
-    """
-    _schema = {'$ref': '#/definitions/TitleFrame'}
-
-    def __init__(self, *args):
-        super(TitleFrame, self).__init__(*args)
-
-
-class TitleOrient(VegaLiteSchema):
-    """TitleOrient schema wrapper
-
-    enum('none', 'left', 'right', 'top', 'bottom')
-    """
-    _schema = {'$ref': '#/definitions/TitleOrient'}
-
-    def __init__(self, *args):
-        super(TitleOrient, self).__init__(*args)
-
-
-class TitleParams(VegaLiteSchema):
-    """TitleParams schema wrapper
-
-    Mapping(required=[text])
-
-    Parameters
-    ----------
-
-    text : anyOf(:class:`Text`, :class:`ExprRef`)
-        The title text.
-    align : :class:`Align`
-        Horizontal text alignment for title text. One of ``"left"``, ``"center"``, or
-        ``"right"``.
-    anchor : :class:`TitleAnchor`
-        The anchor position for placing the title. One of ``"start"``, ``"middle"``, or
-        ``"end"``. For example, with an orientation of top these anchor positions map to a
-        left-, center-, or right-aligned title.
-
-        **Default value:** ``"middle"`` for `single
-        <https://vega.github.io/vega-lite/docs/spec.html>`__ and `layered
-        <https://vega.github.io/vega-lite/docs/layer.html>`__ views. ``"start"`` for other
-        composite views.
-
-        **Note:** `For now <https://github.com/vega/vega-lite/issues/2875>`__, ``anchor`` is
-        only customizable only for `single
-        <https://vega.github.io/vega-lite/docs/spec.html>`__ and `layered
-        <https://vega.github.io/vega-lite/docs/layer.html>`__ views. For other composite
-        views, ``anchor`` is always ``"start"``.
-    angle : anyOf(float, :class:`ExprRef`)
-        Angle in degrees of title and subtitle text.
-    aria : anyOf(boolean, :class:`ExprRef`)
-        A boolean flag indicating if `ARIA attributes
-        <https://developer.mozilla.org/en-US/docs/Web/Accessibility/ARIA>`__ should be
-        included (SVG output only). If ``false``, the "aria-hidden" attribute will be set on
-        the output SVG group, removing the title from the ARIA accessibility tree.
-
-        **Default value:** ``true``
-    baseline : :class:`TextBaseline`
-        Vertical text baseline for title and subtitle text. One of ``"alphabetic"``
-        (default), ``"top"``, ``"middle"``, ``"bottom"``, ``"line-top"``, or
-        ``"line-bottom"``. The ``"line-top"`` and ``"line-bottom"`` values operate similarly
-        to ``"top"`` and ``"bottom"``, but are calculated relative to the *lineHeight*
-        rather than *fontSize* alone.
-    color : anyOf(anyOf(None, :class:`Color`), :class:`ExprRef`)
-        Text color for title text.
-    dx : anyOf(float, :class:`ExprRef`)
-        Delta offset for title and subtitle text x-coordinate.
-    dy : anyOf(float, :class:`ExprRef`)
-        Delta offset for title and subtitle text y-coordinate.
-    font : anyOf(string, :class:`ExprRef`)
-        Font name for title text.
-    fontSize : anyOf(float, :class:`ExprRef`)
-        Font size in pixels for title text.
-    fontStyle : anyOf(:class:`FontStyle`, :class:`ExprRef`)
-        Font style for title text.
-    fontWeight : anyOf(:class:`FontWeight`, :class:`ExprRef`)
-        Font weight for title text. This can be either a string (e.g ``"bold"``,
-        ``"normal"`` ) or a number ( ``100``, ``200``, ``300``, ..., ``900`` where
-        ``"normal"`` = ``400`` and ``"bold"`` = ``700`` ).
-    frame : anyOf(anyOf(:class:`TitleFrame`, string), :class:`ExprRef`)
-        The reference frame for the anchor position, one of ``"bounds"`` (to anchor relative
-        to the full bounding box) or ``"group"`` (to anchor relative to the group width or
-        height).
-    limit : anyOf(float, :class:`ExprRef`)
-        The maximum allowed length in pixels of title and subtitle text.
-    lineHeight : anyOf(float, :class:`ExprRef`)
-        Line height in pixels for multi-line title text or title text with ``"line-top"`` or
-        ``"line-bottom"`` baseline.
-    offset : anyOf(float, :class:`ExprRef`)
-        The orthogonal offset in pixels by which to displace the title group from its
-        position along the edge of the chart.
-    orient : anyOf(:class:`TitleOrient`, :class:`ExprRef`)
-        Default title orientation ( ``"top"``, ``"bottom"``, ``"left"``, or ``"right"`` )
-    style : anyOf(string, List(string))
-        A `mark style property <https://vega.github.io/vega-lite/docs/config.html#style>`__
-        to apply to the title text mark.
-
-        **Default value:** ``"group-title"``.
-    subtitle : :class:`Text`
-        The subtitle Text.
-    subtitleColor : anyOf(anyOf(None, :class:`Color`), :class:`ExprRef`)
-        Text color for subtitle text.
-    subtitleFont : anyOf(string, :class:`ExprRef`)
-        Font name for subtitle text.
-    subtitleFontSize : anyOf(float, :class:`ExprRef`)
-        Font size in pixels for subtitle text.
-    subtitleFontStyle : anyOf(:class:`FontStyle`, :class:`ExprRef`)
-        Font style for subtitle text.
-    subtitleFontWeight : anyOf(:class:`FontWeight`, :class:`ExprRef`)
-        Font weight for subtitle text. This can be either a string (e.g ``"bold"``,
-        ``"normal"`` ) or a number ( ``100``, ``200``, ``300``, ..., ``900`` where
-        ``"normal"`` = ``400`` and ``"bold"`` = ``700`` ).
-    subtitleLineHeight : anyOf(float, :class:`ExprRef`)
-        Line height in pixels for multi-line subtitle text.
-    subtitlePadding : anyOf(float, :class:`ExprRef`)
-        The padding in pixels between title and subtitle text.
-    zindex : float
-        The integer z-index indicating the layering of the title group relative to other
-        axis, mark and legend groups.
-
-        **Default value:** ``0``.
-    """
-    _schema = {'$ref': '#/definitions/TitleParams'}
-
-    def __init__(self, text=Undefined, align=Undefined, anchor=Undefined, angle=Undefined,
-                 aria=Undefined, baseline=Undefined, color=Undefined, dx=Undefined, dy=Undefined,
-                 font=Undefined, fontSize=Undefined, fontStyle=Undefined, fontWeight=Undefined,
-                 frame=Undefined, limit=Undefined, lineHeight=Undefined, offset=Undefined,
-                 orient=Undefined, style=Undefined, subtitle=Undefined, subtitleColor=Undefined,
-                 subtitleFont=Undefined, subtitleFontSize=Undefined, subtitleFontStyle=Undefined,
-                 subtitleFontWeight=Undefined, subtitleLineHeight=Undefined, subtitlePadding=Undefined,
-                 zindex=Undefined, **kwds):
-        super(TitleParams, self).__init__(text=text, align=align, anchor=anchor, angle=angle, aria=aria,
-                                          baseline=baseline, color=color, dx=dx, dy=dy, font=font,
-                                          fontSize=fontSize, fontStyle=fontStyle, fontWeight=fontWeight,
-                                          frame=frame, limit=limit, lineHeight=lineHeight,
-                                          offset=offset, orient=orient, style=style, subtitle=subtitle,
-                                          subtitleColor=subtitleColor, subtitleFont=subtitleFont,
-                                          subtitleFontSize=subtitleFontSize,
-                                          subtitleFontStyle=subtitleFontStyle,
-                                          subtitleFontWeight=subtitleFontWeight,
-                                          subtitleLineHeight=subtitleLineHeight,
-                                          subtitlePadding=subtitlePadding, zindex=zindex, **kwds)
-
-
-class TooltipContent(VegaLiteSchema):
-    """TooltipContent schema wrapper
-
-    Mapping(required=[content])
-
-    Parameters
-    ----------
-
-    content : enum('encoding', 'data')
-
-    """
-    _schema = {'$ref': '#/definitions/TooltipContent'}
-
-    def __init__(self, content=Undefined, **kwds):
-        super(TooltipContent, self).__init__(content=content, **kwds)
-
-
-class TopLevelParameter(VegaLiteSchema):
-    """TopLevelParameter schema wrapper
-
-    anyOf(:class:`VariableParameter`, :class:`TopLevelSelectionParameter`)
-    """
-    _schema = {'$ref': '#/definitions/TopLevelParameter'}
-
-    def __init__(self, *args, **kwds):
-        super(TopLevelParameter, self).__init__(*args, **kwds)
-
-
-class TopLevelSelectionParameter(TopLevelParameter):
-    """TopLevelSelectionParameter schema wrapper
-
-    Mapping(required=[name, select])
-
-    Parameters
-    ----------
-
-    name : :class:`ParameterName`
-        Required. A unique name for the selection parameter. Selection names should be valid
-        JavaScript identifiers: they should contain only alphanumeric characters (or "$", or
-        "_") and may not start with a digit. Reserved keywords that may not be used as
-        parameter names are "datum", "event", "item", and "parent".
-    select : anyOf(:class:`SelectionType`, :class:`PointSelectionConfig`, :class:`IntervalSelectionConfig`)
-        Determines the default event processing and data query for the selection. Vega-Lite
-        currently supports two selection types:
-
-
-        * ``"point"`` -- to select multiple discrete data values; the first value is
-          selected on ``click`` and additional values toggled on shift-click.
-        * ``"interval"`` -- to select a continuous range of data values on ``drag``.
-    bind : anyOf(:class:`Binding`, Mapping(required=[]), :class:`LegendBinding`, string)
-        When set, a selection is populated by input elements (also known as dynamic query
-        widgets) or by interacting with the corresponding legend. Direct manipulation
-        interaction is disabled by default; to re-enable it, set the selection's `on
-        <https://vega.github.io/vega-lite/docs/selection.html#common-selection-properties>`__
-        property.
-
-        Legend bindings are restricted to selections that only specify a single field or
-        encoding.
-
-        Query widget binding takes the form of Vega's `input element binding definition
-        <https://vega.github.io/vega/docs/signals/#bind>`__ or can be a mapping between
-        projected field/encodings and binding definitions.
-
-        **See also:** `bind <https://vega.github.io/vega-lite/docs/bind.html>`__
-        documentation.
-    value : anyOf(:class:`SelectionInit`, List(:class:`SelectionInitMapping`), :class:`SelectionInitIntervalMapping`)
-        Initialize the selection with a mapping between `projected channels or field names
-        <https://vega.github.io/vega-lite/docs/selection.html#project>`__ and initial
-        values.
-
-        **See also:** `init <https://vega.github.io/vega-lite/docs/value.html>`__
-        documentation.
-    views : List(string)
-        By default, top-level selections are applied to every view in the visualization. If
-        this property is specified, selections will only be applied to views with the given
-        names.
-    """
-    _schema = {'$ref': '#/definitions/TopLevelSelectionParameter'}
-
-    def __init__(self, name=Undefined, select=Undefined, bind=Undefined, value=Undefined,
-                 views=Undefined, **kwds):
-        super(TopLevelSelectionParameter, self).__init__(name=name, select=select, bind=bind,
-                                                         value=value, views=views, **kwds)
-
-
-class TopLevelSpec(VegaLiteSchema):
-    """TopLevelSpec schema wrapper
-
-    anyOf(:class:`TopLevelUnitSpec`, :class:`TopLevelFacetSpec`, :class:`TopLevelLayerSpec`,
-    :class:`TopLevelRepeatSpec`, :class:`TopLevelConcatSpec`, :class:`TopLevelVConcatSpec`,
-    :class:`TopLevelHConcatSpec`)
-    A Vega-Lite top-level specification. This is the root class for all Vega-Lite
-    specifications. (The json schema is generated from this type.)
-    """
-    _schema = {'$ref': '#/definitions/TopLevelSpec'}
-
-    def __init__(self, *args, **kwds):
-        super(TopLevelSpec, self).__init__(*args, **kwds)
-
-
-class TopLevelConcatSpec(TopLevelSpec):
-    """TopLevelConcatSpec schema wrapper
-
-    Mapping(required=[concat])
-
-    Parameters
-    ----------
-
-    concat : List(:class:`NonNormalizedSpec`)
-        A list of views to be concatenated.
-    align : anyOf(:class:`LayoutAlign`, :class:`RowColLayoutAlign`)
-        The alignment to apply to grid rows and columns. The supported string values are
-        ``"all"``, ``"each"``, and ``"none"``.
-
-
-        * For ``"none"``, a flow layout will be used, in which adjacent subviews are simply
-          placed one after the other.
-        * For ``"each"``, subviews will be aligned into a clean grid structure, but each row
-          or column may be of variable size.
-        * For ``"all"``, subviews will be aligned and each row or column will be sized
-          identically based on the maximum observed size. String values for this property
-          will be applied to both grid rows and columns.
-
-        Alternatively, an object value of the form ``{"row": string, "column": string}`` can
-        be used to supply different alignments for rows and columns.
-
-        **Default value:** ``"all"``.
-    autosize : anyOf(:class:`AutosizeType`, :class:`AutoSizeParams`)
-        How the visualization size should be determined. If a string, should be one of
-        ``"pad"``, ``"fit"`` or ``"none"``. Object values can additionally specify
-        parameters for content sizing and automatic resizing.
-
-        **Default value** : ``pad``
-    background : anyOf(:class:`Color`, :class:`ExprRef`)
-        CSS color property to use as the background of the entire view.
-
-        **Default value:** ``"white"``
-    bounds : enum('full', 'flush')
-        The bounds calculation method to use for determining the extent of a sub-plot. One
-        of ``full`` (the default) or ``flush``.
-
-
-        * If set to ``full``, the entire calculated bounds (including axes, title, and
-          legend) will be used.
-        * If set to ``flush``, only the specified width and height values for the sub-view
-          will be used. The ``flush`` setting can be useful when attempting to place
-          sub-plots without axes or legends into a uniform grid structure.
-
-        **Default value:** ``"full"``
-    center : anyOf(boolean, :class:`RowColboolean`)
-        Boolean flag indicating if subviews should be centered relative to their respective
-        rows or columns.
-
-        An object value of the form ``{"row": boolean, "column": boolean}`` can be used to
-        supply different centering values for rows and columns.
-
-        **Default value:** ``false``
-    columns : float
-        The number of columns to include in the view composition layout.
-
-        **Default value** : ``undefined`` -- An infinite number of columns (a single row)
-        will be assumed. This is equivalent to ``hconcat`` (for ``concat`` ) and to using
-        the ``column`` channel (for ``facet`` and ``repeat`` ).
-
-        **Note** :
-
-        1) This property is only for:
-
-
-        * the general (wrappable) ``concat`` operator (not ``hconcat`` / ``vconcat`` )
-        * the ``facet`` and ``repeat`` operator with one field/repetition definition
-          (without row/column nesting)
-
-        2) Setting the ``columns`` to ``1`` is equivalent to ``vconcat`` (for ``concat`` )
-        and to using the ``row`` channel (for ``facet`` and ``repeat`` ).
-    config : :class:`Config`
-        Vega-Lite configuration object. This property can only be defined at the top-level
-        of a specification.
-    data : anyOf(:class:`Data`, None)
-        An object describing the data source. Set to ``null`` to ignore the parent's data
-        source. If no data is set, it is derived from the parent.
-    datasets : :class:`Datasets`
-        A global data store for named datasets. This is a mapping from names to inline
-        datasets. This can be an array of objects or primitive values or a string. Arrays of
-        primitive values are ingested as objects with a ``data`` property.
-    description : string
-        Description of this mark for commenting purpose.
-    name : string
-        Name of the visualization for later reference.
-    padding : anyOf(:class:`Padding`, :class:`ExprRef`)
-        The default visualization padding, in pixels, from the edge of the visualization
-        canvas to the data rectangle. If a number, specifies padding for all sides. If an
-        object, the value should have the format ``{"left": 5, "top": 5, "right": 5,
-        "bottom": 5}`` to specify padding for each side of the visualization.
-
-        **Default value** : ``5``
-    params : List(:class:`TopLevelParameter`)
-        Dynamic variables or selections that parameterize a visualization.
-    resolve : :class:`Resolve`
-        Scale, axis, and legend resolutions for view composition specifications.
-    spacing : anyOf(float, :class:`RowColnumber`)
-        The spacing in pixels between sub-views of the composition operator. An object of
-        the form ``{"row": number, "column": number}`` can be used to set different spacing
-        values for rows and columns.
-
-        **Default value** : Depends on ``"spacing"`` property of `the view composition
-        configuration <https://vega.github.io/vega-lite/docs/config.html#view-config>`__ (
-        ``20`` by default)
-    title : anyOf(:class:`Text`, :class:`TitleParams`)
-        Title for the plot.
-    transform : List(:class:`Transform`)
-        An array of data transformations such as filter and new field calculation.
-    usermeta : :class:`Dict`
-        Optional metadata that will be passed to Vega. This object is completely ignored by
-        Vega and Vega-Lite and can be used for custom metadata.
-    $schema : string
-        URL to `JSON schema <http://json-schema.org/>`__ for a Vega-Lite specification.
-        Unless you have a reason to change this, use
-        ``https://vega.github.io/schema/vega-lite/v5.json``. Setting the ``$schema``
-        property allows automatic validation and autocomplete in editors that support JSON
-        schema.
-    """
-    _schema = {'$ref': '#/definitions/TopLevelConcatSpec'}
-
-    def __init__(self, concat=Undefined, align=Undefined, autosize=Undefined, background=Undefined,
-                 bounds=Undefined, center=Undefined, columns=Undefined, config=Undefined,
-                 data=Undefined, datasets=Undefined, description=Undefined, name=Undefined,
-                 padding=Undefined, params=Undefined, resolve=Undefined, spacing=Undefined,
-                 title=Undefined, transform=Undefined, usermeta=Undefined, **kwds):
-        super(TopLevelConcatSpec, self).__init__(concat=concat, align=align, autosize=autosize,
-                                                 background=background, bounds=bounds, center=center,
-                                                 columns=columns, config=config, data=data,
-                                                 datasets=datasets, description=description, name=name,
-                                                 padding=padding, params=params, resolve=resolve,
-                                                 spacing=spacing, title=title, transform=transform,
-                                                 usermeta=usermeta, **kwds)
-
-
-class TopLevelFacetSpec(TopLevelSpec):
-    """TopLevelFacetSpec schema wrapper
-
-    Mapping(required=[data, facet, spec])
-
-    Parameters
-    ----------
-
-    data : anyOf(:class:`Data`, None)
-        An object describing the data source. Set to ``null`` to ignore the parent's data
-        source. If no data is set, it is derived from the parent.
-    facet : anyOf(:class:`FacetFieldDef`, :class:`FacetMapping`)
-        Definition for how to facet the data. One of: 1) `a field definition for faceting
-        the plot by one field
-        <https://vega.github.io/vega-lite/docs/facet.html#field-def>`__ 2) `An object that
-        maps row and column channels to their field definitions
-        <https://vega.github.io/vega-lite/docs/facet.html#mapping>`__
-    spec : anyOf(:class:`LayerSpec`, :class:`UnitSpecWithFrame`)
-        A specification of the view that gets faceted.
-    align : anyOf(:class:`LayoutAlign`, :class:`RowColLayoutAlign`)
-        The alignment to apply to grid rows and columns. The supported string values are
-        ``"all"``, ``"each"``, and ``"none"``.
-
-
-        * For ``"none"``, a flow layout will be used, in which adjacent subviews are simply
-          placed one after the other.
-        * For ``"each"``, subviews will be aligned into a clean grid structure, but each row
-          or column may be of variable size.
-        * For ``"all"``, subviews will be aligned and each row or column will be sized
-          identically based on the maximum observed size. String values for this property
-          will be applied to both grid rows and columns.
-
-        Alternatively, an object value of the form ``{"row": string, "column": string}`` can
-        be used to supply different alignments for rows and columns.
-
-        **Default value:** ``"all"``.
-    autosize : anyOf(:class:`AutosizeType`, :class:`AutoSizeParams`)
-        How the visualization size should be determined. If a string, should be one of
-        ``"pad"``, ``"fit"`` or ``"none"``. Object values can additionally specify
-        parameters for content sizing and automatic resizing.
-
-        **Default value** : ``pad``
-    background : anyOf(:class:`Color`, :class:`ExprRef`)
-        CSS color property to use as the background of the entire view.
-
-        **Default value:** ``"white"``
-    bounds : enum('full', 'flush')
-        The bounds calculation method to use for determining the extent of a sub-plot. One
-        of ``full`` (the default) or ``flush``.
-
-
-        * If set to ``full``, the entire calculated bounds (including axes, title, and
-          legend) will be used.
-        * If set to ``flush``, only the specified width and height values for the sub-view
-          will be used. The ``flush`` setting can be useful when attempting to place
-          sub-plots without axes or legends into a uniform grid structure.
-
-        **Default value:** ``"full"``
-    center : anyOf(boolean, :class:`RowColboolean`)
-        Boolean flag indicating if subviews should be centered relative to their respective
-        rows or columns.
-
-        An object value of the form ``{"row": boolean, "column": boolean}`` can be used to
-        supply different centering values for rows and columns.
-
-        **Default value:** ``false``
-    columns : float
-        The number of columns to include in the view composition layout.
-
-        **Default value** : ``undefined`` -- An infinite number of columns (a single row)
-        will be assumed. This is equivalent to ``hconcat`` (for ``concat`` ) and to using
-        the ``column`` channel (for ``facet`` and ``repeat`` ).
-
-        **Note** :
-
-        1) This property is only for:
-
-
-        * the general (wrappable) ``concat`` operator (not ``hconcat`` / ``vconcat`` )
-        * the ``facet`` and ``repeat`` operator with one field/repetition definition
-          (without row/column nesting)
-
-        2) Setting the ``columns`` to ``1`` is equivalent to ``vconcat`` (for ``concat`` )
-        and to using the ``row`` channel (for ``facet`` and ``repeat`` ).
-    config : :class:`Config`
-        Vega-Lite configuration object. This property can only be defined at the top-level
-        of a specification.
-    datasets : :class:`Datasets`
-        A global data store for named datasets. This is a mapping from names to inline
-        datasets. This can be an array of objects or primitive values or a string. Arrays of
-        primitive values are ingested as objects with a ``data`` property.
-    description : string
-        Description of this mark for commenting purpose.
-    name : string
-        Name of the visualization for later reference.
-    padding : anyOf(:class:`Padding`, :class:`ExprRef`)
-        The default visualization padding, in pixels, from the edge of the visualization
-        canvas to the data rectangle. If a number, specifies padding for all sides. If an
-        object, the value should have the format ``{"left": 5, "top": 5, "right": 5,
-        "bottom": 5}`` to specify padding for each side of the visualization.
-
-        **Default value** : ``5``
-    params : List(:class:`TopLevelParameter`)
-        Dynamic variables or selections that parameterize a visualization.
-    resolve : :class:`Resolve`
-        Scale, axis, and legend resolutions for view composition specifications.
-    spacing : anyOf(float, :class:`RowColnumber`)
-        The spacing in pixels between sub-views of the composition operator. An object of
-        the form ``{"row": number, "column": number}`` can be used to set different spacing
-        values for rows and columns.
-
-        **Default value** : Depends on ``"spacing"`` property of `the view composition
-        configuration <https://vega.github.io/vega-lite/docs/config.html#view-config>`__ (
-        ``20`` by default)
-    title : anyOf(:class:`Text`, :class:`TitleParams`)
-        Title for the plot.
-    transform : List(:class:`Transform`)
-        An array of data transformations such as filter and new field calculation.
-    usermeta : :class:`Dict`
-        Optional metadata that will be passed to Vega. This object is completely ignored by
-        Vega and Vega-Lite and can be used for custom metadata.
-    $schema : string
-        URL to `JSON schema <http://json-schema.org/>`__ for a Vega-Lite specification.
-        Unless you have a reason to change this, use
-        ``https://vega.github.io/schema/vega-lite/v5.json``. Setting the ``$schema``
-        property allows automatic validation and autocomplete in editors that support JSON
-        schema.
-    """
-    _schema = {'$ref': '#/definitions/TopLevelFacetSpec'}
-
-    def __init__(self, data=Undefined, facet=Undefined, spec=Undefined, align=Undefined,
-                 autosize=Undefined, background=Undefined, bounds=Undefined, center=Undefined,
-                 columns=Undefined, config=Undefined, datasets=Undefined, description=Undefined,
-                 name=Undefined, padding=Undefined, params=Undefined, resolve=Undefined,
-                 spacing=Undefined, title=Undefined, transform=Undefined, usermeta=Undefined, **kwds):
-        super(TopLevelFacetSpec, self).__init__(data=data, facet=facet, spec=spec, align=align,
-                                                autosize=autosize, background=background, bounds=bounds,
-                                                center=center, columns=columns, config=config,
-                                                datasets=datasets, description=description, name=name,
-                                                padding=padding, params=params, resolve=resolve,
-                                                spacing=spacing, title=title, transform=transform,
-                                                usermeta=usermeta, **kwds)
-
-
-class TopLevelHConcatSpec(TopLevelSpec):
-    """TopLevelHConcatSpec schema wrapper
-
-    Mapping(required=[hconcat])
-
-    Parameters
-    ----------
-
-    hconcat : List(:class:`NonNormalizedSpec`)
-        A list of views to be concatenated and put into a row.
-    autosize : anyOf(:class:`AutosizeType`, :class:`AutoSizeParams`)
-        How the visualization size should be determined. If a string, should be one of
-        ``"pad"``, ``"fit"`` or ``"none"``. Object values can additionally specify
-        parameters for content sizing and automatic resizing.
-
-        **Default value** : ``pad``
-    background : anyOf(:class:`Color`, :class:`ExprRef`)
-        CSS color property to use as the background of the entire view.
-
-        **Default value:** ``"white"``
-    bounds : enum('full', 'flush')
-        The bounds calculation method to use for determining the extent of a sub-plot. One
-        of ``full`` (the default) or ``flush``.
-
-
-        * If set to ``full``, the entire calculated bounds (including axes, title, and
-          legend) will be used.
-        * If set to ``flush``, only the specified width and height values for the sub-view
-          will be used. The ``flush`` setting can be useful when attempting to place
-          sub-plots without axes or legends into a uniform grid structure.
-
-        **Default value:** ``"full"``
-    center : boolean
-        Boolean flag indicating if subviews should be centered relative to their respective
-        rows or columns.
-
-        **Default value:** ``false``
-    config : :class:`Config`
-        Vega-Lite configuration object. This property can only be defined at the top-level
-        of a specification.
-    data : anyOf(:class:`Data`, None)
-        An object describing the data source. Set to ``null`` to ignore the parent's data
-        source. If no data is set, it is derived from the parent.
-    datasets : :class:`Datasets`
-        A global data store for named datasets. This is a mapping from names to inline
-        datasets. This can be an array of objects or primitive values or a string. Arrays of
-        primitive values are ingested as objects with a ``data`` property.
-    description : string
-        Description of this mark for commenting purpose.
-    name : string
-        Name of the visualization for later reference.
-    padding : anyOf(:class:`Padding`, :class:`ExprRef`)
-        The default visualization padding, in pixels, from the edge of the visualization
-        canvas to the data rectangle. If a number, specifies padding for all sides. If an
-        object, the value should have the format ``{"left": 5, "top": 5, "right": 5,
-        "bottom": 5}`` to specify padding for each side of the visualization.
-
-        **Default value** : ``5``
-    params : List(:class:`TopLevelParameter`)
-        Dynamic variables or selections that parameterize a visualization.
-    resolve : :class:`Resolve`
-        Scale, axis, and legend resolutions for view composition specifications.
-    spacing : float
-        The spacing in pixels between sub-views of the concat operator.
-
-        **Default value** : ``10``
-    title : anyOf(:class:`Text`, :class:`TitleParams`)
-        Title for the plot.
-    transform : List(:class:`Transform`)
-        An array of data transformations such as filter and new field calculation.
-    usermeta : :class:`Dict`
-        Optional metadata that will be passed to Vega. This object is completely ignored by
-        Vega and Vega-Lite and can be used for custom metadata.
-    $schema : string
-        URL to `JSON schema <http://json-schema.org/>`__ for a Vega-Lite specification.
-        Unless you have a reason to change this, use
-        ``https://vega.github.io/schema/vega-lite/v5.json``. Setting the ``$schema``
-        property allows automatic validation and autocomplete in editors that support JSON
-        schema.
-    """
-    _schema = {'$ref': '#/definitions/TopLevelHConcatSpec'}
-
-    def __init__(self, hconcat=Undefined, autosize=Undefined, background=Undefined, bounds=Undefined,
-                 center=Undefined, config=Undefined, data=Undefined, datasets=Undefined,
-                 description=Undefined, name=Undefined, padding=Undefined, params=Undefined,
-                 resolve=Undefined, spacing=Undefined, title=Undefined, transform=Undefined,
-                 usermeta=Undefined, **kwds):
-        super(TopLevelHConcatSpec, self).__init__(hconcat=hconcat, autosize=autosize,
-                                                  background=background, bounds=bounds, center=center,
-                                                  config=config, data=data, datasets=datasets,
-                                                  description=description, name=name, padding=padding,
-                                                  params=params, resolve=resolve, spacing=spacing,
-                                                  title=title, transform=transform, usermeta=usermeta,
-                                                  **kwds)
-
-
-class TopLevelLayerSpec(TopLevelSpec):
-    """TopLevelLayerSpec schema wrapper
-
-    Mapping(required=[layer])
-
-    Parameters
-    ----------
-
-    layer : List(anyOf(:class:`LayerSpec`, :class:`UnitSpec`))
-        Layer or single view specifications to be layered.
-
-        **Note** : Specifications inside ``layer`` cannot use ``row`` and ``column``
-        channels as layering facet specifications is not allowed. Instead, use the `facet
-        operator <https://vega.github.io/vega-lite/docs/facet.html>`__ and place a layer
-        inside a facet.
-    autosize : anyOf(:class:`AutosizeType`, :class:`AutoSizeParams`)
-        How the visualization size should be determined. If a string, should be one of
-        ``"pad"``, ``"fit"`` or ``"none"``. Object values can additionally specify
-        parameters for content sizing and automatic resizing.
-
-        **Default value** : ``pad``
-    background : anyOf(:class:`Color`, :class:`ExprRef`)
-        CSS color property to use as the background of the entire view.
-
-        **Default value:** ``"white"``
-    config : :class:`Config`
-        Vega-Lite configuration object. This property can only be defined at the top-level
-        of a specification.
-    data : anyOf(:class:`Data`, None)
-        An object describing the data source. Set to ``null`` to ignore the parent's data
-        source. If no data is set, it is derived from the parent.
-    datasets : :class:`Datasets`
-        A global data store for named datasets. This is a mapping from names to inline
-        datasets. This can be an array of objects or primitive values or a string. Arrays of
-        primitive values are ingested as objects with a ``data`` property.
-    description : string
-        Description of this mark for commenting purpose.
-    encoding : :class:`SharedEncoding`
-        A shared key-value mapping between encoding channels and definition of fields in the
-        underlying layers.
-    height : anyOf(float, string, :class:`Step`)
-        The height of a visualization.
-
-
-        * For a plot with a continuous y-field, height should be a number.
-        * For a plot with either a discrete y-field or no y-field, height can be either a
-          number indicating a fixed height or an object in the form of ``{step: number}``
-          defining the height per discrete step. (No y-field is equivalent to having one
-          discrete step.)
-        * To enable responsive sizing on height, it should be set to ``"container"``.
-
-        **Default value:** Based on ``config.view.continuousHeight`` for a plot with a
-        continuous y-field and ``config.view.discreteHeight`` otherwise.
-
-        **Note:** For plots with `row and column channels
-        <https://vega.github.io/vega-lite/docs/encoding.html#facet>`__, this represents the
-        height of a single view and the ``"container"`` option cannot be used.
-
-        **See also:** `height <https://vega.github.io/vega-lite/docs/size.html>`__
-        documentation.
-    name : string
-        Name of the visualization for later reference.
-    padding : anyOf(:class:`Padding`, :class:`ExprRef`)
-        The default visualization padding, in pixels, from the edge of the visualization
-        canvas to the data rectangle. If a number, specifies padding for all sides. If an
-        object, the value should have the format ``{"left": 5, "top": 5, "right": 5,
-        "bottom": 5}`` to specify padding for each side of the visualization.
-
-        **Default value** : ``5``
-    params : List(:class:`TopLevelParameter`)
-        Dynamic variables or selections that parameterize a visualization.
-    projection : :class:`Projection`
-        An object defining properties of the geographic projection shared by underlying
-        layers.
-    resolve : :class:`Resolve`
-        Scale, axis, and legend resolutions for view composition specifications.
-    title : anyOf(:class:`Text`, :class:`TitleParams`)
-        Title for the plot.
-    transform : List(:class:`Transform`)
-        An array of data transformations such as filter and new field calculation.
-    usermeta : :class:`Dict`
-        Optional metadata that will be passed to Vega. This object is completely ignored by
-        Vega and Vega-Lite and can be used for custom metadata.
-    view : :class:`ViewBackground`
-        An object defining the view background's fill and stroke.
-
-        **Default value:** none (transparent)
-    width : anyOf(float, string, :class:`Step`)
-        The width of a visualization.
-
-
-        * For a plot with a continuous x-field, width should be a number.
-        * For a plot with either a discrete x-field or no x-field, width can be either a
-          number indicating a fixed width or an object in the form of ``{step: number}``
-          defining the width per discrete step. (No x-field is equivalent to having one
-          discrete step.)
-        * To enable responsive sizing on width, it should be set to ``"container"``.
-
-        **Default value:** Based on ``config.view.continuousWidth`` for a plot with a
-        continuous x-field and ``config.view.discreteWidth`` otherwise.
-
-        **Note:** For plots with `row and column channels
-        <https://vega.github.io/vega-lite/docs/encoding.html#facet>`__, this represents the
-        width of a single view and the ``"container"`` option cannot be used.
-
-        **See also:** `width <https://vega.github.io/vega-lite/docs/size.html>`__
-        documentation.
-    $schema : string
-        URL to `JSON schema <http://json-schema.org/>`__ for a Vega-Lite specification.
-        Unless you have a reason to change this, use
-        ``https://vega.github.io/schema/vega-lite/v5.json``. Setting the ``$schema``
-        property allows automatic validation and autocomplete in editors that support JSON
-        schema.
-    """
-    _schema = {'$ref': '#/definitions/TopLevelLayerSpec'}
-
-    def __init__(self, layer=Undefined, autosize=Undefined, background=Undefined, config=Undefined,
-                 data=Undefined, datasets=Undefined, description=Undefined, encoding=Undefined,
-                 height=Undefined, name=Undefined, padding=Undefined, params=Undefined,
-                 projection=Undefined, resolve=Undefined, title=Undefined, transform=Undefined,
-                 usermeta=Undefined, view=Undefined, width=Undefined, **kwds):
-        super(TopLevelLayerSpec, self).__init__(layer=layer, autosize=autosize, background=background,
-                                                config=config, data=data, datasets=datasets,
-                                                description=description, encoding=encoding,
-                                                height=height, name=name, padding=padding,
-                                                params=params, projection=projection, resolve=resolve,
-                                                title=title, transform=transform, usermeta=usermeta,
-                                                view=view, width=width, **kwds)
-
-
-class TopLevelRepeatSpec(TopLevelSpec):
-    """TopLevelRepeatSpec schema wrapper
-
-    anyOf(Mapping(required=[repeat, spec]), Mapping(required=[repeat, spec]))
-    """
-    _schema = {'$ref': '#/definitions/TopLevelRepeatSpec'}
-
-    def __init__(self, *args, **kwds):
-        super(TopLevelRepeatSpec, self).__init__(*args, **kwds)
-
-
-class TopLevelUnitSpec(TopLevelSpec):
-    """TopLevelUnitSpec schema wrapper
-
-    Mapping(required=[data, mark])
-
-    Parameters
-    ----------
-
-    data : anyOf(:class:`Data`, None)
-        An object describing the data source. Set to ``null`` to ignore the parent's data
-        source. If no data is set, it is derived from the parent.
-    mark : :class:`AnyMark`
-        A string describing the mark type (one of ``"bar"``, ``"circle"``, ``"square"``,
-        ``"tick"``, ``"line"``, ``"area"``, ``"point"``, ``"rule"``, ``"geoshape"``, and
-        ``"text"`` ) or a `mark definition object
-        <https://vega.github.io/vega-lite/docs/mark.html#mark-def>`__.
-    align : anyOf(:class:`LayoutAlign`, :class:`RowColLayoutAlign`)
-        The alignment to apply to grid rows and columns. The supported string values are
-        ``"all"``, ``"each"``, and ``"none"``.
-
-
-        * For ``"none"``, a flow layout will be used, in which adjacent subviews are simply
-          placed one after the other.
-        * For ``"each"``, subviews will be aligned into a clean grid structure, but each row
-          or column may be of variable size.
-        * For ``"all"``, subviews will be aligned and each row or column will be sized
-          identically based on the maximum observed size. String values for this property
-          will be applied to both grid rows and columns.
-
-        Alternatively, an object value of the form ``{"row": string, "column": string}`` can
-        be used to supply different alignments for rows and columns.
-
-        **Default value:** ``"all"``.
-    autosize : anyOf(:class:`AutosizeType`, :class:`AutoSizeParams`)
-        How the visualization size should be determined. If a string, should be one of
-        ``"pad"``, ``"fit"`` or ``"none"``. Object values can additionally specify
-        parameters for content sizing and automatic resizing.
-
-        **Default value** : ``pad``
-    background : anyOf(:class:`Color`, :class:`ExprRef`)
-        CSS color property to use as the background of the entire view.
-
-        **Default value:** ``"white"``
-    bounds : enum('full', 'flush')
-        The bounds calculation method to use for determining the extent of a sub-plot. One
-        of ``full`` (the default) or ``flush``.
-
-
-        * If set to ``full``, the entire calculated bounds (including axes, title, and
-          legend) will be used.
-        * If set to ``flush``, only the specified width and height values for the sub-view
-          will be used. The ``flush`` setting can be useful when attempting to place
-          sub-plots without axes or legends into a uniform grid structure.
-
-        **Default value:** ``"full"``
-    center : anyOf(boolean, :class:`RowColboolean`)
-        Boolean flag indicating if subviews should be centered relative to their respective
-        rows or columns.
-
-        An object value of the form ``{"row": boolean, "column": boolean}`` can be used to
-        supply different centering values for rows and columns.
-
-        **Default value:** ``false``
-    config : :class:`Config`
-        Vega-Lite configuration object. This property can only be defined at the top-level
-        of a specification.
-    datasets : :class:`Datasets`
-        A global data store for named datasets. This is a mapping from names to inline
-        datasets. This can be an array of objects or primitive values or a string. Arrays of
-        primitive values are ingested as objects with a ``data`` property.
-    description : string
-        Description of this mark for commenting purpose.
-    encoding : :class:`FacetedEncoding`
-        A key-value mapping between encoding channels and definition of fields.
-    height : anyOf(float, string, :class:`Step`)
-        The height of a visualization.
-
-
-        * For a plot with a continuous y-field, height should be a number.
-        * For a plot with either a discrete y-field or no y-field, height can be either a
-          number indicating a fixed height or an object in the form of ``{step: number}``
-          defining the height per discrete step. (No y-field is equivalent to having one
-          discrete step.)
-        * To enable responsive sizing on height, it should be set to ``"container"``.
-
-        **Default value:** Based on ``config.view.continuousHeight`` for a plot with a
-        continuous y-field and ``config.view.discreteHeight`` otherwise.
-
-        **Note:** For plots with `row and column channels
-        <https://vega.github.io/vega-lite/docs/encoding.html#facet>`__, this represents the
-        height of a single view and the ``"container"`` option cannot be used.
-
-        **See also:** `height <https://vega.github.io/vega-lite/docs/size.html>`__
-        documentation.
-    name : string
-        Name of the visualization for later reference.
-    padding : anyOf(:class:`Padding`, :class:`ExprRef`)
-        The default visualization padding, in pixels, from the edge of the visualization
-        canvas to the data rectangle. If a number, specifies padding for all sides. If an
-        object, the value should have the format ``{"left": 5, "top": 5, "right": 5,
-        "bottom": 5}`` to specify padding for each side of the visualization.
-
-        **Default value** : ``5``
-    params : List(:class:`TopLevelParameter`)
-        An array of parameters that may either be simple variables, or more complex
-        selections that map user input to data queries.
-    projection : :class:`Projection`
-        An object defining properties of geographic projection, which will be applied to
-        ``shape`` path for ``"geoshape"`` marks and to ``latitude`` and ``"longitude"``
-        channels for other marks.
-    resolve : :class:`Resolve`
-        Scale, axis, and legend resolutions for view composition specifications.
-    spacing : anyOf(float, :class:`RowColnumber`)
-        The spacing in pixels between sub-views of the composition operator. An object of
-        the form ``{"row": number, "column": number}`` can be used to set different spacing
-        values for rows and columns.
-
-        **Default value** : Depends on ``"spacing"`` property of `the view composition
-        configuration <https://vega.github.io/vega-lite/docs/config.html#view-config>`__ (
-        ``20`` by default)
-    title : anyOf(:class:`Text`, :class:`TitleParams`)
-        Title for the plot.
-    transform : List(:class:`Transform`)
-        An array of data transformations such as filter and new field calculation.
-    usermeta : :class:`Dict`
-        Optional metadata that will be passed to Vega. This object is completely ignored by
-        Vega and Vega-Lite and can be used for custom metadata.
-    view : :class:`ViewBackground`
-        An object defining the view background's fill and stroke.
-
-        **Default value:** none (transparent)
-    width : anyOf(float, string, :class:`Step`)
-        The width of a visualization.
-
-
-        * For a plot with a continuous x-field, width should be a number.
-        * For a plot with either a discrete x-field or no x-field, width can be either a
-          number indicating a fixed width or an object in the form of ``{step: number}``
-          defining the width per discrete step. (No x-field is equivalent to having one
-          discrete step.)
-        * To enable responsive sizing on width, it should be set to ``"container"``.
-
-        **Default value:** Based on ``config.view.continuousWidth`` for a plot with a
-        continuous x-field and ``config.view.discreteWidth`` otherwise.
-
-        **Note:** For plots with `row and column channels
-        <https://vega.github.io/vega-lite/docs/encoding.html#facet>`__, this represents the
-        width of a single view and the ``"container"`` option cannot be used.
-
-        **See also:** `width <https://vega.github.io/vega-lite/docs/size.html>`__
-        documentation.
-    $schema : string
-        URL to `JSON schema <http://json-schema.org/>`__ for a Vega-Lite specification.
-        Unless you have a reason to change this, use
-        ``https://vega.github.io/schema/vega-lite/v5.json``. Setting the ``$schema``
-        property allows automatic validation and autocomplete in editors that support JSON
-        schema.
-    """
-    _schema = {'$ref': '#/definitions/TopLevelUnitSpec'}
-
-    def __init__(self, data=Undefined, mark=Undefined, align=Undefined, autosize=Undefined,
-                 background=Undefined, bounds=Undefined, center=Undefined, config=Undefined,
-                 datasets=Undefined, description=Undefined, encoding=Undefined, height=Undefined,
-                 name=Undefined, padding=Undefined, params=Undefined, projection=Undefined,
-                 resolve=Undefined, spacing=Undefined, title=Undefined, transform=Undefined,
-                 usermeta=Undefined, view=Undefined, width=Undefined, **kwds):
-        super(TopLevelUnitSpec, self).__init__(data=data, mark=mark, align=align, autosize=autosize,
-                                               background=background, bounds=bounds, center=center,
-                                               config=config, datasets=datasets,
-                                               description=description, encoding=encoding,
-                                               height=height, name=name, padding=padding, params=params,
-                                               projection=projection, resolve=resolve, spacing=spacing,
-                                               title=title, transform=transform, usermeta=usermeta,
-                                               view=view, width=width, **kwds)
-
-
-class TopLevelVConcatSpec(TopLevelSpec):
-    """TopLevelVConcatSpec schema wrapper
-
-    Mapping(required=[vconcat])
-
-    Parameters
-    ----------
-
-    vconcat : List(:class:`NonNormalizedSpec`)
-        A list of views to be concatenated and put into a column.
-    autosize : anyOf(:class:`AutosizeType`, :class:`AutoSizeParams`)
-        How the visualization size should be determined. If a string, should be one of
-        ``"pad"``, ``"fit"`` or ``"none"``. Object values can additionally specify
-        parameters for content sizing and automatic resizing.
-
-        **Default value** : ``pad``
-    background : anyOf(:class:`Color`, :class:`ExprRef`)
-        CSS color property to use as the background of the entire view.
-
-        **Default value:** ``"white"``
-    bounds : enum('full', 'flush')
-        The bounds calculation method to use for determining the extent of a sub-plot. One
-        of ``full`` (the default) or ``flush``.
-
-
-        * If set to ``full``, the entire calculated bounds (including axes, title, and
-          legend) will be used.
-        * If set to ``flush``, only the specified width and height values for the sub-view
-          will be used. The ``flush`` setting can be useful when attempting to place
-          sub-plots without axes or legends into a uniform grid structure.
-
-        **Default value:** ``"full"``
-    center : boolean
-        Boolean flag indicating if subviews should be centered relative to their respective
-        rows or columns.
-
-        **Default value:** ``false``
-    config : :class:`Config`
-        Vega-Lite configuration object. This property can only be defined at the top-level
-        of a specification.
-    data : anyOf(:class:`Data`, None)
-        An object describing the data source. Set to ``null`` to ignore the parent's data
-        source. If no data is set, it is derived from the parent.
-    datasets : :class:`Datasets`
-        A global data store for named datasets. This is a mapping from names to inline
-        datasets. This can be an array of objects or primitive values or a string. Arrays of
-        primitive values are ingested as objects with a ``data`` property.
-    description : string
-        Description of this mark for commenting purpose.
-    name : string
-        Name of the visualization for later reference.
-    padding : anyOf(:class:`Padding`, :class:`ExprRef`)
-        The default visualization padding, in pixels, from the edge of the visualization
-        canvas to the data rectangle. If a number, specifies padding for all sides. If an
-        object, the value should have the format ``{"left": 5, "top": 5, "right": 5,
-        "bottom": 5}`` to specify padding for each side of the visualization.
-
-        **Default value** : ``5``
-    params : List(:class:`TopLevelParameter`)
-        Dynamic variables or selections that parameterize a visualization.
-    resolve : :class:`Resolve`
-        Scale, axis, and legend resolutions for view composition specifications.
-    spacing : float
-        The spacing in pixels between sub-views of the concat operator.
-
-        **Default value** : ``10``
-    title : anyOf(:class:`Text`, :class:`TitleParams`)
-        Title for the plot.
-    transform : List(:class:`Transform`)
-        An array of data transformations such as filter and new field calculation.
-    usermeta : :class:`Dict`
-        Optional metadata that will be passed to Vega. This object is completely ignored by
-        Vega and Vega-Lite and can be used for custom metadata.
-    $schema : string
-        URL to `JSON schema <http://json-schema.org/>`__ for a Vega-Lite specification.
-        Unless you have a reason to change this, use
-        ``https://vega.github.io/schema/vega-lite/v5.json``. Setting the ``$schema``
-        property allows automatic validation and autocomplete in editors that support JSON
-        schema.
-    """
-    _schema = {'$ref': '#/definitions/TopLevelVConcatSpec'}
-
-    def __init__(self, vconcat=Undefined, autosize=Undefined, background=Undefined, bounds=Undefined,
-                 center=Undefined, config=Undefined, data=Undefined, datasets=Undefined,
-                 description=Undefined, name=Undefined, padding=Undefined, params=Undefined,
-                 resolve=Undefined, spacing=Undefined, title=Undefined, transform=Undefined,
-                 usermeta=Undefined, **kwds):
-        super(TopLevelVConcatSpec, self).__init__(vconcat=vconcat, autosize=autosize,
-                                                  background=background, bounds=bounds, center=center,
-                                                  config=config, data=data, datasets=datasets,
-                                                  description=description, name=name, padding=padding,
-                                                  params=params, resolve=resolve, spacing=spacing,
-                                                  title=title, transform=transform, usermeta=usermeta,
-                                                  **kwds)
-
-
-class TopoDataFormat(DataFormat):
-    """TopoDataFormat schema wrapper
-
-    Mapping(required=[])
-
-    Parameters
-    ----------
-
-    feature : string
-        The name of the TopoJSON object set to convert to a GeoJSON feature collection. For
-        example, in a map of the world, there may be an object set named ``"countries"``.
-        Using the feature property, we can extract this set and generate a GeoJSON feature
-        object for each country.
-    mesh : string
-        The name of the TopoJSON object set to convert to mesh. Similar to the ``feature``
-        option, ``mesh`` extracts a named TopoJSON object set.  Unlike the ``feature``
-        option, the corresponding geo data is returned as a single, unified mesh instance,
-        not as individual GeoJSON features. Extracting a mesh is useful for more efficiently
-        drawing borders or other geographic elements that you do not need to associate with
-        specific regions such as individual countries, states or counties.
-    parse : anyOf(:class:`Parse`, None)
-        If set to ``null``, disable type inference based on the spec and only use type
-        inference based on the data. Alternatively, a parsing directive object can be
-        provided for explicit data types. Each property of the object corresponds to a field
-        name, and the value to the desired data type (one of ``"number"``, ``"boolean"``,
-        ``"date"``, or null (do not parse the field)). For example, ``"parse":
-        {"modified_on": "date"}`` parses the ``modified_on`` field in each input record a
-        Date value.
-
-        For ``"date"``, we parse data based using JavaScript's `Date.parse()
-        <https://developer.mozilla.org/en-US/docs/Web/JavaScript/Reference/Global_Objects/Date/parse>`__.
-        For Specific date formats can be provided (e.g., ``{foo: "date:'%m%d%Y'"}`` ), using
-        the `d3-time-format syntax <https://github.com/d3/d3-time-format#locale_format>`__.
-        UTC date format parsing is supported similarly (e.g., ``{foo: "utc:'%m%d%Y'"}`` ).
-        See more about `UTC time
-        <https://vega.github.io/vega-lite/docs/timeunit.html#utc>`__
-    type : string
-        Type of input data: ``"json"``, ``"csv"``, ``"tsv"``, ``"dsv"``.
-
-        **Default value:**  The default format type is determined by the extension of the
-        file URL. If no extension is detected, ``"json"`` will be used by default.
-    """
-    _schema = {'$ref': '#/definitions/TopoDataFormat'}
-
-    def __init__(self, feature=Undefined, mesh=Undefined, parse=Undefined, type=Undefined, **kwds):
-        super(TopoDataFormat, self).__init__(feature=feature, mesh=mesh, parse=parse, type=type, **kwds)
-
-
-class Transform(VegaLiteSchema):
-    """Transform schema wrapper
-
-    anyOf(:class:`AggregateTransform`, :class:`BinTransform`, :class:`CalculateTransform`,
-    :class:`DensityTransform`, :class:`ExtentTransform`, :class:`FilterTransform`,
-    :class:`FlattenTransform`, :class:`FoldTransform`, :class:`ImputeTransform`,
-    :class:`JoinAggregateTransform`, :class:`LoessTransform`, :class:`LookupTransform`,
-    :class:`QuantileTransform`, :class:`RegressionTransform`, :class:`TimeUnitTransform`,
-    :class:`SampleTransform`, :class:`StackTransform`, :class:`WindowTransform`,
-    :class:`PivotTransform`)
-    """
-    _schema = {'$ref': '#/definitions/Transform'}
-
-    def __init__(self, *args, **kwds):
-        super(Transform, self).__init__(*args, **kwds)
-
-
-class AggregateTransform(Transform):
-    """AggregateTransform schema wrapper
-
-    Mapping(required=[aggregate])
-
-    Parameters
-    ----------
-
-    aggregate : List(:class:`AggregatedFieldDef`)
-        Array of objects that define fields to aggregate.
-    groupby : List(:class:`FieldName`)
-        The data fields to group by. If not specified, a single group containing all data
-        objects will be used.
-    """
-    _schema = {'$ref': '#/definitions/AggregateTransform'}
-
-    def __init__(self, aggregate=Undefined, groupby=Undefined, **kwds):
-        super(AggregateTransform, self).__init__(aggregate=aggregate, groupby=groupby, **kwds)
-
-
-class BinTransform(Transform):
-    """BinTransform schema wrapper
-
-    Mapping(required=[bin, field, as])
-
-    Parameters
-    ----------
-
-    bin : anyOf(boolean, :class:`BinParams`)
-        An object indicating bin properties, or simply ``true`` for using default bin
-        parameters.
-    field : :class:`FieldName`
-        The data field to bin.
-    as : anyOf(:class:`FieldName`, List(:class:`FieldName`))
-        The output fields at which to write the start and end bin values. This can be either
-        a string or an array of strings with two elements denoting the name for the fields
-        for bin start and bin end respectively. If a single string (e.g., ``"val"`` ) is
-        provided, the end field will be ``"val_end"``.
-    """
-    _schema = {'$ref': '#/definitions/BinTransform'}
-
-    def __init__(self, bin=Undefined, field=Undefined, **kwds):
-        super(BinTransform, self).__init__(bin=bin, field=field, **kwds)
-
-
-class CalculateTransform(Transform):
-    """CalculateTransform schema wrapper
-
-    Mapping(required=[calculate, as])
-
-    Parameters
-    ----------
-
-    calculate : string
-        A `expression <https://vega.github.io/vega-lite/docs/types.html#expression>`__
-        string. Use the variable ``datum`` to refer to the current data object.
-    as : :class:`FieldName`
-        The field for storing the computed formula value.
-    """
-    _schema = {'$ref': '#/definitions/CalculateTransform'}
-
-    def __init__(self, calculate=Undefined, **kwds):
-        super(CalculateTransform, self).__init__(calculate=calculate, **kwds)
-
-
-class DensityTransform(Transform):
-    """DensityTransform schema wrapper
-
-    Mapping(required=[density])
-
-    Parameters
-    ----------
-
-    density : :class:`FieldName`
-        The data field for which to perform density estimation.
-    bandwidth : float
-        The bandwidth (standard deviation) of the Gaussian kernel. If unspecified or set to
-        zero, the bandwidth value is automatically estimated from the input data using
-        Scott’s rule.
-    counts : boolean
-        A boolean flag indicating if the output values should be probability estimates
-        (false) or smoothed counts (true).
-
-        **Default value:** ``false``
-    cumulative : boolean
-        A boolean flag indicating whether to produce density estimates (false) or cumulative
-        density estimates (true).
-
-        **Default value:** ``false``
-    extent : List(float)
-        A [min, max] domain from which to sample the distribution. If unspecified, the
-        extent will be determined by the observed minimum and maximum values of the density
-        value field.
-    groupby : List(:class:`FieldName`)
-        The data fields to group by. If not specified, a single group containing all data
-        objects will be used.
-    maxsteps : float
-        The maximum number of samples to take along the extent domain for plotting the
-        density.
-
-        **Default value:** ``200``
-    minsteps : float
-        The minimum number of samples to take along the extent domain for plotting the
-        density.
-
-        **Default value:** ``25``
-    steps : float
-        The exact number of samples to take along the extent domain for plotting the
-        density. If specified, overrides both minsteps and maxsteps to set an exact number
-        of uniform samples. Potentially useful in conjunction with a fixed extent to ensure
-        consistent sample points for stacked densities.
-    as : List(:class:`FieldName`)
-        The output fields for the sample value and corresponding density estimate.
-
-        **Default value:** ``["value", "density"]``
-    """
-    _schema = {'$ref': '#/definitions/DensityTransform'}
-
-    def __init__(self, density=Undefined, bandwidth=Undefined, counts=Undefined, cumulative=Undefined,
-                 extent=Undefined, groupby=Undefined, maxsteps=Undefined, minsteps=Undefined,
-                 steps=Undefined, **kwds):
-        super(DensityTransform, self).__init__(density=density, bandwidth=bandwidth, counts=counts,
-                                               cumulative=cumulative, extent=extent, groupby=groupby,
-                                               maxsteps=maxsteps, minsteps=minsteps, steps=steps, **kwds)
-
-
-class ExtentTransform(Transform):
-    """ExtentTransform schema wrapper
-
-    Mapping(required=[extent, param])
-
-    Parameters
-    ----------
-
-    extent : :class:`FieldName`
-        The field of which to get the extent.
-    param : :class:`ParameterName`
-        The output parameter produced by the extent transform.
-    """
-    _schema = {'$ref': '#/definitions/ExtentTransform'}
-
-    def __init__(self, extent=Undefined, param=Undefined, **kwds):
-        super(ExtentTransform, self).__init__(extent=extent, param=param, **kwds)
-
-
-class FilterTransform(Transform):
-    """FilterTransform schema wrapper
-
-    Mapping(required=[filter])
-
-    Parameters
-    ----------
-
-    filter : :class:`PredicateComposition`
-        The ``filter`` property must be a predication definition, which can take one of the
-        following forms:
-
-        1) an `expression <https://vega.github.io/vega-lite/docs/types.html#expression>`__
-        string, where ``datum`` can be used to refer to the current data object. For
-        example, ``{filter: "datum.b2 > 60"}`` would make the output data includes only
-        items that have values in the field ``b2`` over 60.
-
-        2) one of the `field predicates
-        <https://vega.github.io/vega-lite/docs/predicate.html#field-predicate>`__ : `equal
-        <https://vega.github.io/vega-lite/docs/predicate.html#field-equal-predicate>`__, `lt
-        <https://vega.github.io/vega-lite/docs/predicate.html#lt-predicate>`__, `lte
-        <https://vega.github.io/vega-lite/docs/predicate.html#lte-predicate>`__, `gt
-        <https://vega.github.io/vega-lite/docs/predicate.html#gt-predicate>`__, `gte
-        <https://vega.github.io/vega-lite/docs/predicate.html#gte-predicate>`__, `range
-        <https://vega.github.io/vega-lite/docs/predicate.html#range-predicate>`__, `oneOf
-        <https://vega.github.io/vega-lite/docs/predicate.html#one-of-predicate>`__, or
-        `valid <https://vega.github.io/vega-lite/docs/predicate.html#valid-predicate>`__,
-
-        3) a `selection predicate
-        <https://vega.github.io/vega-lite/docs/predicate.html#selection-predicate>`__, which
-        define the names of a selection that the data point should belong to (or a logical
-        composition of selections).
-
-        4) a `logical composition
-        <https://vega.github.io/vega-lite/docs/predicate.html#composition>`__ of (1), (2),
-        or (3).
-    """
-    _schema = {'$ref': '#/definitions/FilterTransform'}
-
-    def __init__(self, filter=Undefined, **kwds):
-        super(FilterTransform, self).__init__(filter=filter, **kwds)
-
-
-class FlattenTransform(Transform):
-    """FlattenTransform schema wrapper
-
-    Mapping(required=[flatten])
-
-    Parameters
-    ----------
-
-    flatten : List(:class:`FieldName`)
-        An array of one or more data fields containing arrays to flatten. If multiple fields
-        are specified, their array values should have a parallel structure, ideally with the
-        same length. If the lengths of parallel arrays do not match, the longest array will
-        be used with ``null`` values added for missing entries.
-    as : List(:class:`FieldName`)
-        The output field names for extracted array values.
-
-        **Default value:** The field name of the corresponding array field
-    """
-    _schema = {'$ref': '#/definitions/FlattenTransform'}
-
-    def __init__(self, flatten=Undefined, **kwds):
-        super(FlattenTransform, self).__init__(flatten=flatten, **kwds)
-
-
-class FoldTransform(Transform):
-    """FoldTransform schema wrapper
-
-    Mapping(required=[fold])
-
-    Parameters
-    ----------
-
-    fold : List(:class:`FieldName`)
-        An array of data fields indicating the properties to fold.
-    as : List(:class:`FieldName`)
-        The output field names for the key and value properties produced by the fold
-        transform. **Default value:** ``["key", "value"]``
-    """
-    _schema = {'$ref': '#/definitions/FoldTransform'}
-
-    def __init__(self, fold=Undefined, **kwds):
-        super(FoldTransform, self).__init__(fold=fold, **kwds)
-
-
-class ImputeTransform(Transform):
-    """ImputeTransform schema wrapper
-
-    Mapping(required=[impute, key])
-
-    Parameters
-    ----------
-
-    impute : :class:`FieldName`
-        The data field for which the missing values should be imputed.
-    key : :class:`FieldName`
-        A key field that uniquely identifies data objects within a group. Missing key values
-        (those occurring in the data but not in the current group) will be imputed.
-    frame : List(anyOf(None, float))
-        A frame specification as a two-element array used to control the window over which
-        the specified method is applied. The array entries should either be a number
-        indicating the offset from the current data object, or null to indicate unbounded
-        rows preceding or following the current data object. For example, the value ``[-5,
-        5]`` indicates that the window should include five objects preceding and five
-        objects following the current object.
-
-        **Default value:** :  ``[null, null]`` indicating that the window includes all
-        objects.
-    groupby : List(:class:`FieldName`)
-        An optional array of fields by which to group the values. Imputation will then be
-        performed on a per-group basis.
-    keyvals : anyOf(List(Any), :class:`ImputeSequence`)
-        Defines the key values that should be considered for imputation. An array of key
-        values or an object defining a `number sequence
-        <https://vega.github.io/vega-lite/docs/impute.html#sequence-def>`__.
-
-        If provided, this will be used in addition to the key values observed within the
-        input data. If not provided, the values will be derived from all unique values of
-        the ``key`` field. For ``impute`` in ``encoding``, the key field is the x-field if
-        the y-field is imputed, or vice versa.
-
-        If there is no impute grouping, this property *must* be specified.
-    method : :class:`ImputeMethod`
-        The imputation method to use for the field value of imputed data objects. One of
-        ``"value"``, ``"mean"``, ``"median"``, ``"max"`` or ``"min"``.
-
-        **Default value:**  ``"value"``
-    value : Any
-        The field value to use when the imputation ``method`` is ``"value"``.
-    """
-    _schema = {'$ref': '#/definitions/ImputeTransform'}
-
-    def __init__(self, impute=Undefined, key=Undefined, frame=Undefined, groupby=Undefined,
-                 keyvals=Undefined, method=Undefined, value=Undefined, **kwds):
-        super(ImputeTransform, self).__init__(impute=impute, key=key, frame=frame, groupby=groupby,
-                                              keyvals=keyvals, method=method, value=value, **kwds)
-
-
-class JoinAggregateTransform(Transform):
-    """JoinAggregateTransform schema wrapper
-
-    Mapping(required=[joinaggregate])
-
-    Parameters
-    ----------
-
-    joinaggregate : List(:class:`JoinAggregateFieldDef`)
-        The definition of the fields in the join aggregate, and what calculations to use.
-    groupby : List(:class:`FieldName`)
-        The data fields for partitioning the data objects into separate groups. If
-        unspecified, all data points will be in a single group.
-    """
-    _schema = {'$ref': '#/definitions/JoinAggregateTransform'}
-
-    def __init__(self, joinaggregate=Undefined, groupby=Undefined, **kwds):
-        super(JoinAggregateTransform, self).__init__(joinaggregate=joinaggregate, groupby=groupby,
-                                                     **kwds)
-
-
-class LoessTransform(Transform):
-    """LoessTransform schema wrapper
-
-    Mapping(required=[loess, on])
-
-    Parameters
-    ----------
-
-    loess : :class:`FieldName`
-        The data field of the dependent variable to smooth.
-    on : :class:`FieldName`
-        The data field of the independent variable to use a predictor.
-    bandwidth : float
-        A bandwidth parameter in the range ``[0, 1]`` that determines the amount of
-        smoothing.
-
-        **Default value:** ``0.3``
-    groupby : List(:class:`FieldName`)
-        The data fields to group by. If not specified, a single group containing all data
-        objects will be used.
-    as : List(:class:`FieldName`)
-        The output field names for the smoothed points generated by the loess transform.
-
-        **Default value:** The field names of the input x and y values.
-    """
-    _schema = {'$ref': '#/definitions/LoessTransform'}
-
-    def __init__(self, loess=Undefined, on=Undefined, bandwidth=Undefined, groupby=Undefined, **kwds):
-        super(LoessTransform, self).__init__(loess=loess, on=on, bandwidth=bandwidth, groupby=groupby,
-                                             **kwds)
-
-
-class LookupTransform(Transform):
-    """LookupTransform schema wrapper
-
-    Mapping(required=[lookup, from])
-
-    Parameters
-    ----------
-
-    lookup : string
-        Key in primary data source.
-    default : Any
-        The default value to use if lookup fails.
-
-        **Default value:** ``null``
-    as : anyOf(:class:`FieldName`, List(:class:`FieldName`))
-        The output fields on which to store the looked up data values.
-
-        For data lookups, this property may be left blank if ``from.fields`` has been
-        specified (those field names will be used); if ``from.fields`` has not been
-        specified, ``as`` must be a string.
-
-        For selection lookups, this property is optional: if unspecified, looked up values
-        will be stored under a property named for the selection; and if specified, it must
-        correspond to ``from.fields``.
-    from : anyOf(:class:`LookupData`, :class:`LookupSelection`)
-        Data source or selection for secondary data reference.
-    """
-    _schema = {'$ref': '#/definitions/LookupTransform'}
-
-    def __init__(self, lookup=Undefined, default=Undefined, **kwds):
-        super(LookupTransform, self).__init__(lookup=lookup, default=default, **kwds)
-
-
-class PivotTransform(Transform):
-    """PivotTransform schema wrapper
-
-    Mapping(required=[pivot, value])
-
-    Parameters
-    ----------
-
-    pivot : :class:`FieldName`
-        The data field to pivot on. The unique values of this field become new field names
-        in the output stream.
-    value : :class:`FieldName`
-        The data field to populate pivoted fields. The aggregate values of this field become
-        the values of the new pivoted fields.
-    groupby : List(:class:`FieldName`)
-        The optional data fields to group by. If not specified, a single group containing
-        all data objects will be used.
-    limit : float
-        An optional parameter indicating the maximum number of pivoted fields to generate.
-        The default ( ``0`` ) applies no limit. The pivoted ``pivot`` names are sorted in
-        ascending order prior to enforcing the limit. **Default value:** ``0``
-    op : :class:`AggregateOp`
-        The aggregation operation to apply to grouped ``value`` field values. **Default
-        value:** ``sum``
-    """
-    _schema = {'$ref': '#/definitions/PivotTransform'}
-
-    def __init__(self, pivot=Undefined, value=Undefined, groupby=Undefined, limit=Undefined,
-                 op=Undefined, **kwds):
-        super(PivotTransform, self).__init__(pivot=pivot, value=value, groupby=groupby, limit=limit,
-                                             op=op, **kwds)
-
-
-class QuantileTransform(Transform):
-    """QuantileTransform schema wrapper
-
-    Mapping(required=[quantile])
-
-    Parameters
-    ----------
-
-    quantile : :class:`FieldName`
-        The data field for which to perform quantile estimation.
-    groupby : List(:class:`FieldName`)
-        The data fields to group by. If not specified, a single group containing all data
-        objects will be used.
-    probs : List(float)
-        An array of probabilities in the range (0, 1) for which to compute quantile values.
-        If not specified, the *step* parameter will be used.
-    step : float
-        A probability step size (default 0.01) for sampling quantile values. All values from
-        one-half the step size up to 1 (exclusive) will be sampled. This parameter is only
-        used if the *probs* parameter is not provided.
-    as : List(:class:`FieldName`)
-        The output field names for the probability and quantile values.
-
-        **Default value:** ``["prob", "value"]``
-    """
-    _schema = {'$ref': '#/definitions/QuantileTransform'}
-
-    def __init__(self, quantile=Undefined, groupby=Undefined, probs=Undefined, step=Undefined, **kwds):
-        super(QuantileTransform, self).__init__(quantile=quantile, groupby=groupby, probs=probs,
-                                                step=step, **kwds)
-
-
-class RegressionTransform(Transform):
-    """RegressionTransform schema wrapper
-
-    Mapping(required=[regression, on])
-
-    Parameters
-    ----------
-
-    on : :class:`FieldName`
-        The data field of the independent variable to use a predictor.
-    regression : :class:`FieldName`
-        The data field of the dependent variable to predict.
-    extent : List(float)
-        A [min, max] domain over the independent (x) field for the starting and ending
-        points of the generated trend line.
-    groupby : List(:class:`FieldName`)
-        The data fields to group by. If not specified, a single group containing all data
-        objects will be used.
-    method : enum('linear', 'log', 'exp', 'pow', 'quad', 'poly')
-        The functional form of the regression model. One of ``"linear"``, ``"log"``,
-        ``"exp"``, ``"pow"``, ``"quad"``, or ``"poly"``.
-
-        **Default value:** ``"linear"``
-    order : float
-        The polynomial order (number of coefficients) for the 'poly' method.
-
-        **Default value:** ``3``
-    params : boolean
-        A boolean flag indicating if the transform should return the regression model
-        parameters (one object per group), rather than trend line points. The resulting
-        objects include a ``coef`` array of fitted coefficient values (starting with the
-        intercept term and then including terms of increasing order) and an ``rSquared``
-        value (indicating the total variance explained by the model).
-
-        **Default value:** ``false``
-    as : List(:class:`FieldName`)
-        The output field names for the smoothed points generated by the regression
-        transform.
-
-        **Default value:** The field names of the input x and y values.
-    """
-    _schema = {'$ref': '#/definitions/RegressionTransform'}
-
-    def __init__(self, on=Undefined, regression=Undefined, extent=Undefined, groupby=Undefined,
-                 method=Undefined, order=Undefined, params=Undefined, **kwds):
-        super(RegressionTransform, self).__init__(on=on, regression=regression, extent=extent,
-                                                  groupby=groupby, method=method, order=order,
-                                                  params=params, **kwds)
-
-
-class SampleTransform(Transform):
-    """SampleTransform schema wrapper
-
-    Mapping(required=[sample])
-
-    Parameters
-    ----------
-
-    sample : float
-        The maximum number of data objects to include in the sample.
-
-        **Default value:** ``1000``
-    """
-    _schema = {'$ref': '#/definitions/SampleTransform'}
-
-    def __init__(self, sample=Undefined, **kwds):
-        super(SampleTransform, self).__init__(sample=sample, **kwds)
-
-
-class StackTransform(Transform):
-    """StackTransform schema wrapper
-
-    Mapping(required=[stack, groupby, as])
-
-    Parameters
-    ----------
-
-    groupby : List(:class:`FieldName`)
-        The data fields to group by.
-    stack : :class:`FieldName`
-        The field which is stacked.
-    offset : enum('zero', 'center', 'normalize')
-        Mode for stacking marks. One of ``"zero"`` (default), ``"center"``, or
-        ``"normalize"``. The ``"zero"`` offset will stack starting at ``0``. The
-        ``"center"`` offset will center the stacks. The ``"normalize"`` offset will compute
-        percentage values for each stack point, with output values in the range ``[0,1]``.
-
-        **Default value:** ``"zero"``
-    sort : List(:class:`SortField`)
-        Field that determines the order of leaves in the stacked charts.
-    as : anyOf(:class:`FieldName`, List(:class:`FieldName`))
-        Output field names. This can be either a string or an array of strings with two
-        elements denoting the name for the fields for stack start and stack end
-        respectively. If a single string(e.g., ``"val"`` ) is provided, the end field will
-        be ``"val_end"``.
-    """
-    _schema = {'$ref': '#/definitions/StackTransform'}
-
-    def __init__(self, groupby=Undefined, stack=Undefined, offset=Undefined, sort=Undefined, **kwds):
-        super(StackTransform, self).__init__(groupby=groupby, stack=stack, offset=offset, sort=sort,
-                                             **kwds)
-
-
-class TimeUnitTransform(Transform):
-    """TimeUnitTransform schema wrapper
-
-    Mapping(required=[timeUnit, field, as])
-
-    Parameters
-    ----------
-
-    field : :class:`FieldName`
-        The data field to apply time unit.
-    timeUnit : anyOf(:class:`TimeUnit`, :class:`TimeUnitTransformParams`)
-        The timeUnit.
-    as : :class:`FieldName`
-        The output field to write the timeUnit value.
-    """
-    _schema = {'$ref': '#/definitions/TimeUnitTransform'}
-
-    def __init__(self, field=Undefined, timeUnit=Undefined, **kwds):
-        super(TimeUnitTransform, self).__init__(field=field, timeUnit=timeUnit, **kwds)
-
-
-class Type(VegaLiteSchema):
-    """Type schema wrapper
-
-    enum('quantitative', 'ordinal', 'temporal', 'nominal', 'geojson')
-    Data type based on level of measurement
-    """
-    _schema = {'$ref': '#/definitions/Type'}
-
-    def __init__(self, *args):
-        super(Type, self).__init__(*args)
-
-
-class TypeForShape(VegaLiteSchema):
-    """TypeForShape schema wrapper
-
-    enum('nominal', 'ordinal', 'geojson')
-    """
-    _schema = {'$ref': '#/definitions/TypeForShape'}
-
-    def __init__(self, *args):
-        super(TypeForShape, self).__init__(*args)
-
-
-class TypedFieldDef(VegaLiteSchema):
-    """TypedFieldDef schema wrapper
-
-    Mapping(required=[])
-    Definition object for a data field, its type and transformation of an encoding channel.
-
-    Parameters
-    ----------
-
-    aggregate : :class:`Aggregate`
-        Aggregation function for the field (e.g., ``"mean"``, ``"sum"``, ``"median"``,
-        ``"min"``, ``"max"``, ``"count"`` ).
-
-        **Default value:** ``undefined`` (None)
-
-        **See also:** `aggregate <https://vega.github.io/vega-lite/docs/aggregate.html>`__
-        documentation.
-    bandPosition : float
-        Relative position on a band of a stacked, binned, time unit, or band scale. For
-        example, the marks will be positioned at the beginning of the band if set to ``0``,
-        and at the middle of the band if set to ``0.5``.
-    bin : anyOf(boolean, :class:`BinParams`, string, None)
-        A flag for binning a ``quantitative`` field, `an object defining binning parameters
-        <https://vega.github.io/vega-lite/docs/bin.html#bin-parameters>`__, or indicating
-        that the data for ``x`` or ``y`` channel are binned before they are imported into
-        Vega-Lite ( ``"binned"`` ).
-
-
-        If ``true``, default `binning parameters
-        <https://vega.github.io/vega-lite/docs/bin.html#bin-parameters>`__ will be applied.
-
-        If ``"binned"``, this indicates that the data for the ``x`` (or ``y`` ) channel are
-        already binned. You can map the bin-start field to ``x`` (or ``y`` ) and the bin-end
-        field to ``x2`` (or ``y2`` ). The scale and axis will be formatted similar to
-        binning in Vega-Lite.  To adjust the axis ticks based on the bin step, you can also
-        set the axis's `tickMinStep
-        <https://vega.github.io/vega-lite/docs/axis.html#ticks>`__ property.
-
-        **Default value:** ``false``
-
-        **See also:** `bin <https://vega.github.io/vega-lite/docs/bin.html>`__
-        documentation.
-    field : :class:`Field`
-        **Required.** A string defining the name of the field from which to pull a data
-        value or an object defining iterated values from the `repeat
-        <https://vega.github.io/vega-lite/docs/repeat.html>`__ operator.
-
-        **See also:** `field <https://vega.github.io/vega-lite/docs/field.html>`__
-        documentation.
-
-        **Notes:** 1)  Dots ( ``.`` ) and brackets ( ``[`` and ``]`` ) can be used to access
-        nested objects (e.g., ``"field": "foo.bar"`` and ``"field": "foo['bar']"`` ). If
-        field names contain dots or brackets but are not nested, you can use ``\\`` to
-        escape dots and brackets (e.g., ``"a\\.b"`` and ``"a\\[0\\]"`` ). See more details
-        about escaping in the `field documentation
-        <https://vega.github.io/vega-lite/docs/field.html>`__. 2) ``field`` is not required
-        if ``aggregate`` is ``count``.
-    timeUnit : anyOf(:class:`TimeUnit`, :class:`BinnedTimeUnit`, :class:`TimeUnitParams`)
-        Time unit (e.g., ``year``, ``yearmonth``, ``month``, ``hours`` ) for a temporal
-        field. or `a temporal field that gets casted as ordinal
-        <https://vega.github.io/vega-lite/docs/type.html#cast>`__.
-
-        **Default value:** ``undefined`` (None)
-
-        **See also:** `timeUnit <https://vega.github.io/vega-lite/docs/timeunit.html>`__
-        documentation.
-    title : anyOf(:class:`Text`, None)
-        A title for the field. If ``null``, the title will be removed.
-
-        **Default value:**  derived from the field's name and transformation function (
-        ``aggregate``, ``bin`` and ``timeUnit`` ). If the field has an aggregate function,
-        the function is displayed as part of the title (e.g., ``"Sum of Profit"`` ). If the
-        field is binned or has a time unit applied, the applied function is shown in
-        parentheses (e.g., ``"Profit (binned)"``, ``"Transaction Date (year-month)"`` ).
-        Otherwise, the title is simply the field name.
-
-        **Notes** :
-
-        1) You can customize the default field title format by providing the `fieldTitle
-        <https://vega.github.io/vega-lite/docs/config.html#top-level-config>`__ property in
-        the `config <https://vega.github.io/vega-lite/docs/config.html>`__ or `fieldTitle
-        function via the compile function's options
-        <https://vega.github.io/vega-lite/usage/compile.html#field-title>`__.
-
-        2) If both field definition's ``title`` and axis, header, or legend ``title`` are
-        defined, axis/header/legend title will be used.
-    type : :class:`StandardType`
-        The type of measurement ( ``"quantitative"``, ``"temporal"``, ``"ordinal"``, or
-        ``"nominal"`` ) for the encoded field or constant value ( ``datum`` ). It can also
-        be a ``"geojson"`` type for encoding `'geoshape'
-        <https://vega.github.io/vega-lite/docs/geoshape.html>`__.
-
-        Vega-Lite automatically infers data types in many cases as discussed below. However,
-        type is required for a field if: (1) the field is not nominal and the field encoding
-        has no specified ``aggregate`` (except ``argmin`` and ``argmax`` ), ``bin``, scale
-        type, custom ``sort`` order, nor ``timeUnit`` or (2) if you wish to use an ordinal
-        scale for a field with ``bin`` or ``timeUnit``.
-
-        **Default value:**
-
-        1) For a data ``field``, ``"nominal"`` is the default data type unless the field
-        encoding has ``aggregate``, ``channel``, ``bin``, scale type, ``sort``, or
-        ``timeUnit`` that satisfies the following criteria:
-
-
-        * ``"quantitative"`` is the default type if (1) the encoded field contains ``bin``
-          or ``aggregate`` except ``"argmin"`` and ``"argmax"``, (2) the encoding channel is
-          ``latitude`` or ``longitude`` channel or (3) if the specified scale type is `a
-          quantitative scale <https://vega.github.io/vega-lite/docs/scale.html#type>`__.
-        * ``"temporal"`` is the default type if (1) the encoded field contains ``timeUnit``
-          or (2) the specified scale type is a time or utc scale
-        * ``"ordinal"`` is the default type if (1) the encoded field contains a `custom sort
-          order
-          <https://vega.github.io/vega-lite/docs/sort.html#specifying-custom-sort-order>`__,
-          (2) the specified scale type is an ordinal/point/band scale, or (3) the encoding
-          channel is ``order``.
-
-        2) For a constant value in data domain ( ``datum`` ):
-
-
-        * ``"quantitative"`` if the datum is a number
-        * ``"nominal"`` if the datum is a string
-        * ``"temporal"`` if the datum is `a date time object
-          <https://vega.github.io/vega-lite/docs/datetime.html>`__
-
-        **Note:**
-
-
-        * Data ``type`` describes the semantics of the data rather than the primitive data
-          types (number, string, etc.). The same primitive data type can have different
-          types of measurement. For example, numeric data can represent quantitative,
-          ordinal, or nominal data.
-        * Data values for a temporal field can be either a date-time string (e.g.,
-          ``"2015-03-07 12:32:17"``, ``"17:01"``, ``"2015-03-16"``. ``"2015"`` ) or a
-          timestamp number (e.g., ``1552199579097`` ).
-        * When using with `bin <https://vega.github.io/vega-lite/docs/bin.html>`__, the
-          ``type`` property can be either ``"quantitative"`` (for using a linear bin scale)
-          or `"ordinal" (for using an ordinal bin scale)
-          <https://vega.github.io/vega-lite/docs/type.html#cast-bin>`__.
-        * When using with `timeUnit
-          <https://vega.github.io/vega-lite/docs/timeunit.html>`__, the ``type`` property
-          can be either ``"temporal"`` (default, for using a temporal scale) or `"ordinal"
-          (for using an ordinal scale)
-          <https://vega.github.io/vega-lite/docs/type.html#cast-bin>`__.
-        * When using with `aggregate
-          <https://vega.github.io/vega-lite/docs/aggregate.html>`__, the ``type`` property
-          refers to the post-aggregation data type. For example, we can calculate count
-          ``distinct`` of a categorical field ``"cat"`` using ``{"aggregate": "distinct",
-          "field": "cat"}``. The ``"type"`` of the aggregate output is ``"quantitative"``.
-        * Secondary channels (e.g., ``x2``, ``y2``, ``xError``, ``yError`` ) do not have
-          ``type`` as they must have exactly the same type as their primary channels (e.g.,
-          ``x``, ``y`` ).
-
-        **See also:** `type <https://vega.github.io/vega-lite/docs/type.html>`__
-        documentation.
-    """
-    _schema = {'$ref': '#/definitions/TypedFieldDef'}
-
-    def __init__(self, aggregate=Undefined, bandPosition=Undefined, bin=Undefined, field=Undefined,
-                 timeUnit=Undefined, title=Undefined, type=Undefined, **kwds):
-        super(TypedFieldDef, self).__init__(aggregate=aggregate, bandPosition=bandPosition, bin=bin,
-                                            field=field, timeUnit=timeUnit, title=title, type=type,
-                                            **kwds)
-
-
-class URI(VegaLiteSchema):
-    """URI schema wrapper
-
-    string
-    """
-    _schema = {'$ref': '#/definitions/URI'}
-
-    def __init__(self, *args):
-        super(URI, self).__init__(*args)
-
-
-class UnitSpec(VegaLiteSchema):
-    """UnitSpec schema wrapper
-
-    Mapping(required=[mark])
-    Base interface for a unit (single-view) specification.
-
-    Parameters
-    ----------
-
-    mark : :class:`AnyMark`
-        A string describing the mark type (one of ``"bar"``, ``"circle"``, ``"square"``,
-        ``"tick"``, ``"line"``, ``"area"``, ``"point"``, ``"rule"``, ``"geoshape"``, and
-        ``"text"`` ) or a `mark definition object
-        <https://vega.github.io/vega-lite/docs/mark.html#mark-def>`__.
-    data : anyOf(:class:`Data`, None)
-        An object describing the data source. Set to ``null`` to ignore the parent's data
-        source. If no data is set, it is derived from the parent.
-    description : string
-        Description of this mark for commenting purpose.
-    encoding : :class:`Encoding`
-        A key-value mapping between encoding channels and definition of fields.
-    name : string
-        Name of the visualization for later reference.
-    params : List(:class:`SelectionParameter`)
-        An array of parameters that may either be simple variables, or more complex
-        selections that map user input to data queries.
-    projection : :class:`Projection`
-        An object defining properties of geographic projection, which will be applied to
-        ``shape`` path for ``"geoshape"`` marks and to ``latitude`` and ``"longitude"``
-        channels for other marks.
-    title : anyOf(:class:`Text`, :class:`TitleParams`)
-        Title for the plot.
-    transform : List(:class:`Transform`)
-        An array of data transformations such as filter and new field calculation.
-    """
-    _schema = {'$ref': '#/definitions/UnitSpec'}
-
-    def __init__(self, mark=Undefined, data=Undefined, description=Undefined, encoding=Undefined,
-                 name=Undefined, params=Undefined, projection=Undefined, title=Undefined,
-                 transform=Undefined, **kwds):
-        super(UnitSpec, self).__init__(mark=mark, data=data, description=description, encoding=encoding,
-                                       name=name, params=params, projection=projection, title=title,
-                                       transform=transform, **kwds)
-
-
-class UnitSpecWithFrame(VegaLiteSchema):
-    """UnitSpecWithFrame schema wrapper
-
-    Mapping(required=[mark])
-
-    Parameters
-    ----------
-
-    mark : :class:`AnyMark`
-        A string describing the mark type (one of ``"bar"``, ``"circle"``, ``"square"``,
-        ``"tick"``, ``"line"``, ``"area"``, ``"point"``, ``"rule"``, ``"geoshape"``, and
-        ``"text"`` ) or a `mark definition object
-        <https://vega.github.io/vega-lite/docs/mark.html#mark-def>`__.
-    data : anyOf(:class:`Data`, None)
-        An object describing the data source. Set to ``null`` to ignore the parent's data
-        source. If no data is set, it is derived from the parent.
-    description : string
-        Description of this mark for commenting purpose.
-    encoding : :class:`Encoding`
-        A key-value mapping between encoding channels and definition of fields.
-    height : anyOf(float, string, :class:`Step`)
-        The height of a visualization.
-
-
-        * For a plot with a continuous y-field, height should be a number.
-        * For a plot with either a discrete y-field or no y-field, height can be either a
-          number indicating a fixed height or an object in the form of ``{step: number}``
-          defining the height per discrete step. (No y-field is equivalent to having one
-          discrete step.)
-        * To enable responsive sizing on height, it should be set to ``"container"``.
-
-        **Default value:** Based on ``config.view.continuousHeight`` for a plot with a
-        continuous y-field and ``config.view.discreteHeight`` otherwise.
-
-        **Note:** For plots with `row and column channels
-        <https://vega.github.io/vega-lite/docs/encoding.html#facet>`__, this represents the
-        height of a single view and the ``"container"`` option cannot be used.
-
-        **See also:** `height <https://vega.github.io/vega-lite/docs/size.html>`__
-        documentation.
-    name : string
-        Name of the visualization for later reference.
-    params : List(:class:`SelectionParameter`)
-        An array of parameters that may either be simple variables, or more complex
-        selections that map user input to data queries.
-    projection : :class:`Projection`
-        An object defining properties of geographic projection, which will be applied to
-        ``shape`` path for ``"geoshape"`` marks and to ``latitude`` and ``"longitude"``
-        channels for other marks.
-    title : anyOf(:class:`Text`, :class:`TitleParams`)
-        Title for the plot.
-    transform : List(:class:`Transform`)
-        An array of data transformations such as filter and new field calculation.
-    view : :class:`ViewBackground`
-        An object defining the view background's fill and stroke.
-
-        **Default value:** none (transparent)
-    width : anyOf(float, string, :class:`Step`)
-        The width of a visualization.
-
-
-        * For a plot with a continuous x-field, width should be a number.
-        * For a plot with either a discrete x-field or no x-field, width can be either a
-          number indicating a fixed width or an object in the form of ``{step: number}``
-          defining the width per discrete step. (No x-field is equivalent to having one
-          discrete step.)
-        * To enable responsive sizing on width, it should be set to ``"container"``.
-
-        **Default value:** Based on ``config.view.continuousWidth`` for a plot with a
-        continuous x-field and ``config.view.discreteWidth`` otherwise.
-
-        **Note:** For plots with `row and column channels
-        <https://vega.github.io/vega-lite/docs/encoding.html#facet>`__, this represents the
-        width of a single view and the ``"container"`` option cannot be used.
-
-        **See also:** `width <https://vega.github.io/vega-lite/docs/size.html>`__
-        documentation.
-    """
-    _schema = {'$ref': '#/definitions/UnitSpecWithFrame'}
-
-    def __init__(self, mark=Undefined, data=Undefined, description=Undefined, encoding=Undefined,
-                 height=Undefined, name=Undefined, params=Undefined, projection=Undefined,
-                 title=Undefined, transform=Undefined, view=Undefined, width=Undefined, **kwds):
-        super(UnitSpecWithFrame, self).__init__(mark=mark, data=data, description=description,
-                                                encoding=encoding, height=height, name=name,
-                                                params=params, projection=projection, title=title,
-                                                transform=transform, view=view, width=width, **kwds)
-
-
-class UrlData(DataSource):
-    """UrlData schema wrapper
-
-    Mapping(required=[url])
-
-    Parameters
-    ----------
-
-    url : string
-        An URL from which to load the data set. Use the ``format.type`` property to ensure
-        the loaded data is correctly parsed.
-    format : :class:`DataFormat`
-        An object that specifies the format for parsing the data.
-    name : string
-        Provide a placeholder name and bind data at runtime.
-    """
-    _schema = {'$ref': '#/definitions/UrlData'}
-
-    def __init__(self, url=Undefined, format=Undefined, name=Undefined, **kwds):
-        super(UrlData, self).__init__(url=url, format=format, name=name, **kwds)
-
-
-class UtcMultiTimeUnit(MultiTimeUnit):
-    """UtcMultiTimeUnit schema wrapper
-
-    enum('utcyearquarter', 'utcyearquartermonth', 'utcyearmonth', 'utcyearmonthdate',
-    'utcyearmonthdatehours', 'utcyearmonthdatehoursminutes',
-    'utcyearmonthdatehoursminutesseconds', 'utcyearweek', 'utcyearweekday',
-    'utcyearweekdayhours', 'utcyearweekdayhoursminutes', 'utcyearweekdayhoursminutesseconds',
-    'utcyeardayofyear', 'utcquartermonth', 'utcmonthdate', 'utcmonthdatehours',
-    'utcmonthdatehoursminutes', 'utcmonthdatehoursminutesseconds', 'utcweekday',
-    'utcweeksdayhours', 'utcweekdayhoursminutes', 'utcweekdayhoursminutesseconds',
-    'utcdayhours', 'utcdayhoursminutes', 'utcdayhoursminutesseconds', 'utchoursminutes',
-    'utchoursminutesseconds', 'utcminutesseconds', 'utcsecondsmilliseconds')
-    """
-    _schema = {'$ref': '#/definitions/UtcMultiTimeUnit'}
-
-    def __init__(self, *args):
-        super(UtcMultiTimeUnit, self).__init__(*args)
-
-
-class UtcSingleTimeUnit(SingleTimeUnit):
-    """UtcSingleTimeUnit schema wrapper
-
-    enum('utcyear', 'utcquarter', 'utcmonth', 'utcweek', 'utcday', 'utcdayofyear', 'utcdate',
-    'utchours', 'utcminutes', 'utcseconds', 'utcmilliseconds')
-    """
-    _schema = {'$ref': '#/definitions/UtcSingleTimeUnit'}
-
-    def __init__(self, *args):
-        super(UtcSingleTimeUnit, self).__init__(*args)
-
-
-class VConcatSpecGenericSpec(Spec, NonNormalizedSpec):
-    """VConcatSpecGenericSpec schema wrapper
-
-    Mapping(required=[vconcat])
-    Base interface for a vertical concatenation specification.
-
-    Parameters
-    ----------
-
-    vconcat : List(:class:`Spec`)
-        A list of views to be concatenated and put into a column.
-    bounds : enum('full', 'flush')
-        The bounds calculation method to use for determining the extent of a sub-plot. One
-        of ``full`` (the default) or ``flush``.
-
-
-        * If set to ``full``, the entire calculated bounds (including axes, title, and
-          legend) will be used.
-        * If set to ``flush``, only the specified width and height values for the sub-view
-          will be used. The ``flush`` setting can be useful when attempting to place
-          sub-plots without axes or legends into a uniform grid structure.
-
-        **Default value:** ``"full"``
-    center : boolean
-        Boolean flag indicating if subviews should be centered relative to their respective
-        rows or columns.
-
-        **Default value:** ``false``
-    data : anyOf(:class:`Data`, None)
-        An object describing the data source. Set to ``null`` to ignore the parent's data
-        source. If no data is set, it is derived from the parent.
-    description : string
-        Description of this mark for commenting purpose.
-    name : string
-        Name of the visualization for later reference.
-    resolve : :class:`Resolve`
-        Scale, axis, and legend resolutions for view composition specifications.
-    spacing : float
-        The spacing in pixels between sub-views of the concat operator.
-
-        **Default value** : ``10``
-    title : anyOf(:class:`Text`, :class:`TitleParams`)
-        Title for the plot.
-    transform : List(:class:`Transform`)
-        An array of data transformations such as filter and new field calculation.
-    """
-    _schema = {'$ref': '#/definitions/VConcatSpec<GenericSpec>'}
-
-    def __init__(self, vconcat=Undefined, bounds=Undefined, center=Undefined, data=Undefined,
-                 description=Undefined, name=Undefined, resolve=Undefined, spacing=Undefined,
-                 title=Undefined, transform=Undefined, **kwds):
-        super(VConcatSpecGenericSpec, self).__init__(vconcat=vconcat, bounds=bounds, center=center,
-                                                     data=data, description=description, name=name,
-                                                     resolve=resolve, spacing=spacing, title=title,
-                                                     transform=transform, **kwds)
-
-
-class ValueDefWithConditionMarkPropFieldOrDatumDefGradientstringnull(ColorDef, MarkPropDefGradientstringnull):
-    """ValueDefWithConditionMarkPropFieldOrDatumDefGradientstringnull schema wrapper
-
-    Mapping(required=[])
-
-    Parameters
-    ----------
-
-    condition : anyOf(:class:`ConditionalMarkPropFieldOrDatumDef`, :class:`ConditionalValueDefGradientstringnullExprRef`, List(:class:`ConditionalValueDefGradientstringnullExprRef`))
-        A field definition or one or more value definition(s) with a parameter predicate.
-    value : anyOf(:class:`Gradient`, string, None, :class:`ExprRef`)
-        A constant value in visual domain (e.g., ``"red"`` / ``"#0099ff"`` / `gradient
-        definition <https://vega.github.io/vega-lite/docs/types.html#gradient>`__ for color,
-        values between ``0`` to ``1`` for opacity).
-    """
-    _schema = {'$ref': '#/definitions/ValueDefWithCondition<MarkPropFieldOrDatumDef,(Gradient|string|null)>'}
-
-    def __init__(self, condition=Undefined, value=Undefined, **kwds):
-        super(ValueDefWithConditionMarkPropFieldOrDatumDefGradientstringnull, self).__init__(condition=condition,
-                                                                                             value=value,
-                                                                                             **kwds)
-
-
-class ValueDefWithConditionMarkPropFieldOrDatumDefTypeForShapestringnull(MarkPropDefstringnullTypeForShape, ShapeDef):
-    """ValueDefWithConditionMarkPropFieldOrDatumDefTypeForShapestringnull schema wrapper
-
-    Mapping(required=[])
-
-    Parameters
-    ----------
-
-    condition : anyOf(:class:`ConditionalMarkPropFieldOrDatumDefTypeForShape`, :class:`ConditionalValueDefstringnullExprRef`, List(:class:`ConditionalValueDefstringnullExprRef`))
-        A field definition or one or more value definition(s) with a parameter predicate.
-    value : anyOf(string, None, :class:`ExprRef`)
-        A constant value in visual domain (e.g., ``"red"`` / ``"#0099ff"`` / `gradient
-        definition <https://vega.github.io/vega-lite/docs/types.html#gradient>`__ for color,
-        values between ``0`` to ``1`` for opacity).
-    """
-    _schema = {'$ref': '#/definitions/ValueDefWithCondition<MarkPropFieldOrDatumDef<TypeForShape>,(string|null)>'}
-
-    def __init__(self, condition=Undefined, value=Undefined, **kwds):
-        super(ValueDefWithConditionMarkPropFieldOrDatumDefTypeForShapestringnull, self).__init__(condition=condition,
-                                                                                                 value=value,
-                                                                                                 **kwds)
-
-
-class ValueDefWithConditionMarkPropFieldOrDatumDefnumber(MarkPropDefnumber, NumericMarkPropDef):
-    """ValueDefWithConditionMarkPropFieldOrDatumDefnumber schema wrapper
-
-    Mapping(required=[])
-
-    Parameters
-    ----------
-
-    condition : anyOf(:class:`ConditionalMarkPropFieldOrDatumDef`, :class:`ConditionalValueDefnumberExprRef`, List(:class:`ConditionalValueDefnumberExprRef`))
-        A field definition or one or more value definition(s) with a parameter predicate.
-    value : anyOf(float, :class:`ExprRef`)
-        A constant value in visual domain (e.g., ``"red"`` / ``"#0099ff"`` / `gradient
-        definition <https://vega.github.io/vega-lite/docs/types.html#gradient>`__ for color,
-        values between ``0`` to ``1`` for opacity).
-    """
-    _schema = {'$ref': '#/definitions/ValueDefWithCondition<MarkPropFieldOrDatumDef,number>'}
-
-    def __init__(self, condition=Undefined, value=Undefined, **kwds):
-        super(ValueDefWithConditionMarkPropFieldOrDatumDefnumber, self).__init__(condition=condition,
-                                                                                 value=value, **kwds)
-
-
-class ValueDefWithConditionMarkPropFieldOrDatumDefnumberArray(MarkPropDefnumberArray, NumericArrayMarkPropDef):
-    """ValueDefWithConditionMarkPropFieldOrDatumDefnumberArray schema wrapper
-
-    Mapping(required=[])
-
-    Parameters
-    ----------
-
-    condition : anyOf(:class:`ConditionalMarkPropFieldOrDatumDef`, :class:`ConditionalValueDefnumberArrayExprRef`, List(:class:`ConditionalValueDefnumberArrayExprRef`))
-        A field definition or one or more value definition(s) with a parameter predicate.
-    value : anyOf(List(float), :class:`ExprRef`)
-        A constant value in visual domain (e.g., ``"red"`` / ``"#0099ff"`` / `gradient
-        definition <https://vega.github.io/vega-lite/docs/types.html#gradient>`__ for color,
-        values between ``0`` to ``1`` for opacity).
-    """
-    _schema = {'$ref': '#/definitions/ValueDefWithCondition<MarkPropFieldOrDatumDef,number[]>'}
-
-    def __init__(self, condition=Undefined, value=Undefined, **kwds):
-        super(ValueDefWithConditionMarkPropFieldOrDatumDefnumberArray, self).__init__(condition=condition,
-                                                                                      value=value,
-                                                                                      **kwds)
-
-
-class ValueDefWithConditionMarkPropFieldOrDatumDefstringnull(VegaLiteSchema):
-    """ValueDefWithConditionMarkPropFieldOrDatumDefstringnull schema wrapper
-
-    Mapping(required=[])
-
-    Parameters
-    ----------
-
-    condition : anyOf(:class:`ConditionalMarkPropFieldOrDatumDef`, :class:`ConditionalValueDefstringnullExprRef`, List(:class:`ConditionalValueDefstringnullExprRef`))
-        A field definition or one or more value definition(s) with a parameter predicate.
-    value : anyOf(string, None, :class:`ExprRef`)
-        A constant value in visual domain (e.g., ``"red"`` / ``"#0099ff"`` / `gradient
-        definition <https://vega.github.io/vega-lite/docs/types.html#gradient>`__ for color,
-        values between ``0`` to ``1`` for opacity).
-    """
-    _schema = {'$ref': '#/definitions/ValueDefWithCondition<MarkPropFieldOrDatumDef,(string|null)>'}
-
-    def __init__(self, condition=Undefined, value=Undefined, **kwds):
-        super(ValueDefWithConditionMarkPropFieldOrDatumDefstringnull, self).__init__(condition=condition,
-                                                                                     value=value, **kwds)
-
-
-class ValueDefWithConditionStringFieldDefText(TextDef):
-    """ValueDefWithConditionStringFieldDefText schema wrapper
-
-    Mapping(required=[])
-
-    Parameters
-    ----------
-
-    condition : anyOf(:class:`ConditionalStringFieldDef`, :class:`ConditionalValueDefTextExprRef`, List(:class:`ConditionalValueDefTextExprRef`))
-        A field definition or one or more value definition(s) with a parameter predicate.
-    value : anyOf(:class:`Text`, :class:`ExprRef`)
-        A constant value in visual domain (e.g., ``"red"`` / ``"#0099ff"`` / `gradient
-        definition <https://vega.github.io/vega-lite/docs/types.html#gradient>`__ for color,
-        values between ``0`` to ``1`` for opacity).
-    """
-    _schema = {'$ref': '#/definitions/ValueDefWithCondition<StringFieldDef,Text>'}
-
-    def __init__(self, condition=Undefined, value=Undefined, **kwds):
-        super(ValueDefWithConditionStringFieldDefText, self).__init__(condition=condition, value=value,
-                                                                      **kwds)
-
-
-class ValueDefnumber(OffsetDef):
-    """ValueDefnumber schema wrapper
-
-    Mapping(required=[value])
-    Definition object for a constant value (primitive value or gradient definition) of an
-    encoding channel.
-
-    Parameters
-    ----------
-
-    value : float
-        A constant value in visual domain (e.g., ``"red"`` / ``"#0099ff"`` / `gradient
-        definition <https://vega.github.io/vega-lite/docs/types.html#gradient>`__ for color,
-        values between ``0`` to ``1`` for opacity).
-    """
-    _schema = {'$ref': '#/definitions/ValueDef<number>'}
-
-    def __init__(self, value=Undefined, **kwds):
-        super(ValueDefnumber, self).__init__(value=value, **kwds)
-
-
-class ValueDefnumberwidthheightExprRef(VegaLiteSchema):
-    """ValueDefnumberwidthheightExprRef schema wrapper
-
-    Mapping(required=[value])
-    Definition object for a constant value (primitive value or gradient definition) of an
-    encoding channel.
-
-    Parameters
-    ----------
-
-    value : anyOf(float, string, string, :class:`ExprRef`)
-        A constant value in visual domain (e.g., ``"red"`` / ``"#0099ff"`` / `gradient
-        definition <https://vega.github.io/vega-lite/docs/types.html#gradient>`__ for color,
-        values between ``0`` to ``1`` for opacity).
-    """
-    _schema = {'$ref': '#/definitions/ValueDef<(number|"width"|"height"|ExprRef)>'}
-
-    def __init__(self, value=Undefined, **kwds):
-        super(ValueDefnumberwidthheightExprRef, self).__init__(value=value, **kwds)
-
-
-class VariableParameter(TopLevelParameter):
-    """VariableParameter schema wrapper
-
-    Mapping(required=[name])
-
-    Parameters
-    ----------
-
-    name : :class:`ParameterName`
-        A unique name for the variable parameter. Parameter names should be valid JavaScript
-        identifiers: they should contain only alphanumeric characters (or "$", or "_") and
-        may not start with a digit. Reserved keywords that may not be used as parameter
-        names are "datum", "event", "item", and "parent".
-    bind : :class:`Binding`
-        Binds the parameter to an external input element such as a slider, selection list or
-        radio button group.
-    expr : :class:`Expr`
-        An expression for the value of the parameter. This expression may include other
-        parameters, in which case the parameter will automatically update in response to
-        upstream parameter changes.
-    value : Any
-        The `initial value <http://vega.github.io/vega-lite/docs/value.html>`__ of the
-        parameter.
-
-        **Default value:** ``undefined``
-    """
-    _schema = {'$ref': '#/definitions/VariableParameter'}
-
-    def __init__(self, name=Undefined, bind=Undefined, expr=Undefined, value=Undefined, **kwds):
-        super(VariableParameter, self).__init__(name=name, bind=bind, expr=expr, value=value, **kwds)
-
-
-class Vector10string(VegaLiteSchema):
-    """Vector10string schema wrapper
-
-    List(string)
-    """
-    _schema = {'$ref': '#/definitions/Vector10<string>'}
-
-    def __init__(self, *args):
-        super(Vector10string, self).__init__(*args)
-
-
-class Vector12string(VegaLiteSchema):
-    """Vector12string schema wrapper
-
-    List(string)
-    """
-    _schema = {'$ref': '#/definitions/Vector12<string>'}
-
-    def __init__(self, *args):
-        super(Vector12string, self).__init__(*args)
-
-
-class Vector2DateTime(SelectionInitInterval):
-    """Vector2DateTime schema wrapper
-
-    List(:class:`DateTime`)
-    """
-    _schema = {'$ref': '#/definitions/Vector2<DateTime>'}
-
-    def __init__(self, *args):
-        super(Vector2DateTime, self).__init__(*args)
-
-
-class Vector2Vector2number(VegaLiteSchema):
-    """Vector2Vector2number schema wrapper
-
-    List(:class:`Vector2number`)
-    """
-    _schema = {'$ref': '#/definitions/Vector2<Vector2<number>>'}
-
-    def __init__(self, *args):
-        super(Vector2Vector2number, self).__init__(*args)
-
-
-class Vector2boolean(SelectionInitInterval):
-    """Vector2boolean schema wrapper
-
-    List(boolean)
-    """
-    _schema = {'$ref': '#/definitions/Vector2<boolean>'}
-
-    def __init__(self, *args):
-        super(Vector2boolean, self).__init__(*args)
-
-
-class Vector2number(SelectionInitInterval):
-    """Vector2number schema wrapper
-
-    List(float)
-    """
-    _schema = {'$ref': '#/definitions/Vector2<number>'}
-
-    def __init__(self, *args):
-        super(Vector2number, self).__init__(*args)
-
-
-class Vector2string(SelectionInitInterval):
-    """Vector2string schema wrapper
-
-    List(string)
-    """
-    _schema = {'$ref': '#/definitions/Vector2<string>'}
-
-    def __init__(self, *args):
-        super(Vector2string, self).__init__(*args)
-
-
-class Vector3number(VegaLiteSchema):
-    """Vector3number schema wrapper
-
-    List(float)
-    """
-    _schema = {'$ref': '#/definitions/Vector3<number>'}
-
-    def __init__(self, *args):
-        super(Vector3number, self).__init__(*args)
-
-
-class Vector7string(VegaLiteSchema):
-    """Vector7string schema wrapper
-
-    List(string)
-    """
-    _schema = {'$ref': '#/definitions/Vector7<string>'}
-
-    def __init__(self, *args):
-        super(Vector7string, self).__init__(*args)
-
-
-class ViewBackground(VegaLiteSchema):
-    """ViewBackground schema wrapper
-
-    Mapping(required=[])
-
-    Parameters
-    ----------
-
-    cornerRadius : anyOf(float, :class:`ExprRef`)
-        The radius in pixels of rounded rectangles or arcs' corners.
-
-        **Default value:** ``0``
-    cursor : :class:`Cursor`
-        The mouse cursor used over the view. Any valid `CSS cursor type
-        <https://developer.mozilla.org/en-US/docs/Web/CSS/cursor#Values>`__ can be used.
-    fill : anyOf(:class:`Color`, None, :class:`ExprRef`)
-        The fill color.
-
-        **Default value:** ``undefined``
-    fillOpacity : anyOf(float, :class:`ExprRef`)
-        The fill opacity (value between [0,1]).
-
-        **Default value:** ``1``
-    opacity : anyOf(float, :class:`ExprRef`)
-        The overall opacity (value between [0,1]).
-
-        **Default value:** ``0.7`` for non-aggregate plots with ``point``, ``tick``,
-        ``circle``, or ``square`` marks or layered ``bar`` charts and ``1`` otherwise.
-    stroke : anyOf(:class:`Color`, None, :class:`ExprRef`)
-        The stroke color.
-
-        **Default value:** ``"#ddd"``
-    strokeCap : anyOf(:class:`StrokeCap`, :class:`ExprRef`)
-        The stroke cap for line ending style. One of ``"butt"``, ``"round"``, or
-        ``"square"``.
-
-        **Default value:** ``"butt"``
-    strokeDash : anyOf(List(float), :class:`ExprRef`)
-        An array of alternating stroke, space lengths for creating dashed or dotted lines.
-    strokeDashOffset : anyOf(float, :class:`ExprRef`)
-        The offset (in pixels) into which to begin drawing with the stroke dash array.
-    strokeJoin : anyOf(:class:`StrokeJoin`, :class:`ExprRef`)
-        The stroke line join method. One of ``"miter"``, ``"round"`` or ``"bevel"``.
-
-        **Default value:** ``"miter"``
-    strokeMiterLimit : anyOf(float, :class:`ExprRef`)
-        The miter limit at which to bevel a line join.
-    strokeOpacity : anyOf(float, :class:`ExprRef`)
-        The stroke opacity (value between [0,1]).
-
-        **Default value:** ``1``
-    strokeWidth : anyOf(float, :class:`ExprRef`)
-        The stroke width, in pixels.
-    style : anyOf(string, List(string))
-        A string or array of strings indicating the name of custom styles to apply to the
-        view background. A style is a named collection of mark property defaults defined
-        within the `style configuration
-        <https://vega.github.io/vega-lite/docs/mark.html#style-config>`__. If style is an
-        array, later styles will override earlier styles.
-
-        **Default value:** ``"cell"`` **Note:** Any specified view background properties
-        will augment the default style.
-    """
-    _schema = {'$ref': '#/definitions/ViewBackground'}
-
-    def __init__(self, cornerRadius=Undefined, cursor=Undefined, fill=Undefined, fillOpacity=Undefined,
-                 opacity=Undefined, stroke=Undefined, strokeCap=Undefined, strokeDash=Undefined,
-                 strokeDashOffset=Undefined, strokeJoin=Undefined, strokeMiterLimit=Undefined,
-                 strokeOpacity=Undefined, strokeWidth=Undefined, style=Undefined, **kwds):
-        super(ViewBackground, self).__init__(cornerRadius=cornerRadius, cursor=cursor, fill=fill,
-                                             fillOpacity=fillOpacity, opacity=opacity, stroke=stroke,
-                                             strokeCap=strokeCap, strokeDash=strokeDash,
-                                             strokeDashOffset=strokeDashOffset, strokeJoin=strokeJoin,
-                                             strokeMiterLimit=strokeMiterLimit,
-                                             strokeOpacity=strokeOpacity, strokeWidth=strokeWidth,
-                                             style=style, **kwds)
-
-
-class ViewConfig(VegaLiteSchema):
-    """ViewConfig schema wrapper
-
-    Mapping(required=[])
-
-    Parameters
-    ----------
-
-    clip : boolean
-        Whether the view should be clipped.
-    continuousHeight : float
-        The default height when the plot has a continuous y-field for x or latitude, or has
-        arc marks.
-
-        **Default value:** ``200``
-    continuousWidth : float
-        The default width when the plot has a continuous field for x or longitude, or has
-        arc marks.
-
-        **Default value:** ``200``
-    cornerRadius : anyOf(float, :class:`ExprRef`)
-        The radius in pixels of rounded rectangles or arcs' corners.
-
-        **Default value:** ``0``
-    cursor : :class:`Cursor`
-        The mouse cursor used over the view. Any valid `CSS cursor type
-        <https://developer.mozilla.org/en-US/docs/Web/CSS/cursor#Values>`__ can be used.
-    discreteHeight : anyOf(float, Mapping(required=[step]))
-        The default height when the plot has non arc marks and either a discrete y-field or
-        no y-field. The height can be either a number indicating a fixed height or an object
-        in the form of ``{step: number}`` defining the height per discrete step.
-
-        **Default value:** a step size based on ``config.view.step``.
-    discreteWidth : anyOf(float, Mapping(required=[step]))
-        The default width when the plot has non-arc marks and either a discrete x-field or
-        no x-field. The width can be either a number indicating a fixed width or an object
-        in the form of ``{step: number}`` defining the width per discrete step.
-
-        **Default value:** a step size based on ``config.view.step``.
-    fill : anyOf(:class:`Color`, None, :class:`ExprRef`)
-        The fill color.
-
-        **Default value:** ``undefined``
-    fillOpacity : anyOf(float, :class:`ExprRef`)
-        The fill opacity (value between [0,1]).
-
-        **Default value:** ``1``
-    opacity : anyOf(float, :class:`ExprRef`)
-        The overall opacity (value between [0,1]).
-
-        **Default value:** ``0.7`` for non-aggregate plots with ``point``, ``tick``,
-        ``circle``, or ``square`` marks or layered ``bar`` charts and ``1`` otherwise.
-    step : float
-        Default step size for x-/y- discrete fields.
-    stroke : anyOf(:class:`Color`, None, :class:`ExprRef`)
-        The stroke color.
-
-        **Default value:** ``"#ddd"``
-    strokeCap : anyOf(:class:`StrokeCap`, :class:`ExprRef`)
-        The stroke cap for line ending style. One of ``"butt"``, ``"round"``, or
-        ``"square"``.
-
-        **Default value:** ``"butt"``
-    strokeDash : anyOf(List(float), :class:`ExprRef`)
-        An array of alternating stroke, space lengths for creating dashed or dotted lines.
-    strokeDashOffset : anyOf(float, :class:`ExprRef`)
-        The offset (in pixels) into which to begin drawing with the stroke dash array.
-    strokeJoin : anyOf(:class:`StrokeJoin`, :class:`ExprRef`)
-        The stroke line join method. One of ``"miter"``, ``"round"`` or ``"bevel"``.
-
-        **Default value:** ``"miter"``
-    strokeMiterLimit : anyOf(float, :class:`ExprRef`)
-        The miter limit at which to bevel a line join.
-    strokeOpacity : anyOf(float, :class:`ExprRef`)
-        The stroke opacity (value between [0,1]).
-
-        **Default value:** ``1``
-    strokeWidth : anyOf(float, :class:`ExprRef`)
-        The stroke width, in pixels.
-    """
-    _schema = {'$ref': '#/definitions/ViewConfig'}
-
-    def __init__(self, clip=Undefined, continuousHeight=Undefined, continuousWidth=Undefined,
-                 cornerRadius=Undefined, cursor=Undefined, discreteHeight=Undefined,
-                 discreteWidth=Undefined, fill=Undefined, fillOpacity=Undefined, opacity=Undefined,
-                 step=Undefined, stroke=Undefined, strokeCap=Undefined, strokeDash=Undefined,
-                 strokeDashOffset=Undefined, strokeJoin=Undefined, strokeMiterLimit=Undefined,
-                 strokeOpacity=Undefined, strokeWidth=Undefined, **kwds):
-        super(ViewConfig, self).__init__(clip=clip, continuousHeight=continuousHeight,
-                                         continuousWidth=continuousWidth, cornerRadius=cornerRadius,
-                                         cursor=cursor, discreteHeight=discreteHeight,
-                                         discreteWidth=discreteWidth, fill=fill,
-                                         fillOpacity=fillOpacity, opacity=opacity, step=step,
-                                         stroke=stroke, strokeCap=strokeCap, strokeDash=strokeDash,
-                                         strokeDashOffset=strokeDashOffset, strokeJoin=strokeJoin,
-                                         strokeMiterLimit=strokeMiterLimit, strokeOpacity=strokeOpacity,
-                                         strokeWidth=strokeWidth, **kwds)
-
-
-class WindowEventType(VegaLiteSchema):
-    """WindowEventType schema wrapper
-
-    anyOf(:class:`EventType`, string)
-    """
-    _schema = {'$ref': '#/definitions/WindowEventType'}
-
-    def __init__(self, *args, **kwds):
-        super(WindowEventType, self).__init__(*args, **kwds)
-
-
-class EventType(WindowEventType):
-    """EventType schema wrapper
-
-    enum('click', 'dblclick', 'dragenter', 'dragleave', 'dragover', 'keydown', 'keypress',
-    'keyup', 'mousedown', 'mousemove', 'mouseout', 'mouseover', 'mouseup', 'mousewheel',
-    'pointerdown', 'pointermove', 'pointerout', 'pointerover', 'pointerup', 'timer', 'touchend',
-    'touchmove', 'touchstart', 'wheel')
-    """
-    _schema = {'$ref': '#/definitions/EventType'}
-
-    def __init__(self, *args):
-        super(EventType, self).__init__(*args)
-
-
-class WindowFieldDef(VegaLiteSchema):
-    """WindowFieldDef schema wrapper
-
-    Mapping(required=[op, as])
-
-    Parameters
-    ----------
-
-    op : anyOf(:class:`AggregateOp`, :class:`WindowOnlyOp`)
-        The window or aggregation operation to apply within a window (e.g., ``"rank"``,
-        ``"lead"``, ``"sum"``, ``"average"`` or ``"count"`` ). See the list of all supported
-        operations `here <https://vega.github.io/vega-lite/docs/window.html#ops>`__.
-    field : :class:`FieldName`
-        The data field for which to compute the aggregate or window function. This can be
-        omitted for window functions that do not operate over a field such as ``"count"``,
-        ``"rank"``, ``"dense_rank"``.
-    param : float
-        Parameter values for the window functions. Parameter values can be omitted for
-        operations that do not accept a parameter.
-
-        See the list of all supported operations and their parameters `here
-        <https://vega.github.io/vega-lite/docs/transforms/window.html>`__.
-    as : :class:`FieldName`
-        The output name for the window operation.
-    """
-    _schema = {'$ref': '#/definitions/WindowFieldDef'}
-
-    def __init__(self, op=Undefined, field=Undefined, param=Undefined, **kwds):
-        super(WindowFieldDef, self).__init__(op=op, field=field, param=param, **kwds)
-
-
-class WindowOnlyOp(VegaLiteSchema):
-    """WindowOnlyOp schema wrapper
-
-    enum('row_number', 'rank', 'dense_rank', 'percent_rank', 'cume_dist', 'ntile', 'lag',
-    'lead', 'first_value', 'last_value', 'nth_value')
-    """
-    _schema = {'$ref': '#/definitions/WindowOnlyOp'}
-
-    def __init__(self, *args):
-        super(WindowOnlyOp, self).__init__(*args)
-
-
-class WindowTransform(Transform):
-    """WindowTransform schema wrapper
-
-    Mapping(required=[window])
-
-    Parameters
-    ----------
-
-    window : List(:class:`WindowFieldDef`)
-        The definition of the fields in the window, and what calculations to use.
-    frame : List(anyOf(None, float))
-        A frame specification as a two-element array indicating how the sliding window
-        should proceed. The array entries should either be a number indicating the offset
-        from the current data object, or null to indicate unbounded rows preceding or
-        following the current data object. The default value is ``[null, 0]``, indicating
-        that the sliding window includes the current object and all preceding objects. The
-        value ``[-5, 5]`` indicates that the window should include five objects preceding
-        and five objects following the current object. Finally, ``[null, null]`` indicates
-        that the window frame should always include all data objects. If you this frame and
-        want to assign the same value to add objects, you can use the simpler `join
-        aggregate transform <https://vega.github.io/vega-lite/docs/joinaggregate.html>`__.
-        The only operators affected are the aggregation operations and the ``first_value``,
-        ``last_value``, and ``nth_value`` window operations. The other window operations are
-        not affected by this.
-
-        **Default value:** :  ``[null, 0]`` (includes the current object and all preceding
-        objects)
-    groupby : List(:class:`FieldName`)
-        The data fields for partitioning the data objects into separate windows. If
-        unspecified, all data points will be in a single window.
-    ignorePeers : boolean
-        Indicates if the sliding window frame should ignore peer values (data that are
-        considered identical by the sort criteria). The default is false, causing the window
-        frame to expand to include all peer values. If set to true, the window frame will be
-        defined by offset values only. This setting only affects those operations that
-        depend on the window frame, namely aggregation operations and the first_value,
-        last_value, and nth_value window operations.
-
-        **Default value:** ``false``
-    sort : List(:class:`SortField`)
-        A sort field definition for sorting data objects within a window. If two data
-        objects are considered equal by the comparator, they are considered "peer" values of
-        equal rank. If sort is not specified, the order is undefined: data objects are
-        processed in the order they are observed and none are considered peers (the
-        ignorePeers parameter is ignored and treated as if set to ``true`` ).
-    """
-    _schema = {'$ref': '#/definitions/WindowTransform'}
-
-    def __init__(self, window=Undefined, frame=Undefined, groupby=Undefined, ignorePeers=Undefined,
-                 sort=Undefined, **kwds):
-        super(WindowTransform, self).__init__(window=window, frame=frame, groupby=groupby,
-                                              ignorePeers=ignorePeers, sort=sort, **kwds)
-
diff --git a/spaces/profayle/TerrapinTalk/myenv/lib/python3.9/site-packages/fontTools/misc/transform.py b/spaces/profayle/TerrapinTalk/myenv/lib/python3.9/site-packages/fontTools/misc/transform.py
deleted file mode 100644
index f85b54b73121589cb8de284a5e8efe9d20fefa17..0000000000000000000000000000000000000000
--- a/spaces/profayle/TerrapinTalk/myenv/lib/python3.9/site-packages/fontTools/misc/transform.py
+++ /dev/null
@@ -1,495 +0,0 @@
-"""Affine 2D transformation matrix class.
-
-The Transform class implements various transformation matrix operations,
-both on the matrix itself, as well as on 2D coordinates.
-
-Transform instances are effectively immutable: all methods that operate on the
-transformation itself always return a new instance. This has as the
-interesting side effect that Transform instances are hashable, ie. they can be
-used as dictionary keys.
-
-This module exports the following symbols:
-
-Transform
-	this is the main class
-Identity
-	Transform instance set to the identity transformation
-Offset
-	Convenience function that returns a translating transformation
-Scale
-	Convenience function that returns a scaling transformation
-
-The DecomposedTransform class implements a transformation with separate
-translate, rotation, scale, skew, and transformation-center components.
-
-:Example:
-
-	>>> t = Transform(2, 0, 0, 3, 0, 0)
-	>>> t.transformPoint((100, 100))
-	(200, 300)
-	>>> t = Scale(2, 3)
-	>>> t.transformPoint((100, 100))
-	(200, 300)
-	>>> t.transformPoint((0, 0))
-	(0, 0)
-	>>> t = Offset(2, 3)
-	>>> t.transformPoint((100, 100))
-	(102, 103)
-	>>> t.transformPoint((0, 0))
-	(2, 3)
-	>>> t2 = t.scale(0.5)
-	>>> t2.transformPoint((100, 100))
-	(52.0, 53.0)
-	>>> import math
-	>>> t3 = t2.rotate(math.pi / 2)
-	>>> t3.transformPoint((0, 0))
-	(2.0, 3.0)
-	>>> t3.transformPoint((100, 100))
-	(-48.0, 53.0)
-	>>> t = Identity.scale(0.5).translate(100, 200).skew(0.1, 0.2)
-	>>> t.transformPoints([(0, 0), (1, 1), (100, 100)])
-	[(50.0, 100.0), (50.550167336042726, 100.60135501775433), (105.01673360427253, 160.13550177543362)]
-	>>>
-"""
-
-import math
-from typing import NamedTuple
-from dataclasses import dataclass
-
-
-__all__ = ["Transform", "Identity", "Offset", "Scale", "DecomposedTransform"]
-
-
-_EPSILON = 1e-15
-_ONE_EPSILON = 1 - _EPSILON
-_MINUS_ONE_EPSILON = -1 + _EPSILON
-
-
-def _normSinCos(v):
-    if abs(v) < _EPSILON:
-        v = 0
-    elif v > _ONE_EPSILON:
-        v = 1
-    elif v < _MINUS_ONE_EPSILON:
-        v = -1
-    return v
-
-
-class Transform(NamedTuple):
-
-    """2x2 transformation matrix plus offset, a.k.a. Affine transform.
-    Transform instances are immutable: all transforming methods, eg.
-    rotate(), return a new Transform instance.
-
-    :Example:
-
-            >>> t = Transform()
-            >>> t
-            <Transform [1 0 0 1 0 0]>
-            >>> t.scale(2)
-            <Transform [2 0 0 2 0 0]>
-            >>> t.scale(2.5, 5.5)
-            <Transform [2.5 0 0 5.5 0 0]>
-            >>>
-            >>> t.scale(2, 3).transformPoint((100, 100))
-            (200, 300)
-
-    Transform's constructor takes six arguments, all of which are
-    optional, and can be used as keyword arguments::
-
-            >>> Transform(12)
-            <Transform [12 0 0 1 0 0]>
-            >>> Transform(dx=12)
-            <Transform [1 0 0 1 12 0]>
-            >>> Transform(yx=12)
-            <Transform [1 0 12 1 0 0]>
-
-    Transform instances also behave like sequences of length 6::
-
-            >>> len(Identity)
-            6
-            >>> list(Identity)
-            [1, 0, 0, 1, 0, 0]
-            >>> tuple(Identity)
-            (1, 0, 0, 1, 0, 0)
-
-    Transform instances are comparable::
-
-            >>> t1 = Identity.scale(2, 3).translate(4, 6)
-            >>> t2 = Identity.translate(8, 18).scale(2, 3)
-            >>> t1 == t2
-            1
-
-    But beware of floating point rounding errors::
-
-            >>> t1 = Identity.scale(0.2, 0.3).translate(0.4, 0.6)
-            >>> t2 = Identity.translate(0.08, 0.18).scale(0.2, 0.3)
-            >>> t1
-            <Transform [0.2 0 0 0.3 0.08 0.18]>
-            >>> t2
-            <Transform [0.2 0 0 0.3 0.08 0.18]>
-            >>> t1 == t2
-            0
-
-    Transform instances are hashable, meaning you can use them as
-    keys in dictionaries::
-
-            >>> d = {Scale(12, 13): None}
-            >>> d
-            {<Transform [12 0 0 13 0 0]>: None}
-
-    But again, beware of floating point rounding errors::
-
-            >>> t1 = Identity.scale(0.2, 0.3).translate(0.4, 0.6)
-            >>> t2 = Identity.translate(0.08, 0.18).scale(0.2, 0.3)
-            >>> t1
-            <Transform [0.2 0 0 0.3 0.08 0.18]>
-            >>> t2
-            <Transform [0.2 0 0 0.3 0.08 0.18]>
-            >>> d = {t1: None}
-            >>> d
-            {<Transform [0.2 0 0 0.3 0.08 0.18]>: None}
-            >>> d[t2]
-            Traceback (most recent call last):
-              File "<stdin>", line 1, in ?
-            KeyError: <Transform [0.2 0 0 0.3 0.08 0.18]>
-    """
-
-    xx: float = 1
-    xy: float = 0
-    yx: float = 0
-    yy: float = 1
-    dx: float = 0
-    dy: float = 0
-
-    def transformPoint(self, p):
-        """Transform a point.
-
-        :Example:
-
-                >>> t = Transform()
-                >>> t = t.scale(2.5, 5.5)
-                >>> t.transformPoint((100, 100))
-                (250.0, 550.0)
-        """
-        (x, y) = p
-        xx, xy, yx, yy, dx, dy = self
-        return (xx * x + yx * y + dx, xy * x + yy * y + dy)
-
-    def transformPoints(self, points):
-        """Transform a list of points.
-
-        :Example:
-
-                >>> t = Scale(2, 3)
-                >>> t.transformPoints([(0, 0), (0, 100), (100, 100), (100, 0)])
-                [(0, 0), (0, 300), (200, 300), (200, 0)]
-                >>>
-        """
-        xx, xy, yx, yy, dx, dy = self
-        return [(xx * x + yx * y + dx, xy * x + yy * y + dy) for x, y in points]
-
-    def transformVector(self, v):
-        """Transform an (dx, dy) vector, treating translation as zero.
-
-        :Example:
-
-                >>> t = Transform(2, 0, 0, 2, 10, 20)
-                >>> t.transformVector((3, -4))
-                (6, -8)
-                >>>
-        """
-        (dx, dy) = v
-        xx, xy, yx, yy = self[:4]
-        return (xx * dx + yx * dy, xy * dx + yy * dy)
-
-    def transformVectors(self, vectors):
-        """Transform a list of (dx, dy) vector, treating translation as zero.
-
-        :Example:
-                >>> t = Transform(2, 0, 0, 2, 10, 20)
-                >>> t.transformVectors([(3, -4), (5, -6)])
-                [(6, -8), (10, -12)]
-                >>>
-        """
-        xx, xy, yx, yy = self[:4]
-        return [(xx * dx + yx * dy, xy * dx + yy * dy) for dx, dy in vectors]
-
-    def translate(self, x=0, y=0):
-        """Return a new transformation, translated (offset) by x, y.
-
-        :Example:
-                >>> t = Transform()
-                >>> t.translate(20, 30)
-                <Transform [1 0 0 1 20 30]>
-                >>>
-        """
-        return self.transform((1, 0, 0, 1, x, y))
-
-    def scale(self, x=1, y=None):
-        """Return a new transformation, scaled by x, y. The 'y' argument
-        may be None, which implies to use the x value for y as well.
-
-        :Example:
-                >>> t = Transform()
-                >>> t.scale(5)
-                <Transform [5 0 0 5 0 0]>
-                >>> t.scale(5, 6)
-                <Transform [5 0 0 6 0 0]>
-                >>>
-        """
-        if y is None:
-            y = x
-        return self.transform((x, 0, 0, y, 0, 0))
-
-    def rotate(self, angle):
-        """Return a new transformation, rotated by 'angle' (radians).
-
-        :Example:
-                >>> import math
-                >>> t = Transform()
-                >>> t.rotate(math.pi / 2)
-                <Transform [0 1 -1 0 0 0]>
-                >>>
-        """
-        import math
-
-        c = _normSinCos(math.cos(angle))
-        s = _normSinCos(math.sin(angle))
-        return self.transform((c, s, -s, c, 0, 0))
-
-    def skew(self, x=0, y=0):
-        """Return a new transformation, skewed by x and y.
-
-        :Example:
-                >>> import math
-                >>> t = Transform()
-                >>> t.skew(math.pi / 4)
-                <Transform [1 0 1 1 0 0]>
-                >>>
-        """
-        import math
-
-        return self.transform((1, math.tan(y), math.tan(x), 1, 0, 0))
-
-    def transform(self, other):
-        """Return a new transformation, transformed by another
-        transformation.
-
-        :Example:
-                >>> t = Transform(2, 0, 0, 3, 1, 6)
-                >>> t.transform((4, 3, 2, 1, 5, 6))
-                <Transform [8 9 4 3 11 24]>
-                >>>
-        """
-        xx1, xy1, yx1, yy1, dx1, dy1 = other
-        xx2, xy2, yx2, yy2, dx2, dy2 = self
-        return self.__class__(
-            xx1 * xx2 + xy1 * yx2,
-            xx1 * xy2 + xy1 * yy2,
-            yx1 * xx2 + yy1 * yx2,
-            yx1 * xy2 + yy1 * yy2,
-            xx2 * dx1 + yx2 * dy1 + dx2,
-            xy2 * dx1 + yy2 * dy1 + dy2,
-        )
-
-    def reverseTransform(self, other):
-        """Return a new transformation, which is the other transformation
-        transformed by self. self.reverseTransform(other) is equivalent to
-        other.transform(self).
-
-        :Example:
-                >>> t = Transform(2, 0, 0, 3, 1, 6)
-                >>> t.reverseTransform((4, 3, 2, 1, 5, 6))
-                <Transform [8 6 6 3 21 15]>
-                >>> Transform(4, 3, 2, 1, 5, 6).transform((2, 0, 0, 3, 1, 6))
-                <Transform [8 6 6 3 21 15]>
-                >>>
-        """
-        xx1, xy1, yx1, yy1, dx1, dy1 = self
-        xx2, xy2, yx2, yy2, dx2, dy2 = other
-        return self.__class__(
-            xx1 * xx2 + xy1 * yx2,
-            xx1 * xy2 + xy1 * yy2,
-            yx1 * xx2 + yy1 * yx2,
-            yx1 * xy2 + yy1 * yy2,
-            xx2 * dx1 + yx2 * dy1 + dx2,
-            xy2 * dx1 + yy2 * dy1 + dy2,
-        )
-
-    def inverse(self):
-        """Return the inverse transformation.
-
-        :Example:
-                >>> t = Identity.translate(2, 3).scale(4, 5)
-                >>> t.transformPoint((10, 20))
-                (42, 103)
-                >>> it = t.inverse()
-                >>> it.transformPoint((42, 103))
-                (10.0, 20.0)
-                >>>
-        """
-        if self == Identity:
-            return self
-        xx, xy, yx, yy, dx, dy = self
-        det = xx * yy - yx * xy
-        xx, xy, yx, yy = yy / det, -xy / det, -yx / det, xx / det
-        dx, dy = -xx * dx - yx * dy, -xy * dx - yy * dy
-        return self.__class__(xx, xy, yx, yy, dx, dy)
-
-    def toPS(self):
-        """Return a PostScript representation
-
-        :Example:
-
-                >>> t = Identity.scale(2, 3).translate(4, 5)
-                >>> t.toPS()
-                '[2 0 0 3 8 15]'
-                >>>
-        """
-        return "[%s %s %s %s %s %s]" % self
-
-    def toDecomposed(self) -> "DecomposedTransform":
-        """Decompose into a DecomposedTransform."""
-        return DecomposedTransform.fromTransform(self)
-
-    def __bool__(self):
-        """Returns True if transform is not identity, False otherwise.
-
-        :Example:
-
-                >>> bool(Identity)
-                False
-                >>> bool(Transform())
-                False
-                >>> bool(Scale(1.))
-                False
-                >>> bool(Scale(2))
-                True
-                >>> bool(Offset())
-                False
-                >>> bool(Offset(0))
-                False
-                >>> bool(Offset(2))
-                True
-        """
-        return self != Identity
-
-    def __repr__(self):
-        return "<%s [%g %g %g %g %g %g]>" % ((self.__class__.__name__,) + self)
-
-
-Identity = Transform()
-
-
-def Offset(x=0, y=0):
-    """Return the identity transformation offset by x, y.
-
-    :Example:
-            >>> Offset(2, 3)
-            <Transform [1 0 0 1 2 3]>
-            >>>
-    """
-    return Transform(1, 0, 0, 1, x, y)
-
-
-def Scale(x, y=None):
-    """Return the identity transformation scaled by x, y. The 'y' argument
-    may be None, which implies to use the x value for y as well.
-
-    :Example:
-            >>> Scale(2, 3)
-            <Transform [2 0 0 3 0 0]>
-            >>>
-    """
-    if y is None:
-        y = x
-    return Transform(x, 0, 0, y, 0, 0)
-
-
-@dataclass
-class DecomposedTransform:
-    """The DecomposedTransform class implements a transformation with separate
-    translate, rotation, scale, skew, and transformation-center components.
-    """
-
-    translateX: float = 0
-    translateY: float = 0
-    rotation: float = 0  # in degrees, counter-clockwise
-    scaleX: float = 1
-    scaleY: float = 1
-    skewX: float = 0  # in degrees, clockwise
-    skewY: float = 0  # in degrees, counter-clockwise
-    tCenterX: float = 0
-    tCenterY: float = 0
-
-    @classmethod
-    def fromTransform(self, transform):
-        # Adapted from an answer on
-        # https://math.stackexchange.com/questions/13150/extracting-rotation-scale-values-from-2d-transformation-matrix
-        a, b, c, d, x, y = transform
-
-        sx = math.copysign(1, a)
-        if sx < 0:
-            a *= sx
-            b *= sx
-
-        delta = a * d - b * c
-
-        rotation = 0
-        scaleX = scaleY = 0
-        skewX = skewY = 0
-
-        # Apply the QR-like decomposition.
-        if a != 0 or b != 0:
-            r = math.sqrt(a * a + b * b)
-            rotation = math.acos(a / r) if b >= 0 else -math.acos(a / r)
-            scaleX, scaleY = (r, delta / r)
-            skewX, skewY = (math.atan((a * c + b * d) / (r * r)), 0)
-        elif c != 0 or d != 0:
-            s = math.sqrt(c * c + d * d)
-            rotation = math.pi / 2 - (
-                math.acos(-c / s) if d >= 0 else -math.acos(c / s)
-            )
-            scaleX, scaleY = (delta / s, s)
-            skewX, skewY = (0, math.atan((a * c + b * d) / (s * s)))
-        else:
-            # a = b = c = d = 0
-            pass
-
-        return DecomposedTransform(
-            x,
-            y,
-            math.degrees(rotation),
-            scaleX * sx,
-            scaleY,
-            math.degrees(skewX) * sx,
-            math.degrees(skewY),
-            0,
-            0,
-        )
-
-    def toTransform(self):
-        """Return the Transform() equivalent of this transformation.
-
-        :Example:
-                >>> DecomposedTransform(scaleX=2, scaleY=2).toTransform()
-                <Transform [2 0 0 2 0 0]>
-                >>>
-        """
-        t = Transform()
-        t = t.translate(
-            self.translateX + self.tCenterX, self.translateY + self.tCenterY
-        )
-        t = t.rotate(math.radians(self.rotation))
-        t = t.scale(self.scaleX, self.scaleY)
-        t = t.skew(math.radians(self.skewX), math.radians(self.skewY))
-        t = t.translate(-self.tCenterX, -self.tCenterY)
-        return t
-
-
-if __name__ == "__main__":
-    import sys
-    import doctest
-
-    sys.exit(doctest.testmod().failed)
diff --git a/spaces/profayle/TerrapinTalk/myenv/lib/python3.9/site-packages/fsspec/tests/abstract/__init__.py b/spaces/profayle/TerrapinTalk/myenv/lib/python3.9/site-packages/fsspec/tests/abstract/__init__.py
deleted file mode 100644
index 45d081921ad29104bedd336dbf04fa86e1e48b7a..0000000000000000000000000000000000000000
--- a/spaces/profayle/TerrapinTalk/myenv/lib/python3.9/site-packages/fsspec/tests/abstract/__init__.py
+++ /dev/null
@@ -1,287 +0,0 @@
-import os
-from hashlib import md5
-
-import pytest
-
-from fsspec.implementations.local import LocalFileSystem
-from fsspec.tests.abstract.copy import AbstractCopyTests  # noqa
-from fsspec.tests.abstract.get import AbstractGetTests  # noqa
-from fsspec.tests.abstract.put import AbstractPutTests  # noqa
-
-
-class BaseAbstractFixtures:
-    """
-    Abstract base class containing fixtures that are used by but never need to
-    be overridden in derived filesystem-specific classes to run the abstract
-    tests on such filesystems.
-    """
-
-    @pytest.fixture
-    def fs_bulk_operations_scenario_0(self, fs, fs_join, fs_path):
-        """
-        Scenario on remote filesystem that is used for many cp/get/put tests.
-
-        Cleans up at the end of each test it which it is used.
-        """
-        source = self._bulk_operations_scenario_0(fs, fs_join, fs_path)
-        yield source
-        fs.rm(source, recursive=True)
-
-    @pytest.fixture
-    def fs_glob_edge_cases_files(self, fs, fs_join, fs_path):
-        """
-        Scenario on remote filesystem that is used for glob edge cases cp/get/put tests.
-
-        Cleans up at the end of each test it which it is used.
-        """
-        source = self._glob_edge_cases_files(fs, fs_join, fs_path)
-        yield source
-        fs.rm(source, recursive=True)
-
-    @pytest.fixture
-    def fs_dir_and_file_with_same_name_prefix(self, fs, fs_join, fs_path):
-        """
-        Scenario on remote filesystem that is used to check cp/get/put on directory
-        and file with the same name prefixes.
-
-        Cleans up at the end of each test it which it is used.
-        """
-        source = self._dir_and_file_with_same_name_prefix(fs, fs_join, fs_path)
-        yield source
-        fs.rm(source, recursive=True)
-
-    @pytest.fixture
-    def fs_10_files_with_hashed_names(self, fs, fs_join, fs_path):
-        """
-        Scenario on remote filesystem that is used to check cp/get/put files order
-        when source and destination are lists.
-
-        Cleans up at the end of each test it which it is used.
-        """
-        source = self._10_files_with_hashed_names(fs, fs_join, fs_path)
-        yield source
-        fs.rm(source, recursive=True)
-
-    @pytest.fixture
-    def fs_target(self, fs, fs_join, fs_path):
-        """
-        Return name of remote directory that does not yet exist to copy into.
-
-        Cleans up at the end of each test it which it is used.
-        """
-        target = fs_join(fs_path, "target")
-        yield target
-        if fs.exists(target):
-            fs.rm(target, recursive=True)
-
-    @pytest.fixture
-    def local_bulk_operations_scenario_0(self, local_fs, local_join, local_path):
-        """
-        Scenario on local filesystem that is used for many cp/get/put tests.
-
-        Cleans up at the end of each test it which it is used.
-        """
-        source = self._bulk_operations_scenario_0(local_fs, local_join, local_path)
-        yield source
-        local_fs.rm(source, recursive=True)
-
-    @pytest.fixture
-    def local_glob_edge_cases_files(self, local_fs, local_join, local_path):
-        """
-        Scenario on local filesystem that is used for glob edge cases cp/get/put tests.
-
-        Cleans up at the end of each test it which it is used.
-        """
-        source = self._glob_edge_cases_files(local_fs, local_join, local_path)
-        yield source
-        local_fs.rm(source, recursive=True)
-
-    @pytest.fixture
-    def local_dir_and_file_with_same_name_prefix(
-        self, local_fs, local_join, local_path
-    ):
-        """
-        Scenario on local filesystem that is used to check cp/get/put on directory
-        and file with the same name prefixes.
-
-        Cleans up at the end of each test it which it is used.
-        """
-        source = self._dir_and_file_with_same_name_prefix(
-            local_fs, local_join, local_path
-        )
-        yield source
-        local_fs.rm(source, recursive=True)
-
-    @pytest.fixture
-    def local_10_files_with_hashed_names(self, local_fs, local_join, local_path):
-        """
-        Scenario on local filesystem that is used to check cp/get/put files order
-        when source and destination are lists.
-
-        Cleans up at the end of each test it which it is used.
-        """
-        source = self._10_files_with_hashed_names(local_fs, local_join, local_path)
-        yield source
-        local_fs.rm(source, recursive=True)
-
-    @pytest.fixture
-    def local_target(self, local_fs, local_join, local_path):
-        """
-        Return name of local directory that does not yet exist to copy into.
-
-        Cleans up at the end of each test it which it is used.
-        """
-        target = local_join(local_path, "target")
-        yield target
-        if local_fs.exists(target):
-            local_fs.rm(target, recursive=True)
-
-    def _glob_edge_cases_files(self, some_fs, some_join, some_path):
-        """
-        Scenario that is used for glob edge cases cp/get/put tests.
-        Creates the following directory and file structure:
-
-        📁 source
-        ├── 📄 file1
-        ├── 📄 file2
-        ├── 📁 subdir0
-        │   ├── 📄 subfile1
-        │   ├── 📄 subfile2
-        │   └── 📁 nesteddir
-        │       └── 📄 nestedfile
-        └── 📁 subdir1
-            ├── 📄 subfile1
-            ├── 📄 subfile2
-            └── 📁 nesteddir
-                └── 📄 nestedfile
-        """
-        source = some_join(some_path, "source")
-        some_fs.touch(some_join(source, "file1"))
-        some_fs.touch(some_join(source, "file2"))
-
-        for subdir_idx in range(2):
-            subdir = some_join(source, f"subdir{subdir_idx}")
-            nesteddir = some_join(subdir, "nesteddir")
-            some_fs.makedirs(nesteddir)
-            some_fs.touch(some_join(subdir, "subfile1"))
-            some_fs.touch(some_join(subdir, "subfile2"))
-            some_fs.touch(some_join(nesteddir, "nestedfile"))
-
-        return source
-
-    def _bulk_operations_scenario_0(self, some_fs, some_join, some_path):
-        """
-        Scenario that is used for many cp/get/put tests. Creates the following
-        directory and file structure:
-
-        📁 source
-        ├── 📄 file1
-        ├── 📄 file2
-        └── 📁 subdir
-            ├── 📄 subfile1
-            ├── 📄 subfile2
-            └── 📁 nesteddir
-                └── 📄 nestedfile
-        """
-        source = some_join(some_path, "source")
-        subdir = some_join(source, "subdir")
-        nesteddir = some_join(subdir, "nesteddir")
-        some_fs.makedirs(nesteddir)
-        some_fs.touch(some_join(source, "file1"))
-        some_fs.touch(some_join(source, "file2"))
-        some_fs.touch(some_join(subdir, "subfile1"))
-        some_fs.touch(some_join(subdir, "subfile2"))
-        some_fs.touch(some_join(nesteddir, "nestedfile"))
-        return source
-
-    def _dir_and_file_with_same_name_prefix(self, some_fs, some_join, some_path):
-        """
-        Scenario that is used to check cp/get/put on directory and file with
-        the same name prefixes. Creates the following directory and file structure:
-
-        📁 source
-        ├── 📄 subdir.txt
-        └── 📁 subdir
-            └── 📄 subfile.txt
-        """
-        source = some_join(some_path, "source")
-        subdir = some_join(source, "subdir")
-        file = some_join(source, "subdir.txt")
-        subfile = some_join(subdir, "subfile.txt")
-        some_fs.makedirs(subdir)
-        some_fs.touch(file)
-        some_fs.touch(subfile)
-        return source
-
-    def _10_files_with_hashed_names(self, some_fs, some_join, some_path):
-        """
-        Scenario that is used to check cp/get/put files order when source and
-        destination are lists. Creates the following directory and file structure:
-
-        📁 source
-        └── 📄 {hashed([0-9])}.txt
-        """
-        source = some_join(some_path, "source")
-        for i in range(10):
-            hashed_i = md5(str(i).encode("utf-8")).hexdigest()
-            path = some_join(source, f"{hashed_i}.txt")
-            some_fs.pipe(path=path, value=f"{i}".encode("utf-8"))
-        return source
-
-
-class AbstractFixtures(BaseAbstractFixtures):
-    """
-    Abstract base class containing fixtures that may be overridden in derived
-    filesystem-specific classes to run the abstract tests on such filesystems.
-
-    For any particular filesystem some of these fixtures must be overridden,
-    such as ``fs`` and ``fs_path``, and others may be overridden if the
-    default functions here are not appropriate, such as ``fs_join``.
-    """
-
-    @pytest.fixture
-    def fs(self):
-        raise NotImplementedError("This function must be overridden in derived classes")
-
-    @pytest.fixture
-    def fs_join(self):
-        """
-        Return a function that joins its arguments together into a path.
-
-        Most fsspec implementations join paths in a platform-dependent way,
-        but some will override this to always use a forward slash.
-        """
-        return os.path.join
-
-    @pytest.fixture
-    def fs_path(self):
-        raise NotImplementedError("This function must be overridden in derived classes")
-
-    @pytest.fixture(scope="class")
-    def local_fs(self):
-        # Maybe need an option for auto_mkdir=False?  This is only relevant
-        # for certain implementations.
-        return LocalFileSystem(auto_mkdir=True)
-
-    @pytest.fixture
-    def local_join(self):
-        """
-        Return a function that joins its arguments together into a path, on
-        the local filesystem.
-        """
-        return os.path.join
-
-    @pytest.fixture
-    def local_path(self, tmpdir):
-        return tmpdir
-
-    @pytest.fixture
-    def supports_empty_directories(self):
-        """
-        Return whether this implementation supports empty directories.
-        """
-        return True
-
-    @pytest.fixture
-    def fs_sanitize_path(self):
-        return lambda x: x
diff --git a/spaces/profayle/TerrapinTalk/myenv/lib/python3.9/site-packages/gradio/templates/frontend/assets/Index-94cc8d8f.js b/spaces/profayle/TerrapinTalk/myenv/lib/python3.9/site-packages/gradio/templates/frontend/assets/Index-94cc8d8f.js
deleted file mode 100644
index 01414fcdf87c6781ee3fc2b49ea922949eb8ca4e..0000000000000000000000000000000000000000
--- a/spaces/profayle/TerrapinTalk/myenv/lib/python3.9/site-packages/gradio/templates/frontend/assets/Index-94cc8d8f.js
+++ /dev/null
@@ -1,2 +0,0 @@
-import{B as Z}from"./Button-8eeccca1.js";import{B as p}from"./BlockTitle-7572070c.js";import{S as y}from"./Index-c74a8b7c.js";import"./index-50ad4c77.js";import"./svelte/svelte.js";import"./Info-ba93744d.js";const{SvelteComponent:x,append:q,assign:$,attr:f,binding_callbacks:H,create_component:T,destroy_component:U,detach:L,element:E,get_spread_object:ee,get_spread_update:ne,init:ie,insert:M,listen:I,mount_component:A,run_all:le,safe_not_equal:te,set_data:ae,set_input_value:z,space:R,text:ue,to_number:D,transition_in:F,transition_out:G}=window.__gradio__svelte__internal,{afterUpdate:se}=window.__gradio__svelte__internal;function _e(e){let l;return{c(){l=ue(e[5])},m(t,s){M(t,l,s)},p(t,s){s&32&&ae(l,t[5])},d(t){t&&L(l)}}}function fe(e){let l,t,s,m,r,b,N,a,g,w,_,c,o,h,v;const k=[{autoscroll:e[1].autoscroll},{i18n:e[1].i18n},e[14]];let S={};for(let n=0;n<k.length;n+=1)S=$(S,k[n]);return l=new y({props:S}),b=new p({props:{show_label:e[13],info:e[6],$$slots:{default:[_e]},$$scope:{ctx:e}}}),{c(){T(l.$$.fragment),t=R(),s=E("div"),m=E("div"),r=E("label"),T(b.$$.fragment),N=R(),a=E("input"),w=R(),_=E("input"),f(r,"for",e[18]),f(a,"aria-label",g=`number input for ${e[5]}`),f(a,"data-testid","number-input"),f(a,"type","number"),f(a,"min",e[10]),f(a,"max",e[11]),f(a,"step",e[12]),a.disabled=e[17],f(a,"class","svelte-3iwdd6"),f(m,"class","head svelte-3iwdd6"),f(s,"class","wrap svelte-3iwdd6"),f(_,"type","range"),f(_,"id",e[18]),f(_,"name","cowbell"),f(_,"min",e[10]),f(_,"max",e[11]),f(_,"step",e[12]),_.disabled=e[17],f(_,"aria-label",c=`range slider for ${e[5]}`),f(_,"class","svelte-3iwdd6")},m(n,u){A(l,n,u),M(n,t,u),M(n,s,u),q(s,m),q(m,r),A(b,r,null),q(m,N),q(m,a),z(a,e[0]),e[24](a),M(n,w,u),M(n,_,u),z(_,e[0]),e[26](_),o=!0,h||(v=[I(a,"input",e[23]),I(a,"blur",e[20]),I(a,"pointerup",e[19]),I(_,"change",e[25]),I(_,"input",e[25]),I(_,"pointerup",e[19])],h=!0)},p(n,u){const B=u&16386?ne(k,[u&2&&{autoscroll:n[1].autoscroll},u&2&&{i18n:n[1].i18n},u&16384&&ee(n[14])]):{};l.$set(B);const d={};u&8192&&(d.show_label=n[13]),u&64&&(d.info=n[6]),u&1073741856&&(d.$$scope={dirty:u,ctx:n}),b.$set(d),(!o||u&32&&g!==(g=`number input for ${n[5]}`))&&f(a,"aria-label",g),(!o||u&1024)&&f(a,"min",n[10]),(!o||u&2048)&&f(a,"max",n[11]),(!o||u&4096)&&f(a,"step",n[12]),(!o||u&131072)&&(a.disabled=n[17]),u&1&&D(a.value)!==n[0]&&z(a,n[0]),(!o||u&1024)&&f(_,"min",n[10]),(!o||u&2048)&&f(_,"max",n[11]),(!o||u&4096)&&f(_,"step",n[12]),(!o||u&131072)&&(_.disabled=n[17]),(!o||u&32&&c!==(c=`range slider for ${n[5]}`))&&f(_,"aria-label",c),u&1&&z(_,n[0])},i(n){o||(F(l.$$.fragment,n),F(b.$$.fragment,n),o=!0)},o(n){G(l.$$.fragment,n),G(b.$$.fragment,n),o=!1},d(n){n&&(L(t),L(s),L(w),L(_)),U(l,n),U(b),e[24](null),e[26](null),h=!1,le(v)}}}function me(e){let l,t;return l=new Z({props:{visible:e[4],elem_id:e[2],elem_classes:e[3],container:e[7],scale:e[8],min_width:e[9],$$slots:{default:[fe]},$$scope:{ctx:e}}}),{c(){T(l.$$.fragment)},m(s,m){A(l,s,m),t=!0},p(s,[m]){const r={};m&16&&(r.visible=s[4]),m&4&&(r.elem_id=s[2]),m&8&&(r.elem_classes=s[3]),m&128&&(r.container=s[7]),m&256&&(r.scale=s[8]),m&512&&(r.min_width=s[9]),m&1074003043&&(r.$$scope={dirty:m,ctx:s}),l.$set(r)},i(s){t||(F(l.$$.fragment,s),t=!0)},o(s){G(l.$$.fragment,s),t=!1},d(s){U(l,s)}}}let oe=0;function re(e,l,t){let s,{gradio:m}=l,{elem_id:r=""}=l,{elem_classes:b=[]}=l,{visible:N=!0}=l,{value:a=0}=l,{label:g=m.i18n("slider.slider")}=l,{info:w=void 0}=l,{container:_=!0}=l,{scale:c=null}=l,{min_width:o=void 0}=l,{minimum:h}=l,{maximum:v}=l,{step:k}=l,{show_label:S}=l,{interactive:n}=l,{loading_status:u}=l,{value_is_output:B=!1}=l,d,j;const J=`range_id_${oe++}`;function K(){m.dispatch("change"),B||m.dispatch("input")}se(()=>{t(21,B=!1),Q()});function O(i){m.dispatch("release",a)}function P(){m.dispatch("release",a),t(0,a=Math.min(Math.max(a,h),v))}function Q(){C(),d.addEventListener("input",C),j.addEventListener("input",C)}function C(){t(15,d.style.backgroundSize=(Number(d.value)-Number(d.min))/(Number(d.max)-Number(d.min))*100+"% 100%",d)}function V(){a=D(this.value),t(0,a)}function W(i){H[i?"unshift":"push"](()=>{j=i,t(16,j)})}function X(){a=D(this.value),t(0,a)}function Y(i){H[i?"unshift":"push"](()=>{d=i,t(15,d)})}return e.$$set=i=>{"gradio"in i&&t(1,m=i.gradio),"elem_id"in i&&t(2,r=i.elem_id),"elem_classes"in i&&t(3,b=i.elem_classes),"visible"in i&&t(4,N=i.visible),"value"in i&&t(0,a=i.value),"label"in i&&t(5,g=i.label),"info"in i&&t(6,w=i.info),"container"in i&&t(7,_=i.container),"scale"in i&&t(8,c=i.scale),"min_width"in i&&t(9,o=i.min_width),"minimum"in i&&t(10,h=i.minimum),"maximum"in i&&t(11,v=i.maximum),"step"in i&&t(12,k=i.step),"show_label"in i&&t(13,S=i.show_label),"interactive"in i&&t(22,n=i.interactive),"loading_status"in i&&t(14,u=i.loading_status),"value_is_output"in i&&t(21,B=i.value_is_output)},e.$$.update=()=>{e.$$.dirty&4194304&&t(17,s=!n),e.$$.dirty&1&&K()},[a,m,r,b,N,g,w,_,c,o,h,v,k,S,u,d,j,s,J,O,P,B,n,V,W,X,Y]}class ve extends x{constructor(l){super(),ie(this,l,re,me,te,{gradio:1,elem_id:2,elem_classes:3,visible:4,value:0,label:5,info:6,container:7,scale:8,min_width:9,minimum:10,maximum:11,step:12,show_label:13,interactive:22,loading_status:14,value_is_output:21})}}export{ve as default};
-//# sourceMappingURL=Index-94cc8d8f.js.map
diff --git a/spaces/profayle/TerrapinTalk/myenv/lib/python3.9/site-packages/matplotlib/tests/test_legend.py b/spaces/profayle/TerrapinTalk/myenv/lib/python3.9/site-packages/matplotlib/tests/test_legend.py
deleted file mode 100644
index 759ac6aadaff0afbfb1811a8f40b1590ebb383ce..0000000000000000000000000000000000000000
--- a/spaces/profayle/TerrapinTalk/myenv/lib/python3.9/site-packages/matplotlib/tests/test_legend.py
+++ /dev/null
@@ -1,1343 +0,0 @@
-import collections
-import platform
-from unittest import mock
-import warnings
-
-import numpy as np
-from numpy.testing import assert_allclose
-import pytest
-
-from matplotlib.testing.decorators import check_figures_equal, image_comparison
-from matplotlib.testing._markers import needs_usetex
-import matplotlib.pyplot as plt
-import matplotlib as mpl
-import matplotlib.patches as mpatches
-import matplotlib.transforms as mtransforms
-import matplotlib.collections as mcollections
-import matplotlib.lines as mlines
-from matplotlib.legend_handler import HandlerTuple
-import matplotlib.legend as mlegend
-from matplotlib import _api, rc_context
-from matplotlib.font_manager import FontProperties
-
-
-def test_legend_ordereddict():
-    # smoketest that ordereddict inputs work...
-
-    X = np.random.randn(10)
-    Y = np.random.randn(10)
-    labels = ['a'] * 5 + ['b'] * 5
-    colors = ['r'] * 5 + ['g'] * 5
-
-    fig, ax = plt.subplots()
-    for x, y, label, color in zip(X, Y, labels, colors):
-        ax.scatter(x, y, label=label, c=color)
-
-    handles, labels = ax.get_legend_handles_labels()
-    legend = collections.OrderedDict(zip(labels, handles))
-    ax.legend(legend.values(), legend.keys(),
-              loc='center left', bbox_to_anchor=(1, .5))
-
-
-@image_comparison(['legend_auto1'], remove_text=True)
-def test_legend_auto1():
-    """Test automatic legend placement"""
-    fig, ax = plt.subplots()
-    x = np.arange(100)
-    ax.plot(x, 50 - x, 'o', label='y=1')
-    ax.plot(x, x - 50, 'o', label='y=-1')
-    ax.legend(loc='best')
-
-
-@image_comparison(['legend_auto2'], remove_text=True)
-def test_legend_auto2():
-    """Test automatic legend placement"""
-    fig, ax = plt.subplots()
-    x = np.arange(100)
-    b1 = ax.bar(x, x, align='edge', color='m')
-    b2 = ax.bar(x, x[::-1], align='edge', color='g')
-    ax.legend([b1[0], b2[0]], ['up', 'down'], loc='best')
-
-
-@image_comparison(['legend_auto3'])
-def test_legend_auto3():
-    """Test automatic legend placement"""
-    fig, ax = plt.subplots()
-    x = [0.9, 0.1, 0.1, 0.9, 0.9, 0.5]
-    y = [0.95, 0.95, 0.05, 0.05, 0.5, 0.5]
-    ax.plot(x, y, 'o-', label='line')
-    ax.set_xlim(0.0, 1.0)
-    ax.set_ylim(0.0, 1.0)
-    ax.legend(loc='best')
-
-
-def test_legend_auto4():
-    """
-    Check that the legend location with automatic placement is the same,
-    whatever the histogram type is. Related to issue #9580.
-    """
-    # NB: barstacked is pointless with a single dataset.
-    fig, axs = plt.subplots(ncols=3, figsize=(6.4, 2.4))
-    leg_bboxes = []
-    for ax, ht in zip(axs.flat, ('bar', 'step', 'stepfilled')):
-        ax.set_title(ht)
-        # A high bar on the left but an even higher one on the right.
-        ax.hist([0] + 5*[9], bins=range(10), label="Legend", histtype=ht)
-        leg = ax.legend(loc="best")
-        fig.canvas.draw()
-        leg_bboxes.append(
-            leg.get_window_extent().transformed(ax.transAxes.inverted()))
-
-    # The histogram type "bar" is assumed to be the correct reference.
-    assert_allclose(leg_bboxes[1].bounds, leg_bboxes[0].bounds)
-    assert_allclose(leg_bboxes[2].bounds, leg_bboxes[0].bounds)
-
-
-def test_legend_auto5():
-    """
-    Check that the automatic placement handle a rather complex
-    case with non rectangular patch. Related to issue #9580.
-    """
-    fig, axs = plt.subplots(ncols=2, figsize=(9.6, 4.8))
-
-    leg_bboxes = []
-    for ax, loc in zip(axs.flat, ("center", "best")):
-        # An Ellipse patch at the top, a U-shaped Polygon patch at the
-        # bottom and a ring-like Wedge patch: the correct placement of
-        # the legend should be in the center.
-        for _patch in [
-                mpatches.Ellipse(
-                    xy=(0.5, 0.9), width=0.8, height=0.2, fc="C1"),
-                mpatches.Polygon(np.array([
-                    [0, 1], [0, 0], [1, 0], [1, 1], [0.9, 1.0], [0.9, 0.1],
-                    [0.1, 0.1], [0.1, 1.0], [0.1, 1.0]]), fc="C1"),
-                mpatches.Wedge((0.5, 0.5), 0.5, 0, 360, width=0.05, fc="C0")
-                ]:
-            ax.add_patch(_patch)
-
-        ax.plot([0.1, 0.9], [0.9, 0.9], label="A segment")  # sthg to label
-
-        leg = ax.legend(loc=loc)
-        fig.canvas.draw()
-        leg_bboxes.append(
-            leg.get_window_extent().transformed(ax.transAxes.inverted()))
-
-    assert_allclose(leg_bboxes[1].bounds, leg_bboxes[0].bounds)
-
-
-@image_comparison(['legend_various_labels'], remove_text=True)
-def test_various_labels():
-    # tests all sorts of label types
-    fig = plt.figure()
-    ax = fig.add_subplot(121)
-    ax.plot(np.arange(4), 'o', label=1)
-    ax.plot(np.linspace(4, 4.1), 'o', label='Développés')
-    ax.plot(np.arange(4, 1, -1), 'o', label='__nolegend__')
-    ax.legend(numpoints=1, loc='best')
-
-
-def test_legend_label_with_leading_underscore():
-    """
-    Test that artists with labels starting with an underscore are not added to
-    the legend, and that a warning is issued if one tries to add them
-    explicitly.
-    """
-    fig, ax = plt.subplots()
-    line, = ax.plot([0, 1], label='_foo')
-    with pytest.warns(_api.MatplotlibDeprecationWarning, match="with an underscore"):
-        legend = ax.legend(handles=[line])
-    assert len(legend.legend_handles) == 0
-
-
-@image_comparison(['legend_labels_first.png'], remove_text=True)
-def test_labels_first():
-    # test labels to left of markers
-    fig, ax = plt.subplots()
-    ax.plot(np.arange(10), '-o', label=1)
-    ax.plot(np.ones(10)*5, ':x', label="x")
-    ax.plot(np.arange(20, 10, -1), 'd', label="diamond")
-    ax.legend(loc='best', markerfirst=False)
-
-
-@image_comparison(['legend_multiple_keys.png'], remove_text=True)
-def test_multiple_keys():
-    # test legend entries with multiple keys
-    fig, ax = plt.subplots()
-    p1, = ax.plot([1, 2, 3], '-o')
-    p2, = ax.plot([2, 3, 4], '-x')
-    p3, = ax.plot([3, 4, 5], '-d')
-    ax.legend([(p1, p2), (p2, p1), p3], ['two keys', 'pad=0', 'one key'],
-              numpoints=1,
-              handler_map={(p1, p2): HandlerTuple(ndivide=None),
-                           (p2, p1): HandlerTuple(ndivide=None, pad=0)})
-
-
-@image_comparison(['rgba_alpha.png'], remove_text=True,
-                  tol=0 if platform.machine() == 'x86_64' else 0.01)
-def test_alpha_rgba():
-    fig, ax = plt.subplots()
-    ax.plot(range(10), lw=5)
-    leg = plt.legend(['Longlabel that will go away'], loc='center')
-    leg.legendPatch.set_facecolor([1, 0, 0, 0.5])
-
-
-@image_comparison(['rcparam_alpha.png'], remove_text=True,
-                  tol=0 if platform.machine() == 'x86_64' else 0.01)
-def test_alpha_rcparam():
-    fig, ax = plt.subplots()
-    ax.plot(range(10), lw=5)
-    with mpl.rc_context(rc={'legend.framealpha': .75}):
-        leg = plt.legend(['Longlabel that will go away'], loc='center')
-        # this alpha is going to be over-ridden by the rcparam with
-        # sets the alpha of the patch to be non-None which causes the alpha
-        # value of the face color to be discarded.  This behavior may not be
-        # ideal, but it is what it is and we should keep track of it changing
-        leg.legendPatch.set_facecolor([1, 0, 0, 0.5])
-
-
-@image_comparison(['fancy'], remove_text=True, tol=0.05)
-def test_fancy():
-    # Tolerance caused by changing default shadow "shade" from 0.3 to 1 - 0.7 =
-    # 0.30000000000000004
-    # using subplot triggers some offsetbox functionality untested elsewhere
-    plt.subplot(121)
-    plt.plot([5] * 10, 'o--', label='XX')
-    plt.scatter(np.arange(10), np.arange(10, 0, -1), label='XX\nXX')
-    plt.errorbar(np.arange(10), np.arange(10), xerr=0.5,
-                 yerr=0.5, label='XX')
-    plt.legend(loc="center left", bbox_to_anchor=[1.0, 0.5],
-               ncols=2, shadow=True, title="My legend", numpoints=1)
-
-
-@image_comparison(['framealpha'], remove_text=True,
-                  tol=0 if platform.machine() == 'x86_64' else 0.02)
-def test_framealpha():
-    x = np.linspace(1, 100, 100)
-    y = x
-    plt.plot(x, y, label='mylabel', lw=10)
-    plt.legend(framealpha=0.5)
-
-
-@image_comparison(['scatter_rc3', 'scatter_rc1'], remove_text=True)
-def test_rc():
-    # using subplot triggers some offsetbox functionality untested elsewhere
-    plt.figure()
-    ax = plt.subplot(121)
-    ax.scatter(np.arange(10), np.arange(10, 0, -1), label='three')
-    ax.legend(loc="center left", bbox_to_anchor=[1.0, 0.5],
-              title="My legend")
-
-    mpl.rcParams['legend.scatterpoints'] = 1
-    plt.figure()
-    ax = plt.subplot(121)
-    ax.scatter(np.arange(10), np.arange(10, 0, -1), label='one')
-    ax.legend(loc="center left", bbox_to_anchor=[1.0, 0.5],
-              title="My legend")
-
-
-@image_comparison(['legend_expand'], remove_text=True)
-def test_legend_expand():
-    """Test expand mode"""
-    legend_modes = [None, "expand"]
-    fig, axs = plt.subplots(len(legend_modes), 1)
-    x = np.arange(100)
-    for ax, mode in zip(axs, legend_modes):
-        ax.plot(x, 50 - x, 'o', label='y=1')
-        l1 = ax.legend(loc='upper left', mode=mode)
-        ax.add_artist(l1)
-        ax.plot(x, x - 50, 'o', label='y=-1')
-        l2 = ax.legend(loc='right', mode=mode)
-        ax.add_artist(l2)
-        ax.legend(loc='lower left', mode=mode, ncols=2)
-
-
-@image_comparison(['hatching'], remove_text=True, style='default')
-def test_hatching():
-    # Remove legend texts when this image is regenerated.
-    # Remove this line when this test image is regenerated.
-    plt.rcParams['text.kerning_factor'] = 6
-
-    fig, ax = plt.subplots()
-
-    # Patches
-    patch = plt.Rectangle((0, 0), 0.3, 0.3, hatch='xx',
-                          label='Patch\ndefault color\nfilled')
-    ax.add_patch(patch)
-    patch = plt.Rectangle((0.33, 0), 0.3, 0.3, hatch='||', edgecolor='C1',
-                          label='Patch\nexplicit color\nfilled')
-    ax.add_patch(patch)
-    patch = plt.Rectangle((0, 0.4), 0.3, 0.3, hatch='xx', fill=False,
-                          label='Patch\ndefault color\nunfilled')
-    ax.add_patch(patch)
-    patch = plt.Rectangle((0.33, 0.4), 0.3, 0.3, hatch='||', fill=False,
-                          edgecolor='C1',
-                          label='Patch\nexplicit color\nunfilled')
-    ax.add_patch(patch)
-
-    # Paths
-    ax.fill_between([0, .15, .3], [.8, .8, .8], [.9, 1.0, .9],
-                    hatch='+', label='Path\ndefault color')
-    ax.fill_between([.33, .48, .63], [.8, .8, .8], [.9, 1.0, .9],
-                    hatch='+', edgecolor='C2', label='Path\nexplicit color')
-
-    ax.set_xlim(-0.01, 1.1)
-    ax.set_ylim(-0.01, 1.1)
-    ax.legend(handlelength=4, handleheight=4)
-
-
-def test_legend_remove():
-    fig, ax = plt.subplots()
-    lines = ax.plot(range(10))
-    leg = fig.legend(lines, "test")
-    leg.remove()
-    assert fig.legends == []
-    leg = ax.legend("test")
-    leg.remove()
-    assert ax.get_legend() is None
-
-
-def test_reverse_legend_handles_and_labels():
-    """Check that the legend handles and labels are reversed."""
-    fig, ax = plt.subplots()
-    x = 1
-    y = 1
-    labels = ["First label", "Second label", "Third label"]
-    markers = ['.', ',', 'o']
-
-    ax.plot(x, y, markers[0], label=labels[0])
-    ax.plot(x, y, markers[1], label=labels[1])
-    ax.plot(x, y, markers[2], label=labels[2])
-    leg = ax.legend(reverse=True)
-    actual_labels = [t.get_text() for t in leg.get_texts()]
-    actual_markers = [h.get_marker() for h in leg.legend_handles]
-    assert actual_labels == list(reversed(labels))
-    assert actual_markers == list(reversed(markers))
-
-
-@check_figures_equal(extensions=["png"])
-def test_reverse_legend_display(fig_test, fig_ref):
-    """Check that the rendered legend entries are reversed"""
-    ax = fig_test.subplots()
-    ax.plot([1], 'ro', label="first")
-    ax.plot([2], 'bx', label="second")
-    ax.legend(reverse=True)
-
-    ax = fig_ref.subplots()
-    ax.plot([2], 'bx', label="second")
-    ax.plot([1], 'ro', label="first")
-    ax.legend()
-
-
-class TestLegendFunction:
-    # Tests the legend function on the Axes and pyplot.
-    def test_legend_no_args(self):
-        lines = plt.plot(range(10), label='hello world')
-        with mock.patch('matplotlib.legend.Legend') as Legend:
-            plt.legend()
-        Legend.assert_called_with(plt.gca(), lines, ['hello world'])
-
-    def test_legend_positional_handles_labels(self):
-        lines = plt.plot(range(10))
-        with mock.patch('matplotlib.legend.Legend') as Legend:
-            plt.legend(lines, ['hello world'])
-        Legend.assert_called_with(plt.gca(), lines, ['hello world'])
-
-    def test_legend_positional_handles_only(self):
-        lines = plt.plot(range(10))
-        with pytest.raises(TypeError, match='but found an Artist'):
-            # a single arg is interpreted as labels
-            # it's a common error to just pass handles
-            plt.legend(lines)
-
-    def test_legend_positional_labels_only(self):
-        lines = plt.plot(range(10), label='hello world')
-        with mock.patch('matplotlib.legend.Legend') as Legend:
-            plt.legend(['foobar'])
-        Legend.assert_called_with(plt.gca(), lines, ['foobar'])
-
-    def test_legend_three_args(self):
-        lines = plt.plot(range(10), label='hello world')
-        with mock.patch('matplotlib.legend.Legend') as Legend:
-            plt.legend(lines, ['foobar'], loc='right')
-        Legend.assert_called_with(plt.gca(), lines, ['foobar'], loc='right')
-
-    def test_legend_handler_map(self):
-        lines = plt.plot(range(10), label='hello world')
-        with mock.patch('matplotlib.legend.'
-                        '_get_legend_handles_labels') as handles_labels:
-            handles_labels.return_value = lines, ['hello world']
-            plt.legend(handler_map={'1': 2})
-        handles_labels.assert_called_with([plt.gca()], {'1': 2})
-
-    def test_legend_kwargs_handles_only(self):
-        fig, ax = plt.subplots()
-        x = np.linspace(0, 1, 11)
-        ln1, = ax.plot(x, x, label='x')
-        ln2, = ax.plot(x, 2*x, label='2x')
-        ln3, = ax.plot(x, 3*x, label='3x')
-        with mock.patch('matplotlib.legend.Legend') as Legend:
-            ax.legend(handles=[ln3, ln2])  # reversed and not ln1
-        Legend.assert_called_with(ax, [ln3, ln2], ['3x', '2x'])
-
-    def test_legend_kwargs_labels_only(self):
-        fig, ax = plt.subplots()
-        x = np.linspace(0, 1, 11)
-        ln1, = ax.plot(x, x)
-        ln2, = ax.plot(x, 2*x)
-        with mock.patch('matplotlib.legend.Legend') as Legend:
-            ax.legend(labels=['x', '2x'])
-        Legend.assert_called_with(ax, [ln1, ln2], ['x', '2x'])
-
-    def test_legend_kwargs_handles_labels(self):
-        fig, ax = plt.subplots()
-        th = np.linspace(0, 2*np.pi, 1024)
-        lns, = ax.plot(th, np.sin(th), label='sin')
-        lnc, = ax.plot(th, np.cos(th), label='cos')
-        with mock.patch('matplotlib.legend.Legend') as Legend:
-            # labels of lns, lnc are overwritten with explicit ('a', 'b')
-            ax.legend(labels=('a', 'b'), handles=(lnc, lns))
-        Legend.assert_called_with(ax, (lnc, lns), ('a', 'b'))
-
-    def test_warn_mixed_args_and_kwargs(self):
-        fig, ax = plt.subplots()
-        th = np.linspace(0, 2*np.pi, 1024)
-        lns, = ax.plot(th, np.sin(th), label='sin')
-        lnc, = ax.plot(th, np.cos(th), label='cos')
-        with pytest.warns(UserWarning) as record:
-            ax.legend((lnc, lns), labels=('a', 'b'))
-        assert len(record) == 1
-        assert str(record[0].message) == (
-            "You have mixed positional and keyword arguments, some input may "
-            "be discarded.")
-
-    def test_parasite(self):
-        from mpl_toolkits.axes_grid1 import host_subplot  # type: ignore
-
-        host = host_subplot(111)
-        par = host.twinx()
-
-        p1, = host.plot([0, 1, 2], [0, 1, 2], label="Density")
-        p2, = par.plot([0, 1, 2], [0, 3, 2], label="Temperature")
-
-        with mock.patch('matplotlib.legend.Legend') as Legend:
-            plt.legend()
-        Legend.assert_called_with(host, [p1, p2], ['Density', 'Temperature'])
-
-
-class TestLegendFigureFunction:
-    # Tests the legend function for figure
-    def test_legend_handle_label(self):
-        fig, ax = plt.subplots()
-        lines = ax.plot(range(10))
-        with mock.patch('matplotlib.legend.Legend') as Legend:
-            fig.legend(lines, ['hello world'])
-        Legend.assert_called_with(fig, lines, ['hello world'],
-                                  bbox_transform=fig.transFigure)
-
-    def test_legend_no_args(self):
-        fig, ax = plt.subplots()
-        lines = ax.plot(range(10), label='hello world')
-        with mock.patch('matplotlib.legend.Legend') as Legend:
-            fig.legend()
-        Legend.assert_called_with(fig, lines, ['hello world'],
-                                  bbox_transform=fig.transFigure)
-
-    def test_legend_label_arg(self):
-        fig, ax = plt.subplots()
-        lines = ax.plot(range(10))
-        with mock.patch('matplotlib.legend.Legend') as Legend:
-            fig.legend(['foobar'])
-        Legend.assert_called_with(fig, lines, ['foobar'],
-                                  bbox_transform=fig.transFigure)
-
-    def test_legend_label_three_args(self):
-        fig, ax = plt.subplots()
-        lines = ax.plot(range(10))
-        with pytest.raises(TypeError, match="0-2"):
-            fig.legend(lines, ['foobar'], 'right')
-        with pytest.raises(TypeError, match="0-2"):
-            fig.legend(lines, ['foobar'], 'right', loc='left')
-
-    def test_legend_kw_args(self):
-        fig, axs = plt.subplots(1, 2)
-        lines = axs[0].plot(range(10))
-        lines2 = axs[1].plot(np.arange(10) * 2.)
-        with mock.patch('matplotlib.legend.Legend') as Legend:
-            fig.legend(loc='right', labels=('a', 'b'), handles=(lines, lines2))
-        Legend.assert_called_with(
-            fig, (lines, lines2), ('a', 'b'), loc='right',
-            bbox_transform=fig.transFigure)
-
-    def test_warn_args_kwargs(self):
-        fig, axs = plt.subplots(1, 2)
-        lines = axs[0].plot(range(10))
-        lines2 = axs[1].plot(np.arange(10) * 2.)
-        with pytest.warns(UserWarning) as record:
-            fig.legend((lines, lines2), labels=('a', 'b'))
-        assert len(record) == 1
-        assert str(record[0].message) == (
-            "You have mixed positional and keyword arguments, some input may "
-            "be discarded.")
-
-
-def test_figure_legend_outside():
-    todos = ['upper ' + pos for pos in ['left', 'center', 'right']]
-    todos += ['lower ' + pos for pos in ['left', 'center', 'right']]
-    todos += ['left ' + pos for pos in ['lower', 'center', 'upper']]
-    todos += ['right ' + pos for pos in ['lower', 'center', 'upper']]
-
-    upperext = [20.347556,  27.722556, 790.583, 545.499]
-    lowerext = [20.347556,  71.056556, 790.583, 588.833]
-    leftext = [151.681556, 27.722556, 790.583, 588.833]
-    rightext = [20.347556,  27.722556, 659.249, 588.833]
-    axbb = [upperext, upperext, upperext,
-            lowerext, lowerext, lowerext,
-            leftext, leftext, leftext,
-            rightext, rightext, rightext]
-
-    legbb = [[10., 555., 133., 590.],     # upper left
-             [338.5, 555., 461.5, 590.],  # upper center
-             [667, 555., 790.,  590.],    # upper right
-             [10., 10., 133.,  45.],      # lower left
-             [338.5, 10., 461.5,  45.],   # lower center
-             [667., 10., 790.,  45.],     # lower right
-             [10., 10., 133., 45.],       # left lower
-             [10., 282.5, 133., 317.5],   # left center
-             [10., 555., 133., 590.],     # left upper
-             [667, 10., 790., 45.],       # right lower
-             [667., 282.5, 790., 317.5],  # right center
-             [667., 555., 790., 590.]]    # right upper
-
-    for nn, todo in enumerate(todos):
-        print(todo)
-        fig, axs = plt.subplots(constrained_layout=True, dpi=100)
-        axs.plot(range(10), label='Boo1')
-        leg = fig.legend(loc='outside ' + todo)
-        fig.draw_without_rendering()
-
-        assert_allclose(axs.get_window_extent().extents,
-                        axbb[nn])
-        assert_allclose(leg.get_window_extent().extents,
-                        legbb[nn])
-
-
-@image_comparison(['legend_stackplot.png'])
-def test_legend_stackplot():
-    """Test legend for PolyCollection using stackplot."""
-    # related to #1341, #1943, and PR #3303
-    fig, ax = plt.subplots()
-    x = np.linspace(0, 10, 10)
-    y1 = 1.0 * x
-    y2 = 2.0 * x + 1
-    y3 = 3.0 * x + 2
-    ax.stackplot(x, y1, y2, y3, labels=['y1', 'y2', 'y3'])
-    ax.set_xlim((0, 10))
-    ax.set_ylim((0, 70))
-    ax.legend(loc='best')
-
-
-def test_cross_figure_patch_legend():
-    fig, ax = plt.subplots()
-    fig2, ax2 = plt.subplots()
-
-    brs = ax.bar(range(3), range(3))
-    fig2.legend(brs, 'foo')
-
-
-def test_nanscatter():
-    fig, ax = plt.subplots()
-
-    h = ax.scatter([np.nan], [np.nan], marker="o",
-                   facecolor="r", edgecolor="r", s=3)
-
-    ax.legend([h], ["scatter"])
-
-    fig, ax = plt.subplots()
-    for color in ['red', 'green', 'blue']:
-        n = 750
-        x, y = np.random.rand(2, n)
-        scale = 200.0 * np.random.rand(n)
-        ax.scatter(x, y, c=color, s=scale, label=color,
-                   alpha=0.3, edgecolors='none')
-
-    ax.legend()
-    ax.grid(True)
-
-
-def test_legend_repeatcheckok():
-    fig, ax = plt.subplots()
-    ax.scatter(0.0, 1.0, color='k', marker='o', label='test')
-    ax.scatter(0.5, 0.0, color='r', marker='v', label='test')
-    ax.legend()
-    hand, lab = mlegend._get_legend_handles_labels([ax])
-    assert len(lab) == 2
-    fig, ax = plt.subplots()
-    ax.scatter(0.0, 1.0, color='k', marker='o', label='test')
-    ax.scatter(0.5, 0.0, color='k', marker='v', label='test')
-    ax.legend()
-    hand, lab = mlegend._get_legend_handles_labels([ax])
-    assert len(lab) == 2
-
-
-@image_comparison(['not_covering_scatter.png'])
-def test_not_covering_scatter():
-    colors = ['b', 'g', 'r']
-
-    for n in range(3):
-        plt.scatter([n], [n], color=colors[n])
-
-    plt.legend(['foo', 'foo', 'foo'], loc='best')
-    plt.gca().set_xlim(-0.5, 2.2)
-    plt.gca().set_ylim(-0.5, 2.2)
-
-
-@image_comparison(['not_covering_scatter_transform.png'])
-def test_not_covering_scatter_transform():
-    # Offsets point to top left, the default auto position
-    offset = mtransforms.Affine2D().translate(-20, 20)
-    x = np.linspace(0, 30, 1000)
-    plt.plot(x, x)
-
-    plt.scatter([20], [10], transform=offset + plt.gca().transData)
-
-    plt.legend(['foo', 'bar'], loc='best')
-
-
-def test_linecollection_scaled_dashes():
-    lines1 = [[(0, .5), (.5, 1)], [(.3, .6), (.2, .2)]]
-    lines2 = [[[0.7, .2], [.8, .4]], [[.5, .7], [.6, .1]]]
-    lines3 = [[[0.6, .2], [.8, .4]], [[.5, .7], [.1, .1]]]
-    lc1 = mcollections.LineCollection(lines1, linestyles="--", lw=3)
-    lc2 = mcollections.LineCollection(lines2, linestyles="-.")
-    lc3 = mcollections.LineCollection(lines3, linestyles=":", lw=.5)
-
-    fig, ax = plt.subplots()
-    ax.add_collection(lc1)
-    ax.add_collection(lc2)
-    ax.add_collection(lc3)
-
-    leg = ax.legend([lc1, lc2, lc3], ["line1", "line2", 'line 3'])
-    h1, h2, h3 = leg.legend_handles
-
-    for oh, lh in zip((lc1, lc2, lc3), (h1, h2, h3)):
-        assert oh.get_linestyles()[0] == lh._dash_pattern
-
-
-def test_handler_numpoints():
-    """Test legend handler with numpoints <= 1."""
-    # related to #6921 and PR #8478
-    fig, ax = plt.subplots()
-    ax.plot(range(5), label='test')
-    ax.legend(numpoints=0.5)
-
-
-def test_text_nohandler_warning():
-    """Test that Text artists with labels raise a warning"""
-    fig, ax = plt.subplots()
-    ax.text(x=0, y=0, s="text", label="label")
-    with pytest.warns(UserWarning) as record:
-        ax.legend()
-    assert len(record) == 1
-
-    # this should _not_ warn:
-    f, ax = plt.subplots()
-    ax.pcolormesh(np.random.uniform(0, 1, (10, 10)))
-    with warnings.catch_warnings():
-        warnings.simplefilter("error")
-        ax.get_legend_handles_labels()
-
-
-def test_empty_bar_chart_with_legend():
-    """Test legend when bar chart is empty with a label."""
-    # related to issue #13003. Calling plt.legend() should not
-    # raise an IndexError.
-    plt.bar([], [], label='test')
-    plt.legend()
-
-
-@image_comparison(['shadow_argument_types.png'], remove_text=True,
-                  style='mpl20')
-def test_shadow_argument_types():
-    # Test that different arguments for shadow work as expected
-    fig, ax = plt.subplots()
-    ax.plot([1, 2, 3], label='test')
-
-    # Test various shadow configurations
-    # as well as different ways of specifying colors
-    legs = (ax.legend(loc='upper left', shadow=True),    # True
-            ax.legend(loc='upper right', shadow=False),  # False
-            ax.legend(loc='center left',                 # string
-                      shadow={'color': 'red', 'alpha': 0.1}),
-            ax.legend(loc='center right',                # tuple
-                      shadow={'color': (0.1, 0.2, 0.5), 'oy': -5}),
-            ax.legend(loc='lower left',                   # tab
-                      shadow={'color': 'tab:cyan', 'ox': 10})
-            )
-    for l in legs:
-        ax.add_artist(l)
-    ax.legend(loc='lower right')  # default
-
-
-def test_shadow_invalid_argument():
-    # Test if invalid argument to legend shadow
-    # (i.e. not [color|bool]) raises ValueError
-    fig, ax = plt.subplots()
-    ax.plot([1, 2, 3], label='test')
-    with pytest.raises(ValueError, match="dict or bool"):
-        ax.legend(loc="upper left", shadow="aardvark")  # Bad argument
-
-
-def test_shadow_framealpha():
-    # Test if framealpha is activated when shadow is True
-    # and framealpha is not explicitly passed'''
-    fig, ax = plt.subplots()
-    ax.plot(range(100), label="test")
-    leg = ax.legend(shadow=True, facecolor='w')
-    assert leg.get_frame().get_alpha() == 1
-
-
-def test_legend_title_empty():
-    # test that if we don't set the legend title, that
-    # it comes back as an empty string, and that it is not
-    # visible:
-    fig, ax = plt.subplots()
-    ax.plot(range(10))
-    leg = ax.legend()
-    assert leg.get_title().get_text() == ""
-    assert not leg.get_title().get_visible()
-
-
-def test_legend_proper_window_extent():
-    # test that legend returns the expected extent under various dpi...
-    fig, ax = plt.subplots(dpi=100)
-    ax.plot(range(10), label='Aardvark')
-    leg = ax.legend()
-    x01 = leg.get_window_extent(fig.canvas.get_renderer()).x0
-
-    fig, ax = plt.subplots(dpi=200)
-    ax.plot(range(10), label='Aardvark')
-    leg = ax.legend()
-    x02 = leg.get_window_extent(fig.canvas.get_renderer()).x0
-    assert pytest.approx(x01*2, 0.1) == x02
-
-
-def test_window_extent_cached_renderer():
-    fig, ax = plt.subplots(dpi=100)
-    ax.plot(range(10), label='Aardvark')
-    leg = ax.legend()
-    leg2 = fig.legend()
-    fig.canvas.draw()
-    # check that get_window_extent will use the cached renderer
-    leg.get_window_extent()
-    leg2.get_window_extent()
-
-
-def test_legend_title_fontprop_fontsize():
-    # test the title_fontsize kwarg
-    plt.plot(range(10))
-    with pytest.raises(ValueError):
-        plt.legend(title='Aardvark', title_fontsize=22,
-                   title_fontproperties={'family': 'serif', 'size': 22})
-
-    leg = plt.legend(title='Aardvark', title_fontproperties=FontProperties(
-                                       family='serif', size=22))
-    assert leg.get_title().get_size() == 22
-
-    fig, axes = plt.subplots(2, 3, figsize=(10, 6))
-    axes = axes.flat
-    axes[0].plot(range(10))
-    leg0 = axes[0].legend(title='Aardvark', title_fontsize=22)
-    assert leg0.get_title().get_fontsize() == 22
-    axes[1].plot(range(10))
-    leg1 = axes[1].legend(title='Aardvark',
-                          title_fontproperties={'family': 'serif', 'size': 22})
-    assert leg1.get_title().get_fontsize() == 22
-    axes[2].plot(range(10))
-    mpl.rcParams['legend.title_fontsize'] = None
-    leg2 = axes[2].legend(title='Aardvark',
-                          title_fontproperties={'family': 'serif'})
-    assert leg2.get_title().get_fontsize() == mpl.rcParams['font.size']
-    axes[3].plot(range(10))
-    leg3 = axes[3].legend(title='Aardvark')
-    assert leg3.get_title().get_fontsize() == mpl.rcParams['font.size']
-    axes[4].plot(range(10))
-    mpl.rcParams['legend.title_fontsize'] = 20
-    leg4 = axes[4].legend(title='Aardvark',
-                          title_fontproperties={'family': 'serif'})
-    assert leg4.get_title().get_fontsize() == 20
-    axes[5].plot(range(10))
-    leg5 = axes[5].legend(title='Aardvark')
-    assert leg5.get_title().get_fontsize() == 20
-
-
-@pytest.mark.parametrize('alignment', ('center', 'left', 'right'))
-def test_legend_alignment(alignment):
-    fig, ax = plt.subplots()
-    ax.plot(range(10), label='test')
-    leg = ax.legend(title="Aardvark", alignment=alignment)
-    assert leg.get_children()[0].align == alignment
-    assert leg.get_alignment() == alignment
-
-
-@pytest.mark.parametrize('loc', ('center', 'best',))
-def test_ax_legend_set_loc(loc):
-    fig, ax = plt.subplots()
-    ax.plot(range(10), label='test')
-    leg = ax.legend()
-    leg.set_loc(loc)
-    assert leg._get_loc() == mlegend.Legend.codes[loc]
-
-
-@pytest.mark.parametrize('loc', ('outside right', 'right',))
-def test_fig_legend_set_loc(loc):
-    fig, ax = plt.subplots()
-    ax.plot(range(10), label='test')
-    leg = fig.legend()
-    leg.set_loc(loc)
-
-    loc = loc.split()[1] if loc.startswith("outside") else loc
-    assert leg._get_loc() == mlegend.Legend.codes[loc]
-
-
-@pytest.mark.parametrize('alignment', ('center', 'left', 'right'))
-def test_legend_set_alignment(alignment):
-    fig, ax = plt.subplots()
-    ax.plot(range(10), label='test')
-    leg = ax.legend()
-    leg.set_alignment(alignment)
-    assert leg.get_children()[0].align == alignment
-    assert leg.get_alignment() == alignment
-
-
-@pytest.mark.parametrize('color', ('red', 'none', (.5, .5, .5)))
-def test_legend_labelcolor_single(color):
-    # test labelcolor for a single color
-    fig, ax = plt.subplots()
-    ax.plot(np.arange(10), np.arange(10)*1, label='#1')
-    ax.plot(np.arange(10), np.arange(10)*2, label='#2')
-    ax.plot(np.arange(10), np.arange(10)*3, label='#3')
-
-    leg = ax.legend(labelcolor=color)
-    for text in leg.get_texts():
-        assert mpl.colors.same_color(text.get_color(), color)
-
-
-def test_legend_labelcolor_list():
-    # test labelcolor for a list of colors
-    fig, ax = plt.subplots()
-    ax.plot(np.arange(10), np.arange(10)*1, label='#1')
-    ax.plot(np.arange(10), np.arange(10)*2, label='#2')
-    ax.plot(np.arange(10), np.arange(10)*3, label='#3')
-
-    leg = ax.legend(labelcolor=['r', 'g', 'b'])
-    for text, color in zip(leg.get_texts(), ['r', 'g', 'b']):
-        assert mpl.colors.same_color(text.get_color(), color)
-
-
-def test_legend_labelcolor_linecolor():
-    # test the labelcolor for labelcolor='linecolor'
-    fig, ax = plt.subplots()
-    ax.plot(np.arange(10), np.arange(10)*1, label='#1', color='r')
-    ax.plot(np.arange(10), np.arange(10)*2, label='#2', color='g')
-    ax.plot(np.arange(10), np.arange(10)*3, label='#3', color='b')
-
-    leg = ax.legend(labelcolor='linecolor')
-    for text, color in zip(leg.get_texts(), ['r', 'g', 'b']):
-        assert mpl.colors.same_color(text.get_color(), color)
-
-
-def test_legend_pathcollection_labelcolor_linecolor():
-    # test the labelcolor for labelcolor='linecolor' on PathCollection
-    fig, ax = plt.subplots()
-    ax.scatter(np.arange(10), np.arange(10)*1, label='#1', c='r')
-    ax.scatter(np.arange(10), np.arange(10)*2, label='#2', c='g')
-    ax.scatter(np.arange(10), np.arange(10)*3, label='#3', c='b')
-
-    leg = ax.legend(labelcolor='linecolor')
-    for text, color in zip(leg.get_texts(), ['r', 'g', 'b']):
-        assert mpl.colors.same_color(text.get_color(), color)
-
-
-def test_legend_pathcollection_labelcolor_linecolor_iterable():
-    # test the labelcolor for labelcolor='linecolor' on PathCollection
-    # with iterable colors
-    fig, ax = plt.subplots()
-    colors = np.random.default_rng().choice(['r', 'g', 'b'], 10)
-    ax.scatter(np.arange(10), np.arange(10)*1, label='#1', c=colors)
-
-    leg = ax.legend(labelcolor='linecolor')
-    text, = leg.get_texts()
-    assert mpl.colors.same_color(text.get_color(), 'black')
-
-
-def test_legend_pathcollection_labelcolor_linecolor_cmap():
-    # test the labelcolor for labelcolor='linecolor' on PathCollection
-    # with a colormap
-    fig, ax = plt.subplots()
-    ax.scatter(np.arange(10), np.arange(10), c=np.arange(10), label='#1')
-
-    leg = ax.legend(labelcolor='linecolor')
-    text, = leg.get_texts()
-    assert mpl.colors.same_color(text.get_color(), 'black')
-
-
-def test_legend_labelcolor_markeredgecolor():
-    # test the labelcolor for labelcolor='markeredgecolor'
-    fig, ax = plt.subplots()
-    ax.plot(np.arange(10), np.arange(10)*1, label='#1', markeredgecolor='r')
-    ax.plot(np.arange(10), np.arange(10)*2, label='#2', markeredgecolor='g')
-    ax.plot(np.arange(10), np.arange(10)*3, label='#3', markeredgecolor='b')
-
-    leg = ax.legend(labelcolor='markeredgecolor')
-    for text, color in zip(leg.get_texts(), ['r', 'g', 'b']):
-        assert mpl.colors.same_color(text.get_color(), color)
-
-
-def test_legend_pathcollection_labelcolor_markeredgecolor():
-    # test the labelcolor for labelcolor='markeredgecolor' on PathCollection
-    fig, ax = plt.subplots()
-    ax.scatter(np.arange(10), np.arange(10)*1, label='#1', edgecolor='r')
-    ax.scatter(np.arange(10), np.arange(10)*2, label='#2', edgecolor='g')
-    ax.scatter(np.arange(10), np.arange(10)*3, label='#3', edgecolor='b')
-
-    leg = ax.legend(labelcolor='markeredgecolor')
-    for text, color in zip(leg.get_texts(), ['r', 'g', 'b']):
-        assert mpl.colors.same_color(text.get_color(), color)
-
-
-def test_legend_pathcollection_labelcolor_markeredgecolor_iterable():
-    # test the labelcolor for labelcolor='markeredgecolor' on PathCollection
-    # with iterable colors
-    fig, ax = plt.subplots()
-    colors = np.random.default_rng().choice(['r', 'g', 'b'], 10)
-    ax.scatter(np.arange(10), np.arange(10)*1, label='#1', edgecolor=colors)
-
-    leg = ax.legend(labelcolor='markeredgecolor')
-    for text, color in zip(leg.get_texts(), ['k']):
-        assert mpl.colors.same_color(text.get_color(), color)
-
-
-def test_legend_pathcollection_labelcolor_markeredgecolor_cmap():
-    # test the labelcolor for labelcolor='markeredgecolor' on PathCollection
-    # with a colormap
-    fig, ax = plt.subplots()
-    edgecolors = mpl.cm.viridis(np.random.rand(10))
-    ax.scatter(
-        np.arange(10),
-        np.arange(10),
-        label='#1',
-        c=np.arange(10),
-        edgecolor=edgecolors,
-        cmap="Reds"
-    )
-
-    leg = ax.legend(labelcolor='markeredgecolor')
-    for text, color in zip(leg.get_texts(), ['k']):
-        assert mpl.colors.same_color(text.get_color(), color)
-
-
-def test_legend_labelcolor_markerfacecolor():
-    # test the labelcolor for labelcolor='markerfacecolor'
-    fig, ax = plt.subplots()
-    ax.plot(np.arange(10), np.arange(10)*1, label='#1', markerfacecolor='r')
-    ax.plot(np.arange(10), np.arange(10)*2, label='#2', markerfacecolor='g')
-    ax.plot(np.arange(10), np.arange(10)*3, label='#3', markerfacecolor='b')
-
-    leg = ax.legend(labelcolor='markerfacecolor')
-    for text, color in zip(leg.get_texts(), ['r', 'g', 'b']):
-        assert mpl.colors.same_color(text.get_color(), color)
-
-
-def test_legend_pathcollection_labelcolor_markerfacecolor():
-    # test the labelcolor for labelcolor='markerfacecolor' on PathCollection
-    fig, ax = plt.subplots()
-    ax.scatter(np.arange(10), np.arange(10)*1, label='#1', facecolor='r')
-    ax.scatter(np.arange(10), np.arange(10)*2, label='#2', facecolor='g')
-    ax.scatter(np.arange(10), np.arange(10)*3, label='#3', facecolor='b')
-
-    leg = ax.legend(labelcolor='markerfacecolor')
-    for text, color in zip(leg.get_texts(), ['r', 'g', 'b']):
-        assert mpl.colors.same_color(text.get_color(), color)
-
-
-def test_legend_pathcollection_labelcolor_markerfacecolor_iterable():
-    # test the labelcolor for labelcolor='markerfacecolor' on PathCollection
-    # with iterable colors
-    fig, ax = plt.subplots()
-    colors = np.random.default_rng().choice(['r', 'g', 'b'], 10)
-    ax.scatter(np.arange(10), np.arange(10)*1, label='#1', facecolor=colors)
-
-    leg = ax.legend(labelcolor='markerfacecolor')
-    for text, color in zip(leg.get_texts(), ['k']):
-        assert mpl.colors.same_color(text.get_color(), color)
-
-
-def test_legend_pathcollection_labelcolor_markfacecolor_cmap():
-    # test the labelcolor for labelcolor='markerfacecolor' on PathCollection
-    # with colormaps
-    fig, ax = plt.subplots()
-    facecolors = mpl.cm.viridis(np.random.rand(10))
-    ax.scatter(
-        np.arange(10),
-        np.arange(10),
-        label='#1',
-        c=np.arange(10),
-        facecolor=facecolors
-    )
-
-    leg = ax.legend(labelcolor='markerfacecolor')
-    for text, color in zip(leg.get_texts(), ['k']):
-        assert mpl.colors.same_color(text.get_color(), color)
-
-
-@pytest.mark.parametrize('color', ('red', 'none', (.5, .5, .5)))
-def test_legend_labelcolor_rcparam_single(color):
-    # test the rcParams legend.labelcolor for a single color
-    fig, ax = plt.subplots()
-    ax.plot(np.arange(10), np.arange(10)*1, label='#1')
-    ax.plot(np.arange(10), np.arange(10)*2, label='#2')
-    ax.plot(np.arange(10), np.arange(10)*3, label='#3')
-
-    mpl.rcParams['legend.labelcolor'] = color
-    leg = ax.legend()
-    for text in leg.get_texts():
-        assert mpl.colors.same_color(text.get_color(), color)
-
-
-def test_legend_labelcolor_rcparam_linecolor():
-    # test the rcParams legend.labelcolor for a linecolor
-    fig, ax = plt.subplots()
-    ax.plot(np.arange(10), np.arange(10)*1, label='#1', color='r')
-    ax.plot(np.arange(10), np.arange(10)*2, label='#2', color='g')
-    ax.plot(np.arange(10), np.arange(10)*3, label='#3', color='b')
-
-    mpl.rcParams['legend.labelcolor'] = 'linecolor'
-    leg = ax.legend()
-    for text, color in zip(leg.get_texts(), ['r', 'g', 'b']):
-        assert mpl.colors.same_color(text.get_color(), color)
-
-
-def test_legend_labelcolor_rcparam_markeredgecolor():
-    # test the labelcolor for labelcolor='markeredgecolor'
-    fig, ax = plt.subplots()
-    ax.plot(np.arange(10), np.arange(10)*1, label='#1', markeredgecolor='r')
-    ax.plot(np.arange(10), np.arange(10)*2, label='#2', markeredgecolor='g')
-    ax.plot(np.arange(10), np.arange(10)*3, label='#3', markeredgecolor='b')
-
-    mpl.rcParams['legend.labelcolor'] = 'markeredgecolor'
-    leg = ax.legend()
-    for text, color in zip(leg.get_texts(), ['r', 'g', 'b']):
-        assert mpl.colors.same_color(text.get_color(), color)
-
-
-def test_legend_labelcolor_rcparam_markeredgecolor_short():
-    # test the labelcolor for labelcolor='markeredgecolor'
-    fig, ax = plt.subplots()
-    ax.plot(np.arange(10), np.arange(10)*1, label='#1', markeredgecolor='r')
-    ax.plot(np.arange(10), np.arange(10)*2, label='#2', markeredgecolor='g')
-    ax.plot(np.arange(10), np.arange(10)*3, label='#3', markeredgecolor='b')
-
-    mpl.rcParams['legend.labelcolor'] = 'mec'
-    leg = ax.legend()
-    for text, color in zip(leg.get_texts(), ['r', 'g', 'b']):
-        assert mpl.colors.same_color(text.get_color(), color)
-
-
-def test_legend_labelcolor_rcparam_markerfacecolor():
-    # test the labelcolor for labelcolor='markeredgecolor'
-    fig, ax = plt.subplots()
-    ax.plot(np.arange(10), np.arange(10)*1, label='#1', markerfacecolor='r')
-    ax.plot(np.arange(10), np.arange(10)*2, label='#2', markerfacecolor='g')
-    ax.plot(np.arange(10), np.arange(10)*3, label='#3', markerfacecolor='b')
-
-    mpl.rcParams['legend.labelcolor'] = 'markerfacecolor'
-    leg = ax.legend()
-    for text, color in zip(leg.get_texts(), ['r', 'g', 'b']):
-        assert mpl.colors.same_color(text.get_color(), color)
-
-
-def test_legend_labelcolor_rcparam_markerfacecolor_short():
-    # test the labelcolor for labelcolor='markeredgecolor'
-    fig, ax = plt.subplots()
-    ax.plot(np.arange(10), np.arange(10)*1, label='#1', markerfacecolor='r')
-    ax.plot(np.arange(10), np.arange(10)*2, label='#2', markerfacecolor='g')
-    ax.plot(np.arange(10), np.arange(10)*3, label='#3', markerfacecolor='b')
-
-    mpl.rcParams['legend.labelcolor'] = 'mfc'
-    leg = ax.legend()
-    for text, color in zip(leg.get_texts(), ['r', 'g', 'b']):
-        assert mpl.colors.same_color(text.get_color(), color)
-
-
-def test_get_set_draggable():
-    legend = plt.legend()
-    assert not legend.get_draggable()
-    legend.set_draggable(True)
-    assert legend.get_draggable()
-    legend.set_draggable(False)
-    assert not legend.get_draggable()
-
-
-@pytest.mark.parametrize('draggable', (True, False))
-def test_legend_draggable(draggable):
-    fig, ax = plt.subplots()
-    ax.plot(range(10), label='shabnams')
-    leg = ax.legend(draggable=draggable)
-    assert leg.get_draggable() is draggable
-
-
-def test_alpha_handles():
-    x, n, hh = plt.hist([1, 2, 3], alpha=0.25, label='data', color='red')
-    legend = plt.legend()
-    for lh in legend.legend_handles:
-        lh.set_alpha(1.0)
-    assert lh.get_facecolor()[:-1] == hh[1].get_facecolor()[:-1]
-    assert lh.get_edgecolor()[:-1] == hh[1].get_edgecolor()[:-1]
-
-
-@needs_usetex
-def test_usetex_no_warn(caplog):
-    mpl.rcParams['font.family'] = 'serif'
-    mpl.rcParams['font.serif'] = 'Computer Modern'
-    mpl.rcParams['text.usetex'] = True
-
-    fig, ax = plt.subplots()
-    ax.plot(0, 0, label='input')
-    ax.legend(title="My legend")
-
-    fig.canvas.draw()
-    assert "Font family ['serif'] not found." not in caplog.text
-
-
-def test_warn_big_data_best_loc():
-    fig, ax = plt.subplots()
-    fig.canvas.draw()  # So that we can call draw_artist later.
-    for idx in range(1000):
-        ax.plot(np.arange(5000), label=idx)
-    with rc_context({'legend.loc': 'best'}):
-        legend = ax.legend()
-    with pytest.warns(UserWarning) as records:
-        fig.draw_artist(legend)  # Don't bother drawing the lines -- it's slow.
-    # The _find_best_position method of Legend is called twice, duplicating
-    # the warning message.
-    assert len(records) == 2
-    for record in records:
-        assert str(record.message) == (
-            'Creating legend with loc="best" can be slow with large '
-            'amounts of data.')
-
-
-def test_no_warn_big_data_when_loc_specified():
-    fig, ax = plt.subplots()
-    fig.canvas.draw()
-    for idx in range(1000):
-        ax.plot(np.arange(5000), label=idx)
-    legend = ax.legend('best')
-    fig.draw_artist(legend)  # Check that no warning is emitted.
-
-
-@pytest.mark.parametrize('label_array', [['low', 'high'],
-                                         ('low', 'high'),
-                                         np.array(['low', 'high'])])
-def test_plot_multiple_input_multiple_label(label_array):
-    # test ax.plot() with multidimensional input
-    # and multiple labels
-    x = [1, 2, 3]
-    y = [[1, 2],
-         [2, 5],
-         [4, 9]]
-
-    fig, ax = plt.subplots()
-    ax.plot(x, y, label=label_array)
-    leg = ax.legend()
-    legend_texts = [entry.get_text() for entry in leg.get_texts()]
-    assert legend_texts == ['low', 'high']
-
-
-@pytest.mark.parametrize('label', ['one', 1, int])
-def test_plot_multiple_input_single_label(label):
-    # test ax.plot() with multidimensional input
-    # and single label
-    x = [1, 2, 3]
-    y = [[1, 2],
-         [2, 5],
-         [4, 9]]
-
-    fig, ax = plt.subplots()
-    ax.plot(x, y, label=label)
-    leg = ax.legend()
-    legend_texts = [entry.get_text() for entry in leg.get_texts()]
-    assert legend_texts == [str(label)] * 2
-
-
-@pytest.mark.parametrize('label_array', [['low', 'high'],
-                                         ('low', 'high'),
-                                         np.array(['low', 'high'])])
-def test_plot_single_input_multiple_label(label_array):
-    # test ax.plot() with 1D array like input
-    # and iterable label
-    x = [1, 2, 3]
-    y = [2, 5, 6]
-    fig, ax = plt.subplots()
-    ax.plot(x, y, label=label_array)
-    leg = ax.legend()
-    assert len(leg.get_texts()) == 1
-    assert leg.get_texts()[0].get_text() == str(label_array)
-
-
-def test_plot_multiple_label_incorrect_length_exception():
-    # check that exception is raised if multiple labels
-    # are given, but number of on labels != number of lines
-    with pytest.raises(ValueError):
-        x = [1, 2, 3]
-        y = [[1, 2],
-             [2, 5],
-             [4, 9]]
-        label = ['high', 'low', 'medium']
-        fig, ax = plt.subplots()
-        ax.plot(x, y, label=label)
-
-
-def test_legend_face_edgecolor():
-    # Smoke test for PolyCollection legend handler with 'face' edgecolor.
-    fig, ax = plt.subplots()
-    ax.fill_between([0, 1, 2], [1, 2, 3], [2, 3, 4],
-                    facecolor='r', edgecolor='face', label='Fill')
-    ax.legend()
-
-
-def test_legend_text_axes():
-    fig, ax = plt.subplots()
-    ax.plot([1, 2], [3, 4], label='line')
-    leg = ax.legend()
-
-    assert leg.axes is ax
-    assert leg.get_texts()[0].axes is ax
-
-
-def test_handlerline2d():
-    # Test marker consistency for monolithic Line2D legend handler (#11357).
-    fig, ax = plt.subplots()
-    ax.scatter([0, 1], [0, 1], marker="v")
-    handles = [mlines.Line2D([0], [0], marker="v")]
-    leg = ax.legend(handles, ["Aardvark"], numpoints=1)
-    assert handles[0].get_marker() == leg.legend_handles[0].get_marker()
-
-
-def test_subfigure_legend():
-    # Test that legend can be added to subfigure (#20723)
-    subfig = plt.figure().subfigures()
-    ax = subfig.subplots()
-    ax.plot([0, 1], [0, 1], label="line")
-    leg = subfig.legend()
-    assert leg.figure is subfig
-
-
-def test_setting_alpha_keeps_polycollection_color():
-    pc = plt.fill_between([0, 1], [2, 3], color='#123456', label='label')
-    patch = plt.legend().get_patches()[0]
-    patch.set_alpha(0.5)
-    assert patch.get_facecolor()[:3] == tuple(pc.get_facecolor()[0][:3])
-    assert patch.get_edgecolor()[:3] == tuple(pc.get_edgecolor()[0][:3])
-
-
-def test_legend_markers_from_line2d():
-    # Test that markers can be copied for legend lines (#17960)
-    _markers = ['.', '*', 'v']
-    fig, ax = plt.subplots()
-    lines = [mlines.Line2D([0], [0], ls='None', marker=mark)
-             for mark in _markers]
-    labels = ["foo", "bar", "xyzzy"]
-    markers = [line.get_marker() for line in lines]
-    legend = ax.legend(lines, labels)
-
-    new_markers = [line.get_marker() for line in legend.get_lines()]
-    new_labels = [text.get_text() for text in legend.get_texts()]
-
-    assert markers == new_markers == _markers
-    assert labels == new_labels
-
-
-@check_figures_equal()
-def test_ncol_ncols(fig_test, fig_ref):
-    # Test that both ncol and ncols work
-    strings = ["a", "b", "c", "d", "e", "f"]
-    ncols = 3
-    fig_test.legend(strings, ncol=ncols)
-    fig_ref.legend(strings, ncols=ncols)
-
-
-def test_loc_invalid_tuple_exception():
-    # check that exception is raised if the loc arg
-    # of legend is not a 2-tuple of numbers
-    fig, ax = plt.subplots()
-    with pytest.raises(ValueError, match=('loc must be string, coordinate '
-                       'tuple, or an integer 0-10, not \\(1.1,\\)')):
-        ax.legend(loc=(1.1, ))
-
-    with pytest.raises(ValueError, match=('loc must be string, coordinate '
-                       'tuple, or an integer 0-10, not \\(0.481, 0.4227, 0.4523\\)')):
-        ax.legend(loc=(0.481, 0.4227, 0.4523))
-
-    with pytest.raises(ValueError, match=('loc must be string, coordinate '
-                       'tuple, or an integer 0-10, not \\(0.481, \'go blue\'\\)')):
-        ax.legend(loc=(0.481, "go blue"))
-
-
-def test_loc_valid_tuple():
-    fig, ax = plt.subplots()
-    ax.legend(loc=(0.481, 0.442))
-    ax.legend(loc=(1, 2))
-
-
-def test_loc_valid_list():
-    fig, ax = plt.subplots()
-    ax.legend(loc=[0.481, 0.442])
-    ax.legend(loc=[1, 2])
-
-
-def test_loc_invalid_list_exception():
-    fig, ax = plt.subplots()
-    with pytest.raises(ValueError, match=('loc must be string, coordinate '
-                       'tuple, or an integer 0-10, not \\[1.1, 2.2, 3.3\\]')):
-        ax.legend(loc=[1.1, 2.2, 3.3])
-
-
-def test_loc_invalid_type():
-    fig, ax = plt.subplots()
-    with pytest.raises(ValueError, match=("loc must be string, coordinate "
-                       "tuple, or an integer 0-10, not {'not': True}")):
-        ax.legend(loc={'not': True})
-
-
-def test_loc_validation_numeric_value():
-    fig, ax = plt.subplots()
-    ax.legend(loc=0)
-    ax.legend(loc=1)
-    ax.legend(loc=5)
-    ax.legend(loc=10)
-    with pytest.raises(ValueError, match=('loc must be string, coordinate '
-                       'tuple, or an integer 0-10, not 11')):
-        ax.legend(loc=11)
-
-    with pytest.raises(ValueError, match=('loc must be string, coordinate '
-                       'tuple, or an integer 0-10, not -1')):
-        ax.legend(loc=-1)
-
-
-def test_loc_validation_string_value():
-    fig, ax = plt.subplots()
-    ax.legend(loc='best')
-    ax.legend(loc='upper right')
-    ax.legend(loc='best')
-    ax.legend(loc='upper right')
-    ax.legend(loc='upper left')
-    ax.legend(loc='lower left')
-    ax.legend(loc='lower right')
-    ax.legend(loc='right')
-    ax.legend(loc='center left')
-    ax.legend(loc='center right')
-    ax.legend(loc='lower center')
-    ax.legend(loc='upper center')
-    with pytest.raises(ValueError, match="'wrong' is not a valid value for"):
-        ax.legend(loc='wrong')
diff --git a/spaces/profayle/TerrapinTalk/myenv/lib/python3.9/site-packages/numpy/distutils/command/autodist.py b/spaces/profayle/TerrapinTalk/myenv/lib/python3.9/site-packages/numpy/distutils/command/autodist.py
deleted file mode 100644
index b72d0cab1a7da140c504a254a30a772f89be9f8d..0000000000000000000000000000000000000000
--- a/spaces/profayle/TerrapinTalk/myenv/lib/python3.9/site-packages/numpy/distutils/command/autodist.py
+++ /dev/null
@@ -1,148 +0,0 @@
-"""This module implements additional tests ala autoconf which can be useful.
-
-"""
-import textwrap
-
-# We put them here since they could be easily reused outside numpy.distutils
-
-def check_inline(cmd):
-    """Return the inline identifier (may be empty)."""
-    cmd._check_compiler()
-    body = textwrap.dedent("""
-        #ifndef __cplusplus
-        static %(inline)s int static_func (void)
-        {
-            return 0;
-        }
-        %(inline)s int nostatic_func (void)
-        {
-            return 0;
-        }
-        #endif""")
-
-    for kw in ['inline', '__inline__', '__inline']:
-        st = cmd.try_compile(body % {'inline': kw}, None, None)
-        if st:
-            return kw
-
-    return ''
-
-
-def check_restrict(cmd):
-    """Return the restrict identifier (may be empty)."""
-    cmd._check_compiler()
-    body = textwrap.dedent("""
-        static int static_func (char * %(restrict)s a)
-        {
-            return 0;
-        }
-        """)
-
-    for kw in ['restrict', '__restrict__', '__restrict']:
-        st = cmd.try_compile(body % {'restrict': kw}, None, None)
-        if st:
-            return kw
-
-    return ''
-
-
-def check_compiler_gcc(cmd):
-    """Check if the compiler is GCC."""
-
-    cmd._check_compiler()
-    body = textwrap.dedent("""
-        int
-        main()
-        {
-        #if (! defined __GNUC__)
-        #error gcc required
-        #endif
-            return 0;
-        }
-        """)
-    return cmd.try_compile(body, None, None)
-
-
-def check_gcc_version_at_least(cmd, major, minor=0, patchlevel=0):
-    """
-    Check that the gcc version is at least the specified version."""
-
-    cmd._check_compiler()
-    version = '.'.join([str(major), str(minor), str(patchlevel)])
-    body = textwrap.dedent("""
-        int
-        main()
-        {
-        #if (! defined __GNUC__) || (__GNUC__ < %(major)d) || \\
-                (__GNUC_MINOR__ < %(minor)d) || \\
-                (__GNUC_PATCHLEVEL__ < %(patchlevel)d)
-        #error gcc >= %(version)s required
-        #endif
-            return 0;
-        }
-        """)
-    kw = {'version': version, 'major': major, 'minor': minor,
-          'patchlevel': patchlevel}
-
-    return cmd.try_compile(body % kw, None, None)
-
-
-def check_gcc_function_attribute(cmd, attribute, name):
-    """Return True if the given function attribute is supported."""
-    cmd._check_compiler()
-    body = textwrap.dedent("""
-        #pragma GCC diagnostic error "-Wattributes"
-        #pragma clang diagnostic error "-Wattributes"
-
-        int %s %s(void* unused)
-        {
-            return 0;
-        }
-
-        int
-        main()
-        {
-            return 0;
-        }
-        """) % (attribute, name)
-    return cmd.try_compile(body, None, None) != 0
-
-
-def check_gcc_function_attribute_with_intrinsics(cmd, attribute, name, code,
-                                                include):
-    """Return True if the given function attribute is supported with
-    intrinsics."""
-    cmd._check_compiler()
-    body = textwrap.dedent("""
-        #include<%s>
-        int %s %s(void)
-        {
-            %s;
-            return 0;
-        }
-
-        int
-        main()
-        {
-            return 0;
-        }
-        """) % (include, attribute, name, code)
-    return cmd.try_compile(body, None, None) != 0
-
-
-def check_gcc_variable_attribute(cmd, attribute):
-    """Return True if the given variable attribute is supported."""
-    cmd._check_compiler()
-    body = textwrap.dedent("""
-        #pragma GCC diagnostic error "-Wattributes"
-        #pragma clang diagnostic error "-Wattributes"
-
-        int %s foo;
-
-        int
-        main()
-        {
-            return 0;
-        }
-        """) % (attribute, )
-    return cmd.try_compile(body, None, None) != 0
diff --git a/spaces/profayle/TerrapinTalk/myenv/lib/python3.9/site-packages/numpy/distutils/msvc9compiler.py b/spaces/profayle/TerrapinTalk/myenv/lib/python3.9/site-packages/numpy/distutils/msvc9compiler.py
deleted file mode 100644
index 68239495d6c72b70257e51d7ec3ddb35611940a2..0000000000000000000000000000000000000000
--- a/spaces/profayle/TerrapinTalk/myenv/lib/python3.9/site-packages/numpy/distutils/msvc9compiler.py
+++ /dev/null
@@ -1,63 +0,0 @@
-import os
-from distutils.msvc9compiler import MSVCCompiler as _MSVCCompiler
-
-from .system_info import platform_bits
-
-
-def _merge(old, new):
-    """Concatenate two environment paths avoiding repeats.
-
-    Here `old` is the environment string before the base class initialize
-    function is called and `new` is the string after the call. The new string
-    will be a fixed string if it is not obtained from the current environment,
-    or the same as the old string if obtained from the same environment. The aim
-    here is not to append the new string if it is already contained in the old
-    string so as to limit the growth of the environment string.
-
-    Parameters
-    ----------
-    old : string
-        Previous environment string.
-    new : string
-        New environment string.
-
-    Returns
-    -------
-    ret : string
-        Updated environment string.
-
-    """
-    if not old:
-        return new
-    if new in old:
-        return old
-
-    # Neither new nor old is empty. Give old priority.
-    return ';'.join([old, new])
-
-
-class MSVCCompiler(_MSVCCompiler):
-    def __init__(self, verbose=0, dry_run=0, force=0):
-        _MSVCCompiler.__init__(self, verbose, dry_run, force)
-
-    def initialize(self, plat_name=None):
-        # The 'lib' and 'include' variables may be overwritten
-        # by MSVCCompiler.initialize, so save them for later merge.
-        environ_lib = os.getenv('lib')
-        environ_include = os.getenv('include')
-        _MSVCCompiler.initialize(self, plat_name)
-
-        # Merge current and previous values of 'lib' and 'include'
-        os.environ['lib'] = _merge(environ_lib, os.environ['lib'])
-        os.environ['include'] = _merge(environ_include, os.environ['include'])
-
-        # msvc9 building for 32 bits requires SSE2 to work around a
-        # compiler bug.
-        if platform_bits == 32:
-            self.compile_options += ['/arch:SSE2']
-            self.compile_options_debug += ['/arch:SSE2']
-
-    def manifest_setup_ldargs(self, output_filename, build_temp, ld_args):
-        ld_args.append('/MANIFEST')
-        _MSVCCompiler.manifest_setup_ldargs(self, output_filename,
-                                            build_temp, ld_args)
diff --git a/spaces/profayle/TerrapinTalk/myenv/lib/python3.9/site-packages/numpy/matrixlib/defmatrix.py b/spaces/profayle/TerrapinTalk/myenv/lib/python3.9/site-packages/numpy/matrixlib/defmatrix.py
deleted file mode 100644
index d029b13fb8b561247fb031e44a14de285a1d9d4a..0000000000000000000000000000000000000000
--- a/spaces/profayle/TerrapinTalk/myenv/lib/python3.9/site-packages/numpy/matrixlib/defmatrix.py
+++ /dev/null
@@ -1,1114 +0,0 @@
-__all__ = ['matrix', 'bmat', 'mat', 'asmatrix']
-
-import sys
-import warnings
-import ast
-
-from .._utils import set_module
-import numpy.core.numeric as N
-from numpy.core.numeric import concatenate, isscalar
-# While not in __all__, matrix_power used to be defined here, so we import
-# it for backward compatibility.
-from numpy.linalg import matrix_power
-
-
-def _convert_from_string(data):
-    for char in '[]':
-        data = data.replace(char, '')
-
-    rows = data.split(';')
-    newdata = []
-    count = 0
-    for row in rows:
-        trow = row.split(',')
-        newrow = []
-        for col in trow:
-            temp = col.split()
-            newrow.extend(map(ast.literal_eval, temp))
-        if count == 0:
-            Ncols = len(newrow)
-        elif len(newrow) != Ncols:
-            raise ValueError("Rows not the same size.")
-        count += 1
-        newdata.append(newrow)
-    return newdata
-
-
-@set_module('numpy')
-def asmatrix(data, dtype=None):
-    """
-    Interpret the input as a matrix.
-
-    Unlike `matrix`, `asmatrix` does not make a copy if the input is already
-    a matrix or an ndarray.  Equivalent to ``matrix(data, copy=False)``.
-
-    Parameters
-    ----------
-    data : array_like
-        Input data.
-    dtype : data-type
-       Data-type of the output matrix.
-
-    Returns
-    -------
-    mat : matrix
-        `data` interpreted as a matrix.
-
-    Examples
-    --------
-    >>> x = np.array([[1, 2], [3, 4]])
-
-    >>> m = np.asmatrix(x)
-
-    >>> x[0,0] = 5
-
-    >>> m
-    matrix([[5, 2],
-            [3, 4]])
-
-    """
-    return matrix(data, dtype=dtype, copy=False)
-
-
-@set_module('numpy')
-class matrix(N.ndarray):
-    """
-    matrix(data, dtype=None, copy=True)
-
-    .. note:: It is no longer recommended to use this class, even for linear
-              algebra. Instead use regular arrays. The class may be removed
-              in the future.
-
-    Returns a matrix from an array-like object, or from a string of data.
-    A matrix is a specialized 2-D array that retains its 2-D nature
-    through operations.  It has certain special operators, such as ``*``
-    (matrix multiplication) and ``**`` (matrix power).
-
-    Parameters
-    ----------
-    data : array_like or string
-       If `data` is a string, it is interpreted as a matrix with commas
-       or spaces separating columns, and semicolons separating rows.
-    dtype : data-type
-       Data-type of the output matrix.
-    copy : bool
-       If `data` is already an `ndarray`, then this flag determines
-       whether the data is copied (the default), or whether a view is
-       constructed.
-
-    See Also
-    --------
-    array
-
-    Examples
-    --------
-    >>> a = np.matrix('1 2; 3 4')
-    >>> a
-    matrix([[1, 2],
-            [3, 4]])
-
-    >>> np.matrix([[1, 2], [3, 4]])
-    matrix([[1, 2],
-            [3, 4]])
-
-    """
-    __array_priority__ = 10.0
-    def __new__(subtype, data, dtype=None, copy=True):
-        warnings.warn('the matrix subclass is not the recommended way to '
-                      'represent matrices or deal with linear algebra (see '
-                      'https://docs.scipy.org/doc/numpy/user/'
-                      'numpy-for-matlab-users.html). '
-                      'Please adjust your code to use regular ndarray.',
-                      PendingDeprecationWarning, stacklevel=2)
-        if isinstance(data, matrix):
-            dtype2 = data.dtype
-            if (dtype is None):
-                dtype = dtype2
-            if (dtype2 == dtype) and (not copy):
-                return data
-            return data.astype(dtype)
-
-        if isinstance(data, N.ndarray):
-            if dtype is None:
-                intype = data.dtype
-            else:
-                intype = N.dtype(dtype)
-            new = data.view(subtype)
-            if intype != data.dtype:
-                return new.astype(intype)
-            if copy: return new.copy()
-            else: return new
-
-        if isinstance(data, str):
-            data = _convert_from_string(data)
-
-        # now convert data to an array
-        arr = N.array(data, dtype=dtype, copy=copy)
-        ndim = arr.ndim
-        shape = arr.shape
-        if (ndim > 2):
-            raise ValueError("matrix must be 2-dimensional")
-        elif ndim == 0:
-            shape = (1, 1)
-        elif ndim == 1:
-            shape = (1, shape[0])
-
-        order = 'C'
-        if (ndim == 2) and arr.flags.fortran:
-            order = 'F'
-
-        if not (order or arr.flags.contiguous):
-            arr = arr.copy()
-
-        ret = N.ndarray.__new__(subtype, shape, arr.dtype,
-                                buffer=arr,
-                                order=order)
-        return ret
-
-    def __array_finalize__(self, obj):
-        self._getitem = False
-        if (isinstance(obj, matrix) and obj._getitem): return
-        ndim = self.ndim
-        if (ndim == 2):
-            return
-        if (ndim > 2):
-            newshape = tuple([x for x in self.shape if x > 1])
-            ndim = len(newshape)
-            if ndim == 2:
-                self.shape = newshape
-                return
-            elif (ndim > 2):
-                raise ValueError("shape too large to be a matrix.")
-        else:
-            newshape = self.shape
-        if ndim == 0:
-            self.shape = (1, 1)
-        elif ndim == 1:
-            self.shape = (1, newshape[0])
-        return
-
-    def __getitem__(self, index):
-        self._getitem = True
-
-        try:
-            out = N.ndarray.__getitem__(self, index)
-        finally:
-            self._getitem = False
-
-        if not isinstance(out, N.ndarray):
-            return out
-
-        if out.ndim == 0:
-            return out[()]
-        if out.ndim == 1:
-            sh = out.shape[0]
-            # Determine when we should have a column array
-            try:
-                n = len(index)
-            except Exception:
-                n = 0
-            if n > 1 and isscalar(index[1]):
-                out.shape = (sh, 1)
-            else:
-                out.shape = (1, sh)
-        return out
-
-    def __mul__(self, other):
-        if isinstance(other, (N.ndarray, list, tuple)) :
-            # This promotes 1-D vectors to row vectors
-            return N.dot(self, asmatrix(other))
-        if isscalar(other) or not hasattr(other, '__rmul__') :
-            return N.dot(self, other)
-        return NotImplemented
-
-    def __rmul__(self, other):
-        return N.dot(other, self)
-
-    def __imul__(self, other):
-        self[:] = self * other
-        return self
-
-    def __pow__(self, other):
-        return matrix_power(self, other)
-
-    def __ipow__(self, other):
-        self[:] = self ** other
-        return self
-
-    def __rpow__(self, other):
-        return NotImplemented
-
-    def _align(self, axis):
-        """A convenience function for operations that need to preserve axis
-        orientation.
-        """
-        if axis is None:
-            return self[0, 0]
-        elif axis==0:
-            return self
-        elif axis==1:
-            return self.transpose()
-        else:
-            raise ValueError("unsupported axis")
-
-    def _collapse(self, axis):
-        """A convenience function for operations that want to collapse
-        to a scalar like _align, but are using keepdims=True
-        """
-        if axis is None:
-            return self[0, 0]
-        else:
-            return self
-
-    # Necessary because base-class tolist expects dimension
-    #  reduction by x[0]
-    def tolist(self):
-        """
-        Return the matrix as a (possibly nested) list.
-
-        See `ndarray.tolist` for full documentation.
-
-        See Also
-        --------
-        ndarray.tolist
-
-        Examples
-        --------
-        >>> x = np.matrix(np.arange(12).reshape((3,4))); x
-        matrix([[ 0,  1,  2,  3],
-                [ 4,  5,  6,  7],
-                [ 8,  9, 10, 11]])
-        >>> x.tolist()
-        [[0, 1, 2, 3], [4, 5, 6, 7], [8, 9, 10, 11]]
-
-        """
-        return self.__array__().tolist()
-
-    # To preserve orientation of result...
-    def sum(self, axis=None, dtype=None, out=None):
-        """
-        Returns the sum of the matrix elements, along the given axis.
-
-        Refer to `numpy.sum` for full documentation.
-
-        See Also
-        --------
-        numpy.sum
-
-        Notes
-        -----
-        This is the same as `ndarray.sum`, except that where an `ndarray` would
-        be returned, a `matrix` object is returned instead.
-
-        Examples
-        --------
-        >>> x = np.matrix([[1, 2], [4, 3]])
-        >>> x.sum()
-        10
-        >>> x.sum(axis=1)
-        matrix([[3],
-                [7]])
-        >>> x.sum(axis=1, dtype='float')
-        matrix([[3.],
-                [7.]])
-        >>> out = np.zeros((2, 1), dtype='float')
-        >>> x.sum(axis=1, dtype='float', out=np.asmatrix(out))
-        matrix([[3.],
-                [7.]])
-
-        """
-        return N.ndarray.sum(self, axis, dtype, out, keepdims=True)._collapse(axis)
-
-
-    # To update docstring from array to matrix...
-    def squeeze(self, axis=None):
-        """
-        Return a possibly reshaped matrix.
-
-        Refer to `numpy.squeeze` for more documentation.
-
-        Parameters
-        ----------
-        axis : None or int or tuple of ints, optional
-            Selects a subset of the axes of length one in the shape.
-            If an axis is selected with shape entry greater than one,
-            an error is raised.
-
-        Returns
-        -------
-        squeezed : matrix
-            The matrix, but as a (1, N) matrix if it had shape (N, 1).
-
-        See Also
-        --------
-        numpy.squeeze : related function
-
-        Notes
-        -----
-        If `m` has a single column then that column is returned
-        as the single row of a matrix.  Otherwise `m` is returned.
-        The returned matrix is always either `m` itself or a view into `m`.
-        Supplying an axis keyword argument will not affect the returned matrix
-        but it may cause an error to be raised.
-
-        Examples
-        --------
-        >>> c = np.matrix([[1], [2]])
-        >>> c
-        matrix([[1],
-                [2]])
-        >>> c.squeeze()
-        matrix([[1, 2]])
-        >>> r = c.T
-        >>> r
-        matrix([[1, 2]])
-        >>> r.squeeze()
-        matrix([[1, 2]])
-        >>> m = np.matrix([[1, 2], [3, 4]])
-        >>> m.squeeze()
-        matrix([[1, 2],
-                [3, 4]])
-
-        """
-        return N.ndarray.squeeze(self, axis=axis)
-
-
-    # To update docstring from array to matrix...
-    def flatten(self, order='C'):
-        """
-        Return a flattened copy of the matrix.
-
-        All `N` elements of the matrix are placed into a single row.
-
-        Parameters
-        ----------
-        order : {'C', 'F', 'A', 'K'}, optional
-            'C' means to flatten in row-major (C-style) order. 'F' means to
-            flatten in column-major (Fortran-style) order. 'A' means to
-            flatten in column-major order if `m` is Fortran *contiguous* in
-            memory, row-major order otherwise. 'K' means to flatten `m` in
-            the order the elements occur in memory. The default is 'C'.
-
-        Returns
-        -------
-        y : matrix
-            A copy of the matrix, flattened to a `(1, N)` matrix where `N`
-            is the number of elements in the original matrix.
-
-        See Also
-        --------
-        ravel : Return a flattened array.
-        flat : A 1-D flat iterator over the matrix.
-
-        Examples
-        --------
-        >>> m = np.matrix([[1,2], [3,4]])
-        >>> m.flatten()
-        matrix([[1, 2, 3, 4]])
-        >>> m.flatten('F')
-        matrix([[1, 3, 2, 4]])
-
-        """
-        return N.ndarray.flatten(self, order=order)
-
-    def mean(self, axis=None, dtype=None, out=None):
-        """
-        Returns the average of the matrix elements along the given axis.
-
-        Refer to `numpy.mean` for full documentation.
-
-        See Also
-        --------
-        numpy.mean
-
-        Notes
-        -----
-        Same as `ndarray.mean` except that, where that returns an `ndarray`,
-        this returns a `matrix` object.
-
-        Examples
-        --------
-        >>> x = np.matrix(np.arange(12).reshape((3, 4)))
-        >>> x
-        matrix([[ 0,  1,  2,  3],
-                [ 4,  5,  6,  7],
-                [ 8,  9, 10, 11]])
-        >>> x.mean()
-        5.5
-        >>> x.mean(0)
-        matrix([[4., 5., 6., 7.]])
-        >>> x.mean(1)
-        matrix([[ 1.5],
-                [ 5.5],
-                [ 9.5]])
-
-        """
-        return N.ndarray.mean(self, axis, dtype, out, keepdims=True)._collapse(axis)
-
-    def std(self, axis=None, dtype=None, out=None, ddof=0):
-        """
-        Return the standard deviation of the array elements along the given axis.
-
-        Refer to `numpy.std` for full documentation.
-
-        See Also
-        --------
-        numpy.std
-
-        Notes
-        -----
-        This is the same as `ndarray.std`, except that where an `ndarray` would
-        be returned, a `matrix` object is returned instead.
-
-        Examples
-        --------
-        >>> x = np.matrix(np.arange(12).reshape((3, 4)))
-        >>> x
-        matrix([[ 0,  1,  2,  3],
-                [ 4,  5,  6,  7],
-                [ 8,  9, 10, 11]])
-        >>> x.std()
-        3.4520525295346629 # may vary
-        >>> x.std(0)
-        matrix([[ 3.26598632,  3.26598632,  3.26598632,  3.26598632]]) # may vary
-        >>> x.std(1)
-        matrix([[ 1.11803399],
-                [ 1.11803399],
-                [ 1.11803399]])
-
-        """
-        return N.ndarray.std(self, axis, dtype, out, ddof, keepdims=True)._collapse(axis)
-
-    def var(self, axis=None, dtype=None, out=None, ddof=0):
-        """
-        Returns the variance of the matrix elements, along the given axis.
-
-        Refer to `numpy.var` for full documentation.
-
-        See Also
-        --------
-        numpy.var
-
-        Notes
-        -----
-        This is the same as `ndarray.var`, except that where an `ndarray` would
-        be returned, a `matrix` object is returned instead.
-
-        Examples
-        --------
-        >>> x = np.matrix(np.arange(12).reshape((3, 4)))
-        >>> x
-        matrix([[ 0,  1,  2,  3],
-                [ 4,  5,  6,  7],
-                [ 8,  9, 10, 11]])
-        >>> x.var()
-        11.916666666666666
-        >>> x.var(0)
-        matrix([[ 10.66666667,  10.66666667,  10.66666667,  10.66666667]]) # may vary
-        >>> x.var(1)
-        matrix([[1.25],
-                [1.25],
-                [1.25]])
-
-        """
-        return N.ndarray.var(self, axis, dtype, out, ddof, keepdims=True)._collapse(axis)
-
-    def prod(self, axis=None, dtype=None, out=None):
-        """
-        Return the product of the array elements over the given axis.
-
-        Refer to `prod` for full documentation.
-
-        See Also
-        --------
-        prod, ndarray.prod
-
-        Notes
-        -----
-        Same as `ndarray.prod`, except, where that returns an `ndarray`, this
-        returns a `matrix` object instead.
-
-        Examples
-        --------
-        >>> x = np.matrix(np.arange(12).reshape((3,4))); x
-        matrix([[ 0,  1,  2,  3],
-                [ 4,  5,  6,  7],
-                [ 8,  9, 10, 11]])
-        >>> x.prod()
-        0
-        >>> x.prod(0)
-        matrix([[  0,  45, 120, 231]])
-        >>> x.prod(1)
-        matrix([[   0],
-                [ 840],
-                [7920]])
-
-        """
-        return N.ndarray.prod(self, axis, dtype, out, keepdims=True)._collapse(axis)
-
-    def any(self, axis=None, out=None):
-        """
-        Test whether any array element along a given axis evaluates to True.
-
-        Refer to `numpy.any` for full documentation.
-
-        Parameters
-        ----------
-        axis : int, optional
-            Axis along which logical OR is performed
-        out : ndarray, optional
-            Output to existing array instead of creating new one, must have
-            same shape as expected output
-
-        Returns
-        -------
-            any : bool, ndarray
-                Returns a single bool if `axis` is ``None``; otherwise,
-                returns `ndarray`
-
-        """
-        return N.ndarray.any(self, axis, out, keepdims=True)._collapse(axis)
-
-    def all(self, axis=None, out=None):
-        """
-        Test whether all matrix elements along a given axis evaluate to True.
-
-        Parameters
-        ----------
-        See `numpy.all` for complete descriptions
-
-        See Also
-        --------
-        numpy.all
-
-        Notes
-        -----
-        This is the same as `ndarray.all`, but it returns a `matrix` object.
-
-        Examples
-        --------
-        >>> x = np.matrix(np.arange(12).reshape((3,4))); x
-        matrix([[ 0,  1,  2,  3],
-                [ 4,  5,  6,  7],
-                [ 8,  9, 10, 11]])
-        >>> y = x[0]; y
-        matrix([[0, 1, 2, 3]])
-        >>> (x == y)
-        matrix([[ True,  True,  True,  True],
-                [False, False, False, False],
-                [False, False, False, False]])
-        >>> (x == y).all()
-        False
-        >>> (x == y).all(0)
-        matrix([[False, False, False, False]])
-        >>> (x == y).all(1)
-        matrix([[ True],
-                [False],
-                [False]])
-
-        """
-        return N.ndarray.all(self, axis, out, keepdims=True)._collapse(axis)
-
-    def max(self, axis=None, out=None):
-        """
-        Return the maximum value along an axis.
-
-        Parameters
-        ----------
-        See `amax` for complete descriptions
-
-        See Also
-        --------
-        amax, ndarray.max
-
-        Notes
-        -----
-        This is the same as `ndarray.max`, but returns a `matrix` object
-        where `ndarray.max` would return an ndarray.
-
-        Examples
-        --------
-        >>> x = np.matrix(np.arange(12).reshape((3,4))); x
-        matrix([[ 0,  1,  2,  3],
-                [ 4,  5,  6,  7],
-                [ 8,  9, 10, 11]])
-        >>> x.max()
-        11
-        >>> x.max(0)
-        matrix([[ 8,  9, 10, 11]])
-        >>> x.max(1)
-        matrix([[ 3],
-                [ 7],
-                [11]])
-
-        """
-        return N.ndarray.max(self, axis, out, keepdims=True)._collapse(axis)
-
-    def argmax(self, axis=None, out=None):
-        """
-        Indexes of the maximum values along an axis.
-
-        Return the indexes of the first occurrences of the maximum values
-        along the specified axis.  If axis is None, the index is for the
-        flattened matrix.
-
-        Parameters
-        ----------
-        See `numpy.argmax` for complete descriptions
-
-        See Also
-        --------
-        numpy.argmax
-
-        Notes
-        -----
-        This is the same as `ndarray.argmax`, but returns a `matrix` object
-        where `ndarray.argmax` would return an `ndarray`.
-
-        Examples
-        --------
-        >>> x = np.matrix(np.arange(12).reshape((3,4))); x
-        matrix([[ 0,  1,  2,  3],
-                [ 4,  5,  6,  7],
-                [ 8,  9, 10, 11]])
-        >>> x.argmax()
-        11
-        >>> x.argmax(0)
-        matrix([[2, 2, 2, 2]])
-        >>> x.argmax(1)
-        matrix([[3],
-                [3],
-                [3]])
-
-        """
-        return N.ndarray.argmax(self, axis, out)._align(axis)
-
-    def min(self, axis=None, out=None):
-        """
-        Return the minimum value along an axis.
-
-        Parameters
-        ----------
-        See `amin` for complete descriptions.
-
-        See Also
-        --------
-        amin, ndarray.min
-
-        Notes
-        -----
-        This is the same as `ndarray.min`, but returns a `matrix` object
-        where `ndarray.min` would return an ndarray.
-
-        Examples
-        --------
-        >>> x = -np.matrix(np.arange(12).reshape((3,4))); x
-        matrix([[  0,  -1,  -2,  -3],
-                [ -4,  -5,  -6,  -7],
-                [ -8,  -9, -10, -11]])
-        >>> x.min()
-        -11
-        >>> x.min(0)
-        matrix([[ -8,  -9, -10, -11]])
-        >>> x.min(1)
-        matrix([[ -3],
-                [ -7],
-                [-11]])
-
-        """
-        return N.ndarray.min(self, axis, out, keepdims=True)._collapse(axis)
-
-    def argmin(self, axis=None, out=None):
-        """
-        Indexes of the minimum values along an axis.
-
-        Return the indexes of the first occurrences of the minimum values
-        along the specified axis.  If axis is None, the index is for the
-        flattened matrix.
-
-        Parameters
-        ----------
-        See `numpy.argmin` for complete descriptions.
-
-        See Also
-        --------
-        numpy.argmin
-
-        Notes
-        -----
-        This is the same as `ndarray.argmin`, but returns a `matrix` object
-        where `ndarray.argmin` would return an `ndarray`.
-
-        Examples
-        --------
-        >>> x = -np.matrix(np.arange(12).reshape((3,4))); x
-        matrix([[  0,  -1,  -2,  -3],
-                [ -4,  -5,  -6,  -7],
-                [ -8,  -9, -10, -11]])
-        >>> x.argmin()
-        11
-        >>> x.argmin(0)
-        matrix([[2, 2, 2, 2]])
-        >>> x.argmin(1)
-        matrix([[3],
-                [3],
-                [3]])
-
-        """
-        return N.ndarray.argmin(self, axis, out)._align(axis)
-
-    def ptp(self, axis=None, out=None):
-        """
-        Peak-to-peak (maximum - minimum) value along the given axis.
-
-        Refer to `numpy.ptp` for full documentation.
-
-        See Also
-        --------
-        numpy.ptp
-
-        Notes
-        -----
-        Same as `ndarray.ptp`, except, where that would return an `ndarray` object,
-        this returns a `matrix` object.
-
-        Examples
-        --------
-        >>> x = np.matrix(np.arange(12).reshape((3,4))); x
-        matrix([[ 0,  1,  2,  3],
-                [ 4,  5,  6,  7],
-                [ 8,  9, 10, 11]])
-        >>> x.ptp()
-        11
-        >>> x.ptp(0)
-        matrix([[8, 8, 8, 8]])
-        >>> x.ptp(1)
-        matrix([[3],
-                [3],
-                [3]])
-
-        """
-        return N.ndarray.ptp(self, axis, out)._align(axis)
-
-    @property
-    def I(self):
-        """
-        Returns the (multiplicative) inverse of invertible `self`.
-
-        Parameters
-        ----------
-        None
-
-        Returns
-        -------
-        ret : matrix object
-            If `self` is non-singular, `ret` is such that ``ret * self`` ==
-            ``self * ret`` == ``np.matrix(np.eye(self[0,:].size))`` all return
-            ``True``.
-
-        Raises
-        ------
-        numpy.linalg.LinAlgError: Singular matrix
-            If `self` is singular.
-
-        See Also
-        --------
-        linalg.inv
-
-        Examples
-        --------
-        >>> m = np.matrix('[1, 2; 3, 4]'); m
-        matrix([[1, 2],
-                [3, 4]])
-        >>> m.getI()
-        matrix([[-2. ,  1. ],
-                [ 1.5, -0.5]])
-        >>> m.getI() * m
-        matrix([[ 1.,  0.], # may vary
-                [ 0.,  1.]])
-
-        """
-        M, N = self.shape
-        if M == N:
-            from numpy.linalg import inv as func
-        else:
-            from numpy.linalg import pinv as func
-        return asmatrix(func(self))
-
-    @property
-    def A(self):
-        """
-        Return `self` as an `ndarray` object.
-
-        Equivalent to ``np.asarray(self)``.
-
-        Parameters
-        ----------
-        None
-
-        Returns
-        -------
-        ret : ndarray
-            `self` as an `ndarray`
-
-        Examples
-        --------
-        >>> x = np.matrix(np.arange(12).reshape((3,4))); x
-        matrix([[ 0,  1,  2,  3],
-                [ 4,  5,  6,  7],
-                [ 8,  9, 10, 11]])
-        >>> x.getA()
-        array([[ 0,  1,  2,  3],
-               [ 4,  5,  6,  7],
-               [ 8,  9, 10, 11]])
-
-        """
-        return self.__array__()
-
-    @property
-    def A1(self):
-        """
-        Return `self` as a flattened `ndarray`.
-
-        Equivalent to ``np.asarray(x).ravel()``
-
-        Parameters
-        ----------
-        None
-
-        Returns
-        -------
-        ret : ndarray
-            `self`, 1-D, as an `ndarray`
-
-        Examples
-        --------
-        >>> x = np.matrix(np.arange(12).reshape((3,4))); x
-        matrix([[ 0,  1,  2,  3],
-                [ 4,  5,  6,  7],
-                [ 8,  9, 10, 11]])
-        >>> x.getA1()
-        array([ 0,  1,  2, ...,  9, 10, 11])
-
-
-        """
-        return self.__array__().ravel()
-
-
-    def ravel(self, order='C'):
-        """
-        Return a flattened matrix.
-
-        Refer to `numpy.ravel` for more documentation.
-
-        Parameters
-        ----------
-        order : {'C', 'F', 'A', 'K'}, optional
-            The elements of `m` are read using this index order. 'C' means to
-            index the elements in C-like order, with the last axis index
-            changing fastest, back to the first axis index changing slowest.
-            'F' means to index the elements in Fortran-like index order, with
-            the first index changing fastest, and the last index changing
-            slowest. Note that the 'C' and 'F' options take no account of the
-            memory layout of the underlying array, and only refer to the order
-            of axis indexing.  'A' means to read the elements in Fortran-like
-            index order if `m` is Fortran *contiguous* in memory, C-like order
-            otherwise.  'K' means to read the elements in the order they occur
-            in memory, except for reversing the data when strides are negative.
-            By default, 'C' index order is used.
-
-        Returns
-        -------
-        ret : matrix
-            Return the matrix flattened to shape `(1, N)` where `N`
-            is the number of elements in the original matrix.
-            A copy is made only if necessary.
-
-        See Also
-        --------
-        matrix.flatten : returns a similar output matrix but always a copy
-        matrix.flat : a flat iterator on the array.
-        numpy.ravel : related function which returns an ndarray
-
-        """
-        return N.ndarray.ravel(self, order=order)
-
-    @property
-    def T(self):
-        """
-        Returns the transpose of the matrix.
-
-        Does *not* conjugate!  For the complex conjugate transpose, use ``.H``.
-
-        Parameters
-        ----------
-        None
-
-        Returns
-        -------
-        ret : matrix object
-            The (non-conjugated) transpose of the matrix.
-
-        See Also
-        --------
-        transpose, getH
-
-        Examples
-        --------
-        >>> m = np.matrix('[1, 2; 3, 4]')
-        >>> m
-        matrix([[1, 2],
-                [3, 4]])
-        >>> m.getT()
-        matrix([[1, 3],
-                [2, 4]])
-
-        """
-        return self.transpose()
-
-    @property
-    def H(self):
-        """
-        Returns the (complex) conjugate transpose of `self`.
-
-        Equivalent to ``np.transpose(self)`` if `self` is real-valued.
-
-        Parameters
-        ----------
-        None
-
-        Returns
-        -------
-        ret : matrix object
-            complex conjugate transpose of `self`
-
-        Examples
-        --------
-        >>> x = np.matrix(np.arange(12).reshape((3,4)))
-        >>> z = x - 1j*x; z
-        matrix([[  0. +0.j,   1. -1.j,   2. -2.j,   3. -3.j],
-                [  4. -4.j,   5. -5.j,   6. -6.j,   7. -7.j],
-                [  8. -8.j,   9. -9.j,  10.-10.j,  11.-11.j]])
-        >>> z.getH()
-        matrix([[ 0. -0.j,  4. +4.j,  8. +8.j],
-                [ 1. +1.j,  5. +5.j,  9. +9.j],
-                [ 2. +2.j,  6. +6.j, 10.+10.j],
-                [ 3. +3.j,  7. +7.j, 11.+11.j]])
-
-        """
-        if issubclass(self.dtype.type, N.complexfloating):
-            return self.transpose().conjugate()
-        else:
-            return self.transpose()
-
-    # kept for compatibility
-    getT = T.fget
-    getA = A.fget
-    getA1 = A1.fget
-    getH = H.fget
-    getI = I.fget
-
-def _from_string(str, gdict, ldict):
-    rows = str.split(';')
-    rowtup = []
-    for row in rows:
-        trow = row.split(',')
-        newrow = []
-        for x in trow:
-            newrow.extend(x.split())
-        trow = newrow
-        coltup = []
-        for col in trow:
-            col = col.strip()
-            try:
-                thismat = ldict[col]
-            except KeyError:
-                try:
-                    thismat = gdict[col]
-                except KeyError as e:
-                    raise NameError(f"name {col!r} is not defined") from None
-
-            coltup.append(thismat)
-        rowtup.append(concatenate(coltup, axis=-1))
-    return concatenate(rowtup, axis=0)
-
-
-@set_module('numpy')
-def bmat(obj, ldict=None, gdict=None):
-    """
-    Build a matrix object from a string, nested sequence, or array.
-
-    Parameters
-    ----------
-    obj : str or array_like
-        Input data. If a string, variables in the current scope may be
-        referenced by name.
-    ldict : dict, optional
-        A dictionary that replaces local operands in current frame.
-        Ignored if `obj` is not a string or `gdict` is None.
-    gdict : dict, optional
-        A dictionary that replaces global operands in current frame.
-        Ignored if `obj` is not a string.
-
-    Returns
-    -------
-    out : matrix
-        Returns a matrix object, which is a specialized 2-D array.
-
-    See Also
-    --------
-    block :
-        A generalization of this function for N-d arrays, that returns normal
-        ndarrays.
-
-    Examples
-    --------
-    >>> A = np.mat('1 1; 1 1')
-    >>> B = np.mat('2 2; 2 2')
-    >>> C = np.mat('3 4; 5 6')
-    >>> D = np.mat('7 8; 9 0')
-
-    All the following expressions construct the same block matrix:
-
-    >>> np.bmat([[A, B], [C, D]])
-    matrix([[1, 1, 2, 2],
-            [1, 1, 2, 2],
-            [3, 4, 7, 8],
-            [5, 6, 9, 0]])
-    >>> np.bmat(np.r_[np.c_[A, B], np.c_[C, D]])
-    matrix([[1, 1, 2, 2],
-            [1, 1, 2, 2],
-            [3, 4, 7, 8],
-            [5, 6, 9, 0]])
-    >>> np.bmat('A,B; C,D')
-    matrix([[1, 1, 2, 2],
-            [1, 1, 2, 2],
-            [3, 4, 7, 8],
-            [5, 6, 9, 0]])
-
-    """
-    if isinstance(obj, str):
-        if gdict is None:
-            # get previous frame
-            frame = sys._getframe().f_back
-            glob_dict = frame.f_globals
-            loc_dict = frame.f_locals
-        else:
-            glob_dict = gdict
-            loc_dict = ldict
-
-        return matrix(_from_string(obj, glob_dict, loc_dict))
-
-    if isinstance(obj, (tuple, list)):
-        # [[A,B],[C,D]]
-        arr_rows = []
-        for row in obj:
-            if isinstance(row, N.ndarray):  # not 2-d
-                return matrix(concatenate(obj, axis=-1))
-            else:
-                arr_rows.append(concatenate(row, axis=-1))
-        return matrix(concatenate(arr_rows, axis=0))
-    if isinstance(obj, N.ndarray):
-        return matrix(obj)
-
-mat = asmatrix
diff --git a/spaces/profayle/TerrapinTalk/myenv/lib/python3.9/site-packages/pandas/io/formats/string.py b/spaces/profayle/TerrapinTalk/myenv/lib/python3.9/site-packages/pandas/io/formats/string.py
deleted file mode 100644
index 769f9dee1c31a440d82cdb0ca4694750bc744735..0000000000000000000000000000000000000000
--- a/spaces/profayle/TerrapinTalk/myenv/lib/python3.9/site-packages/pandas/io/formats/string.py
+++ /dev/null
@@ -1,206 +0,0 @@
-"""
-Module for formatting output data in console (to string).
-"""
-from __future__ import annotations
-
-from shutil import get_terminal_size
-from typing import TYPE_CHECKING
-
-import numpy as np
-
-from pandas.io.formats.printing import pprint_thing
-
-if TYPE_CHECKING:
-    from collections.abc import Iterable
-
-    from pandas.io.formats.format import DataFrameFormatter
-
-
-class StringFormatter:
-    """Formatter for string representation of a dataframe."""
-
-    def __init__(self, fmt: DataFrameFormatter, line_width: int | None = None) -> None:
-        self.fmt = fmt
-        self.adj = fmt.adj
-        self.frame = fmt.frame
-        self.line_width = line_width
-
-    def to_string(self) -> str:
-        text = self._get_string_representation()
-        if self.fmt.should_show_dimensions:
-            text = "".join([text, self.fmt.dimensions_info])
-        return text
-
-    def _get_strcols(self) -> list[list[str]]:
-        strcols = self.fmt.get_strcols()
-        if self.fmt.is_truncated:
-            strcols = self._insert_dot_separators(strcols)
-        return strcols
-
-    def _get_string_representation(self) -> str:
-        if self.fmt.frame.empty:
-            return self._empty_info_line
-
-        strcols = self._get_strcols()
-
-        if self.line_width is None:
-            # no need to wrap around just print the whole frame
-            return self.adj.adjoin(1, *strcols)
-
-        if self._need_to_wrap_around:
-            return self._join_multiline(strcols)
-
-        return self._fit_strcols_to_terminal_width(strcols)
-
-    @property
-    def _empty_info_line(self) -> str:
-        return (
-            f"Empty {type(self.frame).__name__}\n"
-            f"Columns: {pprint_thing(self.frame.columns)}\n"
-            f"Index: {pprint_thing(self.frame.index)}"
-        )
-
-    @property
-    def _need_to_wrap_around(self) -> bool:
-        return bool(self.fmt.max_cols is None or self.fmt.max_cols > 0)
-
-    def _insert_dot_separators(self, strcols: list[list[str]]) -> list[list[str]]:
-        str_index = self.fmt._get_formatted_index(self.fmt.tr_frame)
-        index_length = len(str_index)
-
-        if self.fmt.is_truncated_horizontally:
-            strcols = self._insert_dot_separator_horizontal(strcols, index_length)
-
-        if self.fmt.is_truncated_vertically:
-            strcols = self._insert_dot_separator_vertical(strcols, index_length)
-
-        return strcols
-
-    @property
-    def _adjusted_tr_col_num(self) -> int:
-        return self.fmt.tr_col_num + 1 if self.fmt.index else self.fmt.tr_col_num
-
-    def _insert_dot_separator_horizontal(
-        self, strcols: list[list[str]], index_length: int
-    ) -> list[list[str]]:
-        strcols.insert(self._adjusted_tr_col_num, [" ..."] * index_length)
-        return strcols
-
-    def _insert_dot_separator_vertical(
-        self, strcols: list[list[str]], index_length: int
-    ) -> list[list[str]]:
-        n_header_rows = index_length - len(self.fmt.tr_frame)
-        row_num = self.fmt.tr_row_num
-        for ix, col in enumerate(strcols):
-            cwidth = self.adj.len(col[row_num])
-
-            if self.fmt.is_truncated_horizontally:
-                is_dot_col = ix == self._adjusted_tr_col_num
-            else:
-                is_dot_col = False
-
-            if cwidth > 3 or is_dot_col:
-                dots = "..."
-            else:
-                dots = ".."
-
-            if ix == 0 and self.fmt.index:
-                dot_mode = "left"
-            elif is_dot_col:
-                cwidth = 4
-                dot_mode = "right"
-            else:
-                dot_mode = "right"
-
-            dot_str = self.adj.justify([dots], cwidth, mode=dot_mode)[0]
-            col.insert(row_num + n_header_rows, dot_str)
-        return strcols
-
-    def _join_multiline(self, strcols_input: Iterable[list[str]]) -> str:
-        lwidth = self.line_width
-        adjoin_width = 1
-        strcols = list(strcols_input)
-
-        if self.fmt.index:
-            idx = strcols.pop(0)
-            lwidth -= np.array([self.adj.len(x) for x in idx]).max() + adjoin_width
-
-        col_widths = [
-            np.array([self.adj.len(x) for x in col]).max() if len(col) > 0 else 0
-            for col in strcols
-        ]
-
-        assert lwidth is not None
-        col_bins = _binify(col_widths, lwidth)
-        nbins = len(col_bins)
-
-        str_lst = []
-        start = 0
-        for i, end in enumerate(col_bins):
-            row = strcols[start:end]
-            if self.fmt.index:
-                row.insert(0, idx)
-            if nbins > 1:
-                nrows = len(row[-1])
-                if end <= len(strcols) and i < nbins - 1:
-                    row.append([" \\"] + ["  "] * (nrows - 1))
-                else:
-                    row.append([" "] * nrows)
-            str_lst.append(self.adj.adjoin(adjoin_width, *row))
-            start = end
-        return "\n\n".join(str_lst)
-
-    def _fit_strcols_to_terminal_width(self, strcols: list[list[str]]) -> str:
-        from pandas import Series
-
-        lines = self.adj.adjoin(1, *strcols).split("\n")
-        max_len = Series(lines).str.len().max()
-        # plus truncate dot col
-        width, _ = get_terminal_size()
-        dif = max_len - width
-        # '+ 1' to avoid too wide repr (GH PR #17023)
-        adj_dif = dif + 1
-        col_lens = Series([Series(ele).str.len().max() for ele in strcols])
-        n_cols = len(col_lens)
-        counter = 0
-        while adj_dif > 0 and n_cols > 1:
-            counter += 1
-            mid = round(n_cols / 2)
-            mid_ix = col_lens.index[mid]
-            col_len = col_lens[mid_ix]
-            # adjoin adds one
-            adj_dif -= col_len + 1
-            col_lens = col_lens.drop(mid_ix)
-            n_cols = len(col_lens)
-
-        # subtract index column
-        max_cols_fitted = n_cols - self.fmt.index
-        # GH-21180. Ensure that we print at least two.
-        max_cols_fitted = max(max_cols_fitted, 2)
-        self.fmt.max_cols_fitted = max_cols_fitted
-
-        # Call again _truncate to cut frame appropriately
-        # and then generate string representation
-        self.fmt.truncate()
-        strcols = self._get_strcols()
-        return self.adj.adjoin(1, *strcols)
-
-
-def _binify(cols: list[int], line_width: int) -> list[int]:
-    adjoin_width = 1
-    bins = []
-    curr_width = 0
-    i_last_column = len(cols) - 1
-    for i, w in enumerate(cols):
-        w_adjoined = w + adjoin_width
-        curr_width += w_adjoined
-        if i_last_column == i:
-            wrap = curr_width + 1 > line_width and i > 0
-        else:
-            wrap = curr_width + 2 > line_width and i > 0
-        if wrap:
-            bins.append(i)
-            curr_width = w_adjoined
-
-    bins.append(len(cols))
-    return bins
diff --git a/spaces/profayle/TerrapinTalk/myenv/lib/python3.9/site-packages/pandas/tseries/offsets.py b/spaces/profayle/TerrapinTalk/myenv/lib/python3.9/site-packages/pandas/tseries/offsets.py
deleted file mode 100644
index 169c9cc18a7fde6289a112ba5932cbb634eb3714..0000000000000000000000000000000000000000
--- a/spaces/profayle/TerrapinTalk/myenv/lib/python3.9/site-packages/pandas/tseries/offsets.py
+++ /dev/null
@@ -1,91 +0,0 @@
-from __future__ import annotations
-
-from pandas._libs.tslibs.offsets import (
-    FY5253,
-    BaseOffset,
-    BDay,
-    BMonthBegin,
-    BMonthEnd,
-    BQuarterBegin,
-    BQuarterEnd,
-    BusinessDay,
-    BusinessHour,
-    BusinessMonthBegin,
-    BusinessMonthEnd,
-    BYearBegin,
-    BYearEnd,
-    CBMonthBegin,
-    CBMonthEnd,
-    CDay,
-    CustomBusinessDay,
-    CustomBusinessHour,
-    CustomBusinessMonthBegin,
-    CustomBusinessMonthEnd,
-    DateOffset,
-    Day,
-    Easter,
-    FY5253Quarter,
-    Hour,
-    LastWeekOfMonth,
-    Micro,
-    Milli,
-    Minute,
-    MonthBegin,
-    MonthEnd,
-    Nano,
-    QuarterBegin,
-    QuarterEnd,
-    Second,
-    SemiMonthBegin,
-    SemiMonthEnd,
-    Tick,
-    Week,
-    WeekOfMonth,
-    YearBegin,
-    YearEnd,
-)
-
-__all__ = [
-    "Day",
-    "BaseOffset",
-    "BusinessDay",
-    "BusinessMonthBegin",
-    "BusinessMonthEnd",
-    "BDay",
-    "CustomBusinessDay",
-    "CustomBusinessMonthBegin",
-    "CustomBusinessMonthEnd",
-    "CDay",
-    "CBMonthEnd",
-    "CBMonthBegin",
-    "MonthBegin",
-    "BMonthBegin",
-    "MonthEnd",
-    "BMonthEnd",
-    "SemiMonthEnd",
-    "SemiMonthBegin",
-    "BusinessHour",
-    "CustomBusinessHour",
-    "YearBegin",
-    "BYearBegin",
-    "YearEnd",
-    "BYearEnd",
-    "QuarterBegin",
-    "BQuarterBegin",
-    "QuarterEnd",
-    "BQuarterEnd",
-    "LastWeekOfMonth",
-    "FY5253Quarter",
-    "FY5253",
-    "Week",
-    "WeekOfMonth",
-    "Easter",
-    "Tick",
-    "Hour",
-    "Minute",
-    "Second",
-    "Milli",
-    "Micro",
-    "Nano",
-    "DateOffset",
-]
diff --git a/spaces/profayle/TerrapinTalk/myenv/lib/python3.9/site-packages/pip/_vendor/idna/uts46data.py b/spaces/profayle/TerrapinTalk/myenv/lib/python3.9/site-packages/pip/_vendor/idna/uts46data.py
deleted file mode 100644
index 8f65705ee91fcf56d8eaf8d538a86d3e5d457d51..0000000000000000000000000000000000000000
--- a/spaces/profayle/TerrapinTalk/myenv/lib/python3.9/site-packages/pip/_vendor/idna/uts46data.py
+++ /dev/null
@@ -1,8512 +0,0 @@
-# This file is automatically generated by tools/idna-data
-# vim: set fileencoding=utf-8 :
-
-from typing import List, Tuple, Union
-
-
-"""IDNA Mapping Table from UTS46."""
-
-
-__version__ = '14.0.0'
-def _seg_0() -> List[Union[Tuple[int, str], Tuple[int, str, str]]]:
-    return [
-    (0x0, '3'),
-    (0x1, '3'),
-    (0x2, '3'),
-    (0x3, '3'),
-    (0x4, '3'),
-    (0x5, '3'),
-    (0x6, '3'),
-    (0x7, '3'),
-    (0x8, '3'),
-    (0x9, '3'),
-    (0xA, '3'),
-    (0xB, '3'),
-    (0xC, '3'),
-    (0xD, '3'),
-    (0xE, '3'),
-    (0xF, '3'),
-    (0x10, '3'),
-    (0x11, '3'),
-    (0x12, '3'),
-    (0x13, '3'),
-    (0x14, '3'),
-    (0x15, '3'),
-    (0x16, '3'),
-    (0x17, '3'),
-    (0x18, '3'),
-    (0x19, '3'),
-    (0x1A, '3'),
-    (0x1B, '3'),
-    (0x1C, '3'),
-    (0x1D, '3'),
-    (0x1E, '3'),
-    (0x1F, '3'),
-    (0x20, '3'),
-    (0x21, '3'),
-    (0x22, '3'),
-    (0x23, '3'),
-    (0x24, '3'),
-    (0x25, '3'),
-    (0x26, '3'),
-    (0x27, '3'),
-    (0x28, '3'),
-    (0x29, '3'),
-    (0x2A, '3'),
-    (0x2B, '3'),
-    (0x2C, '3'),
-    (0x2D, 'V'),
-    (0x2E, 'V'),
-    (0x2F, '3'),
-    (0x30, 'V'),
-    (0x31, 'V'),
-    (0x32, 'V'),
-    (0x33, 'V'),
-    (0x34, 'V'),
-    (0x35, 'V'),
-    (0x36, 'V'),
-    (0x37, 'V'),
-    (0x38, 'V'),
-    (0x39, 'V'),
-    (0x3A, '3'),
-    (0x3B, '3'),
-    (0x3C, '3'),
-    (0x3D, '3'),
-    (0x3E, '3'),
-    (0x3F, '3'),
-    (0x40, '3'),
-    (0x41, 'M', 'a'),
-    (0x42, 'M', 'b'),
-    (0x43, 'M', 'c'),
-    (0x44, 'M', 'd'),
-    (0x45, 'M', 'e'),
-    (0x46, 'M', 'f'),
-    (0x47, 'M', 'g'),
-    (0x48, 'M', 'h'),
-    (0x49, 'M', 'i'),
-    (0x4A, 'M', 'j'),
-    (0x4B, 'M', 'k'),
-    (0x4C, 'M', 'l'),
-    (0x4D, 'M', 'm'),
-    (0x4E, 'M', 'n'),
-    (0x4F, 'M', 'o'),
-    (0x50, 'M', 'p'),
-    (0x51, 'M', 'q'),
-    (0x52, 'M', 'r'),
-    (0x53, 'M', 's'),
-    (0x54, 'M', 't'),
-    (0x55, 'M', 'u'),
-    (0x56, 'M', 'v'),
-    (0x57, 'M', 'w'),
-    (0x58, 'M', 'x'),
-    (0x59, 'M', 'y'),
-    (0x5A, 'M', 'z'),
-    (0x5B, '3'),
-    (0x5C, '3'),
-    (0x5D, '3'),
-    (0x5E, '3'),
-    (0x5F, '3'),
-    (0x60, '3'),
-    (0x61, 'V'),
-    (0x62, 'V'),
-    (0x63, 'V'),
-    ]
-
-def _seg_1() -> List[Union[Tuple[int, str], Tuple[int, str, str]]]:
-    return [
-    (0x64, 'V'),
-    (0x65, 'V'),
-    (0x66, 'V'),
-    (0x67, 'V'),
-    (0x68, 'V'),
-    (0x69, 'V'),
-    (0x6A, 'V'),
-    (0x6B, 'V'),
-    (0x6C, 'V'),
-    (0x6D, 'V'),
-    (0x6E, 'V'),
-    (0x6F, 'V'),
-    (0x70, 'V'),
-    (0x71, 'V'),
-    (0x72, 'V'),
-    (0x73, 'V'),
-    (0x74, 'V'),
-    (0x75, 'V'),
-    (0x76, 'V'),
-    (0x77, 'V'),
-    (0x78, 'V'),
-    (0x79, 'V'),
-    (0x7A, 'V'),
-    (0x7B, '3'),
-    (0x7C, '3'),
-    (0x7D, '3'),
-    (0x7E, '3'),
-    (0x7F, '3'),
-    (0x80, 'X'),
-    (0x81, 'X'),
-    (0x82, 'X'),
-    (0x83, 'X'),
-    (0x84, 'X'),
-    (0x85, 'X'),
-    (0x86, 'X'),
-    (0x87, 'X'),
-    (0x88, 'X'),
-    (0x89, 'X'),
-    (0x8A, 'X'),
-    (0x8B, 'X'),
-    (0x8C, 'X'),
-    (0x8D, 'X'),
-    (0x8E, 'X'),
-    (0x8F, 'X'),
-    (0x90, 'X'),
-    (0x91, 'X'),
-    (0x92, 'X'),
-    (0x93, 'X'),
-    (0x94, 'X'),
-    (0x95, 'X'),
-    (0x96, 'X'),
-    (0x97, 'X'),
-    (0x98, 'X'),
-    (0x99, 'X'),
-    (0x9A, 'X'),
-    (0x9B, 'X'),
-    (0x9C, 'X'),
-    (0x9D, 'X'),
-    (0x9E, 'X'),
-    (0x9F, 'X'),
-    (0xA0, '3', ' '),
-    (0xA1, 'V'),
-    (0xA2, 'V'),
-    (0xA3, 'V'),
-    (0xA4, 'V'),
-    (0xA5, 'V'),
-    (0xA6, 'V'),
-    (0xA7, 'V'),
-    (0xA8, '3', ' ̈'),
-    (0xA9, 'V'),
-    (0xAA, 'M', 'a'),
-    (0xAB, 'V'),
-    (0xAC, 'V'),
-    (0xAD, 'I'),
-    (0xAE, 'V'),
-    (0xAF, '3', ' ̄'),
-    (0xB0, 'V'),
-    (0xB1, 'V'),
-    (0xB2, 'M', '2'),
-    (0xB3, 'M', '3'),
-    (0xB4, '3', ' ́'),
-    (0xB5, 'M', 'μ'),
-    (0xB6, 'V'),
-    (0xB7, 'V'),
-    (0xB8, '3', ' ̧'),
-    (0xB9, 'M', '1'),
-    (0xBA, 'M', 'o'),
-    (0xBB, 'V'),
-    (0xBC, 'M', '1⁄4'),
-    (0xBD, 'M', '1⁄2'),
-    (0xBE, 'M', '3⁄4'),
-    (0xBF, 'V'),
-    (0xC0, 'M', 'à'),
-    (0xC1, 'M', 'á'),
-    (0xC2, 'M', 'â'),
-    (0xC3, 'M', 'ã'),
-    (0xC4, 'M', 'ä'),
-    (0xC5, 'M', 'å'),
-    (0xC6, 'M', 'æ'),
-    (0xC7, 'M', 'ç'),
-    ]
-
-def _seg_2() -> List[Union[Tuple[int, str], Tuple[int, str, str]]]:
-    return [
-    (0xC8, 'M', 'è'),
-    (0xC9, 'M', 'é'),
-    (0xCA, 'M', 'ê'),
-    (0xCB, 'M', 'ë'),
-    (0xCC, 'M', 'ì'),
-    (0xCD, 'M', 'í'),
-    (0xCE, 'M', 'î'),
-    (0xCF, 'M', 'ï'),
-    (0xD0, 'M', 'ð'),
-    (0xD1, 'M', 'ñ'),
-    (0xD2, 'M', 'ò'),
-    (0xD3, 'M', 'ó'),
-    (0xD4, 'M', 'ô'),
-    (0xD5, 'M', 'õ'),
-    (0xD6, 'M', 'ö'),
-    (0xD7, 'V'),
-    (0xD8, 'M', 'ø'),
-    (0xD9, 'M', 'ù'),
-    (0xDA, 'M', 'ú'),
-    (0xDB, 'M', 'û'),
-    (0xDC, 'M', 'ü'),
-    (0xDD, 'M', 'ý'),
-    (0xDE, 'M', 'þ'),
-    (0xDF, 'D', 'ss'),
-    (0xE0, 'V'),
-    (0xE1, 'V'),
-    (0xE2, 'V'),
-    (0xE3, 'V'),
-    (0xE4, 'V'),
-    (0xE5, 'V'),
-    (0xE6, 'V'),
-    (0xE7, 'V'),
-    (0xE8, 'V'),
-    (0xE9, 'V'),
-    (0xEA, 'V'),
-    (0xEB, 'V'),
-    (0xEC, 'V'),
-    (0xED, 'V'),
-    (0xEE, 'V'),
-    (0xEF, 'V'),
-    (0xF0, 'V'),
-    (0xF1, 'V'),
-    (0xF2, 'V'),
-    (0xF3, 'V'),
-    (0xF4, 'V'),
-    (0xF5, 'V'),
-    (0xF6, 'V'),
-    (0xF7, 'V'),
-    (0xF8, 'V'),
-    (0xF9, 'V'),
-    (0xFA, 'V'),
-    (0xFB, 'V'),
-    (0xFC, 'V'),
-    (0xFD, 'V'),
-    (0xFE, 'V'),
-    (0xFF, 'V'),
-    (0x100, 'M', 'ā'),
-    (0x101, 'V'),
-    (0x102, 'M', 'ă'),
-    (0x103, 'V'),
-    (0x104, 'M', 'ą'),
-    (0x105, 'V'),
-    (0x106, 'M', 'ć'),
-    (0x107, 'V'),
-    (0x108, 'M', 'ĉ'),
-    (0x109, 'V'),
-    (0x10A, 'M', 'ċ'),
-    (0x10B, 'V'),
-    (0x10C, 'M', 'č'),
-    (0x10D, 'V'),
-    (0x10E, 'M', 'ď'),
-    (0x10F, 'V'),
-    (0x110, 'M', 'đ'),
-    (0x111, 'V'),
-    (0x112, 'M', 'ē'),
-    (0x113, 'V'),
-    (0x114, 'M', 'ĕ'),
-    (0x115, 'V'),
-    (0x116, 'M', 'ė'),
-    (0x117, 'V'),
-    (0x118, 'M', 'ę'),
-    (0x119, 'V'),
-    (0x11A, 'M', 'ě'),
-    (0x11B, 'V'),
-    (0x11C, 'M', 'ĝ'),
-    (0x11D, 'V'),
-    (0x11E, 'M', 'ğ'),
-    (0x11F, 'V'),
-    (0x120, 'M', 'ġ'),
-    (0x121, 'V'),
-    (0x122, 'M', 'ģ'),
-    (0x123, 'V'),
-    (0x124, 'M', 'ĥ'),
-    (0x125, 'V'),
-    (0x126, 'M', 'ħ'),
-    (0x127, 'V'),
-    (0x128, 'M', 'ĩ'),
-    (0x129, 'V'),
-    (0x12A, 'M', 'ī'),
-    (0x12B, 'V'),
-    ]
-
-def _seg_3() -> List[Union[Tuple[int, str], Tuple[int, str, str]]]:
-    return [
-    (0x12C, 'M', 'ĭ'),
-    (0x12D, 'V'),
-    (0x12E, 'M', 'į'),
-    (0x12F, 'V'),
-    (0x130, 'M', 'i̇'),
-    (0x131, 'V'),
-    (0x132, 'M', 'ij'),
-    (0x134, 'M', 'ĵ'),
-    (0x135, 'V'),
-    (0x136, 'M', 'ķ'),
-    (0x137, 'V'),
-    (0x139, 'M', 'ĺ'),
-    (0x13A, 'V'),
-    (0x13B, 'M', 'ļ'),
-    (0x13C, 'V'),
-    (0x13D, 'M', 'ľ'),
-    (0x13E, 'V'),
-    (0x13F, 'M', 'l·'),
-    (0x141, 'M', 'ł'),
-    (0x142, 'V'),
-    (0x143, 'M', 'ń'),
-    (0x144, 'V'),
-    (0x145, 'M', 'ņ'),
-    (0x146, 'V'),
-    (0x147, 'M', 'ň'),
-    (0x148, 'V'),
-    (0x149, 'M', 'ʼn'),
-    (0x14A, 'M', 'ŋ'),
-    (0x14B, 'V'),
-    (0x14C, 'M', 'ō'),
-    (0x14D, 'V'),
-    (0x14E, 'M', 'ŏ'),
-    (0x14F, 'V'),
-    (0x150, 'M', 'ő'),
-    (0x151, 'V'),
-    (0x152, 'M', 'œ'),
-    (0x153, 'V'),
-    (0x154, 'M', 'ŕ'),
-    (0x155, 'V'),
-    (0x156, 'M', 'ŗ'),
-    (0x157, 'V'),
-    (0x158, 'M', 'ř'),
-    (0x159, 'V'),
-    (0x15A, 'M', 'ś'),
-    (0x15B, 'V'),
-    (0x15C, 'M', 'ŝ'),
-    (0x15D, 'V'),
-    (0x15E, 'M', 'ş'),
-    (0x15F, 'V'),
-    (0x160, 'M', 'š'),
-    (0x161, 'V'),
-    (0x162, 'M', 'ţ'),
-    (0x163, 'V'),
-    (0x164, 'M', 'ť'),
-    (0x165, 'V'),
-    (0x166, 'M', 'ŧ'),
-    (0x167, 'V'),
-    (0x168, 'M', 'ũ'),
-    (0x169, 'V'),
-    (0x16A, 'M', 'ū'),
-    (0x16B, 'V'),
-    (0x16C, 'M', 'ŭ'),
-    (0x16D, 'V'),
-    (0x16E, 'M', 'ů'),
-    (0x16F, 'V'),
-    (0x170, 'M', 'ű'),
-    (0x171, 'V'),
-    (0x172, 'M', 'ų'),
-    (0x173, 'V'),
-    (0x174, 'M', 'ŵ'),
-    (0x175, 'V'),
-    (0x176, 'M', 'ŷ'),
-    (0x177, 'V'),
-    (0x178, 'M', 'ÿ'),
-    (0x179, 'M', 'ź'),
-    (0x17A, 'V'),
-    (0x17B, 'M', 'ż'),
-    (0x17C, 'V'),
-    (0x17D, 'M', 'ž'),
-    (0x17E, 'V'),
-    (0x17F, 'M', 's'),
-    (0x180, 'V'),
-    (0x181, 'M', 'ɓ'),
-    (0x182, 'M', 'ƃ'),
-    (0x183, 'V'),
-    (0x184, 'M', 'ƅ'),
-    (0x185, 'V'),
-    (0x186, 'M', 'ɔ'),
-    (0x187, 'M', 'ƈ'),
-    (0x188, 'V'),
-    (0x189, 'M', 'ɖ'),
-    (0x18A, 'M', 'ɗ'),
-    (0x18B, 'M', 'ƌ'),
-    (0x18C, 'V'),
-    (0x18E, 'M', 'ǝ'),
-    (0x18F, 'M', 'ə'),
-    (0x190, 'M', 'ɛ'),
-    (0x191, 'M', 'ƒ'),
-    (0x192, 'V'),
-    (0x193, 'M', 'ɠ'),
-    ]
-
-def _seg_4() -> List[Union[Tuple[int, str], Tuple[int, str, str]]]:
-    return [
-    (0x194, 'M', 'ɣ'),
-    (0x195, 'V'),
-    (0x196, 'M', 'ɩ'),
-    (0x197, 'M', 'ɨ'),
-    (0x198, 'M', 'ƙ'),
-    (0x199, 'V'),
-    (0x19C, 'M', 'ɯ'),
-    (0x19D, 'M', 'ɲ'),
-    (0x19E, 'V'),
-    (0x19F, 'M', 'ɵ'),
-    (0x1A0, 'M', 'ơ'),
-    (0x1A1, 'V'),
-    (0x1A2, 'M', 'ƣ'),
-    (0x1A3, 'V'),
-    (0x1A4, 'M', 'ƥ'),
-    (0x1A5, 'V'),
-    (0x1A6, 'M', 'ʀ'),
-    (0x1A7, 'M', 'ƨ'),
-    (0x1A8, 'V'),
-    (0x1A9, 'M', 'ʃ'),
-    (0x1AA, 'V'),
-    (0x1AC, 'M', 'ƭ'),
-    (0x1AD, 'V'),
-    (0x1AE, 'M', 'ʈ'),
-    (0x1AF, 'M', 'ư'),
-    (0x1B0, 'V'),
-    (0x1B1, 'M', 'ʊ'),
-    (0x1B2, 'M', 'ʋ'),
-    (0x1B3, 'M', 'ƴ'),
-    (0x1B4, 'V'),
-    (0x1B5, 'M', 'ƶ'),
-    (0x1B6, 'V'),
-    (0x1B7, 'M', 'ʒ'),
-    (0x1B8, 'M', 'ƹ'),
-    (0x1B9, 'V'),
-    (0x1BC, 'M', 'ƽ'),
-    (0x1BD, 'V'),
-    (0x1C4, 'M', 'dž'),
-    (0x1C7, 'M', 'lj'),
-    (0x1CA, 'M', 'nj'),
-    (0x1CD, 'M', 'ǎ'),
-    (0x1CE, 'V'),
-    (0x1CF, 'M', 'ǐ'),
-    (0x1D0, 'V'),
-    (0x1D1, 'M', 'ǒ'),
-    (0x1D2, 'V'),
-    (0x1D3, 'M', 'ǔ'),
-    (0x1D4, 'V'),
-    (0x1D5, 'M', 'ǖ'),
-    (0x1D6, 'V'),
-    (0x1D7, 'M', 'ǘ'),
-    (0x1D8, 'V'),
-    (0x1D9, 'M', 'ǚ'),
-    (0x1DA, 'V'),
-    (0x1DB, 'M', 'ǜ'),
-    (0x1DC, 'V'),
-    (0x1DE, 'M', 'ǟ'),
-    (0x1DF, 'V'),
-    (0x1E0, 'M', 'ǡ'),
-    (0x1E1, 'V'),
-    (0x1E2, 'M', 'ǣ'),
-    (0x1E3, 'V'),
-    (0x1E4, 'M', 'ǥ'),
-    (0x1E5, 'V'),
-    (0x1E6, 'M', 'ǧ'),
-    (0x1E7, 'V'),
-    (0x1E8, 'M', 'ǩ'),
-    (0x1E9, 'V'),
-    (0x1EA, 'M', 'ǫ'),
-    (0x1EB, 'V'),
-    (0x1EC, 'M', 'ǭ'),
-    (0x1ED, 'V'),
-    (0x1EE, 'M', 'ǯ'),
-    (0x1EF, 'V'),
-    (0x1F1, 'M', 'dz'),
-    (0x1F4, 'M', 'ǵ'),
-    (0x1F5, 'V'),
-    (0x1F6, 'M', 'ƕ'),
-    (0x1F7, 'M', 'ƿ'),
-    (0x1F8, 'M', 'ǹ'),
-    (0x1F9, 'V'),
-    (0x1FA, 'M', 'ǻ'),
-    (0x1FB, 'V'),
-    (0x1FC, 'M', 'ǽ'),
-    (0x1FD, 'V'),
-    (0x1FE, 'M', 'ǿ'),
-    (0x1FF, 'V'),
-    (0x200, 'M', 'ȁ'),
-    (0x201, 'V'),
-    (0x202, 'M', 'ȃ'),
-    (0x203, 'V'),
-    (0x204, 'M', 'ȅ'),
-    (0x205, 'V'),
-    (0x206, 'M', 'ȇ'),
-    (0x207, 'V'),
-    (0x208, 'M', 'ȉ'),
-    (0x209, 'V'),
-    (0x20A, 'M', 'ȋ'),
-    (0x20B, 'V'),
-    (0x20C, 'M', 'ȍ'),
-    ]
-
-def _seg_5() -> List[Union[Tuple[int, str], Tuple[int, str, str]]]:
-    return [
-    (0x20D, 'V'),
-    (0x20E, 'M', 'ȏ'),
-    (0x20F, 'V'),
-    (0x210, 'M', 'ȑ'),
-    (0x211, 'V'),
-    (0x212, 'M', 'ȓ'),
-    (0x213, 'V'),
-    (0x214, 'M', 'ȕ'),
-    (0x215, 'V'),
-    (0x216, 'M', 'ȗ'),
-    (0x217, 'V'),
-    (0x218, 'M', 'ș'),
-    (0x219, 'V'),
-    (0x21A, 'M', 'ț'),
-    (0x21B, 'V'),
-    (0x21C, 'M', 'ȝ'),
-    (0x21D, 'V'),
-    (0x21E, 'M', 'ȟ'),
-    (0x21F, 'V'),
-    (0x220, 'M', 'ƞ'),
-    (0x221, 'V'),
-    (0x222, 'M', 'ȣ'),
-    (0x223, 'V'),
-    (0x224, 'M', 'ȥ'),
-    (0x225, 'V'),
-    (0x226, 'M', 'ȧ'),
-    (0x227, 'V'),
-    (0x228, 'M', 'ȩ'),
-    (0x229, 'V'),
-    (0x22A, 'M', 'ȫ'),
-    (0x22B, 'V'),
-    (0x22C, 'M', 'ȭ'),
-    (0x22D, 'V'),
-    (0x22E, 'M', 'ȯ'),
-    (0x22F, 'V'),
-    (0x230, 'M', 'ȱ'),
-    (0x231, 'V'),
-    (0x232, 'M', 'ȳ'),
-    (0x233, 'V'),
-    (0x23A, 'M', 'ⱥ'),
-    (0x23B, 'M', 'ȼ'),
-    (0x23C, 'V'),
-    (0x23D, 'M', 'ƚ'),
-    (0x23E, 'M', 'ⱦ'),
-    (0x23F, 'V'),
-    (0x241, 'M', 'ɂ'),
-    (0x242, 'V'),
-    (0x243, 'M', 'ƀ'),
-    (0x244, 'M', 'ʉ'),
-    (0x245, 'M', 'ʌ'),
-    (0x246, 'M', 'ɇ'),
-    (0x247, 'V'),
-    (0x248, 'M', 'ɉ'),
-    (0x249, 'V'),
-    (0x24A, 'M', 'ɋ'),
-    (0x24B, 'V'),
-    (0x24C, 'M', 'ɍ'),
-    (0x24D, 'V'),
-    (0x24E, 'M', 'ɏ'),
-    (0x24F, 'V'),
-    (0x2B0, 'M', 'h'),
-    (0x2B1, 'M', 'ɦ'),
-    (0x2B2, 'M', 'j'),
-    (0x2B3, 'M', 'r'),
-    (0x2B4, 'M', 'ɹ'),
-    (0x2B5, 'M', 'ɻ'),
-    (0x2B6, 'M', 'ʁ'),
-    (0x2B7, 'M', 'w'),
-    (0x2B8, 'M', 'y'),
-    (0x2B9, 'V'),
-    (0x2D8, '3', ' ̆'),
-    (0x2D9, '3', ' ̇'),
-    (0x2DA, '3', ' ̊'),
-    (0x2DB, '3', ' ̨'),
-    (0x2DC, '3', ' ̃'),
-    (0x2DD, '3', ' ̋'),
-    (0x2DE, 'V'),
-    (0x2E0, 'M', 'ɣ'),
-    (0x2E1, 'M', 'l'),
-    (0x2E2, 'M', 's'),
-    (0x2E3, 'M', 'x'),
-    (0x2E4, 'M', 'ʕ'),
-    (0x2E5, 'V'),
-    (0x340, 'M', '̀'),
-    (0x341, 'M', '́'),
-    (0x342, 'V'),
-    (0x343, 'M', '̓'),
-    (0x344, 'M', '̈́'),
-    (0x345, 'M', 'ι'),
-    (0x346, 'V'),
-    (0x34F, 'I'),
-    (0x350, 'V'),
-    (0x370, 'M', 'ͱ'),
-    (0x371, 'V'),
-    (0x372, 'M', 'ͳ'),
-    (0x373, 'V'),
-    (0x374, 'M', 'ʹ'),
-    (0x375, 'V'),
-    (0x376, 'M', 'ͷ'),
-    (0x377, 'V'),
-    ]
-
-def _seg_6() -> List[Union[Tuple[int, str], Tuple[int, str, str]]]:
-    return [
-    (0x378, 'X'),
-    (0x37A, '3', ' ι'),
-    (0x37B, 'V'),
-    (0x37E, '3', ';'),
-    (0x37F, 'M', 'ϳ'),
-    (0x380, 'X'),
-    (0x384, '3', ' ́'),
-    (0x385, '3', ' ̈́'),
-    (0x386, 'M', 'ά'),
-    (0x387, 'M', '·'),
-    (0x388, 'M', 'έ'),
-    (0x389, 'M', 'ή'),
-    (0x38A, 'M', 'ί'),
-    (0x38B, 'X'),
-    (0x38C, 'M', 'ό'),
-    (0x38D, 'X'),
-    (0x38E, 'M', 'ύ'),
-    (0x38F, 'M', 'ώ'),
-    (0x390, 'V'),
-    (0x391, 'M', 'α'),
-    (0x392, 'M', 'β'),
-    (0x393, 'M', 'γ'),
-    (0x394, 'M', 'δ'),
-    (0x395, 'M', 'ε'),
-    (0x396, 'M', 'ζ'),
-    (0x397, 'M', 'η'),
-    (0x398, 'M', 'θ'),
-    (0x399, 'M', 'ι'),
-    (0x39A, 'M', 'κ'),
-    (0x39B, 'M', 'λ'),
-    (0x39C, 'M', 'μ'),
-    (0x39D, 'M', 'ν'),
-    (0x39E, 'M', 'ξ'),
-    (0x39F, 'M', 'ο'),
-    (0x3A0, 'M', 'π'),
-    (0x3A1, 'M', 'ρ'),
-    (0x3A2, 'X'),
-    (0x3A3, 'M', 'σ'),
-    (0x3A4, 'M', 'τ'),
-    (0x3A5, 'M', 'υ'),
-    (0x3A6, 'M', 'φ'),
-    (0x3A7, 'M', 'χ'),
-    (0x3A8, 'M', 'ψ'),
-    (0x3A9, 'M', 'ω'),
-    (0x3AA, 'M', 'ϊ'),
-    (0x3AB, 'M', 'ϋ'),
-    (0x3AC, 'V'),
-    (0x3C2, 'D', 'σ'),
-    (0x3C3, 'V'),
-    (0x3CF, 'M', 'ϗ'),
-    (0x3D0, 'M', 'β'),
-    (0x3D1, 'M', 'θ'),
-    (0x3D2, 'M', 'υ'),
-    (0x3D3, 'M', 'ύ'),
-    (0x3D4, 'M', 'ϋ'),
-    (0x3D5, 'M', 'φ'),
-    (0x3D6, 'M', 'π'),
-    (0x3D7, 'V'),
-    (0x3D8, 'M', 'ϙ'),
-    (0x3D9, 'V'),
-    (0x3DA, 'M', 'ϛ'),
-    (0x3DB, 'V'),
-    (0x3DC, 'M', 'ϝ'),
-    (0x3DD, 'V'),
-    (0x3DE, 'M', 'ϟ'),
-    (0x3DF, 'V'),
-    (0x3E0, 'M', 'ϡ'),
-    (0x3E1, 'V'),
-    (0x3E2, 'M', 'ϣ'),
-    (0x3E3, 'V'),
-    (0x3E4, 'M', 'ϥ'),
-    (0x3E5, 'V'),
-    (0x3E6, 'M', 'ϧ'),
-    (0x3E7, 'V'),
-    (0x3E8, 'M', 'ϩ'),
-    (0x3E9, 'V'),
-    (0x3EA, 'M', 'ϫ'),
-    (0x3EB, 'V'),
-    (0x3EC, 'M', 'ϭ'),
-    (0x3ED, 'V'),
-    (0x3EE, 'M', 'ϯ'),
-    (0x3EF, 'V'),
-    (0x3F0, 'M', 'κ'),
-    (0x3F1, 'M', 'ρ'),
-    (0x3F2, 'M', 'σ'),
-    (0x3F3, 'V'),
-    (0x3F4, 'M', 'θ'),
-    (0x3F5, 'M', 'ε'),
-    (0x3F6, 'V'),
-    (0x3F7, 'M', 'ϸ'),
-    (0x3F8, 'V'),
-    (0x3F9, 'M', 'σ'),
-    (0x3FA, 'M', 'ϻ'),
-    (0x3FB, 'V'),
-    (0x3FD, 'M', 'ͻ'),
-    (0x3FE, 'M', 'ͼ'),
-    (0x3FF, 'M', 'ͽ'),
-    (0x400, 'M', 'ѐ'),
-    (0x401, 'M', 'ё'),
-    (0x402, 'M', 'ђ'),
-    ]
-
-def _seg_7() -> List[Union[Tuple[int, str], Tuple[int, str, str]]]:
-    return [
-    (0x403, 'M', 'ѓ'),
-    (0x404, 'M', 'є'),
-    (0x405, 'M', 'ѕ'),
-    (0x406, 'M', 'і'),
-    (0x407, 'M', 'ї'),
-    (0x408, 'M', 'ј'),
-    (0x409, 'M', 'љ'),
-    (0x40A, 'M', 'њ'),
-    (0x40B, 'M', 'ћ'),
-    (0x40C, 'M', 'ќ'),
-    (0x40D, 'M', 'ѝ'),
-    (0x40E, 'M', 'ў'),
-    (0x40F, 'M', 'џ'),
-    (0x410, 'M', 'а'),
-    (0x411, 'M', 'б'),
-    (0x412, 'M', 'в'),
-    (0x413, 'M', 'г'),
-    (0x414, 'M', 'д'),
-    (0x415, 'M', 'е'),
-    (0x416, 'M', 'ж'),
-    (0x417, 'M', 'з'),
-    (0x418, 'M', 'и'),
-    (0x419, 'M', 'й'),
-    (0x41A, 'M', 'к'),
-    (0x41B, 'M', 'л'),
-    (0x41C, 'M', 'м'),
-    (0x41D, 'M', 'н'),
-    (0x41E, 'M', 'о'),
-    (0x41F, 'M', 'п'),
-    (0x420, 'M', 'р'),
-    (0x421, 'M', 'с'),
-    (0x422, 'M', 'т'),
-    (0x423, 'M', 'у'),
-    (0x424, 'M', 'ф'),
-    (0x425, 'M', 'х'),
-    (0x426, 'M', 'ц'),
-    (0x427, 'M', 'ч'),
-    (0x428, 'M', 'ш'),
-    (0x429, 'M', 'щ'),
-    (0x42A, 'M', 'ъ'),
-    (0x42B, 'M', 'ы'),
-    (0x42C, 'M', 'ь'),
-    (0x42D, 'M', 'э'),
-    (0x42E, 'M', 'ю'),
-    (0x42F, 'M', 'я'),
-    (0x430, 'V'),
-    (0x460, 'M', 'ѡ'),
-    (0x461, 'V'),
-    (0x462, 'M', 'ѣ'),
-    (0x463, 'V'),
-    (0x464, 'M', 'ѥ'),
-    (0x465, 'V'),
-    (0x466, 'M', 'ѧ'),
-    (0x467, 'V'),
-    (0x468, 'M', 'ѩ'),
-    (0x469, 'V'),
-    (0x46A, 'M', 'ѫ'),
-    (0x46B, 'V'),
-    (0x46C, 'M', 'ѭ'),
-    (0x46D, 'V'),
-    (0x46E, 'M', 'ѯ'),
-    (0x46F, 'V'),
-    (0x470, 'M', 'ѱ'),
-    (0x471, 'V'),
-    (0x472, 'M', 'ѳ'),
-    (0x473, 'V'),
-    (0x474, 'M', 'ѵ'),
-    (0x475, 'V'),
-    (0x476, 'M', 'ѷ'),
-    (0x477, 'V'),
-    (0x478, 'M', 'ѹ'),
-    (0x479, 'V'),
-    (0x47A, 'M', 'ѻ'),
-    (0x47B, 'V'),
-    (0x47C, 'M', 'ѽ'),
-    (0x47D, 'V'),
-    (0x47E, 'M', 'ѿ'),
-    (0x47F, 'V'),
-    (0x480, 'M', 'ҁ'),
-    (0x481, 'V'),
-    (0x48A, 'M', 'ҋ'),
-    (0x48B, 'V'),
-    (0x48C, 'M', 'ҍ'),
-    (0x48D, 'V'),
-    (0x48E, 'M', 'ҏ'),
-    (0x48F, 'V'),
-    (0x490, 'M', 'ґ'),
-    (0x491, 'V'),
-    (0x492, 'M', 'ғ'),
-    (0x493, 'V'),
-    (0x494, 'M', 'ҕ'),
-    (0x495, 'V'),
-    (0x496, 'M', 'җ'),
-    (0x497, 'V'),
-    (0x498, 'M', 'ҙ'),
-    (0x499, 'V'),
-    (0x49A, 'M', 'қ'),
-    (0x49B, 'V'),
-    (0x49C, 'M', 'ҝ'),
-    (0x49D, 'V'),
-    ]
-
-def _seg_8() -> List[Union[Tuple[int, str], Tuple[int, str, str]]]:
-    return [
-    (0x49E, 'M', 'ҟ'),
-    (0x49F, 'V'),
-    (0x4A0, 'M', 'ҡ'),
-    (0x4A1, 'V'),
-    (0x4A2, 'M', 'ң'),
-    (0x4A3, 'V'),
-    (0x4A4, 'M', 'ҥ'),
-    (0x4A5, 'V'),
-    (0x4A6, 'M', 'ҧ'),
-    (0x4A7, 'V'),
-    (0x4A8, 'M', 'ҩ'),
-    (0x4A9, 'V'),
-    (0x4AA, 'M', 'ҫ'),
-    (0x4AB, 'V'),
-    (0x4AC, 'M', 'ҭ'),
-    (0x4AD, 'V'),
-    (0x4AE, 'M', 'ү'),
-    (0x4AF, 'V'),
-    (0x4B0, 'M', 'ұ'),
-    (0x4B1, 'V'),
-    (0x4B2, 'M', 'ҳ'),
-    (0x4B3, 'V'),
-    (0x4B4, 'M', 'ҵ'),
-    (0x4B5, 'V'),
-    (0x4B6, 'M', 'ҷ'),
-    (0x4B7, 'V'),
-    (0x4B8, 'M', 'ҹ'),
-    (0x4B9, 'V'),
-    (0x4BA, 'M', 'һ'),
-    (0x4BB, 'V'),
-    (0x4BC, 'M', 'ҽ'),
-    (0x4BD, 'V'),
-    (0x4BE, 'M', 'ҿ'),
-    (0x4BF, 'V'),
-    (0x4C0, 'X'),
-    (0x4C1, 'M', 'ӂ'),
-    (0x4C2, 'V'),
-    (0x4C3, 'M', 'ӄ'),
-    (0x4C4, 'V'),
-    (0x4C5, 'M', 'ӆ'),
-    (0x4C6, 'V'),
-    (0x4C7, 'M', 'ӈ'),
-    (0x4C8, 'V'),
-    (0x4C9, 'M', 'ӊ'),
-    (0x4CA, 'V'),
-    (0x4CB, 'M', 'ӌ'),
-    (0x4CC, 'V'),
-    (0x4CD, 'M', 'ӎ'),
-    (0x4CE, 'V'),
-    (0x4D0, 'M', 'ӑ'),
-    (0x4D1, 'V'),
-    (0x4D2, 'M', 'ӓ'),
-    (0x4D3, 'V'),
-    (0x4D4, 'M', 'ӕ'),
-    (0x4D5, 'V'),
-    (0x4D6, 'M', 'ӗ'),
-    (0x4D7, 'V'),
-    (0x4D8, 'M', 'ә'),
-    (0x4D9, 'V'),
-    (0x4DA, 'M', 'ӛ'),
-    (0x4DB, 'V'),
-    (0x4DC, 'M', 'ӝ'),
-    (0x4DD, 'V'),
-    (0x4DE, 'M', 'ӟ'),
-    (0x4DF, 'V'),
-    (0x4E0, 'M', 'ӡ'),
-    (0x4E1, 'V'),
-    (0x4E2, 'M', 'ӣ'),
-    (0x4E3, 'V'),
-    (0x4E4, 'M', 'ӥ'),
-    (0x4E5, 'V'),
-    (0x4E6, 'M', 'ӧ'),
-    (0x4E7, 'V'),
-    (0x4E8, 'M', 'ө'),
-    (0x4E9, 'V'),
-    (0x4EA, 'M', 'ӫ'),
-    (0x4EB, 'V'),
-    (0x4EC, 'M', 'ӭ'),
-    (0x4ED, 'V'),
-    (0x4EE, 'M', 'ӯ'),
-    (0x4EF, 'V'),
-    (0x4F0, 'M', 'ӱ'),
-    (0x4F1, 'V'),
-    (0x4F2, 'M', 'ӳ'),
-    (0x4F3, 'V'),
-    (0x4F4, 'M', 'ӵ'),
-    (0x4F5, 'V'),
-    (0x4F6, 'M', 'ӷ'),
-    (0x4F7, 'V'),
-    (0x4F8, 'M', 'ӹ'),
-    (0x4F9, 'V'),
-    (0x4FA, 'M', 'ӻ'),
-    (0x4FB, 'V'),
-    (0x4FC, 'M', 'ӽ'),
-    (0x4FD, 'V'),
-    (0x4FE, 'M', 'ӿ'),
-    (0x4FF, 'V'),
-    (0x500, 'M', 'ԁ'),
-    (0x501, 'V'),
-    (0x502, 'M', 'ԃ'),
-    ]
-
-def _seg_9() -> List[Union[Tuple[int, str], Tuple[int, str, str]]]:
-    return [
-    (0x503, 'V'),
-    (0x504, 'M', 'ԅ'),
-    (0x505, 'V'),
-    (0x506, 'M', 'ԇ'),
-    (0x507, 'V'),
-    (0x508, 'M', 'ԉ'),
-    (0x509, 'V'),
-    (0x50A, 'M', 'ԋ'),
-    (0x50B, 'V'),
-    (0x50C, 'M', 'ԍ'),
-    (0x50D, 'V'),
-    (0x50E, 'M', 'ԏ'),
-    (0x50F, 'V'),
-    (0x510, 'M', 'ԑ'),
-    (0x511, 'V'),
-    (0x512, 'M', 'ԓ'),
-    (0x513, 'V'),
-    (0x514, 'M', 'ԕ'),
-    (0x515, 'V'),
-    (0x516, 'M', 'ԗ'),
-    (0x517, 'V'),
-    (0x518, 'M', 'ԙ'),
-    (0x519, 'V'),
-    (0x51A, 'M', 'ԛ'),
-    (0x51B, 'V'),
-    (0x51C, 'M', 'ԝ'),
-    (0x51D, 'V'),
-    (0x51E, 'M', 'ԟ'),
-    (0x51F, 'V'),
-    (0x520, 'M', 'ԡ'),
-    (0x521, 'V'),
-    (0x522, 'M', 'ԣ'),
-    (0x523, 'V'),
-    (0x524, 'M', 'ԥ'),
-    (0x525, 'V'),
-    (0x526, 'M', 'ԧ'),
-    (0x527, 'V'),
-    (0x528, 'M', 'ԩ'),
-    (0x529, 'V'),
-    (0x52A, 'M', 'ԫ'),
-    (0x52B, 'V'),
-    (0x52C, 'M', 'ԭ'),
-    (0x52D, 'V'),
-    (0x52E, 'M', 'ԯ'),
-    (0x52F, 'V'),
-    (0x530, 'X'),
-    (0x531, 'M', 'ա'),
-    (0x532, 'M', 'բ'),
-    (0x533, 'M', 'գ'),
-    (0x534, 'M', 'դ'),
-    (0x535, 'M', 'ե'),
-    (0x536, 'M', 'զ'),
-    (0x537, 'M', 'է'),
-    (0x538, 'M', 'ը'),
-    (0x539, 'M', 'թ'),
-    (0x53A, 'M', 'ժ'),
-    (0x53B, 'M', 'ի'),
-    (0x53C, 'M', 'լ'),
-    (0x53D, 'M', 'խ'),
-    (0x53E, 'M', 'ծ'),
-    (0x53F, 'M', 'կ'),
-    (0x540, 'M', 'հ'),
-    (0x541, 'M', 'ձ'),
-    (0x542, 'M', 'ղ'),
-    (0x543, 'M', 'ճ'),
-    (0x544, 'M', 'մ'),
-    (0x545, 'M', 'յ'),
-    (0x546, 'M', 'ն'),
-    (0x547, 'M', 'շ'),
-    (0x548, 'M', 'ո'),
-    (0x549, 'M', 'չ'),
-    (0x54A, 'M', 'պ'),
-    (0x54B, 'M', 'ջ'),
-    (0x54C, 'M', 'ռ'),
-    (0x54D, 'M', 'ս'),
-    (0x54E, 'M', 'վ'),
-    (0x54F, 'M', 'տ'),
-    (0x550, 'M', 'ր'),
-    (0x551, 'M', 'ց'),
-    (0x552, 'M', 'ւ'),
-    (0x553, 'M', 'փ'),
-    (0x554, 'M', 'ք'),
-    (0x555, 'M', 'օ'),
-    (0x556, 'M', 'ֆ'),
-    (0x557, 'X'),
-    (0x559, 'V'),
-    (0x587, 'M', 'եւ'),
-    (0x588, 'V'),
-    (0x58B, 'X'),
-    (0x58D, 'V'),
-    (0x590, 'X'),
-    (0x591, 'V'),
-    (0x5C8, 'X'),
-    (0x5D0, 'V'),
-    (0x5EB, 'X'),
-    (0x5EF, 'V'),
-    (0x5F5, 'X'),
-    (0x606, 'V'),
-    (0x61C, 'X'),
-    (0x61D, 'V'),
-    ]
-
-def _seg_10() -> List[Union[Tuple[int, str], Tuple[int, str, str]]]:
-    return [
-    (0x675, 'M', 'اٴ'),
-    (0x676, 'M', 'وٴ'),
-    (0x677, 'M', 'ۇٴ'),
-    (0x678, 'M', 'يٴ'),
-    (0x679, 'V'),
-    (0x6DD, 'X'),
-    (0x6DE, 'V'),
-    (0x70E, 'X'),
-    (0x710, 'V'),
-    (0x74B, 'X'),
-    (0x74D, 'V'),
-    (0x7B2, 'X'),
-    (0x7C0, 'V'),
-    (0x7FB, 'X'),
-    (0x7FD, 'V'),
-    (0x82E, 'X'),
-    (0x830, 'V'),
-    (0x83F, 'X'),
-    (0x840, 'V'),
-    (0x85C, 'X'),
-    (0x85E, 'V'),
-    (0x85F, 'X'),
-    (0x860, 'V'),
-    (0x86B, 'X'),
-    (0x870, 'V'),
-    (0x88F, 'X'),
-    (0x898, 'V'),
-    (0x8E2, 'X'),
-    (0x8E3, 'V'),
-    (0x958, 'M', 'क़'),
-    (0x959, 'M', 'ख़'),
-    (0x95A, 'M', 'ग़'),
-    (0x95B, 'M', 'ज़'),
-    (0x95C, 'M', 'ड़'),
-    (0x95D, 'M', 'ढ़'),
-    (0x95E, 'M', 'फ़'),
-    (0x95F, 'M', 'य़'),
-    (0x960, 'V'),
-    (0x984, 'X'),
-    (0x985, 'V'),
-    (0x98D, 'X'),
-    (0x98F, 'V'),
-    (0x991, 'X'),
-    (0x993, 'V'),
-    (0x9A9, 'X'),
-    (0x9AA, 'V'),
-    (0x9B1, 'X'),
-    (0x9B2, 'V'),
-    (0x9B3, 'X'),
-    (0x9B6, 'V'),
-    (0x9BA, 'X'),
-    (0x9BC, 'V'),
-    (0x9C5, 'X'),
-    (0x9C7, 'V'),
-    (0x9C9, 'X'),
-    (0x9CB, 'V'),
-    (0x9CF, 'X'),
-    (0x9D7, 'V'),
-    (0x9D8, 'X'),
-    (0x9DC, 'M', 'ড়'),
-    (0x9DD, 'M', 'ঢ়'),
-    (0x9DE, 'X'),
-    (0x9DF, 'M', 'য়'),
-    (0x9E0, 'V'),
-    (0x9E4, 'X'),
-    (0x9E6, 'V'),
-    (0x9FF, 'X'),
-    (0xA01, 'V'),
-    (0xA04, 'X'),
-    (0xA05, 'V'),
-    (0xA0B, 'X'),
-    (0xA0F, 'V'),
-    (0xA11, 'X'),
-    (0xA13, 'V'),
-    (0xA29, 'X'),
-    (0xA2A, 'V'),
-    (0xA31, 'X'),
-    (0xA32, 'V'),
-    (0xA33, 'M', 'ਲ਼'),
-    (0xA34, 'X'),
-    (0xA35, 'V'),
-    (0xA36, 'M', 'ਸ਼'),
-    (0xA37, 'X'),
-    (0xA38, 'V'),
-    (0xA3A, 'X'),
-    (0xA3C, 'V'),
-    (0xA3D, 'X'),
-    (0xA3E, 'V'),
-    (0xA43, 'X'),
-    (0xA47, 'V'),
-    (0xA49, 'X'),
-    (0xA4B, 'V'),
-    (0xA4E, 'X'),
-    (0xA51, 'V'),
-    (0xA52, 'X'),
-    (0xA59, 'M', 'ਖ਼'),
-    (0xA5A, 'M', 'ਗ਼'),
-    (0xA5B, 'M', 'ਜ਼'),
-    (0xA5C, 'V'),
-    (0xA5D, 'X'),
-    ]
-
-def _seg_11() -> List[Union[Tuple[int, str], Tuple[int, str, str]]]:
-    return [
-    (0xA5E, 'M', 'ਫ਼'),
-    (0xA5F, 'X'),
-    (0xA66, 'V'),
-    (0xA77, 'X'),
-    (0xA81, 'V'),
-    (0xA84, 'X'),
-    (0xA85, 'V'),
-    (0xA8E, 'X'),
-    (0xA8F, 'V'),
-    (0xA92, 'X'),
-    (0xA93, 'V'),
-    (0xAA9, 'X'),
-    (0xAAA, 'V'),
-    (0xAB1, 'X'),
-    (0xAB2, 'V'),
-    (0xAB4, 'X'),
-    (0xAB5, 'V'),
-    (0xABA, 'X'),
-    (0xABC, 'V'),
-    (0xAC6, 'X'),
-    (0xAC7, 'V'),
-    (0xACA, 'X'),
-    (0xACB, 'V'),
-    (0xACE, 'X'),
-    (0xAD0, 'V'),
-    (0xAD1, 'X'),
-    (0xAE0, 'V'),
-    (0xAE4, 'X'),
-    (0xAE6, 'V'),
-    (0xAF2, 'X'),
-    (0xAF9, 'V'),
-    (0xB00, 'X'),
-    (0xB01, 'V'),
-    (0xB04, 'X'),
-    (0xB05, 'V'),
-    (0xB0D, 'X'),
-    (0xB0F, 'V'),
-    (0xB11, 'X'),
-    (0xB13, 'V'),
-    (0xB29, 'X'),
-    (0xB2A, 'V'),
-    (0xB31, 'X'),
-    (0xB32, 'V'),
-    (0xB34, 'X'),
-    (0xB35, 'V'),
-    (0xB3A, 'X'),
-    (0xB3C, 'V'),
-    (0xB45, 'X'),
-    (0xB47, 'V'),
-    (0xB49, 'X'),
-    (0xB4B, 'V'),
-    (0xB4E, 'X'),
-    (0xB55, 'V'),
-    (0xB58, 'X'),
-    (0xB5C, 'M', 'ଡ଼'),
-    (0xB5D, 'M', 'ଢ଼'),
-    (0xB5E, 'X'),
-    (0xB5F, 'V'),
-    (0xB64, 'X'),
-    (0xB66, 'V'),
-    (0xB78, 'X'),
-    (0xB82, 'V'),
-    (0xB84, 'X'),
-    (0xB85, 'V'),
-    (0xB8B, 'X'),
-    (0xB8E, 'V'),
-    (0xB91, 'X'),
-    (0xB92, 'V'),
-    (0xB96, 'X'),
-    (0xB99, 'V'),
-    (0xB9B, 'X'),
-    (0xB9C, 'V'),
-    (0xB9D, 'X'),
-    (0xB9E, 'V'),
-    (0xBA0, 'X'),
-    (0xBA3, 'V'),
-    (0xBA5, 'X'),
-    (0xBA8, 'V'),
-    (0xBAB, 'X'),
-    (0xBAE, 'V'),
-    (0xBBA, 'X'),
-    (0xBBE, 'V'),
-    (0xBC3, 'X'),
-    (0xBC6, 'V'),
-    (0xBC9, 'X'),
-    (0xBCA, 'V'),
-    (0xBCE, 'X'),
-    (0xBD0, 'V'),
-    (0xBD1, 'X'),
-    (0xBD7, 'V'),
-    (0xBD8, 'X'),
-    (0xBE6, 'V'),
-    (0xBFB, 'X'),
-    (0xC00, 'V'),
-    (0xC0D, 'X'),
-    (0xC0E, 'V'),
-    (0xC11, 'X'),
-    (0xC12, 'V'),
-    (0xC29, 'X'),
-    (0xC2A, 'V'),
-    ]
-
-def _seg_12() -> List[Union[Tuple[int, str], Tuple[int, str, str]]]:
-    return [
-    (0xC3A, 'X'),
-    (0xC3C, 'V'),
-    (0xC45, 'X'),
-    (0xC46, 'V'),
-    (0xC49, 'X'),
-    (0xC4A, 'V'),
-    (0xC4E, 'X'),
-    (0xC55, 'V'),
-    (0xC57, 'X'),
-    (0xC58, 'V'),
-    (0xC5B, 'X'),
-    (0xC5D, 'V'),
-    (0xC5E, 'X'),
-    (0xC60, 'V'),
-    (0xC64, 'X'),
-    (0xC66, 'V'),
-    (0xC70, 'X'),
-    (0xC77, 'V'),
-    (0xC8D, 'X'),
-    (0xC8E, 'V'),
-    (0xC91, 'X'),
-    (0xC92, 'V'),
-    (0xCA9, 'X'),
-    (0xCAA, 'V'),
-    (0xCB4, 'X'),
-    (0xCB5, 'V'),
-    (0xCBA, 'X'),
-    (0xCBC, 'V'),
-    (0xCC5, 'X'),
-    (0xCC6, 'V'),
-    (0xCC9, 'X'),
-    (0xCCA, 'V'),
-    (0xCCE, 'X'),
-    (0xCD5, 'V'),
-    (0xCD7, 'X'),
-    (0xCDD, 'V'),
-    (0xCDF, 'X'),
-    (0xCE0, 'V'),
-    (0xCE4, 'X'),
-    (0xCE6, 'V'),
-    (0xCF0, 'X'),
-    (0xCF1, 'V'),
-    (0xCF3, 'X'),
-    (0xD00, 'V'),
-    (0xD0D, 'X'),
-    (0xD0E, 'V'),
-    (0xD11, 'X'),
-    (0xD12, 'V'),
-    (0xD45, 'X'),
-    (0xD46, 'V'),
-    (0xD49, 'X'),
-    (0xD4A, 'V'),
-    (0xD50, 'X'),
-    (0xD54, 'V'),
-    (0xD64, 'X'),
-    (0xD66, 'V'),
-    (0xD80, 'X'),
-    (0xD81, 'V'),
-    (0xD84, 'X'),
-    (0xD85, 'V'),
-    (0xD97, 'X'),
-    (0xD9A, 'V'),
-    (0xDB2, 'X'),
-    (0xDB3, 'V'),
-    (0xDBC, 'X'),
-    (0xDBD, 'V'),
-    (0xDBE, 'X'),
-    (0xDC0, 'V'),
-    (0xDC7, 'X'),
-    (0xDCA, 'V'),
-    (0xDCB, 'X'),
-    (0xDCF, 'V'),
-    (0xDD5, 'X'),
-    (0xDD6, 'V'),
-    (0xDD7, 'X'),
-    (0xDD8, 'V'),
-    (0xDE0, 'X'),
-    (0xDE6, 'V'),
-    (0xDF0, 'X'),
-    (0xDF2, 'V'),
-    (0xDF5, 'X'),
-    (0xE01, 'V'),
-    (0xE33, 'M', 'ํา'),
-    (0xE34, 'V'),
-    (0xE3B, 'X'),
-    (0xE3F, 'V'),
-    (0xE5C, 'X'),
-    (0xE81, 'V'),
-    (0xE83, 'X'),
-    (0xE84, 'V'),
-    (0xE85, 'X'),
-    (0xE86, 'V'),
-    (0xE8B, 'X'),
-    (0xE8C, 'V'),
-    (0xEA4, 'X'),
-    (0xEA5, 'V'),
-    (0xEA6, 'X'),
-    (0xEA7, 'V'),
-    (0xEB3, 'M', 'ໍາ'),
-    (0xEB4, 'V'),
-    ]
-
-def _seg_13() -> List[Union[Tuple[int, str], Tuple[int, str, str]]]:
-    return [
-    (0xEBE, 'X'),
-    (0xEC0, 'V'),
-    (0xEC5, 'X'),
-    (0xEC6, 'V'),
-    (0xEC7, 'X'),
-    (0xEC8, 'V'),
-    (0xECE, 'X'),
-    (0xED0, 'V'),
-    (0xEDA, 'X'),
-    (0xEDC, 'M', 'ຫນ'),
-    (0xEDD, 'M', 'ຫມ'),
-    (0xEDE, 'V'),
-    (0xEE0, 'X'),
-    (0xF00, 'V'),
-    (0xF0C, 'M', '་'),
-    (0xF0D, 'V'),
-    (0xF43, 'M', 'གྷ'),
-    (0xF44, 'V'),
-    (0xF48, 'X'),
-    (0xF49, 'V'),
-    (0xF4D, 'M', 'ཌྷ'),
-    (0xF4E, 'V'),
-    (0xF52, 'M', 'དྷ'),
-    (0xF53, 'V'),
-    (0xF57, 'M', 'བྷ'),
-    (0xF58, 'V'),
-    (0xF5C, 'M', 'ཛྷ'),
-    (0xF5D, 'V'),
-    (0xF69, 'M', 'ཀྵ'),
-    (0xF6A, 'V'),
-    (0xF6D, 'X'),
-    (0xF71, 'V'),
-    (0xF73, 'M', 'ཱི'),
-    (0xF74, 'V'),
-    (0xF75, 'M', 'ཱུ'),
-    (0xF76, 'M', 'ྲྀ'),
-    (0xF77, 'M', 'ྲཱྀ'),
-    (0xF78, 'M', 'ླྀ'),
-    (0xF79, 'M', 'ླཱྀ'),
-    (0xF7A, 'V'),
-    (0xF81, 'M', 'ཱྀ'),
-    (0xF82, 'V'),
-    (0xF93, 'M', 'ྒྷ'),
-    (0xF94, 'V'),
-    (0xF98, 'X'),
-    (0xF99, 'V'),
-    (0xF9D, 'M', 'ྜྷ'),
-    (0xF9E, 'V'),
-    (0xFA2, 'M', 'ྡྷ'),
-    (0xFA3, 'V'),
-    (0xFA7, 'M', 'ྦྷ'),
-    (0xFA8, 'V'),
-    (0xFAC, 'M', 'ྫྷ'),
-    (0xFAD, 'V'),
-    (0xFB9, 'M', 'ྐྵ'),
-    (0xFBA, 'V'),
-    (0xFBD, 'X'),
-    (0xFBE, 'V'),
-    (0xFCD, 'X'),
-    (0xFCE, 'V'),
-    (0xFDB, 'X'),
-    (0x1000, 'V'),
-    (0x10A0, 'X'),
-    (0x10C7, 'M', 'ⴧ'),
-    (0x10C8, 'X'),
-    (0x10CD, 'M', 'ⴭ'),
-    (0x10CE, 'X'),
-    (0x10D0, 'V'),
-    (0x10FC, 'M', 'ნ'),
-    (0x10FD, 'V'),
-    (0x115F, 'X'),
-    (0x1161, 'V'),
-    (0x1249, 'X'),
-    (0x124A, 'V'),
-    (0x124E, 'X'),
-    (0x1250, 'V'),
-    (0x1257, 'X'),
-    (0x1258, 'V'),
-    (0x1259, 'X'),
-    (0x125A, 'V'),
-    (0x125E, 'X'),
-    (0x1260, 'V'),
-    (0x1289, 'X'),
-    (0x128A, 'V'),
-    (0x128E, 'X'),
-    (0x1290, 'V'),
-    (0x12B1, 'X'),
-    (0x12B2, 'V'),
-    (0x12B6, 'X'),
-    (0x12B8, 'V'),
-    (0x12BF, 'X'),
-    (0x12C0, 'V'),
-    (0x12C1, 'X'),
-    (0x12C2, 'V'),
-    (0x12C6, 'X'),
-    (0x12C8, 'V'),
-    (0x12D7, 'X'),
-    (0x12D8, 'V'),
-    (0x1311, 'X'),
-    (0x1312, 'V'),
-    ]
-
-def _seg_14() -> List[Union[Tuple[int, str], Tuple[int, str, str]]]:
-    return [
-    (0x1316, 'X'),
-    (0x1318, 'V'),
-    (0x135B, 'X'),
-    (0x135D, 'V'),
-    (0x137D, 'X'),
-    (0x1380, 'V'),
-    (0x139A, 'X'),
-    (0x13A0, 'V'),
-    (0x13F6, 'X'),
-    (0x13F8, 'M', 'Ᏸ'),
-    (0x13F9, 'M', 'Ᏹ'),
-    (0x13FA, 'M', 'Ᏺ'),
-    (0x13FB, 'M', 'Ᏻ'),
-    (0x13FC, 'M', 'Ᏼ'),
-    (0x13FD, 'M', 'Ᏽ'),
-    (0x13FE, 'X'),
-    (0x1400, 'V'),
-    (0x1680, 'X'),
-    (0x1681, 'V'),
-    (0x169D, 'X'),
-    (0x16A0, 'V'),
-    (0x16F9, 'X'),
-    (0x1700, 'V'),
-    (0x1716, 'X'),
-    (0x171F, 'V'),
-    (0x1737, 'X'),
-    (0x1740, 'V'),
-    (0x1754, 'X'),
-    (0x1760, 'V'),
-    (0x176D, 'X'),
-    (0x176E, 'V'),
-    (0x1771, 'X'),
-    (0x1772, 'V'),
-    (0x1774, 'X'),
-    (0x1780, 'V'),
-    (0x17B4, 'X'),
-    (0x17B6, 'V'),
-    (0x17DE, 'X'),
-    (0x17E0, 'V'),
-    (0x17EA, 'X'),
-    (0x17F0, 'V'),
-    (0x17FA, 'X'),
-    (0x1800, 'V'),
-    (0x1806, 'X'),
-    (0x1807, 'V'),
-    (0x180B, 'I'),
-    (0x180E, 'X'),
-    (0x180F, 'I'),
-    (0x1810, 'V'),
-    (0x181A, 'X'),
-    (0x1820, 'V'),
-    (0x1879, 'X'),
-    (0x1880, 'V'),
-    (0x18AB, 'X'),
-    (0x18B0, 'V'),
-    (0x18F6, 'X'),
-    (0x1900, 'V'),
-    (0x191F, 'X'),
-    (0x1920, 'V'),
-    (0x192C, 'X'),
-    (0x1930, 'V'),
-    (0x193C, 'X'),
-    (0x1940, 'V'),
-    (0x1941, 'X'),
-    (0x1944, 'V'),
-    (0x196E, 'X'),
-    (0x1970, 'V'),
-    (0x1975, 'X'),
-    (0x1980, 'V'),
-    (0x19AC, 'X'),
-    (0x19B0, 'V'),
-    (0x19CA, 'X'),
-    (0x19D0, 'V'),
-    (0x19DB, 'X'),
-    (0x19DE, 'V'),
-    (0x1A1C, 'X'),
-    (0x1A1E, 'V'),
-    (0x1A5F, 'X'),
-    (0x1A60, 'V'),
-    (0x1A7D, 'X'),
-    (0x1A7F, 'V'),
-    (0x1A8A, 'X'),
-    (0x1A90, 'V'),
-    (0x1A9A, 'X'),
-    (0x1AA0, 'V'),
-    (0x1AAE, 'X'),
-    (0x1AB0, 'V'),
-    (0x1ACF, 'X'),
-    (0x1B00, 'V'),
-    (0x1B4D, 'X'),
-    (0x1B50, 'V'),
-    (0x1B7F, 'X'),
-    (0x1B80, 'V'),
-    (0x1BF4, 'X'),
-    (0x1BFC, 'V'),
-    (0x1C38, 'X'),
-    (0x1C3B, 'V'),
-    (0x1C4A, 'X'),
-    (0x1C4D, 'V'),
-    (0x1C80, 'M', 'в'),
-    ]
-
-def _seg_15() -> List[Union[Tuple[int, str], Tuple[int, str, str]]]:
-    return [
-    (0x1C81, 'M', 'д'),
-    (0x1C82, 'M', 'о'),
-    (0x1C83, 'M', 'с'),
-    (0x1C84, 'M', 'т'),
-    (0x1C86, 'M', 'ъ'),
-    (0x1C87, 'M', 'ѣ'),
-    (0x1C88, 'M', 'ꙋ'),
-    (0x1C89, 'X'),
-    (0x1C90, 'M', 'ა'),
-    (0x1C91, 'M', 'ბ'),
-    (0x1C92, 'M', 'გ'),
-    (0x1C93, 'M', 'დ'),
-    (0x1C94, 'M', 'ე'),
-    (0x1C95, 'M', 'ვ'),
-    (0x1C96, 'M', 'ზ'),
-    (0x1C97, 'M', 'თ'),
-    (0x1C98, 'M', 'ი'),
-    (0x1C99, 'M', 'კ'),
-    (0x1C9A, 'M', 'ლ'),
-    (0x1C9B, 'M', 'მ'),
-    (0x1C9C, 'M', 'ნ'),
-    (0x1C9D, 'M', 'ო'),
-    (0x1C9E, 'M', 'პ'),
-    (0x1C9F, 'M', 'ჟ'),
-    (0x1CA0, 'M', 'რ'),
-    (0x1CA1, 'M', 'ს'),
-    (0x1CA2, 'M', 'ტ'),
-    (0x1CA3, 'M', 'უ'),
-    (0x1CA4, 'M', 'ფ'),
-    (0x1CA5, 'M', 'ქ'),
-    (0x1CA6, 'M', 'ღ'),
-    (0x1CA7, 'M', 'ყ'),
-    (0x1CA8, 'M', 'შ'),
-    (0x1CA9, 'M', 'ჩ'),
-    (0x1CAA, 'M', 'ც'),
-    (0x1CAB, 'M', 'ძ'),
-    (0x1CAC, 'M', 'წ'),
-    (0x1CAD, 'M', 'ჭ'),
-    (0x1CAE, 'M', 'ხ'),
-    (0x1CAF, 'M', 'ჯ'),
-    (0x1CB0, 'M', 'ჰ'),
-    (0x1CB1, 'M', 'ჱ'),
-    (0x1CB2, 'M', 'ჲ'),
-    (0x1CB3, 'M', 'ჳ'),
-    (0x1CB4, 'M', 'ჴ'),
-    (0x1CB5, 'M', 'ჵ'),
-    (0x1CB6, 'M', 'ჶ'),
-    (0x1CB7, 'M', 'ჷ'),
-    (0x1CB8, 'M', 'ჸ'),
-    (0x1CB9, 'M', 'ჹ'),
-    (0x1CBA, 'M', 'ჺ'),
-    (0x1CBB, 'X'),
-    (0x1CBD, 'M', 'ჽ'),
-    (0x1CBE, 'M', 'ჾ'),
-    (0x1CBF, 'M', 'ჿ'),
-    (0x1CC0, 'V'),
-    (0x1CC8, 'X'),
-    (0x1CD0, 'V'),
-    (0x1CFB, 'X'),
-    (0x1D00, 'V'),
-    (0x1D2C, 'M', 'a'),
-    (0x1D2D, 'M', 'æ'),
-    (0x1D2E, 'M', 'b'),
-    (0x1D2F, 'V'),
-    (0x1D30, 'M', 'd'),
-    (0x1D31, 'M', 'e'),
-    (0x1D32, 'M', 'ǝ'),
-    (0x1D33, 'M', 'g'),
-    (0x1D34, 'M', 'h'),
-    (0x1D35, 'M', 'i'),
-    (0x1D36, 'M', 'j'),
-    (0x1D37, 'M', 'k'),
-    (0x1D38, 'M', 'l'),
-    (0x1D39, 'M', 'm'),
-    (0x1D3A, 'M', 'n'),
-    (0x1D3B, 'V'),
-    (0x1D3C, 'M', 'o'),
-    (0x1D3D, 'M', 'ȣ'),
-    (0x1D3E, 'M', 'p'),
-    (0x1D3F, 'M', 'r'),
-    (0x1D40, 'M', 't'),
-    (0x1D41, 'M', 'u'),
-    (0x1D42, 'M', 'w'),
-    (0x1D43, 'M', 'a'),
-    (0x1D44, 'M', 'ɐ'),
-    (0x1D45, 'M', 'ɑ'),
-    (0x1D46, 'M', 'ᴂ'),
-    (0x1D47, 'M', 'b'),
-    (0x1D48, 'M', 'd'),
-    (0x1D49, 'M', 'e'),
-    (0x1D4A, 'M', 'ə'),
-    (0x1D4B, 'M', 'ɛ'),
-    (0x1D4C, 'M', 'ɜ'),
-    (0x1D4D, 'M', 'g'),
-    (0x1D4E, 'V'),
-    (0x1D4F, 'M', 'k'),
-    (0x1D50, 'M', 'm'),
-    (0x1D51, 'M', 'ŋ'),
-    (0x1D52, 'M', 'o'),
-    (0x1D53, 'M', 'ɔ'),
-    ]
-
-def _seg_16() -> List[Union[Tuple[int, str], Tuple[int, str, str]]]:
-    return [
-    (0x1D54, 'M', 'ᴖ'),
-    (0x1D55, 'M', 'ᴗ'),
-    (0x1D56, 'M', 'p'),
-    (0x1D57, 'M', 't'),
-    (0x1D58, 'M', 'u'),
-    (0x1D59, 'M', 'ᴝ'),
-    (0x1D5A, 'M', 'ɯ'),
-    (0x1D5B, 'M', 'v'),
-    (0x1D5C, 'M', 'ᴥ'),
-    (0x1D5D, 'M', 'β'),
-    (0x1D5E, 'M', 'γ'),
-    (0x1D5F, 'M', 'δ'),
-    (0x1D60, 'M', 'φ'),
-    (0x1D61, 'M', 'χ'),
-    (0x1D62, 'M', 'i'),
-    (0x1D63, 'M', 'r'),
-    (0x1D64, 'M', 'u'),
-    (0x1D65, 'M', 'v'),
-    (0x1D66, 'M', 'β'),
-    (0x1D67, 'M', 'γ'),
-    (0x1D68, 'M', 'ρ'),
-    (0x1D69, 'M', 'φ'),
-    (0x1D6A, 'M', 'χ'),
-    (0x1D6B, 'V'),
-    (0x1D78, 'M', 'н'),
-    (0x1D79, 'V'),
-    (0x1D9B, 'M', 'ɒ'),
-    (0x1D9C, 'M', 'c'),
-    (0x1D9D, 'M', 'ɕ'),
-    (0x1D9E, 'M', 'ð'),
-    (0x1D9F, 'M', 'ɜ'),
-    (0x1DA0, 'M', 'f'),
-    (0x1DA1, 'M', 'ɟ'),
-    (0x1DA2, 'M', 'ɡ'),
-    (0x1DA3, 'M', 'ɥ'),
-    (0x1DA4, 'M', 'ɨ'),
-    (0x1DA5, 'M', 'ɩ'),
-    (0x1DA6, 'M', 'ɪ'),
-    (0x1DA7, 'M', 'ᵻ'),
-    (0x1DA8, 'M', 'ʝ'),
-    (0x1DA9, 'M', 'ɭ'),
-    (0x1DAA, 'M', 'ᶅ'),
-    (0x1DAB, 'M', 'ʟ'),
-    (0x1DAC, 'M', 'ɱ'),
-    (0x1DAD, 'M', 'ɰ'),
-    (0x1DAE, 'M', 'ɲ'),
-    (0x1DAF, 'M', 'ɳ'),
-    (0x1DB0, 'M', 'ɴ'),
-    (0x1DB1, 'M', 'ɵ'),
-    (0x1DB2, 'M', 'ɸ'),
-    (0x1DB3, 'M', 'ʂ'),
-    (0x1DB4, 'M', 'ʃ'),
-    (0x1DB5, 'M', 'ƫ'),
-    (0x1DB6, 'M', 'ʉ'),
-    (0x1DB7, 'M', 'ʊ'),
-    (0x1DB8, 'M', 'ᴜ'),
-    (0x1DB9, 'M', 'ʋ'),
-    (0x1DBA, 'M', 'ʌ'),
-    (0x1DBB, 'M', 'z'),
-    (0x1DBC, 'M', 'ʐ'),
-    (0x1DBD, 'M', 'ʑ'),
-    (0x1DBE, 'M', 'ʒ'),
-    (0x1DBF, 'M', 'θ'),
-    (0x1DC0, 'V'),
-    (0x1E00, 'M', 'ḁ'),
-    (0x1E01, 'V'),
-    (0x1E02, 'M', 'ḃ'),
-    (0x1E03, 'V'),
-    (0x1E04, 'M', 'ḅ'),
-    (0x1E05, 'V'),
-    (0x1E06, 'M', 'ḇ'),
-    (0x1E07, 'V'),
-    (0x1E08, 'M', 'ḉ'),
-    (0x1E09, 'V'),
-    (0x1E0A, 'M', 'ḋ'),
-    (0x1E0B, 'V'),
-    (0x1E0C, 'M', 'ḍ'),
-    (0x1E0D, 'V'),
-    (0x1E0E, 'M', 'ḏ'),
-    (0x1E0F, 'V'),
-    (0x1E10, 'M', 'ḑ'),
-    (0x1E11, 'V'),
-    (0x1E12, 'M', 'ḓ'),
-    (0x1E13, 'V'),
-    (0x1E14, 'M', 'ḕ'),
-    (0x1E15, 'V'),
-    (0x1E16, 'M', 'ḗ'),
-    (0x1E17, 'V'),
-    (0x1E18, 'M', 'ḙ'),
-    (0x1E19, 'V'),
-    (0x1E1A, 'M', 'ḛ'),
-    (0x1E1B, 'V'),
-    (0x1E1C, 'M', 'ḝ'),
-    (0x1E1D, 'V'),
-    (0x1E1E, 'M', 'ḟ'),
-    (0x1E1F, 'V'),
-    (0x1E20, 'M', 'ḡ'),
-    (0x1E21, 'V'),
-    (0x1E22, 'M', 'ḣ'),
-    (0x1E23, 'V'),
-    ]
-
-def _seg_17() -> List[Union[Tuple[int, str], Tuple[int, str, str]]]:
-    return [
-    (0x1E24, 'M', 'ḥ'),
-    (0x1E25, 'V'),
-    (0x1E26, 'M', 'ḧ'),
-    (0x1E27, 'V'),
-    (0x1E28, 'M', 'ḩ'),
-    (0x1E29, 'V'),
-    (0x1E2A, 'M', 'ḫ'),
-    (0x1E2B, 'V'),
-    (0x1E2C, 'M', 'ḭ'),
-    (0x1E2D, 'V'),
-    (0x1E2E, 'M', 'ḯ'),
-    (0x1E2F, 'V'),
-    (0x1E30, 'M', 'ḱ'),
-    (0x1E31, 'V'),
-    (0x1E32, 'M', 'ḳ'),
-    (0x1E33, 'V'),
-    (0x1E34, 'M', 'ḵ'),
-    (0x1E35, 'V'),
-    (0x1E36, 'M', 'ḷ'),
-    (0x1E37, 'V'),
-    (0x1E38, 'M', 'ḹ'),
-    (0x1E39, 'V'),
-    (0x1E3A, 'M', 'ḻ'),
-    (0x1E3B, 'V'),
-    (0x1E3C, 'M', 'ḽ'),
-    (0x1E3D, 'V'),
-    (0x1E3E, 'M', 'ḿ'),
-    (0x1E3F, 'V'),
-    (0x1E40, 'M', 'ṁ'),
-    (0x1E41, 'V'),
-    (0x1E42, 'M', 'ṃ'),
-    (0x1E43, 'V'),
-    (0x1E44, 'M', 'ṅ'),
-    (0x1E45, 'V'),
-    (0x1E46, 'M', 'ṇ'),
-    (0x1E47, 'V'),
-    (0x1E48, 'M', 'ṉ'),
-    (0x1E49, 'V'),
-    (0x1E4A, 'M', 'ṋ'),
-    (0x1E4B, 'V'),
-    (0x1E4C, 'M', 'ṍ'),
-    (0x1E4D, 'V'),
-    (0x1E4E, 'M', 'ṏ'),
-    (0x1E4F, 'V'),
-    (0x1E50, 'M', 'ṑ'),
-    (0x1E51, 'V'),
-    (0x1E52, 'M', 'ṓ'),
-    (0x1E53, 'V'),
-    (0x1E54, 'M', 'ṕ'),
-    (0x1E55, 'V'),
-    (0x1E56, 'M', 'ṗ'),
-    (0x1E57, 'V'),
-    (0x1E58, 'M', 'ṙ'),
-    (0x1E59, 'V'),
-    (0x1E5A, 'M', 'ṛ'),
-    (0x1E5B, 'V'),
-    (0x1E5C, 'M', 'ṝ'),
-    (0x1E5D, 'V'),
-    (0x1E5E, 'M', 'ṟ'),
-    (0x1E5F, 'V'),
-    (0x1E60, 'M', 'ṡ'),
-    (0x1E61, 'V'),
-    (0x1E62, 'M', 'ṣ'),
-    (0x1E63, 'V'),
-    (0x1E64, 'M', 'ṥ'),
-    (0x1E65, 'V'),
-    (0x1E66, 'M', 'ṧ'),
-    (0x1E67, 'V'),
-    (0x1E68, 'M', 'ṩ'),
-    (0x1E69, 'V'),
-    (0x1E6A, 'M', 'ṫ'),
-    (0x1E6B, 'V'),
-    (0x1E6C, 'M', 'ṭ'),
-    (0x1E6D, 'V'),
-    (0x1E6E, 'M', 'ṯ'),
-    (0x1E6F, 'V'),
-    (0x1E70, 'M', 'ṱ'),
-    (0x1E71, 'V'),
-    (0x1E72, 'M', 'ṳ'),
-    (0x1E73, 'V'),
-    (0x1E74, 'M', 'ṵ'),
-    (0x1E75, 'V'),
-    (0x1E76, 'M', 'ṷ'),
-    (0x1E77, 'V'),
-    (0x1E78, 'M', 'ṹ'),
-    (0x1E79, 'V'),
-    (0x1E7A, 'M', 'ṻ'),
-    (0x1E7B, 'V'),
-    (0x1E7C, 'M', 'ṽ'),
-    (0x1E7D, 'V'),
-    (0x1E7E, 'M', 'ṿ'),
-    (0x1E7F, 'V'),
-    (0x1E80, 'M', 'ẁ'),
-    (0x1E81, 'V'),
-    (0x1E82, 'M', 'ẃ'),
-    (0x1E83, 'V'),
-    (0x1E84, 'M', 'ẅ'),
-    (0x1E85, 'V'),
-    (0x1E86, 'M', 'ẇ'),
-    (0x1E87, 'V'),
-    ]
-
-def _seg_18() -> List[Union[Tuple[int, str], Tuple[int, str, str]]]:
-    return [
-    (0x1E88, 'M', 'ẉ'),
-    (0x1E89, 'V'),
-    (0x1E8A, 'M', 'ẋ'),
-    (0x1E8B, 'V'),
-    (0x1E8C, 'M', 'ẍ'),
-    (0x1E8D, 'V'),
-    (0x1E8E, 'M', 'ẏ'),
-    (0x1E8F, 'V'),
-    (0x1E90, 'M', 'ẑ'),
-    (0x1E91, 'V'),
-    (0x1E92, 'M', 'ẓ'),
-    (0x1E93, 'V'),
-    (0x1E94, 'M', 'ẕ'),
-    (0x1E95, 'V'),
-    (0x1E9A, 'M', 'aʾ'),
-    (0x1E9B, 'M', 'ṡ'),
-    (0x1E9C, 'V'),
-    (0x1E9E, 'M', 'ss'),
-    (0x1E9F, 'V'),
-    (0x1EA0, 'M', 'ạ'),
-    (0x1EA1, 'V'),
-    (0x1EA2, 'M', 'ả'),
-    (0x1EA3, 'V'),
-    (0x1EA4, 'M', 'ấ'),
-    (0x1EA5, 'V'),
-    (0x1EA6, 'M', 'ầ'),
-    (0x1EA7, 'V'),
-    (0x1EA8, 'M', 'ẩ'),
-    (0x1EA9, 'V'),
-    (0x1EAA, 'M', 'ẫ'),
-    (0x1EAB, 'V'),
-    (0x1EAC, 'M', 'ậ'),
-    (0x1EAD, 'V'),
-    (0x1EAE, 'M', 'ắ'),
-    (0x1EAF, 'V'),
-    (0x1EB0, 'M', 'ằ'),
-    (0x1EB1, 'V'),
-    (0x1EB2, 'M', 'ẳ'),
-    (0x1EB3, 'V'),
-    (0x1EB4, 'M', 'ẵ'),
-    (0x1EB5, 'V'),
-    (0x1EB6, 'M', 'ặ'),
-    (0x1EB7, 'V'),
-    (0x1EB8, 'M', 'ẹ'),
-    (0x1EB9, 'V'),
-    (0x1EBA, 'M', 'ẻ'),
-    (0x1EBB, 'V'),
-    (0x1EBC, 'M', 'ẽ'),
-    (0x1EBD, 'V'),
-    (0x1EBE, 'M', 'ế'),
-    (0x1EBF, 'V'),
-    (0x1EC0, 'M', 'ề'),
-    (0x1EC1, 'V'),
-    (0x1EC2, 'M', 'ể'),
-    (0x1EC3, 'V'),
-    (0x1EC4, 'M', 'ễ'),
-    (0x1EC5, 'V'),
-    (0x1EC6, 'M', 'ệ'),
-    (0x1EC7, 'V'),
-    (0x1EC8, 'M', 'ỉ'),
-    (0x1EC9, 'V'),
-    (0x1ECA, 'M', 'ị'),
-    (0x1ECB, 'V'),
-    (0x1ECC, 'M', 'ọ'),
-    (0x1ECD, 'V'),
-    (0x1ECE, 'M', 'ỏ'),
-    (0x1ECF, 'V'),
-    (0x1ED0, 'M', 'ố'),
-    (0x1ED1, 'V'),
-    (0x1ED2, 'M', 'ồ'),
-    (0x1ED3, 'V'),
-    (0x1ED4, 'M', 'ổ'),
-    (0x1ED5, 'V'),
-    (0x1ED6, 'M', 'ỗ'),
-    (0x1ED7, 'V'),
-    (0x1ED8, 'M', 'ộ'),
-    (0x1ED9, 'V'),
-    (0x1EDA, 'M', 'ớ'),
-    (0x1EDB, 'V'),
-    (0x1EDC, 'M', 'ờ'),
-    (0x1EDD, 'V'),
-    (0x1EDE, 'M', 'ở'),
-    (0x1EDF, 'V'),
-    (0x1EE0, 'M', 'ỡ'),
-    (0x1EE1, 'V'),
-    (0x1EE2, 'M', 'ợ'),
-    (0x1EE3, 'V'),
-    (0x1EE4, 'M', 'ụ'),
-    (0x1EE5, 'V'),
-    (0x1EE6, 'M', 'ủ'),
-    (0x1EE7, 'V'),
-    (0x1EE8, 'M', 'ứ'),
-    (0x1EE9, 'V'),
-    (0x1EEA, 'M', 'ừ'),
-    (0x1EEB, 'V'),
-    (0x1EEC, 'M', 'ử'),
-    (0x1EED, 'V'),
-    (0x1EEE, 'M', 'ữ'),
-    (0x1EEF, 'V'),
-    (0x1EF0, 'M', 'ự'),
-    ]
-
-def _seg_19() -> List[Union[Tuple[int, str], Tuple[int, str, str]]]:
-    return [
-    (0x1EF1, 'V'),
-    (0x1EF2, 'M', 'ỳ'),
-    (0x1EF3, 'V'),
-    (0x1EF4, 'M', 'ỵ'),
-    (0x1EF5, 'V'),
-    (0x1EF6, 'M', 'ỷ'),
-    (0x1EF7, 'V'),
-    (0x1EF8, 'M', 'ỹ'),
-    (0x1EF9, 'V'),
-    (0x1EFA, 'M', 'ỻ'),
-    (0x1EFB, 'V'),
-    (0x1EFC, 'M', 'ỽ'),
-    (0x1EFD, 'V'),
-    (0x1EFE, 'M', 'ỿ'),
-    (0x1EFF, 'V'),
-    (0x1F08, 'M', 'ἀ'),
-    (0x1F09, 'M', 'ἁ'),
-    (0x1F0A, 'M', 'ἂ'),
-    (0x1F0B, 'M', 'ἃ'),
-    (0x1F0C, 'M', 'ἄ'),
-    (0x1F0D, 'M', 'ἅ'),
-    (0x1F0E, 'M', 'ἆ'),
-    (0x1F0F, 'M', 'ἇ'),
-    (0x1F10, 'V'),
-    (0x1F16, 'X'),
-    (0x1F18, 'M', 'ἐ'),
-    (0x1F19, 'M', 'ἑ'),
-    (0x1F1A, 'M', 'ἒ'),
-    (0x1F1B, 'M', 'ἓ'),
-    (0x1F1C, 'M', 'ἔ'),
-    (0x1F1D, 'M', 'ἕ'),
-    (0x1F1E, 'X'),
-    (0x1F20, 'V'),
-    (0x1F28, 'M', 'ἠ'),
-    (0x1F29, 'M', 'ἡ'),
-    (0x1F2A, 'M', 'ἢ'),
-    (0x1F2B, 'M', 'ἣ'),
-    (0x1F2C, 'M', 'ἤ'),
-    (0x1F2D, 'M', 'ἥ'),
-    (0x1F2E, 'M', 'ἦ'),
-    (0x1F2F, 'M', 'ἧ'),
-    (0x1F30, 'V'),
-    (0x1F38, 'M', 'ἰ'),
-    (0x1F39, 'M', 'ἱ'),
-    (0x1F3A, 'M', 'ἲ'),
-    (0x1F3B, 'M', 'ἳ'),
-    (0x1F3C, 'M', 'ἴ'),
-    (0x1F3D, 'M', 'ἵ'),
-    (0x1F3E, 'M', 'ἶ'),
-    (0x1F3F, 'M', 'ἷ'),
-    (0x1F40, 'V'),
-    (0x1F46, 'X'),
-    (0x1F48, 'M', 'ὀ'),
-    (0x1F49, 'M', 'ὁ'),
-    (0x1F4A, 'M', 'ὂ'),
-    (0x1F4B, 'M', 'ὃ'),
-    (0x1F4C, 'M', 'ὄ'),
-    (0x1F4D, 'M', 'ὅ'),
-    (0x1F4E, 'X'),
-    (0x1F50, 'V'),
-    (0x1F58, 'X'),
-    (0x1F59, 'M', 'ὑ'),
-    (0x1F5A, 'X'),
-    (0x1F5B, 'M', 'ὓ'),
-    (0x1F5C, 'X'),
-    (0x1F5D, 'M', 'ὕ'),
-    (0x1F5E, 'X'),
-    (0x1F5F, 'M', 'ὗ'),
-    (0x1F60, 'V'),
-    (0x1F68, 'M', 'ὠ'),
-    (0x1F69, 'M', 'ὡ'),
-    (0x1F6A, 'M', 'ὢ'),
-    (0x1F6B, 'M', 'ὣ'),
-    (0x1F6C, 'M', 'ὤ'),
-    (0x1F6D, 'M', 'ὥ'),
-    (0x1F6E, 'M', 'ὦ'),
-    (0x1F6F, 'M', 'ὧ'),
-    (0x1F70, 'V'),
-    (0x1F71, 'M', 'ά'),
-    (0x1F72, 'V'),
-    (0x1F73, 'M', 'έ'),
-    (0x1F74, 'V'),
-    (0x1F75, 'M', 'ή'),
-    (0x1F76, 'V'),
-    (0x1F77, 'M', 'ί'),
-    (0x1F78, 'V'),
-    (0x1F79, 'M', 'ό'),
-    (0x1F7A, 'V'),
-    (0x1F7B, 'M', 'ύ'),
-    (0x1F7C, 'V'),
-    (0x1F7D, 'M', 'ώ'),
-    (0x1F7E, 'X'),
-    (0x1F80, 'M', 'ἀι'),
-    (0x1F81, 'M', 'ἁι'),
-    (0x1F82, 'M', 'ἂι'),
-    (0x1F83, 'M', 'ἃι'),
-    (0x1F84, 'M', 'ἄι'),
-    (0x1F85, 'M', 'ἅι'),
-    (0x1F86, 'M', 'ἆι'),
-    (0x1F87, 'M', 'ἇι'),
-    ]
-
-def _seg_20() -> List[Union[Tuple[int, str], Tuple[int, str, str]]]:
-    return [
-    (0x1F88, 'M', 'ἀι'),
-    (0x1F89, 'M', 'ἁι'),
-    (0x1F8A, 'M', 'ἂι'),
-    (0x1F8B, 'M', 'ἃι'),
-    (0x1F8C, 'M', 'ἄι'),
-    (0x1F8D, 'M', 'ἅι'),
-    (0x1F8E, 'M', 'ἆι'),
-    (0x1F8F, 'M', 'ἇι'),
-    (0x1F90, 'M', 'ἠι'),
-    (0x1F91, 'M', 'ἡι'),
-    (0x1F92, 'M', 'ἢι'),
-    (0x1F93, 'M', 'ἣι'),
-    (0x1F94, 'M', 'ἤι'),
-    (0x1F95, 'M', 'ἥι'),
-    (0x1F96, 'M', 'ἦι'),
-    (0x1F97, 'M', 'ἧι'),
-    (0x1F98, 'M', 'ἠι'),
-    (0x1F99, 'M', 'ἡι'),
-    (0x1F9A, 'M', 'ἢι'),
-    (0x1F9B, 'M', 'ἣι'),
-    (0x1F9C, 'M', 'ἤι'),
-    (0x1F9D, 'M', 'ἥι'),
-    (0x1F9E, 'M', 'ἦι'),
-    (0x1F9F, 'M', 'ἧι'),
-    (0x1FA0, 'M', 'ὠι'),
-    (0x1FA1, 'M', 'ὡι'),
-    (0x1FA2, 'M', 'ὢι'),
-    (0x1FA3, 'M', 'ὣι'),
-    (0x1FA4, 'M', 'ὤι'),
-    (0x1FA5, 'M', 'ὥι'),
-    (0x1FA6, 'M', 'ὦι'),
-    (0x1FA7, 'M', 'ὧι'),
-    (0x1FA8, 'M', 'ὠι'),
-    (0x1FA9, 'M', 'ὡι'),
-    (0x1FAA, 'M', 'ὢι'),
-    (0x1FAB, 'M', 'ὣι'),
-    (0x1FAC, 'M', 'ὤι'),
-    (0x1FAD, 'M', 'ὥι'),
-    (0x1FAE, 'M', 'ὦι'),
-    (0x1FAF, 'M', 'ὧι'),
-    (0x1FB0, 'V'),
-    (0x1FB2, 'M', 'ὰι'),
-    (0x1FB3, 'M', 'αι'),
-    (0x1FB4, 'M', 'άι'),
-    (0x1FB5, 'X'),
-    (0x1FB6, 'V'),
-    (0x1FB7, 'M', 'ᾶι'),
-    (0x1FB8, 'M', 'ᾰ'),
-    (0x1FB9, 'M', 'ᾱ'),
-    (0x1FBA, 'M', 'ὰ'),
-    (0x1FBB, 'M', 'ά'),
-    (0x1FBC, 'M', 'αι'),
-    (0x1FBD, '3', ' ̓'),
-    (0x1FBE, 'M', 'ι'),
-    (0x1FBF, '3', ' ̓'),
-    (0x1FC0, '3', ' ͂'),
-    (0x1FC1, '3', ' ̈͂'),
-    (0x1FC2, 'M', 'ὴι'),
-    (0x1FC3, 'M', 'ηι'),
-    (0x1FC4, 'M', 'ήι'),
-    (0x1FC5, 'X'),
-    (0x1FC6, 'V'),
-    (0x1FC7, 'M', 'ῆι'),
-    (0x1FC8, 'M', 'ὲ'),
-    (0x1FC9, 'M', 'έ'),
-    (0x1FCA, 'M', 'ὴ'),
-    (0x1FCB, 'M', 'ή'),
-    (0x1FCC, 'M', 'ηι'),
-    (0x1FCD, '3', ' ̓̀'),
-    (0x1FCE, '3', ' ̓́'),
-    (0x1FCF, '3', ' ̓͂'),
-    (0x1FD0, 'V'),
-    (0x1FD3, 'M', 'ΐ'),
-    (0x1FD4, 'X'),
-    (0x1FD6, 'V'),
-    (0x1FD8, 'M', 'ῐ'),
-    (0x1FD9, 'M', 'ῑ'),
-    (0x1FDA, 'M', 'ὶ'),
-    (0x1FDB, 'M', 'ί'),
-    (0x1FDC, 'X'),
-    (0x1FDD, '3', ' ̔̀'),
-    (0x1FDE, '3', ' ̔́'),
-    (0x1FDF, '3', ' ̔͂'),
-    (0x1FE0, 'V'),
-    (0x1FE3, 'M', 'ΰ'),
-    (0x1FE4, 'V'),
-    (0x1FE8, 'M', 'ῠ'),
-    (0x1FE9, 'M', 'ῡ'),
-    (0x1FEA, 'M', 'ὺ'),
-    (0x1FEB, 'M', 'ύ'),
-    (0x1FEC, 'M', 'ῥ'),
-    (0x1FED, '3', ' ̈̀'),
-    (0x1FEE, '3', ' ̈́'),
-    (0x1FEF, '3', '`'),
-    (0x1FF0, 'X'),
-    (0x1FF2, 'M', 'ὼι'),
-    (0x1FF3, 'M', 'ωι'),
-    (0x1FF4, 'M', 'ώι'),
-    (0x1FF5, 'X'),
-    (0x1FF6, 'V'),
-    ]
-
-def _seg_21() -> List[Union[Tuple[int, str], Tuple[int, str, str]]]:
-    return [
-    (0x1FF7, 'M', 'ῶι'),
-    (0x1FF8, 'M', 'ὸ'),
-    (0x1FF9, 'M', 'ό'),
-    (0x1FFA, 'M', 'ὼ'),
-    (0x1FFB, 'M', 'ώ'),
-    (0x1FFC, 'M', 'ωι'),
-    (0x1FFD, '3', ' ́'),
-    (0x1FFE, '3', ' ̔'),
-    (0x1FFF, 'X'),
-    (0x2000, '3', ' '),
-    (0x200B, 'I'),
-    (0x200C, 'D', ''),
-    (0x200E, 'X'),
-    (0x2010, 'V'),
-    (0x2011, 'M', '‐'),
-    (0x2012, 'V'),
-    (0x2017, '3', ' ̳'),
-    (0x2018, 'V'),
-    (0x2024, 'X'),
-    (0x2027, 'V'),
-    (0x2028, 'X'),
-    (0x202F, '3', ' '),
-    (0x2030, 'V'),
-    (0x2033, 'M', '′′'),
-    (0x2034, 'M', '′′′'),
-    (0x2035, 'V'),
-    (0x2036, 'M', '‵‵'),
-    (0x2037, 'M', '‵‵‵'),
-    (0x2038, 'V'),
-    (0x203C, '3', '!!'),
-    (0x203D, 'V'),
-    (0x203E, '3', ' ̅'),
-    (0x203F, 'V'),
-    (0x2047, '3', '??'),
-    (0x2048, '3', '?!'),
-    (0x2049, '3', '!?'),
-    (0x204A, 'V'),
-    (0x2057, 'M', '′′′′'),
-    (0x2058, 'V'),
-    (0x205F, '3', ' '),
-    (0x2060, 'I'),
-    (0x2061, 'X'),
-    (0x2064, 'I'),
-    (0x2065, 'X'),
-    (0x2070, 'M', '0'),
-    (0x2071, 'M', 'i'),
-    (0x2072, 'X'),
-    (0x2074, 'M', '4'),
-    (0x2075, 'M', '5'),
-    (0x2076, 'M', '6'),
-    (0x2077, 'M', '7'),
-    (0x2078, 'M', '8'),
-    (0x2079, 'M', '9'),
-    (0x207A, '3', '+'),
-    (0x207B, 'M', '−'),
-    (0x207C, '3', '='),
-    (0x207D, '3', '('),
-    (0x207E, '3', ')'),
-    (0x207F, 'M', 'n'),
-    (0x2080, 'M', '0'),
-    (0x2081, 'M', '1'),
-    (0x2082, 'M', '2'),
-    (0x2083, 'M', '3'),
-    (0x2084, 'M', '4'),
-    (0x2085, 'M', '5'),
-    (0x2086, 'M', '6'),
-    (0x2087, 'M', '7'),
-    (0x2088, 'M', '8'),
-    (0x2089, 'M', '9'),
-    (0x208A, '3', '+'),
-    (0x208B, 'M', '−'),
-    (0x208C, '3', '='),
-    (0x208D, '3', '('),
-    (0x208E, '3', ')'),
-    (0x208F, 'X'),
-    (0x2090, 'M', 'a'),
-    (0x2091, 'M', 'e'),
-    (0x2092, 'M', 'o'),
-    (0x2093, 'M', 'x'),
-    (0x2094, 'M', 'ə'),
-    (0x2095, 'M', 'h'),
-    (0x2096, 'M', 'k'),
-    (0x2097, 'M', 'l'),
-    (0x2098, 'M', 'm'),
-    (0x2099, 'M', 'n'),
-    (0x209A, 'M', 'p'),
-    (0x209B, 'M', 's'),
-    (0x209C, 'M', 't'),
-    (0x209D, 'X'),
-    (0x20A0, 'V'),
-    (0x20A8, 'M', 'rs'),
-    (0x20A9, 'V'),
-    (0x20C1, 'X'),
-    (0x20D0, 'V'),
-    (0x20F1, 'X'),
-    (0x2100, '3', 'a/c'),
-    (0x2101, '3', 'a/s'),
-    (0x2102, 'M', 'c'),
-    (0x2103, 'M', '°c'),
-    (0x2104, 'V'),
-    ]
-
-def _seg_22() -> List[Union[Tuple[int, str], Tuple[int, str, str]]]:
-    return [
-    (0x2105, '3', 'c/o'),
-    (0x2106, '3', 'c/u'),
-    (0x2107, 'M', 'ɛ'),
-    (0x2108, 'V'),
-    (0x2109, 'M', '°f'),
-    (0x210A, 'M', 'g'),
-    (0x210B, 'M', 'h'),
-    (0x210F, 'M', 'ħ'),
-    (0x2110, 'M', 'i'),
-    (0x2112, 'M', 'l'),
-    (0x2114, 'V'),
-    (0x2115, 'M', 'n'),
-    (0x2116, 'M', 'no'),
-    (0x2117, 'V'),
-    (0x2119, 'M', 'p'),
-    (0x211A, 'M', 'q'),
-    (0x211B, 'M', 'r'),
-    (0x211E, 'V'),
-    (0x2120, 'M', 'sm'),
-    (0x2121, 'M', 'tel'),
-    (0x2122, 'M', 'tm'),
-    (0x2123, 'V'),
-    (0x2124, 'M', 'z'),
-    (0x2125, 'V'),
-    (0x2126, 'M', 'ω'),
-    (0x2127, 'V'),
-    (0x2128, 'M', 'z'),
-    (0x2129, 'V'),
-    (0x212A, 'M', 'k'),
-    (0x212B, 'M', 'å'),
-    (0x212C, 'M', 'b'),
-    (0x212D, 'M', 'c'),
-    (0x212E, 'V'),
-    (0x212F, 'M', 'e'),
-    (0x2131, 'M', 'f'),
-    (0x2132, 'X'),
-    (0x2133, 'M', 'm'),
-    (0x2134, 'M', 'o'),
-    (0x2135, 'M', 'א'),
-    (0x2136, 'M', 'ב'),
-    (0x2137, 'M', 'ג'),
-    (0x2138, 'M', 'ד'),
-    (0x2139, 'M', 'i'),
-    (0x213A, 'V'),
-    (0x213B, 'M', 'fax'),
-    (0x213C, 'M', 'π'),
-    (0x213D, 'M', 'γ'),
-    (0x213F, 'M', 'π'),
-    (0x2140, 'M', '∑'),
-    (0x2141, 'V'),
-    (0x2145, 'M', 'd'),
-    (0x2147, 'M', 'e'),
-    (0x2148, 'M', 'i'),
-    (0x2149, 'M', 'j'),
-    (0x214A, 'V'),
-    (0x2150, 'M', '1⁄7'),
-    (0x2151, 'M', '1⁄9'),
-    (0x2152, 'M', '1⁄10'),
-    (0x2153, 'M', '1⁄3'),
-    (0x2154, 'M', '2⁄3'),
-    (0x2155, 'M', '1⁄5'),
-    (0x2156, 'M', '2⁄5'),
-    (0x2157, 'M', '3⁄5'),
-    (0x2158, 'M', '4⁄5'),
-    (0x2159, 'M', '1⁄6'),
-    (0x215A, 'M', '5⁄6'),
-    (0x215B, 'M', '1⁄8'),
-    (0x215C, 'M', '3⁄8'),
-    (0x215D, 'M', '5⁄8'),
-    (0x215E, 'M', '7⁄8'),
-    (0x215F, 'M', '1⁄'),
-    (0x2160, 'M', 'i'),
-    (0x2161, 'M', 'ii'),
-    (0x2162, 'M', 'iii'),
-    (0x2163, 'M', 'iv'),
-    (0x2164, 'M', 'v'),
-    (0x2165, 'M', 'vi'),
-    (0x2166, 'M', 'vii'),
-    (0x2167, 'M', 'viii'),
-    (0x2168, 'M', 'ix'),
-    (0x2169, 'M', 'x'),
-    (0x216A, 'M', 'xi'),
-    (0x216B, 'M', 'xii'),
-    (0x216C, 'M', 'l'),
-    (0x216D, 'M', 'c'),
-    (0x216E, 'M', 'd'),
-    (0x216F, 'M', 'm'),
-    (0x2170, 'M', 'i'),
-    (0x2171, 'M', 'ii'),
-    (0x2172, 'M', 'iii'),
-    (0x2173, 'M', 'iv'),
-    (0x2174, 'M', 'v'),
-    (0x2175, 'M', 'vi'),
-    (0x2176, 'M', 'vii'),
-    (0x2177, 'M', 'viii'),
-    (0x2178, 'M', 'ix'),
-    (0x2179, 'M', 'x'),
-    (0x217A, 'M', 'xi'),
-    (0x217B, 'M', 'xii'),
-    (0x217C, 'M', 'l'),
-    ]
-
-def _seg_23() -> List[Union[Tuple[int, str], Tuple[int, str, str]]]:
-    return [
-    (0x217D, 'M', 'c'),
-    (0x217E, 'M', 'd'),
-    (0x217F, 'M', 'm'),
-    (0x2180, 'V'),
-    (0x2183, 'X'),
-    (0x2184, 'V'),
-    (0x2189, 'M', '0⁄3'),
-    (0x218A, 'V'),
-    (0x218C, 'X'),
-    (0x2190, 'V'),
-    (0x222C, 'M', '∫∫'),
-    (0x222D, 'M', '∫∫∫'),
-    (0x222E, 'V'),
-    (0x222F, 'M', '∮∮'),
-    (0x2230, 'M', '∮∮∮'),
-    (0x2231, 'V'),
-    (0x2260, '3'),
-    (0x2261, 'V'),
-    (0x226E, '3'),
-    (0x2270, 'V'),
-    (0x2329, 'M', '〈'),
-    (0x232A, 'M', '〉'),
-    (0x232B, 'V'),
-    (0x2427, 'X'),
-    (0x2440, 'V'),
-    (0x244B, 'X'),
-    (0x2460, 'M', '1'),
-    (0x2461, 'M', '2'),
-    (0x2462, 'M', '3'),
-    (0x2463, 'M', '4'),
-    (0x2464, 'M', '5'),
-    (0x2465, 'M', '6'),
-    (0x2466, 'M', '7'),
-    (0x2467, 'M', '8'),
-    (0x2468, 'M', '9'),
-    (0x2469, 'M', '10'),
-    (0x246A, 'M', '11'),
-    (0x246B, 'M', '12'),
-    (0x246C, 'M', '13'),
-    (0x246D, 'M', '14'),
-    (0x246E, 'M', '15'),
-    (0x246F, 'M', '16'),
-    (0x2470, 'M', '17'),
-    (0x2471, 'M', '18'),
-    (0x2472, 'M', '19'),
-    (0x2473, 'M', '20'),
-    (0x2474, '3', '(1)'),
-    (0x2475, '3', '(2)'),
-    (0x2476, '3', '(3)'),
-    (0x2477, '3', '(4)'),
-    (0x2478, '3', '(5)'),
-    (0x2479, '3', '(6)'),
-    (0x247A, '3', '(7)'),
-    (0x247B, '3', '(8)'),
-    (0x247C, '3', '(9)'),
-    (0x247D, '3', '(10)'),
-    (0x247E, '3', '(11)'),
-    (0x247F, '3', '(12)'),
-    (0x2480, '3', '(13)'),
-    (0x2481, '3', '(14)'),
-    (0x2482, '3', '(15)'),
-    (0x2483, '3', '(16)'),
-    (0x2484, '3', '(17)'),
-    (0x2485, '3', '(18)'),
-    (0x2486, '3', '(19)'),
-    (0x2487, '3', '(20)'),
-    (0x2488, 'X'),
-    (0x249C, '3', '(a)'),
-    (0x249D, '3', '(b)'),
-    (0x249E, '3', '(c)'),
-    (0x249F, '3', '(d)'),
-    (0x24A0, '3', '(e)'),
-    (0x24A1, '3', '(f)'),
-    (0x24A2, '3', '(g)'),
-    (0x24A3, '3', '(h)'),
-    (0x24A4, '3', '(i)'),
-    (0x24A5, '3', '(j)'),
-    (0x24A6, '3', '(k)'),
-    (0x24A7, '3', '(l)'),
-    (0x24A8, '3', '(m)'),
-    (0x24A9, '3', '(n)'),
-    (0x24AA, '3', '(o)'),
-    (0x24AB, '3', '(p)'),
-    (0x24AC, '3', '(q)'),
-    (0x24AD, '3', '(r)'),
-    (0x24AE, '3', '(s)'),
-    (0x24AF, '3', '(t)'),
-    (0x24B0, '3', '(u)'),
-    (0x24B1, '3', '(v)'),
-    (0x24B2, '3', '(w)'),
-    (0x24B3, '3', '(x)'),
-    (0x24B4, '3', '(y)'),
-    (0x24B5, '3', '(z)'),
-    (0x24B6, 'M', 'a'),
-    (0x24B7, 'M', 'b'),
-    (0x24B8, 'M', 'c'),
-    (0x24B9, 'M', 'd'),
-    (0x24BA, 'M', 'e'),
-    (0x24BB, 'M', 'f'),
-    (0x24BC, 'M', 'g'),
-    ]
-
-def _seg_24() -> List[Union[Tuple[int, str], Tuple[int, str, str]]]:
-    return [
-    (0x24BD, 'M', 'h'),
-    (0x24BE, 'M', 'i'),
-    (0x24BF, 'M', 'j'),
-    (0x24C0, 'M', 'k'),
-    (0x24C1, 'M', 'l'),
-    (0x24C2, 'M', 'm'),
-    (0x24C3, 'M', 'n'),
-    (0x24C4, 'M', 'o'),
-    (0x24C5, 'M', 'p'),
-    (0x24C6, 'M', 'q'),
-    (0x24C7, 'M', 'r'),
-    (0x24C8, 'M', 's'),
-    (0x24C9, 'M', 't'),
-    (0x24CA, 'M', 'u'),
-    (0x24CB, 'M', 'v'),
-    (0x24CC, 'M', 'w'),
-    (0x24CD, 'M', 'x'),
-    (0x24CE, 'M', 'y'),
-    (0x24CF, 'M', 'z'),
-    (0x24D0, 'M', 'a'),
-    (0x24D1, 'M', 'b'),
-    (0x24D2, 'M', 'c'),
-    (0x24D3, 'M', 'd'),
-    (0x24D4, 'M', 'e'),
-    (0x24D5, 'M', 'f'),
-    (0x24D6, 'M', 'g'),
-    (0x24D7, 'M', 'h'),
-    (0x24D8, 'M', 'i'),
-    (0x24D9, 'M', 'j'),
-    (0x24DA, 'M', 'k'),
-    (0x24DB, 'M', 'l'),
-    (0x24DC, 'M', 'm'),
-    (0x24DD, 'M', 'n'),
-    (0x24DE, 'M', 'o'),
-    (0x24DF, 'M', 'p'),
-    (0x24E0, 'M', 'q'),
-    (0x24E1, 'M', 'r'),
-    (0x24E2, 'M', 's'),
-    (0x24E3, 'M', 't'),
-    (0x24E4, 'M', 'u'),
-    (0x24E5, 'M', 'v'),
-    (0x24E6, 'M', 'w'),
-    (0x24E7, 'M', 'x'),
-    (0x24E8, 'M', 'y'),
-    (0x24E9, 'M', 'z'),
-    (0x24EA, 'M', '0'),
-    (0x24EB, 'V'),
-    (0x2A0C, 'M', '∫∫∫∫'),
-    (0x2A0D, 'V'),
-    (0x2A74, '3', '::='),
-    (0x2A75, '3', '=='),
-    (0x2A76, '3', '==='),
-    (0x2A77, 'V'),
-    (0x2ADC, 'M', '⫝̸'),
-    (0x2ADD, 'V'),
-    (0x2B74, 'X'),
-    (0x2B76, 'V'),
-    (0x2B96, 'X'),
-    (0x2B97, 'V'),
-    (0x2C00, 'M', 'ⰰ'),
-    (0x2C01, 'M', 'ⰱ'),
-    (0x2C02, 'M', 'ⰲ'),
-    (0x2C03, 'M', 'ⰳ'),
-    (0x2C04, 'M', 'ⰴ'),
-    (0x2C05, 'M', 'ⰵ'),
-    (0x2C06, 'M', 'ⰶ'),
-    (0x2C07, 'M', 'ⰷ'),
-    (0x2C08, 'M', 'ⰸ'),
-    (0x2C09, 'M', 'ⰹ'),
-    (0x2C0A, 'M', 'ⰺ'),
-    (0x2C0B, 'M', 'ⰻ'),
-    (0x2C0C, 'M', 'ⰼ'),
-    (0x2C0D, 'M', 'ⰽ'),
-    (0x2C0E, 'M', 'ⰾ'),
-    (0x2C0F, 'M', 'ⰿ'),
-    (0x2C10, 'M', 'ⱀ'),
-    (0x2C11, 'M', 'ⱁ'),
-    (0x2C12, 'M', 'ⱂ'),
-    (0x2C13, 'M', 'ⱃ'),
-    (0x2C14, 'M', 'ⱄ'),
-    (0x2C15, 'M', 'ⱅ'),
-    (0x2C16, 'M', 'ⱆ'),
-    (0x2C17, 'M', 'ⱇ'),
-    (0x2C18, 'M', 'ⱈ'),
-    (0x2C19, 'M', 'ⱉ'),
-    (0x2C1A, 'M', 'ⱊ'),
-    (0x2C1B, 'M', 'ⱋ'),
-    (0x2C1C, 'M', 'ⱌ'),
-    (0x2C1D, 'M', 'ⱍ'),
-    (0x2C1E, 'M', 'ⱎ'),
-    (0x2C1F, 'M', 'ⱏ'),
-    (0x2C20, 'M', 'ⱐ'),
-    (0x2C21, 'M', 'ⱑ'),
-    (0x2C22, 'M', 'ⱒ'),
-    (0x2C23, 'M', 'ⱓ'),
-    (0x2C24, 'M', 'ⱔ'),
-    (0x2C25, 'M', 'ⱕ'),
-    (0x2C26, 'M', 'ⱖ'),
-    (0x2C27, 'M', 'ⱗ'),
-    (0x2C28, 'M', 'ⱘ'),
-    ]
-
-def _seg_25() -> List[Union[Tuple[int, str], Tuple[int, str, str]]]:
-    return [
-    (0x2C29, 'M', 'ⱙ'),
-    (0x2C2A, 'M', 'ⱚ'),
-    (0x2C2B, 'M', 'ⱛ'),
-    (0x2C2C, 'M', 'ⱜ'),
-    (0x2C2D, 'M', 'ⱝ'),
-    (0x2C2E, 'M', 'ⱞ'),
-    (0x2C2F, 'M', 'ⱟ'),
-    (0x2C30, 'V'),
-    (0x2C60, 'M', 'ⱡ'),
-    (0x2C61, 'V'),
-    (0x2C62, 'M', 'ɫ'),
-    (0x2C63, 'M', 'ᵽ'),
-    (0x2C64, 'M', 'ɽ'),
-    (0x2C65, 'V'),
-    (0x2C67, 'M', 'ⱨ'),
-    (0x2C68, 'V'),
-    (0x2C69, 'M', 'ⱪ'),
-    (0x2C6A, 'V'),
-    (0x2C6B, 'M', 'ⱬ'),
-    (0x2C6C, 'V'),
-    (0x2C6D, 'M', 'ɑ'),
-    (0x2C6E, 'M', 'ɱ'),
-    (0x2C6F, 'M', 'ɐ'),
-    (0x2C70, 'M', 'ɒ'),
-    (0x2C71, 'V'),
-    (0x2C72, 'M', 'ⱳ'),
-    (0x2C73, 'V'),
-    (0x2C75, 'M', 'ⱶ'),
-    (0x2C76, 'V'),
-    (0x2C7C, 'M', 'j'),
-    (0x2C7D, 'M', 'v'),
-    (0x2C7E, 'M', 'ȿ'),
-    (0x2C7F, 'M', 'ɀ'),
-    (0x2C80, 'M', 'ⲁ'),
-    (0x2C81, 'V'),
-    (0x2C82, 'M', 'ⲃ'),
-    (0x2C83, 'V'),
-    (0x2C84, 'M', 'ⲅ'),
-    (0x2C85, 'V'),
-    (0x2C86, 'M', 'ⲇ'),
-    (0x2C87, 'V'),
-    (0x2C88, 'M', 'ⲉ'),
-    (0x2C89, 'V'),
-    (0x2C8A, 'M', 'ⲋ'),
-    (0x2C8B, 'V'),
-    (0x2C8C, 'M', 'ⲍ'),
-    (0x2C8D, 'V'),
-    (0x2C8E, 'M', 'ⲏ'),
-    (0x2C8F, 'V'),
-    (0x2C90, 'M', 'ⲑ'),
-    (0x2C91, 'V'),
-    (0x2C92, 'M', 'ⲓ'),
-    (0x2C93, 'V'),
-    (0x2C94, 'M', 'ⲕ'),
-    (0x2C95, 'V'),
-    (0x2C96, 'M', 'ⲗ'),
-    (0x2C97, 'V'),
-    (0x2C98, 'M', 'ⲙ'),
-    (0x2C99, 'V'),
-    (0x2C9A, 'M', 'ⲛ'),
-    (0x2C9B, 'V'),
-    (0x2C9C, 'M', 'ⲝ'),
-    (0x2C9D, 'V'),
-    (0x2C9E, 'M', 'ⲟ'),
-    (0x2C9F, 'V'),
-    (0x2CA0, 'M', 'ⲡ'),
-    (0x2CA1, 'V'),
-    (0x2CA2, 'M', 'ⲣ'),
-    (0x2CA3, 'V'),
-    (0x2CA4, 'M', 'ⲥ'),
-    (0x2CA5, 'V'),
-    (0x2CA6, 'M', 'ⲧ'),
-    (0x2CA7, 'V'),
-    (0x2CA8, 'M', 'ⲩ'),
-    (0x2CA9, 'V'),
-    (0x2CAA, 'M', 'ⲫ'),
-    (0x2CAB, 'V'),
-    (0x2CAC, 'M', 'ⲭ'),
-    (0x2CAD, 'V'),
-    (0x2CAE, 'M', 'ⲯ'),
-    (0x2CAF, 'V'),
-    (0x2CB0, 'M', 'ⲱ'),
-    (0x2CB1, 'V'),
-    (0x2CB2, 'M', 'ⲳ'),
-    (0x2CB3, 'V'),
-    (0x2CB4, 'M', 'ⲵ'),
-    (0x2CB5, 'V'),
-    (0x2CB6, 'M', 'ⲷ'),
-    (0x2CB7, 'V'),
-    (0x2CB8, 'M', 'ⲹ'),
-    (0x2CB9, 'V'),
-    (0x2CBA, 'M', 'ⲻ'),
-    (0x2CBB, 'V'),
-    (0x2CBC, 'M', 'ⲽ'),
-    (0x2CBD, 'V'),
-    (0x2CBE, 'M', 'ⲿ'),
-    (0x2CBF, 'V'),
-    (0x2CC0, 'M', 'ⳁ'),
-    (0x2CC1, 'V'),
-    (0x2CC2, 'M', 'ⳃ'),
-    ]
-
-def _seg_26() -> List[Union[Tuple[int, str], Tuple[int, str, str]]]:
-    return [
-    (0x2CC3, 'V'),
-    (0x2CC4, 'M', 'ⳅ'),
-    (0x2CC5, 'V'),
-    (0x2CC6, 'M', 'ⳇ'),
-    (0x2CC7, 'V'),
-    (0x2CC8, 'M', 'ⳉ'),
-    (0x2CC9, 'V'),
-    (0x2CCA, 'M', 'ⳋ'),
-    (0x2CCB, 'V'),
-    (0x2CCC, 'M', 'ⳍ'),
-    (0x2CCD, 'V'),
-    (0x2CCE, 'M', 'ⳏ'),
-    (0x2CCF, 'V'),
-    (0x2CD0, 'M', 'ⳑ'),
-    (0x2CD1, 'V'),
-    (0x2CD2, 'M', 'ⳓ'),
-    (0x2CD3, 'V'),
-    (0x2CD4, 'M', 'ⳕ'),
-    (0x2CD5, 'V'),
-    (0x2CD6, 'M', 'ⳗ'),
-    (0x2CD7, 'V'),
-    (0x2CD8, 'M', 'ⳙ'),
-    (0x2CD9, 'V'),
-    (0x2CDA, 'M', 'ⳛ'),
-    (0x2CDB, 'V'),
-    (0x2CDC, 'M', 'ⳝ'),
-    (0x2CDD, 'V'),
-    (0x2CDE, 'M', 'ⳟ'),
-    (0x2CDF, 'V'),
-    (0x2CE0, 'M', 'ⳡ'),
-    (0x2CE1, 'V'),
-    (0x2CE2, 'M', 'ⳣ'),
-    (0x2CE3, 'V'),
-    (0x2CEB, 'M', 'ⳬ'),
-    (0x2CEC, 'V'),
-    (0x2CED, 'M', 'ⳮ'),
-    (0x2CEE, 'V'),
-    (0x2CF2, 'M', 'ⳳ'),
-    (0x2CF3, 'V'),
-    (0x2CF4, 'X'),
-    (0x2CF9, 'V'),
-    (0x2D26, 'X'),
-    (0x2D27, 'V'),
-    (0x2D28, 'X'),
-    (0x2D2D, 'V'),
-    (0x2D2E, 'X'),
-    (0x2D30, 'V'),
-    (0x2D68, 'X'),
-    (0x2D6F, 'M', 'ⵡ'),
-    (0x2D70, 'V'),
-    (0x2D71, 'X'),
-    (0x2D7F, 'V'),
-    (0x2D97, 'X'),
-    (0x2DA0, 'V'),
-    (0x2DA7, 'X'),
-    (0x2DA8, 'V'),
-    (0x2DAF, 'X'),
-    (0x2DB0, 'V'),
-    (0x2DB7, 'X'),
-    (0x2DB8, 'V'),
-    (0x2DBF, 'X'),
-    (0x2DC0, 'V'),
-    (0x2DC7, 'X'),
-    (0x2DC8, 'V'),
-    (0x2DCF, 'X'),
-    (0x2DD0, 'V'),
-    (0x2DD7, 'X'),
-    (0x2DD8, 'V'),
-    (0x2DDF, 'X'),
-    (0x2DE0, 'V'),
-    (0x2E5E, 'X'),
-    (0x2E80, 'V'),
-    (0x2E9A, 'X'),
-    (0x2E9B, 'V'),
-    (0x2E9F, 'M', '母'),
-    (0x2EA0, 'V'),
-    (0x2EF3, 'M', '龟'),
-    (0x2EF4, 'X'),
-    (0x2F00, 'M', '一'),
-    (0x2F01, 'M', '丨'),
-    (0x2F02, 'M', '丶'),
-    (0x2F03, 'M', '丿'),
-    (0x2F04, 'M', '乙'),
-    (0x2F05, 'M', '亅'),
-    (0x2F06, 'M', '二'),
-    (0x2F07, 'M', '亠'),
-    (0x2F08, 'M', '人'),
-    (0x2F09, 'M', '儿'),
-    (0x2F0A, 'M', '入'),
-    (0x2F0B, 'M', '八'),
-    (0x2F0C, 'M', '冂'),
-    (0x2F0D, 'M', '冖'),
-    (0x2F0E, 'M', '冫'),
-    (0x2F0F, 'M', '几'),
-    (0x2F10, 'M', '凵'),
-    (0x2F11, 'M', '刀'),
-    (0x2F12, 'M', '力'),
-    (0x2F13, 'M', '勹'),
-    (0x2F14, 'M', '匕'),
-    (0x2F15, 'M', '匚'),
-    ]
-
-def _seg_27() -> List[Union[Tuple[int, str], Tuple[int, str, str]]]:
-    return [
-    (0x2F16, 'M', '匸'),
-    (0x2F17, 'M', '十'),
-    (0x2F18, 'M', '卜'),
-    (0x2F19, 'M', '卩'),
-    (0x2F1A, 'M', '厂'),
-    (0x2F1B, 'M', '厶'),
-    (0x2F1C, 'M', '又'),
-    (0x2F1D, 'M', '口'),
-    (0x2F1E, 'M', '囗'),
-    (0x2F1F, 'M', '土'),
-    (0x2F20, 'M', '士'),
-    (0x2F21, 'M', '夂'),
-    (0x2F22, 'M', '夊'),
-    (0x2F23, 'M', '夕'),
-    (0x2F24, 'M', '大'),
-    (0x2F25, 'M', '女'),
-    (0x2F26, 'M', '子'),
-    (0x2F27, 'M', '宀'),
-    (0x2F28, 'M', '寸'),
-    (0x2F29, 'M', '小'),
-    (0x2F2A, 'M', '尢'),
-    (0x2F2B, 'M', '尸'),
-    (0x2F2C, 'M', '屮'),
-    (0x2F2D, 'M', '山'),
-    (0x2F2E, 'M', '巛'),
-    (0x2F2F, 'M', '工'),
-    (0x2F30, 'M', '己'),
-    (0x2F31, 'M', '巾'),
-    (0x2F32, 'M', '干'),
-    (0x2F33, 'M', '幺'),
-    (0x2F34, 'M', '广'),
-    (0x2F35, 'M', '廴'),
-    (0x2F36, 'M', '廾'),
-    (0x2F37, 'M', '弋'),
-    (0x2F38, 'M', '弓'),
-    (0x2F39, 'M', '彐'),
-    (0x2F3A, 'M', '彡'),
-    (0x2F3B, 'M', '彳'),
-    (0x2F3C, 'M', '心'),
-    (0x2F3D, 'M', '戈'),
-    (0x2F3E, 'M', '戶'),
-    (0x2F3F, 'M', '手'),
-    (0x2F40, 'M', '支'),
-    (0x2F41, 'M', '攴'),
-    (0x2F42, 'M', '文'),
-    (0x2F43, 'M', '斗'),
-    (0x2F44, 'M', '斤'),
-    (0x2F45, 'M', '方'),
-    (0x2F46, 'M', '无'),
-    (0x2F47, 'M', '日'),
-    (0x2F48, 'M', '曰'),
-    (0x2F49, 'M', '月'),
-    (0x2F4A, 'M', '木'),
-    (0x2F4B, 'M', '欠'),
-    (0x2F4C, 'M', '止'),
-    (0x2F4D, 'M', '歹'),
-    (0x2F4E, 'M', '殳'),
-    (0x2F4F, 'M', '毋'),
-    (0x2F50, 'M', '比'),
-    (0x2F51, 'M', '毛'),
-    (0x2F52, 'M', '氏'),
-    (0x2F53, 'M', '气'),
-    (0x2F54, 'M', '水'),
-    (0x2F55, 'M', '火'),
-    (0x2F56, 'M', '爪'),
-    (0x2F57, 'M', '父'),
-    (0x2F58, 'M', '爻'),
-    (0x2F59, 'M', '爿'),
-    (0x2F5A, 'M', '片'),
-    (0x2F5B, 'M', '牙'),
-    (0x2F5C, 'M', '牛'),
-    (0x2F5D, 'M', '犬'),
-    (0x2F5E, 'M', '玄'),
-    (0x2F5F, 'M', '玉'),
-    (0x2F60, 'M', '瓜'),
-    (0x2F61, 'M', '瓦'),
-    (0x2F62, 'M', '甘'),
-    (0x2F63, 'M', '生'),
-    (0x2F64, 'M', '用'),
-    (0x2F65, 'M', '田'),
-    (0x2F66, 'M', '疋'),
-    (0x2F67, 'M', '疒'),
-    (0x2F68, 'M', '癶'),
-    (0x2F69, 'M', '白'),
-    (0x2F6A, 'M', '皮'),
-    (0x2F6B, 'M', '皿'),
-    (0x2F6C, 'M', '目'),
-    (0x2F6D, 'M', '矛'),
-    (0x2F6E, 'M', '矢'),
-    (0x2F6F, 'M', '石'),
-    (0x2F70, 'M', '示'),
-    (0x2F71, 'M', '禸'),
-    (0x2F72, 'M', '禾'),
-    (0x2F73, 'M', '穴'),
-    (0x2F74, 'M', '立'),
-    (0x2F75, 'M', '竹'),
-    (0x2F76, 'M', '米'),
-    (0x2F77, 'M', '糸'),
-    (0x2F78, 'M', '缶'),
-    (0x2F79, 'M', '网'),
-    ]
-
-def _seg_28() -> List[Union[Tuple[int, str], Tuple[int, str, str]]]:
-    return [
-    (0x2F7A, 'M', '羊'),
-    (0x2F7B, 'M', '羽'),
-    (0x2F7C, 'M', '老'),
-    (0x2F7D, 'M', '而'),
-    (0x2F7E, 'M', '耒'),
-    (0x2F7F, 'M', '耳'),
-    (0x2F80, 'M', '聿'),
-    (0x2F81, 'M', '肉'),
-    (0x2F82, 'M', '臣'),
-    (0x2F83, 'M', '自'),
-    (0x2F84, 'M', '至'),
-    (0x2F85, 'M', '臼'),
-    (0x2F86, 'M', '舌'),
-    (0x2F87, 'M', '舛'),
-    (0x2F88, 'M', '舟'),
-    (0x2F89, 'M', '艮'),
-    (0x2F8A, 'M', '色'),
-    (0x2F8B, 'M', '艸'),
-    (0x2F8C, 'M', '虍'),
-    (0x2F8D, 'M', '虫'),
-    (0x2F8E, 'M', '血'),
-    (0x2F8F, 'M', '行'),
-    (0x2F90, 'M', '衣'),
-    (0x2F91, 'M', '襾'),
-    (0x2F92, 'M', '見'),
-    (0x2F93, 'M', '角'),
-    (0x2F94, 'M', '言'),
-    (0x2F95, 'M', '谷'),
-    (0x2F96, 'M', '豆'),
-    (0x2F97, 'M', '豕'),
-    (0x2F98, 'M', '豸'),
-    (0x2F99, 'M', '貝'),
-    (0x2F9A, 'M', '赤'),
-    (0x2F9B, 'M', '走'),
-    (0x2F9C, 'M', '足'),
-    (0x2F9D, 'M', '身'),
-    (0x2F9E, 'M', '車'),
-    (0x2F9F, 'M', '辛'),
-    (0x2FA0, 'M', '辰'),
-    (0x2FA1, 'M', '辵'),
-    (0x2FA2, 'M', '邑'),
-    (0x2FA3, 'M', '酉'),
-    (0x2FA4, 'M', '釆'),
-    (0x2FA5, 'M', '里'),
-    (0x2FA6, 'M', '金'),
-    (0x2FA7, 'M', '長'),
-    (0x2FA8, 'M', '門'),
-    (0x2FA9, 'M', '阜'),
-    (0x2FAA, 'M', '隶'),
-    (0x2FAB, 'M', '隹'),
-    (0x2FAC, 'M', '雨'),
-    (0x2FAD, 'M', '靑'),
-    (0x2FAE, 'M', '非'),
-    (0x2FAF, 'M', '面'),
-    (0x2FB0, 'M', '革'),
-    (0x2FB1, 'M', '韋'),
-    (0x2FB2, 'M', '韭'),
-    (0x2FB3, 'M', '音'),
-    (0x2FB4, 'M', '頁'),
-    (0x2FB5, 'M', '風'),
-    (0x2FB6, 'M', '飛'),
-    (0x2FB7, 'M', '食'),
-    (0x2FB8, 'M', '首'),
-    (0x2FB9, 'M', '香'),
-    (0x2FBA, 'M', '馬'),
-    (0x2FBB, 'M', '骨'),
-    (0x2FBC, 'M', '高'),
-    (0x2FBD, 'M', '髟'),
-    (0x2FBE, 'M', '鬥'),
-    (0x2FBF, 'M', '鬯'),
-    (0x2FC0, 'M', '鬲'),
-    (0x2FC1, 'M', '鬼'),
-    (0x2FC2, 'M', '魚'),
-    (0x2FC3, 'M', '鳥'),
-    (0x2FC4, 'M', '鹵'),
-    (0x2FC5, 'M', '鹿'),
-    (0x2FC6, 'M', '麥'),
-    (0x2FC7, 'M', '麻'),
-    (0x2FC8, 'M', '黃'),
-    (0x2FC9, 'M', '黍'),
-    (0x2FCA, 'M', '黑'),
-    (0x2FCB, 'M', '黹'),
-    (0x2FCC, 'M', '黽'),
-    (0x2FCD, 'M', '鼎'),
-    (0x2FCE, 'M', '鼓'),
-    (0x2FCF, 'M', '鼠'),
-    (0x2FD0, 'M', '鼻'),
-    (0x2FD1, 'M', '齊'),
-    (0x2FD2, 'M', '齒'),
-    (0x2FD3, 'M', '龍'),
-    (0x2FD4, 'M', '龜'),
-    (0x2FD5, 'M', '龠'),
-    (0x2FD6, 'X'),
-    (0x3000, '3', ' '),
-    (0x3001, 'V'),
-    (0x3002, 'M', '.'),
-    (0x3003, 'V'),
-    (0x3036, 'M', '〒'),
-    (0x3037, 'V'),
-    (0x3038, 'M', '十'),
-    ]
-
-def _seg_29() -> List[Union[Tuple[int, str], Tuple[int, str, str]]]:
-    return [
-    (0x3039, 'M', '卄'),
-    (0x303A, 'M', '卅'),
-    (0x303B, 'V'),
-    (0x3040, 'X'),
-    (0x3041, 'V'),
-    (0x3097, 'X'),
-    (0x3099, 'V'),
-    (0x309B, '3', ' ゙'),
-    (0x309C, '3', ' ゚'),
-    (0x309D, 'V'),
-    (0x309F, 'M', 'より'),
-    (0x30A0, 'V'),
-    (0x30FF, 'M', 'コト'),
-    (0x3100, 'X'),
-    (0x3105, 'V'),
-    (0x3130, 'X'),
-    (0x3131, 'M', 'ᄀ'),
-    (0x3132, 'M', 'ᄁ'),
-    (0x3133, 'M', 'ᆪ'),
-    (0x3134, 'M', 'ᄂ'),
-    (0x3135, 'M', 'ᆬ'),
-    (0x3136, 'M', 'ᆭ'),
-    (0x3137, 'M', 'ᄃ'),
-    (0x3138, 'M', 'ᄄ'),
-    (0x3139, 'M', 'ᄅ'),
-    (0x313A, 'M', 'ᆰ'),
-    (0x313B, 'M', 'ᆱ'),
-    (0x313C, 'M', 'ᆲ'),
-    (0x313D, 'M', 'ᆳ'),
-    (0x313E, 'M', 'ᆴ'),
-    (0x313F, 'M', 'ᆵ'),
-    (0x3140, 'M', 'ᄚ'),
-    (0x3141, 'M', 'ᄆ'),
-    (0x3142, 'M', 'ᄇ'),
-    (0x3143, 'M', 'ᄈ'),
-    (0x3144, 'M', 'ᄡ'),
-    (0x3145, 'M', 'ᄉ'),
-    (0x3146, 'M', 'ᄊ'),
-    (0x3147, 'M', 'ᄋ'),
-    (0x3148, 'M', 'ᄌ'),
-    (0x3149, 'M', 'ᄍ'),
-    (0x314A, 'M', 'ᄎ'),
-    (0x314B, 'M', 'ᄏ'),
-    (0x314C, 'M', 'ᄐ'),
-    (0x314D, 'M', 'ᄑ'),
-    (0x314E, 'M', 'ᄒ'),
-    (0x314F, 'M', 'ᅡ'),
-    (0x3150, 'M', 'ᅢ'),
-    (0x3151, 'M', 'ᅣ'),
-    (0x3152, 'M', 'ᅤ'),
-    (0x3153, 'M', 'ᅥ'),
-    (0x3154, 'M', 'ᅦ'),
-    (0x3155, 'M', 'ᅧ'),
-    (0x3156, 'M', 'ᅨ'),
-    (0x3157, 'M', 'ᅩ'),
-    (0x3158, 'M', 'ᅪ'),
-    (0x3159, 'M', 'ᅫ'),
-    (0x315A, 'M', 'ᅬ'),
-    (0x315B, 'M', 'ᅭ'),
-    (0x315C, 'M', 'ᅮ'),
-    (0x315D, 'M', 'ᅯ'),
-    (0x315E, 'M', 'ᅰ'),
-    (0x315F, 'M', 'ᅱ'),
-    (0x3160, 'M', 'ᅲ'),
-    (0x3161, 'M', 'ᅳ'),
-    (0x3162, 'M', 'ᅴ'),
-    (0x3163, 'M', 'ᅵ'),
-    (0x3164, 'X'),
-    (0x3165, 'M', 'ᄔ'),
-    (0x3166, 'M', 'ᄕ'),
-    (0x3167, 'M', 'ᇇ'),
-    (0x3168, 'M', 'ᇈ'),
-    (0x3169, 'M', 'ᇌ'),
-    (0x316A, 'M', 'ᇎ'),
-    (0x316B, 'M', 'ᇓ'),
-    (0x316C, 'M', 'ᇗ'),
-    (0x316D, 'M', 'ᇙ'),
-    (0x316E, 'M', 'ᄜ'),
-    (0x316F, 'M', 'ᇝ'),
-    (0x3170, 'M', 'ᇟ'),
-    (0x3171, 'M', 'ᄝ'),
-    (0x3172, 'M', 'ᄞ'),
-    (0x3173, 'M', 'ᄠ'),
-    (0x3174, 'M', 'ᄢ'),
-    (0x3175, 'M', 'ᄣ'),
-    (0x3176, 'M', 'ᄧ'),
-    (0x3177, 'M', 'ᄩ'),
-    (0x3178, 'M', 'ᄫ'),
-    (0x3179, 'M', 'ᄬ'),
-    (0x317A, 'M', 'ᄭ'),
-    (0x317B, 'M', 'ᄮ'),
-    (0x317C, 'M', 'ᄯ'),
-    (0x317D, 'M', 'ᄲ'),
-    (0x317E, 'M', 'ᄶ'),
-    (0x317F, 'M', 'ᅀ'),
-    (0x3180, 'M', 'ᅇ'),
-    (0x3181, 'M', 'ᅌ'),
-    (0x3182, 'M', 'ᇱ'),
-    (0x3183, 'M', 'ᇲ'),
-    (0x3184, 'M', 'ᅗ'),
-    ]
-
-def _seg_30() -> List[Union[Tuple[int, str], Tuple[int, str, str]]]:
-    return [
-    (0x3185, 'M', 'ᅘ'),
-    (0x3186, 'M', 'ᅙ'),
-    (0x3187, 'M', 'ᆄ'),
-    (0x3188, 'M', 'ᆅ'),
-    (0x3189, 'M', 'ᆈ'),
-    (0x318A, 'M', 'ᆑ'),
-    (0x318B, 'M', 'ᆒ'),
-    (0x318C, 'M', 'ᆔ'),
-    (0x318D, 'M', 'ᆞ'),
-    (0x318E, 'M', 'ᆡ'),
-    (0x318F, 'X'),
-    (0x3190, 'V'),
-    (0x3192, 'M', '一'),
-    (0x3193, 'M', '二'),
-    (0x3194, 'M', '三'),
-    (0x3195, 'M', '四'),
-    (0x3196, 'M', '上'),
-    (0x3197, 'M', '中'),
-    (0x3198, 'M', '下'),
-    (0x3199, 'M', '甲'),
-    (0x319A, 'M', '乙'),
-    (0x319B, 'M', '丙'),
-    (0x319C, 'M', '丁'),
-    (0x319D, 'M', '天'),
-    (0x319E, 'M', '地'),
-    (0x319F, 'M', '人'),
-    (0x31A0, 'V'),
-    (0x31E4, 'X'),
-    (0x31F0, 'V'),
-    (0x3200, '3', '(ᄀ)'),
-    (0x3201, '3', '(ᄂ)'),
-    (0x3202, '3', '(ᄃ)'),
-    (0x3203, '3', '(ᄅ)'),
-    (0x3204, '3', '(ᄆ)'),
-    (0x3205, '3', '(ᄇ)'),
-    (0x3206, '3', '(ᄉ)'),
-    (0x3207, '3', '(ᄋ)'),
-    (0x3208, '3', '(ᄌ)'),
-    (0x3209, '3', '(ᄎ)'),
-    (0x320A, '3', '(ᄏ)'),
-    (0x320B, '3', '(ᄐ)'),
-    (0x320C, '3', '(ᄑ)'),
-    (0x320D, '3', '(ᄒ)'),
-    (0x320E, '3', '(가)'),
-    (0x320F, '3', '(나)'),
-    (0x3210, '3', '(다)'),
-    (0x3211, '3', '(라)'),
-    (0x3212, '3', '(마)'),
-    (0x3213, '3', '(바)'),
-    (0x3214, '3', '(사)'),
-    (0x3215, '3', '(아)'),
-    (0x3216, '3', '(자)'),
-    (0x3217, '3', '(차)'),
-    (0x3218, '3', '(카)'),
-    (0x3219, '3', '(타)'),
-    (0x321A, '3', '(파)'),
-    (0x321B, '3', '(하)'),
-    (0x321C, '3', '(주)'),
-    (0x321D, '3', '(오전)'),
-    (0x321E, '3', '(오후)'),
-    (0x321F, 'X'),
-    (0x3220, '3', '(一)'),
-    (0x3221, '3', '(二)'),
-    (0x3222, '3', '(三)'),
-    (0x3223, '3', '(四)'),
-    (0x3224, '3', '(五)'),
-    (0x3225, '3', '(六)'),
-    (0x3226, '3', '(七)'),
-    (0x3227, '3', '(八)'),
-    (0x3228, '3', '(九)'),
-    (0x3229, '3', '(十)'),
-    (0x322A, '3', '(月)'),
-    (0x322B, '3', '(火)'),
-    (0x322C, '3', '(水)'),
-    (0x322D, '3', '(木)'),
-    (0x322E, '3', '(金)'),
-    (0x322F, '3', '(土)'),
-    (0x3230, '3', '(日)'),
-    (0x3231, '3', '(株)'),
-    (0x3232, '3', '(有)'),
-    (0x3233, '3', '(社)'),
-    (0x3234, '3', '(名)'),
-    (0x3235, '3', '(特)'),
-    (0x3236, '3', '(財)'),
-    (0x3237, '3', '(祝)'),
-    (0x3238, '3', '(労)'),
-    (0x3239, '3', '(代)'),
-    (0x323A, '3', '(呼)'),
-    (0x323B, '3', '(学)'),
-    (0x323C, '3', '(監)'),
-    (0x323D, '3', '(企)'),
-    (0x323E, '3', '(資)'),
-    (0x323F, '3', '(協)'),
-    (0x3240, '3', '(祭)'),
-    (0x3241, '3', '(休)'),
-    (0x3242, '3', '(自)'),
-    (0x3243, '3', '(至)'),
-    (0x3244, 'M', '問'),
-    (0x3245, 'M', '幼'),
-    (0x3246, 'M', '文'),
-    ]
-
-def _seg_31() -> List[Union[Tuple[int, str], Tuple[int, str, str]]]:
-    return [
-    (0x3247, 'M', '箏'),
-    (0x3248, 'V'),
-    (0x3250, 'M', 'pte'),
-    (0x3251, 'M', '21'),
-    (0x3252, 'M', '22'),
-    (0x3253, 'M', '23'),
-    (0x3254, 'M', '24'),
-    (0x3255, 'M', '25'),
-    (0x3256, 'M', '26'),
-    (0x3257, 'M', '27'),
-    (0x3258, 'M', '28'),
-    (0x3259, 'M', '29'),
-    (0x325A, 'M', '30'),
-    (0x325B, 'M', '31'),
-    (0x325C, 'M', '32'),
-    (0x325D, 'M', '33'),
-    (0x325E, 'M', '34'),
-    (0x325F, 'M', '35'),
-    (0x3260, 'M', 'ᄀ'),
-    (0x3261, 'M', 'ᄂ'),
-    (0x3262, 'M', 'ᄃ'),
-    (0x3263, 'M', 'ᄅ'),
-    (0x3264, 'M', 'ᄆ'),
-    (0x3265, 'M', 'ᄇ'),
-    (0x3266, 'M', 'ᄉ'),
-    (0x3267, 'M', 'ᄋ'),
-    (0x3268, 'M', 'ᄌ'),
-    (0x3269, 'M', 'ᄎ'),
-    (0x326A, 'M', 'ᄏ'),
-    (0x326B, 'M', 'ᄐ'),
-    (0x326C, 'M', 'ᄑ'),
-    (0x326D, 'M', 'ᄒ'),
-    (0x326E, 'M', '가'),
-    (0x326F, 'M', '나'),
-    (0x3270, 'M', '다'),
-    (0x3271, 'M', '라'),
-    (0x3272, 'M', '마'),
-    (0x3273, 'M', '바'),
-    (0x3274, 'M', '사'),
-    (0x3275, 'M', '아'),
-    (0x3276, 'M', '자'),
-    (0x3277, 'M', '차'),
-    (0x3278, 'M', '카'),
-    (0x3279, 'M', '타'),
-    (0x327A, 'M', '파'),
-    (0x327B, 'M', '하'),
-    (0x327C, 'M', '참고'),
-    (0x327D, 'M', '주의'),
-    (0x327E, 'M', '우'),
-    (0x327F, 'V'),
-    (0x3280, 'M', '一'),
-    (0x3281, 'M', '二'),
-    (0x3282, 'M', '三'),
-    (0x3283, 'M', '四'),
-    (0x3284, 'M', '五'),
-    (0x3285, 'M', '六'),
-    (0x3286, 'M', '七'),
-    (0x3287, 'M', '八'),
-    (0x3288, 'M', '九'),
-    (0x3289, 'M', '十'),
-    (0x328A, 'M', '月'),
-    (0x328B, 'M', '火'),
-    (0x328C, 'M', '水'),
-    (0x328D, 'M', '木'),
-    (0x328E, 'M', '金'),
-    (0x328F, 'M', '土'),
-    (0x3290, 'M', '日'),
-    (0x3291, 'M', '株'),
-    (0x3292, 'M', '有'),
-    (0x3293, 'M', '社'),
-    (0x3294, 'M', '名'),
-    (0x3295, 'M', '特'),
-    (0x3296, 'M', '財'),
-    (0x3297, 'M', '祝'),
-    (0x3298, 'M', '労'),
-    (0x3299, 'M', '秘'),
-    (0x329A, 'M', '男'),
-    (0x329B, 'M', '女'),
-    (0x329C, 'M', '適'),
-    (0x329D, 'M', '優'),
-    (0x329E, 'M', '印'),
-    (0x329F, 'M', '注'),
-    (0x32A0, 'M', '項'),
-    (0x32A1, 'M', '休'),
-    (0x32A2, 'M', '写'),
-    (0x32A3, 'M', '正'),
-    (0x32A4, 'M', '上'),
-    (0x32A5, 'M', '中'),
-    (0x32A6, 'M', '下'),
-    (0x32A7, 'M', '左'),
-    (0x32A8, 'M', '右'),
-    (0x32A9, 'M', '医'),
-    (0x32AA, 'M', '宗'),
-    (0x32AB, 'M', '学'),
-    (0x32AC, 'M', '監'),
-    (0x32AD, 'M', '企'),
-    (0x32AE, 'M', '資'),
-    (0x32AF, 'M', '協'),
-    (0x32B0, 'M', '夜'),
-    (0x32B1, 'M', '36'),
-    ]
-
-def _seg_32() -> List[Union[Tuple[int, str], Tuple[int, str, str]]]:
-    return [
-    (0x32B2, 'M', '37'),
-    (0x32B3, 'M', '38'),
-    (0x32B4, 'M', '39'),
-    (0x32B5, 'M', '40'),
-    (0x32B6, 'M', '41'),
-    (0x32B7, 'M', '42'),
-    (0x32B8, 'M', '43'),
-    (0x32B9, 'M', '44'),
-    (0x32BA, 'M', '45'),
-    (0x32BB, 'M', '46'),
-    (0x32BC, 'M', '47'),
-    (0x32BD, 'M', '48'),
-    (0x32BE, 'M', '49'),
-    (0x32BF, 'M', '50'),
-    (0x32C0, 'M', '1月'),
-    (0x32C1, 'M', '2月'),
-    (0x32C2, 'M', '3月'),
-    (0x32C3, 'M', '4月'),
-    (0x32C4, 'M', '5月'),
-    (0x32C5, 'M', '6月'),
-    (0x32C6, 'M', '7月'),
-    (0x32C7, 'M', '8月'),
-    (0x32C8, 'M', '9月'),
-    (0x32C9, 'M', '10月'),
-    (0x32CA, 'M', '11月'),
-    (0x32CB, 'M', '12月'),
-    (0x32CC, 'M', 'hg'),
-    (0x32CD, 'M', 'erg'),
-    (0x32CE, 'M', 'ev'),
-    (0x32CF, 'M', 'ltd'),
-    (0x32D0, 'M', 'ア'),
-    (0x32D1, 'M', 'イ'),
-    (0x32D2, 'M', 'ウ'),
-    (0x32D3, 'M', 'エ'),
-    (0x32D4, 'M', 'オ'),
-    (0x32D5, 'M', 'カ'),
-    (0x32D6, 'M', 'キ'),
-    (0x32D7, 'M', 'ク'),
-    (0x32D8, 'M', 'ケ'),
-    (0x32D9, 'M', 'コ'),
-    (0x32DA, 'M', 'サ'),
-    (0x32DB, 'M', 'シ'),
-    (0x32DC, 'M', 'ス'),
-    (0x32DD, 'M', 'セ'),
-    (0x32DE, 'M', 'ソ'),
-    (0x32DF, 'M', 'タ'),
-    (0x32E0, 'M', 'チ'),
-    (0x32E1, 'M', 'ツ'),
-    (0x32E2, 'M', 'テ'),
-    (0x32E3, 'M', 'ト'),
-    (0x32E4, 'M', 'ナ'),
-    (0x32E5, 'M', 'ニ'),
-    (0x32E6, 'M', 'ヌ'),
-    (0x32E7, 'M', 'ネ'),
-    (0x32E8, 'M', 'ノ'),
-    (0x32E9, 'M', 'ハ'),
-    (0x32EA, 'M', 'ヒ'),
-    (0x32EB, 'M', 'フ'),
-    (0x32EC, 'M', 'ヘ'),
-    (0x32ED, 'M', 'ホ'),
-    (0x32EE, 'M', 'マ'),
-    (0x32EF, 'M', 'ミ'),
-    (0x32F0, 'M', 'ム'),
-    (0x32F1, 'M', 'メ'),
-    (0x32F2, 'M', 'モ'),
-    (0x32F3, 'M', 'ヤ'),
-    (0x32F4, 'M', 'ユ'),
-    (0x32F5, 'M', 'ヨ'),
-    (0x32F6, 'M', 'ラ'),
-    (0x32F7, 'M', 'リ'),
-    (0x32F8, 'M', 'ル'),
-    (0x32F9, 'M', 'レ'),
-    (0x32FA, 'M', 'ロ'),
-    (0x32FB, 'M', 'ワ'),
-    (0x32FC, 'M', 'ヰ'),
-    (0x32FD, 'M', 'ヱ'),
-    (0x32FE, 'M', 'ヲ'),
-    (0x32FF, 'M', '令和'),
-    (0x3300, 'M', 'アパート'),
-    (0x3301, 'M', 'アルファ'),
-    (0x3302, 'M', 'アンペア'),
-    (0x3303, 'M', 'アール'),
-    (0x3304, 'M', 'イニング'),
-    (0x3305, 'M', 'インチ'),
-    (0x3306, 'M', 'ウォン'),
-    (0x3307, 'M', 'エスクード'),
-    (0x3308, 'M', 'エーカー'),
-    (0x3309, 'M', 'オンス'),
-    (0x330A, 'M', 'オーム'),
-    (0x330B, 'M', 'カイリ'),
-    (0x330C, 'M', 'カラット'),
-    (0x330D, 'M', 'カロリー'),
-    (0x330E, 'M', 'ガロン'),
-    (0x330F, 'M', 'ガンマ'),
-    (0x3310, 'M', 'ギガ'),
-    (0x3311, 'M', 'ギニー'),
-    (0x3312, 'M', 'キュリー'),
-    (0x3313, 'M', 'ギルダー'),
-    (0x3314, 'M', 'キロ'),
-    (0x3315, 'M', 'キログラム'),
-    ]
-
-def _seg_33() -> List[Union[Tuple[int, str], Tuple[int, str, str]]]:
-    return [
-    (0x3316, 'M', 'キロメートル'),
-    (0x3317, 'M', 'キロワット'),
-    (0x3318, 'M', 'グラム'),
-    (0x3319, 'M', 'グラムトン'),
-    (0x331A, 'M', 'クルゼイロ'),
-    (0x331B, 'M', 'クローネ'),
-    (0x331C, 'M', 'ケース'),
-    (0x331D, 'M', 'コルナ'),
-    (0x331E, 'M', 'コーポ'),
-    (0x331F, 'M', 'サイクル'),
-    (0x3320, 'M', 'サンチーム'),
-    (0x3321, 'M', 'シリング'),
-    (0x3322, 'M', 'センチ'),
-    (0x3323, 'M', 'セント'),
-    (0x3324, 'M', 'ダース'),
-    (0x3325, 'M', 'デシ'),
-    (0x3326, 'M', 'ドル'),
-    (0x3327, 'M', 'トン'),
-    (0x3328, 'M', 'ナノ'),
-    (0x3329, 'M', 'ノット'),
-    (0x332A, 'M', 'ハイツ'),
-    (0x332B, 'M', 'パーセント'),
-    (0x332C, 'M', 'パーツ'),
-    (0x332D, 'M', 'バーレル'),
-    (0x332E, 'M', 'ピアストル'),
-    (0x332F, 'M', 'ピクル'),
-    (0x3330, 'M', 'ピコ'),
-    (0x3331, 'M', 'ビル'),
-    (0x3332, 'M', 'ファラッド'),
-    (0x3333, 'M', 'フィート'),
-    (0x3334, 'M', 'ブッシェル'),
-    (0x3335, 'M', 'フラン'),
-    (0x3336, 'M', 'ヘクタール'),
-    (0x3337, 'M', 'ペソ'),
-    (0x3338, 'M', 'ペニヒ'),
-    (0x3339, 'M', 'ヘルツ'),
-    (0x333A, 'M', 'ペンス'),
-    (0x333B, 'M', 'ページ'),
-    (0x333C, 'M', 'ベータ'),
-    (0x333D, 'M', 'ポイント'),
-    (0x333E, 'M', 'ボルト'),
-    (0x333F, 'M', 'ホン'),
-    (0x3340, 'M', 'ポンド'),
-    (0x3341, 'M', 'ホール'),
-    (0x3342, 'M', 'ホーン'),
-    (0x3343, 'M', 'マイクロ'),
-    (0x3344, 'M', 'マイル'),
-    (0x3345, 'M', 'マッハ'),
-    (0x3346, 'M', 'マルク'),
-    (0x3347, 'M', 'マンション'),
-    (0x3348, 'M', 'ミクロン'),
-    (0x3349, 'M', 'ミリ'),
-    (0x334A, 'M', 'ミリバール'),
-    (0x334B, 'M', 'メガ'),
-    (0x334C, 'M', 'メガトン'),
-    (0x334D, 'M', 'メートル'),
-    (0x334E, 'M', 'ヤード'),
-    (0x334F, 'M', 'ヤール'),
-    (0x3350, 'M', 'ユアン'),
-    (0x3351, 'M', 'リットル'),
-    (0x3352, 'M', 'リラ'),
-    (0x3353, 'M', 'ルピー'),
-    (0x3354, 'M', 'ルーブル'),
-    (0x3355, 'M', 'レム'),
-    (0x3356, 'M', 'レントゲン'),
-    (0x3357, 'M', 'ワット'),
-    (0x3358, 'M', '0点'),
-    (0x3359, 'M', '1点'),
-    (0x335A, 'M', '2点'),
-    (0x335B, 'M', '3点'),
-    (0x335C, 'M', '4点'),
-    (0x335D, 'M', '5点'),
-    (0x335E, 'M', '6点'),
-    (0x335F, 'M', '7点'),
-    (0x3360, 'M', '8点'),
-    (0x3361, 'M', '9点'),
-    (0x3362, 'M', '10点'),
-    (0x3363, 'M', '11点'),
-    (0x3364, 'M', '12点'),
-    (0x3365, 'M', '13点'),
-    (0x3366, 'M', '14点'),
-    (0x3367, 'M', '15点'),
-    (0x3368, 'M', '16点'),
-    (0x3369, 'M', '17点'),
-    (0x336A, 'M', '18点'),
-    (0x336B, 'M', '19点'),
-    (0x336C, 'M', '20点'),
-    (0x336D, 'M', '21点'),
-    (0x336E, 'M', '22点'),
-    (0x336F, 'M', '23点'),
-    (0x3370, 'M', '24点'),
-    (0x3371, 'M', 'hpa'),
-    (0x3372, 'M', 'da'),
-    (0x3373, 'M', 'au'),
-    (0x3374, 'M', 'bar'),
-    (0x3375, 'M', 'ov'),
-    (0x3376, 'M', 'pc'),
-    (0x3377, 'M', 'dm'),
-    (0x3378, 'M', 'dm2'),
-    (0x3379, 'M', 'dm3'),
-    ]
-
-def _seg_34() -> List[Union[Tuple[int, str], Tuple[int, str, str]]]:
-    return [
-    (0x337A, 'M', 'iu'),
-    (0x337B, 'M', '平成'),
-    (0x337C, 'M', '昭和'),
-    (0x337D, 'M', '大正'),
-    (0x337E, 'M', '明治'),
-    (0x337F, 'M', '株式会社'),
-    (0x3380, 'M', 'pa'),
-    (0x3381, 'M', 'na'),
-    (0x3382, 'M', 'μa'),
-    (0x3383, 'M', 'ma'),
-    (0x3384, 'M', 'ka'),
-    (0x3385, 'M', 'kb'),
-    (0x3386, 'M', 'mb'),
-    (0x3387, 'M', 'gb'),
-    (0x3388, 'M', 'cal'),
-    (0x3389, 'M', 'kcal'),
-    (0x338A, 'M', 'pf'),
-    (0x338B, 'M', 'nf'),
-    (0x338C, 'M', 'μf'),
-    (0x338D, 'M', 'μg'),
-    (0x338E, 'M', 'mg'),
-    (0x338F, 'M', 'kg'),
-    (0x3390, 'M', 'hz'),
-    (0x3391, 'M', 'khz'),
-    (0x3392, 'M', 'mhz'),
-    (0x3393, 'M', 'ghz'),
-    (0x3394, 'M', 'thz'),
-    (0x3395, 'M', 'μl'),
-    (0x3396, 'M', 'ml'),
-    (0x3397, 'M', 'dl'),
-    (0x3398, 'M', 'kl'),
-    (0x3399, 'M', 'fm'),
-    (0x339A, 'M', 'nm'),
-    (0x339B, 'M', 'μm'),
-    (0x339C, 'M', 'mm'),
-    (0x339D, 'M', 'cm'),
-    (0x339E, 'M', 'km'),
-    (0x339F, 'M', 'mm2'),
-    (0x33A0, 'M', 'cm2'),
-    (0x33A1, 'M', 'm2'),
-    (0x33A2, 'M', 'km2'),
-    (0x33A3, 'M', 'mm3'),
-    (0x33A4, 'M', 'cm3'),
-    (0x33A5, 'M', 'm3'),
-    (0x33A6, 'M', 'km3'),
-    (0x33A7, 'M', 'm∕s'),
-    (0x33A8, 'M', 'm∕s2'),
-    (0x33A9, 'M', 'pa'),
-    (0x33AA, 'M', 'kpa'),
-    (0x33AB, 'M', 'mpa'),
-    (0x33AC, 'M', 'gpa'),
-    (0x33AD, 'M', 'rad'),
-    (0x33AE, 'M', 'rad∕s'),
-    (0x33AF, 'M', 'rad∕s2'),
-    (0x33B0, 'M', 'ps'),
-    (0x33B1, 'M', 'ns'),
-    (0x33B2, 'M', 'μs'),
-    (0x33B3, 'M', 'ms'),
-    (0x33B4, 'M', 'pv'),
-    (0x33B5, 'M', 'nv'),
-    (0x33B6, 'M', 'μv'),
-    (0x33B7, 'M', 'mv'),
-    (0x33B8, 'M', 'kv'),
-    (0x33B9, 'M', 'mv'),
-    (0x33BA, 'M', 'pw'),
-    (0x33BB, 'M', 'nw'),
-    (0x33BC, 'M', 'μw'),
-    (0x33BD, 'M', 'mw'),
-    (0x33BE, 'M', 'kw'),
-    (0x33BF, 'M', 'mw'),
-    (0x33C0, 'M', 'kω'),
-    (0x33C1, 'M', 'mω'),
-    (0x33C2, 'X'),
-    (0x33C3, 'M', 'bq'),
-    (0x33C4, 'M', 'cc'),
-    (0x33C5, 'M', 'cd'),
-    (0x33C6, 'M', 'c∕kg'),
-    (0x33C7, 'X'),
-    (0x33C8, 'M', 'db'),
-    (0x33C9, 'M', 'gy'),
-    (0x33CA, 'M', 'ha'),
-    (0x33CB, 'M', 'hp'),
-    (0x33CC, 'M', 'in'),
-    (0x33CD, 'M', 'kk'),
-    (0x33CE, 'M', 'km'),
-    (0x33CF, 'M', 'kt'),
-    (0x33D0, 'M', 'lm'),
-    (0x33D1, 'M', 'ln'),
-    (0x33D2, 'M', 'log'),
-    (0x33D3, 'M', 'lx'),
-    (0x33D4, 'M', 'mb'),
-    (0x33D5, 'M', 'mil'),
-    (0x33D6, 'M', 'mol'),
-    (0x33D7, 'M', 'ph'),
-    (0x33D8, 'X'),
-    (0x33D9, 'M', 'ppm'),
-    (0x33DA, 'M', 'pr'),
-    (0x33DB, 'M', 'sr'),
-    (0x33DC, 'M', 'sv'),
-    (0x33DD, 'M', 'wb'),
-    ]
-
-def _seg_35() -> List[Union[Tuple[int, str], Tuple[int, str, str]]]:
-    return [
-    (0x33DE, 'M', 'v∕m'),
-    (0x33DF, 'M', 'a∕m'),
-    (0x33E0, 'M', '1日'),
-    (0x33E1, 'M', '2日'),
-    (0x33E2, 'M', '3日'),
-    (0x33E3, 'M', '4日'),
-    (0x33E4, 'M', '5日'),
-    (0x33E5, 'M', '6日'),
-    (0x33E6, 'M', '7日'),
-    (0x33E7, 'M', '8日'),
-    (0x33E8, 'M', '9日'),
-    (0x33E9, 'M', '10日'),
-    (0x33EA, 'M', '11日'),
-    (0x33EB, 'M', '12日'),
-    (0x33EC, 'M', '13日'),
-    (0x33ED, 'M', '14日'),
-    (0x33EE, 'M', '15日'),
-    (0x33EF, 'M', '16日'),
-    (0x33F0, 'M', '17日'),
-    (0x33F1, 'M', '18日'),
-    (0x33F2, 'M', '19日'),
-    (0x33F3, 'M', '20日'),
-    (0x33F4, 'M', '21日'),
-    (0x33F5, 'M', '22日'),
-    (0x33F6, 'M', '23日'),
-    (0x33F7, 'M', '24日'),
-    (0x33F8, 'M', '25日'),
-    (0x33F9, 'M', '26日'),
-    (0x33FA, 'M', '27日'),
-    (0x33FB, 'M', '28日'),
-    (0x33FC, 'M', '29日'),
-    (0x33FD, 'M', '30日'),
-    (0x33FE, 'M', '31日'),
-    (0x33FF, 'M', 'gal'),
-    (0x3400, 'V'),
-    (0xA48D, 'X'),
-    (0xA490, 'V'),
-    (0xA4C7, 'X'),
-    (0xA4D0, 'V'),
-    (0xA62C, 'X'),
-    (0xA640, 'M', 'ꙁ'),
-    (0xA641, 'V'),
-    (0xA642, 'M', 'ꙃ'),
-    (0xA643, 'V'),
-    (0xA644, 'M', 'ꙅ'),
-    (0xA645, 'V'),
-    (0xA646, 'M', 'ꙇ'),
-    (0xA647, 'V'),
-    (0xA648, 'M', 'ꙉ'),
-    (0xA649, 'V'),
-    (0xA64A, 'M', 'ꙋ'),
-    (0xA64B, 'V'),
-    (0xA64C, 'M', 'ꙍ'),
-    (0xA64D, 'V'),
-    (0xA64E, 'M', 'ꙏ'),
-    (0xA64F, 'V'),
-    (0xA650, 'M', 'ꙑ'),
-    (0xA651, 'V'),
-    (0xA652, 'M', 'ꙓ'),
-    (0xA653, 'V'),
-    (0xA654, 'M', 'ꙕ'),
-    (0xA655, 'V'),
-    (0xA656, 'M', 'ꙗ'),
-    (0xA657, 'V'),
-    (0xA658, 'M', 'ꙙ'),
-    (0xA659, 'V'),
-    (0xA65A, 'M', 'ꙛ'),
-    (0xA65B, 'V'),
-    (0xA65C, 'M', 'ꙝ'),
-    (0xA65D, 'V'),
-    (0xA65E, 'M', 'ꙟ'),
-    (0xA65F, 'V'),
-    (0xA660, 'M', 'ꙡ'),
-    (0xA661, 'V'),
-    (0xA662, 'M', 'ꙣ'),
-    (0xA663, 'V'),
-    (0xA664, 'M', 'ꙥ'),
-    (0xA665, 'V'),
-    (0xA666, 'M', 'ꙧ'),
-    (0xA667, 'V'),
-    (0xA668, 'M', 'ꙩ'),
-    (0xA669, 'V'),
-    (0xA66A, 'M', 'ꙫ'),
-    (0xA66B, 'V'),
-    (0xA66C, 'M', 'ꙭ'),
-    (0xA66D, 'V'),
-    (0xA680, 'M', 'ꚁ'),
-    (0xA681, 'V'),
-    (0xA682, 'M', 'ꚃ'),
-    (0xA683, 'V'),
-    (0xA684, 'M', 'ꚅ'),
-    (0xA685, 'V'),
-    (0xA686, 'M', 'ꚇ'),
-    (0xA687, 'V'),
-    (0xA688, 'M', 'ꚉ'),
-    (0xA689, 'V'),
-    (0xA68A, 'M', 'ꚋ'),
-    (0xA68B, 'V'),
-    (0xA68C, 'M', 'ꚍ'),
-    (0xA68D, 'V'),
-    ]
-
-def _seg_36() -> List[Union[Tuple[int, str], Tuple[int, str, str]]]:
-    return [
-    (0xA68E, 'M', 'ꚏ'),
-    (0xA68F, 'V'),
-    (0xA690, 'M', 'ꚑ'),
-    (0xA691, 'V'),
-    (0xA692, 'M', 'ꚓ'),
-    (0xA693, 'V'),
-    (0xA694, 'M', 'ꚕ'),
-    (0xA695, 'V'),
-    (0xA696, 'M', 'ꚗ'),
-    (0xA697, 'V'),
-    (0xA698, 'M', 'ꚙ'),
-    (0xA699, 'V'),
-    (0xA69A, 'M', 'ꚛ'),
-    (0xA69B, 'V'),
-    (0xA69C, 'M', 'ъ'),
-    (0xA69D, 'M', 'ь'),
-    (0xA69E, 'V'),
-    (0xA6F8, 'X'),
-    (0xA700, 'V'),
-    (0xA722, 'M', 'ꜣ'),
-    (0xA723, 'V'),
-    (0xA724, 'M', 'ꜥ'),
-    (0xA725, 'V'),
-    (0xA726, 'M', 'ꜧ'),
-    (0xA727, 'V'),
-    (0xA728, 'M', 'ꜩ'),
-    (0xA729, 'V'),
-    (0xA72A, 'M', 'ꜫ'),
-    (0xA72B, 'V'),
-    (0xA72C, 'M', 'ꜭ'),
-    (0xA72D, 'V'),
-    (0xA72E, 'M', 'ꜯ'),
-    (0xA72F, 'V'),
-    (0xA732, 'M', 'ꜳ'),
-    (0xA733, 'V'),
-    (0xA734, 'M', 'ꜵ'),
-    (0xA735, 'V'),
-    (0xA736, 'M', 'ꜷ'),
-    (0xA737, 'V'),
-    (0xA738, 'M', 'ꜹ'),
-    (0xA739, 'V'),
-    (0xA73A, 'M', 'ꜻ'),
-    (0xA73B, 'V'),
-    (0xA73C, 'M', 'ꜽ'),
-    (0xA73D, 'V'),
-    (0xA73E, 'M', 'ꜿ'),
-    (0xA73F, 'V'),
-    (0xA740, 'M', 'ꝁ'),
-    (0xA741, 'V'),
-    (0xA742, 'M', 'ꝃ'),
-    (0xA743, 'V'),
-    (0xA744, 'M', 'ꝅ'),
-    (0xA745, 'V'),
-    (0xA746, 'M', 'ꝇ'),
-    (0xA747, 'V'),
-    (0xA748, 'M', 'ꝉ'),
-    (0xA749, 'V'),
-    (0xA74A, 'M', 'ꝋ'),
-    (0xA74B, 'V'),
-    (0xA74C, 'M', 'ꝍ'),
-    (0xA74D, 'V'),
-    (0xA74E, 'M', 'ꝏ'),
-    (0xA74F, 'V'),
-    (0xA750, 'M', 'ꝑ'),
-    (0xA751, 'V'),
-    (0xA752, 'M', 'ꝓ'),
-    (0xA753, 'V'),
-    (0xA754, 'M', 'ꝕ'),
-    (0xA755, 'V'),
-    (0xA756, 'M', 'ꝗ'),
-    (0xA757, 'V'),
-    (0xA758, 'M', 'ꝙ'),
-    (0xA759, 'V'),
-    (0xA75A, 'M', 'ꝛ'),
-    (0xA75B, 'V'),
-    (0xA75C, 'M', 'ꝝ'),
-    (0xA75D, 'V'),
-    (0xA75E, 'M', 'ꝟ'),
-    (0xA75F, 'V'),
-    (0xA760, 'M', 'ꝡ'),
-    (0xA761, 'V'),
-    (0xA762, 'M', 'ꝣ'),
-    (0xA763, 'V'),
-    (0xA764, 'M', 'ꝥ'),
-    (0xA765, 'V'),
-    (0xA766, 'M', 'ꝧ'),
-    (0xA767, 'V'),
-    (0xA768, 'M', 'ꝩ'),
-    (0xA769, 'V'),
-    (0xA76A, 'M', 'ꝫ'),
-    (0xA76B, 'V'),
-    (0xA76C, 'M', 'ꝭ'),
-    (0xA76D, 'V'),
-    (0xA76E, 'M', 'ꝯ'),
-    (0xA76F, 'V'),
-    (0xA770, 'M', 'ꝯ'),
-    (0xA771, 'V'),
-    (0xA779, 'M', 'ꝺ'),
-    (0xA77A, 'V'),
-    (0xA77B, 'M', 'ꝼ'),
-    ]
-
-def _seg_37() -> List[Union[Tuple[int, str], Tuple[int, str, str]]]:
-    return [
-    (0xA77C, 'V'),
-    (0xA77D, 'M', 'ᵹ'),
-    (0xA77E, 'M', 'ꝿ'),
-    (0xA77F, 'V'),
-    (0xA780, 'M', 'ꞁ'),
-    (0xA781, 'V'),
-    (0xA782, 'M', 'ꞃ'),
-    (0xA783, 'V'),
-    (0xA784, 'M', 'ꞅ'),
-    (0xA785, 'V'),
-    (0xA786, 'M', 'ꞇ'),
-    (0xA787, 'V'),
-    (0xA78B, 'M', 'ꞌ'),
-    (0xA78C, 'V'),
-    (0xA78D, 'M', 'ɥ'),
-    (0xA78E, 'V'),
-    (0xA790, 'M', 'ꞑ'),
-    (0xA791, 'V'),
-    (0xA792, 'M', 'ꞓ'),
-    (0xA793, 'V'),
-    (0xA796, 'M', 'ꞗ'),
-    (0xA797, 'V'),
-    (0xA798, 'M', 'ꞙ'),
-    (0xA799, 'V'),
-    (0xA79A, 'M', 'ꞛ'),
-    (0xA79B, 'V'),
-    (0xA79C, 'M', 'ꞝ'),
-    (0xA79D, 'V'),
-    (0xA79E, 'M', 'ꞟ'),
-    (0xA79F, 'V'),
-    (0xA7A0, 'M', 'ꞡ'),
-    (0xA7A1, 'V'),
-    (0xA7A2, 'M', 'ꞣ'),
-    (0xA7A3, 'V'),
-    (0xA7A4, 'M', 'ꞥ'),
-    (0xA7A5, 'V'),
-    (0xA7A6, 'M', 'ꞧ'),
-    (0xA7A7, 'V'),
-    (0xA7A8, 'M', 'ꞩ'),
-    (0xA7A9, 'V'),
-    (0xA7AA, 'M', 'ɦ'),
-    (0xA7AB, 'M', 'ɜ'),
-    (0xA7AC, 'M', 'ɡ'),
-    (0xA7AD, 'M', 'ɬ'),
-    (0xA7AE, 'M', 'ɪ'),
-    (0xA7AF, 'V'),
-    (0xA7B0, 'M', 'ʞ'),
-    (0xA7B1, 'M', 'ʇ'),
-    (0xA7B2, 'M', 'ʝ'),
-    (0xA7B3, 'M', 'ꭓ'),
-    (0xA7B4, 'M', 'ꞵ'),
-    (0xA7B5, 'V'),
-    (0xA7B6, 'M', 'ꞷ'),
-    (0xA7B7, 'V'),
-    (0xA7B8, 'M', 'ꞹ'),
-    (0xA7B9, 'V'),
-    (0xA7BA, 'M', 'ꞻ'),
-    (0xA7BB, 'V'),
-    (0xA7BC, 'M', 'ꞽ'),
-    (0xA7BD, 'V'),
-    (0xA7BE, 'M', 'ꞿ'),
-    (0xA7BF, 'V'),
-    (0xA7C0, 'M', 'ꟁ'),
-    (0xA7C1, 'V'),
-    (0xA7C2, 'M', 'ꟃ'),
-    (0xA7C3, 'V'),
-    (0xA7C4, 'M', 'ꞔ'),
-    (0xA7C5, 'M', 'ʂ'),
-    (0xA7C6, 'M', 'ᶎ'),
-    (0xA7C7, 'M', 'ꟈ'),
-    (0xA7C8, 'V'),
-    (0xA7C9, 'M', 'ꟊ'),
-    (0xA7CA, 'V'),
-    (0xA7CB, 'X'),
-    (0xA7D0, 'M', 'ꟑ'),
-    (0xA7D1, 'V'),
-    (0xA7D2, 'X'),
-    (0xA7D3, 'V'),
-    (0xA7D4, 'X'),
-    (0xA7D5, 'V'),
-    (0xA7D6, 'M', 'ꟗ'),
-    (0xA7D7, 'V'),
-    (0xA7D8, 'M', 'ꟙ'),
-    (0xA7D9, 'V'),
-    (0xA7DA, 'X'),
-    (0xA7F2, 'M', 'c'),
-    (0xA7F3, 'M', 'f'),
-    (0xA7F4, 'M', 'q'),
-    (0xA7F5, 'M', 'ꟶ'),
-    (0xA7F6, 'V'),
-    (0xA7F8, 'M', 'ħ'),
-    (0xA7F9, 'M', 'œ'),
-    (0xA7FA, 'V'),
-    (0xA82D, 'X'),
-    (0xA830, 'V'),
-    (0xA83A, 'X'),
-    (0xA840, 'V'),
-    (0xA878, 'X'),
-    (0xA880, 'V'),
-    (0xA8C6, 'X'),
-    ]
-
-def _seg_38() -> List[Union[Tuple[int, str], Tuple[int, str, str]]]:
-    return [
-    (0xA8CE, 'V'),
-    (0xA8DA, 'X'),
-    (0xA8E0, 'V'),
-    (0xA954, 'X'),
-    (0xA95F, 'V'),
-    (0xA97D, 'X'),
-    (0xA980, 'V'),
-    (0xA9CE, 'X'),
-    (0xA9CF, 'V'),
-    (0xA9DA, 'X'),
-    (0xA9DE, 'V'),
-    (0xA9FF, 'X'),
-    (0xAA00, 'V'),
-    (0xAA37, 'X'),
-    (0xAA40, 'V'),
-    (0xAA4E, 'X'),
-    (0xAA50, 'V'),
-    (0xAA5A, 'X'),
-    (0xAA5C, 'V'),
-    (0xAAC3, 'X'),
-    (0xAADB, 'V'),
-    (0xAAF7, 'X'),
-    (0xAB01, 'V'),
-    (0xAB07, 'X'),
-    (0xAB09, 'V'),
-    (0xAB0F, 'X'),
-    (0xAB11, 'V'),
-    (0xAB17, 'X'),
-    (0xAB20, 'V'),
-    (0xAB27, 'X'),
-    (0xAB28, 'V'),
-    (0xAB2F, 'X'),
-    (0xAB30, 'V'),
-    (0xAB5C, 'M', 'ꜧ'),
-    (0xAB5D, 'M', 'ꬷ'),
-    (0xAB5E, 'M', 'ɫ'),
-    (0xAB5F, 'M', 'ꭒ'),
-    (0xAB60, 'V'),
-    (0xAB69, 'M', 'ʍ'),
-    (0xAB6A, 'V'),
-    (0xAB6C, 'X'),
-    (0xAB70, 'M', 'Ꭰ'),
-    (0xAB71, 'M', 'Ꭱ'),
-    (0xAB72, 'M', 'Ꭲ'),
-    (0xAB73, 'M', 'Ꭳ'),
-    (0xAB74, 'M', 'Ꭴ'),
-    (0xAB75, 'M', 'Ꭵ'),
-    (0xAB76, 'M', 'Ꭶ'),
-    (0xAB77, 'M', 'Ꭷ'),
-    (0xAB78, 'M', 'Ꭸ'),
-    (0xAB79, 'M', 'Ꭹ'),
-    (0xAB7A, 'M', 'Ꭺ'),
-    (0xAB7B, 'M', 'Ꭻ'),
-    (0xAB7C, 'M', 'Ꭼ'),
-    (0xAB7D, 'M', 'Ꭽ'),
-    (0xAB7E, 'M', 'Ꭾ'),
-    (0xAB7F, 'M', 'Ꭿ'),
-    (0xAB80, 'M', 'Ꮀ'),
-    (0xAB81, 'M', 'Ꮁ'),
-    (0xAB82, 'M', 'Ꮂ'),
-    (0xAB83, 'M', 'Ꮃ'),
-    (0xAB84, 'M', 'Ꮄ'),
-    (0xAB85, 'M', 'Ꮅ'),
-    (0xAB86, 'M', 'Ꮆ'),
-    (0xAB87, 'M', 'Ꮇ'),
-    (0xAB88, 'M', 'Ꮈ'),
-    (0xAB89, 'M', 'Ꮉ'),
-    (0xAB8A, 'M', 'Ꮊ'),
-    (0xAB8B, 'M', 'Ꮋ'),
-    (0xAB8C, 'M', 'Ꮌ'),
-    (0xAB8D, 'M', 'Ꮍ'),
-    (0xAB8E, 'M', 'Ꮎ'),
-    (0xAB8F, 'M', 'Ꮏ'),
-    (0xAB90, 'M', 'Ꮐ'),
-    (0xAB91, 'M', 'Ꮑ'),
-    (0xAB92, 'M', 'Ꮒ'),
-    (0xAB93, 'M', 'Ꮓ'),
-    (0xAB94, 'M', 'Ꮔ'),
-    (0xAB95, 'M', 'Ꮕ'),
-    (0xAB96, 'M', 'Ꮖ'),
-    (0xAB97, 'M', 'Ꮗ'),
-    (0xAB98, 'M', 'Ꮘ'),
-    (0xAB99, 'M', 'Ꮙ'),
-    (0xAB9A, 'M', 'Ꮚ'),
-    (0xAB9B, 'M', 'Ꮛ'),
-    (0xAB9C, 'M', 'Ꮜ'),
-    (0xAB9D, 'M', 'Ꮝ'),
-    (0xAB9E, 'M', 'Ꮞ'),
-    (0xAB9F, 'M', 'Ꮟ'),
-    (0xABA0, 'M', 'Ꮠ'),
-    (0xABA1, 'M', 'Ꮡ'),
-    (0xABA2, 'M', 'Ꮢ'),
-    (0xABA3, 'M', 'Ꮣ'),
-    (0xABA4, 'M', 'Ꮤ'),
-    (0xABA5, 'M', 'Ꮥ'),
-    (0xABA6, 'M', 'Ꮦ'),
-    (0xABA7, 'M', 'Ꮧ'),
-    (0xABA8, 'M', 'Ꮨ'),
-    (0xABA9, 'M', 'Ꮩ'),
-    (0xABAA, 'M', 'Ꮪ'),
-    ]
-
-def _seg_39() -> List[Union[Tuple[int, str], Tuple[int, str, str]]]:
-    return [
-    (0xABAB, 'M', 'Ꮫ'),
-    (0xABAC, 'M', 'Ꮬ'),
-    (0xABAD, 'M', 'Ꮭ'),
-    (0xABAE, 'M', 'Ꮮ'),
-    (0xABAF, 'M', 'Ꮯ'),
-    (0xABB0, 'M', 'Ꮰ'),
-    (0xABB1, 'M', 'Ꮱ'),
-    (0xABB2, 'M', 'Ꮲ'),
-    (0xABB3, 'M', 'Ꮳ'),
-    (0xABB4, 'M', 'Ꮴ'),
-    (0xABB5, 'M', 'Ꮵ'),
-    (0xABB6, 'M', 'Ꮶ'),
-    (0xABB7, 'M', 'Ꮷ'),
-    (0xABB8, 'M', 'Ꮸ'),
-    (0xABB9, 'M', 'Ꮹ'),
-    (0xABBA, 'M', 'Ꮺ'),
-    (0xABBB, 'M', 'Ꮻ'),
-    (0xABBC, 'M', 'Ꮼ'),
-    (0xABBD, 'M', 'Ꮽ'),
-    (0xABBE, 'M', 'Ꮾ'),
-    (0xABBF, 'M', 'Ꮿ'),
-    (0xABC0, 'V'),
-    (0xABEE, 'X'),
-    (0xABF0, 'V'),
-    (0xABFA, 'X'),
-    (0xAC00, 'V'),
-    (0xD7A4, 'X'),
-    (0xD7B0, 'V'),
-    (0xD7C7, 'X'),
-    (0xD7CB, 'V'),
-    (0xD7FC, 'X'),
-    (0xF900, 'M', '豈'),
-    (0xF901, 'M', '更'),
-    (0xF902, 'M', '車'),
-    (0xF903, 'M', '賈'),
-    (0xF904, 'M', '滑'),
-    (0xF905, 'M', '串'),
-    (0xF906, 'M', '句'),
-    (0xF907, 'M', '龜'),
-    (0xF909, 'M', '契'),
-    (0xF90A, 'M', '金'),
-    (0xF90B, 'M', '喇'),
-    (0xF90C, 'M', '奈'),
-    (0xF90D, 'M', '懶'),
-    (0xF90E, 'M', '癩'),
-    (0xF90F, 'M', '羅'),
-    (0xF910, 'M', '蘿'),
-    (0xF911, 'M', '螺'),
-    (0xF912, 'M', '裸'),
-    (0xF913, 'M', '邏'),
-    (0xF914, 'M', '樂'),
-    (0xF915, 'M', '洛'),
-    (0xF916, 'M', '烙'),
-    (0xF917, 'M', '珞'),
-    (0xF918, 'M', '落'),
-    (0xF919, 'M', '酪'),
-    (0xF91A, 'M', '駱'),
-    (0xF91B, 'M', '亂'),
-    (0xF91C, 'M', '卵'),
-    (0xF91D, 'M', '欄'),
-    (0xF91E, 'M', '爛'),
-    (0xF91F, 'M', '蘭'),
-    (0xF920, 'M', '鸞'),
-    (0xF921, 'M', '嵐'),
-    (0xF922, 'M', '濫'),
-    (0xF923, 'M', '藍'),
-    (0xF924, 'M', '襤'),
-    (0xF925, 'M', '拉'),
-    (0xF926, 'M', '臘'),
-    (0xF927, 'M', '蠟'),
-    (0xF928, 'M', '廊'),
-    (0xF929, 'M', '朗'),
-    (0xF92A, 'M', '浪'),
-    (0xF92B, 'M', '狼'),
-    (0xF92C, 'M', '郎'),
-    (0xF92D, 'M', '來'),
-    (0xF92E, 'M', '冷'),
-    (0xF92F, 'M', '勞'),
-    (0xF930, 'M', '擄'),
-    (0xF931, 'M', '櫓'),
-    (0xF932, 'M', '爐'),
-    (0xF933, 'M', '盧'),
-    (0xF934, 'M', '老'),
-    (0xF935, 'M', '蘆'),
-    (0xF936, 'M', '虜'),
-    (0xF937, 'M', '路'),
-    (0xF938, 'M', '露'),
-    (0xF939, 'M', '魯'),
-    (0xF93A, 'M', '鷺'),
-    (0xF93B, 'M', '碌'),
-    (0xF93C, 'M', '祿'),
-    (0xF93D, 'M', '綠'),
-    (0xF93E, 'M', '菉'),
-    (0xF93F, 'M', '錄'),
-    (0xF940, 'M', '鹿'),
-    (0xF941, 'M', '論'),
-    (0xF942, 'M', '壟'),
-    (0xF943, 'M', '弄'),
-    (0xF944, 'M', '籠'),
-    (0xF945, 'M', '聾'),
-    ]
-
-def _seg_40() -> List[Union[Tuple[int, str], Tuple[int, str, str]]]:
-    return [
-    (0xF946, 'M', '牢'),
-    (0xF947, 'M', '磊'),
-    (0xF948, 'M', '賂'),
-    (0xF949, 'M', '雷'),
-    (0xF94A, 'M', '壘'),
-    (0xF94B, 'M', '屢'),
-    (0xF94C, 'M', '樓'),
-    (0xF94D, 'M', '淚'),
-    (0xF94E, 'M', '漏'),
-    (0xF94F, 'M', '累'),
-    (0xF950, 'M', '縷'),
-    (0xF951, 'M', '陋'),
-    (0xF952, 'M', '勒'),
-    (0xF953, 'M', '肋'),
-    (0xF954, 'M', '凜'),
-    (0xF955, 'M', '凌'),
-    (0xF956, 'M', '稜'),
-    (0xF957, 'M', '綾'),
-    (0xF958, 'M', '菱'),
-    (0xF959, 'M', '陵'),
-    (0xF95A, 'M', '讀'),
-    (0xF95B, 'M', '拏'),
-    (0xF95C, 'M', '樂'),
-    (0xF95D, 'M', '諾'),
-    (0xF95E, 'M', '丹'),
-    (0xF95F, 'M', '寧'),
-    (0xF960, 'M', '怒'),
-    (0xF961, 'M', '率'),
-    (0xF962, 'M', '異'),
-    (0xF963, 'M', '北'),
-    (0xF964, 'M', '磻'),
-    (0xF965, 'M', '便'),
-    (0xF966, 'M', '復'),
-    (0xF967, 'M', '不'),
-    (0xF968, 'M', '泌'),
-    (0xF969, 'M', '數'),
-    (0xF96A, 'M', '索'),
-    (0xF96B, 'M', '參'),
-    (0xF96C, 'M', '塞'),
-    (0xF96D, 'M', '省'),
-    (0xF96E, 'M', '葉'),
-    (0xF96F, 'M', '說'),
-    (0xF970, 'M', '殺'),
-    (0xF971, 'M', '辰'),
-    (0xF972, 'M', '沈'),
-    (0xF973, 'M', '拾'),
-    (0xF974, 'M', '若'),
-    (0xF975, 'M', '掠'),
-    (0xF976, 'M', '略'),
-    (0xF977, 'M', '亮'),
-    (0xF978, 'M', '兩'),
-    (0xF979, 'M', '凉'),
-    (0xF97A, 'M', '梁'),
-    (0xF97B, 'M', '糧'),
-    (0xF97C, 'M', '良'),
-    (0xF97D, 'M', '諒'),
-    (0xF97E, 'M', '量'),
-    (0xF97F, 'M', '勵'),
-    (0xF980, 'M', '呂'),
-    (0xF981, 'M', '女'),
-    (0xF982, 'M', '廬'),
-    (0xF983, 'M', '旅'),
-    (0xF984, 'M', '濾'),
-    (0xF985, 'M', '礪'),
-    (0xF986, 'M', '閭'),
-    (0xF987, 'M', '驪'),
-    (0xF988, 'M', '麗'),
-    (0xF989, 'M', '黎'),
-    (0xF98A, 'M', '力'),
-    (0xF98B, 'M', '曆'),
-    (0xF98C, 'M', '歷'),
-    (0xF98D, 'M', '轢'),
-    (0xF98E, 'M', '年'),
-    (0xF98F, 'M', '憐'),
-    (0xF990, 'M', '戀'),
-    (0xF991, 'M', '撚'),
-    (0xF992, 'M', '漣'),
-    (0xF993, 'M', '煉'),
-    (0xF994, 'M', '璉'),
-    (0xF995, 'M', '秊'),
-    (0xF996, 'M', '練'),
-    (0xF997, 'M', '聯'),
-    (0xF998, 'M', '輦'),
-    (0xF999, 'M', '蓮'),
-    (0xF99A, 'M', '連'),
-    (0xF99B, 'M', '鍊'),
-    (0xF99C, 'M', '列'),
-    (0xF99D, 'M', '劣'),
-    (0xF99E, 'M', '咽'),
-    (0xF99F, 'M', '烈'),
-    (0xF9A0, 'M', '裂'),
-    (0xF9A1, 'M', '說'),
-    (0xF9A2, 'M', '廉'),
-    (0xF9A3, 'M', '念'),
-    (0xF9A4, 'M', '捻'),
-    (0xF9A5, 'M', '殮'),
-    (0xF9A6, 'M', '簾'),
-    (0xF9A7, 'M', '獵'),
-    (0xF9A8, 'M', '令'),
-    (0xF9A9, 'M', '囹'),
-    ]
-
-def _seg_41() -> List[Union[Tuple[int, str], Tuple[int, str, str]]]:
-    return [
-    (0xF9AA, 'M', '寧'),
-    (0xF9AB, 'M', '嶺'),
-    (0xF9AC, 'M', '怜'),
-    (0xF9AD, 'M', '玲'),
-    (0xF9AE, 'M', '瑩'),
-    (0xF9AF, 'M', '羚'),
-    (0xF9B0, 'M', '聆'),
-    (0xF9B1, 'M', '鈴'),
-    (0xF9B2, 'M', '零'),
-    (0xF9B3, 'M', '靈'),
-    (0xF9B4, 'M', '領'),
-    (0xF9B5, 'M', '例'),
-    (0xF9B6, 'M', '禮'),
-    (0xF9B7, 'M', '醴'),
-    (0xF9B8, 'M', '隸'),
-    (0xF9B9, 'M', '惡'),
-    (0xF9BA, 'M', '了'),
-    (0xF9BB, 'M', '僚'),
-    (0xF9BC, 'M', '寮'),
-    (0xF9BD, 'M', '尿'),
-    (0xF9BE, 'M', '料'),
-    (0xF9BF, 'M', '樂'),
-    (0xF9C0, 'M', '燎'),
-    (0xF9C1, 'M', '療'),
-    (0xF9C2, 'M', '蓼'),
-    (0xF9C3, 'M', '遼'),
-    (0xF9C4, 'M', '龍'),
-    (0xF9C5, 'M', '暈'),
-    (0xF9C6, 'M', '阮'),
-    (0xF9C7, 'M', '劉'),
-    (0xF9C8, 'M', '杻'),
-    (0xF9C9, 'M', '柳'),
-    (0xF9CA, 'M', '流'),
-    (0xF9CB, 'M', '溜'),
-    (0xF9CC, 'M', '琉'),
-    (0xF9CD, 'M', '留'),
-    (0xF9CE, 'M', '硫'),
-    (0xF9CF, 'M', '紐'),
-    (0xF9D0, 'M', '類'),
-    (0xF9D1, 'M', '六'),
-    (0xF9D2, 'M', '戮'),
-    (0xF9D3, 'M', '陸'),
-    (0xF9D4, 'M', '倫'),
-    (0xF9D5, 'M', '崙'),
-    (0xF9D6, 'M', '淪'),
-    (0xF9D7, 'M', '輪'),
-    (0xF9D8, 'M', '律'),
-    (0xF9D9, 'M', '慄'),
-    (0xF9DA, 'M', '栗'),
-    (0xF9DB, 'M', '率'),
-    (0xF9DC, 'M', '隆'),
-    (0xF9DD, 'M', '利'),
-    (0xF9DE, 'M', '吏'),
-    (0xF9DF, 'M', '履'),
-    (0xF9E0, 'M', '易'),
-    (0xF9E1, 'M', '李'),
-    (0xF9E2, 'M', '梨'),
-    (0xF9E3, 'M', '泥'),
-    (0xF9E4, 'M', '理'),
-    (0xF9E5, 'M', '痢'),
-    (0xF9E6, 'M', '罹'),
-    (0xF9E7, 'M', '裏'),
-    (0xF9E8, 'M', '裡'),
-    (0xF9E9, 'M', '里'),
-    (0xF9EA, 'M', '離'),
-    (0xF9EB, 'M', '匿'),
-    (0xF9EC, 'M', '溺'),
-    (0xF9ED, 'M', '吝'),
-    (0xF9EE, 'M', '燐'),
-    (0xF9EF, 'M', '璘'),
-    (0xF9F0, 'M', '藺'),
-    (0xF9F1, 'M', '隣'),
-    (0xF9F2, 'M', '鱗'),
-    (0xF9F3, 'M', '麟'),
-    (0xF9F4, 'M', '林'),
-    (0xF9F5, 'M', '淋'),
-    (0xF9F6, 'M', '臨'),
-    (0xF9F7, 'M', '立'),
-    (0xF9F8, 'M', '笠'),
-    (0xF9F9, 'M', '粒'),
-    (0xF9FA, 'M', '狀'),
-    (0xF9FB, 'M', '炙'),
-    (0xF9FC, 'M', '識'),
-    (0xF9FD, 'M', '什'),
-    (0xF9FE, 'M', '茶'),
-    (0xF9FF, 'M', '刺'),
-    (0xFA00, 'M', '切'),
-    (0xFA01, 'M', '度'),
-    (0xFA02, 'M', '拓'),
-    (0xFA03, 'M', '糖'),
-    (0xFA04, 'M', '宅'),
-    (0xFA05, 'M', '洞'),
-    (0xFA06, 'M', '暴'),
-    (0xFA07, 'M', '輻'),
-    (0xFA08, 'M', '行'),
-    (0xFA09, 'M', '降'),
-    (0xFA0A, 'M', '見'),
-    (0xFA0B, 'M', '廓'),
-    (0xFA0C, 'M', '兀'),
-    (0xFA0D, 'M', '嗀'),
-    ]
-
-def _seg_42() -> List[Union[Tuple[int, str], Tuple[int, str, str]]]:
-    return [
-    (0xFA0E, 'V'),
-    (0xFA10, 'M', '塚'),
-    (0xFA11, 'V'),
-    (0xFA12, 'M', '晴'),
-    (0xFA13, 'V'),
-    (0xFA15, 'M', '凞'),
-    (0xFA16, 'M', '猪'),
-    (0xFA17, 'M', '益'),
-    (0xFA18, 'M', '礼'),
-    (0xFA19, 'M', '神'),
-    (0xFA1A, 'M', '祥'),
-    (0xFA1B, 'M', '福'),
-    (0xFA1C, 'M', '靖'),
-    (0xFA1D, 'M', '精'),
-    (0xFA1E, 'M', '羽'),
-    (0xFA1F, 'V'),
-    (0xFA20, 'M', '蘒'),
-    (0xFA21, 'V'),
-    (0xFA22, 'M', '諸'),
-    (0xFA23, 'V'),
-    (0xFA25, 'M', '逸'),
-    (0xFA26, 'M', '都'),
-    (0xFA27, 'V'),
-    (0xFA2A, 'M', '飯'),
-    (0xFA2B, 'M', '飼'),
-    (0xFA2C, 'M', '館'),
-    (0xFA2D, 'M', '鶴'),
-    (0xFA2E, 'M', '郞'),
-    (0xFA2F, 'M', '隷'),
-    (0xFA30, 'M', '侮'),
-    (0xFA31, 'M', '僧'),
-    (0xFA32, 'M', '免'),
-    (0xFA33, 'M', '勉'),
-    (0xFA34, 'M', '勤'),
-    (0xFA35, 'M', '卑'),
-    (0xFA36, 'M', '喝'),
-    (0xFA37, 'M', '嘆'),
-    (0xFA38, 'M', '器'),
-    (0xFA39, 'M', '塀'),
-    (0xFA3A, 'M', '墨'),
-    (0xFA3B, 'M', '層'),
-    (0xFA3C, 'M', '屮'),
-    (0xFA3D, 'M', '悔'),
-    (0xFA3E, 'M', '慨'),
-    (0xFA3F, 'M', '憎'),
-    (0xFA40, 'M', '懲'),
-    (0xFA41, 'M', '敏'),
-    (0xFA42, 'M', '既'),
-    (0xFA43, 'M', '暑'),
-    (0xFA44, 'M', '梅'),
-    (0xFA45, 'M', '海'),
-    (0xFA46, 'M', '渚'),
-    (0xFA47, 'M', '漢'),
-    (0xFA48, 'M', '煮'),
-    (0xFA49, 'M', '爫'),
-    (0xFA4A, 'M', '琢'),
-    (0xFA4B, 'M', '碑'),
-    (0xFA4C, 'M', '社'),
-    (0xFA4D, 'M', '祉'),
-    (0xFA4E, 'M', '祈'),
-    (0xFA4F, 'M', '祐'),
-    (0xFA50, 'M', '祖'),
-    (0xFA51, 'M', '祝'),
-    (0xFA52, 'M', '禍'),
-    (0xFA53, 'M', '禎'),
-    (0xFA54, 'M', '穀'),
-    (0xFA55, 'M', '突'),
-    (0xFA56, 'M', '節'),
-    (0xFA57, 'M', '練'),
-    (0xFA58, 'M', '縉'),
-    (0xFA59, 'M', '繁'),
-    (0xFA5A, 'M', '署'),
-    (0xFA5B, 'M', '者'),
-    (0xFA5C, 'M', '臭'),
-    (0xFA5D, 'M', '艹'),
-    (0xFA5F, 'M', '著'),
-    (0xFA60, 'M', '褐'),
-    (0xFA61, 'M', '視'),
-    (0xFA62, 'M', '謁'),
-    (0xFA63, 'M', '謹'),
-    (0xFA64, 'M', '賓'),
-    (0xFA65, 'M', '贈'),
-    (0xFA66, 'M', '辶'),
-    (0xFA67, 'M', '逸'),
-    (0xFA68, 'M', '難'),
-    (0xFA69, 'M', '響'),
-    (0xFA6A, 'M', '頻'),
-    (0xFA6B, 'M', '恵'),
-    (0xFA6C, 'M', '𤋮'),
-    (0xFA6D, 'M', '舘'),
-    (0xFA6E, 'X'),
-    (0xFA70, 'M', '並'),
-    (0xFA71, 'M', '况'),
-    (0xFA72, 'M', '全'),
-    (0xFA73, 'M', '侀'),
-    (0xFA74, 'M', '充'),
-    (0xFA75, 'M', '冀'),
-    (0xFA76, 'M', '勇'),
-    (0xFA77, 'M', '勺'),
-    (0xFA78, 'M', '喝'),
-    ]
-
-def _seg_43() -> List[Union[Tuple[int, str], Tuple[int, str, str]]]:
-    return [
-    (0xFA79, 'M', '啕'),
-    (0xFA7A, 'M', '喙'),
-    (0xFA7B, 'M', '嗢'),
-    (0xFA7C, 'M', '塚'),
-    (0xFA7D, 'M', '墳'),
-    (0xFA7E, 'M', '奄'),
-    (0xFA7F, 'M', '奔'),
-    (0xFA80, 'M', '婢'),
-    (0xFA81, 'M', '嬨'),
-    (0xFA82, 'M', '廒'),
-    (0xFA83, 'M', '廙'),
-    (0xFA84, 'M', '彩'),
-    (0xFA85, 'M', '徭'),
-    (0xFA86, 'M', '惘'),
-    (0xFA87, 'M', '慎'),
-    (0xFA88, 'M', '愈'),
-    (0xFA89, 'M', '憎'),
-    (0xFA8A, 'M', '慠'),
-    (0xFA8B, 'M', '懲'),
-    (0xFA8C, 'M', '戴'),
-    (0xFA8D, 'M', '揄'),
-    (0xFA8E, 'M', '搜'),
-    (0xFA8F, 'M', '摒'),
-    (0xFA90, 'M', '敖'),
-    (0xFA91, 'M', '晴'),
-    (0xFA92, 'M', '朗'),
-    (0xFA93, 'M', '望'),
-    (0xFA94, 'M', '杖'),
-    (0xFA95, 'M', '歹'),
-    (0xFA96, 'M', '殺'),
-    (0xFA97, 'M', '流'),
-    (0xFA98, 'M', '滛'),
-    (0xFA99, 'M', '滋'),
-    (0xFA9A, 'M', '漢'),
-    (0xFA9B, 'M', '瀞'),
-    (0xFA9C, 'M', '煮'),
-    (0xFA9D, 'M', '瞧'),
-    (0xFA9E, 'M', '爵'),
-    (0xFA9F, 'M', '犯'),
-    (0xFAA0, 'M', '猪'),
-    (0xFAA1, 'M', '瑱'),
-    (0xFAA2, 'M', '甆'),
-    (0xFAA3, 'M', '画'),
-    (0xFAA4, 'M', '瘝'),
-    (0xFAA5, 'M', '瘟'),
-    (0xFAA6, 'M', '益'),
-    (0xFAA7, 'M', '盛'),
-    (0xFAA8, 'M', '直'),
-    (0xFAA9, 'M', '睊'),
-    (0xFAAA, 'M', '着'),
-    (0xFAAB, 'M', '磌'),
-    (0xFAAC, 'M', '窱'),
-    (0xFAAD, 'M', '節'),
-    (0xFAAE, 'M', '类'),
-    (0xFAAF, 'M', '絛'),
-    (0xFAB0, 'M', '練'),
-    (0xFAB1, 'M', '缾'),
-    (0xFAB2, 'M', '者'),
-    (0xFAB3, 'M', '荒'),
-    (0xFAB4, 'M', '華'),
-    (0xFAB5, 'M', '蝹'),
-    (0xFAB6, 'M', '襁'),
-    (0xFAB7, 'M', '覆'),
-    (0xFAB8, 'M', '視'),
-    (0xFAB9, 'M', '調'),
-    (0xFABA, 'M', '諸'),
-    (0xFABB, 'M', '請'),
-    (0xFABC, 'M', '謁'),
-    (0xFABD, 'M', '諾'),
-    (0xFABE, 'M', '諭'),
-    (0xFABF, 'M', '謹'),
-    (0xFAC0, 'M', '變'),
-    (0xFAC1, 'M', '贈'),
-    (0xFAC2, 'M', '輸'),
-    (0xFAC3, 'M', '遲'),
-    (0xFAC4, 'M', '醙'),
-    (0xFAC5, 'M', '鉶'),
-    (0xFAC6, 'M', '陼'),
-    (0xFAC7, 'M', '難'),
-    (0xFAC8, 'M', '靖'),
-    (0xFAC9, 'M', '韛'),
-    (0xFACA, 'M', '響'),
-    (0xFACB, 'M', '頋'),
-    (0xFACC, 'M', '頻'),
-    (0xFACD, 'M', '鬒'),
-    (0xFACE, 'M', '龜'),
-    (0xFACF, 'M', '𢡊'),
-    (0xFAD0, 'M', '𢡄'),
-    (0xFAD1, 'M', '𣏕'),
-    (0xFAD2, 'M', '㮝'),
-    (0xFAD3, 'M', '䀘'),
-    (0xFAD4, 'M', '䀹'),
-    (0xFAD5, 'M', '𥉉'),
-    (0xFAD6, 'M', '𥳐'),
-    (0xFAD7, 'M', '𧻓'),
-    (0xFAD8, 'M', '齃'),
-    (0xFAD9, 'M', '龎'),
-    (0xFADA, 'X'),
-    (0xFB00, 'M', 'ff'),
-    (0xFB01, 'M', 'fi'),
-    ]
-
-def _seg_44() -> List[Union[Tuple[int, str], Tuple[int, str, str]]]:
-    return [
-    (0xFB02, 'M', 'fl'),
-    (0xFB03, 'M', 'ffi'),
-    (0xFB04, 'M', 'ffl'),
-    (0xFB05, 'M', 'st'),
-    (0xFB07, 'X'),
-    (0xFB13, 'M', 'մն'),
-    (0xFB14, 'M', 'մե'),
-    (0xFB15, 'M', 'մի'),
-    (0xFB16, 'M', 'վն'),
-    (0xFB17, 'M', 'մխ'),
-    (0xFB18, 'X'),
-    (0xFB1D, 'M', 'יִ'),
-    (0xFB1E, 'V'),
-    (0xFB1F, 'M', 'ײַ'),
-    (0xFB20, 'M', 'ע'),
-    (0xFB21, 'M', 'א'),
-    (0xFB22, 'M', 'ד'),
-    (0xFB23, 'M', 'ה'),
-    (0xFB24, 'M', 'כ'),
-    (0xFB25, 'M', 'ל'),
-    (0xFB26, 'M', 'ם'),
-    (0xFB27, 'M', 'ר'),
-    (0xFB28, 'M', 'ת'),
-    (0xFB29, '3', '+'),
-    (0xFB2A, 'M', 'שׁ'),
-    (0xFB2B, 'M', 'שׂ'),
-    (0xFB2C, 'M', 'שּׁ'),
-    (0xFB2D, 'M', 'שּׂ'),
-    (0xFB2E, 'M', 'אַ'),
-    (0xFB2F, 'M', 'אָ'),
-    (0xFB30, 'M', 'אּ'),
-    (0xFB31, 'M', 'בּ'),
-    (0xFB32, 'M', 'גּ'),
-    (0xFB33, 'M', 'דּ'),
-    (0xFB34, 'M', 'הּ'),
-    (0xFB35, 'M', 'וּ'),
-    (0xFB36, 'M', 'זּ'),
-    (0xFB37, 'X'),
-    (0xFB38, 'M', 'טּ'),
-    (0xFB39, 'M', 'יּ'),
-    (0xFB3A, 'M', 'ךּ'),
-    (0xFB3B, 'M', 'כּ'),
-    (0xFB3C, 'M', 'לּ'),
-    (0xFB3D, 'X'),
-    (0xFB3E, 'M', 'מּ'),
-    (0xFB3F, 'X'),
-    (0xFB40, 'M', 'נּ'),
-    (0xFB41, 'M', 'סּ'),
-    (0xFB42, 'X'),
-    (0xFB43, 'M', 'ףּ'),
-    (0xFB44, 'M', 'פּ'),
-    (0xFB45, 'X'),
-    (0xFB46, 'M', 'צּ'),
-    (0xFB47, 'M', 'קּ'),
-    (0xFB48, 'M', 'רּ'),
-    (0xFB49, 'M', 'שּ'),
-    (0xFB4A, 'M', 'תּ'),
-    (0xFB4B, 'M', 'וֹ'),
-    (0xFB4C, 'M', 'בֿ'),
-    (0xFB4D, 'M', 'כֿ'),
-    (0xFB4E, 'M', 'פֿ'),
-    (0xFB4F, 'M', 'אל'),
-    (0xFB50, 'M', 'ٱ'),
-    (0xFB52, 'M', 'ٻ'),
-    (0xFB56, 'M', 'پ'),
-    (0xFB5A, 'M', 'ڀ'),
-    (0xFB5E, 'M', 'ٺ'),
-    (0xFB62, 'M', 'ٿ'),
-    (0xFB66, 'M', 'ٹ'),
-    (0xFB6A, 'M', 'ڤ'),
-    (0xFB6E, 'M', 'ڦ'),
-    (0xFB72, 'M', 'ڄ'),
-    (0xFB76, 'M', 'ڃ'),
-    (0xFB7A, 'M', 'چ'),
-    (0xFB7E, 'M', 'ڇ'),
-    (0xFB82, 'M', 'ڍ'),
-    (0xFB84, 'M', 'ڌ'),
-    (0xFB86, 'M', 'ڎ'),
-    (0xFB88, 'M', 'ڈ'),
-    (0xFB8A, 'M', 'ژ'),
-    (0xFB8C, 'M', 'ڑ'),
-    (0xFB8E, 'M', 'ک'),
-    (0xFB92, 'M', 'گ'),
-    (0xFB96, 'M', 'ڳ'),
-    (0xFB9A, 'M', 'ڱ'),
-    (0xFB9E, 'M', 'ں'),
-    (0xFBA0, 'M', 'ڻ'),
-    (0xFBA4, 'M', 'ۀ'),
-    (0xFBA6, 'M', 'ہ'),
-    (0xFBAA, 'M', 'ھ'),
-    (0xFBAE, 'M', 'ے'),
-    (0xFBB0, 'M', 'ۓ'),
-    (0xFBB2, 'V'),
-    (0xFBC3, 'X'),
-    (0xFBD3, 'M', 'ڭ'),
-    (0xFBD7, 'M', 'ۇ'),
-    (0xFBD9, 'M', 'ۆ'),
-    (0xFBDB, 'M', 'ۈ'),
-    (0xFBDD, 'M', 'ۇٴ'),
-    (0xFBDE, 'M', 'ۋ'),
-    ]
-
-def _seg_45() -> List[Union[Tuple[int, str], Tuple[int, str, str]]]:
-    return [
-    (0xFBE0, 'M', 'ۅ'),
-    (0xFBE2, 'M', 'ۉ'),
-    (0xFBE4, 'M', 'ې'),
-    (0xFBE8, 'M', 'ى'),
-    (0xFBEA, 'M', 'ئا'),
-    (0xFBEC, 'M', 'ئە'),
-    (0xFBEE, 'M', 'ئو'),
-    (0xFBF0, 'M', 'ئۇ'),
-    (0xFBF2, 'M', 'ئۆ'),
-    (0xFBF4, 'M', 'ئۈ'),
-    (0xFBF6, 'M', 'ئې'),
-    (0xFBF9, 'M', 'ئى'),
-    (0xFBFC, 'M', 'ی'),
-    (0xFC00, 'M', 'ئج'),
-    (0xFC01, 'M', 'ئح'),
-    (0xFC02, 'M', 'ئم'),
-    (0xFC03, 'M', 'ئى'),
-    (0xFC04, 'M', 'ئي'),
-    (0xFC05, 'M', 'بج'),
-    (0xFC06, 'M', 'بح'),
-    (0xFC07, 'M', 'بخ'),
-    (0xFC08, 'M', 'بم'),
-    (0xFC09, 'M', 'بى'),
-    (0xFC0A, 'M', 'بي'),
-    (0xFC0B, 'M', 'تج'),
-    (0xFC0C, 'M', 'تح'),
-    (0xFC0D, 'M', 'تخ'),
-    (0xFC0E, 'M', 'تم'),
-    (0xFC0F, 'M', 'تى'),
-    (0xFC10, 'M', 'تي'),
-    (0xFC11, 'M', 'ثج'),
-    (0xFC12, 'M', 'ثم'),
-    (0xFC13, 'M', 'ثى'),
-    (0xFC14, 'M', 'ثي'),
-    (0xFC15, 'M', 'جح'),
-    (0xFC16, 'M', 'جم'),
-    (0xFC17, 'M', 'حج'),
-    (0xFC18, 'M', 'حم'),
-    (0xFC19, 'M', 'خج'),
-    (0xFC1A, 'M', 'خح'),
-    (0xFC1B, 'M', 'خم'),
-    (0xFC1C, 'M', 'سج'),
-    (0xFC1D, 'M', 'سح'),
-    (0xFC1E, 'M', 'سخ'),
-    (0xFC1F, 'M', 'سم'),
-    (0xFC20, 'M', 'صح'),
-    (0xFC21, 'M', 'صم'),
-    (0xFC22, 'M', 'ضج'),
-    (0xFC23, 'M', 'ضح'),
-    (0xFC24, 'M', 'ضخ'),
-    (0xFC25, 'M', 'ضم'),
-    (0xFC26, 'M', 'طح'),
-    (0xFC27, 'M', 'طم'),
-    (0xFC28, 'M', 'ظم'),
-    (0xFC29, 'M', 'عج'),
-    (0xFC2A, 'M', 'عم'),
-    (0xFC2B, 'M', 'غج'),
-    (0xFC2C, 'M', 'غم'),
-    (0xFC2D, 'M', 'فج'),
-    (0xFC2E, 'M', 'فح'),
-    (0xFC2F, 'M', 'فخ'),
-    (0xFC30, 'M', 'فم'),
-    (0xFC31, 'M', 'فى'),
-    (0xFC32, 'M', 'في'),
-    (0xFC33, 'M', 'قح'),
-    (0xFC34, 'M', 'قم'),
-    (0xFC35, 'M', 'قى'),
-    (0xFC36, 'M', 'قي'),
-    (0xFC37, 'M', 'كا'),
-    (0xFC38, 'M', 'كج'),
-    (0xFC39, 'M', 'كح'),
-    (0xFC3A, 'M', 'كخ'),
-    (0xFC3B, 'M', 'كل'),
-    (0xFC3C, 'M', 'كم'),
-    (0xFC3D, 'M', 'كى'),
-    (0xFC3E, 'M', 'كي'),
-    (0xFC3F, 'M', 'لج'),
-    (0xFC40, 'M', 'لح'),
-    (0xFC41, 'M', 'لخ'),
-    (0xFC42, 'M', 'لم'),
-    (0xFC43, 'M', 'لى'),
-    (0xFC44, 'M', 'لي'),
-    (0xFC45, 'M', 'مج'),
-    (0xFC46, 'M', 'مح'),
-    (0xFC47, 'M', 'مخ'),
-    (0xFC48, 'M', 'مم'),
-    (0xFC49, 'M', 'مى'),
-    (0xFC4A, 'M', 'مي'),
-    (0xFC4B, 'M', 'نج'),
-    (0xFC4C, 'M', 'نح'),
-    (0xFC4D, 'M', 'نخ'),
-    (0xFC4E, 'M', 'نم'),
-    (0xFC4F, 'M', 'نى'),
-    (0xFC50, 'M', 'ني'),
-    (0xFC51, 'M', 'هج'),
-    (0xFC52, 'M', 'هم'),
-    (0xFC53, 'M', 'هى'),
-    (0xFC54, 'M', 'هي'),
-    (0xFC55, 'M', 'يج'),
-    (0xFC56, 'M', 'يح'),
-    ]
-
-def _seg_46() -> List[Union[Tuple[int, str], Tuple[int, str, str]]]:
-    return [
-    (0xFC57, 'M', 'يخ'),
-    (0xFC58, 'M', 'يم'),
-    (0xFC59, 'M', 'يى'),
-    (0xFC5A, 'M', 'يي'),
-    (0xFC5B, 'M', 'ذٰ'),
-    (0xFC5C, 'M', 'رٰ'),
-    (0xFC5D, 'M', 'ىٰ'),
-    (0xFC5E, '3', ' ٌّ'),
-    (0xFC5F, '3', ' ٍّ'),
-    (0xFC60, '3', ' َّ'),
-    (0xFC61, '3', ' ُّ'),
-    (0xFC62, '3', ' ِّ'),
-    (0xFC63, '3', ' ّٰ'),
-    (0xFC64, 'M', 'ئر'),
-    (0xFC65, 'M', 'ئز'),
-    (0xFC66, 'M', 'ئم'),
-    (0xFC67, 'M', 'ئن'),
-    (0xFC68, 'M', 'ئى'),
-    (0xFC69, 'M', 'ئي'),
-    (0xFC6A, 'M', 'بر'),
-    (0xFC6B, 'M', 'بز'),
-    (0xFC6C, 'M', 'بم'),
-    (0xFC6D, 'M', 'بن'),
-    (0xFC6E, 'M', 'بى'),
-    (0xFC6F, 'M', 'بي'),
-    (0xFC70, 'M', 'تر'),
-    (0xFC71, 'M', 'تز'),
-    (0xFC72, 'M', 'تم'),
-    (0xFC73, 'M', 'تن'),
-    (0xFC74, 'M', 'تى'),
-    (0xFC75, 'M', 'تي'),
-    (0xFC76, 'M', 'ثر'),
-    (0xFC77, 'M', 'ثز'),
-    (0xFC78, 'M', 'ثم'),
-    (0xFC79, 'M', 'ثن'),
-    (0xFC7A, 'M', 'ثى'),
-    (0xFC7B, 'M', 'ثي'),
-    (0xFC7C, 'M', 'فى'),
-    (0xFC7D, 'M', 'في'),
-    (0xFC7E, 'M', 'قى'),
-    (0xFC7F, 'M', 'قي'),
-    (0xFC80, 'M', 'كا'),
-    (0xFC81, 'M', 'كل'),
-    (0xFC82, 'M', 'كم'),
-    (0xFC83, 'M', 'كى'),
-    (0xFC84, 'M', 'كي'),
-    (0xFC85, 'M', 'لم'),
-    (0xFC86, 'M', 'لى'),
-    (0xFC87, 'M', 'لي'),
-    (0xFC88, 'M', 'ما'),
-    (0xFC89, 'M', 'مم'),
-    (0xFC8A, 'M', 'نر'),
-    (0xFC8B, 'M', 'نز'),
-    (0xFC8C, 'M', 'نم'),
-    (0xFC8D, 'M', 'نن'),
-    (0xFC8E, 'M', 'نى'),
-    (0xFC8F, 'M', 'ني'),
-    (0xFC90, 'M', 'ىٰ'),
-    (0xFC91, 'M', 'ير'),
-    (0xFC92, 'M', 'يز'),
-    (0xFC93, 'M', 'يم'),
-    (0xFC94, 'M', 'ين'),
-    (0xFC95, 'M', 'يى'),
-    (0xFC96, 'M', 'يي'),
-    (0xFC97, 'M', 'ئج'),
-    (0xFC98, 'M', 'ئح'),
-    (0xFC99, 'M', 'ئخ'),
-    (0xFC9A, 'M', 'ئم'),
-    (0xFC9B, 'M', 'ئه'),
-    (0xFC9C, 'M', 'بج'),
-    (0xFC9D, 'M', 'بح'),
-    (0xFC9E, 'M', 'بخ'),
-    (0xFC9F, 'M', 'بم'),
-    (0xFCA0, 'M', 'به'),
-    (0xFCA1, 'M', 'تج'),
-    (0xFCA2, 'M', 'تح'),
-    (0xFCA3, 'M', 'تخ'),
-    (0xFCA4, 'M', 'تم'),
-    (0xFCA5, 'M', 'ته'),
-    (0xFCA6, 'M', 'ثم'),
-    (0xFCA7, 'M', 'جح'),
-    (0xFCA8, 'M', 'جم'),
-    (0xFCA9, 'M', 'حج'),
-    (0xFCAA, 'M', 'حم'),
-    (0xFCAB, 'M', 'خج'),
-    (0xFCAC, 'M', 'خم'),
-    (0xFCAD, 'M', 'سج'),
-    (0xFCAE, 'M', 'سح'),
-    (0xFCAF, 'M', 'سخ'),
-    (0xFCB0, 'M', 'سم'),
-    (0xFCB1, 'M', 'صح'),
-    (0xFCB2, 'M', 'صخ'),
-    (0xFCB3, 'M', 'صم'),
-    (0xFCB4, 'M', 'ضج'),
-    (0xFCB5, 'M', 'ضح'),
-    (0xFCB6, 'M', 'ضخ'),
-    (0xFCB7, 'M', 'ضم'),
-    (0xFCB8, 'M', 'طح'),
-    (0xFCB9, 'M', 'ظم'),
-    (0xFCBA, 'M', 'عج'),
-    ]
-
-def _seg_47() -> List[Union[Tuple[int, str], Tuple[int, str, str]]]:
-    return [
-    (0xFCBB, 'M', 'عم'),
-    (0xFCBC, 'M', 'غج'),
-    (0xFCBD, 'M', 'غم'),
-    (0xFCBE, 'M', 'فج'),
-    (0xFCBF, 'M', 'فح'),
-    (0xFCC0, 'M', 'فخ'),
-    (0xFCC1, 'M', 'فم'),
-    (0xFCC2, 'M', 'قح'),
-    (0xFCC3, 'M', 'قم'),
-    (0xFCC4, 'M', 'كج'),
-    (0xFCC5, 'M', 'كح'),
-    (0xFCC6, 'M', 'كخ'),
-    (0xFCC7, 'M', 'كل'),
-    (0xFCC8, 'M', 'كم'),
-    (0xFCC9, 'M', 'لج'),
-    (0xFCCA, 'M', 'لح'),
-    (0xFCCB, 'M', 'لخ'),
-    (0xFCCC, 'M', 'لم'),
-    (0xFCCD, 'M', 'له'),
-    (0xFCCE, 'M', 'مج'),
-    (0xFCCF, 'M', 'مح'),
-    (0xFCD0, 'M', 'مخ'),
-    (0xFCD1, 'M', 'مم'),
-    (0xFCD2, 'M', 'نج'),
-    (0xFCD3, 'M', 'نح'),
-    (0xFCD4, 'M', 'نخ'),
-    (0xFCD5, 'M', 'نم'),
-    (0xFCD6, 'M', 'نه'),
-    (0xFCD7, 'M', 'هج'),
-    (0xFCD8, 'M', 'هم'),
-    (0xFCD9, 'M', 'هٰ'),
-    (0xFCDA, 'M', 'يج'),
-    (0xFCDB, 'M', 'يح'),
-    (0xFCDC, 'M', 'يخ'),
-    (0xFCDD, 'M', 'يم'),
-    (0xFCDE, 'M', 'يه'),
-    (0xFCDF, 'M', 'ئم'),
-    (0xFCE0, 'M', 'ئه'),
-    (0xFCE1, 'M', 'بم'),
-    (0xFCE2, 'M', 'به'),
-    (0xFCE3, 'M', 'تم'),
-    (0xFCE4, 'M', 'ته'),
-    (0xFCE5, 'M', 'ثم'),
-    (0xFCE6, 'M', 'ثه'),
-    (0xFCE7, 'M', 'سم'),
-    (0xFCE8, 'M', 'سه'),
-    (0xFCE9, 'M', 'شم'),
-    (0xFCEA, 'M', 'شه'),
-    (0xFCEB, 'M', 'كل'),
-    (0xFCEC, 'M', 'كم'),
-    (0xFCED, 'M', 'لم'),
-    (0xFCEE, 'M', 'نم'),
-    (0xFCEF, 'M', 'نه'),
-    (0xFCF0, 'M', 'يم'),
-    (0xFCF1, 'M', 'يه'),
-    (0xFCF2, 'M', 'ـَّ'),
-    (0xFCF3, 'M', 'ـُّ'),
-    (0xFCF4, 'M', 'ـِّ'),
-    (0xFCF5, 'M', 'طى'),
-    (0xFCF6, 'M', 'طي'),
-    (0xFCF7, 'M', 'عى'),
-    (0xFCF8, 'M', 'عي'),
-    (0xFCF9, 'M', 'غى'),
-    (0xFCFA, 'M', 'غي'),
-    (0xFCFB, 'M', 'سى'),
-    (0xFCFC, 'M', 'سي'),
-    (0xFCFD, 'M', 'شى'),
-    (0xFCFE, 'M', 'شي'),
-    (0xFCFF, 'M', 'حى'),
-    (0xFD00, 'M', 'حي'),
-    (0xFD01, 'M', 'جى'),
-    (0xFD02, 'M', 'جي'),
-    (0xFD03, 'M', 'خى'),
-    (0xFD04, 'M', 'خي'),
-    (0xFD05, 'M', 'صى'),
-    (0xFD06, 'M', 'صي'),
-    (0xFD07, 'M', 'ضى'),
-    (0xFD08, 'M', 'ضي'),
-    (0xFD09, 'M', 'شج'),
-    (0xFD0A, 'M', 'شح'),
-    (0xFD0B, 'M', 'شخ'),
-    (0xFD0C, 'M', 'شم'),
-    (0xFD0D, 'M', 'شر'),
-    (0xFD0E, 'M', 'سر'),
-    (0xFD0F, 'M', 'صر'),
-    (0xFD10, 'M', 'ضر'),
-    (0xFD11, 'M', 'طى'),
-    (0xFD12, 'M', 'طي'),
-    (0xFD13, 'M', 'عى'),
-    (0xFD14, 'M', 'عي'),
-    (0xFD15, 'M', 'غى'),
-    (0xFD16, 'M', 'غي'),
-    (0xFD17, 'M', 'سى'),
-    (0xFD18, 'M', 'سي'),
-    (0xFD19, 'M', 'شى'),
-    (0xFD1A, 'M', 'شي'),
-    (0xFD1B, 'M', 'حى'),
-    (0xFD1C, 'M', 'حي'),
-    (0xFD1D, 'M', 'جى'),
-    (0xFD1E, 'M', 'جي'),
-    ]
-
-def _seg_48() -> List[Union[Tuple[int, str], Tuple[int, str, str]]]:
-    return [
-    (0xFD1F, 'M', 'خى'),
-    (0xFD20, 'M', 'خي'),
-    (0xFD21, 'M', 'صى'),
-    (0xFD22, 'M', 'صي'),
-    (0xFD23, 'M', 'ضى'),
-    (0xFD24, 'M', 'ضي'),
-    (0xFD25, 'M', 'شج'),
-    (0xFD26, 'M', 'شح'),
-    (0xFD27, 'M', 'شخ'),
-    (0xFD28, 'M', 'شم'),
-    (0xFD29, 'M', 'شر'),
-    (0xFD2A, 'M', 'سر'),
-    (0xFD2B, 'M', 'صر'),
-    (0xFD2C, 'M', 'ضر'),
-    (0xFD2D, 'M', 'شج'),
-    (0xFD2E, 'M', 'شح'),
-    (0xFD2F, 'M', 'شخ'),
-    (0xFD30, 'M', 'شم'),
-    (0xFD31, 'M', 'سه'),
-    (0xFD32, 'M', 'شه'),
-    (0xFD33, 'M', 'طم'),
-    (0xFD34, 'M', 'سج'),
-    (0xFD35, 'M', 'سح'),
-    (0xFD36, 'M', 'سخ'),
-    (0xFD37, 'M', 'شج'),
-    (0xFD38, 'M', 'شح'),
-    (0xFD39, 'M', 'شخ'),
-    (0xFD3A, 'M', 'طم'),
-    (0xFD3B, 'M', 'ظم'),
-    (0xFD3C, 'M', 'اً'),
-    (0xFD3E, 'V'),
-    (0xFD50, 'M', 'تجم'),
-    (0xFD51, 'M', 'تحج'),
-    (0xFD53, 'M', 'تحم'),
-    (0xFD54, 'M', 'تخم'),
-    (0xFD55, 'M', 'تمج'),
-    (0xFD56, 'M', 'تمح'),
-    (0xFD57, 'M', 'تمخ'),
-    (0xFD58, 'M', 'جمح'),
-    (0xFD5A, 'M', 'حمي'),
-    (0xFD5B, 'M', 'حمى'),
-    (0xFD5C, 'M', 'سحج'),
-    (0xFD5D, 'M', 'سجح'),
-    (0xFD5E, 'M', 'سجى'),
-    (0xFD5F, 'M', 'سمح'),
-    (0xFD61, 'M', 'سمج'),
-    (0xFD62, 'M', 'سمم'),
-    (0xFD64, 'M', 'صحح'),
-    (0xFD66, 'M', 'صمم'),
-    (0xFD67, 'M', 'شحم'),
-    (0xFD69, 'M', 'شجي'),
-    (0xFD6A, 'M', 'شمخ'),
-    (0xFD6C, 'M', 'شمم'),
-    (0xFD6E, 'M', 'ضحى'),
-    (0xFD6F, 'M', 'ضخم'),
-    (0xFD71, 'M', 'طمح'),
-    (0xFD73, 'M', 'طمم'),
-    (0xFD74, 'M', 'طمي'),
-    (0xFD75, 'M', 'عجم'),
-    (0xFD76, 'M', 'عمم'),
-    (0xFD78, 'M', 'عمى'),
-    (0xFD79, 'M', 'غمم'),
-    (0xFD7A, 'M', 'غمي'),
-    (0xFD7B, 'M', 'غمى'),
-    (0xFD7C, 'M', 'فخم'),
-    (0xFD7E, 'M', 'قمح'),
-    (0xFD7F, 'M', 'قمم'),
-    (0xFD80, 'M', 'لحم'),
-    (0xFD81, 'M', 'لحي'),
-    (0xFD82, 'M', 'لحى'),
-    (0xFD83, 'M', 'لجج'),
-    (0xFD85, 'M', 'لخم'),
-    (0xFD87, 'M', 'لمح'),
-    (0xFD89, 'M', 'محج'),
-    (0xFD8A, 'M', 'محم'),
-    (0xFD8B, 'M', 'محي'),
-    (0xFD8C, 'M', 'مجح'),
-    (0xFD8D, 'M', 'مجم'),
-    (0xFD8E, 'M', 'مخج'),
-    (0xFD8F, 'M', 'مخم'),
-    (0xFD90, 'X'),
-    (0xFD92, 'M', 'مجخ'),
-    (0xFD93, 'M', 'همج'),
-    (0xFD94, 'M', 'همم'),
-    (0xFD95, 'M', 'نحم'),
-    (0xFD96, 'M', 'نحى'),
-    (0xFD97, 'M', 'نجم'),
-    (0xFD99, 'M', 'نجى'),
-    (0xFD9A, 'M', 'نمي'),
-    (0xFD9B, 'M', 'نمى'),
-    (0xFD9C, 'M', 'يمم'),
-    (0xFD9E, 'M', 'بخي'),
-    (0xFD9F, 'M', 'تجي'),
-    (0xFDA0, 'M', 'تجى'),
-    (0xFDA1, 'M', 'تخي'),
-    (0xFDA2, 'M', 'تخى'),
-    (0xFDA3, 'M', 'تمي'),
-    (0xFDA4, 'M', 'تمى'),
-    (0xFDA5, 'M', 'جمي'),
-    (0xFDA6, 'M', 'جحى'),
-    ]
-
-def _seg_49() -> List[Union[Tuple[int, str], Tuple[int, str, str]]]:
-    return [
-    (0xFDA7, 'M', 'جمى'),
-    (0xFDA8, 'M', 'سخى'),
-    (0xFDA9, 'M', 'صحي'),
-    (0xFDAA, 'M', 'شحي'),
-    (0xFDAB, 'M', 'ضحي'),
-    (0xFDAC, 'M', 'لجي'),
-    (0xFDAD, 'M', 'لمي'),
-    (0xFDAE, 'M', 'يحي'),
-    (0xFDAF, 'M', 'يجي'),
-    (0xFDB0, 'M', 'يمي'),
-    (0xFDB1, 'M', 'ممي'),
-    (0xFDB2, 'M', 'قمي'),
-    (0xFDB3, 'M', 'نحي'),
-    (0xFDB4, 'M', 'قمح'),
-    (0xFDB5, 'M', 'لحم'),
-    (0xFDB6, 'M', 'عمي'),
-    (0xFDB7, 'M', 'كمي'),
-    (0xFDB8, 'M', 'نجح'),
-    (0xFDB9, 'M', 'مخي'),
-    (0xFDBA, 'M', 'لجم'),
-    (0xFDBB, 'M', 'كمم'),
-    (0xFDBC, 'M', 'لجم'),
-    (0xFDBD, 'M', 'نجح'),
-    (0xFDBE, 'M', 'جحي'),
-    (0xFDBF, 'M', 'حجي'),
-    (0xFDC0, 'M', 'مجي'),
-    (0xFDC1, 'M', 'فمي'),
-    (0xFDC2, 'M', 'بحي'),
-    (0xFDC3, 'M', 'كمم'),
-    (0xFDC4, 'M', 'عجم'),
-    (0xFDC5, 'M', 'صمم'),
-    (0xFDC6, 'M', 'سخي'),
-    (0xFDC7, 'M', 'نجي'),
-    (0xFDC8, 'X'),
-    (0xFDCF, 'V'),
-    (0xFDD0, 'X'),
-    (0xFDF0, 'M', 'صلے'),
-    (0xFDF1, 'M', 'قلے'),
-    (0xFDF2, 'M', 'الله'),
-    (0xFDF3, 'M', 'اكبر'),
-    (0xFDF4, 'M', 'محمد'),
-    (0xFDF5, 'M', 'صلعم'),
-    (0xFDF6, 'M', 'رسول'),
-    (0xFDF7, 'M', 'عليه'),
-    (0xFDF8, 'M', 'وسلم'),
-    (0xFDF9, 'M', 'صلى'),
-    (0xFDFA, '3', 'صلى الله عليه وسلم'),
-    (0xFDFB, '3', 'جل جلاله'),
-    (0xFDFC, 'M', 'ریال'),
-    (0xFDFD, 'V'),
-    (0xFE00, 'I'),
-    (0xFE10, '3', ','),
-    (0xFE11, 'M', '、'),
-    (0xFE12, 'X'),
-    (0xFE13, '3', ':'),
-    (0xFE14, '3', ';'),
-    (0xFE15, '3', '!'),
-    (0xFE16, '3', '?'),
-    (0xFE17, 'M', '〖'),
-    (0xFE18, 'M', '〗'),
-    (0xFE19, 'X'),
-    (0xFE20, 'V'),
-    (0xFE30, 'X'),
-    (0xFE31, 'M', '—'),
-    (0xFE32, 'M', '–'),
-    (0xFE33, '3', '_'),
-    (0xFE35, '3', '('),
-    (0xFE36, '3', ')'),
-    (0xFE37, '3', '{'),
-    (0xFE38, '3', '}'),
-    (0xFE39, 'M', '〔'),
-    (0xFE3A, 'M', '〕'),
-    (0xFE3B, 'M', '【'),
-    (0xFE3C, 'M', '】'),
-    (0xFE3D, 'M', '《'),
-    (0xFE3E, 'M', '》'),
-    (0xFE3F, 'M', '〈'),
-    (0xFE40, 'M', '〉'),
-    (0xFE41, 'M', '「'),
-    (0xFE42, 'M', '」'),
-    (0xFE43, 'M', '『'),
-    (0xFE44, 'M', '』'),
-    (0xFE45, 'V'),
-    (0xFE47, '3', '['),
-    (0xFE48, '3', ']'),
-    (0xFE49, '3', ' ̅'),
-    (0xFE4D, '3', '_'),
-    (0xFE50, '3', ','),
-    (0xFE51, 'M', '、'),
-    (0xFE52, 'X'),
-    (0xFE54, '3', ';'),
-    (0xFE55, '3', ':'),
-    (0xFE56, '3', '?'),
-    (0xFE57, '3', '!'),
-    (0xFE58, 'M', '—'),
-    (0xFE59, '3', '('),
-    (0xFE5A, '3', ')'),
-    (0xFE5B, '3', '{'),
-    (0xFE5C, '3', '}'),
-    (0xFE5D, 'M', '〔'),
-    ]
-
-def _seg_50() -> List[Union[Tuple[int, str], Tuple[int, str, str]]]:
-    return [
-    (0xFE5E, 'M', '〕'),
-    (0xFE5F, '3', '#'),
-    (0xFE60, '3', '&'),
-    (0xFE61, '3', '*'),
-    (0xFE62, '3', '+'),
-    (0xFE63, 'M', '-'),
-    (0xFE64, '3', '<'),
-    (0xFE65, '3', '>'),
-    (0xFE66, '3', '='),
-    (0xFE67, 'X'),
-    (0xFE68, '3', '\\'),
-    (0xFE69, '3', '$'),
-    (0xFE6A, '3', '%'),
-    (0xFE6B, '3', '@'),
-    (0xFE6C, 'X'),
-    (0xFE70, '3', ' ً'),
-    (0xFE71, 'M', 'ـً'),
-    (0xFE72, '3', ' ٌ'),
-    (0xFE73, 'V'),
-    (0xFE74, '3', ' ٍ'),
-    (0xFE75, 'X'),
-    (0xFE76, '3', ' َ'),
-    (0xFE77, 'M', 'ـَ'),
-    (0xFE78, '3', ' ُ'),
-    (0xFE79, 'M', 'ـُ'),
-    (0xFE7A, '3', ' ِ'),
-    (0xFE7B, 'M', 'ـِ'),
-    (0xFE7C, '3', ' ّ'),
-    (0xFE7D, 'M', 'ـّ'),
-    (0xFE7E, '3', ' ْ'),
-    (0xFE7F, 'M', 'ـْ'),
-    (0xFE80, 'M', 'ء'),
-    (0xFE81, 'M', 'آ'),
-    (0xFE83, 'M', 'أ'),
-    (0xFE85, 'M', 'ؤ'),
-    (0xFE87, 'M', 'إ'),
-    (0xFE89, 'M', 'ئ'),
-    (0xFE8D, 'M', 'ا'),
-    (0xFE8F, 'M', 'ب'),
-    (0xFE93, 'M', 'ة'),
-    (0xFE95, 'M', 'ت'),
-    (0xFE99, 'M', 'ث'),
-    (0xFE9D, 'M', 'ج'),
-    (0xFEA1, 'M', 'ح'),
-    (0xFEA5, 'M', 'خ'),
-    (0xFEA9, 'M', 'د'),
-    (0xFEAB, 'M', 'ذ'),
-    (0xFEAD, 'M', 'ر'),
-    (0xFEAF, 'M', 'ز'),
-    (0xFEB1, 'M', 'س'),
-    (0xFEB5, 'M', 'ش'),
-    (0xFEB9, 'M', 'ص'),
-    (0xFEBD, 'M', 'ض'),
-    (0xFEC1, 'M', 'ط'),
-    (0xFEC5, 'M', 'ظ'),
-    (0xFEC9, 'M', 'ع'),
-    (0xFECD, 'M', 'غ'),
-    (0xFED1, 'M', 'ف'),
-    (0xFED5, 'M', 'ق'),
-    (0xFED9, 'M', 'ك'),
-    (0xFEDD, 'M', 'ل'),
-    (0xFEE1, 'M', 'م'),
-    (0xFEE5, 'M', 'ن'),
-    (0xFEE9, 'M', 'ه'),
-    (0xFEED, 'M', 'و'),
-    (0xFEEF, 'M', 'ى'),
-    (0xFEF1, 'M', 'ي'),
-    (0xFEF5, 'M', 'لآ'),
-    (0xFEF7, 'M', 'لأ'),
-    (0xFEF9, 'M', 'لإ'),
-    (0xFEFB, 'M', 'لا'),
-    (0xFEFD, 'X'),
-    (0xFEFF, 'I'),
-    (0xFF00, 'X'),
-    (0xFF01, '3', '!'),
-    (0xFF02, '3', '"'),
-    (0xFF03, '3', '#'),
-    (0xFF04, '3', '$'),
-    (0xFF05, '3', '%'),
-    (0xFF06, '3', '&'),
-    (0xFF07, '3', '\''),
-    (0xFF08, '3', '('),
-    (0xFF09, '3', ')'),
-    (0xFF0A, '3', '*'),
-    (0xFF0B, '3', '+'),
-    (0xFF0C, '3', ','),
-    (0xFF0D, 'M', '-'),
-    (0xFF0E, 'M', '.'),
-    (0xFF0F, '3', '/'),
-    (0xFF10, 'M', '0'),
-    (0xFF11, 'M', '1'),
-    (0xFF12, 'M', '2'),
-    (0xFF13, 'M', '3'),
-    (0xFF14, 'M', '4'),
-    (0xFF15, 'M', '5'),
-    (0xFF16, 'M', '6'),
-    (0xFF17, 'M', '7'),
-    (0xFF18, 'M', '8'),
-    (0xFF19, 'M', '9'),
-    (0xFF1A, '3', ':'),
-    ]
-
-def _seg_51() -> List[Union[Tuple[int, str], Tuple[int, str, str]]]:
-    return [
-    (0xFF1B, '3', ';'),
-    (0xFF1C, '3', '<'),
-    (0xFF1D, '3', '='),
-    (0xFF1E, '3', '>'),
-    (0xFF1F, '3', '?'),
-    (0xFF20, '3', '@'),
-    (0xFF21, 'M', 'a'),
-    (0xFF22, 'M', 'b'),
-    (0xFF23, 'M', 'c'),
-    (0xFF24, 'M', 'd'),
-    (0xFF25, 'M', 'e'),
-    (0xFF26, 'M', 'f'),
-    (0xFF27, 'M', 'g'),
-    (0xFF28, 'M', 'h'),
-    (0xFF29, 'M', 'i'),
-    (0xFF2A, 'M', 'j'),
-    (0xFF2B, 'M', 'k'),
-    (0xFF2C, 'M', 'l'),
-    (0xFF2D, 'M', 'm'),
-    (0xFF2E, 'M', 'n'),
-    (0xFF2F, 'M', 'o'),
-    (0xFF30, 'M', 'p'),
-    (0xFF31, 'M', 'q'),
-    (0xFF32, 'M', 'r'),
-    (0xFF33, 'M', 's'),
-    (0xFF34, 'M', 't'),
-    (0xFF35, 'M', 'u'),
-    (0xFF36, 'M', 'v'),
-    (0xFF37, 'M', 'w'),
-    (0xFF38, 'M', 'x'),
-    (0xFF39, 'M', 'y'),
-    (0xFF3A, 'M', 'z'),
-    (0xFF3B, '3', '['),
-    (0xFF3C, '3', '\\'),
-    (0xFF3D, '3', ']'),
-    (0xFF3E, '3', '^'),
-    (0xFF3F, '3', '_'),
-    (0xFF40, '3', '`'),
-    (0xFF41, 'M', 'a'),
-    (0xFF42, 'M', 'b'),
-    (0xFF43, 'M', 'c'),
-    (0xFF44, 'M', 'd'),
-    (0xFF45, 'M', 'e'),
-    (0xFF46, 'M', 'f'),
-    (0xFF47, 'M', 'g'),
-    (0xFF48, 'M', 'h'),
-    (0xFF49, 'M', 'i'),
-    (0xFF4A, 'M', 'j'),
-    (0xFF4B, 'M', 'k'),
-    (0xFF4C, 'M', 'l'),
-    (0xFF4D, 'M', 'm'),
-    (0xFF4E, 'M', 'n'),
-    (0xFF4F, 'M', 'o'),
-    (0xFF50, 'M', 'p'),
-    (0xFF51, 'M', 'q'),
-    (0xFF52, 'M', 'r'),
-    (0xFF53, 'M', 's'),
-    (0xFF54, 'M', 't'),
-    (0xFF55, 'M', 'u'),
-    (0xFF56, 'M', 'v'),
-    (0xFF57, 'M', 'w'),
-    (0xFF58, 'M', 'x'),
-    (0xFF59, 'M', 'y'),
-    (0xFF5A, 'M', 'z'),
-    (0xFF5B, '3', '{'),
-    (0xFF5C, '3', '|'),
-    (0xFF5D, '3', '}'),
-    (0xFF5E, '3', '~'),
-    (0xFF5F, 'M', '⦅'),
-    (0xFF60, 'M', '⦆'),
-    (0xFF61, 'M', '.'),
-    (0xFF62, 'M', '「'),
-    (0xFF63, 'M', '」'),
-    (0xFF64, 'M', '、'),
-    (0xFF65, 'M', '・'),
-    (0xFF66, 'M', 'ヲ'),
-    (0xFF67, 'M', 'ァ'),
-    (0xFF68, 'M', 'ィ'),
-    (0xFF69, 'M', 'ゥ'),
-    (0xFF6A, 'M', 'ェ'),
-    (0xFF6B, 'M', 'ォ'),
-    (0xFF6C, 'M', 'ャ'),
-    (0xFF6D, 'M', 'ュ'),
-    (0xFF6E, 'M', 'ョ'),
-    (0xFF6F, 'M', 'ッ'),
-    (0xFF70, 'M', 'ー'),
-    (0xFF71, 'M', 'ア'),
-    (0xFF72, 'M', 'イ'),
-    (0xFF73, 'M', 'ウ'),
-    (0xFF74, 'M', 'エ'),
-    (0xFF75, 'M', 'オ'),
-    (0xFF76, 'M', 'カ'),
-    (0xFF77, 'M', 'キ'),
-    (0xFF78, 'M', 'ク'),
-    (0xFF79, 'M', 'ケ'),
-    (0xFF7A, 'M', 'コ'),
-    (0xFF7B, 'M', 'サ'),
-    (0xFF7C, 'M', 'シ'),
-    (0xFF7D, 'M', 'ス'),
-    (0xFF7E, 'M', 'セ'),
-    ]
-
-def _seg_52() -> List[Union[Tuple[int, str], Tuple[int, str, str]]]:
-    return [
-    (0xFF7F, 'M', 'ソ'),
-    (0xFF80, 'M', 'タ'),
-    (0xFF81, 'M', 'チ'),
-    (0xFF82, 'M', 'ツ'),
-    (0xFF83, 'M', 'テ'),
-    (0xFF84, 'M', 'ト'),
-    (0xFF85, 'M', 'ナ'),
-    (0xFF86, 'M', 'ニ'),
-    (0xFF87, 'M', 'ヌ'),
-    (0xFF88, 'M', 'ネ'),
-    (0xFF89, 'M', 'ノ'),
-    (0xFF8A, 'M', 'ハ'),
-    (0xFF8B, 'M', 'ヒ'),
-    (0xFF8C, 'M', 'フ'),
-    (0xFF8D, 'M', 'ヘ'),
-    (0xFF8E, 'M', 'ホ'),
-    (0xFF8F, 'M', 'マ'),
-    (0xFF90, 'M', 'ミ'),
-    (0xFF91, 'M', 'ム'),
-    (0xFF92, 'M', 'メ'),
-    (0xFF93, 'M', 'モ'),
-    (0xFF94, 'M', 'ヤ'),
-    (0xFF95, 'M', 'ユ'),
-    (0xFF96, 'M', 'ヨ'),
-    (0xFF97, 'M', 'ラ'),
-    (0xFF98, 'M', 'リ'),
-    (0xFF99, 'M', 'ル'),
-    (0xFF9A, 'M', 'レ'),
-    (0xFF9B, 'M', 'ロ'),
-    (0xFF9C, 'M', 'ワ'),
-    (0xFF9D, 'M', 'ン'),
-    (0xFF9E, 'M', '゙'),
-    (0xFF9F, 'M', '゚'),
-    (0xFFA0, 'X'),
-    (0xFFA1, 'M', 'ᄀ'),
-    (0xFFA2, 'M', 'ᄁ'),
-    (0xFFA3, 'M', 'ᆪ'),
-    (0xFFA4, 'M', 'ᄂ'),
-    (0xFFA5, 'M', 'ᆬ'),
-    (0xFFA6, 'M', 'ᆭ'),
-    (0xFFA7, 'M', 'ᄃ'),
-    (0xFFA8, 'M', 'ᄄ'),
-    (0xFFA9, 'M', 'ᄅ'),
-    (0xFFAA, 'M', 'ᆰ'),
-    (0xFFAB, 'M', 'ᆱ'),
-    (0xFFAC, 'M', 'ᆲ'),
-    (0xFFAD, 'M', 'ᆳ'),
-    (0xFFAE, 'M', 'ᆴ'),
-    (0xFFAF, 'M', 'ᆵ'),
-    (0xFFB0, 'M', 'ᄚ'),
-    (0xFFB1, 'M', 'ᄆ'),
-    (0xFFB2, 'M', 'ᄇ'),
-    (0xFFB3, 'M', 'ᄈ'),
-    (0xFFB4, 'M', 'ᄡ'),
-    (0xFFB5, 'M', 'ᄉ'),
-    (0xFFB6, 'M', 'ᄊ'),
-    (0xFFB7, 'M', 'ᄋ'),
-    (0xFFB8, 'M', 'ᄌ'),
-    (0xFFB9, 'M', 'ᄍ'),
-    (0xFFBA, 'M', 'ᄎ'),
-    (0xFFBB, 'M', 'ᄏ'),
-    (0xFFBC, 'M', 'ᄐ'),
-    (0xFFBD, 'M', 'ᄑ'),
-    (0xFFBE, 'M', 'ᄒ'),
-    (0xFFBF, 'X'),
-    (0xFFC2, 'M', 'ᅡ'),
-    (0xFFC3, 'M', 'ᅢ'),
-    (0xFFC4, 'M', 'ᅣ'),
-    (0xFFC5, 'M', 'ᅤ'),
-    (0xFFC6, 'M', 'ᅥ'),
-    (0xFFC7, 'M', 'ᅦ'),
-    (0xFFC8, 'X'),
-    (0xFFCA, 'M', 'ᅧ'),
-    (0xFFCB, 'M', 'ᅨ'),
-    (0xFFCC, 'M', 'ᅩ'),
-    (0xFFCD, 'M', 'ᅪ'),
-    (0xFFCE, 'M', 'ᅫ'),
-    (0xFFCF, 'M', 'ᅬ'),
-    (0xFFD0, 'X'),
-    (0xFFD2, 'M', 'ᅭ'),
-    (0xFFD3, 'M', 'ᅮ'),
-    (0xFFD4, 'M', 'ᅯ'),
-    (0xFFD5, 'M', 'ᅰ'),
-    (0xFFD6, 'M', 'ᅱ'),
-    (0xFFD7, 'M', 'ᅲ'),
-    (0xFFD8, 'X'),
-    (0xFFDA, 'M', 'ᅳ'),
-    (0xFFDB, 'M', 'ᅴ'),
-    (0xFFDC, 'M', 'ᅵ'),
-    (0xFFDD, 'X'),
-    (0xFFE0, 'M', '¢'),
-    (0xFFE1, 'M', '£'),
-    (0xFFE2, 'M', '¬'),
-    (0xFFE3, '3', ' ̄'),
-    (0xFFE4, 'M', '¦'),
-    (0xFFE5, 'M', '¥'),
-    (0xFFE6, 'M', '₩'),
-    (0xFFE7, 'X'),
-    (0xFFE8, 'M', '│'),
-    (0xFFE9, 'M', '←'),
-    ]
-
-def _seg_53() -> List[Union[Tuple[int, str], Tuple[int, str, str]]]:
-    return [
-    (0xFFEA, 'M', '↑'),
-    (0xFFEB, 'M', '→'),
-    (0xFFEC, 'M', '↓'),
-    (0xFFED, 'M', '■'),
-    (0xFFEE, 'M', '○'),
-    (0xFFEF, 'X'),
-    (0x10000, 'V'),
-    (0x1000C, 'X'),
-    (0x1000D, 'V'),
-    (0x10027, 'X'),
-    (0x10028, 'V'),
-    (0x1003B, 'X'),
-    (0x1003C, 'V'),
-    (0x1003E, 'X'),
-    (0x1003F, 'V'),
-    (0x1004E, 'X'),
-    (0x10050, 'V'),
-    (0x1005E, 'X'),
-    (0x10080, 'V'),
-    (0x100FB, 'X'),
-    (0x10100, 'V'),
-    (0x10103, 'X'),
-    (0x10107, 'V'),
-    (0x10134, 'X'),
-    (0x10137, 'V'),
-    (0x1018F, 'X'),
-    (0x10190, 'V'),
-    (0x1019D, 'X'),
-    (0x101A0, 'V'),
-    (0x101A1, 'X'),
-    (0x101D0, 'V'),
-    (0x101FE, 'X'),
-    (0x10280, 'V'),
-    (0x1029D, 'X'),
-    (0x102A0, 'V'),
-    (0x102D1, 'X'),
-    (0x102E0, 'V'),
-    (0x102FC, 'X'),
-    (0x10300, 'V'),
-    (0x10324, 'X'),
-    (0x1032D, 'V'),
-    (0x1034B, 'X'),
-    (0x10350, 'V'),
-    (0x1037B, 'X'),
-    (0x10380, 'V'),
-    (0x1039E, 'X'),
-    (0x1039F, 'V'),
-    (0x103C4, 'X'),
-    (0x103C8, 'V'),
-    (0x103D6, 'X'),
-    (0x10400, 'M', '𐐨'),
-    (0x10401, 'M', '𐐩'),
-    (0x10402, 'M', '𐐪'),
-    (0x10403, 'M', '𐐫'),
-    (0x10404, 'M', '𐐬'),
-    (0x10405, 'M', '𐐭'),
-    (0x10406, 'M', '𐐮'),
-    (0x10407, 'M', '𐐯'),
-    (0x10408, 'M', '𐐰'),
-    (0x10409, 'M', '𐐱'),
-    (0x1040A, 'M', '𐐲'),
-    (0x1040B, 'M', '𐐳'),
-    (0x1040C, 'M', '𐐴'),
-    (0x1040D, 'M', '𐐵'),
-    (0x1040E, 'M', '𐐶'),
-    (0x1040F, 'M', '𐐷'),
-    (0x10410, 'M', '𐐸'),
-    (0x10411, 'M', '𐐹'),
-    (0x10412, 'M', '𐐺'),
-    (0x10413, 'M', '𐐻'),
-    (0x10414, 'M', '𐐼'),
-    (0x10415, 'M', '𐐽'),
-    (0x10416, 'M', '𐐾'),
-    (0x10417, 'M', '𐐿'),
-    (0x10418, 'M', '𐑀'),
-    (0x10419, 'M', '𐑁'),
-    (0x1041A, 'M', '𐑂'),
-    (0x1041B, 'M', '𐑃'),
-    (0x1041C, 'M', '𐑄'),
-    (0x1041D, 'M', '𐑅'),
-    (0x1041E, 'M', '𐑆'),
-    (0x1041F, 'M', '𐑇'),
-    (0x10420, 'M', '𐑈'),
-    (0x10421, 'M', '𐑉'),
-    (0x10422, 'M', '𐑊'),
-    (0x10423, 'M', '𐑋'),
-    (0x10424, 'M', '𐑌'),
-    (0x10425, 'M', '𐑍'),
-    (0x10426, 'M', '𐑎'),
-    (0x10427, 'M', '𐑏'),
-    (0x10428, 'V'),
-    (0x1049E, 'X'),
-    (0x104A0, 'V'),
-    (0x104AA, 'X'),
-    (0x104B0, 'M', '𐓘'),
-    (0x104B1, 'M', '𐓙'),
-    (0x104B2, 'M', '𐓚'),
-    (0x104B3, 'M', '𐓛'),
-    (0x104B4, 'M', '𐓜'),
-    (0x104B5, 'M', '𐓝'),
-    ]
-
-def _seg_54() -> List[Union[Tuple[int, str], Tuple[int, str, str]]]:
-    return [
-    (0x104B6, 'M', '𐓞'),
-    (0x104B7, 'M', '𐓟'),
-    (0x104B8, 'M', '𐓠'),
-    (0x104B9, 'M', '𐓡'),
-    (0x104BA, 'M', '𐓢'),
-    (0x104BB, 'M', '𐓣'),
-    (0x104BC, 'M', '𐓤'),
-    (0x104BD, 'M', '𐓥'),
-    (0x104BE, 'M', '𐓦'),
-    (0x104BF, 'M', '𐓧'),
-    (0x104C0, 'M', '𐓨'),
-    (0x104C1, 'M', '𐓩'),
-    (0x104C2, 'M', '𐓪'),
-    (0x104C3, 'M', '𐓫'),
-    (0x104C4, 'M', '𐓬'),
-    (0x104C5, 'M', '𐓭'),
-    (0x104C6, 'M', '𐓮'),
-    (0x104C7, 'M', '𐓯'),
-    (0x104C8, 'M', '𐓰'),
-    (0x104C9, 'M', '𐓱'),
-    (0x104CA, 'M', '𐓲'),
-    (0x104CB, 'M', '𐓳'),
-    (0x104CC, 'M', '𐓴'),
-    (0x104CD, 'M', '𐓵'),
-    (0x104CE, 'M', '𐓶'),
-    (0x104CF, 'M', '𐓷'),
-    (0x104D0, 'M', '𐓸'),
-    (0x104D1, 'M', '𐓹'),
-    (0x104D2, 'M', '𐓺'),
-    (0x104D3, 'M', '𐓻'),
-    (0x104D4, 'X'),
-    (0x104D8, 'V'),
-    (0x104FC, 'X'),
-    (0x10500, 'V'),
-    (0x10528, 'X'),
-    (0x10530, 'V'),
-    (0x10564, 'X'),
-    (0x1056F, 'V'),
-    (0x10570, 'M', '𐖗'),
-    (0x10571, 'M', '𐖘'),
-    (0x10572, 'M', '𐖙'),
-    (0x10573, 'M', '𐖚'),
-    (0x10574, 'M', '𐖛'),
-    (0x10575, 'M', '𐖜'),
-    (0x10576, 'M', '𐖝'),
-    (0x10577, 'M', '𐖞'),
-    (0x10578, 'M', '𐖟'),
-    (0x10579, 'M', '𐖠'),
-    (0x1057A, 'M', '𐖡'),
-    (0x1057B, 'X'),
-    (0x1057C, 'M', '𐖣'),
-    (0x1057D, 'M', '𐖤'),
-    (0x1057E, 'M', '𐖥'),
-    (0x1057F, 'M', '𐖦'),
-    (0x10580, 'M', '𐖧'),
-    (0x10581, 'M', '𐖨'),
-    (0x10582, 'M', '𐖩'),
-    (0x10583, 'M', '𐖪'),
-    (0x10584, 'M', '𐖫'),
-    (0x10585, 'M', '𐖬'),
-    (0x10586, 'M', '𐖭'),
-    (0x10587, 'M', '𐖮'),
-    (0x10588, 'M', '𐖯'),
-    (0x10589, 'M', '𐖰'),
-    (0x1058A, 'M', '𐖱'),
-    (0x1058B, 'X'),
-    (0x1058C, 'M', '𐖳'),
-    (0x1058D, 'M', '𐖴'),
-    (0x1058E, 'M', '𐖵'),
-    (0x1058F, 'M', '𐖶'),
-    (0x10590, 'M', '𐖷'),
-    (0x10591, 'M', '𐖸'),
-    (0x10592, 'M', '𐖹'),
-    (0x10593, 'X'),
-    (0x10594, 'M', '𐖻'),
-    (0x10595, 'M', '𐖼'),
-    (0x10596, 'X'),
-    (0x10597, 'V'),
-    (0x105A2, 'X'),
-    (0x105A3, 'V'),
-    (0x105B2, 'X'),
-    (0x105B3, 'V'),
-    (0x105BA, 'X'),
-    (0x105BB, 'V'),
-    (0x105BD, 'X'),
-    (0x10600, 'V'),
-    (0x10737, 'X'),
-    (0x10740, 'V'),
-    (0x10756, 'X'),
-    (0x10760, 'V'),
-    (0x10768, 'X'),
-    (0x10780, 'V'),
-    (0x10781, 'M', 'ː'),
-    (0x10782, 'M', 'ˑ'),
-    (0x10783, 'M', 'æ'),
-    (0x10784, 'M', 'ʙ'),
-    (0x10785, 'M', 'ɓ'),
-    (0x10786, 'X'),
-    (0x10787, 'M', 'ʣ'),
-    (0x10788, 'M', 'ꭦ'),
-    ]
-
-def _seg_55() -> List[Union[Tuple[int, str], Tuple[int, str, str]]]:
-    return [
-    (0x10789, 'M', 'ʥ'),
-    (0x1078A, 'M', 'ʤ'),
-    (0x1078B, 'M', 'ɖ'),
-    (0x1078C, 'M', 'ɗ'),
-    (0x1078D, 'M', 'ᶑ'),
-    (0x1078E, 'M', 'ɘ'),
-    (0x1078F, 'M', 'ɞ'),
-    (0x10790, 'M', 'ʩ'),
-    (0x10791, 'M', 'ɤ'),
-    (0x10792, 'M', 'ɢ'),
-    (0x10793, 'M', 'ɠ'),
-    (0x10794, 'M', 'ʛ'),
-    (0x10795, 'M', 'ħ'),
-    (0x10796, 'M', 'ʜ'),
-    (0x10797, 'M', 'ɧ'),
-    (0x10798, 'M', 'ʄ'),
-    (0x10799, 'M', 'ʪ'),
-    (0x1079A, 'M', 'ʫ'),
-    (0x1079B, 'M', 'ɬ'),
-    (0x1079C, 'M', '𝼄'),
-    (0x1079D, 'M', 'ꞎ'),
-    (0x1079E, 'M', 'ɮ'),
-    (0x1079F, 'M', '𝼅'),
-    (0x107A0, 'M', 'ʎ'),
-    (0x107A1, 'M', '𝼆'),
-    (0x107A2, 'M', 'ø'),
-    (0x107A3, 'M', 'ɶ'),
-    (0x107A4, 'M', 'ɷ'),
-    (0x107A5, 'M', 'q'),
-    (0x107A6, 'M', 'ɺ'),
-    (0x107A7, 'M', '𝼈'),
-    (0x107A8, 'M', 'ɽ'),
-    (0x107A9, 'M', 'ɾ'),
-    (0x107AA, 'M', 'ʀ'),
-    (0x107AB, 'M', 'ʨ'),
-    (0x107AC, 'M', 'ʦ'),
-    (0x107AD, 'M', 'ꭧ'),
-    (0x107AE, 'M', 'ʧ'),
-    (0x107AF, 'M', 'ʈ'),
-    (0x107B0, 'M', 'ⱱ'),
-    (0x107B1, 'X'),
-    (0x107B2, 'M', 'ʏ'),
-    (0x107B3, 'M', 'ʡ'),
-    (0x107B4, 'M', 'ʢ'),
-    (0x107B5, 'M', 'ʘ'),
-    (0x107B6, 'M', 'ǀ'),
-    (0x107B7, 'M', 'ǁ'),
-    (0x107B8, 'M', 'ǂ'),
-    (0x107B9, 'M', '𝼊'),
-    (0x107BA, 'M', '𝼞'),
-    (0x107BB, 'X'),
-    (0x10800, 'V'),
-    (0x10806, 'X'),
-    (0x10808, 'V'),
-    (0x10809, 'X'),
-    (0x1080A, 'V'),
-    (0x10836, 'X'),
-    (0x10837, 'V'),
-    (0x10839, 'X'),
-    (0x1083C, 'V'),
-    (0x1083D, 'X'),
-    (0x1083F, 'V'),
-    (0x10856, 'X'),
-    (0x10857, 'V'),
-    (0x1089F, 'X'),
-    (0x108A7, 'V'),
-    (0x108B0, 'X'),
-    (0x108E0, 'V'),
-    (0x108F3, 'X'),
-    (0x108F4, 'V'),
-    (0x108F6, 'X'),
-    (0x108FB, 'V'),
-    (0x1091C, 'X'),
-    (0x1091F, 'V'),
-    (0x1093A, 'X'),
-    (0x1093F, 'V'),
-    (0x10940, 'X'),
-    (0x10980, 'V'),
-    (0x109B8, 'X'),
-    (0x109BC, 'V'),
-    (0x109D0, 'X'),
-    (0x109D2, 'V'),
-    (0x10A04, 'X'),
-    (0x10A05, 'V'),
-    (0x10A07, 'X'),
-    (0x10A0C, 'V'),
-    (0x10A14, 'X'),
-    (0x10A15, 'V'),
-    (0x10A18, 'X'),
-    (0x10A19, 'V'),
-    (0x10A36, 'X'),
-    (0x10A38, 'V'),
-    (0x10A3B, 'X'),
-    (0x10A3F, 'V'),
-    (0x10A49, 'X'),
-    (0x10A50, 'V'),
-    (0x10A59, 'X'),
-    (0x10A60, 'V'),
-    (0x10AA0, 'X'),
-    (0x10AC0, 'V'),
-    ]
-
-def _seg_56() -> List[Union[Tuple[int, str], Tuple[int, str, str]]]:
-    return [
-    (0x10AE7, 'X'),
-    (0x10AEB, 'V'),
-    (0x10AF7, 'X'),
-    (0x10B00, 'V'),
-    (0x10B36, 'X'),
-    (0x10B39, 'V'),
-    (0x10B56, 'X'),
-    (0x10B58, 'V'),
-    (0x10B73, 'X'),
-    (0x10B78, 'V'),
-    (0x10B92, 'X'),
-    (0x10B99, 'V'),
-    (0x10B9D, 'X'),
-    (0x10BA9, 'V'),
-    (0x10BB0, 'X'),
-    (0x10C00, 'V'),
-    (0x10C49, 'X'),
-    (0x10C80, 'M', '𐳀'),
-    (0x10C81, 'M', '𐳁'),
-    (0x10C82, 'M', '𐳂'),
-    (0x10C83, 'M', '𐳃'),
-    (0x10C84, 'M', '𐳄'),
-    (0x10C85, 'M', '𐳅'),
-    (0x10C86, 'M', '𐳆'),
-    (0x10C87, 'M', '𐳇'),
-    (0x10C88, 'M', '𐳈'),
-    (0x10C89, 'M', '𐳉'),
-    (0x10C8A, 'M', '𐳊'),
-    (0x10C8B, 'M', '𐳋'),
-    (0x10C8C, 'M', '𐳌'),
-    (0x10C8D, 'M', '𐳍'),
-    (0x10C8E, 'M', '𐳎'),
-    (0x10C8F, 'M', '𐳏'),
-    (0x10C90, 'M', '𐳐'),
-    (0x10C91, 'M', '𐳑'),
-    (0x10C92, 'M', '𐳒'),
-    (0x10C93, 'M', '𐳓'),
-    (0x10C94, 'M', '𐳔'),
-    (0x10C95, 'M', '𐳕'),
-    (0x10C96, 'M', '𐳖'),
-    (0x10C97, 'M', '𐳗'),
-    (0x10C98, 'M', '𐳘'),
-    (0x10C99, 'M', '𐳙'),
-    (0x10C9A, 'M', '𐳚'),
-    (0x10C9B, 'M', '𐳛'),
-    (0x10C9C, 'M', '𐳜'),
-    (0x10C9D, 'M', '𐳝'),
-    (0x10C9E, 'M', '𐳞'),
-    (0x10C9F, 'M', '𐳟'),
-    (0x10CA0, 'M', '𐳠'),
-    (0x10CA1, 'M', '𐳡'),
-    (0x10CA2, 'M', '𐳢'),
-    (0x10CA3, 'M', '𐳣'),
-    (0x10CA4, 'M', '𐳤'),
-    (0x10CA5, 'M', '𐳥'),
-    (0x10CA6, 'M', '𐳦'),
-    (0x10CA7, 'M', '𐳧'),
-    (0x10CA8, 'M', '𐳨'),
-    (0x10CA9, 'M', '𐳩'),
-    (0x10CAA, 'M', '𐳪'),
-    (0x10CAB, 'M', '𐳫'),
-    (0x10CAC, 'M', '𐳬'),
-    (0x10CAD, 'M', '𐳭'),
-    (0x10CAE, 'M', '𐳮'),
-    (0x10CAF, 'M', '𐳯'),
-    (0x10CB0, 'M', '𐳰'),
-    (0x10CB1, 'M', '𐳱'),
-    (0x10CB2, 'M', '𐳲'),
-    (0x10CB3, 'X'),
-    (0x10CC0, 'V'),
-    (0x10CF3, 'X'),
-    (0x10CFA, 'V'),
-    (0x10D28, 'X'),
-    (0x10D30, 'V'),
-    (0x10D3A, 'X'),
-    (0x10E60, 'V'),
-    (0x10E7F, 'X'),
-    (0x10E80, 'V'),
-    (0x10EAA, 'X'),
-    (0x10EAB, 'V'),
-    (0x10EAE, 'X'),
-    (0x10EB0, 'V'),
-    (0x10EB2, 'X'),
-    (0x10F00, 'V'),
-    (0x10F28, 'X'),
-    (0x10F30, 'V'),
-    (0x10F5A, 'X'),
-    (0x10F70, 'V'),
-    (0x10F8A, 'X'),
-    (0x10FB0, 'V'),
-    (0x10FCC, 'X'),
-    (0x10FE0, 'V'),
-    (0x10FF7, 'X'),
-    (0x11000, 'V'),
-    (0x1104E, 'X'),
-    (0x11052, 'V'),
-    (0x11076, 'X'),
-    (0x1107F, 'V'),
-    (0x110BD, 'X'),
-    (0x110BE, 'V'),
-    ]
-
-def _seg_57() -> List[Union[Tuple[int, str], Tuple[int, str, str]]]:
-    return [
-    (0x110C3, 'X'),
-    (0x110D0, 'V'),
-    (0x110E9, 'X'),
-    (0x110F0, 'V'),
-    (0x110FA, 'X'),
-    (0x11100, 'V'),
-    (0x11135, 'X'),
-    (0x11136, 'V'),
-    (0x11148, 'X'),
-    (0x11150, 'V'),
-    (0x11177, 'X'),
-    (0x11180, 'V'),
-    (0x111E0, 'X'),
-    (0x111E1, 'V'),
-    (0x111F5, 'X'),
-    (0x11200, 'V'),
-    (0x11212, 'X'),
-    (0x11213, 'V'),
-    (0x1123F, 'X'),
-    (0x11280, 'V'),
-    (0x11287, 'X'),
-    (0x11288, 'V'),
-    (0x11289, 'X'),
-    (0x1128A, 'V'),
-    (0x1128E, 'X'),
-    (0x1128F, 'V'),
-    (0x1129E, 'X'),
-    (0x1129F, 'V'),
-    (0x112AA, 'X'),
-    (0x112B0, 'V'),
-    (0x112EB, 'X'),
-    (0x112F0, 'V'),
-    (0x112FA, 'X'),
-    (0x11300, 'V'),
-    (0x11304, 'X'),
-    (0x11305, 'V'),
-    (0x1130D, 'X'),
-    (0x1130F, 'V'),
-    (0x11311, 'X'),
-    (0x11313, 'V'),
-    (0x11329, 'X'),
-    (0x1132A, 'V'),
-    (0x11331, 'X'),
-    (0x11332, 'V'),
-    (0x11334, 'X'),
-    (0x11335, 'V'),
-    (0x1133A, 'X'),
-    (0x1133B, 'V'),
-    (0x11345, 'X'),
-    (0x11347, 'V'),
-    (0x11349, 'X'),
-    (0x1134B, 'V'),
-    (0x1134E, 'X'),
-    (0x11350, 'V'),
-    (0x11351, 'X'),
-    (0x11357, 'V'),
-    (0x11358, 'X'),
-    (0x1135D, 'V'),
-    (0x11364, 'X'),
-    (0x11366, 'V'),
-    (0x1136D, 'X'),
-    (0x11370, 'V'),
-    (0x11375, 'X'),
-    (0x11400, 'V'),
-    (0x1145C, 'X'),
-    (0x1145D, 'V'),
-    (0x11462, 'X'),
-    (0x11480, 'V'),
-    (0x114C8, 'X'),
-    (0x114D0, 'V'),
-    (0x114DA, 'X'),
-    (0x11580, 'V'),
-    (0x115B6, 'X'),
-    (0x115B8, 'V'),
-    (0x115DE, 'X'),
-    (0x11600, 'V'),
-    (0x11645, 'X'),
-    (0x11650, 'V'),
-    (0x1165A, 'X'),
-    (0x11660, 'V'),
-    (0x1166D, 'X'),
-    (0x11680, 'V'),
-    (0x116BA, 'X'),
-    (0x116C0, 'V'),
-    (0x116CA, 'X'),
-    (0x11700, 'V'),
-    (0x1171B, 'X'),
-    (0x1171D, 'V'),
-    (0x1172C, 'X'),
-    (0x11730, 'V'),
-    (0x11747, 'X'),
-    (0x11800, 'V'),
-    (0x1183C, 'X'),
-    (0x118A0, 'M', '𑣀'),
-    (0x118A1, 'M', '𑣁'),
-    (0x118A2, 'M', '𑣂'),
-    (0x118A3, 'M', '𑣃'),
-    (0x118A4, 'M', '𑣄'),
-    (0x118A5, 'M', '𑣅'),
-    (0x118A6, 'M', '𑣆'),
-    ]
-
-def _seg_58() -> List[Union[Tuple[int, str], Tuple[int, str, str]]]:
-    return [
-    (0x118A7, 'M', '𑣇'),
-    (0x118A8, 'M', '𑣈'),
-    (0x118A9, 'M', '𑣉'),
-    (0x118AA, 'M', '𑣊'),
-    (0x118AB, 'M', '𑣋'),
-    (0x118AC, 'M', '𑣌'),
-    (0x118AD, 'M', '𑣍'),
-    (0x118AE, 'M', '𑣎'),
-    (0x118AF, 'M', '𑣏'),
-    (0x118B0, 'M', '𑣐'),
-    (0x118B1, 'M', '𑣑'),
-    (0x118B2, 'M', '𑣒'),
-    (0x118B3, 'M', '𑣓'),
-    (0x118B4, 'M', '𑣔'),
-    (0x118B5, 'M', '𑣕'),
-    (0x118B6, 'M', '𑣖'),
-    (0x118B7, 'M', '𑣗'),
-    (0x118B8, 'M', '𑣘'),
-    (0x118B9, 'M', '𑣙'),
-    (0x118BA, 'M', '𑣚'),
-    (0x118BB, 'M', '𑣛'),
-    (0x118BC, 'M', '𑣜'),
-    (0x118BD, 'M', '𑣝'),
-    (0x118BE, 'M', '𑣞'),
-    (0x118BF, 'M', '𑣟'),
-    (0x118C0, 'V'),
-    (0x118F3, 'X'),
-    (0x118FF, 'V'),
-    (0x11907, 'X'),
-    (0x11909, 'V'),
-    (0x1190A, 'X'),
-    (0x1190C, 'V'),
-    (0x11914, 'X'),
-    (0x11915, 'V'),
-    (0x11917, 'X'),
-    (0x11918, 'V'),
-    (0x11936, 'X'),
-    (0x11937, 'V'),
-    (0x11939, 'X'),
-    (0x1193B, 'V'),
-    (0x11947, 'X'),
-    (0x11950, 'V'),
-    (0x1195A, 'X'),
-    (0x119A0, 'V'),
-    (0x119A8, 'X'),
-    (0x119AA, 'V'),
-    (0x119D8, 'X'),
-    (0x119DA, 'V'),
-    (0x119E5, 'X'),
-    (0x11A00, 'V'),
-    (0x11A48, 'X'),
-    (0x11A50, 'V'),
-    (0x11AA3, 'X'),
-    (0x11AB0, 'V'),
-    (0x11AF9, 'X'),
-    (0x11C00, 'V'),
-    (0x11C09, 'X'),
-    (0x11C0A, 'V'),
-    (0x11C37, 'X'),
-    (0x11C38, 'V'),
-    (0x11C46, 'X'),
-    (0x11C50, 'V'),
-    (0x11C6D, 'X'),
-    (0x11C70, 'V'),
-    (0x11C90, 'X'),
-    (0x11C92, 'V'),
-    (0x11CA8, 'X'),
-    (0x11CA9, 'V'),
-    (0x11CB7, 'X'),
-    (0x11D00, 'V'),
-    (0x11D07, 'X'),
-    (0x11D08, 'V'),
-    (0x11D0A, 'X'),
-    (0x11D0B, 'V'),
-    (0x11D37, 'X'),
-    (0x11D3A, 'V'),
-    (0x11D3B, 'X'),
-    (0x11D3C, 'V'),
-    (0x11D3E, 'X'),
-    (0x11D3F, 'V'),
-    (0x11D48, 'X'),
-    (0x11D50, 'V'),
-    (0x11D5A, 'X'),
-    (0x11D60, 'V'),
-    (0x11D66, 'X'),
-    (0x11D67, 'V'),
-    (0x11D69, 'X'),
-    (0x11D6A, 'V'),
-    (0x11D8F, 'X'),
-    (0x11D90, 'V'),
-    (0x11D92, 'X'),
-    (0x11D93, 'V'),
-    (0x11D99, 'X'),
-    (0x11DA0, 'V'),
-    (0x11DAA, 'X'),
-    (0x11EE0, 'V'),
-    (0x11EF9, 'X'),
-    (0x11FB0, 'V'),
-    (0x11FB1, 'X'),
-    (0x11FC0, 'V'),
-    ]
-
-def _seg_59() -> List[Union[Tuple[int, str], Tuple[int, str, str]]]:
-    return [
-    (0x11FF2, 'X'),
-    (0x11FFF, 'V'),
-    (0x1239A, 'X'),
-    (0x12400, 'V'),
-    (0x1246F, 'X'),
-    (0x12470, 'V'),
-    (0x12475, 'X'),
-    (0x12480, 'V'),
-    (0x12544, 'X'),
-    (0x12F90, 'V'),
-    (0x12FF3, 'X'),
-    (0x13000, 'V'),
-    (0x1342F, 'X'),
-    (0x14400, 'V'),
-    (0x14647, 'X'),
-    (0x16800, 'V'),
-    (0x16A39, 'X'),
-    (0x16A40, 'V'),
-    (0x16A5F, 'X'),
-    (0x16A60, 'V'),
-    (0x16A6A, 'X'),
-    (0x16A6E, 'V'),
-    (0x16ABF, 'X'),
-    (0x16AC0, 'V'),
-    (0x16ACA, 'X'),
-    (0x16AD0, 'V'),
-    (0x16AEE, 'X'),
-    (0x16AF0, 'V'),
-    (0x16AF6, 'X'),
-    (0x16B00, 'V'),
-    (0x16B46, 'X'),
-    (0x16B50, 'V'),
-    (0x16B5A, 'X'),
-    (0x16B5B, 'V'),
-    (0x16B62, 'X'),
-    (0x16B63, 'V'),
-    (0x16B78, 'X'),
-    (0x16B7D, 'V'),
-    (0x16B90, 'X'),
-    (0x16E40, 'M', '𖹠'),
-    (0x16E41, 'M', '𖹡'),
-    (0x16E42, 'M', '𖹢'),
-    (0x16E43, 'M', '𖹣'),
-    (0x16E44, 'M', '𖹤'),
-    (0x16E45, 'M', '𖹥'),
-    (0x16E46, 'M', '𖹦'),
-    (0x16E47, 'M', '𖹧'),
-    (0x16E48, 'M', '𖹨'),
-    (0x16E49, 'M', '𖹩'),
-    (0x16E4A, 'M', '𖹪'),
-    (0x16E4B, 'M', '𖹫'),
-    (0x16E4C, 'M', '𖹬'),
-    (0x16E4D, 'M', '𖹭'),
-    (0x16E4E, 'M', '𖹮'),
-    (0x16E4F, 'M', '𖹯'),
-    (0x16E50, 'M', '𖹰'),
-    (0x16E51, 'M', '𖹱'),
-    (0x16E52, 'M', '𖹲'),
-    (0x16E53, 'M', '𖹳'),
-    (0x16E54, 'M', '𖹴'),
-    (0x16E55, 'M', '𖹵'),
-    (0x16E56, 'M', '𖹶'),
-    (0x16E57, 'M', '𖹷'),
-    (0x16E58, 'M', '𖹸'),
-    (0x16E59, 'M', '𖹹'),
-    (0x16E5A, 'M', '𖹺'),
-    (0x16E5B, 'M', '𖹻'),
-    (0x16E5C, 'M', '𖹼'),
-    (0x16E5D, 'M', '𖹽'),
-    (0x16E5E, 'M', '𖹾'),
-    (0x16E5F, 'M', '𖹿'),
-    (0x16E60, 'V'),
-    (0x16E9B, 'X'),
-    (0x16F00, 'V'),
-    (0x16F4B, 'X'),
-    (0x16F4F, 'V'),
-    (0x16F88, 'X'),
-    (0x16F8F, 'V'),
-    (0x16FA0, 'X'),
-    (0x16FE0, 'V'),
-    (0x16FE5, 'X'),
-    (0x16FF0, 'V'),
-    (0x16FF2, 'X'),
-    (0x17000, 'V'),
-    (0x187F8, 'X'),
-    (0x18800, 'V'),
-    (0x18CD6, 'X'),
-    (0x18D00, 'V'),
-    (0x18D09, 'X'),
-    (0x1AFF0, 'V'),
-    (0x1AFF4, 'X'),
-    (0x1AFF5, 'V'),
-    (0x1AFFC, 'X'),
-    (0x1AFFD, 'V'),
-    (0x1AFFF, 'X'),
-    (0x1B000, 'V'),
-    (0x1B123, 'X'),
-    (0x1B150, 'V'),
-    (0x1B153, 'X'),
-    (0x1B164, 'V'),
-    ]
-
-def _seg_60() -> List[Union[Tuple[int, str], Tuple[int, str, str]]]:
-    return [
-    (0x1B168, 'X'),
-    (0x1B170, 'V'),
-    (0x1B2FC, 'X'),
-    (0x1BC00, 'V'),
-    (0x1BC6B, 'X'),
-    (0x1BC70, 'V'),
-    (0x1BC7D, 'X'),
-    (0x1BC80, 'V'),
-    (0x1BC89, 'X'),
-    (0x1BC90, 'V'),
-    (0x1BC9A, 'X'),
-    (0x1BC9C, 'V'),
-    (0x1BCA0, 'I'),
-    (0x1BCA4, 'X'),
-    (0x1CF00, 'V'),
-    (0x1CF2E, 'X'),
-    (0x1CF30, 'V'),
-    (0x1CF47, 'X'),
-    (0x1CF50, 'V'),
-    (0x1CFC4, 'X'),
-    (0x1D000, 'V'),
-    (0x1D0F6, 'X'),
-    (0x1D100, 'V'),
-    (0x1D127, 'X'),
-    (0x1D129, 'V'),
-    (0x1D15E, 'M', '𝅗𝅥'),
-    (0x1D15F, 'M', '𝅘𝅥'),
-    (0x1D160, 'M', '𝅘𝅥𝅮'),
-    (0x1D161, 'M', '𝅘𝅥𝅯'),
-    (0x1D162, 'M', '𝅘𝅥𝅰'),
-    (0x1D163, 'M', '𝅘𝅥𝅱'),
-    (0x1D164, 'M', '𝅘𝅥𝅲'),
-    (0x1D165, 'V'),
-    (0x1D173, 'X'),
-    (0x1D17B, 'V'),
-    (0x1D1BB, 'M', '𝆹𝅥'),
-    (0x1D1BC, 'M', '𝆺𝅥'),
-    (0x1D1BD, 'M', '𝆹𝅥𝅮'),
-    (0x1D1BE, 'M', '𝆺𝅥𝅮'),
-    (0x1D1BF, 'M', '𝆹𝅥𝅯'),
-    (0x1D1C0, 'M', '𝆺𝅥𝅯'),
-    (0x1D1C1, 'V'),
-    (0x1D1EB, 'X'),
-    (0x1D200, 'V'),
-    (0x1D246, 'X'),
-    (0x1D2E0, 'V'),
-    (0x1D2F4, 'X'),
-    (0x1D300, 'V'),
-    (0x1D357, 'X'),
-    (0x1D360, 'V'),
-    (0x1D379, 'X'),
-    (0x1D400, 'M', 'a'),
-    (0x1D401, 'M', 'b'),
-    (0x1D402, 'M', 'c'),
-    (0x1D403, 'M', 'd'),
-    (0x1D404, 'M', 'e'),
-    (0x1D405, 'M', 'f'),
-    (0x1D406, 'M', 'g'),
-    (0x1D407, 'M', 'h'),
-    (0x1D408, 'M', 'i'),
-    (0x1D409, 'M', 'j'),
-    (0x1D40A, 'M', 'k'),
-    (0x1D40B, 'M', 'l'),
-    (0x1D40C, 'M', 'm'),
-    (0x1D40D, 'M', 'n'),
-    (0x1D40E, 'M', 'o'),
-    (0x1D40F, 'M', 'p'),
-    (0x1D410, 'M', 'q'),
-    (0x1D411, 'M', 'r'),
-    (0x1D412, 'M', 's'),
-    (0x1D413, 'M', 't'),
-    (0x1D414, 'M', 'u'),
-    (0x1D415, 'M', 'v'),
-    (0x1D416, 'M', 'w'),
-    (0x1D417, 'M', 'x'),
-    (0x1D418, 'M', 'y'),
-    (0x1D419, 'M', 'z'),
-    (0x1D41A, 'M', 'a'),
-    (0x1D41B, 'M', 'b'),
-    (0x1D41C, 'M', 'c'),
-    (0x1D41D, 'M', 'd'),
-    (0x1D41E, 'M', 'e'),
-    (0x1D41F, 'M', 'f'),
-    (0x1D420, 'M', 'g'),
-    (0x1D421, 'M', 'h'),
-    (0x1D422, 'M', 'i'),
-    (0x1D423, 'M', 'j'),
-    (0x1D424, 'M', 'k'),
-    (0x1D425, 'M', 'l'),
-    (0x1D426, 'M', 'm'),
-    (0x1D427, 'M', 'n'),
-    (0x1D428, 'M', 'o'),
-    (0x1D429, 'M', 'p'),
-    (0x1D42A, 'M', 'q'),
-    (0x1D42B, 'M', 'r'),
-    (0x1D42C, 'M', 's'),
-    (0x1D42D, 'M', 't'),
-    (0x1D42E, 'M', 'u'),
-    (0x1D42F, 'M', 'v'),
-    (0x1D430, 'M', 'w'),
-    ]
-
-def _seg_61() -> List[Union[Tuple[int, str], Tuple[int, str, str]]]:
-    return [
-    (0x1D431, 'M', 'x'),
-    (0x1D432, 'M', 'y'),
-    (0x1D433, 'M', 'z'),
-    (0x1D434, 'M', 'a'),
-    (0x1D435, 'M', 'b'),
-    (0x1D436, 'M', 'c'),
-    (0x1D437, 'M', 'd'),
-    (0x1D438, 'M', 'e'),
-    (0x1D439, 'M', 'f'),
-    (0x1D43A, 'M', 'g'),
-    (0x1D43B, 'M', 'h'),
-    (0x1D43C, 'M', 'i'),
-    (0x1D43D, 'M', 'j'),
-    (0x1D43E, 'M', 'k'),
-    (0x1D43F, 'M', 'l'),
-    (0x1D440, 'M', 'm'),
-    (0x1D441, 'M', 'n'),
-    (0x1D442, 'M', 'o'),
-    (0x1D443, 'M', 'p'),
-    (0x1D444, 'M', 'q'),
-    (0x1D445, 'M', 'r'),
-    (0x1D446, 'M', 's'),
-    (0x1D447, 'M', 't'),
-    (0x1D448, 'M', 'u'),
-    (0x1D449, 'M', 'v'),
-    (0x1D44A, 'M', 'w'),
-    (0x1D44B, 'M', 'x'),
-    (0x1D44C, 'M', 'y'),
-    (0x1D44D, 'M', 'z'),
-    (0x1D44E, 'M', 'a'),
-    (0x1D44F, 'M', 'b'),
-    (0x1D450, 'M', 'c'),
-    (0x1D451, 'M', 'd'),
-    (0x1D452, 'M', 'e'),
-    (0x1D453, 'M', 'f'),
-    (0x1D454, 'M', 'g'),
-    (0x1D455, 'X'),
-    (0x1D456, 'M', 'i'),
-    (0x1D457, 'M', 'j'),
-    (0x1D458, 'M', 'k'),
-    (0x1D459, 'M', 'l'),
-    (0x1D45A, 'M', 'm'),
-    (0x1D45B, 'M', 'n'),
-    (0x1D45C, 'M', 'o'),
-    (0x1D45D, 'M', 'p'),
-    (0x1D45E, 'M', 'q'),
-    (0x1D45F, 'M', 'r'),
-    (0x1D460, 'M', 's'),
-    (0x1D461, 'M', 't'),
-    (0x1D462, 'M', 'u'),
-    (0x1D463, 'M', 'v'),
-    (0x1D464, 'M', 'w'),
-    (0x1D465, 'M', 'x'),
-    (0x1D466, 'M', 'y'),
-    (0x1D467, 'M', 'z'),
-    (0x1D468, 'M', 'a'),
-    (0x1D469, 'M', 'b'),
-    (0x1D46A, 'M', 'c'),
-    (0x1D46B, 'M', 'd'),
-    (0x1D46C, 'M', 'e'),
-    (0x1D46D, 'M', 'f'),
-    (0x1D46E, 'M', 'g'),
-    (0x1D46F, 'M', 'h'),
-    (0x1D470, 'M', 'i'),
-    (0x1D471, 'M', 'j'),
-    (0x1D472, 'M', 'k'),
-    (0x1D473, 'M', 'l'),
-    (0x1D474, 'M', 'm'),
-    (0x1D475, 'M', 'n'),
-    (0x1D476, 'M', 'o'),
-    (0x1D477, 'M', 'p'),
-    (0x1D478, 'M', 'q'),
-    (0x1D479, 'M', 'r'),
-    (0x1D47A, 'M', 's'),
-    (0x1D47B, 'M', 't'),
-    (0x1D47C, 'M', 'u'),
-    (0x1D47D, 'M', 'v'),
-    (0x1D47E, 'M', 'w'),
-    (0x1D47F, 'M', 'x'),
-    (0x1D480, 'M', 'y'),
-    (0x1D481, 'M', 'z'),
-    (0x1D482, 'M', 'a'),
-    (0x1D483, 'M', 'b'),
-    (0x1D484, 'M', 'c'),
-    (0x1D485, 'M', 'd'),
-    (0x1D486, 'M', 'e'),
-    (0x1D487, 'M', 'f'),
-    (0x1D488, 'M', 'g'),
-    (0x1D489, 'M', 'h'),
-    (0x1D48A, 'M', 'i'),
-    (0x1D48B, 'M', 'j'),
-    (0x1D48C, 'M', 'k'),
-    (0x1D48D, 'M', 'l'),
-    (0x1D48E, 'M', 'm'),
-    (0x1D48F, 'M', 'n'),
-    (0x1D490, 'M', 'o'),
-    (0x1D491, 'M', 'p'),
-    (0x1D492, 'M', 'q'),
-    (0x1D493, 'M', 'r'),
-    (0x1D494, 'M', 's'),
-    ]
-
-def _seg_62() -> List[Union[Tuple[int, str], Tuple[int, str, str]]]:
-    return [
-    (0x1D495, 'M', 't'),
-    (0x1D496, 'M', 'u'),
-    (0x1D497, 'M', 'v'),
-    (0x1D498, 'M', 'w'),
-    (0x1D499, 'M', 'x'),
-    (0x1D49A, 'M', 'y'),
-    (0x1D49B, 'M', 'z'),
-    (0x1D49C, 'M', 'a'),
-    (0x1D49D, 'X'),
-    (0x1D49E, 'M', 'c'),
-    (0x1D49F, 'M', 'd'),
-    (0x1D4A0, 'X'),
-    (0x1D4A2, 'M', 'g'),
-    (0x1D4A3, 'X'),
-    (0x1D4A5, 'M', 'j'),
-    (0x1D4A6, 'M', 'k'),
-    (0x1D4A7, 'X'),
-    (0x1D4A9, 'M', 'n'),
-    (0x1D4AA, 'M', 'o'),
-    (0x1D4AB, 'M', 'p'),
-    (0x1D4AC, 'M', 'q'),
-    (0x1D4AD, 'X'),
-    (0x1D4AE, 'M', 's'),
-    (0x1D4AF, 'M', 't'),
-    (0x1D4B0, 'M', 'u'),
-    (0x1D4B1, 'M', 'v'),
-    (0x1D4B2, 'M', 'w'),
-    (0x1D4B3, 'M', 'x'),
-    (0x1D4B4, 'M', 'y'),
-    (0x1D4B5, 'M', 'z'),
-    (0x1D4B6, 'M', 'a'),
-    (0x1D4B7, 'M', 'b'),
-    (0x1D4B8, 'M', 'c'),
-    (0x1D4B9, 'M', 'd'),
-    (0x1D4BA, 'X'),
-    (0x1D4BB, 'M', 'f'),
-    (0x1D4BC, 'X'),
-    (0x1D4BD, 'M', 'h'),
-    (0x1D4BE, 'M', 'i'),
-    (0x1D4BF, 'M', 'j'),
-    (0x1D4C0, 'M', 'k'),
-    (0x1D4C1, 'M', 'l'),
-    (0x1D4C2, 'M', 'm'),
-    (0x1D4C3, 'M', 'n'),
-    (0x1D4C4, 'X'),
-    (0x1D4C5, 'M', 'p'),
-    (0x1D4C6, 'M', 'q'),
-    (0x1D4C7, 'M', 'r'),
-    (0x1D4C8, 'M', 's'),
-    (0x1D4C9, 'M', 't'),
-    (0x1D4CA, 'M', 'u'),
-    (0x1D4CB, 'M', 'v'),
-    (0x1D4CC, 'M', 'w'),
-    (0x1D4CD, 'M', 'x'),
-    (0x1D4CE, 'M', 'y'),
-    (0x1D4CF, 'M', 'z'),
-    (0x1D4D0, 'M', 'a'),
-    (0x1D4D1, 'M', 'b'),
-    (0x1D4D2, 'M', 'c'),
-    (0x1D4D3, 'M', 'd'),
-    (0x1D4D4, 'M', 'e'),
-    (0x1D4D5, 'M', 'f'),
-    (0x1D4D6, 'M', 'g'),
-    (0x1D4D7, 'M', 'h'),
-    (0x1D4D8, 'M', 'i'),
-    (0x1D4D9, 'M', 'j'),
-    (0x1D4DA, 'M', 'k'),
-    (0x1D4DB, 'M', 'l'),
-    (0x1D4DC, 'M', 'm'),
-    (0x1D4DD, 'M', 'n'),
-    (0x1D4DE, 'M', 'o'),
-    (0x1D4DF, 'M', 'p'),
-    (0x1D4E0, 'M', 'q'),
-    (0x1D4E1, 'M', 'r'),
-    (0x1D4E2, 'M', 's'),
-    (0x1D4E3, 'M', 't'),
-    (0x1D4E4, 'M', 'u'),
-    (0x1D4E5, 'M', 'v'),
-    (0x1D4E6, 'M', 'w'),
-    (0x1D4E7, 'M', 'x'),
-    (0x1D4E8, 'M', 'y'),
-    (0x1D4E9, 'M', 'z'),
-    (0x1D4EA, 'M', 'a'),
-    (0x1D4EB, 'M', 'b'),
-    (0x1D4EC, 'M', 'c'),
-    (0x1D4ED, 'M', 'd'),
-    (0x1D4EE, 'M', 'e'),
-    (0x1D4EF, 'M', 'f'),
-    (0x1D4F0, 'M', 'g'),
-    (0x1D4F1, 'M', 'h'),
-    (0x1D4F2, 'M', 'i'),
-    (0x1D4F3, 'M', 'j'),
-    (0x1D4F4, 'M', 'k'),
-    (0x1D4F5, 'M', 'l'),
-    (0x1D4F6, 'M', 'm'),
-    (0x1D4F7, 'M', 'n'),
-    (0x1D4F8, 'M', 'o'),
-    (0x1D4F9, 'M', 'p'),
-    (0x1D4FA, 'M', 'q'),
-    (0x1D4FB, 'M', 'r'),
-    ]
-
-def _seg_63() -> List[Union[Tuple[int, str], Tuple[int, str, str]]]:
-    return [
-    (0x1D4FC, 'M', 's'),
-    (0x1D4FD, 'M', 't'),
-    (0x1D4FE, 'M', 'u'),
-    (0x1D4FF, 'M', 'v'),
-    (0x1D500, 'M', 'w'),
-    (0x1D501, 'M', 'x'),
-    (0x1D502, 'M', 'y'),
-    (0x1D503, 'M', 'z'),
-    (0x1D504, 'M', 'a'),
-    (0x1D505, 'M', 'b'),
-    (0x1D506, 'X'),
-    (0x1D507, 'M', 'd'),
-    (0x1D508, 'M', 'e'),
-    (0x1D509, 'M', 'f'),
-    (0x1D50A, 'M', 'g'),
-    (0x1D50B, 'X'),
-    (0x1D50D, 'M', 'j'),
-    (0x1D50E, 'M', 'k'),
-    (0x1D50F, 'M', 'l'),
-    (0x1D510, 'M', 'm'),
-    (0x1D511, 'M', 'n'),
-    (0x1D512, 'M', 'o'),
-    (0x1D513, 'M', 'p'),
-    (0x1D514, 'M', 'q'),
-    (0x1D515, 'X'),
-    (0x1D516, 'M', 's'),
-    (0x1D517, 'M', 't'),
-    (0x1D518, 'M', 'u'),
-    (0x1D519, 'M', 'v'),
-    (0x1D51A, 'M', 'w'),
-    (0x1D51B, 'M', 'x'),
-    (0x1D51C, 'M', 'y'),
-    (0x1D51D, 'X'),
-    (0x1D51E, 'M', 'a'),
-    (0x1D51F, 'M', 'b'),
-    (0x1D520, 'M', 'c'),
-    (0x1D521, 'M', 'd'),
-    (0x1D522, 'M', 'e'),
-    (0x1D523, 'M', 'f'),
-    (0x1D524, 'M', 'g'),
-    (0x1D525, 'M', 'h'),
-    (0x1D526, 'M', 'i'),
-    (0x1D527, 'M', 'j'),
-    (0x1D528, 'M', 'k'),
-    (0x1D529, 'M', 'l'),
-    (0x1D52A, 'M', 'm'),
-    (0x1D52B, 'M', 'n'),
-    (0x1D52C, 'M', 'o'),
-    (0x1D52D, 'M', 'p'),
-    (0x1D52E, 'M', 'q'),
-    (0x1D52F, 'M', 'r'),
-    (0x1D530, 'M', 's'),
-    (0x1D531, 'M', 't'),
-    (0x1D532, 'M', 'u'),
-    (0x1D533, 'M', 'v'),
-    (0x1D534, 'M', 'w'),
-    (0x1D535, 'M', 'x'),
-    (0x1D536, 'M', 'y'),
-    (0x1D537, 'M', 'z'),
-    (0x1D538, 'M', 'a'),
-    (0x1D539, 'M', 'b'),
-    (0x1D53A, 'X'),
-    (0x1D53B, 'M', 'd'),
-    (0x1D53C, 'M', 'e'),
-    (0x1D53D, 'M', 'f'),
-    (0x1D53E, 'M', 'g'),
-    (0x1D53F, 'X'),
-    (0x1D540, 'M', 'i'),
-    (0x1D541, 'M', 'j'),
-    (0x1D542, 'M', 'k'),
-    (0x1D543, 'M', 'l'),
-    (0x1D544, 'M', 'm'),
-    (0x1D545, 'X'),
-    (0x1D546, 'M', 'o'),
-    (0x1D547, 'X'),
-    (0x1D54A, 'M', 's'),
-    (0x1D54B, 'M', 't'),
-    (0x1D54C, 'M', 'u'),
-    (0x1D54D, 'M', 'v'),
-    (0x1D54E, 'M', 'w'),
-    (0x1D54F, 'M', 'x'),
-    (0x1D550, 'M', 'y'),
-    (0x1D551, 'X'),
-    (0x1D552, 'M', 'a'),
-    (0x1D553, 'M', 'b'),
-    (0x1D554, 'M', 'c'),
-    (0x1D555, 'M', 'd'),
-    (0x1D556, 'M', 'e'),
-    (0x1D557, 'M', 'f'),
-    (0x1D558, 'M', 'g'),
-    (0x1D559, 'M', 'h'),
-    (0x1D55A, 'M', 'i'),
-    (0x1D55B, 'M', 'j'),
-    (0x1D55C, 'M', 'k'),
-    (0x1D55D, 'M', 'l'),
-    (0x1D55E, 'M', 'm'),
-    (0x1D55F, 'M', 'n'),
-    (0x1D560, 'M', 'o'),
-    (0x1D561, 'M', 'p'),
-    (0x1D562, 'M', 'q'),
-    ]
-
-def _seg_64() -> List[Union[Tuple[int, str], Tuple[int, str, str]]]:
-    return [
-    (0x1D563, 'M', 'r'),
-    (0x1D564, 'M', 's'),
-    (0x1D565, 'M', 't'),
-    (0x1D566, 'M', 'u'),
-    (0x1D567, 'M', 'v'),
-    (0x1D568, 'M', 'w'),
-    (0x1D569, 'M', 'x'),
-    (0x1D56A, 'M', 'y'),
-    (0x1D56B, 'M', 'z'),
-    (0x1D56C, 'M', 'a'),
-    (0x1D56D, 'M', 'b'),
-    (0x1D56E, 'M', 'c'),
-    (0x1D56F, 'M', 'd'),
-    (0x1D570, 'M', 'e'),
-    (0x1D571, 'M', 'f'),
-    (0x1D572, 'M', 'g'),
-    (0x1D573, 'M', 'h'),
-    (0x1D574, 'M', 'i'),
-    (0x1D575, 'M', 'j'),
-    (0x1D576, 'M', 'k'),
-    (0x1D577, 'M', 'l'),
-    (0x1D578, 'M', 'm'),
-    (0x1D579, 'M', 'n'),
-    (0x1D57A, 'M', 'o'),
-    (0x1D57B, 'M', 'p'),
-    (0x1D57C, 'M', 'q'),
-    (0x1D57D, 'M', 'r'),
-    (0x1D57E, 'M', 's'),
-    (0x1D57F, 'M', 't'),
-    (0x1D580, 'M', 'u'),
-    (0x1D581, 'M', 'v'),
-    (0x1D582, 'M', 'w'),
-    (0x1D583, 'M', 'x'),
-    (0x1D584, 'M', 'y'),
-    (0x1D585, 'M', 'z'),
-    (0x1D586, 'M', 'a'),
-    (0x1D587, 'M', 'b'),
-    (0x1D588, 'M', 'c'),
-    (0x1D589, 'M', 'd'),
-    (0x1D58A, 'M', 'e'),
-    (0x1D58B, 'M', 'f'),
-    (0x1D58C, 'M', 'g'),
-    (0x1D58D, 'M', 'h'),
-    (0x1D58E, 'M', 'i'),
-    (0x1D58F, 'M', 'j'),
-    (0x1D590, 'M', 'k'),
-    (0x1D591, 'M', 'l'),
-    (0x1D592, 'M', 'm'),
-    (0x1D593, 'M', 'n'),
-    (0x1D594, 'M', 'o'),
-    (0x1D595, 'M', 'p'),
-    (0x1D596, 'M', 'q'),
-    (0x1D597, 'M', 'r'),
-    (0x1D598, 'M', 's'),
-    (0x1D599, 'M', 't'),
-    (0x1D59A, 'M', 'u'),
-    (0x1D59B, 'M', 'v'),
-    (0x1D59C, 'M', 'w'),
-    (0x1D59D, 'M', 'x'),
-    (0x1D59E, 'M', 'y'),
-    (0x1D59F, 'M', 'z'),
-    (0x1D5A0, 'M', 'a'),
-    (0x1D5A1, 'M', 'b'),
-    (0x1D5A2, 'M', 'c'),
-    (0x1D5A3, 'M', 'd'),
-    (0x1D5A4, 'M', 'e'),
-    (0x1D5A5, 'M', 'f'),
-    (0x1D5A6, 'M', 'g'),
-    (0x1D5A7, 'M', 'h'),
-    (0x1D5A8, 'M', 'i'),
-    (0x1D5A9, 'M', 'j'),
-    (0x1D5AA, 'M', 'k'),
-    (0x1D5AB, 'M', 'l'),
-    (0x1D5AC, 'M', 'm'),
-    (0x1D5AD, 'M', 'n'),
-    (0x1D5AE, 'M', 'o'),
-    (0x1D5AF, 'M', 'p'),
-    (0x1D5B0, 'M', 'q'),
-    (0x1D5B1, 'M', 'r'),
-    (0x1D5B2, 'M', 's'),
-    (0x1D5B3, 'M', 't'),
-    (0x1D5B4, 'M', 'u'),
-    (0x1D5B5, 'M', 'v'),
-    (0x1D5B6, 'M', 'w'),
-    (0x1D5B7, 'M', 'x'),
-    (0x1D5B8, 'M', 'y'),
-    (0x1D5B9, 'M', 'z'),
-    (0x1D5BA, 'M', 'a'),
-    (0x1D5BB, 'M', 'b'),
-    (0x1D5BC, 'M', 'c'),
-    (0x1D5BD, 'M', 'd'),
-    (0x1D5BE, 'M', 'e'),
-    (0x1D5BF, 'M', 'f'),
-    (0x1D5C0, 'M', 'g'),
-    (0x1D5C1, 'M', 'h'),
-    (0x1D5C2, 'M', 'i'),
-    (0x1D5C3, 'M', 'j'),
-    (0x1D5C4, 'M', 'k'),
-    (0x1D5C5, 'M', 'l'),
-    (0x1D5C6, 'M', 'm'),
-    ]
-
-def _seg_65() -> List[Union[Tuple[int, str], Tuple[int, str, str]]]:
-    return [
-    (0x1D5C7, 'M', 'n'),
-    (0x1D5C8, 'M', 'o'),
-    (0x1D5C9, 'M', 'p'),
-    (0x1D5CA, 'M', 'q'),
-    (0x1D5CB, 'M', 'r'),
-    (0x1D5CC, 'M', 's'),
-    (0x1D5CD, 'M', 't'),
-    (0x1D5CE, 'M', 'u'),
-    (0x1D5CF, 'M', 'v'),
-    (0x1D5D0, 'M', 'w'),
-    (0x1D5D1, 'M', 'x'),
-    (0x1D5D2, 'M', 'y'),
-    (0x1D5D3, 'M', 'z'),
-    (0x1D5D4, 'M', 'a'),
-    (0x1D5D5, 'M', 'b'),
-    (0x1D5D6, 'M', 'c'),
-    (0x1D5D7, 'M', 'd'),
-    (0x1D5D8, 'M', 'e'),
-    (0x1D5D9, 'M', 'f'),
-    (0x1D5DA, 'M', 'g'),
-    (0x1D5DB, 'M', 'h'),
-    (0x1D5DC, 'M', 'i'),
-    (0x1D5DD, 'M', 'j'),
-    (0x1D5DE, 'M', 'k'),
-    (0x1D5DF, 'M', 'l'),
-    (0x1D5E0, 'M', 'm'),
-    (0x1D5E1, 'M', 'n'),
-    (0x1D5E2, 'M', 'o'),
-    (0x1D5E3, 'M', 'p'),
-    (0x1D5E4, 'M', 'q'),
-    (0x1D5E5, 'M', 'r'),
-    (0x1D5E6, 'M', 's'),
-    (0x1D5E7, 'M', 't'),
-    (0x1D5E8, 'M', 'u'),
-    (0x1D5E9, 'M', 'v'),
-    (0x1D5EA, 'M', 'w'),
-    (0x1D5EB, 'M', 'x'),
-    (0x1D5EC, 'M', 'y'),
-    (0x1D5ED, 'M', 'z'),
-    (0x1D5EE, 'M', 'a'),
-    (0x1D5EF, 'M', 'b'),
-    (0x1D5F0, 'M', 'c'),
-    (0x1D5F1, 'M', 'd'),
-    (0x1D5F2, 'M', 'e'),
-    (0x1D5F3, 'M', 'f'),
-    (0x1D5F4, 'M', 'g'),
-    (0x1D5F5, 'M', 'h'),
-    (0x1D5F6, 'M', 'i'),
-    (0x1D5F7, 'M', 'j'),
-    (0x1D5F8, 'M', 'k'),
-    (0x1D5F9, 'M', 'l'),
-    (0x1D5FA, 'M', 'm'),
-    (0x1D5FB, 'M', 'n'),
-    (0x1D5FC, 'M', 'o'),
-    (0x1D5FD, 'M', 'p'),
-    (0x1D5FE, 'M', 'q'),
-    (0x1D5FF, 'M', 'r'),
-    (0x1D600, 'M', 's'),
-    (0x1D601, 'M', 't'),
-    (0x1D602, 'M', 'u'),
-    (0x1D603, 'M', 'v'),
-    (0x1D604, 'M', 'w'),
-    (0x1D605, 'M', 'x'),
-    (0x1D606, 'M', 'y'),
-    (0x1D607, 'M', 'z'),
-    (0x1D608, 'M', 'a'),
-    (0x1D609, 'M', 'b'),
-    (0x1D60A, 'M', 'c'),
-    (0x1D60B, 'M', 'd'),
-    (0x1D60C, 'M', 'e'),
-    (0x1D60D, 'M', 'f'),
-    (0x1D60E, 'M', 'g'),
-    (0x1D60F, 'M', 'h'),
-    (0x1D610, 'M', 'i'),
-    (0x1D611, 'M', 'j'),
-    (0x1D612, 'M', 'k'),
-    (0x1D613, 'M', 'l'),
-    (0x1D614, 'M', 'm'),
-    (0x1D615, 'M', 'n'),
-    (0x1D616, 'M', 'o'),
-    (0x1D617, 'M', 'p'),
-    (0x1D618, 'M', 'q'),
-    (0x1D619, 'M', 'r'),
-    (0x1D61A, 'M', 's'),
-    (0x1D61B, 'M', 't'),
-    (0x1D61C, 'M', 'u'),
-    (0x1D61D, 'M', 'v'),
-    (0x1D61E, 'M', 'w'),
-    (0x1D61F, 'M', 'x'),
-    (0x1D620, 'M', 'y'),
-    (0x1D621, 'M', 'z'),
-    (0x1D622, 'M', 'a'),
-    (0x1D623, 'M', 'b'),
-    (0x1D624, 'M', 'c'),
-    (0x1D625, 'M', 'd'),
-    (0x1D626, 'M', 'e'),
-    (0x1D627, 'M', 'f'),
-    (0x1D628, 'M', 'g'),
-    (0x1D629, 'M', 'h'),
-    (0x1D62A, 'M', 'i'),
-    ]
-
-def _seg_66() -> List[Union[Tuple[int, str], Tuple[int, str, str]]]:
-    return [
-    (0x1D62B, 'M', 'j'),
-    (0x1D62C, 'M', 'k'),
-    (0x1D62D, 'M', 'l'),
-    (0x1D62E, 'M', 'm'),
-    (0x1D62F, 'M', 'n'),
-    (0x1D630, 'M', 'o'),
-    (0x1D631, 'M', 'p'),
-    (0x1D632, 'M', 'q'),
-    (0x1D633, 'M', 'r'),
-    (0x1D634, 'M', 's'),
-    (0x1D635, 'M', 't'),
-    (0x1D636, 'M', 'u'),
-    (0x1D637, 'M', 'v'),
-    (0x1D638, 'M', 'w'),
-    (0x1D639, 'M', 'x'),
-    (0x1D63A, 'M', 'y'),
-    (0x1D63B, 'M', 'z'),
-    (0x1D63C, 'M', 'a'),
-    (0x1D63D, 'M', 'b'),
-    (0x1D63E, 'M', 'c'),
-    (0x1D63F, 'M', 'd'),
-    (0x1D640, 'M', 'e'),
-    (0x1D641, 'M', 'f'),
-    (0x1D642, 'M', 'g'),
-    (0x1D643, 'M', 'h'),
-    (0x1D644, 'M', 'i'),
-    (0x1D645, 'M', 'j'),
-    (0x1D646, 'M', 'k'),
-    (0x1D647, 'M', 'l'),
-    (0x1D648, 'M', 'm'),
-    (0x1D649, 'M', 'n'),
-    (0x1D64A, 'M', 'o'),
-    (0x1D64B, 'M', 'p'),
-    (0x1D64C, 'M', 'q'),
-    (0x1D64D, 'M', 'r'),
-    (0x1D64E, 'M', 's'),
-    (0x1D64F, 'M', 't'),
-    (0x1D650, 'M', 'u'),
-    (0x1D651, 'M', 'v'),
-    (0x1D652, 'M', 'w'),
-    (0x1D653, 'M', 'x'),
-    (0x1D654, 'M', 'y'),
-    (0x1D655, 'M', 'z'),
-    (0x1D656, 'M', 'a'),
-    (0x1D657, 'M', 'b'),
-    (0x1D658, 'M', 'c'),
-    (0x1D659, 'M', 'd'),
-    (0x1D65A, 'M', 'e'),
-    (0x1D65B, 'M', 'f'),
-    (0x1D65C, 'M', 'g'),
-    (0x1D65D, 'M', 'h'),
-    (0x1D65E, 'M', 'i'),
-    (0x1D65F, 'M', 'j'),
-    (0x1D660, 'M', 'k'),
-    (0x1D661, 'M', 'l'),
-    (0x1D662, 'M', 'm'),
-    (0x1D663, 'M', 'n'),
-    (0x1D664, 'M', 'o'),
-    (0x1D665, 'M', 'p'),
-    (0x1D666, 'M', 'q'),
-    (0x1D667, 'M', 'r'),
-    (0x1D668, 'M', 's'),
-    (0x1D669, 'M', 't'),
-    (0x1D66A, 'M', 'u'),
-    (0x1D66B, 'M', 'v'),
-    (0x1D66C, 'M', 'w'),
-    (0x1D66D, 'M', 'x'),
-    (0x1D66E, 'M', 'y'),
-    (0x1D66F, 'M', 'z'),
-    (0x1D670, 'M', 'a'),
-    (0x1D671, 'M', 'b'),
-    (0x1D672, 'M', 'c'),
-    (0x1D673, 'M', 'd'),
-    (0x1D674, 'M', 'e'),
-    (0x1D675, 'M', 'f'),
-    (0x1D676, 'M', 'g'),
-    (0x1D677, 'M', 'h'),
-    (0x1D678, 'M', 'i'),
-    (0x1D679, 'M', 'j'),
-    (0x1D67A, 'M', 'k'),
-    (0x1D67B, 'M', 'l'),
-    (0x1D67C, 'M', 'm'),
-    (0x1D67D, 'M', 'n'),
-    (0x1D67E, 'M', 'o'),
-    (0x1D67F, 'M', 'p'),
-    (0x1D680, 'M', 'q'),
-    (0x1D681, 'M', 'r'),
-    (0x1D682, 'M', 's'),
-    (0x1D683, 'M', 't'),
-    (0x1D684, 'M', 'u'),
-    (0x1D685, 'M', 'v'),
-    (0x1D686, 'M', 'w'),
-    (0x1D687, 'M', 'x'),
-    (0x1D688, 'M', 'y'),
-    (0x1D689, 'M', 'z'),
-    (0x1D68A, 'M', 'a'),
-    (0x1D68B, 'M', 'b'),
-    (0x1D68C, 'M', 'c'),
-    (0x1D68D, 'M', 'd'),
-    (0x1D68E, 'M', 'e'),
-    ]
-
-def _seg_67() -> List[Union[Tuple[int, str], Tuple[int, str, str]]]:
-    return [
-    (0x1D68F, 'M', 'f'),
-    (0x1D690, 'M', 'g'),
-    (0x1D691, 'M', 'h'),
-    (0x1D692, 'M', 'i'),
-    (0x1D693, 'M', 'j'),
-    (0x1D694, 'M', 'k'),
-    (0x1D695, 'M', 'l'),
-    (0x1D696, 'M', 'm'),
-    (0x1D697, 'M', 'n'),
-    (0x1D698, 'M', 'o'),
-    (0x1D699, 'M', 'p'),
-    (0x1D69A, 'M', 'q'),
-    (0x1D69B, 'M', 'r'),
-    (0x1D69C, 'M', 's'),
-    (0x1D69D, 'M', 't'),
-    (0x1D69E, 'M', 'u'),
-    (0x1D69F, 'M', 'v'),
-    (0x1D6A0, 'M', 'w'),
-    (0x1D6A1, 'M', 'x'),
-    (0x1D6A2, 'M', 'y'),
-    (0x1D6A3, 'M', 'z'),
-    (0x1D6A4, 'M', 'ı'),
-    (0x1D6A5, 'M', 'ȷ'),
-    (0x1D6A6, 'X'),
-    (0x1D6A8, 'M', 'α'),
-    (0x1D6A9, 'M', 'β'),
-    (0x1D6AA, 'M', 'γ'),
-    (0x1D6AB, 'M', 'δ'),
-    (0x1D6AC, 'M', 'ε'),
-    (0x1D6AD, 'M', 'ζ'),
-    (0x1D6AE, 'M', 'η'),
-    (0x1D6AF, 'M', 'θ'),
-    (0x1D6B0, 'M', 'ι'),
-    (0x1D6B1, 'M', 'κ'),
-    (0x1D6B2, 'M', 'λ'),
-    (0x1D6B3, 'M', 'μ'),
-    (0x1D6B4, 'M', 'ν'),
-    (0x1D6B5, 'M', 'ξ'),
-    (0x1D6B6, 'M', 'ο'),
-    (0x1D6B7, 'M', 'π'),
-    (0x1D6B8, 'M', 'ρ'),
-    (0x1D6B9, 'M', 'θ'),
-    (0x1D6BA, 'M', 'σ'),
-    (0x1D6BB, 'M', 'τ'),
-    (0x1D6BC, 'M', 'υ'),
-    (0x1D6BD, 'M', 'φ'),
-    (0x1D6BE, 'M', 'χ'),
-    (0x1D6BF, 'M', 'ψ'),
-    (0x1D6C0, 'M', 'ω'),
-    (0x1D6C1, 'M', '∇'),
-    (0x1D6C2, 'M', 'α'),
-    (0x1D6C3, 'M', 'β'),
-    (0x1D6C4, 'M', 'γ'),
-    (0x1D6C5, 'M', 'δ'),
-    (0x1D6C6, 'M', 'ε'),
-    (0x1D6C7, 'M', 'ζ'),
-    (0x1D6C8, 'M', 'η'),
-    (0x1D6C9, 'M', 'θ'),
-    (0x1D6CA, 'M', 'ι'),
-    (0x1D6CB, 'M', 'κ'),
-    (0x1D6CC, 'M', 'λ'),
-    (0x1D6CD, 'M', 'μ'),
-    (0x1D6CE, 'M', 'ν'),
-    (0x1D6CF, 'M', 'ξ'),
-    (0x1D6D0, 'M', 'ο'),
-    (0x1D6D1, 'M', 'π'),
-    (0x1D6D2, 'M', 'ρ'),
-    (0x1D6D3, 'M', 'σ'),
-    (0x1D6D5, 'M', 'τ'),
-    (0x1D6D6, 'M', 'υ'),
-    (0x1D6D7, 'M', 'φ'),
-    (0x1D6D8, 'M', 'χ'),
-    (0x1D6D9, 'M', 'ψ'),
-    (0x1D6DA, 'M', 'ω'),
-    (0x1D6DB, 'M', '∂'),
-    (0x1D6DC, 'M', 'ε'),
-    (0x1D6DD, 'M', 'θ'),
-    (0x1D6DE, 'M', 'κ'),
-    (0x1D6DF, 'M', 'φ'),
-    (0x1D6E0, 'M', 'ρ'),
-    (0x1D6E1, 'M', 'π'),
-    (0x1D6E2, 'M', 'α'),
-    (0x1D6E3, 'M', 'β'),
-    (0x1D6E4, 'M', 'γ'),
-    (0x1D6E5, 'M', 'δ'),
-    (0x1D6E6, 'M', 'ε'),
-    (0x1D6E7, 'M', 'ζ'),
-    (0x1D6E8, 'M', 'η'),
-    (0x1D6E9, 'M', 'θ'),
-    (0x1D6EA, 'M', 'ι'),
-    (0x1D6EB, 'M', 'κ'),
-    (0x1D6EC, 'M', 'λ'),
-    (0x1D6ED, 'M', 'μ'),
-    (0x1D6EE, 'M', 'ν'),
-    (0x1D6EF, 'M', 'ξ'),
-    (0x1D6F0, 'M', 'ο'),
-    (0x1D6F1, 'M', 'π'),
-    (0x1D6F2, 'M', 'ρ'),
-    (0x1D6F3, 'M', 'θ'),
-    (0x1D6F4, 'M', 'σ'),
-    ]
-
-def _seg_68() -> List[Union[Tuple[int, str], Tuple[int, str, str]]]:
-    return [
-    (0x1D6F5, 'M', 'τ'),
-    (0x1D6F6, 'M', 'υ'),
-    (0x1D6F7, 'M', 'φ'),
-    (0x1D6F8, 'M', 'χ'),
-    (0x1D6F9, 'M', 'ψ'),
-    (0x1D6FA, 'M', 'ω'),
-    (0x1D6FB, 'M', '∇'),
-    (0x1D6FC, 'M', 'α'),
-    (0x1D6FD, 'M', 'β'),
-    (0x1D6FE, 'M', 'γ'),
-    (0x1D6FF, 'M', 'δ'),
-    (0x1D700, 'M', 'ε'),
-    (0x1D701, 'M', 'ζ'),
-    (0x1D702, 'M', 'η'),
-    (0x1D703, 'M', 'θ'),
-    (0x1D704, 'M', 'ι'),
-    (0x1D705, 'M', 'κ'),
-    (0x1D706, 'M', 'λ'),
-    (0x1D707, 'M', 'μ'),
-    (0x1D708, 'M', 'ν'),
-    (0x1D709, 'M', 'ξ'),
-    (0x1D70A, 'M', 'ο'),
-    (0x1D70B, 'M', 'π'),
-    (0x1D70C, 'M', 'ρ'),
-    (0x1D70D, 'M', 'σ'),
-    (0x1D70F, 'M', 'τ'),
-    (0x1D710, 'M', 'υ'),
-    (0x1D711, 'M', 'φ'),
-    (0x1D712, 'M', 'χ'),
-    (0x1D713, 'M', 'ψ'),
-    (0x1D714, 'M', 'ω'),
-    (0x1D715, 'M', '∂'),
-    (0x1D716, 'M', 'ε'),
-    (0x1D717, 'M', 'θ'),
-    (0x1D718, 'M', 'κ'),
-    (0x1D719, 'M', 'φ'),
-    (0x1D71A, 'M', 'ρ'),
-    (0x1D71B, 'M', 'π'),
-    (0x1D71C, 'M', 'α'),
-    (0x1D71D, 'M', 'β'),
-    (0x1D71E, 'M', 'γ'),
-    (0x1D71F, 'M', 'δ'),
-    (0x1D720, 'M', 'ε'),
-    (0x1D721, 'M', 'ζ'),
-    (0x1D722, 'M', 'η'),
-    (0x1D723, 'M', 'θ'),
-    (0x1D724, 'M', 'ι'),
-    (0x1D725, 'M', 'κ'),
-    (0x1D726, 'M', 'λ'),
-    (0x1D727, 'M', 'μ'),
-    (0x1D728, 'M', 'ν'),
-    (0x1D729, 'M', 'ξ'),
-    (0x1D72A, 'M', 'ο'),
-    (0x1D72B, 'M', 'π'),
-    (0x1D72C, 'M', 'ρ'),
-    (0x1D72D, 'M', 'θ'),
-    (0x1D72E, 'M', 'σ'),
-    (0x1D72F, 'M', 'τ'),
-    (0x1D730, 'M', 'υ'),
-    (0x1D731, 'M', 'φ'),
-    (0x1D732, 'M', 'χ'),
-    (0x1D733, 'M', 'ψ'),
-    (0x1D734, 'M', 'ω'),
-    (0x1D735, 'M', '∇'),
-    (0x1D736, 'M', 'α'),
-    (0x1D737, 'M', 'β'),
-    (0x1D738, 'M', 'γ'),
-    (0x1D739, 'M', 'δ'),
-    (0x1D73A, 'M', 'ε'),
-    (0x1D73B, 'M', 'ζ'),
-    (0x1D73C, 'M', 'η'),
-    (0x1D73D, 'M', 'θ'),
-    (0x1D73E, 'M', 'ι'),
-    (0x1D73F, 'M', 'κ'),
-    (0x1D740, 'M', 'λ'),
-    (0x1D741, 'M', 'μ'),
-    (0x1D742, 'M', 'ν'),
-    (0x1D743, 'M', 'ξ'),
-    (0x1D744, 'M', 'ο'),
-    (0x1D745, 'M', 'π'),
-    (0x1D746, 'M', 'ρ'),
-    (0x1D747, 'M', 'σ'),
-    (0x1D749, 'M', 'τ'),
-    (0x1D74A, 'M', 'υ'),
-    (0x1D74B, 'M', 'φ'),
-    (0x1D74C, 'M', 'χ'),
-    (0x1D74D, 'M', 'ψ'),
-    (0x1D74E, 'M', 'ω'),
-    (0x1D74F, 'M', '∂'),
-    (0x1D750, 'M', 'ε'),
-    (0x1D751, 'M', 'θ'),
-    (0x1D752, 'M', 'κ'),
-    (0x1D753, 'M', 'φ'),
-    (0x1D754, 'M', 'ρ'),
-    (0x1D755, 'M', 'π'),
-    (0x1D756, 'M', 'α'),
-    (0x1D757, 'M', 'β'),
-    (0x1D758, 'M', 'γ'),
-    (0x1D759, 'M', 'δ'),
-    (0x1D75A, 'M', 'ε'),
-    ]
-
-def _seg_69() -> List[Union[Tuple[int, str], Tuple[int, str, str]]]:
-    return [
-    (0x1D75B, 'M', 'ζ'),
-    (0x1D75C, 'M', 'η'),
-    (0x1D75D, 'M', 'θ'),
-    (0x1D75E, 'M', 'ι'),
-    (0x1D75F, 'M', 'κ'),
-    (0x1D760, 'M', 'λ'),
-    (0x1D761, 'M', 'μ'),
-    (0x1D762, 'M', 'ν'),
-    (0x1D763, 'M', 'ξ'),
-    (0x1D764, 'M', 'ο'),
-    (0x1D765, 'M', 'π'),
-    (0x1D766, 'M', 'ρ'),
-    (0x1D767, 'M', 'θ'),
-    (0x1D768, 'M', 'σ'),
-    (0x1D769, 'M', 'τ'),
-    (0x1D76A, 'M', 'υ'),
-    (0x1D76B, 'M', 'φ'),
-    (0x1D76C, 'M', 'χ'),
-    (0x1D76D, 'M', 'ψ'),
-    (0x1D76E, 'M', 'ω'),
-    (0x1D76F, 'M', '∇'),
-    (0x1D770, 'M', 'α'),
-    (0x1D771, 'M', 'β'),
-    (0x1D772, 'M', 'γ'),
-    (0x1D773, 'M', 'δ'),
-    (0x1D774, 'M', 'ε'),
-    (0x1D775, 'M', 'ζ'),
-    (0x1D776, 'M', 'η'),
-    (0x1D777, 'M', 'θ'),
-    (0x1D778, 'M', 'ι'),
-    (0x1D779, 'M', 'κ'),
-    (0x1D77A, 'M', 'λ'),
-    (0x1D77B, 'M', 'μ'),
-    (0x1D77C, 'M', 'ν'),
-    (0x1D77D, 'M', 'ξ'),
-    (0x1D77E, 'M', 'ο'),
-    (0x1D77F, 'M', 'π'),
-    (0x1D780, 'M', 'ρ'),
-    (0x1D781, 'M', 'σ'),
-    (0x1D783, 'M', 'τ'),
-    (0x1D784, 'M', 'υ'),
-    (0x1D785, 'M', 'φ'),
-    (0x1D786, 'M', 'χ'),
-    (0x1D787, 'M', 'ψ'),
-    (0x1D788, 'M', 'ω'),
-    (0x1D789, 'M', '∂'),
-    (0x1D78A, 'M', 'ε'),
-    (0x1D78B, 'M', 'θ'),
-    (0x1D78C, 'M', 'κ'),
-    (0x1D78D, 'M', 'φ'),
-    (0x1D78E, 'M', 'ρ'),
-    (0x1D78F, 'M', 'π'),
-    (0x1D790, 'M', 'α'),
-    (0x1D791, 'M', 'β'),
-    (0x1D792, 'M', 'γ'),
-    (0x1D793, 'M', 'δ'),
-    (0x1D794, 'M', 'ε'),
-    (0x1D795, 'M', 'ζ'),
-    (0x1D796, 'M', 'η'),
-    (0x1D797, 'M', 'θ'),
-    (0x1D798, 'M', 'ι'),
-    (0x1D799, 'M', 'κ'),
-    (0x1D79A, 'M', 'λ'),
-    (0x1D79B, 'M', 'μ'),
-    (0x1D79C, 'M', 'ν'),
-    (0x1D79D, 'M', 'ξ'),
-    (0x1D79E, 'M', 'ο'),
-    (0x1D79F, 'M', 'π'),
-    (0x1D7A0, 'M', 'ρ'),
-    (0x1D7A1, 'M', 'θ'),
-    (0x1D7A2, 'M', 'σ'),
-    (0x1D7A3, 'M', 'τ'),
-    (0x1D7A4, 'M', 'υ'),
-    (0x1D7A5, 'M', 'φ'),
-    (0x1D7A6, 'M', 'χ'),
-    (0x1D7A7, 'M', 'ψ'),
-    (0x1D7A8, 'M', 'ω'),
-    (0x1D7A9, 'M', '∇'),
-    (0x1D7AA, 'M', 'α'),
-    (0x1D7AB, 'M', 'β'),
-    (0x1D7AC, 'M', 'γ'),
-    (0x1D7AD, 'M', 'δ'),
-    (0x1D7AE, 'M', 'ε'),
-    (0x1D7AF, 'M', 'ζ'),
-    (0x1D7B0, 'M', 'η'),
-    (0x1D7B1, 'M', 'θ'),
-    (0x1D7B2, 'M', 'ι'),
-    (0x1D7B3, 'M', 'κ'),
-    (0x1D7B4, 'M', 'λ'),
-    (0x1D7B5, 'M', 'μ'),
-    (0x1D7B6, 'M', 'ν'),
-    (0x1D7B7, 'M', 'ξ'),
-    (0x1D7B8, 'M', 'ο'),
-    (0x1D7B9, 'M', 'π'),
-    (0x1D7BA, 'M', 'ρ'),
-    (0x1D7BB, 'M', 'σ'),
-    (0x1D7BD, 'M', 'τ'),
-    (0x1D7BE, 'M', 'υ'),
-    (0x1D7BF, 'M', 'φ'),
-    (0x1D7C0, 'M', 'χ'),
-    ]
-
-def _seg_70() -> List[Union[Tuple[int, str], Tuple[int, str, str]]]:
-    return [
-    (0x1D7C1, 'M', 'ψ'),
-    (0x1D7C2, 'M', 'ω'),
-    (0x1D7C3, 'M', '∂'),
-    (0x1D7C4, 'M', 'ε'),
-    (0x1D7C5, 'M', 'θ'),
-    (0x1D7C6, 'M', 'κ'),
-    (0x1D7C7, 'M', 'φ'),
-    (0x1D7C8, 'M', 'ρ'),
-    (0x1D7C9, 'M', 'π'),
-    (0x1D7CA, 'M', 'ϝ'),
-    (0x1D7CC, 'X'),
-    (0x1D7CE, 'M', '0'),
-    (0x1D7CF, 'M', '1'),
-    (0x1D7D0, 'M', '2'),
-    (0x1D7D1, 'M', '3'),
-    (0x1D7D2, 'M', '4'),
-    (0x1D7D3, 'M', '5'),
-    (0x1D7D4, 'M', '6'),
-    (0x1D7D5, 'M', '7'),
-    (0x1D7D6, 'M', '8'),
-    (0x1D7D7, 'M', '9'),
-    (0x1D7D8, 'M', '0'),
-    (0x1D7D9, 'M', '1'),
-    (0x1D7DA, 'M', '2'),
-    (0x1D7DB, 'M', '3'),
-    (0x1D7DC, 'M', '4'),
-    (0x1D7DD, 'M', '5'),
-    (0x1D7DE, 'M', '6'),
-    (0x1D7DF, 'M', '7'),
-    (0x1D7E0, 'M', '8'),
-    (0x1D7E1, 'M', '9'),
-    (0x1D7E2, 'M', '0'),
-    (0x1D7E3, 'M', '1'),
-    (0x1D7E4, 'M', '2'),
-    (0x1D7E5, 'M', '3'),
-    (0x1D7E6, 'M', '4'),
-    (0x1D7E7, 'M', '5'),
-    (0x1D7E8, 'M', '6'),
-    (0x1D7E9, 'M', '7'),
-    (0x1D7EA, 'M', '8'),
-    (0x1D7EB, 'M', '9'),
-    (0x1D7EC, 'M', '0'),
-    (0x1D7ED, 'M', '1'),
-    (0x1D7EE, 'M', '2'),
-    (0x1D7EF, 'M', '3'),
-    (0x1D7F0, 'M', '4'),
-    (0x1D7F1, 'M', '5'),
-    (0x1D7F2, 'M', '6'),
-    (0x1D7F3, 'M', '7'),
-    (0x1D7F4, 'M', '8'),
-    (0x1D7F5, 'M', '9'),
-    (0x1D7F6, 'M', '0'),
-    (0x1D7F7, 'M', '1'),
-    (0x1D7F8, 'M', '2'),
-    (0x1D7F9, 'M', '3'),
-    (0x1D7FA, 'M', '4'),
-    (0x1D7FB, 'M', '5'),
-    (0x1D7FC, 'M', '6'),
-    (0x1D7FD, 'M', '7'),
-    (0x1D7FE, 'M', '8'),
-    (0x1D7FF, 'M', '9'),
-    (0x1D800, 'V'),
-    (0x1DA8C, 'X'),
-    (0x1DA9B, 'V'),
-    (0x1DAA0, 'X'),
-    (0x1DAA1, 'V'),
-    (0x1DAB0, 'X'),
-    (0x1DF00, 'V'),
-    (0x1DF1F, 'X'),
-    (0x1E000, 'V'),
-    (0x1E007, 'X'),
-    (0x1E008, 'V'),
-    (0x1E019, 'X'),
-    (0x1E01B, 'V'),
-    (0x1E022, 'X'),
-    (0x1E023, 'V'),
-    (0x1E025, 'X'),
-    (0x1E026, 'V'),
-    (0x1E02B, 'X'),
-    (0x1E100, 'V'),
-    (0x1E12D, 'X'),
-    (0x1E130, 'V'),
-    (0x1E13E, 'X'),
-    (0x1E140, 'V'),
-    (0x1E14A, 'X'),
-    (0x1E14E, 'V'),
-    (0x1E150, 'X'),
-    (0x1E290, 'V'),
-    (0x1E2AF, 'X'),
-    (0x1E2C0, 'V'),
-    (0x1E2FA, 'X'),
-    (0x1E2FF, 'V'),
-    (0x1E300, 'X'),
-    (0x1E7E0, 'V'),
-    (0x1E7E7, 'X'),
-    (0x1E7E8, 'V'),
-    (0x1E7EC, 'X'),
-    (0x1E7ED, 'V'),
-    (0x1E7EF, 'X'),
-    (0x1E7F0, 'V'),
-    ]
-
-def _seg_71() -> List[Union[Tuple[int, str], Tuple[int, str, str]]]:
-    return [
-    (0x1E7FF, 'X'),
-    (0x1E800, 'V'),
-    (0x1E8C5, 'X'),
-    (0x1E8C7, 'V'),
-    (0x1E8D7, 'X'),
-    (0x1E900, 'M', '𞤢'),
-    (0x1E901, 'M', '𞤣'),
-    (0x1E902, 'M', '𞤤'),
-    (0x1E903, 'M', '𞤥'),
-    (0x1E904, 'M', '𞤦'),
-    (0x1E905, 'M', '𞤧'),
-    (0x1E906, 'M', '𞤨'),
-    (0x1E907, 'M', '𞤩'),
-    (0x1E908, 'M', '𞤪'),
-    (0x1E909, 'M', '𞤫'),
-    (0x1E90A, 'M', '𞤬'),
-    (0x1E90B, 'M', '𞤭'),
-    (0x1E90C, 'M', '𞤮'),
-    (0x1E90D, 'M', '𞤯'),
-    (0x1E90E, 'M', '𞤰'),
-    (0x1E90F, 'M', '𞤱'),
-    (0x1E910, 'M', '𞤲'),
-    (0x1E911, 'M', '𞤳'),
-    (0x1E912, 'M', '𞤴'),
-    (0x1E913, 'M', '𞤵'),
-    (0x1E914, 'M', '𞤶'),
-    (0x1E915, 'M', '𞤷'),
-    (0x1E916, 'M', '𞤸'),
-    (0x1E917, 'M', '𞤹'),
-    (0x1E918, 'M', '𞤺'),
-    (0x1E919, 'M', '𞤻'),
-    (0x1E91A, 'M', '𞤼'),
-    (0x1E91B, 'M', '𞤽'),
-    (0x1E91C, 'M', '𞤾'),
-    (0x1E91D, 'M', '𞤿'),
-    (0x1E91E, 'M', '𞥀'),
-    (0x1E91F, 'M', '𞥁'),
-    (0x1E920, 'M', '𞥂'),
-    (0x1E921, 'M', '𞥃'),
-    (0x1E922, 'V'),
-    (0x1E94C, 'X'),
-    (0x1E950, 'V'),
-    (0x1E95A, 'X'),
-    (0x1E95E, 'V'),
-    (0x1E960, 'X'),
-    (0x1EC71, 'V'),
-    (0x1ECB5, 'X'),
-    (0x1ED01, 'V'),
-    (0x1ED3E, 'X'),
-    (0x1EE00, 'M', 'ا'),
-    (0x1EE01, 'M', 'ب'),
-    (0x1EE02, 'M', 'ج'),
-    (0x1EE03, 'M', 'د'),
-    (0x1EE04, 'X'),
-    (0x1EE05, 'M', 'و'),
-    (0x1EE06, 'M', 'ز'),
-    (0x1EE07, 'M', 'ح'),
-    (0x1EE08, 'M', 'ط'),
-    (0x1EE09, 'M', 'ي'),
-    (0x1EE0A, 'M', 'ك'),
-    (0x1EE0B, 'M', 'ل'),
-    (0x1EE0C, 'M', 'م'),
-    (0x1EE0D, 'M', 'ن'),
-    (0x1EE0E, 'M', 'س'),
-    (0x1EE0F, 'M', 'ع'),
-    (0x1EE10, 'M', 'ف'),
-    (0x1EE11, 'M', 'ص'),
-    (0x1EE12, 'M', 'ق'),
-    (0x1EE13, 'M', 'ر'),
-    (0x1EE14, 'M', 'ش'),
-    (0x1EE15, 'M', 'ت'),
-    (0x1EE16, 'M', 'ث'),
-    (0x1EE17, 'M', 'خ'),
-    (0x1EE18, 'M', 'ذ'),
-    (0x1EE19, 'M', 'ض'),
-    (0x1EE1A, 'M', 'ظ'),
-    (0x1EE1B, 'M', 'غ'),
-    (0x1EE1C, 'M', 'ٮ'),
-    (0x1EE1D, 'M', 'ں'),
-    (0x1EE1E, 'M', 'ڡ'),
-    (0x1EE1F, 'M', 'ٯ'),
-    (0x1EE20, 'X'),
-    (0x1EE21, 'M', 'ب'),
-    (0x1EE22, 'M', 'ج'),
-    (0x1EE23, 'X'),
-    (0x1EE24, 'M', 'ه'),
-    (0x1EE25, 'X'),
-    (0x1EE27, 'M', 'ح'),
-    (0x1EE28, 'X'),
-    (0x1EE29, 'M', 'ي'),
-    (0x1EE2A, 'M', 'ك'),
-    (0x1EE2B, 'M', 'ل'),
-    (0x1EE2C, 'M', 'م'),
-    (0x1EE2D, 'M', 'ن'),
-    (0x1EE2E, 'M', 'س'),
-    (0x1EE2F, 'M', 'ع'),
-    (0x1EE30, 'M', 'ف'),
-    (0x1EE31, 'M', 'ص'),
-    (0x1EE32, 'M', 'ق'),
-    (0x1EE33, 'X'),
-    ]
-
-def _seg_72() -> List[Union[Tuple[int, str], Tuple[int, str, str]]]:
-    return [
-    (0x1EE34, 'M', 'ش'),
-    (0x1EE35, 'M', 'ت'),
-    (0x1EE36, 'M', 'ث'),
-    (0x1EE37, 'M', 'خ'),
-    (0x1EE38, 'X'),
-    (0x1EE39, 'M', 'ض'),
-    (0x1EE3A, 'X'),
-    (0x1EE3B, 'M', 'غ'),
-    (0x1EE3C, 'X'),
-    (0x1EE42, 'M', 'ج'),
-    (0x1EE43, 'X'),
-    (0x1EE47, 'M', 'ح'),
-    (0x1EE48, 'X'),
-    (0x1EE49, 'M', 'ي'),
-    (0x1EE4A, 'X'),
-    (0x1EE4B, 'M', 'ل'),
-    (0x1EE4C, 'X'),
-    (0x1EE4D, 'M', 'ن'),
-    (0x1EE4E, 'M', 'س'),
-    (0x1EE4F, 'M', 'ع'),
-    (0x1EE50, 'X'),
-    (0x1EE51, 'M', 'ص'),
-    (0x1EE52, 'M', 'ق'),
-    (0x1EE53, 'X'),
-    (0x1EE54, 'M', 'ش'),
-    (0x1EE55, 'X'),
-    (0x1EE57, 'M', 'خ'),
-    (0x1EE58, 'X'),
-    (0x1EE59, 'M', 'ض'),
-    (0x1EE5A, 'X'),
-    (0x1EE5B, 'M', 'غ'),
-    (0x1EE5C, 'X'),
-    (0x1EE5D, 'M', 'ں'),
-    (0x1EE5E, 'X'),
-    (0x1EE5F, 'M', 'ٯ'),
-    (0x1EE60, 'X'),
-    (0x1EE61, 'M', 'ب'),
-    (0x1EE62, 'M', 'ج'),
-    (0x1EE63, 'X'),
-    (0x1EE64, 'M', 'ه'),
-    (0x1EE65, 'X'),
-    (0x1EE67, 'M', 'ح'),
-    (0x1EE68, 'M', 'ط'),
-    (0x1EE69, 'M', 'ي'),
-    (0x1EE6A, 'M', 'ك'),
-    (0x1EE6B, 'X'),
-    (0x1EE6C, 'M', 'م'),
-    (0x1EE6D, 'M', 'ن'),
-    (0x1EE6E, 'M', 'س'),
-    (0x1EE6F, 'M', 'ع'),
-    (0x1EE70, 'M', 'ف'),
-    (0x1EE71, 'M', 'ص'),
-    (0x1EE72, 'M', 'ق'),
-    (0x1EE73, 'X'),
-    (0x1EE74, 'M', 'ش'),
-    (0x1EE75, 'M', 'ت'),
-    (0x1EE76, 'M', 'ث'),
-    (0x1EE77, 'M', 'خ'),
-    (0x1EE78, 'X'),
-    (0x1EE79, 'M', 'ض'),
-    (0x1EE7A, 'M', 'ظ'),
-    (0x1EE7B, 'M', 'غ'),
-    (0x1EE7C, 'M', 'ٮ'),
-    (0x1EE7D, 'X'),
-    (0x1EE7E, 'M', 'ڡ'),
-    (0x1EE7F, 'X'),
-    (0x1EE80, 'M', 'ا'),
-    (0x1EE81, 'M', 'ب'),
-    (0x1EE82, 'M', 'ج'),
-    (0x1EE83, 'M', 'د'),
-    (0x1EE84, 'M', 'ه'),
-    (0x1EE85, 'M', 'و'),
-    (0x1EE86, 'M', 'ز'),
-    (0x1EE87, 'M', 'ح'),
-    (0x1EE88, 'M', 'ط'),
-    (0x1EE89, 'M', 'ي'),
-    (0x1EE8A, 'X'),
-    (0x1EE8B, 'M', 'ل'),
-    (0x1EE8C, 'M', 'م'),
-    (0x1EE8D, 'M', 'ن'),
-    (0x1EE8E, 'M', 'س'),
-    (0x1EE8F, 'M', 'ع'),
-    (0x1EE90, 'M', 'ف'),
-    (0x1EE91, 'M', 'ص'),
-    (0x1EE92, 'M', 'ق'),
-    (0x1EE93, 'M', 'ر'),
-    (0x1EE94, 'M', 'ش'),
-    (0x1EE95, 'M', 'ت'),
-    (0x1EE96, 'M', 'ث'),
-    (0x1EE97, 'M', 'خ'),
-    (0x1EE98, 'M', 'ذ'),
-    (0x1EE99, 'M', 'ض'),
-    (0x1EE9A, 'M', 'ظ'),
-    (0x1EE9B, 'M', 'غ'),
-    (0x1EE9C, 'X'),
-    (0x1EEA1, 'M', 'ب'),
-    (0x1EEA2, 'M', 'ج'),
-    (0x1EEA3, 'M', 'د'),
-    (0x1EEA4, 'X'),
-    (0x1EEA5, 'M', 'و'),
-    ]
-
-def _seg_73() -> List[Union[Tuple[int, str], Tuple[int, str, str]]]:
-    return [
-    (0x1EEA6, 'M', 'ز'),
-    (0x1EEA7, 'M', 'ح'),
-    (0x1EEA8, 'M', 'ط'),
-    (0x1EEA9, 'M', 'ي'),
-    (0x1EEAA, 'X'),
-    (0x1EEAB, 'M', 'ل'),
-    (0x1EEAC, 'M', 'م'),
-    (0x1EEAD, 'M', 'ن'),
-    (0x1EEAE, 'M', 'س'),
-    (0x1EEAF, 'M', 'ع'),
-    (0x1EEB0, 'M', 'ف'),
-    (0x1EEB1, 'M', 'ص'),
-    (0x1EEB2, 'M', 'ق'),
-    (0x1EEB3, 'M', 'ر'),
-    (0x1EEB4, 'M', 'ش'),
-    (0x1EEB5, 'M', 'ت'),
-    (0x1EEB6, 'M', 'ث'),
-    (0x1EEB7, 'M', 'خ'),
-    (0x1EEB8, 'M', 'ذ'),
-    (0x1EEB9, 'M', 'ض'),
-    (0x1EEBA, 'M', 'ظ'),
-    (0x1EEBB, 'M', 'غ'),
-    (0x1EEBC, 'X'),
-    (0x1EEF0, 'V'),
-    (0x1EEF2, 'X'),
-    (0x1F000, 'V'),
-    (0x1F02C, 'X'),
-    (0x1F030, 'V'),
-    (0x1F094, 'X'),
-    (0x1F0A0, 'V'),
-    (0x1F0AF, 'X'),
-    (0x1F0B1, 'V'),
-    (0x1F0C0, 'X'),
-    (0x1F0C1, 'V'),
-    (0x1F0D0, 'X'),
-    (0x1F0D1, 'V'),
-    (0x1F0F6, 'X'),
-    (0x1F101, '3', '0,'),
-    (0x1F102, '3', '1,'),
-    (0x1F103, '3', '2,'),
-    (0x1F104, '3', '3,'),
-    (0x1F105, '3', '4,'),
-    (0x1F106, '3', '5,'),
-    (0x1F107, '3', '6,'),
-    (0x1F108, '3', '7,'),
-    (0x1F109, '3', '8,'),
-    (0x1F10A, '3', '9,'),
-    (0x1F10B, 'V'),
-    (0x1F110, '3', '(a)'),
-    (0x1F111, '3', '(b)'),
-    (0x1F112, '3', '(c)'),
-    (0x1F113, '3', '(d)'),
-    (0x1F114, '3', '(e)'),
-    (0x1F115, '3', '(f)'),
-    (0x1F116, '3', '(g)'),
-    (0x1F117, '3', '(h)'),
-    (0x1F118, '3', '(i)'),
-    (0x1F119, '3', '(j)'),
-    (0x1F11A, '3', '(k)'),
-    (0x1F11B, '3', '(l)'),
-    (0x1F11C, '3', '(m)'),
-    (0x1F11D, '3', '(n)'),
-    (0x1F11E, '3', '(o)'),
-    (0x1F11F, '3', '(p)'),
-    (0x1F120, '3', '(q)'),
-    (0x1F121, '3', '(r)'),
-    (0x1F122, '3', '(s)'),
-    (0x1F123, '3', '(t)'),
-    (0x1F124, '3', '(u)'),
-    (0x1F125, '3', '(v)'),
-    (0x1F126, '3', '(w)'),
-    (0x1F127, '3', '(x)'),
-    (0x1F128, '3', '(y)'),
-    (0x1F129, '3', '(z)'),
-    (0x1F12A, 'M', '〔s〕'),
-    (0x1F12B, 'M', 'c'),
-    (0x1F12C, 'M', 'r'),
-    (0x1F12D, 'M', 'cd'),
-    (0x1F12E, 'M', 'wz'),
-    (0x1F12F, 'V'),
-    (0x1F130, 'M', 'a'),
-    (0x1F131, 'M', 'b'),
-    (0x1F132, 'M', 'c'),
-    (0x1F133, 'M', 'd'),
-    (0x1F134, 'M', 'e'),
-    (0x1F135, 'M', 'f'),
-    (0x1F136, 'M', 'g'),
-    (0x1F137, 'M', 'h'),
-    (0x1F138, 'M', 'i'),
-    (0x1F139, 'M', 'j'),
-    (0x1F13A, 'M', 'k'),
-    (0x1F13B, 'M', 'l'),
-    (0x1F13C, 'M', 'm'),
-    (0x1F13D, 'M', 'n'),
-    (0x1F13E, 'M', 'o'),
-    (0x1F13F, 'M', 'p'),
-    (0x1F140, 'M', 'q'),
-    (0x1F141, 'M', 'r'),
-    (0x1F142, 'M', 's'),
-    (0x1F143, 'M', 't'),
-    ]
-
-def _seg_74() -> List[Union[Tuple[int, str], Tuple[int, str, str]]]:
-    return [
-    (0x1F144, 'M', 'u'),
-    (0x1F145, 'M', 'v'),
-    (0x1F146, 'M', 'w'),
-    (0x1F147, 'M', 'x'),
-    (0x1F148, 'M', 'y'),
-    (0x1F149, 'M', 'z'),
-    (0x1F14A, 'M', 'hv'),
-    (0x1F14B, 'M', 'mv'),
-    (0x1F14C, 'M', 'sd'),
-    (0x1F14D, 'M', 'ss'),
-    (0x1F14E, 'M', 'ppv'),
-    (0x1F14F, 'M', 'wc'),
-    (0x1F150, 'V'),
-    (0x1F16A, 'M', 'mc'),
-    (0x1F16B, 'M', 'md'),
-    (0x1F16C, 'M', 'mr'),
-    (0x1F16D, 'V'),
-    (0x1F190, 'M', 'dj'),
-    (0x1F191, 'V'),
-    (0x1F1AE, 'X'),
-    (0x1F1E6, 'V'),
-    (0x1F200, 'M', 'ほか'),
-    (0x1F201, 'M', 'ココ'),
-    (0x1F202, 'M', 'サ'),
-    (0x1F203, 'X'),
-    (0x1F210, 'M', '手'),
-    (0x1F211, 'M', '字'),
-    (0x1F212, 'M', '双'),
-    (0x1F213, 'M', 'デ'),
-    (0x1F214, 'M', '二'),
-    (0x1F215, 'M', '多'),
-    (0x1F216, 'M', '解'),
-    (0x1F217, 'M', '天'),
-    (0x1F218, 'M', '交'),
-    (0x1F219, 'M', '映'),
-    (0x1F21A, 'M', '無'),
-    (0x1F21B, 'M', '料'),
-    (0x1F21C, 'M', '前'),
-    (0x1F21D, 'M', '後'),
-    (0x1F21E, 'M', '再'),
-    (0x1F21F, 'M', '新'),
-    (0x1F220, 'M', '初'),
-    (0x1F221, 'M', '終'),
-    (0x1F222, 'M', '生'),
-    (0x1F223, 'M', '販'),
-    (0x1F224, 'M', '声'),
-    (0x1F225, 'M', '吹'),
-    (0x1F226, 'M', '演'),
-    (0x1F227, 'M', '投'),
-    (0x1F228, 'M', '捕'),
-    (0x1F229, 'M', '一'),
-    (0x1F22A, 'M', '三'),
-    (0x1F22B, 'M', '遊'),
-    (0x1F22C, 'M', '左'),
-    (0x1F22D, 'M', '中'),
-    (0x1F22E, 'M', '右'),
-    (0x1F22F, 'M', '指'),
-    (0x1F230, 'M', '走'),
-    (0x1F231, 'M', '打'),
-    (0x1F232, 'M', '禁'),
-    (0x1F233, 'M', '空'),
-    (0x1F234, 'M', '合'),
-    (0x1F235, 'M', '満'),
-    (0x1F236, 'M', '有'),
-    (0x1F237, 'M', '月'),
-    (0x1F238, 'M', '申'),
-    (0x1F239, 'M', '割'),
-    (0x1F23A, 'M', '営'),
-    (0x1F23B, 'M', '配'),
-    (0x1F23C, 'X'),
-    (0x1F240, 'M', '〔本〕'),
-    (0x1F241, 'M', '〔三〕'),
-    (0x1F242, 'M', '〔二〕'),
-    (0x1F243, 'M', '〔安〕'),
-    (0x1F244, 'M', '〔点〕'),
-    (0x1F245, 'M', '〔打〕'),
-    (0x1F246, 'M', '〔盗〕'),
-    (0x1F247, 'M', '〔勝〕'),
-    (0x1F248, 'M', '〔敗〕'),
-    (0x1F249, 'X'),
-    (0x1F250, 'M', '得'),
-    (0x1F251, 'M', '可'),
-    (0x1F252, 'X'),
-    (0x1F260, 'V'),
-    (0x1F266, 'X'),
-    (0x1F300, 'V'),
-    (0x1F6D8, 'X'),
-    (0x1F6DD, 'V'),
-    (0x1F6ED, 'X'),
-    (0x1F6F0, 'V'),
-    (0x1F6FD, 'X'),
-    (0x1F700, 'V'),
-    (0x1F774, 'X'),
-    (0x1F780, 'V'),
-    (0x1F7D9, 'X'),
-    (0x1F7E0, 'V'),
-    (0x1F7EC, 'X'),
-    (0x1F7F0, 'V'),
-    (0x1F7F1, 'X'),
-    (0x1F800, 'V'),
-    ]
-
-def _seg_75() -> List[Union[Tuple[int, str], Tuple[int, str, str]]]:
-    return [
-    (0x1F80C, 'X'),
-    (0x1F810, 'V'),
-    (0x1F848, 'X'),
-    (0x1F850, 'V'),
-    (0x1F85A, 'X'),
-    (0x1F860, 'V'),
-    (0x1F888, 'X'),
-    (0x1F890, 'V'),
-    (0x1F8AE, 'X'),
-    (0x1F8B0, 'V'),
-    (0x1F8B2, 'X'),
-    (0x1F900, 'V'),
-    (0x1FA54, 'X'),
-    (0x1FA60, 'V'),
-    (0x1FA6E, 'X'),
-    (0x1FA70, 'V'),
-    (0x1FA75, 'X'),
-    (0x1FA78, 'V'),
-    (0x1FA7D, 'X'),
-    (0x1FA80, 'V'),
-    (0x1FA87, 'X'),
-    (0x1FA90, 'V'),
-    (0x1FAAD, 'X'),
-    (0x1FAB0, 'V'),
-    (0x1FABB, 'X'),
-    (0x1FAC0, 'V'),
-    (0x1FAC6, 'X'),
-    (0x1FAD0, 'V'),
-    (0x1FADA, 'X'),
-    (0x1FAE0, 'V'),
-    (0x1FAE8, 'X'),
-    (0x1FAF0, 'V'),
-    (0x1FAF7, 'X'),
-    (0x1FB00, 'V'),
-    (0x1FB93, 'X'),
-    (0x1FB94, 'V'),
-    (0x1FBCB, 'X'),
-    (0x1FBF0, 'M', '0'),
-    (0x1FBF1, 'M', '1'),
-    (0x1FBF2, 'M', '2'),
-    (0x1FBF3, 'M', '3'),
-    (0x1FBF4, 'M', '4'),
-    (0x1FBF5, 'M', '5'),
-    (0x1FBF6, 'M', '6'),
-    (0x1FBF7, 'M', '7'),
-    (0x1FBF8, 'M', '8'),
-    (0x1FBF9, 'M', '9'),
-    (0x1FBFA, 'X'),
-    (0x20000, 'V'),
-    (0x2A6E0, 'X'),
-    (0x2A700, 'V'),
-    (0x2B739, 'X'),
-    (0x2B740, 'V'),
-    (0x2B81E, 'X'),
-    (0x2B820, 'V'),
-    (0x2CEA2, 'X'),
-    (0x2CEB0, 'V'),
-    (0x2EBE1, 'X'),
-    (0x2F800, 'M', '丽'),
-    (0x2F801, 'M', '丸'),
-    (0x2F802, 'M', '乁'),
-    (0x2F803, 'M', '𠄢'),
-    (0x2F804, 'M', '你'),
-    (0x2F805, 'M', '侮'),
-    (0x2F806, 'M', '侻'),
-    (0x2F807, 'M', '倂'),
-    (0x2F808, 'M', '偺'),
-    (0x2F809, 'M', '備'),
-    (0x2F80A, 'M', '僧'),
-    (0x2F80B, 'M', '像'),
-    (0x2F80C, 'M', '㒞'),
-    (0x2F80D, 'M', '𠘺'),
-    (0x2F80E, 'M', '免'),
-    (0x2F80F, 'M', '兔'),
-    (0x2F810, 'M', '兤'),
-    (0x2F811, 'M', '具'),
-    (0x2F812, 'M', '𠔜'),
-    (0x2F813, 'M', '㒹'),
-    (0x2F814, 'M', '內'),
-    (0x2F815, 'M', '再'),
-    (0x2F816, 'M', '𠕋'),
-    (0x2F817, 'M', '冗'),
-    (0x2F818, 'M', '冤'),
-    (0x2F819, 'M', '仌'),
-    (0x2F81A, 'M', '冬'),
-    (0x2F81B, 'M', '况'),
-    (0x2F81C, 'M', '𩇟'),
-    (0x2F81D, 'M', '凵'),
-    (0x2F81E, 'M', '刃'),
-    (0x2F81F, 'M', '㓟'),
-    (0x2F820, 'M', '刻'),
-    (0x2F821, 'M', '剆'),
-    (0x2F822, 'M', '割'),
-    (0x2F823, 'M', '剷'),
-    (0x2F824, 'M', '㔕'),
-    (0x2F825, 'M', '勇'),
-    (0x2F826, 'M', '勉'),
-    (0x2F827, 'M', '勤'),
-    (0x2F828, 'M', '勺'),
-    (0x2F829, 'M', '包'),
-    ]
-
-def _seg_76() -> List[Union[Tuple[int, str], Tuple[int, str, str]]]:
-    return [
-    (0x2F82A, 'M', '匆'),
-    (0x2F82B, 'M', '北'),
-    (0x2F82C, 'M', '卉'),
-    (0x2F82D, 'M', '卑'),
-    (0x2F82E, 'M', '博'),
-    (0x2F82F, 'M', '即'),
-    (0x2F830, 'M', '卽'),
-    (0x2F831, 'M', '卿'),
-    (0x2F834, 'M', '𠨬'),
-    (0x2F835, 'M', '灰'),
-    (0x2F836, 'M', '及'),
-    (0x2F837, 'M', '叟'),
-    (0x2F838, 'M', '𠭣'),
-    (0x2F839, 'M', '叫'),
-    (0x2F83A, 'M', '叱'),
-    (0x2F83B, 'M', '吆'),
-    (0x2F83C, 'M', '咞'),
-    (0x2F83D, 'M', '吸'),
-    (0x2F83E, 'M', '呈'),
-    (0x2F83F, 'M', '周'),
-    (0x2F840, 'M', '咢'),
-    (0x2F841, 'M', '哶'),
-    (0x2F842, 'M', '唐'),
-    (0x2F843, 'M', '啓'),
-    (0x2F844, 'M', '啣'),
-    (0x2F845, 'M', '善'),
-    (0x2F847, 'M', '喙'),
-    (0x2F848, 'M', '喫'),
-    (0x2F849, 'M', '喳'),
-    (0x2F84A, 'M', '嗂'),
-    (0x2F84B, 'M', '圖'),
-    (0x2F84C, 'M', '嘆'),
-    (0x2F84D, 'M', '圗'),
-    (0x2F84E, 'M', '噑'),
-    (0x2F84F, 'M', '噴'),
-    (0x2F850, 'M', '切'),
-    (0x2F851, 'M', '壮'),
-    (0x2F852, 'M', '城'),
-    (0x2F853, 'M', '埴'),
-    (0x2F854, 'M', '堍'),
-    (0x2F855, 'M', '型'),
-    (0x2F856, 'M', '堲'),
-    (0x2F857, 'M', '報'),
-    (0x2F858, 'M', '墬'),
-    (0x2F859, 'M', '𡓤'),
-    (0x2F85A, 'M', '売'),
-    (0x2F85B, 'M', '壷'),
-    (0x2F85C, 'M', '夆'),
-    (0x2F85D, 'M', '多'),
-    (0x2F85E, 'M', '夢'),
-    (0x2F85F, 'M', '奢'),
-    (0x2F860, 'M', '𡚨'),
-    (0x2F861, 'M', '𡛪'),
-    (0x2F862, 'M', '姬'),
-    (0x2F863, 'M', '娛'),
-    (0x2F864, 'M', '娧'),
-    (0x2F865, 'M', '姘'),
-    (0x2F866, 'M', '婦'),
-    (0x2F867, 'M', '㛮'),
-    (0x2F868, 'X'),
-    (0x2F869, 'M', '嬈'),
-    (0x2F86A, 'M', '嬾'),
-    (0x2F86C, 'M', '𡧈'),
-    (0x2F86D, 'M', '寃'),
-    (0x2F86E, 'M', '寘'),
-    (0x2F86F, 'M', '寧'),
-    (0x2F870, 'M', '寳'),
-    (0x2F871, 'M', '𡬘'),
-    (0x2F872, 'M', '寿'),
-    (0x2F873, 'M', '将'),
-    (0x2F874, 'X'),
-    (0x2F875, 'M', '尢'),
-    (0x2F876, 'M', '㞁'),
-    (0x2F877, 'M', '屠'),
-    (0x2F878, 'M', '屮'),
-    (0x2F879, 'M', '峀'),
-    (0x2F87A, 'M', '岍'),
-    (0x2F87B, 'M', '𡷤'),
-    (0x2F87C, 'M', '嵃'),
-    (0x2F87D, 'M', '𡷦'),
-    (0x2F87E, 'M', '嵮'),
-    (0x2F87F, 'M', '嵫'),
-    (0x2F880, 'M', '嵼'),
-    (0x2F881, 'M', '巡'),
-    (0x2F882, 'M', '巢'),
-    (0x2F883, 'M', '㠯'),
-    (0x2F884, 'M', '巽'),
-    (0x2F885, 'M', '帨'),
-    (0x2F886, 'M', '帽'),
-    (0x2F887, 'M', '幩'),
-    (0x2F888, 'M', '㡢'),
-    (0x2F889, 'M', '𢆃'),
-    (0x2F88A, 'M', '㡼'),
-    (0x2F88B, 'M', '庰'),
-    (0x2F88C, 'M', '庳'),
-    (0x2F88D, 'M', '庶'),
-    (0x2F88E, 'M', '廊'),
-    (0x2F88F, 'M', '𪎒'),
-    (0x2F890, 'M', '廾'),
-    (0x2F891, 'M', '𢌱'),
-    ]
-
-def _seg_77() -> List[Union[Tuple[int, str], Tuple[int, str, str]]]:
-    return [
-    (0x2F893, 'M', '舁'),
-    (0x2F894, 'M', '弢'),
-    (0x2F896, 'M', '㣇'),
-    (0x2F897, 'M', '𣊸'),
-    (0x2F898, 'M', '𦇚'),
-    (0x2F899, 'M', '形'),
-    (0x2F89A, 'M', '彫'),
-    (0x2F89B, 'M', '㣣'),
-    (0x2F89C, 'M', '徚'),
-    (0x2F89D, 'M', '忍'),
-    (0x2F89E, 'M', '志'),
-    (0x2F89F, 'M', '忹'),
-    (0x2F8A0, 'M', '悁'),
-    (0x2F8A1, 'M', '㤺'),
-    (0x2F8A2, 'M', '㤜'),
-    (0x2F8A3, 'M', '悔'),
-    (0x2F8A4, 'M', '𢛔'),
-    (0x2F8A5, 'M', '惇'),
-    (0x2F8A6, 'M', '慈'),
-    (0x2F8A7, 'M', '慌'),
-    (0x2F8A8, 'M', '慎'),
-    (0x2F8A9, 'M', '慌'),
-    (0x2F8AA, 'M', '慺'),
-    (0x2F8AB, 'M', '憎'),
-    (0x2F8AC, 'M', '憲'),
-    (0x2F8AD, 'M', '憤'),
-    (0x2F8AE, 'M', '憯'),
-    (0x2F8AF, 'M', '懞'),
-    (0x2F8B0, 'M', '懲'),
-    (0x2F8B1, 'M', '懶'),
-    (0x2F8B2, 'M', '成'),
-    (0x2F8B3, 'M', '戛'),
-    (0x2F8B4, 'M', '扝'),
-    (0x2F8B5, 'M', '抱'),
-    (0x2F8B6, 'M', '拔'),
-    (0x2F8B7, 'M', '捐'),
-    (0x2F8B8, 'M', '𢬌'),
-    (0x2F8B9, 'M', '挽'),
-    (0x2F8BA, 'M', '拼'),
-    (0x2F8BB, 'M', '捨'),
-    (0x2F8BC, 'M', '掃'),
-    (0x2F8BD, 'M', '揤'),
-    (0x2F8BE, 'M', '𢯱'),
-    (0x2F8BF, 'M', '搢'),
-    (0x2F8C0, 'M', '揅'),
-    (0x2F8C1, 'M', '掩'),
-    (0x2F8C2, 'M', '㨮'),
-    (0x2F8C3, 'M', '摩'),
-    (0x2F8C4, 'M', '摾'),
-    (0x2F8C5, 'M', '撝'),
-    (0x2F8C6, 'M', '摷'),
-    (0x2F8C7, 'M', '㩬'),
-    (0x2F8C8, 'M', '敏'),
-    (0x2F8C9, 'M', '敬'),
-    (0x2F8CA, 'M', '𣀊'),
-    (0x2F8CB, 'M', '旣'),
-    (0x2F8CC, 'M', '書'),
-    (0x2F8CD, 'M', '晉'),
-    (0x2F8CE, 'M', '㬙'),
-    (0x2F8CF, 'M', '暑'),
-    (0x2F8D0, 'M', '㬈'),
-    (0x2F8D1, 'M', '㫤'),
-    (0x2F8D2, 'M', '冒'),
-    (0x2F8D3, 'M', '冕'),
-    (0x2F8D4, 'M', '最'),
-    (0x2F8D5, 'M', '暜'),
-    (0x2F8D6, 'M', '肭'),
-    (0x2F8D7, 'M', '䏙'),
-    (0x2F8D8, 'M', '朗'),
-    (0x2F8D9, 'M', '望'),
-    (0x2F8DA, 'M', '朡'),
-    (0x2F8DB, 'M', '杞'),
-    (0x2F8DC, 'M', '杓'),
-    (0x2F8DD, 'M', '𣏃'),
-    (0x2F8DE, 'M', '㭉'),
-    (0x2F8DF, 'M', '柺'),
-    (0x2F8E0, 'M', '枅'),
-    (0x2F8E1, 'M', '桒'),
-    (0x2F8E2, 'M', '梅'),
-    (0x2F8E3, 'M', '𣑭'),
-    (0x2F8E4, 'M', '梎'),
-    (0x2F8E5, 'M', '栟'),
-    (0x2F8E6, 'M', '椔'),
-    (0x2F8E7, 'M', '㮝'),
-    (0x2F8E8, 'M', '楂'),
-    (0x2F8E9, 'M', '榣'),
-    (0x2F8EA, 'M', '槪'),
-    (0x2F8EB, 'M', '檨'),
-    (0x2F8EC, 'M', '𣚣'),
-    (0x2F8ED, 'M', '櫛'),
-    (0x2F8EE, 'M', '㰘'),
-    (0x2F8EF, 'M', '次'),
-    (0x2F8F0, 'M', '𣢧'),
-    (0x2F8F1, 'M', '歔'),
-    (0x2F8F2, 'M', '㱎'),
-    (0x2F8F3, 'M', '歲'),
-    (0x2F8F4, 'M', '殟'),
-    (0x2F8F5, 'M', '殺'),
-    (0x2F8F6, 'M', '殻'),
-    (0x2F8F7, 'M', '𣪍'),
-    ]
-
-def _seg_78() -> List[Union[Tuple[int, str], Tuple[int, str, str]]]:
-    return [
-    (0x2F8F8, 'M', '𡴋'),
-    (0x2F8F9, 'M', '𣫺'),
-    (0x2F8FA, 'M', '汎'),
-    (0x2F8FB, 'M', '𣲼'),
-    (0x2F8FC, 'M', '沿'),
-    (0x2F8FD, 'M', '泍'),
-    (0x2F8FE, 'M', '汧'),
-    (0x2F8FF, 'M', '洖'),
-    (0x2F900, 'M', '派'),
-    (0x2F901, 'M', '海'),
-    (0x2F902, 'M', '流'),
-    (0x2F903, 'M', '浩'),
-    (0x2F904, 'M', '浸'),
-    (0x2F905, 'M', '涅'),
-    (0x2F906, 'M', '𣴞'),
-    (0x2F907, 'M', '洴'),
-    (0x2F908, 'M', '港'),
-    (0x2F909, 'M', '湮'),
-    (0x2F90A, 'M', '㴳'),
-    (0x2F90B, 'M', '滋'),
-    (0x2F90C, 'M', '滇'),
-    (0x2F90D, 'M', '𣻑'),
-    (0x2F90E, 'M', '淹'),
-    (0x2F90F, 'M', '潮'),
-    (0x2F910, 'M', '𣽞'),
-    (0x2F911, 'M', '𣾎'),
-    (0x2F912, 'M', '濆'),
-    (0x2F913, 'M', '瀹'),
-    (0x2F914, 'M', '瀞'),
-    (0x2F915, 'M', '瀛'),
-    (0x2F916, 'M', '㶖'),
-    (0x2F917, 'M', '灊'),
-    (0x2F918, 'M', '災'),
-    (0x2F919, 'M', '灷'),
-    (0x2F91A, 'M', '炭'),
-    (0x2F91B, 'M', '𠔥'),
-    (0x2F91C, 'M', '煅'),
-    (0x2F91D, 'M', '𤉣'),
-    (0x2F91E, 'M', '熜'),
-    (0x2F91F, 'X'),
-    (0x2F920, 'M', '爨'),
-    (0x2F921, 'M', '爵'),
-    (0x2F922, 'M', '牐'),
-    (0x2F923, 'M', '𤘈'),
-    (0x2F924, 'M', '犀'),
-    (0x2F925, 'M', '犕'),
-    (0x2F926, 'M', '𤜵'),
-    (0x2F927, 'M', '𤠔'),
-    (0x2F928, 'M', '獺'),
-    (0x2F929, 'M', '王'),
-    (0x2F92A, 'M', '㺬'),
-    (0x2F92B, 'M', '玥'),
-    (0x2F92C, 'M', '㺸'),
-    (0x2F92E, 'M', '瑇'),
-    (0x2F92F, 'M', '瑜'),
-    (0x2F930, 'M', '瑱'),
-    (0x2F931, 'M', '璅'),
-    (0x2F932, 'M', '瓊'),
-    (0x2F933, 'M', '㼛'),
-    (0x2F934, 'M', '甤'),
-    (0x2F935, 'M', '𤰶'),
-    (0x2F936, 'M', '甾'),
-    (0x2F937, 'M', '𤲒'),
-    (0x2F938, 'M', '異'),
-    (0x2F939, 'M', '𢆟'),
-    (0x2F93A, 'M', '瘐'),
-    (0x2F93B, 'M', '𤾡'),
-    (0x2F93C, 'M', '𤾸'),
-    (0x2F93D, 'M', '𥁄'),
-    (0x2F93E, 'M', '㿼'),
-    (0x2F93F, 'M', '䀈'),
-    (0x2F940, 'M', '直'),
-    (0x2F941, 'M', '𥃳'),
-    (0x2F942, 'M', '𥃲'),
-    (0x2F943, 'M', '𥄙'),
-    (0x2F944, 'M', '𥄳'),
-    (0x2F945, 'M', '眞'),
-    (0x2F946, 'M', '真'),
-    (0x2F948, 'M', '睊'),
-    (0x2F949, 'M', '䀹'),
-    (0x2F94A, 'M', '瞋'),
-    (0x2F94B, 'M', '䁆'),
-    (0x2F94C, 'M', '䂖'),
-    (0x2F94D, 'M', '𥐝'),
-    (0x2F94E, 'M', '硎'),
-    (0x2F94F, 'M', '碌'),
-    (0x2F950, 'M', '磌'),
-    (0x2F951, 'M', '䃣'),
-    (0x2F952, 'M', '𥘦'),
-    (0x2F953, 'M', '祖'),
-    (0x2F954, 'M', '𥚚'),
-    (0x2F955, 'M', '𥛅'),
-    (0x2F956, 'M', '福'),
-    (0x2F957, 'M', '秫'),
-    (0x2F958, 'M', '䄯'),
-    (0x2F959, 'M', '穀'),
-    (0x2F95A, 'M', '穊'),
-    (0x2F95B, 'M', '穏'),
-    (0x2F95C, 'M', '𥥼'),
-    (0x2F95D, 'M', '𥪧'),
-    ]
-
-def _seg_79() -> List[Union[Tuple[int, str], Tuple[int, str, str]]]:
-    return [
-    (0x2F95F, 'X'),
-    (0x2F960, 'M', '䈂'),
-    (0x2F961, 'M', '𥮫'),
-    (0x2F962, 'M', '篆'),
-    (0x2F963, 'M', '築'),
-    (0x2F964, 'M', '䈧'),
-    (0x2F965, 'M', '𥲀'),
-    (0x2F966, 'M', '糒'),
-    (0x2F967, 'M', '䊠'),
-    (0x2F968, 'M', '糨'),
-    (0x2F969, 'M', '糣'),
-    (0x2F96A, 'M', '紀'),
-    (0x2F96B, 'M', '𥾆'),
-    (0x2F96C, 'M', '絣'),
-    (0x2F96D, 'M', '䌁'),
-    (0x2F96E, 'M', '緇'),
-    (0x2F96F, 'M', '縂'),
-    (0x2F970, 'M', '繅'),
-    (0x2F971, 'M', '䌴'),
-    (0x2F972, 'M', '𦈨'),
-    (0x2F973, 'M', '𦉇'),
-    (0x2F974, 'M', '䍙'),
-    (0x2F975, 'M', '𦋙'),
-    (0x2F976, 'M', '罺'),
-    (0x2F977, 'M', '𦌾'),
-    (0x2F978, 'M', '羕'),
-    (0x2F979, 'M', '翺'),
-    (0x2F97A, 'M', '者'),
-    (0x2F97B, 'M', '𦓚'),
-    (0x2F97C, 'M', '𦔣'),
-    (0x2F97D, 'M', '聠'),
-    (0x2F97E, 'M', '𦖨'),
-    (0x2F97F, 'M', '聰'),
-    (0x2F980, 'M', '𣍟'),
-    (0x2F981, 'M', '䏕'),
-    (0x2F982, 'M', '育'),
-    (0x2F983, 'M', '脃'),
-    (0x2F984, 'M', '䐋'),
-    (0x2F985, 'M', '脾'),
-    (0x2F986, 'M', '媵'),
-    (0x2F987, 'M', '𦞧'),
-    (0x2F988, 'M', '𦞵'),
-    (0x2F989, 'M', '𣎓'),
-    (0x2F98A, 'M', '𣎜'),
-    (0x2F98B, 'M', '舁'),
-    (0x2F98C, 'M', '舄'),
-    (0x2F98D, 'M', '辞'),
-    (0x2F98E, 'M', '䑫'),
-    (0x2F98F, 'M', '芑'),
-    (0x2F990, 'M', '芋'),
-    (0x2F991, 'M', '芝'),
-    (0x2F992, 'M', '劳'),
-    (0x2F993, 'M', '花'),
-    (0x2F994, 'M', '芳'),
-    (0x2F995, 'M', '芽'),
-    (0x2F996, 'M', '苦'),
-    (0x2F997, 'M', '𦬼'),
-    (0x2F998, 'M', '若'),
-    (0x2F999, 'M', '茝'),
-    (0x2F99A, 'M', '荣'),
-    (0x2F99B, 'M', '莭'),
-    (0x2F99C, 'M', '茣'),
-    (0x2F99D, 'M', '莽'),
-    (0x2F99E, 'M', '菧'),
-    (0x2F99F, 'M', '著'),
-    (0x2F9A0, 'M', '荓'),
-    (0x2F9A1, 'M', '菊'),
-    (0x2F9A2, 'M', '菌'),
-    (0x2F9A3, 'M', '菜'),
-    (0x2F9A4, 'M', '𦰶'),
-    (0x2F9A5, 'M', '𦵫'),
-    (0x2F9A6, 'M', '𦳕'),
-    (0x2F9A7, 'M', '䔫'),
-    (0x2F9A8, 'M', '蓱'),
-    (0x2F9A9, 'M', '蓳'),
-    (0x2F9AA, 'M', '蔖'),
-    (0x2F9AB, 'M', '𧏊'),
-    (0x2F9AC, 'M', '蕤'),
-    (0x2F9AD, 'M', '𦼬'),
-    (0x2F9AE, 'M', '䕝'),
-    (0x2F9AF, 'M', '䕡'),
-    (0x2F9B0, 'M', '𦾱'),
-    (0x2F9B1, 'M', '𧃒'),
-    (0x2F9B2, 'M', '䕫'),
-    (0x2F9B3, 'M', '虐'),
-    (0x2F9B4, 'M', '虜'),
-    (0x2F9B5, 'M', '虧'),
-    (0x2F9B6, 'M', '虩'),
-    (0x2F9B7, 'M', '蚩'),
-    (0x2F9B8, 'M', '蚈'),
-    (0x2F9B9, 'M', '蜎'),
-    (0x2F9BA, 'M', '蛢'),
-    (0x2F9BB, 'M', '蝹'),
-    (0x2F9BC, 'M', '蜨'),
-    (0x2F9BD, 'M', '蝫'),
-    (0x2F9BE, 'M', '螆'),
-    (0x2F9BF, 'X'),
-    (0x2F9C0, 'M', '蟡'),
-    (0x2F9C1, 'M', '蠁'),
-    (0x2F9C2, 'M', '䗹'),
-    ]
-
-def _seg_80() -> List[Union[Tuple[int, str], Tuple[int, str, str]]]:
-    return [
-    (0x2F9C3, 'M', '衠'),
-    (0x2F9C4, 'M', '衣'),
-    (0x2F9C5, 'M', '𧙧'),
-    (0x2F9C6, 'M', '裗'),
-    (0x2F9C7, 'M', '裞'),
-    (0x2F9C8, 'M', '䘵'),
-    (0x2F9C9, 'M', '裺'),
-    (0x2F9CA, 'M', '㒻'),
-    (0x2F9CB, 'M', '𧢮'),
-    (0x2F9CC, 'M', '𧥦'),
-    (0x2F9CD, 'M', '䚾'),
-    (0x2F9CE, 'M', '䛇'),
-    (0x2F9CF, 'M', '誠'),
-    (0x2F9D0, 'M', '諭'),
-    (0x2F9D1, 'M', '變'),
-    (0x2F9D2, 'M', '豕'),
-    (0x2F9D3, 'M', '𧲨'),
-    (0x2F9D4, 'M', '貫'),
-    (0x2F9D5, 'M', '賁'),
-    (0x2F9D6, 'M', '贛'),
-    (0x2F9D7, 'M', '起'),
-    (0x2F9D8, 'M', '𧼯'),
-    (0x2F9D9, 'M', '𠠄'),
-    (0x2F9DA, 'M', '跋'),
-    (0x2F9DB, 'M', '趼'),
-    (0x2F9DC, 'M', '跰'),
-    (0x2F9DD, 'M', '𠣞'),
-    (0x2F9DE, 'M', '軔'),
-    (0x2F9DF, 'M', '輸'),
-    (0x2F9E0, 'M', '𨗒'),
-    (0x2F9E1, 'M', '𨗭'),
-    (0x2F9E2, 'M', '邔'),
-    (0x2F9E3, 'M', '郱'),
-    (0x2F9E4, 'M', '鄑'),
-    (0x2F9E5, 'M', '𨜮'),
-    (0x2F9E6, 'M', '鄛'),
-    (0x2F9E7, 'M', '鈸'),
-    (0x2F9E8, 'M', '鋗'),
-    (0x2F9E9, 'M', '鋘'),
-    (0x2F9EA, 'M', '鉼'),
-    (0x2F9EB, 'M', '鏹'),
-    (0x2F9EC, 'M', '鐕'),
-    (0x2F9ED, 'M', '𨯺'),
-    (0x2F9EE, 'M', '開'),
-    (0x2F9EF, 'M', '䦕'),
-    (0x2F9F0, 'M', '閷'),
-    (0x2F9F1, 'M', '𨵷'),
-    (0x2F9F2, 'M', '䧦'),
-    (0x2F9F3, 'M', '雃'),
-    (0x2F9F4, 'M', '嶲'),
-    (0x2F9F5, 'M', '霣'),
-    (0x2F9F6, 'M', '𩅅'),
-    (0x2F9F7, 'M', '𩈚'),
-    (0x2F9F8, 'M', '䩮'),
-    (0x2F9F9, 'M', '䩶'),
-    (0x2F9FA, 'M', '韠'),
-    (0x2F9FB, 'M', '𩐊'),
-    (0x2F9FC, 'M', '䪲'),
-    (0x2F9FD, 'M', '𩒖'),
-    (0x2F9FE, 'M', '頋'),
-    (0x2FA00, 'M', '頩'),
-    (0x2FA01, 'M', '𩖶'),
-    (0x2FA02, 'M', '飢'),
-    (0x2FA03, 'M', '䬳'),
-    (0x2FA04, 'M', '餩'),
-    (0x2FA05, 'M', '馧'),
-    (0x2FA06, 'M', '駂'),
-    (0x2FA07, 'M', '駾'),
-    (0x2FA08, 'M', '䯎'),
-    (0x2FA09, 'M', '𩬰'),
-    (0x2FA0A, 'M', '鬒'),
-    (0x2FA0B, 'M', '鱀'),
-    (0x2FA0C, 'M', '鳽'),
-    (0x2FA0D, 'M', '䳎'),
-    (0x2FA0E, 'M', '䳭'),
-    (0x2FA0F, 'M', '鵧'),
-    (0x2FA10, 'M', '𪃎'),
-    (0x2FA11, 'M', '䳸'),
-    (0x2FA12, 'M', '𪄅'),
-    (0x2FA13, 'M', '𪈎'),
-    (0x2FA14, 'M', '𪊑'),
-    (0x2FA15, 'M', '麻'),
-    (0x2FA16, 'M', '䵖'),
-    (0x2FA17, 'M', '黹'),
-    (0x2FA18, 'M', '黾'),
-    (0x2FA19, 'M', '鼅'),
-    (0x2FA1A, 'M', '鼏'),
-    (0x2FA1B, 'M', '鼖'),
-    (0x2FA1C, 'M', '鼻'),
-    (0x2FA1D, 'M', '𪘀'),
-    (0x2FA1E, 'X'),
-    (0x30000, 'V'),
-    (0x3134B, 'X'),
-    (0xE0100, 'I'),
-    (0xE01F0, 'X'),
-    ]
-
-uts46data = tuple(
-    _seg_0()
-    + _seg_1()
-    + _seg_2()
-    + _seg_3()
-    + _seg_4()
-    + _seg_5()
-    + _seg_6()
-    + _seg_7()
-    + _seg_8()
-    + _seg_9()
-    + _seg_10()
-    + _seg_11()
-    + _seg_12()
-    + _seg_13()
-    + _seg_14()
-    + _seg_15()
-    + _seg_16()
-    + _seg_17()
-    + _seg_18()
-    + _seg_19()
-    + _seg_20()
-    + _seg_21()
-    + _seg_22()
-    + _seg_23()
-    + _seg_24()
-    + _seg_25()
-    + _seg_26()
-    + _seg_27()
-    + _seg_28()
-    + _seg_29()
-    + _seg_30()
-    + _seg_31()
-    + _seg_32()
-    + _seg_33()
-    + _seg_34()
-    + _seg_35()
-    + _seg_36()
-    + _seg_37()
-    + _seg_38()
-    + _seg_39()
-    + _seg_40()
-    + _seg_41()
-    + _seg_42()
-    + _seg_43()
-    + _seg_44()
-    + _seg_45()
-    + _seg_46()
-    + _seg_47()
-    + _seg_48()
-    + _seg_49()
-    + _seg_50()
-    + _seg_51()
-    + _seg_52()
-    + _seg_53()
-    + _seg_54()
-    + _seg_55()
-    + _seg_56()
-    + _seg_57()
-    + _seg_58()
-    + _seg_59()
-    + _seg_60()
-    + _seg_61()
-    + _seg_62()
-    + _seg_63()
-    + _seg_64()
-    + _seg_65()
-    + _seg_66()
-    + _seg_67()
-    + _seg_68()
-    + _seg_69()
-    + _seg_70()
-    + _seg_71()
-    + _seg_72()
-    + _seg_73()
-    + _seg_74()
-    + _seg_75()
-    + _seg_76()
-    + _seg_77()
-    + _seg_78()
-    + _seg_79()
-    + _seg_80()
-)  # type: Tuple[Union[Tuple[int, str], Tuple[int, str, str]], ...]
diff --git a/spaces/profayle/TerrapinTalk/myenv/lib/python3.9/site-packages/pip/_vendor/tomli/_parser.py b/spaces/profayle/TerrapinTalk/myenv/lib/python3.9/site-packages/pip/_vendor/tomli/_parser.py
deleted file mode 100644
index 730a746843b98732f964e7b4111b30782b99c0c3..0000000000000000000000000000000000000000
--- a/spaces/profayle/TerrapinTalk/myenv/lib/python3.9/site-packages/pip/_vendor/tomli/_parser.py
+++ /dev/null
@@ -1,703 +0,0 @@
-import string
-from types import MappingProxyType
-from typing import (
-    TYPE_CHECKING,
-    Any,
-    Callable,
-    Dict,
-    FrozenSet,
-    Iterable,
-    Optional,
-    TextIO,
-    Tuple,
-)
-
-from pip._vendor.tomli._re import (
-    RE_BIN,
-    RE_DATETIME,
-    RE_HEX,
-    RE_LOCALTIME,
-    RE_NUMBER,
-    RE_OCT,
-    match_to_datetime,
-    match_to_localtime,
-    match_to_number,
-)
-
-if TYPE_CHECKING:
-    from re import Pattern
-
-
-ASCII_CTRL = frozenset(chr(i) for i in range(32)) | frozenset(chr(127))
-
-# Neither of these sets include quotation mark or backslash. They are
-# currently handled as separate cases in the parser functions.
-ILLEGAL_BASIC_STR_CHARS = ASCII_CTRL - frozenset("\t")
-ILLEGAL_MULTILINE_BASIC_STR_CHARS = ASCII_CTRL - frozenset("\t\n\r")
-
-ILLEGAL_LITERAL_STR_CHARS = ILLEGAL_BASIC_STR_CHARS
-ILLEGAL_MULTILINE_LITERAL_STR_CHARS = ASCII_CTRL - frozenset("\t\n")
-
-ILLEGAL_COMMENT_CHARS = ILLEGAL_BASIC_STR_CHARS
-
-TOML_WS = frozenset(" \t")
-TOML_WS_AND_NEWLINE = TOML_WS | frozenset("\n")
-BARE_KEY_CHARS = frozenset(string.ascii_letters + string.digits + "-_")
-KEY_INITIAL_CHARS = BARE_KEY_CHARS | frozenset("\"'")
-
-BASIC_STR_ESCAPE_REPLACEMENTS = MappingProxyType(
-    {
-        "\\b": "\u0008",  # backspace
-        "\\t": "\u0009",  # tab
-        "\\n": "\u000A",  # linefeed
-        "\\f": "\u000C",  # form feed
-        "\\r": "\u000D",  # carriage return
-        '\\"': "\u0022",  # quote
-        "\\\\": "\u005C",  # backslash
-    }
-)
-
-# Type annotations
-ParseFloat = Callable[[str], Any]
-Key = Tuple[str, ...]
-Pos = int
-
-
-class TOMLDecodeError(ValueError):
-    """An error raised if a document is not valid TOML."""
-
-
-def load(fp: TextIO, *, parse_float: ParseFloat = float) -> Dict[str, Any]:
-    """Parse TOML from a file object."""
-    s = fp.read()
-    return loads(s, parse_float=parse_float)
-
-
-def loads(s: str, *, parse_float: ParseFloat = float) -> Dict[str, Any]:  # noqa: C901
-    """Parse TOML from a string."""
-
-    # The spec allows converting "\r\n" to "\n", even in string
-    # literals. Let's do so to simplify parsing.
-    src = s.replace("\r\n", "\n")
-    pos = 0
-    state = State()
-
-    # Parse one statement at a time
-    # (typically means one line in TOML source)
-    while True:
-        # 1. Skip line leading whitespace
-        pos = skip_chars(src, pos, TOML_WS)
-
-        # 2. Parse rules. Expect one of the following:
-        #    - end of file
-        #    - end of line
-        #    - comment
-        #    - key/value pair
-        #    - append dict to list (and move to its namespace)
-        #    - create dict (and move to its namespace)
-        # Skip trailing whitespace when applicable.
-        try:
-            char = src[pos]
-        except IndexError:
-            break
-        if char == "\n":
-            pos += 1
-            continue
-        if char in KEY_INITIAL_CHARS:
-            pos = key_value_rule(src, pos, state, parse_float)
-            pos = skip_chars(src, pos, TOML_WS)
-        elif char == "[":
-            try:
-                second_char: Optional[str] = src[pos + 1]
-            except IndexError:
-                second_char = None
-            if second_char == "[":
-                pos = create_list_rule(src, pos, state)
-            else:
-                pos = create_dict_rule(src, pos, state)
-            pos = skip_chars(src, pos, TOML_WS)
-        elif char != "#":
-            raise suffixed_err(src, pos, "Invalid statement")
-
-        # 3. Skip comment
-        pos = skip_comment(src, pos)
-
-        # 4. Expect end of line or end of file
-        try:
-            char = src[pos]
-        except IndexError:
-            break
-        if char != "\n":
-            raise suffixed_err(
-                src, pos, "Expected newline or end of document after a statement"
-            )
-        pos += 1
-
-    return state.out.dict
-
-
-class State:
-    def __init__(self) -> None:
-        # Mutable, read-only
-        self.out = NestedDict()
-        self.flags = Flags()
-
-        # Immutable, read and write
-        self.header_namespace: Key = ()
-
-
-class Flags:
-    """Flags that map to parsed keys/namespaces."""
-
-    # Marks an immutable namespace (inline array or inline table).
-    FROZEN = 0
-    # Marks a nest that has been explicitly created and can no longer
-    # be opened using the "[table]" syntax.
-    EXPLICIT_NEST = 1
-
-    def __init__(self) -> None:
-        self._flags: Dict[str, dict] = {}
-
-    def unset_all(self, key: Key) -> None:
-        cont = self._flags
-        for k in key[:-1]:
-            if k not in cont:
-                return
-            cont = cont[k]["nested"]
-        cont.pop(key[-1], None)
-
-    def set_for_relative_key(self, head_key: Key, rel_key: Key, flag: int) -> None:
-        cont = self._flags
-        for k in head_key:
-            if k not in cont:
-                cont[k] = {"flags": set(), "recursive_flags": set(), "nested": {}}
-            cont = cont[k]["nested"]
-        for k in rel_key:
-            if k in cont:
-                cont[k]["flags"].add(flag)
-            else:
-                cont[k] = {"flags": {flag}, "recursive_flags": set(), "nested": {}}
-            cont = cont[k]["nested"]
-
-    def set(self, key: Key, flag: int, *, recursive: bool) -> None:  # noqa: A003
-        cont = self._flags
-        key_parent, key_stem = key[:-1], key[-1]
-        for k in key_parent:
-            if k not in cont:
-                cont[k] = {"flags": set(), "recursive_flags": set(), "nested": {}}
-            cont = cont[k]["nested"]
-        if key_stem not in cont:
-            cont[key_stem] = {"flags": set(), "recursive_flags": set(), "nested": {}}
-        cont[key_stem]["recursive_flags" if recursive else "flags"].add(flag)
-
-    def is_(self, key: Key, flag: int) -> bool:
-        if not key:
-            return False  # document root has no flags
-        cont = self._flags
-        for k in key[:-1]:
-            if k not in cont:
-                return False
-            inner_cont = cont[k]
-            if flag in inner_cont["recursive_flags"]:
-                return True
-            cont = inner_cont["nested"]
-        key_stem = key[-1]
-        if key_stem in cont:
-            cont = cont[key_stem]
-            return flag in cont["flags"] or flag in cont["recursive_flags"]
-        return False
-
-
-class NestedDict:
-    def __init__(self) -> None:
-        # The parsed content of the TOML document
-        self.dict: Dict[str, Any] = {}
-
-    def get_or_create_nest(
-        self,
-        key: Key,
-        *,
-        access_lists: bool = True,
-    ) -> dict:
-        cont: Any = self.dict
-        for k in key:
-            if k not in cont:
-                cont[k] = {}
-            cont = cont[k]
-            if access_lists and isinstance(cont, list):
-                cont = cont[-1]
-            if not isinstance(cont, dict):
-                raise KeyError("There is no nest behind this key")
-        return cont
-
-    def append_nest_to_list(self, key: Key) -> None:
-        cont = self.get_or_create_nest(key[:-1])
-        last_key = key[-1]
-        if last_key in cont:
-            list_ = cont[last_key]
-            if not isinstance(list_, list):
-                raise KeyError("An object other than list found behind this key")
-            list_.append({})
-        else:
-            cont[last_key] = [{}]
-
-
-def skip_chars(src: str, pos: Pos, chars: Iterable[str]) -> Pos:
-    try:
-        while src[pos] in chars:
-            pos += 1
-    except IndexError:
-        pass
-    return pos
-
-
-def skip_until(
-    src: str,
-    pos: Pos,
-    expect: str,
-    *,
-    error_on: FrozenSet[str],
-    error_on_eof: bool,
-) -> Pos:
-    try:
-        new_pos = src.index(expect, pos)
-    except ValueError:
-        new_pos = len(src)
-        if error_on_eof:
-            raise suffixed_err(src, new_pos, f'Expected "{expect!r}"')
-
-    bad_chars = error_on.intersection(src[pos:new_pos])
-    if bad_chars:
-        bad_char = next(iter(bad_chars))
-        bad_pos = src.index(bad_char, pos)
-        raise suffixed_err(src, bad_pos, f'Found invalid character "{bad_char!r}"')
-    return new_pos
-
-
-def skip_comment(src: str, pos: Pos) -> Pos:
-    try:
-        char: Optional[str] = src[pos]
-    except IndexError:
-        char = None
-    if char == "#":
-        return skip_until(
-            src, pos + 1, "\n", error_on=ILLEGAL_COMMENT_CHARS, error_on_eof=False
-        )
-    return pos
-
-
-def skip_comments_and_array_ws(src: str, pos: Pos) -> Pos:
-    while True:
-        pos_before_skip = pos
-        pos = skip_chars(src, pos, TOML_WS_AND_NEWLINE)
-        pos = skip_comment(src, pos)
-        if pos == pos_before_skip:
-            return pos
-
-
-def create_dict_rule(src: str, pos: Pos, state: State) -> Pos:
-    pos += 1  # Skip "["
-    pos = skip_chars(src, pos, TOML_WS)
-    pos, key = parse_key(src, pos)
-
-    if state.flags.is_(key, Flags.EXPLICIT_NEST) or state.flags.is_(key, Flags.FROZEN):
-        raise suffixed_err(src, pos, f"Can not declare {key} twice")
-    state.flags.set(key, Flags.EXPLICIT_NEST, recursive=False)
-    try:
-        state.out.get_or_create_nest(key)
-    except KeyError:
-        raise suffixed_err(src, pos, "Can not overwrite a value")
-    state.header_namespace = key
-
-    if src[pos : pos + 1] != "]":
-        raise suffixed_err(src, pos, 'Expected "]" at the end of a table declaration')
-    return pos + 1
-
-
-def create_list_rule(src: str, pos: Pos, state: State) -> Pos:
-    pos += 2  # Skip "[["
-    pos = skip_chars(src, pos, TOML_WS)
-    pos, key = parse_key(src, pos)
-
-    if state.flags.is_(key, Flags.FROZEN):
-        raise suffixed_err(src, pos, f"Can not mutate immutable namespace {key}")
-    # Free the namespace now that it points to another empty list item...
-    state.flags.unset_all(key)
-    # ...but this key precisely is still prohibited from table declaration
-    state.flags.set(key, Flags.EXPLICIT_NEST, recursive=False)
-    try:
-        state.out.append_nest_to_list(key)
-    except KeyError:
-        raise suffixed_err(src, pos, "Can not overwrite a value")
-    state.header_namespace = key
-
-    end_marker = src[pos : pos + 2]
-    if end_marker != "]]":
-        raise suffixed_err(
-            src,
-            pos,
-            f'Found "{end_marker!r}" at the end of an array declaration.'
-            ' Expected "]]"',
-        )
-    return pos + 2
-
-
-def key_value_rule(src: str, pos: Pos, state: State, parse_float: ParseFloat) -> Pos:
-    pos, key, value = parse_key_value_pair(src, pos, parse_float)
-    key_parent, key_stem = key[:-1], key[-1]
-    abs_key_parent = state.header_namespace + key_parent
-
-    if state.flags.is_(abs_key_parent, Flags.FROZEN):
-        raise suffixed_err(
-            src, pos, f"Can not mutate immutable namespace {abs_key_parent}"
-        )
-    # Containers in the relative path can't be opened with the table syntax after this
-    state.flags.set_for_relative_key(state.header_namespace, key, Flags.EXPLICIT_NEST)
-    try:
-        nest = state.out.get_or_create_nest(abs_key_parent)
-    except KeyError:
-        raise suffixed_err(src, pos, "Can not overwrite a value")
-    if key_stem in nest:
-        raise suffixed_err(src, pos, "Can not overwrite a value")
-    # Mark inline table and array namespaces recursively immutable
-    if isinstance(value, (dict, list)):
-        abs_key = state.header_namespace + key
-        state.flags.set(abs_key, Flags.FROZEN, recursive=True)
-    nest[key_stem] = value
-    return pos
-
-
-def parse_key_value_pair(
-    src: str, pos: Pos, parse_float: ParseFloat
-) -> Tuple[Pos, Key, Any]:
-    pos, key = parse_key(src, pos)
-    try:
-        char: Optional[str] = src[pos]
-    except IndexError:
-        char = None
-    if char != "=":
-        raise suffixed_err(src, pos, 'Expected "=" after a key in a key/value pair')
-    pos += 1
-    pos = skip_chars(src, pos, TOML_WS)
-    pos, value = parse_value(src, pos, parse_float)
-    return pos, key, value
-
-
-def parse_key(src: str, pos: Pos) -> Tuple[Pos, Key]:
-    pos, key_part = parse_key_part(src, pos)
-    key = [key_part]
-    pos = skip_chars(src, pos, TOML_WS)
-    while True:
-        try:
-            char: Optional[str] = src[pos]
-        except IndexError:
-            char = None
-        if char != ".":
-            return pos, tuple(key)
-        pos += 1
-        pos = skip_chars(src, pos, TOML_WS)
-        pos, key_part = parse_key_part(src, pos)
-        key.append(key_part)
-        pos = skip_chars(src, pos, TOML_WS)
-
-
-def parse_key_part(src: str, pos: Pos) -> Tuple[Pos, str]:
-    try:
-        char: Optional[str] = src[pos]
-    except IndexError:
-        char = None
-    if char in BARE_KEY_CHARS:
-        start_pos = pos
-        pos = skip_chars(src, pos, BARE_KEY_CHARS)
-        return pos, src[start_pos:pos]
-    if char == "'":
-        return parse_literal_str(src, pos)
-    if char == '"':
-        return parse_one_line_basic_str(src, pos)
-    raise suffixed_err(src, pos, "Invalid initial character for a key part")
-
-
-def parse_one_line_basic_str(src: str, pos: Pos) -> Tuple[Pos, str]:
-    pos += 1
-    return parse_basic_str(src, pos, multiline=False)
-
-
-def parse_array(src: str, pos: Pos, parse_float: ParseFloat) -> Tuple[Pos, list]:
-    pos += 1
-    array: list = []
-
-    pos = skip_comments_and_array_ws(src, pos)
-    if src[pos : pos + 1] == "]":
-        return pos + 1, array
-    while True:
-        pos, val = parse_value(src, pos, parse_float)
-        array.append(val)
-        pos = skip_comments_and_array_ws(src, pos)
-
-        c = src[pos : pos + 1]
-        if c == "]":
-            return pos + 1, array
-        if c != ",":
-            raise suffixed_err(src, pos, "Unclosed array")
-        pos += 1
-
-        pos = skip_comments_and_array_ws(src, pos)
-        if src[pos : pos + 1] == "]":
-            return pos + 1, array
-
-
-def parse_inline_table(src: str, pos: Pos, parse_float: ParseFloat) -> Tuple[Pos, dict]:
-    pos += 1
-    nested_dict = NestedDict()
-    flags = Flags()
-
-    pos = skip_chars(src, pos, TOML_WS)
-    if src[pos : pos + 1] == "}":
-        return pos + 1, nested_dict.dict
-    while True:
-        pos, key, value = parse_key_value_pair(src, pos, parse_float)
-        key_parent, key_stem = key[:-1], key[-1]
-        if flags.is_(key, Flags.FROZEN):
-            raise suffixed_err(src, pos, f"Can not mutate immutable namespace {key}")
-        try:
-            nest = nested_dict.get_or_create_nest(key_parent, access_lists=False)
-        except KeyError:
-            raise suffixed_err(src, pos, "Can not overwrite a value")
-        if key_stem in nest:
-            raise suffixed_err(src, pos, f'Duplicate inline table key "{key_stem}"')
-        nest[key_stem] = value
-        pos = skip_chars(src, pos, TOML_WS)
-        c = src[pos : pos + 1]
-        if c == "}":
-            return pos + 1, nested_dict.dict
-        if c != ",":
-            raise suffixed_err(src, pos, "Unclosed inline table")
-        if isinstance(value, (dict, list)):
-            flags.set(key, Flags.FROZEN, recursive=True)
-        pos += 1
-        pos = skip_chars(src, pos, TOML_WS)
-
-
-def parse_basic_str_escape(
-    src: str, pos: Pos, *, multiline: bool = False
-) -> Tuple[Pos, str]:
-    escape_id = src[pos : pos + 2]
-    pos += 2
-    if multiline and escape_id in {"\\ ", "\\\t", "\\\n"}:
-        # Skip whitespace until next non-whitespace character or end of
-        # the doc. Error if non-whitespace is found before newline.
-        if escape_id != "\\\n":
-            pos = skip_chars(src, pos, TOML_WS)
-            char = src[pos : pos + 1]
-            if not char:
-                return pos, ""
-            if char != "\n":
-                raise suffixed_err(src, pos, 'Unescaped "\\" in a string')
-            pos += 1
-        pos = skip_chars(src, pos, TOML_WS_AND_NEWLINE)
-        return pos, ""
-    if escape_id == "\\u":
-        return parse_hex_char(src, pos, 4)
-    if escape_id == "\\U":
-        return parse_hex_char(src, pos, 8)
-    try:
-        return pos, BASIC_STR_ESCAPE_REPLACEMENTS[escape_id]
-    except KeyError:
-        if len(escape_id) != 2:
-            raise suffixed_err(src, pos, "Unterminated string")
-        raise suffixed_err(src, pos, 'Unescaped "\\" in a string')
-
-
-def parse_basic_str_escape_multiline(src: str, pos: Pos) -> Tuple[Pos, str]:
-    return parse_basic_str_escape(src, pos, multiline=True)
-
-
-def parse_hex_char(src: str, pos: Pos, hex_len: int) -> Tuple[Pos, str]:
-    hex_str = src[pos : pos + hex_len]
-    if len(hex_str) != hex_len or any(c not in string.hexdigits for c in hex_str):
-        raise suffixed_err(src, pos, "Invalid hex value")
-    pos += hex_len
-    hex_int = int(hex_str, 16)
-    if not is_unicode_scalar_value(hex_int):
-        raise suffixed_err(src, pos, "Escaped character is not a Unicode scalar value")
-    return pos, chr(hex_int)
-
-
-def parse_literal_str(src: str, pos: Pos) -> Tuple[Pos, str]:
-    pos += 1  # Skip starting apostrophe
-    start_pos = pos
-    pos = skip_until(
-        src, pos, "'", error_on=ILLEGAL_LITERAL_STR_CHARS, error_on_eof=True
-    )
-    return pos + 1, src[start_pos:pos]  # Skip ending apostrophe
-
-
-def parse_multiline_str(src: str, pos: Pos, *, literal: bool) -> Tuple[Pos, str]:
-    pos += 3
-    if src[pos : pos + 1] == "\n":
-        pos += 1
-
-    if literal:
-        delim = "'"
-        end_pos = skip_until(
-            src,
-            pos,
-            "'''",
-            error_on=ILLEGAL_MULTILINE_LITERAL_STR_CHARS,
-            error_on_eof=True,
-        )
-        result = src[pos:end_pos]
-        pos = end_pos + 3
-    else:
-        delim = '"'
-        pos, result = parse_basic_str(src, pos, multiline=True)
-
-    # Add at maximum two extra apostrophes/quotes if the end sequence
-    # is 4 or 5 chars long instead of just 3.
-    if src[pos : pos + 1] != delim:
-        return pos, result
-    pos += 1
-    if src[pos : pos + 1] != delim:
-        return pos, result + delim
-    pos += 1
-    return pos, result + (delim * 2)
-
-
-def parse_basic_str(src: str, pos: Pos, *, multiline: bool) -> Tuple[Pos, str]:
-    if multiline:
-        error_on = ILLEGAL_MULTILINE_BASIC_STR_CHARS
-        parse_escapes = parse_basic_str_escape_multiline
-    else:
-        error_on = ILLEGAL_BASIC_STR_CHARS
-        parse_escapes = parse_basic_str_escape
-    result = ""
-    start_pos = pos
-    while True:
-        try:
-            char = src[pos]
-        except IndexError:
-            raise suffixed_err(src, pos, "Unterminated string")
-        if char == '"':
-            if not multiline:
-                return pos + 1, result + src[start_pos:pos]
-            if src[pos + 1 : pos + 3] == '""':
-                return pos + 3, result + src[start_pos:pos]
-            pos += 1
-            continue
-        if char == "\\":
-            result += src[start_pos:pos]
-            pos, parsed_escape = parse_escapes(src, pos)
-            result += parsed_escape
-            start_pos = pos
-            continue
-        if char in error_on:
-            raise suffixed_err(src, pos, f'Illegal character "{char!r}"')
-        pos += 1
-
-
-def parse_regex(src: str, pos: Pos, regex: "Pattern") -> Tuple[Pos, str]:
-    match = regex.match(src, pos)
-    if not match:
-        raise suffixed_err(src, pos, "Unexpected sequence")
-    return match.end(), match.group()
-
-
-def parse_value(  # noqa: C901
-    src: str, pos: Pos, parse_float: ParseFloat
-) -> Tuple[Pos, Any]:
-    try:
-        char: Optional[str] = src[pos]
-    except IndexError:
-        char = None
-
-    # Basic strings
-    if char == '"':
-        if src[pos + 1 : pos + 3] == '""':
-            return parse_multiline_str(src, pos, literal=False)
-        return parse_one_line_basic_str(src, pos)
-
-    # Literal strings
-    if char == "'":
-        if src[pos + 1 : pos + 3] == "''":
-            return parse_multiline_str(src, pos, literal=True)
-        return parse_literal_str(src, pos)
-
-    # Booleans
-    if char == "t":
-        if src[pos + 1 : pos + 4] == "rue":
-            return pos + 4, True
-    if char == "f":
-        if src[pos + 1 : pos + 5] == "alse":
-            return pos + 5, False
-
-    # Dates and times
-    datetime_match = RE_DATETIME.match(src, pos)
-    if datetime_match:
-        try:
-            datetime_obj = match_to_datetime(datetime_match)
-        except ValueError:
-            raise suffixed_err(src, pos, "Invalid date or datetime")
-        return datetime_match.end(), datetime_obj
-    localtime_match = RE_LOCALTIME.match(src, pos)
-    if localtime_match:
-        return localtime_match.end(), match_to_localtime(localtime_match)
-
-    # Non-decimal integers
-    if char == "0":
-        second_char = src[pos + 1 : pos + 2]
-        if second_char == "x":
-            pos, hex_str = parse_regex(src, pos + 2, RE_HEX)
-            return pos, int(hex_str, 16)
-        if second_char == "o":
-            pos, oct_str = parse_regex(src, pos + 2, RE_OCT)
-            return pos, int(oct_str, 8)
-        if second_char == "b":
-            pos, bin_str = parse_regex(src, pos + 2, RE_BIN)
-            return pos, int(bin_str, 2)
-
-    # Decimal integers and "normal" floats.
-    # The regex will greedily match any type starting with a decimal
-    # char, so needs to be located after handling of non-decimal ints,
-    # and dates and times.
-    number_match = RE_NUMBER.match(src, pos)
-    if number_match:
-        return number_match.end(), match_to_number(number_match, parse_float)
-
-    # Arrays
-    if char == "[":
-        return parse_array(src, pos, parse_float)
-
-    # Inline tables
-    if char == "{":
-        return parse_inline_table(src, pos, parse_float)
-
-    # Special floats
-    first_three = src[pos : pos + 3]
-    if first_three in {"inf", "nan"}:
-        return pos + 3, parse_float(first_three)
-    first_four = src[pos : pos + 4]
-    if first_four in {"-inf", "+inf", "-nan", "+nan"}:
-        return pos + 4, parse_float(first_four)
-
-    raise suffixed_err(src, pos, "Invalid value")
-
-
-def suffixed_err(src: str, pos: Pos, msg: str) -> TOMLDecodeError:
-    """Return a `TOMLDecodeError` where error message is suffixed with
-    coordinates in source."""
-
-    def coord_repr(src: str, pos: Pos) -> str:
-        if pos >= len(src):
-            return "end of document"
-        line = src.count("\n", 0, pos) + 1
-        if line == 1:
-            column = pos + 1
-        else:
-            column = pos - src.rindex("\n", 0, pos)
-        return f"line {line}, column {column}"
-
-    return TOMLDecodeError(f"{msg} (at {coord_repr(src, pos)})")
-
-
-def is_unicode_scalar_value(codepoint: int) -> bool:
-    return (0 <= codepoint <= 55295) or (57344 <= codepoint <= 1114111)
diff --git a/spaces/pyodide-demo/self-hosted/pydantic.js b/spaces/pyodide-demo/self-hosted/pydantic.js
deleted file mode 100644
index 1284d97f1ed389203da5459a4737ee3a342ef2d2..0000000000000000000000000000000000000000
--- a/spaces/pyodide-demo/self-hosted/pydantic.js
+++ /dev/null
@@ -1 +0,0 @@
-var Module=typeof globalThis.__pyodide_module!=="undefined"?globalThis.__pyodide_module:{};if(!Module.expectedDataFileDownloads){Module.expectedDataFileDownloads=0}Module.expectedDataFileDownloads++;(function(){var loadPackage=function(metadata){var PACKAGE_PATH="";if(typeof window==="object"){PACKAGE_PATH=window["encodeURIComponent"](window.location.pathname.toString().substring(0,window.location.pathname.toString().lastIndexOf("/"))+"/")}else if(typeof process==="undefined"&&typeof location!=="undefined"){PACKAGE_PATH=encodeURIComponent(location.pathname.toString().substring(0,location.pathname.toString().lastIndexOf("/"))+"/")}var PACKAGE_NAME="pydantic.data";var REMOTE_PACKAGE_BASE="pydantic.data";if(typeof Module["locateFilePackage"]==="function"&&!Module["locateFile"]){Module["locateFile"]=Module["locateFilePackage"];err("warning: you defined Module.locateFilePackage, that has been renamed to Module.locateFile (using your locateFilePackage for now)")}var REMOTE_PACKAGE_NAME=Module["locateFile"]?Module["locateFile"](REMOTE_PACKAGE_BASE,""):REMOTE_PACKAGE_BASE;var REMOTE_PACKAGE_SIZE=metadata["remote_package_size"];var PACKAGE_UUID=metadata["package_uuid"];function fetchRemotePackage(packageName,packageSize,callback,errback){if(typeof process==="object"){require("fs").readFile(packageName,(function(err,contents){if(err){errback(err)}else{callback(contents.buffer)}}));return}var xhr=new XMLHttpRequest;xhr.open("GET",packageName,true);xhr.responseType="arraybuffer";xhr.onprogress=function(event){var url=packageName;var size=packageSize;if(event.total)size=event.total;if(event.loaded){if(!xhr.addedTotal){xhr.addedTotal=true;if(!Module.dataFileDownloads)Module.dataFileDownloads={};Module.dataFileDownloads[url]={loaded:event.loaded,total:size}}else{Module.dataFileDownloads[url].loaded=event.loaded}var total=0;var loaded=0;var num=0;for(var download in Module.dataFileDownloads){var data=Module.dataFileDownloads[download];total+=data.total;loaded+=data.loaded;num++}total=Math.ceil(total*Module.expectedDataFileDownloads/num);if(Module["setStatus"])Module["setStatus"]("Downloading data... ("+loaded+"/"+total+")")}else if(!Module.dataFileDownloads){if(Module["setStatus"])Module["setStatus"]("Downloading data...")}};xhr.onerror=function(event){throw new Error("NetworkError for: "+packageName)};xhr.onload=function(event){if(xhr.status==200||xhr.status==304||xhr.status==206||xhr.status==0&&xhr.response){var packageData=xhr.response;callback(packageData)}else{throw new Error(xhr.statusText+" : "+xhr.responseURL)}};xhr.send(null)}function handleError(error){console.error("package error:",error)}var fetchedCallback=null;var fetched=Module["getPreloadedPackage"]?Module["getPreloadedPackage"](REMOTE_PACKAGE_NAME,REMOTE_PACKAGE_SIZE):null;if(!fetched)fetchRemotePackage(REMOTE_PACKAGE_NAME,REMOTE_PACKAGE_SIZE,(function(data){if(fetchedCallback){fetchedCallback(data);fetchedCallback=null}else{fetched=data}}),handleError);function runWithFS(){function assert(check,msg){if(!check)throw msg+(new Error).stack}Module["FS_createPath"]("/","lib",true,true);Module["FS_createPath"]("/lib","python3.9",true,true);Module["FS_createPath"]("/lib/python3.9","site-packages",true,true);Module["FS_createPath"]("/lib/python3.9/site-packages","pydantic",true,true);Module["FS_createPath"]("/lib/python3.9/site-packages","pydantic-1.9.0-py3.9.egg-info",true,true);function processPackageData(arrayBuffer){assert(arrayBuffer,"Loading data file failed.");assert(arrayBuffer instanceof ArrayBuffer,"bad input to processPackageData");var byteArray=new Uint8Array(arrayBuffer);var curr;var compressedData={data:null,cachedOffset:3241131,cachedIndexes:[-1,-1],cachedChunks:[null,null],offsets:[0,1129,2486,3979,5225,6327,7644,8416,9573,10913,12086,13357,14543,15649,16848,17559,18586,19860,21079,22069,23251,24233,25511,26624,27889,29208,30373,31540,32759,33972,34865,36329,37629,38684,39748,40956,42071,43126,44075,45029,46375,47492,48643,49725,50908,52071,53365,54525,55858,56737,57840,58758,59408,60031,60805,61566,62225,63463,64561,65538,66697,67591,68693,69876,71040,72079,73140,74188,75312,76080,76875,78125,79120,80137,81213,82196,83320,84446,85477,86709,87928,89350,90609,91795,92979,94033,95375,96683,98053,99358,100732,102147,103457,104659,105548,106491,107709,108963,110020,110956,112210,113198,114383,115529,116441,117425,118455,119470,120681,121935,123081,124459,125570,126880,128080,129220,130361,131587,132765,133980,135214,136313,137459,138892,140129,141334,142479,143380,144565,145597,146655,147608,148660,150001,151258,152569,153838,155160,156516,157601,158642,159878,160915,162152,163150,164095,165260,166457,167679,168702,170031,171078,172116,173386,174582,175335,176457,177438,178504,179757,180779,181764,182733,183815,184932,186017,187189,188265,189215,190024,190885,192056,193045,194154,195161,196439,197660,198945,200098,201327,202472,203630,204945,206377,207670,208896,210286,211564,212796,213955,215054,216270,217643,218763,220010,220841,221828,222670,223485,224478,225400,226489,227490,228481,229871,231154,232277,233666,234496,235422,236529,237144,238469,240032,241342,242174,243338,244645,245775,247122,248280,249173,250214,251406,252667,253854,255002,256149,257142,258354,259362,260393,261541,262563,263993,265448,266781,267822,269310,270851,272408,273781,275224,276730,278321,279679,280726,281225,282434,283734,284939,285984,287027,288086,289491,290509,291340,292299,293222,294469,295659,296980,298223,299606,300664,301645,302651,303559,304712,306041,307171,308148,309199,310231,311362,312563,313806,314814,315897,317078,318331,319390,320484,321550,322662,323828,324823,325841,326894,327999,329379,330796,332184,333809,334982,335854,337176,338432,339849,341120,342534,343970,345391,346716,348114,349406,350592,351943,353236,354517,355714,357123,358555,359898,361235,362370,363642,365e3,366509,367650,368817,370204,371660,372998,374255,375586,376724,378230,379698,381210,382369,383323,384402,385245,385425,385450,386531,387800,389220,390385,391561,392602,393641,394674,395710,396747,397782,398799,399834,400965,401897,403130,403932,404902,405832,406529,407413,408334,408918,409639,410616,411743,412851,414103,415291,416443,417675,419035,419980,421145,422216,423554,424629,425776,426809,427959,429144,430387,431636,432895,434082,435238,436343,437381,438672,439716,440883,442208,443427,444329,445614,446550,447870,449128,450317,451320,452409,453433,454571,455975,457040,458063,459370,460525,461778,463124,464446,465729,467084,468194,469029,470106,471131,472141,473154,474373,475426,476319,477584,479035,480333,481475,482776,484024,485160,486584,488017,489149,489892,490656,491402,492051,492722,493610,495097,496709,498115,499254,500432,501894,503264,503905,504439,504925,506420,507739,509134,510675,512186,513466,514745,516055,517119,518445,519719,521206,522147,523603,525046,525954,527300,528817,530237,531669,532868,534418,535883,537361,538589,540101,541553,542963,544410,545787,547301,548878,550324,551911,553297,554641,556078,557397,558749,560133,561175,562517,564067,565395,566743,568207,569507,570952,572364,573868,575306,576814,578224,579676,581165,582661,584120,585529,586919,587929,589488,591089,592518,593809,595276,596546,598068,599444,600919,602353,603649,605182,606588,608042,609540,611e3,612601,613933,614652,615604,617079,617933,619021,619734,620644,621622,622688,623740,624768,625793,626783,627132,627468,628054,628079,628104,628129,628647,629941,631146,632524,633530,634728,635983,637414,638723,639761,641221,642693,644172,645621,647151,648545,649902,651122,652230,653502,654800,656118,657225,658265,659301,660350,661395,662440,663527,664608,665983,667082,668151,669201,670275,671381,672306,673223,673907,674891,675584,676489,677014,677515,678090,678826,679567,680723,681793,682599,683655,684412,685584,686536,687735,688758,689596,690431,691486,692454,693508,694549,695401,696366,697357,698373,699414,700471,701392,702106,702959,704151,705126,706265,707117,708241,709066,709985,710999,711829,712912,713974,715180,716053,717120,717854,718578,719375,720492,721366,722363,723517,724471,725572,726465,727248,728612,729996,731310,732351,733588,735093,736470,737919,738712,739401,740605,742096,743677,745174,746635,748040,749483,750918,752314,753360,754678,756130,757569,758885,760262,761731,763047,764487,765829,767358,768724,769965,771326,772732,773905,775310,776774,778083,779291,780546,781916,783465,784953,786436,787374,788581,789998,791231,792702,794070,795491,796887,798371,799564,800938,802452,803815,805161,806422,807844,809282,810752,812193,813452,814773,815967,817332,818788,820218,821749,823229,824755,826184,827692,829179,830429,831598,832874,834198,835566,836970,838439,839879,841175,842643,843942,845425,846883,848285,849748,851037,852480,853831,855303,856763,858220,859698,861149,862364,863574,864799,866034,867350,868688,870046,871478,872553,873762,875089,876538,877984,879394,880695,882216,883849,885192,886679,888041,889116,890065,891132,892178,893250,894318,895342,895742,896901,898133,899308,900444,901756,902252,902277,902302,902327,903280,904537,905947,907087,908125,909178,910241,911233,912600,913572,914489,915564,916283,917223,918620,919688,920755,921822,922970,924173,925285,926576,927827,928990,930087,931067,932259,933433,934891,936481,937699,938762,939988,941502,942874,944043,944759,946026,947506,948885,950265,951838,953260,954614,955996,957515,958978,960388,961939,963362,964882,966414,967884,969323,970722,972047,973556,974931,976154,977555,979045,980244,980931,982293,983618,984908,986138,987192,988217,989758,990633,991366,992839,993931,995033,996233,997301,998751,999997,1001375,1002734,1003820,1004861,1005495,1006539,1007584,1008251,1009579,1009729,1010229,1011531,1012828,1014120,1015203,1016247,1017290,1018327,1019367,1020426,1021657,1022292,1023036,1024090,1024854,1025993,1027124,1028351,1029312,1030355,1031467,1032498,1033494,1034705,1036077,1037278,1038477,1039649,1040965,1042078,1043193,1044412,1045571,1046464,1047374,1048518,1049807,1051119,1051912,1052903,1053889,1054880,1055860,1056822,1058028,1059645,1061263,1062535,1063490,1064873,1066300,1067755,1068509,1069885,1071309,1072652,1074051,1075536,1076906,1078356,1079408,1080792,1082285,1083573,1084926,1086487,1087761,1089181,1090581,1091961,1093347,1094719,1096157,1097594,1099053,1100527,1102016,1103391,1104671,1105965,1107263,1108552,1109978,1111446,1112813,1114203,1115713,1117317,1118751,1120018,1121455,1122953,1124398,1125872,1127282,1128703,1130157,1131573,1133330,1134675,1136114,1137441,1138636,1139695,1140768,1141835,1142908,1143739,1144645,1144670,1144695,1145874,1147210,1148335,1149474,1150879,1152105,1152917,1154117,1155347,1156521,1157582,1158924,1159804,1160760,1161851,1163069,1164564,1166088,1167484,1168523,1170095,1171434,1172982,1174490,1175946,1177485,1178921,1180240,1181260,1181909,1183183,1184351,1185848,1187043,1188075,1189115,1190166,1191220,1192280,1193459,1194620,1195292,1195951,1196560,1197456,1198584,1199527,1200498,1201424,1202086,1203038,1203796,1204860,1206018,1207103,1208169,1209180,1210156,1211141,1211926,1212891,1214019,1215095,1216263,1217334,1218480,1219628,1220740,1221845,1222947,1224047,1225153,1226237,1227043,1228146,1229276,1230368,1231511,1232654,1233651,1234759,1235992,1237210,1238282,1239425,1240591,1241590,1242506,1243445,1244346,1245244,1246471,1247755,1248957,1250541,1251865,1252848,1254168,1255634,1256919,1258281,1258996,1259954,1261345,1262687,1263934,1265330,1266659,1268030,1269510,1270820,1272321,1273324,1274554,1275980,1277214,1278620,1279921,1281003,1282203,1283442,1284967,1286372,1287712,1289071,1290442,1291774,1293085,1294484,1295816,1297126,1298455,1299807,1301177,1302524,1303857,1305e3,1306382,1307867,1309154,1310541,1311716,1313234,1314469,1315860,1317332,1318479,1319799,1321296,1322650,1324175,1325608,1327088,1328587,1329992,1331218,1332184,1333362,1334292,1335512,1336904,1338318,1339809,1340955,1342138,1343488,1344794,1345890,1346764,1347445,1348489,1349493,1350508,1351569,1352471,1353230,1353255,1353280,1353305,1354039,1355369,1356698,1357811,1358849,1359893,1361120,1362250,1363310,1364341,1365190,1366083,1367119,1368373,1369549,1370802,1371963,1373096,1374103,1375126,1376258,1377324,1378573,1379651,1380874,1382316,1383940,1385216,1386376,1387591,1389039,1390481,1391844,1392541,1393849,1395395,1396937,1398377,1399850,1401303,1402840,1404272,1405766,1407099,1408608,1410064,1411547,1413026,1414416,1415719,1416907,1418077,1419390,1420889,1422190,1423685,1425183,1426599,1427964,1429035,1430133,1431113,1431949,1432521,1433183,1434535,1435829,1436998,1438022,1439073,1440114,1441163,1442458,1443292,1444291,1445068,1446088,1446827,1447366,1448255,1449437,1450660,1451691,1452869,1453776,1454616,1455683,1456722,1457813,1458877,1459887,1461037,1462208,1463323,1464429,1465471,1466565,1467716,1468749,1469987,1471093,1472167,1473261,1474163,1475215,1476231,1477321,1478381,1479466,1480595,1481723,1482861,1483889,1484971,1486113,1487222,1488420,1489508,1490713,1491863,1492965,1494099,1495228,1496586,1498182,1499576,1500747,1501973,1503442,1504889,1506283,1507616,1509129,1510633,1511992,1513491,1514867,1516135,1517488,1518858,1520085,1521288,1522530,1523924,1525347,1526856,1528071,1529300,1530620,1531810,1532914,1534220,1535724,1536904,1538125,1539409,1540790,1542162,1543525,1544918,1546289,1547607,1548909,1550046,1551219,1552548,1554105,1555414,1556832,1557864,1558908,1559924,1560920,1562117,1563104,1563129,1563154,1564049,1565270,1566550,1567649,1569016,1570120,1571114,1572213,1573456,1574438,1575676,1576923,1578096,1579238,1580527,1582148,1583541,1584636,1586051,1587541,1588841,1590206,1591677,1593081,1594517,1595895,1597256,1598610,1599982,1601404,1602749,1604045,1605429,1606807,1608038,1609428,1610664,1612014,1613440,1614688,1615927,1616933,1618169,1619639,1621021,1622375,1623432,1624337,1624771,1626039,1627352,1628457,1629498,1630545,1631748,1633054,1633948,1635039,1635670,1636558,1637796,1638973,1640255,1641420,1642501,1643639,1644863,1646403,1647985,1649255,1650282,1651543,1653132,1654444,1655742,1657240,1658480,1659845,1661061,1662391,1663405,1664618,1665907,1667199,1668685,1670228,1671737,1673287,1674705,1676065,1677392,1678824,1680232,1681679,1683037,1684616,1685964,1687120,1688243,1689574,1690849,1692294,1693570,1695096,1696694,1698157,1699694,1700931,1702215,1703393,1704446,1705502,1706162,1706256,1707534,1708858,1710003,1711417,1712907,1714224,1715316,1716531,1718063,1719466,1720866,1722220,1723645,1724901,1726346,1727864,1729217,1730290,1731024,1732295,1733485,1734868,1735956,1737001,1738052,1739097,1740423,1741429,1742372,1743507,1744219,1745129,1746344,1747531,1748627,1749544,1750692,1751830,1752973,1754359,1755546,1756729,1757915,1759133,1760386,1761446,1762691,1763969,1765377,1767007,1768264,1769226,1770617,1772140,1773540,1774380,1775792,1777311,1778636,1779969,1781519,1782884,1784300,1785846,1787395,1788869,1790302,1791671,1792927,1794307,1795723,1797115,1798514,1799736,1801217,1802716,1804129,1805614,1807141,1808581,1809977,1811358,1812771,1814055,1815588,1816924,1818372,1819754,1821113,1822405,1824007,1825398,1826809,1827967,1829343,1830518,1831425,1832526,1833556,1834350,1834377,1835338,1836686,1838073,1839336,1840469,1841511,1842546,1843588,1844632,1845680,1846725,1847765,1848916,1850133,1850988,1852007,1852973,1853722,1854587,1855481,1856538,1857392,1858090,1858882,1859757,1860926,1861820,1862959,1864048,1865233,1866345,1867431,1868507,1869691,1870913,1872064,1873174,1874304,1875420,1876766,1877791,1878849,1880023,1881120,1882283,1883454,1884586,1885614,1886954,1888020,1889179,1890373,1891465,1892710,1893923,1894917,1896164,1897246,1898465,1899645,1900864,1902429,1903897,1905201,1906219,1907458,1908970,1910356,1911555,1912180,1912820,1914277,1915649,1917013,1918577,1920035,1921378,1922982,1924563,1925823,1927197,1928544,1930013,1931530,1932999,1934331,1935818,1937353,1938822,1940289,1941675,1943085,1944585,1946142,1947661,1949116,1950666,1952226,1953735,1954930,1956129,1957580,1959122,1960613,1962052,1963507,1965100,1966564,1968046,1969448,1970750,1972288,1973712,1975108,1976572,1977849,1979176,1980624,1982042,1983550,1985085,1986581,1987874,1989296,1990733,1992279,1993714,1995033,1996439,1997682,1999032,2000472,2001936,2003404,2004856,2006435,2007889,2009457,2010780,2012110,2013584,2014887,2016066,2017016,2018048,2019075,2020190,2021274,2022322,2023359,2023793,2024962,2026251,2026828,2026853,2026878,2028096,2029315,2030636,2031688,2032723,2033869,2035058,2035928,2037068,2037762,2038817,2040041,2041331,2042522,2043540,2044865,2046067,2047250,2048405,2049511,2050731,2052082,2053669,2055008,2055970,2057313,2058804,2060139,2061521,2062199,2063677,2065196,2066550,2067994,2069423,2070894,2072429,2073676,2075169,2076609,2077976,2079549,2080979,2082170,2083462,2084969,2086515,2087809,2089275,2090627,2091775,2092999,2094017,2095052,2095718,2095813,2097099,2098435,2099609,2100652,2101666,2102687,2103708,2104765,2105800,2106830,2107996,2109226,2110601,2111253,2112005,2112908,2114015,2115298,2116623,2117850,2118957,2120271,2121408,2122484,2123610,2125004,2126088,2127137,2128375,2129433,2130805,2131860,2132887,2133945,2134989,2136223,2137546,2138887,2140099,2141434,2142769,2144073,2145366,2146726,2147997,2149346,2150392,2151483,2152709,2153783,2155060,2156347,2157626,2158679,2159706,2160764,2162023,2163304,2164441,2165742,2166766,2167818,2168862,2169896,2171024,2172060,2173130,2174167,2175206,2176263,2177312,2178402,2179465,2180964,2182397,2183520,2184668,2186123,2187603,2189047,2190086,2191660,2193130,2194663,2196176,2197478,2198443,2199406,2200349,2201297,2202583,2203587,2204574,2205569,2206949,2208369,2209874,2211177,2212167,2213309,2214340,2215338,2216541,2217350,2218395,2219406,2220460,2221606,2222509,2222823,2222848,2223906,2225208,2226649,2227887,2228944,2229995,2231027,2232063,2233100,2234129,2235163,2236237,2237255,2238474,2239393,2240537,2241565,2242500,2243392,2244522,2245402,2246007,2246859,2247796,2248669,2249496,2250316,2251583,2252789,2254104,2255210,2256300,2257497,2258792,2260018,2261047,2262076,2263022,2263717,2264831,2265874,2266850,2267966,2268990,2269952,2271222,2271961,2273076,2274210,2275367,2276508,2277689,2278856,2279995,2281183,2282339,2283466,2284765,2286009,2287128,2288441,2289663,2291122,2292358,2293809,2294961,2295962,2297375,2298797,2300281,2301006,2301925,2303181,2303729,2305311,2306712,2308215,2309677,2311135,2312456,2313844,2315280,2316640,2318049,2318973,2320339,2321754,2323155,2324326,2325723,2327227,2328572,2329998,2331267,2332607,2333989,2334992,2336221,2337509,2338861,2340309,2341646,2342674,2343847,2344768,2345959,2347111,2348041,2349208,2350171,2351359,2352683,2354170,2355494,2356694,2357899,2358996,2360046,2361475,2362706,2364103,2365497,2366850,2368076,2369420,2370847,2372328,2373651,2375084,2376606,2377783,2379248,2380639,2382082,2383606,2385108,2386356,2387750,2389200,2390646,2392050,2393191,2394495,2395810,2397142,2398138,2399567,2400987,2402299,2403401,2404750,2406102,2407392,2408754,2410145,2411498,2412990,2414406,2415911,2417247,2418221,2419482,2420960,2422007,2423346,2424611,2426044,2427519,2428832,2430105,2431709,2433110,2434507,2435997,2437249,2438662,2440050,2441535,2443093,2444307,2445532,2446968,2448404,2449695,2451136,2452544,2453928,2455344,2456652,2458066,2459346,2460709,2462138,2463489,2464893,2466173,2467652,2469056,2470387,2471836,2473058,2474365,2475715,2476942,2478272,2479752,2481026,2482536,2483970,2485455,2486775,2488014,2489396,2490599,2491606,2492569,2493680,2494778,2495808,2496826,2497755,2498476,2499437,2500602,2501895,2502410,2502435,2502460,2502485,2503539,2504868,2505999,2507118,2508522,2509668,2510509,2511368,2512524,2513741,2514973,2515930,2516850,2517792,2518508,2519347,2520145,2521192,2522215,2523734,2525304,2526391,2527705,2528885,2530221,2531753,2533161,2534730,2536069,2537364,2538790,2540252,2541493,2542491,2543062,2544344,2545569,2547064,2548259,2549301,2550337,2551377,2552423,2553473,2554517,2555554,2556633,2557657,2558890,2559651,2560896,2561822,2562716,2563676,2564736,2565631,2566400,2566910,2567674,2568452,2569194,2569990,2570790,2571539,2572104,2573073,2573714,2574943,2576036,2577240,2578363,2579531,2580916,2582044,2583154,2584330,2585510,2586599,2587830,2589029,2590304,2591665,2592832,2594054,2595298,2596562,2597781,2598878,2600181,2601515,2602580,2603858,2605058,2606288,2607349,2608501,2609657,2610755,2611997,2613361,2614699,2616272,2617754,2618963,2620132,2621101,2622478,2623991,2625399,2626119,2626793,2627983,2629445,2631008,2632286,2633592,2634961,2636223,2637515,2638834,2640201,2641181,2642495,2643792,2645169,2646435,2647645,2648782,2649974,2651249,2652416,2653840,2655211,2656280,2657320,2658693,2660014,2661267,2662340,2663414,2664783,2665955,2667258,2668786,2670161,2671711,2673096,2674374,2675671,2677045,2678165,2679497,2680824,2682162,2683439,2684907,2686113,2687385,2688740,2690069,2691341,2692674,2694052,2695495,2697079,2698389,2699788,2701209,2702717,2704167,2705600,2706905,2708328,2709775,2711255,2712764,2714093,2715633,2716933,2718265,2719706,2721060,2722566,2723822,2725273,2726701,2728171,2729516,2730914,2732186,2733695,2735180,2736734,2738275,2739723,2741134,2742626,2744107,2745379,2746517,2747853,2749267,2750652,2751778,2752981,2754381,2755821,2757325,2758813,2760103,2761377,2762833,2763994,2765274,2766646,2768034,2769451,2770783,2772255,2773555,2774887,2776329,2777753,2779065,2780563,2781799,2783080,2784457,2785949,2787240,2788488,2789810,2790999,2792281,2793721,2795082,2796435,2797677,2798999,2800249,2801717,2803178,2804295,2805370,2806392,2807438,2808497,2809528,2810549,2811527,2812087,2813325,2813923,2813948,2813973,2814184,2815462,2816659,2818104,2819262,2820301,2821347,2822393,2823434,2824479,2825527,2826540,2827778,2828874,2829949,2830867,2831785,2832826,2833908,2834551,2835290,2835852,2836424,2837082,2837813,2838612,2839270,2840217,2841457,2842706,2843829,2845017,2846153,2847096,2848087,2848954,2850006,2850981,2851951,2853028,2854093,2855103,2856208,2857078,2857979,2859195,2860035,2861170,2862096,2862913,2863866,2864735,2865605,2866536,2867458,2868464,2869598,2870588,2871826,2873412,2874946,2876117,2877079,2878461,2879869,2881338,2882100,2883584,2885154,2886481,2887779,2889367,2890856,2892223,2893567,2895041,2896155,2897543,2898948,2900503,2901747,2903078,2904392,2905762,2907109,2908374,2909827,2911128,2912529,2914012,2915440,2916642,2918182,2919610,2920914,2922248,2923723,2925057,2926215,2927599,2928906,2930256,2931699,2933103,2934414,2935717,2937059,2938350,2939622,2941056,2942386,2943740,2945157,2946388,2947813,2949130,2950613,2951789,2953113,2954440,2955895,2957323,2958820,2960340,2961782,2963195,2964630,2966005,2967441,2968829,2970159,2971664,2973074,2974608,2976054,2977477,2978689,2979980,2981236,2982760,2984193,2985522,2986775,2988013,2989288,2990536,2991858,2993175,2994578,2995870,2996977,2998378,2999659,3000907,3002289,3003532,3004329,3005388,3006508,3007572,3008612,3009700,3010517,3011828,3012630,3012655,3012680,3013536,3014883,3016244,3017446,3018478,3019512,3020554,3021594,3022636,3023759,3025112,3026010,3026796,3027485,3028665,3029462,3030199,3031240,3032336,3033628,3034727,3035677,3036917,3037823,3038916,3039740,3040892,3041820,3042982,3044094,3045233,3046499,3047504,3048738,3050006,3051005,3052273,3053441,3054702,3055728,3057093,3058241,3059468,3060771,3061897,3063282,3064310,3065588,3066786,3068216,3069747,3071193,3072379,3073401,3074826,3076355,3077742,3078378,3079600,3080912,3082261,3083818,3085330,3086635,3088085,3089596,3091116,3092450,3093793,3094949,3096071,3097594,3098991,3100195,3101649,3102624,3103940,3105409,3106936,3108408,3109828,3111253,3112821,3114263,3115638,3117168,3118626,3120127,3121470,3122963,3124005,3125499,3127036,3128281,3129698,3131085,3132405,3133618,3135031,3136365,3137885,3139132,3140401,3141624,3142833,3143626,3144672,3145750,3146822,3147496,3148396,3148421,3148787,3150012,3151274,3152513,3153908,3154854,3156127,3157413,3158508,3159818,3161335,3162643,3163802,3165034,3166333,3167800,3169263,3170515,3172017,3173412,3174575,3175319,3176601,3177825,3178887,3179989,3181162,3182228,3183324,3184479,3185659,3186817,3187992,3188983,3190034,3191154,3192158,3193270,3194422,3195554,3196840,3197995,3199044,3200233,3201311,3202421,3203649,3204833,3206025,3207224,3208365,3209450,3210530,3211631,3212694,3213733,3214855,3215824,3216950,3218036,3219055,3220113,3221121,3222249,3223343,3224424,3225399,3226357,3227526,3228522,3229434,3230580,3231609,3232531,3233502,3234375,3235433,3236437,3237439,3238534,3239758,3240651],sizes:[1129,1357,1493,1246,1102,1317,772,1157,1340,1173,1271,1186,1106,1199,711,1027,1274,1219,990,1182,982,1278,1113,1265,1319,1165,1167,1219,1213,893,1464,1300,1055,1064,1208,1115,1055,949,954,1346,1117,1151,1082,1183,1163,1294,1160,1333,879,1103,918,650,623,774,761,659,1238,1098,977,1159,894,1102,1183,1164,1039,1061,1048,1124,768,795,1250,995,1017,1076,983,1124,1126,1031,1232,1219,1422,1259,1186,1184,1054,1342,1308,1370,1305,1374,1415,1310,1202,889,943,1218,1254,1057,936,1254,988,1185,1146,912,984,1030,1015,1211,1254,1146,1378,1111,1310,1200,1140,1141,1226,1178,1215,1234,1099,1146,1433,1237,1205,1145,901,1185,1032,1058,953,1052,1341,1257,1311,1269,1322,1356,1085,1041,1236,1037,1237,998,945,1165,1197,1222,1023,1329,1047,1038,1270,1196,753,1122,981,1066,1253,1022,985,969,1082,1117,1085,1172,1076,950,809,861,1171,989,1109,1007,1278,1221,1285,1153,1229,1145,1158,1315,1432,1293,1226,1390,1278,1232,1159,1099,1216,1373,1120,1247,831,987,842,815,993,922,1089,1001,991,1390,1283,1123,1389,830,926,1107,615,1325,1563,1310,832,1164,1307,1130,1347,1158,893,1041,1192,1261,1187,1148,1147,993,1212,1008,1031,1148,1022,1430,1455,1333,1041,1488,1541,1557,1373,1443,1506,1591,1358,1047,499,1209,1300,1205,1045,1043,1059,1405,1018,831,959,923,1247,1190,1321,1243,1383,1058,981,1006,908,1153,1329,1130,977,1051,1032,1131,1201,1243,1008,1083,1181,1253,1059,1094,1066,1112,1166,995,1018,1053,1105,1380,1417,1388,1625,1173,872,1322,1256,1417,1271,1414,1436,1421,1325,1398,1292,1186,1351,1293,1281,1197,1409,1432,1343,1337,1135,1272,1358,1509,1141,1167,1387,1456,1338,1257,1331,1138,1506,1468,1512,1159,954,1079,843,180,25,1081,1269,1420,1165,1176,1041,1039,1033,1036,1037,1035,1017,1035,1131,932,1233,802,970,930,697,884,921,584,721,977,1127,1108,1252,1188,1152,1232,1360,945,1165,1071,1338,1075,1147,1033,1150,1185,1243,1249,1259,1187,1156,1105,1038,1291,1044,1167,1325,1219,902,1285,936,1320,1258,1189,1003,1089,1024,1138,1404,1065,1023,1307,1155,1253,1346,1322,1283,1355,1110,835,1077,1025,1010,1013,1219,1053,893,1265,1451,1298,1142,1301,1248,1136,1424,1433,1132,743,764,746,649,671,888,1487,1612,1406,1139,1178,1462,1370,641,534,486,1495,1319,1395,1541,1511,1280,1279,1310,1064,1326,1274,1487,941,1456,1443,908,1346,1517,1420,1432,1199,1550,1465,1478,1228,1512,1452,1410,1447,1377,1514,1577,1446,1587,1386,1344,1437,1319,1352,1384,1042,1342,1550,1328,1348,1464,1300,1445,1412,1504,1438,1508,1410,1452,1489,1496,1459,1409,1390,1010,1559,1601,1429,1291,1467,1270,1522,1376,1475,1434,1296,1533,1406,1454,1498,1460,1601,1332,719,952,1475,854,1088,713,910,978,1066,1052,1028,1025,990,349,336,586,25,25,25,518,1294,1205,1378,1006,1198,1255,1431,1309,1038,1460,1472,1479,1449,1530,1394,1357,1220,1108,1272,1298,1318,1107,1040,1036,1049,1045,1045,1087,1081,1375,1099,1069,1050,1074,1106,925,917,684,984,693,905,525,501,575,736,741,1156,1070,806,1056,757,1172,952,1199,1023,838,835,1055,968,1054,1041,852,965,991,1016,1041,1057,921,714,853,1192,975,1139,852,1124,825,919,1014,830,1083,1062,1206,873,1067,734,724,797,1117,874,997,1154,954,1101,893,783,1364,1384,1314,1041,1237,1505,1377,1449,793,689,1204,1491,1581,1497,1461,1405,1443,1435,1396,1046,1318,1452,1439,1316,1377,1469,1316,1440,1342,1529,1366,1241,1361,1406,1173,1405,1464,1309,1208,1255,1370,1549,1488,1483,938,1207,1417,1233,1471,1368,1421,1396,1484,1193,1374,1514,1363,1346,1261,1422,1438,1470,1441,1259,1321,1194,1365,1456,1430,1531,1480,1526,1429,1508,1487,1250,1169,1276,1324,1368,1404,1469,1440,1296,1468,1299,1483,1458,1402,1463,1289,1443,1351,1472,1460,1457,1478,1451,1215,1210,1225,1235,1316,1338,1358,1432,1075,1209,1327,1449,1446,1410,1301,1521,1633,1343,1487,1362,1075,949,1067,1046,1072,1068,1024,400,1159,1232,1175,1136,1312,496,25,25,25,953,1257,1410,1140,1038,1053,1063,992,1367,972,917,1075,719,940,1397,1068,1067,1067,1148,1203,1112,1291,1251,1163,1097,980,1192,1174,1458,1590,1218,1063,1226,1514,1372,1169,716,1267,1480,1379,1380,1573,1422,1354,1382,1519,1463,1410,1551,1423,1520,1532,1470,1439,1399,1325,1509,1375,1223,1401,1490,1199,687,1362,1325,1290,1230,1054,1025,1541,875,733,1473,1092,1102,1200,1068,1450,1246,1378,1359,1086,1041,634,1044,1045,667,1328,150,500,1302,1297,1292,1083,1044,1043,1037,1040,1059,1231,635,744,1054,764,1139,1131,1227,961,1043,1112,1031,996,1211,1372,1201,1199,1172,1316,1113,1115,1219,1159,893,910,1144,1289,1312,793,991,986,991,980,962,1206,1617,1618,1272,955,1383,1427,1455,754,1376,1424,1343,1399,1485,1370,1450,1052,1384,1493,1288,1353,1561,1274,1420,1400,1380,1386,1372,1438,1437,1459,1474,1489,1375,1280,1294,1298,1289,1426,1468,1367,1390,1510,1604,1434,1267,1437,1498,1445,1474,1410,1421,1454,1416,1757,1345,1439,1327,1195,1059,1073,1067,1073,831,906,25,25,1179,1336,1125,1139,1405,1226,812,1200,1230,1174,1061,1342,880,956,1091,1218,1495,1524,1396,1039,1572,1339,1548,1508,1456,1539,1436,1319,1020,649,1274,1168,1497,1195,1032,1040,1051,1054,1060,1179,1161,672,659,609,896,1128,943,971,926,662,952,758,1064,1158,1085,1066,1011,976,985,785,965,1128,1076,1168,1071,1146,1148,1112,1105,1102,1100,1106,1084,806,1103,1130,1092,1143,1143,997,1108,1233,1218,1072,1143,1166,999,916,939,901,898,1227,1284,1202,1584,1324,983,1320,1466,1285,1362,715,958,1391,1342,1247,1396,1329,1371,1480,1310,1501,1003,1230,1426,1234,1406,1301,1082,1200,1239,1525,1405,1340,1359,1371,1332,1311,1399,1332,1310,1329,1352,1370,1347,1333,1143,1382,1485,1287,1387,1175,1518,1235,1391,1472,1147,1320,1497,1354,1525,1433,1480,1499,1405,1226,966,1178,930,1220,1392,1414,1491,1146,1183,1350,1306,1096,874,681,1044,1004,1015,1061,902,759,25,25,25,734,1330,1329,1113,1038,1044,1227,1130,1060,1031,849,893,1036,1254,1176,1253,1161,1133,1007,1023,1132,1066,1249,1078,1223,1442,1624,1276,1160,1215,1448,1442,1363,697,1308,1546,1542,1440,1473,1453,1537,1432,1494,1333,1509,1456,1483,1479,1390,1303,1188,1170,1313,1499,1301,1495,1498,1416,1365,1071,1098,980,836,572,662,1352,1294,1169,1024,1051,1041,1049,1295,834,999,777,1020,739,539,889,1182,1223,1031,1178,907,840,1067,1039,1091,1064,1010,1150,1171,1115,1106,1042,1094,1151,1033,1238,1106,1074,1094,902,1052,1016,1090,1060,1085,1129,1128,1138,1028,1082,1142,1109,1198,1088,1205,1150,1102,1134,1129,1358,1596,1394,1171,1226,1469,1447,1394,1333,1513,1504,1359,1499,1376,1268,1353,1370,1227,1203,1242,1394,1423,1509,1215,1229,1320,1190,1104,1306,1504,1180,1221,1284,1381,1372,1363,1393,1371,1318,1302,1137,1173,1329,1557,1309,1418,1032,1044,1016,996,1197,987,25,25,895,1221,1280,1099,1367,1104,994,1099,1243,982,1238,1247,1173,1142,1289,1621,1393,1095,1415,1490,1300,1365,1471,1404,1436,1378,1361,1354,1372,1422,1345,1296,1384,1378,1231,1390,1236,1350,1426,1248,1239,1006,1236,1470,1382,1354,1057,905,434,1268,1313,1105,1041,1047,1203,1306,894,1091,631,888,1238,1177,1282,1165,1081,1138,1224,1540,1582,1270,1027,1261,1589,1312,1298,1498,1240,1365,1216,1330,1014,1213,1289,1292,1486,1543,1509,1550,1418,1360,1327,1432,1408,1447,1358,1579,1348,1156,1123,1331,1275,1445,1276,1526,1598,1463,1537,1237,1284,1178,1053,1056,660,94,1278,1324,1145,1414,1490,1317,1092,1215,1532,1403,1400,1354,1425,1256,1445,1518,1353,1073,734,1271,1190,1383,1088,1045,1051,1045,1326,1006,943,1135,712,910,1215,1187,1096,917,1148,1138,1143,1386,1187,1183,1186,1218,1253,1060,1245,1278,1408,1630,1257,962,1391,1523,1400,840,1412,1519,1325,1333,1550,1365,1416,1546,1549,1474,1433,1369,1256,1380,1416,1392,1399,1222,1481,1499,1413,1485,1527,1440,1396,1381,1413,1284,1533,1336,1448,1382,1359,1292,1602,1391,1411,1158,1376,1175,907,1101,1030,794,27,961,1348,1387,1263,1133,1042,1035,1042,1044,1048,1045,1040,1151,1217,855,1019,966,749,865,894,1057,854,698,792,875,1169,894,1139,1089,1185,1112,1086,1076,1184,1222,1151,1110,1130,1116,1346,1025,1058,1174,1097,1163,1171,1132,1028,1340,1066,1159,1194,1092,1245,1213,994,1247,1082,1219,1180,1219,1565,1468,1304,1018,1239,1512,1386,1199,625,640,1457,1372,1364,1564,1458,1343,1604,1581,1260,1374,1347,1469,1517,1469,1332,1487,1535,1469,1467,1386,1410,1500,1557,1519,1455,1550,1560,1509,1195,1199,1451,1542,1491,1439,1455,1593,1464,1482,1402,1302,1538,1424,1396,1464,1277,1327,1448,1418,1508,1535,1496,1293,1422,1437,1546,1435,1319,1406,1243,1350,1440,1464,1468,1452,1579,1454,1568,1323,1330,1474,1303,1179,950,1032,1027,1115,1084,1048,1037,434,1169,1289,577,25,25,1218,1219,1321,1052,1035,1146,1189,870,1140,694,1055,1224,1290,1191,1018,1325,1202,1183,1155,1106,1220,1351,1587,1339,962,1343,1491,1335,1382,678,1478,1519,1354,1444,1429,1471,1535,1247,1493,1440,1367,1573,1430,1191,1292,1507,1546,1294,1466,1352,1148,1224,1018,1035,666,95,1286,1336,1174,1043,1014,1021,1021,1057,1035,1030,1166,1230,1375,652,752,903,1107,1283,1325,1227,1107,1314,1137,1076,1126,1394,1084,1049,1238,1058,1372,1055,1027,1058,1044,1234,1323,1341,1212,1335,1335,1304,1293,1360,1271,1349,1046,1091,1226,1074,1277,1287,1279,1053,1027,1058,1259,1281,1137,1301,1024,1052,1044,1034,1128,1036,1070,1037,1039,1057,1049,1090,1063,1499,1433,1123,1148,1455,1480,1444,1039,1574,1470,1533,1513,1302,965,963,943,948,1286,1004,987,995,1380,1420,1505,1303,990,1142,1031,998,1203,809,1045,1011,1054,1146,903,314,25,1058,1302,1441,1238,1057,1051,1032,1036,1037,1029,1034,1074,1018,1219,919,1144,1028,935,892,1130,880,605,852,937,873,827,820,1267,1206,1315,1106,1090,1197,1295,1226,1029,1029,946,695,1114,1043,976,1116,1024,962,1270,739,1115,1134,1157,1141,1181,1167,1139,1188,1156,1127,1299,1244,1119,1313,1222,1459,1236,1451,1152,1001,1413,1422,1484,725,919,1256,548,1582,1401,1503,1462,1458,1321,1388,1436,1360,1409,924,1366,1415,1401,1171,1397,1504,1345,1426,1269,1340,1382,1003,1229,1288,1352,1448,1337,1028,1173,921,1191,1152,930,1167,963,1188,1324,1487,1324,1200,1205,1097,1050,1429,1231,1397,1394,1353,1226,1344,1427,1481,1323,1433,1522,1177,1465,1391,1443,1524,1502,1248,1394,1450,1446,1404,1141,1304,1315,1332,996,1429,1420,1312,1102,1349,1352,1290,1362,1391,1353,1492,1416,1505,1336,974,1261,1478,1047,1339,1265,1433,1475,1313,1273,1604,1401,1397,1490,1252,1413,1388,1485,1558,1214,1225,1436,1436,1291,1441,1408,1384,1416,1308,1414,1280,1363,1429,1351,1404,1280,1479,1404,1331,1449,1222,1307,1350,1227,1330,1480,1274,1510,1434,1485,1320,1239,1382,1203,1007,963,1111,1098,1030,1018,929,721,961,1165,1293,515,25,25,25,1054,1329,1131,1119,1404,1146,841,859,1156,1217,1232,957,920,942,716,839,798,1047,1023,1519,1570,1087,1314,1180,1336,1532,1408,1569,1339,1295,1426,1462,1241,998,571,1282,1225,1495,1195,1042,1036,1040,1046,1050,1044,1037,1079,1024,1233,761,1245,926,894,960,1060,895,769,510,764,778,742,796,800,749,565,969,641,1229,1093,1204,1123,1168,1385,1128,1110,1176,1180,1089,1231,1199,1275,1361,1167,1222,1244,1264,1219,1097,1303,1334,1065,1278,1200,1230,1061,1152,1156,1098,1242,1364,1338,1573,1482,1209,1169,969,1377,1513,1408,720,674,1190,1462,1563,1278,1306,1369,1262,1292,1319,1367,980,1314,1297,1377,1266,1210,1137,1192,1275,1167,1424,1371,1069,1040,1373,1321,1253,1073,1074,1369,1172,1303,1528,1375,1550,1385,1278,1297,1374,1120,1332,1327,1338,1277,1468,1206,1272,1355,1329,1272,1333,1378,1443,1584,1310,1399,1421,1508,1450,1433,1305,1423,1447,1480,1509,1329,1540,1300,1332,1441,1354,1506,1256,1451,1428,1470,1345,1398,1272,1509,1485,1554,1541,1448,1411,1492,1481,1272,1138,1336,1414,1385,1126,1203,1400,1440,1504,1488,1290,1274,1456,1161,1280,1372,1388,1417,1332,1472,1300,1332,1442,1424,1312,1498,1236,1281,1377,1492,1291,1248,1322,1189,1282,1440,1361,1353,1242,1322,1250,1468,1461,1117,1075,1022,1046,1059,1031,1021,978,560,1238,598,25,25,211,1278,1197,1445,1158,1039,1046,1046,1041,1045,1048,1013,1238,1096,1075,918,918,1041,1082,643,739,562,572,658,731,799,658,947,1240,1249,1123,1188,1136,943,991,867,1052,975,970,1077,1065,1010,1105,870,901,1216,840,1135,926,817,953,869,870,931,922,1006,1134,990,1238,1586,1534,1171,962,1382,1408,1469,762,1484,1570,1327,1298,1588,1489,1367,1344,1474,1114,1388,1405,1555,1244,1331,1314,1370,1347,1265,1453,1301,1401,1483,1428,1202,1540,1428,1304,1334,1475,1334,1158,1384,1307,1350,1443,1404,1311,1303,1342,1291,1272,1434,1330,1354,1417,1231,1425,1317,1483,1176,1324,1327,1455,1428,1497,1520,1442,1413,1435,1375,1436,1388,1330,1505,1410,1534,1446,1423,1212,1291,1256,1524,1433,1329,1253,1238,1275,1248,1322,1317,1403,1292,1107,1401,1281,1248,1382,1243,797,1059,1120,1064,1040,1088,817,1311,802,25,25,856,1347,1361,1202,1032,1034,1042,1040,1042,1123,1353,898,786,689,1180,797,737,1041,1096,1292,1099,950,1240,906,1093,824,1152,928,1162,1112,1139,1266,1005,1234,1268,999,1268,1168,1261,1026,1365,1148,1227,1303,1126,1385,1028,1278,1198,1430,1531,1446,1186,1022,1425,1529,1387,636,1222,1312,1349,1557,1512,1305,1450,1511,1520,1334,1343,1156,1122,1523,1397,1204,1454,975,1316,1469,1527,1472,1420,1425,1568,1442,1375,1530,1458,1501,1343,1493,1042,1494,1537,1245,1417,1387,1320,1213,1413,1334,1520,1247,1269,1223,1209,793,1046,1078,1072,674,900,25,366,1225,1262,1239,1395,946,1273,1286,1095,1310,1517,1308,1159,1232,1299,1467,1463,1252,1502,1395,1163,744,1282,1224,1062,1102,1173,1066,1096,1155,1180,1158,1175,991,1051,1120,1004,1112,1152,1132,1286,1155,1049,1189,1078,1110,1228,1184,1192,1199,1141,1085,1080,1101,1063,1039,1122,969,1126,1086,1019,1058,1008,1128,1094,1081,975,958,1169,996,912,1146,1029,922,971,873,1058,1004,1002,1095,1224,893,480],successes:[1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1]};compressedData["data"]=byteArray;assert(typeof Module.LZ4==="object","LZ4 not present - was your app build with  -s LZ4=1  ?");Module.LZ4.loadPackage({metadata:metadata,compressedData:compressedData},true);Module["removeRunDependency"]("datafile_pydantic.data")}Module["addRunDependency"]("datafile_pydantic.data");if(!Module.preloadResults)Module.preloadResults={};Module.preloadResults[PACKAGE_NAME]={fromCache:false};if(fetched){processPackageData(fetched);fetched=null}else{fetchedCallback=processPackageData}}if(Module["calledRun"]){runWithFS()}else{if(!Module["preRun"])Module["preRun"]=[];Module["preRun"].push(runWithFS)}};loadPackage({files:[{filename:"/lib/python3.9/site-packages/pydantic/__init__.py",start:0,end:2619,audio:0},{filename:"/lib/python3.9/site-packages/pydantic/_hypothesis_plugin.py",start:2619,end:16378,audio:0},{filename:"/lib/python3.9/site-packages/pydantic/annotated_types.py",start:16378,end:18777,audio:0},{filename:"/lib/python3.9/site-packages/pydantic/class_validators.py",start:18777,end:32292,audio:0},{filename:"/lib/python3.9/site-packages/pydantic/color.py",start:32292,end:48899,audio:0},{filename:"/lib/python3.9/site-packages/pydantic/config.py",start:48899,end:53073,audio:0},{filename:"/lib/python3.9/site-packages/pydantic/dataclasses.py",start:53073,end:62568,audio:0},{filename:"/lib/python3.9/site-packages/pydantic/datetime_parse.py",start:62568,end:70282,audio:0},{filename:"/lib/python3.9/site-packages/pydantic/decorator.py",start:70282,end:80322,audio:0},{filename:"/lib/python3.9/site-packages/pydantic/env_settings.py",start:80322,end:92545,audio:0},{filename:"/lib/python3.9/site-packages/pydantic/error_wrappers.py",start:92545,end:97687,audio:0},{filename:"/lib/python3.9/site-packages/pydantic/errors.py",start:97687,end:115234,audio:0},{filename:"/lib/python3.9/site-packages/pydantic/fields.py",start:115234,end:163822,audio:0},{filename:"/lib/python3.9/site-packages/pydantic/generics.py",start:163822,end:179733,audio:0},{filename:"/lib/python3.9/site-packages/pydantic/json.py",start:179733,end:183151,audio:0},{filename:"/lib/python3.9/site-packages/pydantic/main.py",start:183151,end:224614,audio:0},{filename:"/lib/python3.9/site-packages/pydantic/mypy.py",start:224614,end:254340,audio:0},{filename:"/lib/python3.9/site-packages/pydantic/networks.py",start:254340,end:271138,audio:0},{filename:"/lib/python3.9/site-packages/pydantic/parse.py",start:271138,end:272948,audio:0},{filename:"/lib/python3.9/site-packages/pydantic/schema.py",start:272948,end:319298,audio:0},{filename:"/lib/python3.9/site-packages/pydantic/tools.py",start:319298,end:322132,audio:0},{filename:"/lib/python3.9/site-packages/pydantic/types.py",start:322132,end:354801,audio:0},{filename:"/lib/python3.9/site-packages/pydantic/typing.py",start:354801,end:371409,audio:0},{filename:"/lib/python3.9/site-packages/pydantic/utils.py",start:371409,end:395740,audio:0},{filename:"/lib/python3.9/site-packages/pydantic/validators.py",start:395740,end:415763,audio:0},{filename:"/lib/python3.9/site-packages/pydantic/version.py",start:415763,end:416611,audio:0},{filename:"/lib/python3.9/site-packages/pydantic/py.typed",start:416611,end:416611,audio:0},{filename:"/lib/python3.9/site-packages/pydantic/__init__.so",start:416611,end:440511,audio:0},{filename:"/lib/python3.9/site-packages/pydantic/tools.so",start:440511,end:506006,audio:0},{filename:"/lib/python3.9/site-packages/pydantic/_hypothesis_plugin.so",start:506006,end:686421,audio:0},{filename:"/lib/python3.9/site-packages/pydantic/types.so",start:686421,end:1107271,audio:0},{filename:"/lib/python3.9/site-packages/pydantic/annotated_types.so",start:1107271,end:1144185,audio:0},{filename:"/lib/python3.9/site-packages/pydantic/schema.so",start:1144185,end:1579575,audio:0},{filename:"/lib/python3.9/site-packages/pydantic/class_validators.so",start:1579575,end:1762669,audio:0},{filename:"/lib/python3.9/site-packages/pydantic/color.so",start:1762669,end:1988797,audio:0},{filename:"/lib/python3.9/site-packages/pydantic/config.so",start:1988797,end:2049984,audio:0},{filename:"/lib/python3.9/site-packages/pydantic/validators.so",start:2049984,end:2356151,audio:0},{filename:"/lib/python3.9/site-packages/pydantic/dataclasses.so",start:2356151,end:2487379,audio:0},{filename:"/lib/python3.9/site-packages/pydantic/typing.so",start:2487379,end:2718397,audio:0},{filename:"/lib/python3.9/site-packages/pydantic/datetime_parse.so",start:2718397,end:2817511,audio:0},{filename:"/lib/python3.9/site-packages/pydantic/decorator.so",start:2817511,end:2951079,audio:0},{filename:"/lib/python3.9/site-packages/pydantic/version.so",start:2951079,end:2990039,audio:0},{filename:"/lib/python3.9/site-packages/pydantic/env_settings.so",start:2990039,end:3158616,audio:0},{filename:"/lib/python3.9/site-packages/pydantic/utils.so",start:3158616,end:3477593,audio:0},{filename:"/lib/python3.9/site-packages/pydantic/error_wrappers.so",start:3477593,end:3592198,audio:0},{filename:"/lib/python3.9/site-packages/pydantic/errors.so",start:3592198,end:3819917,audio:0},{filename:"/lib/python3.9/site-packages/pydantic/fields.so",start:3819917,end:4288912,audio:0},{filename:"/lib/python3.9/site-packages/pydantic/json.so",start:4288912,end:4360143,audio:0},{filename:"/lib/python3.9/site-packages/pydantic/main.so",start:4360143,end:4812558,audio:0},{filename:"/lib/python3.9/site-packages/pydantic/mypy.so",start:4812558,end:5153514,audio:0},{filename:"/lib/python3.9/site-packages/pydantic/networks.so",start:5153514,end:5383751,audio:0},{filename:"/lib/python3.9/site-packages/pydantic/parse.so",start:5383751,end:5426215,audio:0},{filename:"/lib/python3.9/site-packages/pydantic-1.9.0-py3.9.egg-info/PKG-INFO",start:5426215,end:5547760,audio:0},{filename:"/lib/python3.9/site-packages/pydantic-1.9.0-py3.9.egg-info/SOURCES.txt",start:5547760,end:5551007,audio:0},{filename:"/lib/python3.9/site-packages/pydantic-1.9.0-py3.9.egg-info/dependency_links.txt",start:5551007,end:5551008,audio:0},{filename:"/lib/python3.9/site-packages/pydantic-1.9.0-py3.9.egg-info/entry_points.txt",start:5551008,end:5551054,audio:0},{filename:"/lib/python3.9/site-packages/pydantic-1.9.0-py3.9.egg-info/not-zip-safe",start:5551054,end:5551055,audio:0},{filename:"/lib/python3.9/site-packages/pydantic-1.9.0-py3.9.egg-info/requires.txt",start:5551055,end:5551190,audio:0},{filename:"/lib/python3.9/site-packages/pydantic-1.9.0-py3.9.egg-info/top_level.txt",start:5551190,end:5551199,audio:0}],remote_package_size:3245227,package_uuid:"63d9460d-8856-4f1f-bd9e-ab04ab35daa9"})})();
\ No newline at end of file
diff --git a/spaces/pytorch/open-unmix/README.md b/spaces/pytorch/open-unmix/README.md
deleted file mode 100644
index 8874d739fc11fc73747c3acfe6bc9c8945d41b2d..0000000000000000000000000000000000000000
--- a/spaces/pytorch/open-unmix/README.md
+++ /dev/null
@@ -1,33 +0,0 @@
----
-title: Open Unmix
-emoji: ⚡
-colorFrom: purple
-colorTo: pink
-sdk: gradio
-app_file: app.py
-pinned: false
----
-
-# Configuration
-
-`title`: _string_  
-Display title for the Space
-
-`emoji`: _string_  
-Space emoji (emoji-only character allowed)
-
-`colorFrom`: _string_  
-Color for Thumbnail gradient (red, yellow, green, blue, indigo, purple, pink, gray)
-
-`colorTo`: _string_  
-Color for Thumbnail gradient (red, yellow, green, blue, indigo, purple, pink, gray)
-
-`sdk`: _string_  
-Can be either `gradio` or `streamlit`
-
-`app_file`: _string_  
-Path to your main application file (which contains either `gradio` or `streamlit` Python code).  
-Path is relative to the root of the repository.
-
-`pinned`: _boolean_  
-Whether the Space stays on top of your list.
diff --git a/spaces/quidiaMuxgu/Expedit-SAM/AutoMacro VBA Code Generator Developer Edition TOP.md b/spaces/quidiaMuxgu/Expedit-SAM/AutoMacro VBA Code Generator Developer Edition TOP.md
deleted file mode 100644
index 342591fc9834d57607ad4eb58c0189d20383488d..0000000000000000000000000000000000000000
--- a/spaces/quidiaMuxgu/Expedit-SAM/AutoMacro VBA Code Generator Developer Edition TOP.md	
+++ /dev/null
@@ -1,6 +0,0 @@
-<h2>AutoMacro VBA Code Generator Developer Edition</h2><br /><p><b><b>Download</b> &mdash;&mdash;&mdash; <a href="https://geags.com/2uCq1c">https://geags.com/2uCq1c</a></b></p><br /><br />
-<br />
-J.A. Gomez is a Microsoft Excel trainer, researcher and developer. ... VBA Code Generator and Coding Tools ... Describe the main reasons that explain why I find AutoMacro useful and believe most macro/VBA users have the potential to ... 4d29de3e1b<br />
-<br />
-<br />
-<p></p>
diff --git a/spaces/quidiaMuxgu/Expedit-SAM/Ejercicios Econometria Resueltos Gujarati.md b/spaces/quidiaMuxgu/Expedit-SAM/Ejercicios Econometria Resueltos Gujarati.md
deleted file mode 100644
index e6ce93aaf86fb2968fe889a804f1ec8dfded890b..0000000000000000000000000000000000000000
--- a/spaces/quidiaMuxgu/Expedit-SAM/Ejercicios Econometria Resueltos Gujarati.md	
+++ /dev/null
@@ -1,6 +0,0 @@
-<h2>ejercicios econometria resueltos gujarati</h2><br /><p><b><b>DOWNLOAD</b> &#10031; <a href="https://geags.com/2uCrsQ">https://geags.com/2uCrsQ</a></b></p><br /><br />
-<br />
-ejercicios de econometria resueltos gujarati, ejercicios de econometria resueltos gujarati pdf, ejercicios resueltos del libro econometria de ... 4d29de3e1b<br />
-<br />
-<br />
-<p></p>
diff --git a/spaces/quidiaMuxgu/Expedit-SAM/Getflv Keygen !!HOT!!.md b/spaces/quidiaMuxgu/Expedit-SAM/Getflv Keygen !!HOT!!.md
deleted file mode 100644
index ff4abafc845df7944762181693a7f89fa70242f9..0000000000000000000000000000000000000000
--- a/spaces/quidiaMuxgu/Expedit-SAM/Getflv Keygen !!HOT!!.md	
+++ /dev/null
@@ -1,26 +0,0 @@
-
-```html
-<h1>How to Download and Install Getflv Keygen</h1>
-<p>Getflv is a powerful software that allows you to download, convert, edit and play any video from the internet. With Getflv, you can easily download videos from popular sites like YouTube, Vimeo, Dailymotion and more. You can also convert videos to various formats, such as MP4, AVI, WMV, MOV and FLV. You can also edit videos by trimming, cropping, adding watermarks and subtitles. You can also play videos with the built-in media player.</p>
-<p>However, Getflv is not a free software. You need to purchase a license key to activate the full features of the software. If you don't want to pay for the license key, you can try to use a keygen to generate a valid serial number for Getflv. A keygen is a program that can create random keys for software activation. However, using a keygen is illegal and risky. You may encounter viruses, malware or other threats when you download or run a keygen. Therefore, we do not recommend using a keygen to activate Getflv.</p>
-<h2>Getflv keygen</h2><br /><p><b><b>Download</b> &ndash;&ndash;&ndash;&ndash;&ndash;>>> <a href="https://geags.com/2uCsxp">https://geags.com/2uCsxp</a></b></p><br /><br />
-<p>If you still want to try to use a keygen for Getflv, you need to follow these steps:</p>
-<ol>
-<li>Download Getflv from the official website: <a href="https://www.getflv.net/">https://www.getflv.net/</a></li>
-<li>Install Getflv on your computer and launch it.</li>
-<li>Download a keygen for Getflv from a reliable source. You can search online for "Getflv keygen" and choose one of the results. Be careful of fake or malicious links.</li>
-<li>Run the keygen and click on "Generate" button. You will see a serial number on the screen.</li>
-<li>Copy the serial number and paste it into the registration window of Getflv. Click on "Register" button.</li>
-<li>If the registration is successful, you will see a message saying "Thank you for registering Getflv". You can now enjoy the full features of Getflv.</li>
-</ol>
-<p>Note: This article is for educational purposes only. We do not condone or encourage the use of keygens or any other illegal methods to activate software. Please support the developers by purchasing a legitimate license key for Getflv.</p>
-```
-
-```html
-<p>Getflv is not only a video downloader and converter, but also a video editor and player. You can use Getflv to edit your downloaded or converted videos with ease. You can trim or crop the video to remove unwanted parts, add watermarks or subtitles to personalize the video, adjust the brightness, contrast, saturation and volume of the video, and more. You can also merge or split videos as you like.</p>
-<p>Getflv also has a built-in media player that can play any video format. You can use Getflv to play your downloaded or converted videos without any hassle. You can also create playlists and manage your video library with Getflv. You can also capture screenshots from the video and save them as images.</p>
-<p>Getflv is a versatile and powerful software that can meet all your video needs. However, as we mentioned before, Getflv is not a free software. You need to purchase a license key to activate the full features of the software. If you use a keygen to generate a serial number for Getflv, you may face legal issues or security risks. Therefore, we advise you to buy a genuine license key from the official website of Getflv.</p>
-<p></p>
-```</p> d5da3c52bf<br />
-<br />
-<br />
\ No newline at end of file
diff --git a/spaces/rachana219/MODT2/trackers/strongsort/deep/models/resnet.py b/spaces/rachana219/MODT2/trackers/strongsort/deep/models/resnet.py
deleted file mode 100644
index 63d7f43ff43373d28c45de3930da0bdbee817b61..0000000000000000000000000000000000000000
--- a/spaces/rachana219/MODT2/trackers/strongsort/deep/models/resnet.py
+++ /dev/null
@@ -1,530 +0,0 @@
-"""
-Code source: https://github.com/pytorch/vision
-"""
-from __future__ import division, absolute_import
-import torch.utils.model_zoo as model_zoo
-from torch import nn
-
-__all__ = [
-    'resnet18', 'resnet34', 'resnet50', 'resnet101', 'resnet152',
-    'resnext50_32x4d', 'resnext101_32x8d', 'resnet50_fc512'
-]
-
-model_urls = {
-    'resnet18':
-    'https://download.pytorch.org/models/resnet18-5c106cde.pth',
-    'resnet34':
-    'https://download.pytorch.org/models/resnet34-333f7ec4.pth',
-    'resnet50':
-    'https://download.pytorch.org/models/resnet50-19c8e357.pth',
-    'resnet101':
-    'https://download.pytorch.org/models/resnet101-5d3b4d8f.pth',
-    'resnet152':
-    'https://download.pytorch.org/models/resnet152-b121ed2d.pth',
-    'resnext50_32x4d':
-    'https://download.pytorch.org/models/resnext50_32x4d-7cdf4587.pth',
-    'resnext101_32x8d':
-    'https://download.pytorch.org/models/resnext101_32x8d-8ba56ff5.pth',
-}
-
-
-def conv3x3(in_planes, out_planes, stride=1, groups=1, dilation=1):
-    """3x3 convolution with padding"""
-    return nn.Conv2d(
-        in_planes,
-        out_planes,
-        kernel_size=3,
-        stride=stride,
-        padding=dilation,
-        groups=groups,
-        bias=False,
-        dilation=dilation
-    )
-
-
-def conv1x1(in_planes, out_planes, stride=1):
-    """1x1 convolution"""
-    return nn.Conv2d(
-        in_planes, out_planes, kernel_size=1, stride=stride, bias=False
-    )
-
-
-class BasicBlock(nn.Module):
-    expansion = 1
-
-    def __init__(
-        self,
-        inplanes,
-        planes,
-        stride=1,
-        downsample=None,
-        groups=1,
-        base_width=64,
-        dilation=1,
-        norm_layer=None
-    ):
-        super(BasicBlock, self).__init__()
-        if norm_layer is None:
-            norm_layer = nn.BatchNorm2d
-        if groups != 1 or base_width != 64:
-            raise ValueError(
-                'BasicBlock only supports groups=1 and base_width=64'
-            )
-        if dilation > 1:
-            raise NotImplementedError(
-                "Dilation > 1 not supported in BasicBlock"
-            )
-        # Both self.conv1 and self.downsample layers downsample the input when stride != 1
-        self.conv1 = conv3x3(inplanes, planes, stride)
-        self.bn1 = norm_layer(planes)
-        self.relu = nn.ReLU(inplace=True)
-        self.conv2 = conv3x3(planes, planes)
-        self.bn2 = norm_layer(planes)
-        self.downsample = downsample
-        self.stride = stride
-
-    def forward(self, x):
-        identity = x
-
-        out = self.conv1(x)
-        out = self.bn1(out)
-        out = self.relu(out)
-
-        out = self.conv2(out)
-        out = self.bn2(out)
-
-        if self.downsample is not None:
-            identity = self.downsample(x)
-
-        out += identity
-        out = self.relu(out)
-
-        return out
-
-
-class Bottleneck(nn.Module):
-    expansion = 4
-
-    def __init__(
-        self,
-        inplanes,
-        planes,
-        stride=1,
-        downsample=None,
-        groups=1,
-        base_width=64,
-        dilation=1,
-        norm_layer=None
-    ):
-        super(Bottleneck, self).__init__()
-        if norm_layer is None:
-            norm_layer = nn.BatchNorm2d
-        width = int(planes * (base_width/64.)) * groups
-        # Both self.conv2 and self.downsample layers downsample the input when stride != 1
-        self.conv1 = conv1x1(inplanes, width)
-        self.bn1 = norm_layer(width)
-        self.conv2 = conv3x3(width, width, stride, groups, dilation)
-        self.bn2 = norm_layer(width)
-        self.conv3 = conv1x1(width, planes * self.expansion)
-        self.bn3 = norm_layer(planes * self.expansion)
-        self.relu = nn.ReLU(inplace=True)
-        self.downsample = downsample
-        self.stride = stride
-
-    def forward(self, x):
-        identity = x
-
-        out = self.conv1(x)
-        out = self.bn1(out)
-        out = self.relu(out)
-
-        out = self.conv2(out)
-        out = self.bn2(out)
-        out = self.relu(out)
-
-        out = self.conv3(out)
-        out = self.bn3(out)
-
-        if self.downsample is not None:
-            identity = self.downsample(x)
-
-        out += identity
-        out = self.relu(out)
-
-        return out
-
-
-class ResNet(nn.Module):
-    """Residual network.
-    
-    Reference:
-        - He et al. Deep Residual Learning for Image Recognition. CVPR 2016.
-        - Xie et al. Aggregated Residual Transformations for Deep Neural Networks. CVPR 2017.
-
-    Public keys:
-        - ``resnet18``: ResNet18.
-        - ``resnet34``: ResNet34.
-        - ``resnet50``: ResNet50.
-        - ``resnet101``: ResNet101.
-        - ``resnet152``: ResNet152.
-        - ``resnext50_32x4d``: ResNeXt50.
-        - ``resnext101_32x8d``: ResNeXt101.
-        - ``resnet50_fc512``: ResNet50 + FC.
-    """
-
-    def __init__(
-        self,
-        num_classes,
-        loss,
-        block,
-        layers,
-        zero_init_residual=False,
-        groups=1,
-        width_per_group=64,
-        replace_stride_with_dilation=None,
-        norm_layer=None,
-        last_stride=2,
-        fc_dims=None,
-        dropout_p=None,
-        **kwargs
-    ):
-        super(ResNet, self).__init__()
-        if norm_layer is None:
-            norm_layer = nn.BatchNorm2d
-        self._norm_layer = norm_layer
-        self.loss = loss
-        self.feature_dim = 512 * block.expansion
-        self.inplanes = 64
-        self.dilation = 1
-        if replace_stride_with_dilation is None:
-            # each element in the tuple indicates if we should replace
-            # the 2x2 stride with a dilated convolution instead
-            replace_stride_with_dilation = [False, False, False]
-        if len(replace_stride_with_dilation) != 3:
-            raise ValueError(
-                "replace_stride_with_dilation should be None "
-                "or a 3-element tuple, got {}".
-                format(replace_stride_with_dilation)
-            )
-        self.groups = groups
-        self.base_width = width_per_group
-        self.conv1 = nn.Conv2d(
-            3, self.inplanes, kernel_size=7, stride=2, padding=3, bias=False
-        )
-        self.bn1 = norm_layer(self.inplanes)
-        self.relu = nn.ReLU(inplace=True)
-        self.maxpool = nn.MaxPool2d(kernel_size=3, stride=2, padding=1)
-        self.layer1 = self._make_layer(block, 64, layers[0])
-        self.layer2 = self._make_layer(
-            block,
-            128,
-            layers[1],
-            stride=2,
-            dilate=replace_stride_with_dilation[0]
-        )
-        self.layer3 = self._make_layer(
-            block,
-            256,
-            layers[2],
-            stride=2,
-            dilate=replace_stride_with_dilation[1]
-        )
-        self.layer4 = self._make_layer(
-            block,
-            512,
-            layers[3],
-            stride=last_stride,
-            dilate=replace_stride_with_dilation[2]
-        )
-        self.global_avgpool = nn.AdaptiveAvgPool2d((1, 1))
-        self.fc = self._construct_fc_layer(
-            fc_dims, 512 * block.expansion, dropout_p
-        )
-        self.classifier = nn.Linear(self.feature_dim, num_classes)
-
-        self._init_params()
-
-        # Zero-initialize the last BN in each residual branch,
-        # so that the residual branch starts with zeros, and each residual block behaves like an identity.
-        # This improves the model by 0.2~0.3% according to https://arxiv.org/abs/1706.02677
-        if zero_init_residual:
-            for m in self.modules():
-                if isinstance(m, Bottleneck):
-                    nn.init.constant_(m.bn3.weight, 0)
-                elif isinstance(m, BasicBlock):
-                    nn.init.constant_(m.bn2.weight, 0)
-
-    def _make_layer(self, block, planes, blocks, stride=1, dilate=False):
-        norm_layer = self._norm_layer
-        downsample = None
-        previous_dilation = self.dilation
-        if dilate:
-            self.dilation *= stride
-            stride = 1
-        if stride != 1 or self.inplanes != planes * block.expansion:
-            downsample = nn.Sequential(
-                conv1x1(self.inplanes, planes * block.expansion, stride),
-                norm_layer(planes * block.expansion),
-            )
-
-        layers = []
-        layers.append(
-            block(
-                self.inplanes, planes, stride, downsample, self.groups,
-                self.base_width, previous_dilation, norm_layer
-            )
-        )
-        self.inplanes = planes * block.expansion
-        for _ in range(1, blocks):
-            layers.append(
-                block(
-                    self.inplanes,
-                    planes,
-                    groups=self.groups,
-                    base_width=self.base_width,
-                    dilation=self.dilation,
-                    norm_layer=norm_layer
-                )
-            )
-
-        return nn.Sequential(*layers)
-
-    def _construct_fc_layer(self, fc_dims, input_dim, dropout_p=None):
-        """Constructs fully connected layer
-
-        Args:
-            fc_dims (list or tuple): dimensions of fc layers, if None, no fc layers are constructed
-            input_dim (int): input dimension
-            dropout_p (float): dropout probability, if None, dropout is unused
-        """
-        if fc_dims is None:
-            self.feature_dim = input_dim
-            return None
-
-        assert isinstance(
-            fc_dims, (list, tuple)
-        ), 'fc_dims must be either list or tuple, but got {}'.format(
-            type(fc_dims)
-        )
-
-        layers = []
-        for dim in fc_dims:
-            layers.append(nn.Linear(input_dim, dim))
-            layers.append(nn.BatchNorm1d(dim))
-            layers.append(nn.ReLU(inplace=True))
-            if dropout_p is not None:
-                layers.append(nn.Dropout(p=dropout_p))
-            input_dim = dim
-
-        self.feature_dim = fc_dims[-1]
-
-        return nn.Sequential(*layers)
-
-    def _init_params(self):
-        for m in self.modules():
-            if isinstance(m, nn.Conv2d):
-                nn.init.kaiming_normal_(
-                    m.weight, mode='fan_out', nonlinearity='relu'
-                )
-                if m.bias is not None:
-                    nn.init.constant_(m.bias, 0)
-            elif isinstance(m, nn.BatchNorm2d):
-                nn.init.constant_(m.weight, 1)
-                nn.init.constant_(m.bias, 0)
-            elif isinstance(m, nn.BatchNorm1d):
-                nn.init.constant_(m.weight, 1)
-                nn.init.constant_(m.bias, 0)
-            elif isinstance(m, nn.Linear):
-                nn.init.normal_(m.weight, 0, 0.01)
-                if m.bias is not None:
-                    nn.init.constant_(m.bias, 0)
-
-    def featuremaps(self, x):
-        x = self.conv1(x)
-        x = self.bn1(x)
-        x = self.relu(x)
-        x = self.maxpool(x)
-        x = self.layer1(x)
-        x = self.layer2(x)
-        x = self.layer3(x)
-        x = self.layer4(x)
-        return x
-
-    def forward(self, x):
-        f = self.featuremaps(x)
-        v = self.global_avgpool(f)
-        v = v.view(v.size(0), -1)
-
-        if self.fc is not None:
-            v = self.fc(v)
-
-        if not self.training:
-            return v
-
-        y = self.classifier(v)
-
-        if self.loss == 'softmax':
-            return y
-        elif self.loss == 'triplet':
-            return y, v
-        else:
-            raise KeyError("Unsupported loss: {}".format(self.loss))
-
-
-def init_pretrained_weights(model, model_url):
-    """Initializes model with pretrained weights.
-    
-    Layers that don't match with pretrained layers in name or size are kept unchanged.
-    """
-    pretrain_dict = model_zoo.load_url(model_url)
-    model_dict = model.state_dict()
-    pretrain_dict = {
-        k: v
-        for k, v in pretrain_dict.items()
-        if k in model_dict and model_dict[k].size() == v.size()
-    }
-    model_dict.update(pretrain_dict)
-    model.load_state_dict(model_dict)
-
-
-"""ResNet"""
-
-
-def resnet18(num_classes, loss='softmax', pretrained=True, **kwargs):
-    model = ResNet(
-        num_classes=num_classes,
-        loss=loss,
-        block=BasicBlock,
-        layers=[2, 2, 2, 2],
-        last_stride=2,
-        fc_dims=None,
-        dropout_p=None,
-        **kwargs
-    )
-    if pretrained:
-        init_pretrained_weights(model, model_urls['resnet18'])
-    return model
-
-
-def resnet34(num_classes, loss='softmax', pretrained=True, **kwargs):
-    model = ResNet(
-        num_classes=num_classes,
-        loss=loss,
-        block=BasicBlock,
-        layers=[3, 4, 6, 3],
-        last_stride=2,
-        fc_dims=None,
-        dropout_p=None,
-        **kwargs
-    )
-    if pretrained:
-        init_pretrained_weights(model, model_urls['resnet34'])
-    return model
-
-
-def resnet50(num_classes, loss='softmax', pretrained=True, **kwargs):
-    model = ResNet(
-        num_classes=num_classes,
-        loss=loss,
-        block=Bottleneck,
-        layers=[3, 4, 6, 3],
-        last_stride=2,
-        fc_dims=None,
-        dropout_p=None,
-        **kwargs
-    )
-    if pretrained:
-        init_pretrained_weights(model, model_urls['resnet50'])
-    return model
-
-
-def resnet101(num_classes, loss='softmax', pretrained=True, **kwargs):
-    model = ResNet(
-        num_classes=num_classes,
-        loss=loss,
-        block=Bottleneck,
-        layers=[3, 4, 23, 3],
-        last_stride=2,
-        fc_dims=None,
-        dropout_p=None,
-        **kwargs
-    )
-    if pretrained:
-        init_pretrained_weights(model, model_urls['resnet101'])
-    return model
-
-
-def resnet152(num_classes, loss='softmax', pretrained=True, **kwargs):
-    model = ResNet(
-        num_classes=num_classes,
-        loss=loss,
-        block=Bottleneck,
-        layers=[3, 8, 36, 3],
-        last_stride=2,
-        fc_dims=None,
-        dropout_p=None,
-        **kwargs
-    )
-    if pretrained:
-        init_pretrained_weights(model, model_urls['resnet152'])
-    return model
-
-
-"""ResNeXt"""
-
-
-def resnext50_32x4d(num_classes, loss='softmax', pretrained=True, **kwargs):
-    model = ResNet(
-        num_classes=num_classes,
-        loss=loss,
-        block=Bottleneck,
-        layers=[3, 4, 6, 3],
-        last_stride=2,
-        fc_dims=None,
-        dropout_p=None,
-        groups=32,
-        width_per_group=4,
-        **kwargs
-    )
-    if pretrained:
-        init_pretrained_weights(model, model_urls['resnext50_32x4d'])
-    return model
-
-
-def resnext101_32x8d(num_classes, loss='softmax', pretrained=True, **kwargs):
-    model = ResNet(
-        num_classes=num_classes,
-        loss=loss,
-        block=Bottleneck,
-        layers=[3, 4, 23, 3],
-        last_stride=2,
-        fc_dims=None,
-        dropout_p=None,
-        groups=32,
-        width_per_group=8,
-        **kwargs
-    )
-    if pretrained:
-        init_pretrained_weights(model, model_urls['resnext101_32x8d'])
-    return model
-
-
-"""
-ResNet + FC
-"""
-
-
-def resnet50_fc512(num_classes, loss='softmax', pretrained=True, **kwargs):
-    model = ResNet(
-        num_classes=num_classes,
-        loss=loss,
-        block=Bottleneck,
-        layers=[3, 4, 6, 3],
-        last_stride=1,
-        fc_dims=[512],
-        dropout_p=None,
-        **kwargs
-    )
-    if pretrained:
-        init_pretrained_weights(model, model_urls['resnet50'])
-    return model
diff --git a/spaces/radames/SPIGA-face-alignment-headpose-estimator/SPIGA/spiga/models/gnn/step_regressor.py b/spaces/radames/SPIGA-face-alignment-headpose-estimator/SPIGA/spiga/models/gnn/step_regressor.py
deleted file mode 100644
index c6396590490546e882eab987d40b1ba9078922c5..0000000000000000000000000000000000000000
--- a/spaces/radames/SPIGA-face-alignment-headpose-estimator/SPIGA/spiga/models/gnn/step_regressor.py
+++ /dev/null
@@ -1,43 +0,0 @@
-import torch.nn as nn
-
-from spiga.models.gnn.layers import MLP
-from spiga.models.gnn.gat import GAT
-
-
-class StepRegressor(nn.Module):
-
-    def __init__(self, input_dim: int, feature_dim: int, nstack=4, decoding=[256, 128, 64, 32]):
-        super(StepRegressor, self).__init__()
-        assert nstack > 0
-        self.nstack = nstack
-        self.gat = nn.ModuleList([GAT(input_dim, feature_dim, 4)])
-        for _ in range(nstack-1):
-            self.gat.append(GAT(feature_dim, feature_dim, 4))
-        self.decoder = OffsetDecoder(feature_dim, decoding)
-
-    def forward(self, embedded, prob_list=[]):
-        embedded = embedded.transpose(-1, -2)
-        for i in range(self.nstack):
-            embedded, prob = self.gat[i](embedded)
-            prob_list.append(prob)
-        offset = self.decoder(embedded)
-        return offset.transpose(-1, -2), prob_list
-
-
-class OffsetDecoder(nn.Module):
-    def __init__(self, feature_dim, layers):
-        super().__init__()
-        self.decoder = MLP([feature_dim] + layers + [2])
-
-    def forward(self, embedded):
-        return self.decoder(embedded)
-
-
-class RelativePositionEncoder(nn.Module):
-    def __init__(self, input_dim, feature_dim, layers):
-        super().__init__()
-        self.encoder = MLP([input_dim] + layers + [feature_dim])
-
-    def forward(self, feature):
-        feature = feature.transpose(-1, -2)
-        return self.encoder(feature).transpose(-1, -2)
diff --git a/spaces/raedeXanto/academic-chatgpt-beta/ASC Timetable 2016 Registration Code Keygen Crack Download and Install Guide.md b/spaces/raedeXanto/academic-chatgpt-beta/ASC Timetable 2016 Registration Code Keygen Crack Download and Install Guide.md
deleted file mode 100644
index a52eae614fb9b3635437983af46de38d07d90faa..0000000000000000000000000000000000000000
--- a/spaces/raedeXanto/academic-chatgpt-beta/ASC Timetable 2016 Registration Code Keygen Crack Download and Install Guide.md	
+++ /dev/null
@@ -1,98 +0,0 @@
-
-<h1>How to Crack ASC Timetable 2016 Registration Code</h1>
-<p>If you are looking for a way to crack ASC Timetable 2016 registration code, you have come to the right place. In this article, we will show you two methods to crack ASC Timetable 2016 registration code using a keygen program or a patch file. But before we get into that, let's first understand what ASC Timetable 2016 is, why you need a registration code, and what are the risks of using a cracked registration code.</p>
-<h2>Introduction</h2>
-<h3>What is ASC Timetable 2016?</h3>
-<p>ASC Timetable 2016 is a software that helps you create and manage school timetables. It allows you to enter various data such as teachers, classes, subjects, rooms, and lessons. It then automatically generates a timetable that meets your requirements and preferences. You can also edit, print, export, or share your timetable with others.</p>
-<h2>asc timetable 2016 registration code keygen crack</h2><br /><p><b><b>Download</b> &rArr;&rArr;&rArr; <a href="https://tinourl.com/2uL1f1">https://tinourl.com/2uL1f1</a></b></p><br /><br />
-<h3>Why do you need a registration code?</h3>
-<p>ASC Timetable 2016 is not a free software. You need to purchase a license to use it without any limitations. A license costs $149 for one year or $299 for unlimited use. When you buy a license, you will receive a registration code that you need to enter in the software to activate it. Without a registration code, you can only use ASC Timetable 2016 as a trial version for 30 days.</p>
-<h3>What are the risks of using a cracked registration code?</h3>
-<p>Some people may try to crack ASC Timetable 2016 registration code using illegal methods such as keygen programs or patch files. These methods may seem tempting because they allow you to use ASC Timetable 2016 for free without paying for a license. However, they also come with many risks such as:</p>
-<ul>
-<li>Virus or malware infection: Keygen programs or patch files may contain malicious codes that can harm your computer or steal your personal information.</li>
-<li>Software malfunction: Cracked registration codes may not work properly or cause errors in the software.</li>
-<li>Legal consequences: Cracking ASC Timetable 2016 registration code is against the law and may result in fines or lawsuits.</li>
-</ul>
-<p>Therefore, we do not recommend using cracked registration codes for ASC Timetable 2016. Instead, we suggest you buy a legitimate license from the official website of ASC Timetable 2016.</p>
-<p>asc timetable 2016 activation key generator<br />
-asc timetable 2016 license code serial number<br />
-asc timetable 2016 product key patch<br />
-asc timetable 2016 full version crack download<br />
-asc timetable 2016 cracked software free<br />
-asc timetable 2016 registration code keygen online<br />
-asc timetable 2016 license key crack activation<br />
-asc timetable 2016 serial number generator download<br />
-asc timetable 2016 patch keygen crack software<br />
-asc timetable 2016 crack download full version<br />
-asc timetable 2016 keygen generator online free<br />
-asc timetable 2016 activation code serial key<br />
-asc timetable 2016 license code crack patch<br />
-asc timetable 2016 product key generator download<br />
-asc timetable 2016 cracked software download free<br />
-asc timetable 2016 registration code keygen software<br />
-asc timetable 2016 license key generator online<br />
-asc timetable 2016 serial number crack patch<br />
-asc timetable 2016 patch keygen crack download<br />
-asc timetable 2016 crack download free full version<br />
-asc timetable 2016 keygen generator download free<br />
-asc timetable 2016 activation code crack keygen<br />
-asc timetable 2016 license code generator online<br />
-asc timetable 2016 product key crack patch download<br />
-asc timetable 2016 cracked software online free<br />
-asc timetable 2016 registration code keygen download<br />
-asc timetable 2016 license key crack keygen download<br />
-asc timetable 2016 serial number generator online free<br />
-asc timetable 2016 patch keygen crack online<br />
-asc timetable 2016 crack download online free full version<br />
-asc timetable 2016 keygen generator online software<br />
-asc timetable 2016 activation code generator download free<br />
-asc timetable 2016 license code serial key generator<br />
-asc timetable 2016 product key generator online free<br />
-asc timetable 2016 cracked software download full version<br />
-asc timetable 2016 registration code keygen online free<br />
-asc timetable 2016 license key generator download free<br />
-asc timetable 2016 serial number crack keygen online<br />
-asc timetable 2016 patch keygen crack software download<br />
-asc timetable 2016 crack download full version free online<br />
-asc timetable 2016 keygen generator software download free<br />
-asc timetable 2016 activation code serial key generator online<br />
-asc timetable 2016 license code generator download free online<br />
-asc timetable 2016 product key generator software online free<br />
-asc timetable 2016 cracked software online full version free<br />
-asc timetable 2016 registration code keygen software download free<br />
-asc timetable 2016 license key generator software online free<br />
-asc timetable 2016 serial number generator software download free online <br />
-asc timetable 2016 patch keygen crack software online free <br />
-asc timetable 2016 crack download software full version free online</p>
-<h2>How to crack ASC Timetable 2016 registration code</h2>
-<p>If you still want to crack ASC Timetable 2016 registration code despite the risks, here are two methods that you can try at your own risk. We do not guarantee that these methods will work or that they are safe. Use them at your own discretion.</p>
-<h3>Method 1: Use a keygen program</h3>
-<p>A keygen program is a software that generates random registration codes for various programs. You can use a keygen program to generate a registration code for ASC Timetable 2016. Here are the steps to follow:</p>
-<h4>Step 1: Download and install a keygen program</h4>
-<p>You can search online for a keygen program that supports ASC Timetable 2016. For example, you can try this link: https://crackzsoft.me/asc-timetables-2020-crack/. Download the keygen program from the link and install it on your computer.</p>
-<h4>Step 2: Run the keygen program and generate a registration code</h4>
-<p>Run the keygen program and select ASC Timetable 2016 from the list of programs. Click on the Generate button and wait for a few seconds. The keygen program will generate a random registration code for ASC Timetable 2016.</p>
-<h4>Step 3: Enter the registration code in ASC Timetable 2016 and activate it</h4>
-<p>Open ASC Timetable 2016 and go to Help > Registration > Enter Registration Code. Enter the registration code that you generated from the keygen program and click on OK. The software will verify the registration code and activate it.</p>
-<h3>Method 2: Use a patch file</h3>
-<p>A patch file is a software that modifies or replaces some files in another software. You can use a patch file to bypass the registration process of ASC Timetable 2016. Here are the steps to follow:</p>
-<h4>Step 1: Download and install a patch file</h4>
-<p>You can search online for a patch file that supports ASC Timetable 2016. For example, you can try this link: https://www.crackzinn.com/t/s/l/asc+timetables/. Download the patch file from the link and install it on your computer.</p>
-<h4>Step 2: Run the patch file and locate the ASC Timetable 2016 installation folder</h4>
-<h4>Step 3: Apply the patch and restart ASC Timetable 2016</h4>
-<p>Click on Patch and wait for a few seconds. The patch file will modify or replace some files in the ASC Timetable 2016 installation folder. Click on Exit and restart ASC Timetable 2016. The software will skip the registration process and activate itself.</p>
-<h2>Conclusion</h2>
-<p>In this article, we have shown you two methods to crack ASC Timetable 2016 registration code using a keygen program or a patch file. These methods may allow you to use ASC Timetable 2016 for free without paying for a license. However, they also come with many risks such as virus or malware infection, software malfunction, and legal consequences. Therefore, we do not recommend using cracked registration codes for ASC Timetable 2016. Instead, we suggest you buy a legitimate license from the official website of ASC Timetable 2016.</p>
-<h2>FAQs</h2>
-<p>Here are some frequently asked questions about cracking ASC Timetable 2016 registration code.</p>
-<ol>
-<li>Q: Is cracking ASC Timetable 2016 registration code illegal?<br>A: Yes, cracking ASC Timetable 2016 registration code is illegal and may result in fines or lawsuits.</li>
-<li>Q: Is cracking ASC Timetable 2016 registration code safe?<br>A: No, cracking ASC Timetable 2016 registration code is not safe and may expose your computer to virus or malware infection, software malfunction, and other problems.</li>
-<li>Q: How can I get a legitimate license for ASC Timetable 2016?<br>A: You can get a legitimate license for ASC Timetable 2016 by visiting the official website of ASC Timetable 2016 and purchasing a license for $149 for one year or $299 for unlimited use.</li>
-<li>Q: What are the benefits of using a legitimate license for ASC Timetable 2016?<br>A: The benefits of using a legitimate license for ASC Timetable 2016 are that you can use the software without any limitations, receive updates and support, and avoid any risks or problems associated with cracked registration codes.</li>
-<li>Q: What are the alternatives to cracking ASC Timetable 2016 registration code?<br>A: The alternatives to cracking ASC Timetable 2016 registration code are to use a free trial version for 30 days, use another software that is free or cheaper, or create your own timetable manually.</li>
-</ol>
-</p> 0a6ba089eb<br />
-<br />
-<br />
\ No newline at end of file
diff --git a/spaces/raedeXanto/academic-chatgpt-beta/Agi32 Lighting Software Crack 46 Everything You Need to Create Stunning Lighting Effects.md b/spaces/raedeXanto/academic-chatgpt-beta/Agi32 Lighting Software Crack 46 Everything You Need to Create Stunning Lighting Effects.md
deleted file mode 100644
index b93e49fd4dd20bf60e6fb73db319a7c185e31444..0000000000000000000000000000000000000000
--- a/spaces/raedeXanto/academic-chatgpt-beta/Agi32 Lighting Software Crack 46 Everything You Need to Create Stunning Lighting Effects.md	
+++ /dev/null
@@ -1,181 +0,0 @@
-<br />
-<h1>How to Download and Install Catia V5R21 Crack Torrent</h1>
- <p>Catia V5R21 is one of the most popular and powerful software solutions for product design and engineering. It offers a wide range of features and capabilities that enable you to create, simulate, analyze, and optimize complex products in various industries. However, Catia V5R21 is also a very expensive software that requires a license to use. If you want to use Catia V5R21 without paying for a license, you might be interested in downloading and installing a crack torrent for it. In this article, we will show you how to do that, as well as the advantages and risks of using a crack torrent for Catia V5R21.</p>
- <h2>What is Catia V5R21?</h2>
- <p>Catia V5R21 is the latest version of Catia V5, which is a computer-aided design (CAD), computer-aided engineering (CAE), and computer-aided manufacturing (CAM) software developed by Dassault Systemes. Catia V5R21 was released in 2011 and it includes several improvements and enhancements over the previous versions.</p>
-<h2>catia v5r21 crack torrent</h2><br /><p><b><b>DOWNLOAD</b> &#127383; <a href="https://tinourl.com/2uL49a">https://tinourl.com/2uL49a</a></b></p><br /><br />
- <h3>Features and benefits of Catia V5R21</h3>
- <p>Some of the features and benefits of Catia V5R21 are:</p>
- <ul>
-<li>It supports both Windows and Linux operating systems.</li>
-<li>It has a user-friendly interface that allows you to easily access and manage various tools and functions.</li>
-<li>It has a powerful modeling engine that supports parametric, associative, generative, hybrid, and direct modeling techniques.</li>
-<li>It has a comprehensive library of standard and specialized parts, materials, fasteners, symbols, annotations, etc.</li>
-<li>It has advanced simulation capabilities that allow you to perform static, dynamic, thermal, fluid, acoustic, electromagnetic, etc. analyses on your models.</li>
-<li>It has sophisticated optimization tools that allow you to improve the performance, quality, cost, sustainability, etc. of your products.</li>
-<li>It has seamless integration with other Dassault Systemes products such as SolidWorks, Enovia, Delmia, Simulia, etc.</li>
-<li>It has a large community of users and developers that provide support, tutorials, tips, plugins, etc.</li>
-</ul>
- <h3>System requirements for Catia V5R21</h3>
- <p>The minimum system requirements for Catia V5R21 are:</p>
- <table>
-<tr><td>Operating system</td><td>Windows 7 SP1 x64 or Linux x64</td></tr>
-<tr><td>CPU</td><td>Intel Core i3 or AMD equivalent</td></tr>
-<tr><td>RAM</td><td>4 GB</td></tr>
-<tr><td>Graphics card</td><td>NVIDIA GeForce GT 630 or AMD equivalent</td></tr>
-<tr><td>Hard disk space</td><td>10 GB</td></tr>
-<tr><td>Internet connection</td><td>Required for activation and updates</td></tr>
-</table>
- <p>The recommended system requirements for Catia V5R21 are:</p>
-<p>catia v5r21 full version download with crack<br />
-how to install catia v5r21 on windows 10 with crack<br />
-catia v5r21 sp6 crack free download<br />
-catia v5r21 64 bit crack torrent download<br />
-catia v5r21 license key generator torrent<br />
-catia v5r21 software free download with crack<br />
-catia v5r21 crack only torrent link<br />
-catia v5r21 sp9 crack torrent magnet<br />
-catia v5r21 activation code crack torrent<br />
-catia v5r21 crack for windows 7 32 bit torrent<br />
-catia v5r21 sp4 crack torrent kickass<br />
-catia v5r21 crack file download torrent<br />
-catia v5r21 patch crack torrent rar<br />
-catia v5r21 serial number crack torrent<br />
-catia v5r21 portable edition with crack torrent<br />
-catia v5r21 sp2 crack torrent iso<br />
-catia v5r21 setup with crack torrent zip<br />
-catia v5r21 offline installer with crack torrent<br />
-catia v5r21 latest version with crack torrent<br />
-catia v5r21 system requirements and crack torrent<br />
-catia v5r21 tutorial pdf with crack torrent<br />
-catia v5r21 user guide with crack torrent<br />
-catia v5r21 training videos with crack torrent<br />
-catia v5r21 modules and features with crack torrent<br />
-catia v5r21 tips and tricks with crack torrent<br />
-catia v5r21 best practices with crack torrent<br />
-catia v5r21 keyboard shortcuts with crack torrent<br />
-catia v5r21 error solutions with crack torrent<br />
-catia v5r21 updates and fixes with crack torrent<br />
-catia v5r21 compatibility issues with crack torrent<br />
-catia v5r21 alternatives and competitors with crack torrent<br />
-catia v5r21 reviews and ratings with crack torrent<br />
-catia v5r21 benefits and drawbacks with crack torrent<br />
-catia v5r21 price and discount with crack torrent<br />
-catia v5r21 trial and demo with crack torrent<br />
-catia v5r21 support and help with crack torrent<br />
-catia v5r21 forum and community with crack torrent<br />
-catia v5r21 blog and news with crack torrent<br />
-catia v5r21 faq and q&a with crack torrent<br />
-catia v5r21 case studies and testimonials with crack torrent<br />
-how to uninstall catia v5r21 with crack torrent<br />
-how to upgrade to catia v6 from v5r21 with crack torrent<br />
-how to migrate data from catia v4 to v5r21 with crack torrent<br />
-how to integrate catia v5r21 with other software with crack torrent<br />
-how to customize and optimize catia v5r21 with crack torrent<br />
-how to troubleshoot and debug catia v5r21 with crack torrent<br />
-how to backup and restore catia v5r21 with crack torrent<br />
-how to export and import data in catia v5r21 with crack torrent<br />
-how to create and edit models in catia v5r21 with crack torrent<br />
-how to simulate and analyze designs in catia v5r21 with crack torrent</p>
- <table>
-<tr><td>Operating system</td><td>Windows 10 x64 or Linux x64</td></tr>
-<tr><td>CPU</td><td>Intel Core i7 or AMD equivalent</td></tr>
-<tr><td>RAM</td><td>8 GB or more</td></tr>
-<tr><td>Graphics card</td><td>NVIDIA GeForce GTX 1050 or AMD equivalent</td></tr>
-<tr><td>Hard disk space</td><td>20 GB or more</td></tr>
-<tr><td>Internet connection</td><td>Required for activation and updates</td></tr>
-</table>
- <h2>Why use a crack torrent for Catia V5R21?</h2>
- <p>A crack torrent is a file that contains both the software installation files and the crack files that bypass the software protection mechanisms. By using a crack torrent for Catia V5R21, you can install and use the software without paying for a license or registering an account. This can save you a lot of money and time.</p>
- <h3>Advantages of using a crack torrent</h3>
- <p>Some of the advantages of using a crack torrent for Catia V5R21 are:</p>
- <ul>
-<li>You can access all the features and functions of Catia V5R21 without any limitations or restrictions.</li>
-<li>You can use Catia V5R21 offline without requiring an internet connection.</li>
-<li>You can use Catia V5R21 on multiple devices without needing multiple licenses.</li>
-<li>You can update Catia V5R21 with new patches and fixes without losing the crack.</li>
-<li>You can learn and practice Catia V5R21 skills without investing in expensive courses or certifications.</li>
-<li>You can create personal or professional projects with Catia V5R21 without worrying about legal issues or penalties.</li>
-</ul>
- <h3>Risks and precautions of using a crack torrent</h3>
- <p>Some of the risks and precautions of using a crack torrent for Catia V5R21 are:</p>
- <ul>
-<li>You might download a fake or malicious crack torrent that contains viruses, malware, spyware, ransomware, etc. that can harm your device or data.</li>
-<li>You might download an outdated or incompatible crack torrent that does not work properly with your device or operating system.</li>
-<li>You might download an incomplete or corrupted crack torrent that causes errors or crashes during installation or usage.</li>
-<li>You might face legal issues or penalties if you are caught using a cracked version of Catia V5R21 by Dassault Systemes or other authorities.</li>
-<li>You might lose access to official support, updates, plugins, etc. from Dassault Systemes or other sources.</li>
-<li>You might compromise the quality, security, reliability, etc. of your projects by using a cracked version of Catia V5R21.</li>
-</ul>
- <p>To avoid these risks and precautions, you should:</p>
- <ul>
-<li>Download crack torrents only from trusted and verified sources that have positive reviews and ratings from other users.</li>
-<li>Scan the crack torrent files with an antivirus software before opening or installing them on your device.</li>
-<li>Backup your device data before installing or using the crack torrent files on your device.</li>
-<li>Use a VPN service to hide your IP address and location when downloading or using the crack torrent files on your device.</li>
-<li>Avoid sharing or distributing the crack torrent files with others online or offline.</li>
-<li>Acknowledge the ethical and legal implications of using a cracked version of Catia V5R21 and respect the intellectual property rights of Dassault Systemes.</li>
-</ul>
- <h2>How to download a crack torrent for Catia V5R21?</h2>
- <p>To download a crack torrent for Catia V5R21, you need to have a torrent client software such as uTorrent, BitTorrent, qBittorrent, etc. installed on your device. A torrent client software allows you to download files from peer-to-peer networks by connecting to other users who have the same files on their devices. You also need to have a VPN service such as NordVPN, ExpressVPN, Surfshark, etc. installed on your device. A VPN service allows you to encrypt your internet traffic and change your IP address and location to protect your privacy and security online.</p>
- <h3>Sources and links for crack torrents</h3>
- <p>To find sources and links for crack torrents for Catia V5R21, you can use various websites such as The Pirate Bay, 1337x, RARBG, LimeTorrents, etc. These websites are known as torrent indexers that provide lists of torrents for various files such as movies, music, games, software <h3>Steps to download and install a crack torrent for Catia V5R21</h3>
- <p>To download and install a crack torrent for Catia V5R21, you can follow these steps:</p>
- <ol>
-<li>Open your torrent client software and your VPN service on your device.</li>
-<li>Go to one of the torrent indexers websites mentioned above and search for "catia v5r21 crack torrent".</li>
-<li>Select a crack torrent that has a high number of seeders, leechers, and positive comments. Avoid crack torrents that have low ratings, negative feedback, or suspicious files.</li>
-<li>Copy the magnet link or download the torrent file of the crack torrent and add it to your torrent client software.</li>
-<li>Wait for the crack torrent to finish downloading on your device. The download speed and time may vary depending on your internet connection and the size of the crack torrent.</li>
-<li>Once the download is complete, open the crack torrent folder and extract the files using a software such as WinRAR, 7-Zip, etc.</li>
-<li>Run the setup file of Catia V5R21 and follow the installation instructions. Choose a destination folder for Catia V5R21 on your device.</li>
-<li>After the installation is done, do not run Catia V5R21 yet. Go to the crack folder and copy the crack files.</li>
-<li>Paste the crack files into the destination folder of Catia V5R21 and replace the original files.</li>
-<li>Run Catia V5R21 as an administrator and enjoy using it without any license or registration.</li>
-</ol>
- <h2>How to use Catia V5R21 after installation?</h2>
- <p>After installing Catia V5R21 with a crack torrent, you can use it for various purposes such as designing, modeling, simulating, analyzing, optimizing, etc. However, you should also be aware of some tips and tricks for using Catia V5R21 effectively and safely.</p>
- <h3>Tips and tricks for using Catia V5R21</h3>
- <p>Some of the tips and tricks for using Catia V5R21 are:</p>
- <ul>
-<li>Learn the basics and advanced features of Catia V5R21 by watching online tutorials, reading manuals, joining forums, etc.</li>
-<li>Customize your workspace and preferences according to your needs and preferences by using the tools and options menus.</li>
-<li>Create and save your projects in different formats such as CATPart, CATProduct, CATDrawing, etc. by using the file menu.</li>
-<li>Use keyboard shortcuts and mouse gestures to perform common tasks faster and easier by using the help menu.</li>
-<li>Use different workbenches such as Part Design, Assembly Design, Drafting, Generative Shape Design, etc. to access different tools and functions by using the start menu.</li>
-<li>Use different commands such as Sketcher, Pad, Pocket, Hole, Fillet, Chamfer, etc. to create and modify different shapes and features by using the toolbar.</li>
-<li>Use different constraints such as Coincidence, Parallelism, Perpendicularity, Tangency, etc. to define and control the geometry and dimensions of your sketches by using the constraint menu.</li>
-<li>Use different parameters such as Length, Angle, Radius, Diameter, etc. to specify and change the values of your sketches by using the formula menu.</li>
-<li>Use different views such as Front View, Top View, Right View, Isometric View, etc. to display and manipulate your models from different perspectives by using the view menu.</li>
-<li>Use different modes such as Wireframe, Shading, Shading with Edges, Hidden Lines, etc. to display and edit your models with different levels of detail by using the visualization menu.</li>
-</ul>
- <h3>Common errors and solutions for Catia V5R21</h3>
- <p>Some of the common errors and solutions for Catia V5R21 are:</p>
- <table>
-<tr><td>Error</td><td>Solution</td></tr>
-<tr><td>Catia V5R21 does not start or crashes after installation.</td><td>Make sure you have copied and pasted the crack files correctly into the destination folder of Catia V5R21. Make sure you have run Catia V5R21 as an administrator. Make sure you have disabled your antivirus software or firewall before running Catia V5R21.</td></tr>
-<tr><td>Catia V5R21 shows a license error or expiration message.</td><td>Make sure you have downloaded a valid crack torrent for Catia V5R21 that has not expired or been blocked by Dassault Systemes. Make sure you have used a VPN service to hide your IP address and location when downloading or using Catia V5R21.</td></tr>
-<tr><td>Catia V5R21 does not work properly with your device or operating system.</td><td>Make sure you have downloaded a compatible crack torrent for Catia V5R21 that matches your device specifications and operating system version. Make sure you have updated your device drivers and operating system patches before installing or using Catia V5R21.</td></tr>
-<tr><td>Catia V5R21 does not save or open your projects correctly.</td><td>Make sure you have saved or opened your projects in the correct format and location on your device. Make sure you have enough disk space and memory on your device to store or load your projects. Make sure you have backed up your projects regularly to avoid data loss or corruption.</td></tr>
-<tr><td>Catia V5R21 does not perform well or fast enough on your device.</td><td>Make sure you have closed any unnecessary programs or processes on your device that might consume CPU, RAM, or GPU resources. Make sure you have optimized your models by reducing their complexity, size, or number of features. Make sure you have adjusted your settings by lowering your resolution, quality, or effects.</td></tr>
-</table>
- <h2>Conclusion</h2>
- <p>In conclusion, Catia V5R21 is a powerful software solution for product design and engineering that offers many features and benefits. However, Catia V5R21 is also a very expensive software that requires a license to use. If you want to use Catia V5R21 without paying for a license, you might be interested in downloading and installing a crack torrent for it. In this article, we showed you how to do that, as well as the advantages and risks of using a crack torrent for Catia V5R21. We also gave you some tips and tricks for using Catia V5R21 effectively and safely after installation. We hope this article was helpful and informative for you. If you have any questions or feedback, please feel free to contact us. Thank you for reading!</p>
- <h2>FAQs</h2>
- <p>Here are some frequently asked questions about Catia V5R21 crack torrent:</p>
- <ol>
-<li><b>What is the difference between Catia V5 and Catia V6?</b></li>
-<p>Catia V6 is the successor of Catia V5 that was released in 2008. Catia V6 has some new features and improvements over Catia V5 such as cloud-based collaboration, 3DExperience platform integration, and enhanced user interface. However, Catia V6 is also more complex and expensive than Catia V5 and requires more hardware and software resources to run smoothly. Therefore, many users still prefer to use Catia V5 for their projects.</p>
- <li><b>Is it legal to use a crack torrent for Catia V5R21?</b></li>
-<p>No, it is not legal to use a crack torrent for Catia V5R21. Using a crack torrent for Catia V5R21 violates the intellectual property rights of Dassault Systemes and can result in legal issues or penalties if you are caught. You should always respect the copyright laws and regulations of your country and region when using any software. You should also support the developers and creators of any software by purchasing a license or subscription if you can afford it.</p>
- <li><b>Can I update Catia V5R21 with a crack torrent?</b></li>
-<p>Yes, you can update Catia V5R21 with a crack torrent if you find a newer version of the crack torrent that works with the latest patches and fixes from Dassault Systemes. However, you should be careful when updating Catia V5R21 with a crack torrent because some updates might break or remove the crack files from your device. You should always backup your data before updating anything on your device. You should also scan any new files with an antivirus software before installing them on your device.</p>
- <li><b>Can I use other Dassault Systemes products with Catia V5R21 with a crack torrent?</b></li>
-<p>Yes, you can use other Dassault Systemes products with Catia V5 R21 with a crack torrent if you have the corresponding crack torrents for those products as well. However, you should be careful when using other Dassault Systemes products with Catia V5R21 with a crack torrent because some products might not be compatible or stable with each other. You should also check the license agreements and terms of use of those products before using them with Catia V5R21 with a crack torrent.</p>
- <li><b>Can I use other CAD/CAM/CAE software with Catia V5R21 with a crack torrent?</b></li>
-<p>Yes, you can use other CAD/CAM/CAE software with Catia V5R21 with a crack torrent if you can export or import your models in compatible formats such as STEP, IGES, STL, DXF, DWG, etc. However, you should be aware that some formats might not preserve all the features, properties, or quality of your models when transferring them between different software. You should also check the compatibility and performance of your models when using them with other software.</p>
-</ol>
- <h2>ed</h2>
- <p>This is the end of the article on catia v5r21 crack torrent. I hope you enjoyed reading it and learned something new. If you have any questions or feedback, please feel free to contact me. Thank you for your time and attention.</p> 0a6ba089eb<br />
-<br />
-<br />
\ No newline at end of file
diff --git a/spaces/raedeXanto/academic-chatgpt-beta/Experience the Thrill of Clash Of Clans Pc Game Download Torrent Downloadl on a Bigger Screen.md b/spaces/raedeXanto/academic-chatgpt-beta/Experience the Thrill of Clash Of Clans Pc Game Download Torrent Downloadl on a Bigger Screen.md
deleted file mode 100644
index c9d0d85752d0b029c67a481ca36d891b06038cba..0000000000000000000000000000000000000000
--- a/spaces/raedeXanto/academic-chatgpt-beta/Experience the Thrill of Clash Of Clans Pc Game Download Torrent Downloadl on a Bigger Screen.md	
+++ /dev/null
@@ -1,94 +0,0 @@
-
-<h1>Clash of Clans PC Game Download Torrent Downloadl</h1>
-<p>Are you a fan of strategy games that challenge your mind and test your skills? Do you love building your own village, training your troops, and fighting against other players? If so, you might have heard of <strong>Clash of Clans</strong>, one of the most popular mobile games in the world.</p>
-<h2>Clash Of Clans Pc Game Download Torrent Downloadl</h2><br /><p><b><b>Download</b> &#128504;&#128504;&#128504; <a href="https://tinourl.com/2uKZvi">https://tinourl.com/2uKZvi</a></b></p><br /><br />
-<p>Clash of Clans is a free-to-play game that lets you create your own clan, customize your village, and wage war against other clans. You can also join forces with other players, chat with them, and participate in clan wars. The game is fun, addictive, and constantly updated with new features and content.</p>
-<p>But what if you want to play Clash of Clans on your PC instead of your mobile device? Maybe you want to enjoy the game on a bigger screen, or use a mouse and keyboard for better control. Or maybe you want to save your phone's battery and avoid interruptions from calls and notifications.</p>
-<p>Whatever your reason, you can play Clash of Clans on your PC with a simple trick. All you need is an Android emulator, a software that lets you run Android apps on your computer. In this article, we will show you how to download and install Clash of Clans on your PC using an emulator, as well as some benefits and tips for playing the game on your PC.</p>
- <h2>How to Download and Install Clash of Clans on PC</h2>
-<p>To play Clash of Clans on your PC, you need to follow these steps:</p>
- <h3>Step 1: Download an Android emulator</h3>
-<p>An Android emulator is a program that mimics the Android operating system on your computer. It allows you to run Android apps and games on your PC, just like you would on your phone or tablet. There are many Android emulators available online, but some of the most popular ones are Bluestacks, NoxPlayer, and LDPlayer. You can choose any emulator that suits your preferences and system requirements.</p>
-<p>How to play Clash Of Clans on Pc with emulator<br />
-Clash Of Clans Pc version free download full game<br />
-Best torrent sites for downloading Clash Of Clans Pc game<br />
-Clash Of Clans Pc game system requirements and features<br />
-Clash Of Clans Pc game cheats and hacks<br />
-Clash Of Clans Pc game review and ratings<br />
-Clash Of Clans Pc game online multiplayer mode<br />
-Clash Of Clans Pc game offline installer<br />
-Clash Of Clans Pc game latest update and patch<br />
-Clash Of Clans Pc game mods and customizations<br />
-Clash Of Clans Pc game tips and tricks<br />
-Clash Of Clans Pc game comparison with mobile version<br />
-Clash Of Clans Pc game screenshots and videos<br />
-Clash Of Clans Pc game download error and solution<br />
-Clash Of Clans Pc game installation guide and tutorial<br />
-Clash Of Clans Pc game alternatives and similar games<br />
-Clash Of Clans Pc game crack and activation key<br />
-Clash Of Clans Pc game support and customer service<br />
-Clash Of Clans Pc game forums and communities<br />
-Clash Of Clans Pc game official website and social media<br />
-Clash Of Clans Pc game download speed and performance<br />
-Clash Of Clans Pc game size and file format<br />
-Clash Of Clans Pc game minimum and recommended specifications<br />
-Clash Of Clans Pc game genre and theme<br />
-Clash Of Clans Pc game developer and publisher<br />
-Clash Of Clans Pc game release date and price<br />
-Clash Of Clans Pc game awards and nominations<br />
-Clash Of Clans Pc game fan art and merchandise<br />
-Clash Of Clans Pc game history and background<br />
-Clash Of Clans Pc game characters and clans<br />
-Clash Of Clans Pc game strategy and gameplay<br />
-Clash Of Clans Pc game secrets and easter eggs<br />
-Clash Of Clans Pc game bugs and glitches<br />
-Clash Of Clans Pc game soundtrack and music<br />
-Clash Of Clans Pc game languages and subtitles<br />
-Clash Of Clans Pc game demo and trial version<br />
-Clash Of Clans Pc game refund policy and terms of service<br />
-Clash Of Clans Pc game compatibility and optimization<br />
-Clash Of Clans Pc game security and privacy issues<br />
-Clash Of Clans Pc game feedback and suggestions<br />
-How to uninstall or remove Clash Of Clans from your PC <br />
-How to backup or restore your progress in Clash Of Clans PC <br />
-How to connect your account from mobile to PC in Clash of clans <br />
-How to join or create a clan in clash of clans PC <br />
-How to upgrade your buildings and troops in clash of clans PC <br />
-How to earn or spend gems in clash of clans PC <br />
-How to chat or communicate with other players in clash of clans PC <br />
-How to watch or record replays in clash of clans PC <br />
-How to participate or win in clan wars in clash of clans PC <br />
-How to get help or report a problem in clash of clans PC</p>
-<p>To download an emulator, go to its official website and click on the download button. You will get an executable file that you need to run to install the emulator on your PC.</p>
- <h3>Step 2: Install the emulator and launch it</h3>
-<p>Once you have downloaded the emulator file, double-click on it to start the installation process. Follow the instructions on the screen to complete the installation. You might need to agree to some terms and conditions, choose a destination folder, and create a shortcut icon.</p>
-<p>After the installation is done, launch the emulator by clicking on its icon. You will see a window that looks like an Android device. You might need to sign in with your Google account to access the Google Play Store and other services.</p>
- <h3>Step 3: Search for Clash of Clans in the emulator's app store</h3>
-<p>Now that you have set up the emulator, you can search for Clash of Clans in its app store. The app store is usually located at the bottom or the side of the emulator window. Click on it to open it.</p>
-<p>In the app store, type "Clash of Clans" in the search bar and hit enter. You will see a list of results that match your query. Look for the official Clash of Clans app by Supercell, which has a red shield icon with two swords crossing over it.</p>
- <h3>Step 4: Download and install Clash of Clans</h3>
-<p>Once you have found the Clash of Clans app, click on it to open its page. You will see some information about the game, such as its description, screenshots, ratings, reviews, etc. You will also see a green "Install" button at the top right corner.</p>
-<p>Click on the "Install" button to start downloading and installing Clash of Clans on your PC. The process might take a few minutes depending on your internet speed and system performance. You can check the progress bar at the top or bottom of the app store window.</p>
-<p>When the installation is complete, you will see an "Open" button next to the "Install" button. Click on it to launch Clash of Clans on your PC.</p>
- <h3>Step 5: Enjoy the game on your PC</h3>
-<p>Congratulations! You have successfully downloaded and installed Clash of Clans on your PC using an Android emulator. You can now enjoy the game on a bigger screen, with better graphics, easier controls, faster actions, more stable performance, and less battery drain.</p>
-<p>You can play Clash of Clans on your PC just like you would on your mobile device. You can use your mouse to click or drag on the screen, or use your keyboard shortcuts to perform certain actions. You can also customize your settings in the emulator's menu to adjust the resolution, sound, keyboard mapping, etc.</p>
- <h2>Benefits of Playing Clash of Clans on PC</h2>
-<p>Playing Clash of Clans on PC has many advantages over playing it on mobile devices. Here are some of them:</p>
- <h3>Bigger screen and better graphics</h3>
-<p>One of the main benefits of playing Clash of Clans on PC is that you can enjoy the game on a larger screen with higher resolution and quality. This makes the game more immersive and visually appealing. You can see more details in your village, troops, enemies, battles, etc.</p>
-<p>You can also zoom in or out easily using your mouse wheel or keyboard keys. This gives you more control over how much you want to see or focus on in the game.</p>
- <h3>Easier controls and faster actions</h3>
-<p>Another benefit of playing Clash of Clans on PC is that you can use a mouse and keyboard instead of a touchscreen. This makes it easier to control your village, train your troops, attack other players, etc.</p>
-<p>You can also perform actions faster using keyboard shortcuts or hotkeys. For example, you can press "A" to select all troops in barracks or camps; press "S" to select spells; press "D" to deploy troops or spells; press "R" to rotate buildings; press "F" to flip walls; etc.</p>
-<p>You can also customize these shortcuts or create new ones in the emulator's settings menu.</p>
- <h3>More stable performance and less battery drain</h3>
-<p>A third benefit of playing Clash of Clans on PC is that you can avoid some common issues that affect mobile devices such as lagging, crashing, overheating, or draining battery life. These issues can ruin your gaming experience and cause frustration or loss. By playing Clash of Clans on PC, you can ensure a more stable performance and less battery drain. You can also play the game for longer periods without worrying about charging your device or running out of power. <h2>Tips and Tricks for Playing Clash of Clans on PC</h2>
- <p>If you want to improve your skills and strategies for playing Clash of Clans, here are some tips and tricks that might help:</p>
- <h3>Join a clan  and communicate with other players</h3>
- <p>One  of  the most important aspects  of  Clash  of  Cl problems or questions about the game?</strong></li>
-<li>A: To contact Supercell support, you can go to the game settings menu and tap on "Help and Support". There you will see a list of frequently asked questions and answers that might solve your problem. If you still need to contact Supercell support, you can tap on the "Contact Us" button at the top right corner and write your message. You will get a reply from Supercell support within 24 hours.</li>
-</ul>
- </p> 0a6ba089eb<br />
-<br />
-<br />
\ No newline at end of file
diff --git a/spaces/raedeXanto/academic-chatgpt-beta/Free WORK Download Film Dr. Cabbie Download.md b/spaces/raedeXanto/academic-chatgpt-beta/Free WORK Download Film Dr. Cabbie Download.md
deleted file mode 100644
index a37dc08f42278438a5fbb53ba6753deb97916f54..0000000000000000000000000000000000000000
--- a/spaces/raedeXanto/academic-chatgpt-beta/Free WORK Download Film Dr. Cabbie Download.md	
+++ /dev/null
@@ -1,37 +0,0 @@
-<br />
-<h1>How to Watch Dr. Cabbie Online for Free</h1>
-<p>Dr. Cabbie is a 2014 comedy film starring Vinay Virmani, Adrianne Palicki, Kunal Nayyar and Lillete Dubey. It tells the story of an Indian doctor who emigrates to Canada and becomes a taxi driver, but secretly treats patients from his cab. The film was produced by Salman Khan and directed by Jean-François Pouliot.</p>
-<p>If you are looking for a fun and heartwarming movie to watch online, you might be interested in Dr. Cabbie. But how can you watch it for free? Here are some options:</p>
-<h2>free download film Dr. Cabbie download</h2><br /><p><b><b>Download File</b> &#187;&#187;&#187; <a href="https://tinourl.com/2uL17Z">https://tinourl.com/2uL17Z</a></b></p><br /><br />
-<ul>
-<li>IMDb: IMDb is a popular website that offers information, ratings and reviews of movies and TV shows. You can also watch some movies for free on IMDb, including Dr. Cabbie. All you need is an IMDb account and an internet connection. You can watch Dr. Cabbie on IMDb here[^1^].</li>
-<li>Internet Archive: Internet Archive is a non-profit digital library that preserves and provides access to millions of free books, movies, music and more. You can find many Bollywood movies on Internet Archive, including Dr. Cabbie. You can download or stream Dr. Cabbie on Internet Archive here[^2^].</li>
-<li>SoundCloud: SoundCloud is a platform that lets you listen to music and podcasts from around the world. You can also find some movies on SoundCloud, such as Dr. Cabbie. You can download or stream Dr. Cabbie on SoundCloud here[^3^].</li>
-</ul>
-<p>These are some of the ways you can watch Dr. Cabbie online for free. However, please be aware that some of these websites may not have the legal rights to distribute the movie, and may be violating copyright laws. Therefore, we recommend that you watch Dr. Cabbie legally and support the filmmakers.</p>
-<p>Dr. Cabbie is a movie that celebrates diversity, compassion and humor. It is a movie that will make you laugh, cry and think. If you are looking for a movie that will entertain you and inspire you, give Dr. Cabbie a try.</p>
-
-<h2>What are the critics saying about Dr. Cabbie?</h2>
-<p>Dr. Cabbie received mixed reviews from critics, who praised the performances of the cast, but criticized the script, direction and humor. The film has a rating of 6.0 out of 10 on IMDb[^1^], based on 3,811 user ratings. It also has a rating of 40% on Rotten Tomatoes[^2^], based on 10 critic reviews.</p>
-<p>Some of the positive reviews include:</p>
-<blockquote>
-<p>"Dr. Cabbie is a sweet-natured comedy that doesn't take itself too seriously and delivers some laughs along the way." - Linda Barnard, Toronto Star</p>
-<p>"Dr. Cabbie is a feel-good movie that has its heart in the right place. It tackles the issue of immigrant integration with humor and sensitivity, and showcases the talent and charisma of its lead actor, Vinay Virmani." - Anupama Chopra, Hindustan Times</p>
-</blockquote>
-<p>Some of the negative reviews include:</p>
-<p></p>
-<blockquote>
-<p>"Dr. Cabbie is a crude comedy that relies on stereotypes and cliches to generate laughs. It wastes the potential of its premise and its cast, and fails to deliver any meaningful message or insight." - Peter Bradshaw, The Guardian</p>
-<p>"Dr. Cabbie is a disappointing film that tries to be a cross-cultural comedy, a romantic comedy and a social commentary, but ends up being none of them. It is poorly written, poorly directed and poorly executed." - Rajeev Masand, CNN-IBN</p>
-</blockquote>
-<h2>Why should you watch Dr. Cabbie?</h2>
-<p>Despite the mixed reviews, Dr. Cabbie has some redeeming qualities that might make it worth watching for some viewers. Here are some reasons why you might enjoy Dr. Cabbie:</p>
-<ul>
-<li>If you are a fan of Bollywood movies, you might appreciate the references, songs and cameo appearances by Salman Khan and Isabelle Kaif.</li>
-<li>If you are looking for a light-hearted comedy that does not require much thinking or analysis, you might find Dr. Cabbie entertaining and amusing.</li>
-<li>If you are interested in the experiences and challenges of immigrants in Canada, you might relate to some of the characters and situations in Dr. Cabbie.</li>
-<li>If you are looking for a positive and uplifting message about following your dreams and helping others, you might be inspired by Dr. Cabbie.</li>
-</ul>
-<p>Dr. Cabbie is not a masterpiece of cinema, but it is not a complete disaster either. It is a movie that has its flaws and strengths, its fans and critics, its moments of laughter and boredom. It is a movie that you might love or hate, depending on your taste and mood.</p> cec2833e83<br />
-<br />
-<br />
\ No newline at end of file
diff --git a/spaces/rajesh1729/NER-using-spacy-gradio/app.py b/spaces/rajesh1729/NER-using-spacy-gradio/app.py
deleted file mode 100644
index 7d0738ead803fbccece91e6c12621d2a3fb24e42..0000000000000000000000000000000000000000
--- a/spaces/rajesh1729/NER-using-spacy-gradio/app.py
+++ /dev/null
@@ -1,12 +0,0 @@
-import spacy
-import gradio as gr
-
-nlp = spacy.load("en_core_web_sm")
-
-def ner(sentence):
-    doc = nlp(sentence)
-    ents = [(e.text, e.label_) for e in doc.ents]
-    return ents
-
-iface = gr.Interface(fn=ner, inputs="text", outputs = "text")
-iface.launch()
\ No newline at end of file
diff --git a/spaces/ranjangoel/GPT-PDF/gpt_reader/pdf_reader.py b/spaces/ranjangoel/GPT-PDF/gpt_reader/pdf_reader.py
deleted file mode 100644
index a6d356613a466c1b92b53a77f472298fa68b43f0..0000000000000000000000000000000000000000
--- a/spaces/ranjangoel/GPT-PDF/gpt_reader/pdf_reader.py
+++ /dev/null
@@ -1,127 +0,0 @@
-from PyPDF2 import PdfReader
-import openai
-from .prompt import BASE_POINTS, READING_PROMT_V2
-from .paper import Paper
-from .model_interface import OpenAIModel
-
-
-# Setting the API key to use the OpenAI API
-class PaperReader:
-
-    """
-    A class for summarizing research papers using the OpenAI API.
-
-    Attributes:
-        openai_key (str): The API key to use the OpenAI API.
-        token_length (int): The length of text to send to the API at a time.
-        model (str): The GPT model to use for summarization.
-        points_to_focus (str): The key points to focus on while summarizing.
-        verbose (bool): A flag to enable/disable verbose logging.
-
-    """
-
-    def __init__(self, openai_key, token_length=4000, model="gpt-3.5-turbo",
-                 points_to_focus=BASE_POINTS, verbose=False):
-
-        # Setting the API key to use the OpenAI API
-        openai.api_key = openai_key
-
-        # Initializing prompts for the conversation
-        self.init_prompt = READING_PROMT_V2.format(points_to_focus)
-
-        self.summary_prompt = 'You are a researcher helper bot. Now you need to read the summaries of a research paper.'
-        self.messages = []  # Initializing the conversation messages
-        self.summary_msg = []  # Initializing the summary messages
-        self.token_len = token_length  # Setting the token length to use
-        self.keep_round = 2  # Rounds of previous dialogues to keep in conversation
-        self.model = model  # Setting the GPT model to use
-        self.verbose = verbose  # Flag to enable/disable verbose logging
-        self.model = OpenAIModel(api_key=openai_key, model=model)
-
-    def drop_conversation(self, msg):
-        # This method is used to drop previous messages from the conversation and keep only recent ones
-        if len(msg) >= (self.keep_round + 1) * 2 + 1:
-            new_msg = [msg[0]]
-            for i in range(3, len(msg)):
-                new_msg.append(msg[i])
-            return new_msg
-        else:
-            return msg
-
-    def send_msg(self, msg):
-        return self.model.send_msg(msg)
-
-    def _chat(self, message):
-        # This method is used to send a message and get a response from the OpenAI API
-
-        # Adding the user message to the conversation messages
-        self.messages.append({"role": "user", "content": message})
-        # Sending the messages to the API and getting the response
-        response = self.send_msg(self.messages)
-        # Adding the system response to the conversation messages
-        self.messages.append({"role": "system", "content": response})
-        # Dropping previous conversation messages to keep the conversation history short
-        self.messages = self.drop_conversation(self.messages)
-        # Returning the system response
-        return response
-
-    def summarize(self, paper: Paper):
-        # This method is used to summarize a given research paper
-
-        # Adding the initial prompt to the conversation messages
-        self.messages = [
-            {"role": "system", "content": self.init_prompt},
-        ]
-        # Adding the summary prompt to the summary messages
-        self.summary_msg = [{"role": "system", "content": self.summary_prompt}]
-
-         # Reading and summarizing each part of the research paper
-        for (page_idx, part_idx, text) in paper.iter_pages():
-            print('page: {}, part: {}'.format(page_idx, part_idx))
-            # Sending the text to the API and getting the response
-            summary = self._chat('now I send you page {}, part {}：{}'.format(page_idx, part_idx, text))
-            # Logging the summary if verbose logging is enabled
-            if self.verbose:
-                print(summary)
-            # Adding the summary of the part to the summary messages
-            self.summary_msg.append({"role": "user", "content": '{}'.format(summary)})
-
-        # Adding a prompt for the user to summarize the whole paper to the summary messages
-        self.summary_msg.append({"role": "user", "content": 'Now please make a summary of the whole paper'})
-        # Sending the summary messages to the API and getting the response
-        result = self.send_msg(self.summary_msg)
-        # Returning the summary of the whole paper
-        return result
-
-    def read_pdf_and_summarize(self, pdf_path):
-        # This method is used to read a research paper from a PDF file and summarize it
-        
-        # Creating a PdfReader object to read the PDF file
-        print(pdf_path)
-        pdf_reader = PdfReader(pdf_path)
-        pdf_data = ""
-        for page in pdf_reader.pages:
-            file_data += page.extract_text()
-        print(file_data)
-        
-        paper = Paper(pdf_reader)
-        # Summarizing the full text of the research paper and returning the summary
-        print('reading pdf finished')
-        summary = self.summarize(paper)
-        return summary
-
-    def get_summary_of_each_part(self):
-        # This method is used to get the summary of each part of the research paper
-        return self.summary_msg
-
-    def question(self, question):
-        # This method is used to ask a question after summarizing a paper
-
-        # Adding the question to the summary messages
-        self.summary_msg.append({"role": "user", "content": question})
-        # Sending the summary messages to the API and getting the response
-        response = self.send_msg(self.summary_msg)
-        # Adding the system response to the summary messages
-        self.summary_msg.append({"role": "system", "content": response})
-        # Returning the system response
-        return response
diff --git a/spaces/rayan-saleh/whisper2notion/docs/colab.md b/spaces/rayan-saleh/whisper2notion/docs/colab.md
deleted file mode 100644
index 3fcdb835327238764fb643b9bbd2e27b6e14f58c..0000000000000000000000000000000000000000
--- a/spaces/rayan-saleh/whisper2notion/docs/colab.md
+++ /dev/null
@@ -1,20 +0,0 @@
-# Running Whisper on Google Colab
-
-If you don't have a decent GPU or any experience in running command-line applications, you might want to try this Google Colab instead:
-
-* [Google Colab - Whisper WebUI GPU](https://colab.research.google.com/drive/1qeTSvi7Bt_5RMm88ipW4fkcsMOKlDDss?usp=sharing)
-* [Screenshots](https://imgur.com/a/ZfY6uBO)
-
-The runtime (Runtime -> Change runtime type -> Hardware accelerator) should already be set top GPU. But if not, change it to GPU.
-
-Then, sign in to Google if you haven't already. Next, click on "Connect" at the top right.
-
-Under "Checking out WebUI from Git", click on the [play icon](https://imgur.com/a/81gOLyD) that appears in "[ ]" at the left. If you get a warning, click "Run anyway".
-
-After this step has completed, it should be get a green check mark. Then move on to the next section under "Installing dependencies", and click in "[ ]" again. This might take approximately 30 seconds.
-
-Once this has completed, scroll down to the "Run WebUI" section, and click on "[ ]". This will launch the WebUI in a shared link (expires in 72 hours). To open the UI, click on the link next to "Running on public URL", which will be something like https://12xxx.gradio.app/
-
-The audio length in this version is not restricted, and it will run much faster as it is backed by a GPU. You can also run it using the "Large" model. Also note that it might take some time to start the model the first time, as it may need to download a 2.8 GB file on Google's servers.
-
-Once you're done, you can close the WebUI session by clicking the animated close button under "Run WebUI". You can also do this if you encounter any errors and need to restart the UI. You should also go to "Manage Sessions" and terminate the session, otherwise you may end up using all your free compute credits.
\ No newline at end of file
diff --git a/spaces/realfill-library/RealFill-Training-UI/app_inference.py b/spaces/realfill-library/RealFill-Training-UI/app_inference.py
deleted file mode 100644
index a1c864e512454fcc83e3e6331c2f2be450a92a92..0000000000000000000000000000000000000000
--- a/spaces/realfill-library/RealFill-Training-UI/app_inference.py
+++ /dev/null
@@ -1,166 +0,0 @@
-#!/usr/bin/env python
-
-from __future__ import annotations
-
-import enum
-
-import gradio as gr
-from huggingface_hub import HfApi
-
-from inference import InferencePipeline
-from utils import find_exp_dirs
-
-SAMPLE_MODEL_IDS = ['thuanz123/flowerwoman']
-
-
-class ModelSource(enum.Enum):
-    SAMPLE = 'Sample'
-    HUB_LIB = 'Hub (realfill-library)'
-    LOCAL = 'Local'
-
-
-class InferenceUtil:
-    def __init__(self, hf_token: str | None):
-        self.hf_token = hf_token
-
-    @staticmethod
-    def load_sample_model_list():
-        return gr.update(choices=SAMPLE_MODEL_IDS, value=SAMPLE_MODEL_IDS[0])
-    
-    def load_hub_model_list(self) -> dict:
-        api = HfApi(token=self.hf_token)
-        choices = [
-            info.modelId for info in api.list_models(author='realfill-library')
-        ]
-        return gr.update(choices=choices,
-                         value=choices[0] if choices else None)
-
-    @staticmethod
-    def load_local_model_list() -> dict:
-        choices = find_exp_dirs()
-        return gr.update(choices=choices,
-                         value=choices[0] if choices else None)
-
-    def reload_model_list(self, model_source: str) -> dict:
-        if model_source == ModelSource.SAMPLE.value:
-            return self.load_sample_model_list()
-        elif model_source == ModelSource.HUB_LIB.value:
-            return self.load_hub_model_list()
-        elif model_source == ModelSource.LOCAL.value:
-            return self.load_local_model_list()
-        else:
-            raise ValueError
-
-    def load_model_info(self, model_id: str) -> tuple[str, str]:
-        try:
-            card = InferencePipeline.get_model_card(model_id, self.hf_token)
-        except Exception:
-            return '', ''
-        target_image = getattr(card.data, 'target_image', '')
-        target_mask = getattr(card.data, 'target_mask', '')
-        return target_image, target_mask 
-
-    def reload_model_list_and_update_model_info(
-            self, model_source: str
-        ) -> tuple[dict, str, str]:
-        model_list_update = self.reload_model_list(model_source)
-        model_list = model_list_update['choices']
-        model_info = self.load_model_info(model_list[0] if model_list else '')
-        return model_list_update, *model_info
-
-
-def create_inference_demo(pipe: InferencePipeline,
-                          hf_token: str | None = None) -> gr.Blocks:
-    app = InferenceUtil(hf_token)
-
-    with gr.Blocks() as demo:
-        with gr.Row():
-            with gr.Column():
-                with gr.Box():
-                    model_source = gr.Radio(
-                        label='Model Source',
-                        choices=[_.value for _ in ModelSource],
-                        value=ModelSource.SAMPLE.value)
-                    reload_button = gr.Button('Reload Model List')
-                    model_id = gr.Dropdown(label='Model ID',
-                                                choices=SAMPLE_MODEL_IDS,
-                                                value=SAMPLE_MODEL_IDS[0])
-                    with gr.Accordion(
-                            label=
-                            'Model info (Target image and mask used for both training and inference)',
-                            open=False):
-                        with gr.Row():
-                            target_image = gr.Image(
-                                label='Target Image', 
-                                interactive=False,
-                                type='filepath')
-                            target_mask = gr.Image(
-                                label='Target Mask', 
-                                interactive=False,
-                                type='filepath')
-                seed = gr.Slider(label='Seed',
-                                 minimum=0,
-                                 maximum=100000,
-                                 step=1,
-                                 value=0)
-                with gr.Accordion('Other Parameters', open=False):
-                    num_steps = gr.Slider(label='Number of Steps',
-                                          minimum=0,
-                                          maximum=100,
-                                          step=1,
-                                          value=25)
-                    guidance_scale = gr.Slider(label='CFG Scale',
-                                               minimum=0,
-                                               maximum=50,
-                                               step=0.1,
-                                               value=5.0)
-
-                run_button = gr.Button('Generate')
-
-                gr.Markdown('''
-                - After training, you can press "Reload Model List" button to load your trained model names.
-                ''')
-            with gr.Column():
-                result = gr.Image(label='Result')
-
-        model_source.change(
-            fn=app.reload_model_list_and_update_model_info,
-            inputs=model_source,
-            outputs=[
-                model_id, 
-                target_image, 
-                target_mask
-            ])
-        reload_button.click(
-            fn=app.reload_model_list_and_update_model_info,
-            inputs=model_source,
-            outputs=[
-                model_id,
-                target_image, 
-                target_mask
-            ])
-        model_id.change(fn=app.load_model_info,
-                             inputs=model_id,
-                             outputs=[
-                                 target_image, 
-                                 target_mask
-                             ])
-        inputs = [
-            model_id,
-            seed,
-            target_image,
-            target_mask,
-            num_steps,
-            guidance_scale,
-        ]
-        run_button.click(fn=pipe.run, inputs=inputs, outputs=result)
-    return demo
-
-
-if __name__ == '__main__':
-    import os
-
-    hf_token = os.getenv('HF_TOKEN')
-    pipe = InferencePipeline(hf_token)
-    demo = create_inference_demo(pipe, hf_token)
-    demo.queue(max_size=10).launch(share=False)
diff --git a/spaces/recenWmenso/ChatGPT-with-Voice-Cloning-for-All/datasets/Haarp Cord Dragoste Sau Frica Download Album Zippy.md b/spaces/recenWmenso/ChatGPT-with-Voice-Cloning-for-All/datasets/Haarp Cord Dragoste Sau Frica Download Album Zippy.md
deleted file mode 100644
index fd06dc8589d4bb0e13d3d4218ab35f03e0769fa9..0000000000000000000000000000000000000000
--- a/spaces/recenWmenso/ChatGPT-with-Voice-Cloning-for-All/datasets/Haarp Cord Dragoste Sau Frica Download Album Zippy.md	
+++ /dev/null
@@ -1,110 +0,0 @@
-<br />
-<h1>Haarp Cord Dragoste Sau Frica: A Romanian Rap Masterpiece</h1>
-
-<p>If you are a fan of hip-hop and rap music, you might have heard of Haarp Cord, a Romanian rap group that consists of four members: Cedry2k, Dragonu AK47, Sisu Tudor and Stres. Haarp Cord is one of the most popular and influential rap groups in Romania, with a loyal fan base and a distinctive style that blends hardcore lyrics, social commentary, metaphors and wordplay.</p>
-
-<p>One of their most acclaimed albums is <strong>Haarp Cord Dragoste Sau Frica</strong> (Haarp Cord Love or Fear), which was released in 2014. This album is considered by many critics and fans as a masterpiece of Romanian rap, as it showcases the group's versatility, creativity and talent. The album contains 15 tracks that cover various topics such as identity, politics, spirituality, street life, love and hate.</p>
-<h2>Haarp Cord Dragoste Sau Frica Download Album Zippy</h2><br /><p><b><b>DOWNLOAD</b> ->>> <a href="https://urlgoal.com/2uCKhj">https://urlgoal.com/2uCKhj</a></b></p><br /><br />
-
-<p>If you want to listen to this amazing album, you might be wondering where to find it online. Well, you are in luck, because we have found a reliable and easy way to <strong>download Haarp Cord Dragoste Sau Frica</strong> from the internet. All you need is a zippy download link that will allow you to get the full album in high quality mp3 format.</p>
-
-<h2>How to Download Haarp Cord Dragoste Sau Frica Album Zippy</h2>
-
-<p>To download Haarp Cord Dragoste Sau Frica album zippy, you just need to follow these simple steps:</p>
-
-<ol>
-<li>Click on this link: https://www.danparfum.net/download-albume/HAARP-CORD---DRAGOSTE-SAU-FRICA--ALBUM-ORIGINAL-_1828.html</li>
-<li>Select one of the download options: hotfil.es or upl.me</li>
-<li>Wait for the download to start and complete</li>
-<li>Enjoy listening to Haarp Cord Dragoste Sau Frica album zippy on your device</li>
-</ol>
-
-<p>That's it! You have successfully downloaded Haarp Cord Dragoste Sau Frica album zippy. Now you can enjoy listening to this amazing rap album anytime and anywhere.</p>
-
-<h3>Why You Should Listen to Haarp Cord Dragoste Sau Frica Album Zippy</h3>
-
-<p>If you are still not convinced that Haarp Cord Dragoste Sau Frica album zippy is worth downloading, here are some reasons why you should give it a try:</p>
-
-<ul>
-<li>Haarp Cord Dragoste Sau Frica album zippy is a rap masterpiece that showcases the group's skills and diversity. You will find tracks that are hard-hitting, emotional, inspirational, witty and catchy.</li>
-<li>Haarp Cord Dragoste Sau Frica album zippy features some of the best Romanian rap artists as guests, such as Carbon, Cabron, Deliric1 and C.T.C. You will get to hear some amazing collaborations and verses from these rap legends.</li>
-<li>Haarp Cord Dragoste Sau Frica album zippy is a reflection of the Romanian society and culture. You will get to learn more about the history, politics, religion, values and struggles of the Romanian people through the lyrics and messages of the songs.</li>
-<li>Haarp Cord Dragoste Sau Frica album zippy is a source of inspiration and motivation for anyone who loves rap music. You will get to hear some powerful and uplifting words that will make you think, feel and act.</li>
-</ul>
-
-<p>So what are you waiting for? Download Haarp Cord Dragoste Sau Frica album zippy today and enjoy one of the best rap albums ever made!</p>
-<h4>What are the Best Songs from Haarp Cord Dragoste Sau Frica Album Zippy</h4>
-
-<p>Haarp Cord Dragoste Sau Frica album zippy is full of amazing songs that showcase the group's talent and diversity. However, some songs stand out more than others, either because of their popularity, their message, their style or their impact. Here are some of the best songs from Haarp Cord Dragoste Sau Frica album zippy that you should definitely listen to:</p>
-<p></p>
-
-<ul>
-<li><strong>Reprezint</strong>: This is the first track of the album and it sets the tone for the rest of the songs. It is a powerful and energetic song that expresses the group's pride and identity as Romanian rap artists. It also features some impressive wordplay and metaphors that show the group's skills and creativity.</li>
-<li><strong>Dragoste sau frica</strong>: This is the title track of the album and it is one of the most emotional and profound songs of the group. It explores the theme of love and fear, and how they affect our lives and choices. It also features some beautiful vocals from a female singer that add more depth and contrast to the song.</li>
-<li><strong>Nu mai sunt copil</strong>: This is one of the most popular and catchy songs of the album, and it has a positive and motivational message. It talks about growing up and becoming mature, and how that changes our perspective and attitude towards life. It also encourages us to follow our dreams and passions, and not to let anyone or anything stop us.</li>
-<li><strong>Titani</strong>: This is one of the most epic and impressive songs of the album, and it features some of the best Romanian rap artists as guests: C.T.C., a legendary rap group that consists of DOC, Deliric1, Vlad Dobrescu and DJ Paul. This song is a collaboration between two generations of rap artists, and it shows their respect and admiration for each other. It also showcases their incredible flow, delivery and lyrics that make them titans of rap.</li>
-<li><strong>Recunoaste</strong>: This is the last track of the album and it is a powerful and honest song that reflects on the group's journey and achievements. It also acknowledges their fans and supporters, and thanks them for their loyalty and love. It also challenges their critics and haters, and asks them to recognize their talent and success.</li>
-</ul>
-
-<p>These are just some of the best songs from Haarp Cord Dragoste Sau Frica album zippy, but there are many more that you can discover by downloading the album today. You will not regret it!</p>
-
-<h5>Conclusion: Haarp Cord Dragoste Sau Frica Album Zippy is a Must-Have for Rap Lovers</h5>
-
-<p>If you are looking for a rap album that will blow your mind with its quality, diversity, creativity and impact, then you should definitely download Haarp Cord Dragoste Sau Frica album zippy today. This album is a masterpiece of Romanian rap, and it will make you appreciate the talent and culture of this amazing rap group.</p>
-
-<p>Haarp Cord Dragoste Sau Frica album zippy is easy to download from our website, and you can enjoy listening to it on any device. You will not regret downloading this amazing rap album!</p>
-
-<p>So what are you waiting for? Download Haarp Cord Dragoste Sau Frica album zippy today!</p>
-<h6>Where to Find More Information about Haarp Cord Dragoste Sau Frica Album Zippy</h6>
-
-<p>If you want to learn more about Haarp Cord Dragoste Sau Frica album zippy, you can visit some of the following websites that provide more information and reviews about this rap album:</p>
-
-<ul>
-<li><strong>Last.fm</strong>: This is a music streaming and discovery platform that allows you to listen to Haarp Cord Dragoste Sau Frica album zippy online and see its tracklist, release date, listeners and scrobbles. You can also read some user comments and ratings about the album and join the Haarp Cord fan community. You can visit Last.fm here: https://www.last.fm/music/Haarp+Cord/Dragoste+sau+Frica</li>
-<li><strong>Bandcamp</strong>: This is a music distribution and merchandising platform that allows you to buy Haarp Cord Dragoste Sau Frica album zippy in digital or physical format. You can also stream the album online and see its credits and tags. You can also support the group directly by purchasing their other albums and merchandise. You can visit Bandcamp here: https://haarpcord.bandcamp.com/album/haarp-cord-dragoste-sau-frica</li>
-<li><strong>SoundCloud</strong>: This is a music sharing and social networking platform that allows you to listen to Haarp Cord Dragoste Sau Frica album zippy online and see its waveform, comments and likes. You can also follow the group and their official account and listen to their other songs and playlists. You can also download the album from SoundCloud using a zippy download link. You can visit SoundCloud here: https://soundcloud.com/rbwyozgayxe1988/haarp-cord-dragoste-sau-frica-download-album-zippy-upd</li>
-</ul>
-
-<p>These are some of the best websites where you can find more information about Haarp Cord Dragoste Sau Frica album zippy. You can also search for other websites and blogs that review or discuss this rap album.</p>
-
-<h7>Final Words: Haarp Cord Dragoste Sau Frica Album Zippy is a Rap Album You Should Not Miss</h7>
-
-<p>In conclusion, Haarp Cord Dragoste Sau Frica album zippy is a rap album that you should not miss if you love rap music and want to discover some of the best Romanian rap artists. This album is a masterpiece of rap music that will make you appreciate the talent, culture and message of Haarp Cord.</p>
-
-<p>Haarp Cord Dragoste Sau Frica album zippy is easy to download from our website using a zippy download link that will give you access to the full album in high quality mp3 format. You can also listen to the album online on various platforms such as Last.fm, Bandcamp and SoundCloud.</p>
-
-<p>So what are you waiting for? Download Haarp Cord Dragoste Sau Frica album zippy today and enjoy one of the best rap albums ever made!</p>
-<h8>How to Share Your Opinion about Haarp Cord Dragoste Sau Frica Album Zippy</h8>
-
-<p>If you have downloaded and listened to Haarp Cord Dragoste Sau Frica album zippy, you might want to share your opinion and feedback about this rap album with other rap lovers and Haarp Cord fans. There are many ways you can do that online, such as:</p>
-
-<ul>
-<li><strong>Commenting</strong>: You can leave a comment on the websites where you downloaded or listened to the album, such as our website, Last.fm, Bandcamp or SoundCloud. You can also comment on the group's social media pages, such as Facebook, Instagram or YouTube. You can express your thoughts and feelings about the album, your favorite songs, your rating and your suggestions.</li>
-<li><strong>Reviewing</strong>: You can write a review of the album on platforms that allow you to rate and review music, such as RateYourMusic, AllMusic or Metacritic. You can also write a review on your own blog or website if you have one. You can give a detailed and honest analysis of the album, its strengths and weaknesses, its style and genre, its lyrics and message, its production and quality.</li>
-<li><strong>Recommending</strong>: You can recommend the album to your friends and family who love rap music or want to discover new rap artists. You can also recommend the album to other rap lovers online, such as on forums, groups or communities that are dedicated to rap music or Romanian music. You can share the link to download or listen to the album online, and explain why you think they should check it out.</li>
-</ul>
-
-<p>These are some of the ways you can share your opinion about Haarp Cord Dragoste Sau Frica album zippy online. By doing so, you will help spread the word about this amazing rap album and support the group and their music.</p>
-
-<h9>FAQs about Haarp Cord Dragoste Sau Frica Album Zippy</h9>
-
-<p>If you have any questions or doubts about Haarp Cord Dragoste Sau Frica album zippy, you might find the answers in this section. Here are some of the most frequently asked questions about this rap album:</p>
-
-<ol>
-<li><strong>What is Haarp Cord?</strong>: Haarp Cord is a Romanian rap group that consists of four members: Cedry2k, Dragonu AK47, Sisu Tudor and Stres. They are one of the most popular and influential rap groups in Romania, with a loyal fan base and a distinctive style that blends hardcore lyrics, social commentary, metaphors and wordplay.</li>
-<li><strong>What is Dragoste sau Frica?</strong>: Dragoste sau Frica (Love or Fear) is the third studio album by Haarp Cord, released in 2014. It is considered by many critics and fans as a masterpiece of Romanian rap, as it showcases the group's versatility, creativity and talent. The album contains 15 tracks that cover various topics such as identity, politics, spirituality, street life, love and hate.</li>
-<li><strong>What is Zippy?</strong>: Zippy is a file hosting service that allows users to upload and download files for free. It is often used by music lovers to share and download music albums in mp3 format. Zippy download links are fast and reliable, and they do not require registration or subscription.</li>
-<li><strong>Is it legal to download Haarp Cord Dragoste Sau Frica album zippy?</strong>: It depends on your location and the laws of your country. In some countries, it is legal to download music for personal use only, as long as you do not distribute or sell it. In other countries, it is illegal to download music without the permission of the rights holders. We advise you to check the laws of your country before downloading any music from our website or any other website.</li>
-<li><strong>Is it safe to download Haarp Cord Dragoste Sau Frica album zippy?</strong>: Yes, it is safe to download Haarp Cord Dragoste Sau Frica album zippy from our website or any other website that we provide links to. We only provide links to trusted and reputable file hosting services that do not contain any viruses or malware. However, we recommend you to scan any file you download with an antivirus software before opening it.</li>
-</ol>
-
-<p>If you have any other questions about Haarp Cord Dragoste Sau Frica album zippy, feel free to contact us or leave a comment below.</p>
-<h10>Conclusion: Haarp Cord Dragoste Sau Frica Album Zippy is a Rap Album You Should Not Miss</h10>
-
-<p>In conclusion, Haarp Cord Dragoste Sau Frica album zippy is a rap album that you should not miss if you love rap music and want to discover some of the best Romanian rap artists. This album is a masterpiece of rap music that will make you appreciate the talent, culture and message of Haarp Cord.</p>
-
-<p>Haarp Cord Dragoste Sau Frica album zippy is easy to download from our website using a zippy download link that will give you access to the full album in high quality mp3 format. You can also listen to the album online on various platforms such as Last.fm, Bandcamp and SoundCloud.</p>
-
-<p>So what are you waiting for? Download Haarp Cord Dragoste Sau Frica album zippy today and enjoy one of the best rap albums ever made!</p> 3cee63e6c2<br />
-<br />
-<br />
\ No newline at end of file
diff --git a/spaces/renumics/stable-diffusion-strengths-weaknesses/README.md b/spaces/renumics/stable-diffusion-strengths-weaknesses/README.md
deleted file mode 100644
index 2e66f7a7a7f5eeb4e7332311a1fc9b4b1f11b2f8..0000000000000000000000000000000000000000
--- a/spaces/renumics/stable-diffusion-strengths-weaknesses/README.md
+++ /dev/null
@@ -1,11 +0,0 @@
----
-title: Stable Diffusion Strengths Weaknesses
-emoji: 👁
-colorFrom: green
-colorTo: purple
-sdk: docker
-pinned: false
-license: mit
----
-
-Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
diff --git a/spaces/rishi9440/remove-photo-background/src/models/backbones/wrapper.py b/spaces/rishi9440/remove-photo-background/src/models/backbones/wrapper.py
deleted file mode 100644
index 72b8f17b2e497409ce6b9a0561fd04175a3f4630..0000000000000000000000000000000000000000
--- a/spaces/rishi9440/remove-photo-background/src/models/backbones/wrapper.py
+++ /dev/null
@@ -1,82 +0,0 @@
-import os
-from functools import reduce
-
-import torch
-import torch.nn as nn
-
-from .mobilenetv2 import MobileNetV2
-
-
-class BaseBackbone(nn.Module):
-    """ Superclass of Replaceable Backbone Model for Semantic Estimation
-    """
-
-    def __init__(self, in_channels):
-        super(BaseBackbone, self).__init__()
-        self.in_channels = in_channels
-
-        self.model = None
-        self.enc_channels = []
-
-    def forward(self, x):
-        raise NotImplementedError
-
-    def load_pretrained_ckpt(self):
-        raise NotImplementedError
-
-
-class MobileNetV2Backbone(BaseBackbone):
-    """ MobileNetV2 Backbone 
-    """
-
-    def __init__(self, in_channels):
-        super(MobileNetV2Backbone, self).__init__(in_channels)
-
-        self.model = MobileNetV2(self.in_channels, alpha=1.0, expansion=6, num_classes=None)
-        self.enc_channels = [16, 24, 32, 96, 1280]
-
-    def forward(self, x):
-        # x = reduce(lambda x, n: self.model.features[n](x), list(range(0, 2)), x)
-        x = self.model.features[0](x)
-        x = self.model.features[1](x)
-        enc2x = x
-
-        # x = reduce(lambda x, n: self.model.features[n](x), list(range(2, 4)), x)
-        x = self.model.features[2](x)
-        x = self.model.features[3](x)
-        enc4x = x
-
-        # x = reduce(lambda x, n: self.model.features[n](x), list(range(4, 7)), x)
-        x = self.model.features[4](x)
-        x = self.model.features[5](x)
-        x = self.model.features[6](x)
-        enc8x = x
-
-        # x = reduce(lambda x, n: self.model.features[n](x), list(range(7, 14)), x)
-        x = self.model.features[7](x)
-        x = self.model.features[8](x)
-        x = self.model.features[9](x)
-        x = self.model.features[10](x)
-        x = self.model.features[11](x)
-        x = self.model.features[12](x)
-        x = self.model.features[13](x)
-        enc16x = x
-
-        # x = reduce(lambda x, n: self.model.features[n](x), list(range(14, 19)), x)
-        x = self.model.features[14](x)
-        x = self.model.features[15](x)
-        x = self.model.features[16](x)
-        x = self.model.features[17](x)
-        x = self.model.features[18](x)
-        enc32x = x
-        return [enc2x, enc4x, enc8x, enc16x, enc32x]
-
-    def load_pretrained_ckpt(self):
-        # the pre-trained model is provided by https://github.com/thuyngch/Human-Segmentation-PyTorch 
-        ckpt_path = './pretrained/mobilenetv2_human_seg.ckpt'
-        if not os.path.exists(ckpt_path):
-            print('cannot find the pretrained mobilenetv2 backbone')
-            exit()
-        
-        ckpt = torch.load(ckpt_path)
-        self.model.load_state_dict(ckpt)
diff --git a/spaces/rockeycoss/Prompt-Segment-Anything-Demo/mmdet/models/detectors/point_rend.py b/spaces/rockeycoss/Prompt-Segment-Anything-Demo/mmdet/models/detectors/point_rend.py
deleted file mode 100644
index 90eb4d40eb179e41cfe0cc2772c9120c093b3d93..0000000000000000000000000000000000000000
--- a/spaces/rockeycoss/Prompt-Segment-Anything-Demo/mmdet/models/detectors/point_rend.py
+++ /dev/null
@@ -1,32 +0,0 @@
-# Copyright (c) OpenMMLab. All rights reserved.
-from ..builder import DETECTORS
-from .two_stage import TwoStageDetector
-
-
-@DETECTORS.register_module()
-class PointRend(TwoStageDetector):
-    """PointRend: Image Segmentation as Rendering
-
-    This detector is the implementation of
-    `PointRend <https://arxiv.org/abs/1912.08193>`_.
-
-    """
-
-    def __init__(self,
-                 backbone,
-                 rpn_head,
-                 roi_head,
-                 train_cfg,
-                 test_cfg,
-                 neck=None,
-                 pretrained=None,
-                 init_cfg=None):
-        super(PointRend, self).__init__(
-            backbone=backbone,
-            neck=neck,
-            rpn_head=rpn_head,
-            roi_head=roi_head,
-            train_cfg=train_cfg,
-            test_cfg=test_cfg,
-            pretrained=pretrained,
-            init_cfg=init_cfg)
diff --git a/spaces/rorallitri/biomedical-language-models/logs/Helen Lethal Pressure Crush 24l.md b/spaces/rorallitri/biomedical-language-models/logs/Helen Lethal Pressure Crush 24l.md
deleted file mode 100644
index 64196f2ae5d7c909e96a7c30438e9d64e53b4d8c..0000000000000000000000000000000000000000
--- a/spaces/rorallitri/biomedical-language-models/logs/Helen Lethal Pressure Crush 24l.md	
+++ /dev/null
@@ -1,6 +0,0 @@
-<h2>Helen Lethal Pressure Crush 24l</h2><br /><p><b><b>Download File</b> &#10037;&#10037;&#10037; <a href="https://tinurll.com/2uznRd">https://tinurll.com/2uznRd</a></b></p><br /><br />
-
- aaccfb2cb3<br />
-<br />
-<br />
-<p></p>
diff --git a/spaces/ryancahildebrandt/all_in_one_sentence_embeddings/readin.py b/spaces/ryancahildebrandt/all_in_one_sentence_embeddings/readin.py
deleted file mode 100644
index 3fbb51942608cc6b7d6c7b9e057d8a9766c6b576..0000000000000000000000000000000000000000
--- a/spaces/ryancahildebrandt/all_in_one_sentence_embeddings/readin.py
+++ /dev/null
@@ -1,39 +0,0 @@
-#!/usr/bin/env python3
-# -*- coding: utf-8 -*-
-"""
-Created on Sun Jul 17 06:45:29 PM EDT 2022 
-author: Ryan Hildebrandt, github.com/ryancahildebrandt
-"""
-# imports
-import random
-
-from sklearn.datasets import fetch_20newsgroups
-
-random.seed(42)
-
-#ng = fetch_20newsgroups(categories = ["alt.atheism"])
-
-"""
-['alt.atheism',
-  'comp.graphics',
-  'comp.os.ms-windows.misc',
-  'comp.sys.ibm.pc.hardware',
-  'comp.sys.mac.hardware',
-  'comp.windows.x',
-  'misc.forsale',
-  'rec.autos',
-  'rec.motorcycles',
-  'rec.sport.baseball',
-  'rec.sport.hockey',
-  'sci.crypt',
-  'sci.electronics',
-  'sci.med',
-  'sci.space',
-  'soc.religion.christian',
-  'talk.politics.guns',
-  'talk.politics.mideast',
-  'talk.politics.misc',
-  'talk.religion.misc']
-"""
-
-default = ["She got hiccups and couldn't get rid of them for three hours.","Big Brother is watching.","He snuck into the house after midnight to investigate.","We stayed on a boat last night.","Her mother offered to send her money every month but she was too embarrassed to accept it.","Alone in the big city I began to get homesick.","He was exhausted by the job search but knew he wouldn't get to relax until he had found a job.","It felt great to disconnect with technology.","I like open spaces.","Tragedy brings hope.","The banana was completely brown.","I'm going to the concert.","We've been trying to go there for so long.","Dozens of houses were burned down in that big fire.","She was depressed by the unrelenting forward march of time.","We will make a snowman this winter.","When are we going to start the grill?","Do you eat ice cream?","Go home weirdo!","Keep it up!","There was a big fire in my neighborhood.","He wanted to move in with his girlfriend but she had painted every wall of her house pink and he couldn't stand it.","I like rice and beans for dinner.","There are many things that confuse me about that.","No sport should be called football.","The school principal was so mean that all the children were scared of him.","The spa was called Blue Mercury.","She refused to believe that anyone could actually like mashed potatoes.","She ate a sandwich for lunch which contained turkey cheddar cheese and slices of strawberries.","He slowly began to realize the error of his ways.","She ordered a mass box of fifty-two mac and cheese packets online.","The mailbox was bent and broken and looked like someone had knocked it over on purpose.","Juice was something I never drank.","She was the mother of my children.","Of course I will help you with the move.","That is a pencil.","Where do you come from?","Don't go there!","What are you talking about?","She washed the grapes.","There was a big fire in my neighborhood.","He wanted to move in with his girlfriend but she had painted every wall of her house pink and he couldn't stand it.","I like rice and beans for dinner.","There are many things that confuse me about that.","No sport should be called football.","The school principal was so mean that all the children were scared of him.","The spa was called Blue Mercury.","She refused to believe that anyone could actually like mashed potatoes.","She ate a sandwich for lunch which contained turkey cheddar cheese and slices of strawberries.","He slowly began to realize the error of his ways.","She ordered a mass box of fifty-two mac and cheese packets online.","The mailbox was bent and broken and looked like someone had knocked it over on purpose.","Juice was something I never drank.","She was the mother of my children.","Of course I will help you with the move.","That is a pencil.","Where do you come from?","Don't go there!","What are you talking about?","She washed the grapes.","He is now looking for a bigger house to live in.","Sue was her favorite classmate.","You're pulling my leg.","They employed him as a consultant.","We can go to Paris.","That's a pretty big job to do all by yourself.","Apple picking is not in season.","She wasn't sure if she liked her job or not but she was sure it was better than being unemployed.","She had never read any Nabokov though she knew he was a classic writer.","I was so thirsty that I couldn't wait to get a drink of water.","If you turn right you will see a big building.","I have no idea.","She was shaking like a chihuahua.","He wanted to find out what had happened to his brother.","I am dreaming of a better world.","There is one open baby swing.","A turkey is a little bigger than a chicken.","Sit down and cross your legs please!","What a big supermarket!","Does he go to school?","Soccer is the devil's sport.","The course starts next Sunday.","It is clear that he has made a big mistake.","This recipe has been in my family for 100 years.","I’m the designated driver.","She wasn't sure if she liked him or not.","The dog chased the cat around the block four times.","Meredith made a list of songs she doesn't like.","The gum was stuck under the desk and I couldn't get it off.","She constantly worried about accidentally burning her house down.","I am just extremely proud of him.","She washed the tomatoes.","He said he didn’t want to hotwire a car.","Uncle Joe gave me a red toy truck.","Happy Birthday to my 152 year old lover Canada.","He looked puzzled.","Would you like to have some coffee?","It would be quite impossible to enumerate all the things in existence.","Cows are smelly.","Who's Archibald?"]
\ No newline at end of file
diff --git a/spaces/samcaicn/bingai/src/components/providers.tsx b/spaces/samcaicn/bingai/src/components/providers.tsx
deleted file mode 100644
index 892226412d80fe0b05211911b9e245cd22876460..0000000000000000000000000000000000000000
--- a/spaces/samcaicn/bingai/src/components/providers.tsx
+++ /dev/null
@@ -1,15 +0,0 @@
-'use client'
-
-import * as React from 'react'
-import { ThemeProvider as NextThemesProvider } from 'next-themes'
-import { ThemeProviderProps } from 'next-themes/dist/types'
-
-import { TooltipProvider } from '@/components/ui/tooltip'
-
-export function Providers({ children, ...props }: ThemeProviderProps) {
-  return (
-    <NextThemesProvider {...props}>
-      <TooltipProvider>{children}</TooltipProvider>
-    </NextThemesProvider>
-  )
-}
diff --git a/spaces/santhosh/NLLB-Translator/README.md b/spaces/santhosh/NLLB-Translator/README.md
deleted file mode 100644
index e6440c1f0cfbaebe6573193e597bf5cfa934e231..0000000000000000000000000000000000000000
--- a/spaces/santhosh/NLLB-Translator/README.md
+++ /dev/null
@@ -1,14 +0,0 @@
----
-title: NLLB Translator
-emoji: 🗺️
-colorFrom: purple
-colorTo: pink
-sdk: gradio
-sdk_version: 3.0.26
-app_file: app.py
-pinned: false
-license: wtfpl
-duplicated_from: Narrativaai/NLLB-Translator
----
-
-Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
diff --git a/spaces/scedlatioru/img-to-music/example/Autodesk VRED Professional 2020 ((HOT)) Free Download With Activation.md b/spaces/scedlatioru/img-to-music/example/Autodesk VRED Professional 2020 ((HOT)) Free Download With Activation.md
deleted file mode 100644
index c1514fe9e2b55c4718f3bd1911f9729515d5455f..0000000000000000000000000000000000000000
--- a/spaces/scedlatioru/img-to-music/example/Autodesk VRED Professional 2020 ((HOT)) Free Download With Activation.md	
+++ /dev/null
@@ -1,98 +0,0 @@
-<br />
-<h1>Autodesk VRED Professional 2020 Free Download with Activation</h1>
-<p>If you are looking for a powerful 3D visualization and virtual prototyping software for automotive designers, you might want to check out Autodesk VRED Professional 2020. This software allows you to create high-quality renderings on premises or in the cloud, visualize, review, and validate your designs with ease and accuracy, and collaborate on any device, including VR. In this article, we will show you how to get Autodesk VRED Professional 2020 free download with activation code.</p>
-<h2>Autodesk VRED Professional 2020 Free Download with activation</h2><br /><p><b><b>Download File</b> &#9913; <a href="https://gohhs.com/2uEzZc">https://gohhs.com/2uEzZc</a></b></p><br /><br />
-<h2>What is Autodesk VRED Professional 2020?</h2>
-<p>Autodesk VRED Professional 2020 is a professional 3D visualization software that brings your complex data to life. It is designed for automotive designers who need to showcase photorealistic prototypes of their vehicles, interiors, and accessories. With Autodesk VRED Professional 2020, you can:</p>
-<ul>
-<li>Import various CAD formats and create stunning renderings with ray tracing and global illumination.</li>
-<li>Use interactive tools to manipulate materials, lighting, cameras, and animations.</li>
-<li>Perform design reviews and validation with real-time feedback and measurements.</li>
-<li>Share your designs with stakeholders and clients using cloud rendering, VR, AR, or web streaming.</li>
-<li>Integrate with other Autodesk products such as Alias, Maya, 3ds Max, and Revit.</li>
-</ul>
-<h2>How to Get Autodesk VRED Professional 2020 Free Download with Activation Code?</h2>
-<p>The easiest way to get Autodesk VRED Professional 2020 free download with activation code is to use the free trial offer from Autodesk. You can download VRED software and the asset library from the official website and enjoy the full product experience for 30 days. Here are the steps to follow:</p>
-<ol>
-<li>Go to <a href="https://www.autodesk.com/products/vred/free-trial">https://www.autodesk.com/products/vred/free-trial</a> and click on "Download free trial".</li>
-<li>Sign in with your Autodesk account or create one if you don't have one.</li>
-<li>Select your operating system (Windows or Mac) and click on "Download now".</li>
-<li>Follow the instructions to install the software on your computer.</li>
-<li>After installation, launch the software and enter your activation code. You can find your activation code in your Autodesk account or in the email you received after downloading the trial.</li>
-<li>Enjoy using Autodesk VRED Professional 2020 for free for 30 days.</li>
-</ol>
-<h2>Conclusion</h2>
-<p>Autodesk VRED Professional 2020 is a great software for automotive designers who want to create realistic and immersive 3D visualizations of their products. You can get Autodesk VRED Professional 2020 free download with activation code by using the free trial offer from Autodesk. However, if you want to use the software beyond the trial period, you will need to purchase a subscription from Autodesk or an authorized reseller. You can compare the different subscription options and prices on the Autodesk website. We hope this article was helpful and informative. If you have any questions or feedback, feel free to leave a comment below.</p>
-<h2>What are the Features of Autodesk VRED Professional 2020?</h2>
-<p>Autodesk VRED Professional 2020 has many features that make it a powerful and versatile software for 3D visualization and virtual prototyping. Some of the features are:</p>
-<p></p>
-<ul>
-<li>GPU ray tracing: You can use your graphics card to render realistic images with shadows, reflections, and refractions in real time.</li>
-<li>Global illumination: You can simulate the natural lighting of your scene with accurate color and brightness.</li>
-<li>Material Editor: You can create and edit complex materials with a node-based interface and full Python API access.</li>
-<li>Render Layer: You can set material overrides and store multiple render passes in layered EXR and PSD files.</li>
-<li>Extended Reality: You can view your designs in VR or AR using various devices and platforms.</li>
-</ul>
-<h2>How to Use Autodesk VRED Professional 2020?</h2>
-<p>Autodesk VRED Professional 2020 is easy to use and has a simple user interface. You can follow these steps to use the software:</p>
-<ol>
-<li>Import your CAD data from various formats such as Alias, CATIA, FBX, or NURBS.</li>
-<li>Set up your scene with cameras, lights, materials, and animations.</li>
-<li>Render your scene with GPU ray tracing or global illumination.</li>
-<li>Review and validate your design with interactive tools and measurements.</li>
-<li>Share your design with others using cloud rendering, VR, AR, or web streaming.</li>
-</ol>
-<h2>Where to Get Help and Support for Autodesk VRED Professional 2020?</h2>
-<p>If you need help and support for Autodesk VRED Professional 2020, you can access various resources from Autodesk. Some of the resources are:</p>
-<ul>
-<li>Tutorials: You can watch video tutorials on how to use the software on the Autodesk website or YouTube channel.</li>
-<li>Documentation: You can read the user guide and reference manual on the Autodesk website or download them as PDF files.</li>
-<li>Forums: You can ask questions and get answers from other users and experts on the Autodesk forums.</li>
-<li>Support: You can contact Autodesk support by phone, email, or chat for technical issues or feedback.</li>
-</ul>
-<h2>What are the System Requirements for Autodesk VRED Professional 2020?</h2>
-<p>Before you download and install Autodesk VRED Professional 2020, you need to make sure your computer meets the minimum system requirements for the software. Here are the system requirements for Autodesk VRED Professional 2020:</p>
-<ul>
-<li>Hardware: You need a 64-bit Intel® processor with Intel® EM64T-capable or AMD® Athlon 64®, AMD Opteron® processor. You also need at least 1 GB of RAM, but 8 GB or more is recommended. For graphics, you need a supported NVIDIA® or AMD graphics card with OpenGL 4.3 support and a certified driver.</li>
-<li>Operating Systems: You can run Autodesk VRED Professional 2020 on Microsoft® Windows® 10 (64-bit), Microsoft Windows 8.1 Professional (64-bit), or Microsoft Windows 7 (64-Bit) SP1 or higher. For VRED Render Node, you can also use Linux with GNU C Library stable release version 2.5 with installed X-Server.</li>
-<li>Other Software: You need Adobe® Acrobat® Reader to view PDF documentation provided, an Internet Browser (certified: Mozilla Firefox, Internet Explorer 9 or higher), and Flash Player to view Tutorials. You also need appropriate graphics card driver and driver software for optional hardware.</li>
-<li>Optional Hardware: You can use a 3D Mouse, Oculus VR, HP Reverb Virtual Reality Headset, HTC Vive, StarVR, WinMR, Varjo VRHero/VRgineers XTAL to enhance your experience with Autodesk VRED Professional 2020.</li>
-</ul>
-<h2>How to Update Autodesk VRED Professional 2020?</h2>
-<p>If you want to keep your Autodesk VRED Professional 2020 up to date with the latest features and fixes, you need to install the updates released by Autodesk. You can check for updates from within the software or from the Autodesk website. Here are the steps to update Autodesk VRED Professional 2020:</p>
-<ol>
-<li>From within the software: Launch Autodesk VRED Professional 2020 and go to Help > Check for Updates. If there are any updates available, you will see a notification window with the details of the update. Click on Download and Install to start the update process.</li>
-<li>From the website: Go to <a href="https://knowledge.autodesk.com/support/vred-products/downloads">https://knowledge.autodesk.com/support/vred-products/downloads</a> and find the latest update for Autodesk VRED Professional 2020. Click on Download and follow the instructions to install the update.</li>
-</ol>
-<h2>How to Uninstall Autodesk VRED Professional 2020?</h2>
-<p>If you want to uninstall Autodesk VRED Professional 2020 from your computer, you need to follow these steps:</p>
-<ol>
-<li>Close any running instances of Autodesk VRED Professional 2020.</li>
-<li>Go to Control Panel > Programs > Programs and Features and find Autodesk VRED Professional 2020 in the list of installed programs.</li>
-<li>Select Autodesk VRED Professional 2020 and click on Uninstall/Change.</li>
-<li>Follow the instructions on the screen to complete the uninstallation process.</li>
-</ol>
-<h2>What are the Benefits of Autodesk VRED Professional 2020?</h2>
-<p>Autodesk VRED Professional 2020 has many benefits that make it a valuable software for 3D visualization and virtual prototyping. Some of the benefits are:</p>
-<ul>
-<li>It saves time and money by reducing the need for physical prototypes and mockups.</li>
-<li>It improves communication and collaboration by enabling visual feedback and interaction with stakeholders and clients.</li>
-<li>It enhances creativity and innovation by allowing you to explore different design options and scenarios.</li>
-<li>It increases quality and accuracy by enabling you to detect and correct errors and flaws in your design.</li>
-<li>It boosts customer satisfaction and loyalty by delivering stunning and immersive presentations of your products.</li>
-</ul>
-<h2>What are the Reviews of Autodesk VRED Professional 2020?</h2>
-<p>Autodesk VRED Professional 2020 has received positive reviews from users and experts who have used the software for 3D visualization and virtual prototyping. Here are some of the reviews of Autodesk VRED Professional 2020:</p>
-<blockquote>
-<p>"The renders out of VRED are second to none. The quality is astounding. The integration with physical studio setups is top notch and the speed of the VRAY engine is very good. The materials editor is also quite powerful and when integrated with Illustrator you get a great solution for custom textures." - User review on G2</p>
-</blockquote>
-<blockquote>
-<p>"VRED is a great tool for creating realistic images of products, especially cars. It has a lot of features that allow you to adjust the lighting, materials, cameras, and animations. It also supports VR and AR, which is very useful for presenting your designs in an immersive way." - User review on Capterra</p>
-</blockquote>
-<blockquote>
-<p>"VRED is one of the best software for 3D visualization and virtual prototyping. It is very easy to use and has a lot of options to customize your scene. It also integrates well with other Autodesk products such as Alias, Maya, 3ds Max, and Revit. It is a must-have software for automotive designers." - Expert review on Software Advice</p>
-</blockquote>
-<h2>Conclusion</h2>
-<p>In this article, we have shown you how to get Autodesk VRED Professional 2020 free download with activation code. We have also explained what Autodesk VRED Professional 2020 is, what are its features, benefits, system requirements, and reviews. Autodesk VRED Professional 2020 is a professional 3D visualization software that helps you create high-quality renderings and virtual prototypes of your products. It is designed for automotive designers who need to showcase photorealistic prototypes of their vehicles, interiors, and accessories. It also allows you to visualize, review, validate, and collaborate on your designs with ease and accuracy. If you are looking for a powerful and versatile software for 3D visualization and virtual prototyping, you should definitely try Autodesk VRED Professional 2020.</p> 3cee63e6c2<br />
-<br />
-<br />
\ No newline at end of file
diff --git a/spaces/scedlatioru/img-to-music/example/Chocolate Starfish And The Hotdog Flavored Water.rar Download.md b/spaces/scedlatioru/img-to-music/example/Chocolate Starfish And The Hotdog Flavored Water.rar Download.md
deleted file mode 100644
index 947d482f7a9a45f633cccbe32987cfa9c6b68270..0000000000000000000000000000000000000000
--- a/spaces/scedlatioru/img-to-music/example/Chocolate Starfish And The Hotdog Flavored Water.rar Download.md	
+++ /dev/null
@@ -1,14 +0,0 @@
-<h2>Chocolate Starfish And The Hotdog Flavored Water.rar Download</h2><br /><p><b><b>Download</b> &#8250;&#8250;&#8250; <a href="https://gohhs.com/2uEAjY">https://gohhs.com/2uEAjY</a></b></p><br /><br />
-
-3. Flavored Water. 4. Natural Disaster. 5. Idiot Box. 6. A$$hole. 7. Stan. 8. Asshole. 9. Waste Of Time. 10. This Song Is About You. 11. Old Person. 12. Nutritious. 13. That Was F@#$%*ed Up.
-
-Like How I Met Your Mother, the premise of The Sarah Silverman Program sounds like it could have been the basis of a sitcom on every network except the biggest. The 30-minute series is centered on a comedian, played by Sarah Silverman, who runs her own talk show out of her apartment. Its in-jokes about Julia Louis-Dreyfus and David Letterman run deep, and the only thing that’s not mentioned in the pilot is Nickelodeon. But just because it takes a little while to understand Sarah Silverman—what she’s into, what she doesn’t like—doesn’t mean The Sarah Silverman Program is a bad show.
-
-With a rating of 1.0, the first episode of The Sarah Silverman Program was the highest-rated episode of the night, outdistancing the rest of the season premieres by large margins.
-
-Zadie Smith is a doctor with all the time in the world. Her critically acclaimed debut novel White Teeth was released just three years ago. Smith is an extremely astute observer of the twenty-first century: one of the most perceptive writers on the subject of twenty-first century English life. Over the course of her latest novel, On Beauty, she offers a “History of Skin” that clarifies what is going on with our most intimate – and most visible – organs. Skin should be more than a topic for literary analysis. For it is the means by which our identities are revealed to us. And Smith’s exploration of skin is both hilarious and gripping.
-
-On Beauty is very funny. The novel follows the trials and tribulations of a young lawyer who meets and falls in love with the girl of his dreams. What happens next is perhaps Smith’s most successful performance: her willingness to allow her characters to use the entire range of human emotional response, even if it leads them to mistakes, missteps and delusions. This is very funny and it’s also rich with anger. It is also insightful. Smith demonstrates her genius as a chronicler of a certain time and place, as she does in 4fefd39f24<br />
-<br />
-<br />
-<p></p>
diff --git a/spaces/scedlatioru/img-to-music/example/Curse By The Sea Telenovela 46.md b/spaces/scedlatioru/img-to-music/example/Curse By The Sea Telenovela 46.md
deleted file mode 100644
index 1d9a98b78d9c1cf7ad794709cd1483675adeab87..0000000000000000000000000000000000000000
--- a/spaces/scedlatioru/img-to-music/example/Curse By The Sea Telenovela 46.md	
+++ /dev/null
@@ -1,8 +0,0 @@
-<h2>Curse By The Sea Telenovela 46</h2><br /><p><b><b>Download</b> &#10003;&#10003;&#10003; <a href="https://gohhs.com/2uEzJH">https://gohhs.com/2uEzJH</a></b></p><br /><br />
-
-Review: Mar de amor (Eng. Curse By The Sea) is a Mexican telenovela in Spanish created by Nathalie Lartillo for Televisa in 2009. . The series tells the story of the girl Esperanza.
-She was born into a family where, since childhood, she was surrounded by deceitful people who were ready to do anything for the sake of profit.
-After the death of her mother, Esperanza was forced to 8a78ff9644<br />
-<br />
-<br />
-<p></p>
diff --git a/spaces/scedlatioru/img-to-music/example/LEGO DC Super-Villains Aquaman Bundle Pack Crack Activation Code Downloadl [UPD].md b/spaces/scedlatioru/img-to-music/example/LEGO DC Super-Villains Aquaman Bundle Pack Crack Activation Code Downloadl [UPD].md
deleted file mode 100644
index 858f9382527cb90901d411e3835108d484178b80..0000000000000000000000000000000000000000
--- a/spaces/scedlatioru/img-to-music/example/LEGO DC Super-Villains Aquaman Bundle Pack Crack Activation Code Downloadl [UPD].md	
+++ /dev/null
@@ -1,7 +0,0 @@
-<br />
-<p>lego dc super-villains aquaman bundle pack crack activation code download is available for free at hacksup. lego dc super-villains aquaman bundle pack crack activation code download is compatible with all versions of windows like windows xp, windows vista, windows 7, windows 8 and windows 10. download activation software from virustotal. </p>
-<p>lego dc super-villains aquaman bundle pack crack activation code download. in the following list of programs will be provided with lego dc super-villains aquaman bundle pack crack activation code download with their required software key, so that they can be activated or activated. the software link activated for their products can be downloaded by clicking on the software. </p>
-<h2>LEGO DC Super-Villains Aquaman Bundle Pack Crack Activation Code Downloadl</h2><br /><p><b><b>Download File</b> &#9658;&#9658;&#9658;&#9658;&#9658; <a href="https://gohhs.com/2uEA2l">https://gohhs.com/2uEA2l</a></b></p><br /><br />
-<p>lego dc super-villains aquaman bundle pack crack activation code download. to activate the device.jagoda martin jagoda martin (born 19 june 1945 in zagreb) is a croatian-born and boston-raised sculptor. she grew up in zagreb. she graduated from the croatian school of applied arts and design, zagreb, in 1969 and completed her formal education from the brooklyn museum and corcoran school of art, washington d.c. in 1971. she has had numerous solo and group exhibitions in the u.s. and abroad, including kaleidoscope, a space odyssey, the isomorphic objectivism of jagoda martin, a collaborative exhibition at the wadsworth athenaeum museum and library in hartford, ct, in 1989. she exhibited "vast masterpieces" representing "a decade of explorations through bronze and wood on this earth that calls us home," at the ica boston in a major exhibition presented by the portland art museum. in 2003, she was named the first "bicentennial professor" at bentley university in boston. her work was the subject of an october 14, 1996, "art on tap" segment of the npr program weekend edition saturday. in 2015 her water fountains of the world were commissioned for loyola marymount university, including a fountain on the entrance steps to the wilshire campus quad.</p> 899543212b<br />
-<br />
-<br />
\ No newline at end of file
diff --git a/spaces/senger/AI-Text-Generator/README.md b/spaces/senger/AI-Text-Generator/README.md
deleted file mode 100644
index fd46f50fd362f15986d7f6525755c1ce9746dc4d..0000000000000000000000000000000000000000
--- a/spaces/senger/AI-Text-Generator/README.md
+++ /dev/null
@@ -1,11 +0,0 @@
----
-title: AI Text Generator
-emoji: 🐠
-colorFrom: red
-colorTo: gray
-sdk: static
-pinned: false
-license: gpl-2.0
----
-
-Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
diff --git a/spaces/sgxz/bingo/src/lib/hooks/use-enter-submit.tsx b/spaces/sgxz/bingo/src/lib/hooks/use-enter-submit.tsx
deleted file mode 100644
index d66b2d3253baff164235d4ca791aae6d84721835..0000000000000000000000000000000000000000
--- a/spaces/sgxz/bingo/src/lib/hooks/use-enter-submit.tsx
+++ /dev/null
@@ -1,23 +0,0 @@
-import { useRef, type RefObject } from 'react'
-
-export function useEnterSubmit(): {
-  formRef: RefObject<HTMLFormElement>
-  onKeyDown: (event: React.KeyboardEvent<HTMLTextAreaElement>) => void
-} {
-  const formRef = useRef<HTMLFormElement>(null)
-
-  const handleKeyDown = (
-    event: React.KeyboardEvent<HTMLTextAreaElement>
-  ): void => {
-    if (
-      event.key === 'Enter' &&
-      !event.shiftKey &&
-      !event.nativeEvent.isComposing
-    ) {
-      formRef.current?.requestSubmit()
-      event.preventDefault()
-    }
-  }
-
-  return { formRef, onKeyDown: handleKeyDown }
-}
diff --git a/spaces/shi-labs/Prompt-Free-Diffusion/lib/model_zoo/controlnet_annotator/midas/utils.py b/spaces/shi-labs/Prompt-Free-Diffusion/lib/model_zoo/controlnet_annotator/midas/utils.py
deleted file mode 100644
index 9a9d3b5b66370fa98da9e067ba53ead848ea9a59..0000000000000000000000000000000000000000
--- a/spaces/shi-labs/Prompt-Free-Diffusion/lib/model_zoo/controlnet_annotator/midas/utils.py
+++ /dev/null
@@ -1,189 +0,0 @@
-"""Utils for monoDepth."""
-import sys
-import re
-import numpy as np
-import cv2
-import torch
-
-
-def read_pfm(path):
-    """Read pfm file.
-
-    Args:
-        path (str): path to file
-
-    Returns:
-        tuple: (data, scale)
-    """
-    with open(path, "rb") as file:
-
-        color = None
-        width = None
-        height = None
-        scale = None
-        endian = None
-
-        header = file.readline().rstrip()
-        if header.decode("ascii") == "PF":
-            color = True
-        elif header.decode("ascii") == "Pf":
-            color = False
-        else:
-            raise Exception("Not a PFM file: " + path)
-
-        dim_match = re.match(r"^(\d+)\s(\d+)\s$", file.readline().decode("ascii"))
-        if dim_match:
-            width, height = list(map(int, dim_match.groups()))
-        else:
-            raise Exception("Malformed PFM header.")
-
-        scale = float(file.readline().decode("ascii").rstrip())
-        if scale < 0:
-            # little-endian
-            endian = "<"
-            scale = -scale
-        else:
-            # big-endian
-            endian = ">"
-
-        data = np.fromfile(file, endian + "f")
-        shape = (height, width, 3) if color else (height, width)
-
-        data = np.reshape(data, shape)
-        data = np.flipud(data)
-
-        return data, scale
-
-
-def write_pfm(path, image, scale=1):
-    """Write pfm file.
-
-    Args:
-        path (str): pathto file
-        image (array): data
-        scale (int, optional): Scale. Defaults to 1.
-    """
-
-    with open(path, "wb") as file:
-        color = None
-
-        if image.dtype.name != "float32":
-            raise Exception("Image dtype must be float32.")
-
-        image = np.flipud(image)
-
-        if len(image.shape) == 3 and image.shape[2] == 3:  # color image
-            color = True
-        elif (
-            len(image.shape) == 2 or len(image.shape) == 3 and image.shape[2] == 1
-        ):  # greyscale
-            color = False
-        else:
-            raise Exception("Image must have H x W x 3, H x W x 1 or H x W dimensions.")
-
-        file.write("PF\n" if color else "Pf\n".encode())
-        file.write("%d %d\n".encode() % (image.shape[1], image.shape[0]))
-
-        endian = image.dtype.byteorder
-
-        if endian == "<" or endian == "=" and sys.byteorder == "little":
-            scale = -scale
-
-        file.write("%f\n".encode() % scale)
-
-        image.tofile(file)
-
-
-def read_image(path):
-    """Read image and output RGB image (0-1).
-
-    Args:
-        path (str): path to file
-
-    Returns:
-        array: RGB image (0-1)
-    """
-    img = cv2.imread(path)
-
-    if img.ndim == 2:
-        img = cv2.cvtColor(img, cv2.COLOR_GRAY2BGR)
-
-    img = cv2.cvtColor(img, cv2.COLOR_BGR2RGB) / 255.0
-
-    return img
-
-
-def resize_image(img):
-    """Resize image and make it fit for network.
-
-    Args:
-        img (array): image
-
-    Returns:
-        tensor: data ready for network
-    """
-    height_orig = img.shape[0]
-    width_orig = img.shape[1]
-
-    if width_orig > height_orig:
-        scale = width_orig / 384
-    else:
-        scale = height_orig / 384
-
-    height = (np.ceil(height_orig / scale / 32) * 32).astype(int)
-    width = (np.ceil(width_orig / scale / 32) * 32).astype(int)
-
-    img_resized = cv2.resize(img, (width, height), interpolation=cv2.INTER_AREA)
-
-    img_resized = (
-        torch.from_numpy(np.transpose(img_resized, (2, 0, 1))).contiguous().float()
-    )
-    img_resized = img_resized.unsqueeze(0)
-
-    return img_resized
-
-
-def resize_depth(depth, width, height):
-    """Resize depth map and bring to CPU (numpy).
-
-    Args:
-        depth (tensor): depth
-        width (int): image width
-        height (int): image height
-
-    Returns:
-        array: processed depth
-    """
-    depth = torch.squeeze(depth[0, :, :, :]).to("cpu")
-
-    depth_resized = cv2.resize(
-        depth.numpy(), (width, height), interpolation=cv2.INTER_CUBIC
-    )
-
-    return depth_resized
-
-def write_depth(path, depth, bits=1):
-    """Write depth map to pfm and png file.
-
-    Args:
-        path (str): filepath without extension
-        depth (array): depth
-    """
-    write_pfm(path + ".pfm", depth.astype(np.float32))
-
-    depth_min = depth.min()
-    depth_max = depth.max()
-
-    max_val = (2**(8*bits))-1
-
-    if depth_max - depth_min > np.finfo("float").eps:
-        out = max_val * (depth - depth_min) / (depth_max - depth_min)
-    else:
-        out = np.zeros(depth.shape, dtype=depth.type)
-
-    if bits == 1:
-        cv2.imwrite(path + ".png", out.astype("uint8"))
-    elif bits == 2:
-        cv2.imwrite(path + ".png", out.astype("uint16"))
-
-    return
diff --git a/spaces/simonduerr/ProteinMPNN/af_backprop/examples/sc_hall/README.md b/spaces/simonduerr/ProteinMPNN/af_backprop/examples/sc_hall/README.md
deleted file mode 100644
index 8b137891791fe96927ad78e64b0aad7bded08bdc..0000000000000000000000000000000000000000
--- a/spaces/simonduerr/ProteinMPNN/af_backprop/examples/sc_hall/README.md
+++ /dev/null
@@ -1 +0,0 @@
-
diff --git a/spaces/simple0urra/skops-model-card-creator-2a23515a-d54e-4804-b365-27ed6e938735/example/Avara Bold A Unique and Open Source Font for Your Website.md b/spaces/simple0urra/skops-model-card-creator-2a23515a-d54e-4804-b365-27ed6e938735/example/Avara Bold A Unique and Open Source Font for Your Website.md
deleted file mode 100644
index e053bb29ea486addc32f26c984b86dae5ce75e43..0000000000000000000000000000000000000000
--- a/spaces/simple0urra/skops-model-card-creator-2a23515a-d54e-4804-b365-27ed6e938735/example/Avara Bold A Unique and Open Source Font for Your Website.md	
+++ /dev/null
@@ -1,118 +0,0 @@
-<br />
-<h1>Avara Bold Font: A Unique and Versatile Typeface</h1>
-<p>If you are looking for a font that is both modern and distinctive, you might want to check out Avara Bold. This font is a geometric sans serif that features sharp angles, straight lines, and no curves. It is designed to be eye-catching, dynamic, and adaptable. In this article, we will explore what Avara Bold font is, why you should use it, how to download it for free, and how to use it in your projects. We will also share some best practices for choosing and using fonts in general.</p>
-<h2>avara bold font free download</h2><br /><p><b><b>Download File</b> &#9658;&#9658;&#9658;&#9658;&#9658; <a href="https://ssurll.com/2uNYqz">https://ssurll.com/2uNYqz</a></b></p><br /><br />
- <h2>What is Avara Bold Font?</h2>
-<p>Avara Bold font is a typeface created by Raphaël Bastide, a French graphic designer and artist. He started working on it in 2016 as a personal project, inspired by his interest in typography and geometry. He wanted to create a font that was based on simple shapes and had no curves at all. He also wanted to make it open source, so anyone could use it or modify it as they wish.</p>
-<p>The result is Avara Bold, a font that consists of only straight lines and angles. It has a futuristic and minimalist look, but also a playful and expressive feel. It has uppercase and lowercase letters, numbers, punctuation marks, symbols, and some special characters. It supports multiple languages, including Latin, Greek, Cyrillic, Hebrew, Arabic, Thai, and more. It also has some stylistic alternates and ligatures that add some variety and flair.</p>
- <h3>Why Use Avara Bold Font?</h3>
-<p>There are many reasons why you might want to use Avara Bold font for your design projects. Here are some of them:</p>
-<ul>
-<li>It is unique and original. There are not many fonts that have no curves at all. Avara Bold stands out from the crowd with its geometric and angular design. It can help you create a memorable impression and a strong identity.</li>
-<li>It is versatile and adaptable. You can use Avara Bold for various purposes, such as logos, headlines, posters, banners, flyers, brochures, websites, apps, games, etc. It can work well with different themes, such as technology, science fiction, music, art, sports, etc. It can also match well with other fonts, especially those that have curves or rounded shapes.</li>
-<li>It is free and open source. You can download Avara Bold font for free from various websites (see below). You can also modify it or create your own version of it using the source files available on GitHub. <h4>How to Download Avara Bold Font for Free?</h4>
-<p>If you are interested in using Avara Bold font for your projects, you will be glad to know that you can download it for free from various websites. Here are some of the sources where you can find and download Avara Bold font:</p>
-<ul>
-<li>[Cufon Fonts](^1^): This website offers a wide range of free fonts for desktop and web use. You can download Avara Bold font as a zip file that contains the font files in TTF and OTF formats, as well as a @font-face kit that you can use to embed the font on your website.</li>
-<li>[Font Library](^2^): This website is a collection of open source fonts that you can use for any purpose. You can download Avara Bold font as a zip file that contains the font files in TTF, OTF, WOFF, and SVG formats, as well as a CSS file that you can use to link the font on your website.</li>
-<li>[Free Fonts](^3^): This website is a directory of free fonts that you can browse and download. You can download Avara Bold font as a zip file that contains the font files in TTF and OTF formats.</li>
-</ul>
-<p>Alternatively, you can also download Avara Bold font from its official GitHub repository, where you can also find the source files and the license information.</p>
- <h4>How to Install Avara Bold Font on Your Device?</h4>
-<p>Once you have downloaded Avara Bold font, you will need to install it on your device before you can use it in your projects. The installation process may vary depending on your operating system, but here are some general steps that you can follow:</p>
-<ul>
-<li>Extract the zip file that contains the font files to a folder on your device.</li>
-<li>For Windows users: Right-click on the font file (TTF or OTF) and select "Install". Alternatively, you can also copy and paste the font file to the Fonts folder in the Control Panel.</li>
-<li>For Mac users: Double-click on the font file (TTF or OTF) and click on "Install Font". Alternatively, you can also drag and drop the font file to the Fonts folder in the Library.</li>
-<li>For Linux users: Copy and paste the font file (TTF or OTF) to the ~/.fonts folder in your home directory. Alternatively, you can also use a font manager application to install the font.</li>
-</ul>
-<p>After installing the font, you may need to restart your device or your applications for the changes to take effect.</p>
- <h4>How to Use Avara Bold Font in Your Projects?</h4>
-<p>Now that you have installed Avara Bold font on your device, you can start using it in your projects. Here are some tips and examples on how to apply the font in different design scenarios:</p>
-<ul>
-<li>If you want to use Avara Bold font for your logo, headline, or poster, you can make it stand out by using a large font size, a bright color, or a gradient effect. You can also combine it with a curved or rounded font for contrast and balance.</li>
-<li>If you want to use Avara Bold font for your website, app, or game, you can make it look sleek and futuristic by using a dark background, a neon glow, or a 3D effect. You can also pair it with a sans serif or monospaced font for readability and consistency.</li>
-<li>If you want to use Avara Bold font for your flyer, brochure, or magazine, you can make it look dynamic and expressive by using different stylistic alternates and ligatures. You can also mix it with a serif or script font for elegance and flair.</li>
-</ul>
-<p>Here are some examples of how Avara Bold font looks like in different design contexts:</p>
-<p>avara bold font for web design<br />
-avara bold font open source<br />
-avara bold font character set<br />
-avara bold font similar fonts<br />
-avara bold font test drive<br />
-avara bold font embed code<br />
-avara bold font license<br />
-avara bold font no curve<br />
-avara bold font opentype<br />
-avara bold font commercial use<br />
-avara bold font cufonfonts<br />
-avara bold font fontlibrary<br />
-avara bold font free-fonts<br />
-avara bold font serif style<br />
-avara bold font square grid<br />
-avara bold font transitional serif<br />
-avara bold font curveless font<br />
-avara bold font libre font<br />
-avara bold font based on grid<br />
-avara bold font desktop and webfont<br />
-how to download avara bold font<br />
-where to download avara bold font<br />
-best sites to download avara bold font<br />
-how to install avara bold font<br />
-how to use avara bold font<br />
-how to customize avara bold font<br />
-how to pair avara bold font with other fonts<br />
-how to create logos with avara bold font<br />
-how to make posters with avara bold font<br />
-how to design websites with avara bold font<br />
-examples of avara bold font in use<br />
-reviews of avara bold font by users<br />
-benefits of using avara bold font for your projects<br />
-drawbacks of using avara bold font for your projects<br />
-alternatives to using avara bold font for your projects<br />
-tips and tricks for using avara bold font effectively<br />
-tutorials and guides for using avara bold font creatively<br />
-history and origin of avara bold font<br />
-inspiration and ideas for using avara bold font beautifully<br />
-fonts that complement and contrast with avara bold font</p>
- <table border="1">
-<tr><td><img src="https://i.imgur.com/8QXyf0u.png" alt="Logo example"></td><td><img src="https://i.imgur.com/5VzGx9w.png" alt="Website example"></td></tr>
-<tr><td><img src="https://i.imgur.com/9bOZM7o.png" alt="Flyer example"></td><td><img src="https://i.imgur.com/8lHqj6n.png" alt="Magazine example"></td></tr>
-</table> <h2>Best Practices for Choosing and Using Fonts</h2>
-<p>Avara Bold font is a great choice for many design projects, but it is not the only font that you can use. There are thousands of fonts available online, and each one has its own characteristics, strengths, and weaknesses. How do you choose and use fonts effectively? Here are some best practices that you can follow:</p>
- <h3>Know Your Font's Purpose and Audience</h3>
-<p>The first thing you need to consider when choosing a font is the purpose and the audience of your design project. What are you trying to communicate? Who are you trying to reach? Different fonts can convey different messages, emotions, and tones. For example, a serif font can look formal, elegant, and traditional, while a sans serif font can look modern, clean, and simple. A script font can look fancy, artistic, and romantic, while a display font can look fun, quirky, and creative. You need to choose a font that matches the goal and the target of your design project.</p>
- <h3>Plan for a Pair or a Family of Fonts</h3>
-<p>The second thing you need to consider when choosing a font is the number and the variety of fonts that you will use. Unless you are going for a minimalist or monochromatic style, you will probably need more than one font for your design project. You will need to pair or group fonts that complement each other and create contrast and harmony. For example, you can pair a bold and geometric font with a light and rounded font, or a serif font with a sans serif font. You can also use a family of fonts that share the same design features but have different weights, widths, or styles. You need to plan for a pair or a family of fonts that work well together and create interest and balance.</p>
- <h3>Look for Readability and Legibility</h3>
-<p>The third thing you need to consider when choosing a font is the readability and the legibility of the font. Readability refers to how easy it is to read and understand the text as a whole, while legibility refers to how easy it is to recognize and distinguish the individual letters or characters. Different fonts have different levels of readability and legibility, depending on their size, shape, spacing, alignment, color, etc. For example, a small or thin font can be hard to read on a screen or from a distance, while a complex or decorative font can be hard to recognize or distinguish from other fonts. You need to choose a font that is readable and legible for your design project.</p> <h3>Avoid Too Many or Too Trendy Fonts</h3>
-<p>The fourth thing you need to consider when choosing a font is the quantity and the quality of the fonts that you will use. While it is tempting to use many or trendy fonts for your design project, you should be careful not to overdo it or follow the crowd. Using too many fonts can make your design look cluttered, chaotic, and confusing, while using too trendy fonts can make your design look outdated, generic, and boring. You need to avoid too many or too trendy fonts for your design project.</p>
- <h3>Create High Contrast and Visual Hierarchy</h3>
-<p>The fifth thing you need to consider when choosing a font is the contrast and the hierarchy of the fonts that you will use. Contrast refers to how different the fonts are from each other and from the background, while hierarchy refers to how important the fonts are in relation to each other and to the content. Using different font sizes, weights, colors, etc. can help you create contrast and hierarchy in your design. For example, you can use a large and bold font for your headline, a medium and regular font for your subheadings, and a small and light font for your body text. You can also use different colors or effects to highlight or emphasize certain words or phrases. You need to create high contrast and visual hierarchy for your design project.</p>
- <h3>Break the Rules Occasionally</h3>
-<p>The sixth and final thing you need to consider when choosing a font is your own creativity and intuition. While it is good to follow some rules and guidelines when choosing and using fonts, it is also good to break them occasionally and try something new or different. Experimenting with fonts can help you discover new possibilities and solutions for your design project. You can also express your own personality and style with fonts. You need to break the rules occasionally and have fun with fonts.</p>
- <h2>Conclusion and FAQs</h2>
-<p>In conclusion, Avara Bold font is a unique and versatile typeface that features sharp angles, straight lines, and no curves. It is designed to be eye-catching, dynamic, and adaptable. You can use it for various purposes, such as logos, headlines, posters, websites, apps, games, etc. You can also download it for free from various websites or from its official GitHub repository. You can install it on your device and use it in your projects with some tips and examples that we have shared in this article.</p>
-<p>We hope that this article has helped you learn more about Avara Bold font and how to choose and use fonts in general. If you have any questions or comments, feel free to leave them below. Here are some frequently asked questions that you might find useful:</p>
- <h4>What is the difference between Avara Bold and Avara?</h4>
-<p>Avara Bold is a variant of Avara, which is the original version of the font created by Raphaël Bastide. Avara Bold has thicker strokes and more weight than Avara, which makes it more suitable for larger sizes and display purposes.</p>
- <h4>Can I use Avara Bold font for commercial projects?</h4>
-<p>Yes, you can use Avara Bold font for commercial projects without any restrictions or limitations. The font is licensed under the SIL Open Font License (OFL), which allows you to use, modify, distribute, or sell the font as long as you keep the license file with the font files.</p>
- <h4>How can I modify or create my own version of Avara Bold font?</h4>
-<p>If you want to modify or create your own version of Avara Bold font, you will need to download the source files from its GitHub repository. The source files are in UFO format, which is a universal font object format that can be opened by various font editing software. You can also find some documentation on how to work with the source files on the GitHub page.</p>
- <h4>What are some similar fonts to Avara Bold?</h4>
-<p>If you like Avara Bold font but want to try some other fonts that have a similar style or vibe, here are some suggestions:</p>
-<ul>
-<li>[Orbitron]: This is a geometric sans serif font that has a futuristic and sci-fi look. It has four weights (light, medium, bold, black) and supports Latin languages.</li>
-<li>[Kanit]: This is a geometric sans serif font that has a modern and elegant look. It has 18 styles (nine weights with matching italics) and supports Latin and Thai languages.</li>
-<li>[Bebas Neue]: This is a geometric sans serif font that has a simple and clean look. It has five weights (thin, light, book, regular, bold) and supports Latin languages.</li>
-</ul>
- <h4>Where can I find more free fonts?</h4 <p>If you are looking for more free fonts, you can browse and download them from various websites that offer a wide range of fonts for different purposes and styles. Here are some of the websites where you can find and download free fonts:</p>
-<ul>
-<li>[FontSpace](^1^): This website offers over 100,000 free fonts for desktop and web use. You can search by category, theme, designer, or popularity. You can also use their font generator to create custom fonts that you can copy and paste into your website or social media profiles.</li>
-<li>[DaFont](^2^): This website is a directory of free fonts that you can browse by alphabetical listing, style, author, or popularity. You can download fonts in zip files that contain the font files in TTF or OTF formats. You can also preview the fonts before downloading them.</li>
-<li>[Google Fonts](^3^): This website is a collection of free and open source fonts that you can use for any project. You can download fonts in zip files that contain the font files in TTF, OTF, WOFF, or SVG formats. You can also embed the fonts on your website using the provided code.</li>
-</ul>
-<p>These are just some of the websites where you can find and download free fonts. There are many more websites that offer free fonts, but be careful to check the license and the quality of the fonts before using them.</p> 401be4b1e0<br />
-<br />
-<br />
\ No newline at end of file
diff --git a/spaces/simple0urra/skops-model-card-creator-2a23515a-d54e-4804-b365-27ed6e938735/example/Blacklight Retribution - The Best Way to Enjoy Futuristic Firefights.md b/spaces/simple0urra/skops-model-card-creator-2a23515a-d54e-4804-b365-27ed6e938735/example/Blacklight Retribution - The Best Way to Enjoy Futuristic Firefights.md
deleted file mode 100644
index 7c8803b0aad0005d63e219b2bab979daf41cdab2..0000000000000000000000000000000000000000
--- a/spaces/simple0urra/skops-model-card-creator-2a23515a-d54e-4804-b365-27ed6e938735/example/Blacklight Retribution - The Best Way to Enjoy Futuristic Firefights.md	
+++ /dev/null
@@ -1,102 +0,0 @@
-
-<h1>Download Blacklight Retribution: A Free-to-Play Cyberpunk FPS</h1>
-<p>If you are looking for a fast-paced, futuristic, and action-packed first-person shooter, you should download Blacklight Retribution. This is a free-to-play game that offers a unique gameplay experience with its cyberpunk theme, advanced mechanics, and deep customization. In this article, we will tell you what Blacklight Retribution is, what features it has, what game modes it offers, how to download it, and some tips and tricks to help you get started.</p>
-<h2>download blacklight retribution</h2><br /><p><b><b>DOWNLOAD</b> &#128504;&#128504;&#128504; <a href="https://ssurll.com/2uNX04">https://ssurll.com/2uNX04</a></b></p><br /><br />
- <h2>Features of Blacklight Retribution</h2>
-<p>Blacklight Retribution is not your typical FPS. It has some distinctive features that set it apart from other games in the genre. Here are some of them:</p>
-<ul>
-<li><b>HRV:</b> This stands for Hyper Reality Visor, a device that allows you to see through walls and locate enemies, objectives, weapon depots, and more. However, using it will temporarily disable your weapon, so you have to be careful when and where you activate it.</li>
-<li><b>Weapon Depots:</b> These are stations that you can access on the battlefield to replenish your health, ammo, or buy special weapons such as rocket launchers, flamethrowers, or mechanized suits called Hardsuits. You need to earn CP (Combat Points) by killing enemies or completing objectives to use them.</li>
-<li><b>Customization:</b> You can create your own loadout with a variety of weapons, armor, and cosmetic items. You can also modify your weapons with different barrels, scopes, magazines, stocks, muzzles, and camos. You can earn GP (Game Points) by playing matches or buy ZEN (Real Money Currency) to purchase additional items.</li>
-</ul>
- <h2>Game Modes of Blacklight Retribution</h2>
-<p>Blacklight Retribution has several game modes that cater to different preferences and playstyles. Here are some of them:</p>
-<ul>
-<li><b>Deathmatch:</b> This is a free-for-all mode where you have to fight for yourself and kill as many enemies as possible. <li><b>Team Deathmatch:</b> This is a team-based mode where you have to work with your teammates and eliminate the opposing team.</li>
-<li><b>Capture the Flag:</b> This is a classic mode where you have to steal the enemy's flag and bring it back to your base while preventing them from doing the same.</li>
-<li><b>Domination:</b> This is a mode where you have to capture and hold strategic points on the map to reduce the enemy's tickets. The team with the most tickets at the end of the match wins.</li>
-<li><b>King of the Hill:</b> This is a mode where you have to control a single point on the map for as long as possible. The team with the most time on the point wins.</li>
-<li><b>Kill Confirmed:</b> This is a mode where you have to collect tokens from your dead opponents to score points for your team. The team with the most points at the end of the match wins.</li>
-<li><b>OnSlaught:</b> This is a co-op mode where you have to survive waves of zombies with your teammates. You can use weapon depots and HRV to help you fend off the undead horde.</li>
-<li><b>Siege Mode:</b> This is a mode where you have to escort a tank to the enemy's base while defending it from attacks. The tank can be controlled by a player or an AI. The team that successfully delivers the tank or prevents the enemy from doing so wins.</li>
-</ul>
- <h2>How to Download Blacklight Retribution</h2>
-<p>If you are interested in playing Blacklight Retribution, here are the steps you need to follow to download it:</p>
-<p>How to download blacklight retribution for free<br />
-Blacklight retribution download size<br />
-Blacklight retribution download steam<br />
-Blacklight retribution download pc<br />
-Blacklight retribution download windows 10<br />
-Blacklight retribution download full version<br />
-Blacklight retribution download offline<br />
-Blacklight retribution download utorrent<br />
-Blacklight retribution download mac<br />
-Blacklight retribution download apk<br />
-Blacklight retribution download android<br />
-Blacklight retribution download ps4<br />
-Blacklight retribution download xbox one<br />
-Blacklight retribution download link<br />
-Blacklight retribution download crack<br />
-Blacklight retribution download highly compressed<br />
-Blacklight retribution download update<br />
-Blacklight retribution download error<br />
-Blacklight retribution download requirements<br />
-Blacklight retribution download speed<br />
-Blacklight retribution download mods<br />
-Blacklight retribution download maps<br />
-Blacklight retribution download skins<br />
-Blacklight retribution download weapons<br />
-Blacklight retribution download cheats<br />
-Blacklight retribution download hacks<br />
-Blacklight retribution download trainer<br />
-Blacklight retribution download patch<br />
-Blacklight retribution download launcher<br />
-Blacklight retribution download server<br />
-Blacklight retribution download client<br />
-Blacklight retribution download reddit<br />
-Blacklight retribution download review<br />
-Blacklight retribution download gameplay<br />
-Blacklight retribution download guide<br />
-Blacklight retribution download tips<br />
-Blacklight retribution download tricks<br />
-Blacklight retribution download tutorial<br />
-Blacklight retribution download walkthrough<br />
-Blacklight retribution download wiki<br />
-Download blacklight retribution online free<br />
-Download blacklight retribution latest version <br />
-Download blacklight retribution from mediafire <br />
-Download blacklight retribution from cnet <br />
-Download blacklight retribution from steam community <br />
-Download blacklight retribution for windows 7 <br />
-Download blacklight retribution for windows 8 <br />
-Download blacklight retribution for windows 8.1 <br />
-Download blacklight retribution for linux <br />
-Download blacklight retribution for mac os x</p>
-<ol>
-<li><b>Go to the official website or the Steam page of the game:</b> You can find the links to both sites at the end of this article. You can choose either option depending on your preference.</li>
-<li><b>Create an account or log in with your existing one:</b> You will need an account to play Blacklight Retribution. You can create one for free on either site or use your existing Steam account if you choose that option.</li>
-<li><b>Download and install the game client:</b> You will need to download and install the game client on your computer. The download size is about 5 GB, so make sure you have enough space and a stable internet connection.</li>
-<li><b>Launch the game and enjoy:</b> Once you have installed the game, you can launch it from your desktop or Steam library and start playing. You can choose from different servers and regions depending on your location and ping.</li>
-</ol>
- <h2>Tips and Tricks for Blacklight Retribution</h2>
-<p>To help you get started with Blacklight Retribution, here are some tips and tricks that you should keep in mind:</p>
-<ul>
-<li><b>Use your HRV wisely and avoid being exposed:</b> Your HRV is a powerful tool that can give you an edge over your enemies, but it also has some drawbacks. It will disable your weapon while active, so make sure you are in a safe spot before using it. It will also reveal your position to other players using HRV, so be careful not to expose yourself too much.</li>
-<li><b>Experiment with different weapons and attachments to find your preferred style:</b> There are many weapons and attachments in Blacklight Retribution that you can use to customize your loadout. You can try them out in the training mode or rent them for a limited time with GP. Find out what works best for you and suits your playstyle.</li>
-<li><b>Communicate and coordinate with your teammates for better results:</b> Blacklight Retribution is a team-based game, so communication and coordination are essential for success. You can use voice chat or text chat to communicate with your teammates and share information, strategies, and requests. You can also use pings and markers to indicate enemies, objectives, and weapon depots.</li>
-<li><b>Use cover and movement to avoid being an easy target:</b> Blacklight Retribution is a fast-paced game, so staying still is not a good idea. You should always use cover and movement to avoid being an easy target for your enemies. You can crouch, slide, sprint, jump, and mantle over obstacles to evade fire and surprise your foes.</li>
-<li><b>Spend your GP wisely and save up for the items you want:</b> GP is the currency that you earn by playing matches in Blacklight Retribution. You can use it to buy or rent items from the store or customize your loadout. However, GP is not easy to come by, so you should spend it wisely and save up for the items you really want. You can also earn additional GP by completing daily missions or achievements.</li>
-</ul>
- <h2>Conclusion and FAQs</h2>
-<p>Blacklight Retribution is a fun and exciting FPS that you can download for free and enjoy with your friends or other players online. It has a unique cyberpunk theme, advanced mechanics, and deep customization that make it stand out from other games in the genre. If you are looking for a new and thrilling shooter experience, you should give Blacklight Retribution a try.</p>
-<p>Here are some FAQs that you might have about the game:</p>
-<table>
-<tr><td><b>Q:</b> Is Blacklight Retribution still active?</td><td><b>A:</b> Yes, Blacklight Retribution is still active and has a loyal fanbase. However, the game is no longer supported by the original developers, Hardsuit Labs, and is now maintained by a community-run team called BLR: Phoenix.</td></tr>
-<tr><td><b>Q:</b> What are the system requirements for Blacklight Retribution?</td><td><b>A:</b> The minimum system requirements for Blacklight Retribution are: Windows 7 64-bit, Intel Core 2 Duo E6750 or AMD Athlon X2 6400+, 4 GB RAM, NVIDIA GeForce GTX 260 or ATI Radeon HD 4870, DirectX 9.0c compatible sound card, and 8 GB available hard drive space.</td></tr>
-<tr><td><b>Q:</b> How can I get ZEN in Blacklight Retribution?</td><td><b>A:</b> ZEN is the real money currency in Blacklight Retribution that you can use to buy premium items from the store. You can get ZEN by purchasing it with your credit card, PayPal, or other payment methods on the official website or the Steam page of the game.</td></tr>
-<tr><td><b>Q:</b> How can I join a clan in Blacklight Retribution?</td><td><b>A:</b> A clan is a group of players who share a common name, tag, and chat channel in Blacklight Retribution. You can join a clan by applying to one on the official website or the Steam page of the game, or by creating your own clan with GP or ZEN.</td></tr>
-<tr><td><b>Q:</b> How can I report a hacker or cheater in Blacklight Retribution?</td><td><b>A:</b> If you encounter a hacker or cheater in Blacklight Retribution, you can report them by using the in-game report function or by sending an email to support@blacklightretribution.com with evidence such as screenshots or videos.</td></tr>
-</table>
- <p>I hope you found this article helpful and informative. If you have any questions or feedback, feel free to leave a comment below. Thank you for reading and have fun playing Blacklight Retribution!</p> 401be4b1e0<br />
-<br />
-<br />
\ No newline at end of file
diff --git a/spaces/simple0urra/skops-model-card-creator-2a23515a-d54e-4804-b365-27ed6e938735/example/Download Mod Township 7.3 5 and Explore a World of Possibilities in this Game.md b/spaces/simple0urra/skops-model-card-creator-2a23515a-d54e-4804-b365-27ed6e938735/example/Download Mod Township 7.3 5 and Explore a World of Possibilities in this Game.md
deleted file mode 100644
index 36e417fa58f9c6402a9d760d467ce20db19b86c4..0000000000000000000000000000000000000000
--- a/spaces/simple0urra/skops-model-card-creator-2a23515a-d54e-4804-b365-27ed6e938735/example/Download Mod Township 7.3 5 and Explore a World of Possibilities in this Game.md	
+++ /dev/null
@@ -1,178 +0,0 @@
-
-<h1>Download Mod Township 7.3 5: A Guide for Android Users</h1>
-<p>Township is a popular casual game that combines city-building and farming elements. You can create your dream town, harvest crops, process them at your factories, trade with exotic countries, run your own zoo, and more. But what if you want to enjoy the game without any limitations or restrictions? That's where mod Township 7.3 5 comes in.</p>
-<h2>download mod township 7.3 5</h2><br /><p><b><b>Download Zip</b> &#10042;&#10042;&#10042; <a href="https://ssurll.com/2uNU3V">https://ssurll.com/2uNU3V</a></b></p><br /><br />
-<p>Mod Township 7.3 5 is a modified version of the original game that gives you unlimited money, unlimited cash, and other benefits. You can build your town faster, unlock all buildings and decorations, expand your land, and have more fun. In this article, we will show you how to download and install mod Township 7.3 5 on your Android device. We will also discuss the benefits and risks of using modded apps in general.</p>
- <h2>What is Township?</h2>
-<p>Township is a game developed by Playrix that was released in 2012. It is available on multiple platforms, including iOS, Android, Windows, Mac, and Facebook. The game has over 100 million downloads on Google Play Store and has a rating of 4.6 out of 5 stars.</p>
-<p>The game features:</p>
-<ul>
-<li>Different buildings and decorations you can use to create your dream town</li>
-<li>Various crops to grow and later process at your factories</li>
-<li>Fun, charismatic townspeople with orders you need to fill</li>
-<li>Your town's mine packed with ancient artifacts to discover and collect</li>
-<li>Lovely animals to take care of</li>
-<li>Farms to manage and expand</li>
-<li>Exotic goods brought from islands</li>
-<li>A zoo to build where you can even breed animals</li>
-<li>Country flags and famous landmarks you can use to decorate your town, like the Statue of Liberty, Big Ben, and many more</li>
-<li>Play with your Facebook and Google+ friends, make new friends in the game community create your own clans</li>
-</ul>
- <h2>What is Mod Township 7.3 5?</h2>
-<p>Mod Township 7.3 5 is a hacked version of the original game that gives you some extra features that are not available in the official version. These features include:</p>
-<ul>
-<li>Unlimited money: You can buy anything you want without worrying about running out of coins</li>
-<li>Unlimited cash: You can speed up any process or task without spending real money</li <p>- No ads: You can enjoy the game without any annoying ads or pop-ups</li>
-<li>- All buildings and decorations unlocked: You can access all the items in the game without any level or cash requirements</li>
-<li>- All land expansions unlocked: You can expand your town as much as you want without any coins or materials needed</li>
-</ul>
-<p>Mod Township 7.3 5 is based on the latest version of the game, which is 7.3.5. It was released on June 8, 2023 and has a size of 147 MB. It requires Android 4.2 and up to run.</p>
-<p>download mod township 7.3 5 unlimited money<br />
-download mod township 7.3 5 apk<br />
-download mod township 7.3 5 latest version<br />
-download mod township 7.3 5 android<br />
-download mod township 7.3 5 free<br />
-download mod township 7.3 5 hack<br />
-download mod township 7.3 5 offline<br />
-download mod township 7.3 5 for pc<br />
-download mod township 7.3 5 ios<br />
-download mod township 7.3 5 no root<br />
-download mod township 7.3 5 online<br />
-download mod township 7.3 5 unlimited cash<br />
-download mod township 7.3 5 obb<br />
-download mod township 7.3 5 update<br />
-download mod township 7.3 5 full version<br />
-download mod township 7.3 5 cheats<br />
-download mod township 7.3 5 mega mod<br />
-download mod township 7.3 5 revdl<br />
-download mod township 7.3 5 rexdl<br />
-download mod township 7.3 5 data<br />
-download mod township game for android<br />
-download mod township game apk<br />
-download mod township game latest version<br />
-download mod township game unlimited money<br />
-download mod township game hack<br />
-how to download mod township game<br />
-how to install mod township game<br />
-how to play mod township game<br />
-how to update mod township game<br />
-how to use mod township game<br />
-best site to download mod township game<br />
-best way to download mod township game<br />
-safe site to download mod township game<br />
-safe way to download mod township game<br />
-easy way to download mod township game<br />
-fast way to download mod township game<br />
-free site to download mod township game<br />
-free way to download mod township game<br />
-working link to download mod township game<br />
-working method to download mod township game</p>
- <h2>How to Download and Install Mod Township 7.3 5?</h2>
-<p>If you want to download and install mod Township 7.3 5 on your Android device, you will need two files: the mod apk file and the obb file. The mod apk file is the modified application file that contains the game code and the mod features. The obb file is the data file that contains the game graphics and sounds. You will need to download both files and install them correctly on your device. Here are the steps to follow:</p>
- <h3>Step 1: Enable Unknown Sources</h3>
-<p>Before you can install any app that is not from the Google Play Store, you need to enable unknown sources on your device. This will allow you to install apps from outside sources without any security issues. To enable unknown sources, follow these steps:</p>
-<ol>
-<li>Go to your device settings and tap on security or privacy</li>
-<li>Find the option that says unknown sources or install unknown apps and toggle it on</li>
-<li>A warning message will pop up, tap on OK to confirm</li>
-</ol>
-<p>You have now enabled unknown sources on your device and you can proceed to the next step.</p>
- <h3>Step 2: Download the Mod APK File</h3>
-<p>The next step is to download the mod apk file of Township 7.3 5. You can find many websites that offer this file, but be careful as some of them may contain viruses or malware. We recommend using a trusted source like [this one] that provides a safe and fast download link.</p>
-<p>To download the mod apk file, follow these steps:</p>
-<ol>
-<li>Open your browser and go to [this website]</li>
-<li>Scroll down and find the download button that says "Download Mod APK"</li>
-<li>Tap on it and wait for the download to start</li>
-<li>Once the download is complete, you will see a notification on your device</li>
-</ol>
-<p>You have now downloaded the mod apk file of Township 7.3 5 and you can proceed to the next step.</p>
- <h3>Step 3: Install the Mod APK File</h3>
-<p>The next step is to install the mod apk file of Township 7.3 5 on your device. To do this, follow these steps:</p>
-<ol>
-<li>Open your file manager and locate the mod apk file that you downloaded in the previous step</li>
-<li>Tap on it and a pop-up window will appear asking you to install the app</li>
-<li>Tap on install and wait for the installation to finish</li <li>Once the installation is done, you will see a message that says "App installed"</li>
-<li>Tap on open to launch the app or tap on done to exit the window</li>
-</ol>
-<p>You have now installed the mod apk file of Township 7.3 5 on your device and you can proceed to the next step.</p>
- <h3>Step 4: Download and Extract the OBB File</h3>
-<p>The next step is to download and extract the obb file of Township 7.3 5. The obb file is the data file that contains the game graphics and sounds. You will need to download this file and place it in the right folder on your device. To do this, follow these steps:</p>
-<ol>
-<li>Open your browser and go to [this website] again</li>
-<li>Scroll down and find the download button that says "Download OBB"</li>
-<li>Tap on it and wait for the download to start</li>
-<li>Once the download is complete, you will see a notification on your device</li>
-<li>Open your file manager and locate the obb file that you downloaded in the previous step</li>
-<li>Tap on it and a pop-up window will appear asking you to extract the file</li>
-<li>Tap on extract and choose a destination folder</li>
-<li>You need to extract the file to the folder named "Android/obb" on your device storage</li>
-<li>If you don't have this folder, you can create it manually</li>
-<li>Once the extraction is done, you will see a message that says "Extraction completed"</li>
-</ol>
-<p>You have now downloaded and extracted the obb file of Township 7.3 5 and you can proceed to the next step.</p>
- <h3>Step 5: Launch the Game and Enjoy</h3>
-<p>The final step is to launch the game and enjoy the modded version of Township 7.3 5. To do this, follow these steps:</p>
-<ol>
-<li>Go back to your home screen and find the app icon of Township</li>
-<li>Tap on it and wait for the game to load</li <li>You will see a welcome screen that says "Township 7.3 5 Mod"</li>
-<li>Tap on continue and choose your language</li>
-<li>You will see a tutorial that explains the basics of the game</li>
-<li>You can skip the tutorial or follow it as you wish</li>
-<li>You will see your town with unlimited money and cash</li>
-<li>You can start building your town as you like</li>
-<li>You can also access the settings, achievements, friends, and other features from the menu</li>
-</ol>
-<p>Congratulations! You have successfully downloaded and installed mod Township 7.3 5 on your Android device. You can now enjoy the game with unlimited resources and features.</p>
- <h2>What are the Benefits and Risks of Mod APKs?</h2>
-<p>Mod APKs are modified versions of original apps that offer some extra features or advantages that are not available in the official versions. They are usually created by third-party developers or hackers who modify the app code and data. Mod APKs can be very tempting for users who want to get more out of their apps, but they also come with some risks and drawbacks. Let's compare the benefits and risks of mod APKs in general.</p>
- <h3>Benefits of Mod APKs</h3>
-<p>Some of the benefits of using mod APKs are:</p>
-<ul>
-<li>You can get unlimited resources, such as money, gems, coins, lives, etc.</li>
-<li>You can unlock all features, levels, characters, items, etc.</li>
-<li>You can customize your app according to your preferences</li>
-<li>You can bypass ads, in-app purchases, and other restrictions</li>
-<li>You can access premium or paid features for free</li>
-<li>You can have more fun and excitement with your app</li>
-</ul>
- <h3>Risks of Mod APKs</h3>
-<p>Some of the risks of using mod APKs are:</p>
-<ul>
-<li>You can get malware, viruses, or spyware on your device</li>
-<li>You can lose your personal data or information to hackers or scammers</li <li>You can get banned from your app or account for violating the terms of service</li>
-<li>You can face legal issues or lawsuits for infringing the intellectual property rights of the app developers or owners</li>
-<li>You can miss out on the updates, bug fixes, and new features of the official app</li>
-<li>You can ruin the balance, challenge, and fun of the original app</li>
-</ul>
-<p>As you can see, mod APKs have both pros and cons. You should weigh them carefully before deciding to use them. You should also be aware of the sources and quality of the mod APKs you download and install. Not all mod APKs are safe and reliable. You should always scan them for viruses and malware before installing them. You should also backup your data and device before using them. And you should always use them at your own risk and responsibility.</p>
- <h2>Conclusion</h2>
-<p>In this article, we have shown you how to download and install mod Township 7.3 5 on your Android device. We have also discussed the benefits and risks of using modded apps in general. Mod Township 7.3 5 is a modified version of the original game that gives you unlimited money, cash, and other features. You can build your dream town faster, unlock all buildings and decorations, expand your land, and have more fun. However, you should also be careful of the potential dangers and drawbacks of using modded apps, such as malware, data theft, account ban, and legal issues. You should always use modded apps with caution and discretion.</p>
-<p>If you found this article helpful, please share it with your friends and family who might be interested in downloading mod Township 7.3 5. If you have any questions or feedback, please leave a comment below. We would love to hear from you. Thank you for reading and happy gaming!</p>
- <h2>FAQs</h2>
-<p>Here are some frequently asked questions and answers about mod Township 7.3 5:</p>
-<ol>
-<li>Q: Is mod Township 7.3 5 safe to use?</li>
-<li>A: Mod Township 7.3 5 is not an official app from Playrix, the developer of Township. It is a hacked version created by third-party developers or hackers who may have malicious intentions. Therefore, it is not guaranteed to be safe or secure to use. You may encounter viruses, malware, spyware, data theft, account ban, or legal issues when using it. You should always scan the files for viruses and malware before installing them. You should also backup your data and device before using them. And you should always use them at your own risk and responsibility.</li>
-<li>Q: How do I update mod Township 7.3 5?</li>
-<li>A: Mod Township 7.3 5 is based on the latest version of the game, which is 7.3.5 as of June 8, 2023. If there is a new update for the game, you will need to wait for the modders to release a new version of the mod APK and OBB files that are compatible with the update. You will then need to download and install them again following the same steps as before. However, there is no guarantee that the modders will update their files regularly or at all. You may miss out on the updates, bug fixes, and new features of the official app if you use the modded version.</li <li>Q: Can I play mod Township 7.3 5 with my friends?</li>
-<li>A: Mod Township 7.3 5 allows you to play with your Facebook and Google+ friends, make new friends in the game community, and create your own clans. However, you should be aware that your friends may not have the same modded version as you, and they may not be able to see your town or interact with you in the same way as in the official version. You may also face some compatibility issues or errors when playing online with other players. You should also respect the rules and etiquette of the game community and avoid cheating or exploiting the game.</li>
-<li>Q: What are some alternatives to mod Township 7.3 5?</li>
-<li>A: If you are looking for some alternatives to mod Township 7.3 5, you may want to try some other similar games that offer city-building and farming elements. Some of these games are:</li>
-<ul>
-<li>FarmVille 2: Country Escape: A sequel to the popular FarmVille game that lets you build your own farm, harvest crops, craft goods, trade with friends, and explore new areas</li>
-<li>SimCity BuildIt: A simulation game that lets you create and manage your own city, deal with disasters, trade with other players, and compete in challenges</li>
-<li>Hay Day: A farming game that lets you grow and customize your own farm, trade with neighbors, fulfill orders, and discover new lands</li>
-<li>City Island 5: A city-building game that lets you create and expand your own island city, collect rewards, unlock new buildings, and visit other players' islands</li>
-</ul>
-<li>Q: How do I uninstall mod Township 7.3 5?</li>
-<li>A: If you want to uninstall mod Township 7.3 5 from your device, you can follow these steps:</li>
-<ol>
-<li>Go to your device settings and tap on apps or applications</li>
-<li>Find and tap on Township</li <li>Tap on uninstall and confirm your choice</li>
-<li>Wait for the uninstallation to finish</li>
-<li>Go to your file manager and delete the mod apk and obb files that you downloaded and installed before</li>
-</ol>
-<p>You have now uninstalled mod Township 7.3 5 from your device and you can install the official version of the game from the Google Play Store if you want.</p> 197e85843d<br />
-<br />
-<br />
\ No newline at end of file
diff --git a/spaces/simple0urra/skops-model-card-creator-2a23515a-d54e-4804-b365-27ed6e938735/example/Enjoy PUBG Mobile 2.5 on Android Without VPN Heres How to Download and Install.md b/spaces/simple0urra/skops-model-card-creator-2a23515a-d54e-4804-b365-27ed6e938735/example/Enjoy PUBG Mobile 2.5 on Android Without VPN Heres How to Download and Install.md
deleted file mode 100644
index 048a8cf02cc027b740a8d3aa1e812a6e564ddc4d..0000000000000000000000000000000000000000
--- a/spaces/simple0urra/skops-model-card-creator-2a23515a-d54e-4804-b365-27ed6e938735/example/Enjoy PUBG Mobile 2.5 on Android Without VPN Heres How to Download and Install.md	
+++ /dev/null
@@ -1,153 +0,0 @@
-<br />
-<h1>How to Download PUBG Mobile 2.5 Without VPN</h1>
-<p>PUBG Mobile is one of the most popular and addictive battle royale games in the world, with millions of players enjoying its thrilling gameplay and graphics. However, some players may face difficulties in accessing the latest version of the game, PUBG Mobile 2.5, due to various reasons such as regional restrictions, network issues, or device compatibility.</p>
-<p>If you are one of those players who want to download and play PUBG Mobile 2.5 without using a VPN, then you are in luck. In this article, we will show you how to do that in a few simple steps. We will also explain what PUBG Mobile 2.5 is and why you need it, as well as how to play it without VPN and avoid its risks and disadvantages.</p>
-<h2>download pubg mobile 2.5 without vpn</h2><br /><p><b><b>Download File</b> &#8250;&#8250;&#8250;&#8250;&#8250; <a href="https://ssurll.com/2uNZAH">https://ssurll.com/2uNZAH</a></b></p><br /><br />
-<h2>What is PUBG Mobile 2.5 and Why You Need It</h2>
-<p>PUBG Mobile 2.5 is the second major update of 2023, and it is set to bring tons of new content and features to the game. The update also coincides with the fifth anniversary of PUBG Mobile, so players can expect some free rewards and special events soon.</p>
-<h3>New Features and Content in PUBG Mobile 2.5</h3>
-<p>Here is a quick summary of everything new that is coming to PUBG Mobile 2.5 next month:</p>
-<ul>
-<li><b>New item - Block Cover:</b> The new item will be discoverable in crates across the maps. Block Covers can be used to spawn defensive walls and can also be creatively used to form bridges or elevators.</li>
-<li><b>New item - Portable Trampoline:</b> The Portable Trampoline will allow players to gain vertical height, and the item can be found anywhere on the map.</li>
-<li><b>New item - Portable Cannon:</b> The Portable Cannon will spawn throughout Erangel, and it can be used to launch not just projectiles from a distance, but can also throw players across long distances.</li>
-<li><b>5th anniversary event:</b> Players can expect free cosmetics and special game modes that will be available as part of the update. Krafton has kept details about the anniversary rewards under wraps so far, but we will learn more in the coming weeks.</li>
-<li><b>Bugatti collab event:</b> PUBG is set to collaborate with carmaker Bugatti as part of the fifth-year anniversary celebrations next month.</li>
-</ul>
-<h3>Benefits of Playing PUBG Mobile 2.5</h3>
-<p>Playing PUBG Mobile 2.5 has many benefits for players, such as:</p>
-<ul>
-<li><b>Enhanced gameplay experience:</b> With new items, maps, events, and collaborations, players can enjoy a more diverse and exciting gameplay experience in PUBG Mobile 2.5.</li>
-<li><b>Better performance and stability:</b> The update also brings some improvements and optimizations to the game's performance and stability, making it run smoother and faster on various devices.</li>
-<li><b>More rewards and achievements:</b> By playing PUBG Mobile 2.5, players can earn more rewards and achievements, such as BP, AG, skins, outfits, emotes, titles, medals, and more.</li>
-<li><b>More fun and challenge:</b> Playing PUBG Mobile 2.5 also offers more fun and challenge for players who want to test their skills and strategies against other players in the game.</li>
-</ul>
-<h2>How to Download PUBG Mobile 2.5 APK File</h2>
-<p>If you want to download PUBG Mobile 2.5 without VPN, you will need to get the APK file of the game from a reliable source. The APK file is a package file that contains the installation files and data of the game. Here are the steps to download PUBG Mobile 2.5 APK file:</p>
-<h3>Step 1: Find a Reliable Source for the APK File</h3>
-<p>The first step is to find a trustworthy and safe website that offers the PUBG Mobile 2.5 APK file for download. You can use Google or any other search engine to look for such websites, but make sure to check their reviews and ratings before downloading anything. Some of the websites that we recommend are:</p>
-<ul>
-<li><a href="">APKPure.com</a></li>
-<li><a href="">APKMody.io</a></li>
-<li><a href="">TapTap.com</a></li>
-</ul>
-<p>These websites are known for providing authentic and updated APK files for various games and apps, including PUBG Mobile 2.5. You can also scan the APK file with an antivirus software before installing it to ensure its safety.</p>
-<p>How to download pubg mobile 2.5 update without vpn<br />
-Pubg mobile 2.5 apk download link for android no vpn<br />
-Pubg mobile 2.5 patch notes and download guide without vpn<br />
-Download pubg mobile 2.5 latest version without vpn for free<br />
-Pubg mobile 2.5 direct download without vpn for ios and android<br />
-Pubg mobile 2.5 new features and how to download without vpn<br />
-Pubg mobile 2.5 anniversary update download without vpn<br />
-Best way to download pubg mobile 2.5 without vpn in India<br />
-Pubg mobile 2.5 global version download without vpn<br />
-Pubg mobile 2.5 beta download without vpn and invitation code<br />
-Download pubg mobile 2.5 without vpn and play with friends<br />
-Pubg mobile 2.5 release date and download link without vpn<br />
-Pubg mobile 2.5 installation error and how to fix it without vpn<br />
-Pubg mobile 2.5 tips and tricks and how to download without vpn<br />
-Pubg mobile 2.5 review and download without vpn for pc<br />
-Download pubg mobile 2.5 without vpn and get free rewards<br />
-Pubg mobile 2.5 system requirements and download size without vpn<br />
-Pubg mobile 2.5 gameplay and how to download without vpn<br />
-Download pubg mobile 2.5 without vpn and enjoy new maps and modes<br />
-Pubg mobile 2.5 comparison with previous versions and how to download without vpn<br />
-Download pubg mobile 2.5 without vpn and unlock new skins and outfits<br />
-Pubg mobile 2.5 problems and solutions and how to download without vpn<br />
-Pubg mobile 2.5 performance and optimization and how to download without vpn<br />
-Download pubg mobile 2.5 without vpn and join the fifth anniversary celebration<br />
-Pubg mobile 2.5 secrets and hidden features and how to download without vpn<br />
-Download pubg mobile 2.5 without vpn and participate in new events and missions<br />
-Pubg mobile 2.5 weapons and vehicles and how to download without vpn<br />
-Download pubg mobile 2.5 without vpn and experience the new karakin map<br />
-Pubg mobile 2.5 graphics settings and how to download without vpn<br />
-Download pubg mobile 2.5 without vpn and check out the new royale pass season<br />
-Pubg mobile 2.5 ranking system and how to download without vpn<br />
-Download pubg mobile 2.5 without vpn and learn the new controls and settings<br />
-Pubg mobile 2.5 bugs and glitches and how to download without vpn<br />
-Download pubg mobile 2.5 without vpn and watch the live stream of the anniversary party<br />
-Pubg mobile 2.5 esports news and how to download without vpn<br />
-Download pubg mobile 2.5 without vpn and try the new training mode<br />
-Pubg mobile 2.5 sound effects and voice chat and how to download without vpn<br />
-Download pubg mobile 2.5 without vpn and customize your character and lobby<br />
-Pubg mobile 2.5 clans and crews and how to download without vpn<br />
-Download pubg mobile 2.5 without vpn and access the new shop items</p>
-<h3>Step 2: Enable Installation from Unknown Sources</h3>
-<p>The next step is to enable installation from unknown sources on your device. This is because the APK file is not from the official Google Play Store, and your device may block it by default. To enable installation from unknown sources, follow these steps:</p>
-<ul>
-<li>Go to Settings on your device and tap on Security or Privacy.</li>
-<li>Find the option that says Install apps from unknown sources or Allow installation of apps from unknown sources and toggle it on.</li>
-<li>A warning message may pop up, asking you to confirm your choice. Tap on OK or Yes to proceed.</li>
-</ul>
-<p>Now you are ready to install the PUBG Mobile 2.5 APK file on your device.</p> <h3>Step 3: Install the APK File and Select the Resource Pack</h3>
-<p>The third step is to install the PUBG Mobile 2.5 APK file on your device and select the resource pack that suits your device. To do this, follow these steps:</p>
-<ul>
-<li>Locate the downloaded PUBG Mobile 2.5 APK file on your device and tap on it to start the installation process.</li>
-<li>A prompt may appear, asking you to confirm the installation. Tap on Install or Next to continue.</li>
-<li>Wait for the installation to complete, which may take a few minutes depending on your device and network speed.</li>
-<li>Once the installation is done, launch the game and select the resource pack that matches your device's specifications. There are two options: Low-spec Resource Pack and HD Resource Pack. The Low-spec Resource Pack is recommended for devices with less than 2 GB of RAM, while the HD Resource Pack is recommended for devices with more than 2 GB of RAM.</li>
-<li>Wait for the resource pack to download and install, which may take another few minutes depending on your device and network speed.</li>
-</ul>
-<p>Now you have successfully installed PUBG Mobile 2.5 on your device.</p>
-<h3>Step 4: Enjoy the Game and Claim Your Rewards</h3>
-<p>The final step is to enjoy the game and claim your rewards for updating to PUBG Mobile 2.5. To do this, follow these steps:</p>
-<ul>
-<li>Log in to your PUBG Mobile account using your preferred method, such as Facebook, Twitter, Google Play, or Guest.</li>
-<li>Go to the Events section and find the Update Rewards event. Tap on it and claim your rewards, which include 2888 BP, 100 AG, and a Classic Crate Coupon.</li>
-<li>Go to the Inventory section and check out your new items and skins that you have received from the update rewards.</li>
-<li>Go to the Lobby and select your preferred game mode, such as Classic, Arcade, Arena, or EvoGround. You can also try out the new items and features that are available in PUBG Mobile 2.5.</li>
-<li>Enjoy the game and have fun with your friends or other players from around the world.</li>
-</ul>
-<p>Congratulations! You have successfully downloaded and played PUBG Mobile 2.5 without VPN.</p>
-<h2>How to Play PUBG Mobile 2.5 Without VPN</h2>
-<p>If you are wondering how to play PUBG Mobile 2.5 without VPN, you may be surprised to know that you don't need a VPN at all for this version of the game. This is because PUBG Mobile 2.5 is a global version that is available for all regions and countries, unlike some previous versions that were restricted or banned in some places.</p>
-<h3>Why You Don't Need a VPN for PUBG Mobile 2.5</h3>
-<p>You don't need a VPN for PUBG Mobile 2.5 because of these reasons:</p>
-<ul>
-<li><b>PUBG Mobile 2.5 is a global version:</b> As mentioned earlier, PUBG Mobile 2.5 is a global version that is accessible for all players from different regions and countries. You don't need to change your IP address or location to play the game.</li>
-<li><b>PUBG Mobile 2.5 has multiple servers:</b> PUBG Mobile 2.5 has multiple servers that cater to different regions and countries, such as Asia, Europe, North America, South America, Middle East, KRJP, etc. You can choose the server that suits your location and ping best.</li>
-<li><b>PUBG Mobile 2.5 has anti-cheat measures:</b> PUBG Mobile 2.5 has anti-cheat measures that detect and ban players who use VPNs or other hacks or cheats in the game. Using a VPN may result in your account being suspended or banned permanently.</li>
-</ul>
-<h3>How to Avoid VPN Risks and Disadvantages</h3>
-<p>If you still want to use a VPN for some reason, you should be aware of its risks and disadvantages, such as:</p>
-<ul>
-<li><b>Poor performance and stability:</b> Using a VPN may affect your game's performance and stability, as it may cause lag, latency, packet loss, or disconnection issues.</li>
-<li><b>Limited server options:</b> Using a VPN may limit your server options, as you may not be able to join some servers that are not compatible with your VPN location or IP address.</li>
-<li><b>Potential security threats:</b> Using a VPN may expose your device or data to potential security threats, as some VPNs may contain malware, spyware, or other harmful software that may compromise your privacy or security.</li>
-<li><b>Legal issues:</b> Using a VPN may also cause legal issues, as some countries or regions may have laws or regulations that prohibit or restrict the use of VPNs or online gaming. You may face fines, penalties, or legal actions if you violate these laws or regulations.</li>
-</ul>
-<p>To avoid these risks and disadvantages, you should use a VPN only when necessary and with caution. You should also choose a reputable and reliable VPN service that has good reviews and ratings, and that offers fast and secure servers, encryption, and customer support. Some of the VPN services that we recommend are:</p>
-<ul>
-<li><a href="">ExpressVPN</a></li>
-<li><a href="">NordVPN</a></li>
-<li><a href="">Surfshark</a></li>
-</ul>
-<p>However, we still advise you to play PUBG Mobile 2.5 without VPN, as it is safer, easier, and more enjoyable.</p>
-<h2>Conclusion</h2>
-<p>PUBG Mobile 2.5 is the latest version of the game that brings a lot of new content and features to the players. It is also a global version that is available for all regions and countries, so you don't need a VPN to download or play it. In this article, we have shown you how to download PUBG Mobile 2.5 without VPN in a few simple steps. We have also explained what PUBG Mobile 2.5 is and why you need it, as well as how to play it without VPN and avoid its risks and disadvantages.</p>
-<p>We hope that this article has helped you to download and play PUBG Mobile 2.5 without VPN. If you have any questions or feedback, please feel free to leave a comment below. Thank you for reading and happy gaming!</p>
-<h2>FAQs</h2>
-<p>Here are some frequently asked questions about PUBG Mobile 2.5 and VPN:</p>
-<h3>Q: When will PUBG Mobile 2.5 be released?</h3>
-<p>A: PUBG Mobile 2.5 is expected to be released on March 9, 2023, according to the official announcement by Krafton.</p>
-<h3>Q: How big is the PUBG Mobile 2.5 update?</h3>
-<p>A: The PUBG Mobile 2.5 update is estimated to be around 1 GB in size for Android devices and 1.5 GB for iOS devices.</p>
-<h3>Q: How can I update PUBG Mobile 2.5 from the Google Play Store or the App Store?</h3>
-<p>A: If you have already installed PUBG Mobile on your device from the Google Play Store or the App Store, you can update it to PUBG Mobile 2.5 by following these steps:</p>
-<ul>
-<li>Open the Google Play Store or the App Store on your device and search for PUBG Mobile.</li>
-<li>Tap on the Update button next to the game icon and wait for the update to download and install.</li>
-<li>Launch the game and select the resource pack that suits your device.</li>
-<li>Enjoy the game and claim your update rewards.</li>
-</ul>
-<h3>Q: How can I get free UC in PUBG Mobile 2.5?</h3>
-<p>A: UC is the in-game currency of PUBG Mobile that can be used to buy various items and services in the game, such as crates, skins, outfits, emotes, royale pass, etc. There are several ways to get free UC in PUBG Mobile 2.5, such as:</p>
-<ul>
-<li><b>Participating in events and missions:</b> You can earn free UC by participating in various events and missions that are available in the game, such as daily login rewards, anniversary rewards, seasonal rewards, etc.</li>
-<li><b>Using redeem codes:</b> You can also get free UC by using redeem codes that are given by Krafton or other official sources on their social media platforms or websites. You can enter these codes in the Redeem section of the game and claim your free UC.</li>
-<li><b>Using third-party apps or websites:</b> Another way to get free UC is to use third-party apps or websites that offer UC as rewards for completing surveys, tasks, quizzes, etc. However, you should be careful with these apps or websites, as some of them may be scams or contain malware that may harm your device or data.</li>
-</ul>
-<h3>Q: Is PUBG Mobile 2.5 banned in India?</h3>
-<p>A: No, PUBG Mobile 2.5 is not banned in India. In fact, Krafton has recently announced that they will launch a new version of PUBG Mobile specifically for India, called PUBG Mobile India, which will be compliant with the local laws and regulations. PUBG Mobile India will have some exclusive features and content for Indian players, such as green blood, fully clothed characters, and a virtual simulation training ground. PUBG Mobile India is expected to be released soon, and players can pre-register for it on the Google Play Store or the App Store.</p> 401be4b1e0<br />
-<br />
-<br />
\ No newline at end of file
diff --git a/spaces/simple0urra/skops-model-card-creator-2a23515a-d54e-4804-b365-27ed6e938735/example/Five Nights at Freddys APK - Freddynin Gizemlerini zn.md b/spaces/simple0urra/skops-model-card-creator-2a23515a-d54e-4804-b365-27ed6e938735/example/Five Nights at Freddys APK - Freddynin Gizemlerini zn.md
deleted file mode 100644
index dda263a7d0a8b4ab98128842a5656197b669e460..0000000000000000000000000000000000000000
--- a/spaces/simple0urra/skops-model-card-creator-2a23515a-d54e-4804-b365-27ed6e938735/example/Five Nights at Freddys APK - Freddynin Gizemlerini zn.md	
+++ /dev/null
@@ -1,135 +0,0 @@
-<br />
-<h1>What is Freddy APK Indir?</h1>
-<p>If you are a fan of horror games, you might have heard of Five Nights at Freddy's, a popular series of games that challenge you to survive in a haunted pizzeria with animatronic robots. But did you know that you can download the APK file of the game from the Google Play Store and enjoy it on your Android device? In this article, we will tell you everything you need to know about Freddy APK Indir, how to download it, how to install it, and what are the alternatives.</p>
- <h2>What is Freddy Game?</h2>
-<p>Freddy Game is the first installment of Five Nights at Freddy's, a horror game developed by Scott Cawthon. The game was released in 2014 and has spawned several sequels and spin-offs. The game puts you in the role of a night guard at Freddy Fazbear's Pizza, a family-friendly restaurant that features animatronic animals that entertain children during the day. However, at night, the robots become hostile and try to kill you. You have to use cameras, doors, lights, and other tools to survive five nights at Freddy's.</p>
-<h2>freddy apk indir</h2><br /><p><b><b>DOWNLOAD</b> &#10040;&#10040;&#10040; <a href="https://ssurll.com/2uO1eO">https://ssurll.com/2uO1eO</a></b></p><br /><br />
- <p>The game is known for its jump scares, suspenseful atmosphere, and lore. The game has received positive reviews from critics and fans alike, and has become one of the most successful indie games of all time. The game is available for Windows, iOS, Android, and other platforms.</p>
- <h3>Why Download Freddy APK Indir?</h3>
-<p>There are many reasons why you might want to download Freddy APK Indir from the Google Play Store instead of installing it directly from the store. Here are some of them:</p>
-<ul>
-<li>You can save storage space on your device by downloading only the APK file instead of the whole app.</li>
-<li>You can access older versions of the game that might not be available on the store anymore.</li>
-<li>You can bypass regional restrictions and download the game even if it is not available in your country.</li>
-<li>You can avoid ads and in-app purchases that might be present in the store version.</li>
-<li>You can share the APK file with your friends and family without using data or Wi-Fi.</li>
-</ul>
- <h4>How to Download Freddy APK Indir from Google Play Store?</h4>
-<p>To download Freddy APK Indir from Google Play Store, you need an Internet connection and a web browser. You can use a web tool or an app to generate download links for APK files from Google Play URLs. Here are the steps:</p>
-<ol>
-<li>Open the Google Play Store on your device or computer and search for Five Nights at Freddy's.</li>
-<li>Copy the URL of the app from the address bar or tap on the three-dot menu and select Share > Copy to clipboard.</li>
-<li>Go to [5](https://apps.evozi.com/apk-downloader/) or any other APK downloader website in your web browser.</li>
-<li>Paste the URL in the box at the top and click on Generate Download Link.</li>
-<li>Click on Click here to download or Download APK to save the file to your device or computer.</li>
-</ol>
- <h4>How to Install Freddy APK Indir on Android Device?</h4>
-<p>To install Freddy APK Indir on your Android device, you need to enable unknown sources in your device settings. This will allow you to install apps from sources other than the Google Play Store. Here are the steps:</p>
-<ol>
-<li>Go to Settings > Security > Unknown sources and toggle it on. You might see a warning message, but tap on OK to confirm.</li>
-<li>Locate the Freddy APK Indir file that you downloaded in your device's storage. You can use a file manager app to do this.</li>
-<li>Tap on the file and follow the instructions to install the app. You might see a prompt asking for permissions, but tap on Install to proceed.</li>
-<li>Once the installation is complete, you can launch the app from your app drawer or home screen.</li>
-</ol>
- <h3>What are the Alternatives to Freddy APK Indir?</h3>
-<p>If you are looking for other games and apps that are similar to Freddy APK Indir, you have plenty of options. Here are some of them:</p>
-<table>
-<tr>
-<th>Name</th>
-<th>Description</th>
-</tr>
-<tr>
-<td>Freddy 2 APK Indir</td>
-<td>The second installment of Five Nights at Freddy's, where you have to deal with new and old animatronics in a new location.</td>
-</tr>
-<tr>
-<td>Freddy 3 APK Indir</td>
-<td>The third installment of Five Nights at Freddy's, where you have to survive in a horror attraction based on the original pizzeria.</td>
-</tr>
-<tr>
-<td>Freddy 4 APK Indir</td>
-<td>The fourth installment of Five Nights at Freddy's, where you have to fend off nightmare versions of the animatronics in your own home.</td>
-</tr>
-<tr>
-<td>Freddy 5 APK Indir</td>
-<td>The fifth installment of Five Nights at Freddy's, where you have to escape from a secret underground facility with advanced animatronics.</td>
-</tr>
-<tr>
-<td>Freddy 6 APK Indir</td>
-<td>The sixth installment of Five Nights at Freddy's, where you have to manage your own pizzeria and deal with the consequences of your actions.</td>
-</tr>
-<tr>
-<td>Freddy 7 APK Indir</td>
-<td>The seventh installment of Five Nights at Freddy's, where you have to explore a virtual reality game that contains glitches and secrets.</td>
-</tr>
-<tr>
-<td>Freddy 8 APK Indir</td>
-<td>The eighth installment of Five Nights at Freddy's, where you have to survive in a mall with new and old animatronics.</td>
-</tr>
- </table>
- <h2>Conclusion</h2>
- <p>Freddy APK Indir is a great way to enjoy one of the most popular horror games of all time on your Android device. You can download the APK file from the Google Play Store and install it easily on your device. You can also try other alternatives that are similar to Freddy APK Indir. However, be warned that these games are not for the faint of heart. They will scare you, thrill you, and keep you hooked for hours. Are you ready to face your fears?</p>
-<p>freddy fazbear's pizzeria simulator apk indir<br />
-five nights at freddy's security breach apk indir<br />
-fnaf ar special delivery apk indir<br />
-five nights at freddy's sister location apk indir<br />
-ultimate custom night apk indir<br />
-five nights at freddy's 4 apk indir<br />
-five nights at freddy's 3 apk indir<br />
-five nights at freddy's 2 apk indir<br />
-five nights at freddy's 1 apk indir<br />
-fnaf world update 2 apk indir<br />
-fnaf world adventure apk indir<br />
-fnaf fan games apk indir<br />
-fnaf the joy of creation apk indir<br />
-fnaf the twisted ones apk indir<br />
-fnaf the silver eyes apk indir<br />
-fnaf the fourth closet apk indir<br />
-fnaf the final chapter apk indir<br />
-fnaf the fredbear archives apk indir<br />
-fnaf the return to freddy's apk indir<br />
-fnaf the novel series apk indir<br />
-fnaf help wanted mobile apk indir<br />
-fnaf vr help wanted android apk indir<br />
-fnaf vr help wanted non vr apk indir<br />
-fnaf vr help wanted free download apk indir<br />
-fnaf vr help wanted full game apk indir<br />
-fnaf into madness apk indir<br />
-fnaf in space 2 apk indir<br />
-fnaf in space 1 apk indir<br />
-fnaf in real life game apk indir<br />
-fnaf in real life camera prank apk indir<br />
-fnaf high school simulator apk indir<br />
-fnaf halloween edition apk indir<br />
-fnaf golden memory 2 apk indir<br />
-fnaf golden memory 1 apk indir<br />
-fnaf gamejolt games android apk indir<br />
-fnaf game collection android apk indir<br />
-fnaf fan made games android apk indir<br />
-fnaf fan made android port apk indir<br />
-fnaf evolution 2 android download apk indir<br />
-fnaf evolution 1 android download apk indir<br />
-fnaf endless tycoon android download apk indir<br />
-fnaf download free full version android apk indir<br />
-fnaf download all games android free apk indir<br />
-fnaf dating simulator android download free apk indir<br />
-fnaf custom night ultimate edition android download free apk indir<br />
-freddy fazbear's pizza place simulator android download free apk indir</p>
- <h3>FAQs</h3>
- <p>Here are some frequently asked questions and answers about Freddy APK Indir:</p>
- <ol>
- <li><b>What is an APK file?</b></li>
- <p>An APK file is an Android Package file that contains all the components of an Android app. It is similar to an EXE file for Windows or a DMG file for Mac. You can use an APK file to install an app on your Android device without using the Google Play Store.</p>
- <li><b>Is Freddy APK Indir safe?</b></li>
- <p>Freddy APK Indir is safe as long as you download it from a trusted source and scan it for viruses before installing it. However, you should always be careful when installing apps from unknown sources, as they might contain malware or spyware that can harm your device or compromise your privacy.</p>
- <li><b>How much space does Freddy APK Indir take?</b></li>
- <p>Freddy APK Indir takes about 50 MB of space on your device. However, this might vary depending on the version and device you are using.</p>
- <li><b>Can I play Freddy APK Indir offline?</b></li>
- <p>Yes, you can play Freddy APK Indir offline without any Internet connection. However, you might need an Internet connection to download updates or access some features.</p>
- <li><b>Can I play Freddy APK Indir on PC?</b></li>
- <p>Yes, you can play Freddy APK Indir on PC using an Android emulator. An Android emulator is a software that simulates an Android device on your computer. You can use an Android emulator to run any Android app or game on your PC. Some of the popular Android emulators are some of the popular Android emulators are BlueStacks, NoxPlayer, LDPlayer, MeMu Play, and Genymotion. You can download and install any of these emulators on your PC and then run Freddy APK Indir on them.</p>
- <li><b>Can I play Freddy APK Indir with friends?</b></li>
- <p>Yes, you can play Freddy APK Indir with friends online or offline. The game supports multiplayer mode, where you can join or create a private room and invite your friends to play with you. You can also chat with your friends using the in-game voice or text chat feature. However, you need an Internet connection to play online multiplayer mode.</p>
- </ol></p> 197e85843d<br />
-<br />
-<br />
\ No newline at end of file
diff --git a/spaces/siya02/Konakni-TTS/ttsv/src/hifi_gan/inference.py b/spaces/siya02/Konakni-TTS/ttsv/src/hifi_gan/inference.py
deleted file mode 100644
index c70ee09b4110677b7cf9732d76a5e6ca93c8860c..0000000000000000000000000000000000000000
--- a/spaces/siya02/Konakni-TTS/ttsv/src/hifi_gan/inference.py
+++ /dev/null
@@ -1,98 +0,0 @@
-from __future__ import absolute_import, division, print_function, unicode_literals
-
-import glob
-import os
-import argparse
-import json
-import torch
-from scipy.io.wavfile import write
-from env import AttrDict
-from meldataset import mel_spectrogram, MAX_WAV_VALUE, load_wav
-from models import Generator
-
-h = None
-device = None
-
-
-def load_checkpoint(filepath, device):
-    assert os.path.isfile(filepath)
-    print("Loading '{}'".format(filepath))
-    checkpoint_dict = torch.load(filepath, map_location=device)
-    print("Complete.")
-    return checkpoint_dict
-
-
-def get_mel(x):
-    return mel_spectrogram(
-        x, h.n_fft, h.num_mels, h.sampling_rate, h.hop_size, h.win_size, h.fmin, h.fmax
-    )
-
-
-def scan_checkpoint(cp_dir, prefix):
-    pattern = os.path.join(cp_dir, prefix + "*")
-    cp_list = glob.glob(pattern)
-    if len(cp_list) == 0:
-        return ""
-    return sorted(cp_list)[-1]
-
-
-def inference(a):
-    generator = Generator(h).to(device)
-
-    state_dict_g = load_checkpoint(a.checkpoint_file, device)
-    generator.load_state_dict(state_dict_g["generator"])
-
-    filelist = os.listdir(a.input_wavs_dir)
-
-    os.makedirs(a.output_dir, exist_ok=True)
-
-    generator.eval()
-    generator.remove_weight_norm()
-    with torch.no_grad():
-        for i, filname in enumerate(filelist):
-            wav, sr = load_wav(os.path.join(a.input_wavs_dir, filname))
-            wav = wav / MAX_WAV_VALUE
-            wav = torch.FloatTensor(wav).to(device)
-            x = get_mel(wav.unsqueeze(0))
-            y_g_hat = generator(x)
-            audio = y_g_hat.squeeze()
-            audio = audio * MAX_WAV_VALUE
-            audio = audio.cpu().numpy().astype("int16")
-
-            output_file = os.path.join(
-                a.output_dir, os.path.splitext(filname)[0] + "_generated.wav"
-            )
-            write(output_file, h.sampling_rate, audio)
-            print(output_file)
-
-
-def main():
-    print("Initializing Inference Process..")
-
-    parser = argparse.ArgumentParser()
-    parser.add_argument("--input_wavs_dir", default="test_files")
-    parser.add_argument("--output_dir", default="generated_files")
-    parser.add_argument("--checkpoint_file", required=True)
-    a = parser.parse_args()
-
-    config_file = os.path.join(os.path.split(a.checkpoint_file)[0], "config.json")
-    with open(config_file) as f:
-        data = f.read()
-
-    global h
-    json_config = json.loads(data)
-    h = AttrDict(json_config)
-
-    torch.manual_seed(h.seed)
-    global device
-    if torch.cuda.is_available():
-        torch.cuda.manual_seed(h.seed)
-        device = torch.device("cuda")
-    else:
-        device = torch.device("cpu")
-
-    inference(a)
-
-
-if __name__ == "__main__":
-    main()
diff --git a/spaces/sriramelango/Social_Classification_Public/fairseq/examples/m2m_100/process_data/clean_histogram.py b/spaces/sriramelango/Social_Classification_Public/fairseq/examples/m2m_100/process_data/clean_histogram.py
deleted file mode 100644
index e24e073dc0eb43c76e2ce717f52bb848c5b026b8..0000000000000000000000000000000000000000
--- a/spaces/sriramelango/Social_Classification_Public/fairseq/examples/m2m_100/process_data/clean_histogram.py
+++ /dev/null
@@ -1,52 +0,0 @@
-import argparse
-
-parser = argparse.ArgumentParser()
-parser.add_argument('--src', type=str, help='Source language')
-parser.add_argument('--tgt', type=str, help='Target language')
-parser.add_argument('--src-file', type=str, help='Input source file')
-parser.add_argument('--tgt-file', type=str, help='Input target file')
-parser.add_argument('--src-output-file', type=str, help='Output source file')
-parser.add_argument('--tgt-output-file', type=str, help='Output target file')
-parser.add_argument('--threshold', type=float, default=0.5, help='Threshold')
-parser.add_argument('--threshold-character', type=str, default=']', help='Threshold character')
-parser.add_argument('--histograms', type=str, help='Path to histograms')
-
-args = parser.parse_args()
-
-
-def read_hist(f):
-    ch = []
-    for line in f:
-        c = line[0]
-        if c == args.threshold_character:
-            break
-        ch.append(c)
-    return ch
-
-
-with(open("{}/{}".format(args.histograms, args.src), 'r', encoding='utf8')) as f:
-    ch1 = read_hist(f)
-
-with(open("{}/{}".format(args.histograms, args.tgt), 'r', encoding='utf8')) as f:
-    ch2 = read_hist(f)
-
-print("Accepted characters for {}: {}".format(args.src, ch1))
-print("Accepted characters for {}: {}".format(args.tgt, ch2))
-
-with open(args.src_file, 'r', encoding='utf8') as fs1, open(args.tgt_file, 'r', encoding='utf8') as fs2, open(args.src_output_file, 'w', encoding='utf8') as fos1, open(args.tgt_output_file, 'w', encoding='utf8') as fos2:
-    ls1 = fs1.readline()
-    ls2 = fs2.readline()
-
-    while ls1 or ls2:
-        cnt1 = len([c for c in ls1.strip() if c in ch1])
-        cnt2 = len([c for c in ls2.strip() if c in ch2])
-
-        if cnt1 / len(ls1) > args.threshold and cnt2 / len(ls2) > args.threshold:
-            fos1.write(ls1)
-            fos2.write(ls2)
-        else:
-            print("{} {} {} \n{} {} {}".format(args.src, cnt1 / len(ls1), ls1.strip(), args.tgt, cnt2 / len(ls2), ls2.strip()))
-
-        ls1 = fs1.readline()
-        ls2 = fs2.readline()
-        
\ No newline at end of file
diff --git a/spaces/sriramelango/Social_Classification_Public/fairseq/fairseq/modules/quantization/scalar/utils.py b/spaces/sriramelango/Social_Classification_Public/fairseq/fairseq/modules/quantization/scalar/utils.py
deleted file mode 100644
index 2ec6af3fcb09ccaf853be15a84ed8181f9e2f546..0000000000000000000000000000000000000000
--- a/spaces/sriramelango/Social_Classification_Public/fairseq/fairseq/modules/quantization/scalar/utils.py
+++ /dev/null
@@ -1,78 +0,0 @@
-# Copyright (c) Facebook, Inc. and its affiliates.
-#
-# This source code is licensed under the MIT license found in the
-# LICENSE file in the root directory of this source tree.
-
-import logging
-from operator import attrgetter
-
-import torch.distributed as dist
-import torch.nn as nn
-
-from ..pq.utils import attrsetter, get_layers
-from .modules import ActivationQuantizer, IntConv2d, IntEmbedding, IntLinear
-
-
-MAPPING = {nn.Linear: IntLinear, nn.Embedding: IntEmbedding, nn.Conv2d: IntConv2d}
-
-
-def quantize_model_(model, p=0.2, bits=8, update_step=3000, method="histogram", remove_weights=False):
-    """
-    Replaces all modules with their scalar quantized counterpart and
-    registers hooks to quantize the post-ativations of those modules.
-
-    Args:
-        - model: a nn.Module
-        - p: amount of noise (0 for no noise, 1 to quantize all the weights/activations)
-        - bits: number of bits
-        - update_step: update quantization parameters every update_step steps
-    """
-    # quantize all layers
-    # remove weights indicates whether the weights extension should be removed, in addition to
-    # weight_orig and weight extension on names
-    quantized_layers = get_layers(model, "(.*?)", remove_weights=remove_weights)
-
-    for layer in quantized_layers:
-
-        # book-keeping
-        is_master_process = (not dist.is_initialized()) or (
-            dist.is_initialized() and dist.get_rank() == 0
-        )
-
-        # recover module
-        module = attrgetter(layer)(model)
-        if is_master_process:
-            logging.info(
-                f"Quantizing layer {layer} with bits={bits} and QuantNoise={p}"
-            )
-
-        # quantization params
-        q_params = {
-            "p": p,
-            "update_step": update_step,
-            "bits": bits,
-            "method": method,
-            "counter": 0,
-        }
-
-        # instantiate the quantized counterpart
-        if isinstance(module, tuple(MAPPING.keys())):
-            QuantizedModule = MAPPING[module.__class__]
-            quantized_module = QuantizedModule.__new__(QuantizedModule)
-            params = module.__dict__
-            params.update(q_params)
-            quantized_module.__dict__.update(params)
-
-        else:
-            if is_master_process:
-                logging.info(f"Module {module} not yet supported for quantization")
-            continue
-
-        # activation quantization
-        a_q = ActivationQuantizer(quantized_module, p=0, bits=bits, method=method)
-
-        # replace layer by its quantized counterpart
-        attrsetter(layer)(model, quantized_module)
-
-    # return name of quantized layers
-    return quantized_layers
diff --git a/spaces/sriramelango/Social_Classification_Public/tasks/mm_tasks/__init__.py b/spaces/sriramelango/Social_Classification_Public/tasks/mm_tasks/__init__.py
deleted file mode 100644
index 925b5f8a7098b25af1b77b7dbe77cd14a9aa4001..0000000000000000000000000000000000000000
--- a/spaces/sriramelango/Social_Classification_Public/tasks/mm_tasks/__init__.py
+++ /dev/null
@@ -1 +0,0 @@
-from .caption import CaptionTask
\ No newline at end of file
diff --git a/spaces/stomexserde/gpt4-ui/Examples/Download Karafun Studio 1.18 Full Crackl !!HOT!!.md b/spaces/stomexserde/gpt4-ui/Examples/Download Karafun Studio 1.18 Full Crackl !!HOT!!.md
deleted file mode 100644
index 1f2ffb0e9786c08bc56bb65bc1e7075b4ce244d1..0000000000000000000000000000000000000000
--- a/spaces/stomexserde/gpt4-ui/Examples/Download Karafun Studio 1.18 Full Crackl !!HOT!!.md	
+++ /dev/null
@@ -1,29 +0,0 @@
-<br />
-<h1>How to Download Karafun Studio 1.18 Full Crackl for Free</h1>
-<p>Karafun Studio is a software that allows you to create your own karaoke files and have fun with your friends. You can import audio files, enter the lyrics, sync them with the music, and customize the appearance of the text and the background. You can also use videos or pictures as backgrounds for your karaoke songs.</p>
-<h2>Download Karafun Studio 1.18 Full Crackl</h2><br /><p><b><b>DOWNLOAD</b> &middot;&middot;&middot; <a href="https://urlgoal.com/2uI753">https://urlgoal.com/2uI753</a></b></p><br /><br />
-<p>If you want to download Karafun Studio 1.18 full crackl for free, you need to follow these steps:</p>
-<ol>
-<li>Go to this link: <a href="https://soundcloud.com/oramusimuet6/karafun-studio-118-full-version">Karafun Studio 1.18 [Full Version]</a> [^3^]. This is a SoundCloud page that has the download link for the software.</li>
-<li>Click on the "More" button and then select "Download file". This will start downloading the software to your computer.</li>
-<li>Extract the zip file and run the setup.exe file. Follow the instructions to install the software on your computer.</li>
-<li>Copy the crack file from the crack folder and paste it into the installation directory of Karafun Studio. This will activate the full version of the software.</li>
-<li>Enjoy creating your own karaoke files with Karafun Studio 1.18 full crackl!</li>
-</ol>
-<p>Note: This is an illegal way of downloading Karafun Studio 1.18 full crackl and we do not recommend it. You may face legal consequences or malware infections if you use this method. The best way to get Karafun Studio is to buy it from its official website: <a href="https://www.karafun.com/studio/">Karafun Studio</a> [^1^]. You can also download a free trial version of Karafun Studio from there.</p>
-
-<p>Now that you have downloaded Karafun Studio 1.18 full crackl, you may wonder how to use it to create your own karaoke files. Here are some tips to help you get started:</p>
-<ul>
-<li>Choose a song that you like and that has clear lyrics. You can use any audio file format that Karafun Studio supports, such as MP3, OGG, MIDI, or KAR.</li>
-<li>Import the audio file into Karafun Studio by clicking on the "Import" button on the toolbar. You can also drag and drop the file into the interface.</li>
-<li>Enter the lyrics of the song in the box below the audio waveform. You can type them manually or copy and paste them from another source. Make sure to separate each line with a carriage return.</li>
-<li>Sync the lyrics with the music by using the "Sync" button on the toolbar. You can adjust the timing of each word or syllable by dragging them on the waveform. You can also use keyboard shortcuts to speed up the process.</li>
-<li>Customize the appearance of the lyrics by using the "Style" button on the toolbar. You can change the font, size, color, alignment, and effects of the text. You can also add shadows, outlines, or gradients to make them more visible.</li>
-<li>Customize the background of the karaoke file by using the "Background" button on the toolbar. You can choose from different types of backgrounds, such as images, videos, colors, or patterns. You can also adjust the brightness, contrast, and transparency of the background.</li>
-<li>Preview your karaoke file by using the "Play" button on the toolbar. You can see how it looks and sounds on your screen. You can also use the "Record" button to record your own voice over the music.</li>
-<li>Save your karaoke file by using the "Save" button on the toolbar. You can choose to save it as a KFN file, which is a proprietary format of Karafun Studio that contains all your settings and customizations. You can also export it as a CDG + MP3 file, which is a standard format for karaoke players.</li>
-</ul>
-<p>Congratulations! You have created your own karaoke file with Karafun Studio 1.18 full crackl. You can now enjoy singing along with your friends or share your creation online.</p>
-<p></p> 7b8c122e87<br />
-<br />
-<br />
\ No newline at end of file
diff --git a/spaces/stomexserde/gpt4-ui/Examples/Flowjo 10 Serial Number Crack Software.md b/spaces/stomexserde/gpt4-ui/Examples/Flowjo 10 Serial Number Crack Software.md
deleted file mode 100644
index 5a98e3c312842d4ddddebef8d066a543e15d361c..0000000000000000000000000000000000000000
--- a/spaces/stomexserde/gpt4-ui/Examples/Flowjo 10 Serial Number Crack Software.md	
+++ /dev/null
@@ -1,51 +0,0 @@
-
-<h1>Flowjo 10 Serial Number Crack Software: What You Need to Know</h1>
- <p>Flowjo 10 is a powerful software for analyzing cytometry data, which are measurements of cells and cell components. Flowjo 10 can create new files in the cytometry standard format, display and manipulate data in various ways, perform statistical analysis, and generate reports and graphs. Flowjo 10 is widely used by researchers and professionals in fields such as immunology, oncology, stem cell biology, and microbiology.</p>
- <p>However, Flowjo 10 is not a cheap software. It requires a license key and a serial number to activate and use. The license key and the serial number are unique for each user and computer, and they are linked to the user's email address. If you lose or forget your license key or serial number, you will not be able to use Flowjo 10 anymore.</p>
-<h2>Flowjo 10 Serial Number Crack Software</h2><br /><p><b><b>Download Zip</b> &#10003; <a href="https://urlgoal.com/2uI67J">https://urlgoal.com/2uI67J</a></b></p><br /><br />
- <p>That is why some people may look for ways to crack Flowjo 10 and bypass the activation process. They may search for Flowjo 10 serial number crack software online, hoping to find a tool that can generate a valid license key and serial number for them. However, this is not a good idea for several reasons. In this article, we will explain why you should avoid using Flowjo 10 serial number crack software, what are the risks and consequences of doing so, and what are the alternatives to get Flowjo 10 legally and safely.</p>
- <h2>Why You Should Avoid Using Flowjo 10 Serial Number Crack Software</h2>
- <p>Using Flowjo 10 serial number crack software may seem like an easy and convenient way to get Flowjo 10 for free, but it is actually a very bad idea. Here are some of the reasons why you should avoid using Flowjo 10 serial number crack software:</p>
- <h3>It Is Illegal</h3>
- <p>Using Flowjo 10 serial number crack software is a form of software piracy, which is illegal in most countries. Software piracy is the unauthorized copying, distribution, or use of software that is protected by intellectual property rights. Software piracy violates the rights of the software developers and owners, who invest time, money, and effort to create and maintain their products.</p>
- <p>Software piracy can result in civil or criminal penalties, depending on the laws of your country. For example, in the United States, software piracy can lead to fines of up to $150,000 per infringement, or imprisonment of up to five years, or both. In addition, you may also face legal action from the software company or its representatives, who may sue you for damages or injunctions.</p>
- <h3>It Is Unsafe</h3>
- <p>Using Flowjo 10 serial number crack software is also unsafe for your computer and your data. Most of the Flowjo 10 serial number crack software that you can find online are not reliable or trustworthy. They may contain viruses, malware, spyware, or other harmful programs that can infect your computer and compromise your security and privacy.</p>
- <p>For example, some Flowjo 10 serial number crack software may steal your personal information, such as your email address, passwords, credit card numbers, or bank account details. Some may also damage your files, corrupt your system, or delete your data. Some may even lock your computer or encrypt your data and demand ransom for their release.</p>
- <p>Moreover, using Flowjo 10 serial number crack software may also expose you to cyberattacks from hackers or cybercriminals who may exploit the vulnerabilities or backdoors that the crack software may create on your computer. They may access your computer remotely, monitor your activities, steal your data, or use your computer for illegal purposes.</p>
- <h3>It Is Unethical</h3>
- <p>Using Flowjo 10 serial number crack software is also unethical and unfair to the software developers and owners. As we mentioned earlier, software developers and owners invest time, money, and effort to create and maintain their products. They also provide support and updates to their customers who pay for their products.</p>
-<p></p>
- <p>By using Flowjo 10 serial number crack software, you are not only violating their rights but also depriving them of their deserved income and recognition. You are also undermining their motivation and innovation to improve their products and services. You are also disrespecting their work and contribution to the scientific community.</p>
- <h3>It Is Ineffective</h3>
- <p>Finally, using Flowjo 10 serial number crack software is also ineffective and inefficient for your work and research. Most of the Flowjo 10 serial number crack software that you can find online are not reliable or trustworthy. They may not work properly or at all. They may cause errors, crashes, or glitches on your computer or on Flowjo 10. They may also be incompatible with the latest versions or updates of Flowjo 10, which may affect the quality and accuracy of your data analysis and results.</p>
- <p>Furthermore, using Flowjo 10 serial number crack software may also affect your reputation and credibility as a researcher or professional. If you use Flowjo 10 serial number crack software to analyze your data and publish your findings, you may face ethical issues or plagiarism accusations. You may also lose the trust and respect of your peers, colleagues, or clients who may question the validity and integrity of your work.</p>
- <h2>What Are the Alternatives to Get Flowjo 10 Legally and Safely</h2>
- <p>Now that you know why you should avoid using Flowjo 10 serial number crack software, you may wonder what are the alternatives to get Flowjo 10 legally and safely. Here are some of the options that you can consider:</p>
- <h3>Buy a License Key and Serial Number from the Official Website</h3>
- <p>The best and most obvious way to get Flowjo 10 legally and safely is to buy a license key and serial number from the official website of Flowjo 10. This way, you will get a genuine and valid license key and serial number that will activate and use Flowjo 10 without any problems. You will also get access to the latest versions and updates of Flowjo 10, as well as support and assistance from the Flowjo 10 team.</p>
- <p>The price of a license key and serial number for Flowjo 10 depends on the type and duration of the license that you choose. There are different types of licenses available, such as individual, group, site, or enterprise licenses. There are also different durations available, such as monthly, yearly, or perpetual licenses. You can check the pricing and features of each license type and duration on the official website of Flowjo 10.</p>
- <h3>Request a Free Trial or a Demo Version of Flowjo 10</h3>
- <p>If you are not sure whether you want to buy a license key and serial number for Flowjo 10, you can request a free trial or a demo version of Flowjo 10 from the official website of Flowjo 10. This way, you can test and evaluate Flowjo 10 for a limited period of time before making a purchase decision. You will also get access to some of the features and functions of Flowjo 10, as well as support and assistance from the Flowjo 10 team.</p>
- <p>The free trial or demo version of Flowjo 10 is available for both Windows and Mac operating systems. The free trial lasts for 30 days, while the demo version lasts for 7 days. You can request a free trial or a demo version of Flowjo 10 by filling out a form on the official website of Flowjo 10. You will need to provide some basic information, such as your name, email address, institution, country, and operating system.</p>
- <h3>Use an Alternative Software for Analyzing Cytometry Data</h3>
- <p>If you are not satisfied with Flowjo 10 or its price, you can use an alternative software for analyzing cytometry data. There are many other software options available in the market that can perform similar or different functions as Flowjo 10. Some of them are free or open source, while others are paid or proprietary. Some of them are compatible with Windows or Mac operating systems, while others are web-based or cloud-based.</p>
- <p>Some examples of alternative software for analyzing cytometry data are: - FCS Express: A paid software that can import, analyze, report, and export cytometry data in various formats. It has features such as gating tools, compensation tools, statistics tools, graphing tools, batch analysis tools, and report generation tools. - Cytobank: A web-based software that can store, analyze, visualize, and share cytometry data online. It has features such as clustering tools, - FlowLogic: A paid software that can import, analyze, visualize, and export cytometry data in various formats. It has features such as gating tools, compensation tools, statistics tools, graphing tools, quality control tools, and report generation tools. - Flowing Software: A free software that can import, analyze, and export cytometry data in various formats. It has features such as gating tools, compensation tools, statistics tools, graphing tools, and batch analysis tools. - Cyflogic: A free software that can import, analyze, and export cytometry data in various formats. It has features such as gating tools, compensation tools, statistics tools, graphing tools, and report generation tools.</p>
- <p>You can compare the features, functions, prices, and reviews of these and other alternative software for analyzing cytometry data online. You can also download or access them from their official websites or platforms.</p>
- <h2>Conclusion</h2>
- <p>Flowjo 10 is a powerful software for analyzing cytometry data, but it is not a cheap software. It requires a license key and a serial number to activate and use. Some people may look for ways to crack Flowjo 10 and bypass the activation process by using Flowjo 10 serial number crack software. However, this is not a good idea for several reasons. Using Flowjo 10 serial number crack software is illegal, unsafe, unethical, and ineffective.</p>
- <p>Instead of using Flowjo 10 serial number crack software, you should consider the alternatives to get Flowjo 10 legally and safely. You can buy a license key and serial number from the official website of Flowjo 10, request a free trial or a demo version of Flowjo 10 from the official website of Flowjo 10, or use an alternative software for analyzing cytometry data. These options will help you get Flowjo 10 or a similar software without any problems or risks.</p>
- <h2>FAQs</h2>
- <p>Here are some of the frequently asked questions about Flowjo 10 serial number crack software:</p>
- <h3>Q: What is Flowjo 10?</h3>
-<p>A: Flowjo 10 is a powerful software for analyzing cytometry data, which are measurements of cells and cell components. Flowjo 10 can create new files in the cytometry standard format, display and manipulate data in various ways, perform statistical analysis, and generate reports and graphs.</p>
- <h3>Q: What is Flowjo 10 serial number crack software?</h3>
-<p>A: Flowjo 10 serial number crack software is a tool that can generate a valid license key and serial number for Flowjo 10 without paying for it. It can bypass the activation process of Flowjo 10 and allow the user to use Flowjo 10 for free.</p>
- <h3>Q: Why should I avoid using Flowjo 10 serial number crack software?</h3>
-<p>A: You should avoid using Flowjo 10 serial number crack software because it is illegal, unsafe, unethical, and ineffective. It can result in legal penalties, computer infections, data loss, ethical issues, or reputation damage. It can also affect the quality and accuracy of your data analysis and results.</p>
- <h3>Q: How can I get Flowjo 10 legally and safely?</h3>
-<p>A: You can get Flowjo 10 legally and safely by buying a license key and serial number from the official website of Flowjo 10, requesting a free trial or a demo version of Flowjo 10 from the official website of Flowjo 10, or using an alternative software for analyzing cytometry data. These options will help you get Flowjo 10 or a similar software without any problems or risks.</p>
- <h3>Q: What are some of the alternative software for analyzing cytometry data?</h3>
-<p>A: Some of the alternative software for analyzing cytometry data are FCS Express, Cytobank, FlowLogic, Flowing Software, and Cyflogic. They can perform similar or different functions as Flowjo 10, and they have different features, prices, and reviews. You can compare them online and download or access them from their official websites or platforms.</p> b2dd77e56b<br />
-<br />
-<br />
\ No newline at end of file
diff --git a/spaces/stomexserde/gpt4-ui/Examples/Free Download Pinnacle Studio 12 Full Crack ((INSTALL)).md b/spaces/stomexserde/gpt4-ui/Examples/Free Download Pinnacle Studio 12 Full Crack ((INSTALL)).md
deleted file mode 100644
index e28507b25dc6ee6af50f23b22da2bc0f33b61985..0000000000000000000000000000000000000000
--- a/spaces/stomexserde/gpt4-ui/Examples/Free Download Pinnacle Studio 12 Full Crack ((INSTALL)).md	
+++ /dev/null
@@ -1,24 +0,0 @@
-<br />
-<h1>How to Download and Install Pinnacle Studio 12 Ultimate for Free</h1>
-<p>Pinnacle Studio 12 Ultimate is a powerful video editing software that allows you to create professional-looking movies and slideshows with ease. It offers a range of features and capabilities, such as Pinnacle Montage, an innovative tool that lets you add high-end compositing and animation effects to your videos. It also supports Blu-ray authoring, HD editing, and more than 25 new enhancements requested by users.</p>
-<h2>Free Download Pinnacle Studio 12 Full Crack</h2><br /><p><b><b>Download File</b> &#10037; <a href="https://urlgoal.com/2uIbiA">https://urlgoal.com/2uIbiA</a></b></p><br /><br />
-<p>If you want to download and install Pinnacle Studio 12 Ultimate for free, you might be tempted to look for a cracked version online. However, this is not a good idea, as cracked software can be unsafe, illegal, and unreliable. You might end up with malware, viruses, or other problems that can harm your computer or compromise your privacy. Moreover, you will not be able to access the official updates, support, and tutorials from Pinnacle.</p>
-<p>The best way to get Pinnacle Studio 12 Ultimate for free is to use the trial version that is available on the official website[^1^]. The trial version lets you use the software for 30 days without any limitations or watermarks. You can explore all the features and functions of Pinnacle Studio 12 Ultimate and see if it suits your needs and preferences. You can also access the online help and user guide from within the software.</p>
-<p>To download and install the trial version of Pinnacle Studio 12 Ultimate, follow these steps:</p>
-<ol>
-<li>Go to <a href="https://www.pinnaclesys.com/en/products/studio/trial/">https://www.pinnaclesys.com/en/products/studio/trial/</a> and click on the "Download Now" button.</li>
-<li>Fill in your name and email address and click on "Start Download". You will receive an email with a download link and a serial number.</li>
-<li>Click on the download link in the email and save the file to your computer.</li>
-<li>Double-click on the downloaded file and follow the instructions to install Pinnacle Studio 12 Ultimate.</li>
-<li>When prompted, enter the serial number that you received in the email.</li>
-<li>Launch Pinnacle Studio 12 Ultimate and enjoy your free trial.</li>
-</ol>
-<p>If you like Pinnacle Studio 12 Ultimate and want to continue using it after the trial period expires, you can purchase a license from the official website or from an authorized reseller. You will receive a new serial number that will activate your software permanently. You will also be able to access the latest updates, support, and tutorials from Pinnacle.</p>
-<p>Pinnacle Studio 12 Ultimate is a great video editing software that can help you create amazing videos with ease. However, downloading a cracked version is not worth the risk. Instead, try the free trial version and see for yourself what Pinnacle Studio 12 Ultimate can do for you.</p>
-
-<p>Pinnacle Studio 12 Ultimate is not the only video editing software that you can try for free. There are other alternatives that you can download and install on your computer, such as Adobe Premiere Pro, Sony Vegas Pro, or DaVinci Resolve. These software also offer advanced features and capabilities for video editing, such as color grading, motion graphics, audio mixing, and more. However, they might have different interfaces, workflows, and requirements than Pinnacle Studio 12 Ultimate. You might need to spend some time learning how to use them and see if they match your expectations and needs.</p>
-<p></p>
-<p>Another option that you can consider is to use online video editing tools, such as WeVideo, Clipchamp, or Kapwing. These tools allow you to edit your videos directly on your browser, without having to download or install anything on your computer. They also offer a range of features and functions for video editing, such as transitions, filters, text, music, and more. However, they might have some limitations in terms of file size, quality, speed, and customization. You might also need to create an account and pay a subscription fee to access some of the premium features and options.</p>
-<p>Ultimately, the best video editing software for you depends on your personal preferences, goals, and budget. You should try different options and compare their pros and cons before making a final decision. You should also look for reviews, ratings, and feedback from other users who have used the software that you are interested in. This way, you can get a better idea of what to expect and what to avoid when using the software.</p> 7b8c122e87<br />
-<br />
-<br />
\ No newline at end of file
diff --git a/spaces/sub314xxl/MetaGPT/metagpt/inspect_module.py b/spaces/sub314xxl/MetaGPT/metagpt/inspect_module.py
deleted file mode 100644
index fcdd4f0b720da3a526db16e9337b12e6f93a852b..0000000000000000000000000000000000000000
--- a/spaces/sub314xxl/MetaGPT/metagpt/inspect_module.py
+++ /dev/null
@@ -1,28 +0,0 @@
-#!/usr/bin/env python
-# -*- coding: utf-8 -*-
-"""
-@Time    : 2023/5/28 14:54
-@Author  : alexanderwu
-@File    : inspect_module.py
-"""
-
-import inspect
-
-import metagpt  # replace with your module
-
-
-def print_classes_and_functions(module):
-    """FIXME: NOT WORK.. """
-    for name, obj in inspect.getmembers(module):
-        if inspect.isclass(obj):
-            print(f'Class: {name}')
-        elif inspect.isfunction(obj):
-            print(f'Function: {name}')
-        else:
-            print(name)
-
-    print(dir(module))
-
-
-if __name__ == '__main__':
-    print_classes_and_functions(metagpt)
diff --git a/spaces/sub314xxl/MetaGPT/metagpt/static/assets/vue-e0bc46a9.js b/spaces/sub314xxl/MetaGPT/metagpt/static/assets/vue-e0bc46a9.js
deleted file mode 100644
index ac16c5935d37a113c4a4e92bce50dab25973aec9..0000000000000000000000000000000000000000
--- a/spaces/sub314xxl/MetaGPT/metagpt/static/assets/vue-e0bc46a9.js
+++ /dev/null
@@ -1,5 +0,0 @@
-function ls(e,t){const n=Object.create(null),s=e.split(",");for(let r=0;r<s.length;r++)n[s[r]]=!0;return t?r=>!!n[r.toLowerCase()]:r=>!!n[r]}const ie={},$t=[],He=()=>{},$l=()=>!1,jl=/^on[^a-z]/,An=e=>jl.test(e),fr=e=>e.startsWith("onUpdate:"),ue=Object.assign,ar=(e,t)=>{const n=e.indexOf(t);n>-1&&e.splice(n,1)},Ul=Object.prototype.hasOwnProperty,ee=(e,t)=>Ul.call(e,t),D=Array.isArray,jt=e=>Xt(e)==="[object Map]",It=e=>Xt(e)==="[object Set]",zr=e=>Xt(e)==="[object Date]",Kl=e=>Xt(e)==="[object RegExp]",Q=e=>typeof e=="function",ae=e=>typeof e=="string",yn=e=>typeof e=="symbol",le=e=>e!==null&&typeof e=="object",dr=e=>le(e)&&Q(e.then)&&Q(e.catch),Qo=Object.prototype.toString,Xt=e=>Qo.call(e),Vl=e=>Xt(e).slice(8,-1),Jo=e=>Xt(e)==="[object Object]",hr=e=>ae(e)&&e!=="NaN"&&e[0]!=="-"&&""+parseInt(e,10)===e,un=ls(",key,ref,ref_for,ref_key,onVnodeBeforeMount,onVnodeMounted,onVnodeBeforeUpdate,onVnodeUpdated,onVnodeBeforeUnmount,onVnodeUnmounted"),cs=e=>{const t=Object.create(null);return n=>t[n]||(t[n]=e(n))},Wl=/-(\w)/g,Te=cs(e=>e.replace(Wl,(t,n)=>n?n.toUpperCase():"")),ql=/\B([A-Z])/g,Fe=cs(e=>e.replace(ql,"-$1").toLowerCase()),Sn=cs(e=>e.charAt(0).toUpperCase()+e.slice(1)),fn=cs(e=>e?`on${Sn(e)}`:""),Wt=(e,t)=>!Object.is(e,t),Ut=(e,t)=>{for(let n=0;n<e.length;n++)e[n](t)},Xn=(e,t,n)=>{Object.defineProperty(e,t,{configurable:!0,enumerable:!1,value:n})},Zn=e=>{const t=parseFloat(e);return isNaN(t)?e:t},Gn=e=>{const t=ae(e)?Number(e):NaN;return isNaN(t)?e:t};let Yr;const Us=()=>Yr||(Yr=typeof globalThis<"u"?globalThis:typeof self<"u"?self:typeof window<"u"?window:typeof global<"u"?global:{}),zl="Infinity,undefined,NaN,isFinite,isNaN,parseFloat,parseInt,decodeURI,decodeURIComponent,encodeURI,encodeURIComponent,Math,Number,Date,Array,Object,Boolean,String,RegExp,Map,Set,JSON,Intl,BigInt,console",Yl=ls(zl);function On(e){if(D(e)){const t={};for(let n=0;n<e.length;n++){const s=e[n],r=ae(s)?Zl(s):On(s);if(r)for(const o in r)t[o]=r[o]}return t}else{if(ae(e))return e;if(le(e))return e}}const Ql=/;(?![^(]*\))/g,Jl=/:([^]+)/,Xl=/\/\*[^]*?\*\//g;function Zl(e){const t={};return e.replace(Xl,"").split(Ql).forEach(n=>{if(n){const s=n.split(Jl);s.length>1&&(t[s[0].trim()]=s[1].trim())}}),t}function Mn(e){let t="";if(ae(e))t=e;else if(D(e))for(let n=0;n<e.length;n++){const s=Mn(e[n]);s&&(t+=s+" ")}else if(le(e))for(const n in e)e[n]&&(t+=n+" ");return t.trim()}function Gl(e){if(!e)return null;let{class:t,style:n}=e;return t&&!ae(t)&&(e.class=Mn(t)),n&&(e.style=On(n)),e}const ec="itemscope,allowfullscreen,formnovalidate,ismap,nomodule,novalidate,readonly",tc=ls(ec);function Xo(e){return!!e||e===""}function nc(e,t){if(e.length!==t.length)return!1;let n=!0;for(let s=0;n&&s<e.length;s++)n=ht(e[s],t[s]);return n}function ht(e,t){if(e===t)return!0;let n=zr(e),s=zr(t);if(n||s)return n&&s?e.getTime()===t.getTime():!1;if(n=yn(e),s=yn(t),n||s)return e===t;if(n=D(e),s=D(t),n||s)return n&&s?nc(e,t):!1;if(n=le(e),s=le(t),n||s){if(!n||!s)return!1;const r=Object.keys(e).length,o=Object.keys(t).length;if(r!==o)return!1;for(const i in e){const l=e.hasOwnProperty(i),c=t.hasOwnProperty(i);if(l&&!c||!l&&c||!ht(e[i],t[i]))return!1}}return String(e)===String(t)}function us(e,t){return e.findIndex(n=>ht(n,t))}const sc=e=>ae(e)?e:e==null?"":D(e)||le(e)&&(e.toString===Qo||!Q(e.toString))?JSON.stringify(e,Zo,2):String(e),Zo=(e,t)=>t&&t.__v_isRef?Zo(e,t.value):jt(t)?{[`Map(${t.size})`]:[...t.entries()].reduce((n,[s,r])=>(n[`${s} =>`]=r,n),{})}:It(t)?{[`Set(${t.size})`]:[...t.values()]}:le(t)&&!D(t)&&!Jo(t)?String(t):t;let Se;class pr{constructor(t=!1){this.detached=t,this._active=!0,this.effects=[],this.cleanups=[],this.parent=Se,!t&&Se&&(this.index=(Se.scopes||(Se.scopes=[])).push(this)-1)}get active(){return this._active}run(t){if(this._active){const n=Se;try{return Se=this,t()}finally{Se=n}}}on(){Se=this}off(){Se=this.parent}stop(t){if(this._active){let n,s;for(n=0,s=this.effects.length;n<s;n++)this.effects[n].stop();for(n=0,s=this.cleanups.length;n<s;n++)this.cleanups[n]();if(this.scopes)for(n=0,s=this.scopes.length;n<s;n++)this.scopes[n].stop(!0);if(!this.detached&&this.parent&&!t){const r=this.parent.scopes.pop();r&&r!==this&&(this.parent.scopes[this.index]=r,r.index=this.index)}this.parent=void 0,this._active=!1}}}function rc(e){return new pr(e)}function Go(e,t=Se){t&&t.active&&t.effects.push(e)}function ei(){return Se}function oc(e){Se&&Se.cleanups.push(e)}const gr=e=>{const t=new Set(e);return t.w=0,t.n=0,t},ti=e=>(e.w&pt)>0,ni=e=>(e.n&pt)>0,ic=({deps:e})=>{if(e.length)for(let t=0;t<e.length;t++)e[t].w|=pt},lc=e=>{const{deps:t}=e;if(t.length){let n=0;for(let s=0;s<t.length;s++){const r=t[s];ti(r)&&!ni(r)?r.delete(e):t[n++]=r,r.w&=~pt,r.n&=~pt}t.length=n}},es=new WeakMap;let on=0,pt=1;const Ks=30;let Le;const wt=Symbol(""),Vs=Symbol("");class In{constructor(t,n=null,s){this.fn=t,this.scheduler=n,this.active=!0,this.deps=[],this.parent=void 0,Go(this,s)}run(){if(!this.active)return this.fn();let t=Le,n=ut;for(;t;){if(t===this)return;t=t.parent}try{return this.parent=Le,Le=this,ut=!0,pt=1<<++on,on<=Ks?ic(this):Qr(this),this.fn()}finally{on<=Ks&&lc(this),pt=1<<--on,Le=this.parent,ut=n,this.parent=void 0,this.deferStop&&this.stop()}}stop(){Le===this?this.deferStop=!0:this.active&&(Qr(this),this.onStop&&this.onStop(),this.active=!1)}}function Qr(e){const{deps:t}=e;if(t.length){for(let n=0;n<t.length;n++)t[n].delete(e);t.length=0}}function cc(e,t){e.effect&&(e=e.effect.fn);const n=new In(e);t&&(ue(n,t),t.scope&&Go(n,t.scope)),(!t||!t.lazy)&&n.run();const s=n.run.bind(n);return s.effect=n,s}function uc(e){e.effect.stop()}let ut=!0;const si=[];function Zt(){si.push(ut),ut=!1}function Gt(){const e=si.pop();ut=e===void 0?!0:e}function Pe(e,t,n){if(ut&&Le){let s=es.get(e);s||es.set(e,s=new Map);let r=s.get(n);r||s.set(n,r=gr()),ri(r)}}function ri(e,t){let n=!1;on<=Ks?ni(e)||(e.n|=pt,n=!ti(e)):n=!e.has(Le),n&&(e.add(Le),Le.deps.push(e))}function Ze(e,t,n,s,r,o){const i=es.get(e);if(!i)return;let l=[];if(t==="clear")l=[...i.values()];else if(n==="length"&&D(e)){const c=Number(s);i.forEach((u,f)=>{(f==="length"||f>=c)&&l.push(u)})}else switch(n!==void 0&&l.push(i.get(n)),t){case"add":D(e)?hr(n)&&l.push(i.get("length")):(l.push(i.get(wt)),jt(e)&&l.push(i.get(Vs)));break;case"delete":D(e)||(l.push(i.get(wt)),jt(e)&&l.push(i.get(Vs)));break;case"set":jt(e)&&l.push(i.get(wt));break}if(l.length===1)l[0]&&Ws(l[0]);else{const c=[];for(const u of l)u&&c.push(...u);Ws(gr(c))}}function Ws(e,t){const n=D(e)?e:[...e];for(const s of n)s.computed&&Jr(s);for(const s of n)s.computed||Jr(s)}function Jr(e,t){(e!==Le||e.allowRecurse)&&(e.scheduler?e.scheduler():e.run())}function fc(e,t){var n;return(n=es.get(e))==null?void 0:n.get(t)}const ac=ls("__proto__,__v_isRef,__isVue"),oi=new Set(Object.getOwnPropertyNames(Symbol).filter(e=>e!=="arguments"&&e!=="caller").map(e=>Symbol[e]).filter(yn)),dc=fs(),hc=fs(!1,!0),pc=fs(!0),gc=fs(!0,!0),Xr=mc();function mc(){const e={};return["includes","indexOf","lastIndexOf"].forEach(t=>{e[t]=function(...n){const s=Z(this);for(let o=0,i=this.length;o<i;o++)Pe(s,"get",o+"");const r=s[t](...n);return r===-1||r===!1?s[t](...n.map(Z)):r}}),["push","pop","shift","unshift","splice"].forEach(t=>{e[t]=function(...n){Zt();const s=Z(this)[t].apply(this,n);return Gt(),s}}),e}function _c(e){const t=Z(this);return Pe(t,"has",e),t.hasOwnProperty(e)}function fs(e=!1,t=!1){return function(s,r,o){if(r==="__v_isReactive")return!e;if(r==="__v_isReadonly")return e;if(r==="__v_isShallow")return t;if(r==="__v_raw"&&o===(e?t?di:ai:t?fi:ui).get(s))return s;const i=D(s);if(!e){if(i&&ee(Xr,r))return Reflect.get(Xr,r,o);if(r==="hasOwnProperty")return _c}const l=Reflect.get(s,r,o);return(yn(r)?oi.has(r):ac(r))||(e||Pe(s,"get",r),t)?l:ge(l)?i&&hr(r)?l:l.value:le(l)?e?_r(l):en(l):l}}const yc=ii(),bc=ii(!0);function ii(e=!1){return function(n,s,r,o){let i=n[s];if(At(i)&&ge(i)&&!ge(r))return!1;if(!e&&(!bn(r)&&!At(r)&&(i=Z(i),r=Z(r)),!D(n)&&ge(i)&&!ge(r)))return i.value=r,!0;const l=D(n)&&hr(s)?Number(s)<n.length:ee(n,s),c=Reflect.set(n,s,r,o);return n===Z(o)&&(l?Wt(r,i)&&Ze(n,"set",s,r):Ze(n,"add",s,r)),c}}function vc(e,t){const n=ee(e,t);e[t];const s=Reflect.deleteProperty(e,t);return s&&n&&Ze(e,"delete",t,void 0),s}function Ec(e,t){const n=Reflect.has(e,t);return(!yn(t)||!oi.has(t))&&Pe(e,"has",t),n}function Cc(e){return Pe(e,"iterate",D(e)?"length":wt),Reflect.ownKeys(e)}const li={get:dc,set:yc,deleteProperty:vc,has:Ec,ownKeys:Cc},ci={get:pc,set(e,t){return!0},deleteProperty(e,t){return!0}},wc=ue({},li,{get:hc,set:bc}),xc=ue({},ci,{get:gc}),mr=e=>e,as=e=>Reflect.getPrototypeOf(e);function Hn(e,t,n=!1,s=!1){e=e.__v_raw;const r=Z(e),o=Z(t);n||(t!==o&&Pe(r,"get",t),Pe(r,"get",o));const{has:i}=as(r),l=s?mr:n?vr:vn;if(i.call(r,t))return l(e.get(t));if(i.call(r,o))return l(e.get(o));e!==r&&e.get(t)}function Dn(e,t=!1){const n=this.__v_raw,s=Z(n),r=Z(e);return t||(e!==r&&Pe(s,"has",e),Pe(s,"has",r)),e===r?n.has(e):n.has(e)||n.has(r)}function $n(e,t=!1){return e=e.__v_raw,!t&&Pe(Z(e),"iterate",wt),Reflect.get(e,"size",e)}function Zr(e){e=Z(e);const t=Z(this);return as(t).has.call(t,e)||(t.add(e),Ze(t,"add",e,e)),this}function Gr(e,t){t=Z(t);const n=Z(this),{has:s,get:r}=as(n);let o=s.call(n,e);o||(e=Z(e),o=s.call(n,e));const i=r.call(n,e);return n.set(e,t),o?Wt(t,i)&&Ze(n,"set",e,t):Ze(n,"add",e,t),this}function eo(e){const t=Z(this),{has:n,get:s}=as(t);let r=n.call(t,e);r||(e=Z(e),r=n.call(t,e)),s&&s.call(t,e);const o=t.delete(e);return r&&Ze(t,"delete",e,void 0),o}function to(){const e=Z(this),t=e.size!==0,n=e.clear();return t&&Ze(e,"clear",void 0,void 0),n}function jn(e,t){return function(s,r){const o=this,i=o.__v_raw,l=Z(i),c=t?mr:e?vr:vn;return!e&&Pe(l,"iterate",wt),i.forEach((u,f)=>s.call(r,c(u),c(f),o))}}function Un(e,t,n){return function(...s){const r=this.__v_raw,o=Z(r),i=jt(o),l=e==="entries"||e===Symbol.iterator&&i,c=e==="keys"&&i,u=r[e](...s),f=n?mr:t?vr:vn;return!t&&Pe(o,"iterate",c?Vs:wt),{next(){const{value:a,done:p}=u.next();return p?{value:a,done:p}:{value:l?[f(a[0]),f(a[1])]:f(a),done:p}},[Symbol.iterator](){return this}}}}function nt(e){return function(...t){return e==="delete"?!1:this}}function Rc(){const e={get(o){return Hn(this,o)},get size(){return $n(this)},has:Dn,add:Zr,set:Gr,delete:eo,clear:to,forEach:jn(!1,!1)},t={get(o){return Hn(this,o,!1,!0)},get size(){return $n(this)},has:Dn,add:Zr,set:Gr,delete:eo,clear:to,forEach:jn(!1,!0)},n={get(o){return Hn(this,o,!0)},get size(){return $n(this,!0)},has(o){return Dn.call(this,o,!0)},add:nt("add"),set:nt("set"),delete:nt("delete"),clear:nt("clear"),forEach:jn(!0,!1)},s={get(o){return Hn(this,o,!0,!0)},get size(){return $n(this,!0)},has(o){return Dn.call(this,o,!0)},add:nt("add"),set:nt("set"),delete:nt("delete"),clear:nt("clear"),forEach:jn(!0,!0)};return["keys","values","entries",Symbol.iterator].forEach(o=>{e[o]=Un(o,!1,!1),n[o]=Un(o,!0,!1),t[o]=Un(o,!1,!0),s[o]=Un(o,!0,!0)}),[e,n,t,s]}const[Tc,Pc,Ac,Sc]=Rc();function ds(e,t){const n=t?e?Sc:Ac:e?Pc:Tc;return(s,r,o)=>r==="__v_isReactive"?!e:r==="__v_isReadonly"?e:r==="__v_raw"?s:Reflect.get(ee(n,r)&&r in s?n:s,r,o)}const Oc={get:ds(!1,!1)},Mc={get:ds(!1,!0)},Ic={get:ds(!0,!1)},kc={get:ds(!0,!0)},ui=new WeakMap,fi=new WeakMap,ai=new WeakMap,di=new WeakMap;function Fc(e){switch(e){case"Object":case"Array":return 1;case"Map":case"Set":case"WeakMap":case"WeakSet":return 2;default:return 0}}function Nc(e){return e.__v_skip||!Object.isExtensible(e)?0:Fc(Vl(e))}function en(e){return At(e)?e:hs(e,!1,li,Oc,ui)}function hi(e){return hs(e,!1,wc,Mc,fi)}function _r(e){return hs(e,!0,ci,Ic,ai)}function Lc(e){return hs(e,!0,xc,kc,di)}function hs(e,t,n,s,r){if(!le(e)||e.__v_raw&&!(t&&e.__v_isReactive))return e;const o=r.get(e);if(o)return o;const i=Nc(e);if(i===0)return e;const l=new Proxy(e,i===2?s:n);return r.set(e,l),l}function xt(e){return At(e)?xt(e.__v_raw):!!(e&&e.__v_isReactive)}function At(e){return!!(e&&e.__v_isReadonly)}function bn(e){return!!(e&&e.__v_isShallow)}function yr(e){return xt(e)||At(e)}function Z(e){const t=e&&e.__v_raw;return t?Z(t):e}function br(e){return Xn(e,"__v_skip",!0),e}const vn=e=>le(e)?en(e):e,vr=e=>le(e)?_r(e):e;function Er(e){ut&&Le&&(e=Z(e),ri(e.dep||(e.dep=gr())))}function ps(e,t){e=Z(e);const n=e.dep;n&&Ws(n)}function ge(e){return!!(e&&e.__v_isRef===!0)}function Rt(e){return gi(e,!1)}function pi(e){return gi(e,!0)}function gi(e,t){return ge(e)?e:new Bc(e,t)}class Bc{constructor(t,n){this.__v_isShallow=n,this.dep=void 0,this.__v_isRef=!0,this._rawValue=n?t:Z(t),this._value=n?t:vn(t)}get value(){return Er(this),this._value}set value(t){const n=this.__v_isShallow||bn(t)||At(t);t=n?t:Z(t),Wt(t,this._rawValue)&&(this._rawValue=t,this._value=n?t:vn(t),ps(this))}}function Hc(e){ps(e)}function ft(e){return ge(e)?e.value:e}function Dc(e){return Q(e)?e():ft(e)}const $c={get:(e,t,n)=>ft(Reflect.get(e,t,n)),set:(e,t,n,s)=>{const r=e[t];return ge(r)&&!ge(n)?(r.value=n,!0):Reflect.set(e,t,n,s)}};function Cr(e){return xt(e)?e:new Proxy(e,$c)}class jc{constructor(t){this.dep=void 0,this.__v_isRef=!0;const{get:n,set:s}=t(()=>Er(this),()=>ps(this));this._get=n,this._set=s}get value(){return this._get()}set value(t){this._set(t)}}function Uc(e){return new jc(e)}function Kc(e){const t=D(e)?new Array(e.length):{};for(const n in e)t[n]=mi(e,n);return t}class Vc{constructor(t,n,s){this._object=t,this._key=n,this._defaultValue=s,this.__v_isRef=!0}get value(){const t=this._object[this._key];return t===void 0?this._defaultValue:t}set value(t){this._object[this._key]=t}get dep(){return fc(Z(this._object),this._key)}}class Wc{constructor(t){this._getter=t,this.__v_isRef=!0,this.__v_isReadonly=!0}get value(){return this._getter()}}function qc(e,t,n){return ge(e)?e:Q(e)?new Wc(e):le(e)&&arguments.length>1?mi(e,t,n):Rt(e)}function mi(e,t,n){const s=e[t];return ge(s)?s:new Vc(e,t,n)}class zc{constructor(t,n,s,r){this._setter=n,this.dep=void 0,this.__v_isRef=!0,this.__v_isReadonly=!1,this._dirty=!0,this.effect=new In(t,()=>{this._dirty||(this._dirty=!0,ps(this))}),this.effect.computed=this,this.effect.active=this._cacheable=!r,this.__v_isReadonly=s}get value(){const t=Z(this);return Er(t),(t._dirty||!t._cacheable)&&(t._dirty=!1,t._value=t.effect.run()),t._value}set value(t){this._setter(t)}}function Yc(e,t,n=!1){let s,r;const o=Q(e);return o?(s=e,r=He):(s=e.get,r=e.set),new zc(s,r,o||!r,n)}function Qc(e,...t){}function Jc(e,t){}function Xe(e,t,n,s){let r;try{r=s?e(...s):e()}catch(o){kt(o,t,n)}return r}function Ie(e,t,n,s){if(Q(e)){const o=Xe(e,t,n,s);return o&&dr(o)&&o.catch(i=>{kt(i,t,n)}),o}const r=[];for(let o=0;o<e.length;o++)r.push(Ie(e[o],t,n,s));return r}function kt(e,t,n,s=!0){const r=t?t.vnode:null;if(t){let o=t.parent;const i=t.proxy,l=n;for(;o;){const u=o.ec;if(u){for(let f=0;f<u.length;f++)if(u[f](e,i,l)===!1)return}o=o.parent}const c=t.appContext.config.errorHandler;if(c){Xe(c,null,10,[e,i,l]);return}}Xc(e,n,r,s)}function Xc(e,t,n,s=!0){console.error(e)}let En=!1,qs=!1;const ve=[];let Ve=0;const Kt=[];let Qe=null,vt=0;const _i=Promise.resolve();let wr=null;function gs(e){const t=wr||_i;return e?t.then(this?e.bind(this):e):t}function Zc(e){let t=Ve+1,n=ve.length;for(;t<n;){const s=t+n>>>1;Cn(ve[s])<e?t=s+1:n=s}return t}function ms(e){(!ve.length||!ve.includes(e,En&&e.allowRecurse?Ve+1:Ve))&&(e.id==null?ve.push(e):ve.splice(Zc(e.id),0,e),yi())}function yi(){!En&&!qs&&(qs=!0,wr=_i.then(bi))}function Gc(e){const t=ve.indexOf(e);t>Ve&&ve.splice(t,1)}function xr(e){D(e)?Kt.push(...e):(!Qe||!Qe.includes(e,e.allowRecurse?vt+1:vt))&&Kt.push(e),yi()}function no(e,t=En?Ve+1:0){for(;t<ve.length;t++){const n=ve[t];n&&n.pre&&(ve.splice(t,1),t--,n())}}function ts(e){if(Kt.length){const t=[...new Set(Kt)];if(Kt.length=0,Qe){Qe.push(...t);return}for(Qe=t,Qe.sort((n,s)=>Cn(n)-Cn(s)),vt=0;vt<Qe.length;vt++)Qe[vt]();Qe=null,vt=0}}const Cn=e=>e.id==null?1/0:e.id,eu=(e,t)=>{const n=Cn(e)-Cn(t);if(n===0){if(e.pre&&!t.pre)return-1;if(t.pre&&!e.pre)return 1}return n};function bi(e){qs=!1,En=!0,ve.sort(eu);const t=He;try{for(Ve=0;Ve<ve.length;Ve++){const n=ve[Ve];n&&n.active!==!1&&Xe(n,null,14)}}finally{Ve=0,ve.length=0,ts(),En=!1,wr=null,(ve.length||Kt.length)&&bi()}}let Ht,Kn=[];function vi(e,t){var n,s;Ht=e,Ht?(Ht.enabled=!0,Kn.forEach(({event:r,args:o})=>Ht.emit(r,...o)),Kn=[]):typeof window<"u"&&window.HTMLElement&&!((s=(n=window.navigator)==null?void 0:n.userAgent)!=null&&s.includes("jsdom"))?((t.__VUE_DEVTOOLS_HOOK_REPLAY__=t.__VUE_DEVTOOLS_HOOK_REPLAY__||[]).push(o=>{vi(o,t)}),setTimeout(()=>{Ht||(t.__VUE_DEVTOOLS_HOOK_REPLAY__=null,Kn=[])},3e3)):Kn=[]}function tu(e,t,...n){if(e.isUnmounted)return;const s=e.vnode.props||ie;let r=n;const o=t.startsWith("update:"),i=o&&t.slice(7);if(i&&i in s){const f=`${i==="modelValue"?"model":i}Modifiers`,{number:a,trim:p}=s[f]||ie;p&&(r=n.map(y=>ae(y)?y.trim():y)),a&&(r=n.map(Zn))}let l,c=s[l=fn(t)]||s[l=fn(Te(t))];!c&&o&&(c=s[l=fn(Fe(t))]),c&&Ie(c,e,6,r);const u=s[l+"Once"];if(u){if(!e.emitted)e.emitted={};else if(e.emitted[l])return;e.emitted[l]=!0,Ie(u,e,6,r)}}function Ei(e,t,n=!1){const s=t.emitsCache,r=s.get(e);if(r!==void 0)return r;const o=e.emits;let i={},l=!1;if(!Q(e)){const c=u=>{const f=Ei(u,t,!0);f&&(l=!0,ue(i,f))};!n&&t.mixins.length&&t.mixins.forEach(c),e.extends&&c(e.extends),e.mixins&&e.mixins.forEach(c)}return!o&&!l?(le(e)&&s.set(e,null),null):(D(o)?o.forEach(c=>i[c]=null):ue(i,o),le(e)&&s.set(e,i),i)}function _s(e,t){return!e||!An(t)?!1:(t=t.slice(2).replace(/Once$/,""),ee(e,t[0].toLowerCase()+t.slice(1))||ee(e,Fe(t))||ee(e,t))}let me=null,ys=null;function wn(e){const t=me;return me=e,ys=e&&e.type.__scopeId||null,t}function nu(e){ys=e}function su(){ys=null}const ru=e=>Rr;function Rr(e,t=me,n){if(!t||e._n)return e;const s=(...r)=>{s._d&&Gs(-1);const o=wn(t);let i;try{i=e(...r)}finally{wn(o),s._d&&Gs(1)}return i};return s._n=!0,s._c=!0,s._d=!0,s}function Qn(e){const{type:t,vnode:n,proxy:s,withProxy:r,props:o,propsOptions:[i],slots:l,attrs:c,emit:u,render:f,renderCache:a,data:p,setupState:y,ctx:E,inheritAttrs:A}=e;let k,b;const g=wn(e);try{if(n.shapeFlag&4){const _=r||s;k=Oe(f.call(_,_,a,o,y,p,E)),b=c}else{const _=t;k=Oe(_.length>1?_(o,{attrs:c,slots:l,emit:u}):_(o,null)),b=t.props?c:iu(c)}}catch(_){pn.length=0,kt(_,e,1),k=fe(Ee)}let R=k;if(b&&A!==!1){const _=Object.keys(b),{shapeFlag:S}=R;_.length&&S&7&&(i&&_.some(fr)&&(b=lu(b,i)),R=We(R,b))}return n.dirs&&(R=We(R),R.dirs=R.dirs?R.dirs.concat(n.dirs):n.dirs),n.transition&&(R.transition=n.transition),k=R,wn(g),k}function ou(e){let t;for(let n=0;n<e.length;n++){const s=e[n];if(gt(s)){if(s.type!==Ee||s.children==="v-if"){if(t)return;t=s}}else return}return t}const iu=e=>{let t;for(const n in e)(n==="class"||n==="style"||An(n))&&((t||(t={}))[n]=e[n]);return t},lu=(e,t)=>{const n={};for(const s in e)(!fr(s)||!(s.slice(9)in t))&&(n[s]=e[s]);return n};function cu(e,t,n){const{props:s,children:r,component:o}=e,{props:i,children:l,patchFlag:c}=t,u=o.emitsOptions;if(t.dirs||t.transition)return!0;if(n&&c>=0){if(c&1024)return!0;if(c&16)return s?so(s,i,u):!!i;if(c&8){const f=t.dynamicProps;for(let a=0;a<f.length;a++){const p=f[a];if(i[p]!==s[p]&&!_s(u,p))return!0}}}else return(r||l)&&(!l||!l.$stable)?!0:s===i?!1:s?i?so(s,i,u):!0:!!i;return!1}function so(e,t,n){const s=Object.keys(t);if(s.length!==Object.keys(e).length)return!0;for(let r=0;r<s.length;r++){const o=s[r];if(t[o]!==e[o]&&!_s(n,o))return!0}return!1}function Tr({vnode:e,parent:t},n){for(;t&&t.subTree===e;)(e=t.vnode).el=n,t=t.parent}const Ci=e=>e.__isSuspense,uu={name:"Suspense",__isSuspense:!0,process(e,t,n,s,r,o,i,l,c,u){e==null?au(t,n,s,r,o,i,l,c,u):du(e,t,n,s,r,i,l,c,u)},hydrate:hu,create:Pr,normalize:pu},fu=uu;function xn(e,t){const n=e.props&&e.props[t];Q(n)&&n()}function au(e,t,n,s,r,o,i,l,c){const{p:u,o:{createElement:f}}=c,a=f("div"),p=e.suspense=Pr(e,r,s,t,a,n,o,i,l,c);u(null,p.pendingBranch=e.ssContent,a,null,s,p,o,i),p.deps>0?(xn(e,"onPending"),xn(e,"onFallback"),u(null,e.ssFallback,t,n,s,null,o,i),Vt(p,e.ssFallback)):p.resolve(!1,!0)}function du(e,t,n,s,r,o,i,l,{p:c,um:u,o:{createElement:f}}){const a=t.suspense=e.suspense;a.vnode=t,t.el=e.el;const p=t.ssContent,y=t.ssFallback,{activeBranch:E,pendingBranch:A,isInFallback:k,isHydrating:b}=a;if(A)a.pendingBranch=p,Be(p,A)?(c(A,p,a.hiddenContainer,null,r,a,o,i,l),a.deps<=0?a.resolve():k&&(c(E,y,n,s,r,null,o,i,l),Vt(a,y))):(a.pendingId++,b?(a.isHydrating=!1,a.activeBranch=A):u(A,r,a),a.deps=0,a.effects.length=0,a.hiddenContainer=f("div"),k?(c(null,p,a.hiddenContainer,null,r,a,o,i,l),a.deps<=0?a.resolve():(c(E,y,n,s,r,null,o,i,l),Vt(a,y))):E&&Be(p,E)?(c(E,p,n,s,r,a,o,i,l),a.resolve(!0)):(c(null,p,a.hiddenContainer,null,r,a,o,i,l),a.deps<=0&&a.resolve()));else if(E&&Be(p,E))c(E,p,n,s,r,a,o,i,l),Vt(a,p);else if(xn(t,"onPending"),a.pendingBranch=p,a.pendingId++,c(null,p,a.hiddenContainer,null,r,a,o,i,l),a.deps<=0)a.resolve();else{const{timeout:g,pendingId:R}=a;g>0?setTimeout(()=>{a.pendingId===R&&a.fallback(y)},g):g===0&&a.fallback(y)}}function Pr(e,t,n,s,r,o,i,l,c,u,f=!1){const{p:a,m:p,um:y,n:E,o:{parentNode:A,remove:k}}=u;let b;const g=gu(e);g&&t!=null&&t.pendingBranch&&(b=t.pendingId,t.deps++);const R=e.props?Gn(e.props.timeout):void 0,_={vnode:e,parent:t,parentComponent:n,isSVG:i,container:s,hiddenContainer:r,anchor:o,deps:0,pendingId:0,timeout:typeof R=="number"?R:-1,activeBranch:null,pendingBranch:null,isInFallback:!0,isHydrating:f,isUnmounted:!1,effects:[],resolve(S=!1,B=!1){const{vnode:N,activeBranch:x,pendingBranch:j,pendingId:U,effects:z,parentComponent:L,container:Y}=_;if(_.isHydrating)_.isHydrating=!1;else if(!S){const G=x&&j.transition&&j.transition.mode==="out-in";G&&(x.transition.afterLeave=()=>{U===_.pendingId&&p(j,Y,te,0)});let{anchor:te}=_;x&&(te=E(x),y(x,L,_,!0)),G||p(j,Y,te,0)}Vt(_,j),_.pendingBranch=null,_.isInFallback=!1;let $=_.parent,de=!1;for(;$;){if($.pendingBranch){$.effects.push(...z),de=!0;break}$=$.parent}de||xr(z),_.effects=[],g&&t&&t.pendingBranch&&b===t.pendingId&&(t.deps--,t.deps===0&&!B&&t.resolve()),xn(N,"onResolve")},fallback(S){if(!_.pendingBranch)return;const{vnode:B,activeBranch:N,parentComponent:x,container:j,isSVG:U}=_;xn(B,"onFallback");const z=E(N),L=()=>{_.isInFallback&&(a(null,S,j,z,x,null,U,l,c),Vt(_,S))},Y=S.transition&&S.transition.mode==="out-in";Y&&(N.transition.afterLeave=L),_.isInFallback=!0,y(N,x,null,!0),Y||L()},move(S,B,N){_.activeBranch&&p(_.activeBranch,S,B,N),_.container=S},next(){return _.activeBranch&&E(_.activeBranch)},registerDep(S,B){const N=!!_.pendingBranch;N&&_.deps++;const x=S.vnode.el;S.asyncDep.catch(j=>{kt(j,S,0)}).then(j=>{if(S.isUnmounted||_.isUnmounted||_.pendingId!==S.suspenseId)return;S.asyncResolved=!0;const{vnode:U}=S;er(S,j,!1),x&&(U.el=x);const z=!x&&S.subTree.el;B(S,U,A(x||S.subTree.el),x?null:E(S.subTree),_,i,c),z&&k(z),Tr(S,U.el),N&&--_.deps===0&&_.resolve()})},unmount(S,B){_.isUnmounted=!0,_.activeBranch&&y(_.activeBranch,n,S,B),_.pendingBranch&&y(_.pendingBranch,n,S,B)}};return _}function hu(e,t,n,s,r,o,i,l,c){const u=t.suspense=Pr(t,s,n,e.parentNode,document.createElement("div"),null,r,o,i,l,!0),f=c(e,u.pendingBranch=t.ssContent,n,u,o,i);return u.deps===0&&u.resolve(!1,!0),f}function pu(e){const{shapeFlag:t,children:n}=e,s=t&32;e.ssContent=ro(s?n.default:n),e.ssFallback=s?ro(n.fallback):fe(Ee)}function ro(e){let t;if(Q(e)){const n=Mt&&e._c;n&&(e._d=!1,xs()),e=e(),n&&(e._d=!0,t=Re,Xi())}return D(e)&&(e=ou(e)),e=Oe(e),t&&!e.dynamicChildren&&(e.dynamicChildren=t.filter(n=>n!==e)),e}function wi(e,t){t&&t.pendingBranch?D(e)?t.effects.push(...e):t.effects.push(e):xr(e)}function Vt(e,t){e.activeBranch=t;const{vnode:n,parentComponent:s}=e,r=n.el=t.el;s&&s.subTree===n&&(s.vnode.el=r,Tr(s,r))}function gu(e){var t;return((t=e.props)==null?void 0:t.suspensible)!=null&&e.props.suspensible!==!1}function mu(e,t){return kn(e,null,t)}function xi(e,t){return kn(e,null,{flush:"post"})}function _u(e,t){return kn(e,null,{flush:"sync"})}const Vn={};function at(e,t,n){return kn(e,t,n)}function kn(e,t,{immediate:n,deep:s,flush:r,onTrack:o,onTrigger:i}=ie){var l;const c=ei()===((l=pe)==null?void 0:l.scope)?pe:null;let u,f=!1,a=!1;if(ge(e)?(u=()=>e.value,f=bn(e)):xt(e)?(u=()=>e,s=!0):D(e)?(a=!0,f=e.some(_=>xt(_)||bn(_)),u=()=>e.map(_=>{if(ge(_))return _.value;if(xt(_))return Ct(_);if(Q(_))return Xe(_,c,2)})):Q(e)?t?u=()=>Xe(e,c,2):u=()=>{if(!(c&&c.isUnmounted))return p&&p(),Ie(e,c,3,[y])}:u=He,t&&s){const _=u;u=()=>Ct(_())}let p,y=_=>{p=g.onStop=()=>{Xe(_,c,4)}},E;if(zt)if(y=He,t?n&&Ie(t,c,3,[u(),a?[]:void 0,y]):u(),r==="sync"){const _=cl();E=_.__watcherHandles||(_.__watcherHandles=[])}else return He;let A=a?new Array(e.length).fill(Vn):Vn;const k=()=>{if(g.active)if(t){const _=g.run();(s||f||(a?_.some((S,B)=>Wt(S,A[B])):Wt(_,A)))&&(p&&p(),Ie(t,c,3,[_,A===Vn?void 0:a&&A[0]===Vn?[]:A,y]),A=_)}else g.run()};k.allowRecurse=!!t;let b;r==="sync"?b=k:r==="post"?b=()=>_e(k,c&&c.suspense):(k.pre=!0,c&&(k.id=c.uid),b=()=>ms(k));const g=new In(u,b);t?n?k():A=g.run():r==="post"?_e(g.run.bind(g),c&&c.suspense):g.run();const R=()=>{g.stop(),c&&c.scope&&ar(c.scope.effects,g)};return E&&E.push(R),R}function yu(e,t,n){const s=this.proxy,r=ae(e)?e.includes(".")?Ri(s,e):()=>s[e]:e.bind(s,s);let o;Q(t)?o=t:(o=t.handler,n=t);const i=pe;mt(this);const l=kn(r,o.bind(s),n);return i?mt(i):dt(),l}function Ri(e,t){const n=t.split(".");return()=>{let s=e;for(let r=0;r<n.length&&s;r++)s=s[n[r]];return s}}function Ct(e,t){if(!le(e)||e.__v_skip||(t=t||new Set,t.has(e)))return e;if(t.add(e),ge(e))Ct(e.value,t);else if(D(e))for(let n=0;n<e.length;n++)Ct(e[n],t);else if(It(e)||jt(e))e.forEach(n=>{Ct(n,t)});else if(Jo(e))for(const n in e)Ct(e[n],t);return e}function bu(e,t){const n=me;if(n===null)return e;const s=Ts(n)||n.proxy,r=e.dirs||(e.dirs=[]);for(let o=0;o<t.length;o++){let[i,l,c,u=ie]=t[o];i&&(Q(i)&&(i={mounted:i,updated:i}),i.deep&&Ct(l),r.push({dir:i,instance:s,value:l,oldValue:void 0,arg:c,modifiers:u}))}return e}function Ke(e,t,n,s){const r=e.dirs,o=t&&t.dirs;for(let i=0;i<r.length;i++){const l=r[i];o&&(l.oldValue=o[i].value);let c=l.dir[s];c&&(Zt(),Ie(c,n,8,[e.el,l,e,t]),Gt())}}function Ar(){const e={isMounted:!1,isLeaving:!1,isUnmounting:!1,leavingVNodes:new Map};return Ln(()=>{e.isMounted=!0}),Cs(()=>{e.isUnmounting=!0}),e}const ke=[Function,Array],Sr={mode:String,appear:Boolean,persisted:Boolean,onBeforeEnter:ke,onEnter:ke,onAfterEnter:ke,onEnterCancelled:ke,onBeforeLeave:ke,onLeave:ke,onAfterLeave:ke,onLeaveCancelled:ke,onBeforeAppear:ke,onAppear:ke,onAfterAppear:ke,onAppearCancelled:ke},vu={name:"BaseTransition",props:Sr,setup(e,{slots:t}){const n=et(),s=Ar();let r;return()=>{const o=t.default&&bs(t.default(),!0);if(!o||!o.length)return;let i=o[0];if(o.length>1){for(const A of o)if(A.type!==Ee){i=A;break}}const l=Z(e),{mode:c}=l;if(s.isLeaving)return Ms(i);const u=oo(i);if(!u)return Ms(i);const f=qt(u,l,s,n);St(u,f);const a=n.subTree,p=a&&oo(a);let y=!1;const{getTransitionKey:E}=u.type;if(E){const A=E();r===void 0?r=A:A!==r&&(r=A,y=!0)}if(p&&p.type!==Ee&&(!Be(u,p)||y)){const A=qt(p,l,s,n);if(St(p,A),c==="out-in")return s.isLeaving=!0,A.afterLeave=()=>{s.isLeaving=!1,n.update.active!==!1&&n.update()},Ms(i);c==="in-out"&&u.type!==Ee&&(A.delayLeave=(k,b,g)=>{const R=Pi(s,p);R[String(p.key)]=p,k._leaveCb=()=>{b(),k._leaveCb=void 0,delete f.delayedLeave},f.delayedLeave=g})}return i}}},Ti=vu;function Pi(e,t){const{leavingVNodes:n}=e;let s=n.get(t.type);return s||(s=Object.create(null),n.set(t.type,s)),s}function qt(e,t,n,s){const{appear:r,mode:o,persisted:i=!1,onBeforeEnter:l,onEnter:c,onAfterEnter:u,onEnterCancelled:f,onBeforeLeave:a,onLeave:p,onAfterLeave:y,onLeaveCancelled:E,onBeforeAppear:A,onAppear:k,onAfterAppear:b,onAppearCancelled:g}=t,R=String(e.key),_=Pi(n,e),S=(x,j)=>{x&&Ie(x,s,9,j)},B=(x,j)=>{const U=j[1];S(x,j),D(x)?x.every(z=>z.length<=1)&&U():x.length<=1&&U()},N={mode:o,persisted:i,beforeEnter(x){let j=l;if(!n.isMounted)if(r)j=A||l;else return;x._leaveCb&&x._leaveCb(!0);const U=_[R];U&&Be(e,U)&&U.el._leaveCb&&U.el._leaveCb(),S(j,[x])},enter(x){let j=c,U=u,z=f;if(!n.isMounted)if(r)j=k||c,U=b||u,z=g||f;else return;let L=!1;const Y=x._enterCb=$=>{L||(L=!0,$?S(z,[x]):S(U,[x]),N.delayedLeave&&N.delayedLeave(),x._enterCb=void 0)};j?B(j,[x,Y]):Y()},leave(x,j){const U=String(e.key);if(x._enterCb&&x._enterCb(!0),n.isUnmounting)return j();S(a,[x]);let z=!1;const L=x._leaveCb=Y=>{z||(z=!0,j(),Y?S(E,[x]):S(y,[x]),x._leaveCb=void 0,_[U]===e&&delete _[U])};_[U]=e,p?B(p,[x,L]):L()},clone(x){return qt(x,t,n,s)}};return N}function Ms(e){if(Nn(e))return e=We(e),e.children=null,e}function oo(e){return Nn(e)?e.children?e.children[0]:void 0:e}function St(e,t){e.shapeFlag&6&&e.component?St(e.component.subTree,t):e.shapeFlag&128?(e.ssContent.transition=t.clone(e.ssContent),e.ssFallback.transition=t.clone(e.ssFallback)):e.transition=t}function bs(e,t=!1,n){let s=[],r=0;for(let o=0;o<e.length;o++){let i=e[o];const l=n==null?i.key:String(n)+String(i.key!=null?i.key:o);i.type===ye?(i.patchFlag&128&&r++,s=s.concat(bs(i.children,t,l))):(t||i.type!==Ee)&&s.push(l!=null?We(i,{key:l}):i)}if(r>1)for(let o=0;o<s.length;o++)s[o].patchFlag=-2;return s}function Fn(e,t){return Q(e)?(()=>ue({name:e.name},t,{setup:e}))():e}const Tt=e=>!!e.type.__asyncLoader;function Eu(e){Q(e)&&(e={loader:e});const{loader:t,loadingComponent:n,errorComponent:s,delay:r=200,timeout:o,suspensible:i=!0,onError:l}=e;let c=null,u,f=0;const a=()=>(f++,c=null,p()),p=()=>{let y;return c||(y=c=t().catch(E=>{if(E=E instanceof Error?E:new Error(String(E)),l)return new Promise((A,k)=>{l(E,()=>A(a()),()=>k(E),f+1)});throw E}).then(E=>y!==c&&c?c:(E&&(E.__esModule||E[Symbol.toStringTag]==="Module")&&(E=E.default),u=E,E)))};return Fn({name:"AsyncComponentWrapper",__asyncLoader:p,get __asyncResolved(){return u},setup(){const y=pe;if(u)return()=>Is(u,y);const E=g=>{c=null,kt(g,y,13,!s)};if(i&&y.suspense||zt)return p().then(g=>()=>Is(g,y)).catch(g=>(E(g),()=>s?fe(s,{error:g}):null));const A=Rt(!1),k=Rt(),b=Rt(!!r);return r&&setTimeout(()=>{b.value=!1},r),o!=null&&setTimeout(()=>{if(!A.value&&!k.value){const g=new Error(`Async component timed out after ${o}ms.`);E(g),k.value=g}},o),p().then(()=>{A.value=!0,y.parent&&Nn(y.parent.vnode)&&ms(y.parent.update)}).catch(g=>{E(g),k.value=g}),()=>{if(A.value&&u)return Is(u,y);if(k.value&&s)return fe(s,{error:k.value});if(n&&!b.value)return fe(n)}}})}function Is(e,t){const{ref:n,props:s,children:r,ce:o}=t.vnode,i=fe(e,s,r);return i.ref=n,i.ce=o,delete t.vnode.ce,i}const Nn=e=>e.type.__isKeepAlive,Cu={name:"KeepAlive",__isKeepAlive:!0,props:{include:[String,RegExp,Array],exclude:[String,RegExp,Array],max:[String,Number]},setup(e,{slots:t}){const n=et(),s=n.ctx;if(!s.renderer)return()=>{const g=t.default&&t.default();return g&&g.length===1?g[0]:g};const r=new Map,o=new Set;let i=null;const l=n.suspense,{renderer:{p:c,m:u,um:f,o:{createElement:a}}}=s,p=a("div");s.activate=(g,R,_,S,B)=>{const N=g.component;u(g,R,_,0,l),c(N.vnode,g,R,_,N,l,S,g.slotScopeIds,B),_e(()=>{N.isDeactivated=!1,N.a&&Ut(N.a);const x=g.props&&g.props.onVnodeMounted;x&&xe(x,N.parent,g)},l)},s.deactivate=g=>{const R=g.component;u(g,p,null,1,l),_e(()=>{R.da&&Ut(R.da);const _=g.props&&g.props.onVnodeUnmounted;_&&xe(_,R.parent,g),R.isDeactivated=!0},l)};function y(g){ks(g),f(g,n,l,!0)}function E(g){r.forEach((R,_)=>{const S=nr(R.type);S&&(!g||!g(S))&&A(_)})}function A(g){const R=r.get(g);!i||!Be(R,i)?y(R):i&&ks(i),r.delete(g),o.delete(g)}at(()=>[e.include,e.exclude],([g,R])=>{g&&E(_=>ln(g,_)),R&&E(_=>!ln(R,_))},{flush:"post",deep:!0});let k=null;const b=()=>{k!=null&&r.set(k,Fs(n.subTree))};return Ln(b),Es(b),Cs(()=>{r.forEach(g=>{const{subTree:R,suspense:_}=n,S=Fs(R);if(g.type===S.type&&g.key===S.key){ks(S);const B=S.component.da;B&&_e(B,_);return}y(g)})}),()=>{if(k=null,!t.default)return null;const g=t.default(),R=g[0];if(g.length>1)return i=null,g;if(!gt(R)||!(R.shapeFlag&4)&&!(R.shapeFlag&128))return i=null,R;let _=Fs(R);const S=_.type,B=nr(Tt(_)?_.type.__asyncResolved||{}:S),{include:N,exclude:x,max:j}=e;if(N&&(!B||!ln(N,B))||x&&B&&ln(x,B))return i=_,R;const U=_.key==null?S:_.key,z=r.get(U);return _.el&&(_=We(_),R.shapeFlag&128&&(R.ssContent=_)),k=U,z?(_.el=z.el,_.component=z.component,_.transition&&St(_,_.transition),_.shapeFlag|=512,o.delete(U),o.add(U)):(o.add(U),j&&o.size>parseInt(j,10)&&A(o.values().next().value)),_.shapeFlag|=256,i=_,Ci(R.type)?R:_}}},wu=Cu;function ln(e,t){return D(e)?e.some(n=>ln(n,t)):ae(e)?e.split(",").includes(t):Kl(e)?e.test(t):!1}function Ai(e,t){Oi(e,"a",t)}function Si(e,t){Oi(e,"da",t)}function Oi(e,t,n=pe){const s=e.__wdc||(e.__wdc=()=>{let r=n;for(;r;){if(r.isDeactivated)return;r=r.parent}return e()});if(vs(t,s,n),n){let r=n.parent;for(;r&&r.parent;)Nn(r.parent.vnode)&&xu(s,t,n,r),r=r.parent}}function xu(e,t,n,s){const r=vs(t,e,s,!0);ws(()=>{ar(s[t],r)},n)}function ks(e){e.shapeFlag&=-257,e.shapeFlag&=-513}function Fs(e){return e.shapeFlag&128?e.ssContent:e}function vs(e,t,n=pe,s=!1){if(n){const r=n[e]||(n[e]=[]),o=t.__weh||(t.__weh=(...i)=>{if(n.isUnmounted)return;Zt(),mt(n);const l=Ie(t,n,e,i);return dt(),Gt(),l});return s?r.unshift(o):r.push(o),o}}const Ge=e=>(t,n=pe)=>(!zt||e==="sp")&&vs(e,(...s)=>t(...s),n),Mi=Ge("bm"),Ln=Ge("m"),Ii=Ge("bu"),Es=Ge("u"),Cs=Ge("bum"),ws=Ge("um"),ki=Ge("sp"),Fi=Ge("rtg"),Ni=Ge("rtc");function Li(e,t=pe){vs("ec",e,t)}const Or="components",Ru="directives";function Tu(e,t){return Mr(Or,e,!0,t)||e}const Bi=Symbol.for("v-ndc");function Pu(e){return ae(e)?Mr(Or,e,!1)||e:e||Bi}function Au(e){return Mr(Ru,e)}function Mr(e,t,n=!0,s=!1){const r=me||pe;if(r){const o=r.type;if(e===Or){const l=nr(o,!1);if(l&&(l===t||l===Te(t)||l===Sn(Te(t))))return o}const i=io(r[e]||o[e],t)||io(r.appContext[e],t);return!i&&s?o:i}}function io(e,t){return e&&(e[t]||e[Te(t)]||e[Sn(Te(t))])}function Su(e,t,n,s){let r;const o=n&&n[s];if(D(e)||ae(e)){r=new Array(e.length);for(let i=0,l=e.length;i<l;i++)r[i]=t(e[i],i,void 0,o&&o[i])}else if(typeof e=="number"){r=new Array(e);for(let i=0;i<e;i++)r[i]=t(i+1,i,void 0,o&&o[i])}else if(le(e))if(e[Symbol.iterator])r=Array.from(e,(i,l)=>t(i,l,void 0,o&&o[l]));else{const i=Object.keys(e);r=new Array(i.length);for(let l=0,c=i.length;l<c;l++){const u=i[l];r[l]=t(e[u],u,l,o&&o[l])}}else r=[];return n&&(n[s]=r),r}function Ou(e,t){for(let n=0;n<t.length;n++){const s=t[n];if(D(s))for(let r=0;r<s.length;r++)e[s[r].name]=s[r].fn;else s&&(e[s.name]=s.key?(...r)=>{const o=s.fn(...r);return o&&(o.key=s.key),o}:s.fn)}return e}function Mu(e,t,n={},s,r){if(me.isCE||me.parent&&Tt(me.parent)&&me.parent.isCE)return t!=="default"&&(n.name=t),fe("slot",n,s&&s());let o=e[t];o&&o._c&&(o._d=!1),xs();const i=o&&Hi(o(n)),l=Nr(ye,{key:n.key||i&&i.key||`_${t}`},i||(s?s():[]),i&&e._===1?64:-2);return!r&&l.scopeId&&(l.slotScopeIds=[l.scopeId+"-s"]),o&&o._c&&(o._d=!0),l}function Hi(e){return e.some(t=>gt(t)?!(t.type===Ee||t.type===ye&&!Hi(t.children)):!0)?e:null}function Iu(e,t){const n={};for(const s in e)n[t&&/[A-Z]/.test(s)?`on:${s}`:fn(s)]=e[s];return n}const zs=e=>e?sl(e)?Ts(e)||e.proxy:zs(e.parent):null,an=ue(Object.create(null),{$:e=>e,$el:e=>e.vnode.el,$data:e=>e.data,$props:e=>e.props,$attrs:e=>e.attrs,$slots:e=>e.slots,$refs:e=>e.refs,$parent:e=>zs(e.parent),$root:e=>zs(e.root),$emit:e=>e.emit,$options:e=>Ir(e),$forceUpdate:e=>e.f||(e.f=()=>ms(e.update)),$nextTick:e=>e.n||(e.n=gs.bind(e.proxy)),$watch:e=>yu.bind(e)}),Ns=(e,t)=>e!==ie&&!e.__isScriptSetup&&ee(e,t),Ys={get({_:e},t){const{ctx:n,setupState:s,data:r,props:o,accessCache:i,type:l,appContext:c}=e;let u;if(t[0]!=="$"){const y=i[t];if(y!==void 0)switch(y){case 1:return s[t];case 2:return r[t];case 4:return n[t];case 3:return o[t]}else{if(Ns(s,t))return i[t]=1,s[t];if(r!==ie&&ee(r,t))return i[t]=2,r[t];if((u=e.propsOptions[0])&&ee(u,t))return i[t]=3,o[t];if(n!==ie&&ee(n,t))return i[t]=4,n[t];Qs&&(i[t]=0)}}const f=an[t];let a,p;if(f)return t==="$attrs"&&Pe(e,"get",t),f(e);if((a=l.__cssModules)&&(a=a[t]))return a;if(n!==ie&&ee(n,t))return i[t]=4,n[t];if(p=c.config.globalProperties,ee(p,t))return p[t]},set({_:e},t,n){const{data:s,setupState:r,ctx:o}=e;return Ns(r,t)?(r[t]=n,!0):s!==ie&&ee(s,t)?(s[t]=n,!0):ee(e.props,t)||t[0]==="$"&&t.slice(1)in e?!1:(o[t]=n,!0)},has({_:{data:e,setupState:t,accessCache:n,ctx:s,appContext:r,propsOptions:o}},i){let l;return!!n[i]||e!==ie&&ee(e,i)||Ns(t,i)||(l=o[0])&&ee(l,i)||ee(s,i)||ee(an,i)||ee(r.config.globalProperties,i)},defineProperty(e,t,n){return n.get!=null?e._.accessCache[t]=0:ee(n,"value")&&this.set(e,t,n.value,null),Reflect.defineProperty(e,t,n)}},ku=ue({},Ys,{get(e,t){if(t!==Symbol.unscopables)return Ys.get(e,t,e)},has(e,t){return t[0]!=="_"&&!Yl(t)}});function Fu(){return null}function Nu(){return null}function Lu(e){}function Bu(e){}function Hu(){return null}function Du(){}function $u(e,t){return null}function ju(){return Di().slots}function Uu(){return Di().attrs}function Ku(e,t,n){const s=et();if(n&&n.local){const r=Rt(e[t]);return at(()=>e[t],o=>r.value=o),at(r,o=>{o!==e[t]&&s.emit(`update:${t}`,o)}),r}else return{__v_isRef:!0,get value(){return e[t]},set value(r){s.emit(`update:${t}`,r)}}}function Di(){const e=et();return e.setupContext||(e.setupContext=il(e))}function Rn(e){return D(e)?e.reduce((t,n)=>(t[n]=null,t),{}):e}function Vu(e,t){const n=Rn(e);for(const s in t){if(s.startsWith("__skip"))continue;let r=n[s];r?D(r)||Q(r)?r=n[s]={type:r,default:t[s]}:r.default=t[s]:r===null&&(r=n[s]={default:t[s]}),r&&t[`__skip_${s}`]&&(r.skipFactory=!0)}return n}function Wu(e,t){return!e||!t?e||t:D(e)&&D(t)?e.concat(t):ue({},Rn(e),Rn(t))}function qu(e,t){const n={};for(const s in e)t.includes(s)||Object.defineProperty(n,s,{enumerable:!0,get:()=>e[s]});return n}function zu(e){const t=et();let n=e();return dt(),dr(n)&&(n=n.catch(s=>{throw mt(t),s})),[n,()=>mt(t)]}let Qs=!0;function Yu(e){const t=Ir(e),n=e.proxy,s=e.ctx;Qs=!1,t.beforeCreate&&lo(t.beforeCreate,e,"bc");const{data:r,computed:o,methods:i,watch:l,provide:c,inject:u,created:f,beforeMount:a,mounted:p,beforeUpdate:y,updated:E,activated:A,deactivated:k,beforeDestroy:b,beforeUnmount:g,destroyed:R,unmounted:_,render:S,renderTracked:B,renderTriggered:N,errorCaptured:x,serverPrefetch:j,expose:U,inheritAttrs:z,components:L,directives:Y,filters:$}=t;if(u&&Qu(u,s,null),i)for(const te in i){const ne=i[te];Q(ne)&&(s[te]=ne.bind(n))}if(r){const te=r.call(n,n);le(te)&&(e.data=en(te))}if(Qs=!0,o)for(const te in o){const ne=o[te],qe=Q(ne)?ne.bind(n,n):Q(ne.get)?ne.get.bind(n,n):He,tt=!Q(ne)&&Q(ne.set)?ne.set.bind(n):He,je=Me({get:qe,set:tt});Object.defineProperty(s,te,{enumerable:!0,configurable:!0,get:()=>je.value,set:we=>je.value=we})}if(l)for(const te in l)$i(l[te],s,n,te);if(c){const te=Q(c)?c.call(n):c;Reflect.ownKeys(te).forEach(ne=>{dn(ne,te[ne])})}f&&lo(f,e,"c");function G(te,ne){D(ne)?ne.forEach(qe=>te(qe.bind(n))):ne&&te(ne.bind(n))}if(G(Mi,a),G(Ln,p),G(Ii,y),G(Es,E),G(Ai,A),G(Si,k),G(Li,x),G(Ni,B),G(Fi,N),G(Cs,g),G(ws,_),G(ki,j),D(U))if(U.length){const te=e.exposed||(e.exposed={});U.forEach(ne=>{Object.defineProperty(te,ne,{get:()=>n[ne],set:qe=>n[ne]=qe})})}else e.exposed||(e.exposed={});S&&e.render===He&&(e.render=S),z!=null&&(e.inheritAttrs=z),L&&(e.components=L),Y&&(e.directives=Y)}function Qu(e,t,n=He){D(e)&&(e=Js(e));for(const s in e){const r=e[s];let o;le(r)?"default"in r?o=De(r.from||s,r.default,!0):o=De(r.from||s):o=De(r),ge(o)?Object.defineProperty(t,s,{enumerable:!0,configurable:!0,get:()=>o.value,set:i=>o.value=i}):t[s]=o}}function lo(e,t,n){Ie(D(e)?e.map(s=>s.bind(t.proxy)):e.bind(t.proxy),t,n)}function $i(e,t,n,s){const r=s.includes(".")?Ri(n,s):()=>n[s];if(ae(e)){const o=t[e];Q(o)&&at(r,o)}else if(Q(e))at(r,e.bind(n));else if(le(e))if(D(e))e.forEach(o=>$i(o,t,n,s));else{const o=Q(e.handler)?e.handler.bind(n):t[e.handler];Q(o)&&at(r,o,e)}}function Ir(e){const t=e.type,{mixins:n,extends:s}=t,{mixins:r,optionsCache:o,config:{optionMergeStrategies:i}}=e.appContext,l=o.get(t);let c;return l?c=l:!r.length&&!n&&!s?c=t:(c={},r.length&&r.forEach(u=>ns(c,u,i,!0)),ns(c,t,i)),le(t)&&o.set(t,c),c}function ns(e,t,n,s=!1){const{mixins:r,extends:o}=t;o&&ns(e,o,n,!0),r&&r.forEach(i=>ns(e,i,n,!0));for(const i in t)if(!(s&&i==="expose")){const l=Ju[i]||n&&n[i];e[i]=l?l(e[i],t[i]):t[i]}return e}const Ju={data:co,props:uo,emits:uo,methods:cn,computed:cn,beforeCreate:Ce,created:Ce,beforeMount:Ce,mounted:Ce,beforeUpdate:Ce,updated:Ce,beforeDestroy:Ce,beforeUnmount:Ce,destroyed:Ce,unmounted:Ce,activated:Ce,deactivated:Ce,errorCaptured:Ce,serverPrefetch:Ce,components:cn,directives:cn,watch:Zu,provide:co,inject:Xu};function co(e,t){return t?e?function(){return ue(Q(e)?e.call(this,this):e,Q(t)?t.call(this,this):t)}:t:e}function Xu(e,t){return cn(Js(e),Js(t))}function Js(e){if(D(e)){const t={};for(let n=0;n<e.length;n++)t[e[n]]=e[n];return t}return e}function Ce(e,t){return e?[...new Set([].concat(e,t))]:t}function cn(e,t){return e?ue(Object.create(null),e,t):t}function uo(e,t){return e?D(e)&&D(t)?[...new Set([...e,...t])]:ue(Object.create(null),Rn(e),Rn(t??{})):t}function Zu(e,t){if(!e)return t;if(!t)return e;const n=ue(Object.create(null),e);for(const s in t)n[s]=Ce(e[s],t[s]);return n}function ji(){return{app:null,config:{isNativeTag:$l,performance:!1,globalProperties:{},optionMergeStrategies:{},errorHandler:void 0,warnHandler:void 0,compilerOptions:{}},mixins:[],components:{},directives:{},provides:Object.create(null),optionsCache:new WeakMap,propsCache:new WeakMap,emitsCache:new WeakMap}}let Gu=0;function ef(e,t){return function(s,r=null){Q(s)||(s=ue({},s)),r!=null&&!le(r)&&(r=null);const o=ji(),i=new Set;let l=!1;const c=o.app={_uid:Gu++,_component:s,_props:r,_container:null,_context:o,_instance:null,version:fl,get config(){return o.config},set config(u){},use(u,...f){return i.has(u)||(u&&Q(u.install)?(i.add(u),u.install(c,...f)):Q(u)&&(i.add(u),u(c,...f))),c},mixin(u){return o.mixins.includes(u)||o.mixins.push(u),c},component(u,f){return f?(o.components[u]=f,c):o.components[u]},directive(u,f){return f?(o.directives[u]=f,c):o.directives[u]},mount(u,f,a){if(!l){const p=fe(s,r);return p.appContext=o,f&&t?t(p,u):e(p,u,a),l=!0,c._container=u,u.__vue_app__=c,Ts(p.component)||p.component.proxy}},unmount(){l&&(e(null,c._container),delete c._container.__vue_app__)},provide(u,f){return o.provides[u]=f,c},runWithContext(u){Tn=c;try{return u()}finally{Tn=null}}};return c}}let Tn=null;function dn(e,t){if(pe){let n=pe.provides;const s=pe.parent&&pe.parent.provides;s===n&&(n=pe.provides=Object.create(s)),n[e]=t}}function De(e,t,n=!1){const s=pe||me;if(s||Tn){const r=s?s.parent==null?s.vnode.appContext&&s.vnode.appContext.provides:s.parent.provides:Tn._context.provides;if(r&&e in r)return r[e];if(arguments.length>1)return n&&Q(t)?t.call(s&&s.proxy):t}}function tf(){return!!(pe||me||Tn)}function nf(e,t,n,s=!1){const r={},o={};Xn(o,Rs,1),e.propsDefaults=Object.create(null),Ui(e,t,r,o);for(const i in e.propsOptions[0])i in r||(r[i]=void 0);n?e.props=s?r:hi(r):e.type.props?e.props=r:e.props=o,e.attrs=o}function sf(e,t,n,s){const{props:r,attrs:o,vnode:{patchFlag:i}}=e,l=Z(r),[c]=e.propsOptions;let u=!1;if((s||i>0)&&!(i&16)){if(i&8){const f=e.vnode.dynamicProps;for(let a=0;a<f.length;a++){let p=f[a];if(_s(e.emitsOptions,p))continue;const y=t[p];if(c)if(ee(o,p))y!==o[p]&&(o[p]=y,u=!0);else{const E=Te(p);r[E]=Xs(c,l,E,y,e,!1)}else y!==o[p]&&(o[p]=y,u=!0)}}}else{Ui(e,t,r,o)&&(u=!0);let f;for(const a in l)(!t||!ee(t,a)&&((f=Fe(a))===a||!ee(t,f)))&&(c?n&&(n[a]!==void 0||n[f]!==void 0)&&(r[a]=Xs(c,l,a,void 0,e,!0)):delete r[a]);if(o!==l)for(const a in o)(!t||!ee(t,a))&&(delete o[a],u=!0)}u&&Ze(e,"set","$attrs")}function Ui(e,t,n,s){const[r,o]=e.propsOptions;let i=!1,l;if(t)for(let c in t){if(un(c))continue;const u=t[c];let f;r&&ee(r,f=Te(c))?!o||!o.includes(f)?n[f]=u:(l||(l={}))[f]=u:_s(e.emitsOptions,c)||(!(c in s)||u!==s[c])&&(s[c]=u,i=!0)}if(o){const c=Z(n),u=l||ie;for(let f=0;f<o.length;f++){const a=o[f];n[a]=Xs(r,c,a,u[a],e,!ee(u,a))}}return i}function Xs(e,t,n,s,r,o){const i=e[n];if(i!=null){const l=ee(i,"default");if(l&&s===void 0){const c=i.default;if(i.type!==Function&&!i.skipFactory&&Q(c)){const{propsDefaults:u}=r;n in u?s=u[n]:(mt(r),s=u[n]=c.call(null,t),dt())}else s=c}i[0]&&(o&&!l?s=!1:i[1]&&(s===""||s===Fe(n))&&(s=!0))}return s}function Ki(e,t,n=!1){const s=t.propsCache,r=s.get(e);if(r)return r;const o=e.props,i={},l=[];let c=!1;if(!Q(e)){const f=a=>{c=!0;const[p,y]=Ki(a,t,!0);ue(i,p),y&&l.push(...y)};!n&&t.mixins.length&&t.mixins.forEach(f),e.extends&&f(e.extends),e.mixins&&e.mixins.forEach(f)}if(!o&&!c)return le(e)&&s.set(e,$t),$t;if(D(o))for(let f=0;f<o.length;f++){const a=Te(o[f]);fo(a)&&(i[a]=ie)}else if(o)for(const f in o){const a=Te(f);if(fo(a)){const p=o[f],y=i[a]=D(p)||Q(p)?{type:p}:ue({},p);if(y){const E=po(Boolean,y.type),A=po(String,y.type);y[0]=E>-1,y[1]=A<0||E<A,(E>-1||ee(y,"default"))&&l.push(a)}}}const u=[i,l];return le(e)&&s.set(e,u),u}function fo(e){return e[0]!=="$"}function ao(e){const t=e&&e.toString().match(/^\s*(function|class) (\w+)/);return t?t[2]:e===null?"null":""}function ho(e,t){return ao(e)===ao(t)}function po(e,t){return D(t)?t.findIndex(n=>ho(n,e)):Q(t)&&ho(t,e)?0:-1}const Vi=e=>e[0]==="_"||e==="$stable",kr=e=>D(e)?e.map(Oe):[Oe(e)],rf=(e,t,n)=>{if(t._n)return t;const s=Rr((...r)=>kr(t(...r)),n);return s._c=!1,s},Wi=(e,t,n)=>{const s=e._ctx;for(const r in e){if(Vi(r))continue;const o=e[r];if(Q(o))t[r]=rf(r,o,s);else if(o!=null){const i=kr(o);t[r]=()=>i}}},qi=(e,t)=>{const n=kr(t);e.slots.default=()=>n},of=(e,t)=>{if(e.vnode.shapeFlag&32){const n=t._;n?(e.slots=Z(t),Xn(t,"_",n)):Wi(t,e.slots={})}else e.slots={},t&&qi(e,t);Xn(e.slots,Rs,1)},lf=(e,t,n)=>{const{vnode:s,slots:r}=e;let o=!0,i=ie;if(s.shapeFlag&32){const l=t._;l?n&&l===1?o=!1:(ue(r,t),!n&&l===1&&delete r._):(o=!t.$stable,Wi(t,r)),i=t}else t&&(qi(e,t),i={default:1});if(o)for(const l in r)!Vi(l)&&!(l in i)&&delete r[l]};function ss(e,t,n,s,r=!1){if(D(e)){e.forEach((p,y)=>ss(p,t&&(D(t)?t[y]:t),n,s,r));return}if(Tt(s)&&!r)return;const o=s.shapeFlag&4?Ts(s.component)||s.component.proxy:s.el,i=r?null:o,{i:l,r:c}=e,u=t&&t.r,f=l.refs===ie?l.refs={}:l.refs,a=l.setupState;if(u!=null&&u!==c&&(ae(u)?(f[u]=null,ee(a,u)&&(a[u]=null)):ge(u)&&(u.value=null)),Q(c))Xe(c,l,12,[i,f]);else{const p=ae(c),y=ge(c);if(p||y){const E=()=>{if(e.f){const A=p?ee(a,c)?a[c]:f[c]:c.value;r?D(A)&&ar(A,o):D(A)?A.includes(o)||A.push(o):p?(f[c]=[o],ee(a,c)&&(a[c]=f[c])):(c.value=[o],e.k&&(f[e.k]=c.value))}else p?(f[c]=i,ee(a,c)&&(a[c]=i)):y&&(c.value=i,e.k&&(f[e.k]=i))};i?(E.id=-1,_e(E,n)):E()}}}let st=!1;const Wn=e=>/svg/.test(e.namespaceURI)&&e.tagName!=="foreignObject",qn=e=>e.nodeType===8;function cf(e){const{mt:t,p:n,o:{patchProp:s,createText:r,nextSibling:o,parentNode:i,remove:l,insert:c,createComment:u}}=e,f=(b,g)=>{if(!g.hasChildNodes()){n(null,b,g),ts(),g._vnode=b;return}st=!1,a(g.firstChild,b,null,null,null),ts(),g._vnode=b,st&&console.error("Hydration completed but contains mismatches.")},a=(b,g,R,_,S,B=!1)=>{const N=qn(b)&&b.data==="[",x=()=>A(b,g,R,_,S,N),{type:j,ref:U,shapeFlag:z,patchFlag:L}=g;let Y=b.nodeType;g.el=b,L===-2&&(B=!1,g.dynamicChildren=null);let $=null;switch(j){case Ot:Y!==3?g.children===""?(c(g.el=r(""),i(b),b),$=b):$=x():(b.data!==g.children&&(st=!0,b.data=g.children),$=o(b));break;case Ee:Y!==8||N?$=x():$=o(b);break;case Pt:if(N&&(b=o(b),Y=b.nodeType),Y===1||Y===3){$=b;const de=!g.children.length;for(let G=0;G<g.staticCount;G++)de&&(g.children+=$.nodeType===1?$.outerHTML:$.data),G===g.staticCount-1&&(g.anchor=$),$=o($);return N?o($):$}else x();break;case ye:N?$=E(b,g,R,_,S,B):$=x();break;default:if(z&1)Y!==1||g.type.toLowerCase()!==b.tagName.toLowerCase()?$=x():$=p(b,g,R,_,S,B);else if(z&6){g.slotScopeIds=S;const de=i(b);if(t(g,de,null,R,_,Wn(de),B),$=N?k(b):o(b),$&&qn($)&&$.data==="teleport end"&&($=o($)),Tt(g)){let G;N?(G=fe(ye),G.anchor=$?$.previousSibling:de.lastChild):G=b.nodeType===3?Br(""):fe("div"),G.el=b,g.component.subTree=G}}else z&64?Y!==8?$=x():$=g.type.hydrate(b,g,R,_,S,B,e,y):z&128&&($=g.type.hydrate(b,g,R,_,Wn(i(b)),S,B,e,a))}return U!=null&&ss(U,null,_,g),$},p=(b,g,R,_,S,B)=>{B=B||!!g.dynamicChildren;const{type:N,props:x,patchFlag:j,shapeFlag:U,dirs:z}=g,L=N==="input"&&z||N==="option";if(L||j!==-1){if(z&&Ke(g,null,R,"created"),x)if(L||!B||j&48)for(const $ in x)(L&&$.endsWith("value")||An($)&&!un($))&&s(b,$,null,x[$],!1,void 0,R);else x.onClick&&s(b,"onClick",null,x.onClick,!1,void 0,R);let Y;if((Y=x&&x.onVnodeBeforeMount)&&xe(Y,R,g),z&&Ke(g,null,R,"beforeMount"),((Y=x&&x.onVnodeMounted)||z)&&wi(()=>{Y&&xe(Y,R,g),z&&Ke(g,null,R,"mounted")},_),U&16&&!(x&&(x.innerHTML||x.textContent))){let $=y(b.firstChild,g,b,R,_,S,B);for(;$;){st=!0;const de=$;$=$.nextSibling,l(de)}}else U&8&&b.textContent!==g.children&&(st=!0,b.textContent=g.children)}return b.nextSibling},y=(b,g,R,_,S,B,N)=>{N=N||!!g.dynamicChildren;const x=g.children,j=x.length;for(let U=0;U<j;U++){const z=N?x[U]:x[U]=Oe(x[U]);if(b)b=a(b,z,_,S,B,N);else{if(z.type===Ot&&!z.children)continue;st=!0,n(null,z,R,null,_,S,Wn(R),B)}}return b},E=(b,g,R,_,S,B)=>{const{slotScopeIds:N}=g;N&&(S=S?S.concat(N):N);const x=i(b),j=y(o(b),g,x,R,_,S,B);return j&&qn(j)&&j.data==="]"?o(g.anchor=j):(st=!0,c(g.anchor=u("]"),x,j),j)},A=(b,g,R,_,S,B)=>{if(st=!0,g.el=null,B){const j=k(b);for(;;){const U=o(b);if(U&&U!==j)l(U);else break}}const N=o(b),x=i(b);return l(b),n(null,g,x,N,R,_,Wn(x),S),N},k=b=>{let g=0;for(;b;)if(b=o(b),b&&qn(b)&&(b.data==="["&&g++,b.data==="]")){if(g===0)return o(b);g--}return b};return[f,a]}const _e=wi;function zi(e){return Qi(e)}function Yi(e){return Qi(e,cf)}function Qi(e,t){const n=Us();n.__VUE__=!0;const{insert:s,remove:r,patchProp:o,createElement:i,createText:l,createComment:c,setText:u,setElementText:f,parentNode:a,nextSibling:p,setScopeId:y=He,insertStaticContent:E}=e,A=(d,h,m,v=null,w=null,T=null,F=!1,O=null,M=!!h.dynamicChildren)=>{if(d===h)return;d&&!Be(d,h)&&(v=C(d),we(d,w,T,!0),d=null),h.patchFlag===-2&&(M=!1,h.dynamicChildren=null);const{type:P,ref:W,shapeFlag:K}=h;switch(P){case Ot:k(d,h,m,v);break;case Ee:b(d,h,m,v);break;case Pt:d==null&&g(h,m,v,F);break;case ye:L(d,h,m,v,w,T,F,O,M);break;default:K&1?S(d,h,m,v,w,T,F,O,M):K&6?Y(d,h,m,v,w,T,F,O,M):(K&64||K&128)&&P.process(d,h,m,v,w,T,F,O,M,I)}W!=null&&w&&ss(W,d&&d.ref,T,h||d,!h)},k=(d,h,m,v)=>{if(d==null)s(h.el=l(h.children),m,v);else{const w=h.el=d.el;h.children!==d.children&&u(w,h.children)}},b=(d,h,m,v)=>{d==null?s(h.el=c(h.children||""),m,v):h.el=d.el},g=(d,h,m,v)=>{[d.el,d.anchor]=E(d.children,h,m,v,d.el,d.anchor)},R=({el:d,anchor:h},m,v)=>{let w;for(;d&&d!==h;)w=p(d),s(d,m,v),d=w;s(h,m,v)},_=({el:d,anchor:h})=>{let m;for(;d&&d!==h;)m=p(d),r(d),d=m;r(h)},S=(d,h,m,v,w,T,F,O,M)=>{F=F||h.type==="svg",d==null?B(h,m,v,w,T,F,O,M):j(d,h,w,T,F,O,M)},B=(d,h,m,v,w,T,F,O)=>{let M,P;const{type:W,props:K,shapeFlag:q,transition:J,dirs:X}=d;if(M=d.el=i(d.type,T,K&&K.is,K),q&8?f(M,d.children):q&16&&x(d.children,M,null,v,w,T&&W!=="foreignObject",F,O),X&&Ke(d,null,v,"created"),N(M,d,d.scopeId,F,v),K){for(const oe in K)oe!=="value"&&!un(oe)&&o(M,oe,null,K[oe],T,d.children,v,w,be);"value"in K&&o(M,"value",null,K.value),(P=K.onVnodeBeforeMount)&&xe(P,v,d)}X&&Ke(d,null,v,"beforeMount");const ce=(!w||w&&!w.pendingBranch)&&J&&!J.persisted;ce&&J.beforeEnter(M),s(M,h,m),((P=K&&K.onVnodeMounted)||ce||X)&&_e(()=>{P&&xe(P,v,d),ce&&J.enter(M),X&&Ke(d,null,v,"mounted")},w)},N=(d,h,m,v,w)=>{if(m&&y(d,m),v)for(let T=0;T<v.length;T++)y(d,v[T]);if(w){let T=w.subTree;if(h===T){const F=w.vnode;N(d,F,F.scopeId,F.slotScopeIds,w.parent)}}},x=(d,h,m,v,w,T,F,O,M=0)=>{for(let P=M;P<d.length;P++){const W=d[P]=O?lt(d[P]):Oe(d[P]);A(null,W,h,m,v,w,T,F,O)}},j=(d,h,m,v,w,T,F)=>{const O=h.el=d.el;let{patchFlag:M,dynamicChildren:P,dirs:W}=h;M|=d.patchFlag&16;const K=d.props||ie,q=h.props||ie;let J;m&&yt(m,!1),(J=q.onVnodeBeforeUpdate)&&xe(J,m,h,d),W&&Ke(h,d,m,"beforeUpdate"),m&&yt(m,!0);const X=w&&h.type!=="foreignObject";if(P?U(d.dynamicChildren,P,O,m,v,X,T):F||ne(d,h,O,null,m,v,X,T,!1),M>0){if(M&16)z(O,h,K,q,m,v,w);else if(M&2&&K.class!==q.class&&o(O,"class",null,q.class,w),M&4&&o(O,"style",K.style,q.style,w),M&8){const ce=h.dynamicProps;for(let oe=0;oe<ce.length;oe++){const he=ce[oe],Ne=K[he],Lt=q[he];(Lt!==Ne||he==="value")&&o(O,he,Ne,Lt,w,d.children,m,v,be)}}M&1&&d.children!==h.children&&f(O,h.children)}else!F&&P==null&&z(O,h,K,q,m,v,w);((J=q.onVnodeUpdated)||W)&&_e(()=>{J&&xe(J,m,h,d),W&&Ke(h,d,m,"updated")},v)},U=(d,h,m,v,w,T,F)=>{for(let O=0;O<h.length;O++){const M=d[O],P=h[O],W=M.el&&(M.type===ye||!Be(M,P)||M.shapeFlag&70)?a(M.el):m;A(M,P,W,null,v,w,T,F,!0)}},z=(d,h,m,v,w,T,F)=>{if(m!==v){if(m!==ie)for(const O in m)!un(O)&&!(O in v)&&o(d,O,m[O],null,F,h.children,w,T,be);for(const O in v){if(un(O))continue;const M=v[O],P=m[O];M!==P&&O!=="value"&&o(d,O,P,M,F,h.children,w,T,be)}"value"in v&&o(d,"value",m.value,v.value)}},L=(d,h,m,v,w,T,F,O,M)=>{const P=h.el=d?d.el:l(""),W=h.anchor=d?d.anchor:l("");let{patchFlag:K,dynamicChildren:q,slotScopeIds:J}=h;J&&(O=O?O.concat(J):J),d==null?(s(P,m,v),s(W,m,v),x(h.children,m,W,w,T,F,O,M)):K>0&&K&64&&q&&d.dynamicChildren?(U(d.dynamicChildren,q,m,w,T,F,O),(h.key!=null||w&&h===w.subTree)&&Fr(d,h,!0)):ne(d,h,m,W,w,T,F,O,M)},Y=(d,h,m,v,w,T,F,O,M)=>{h.slotScopeIds=O,d==null?h.shapeFlag&512?w.ctx.activate(h,m,v,F,M):$(h,m,v,w,T,F,M):de(d,h,M)},$=(d,h,m,v,w,T,F)=>{const O=d.component=nl(d,v,w);if(Nn(d)&&(O.ctx.renderer=I),rl(O),O.asyncDep){if(w&&w.registerDep(O,G),!d.el){const M=O.subTree=fe(Ee);b(null,M,h,m)}return}G(O,d,h,m,w,T,F)},de=(d,h,m)=>{const v=h.component=d.component;if(cu(d,h,m))if(v.asyncDep&&!v.asyncResolved){te(v,h,m);return}else v.next=h,Gc(v.update),v.update();else h.el=d.el,v.vnode=h},G=(d,h,m,v,w,T,F)=>{const O=()=>{if(d.isMounted){let{next:W,bu:K,u:q,parent:J,vnode:X}=d,ce=W,oe;yt(d,!1),W?(W.el=X.el,te(d,W,F)):W=X,K&&Ut(K),(oe=W.props&&W.props.onVnodeBeforeUpdate)&&xe(oe,J,W,X),yt(d,!0);const he=Qn(d),Ne=d.subTree;d.subTree=he,A(Ne,he,a(Ne.el),C(Ne),d,w,T),W.el=he.el,ce===null&&Tr(d,he.el),q&&_e(q,w),(oe=W.props&&W.props.onVnodeUpdated)&&_e(()=>xe(oe,J,W,X),w)}else{let W;const{el:K,props:q}=h,{bm:J,m:X,parent:ce}=d,oe=Tt(h);if(yt(d,!1),J&&Ut(J),!oe&&(W=q&&q.onVnodeBeforeMount)&&xe(W,ce,h),yt(d,!0),K&&se){const he=()=>{d.subTree=Qn(d),se(K,d.subTree,d,w,null)};oe?h.type.__asyncLoader().then(()=>!d.isUnmounted&&he()):he()}else{const he=d.subTree=Qn(d);A(null,he,m,v,d,w,T),h.el=he.el}if(X&&_e(X,w),!oe&&(W=q&&q.onVnodeMounted)){const he=h;_e(()=>xe(W,ce,he),w)}(h.shapeFlag&256||ce&&Tt(ce.vnode)&&ce.vnode.shapeFlag&256)&&d.a&&_e(d.a,w),d.isMounted=!0,h=m=v=null}},M=d.effect=new In(O,()=>ms(P),d.scope),P=d.update=()=>M.run();P.id=d.uid,yt(d,!0),P()},te=(d,h,m)=>{h.component=d;const v=d.vnode.props;d.vnode=h,d.next=null,sf(d,h.props,v,m),lf(d,h.children,m),Zt(),no(),Gt()},ne=(d,h,m,v,w,T,F,O,M=!1)=>{const P=d&&d.children,W=d?d.shapeFlag:0,K=h.children,{patchFlag:q,shapeFlag:J}=h;if(q>0){if(q&128){tt(P,K,m,v,w,T,F,O,M);return}else if(q&256){qe(P,K,m,v,w,T,F,O,M);return}}J&8?(W&16&&be(P,w,T),K!==P&&f(m,K)):W&16?J&16?tt(P,K,m,v,w,T,F,O,M):be(P,w,T,!0):(W&8&&f(m,""),J&16&&x(K,m,v,w,T,F,O,M))},qe=(d,h,m,v,w,T,F,O,M)=>{d=d||$t,h=h||$t;const P=d.length,W=h.length,K=Math.min(P,W);let q;for(q=0;q<K;q++){const J=h[q]=M?lt(h[q]):Oe(h[q]);A(d[q],J,m,null,w,T,F,O,M)}P>W?be(d,w,T,!0,!1,K):x(h,m,v,w,T,F,O,M,K)},tt=(d,h,m,v,w,T,F,O,M)=>{let P=0;const W=h.length;let K=d.length-1,q=W-1;for(;P<=K&&P<=q;){const J=d[P],X=h[P]=M?lt(h[P]):Oe(h[P]);if(Be(J,X))A(J,X,m,null,w,T,F,O,M);else break;P++}for(;P<=K&&P<=q;){const J=d[K],X=h[q]=M?lt(h[q]):Oe(h[q]);if(Be(J,X))A(J,X,m,null,w,T,F,O,M);else break;K--,q--}if(P>K){if(P<=q){const J=q+1,X=J<W?h[J].el:v;for(;P<=q;)A(null,h[P]=M?lt(h[P]):Oe(h[P]),m,X,w,T,F,O,M),P++}}else if(P>q)for(;P<=K;)we(d[P],w,T,!0),P++;else{const J=P,X=P,ce=new Map;for(P=X;P<=q;P++){const Ae=h[P]=M?lt(h[P]):Oe(h[P]);Ae.key!=null&&ce.set(Ae.key,P)}let oe,he=0;const Ne=q-X+1;let Lt=!1,Vr=0;const tn=new Array(Ne);for(P=0;P<Ne;P++)tn[P]=0;for(P=J;P<=K;P++){const Ae=d[P];if(he>=Ne){we(Ae,w,T,!0);continue}let Ue;if(Ae.key!=null)Ue=ce.get(Ae.key);else for(oe=X;oe<=q;oe++)if(tn[oe-X]===0&&Be(Ae,h[oe])){Ue=oe;break}Ue===void 0?we(Ae,w,T,!0):(tn[Ue-X]=P+1,Ue>=Vr?Vr=Ue:Lt=!0,A(Ae,h[Ue],m,null,w,T,F,O,M),he++)}const Wr=Lt?uf(tn):$t;for(oe=Wr.length-1,P=Ne-1;P>=0;P--){const Ae=X+P,Ue=h[Ae],qr=Ae+1<W?h[Ae+1].el:v;tn[P]===0?A(null,Ue,m,qr,w,T,F,O,M):Lt&&(oe<0||P!==Wr[oe]?je(Ue,m,qr,2):oe--)}}},je=(d,h,m,v,w=null)=>{const{el:T,type:F,transition:O,children:M,shapeFlag:P}=d;if(P&6){je(d.component.subTree,h,m,v);return}if(P&128){d.suspense.move(h,m,v);return}if(P&64){F.move(d,h,m,I);return}if(F===ye){s(T,h,m);for(let K=0;K<M.length;K++)je(M[K],h,m,v);s(d.anchor,h,m);return}if(F===Pt){R(d,h,m);return}if(v!==2&&P&1&&O)if(v===0)O.beforeEnter(T),s(T,h,m),_e(()=>O.enter(T),w);else{const{leave:K,delayLeave:q,afterLeave:J}=O,X=()=>s(T,h,m),ce=()=>{K(T,()=>{X(),J&&J()})};q?q(T,X,ce):ce()}else s(T,h,m)},we=(d,h,m,v=!1,w=!1)=>{const{type:T,props:F,ref:O,children:M,dynamicChildren:P,shapeFlag:W,patchFlag:K,dirs:q}=d;if(O!=null&&ss(O,null,m,d,!0),W&256){h.ctx.deactivate(d);return}const J=W&1&&q,X=!Tt(d);let ce;if(X&&(ce=F&&F.onVnodeBeforeUnmount)&&xe(ce,h,d),W&6)Bn(d.component,m,v);else{if(W&128){d.suspense.unmount(m,v);return}J&&Ke(d,null,h,"beforeUnmount"),W&64?d.type.remove(d,h,m,w,I,v):P&&(T!==ye||K>0&&K&64)?be(P,h,m,!1,!0):(T===ye&&K&384||!w&&W&16)&&be(M,h,m),v&&Ft(d)}(X&&(ce=F&&F.onVnodeUnmounted)||J)&&_e(()=>{ce&&xe(ce,h,d),J&&Ke(d,null,h,"unmounted")},m)},Ft=d=>{const{type:h,el:m,anchor:v,transition:w}=d;if(h===ye){Nt(m,v);return}if(h===Pt){_(d);return}const T=()=>{r(m),w&&!w.persisted&&w.afterLeave&&w.afterLeave()};if(d.shapeFlag&1&&w&&!w.persisted){const{leave:F,delayLeave:O}=w,M=()=>F(m,T);O?O(d.el,T,M):M()}else T()},Nt=(d,h)=>{let m;for(;d!==h;)m=p(d),r(d),d=m;r(h)},Bn=(d,h,m)=>{const{bum:v,scope:w,update:T,subTree:F,um:O}=d;v&&Ut(v),w.stop(),T&&(T.active=!1,we(F,d,h,m)),O&&_e(O,h),_e(()=>{d.isUnmounted=!0},h),h&&h.pendingBranch&&!h.isUnmounted&&d.asyncDep&&!d.asyncResolved&&d.suspenseId===h.pendingId&&(h.deps--,h.deps===0&&h.resolve())},be=(d,h,m,v=!1,w=!1,T=0)=>{for(let F=T;F<d.length;F++)we(d[F],h,m,v,w)},C=d=>d.shapeFlag&6?C(d.component.subTree):d.shapeFlag&128?d.suspense.next():p(d.anchor||d.el),H=(d,h,m)=>{d==null?h._vnode&&we(h._vnode,null,null,!0):A(h._vnode||null,d,h,null,null,null,m),no(),ts(),h._vnode=d},I={p:A,um:we,m:je,r:Ft,mt:$,mc:x,pc:ne,pbc:U,n:C,o:e};let V,se;return t&&([V,se]=t(I)),{render:H,hydrate:V,createApp:ef(H,V)}}function yt({effect:e,update:t},n){e.allowRecurse=t.allowRecurse=n}function Fr(e,t,n=!1){const s=e.children,r=t.children;if(D(s)&&D(r))for(let o=0;o<s.length;o++){const i=s[o];let l=r[o];l.shapeFlag&1&&!l.dynamicChildren&&((l.patchFlag<=0||l.patchFlag===32)&&(l=r[o]=lt(r[o]),l.el=i.el),n||Fr(i,l)),l.type===Ot&&(l.el=i.el)}}function uf(e){const t=e.slice(),n=[0];let s,r,o,i,l;const c=e.length;for(s=0;s<c;s++){const u=e[s];if(u!==0){if(r=n[n.length-1],e[r]<u){t[s]=r,n.push(s);continue}for(o=0,i=n.length-1;o<i;)l=o+i>>1,e[n[l]]<u?o=l+1:i=l;u<e[n[o]]&&(o>0&&(t[s]=n[o-1]),n[o]=s)}}for(o=n.length,i=n[o-1];o-- >0;)n[o]=i,i=t[i];return n}const ff=e=>e.__isTeleport,hn=e=>e&&(e.disabled||e.disabled===""),go=e=>typeof SVGElement<"u"&&e instanceof SVGElement,Zs=(e,t)=>{const n=e&&e.to;return ae(n)?t?t(n):null:n},af={__isTeleport:!0,process(e,t,n,s,r,o,i,l,c,u){const{mc:f,pc:a,pbc:p,o:{insert:y,querySelector:E,createText:A,createComment:k}}=u,b=hn(t.props);let{shapeFlag:g,children:R,dynamicChildren:_}=t;if(e==null){const S=t.el=A(""),B=t.anchor=A("");y(S,n,s),y(B,n,s);const N=t.target=Zs(t.props,E),x=t.targetAnchor=A("");N&&(y(x,N),i=i||go(N));const j=(U,z)=>{g&16&&f(R,U,z,r,o,i,l,c)};b?j(n,B):N&&j(N,x)}else{t.el=e.el;const S=t.anchor=e.anchor,B=t.target=e.target,N=t.targetAnchor=e.targetAnchor,x=hn(e.props),j=x?n:B,U=x?S:N;if(i=i||go(B),_?(p(e.dynamicChildren,_,j,r,o,i,l),Fr(e,t,!0)):c||a(e,t,j,U,r,o,i,l,!1),b)x||zn(t,n,S,u,1);else if((t.props&&t.props.to)!==(e.props&&e.props.to)){const z=t.target=Zs(t.props,E);z&&zn(t,z,null,u,0)}else x&&zn(t,B,N,u,1)}Ji(t)},remove(e,t,n,s,{um:r,o:{remove:o}},i){const{shapeFlag:l,children:c,anchor:u,targetAnchor:f,target:a,props:p}=e;if(a&&o(f),(i||!hn(p))&&(o(u),l&16))for(let y=0;y<c.length;y++){const E=c[y];r(E,t,n,!0,!!E.dynamicChildren)}},move:zn,hydrate:df};function zn(e,t,n,{o:{insert:s},m:r},o=2){o===0&&s(e.targetAnchor,t,n);const{el:i,anchor:l,shapeFlag:c,children:u,props:f}=e,a=o===2;if(a&&s(i,t,n),(!a||hn(f))&&c&16)for(let p=0;p<u.length;p++)r(u[p],t,n,2);a&&s(l,t,n)}function df(e,t,n,s,r,o,{o:{nextSibling:i,parentNode:l,querySelector:c}},u){const f=t.target=Zs(t.props,c);if(f){const a=f._lpa||f.firstChild;if(t.shapeFlag&16)if(hn(t.props))t.anchor=u(i(e),t,l(e),n,s,r,o),t.targetAnchor=a;else{t.anchor=i(e);let p=a;for(;p;)if(p=i(p),p&&p.nodeType===8&&p.data==="teleport anchor"){t.targetAnchor=p,f._lpa=t.targetAnchor&&i(t.targetAnchor);break}u(a,t,f,n,s,r,o)}Ji(t)}return t.anchor&&i(t.anchor)}const hf=af;function Ji(e){const t=e.ctx;if(t&&t.ut){let n=e.children[0].el;for(;n!==e.targetAnchor;)n.nodeType===1&&n.setAttribute("data-v-owner",t.uid),n=n.nextSibling;t.ut()}}const ye=Symbol.for("v-fgt"),Ot=Symbol.for("v-txt"),Ee=Symbol.for("v-cmt"),Pt=Symbol.for("v-stc"),pn=[];let Re=null;function xs(e=!1){pn.push(Re=e?null:[])}function Xi(){pn.pop(),Re=pn[pn.length-1]||null}let Mt=1;function Gs(e){Mt+=e}function Zi(e){return e.dynamicChildren=Mt>0?Re||$t:null,Xi(),Mt>0&&Re&&Re.push(e),e}function pf(e,t,n,s,r,o){return Zi(Lr(e,t,n,s,r,o,!0))}function Nr(e,t,n,s,r){return Zi(fe(e,t,n,s,r,!0))}function gt(e){return e?e.__v_isVNode===!0:!1}function Be(e,t){return e.type===t.type&&e.key===t.key}function gf(e){}const Rs="__vInternal",Gi=({key:e})=>e??null,Jn=({ref:e,ref_key:t,ref_for:n})=>(typeof e=="number"&&(e=""+e),e!=null?ae(e)||ge(e)||Q(e)?{i:me,r:e,k:t,f:!!n}:e:null);function Lr(e,t=null,n=null,s=0,r=null,o=e===ye?0:1,i=!1,l=!1){const c={__v_isVNode:!0,__v_skip:!0,type:e,props:t,key:t&&Gi(t),ref:t&&Jn(t),scopeId:ys,slotScopeIds:null,children:n,component:null,suspense:null,ssContent:null,ssFallback:null,dirs:null,transition:null,el:null,anchor:null,target:null,targetAnchor:null,staticCount:0,shapeFlag:o,patchFlag:s,dynamicProps:r,dynamicChildren:null,appContext:null,ctx:me};return l?(Hr(c,n),o&128&&e.normalize(c)):n&&(c.shapeFlag|=ae(n)?8:16),Mt>0&&!i&&Re&&(c.patchFlag>0||o&6)&&c.patchFlag!==32&&Re.push(c),c}const fe=mf;function mf(e,t=null,n=null,s=0,r=null,o=!1){if((!e||e===Bi)&&(e=Ee),gt(e)){const l=We(e,t,!0);return n&&Hr(l,n),Mt>0&&!o&&Re&&(l.shapeFlag&6?Re[Re.indexOf(e)]=l:Re.push(l)),l.patchFlag|=-2,l}if(Rf(e)&&(e=e.__vccOpts),t){t=el(t);let{class:l,style:c}=t;l&&!ae(l)&&(t.class=Mn(l)),le(c)&&(yr(c)&&!D(c)&&(c=ue({},c)),t.style=On(c))}const i=ae(e)?1:Ci(e)?128:ff(e)?64:le(e)?4:Q(e)?2:0;return Lr(e,t,n,s,r,i,o,!0)}function el(e){return e?yr(e)||Rs in e?ue({},e):e:null}function We(e,t,n=!1){const{props:s,ref:r,patchFlag:o,children:i}=e,l=t?tl(s||{},t):s;return{__v_isVNode:!0,__v_skip:!0,type:e.type,props:l,key:l&&Gi(l),ref:t&&t.ref?n&&r?D(r)?r.concat(Jn(t)):[r,Jn(t)]:Jn(t):r,scopeId:e.scopeId,slotScopeIds:e.slotScopeIds,children:i,target:e.target,targetAnchor:e.targetAnchor,staticCount:e.staticCount,shapeFlag:e.shapeFlag,patchFlag:t&&e.type!==ye?o===-1?16:o|16:o,dynamicProps:e.dynamicProps,dynamicChildren:e.dynamicChildren,appContext:e.appContext,dirs:e.dirs,transition:e.transition,component:e.component,suspense:e.suspense,ssContent:e.ssContent&&We(e.ssContent),ssFallback:e.ssFallback&&We(e.ssFallback),el:e.el,anchor:e.anchor,ctx:e.ctx,ce:e.ce}}function Br(e=" ",t=0){return fe(Ot,null,e,t)}function _f(e,t){const n=fe(Pt,null,e);return n.staticCount=t,n}function yf(e="",t=!1){return t?(xs(),Nr(Ee,null,e)):fe(Ee,null,e)}function Oe(e){return e==null||typeof e=="boolean"?fe(Ee):D(e)?fe(ye,null,e.slice()):typeof e=="object"?lt(e):fe(Ot,null,String(e))}function lt(e){return e.el===null&&e.patchFlag!==-1||e.memo?e:We(e)}function Hr(e,t){let n=0;const{shapeFlag:s}=e;if(t==null)t=null;else if(D(t))n=16;else if(typeof t=="object")if(s&65){const r=t.default;r&&(r._c&&(r._d=!1),Hr(e,r()),r._c&&(r._d=!0));return}else{n=32;const r=t._;!r&&!(Rs in t)?t._ctx=me:r===3&&me&&(me.slots._===1?t._=1:(t._=2,e.patchFlag|=1024))}else Q(t)?(t={default:t,_ctx:me},n=32):(t=String(t),s&64?(n=16,t=[Br(t)]):n=8);e.children=t,e.shapeFlag|=n}function tl(...e){const t={};for(let n=0;n<e.length;n++){const s=e[n];for(const r in s)if(r==="class")t.class!==s.class&&(t.class=Mn([t.class,s.class]));else if(r==="style")t.style=On([t.style,s.style]);else if(An(r)){const o=t[r],i=s[r];i&&o!==i&&!(D(o)&&o.includes(i))&&(t[r]=o?[].concat(o,i):i)}else r!==""&&(t[r]=s[r])}return t}function xe(e,t,n,s=null){Ie(e,t,7,[n,s])}const bf=ji();let vf=0;function nl(e,t,n){const s=e.type,r=(t?t.appContext:e.appContext)||bf,o={uid:vf++,vnode:e,type:s,parent:t,appContext:r,root:null,next:null,subTree:null,effect:null,update:null,scope:new pr(!0),render:null,proxy:null,exposed:null,exposeProxy:null,withProxy:null,provides:t?t.provides:Object.create(r.provides),accessCache:null,renderCache:[],components:null,directives:null,propsOptions:Ki(s,r),emitsOptions:Ei(s,r),emit:null,emitted:null,propsDefaults:ie,inheritAttrs:s.inheritAttrs,ctx:ie,data:ie,props:ie,attrs:ie,slots:ie,refs:ie,setupState:ie,setupContext:null,attrsProxy:null,slotsProxy:null,suspense:n,suspenseId:n?n.pendingId:0,asyncDep:null,asyncResolved:!1,isMounted:!1,isUnmounted:!1,isDeactivated:!1,bc:null,c:null,bm:null,m:null,bu:null,u:null,um:null,bum:null,da:null,a:null,rtg:null,rtc:null,ec:null,sp:null};return o.ctx={_:o},o.root=t?t.root:o,o.emit=tu.bind(null,o),e.ce&&e.ce(o),o}let pe=null;const et=()=>pe||me;let Dr,Bt,mo="__VUE_INSTANCE_SETTERS__";(Bt=Us()[mo])||(Bt=Us()[mo]=[]),Bt.push(e=>pe=e),Dr=e=>{Bt.length>1?Bt.forEach(t=>t(e)):Bt[0](e)};const mt=e=>{Dr(e),e.scope.on()},dt=()=>{pe&&pe.scope.off(),Dr(null)};function sl(e){return e.vnode.shapeFlag&4}let zt=!1;function rl(e,t=!1){zt=t;const{props:n,children:s}=e.vnode,r=sl(e);nf(e,n,r,t),of(e,s);const o=r?Ef(e,t):void 0;return zt=!1,o}function Ef(e,t){const n=e.type;e.accessCache=Object.create(null),e.proxy=br(new Proxy(e.ctx,Ys));const{setup:s}=n;if(s){const r=e.setupContext=s.length>1?il(e):null;mt(e),Zt();const o=Xe(s,e,0,[e.props,r]);if(Gt(),dt(),dr(o)){if(o.then(dt,dt),t)return o.then(i=>{er(e,i,t)}).catch(i=>{kt(i,e,0)});e.asyncDep=o}else er(e,o,t)}else ol(e,t)}function er(e,t,n){Q(t)?e.type.__ssrInlineRender?e.ssrRender=t:e.render=t:le(t)&&(e.setupState=Cr(t)),ol(e,n)}let rs,tr;function Cf(e){rs=e,tr=t=>{t.render._rc&&(t.withProxy=new Proxy(t.ctx,ku))}}const wf=()=>!rs;function ol(e,t,n){const s=e.type;if(!e.render){if(!t&&rs&&!s.render){const r=s.template||Ir(e).template;if(r){const{isCustomElement:o,compilerOptions:i}=e.appContext.config,{delimiters:l,compilerOptions:c}=s,u=ue(ue({isCustomElement:o,delimiters:l},i),c);s.render=rs(r,u)}}e.render=s.render||He,tr&&tr(e)}mt(e),Zt(),Yu(e),Gt(),dt()}function xf(e){return e.attrsProxy||(e.attrsProxy=new Proxy(e.attrs,{get(t,n){return Pe(e,"get","$attrs"),t[n]}}))}function il(e){const t=n=>{e.exposed=n||{}};return{get attrs(){return xf(e)},slots:e.slots,emit:e.emit,expose:t}}function Ts(e){if(e.exposed)return e.exposeProxy||(e.exposeProxy=new Proxy(Cr(br(e.exposed)),{get(t,n){if(n in t)return t[n];if(n in an)return an[n](e)},has(t,n){return n in t||n in an}}))}function nr(e,t=!0){return Q(e)?e.displayName||e.name:e.name||t&&e.__name}function Rf(e){return Q(e)&&"__vccOpts"in e}const Me=(e,t)=>Yc(e,t,zt);function Ps(e,t,n){const s=arguments.length;return s===2?le(t)&&!D(t)?gt(t)?fe(e,null,[t]):fe(e,t):fe(e,null,t):(s>3?n=Array.prototype.slice.call(arguments,2):s===3&&gt(n)&&(n=[n]),fe(e,t,n))}const ll=Symbol.for("v-scx"),cl=()=>De(ll);function Tf(){}function Pf(e,t,n,s){const r=n[s];if(r&&ul(r,e))return r;const o=t();return o.memo=e.slice(),n[s]=o}function ul(e,t){const n=e.memo;if(n.length!=t.length)return!1;for(let s=0;s<n.length;s++)if(Wt(n[s],t[s]))return!1;return Mt>0&&Re&&Re.push(e),!0}const fl="3.3.4",Af={createComponentInstance:nl,setupComponent:rl,renderComponentRoot:Qn,setCurrentRenderingInstance:wn,isVNode:gt,normalizeVNode:Oe},Sf=Af,Of=null,Mf=null,If="http://www.w3.org/2000/svg",Et=typeof document<"u"?document:null,_o=Et&&Et.createElement("template"),kf={insert:(e,t,n)=>{t.insertBefore(e,n||null)},remove:e=>{const t=e.parentNode;t&&t.removeChild(e)},createElement:(e,t,n,s)=>{const r=t?Et.createElementNS(If,e):Et.createElement(e,n?{is:n}:void 0);return e==="select"&&s&&s.multiple!=null&&r.setAttribute("multiple",s.multiple),r},createText:e=>Et.createTextNode(e),createComment:e=>Et.createComment(e),setText:(e,t)=>{e.nodeValue=t},setElementText:(e,t)=>{e.textContent=t},parentNode:e=>e.parentNode,nextSibling:e=>e.nextSibling,querySelector:e=>Et.querySelector(e),setScopeId(e,t){e.setAttribute(t,"")},insertStaticContent(e,t,n,s,r,o){const i=n?n.previousSibling:t.lastChild;if(r&&(r===o||r.nextSibling))for(;t.insertBefore(r.cloneNode(!0),n),!(r===o||!(r=r.nextSibling)););else{_o.innerHTML=s?`<svg>${e}</svg>`:e;const l=_o.content;if(s){const c=l.firstChild;for(;c.firstChild;)l.appendChild(c.firstChild);l.removeChild(c)}t.insertBefore(l,n)}return[i?i.nextSibling:t.firstChild,n?n.previousSibling:t.lastChild]}};function Ff(e,t,n){const s=e._vtc;s&&(t=(t?[t,...s]:[...s]).join(" ")),t==null?e.removeAttribute("class"):n?e.setAttribute("class",t):e.className=t}function Nf(e,t,n){const s=e.style,r=ae(n);if(n&&!r){if(t&&!ae(t))for(const o in t)n[o]==null&&sr(s,o,"");for(const o in n)sr(s,o,n[o])}else{const o=s.display;r?t!==n&&(s.cssText=n):t&&e.removeAttribute("style"),"_vod"in e&&(s.display=o)}}const yo=/\s*!important$/;function sr(e,t,n){if(D(n))n.forEach(s=>sr(e,t,s));else if(n==null&&(n=""),t.startsWith("--"))e.setProperty(t,n);else{const s=Lf(e,t);yo.test(n)?e.setProperty(Fe(s),n.replace(yo,""),"important"):e[s]=n}}const bo=["Webkit","Moz","ms"],Ls={};function Lf(e,t){const n=Ls[t];if(n)return n;let s=Te(t);if(s!=="filter"&&s in e)return Ls[t]=s;s=Sn(s);for(let r=0;r<bo.length;r++){const o=bo[r]+s;if(o in e)return Ls[t]=o}return t}const vo="http://www.w3.org/1999/xlink";function Bf(e,t,n,s,r){if(s&&t.startsWith("xlink:"))n==null?e.removeAttributeNS(vo,t.slice(6,t.length)):e.setAttributeNS(vo,t,n);else{const o=tc(t);n==null||o&&!Xo(n)?e.removeAttribute(t):e.setAttribute(t,o?"":n)}}function Hf(e,t,n,s,r,o,i){if(t==="innerHTML"||t==="textContent"){s&&i(s,r,o),e[t]=n??"";return}const l=e.tagName;if(t==="value"&&l!=="PROGRESS"&&!l.includes("-")){e._value=n;const u=l==="OPTION"?e.getAttribute("value"):e.value,f=n??"";u!==f&&(e.value=f),n==null&&e.removeAttribute(t);return}let c=!1;if(n===""||n==null){const u=typeof e[t];u==="boolean"?n=Xo(n):n==null&&u==="string"?(n="",c=!0):u==="number"&&(n=0,c=!0)}try{e[t]=n}catch{}c&&e.removeAttribute(t)}function Je(e,t,n,s){e.addEventListener(t,n,s)}function Df(e,t,n,s){e.removeEventListener(t,n,s)}function $f(e,t,n,s,r=null){const o=e._vei||(e._vei={}),i=o[t];if(s&&i)i.value=s;else{const[l,c]=jf(t);if(s){const u=o[t]=Vf(s,r);Je(e,l,u,c)}else i&&(Df(e,l,i,c),o[t]=void 0)}}const Eo=/(?:Once|Passive|Capture)$/;function jf(e){let t;if(Eo.test(e)){t={};let s;for(;s=e.match(Eo);)e=e.slice(0,e.length-s[0].length),t[s[0].toLowerCase()]=!0}return[e[2]===":"?e.slice(3):Fe(e.slice(2)),t]}let Bs=0;const Uf=Promise.resolve(),Kf=()=>Bs||(Uf.then(()=>Bs=0),Bs=Date.now());function Vf(e,t){const n=s=>{if(!s._vts)s._vts=Date.now();else if(s._vts<=n.attached)return;Ie(Wf(s,n.value),t,5,[s])};return n.value=e,n.attached=Kf(),n}function Wf(e,t){if(D(t)){const n=e.stopImmediatePropagation;return e.stopImmediatePropagation=()=>{n.call(e),e._stopped=!0},t.map(s=>r=>!r._stopped&&s&&s(r))}else return t}const Co=/^on[a-z]/,qf=(e,t,n,s,r=!1,o,i,l,c)=>{t==="class"?Ff(e,s,r):t==="style"?Nf(e,n,s):An(t)?fr(t)||$f(e,t,n,s,i):(t[0]==="."?(t=t.slice(1),!0):t[0]==="^"?(t=t.slice(1),!1):zf(e,t,s,r))?Hf(e,t,s,o,i,l,c):(t==="true-value"?e._trueValue=s:t==="false-value"&&(e._falseValue=s),Bf(e,t,s,r))};function zf(e,t,n,s){return s?!!(t==="innerHTML"||t==="textContent"||t in e&&Co.test(t)&&Q(n)):t==="spellcheck"||t==="draggable"||t==="translate"||t==="form"||t==="list"&&e.tagName==="INPUT"||t==="type"&&e.tagName==="TEXTAREA"||Co.test(t)&&ae(n)?!1:t in e}function al(e,t){const n=Fn(e);class s extends As{constructor(o){super(n,o,t)}}return s.def=n,s}const Yf=e=>al(e,Pl),Qf=typeof HTMLElement<"u"?HTMLElement:class{};class As extends Qf{constructor(t,n={},s){super(),this._def=t,this._props=n,this._instance=null,this._connected=!1,this._resolved=!1,this._numberProps=null,this.shadowRoot&&s?s(this._createVNode(),this.shadowRoot):(this.attachShadow({mode:"open"}),this._def.__asyncLoader||this._resolveProps(this._def))}connectedCallback(){this._connected=!0,this._instance||(this._resolved?this._update():this._resolveDef())}disconnectedCallback(){this._connected=!1,gs(()=>{this._connected||(ir(null,this.shadowRoot),this._instance=null)})}_resolveDef(){this._resolved=!0;for(let s=0;s<this.attributes.length;s++)this._setAttr(this.attributes[s].name);new MutationObserver(s=>{for(const r of s)this._setAttr(r.attributeName)}).observe(this,{attributes:!0});const t=(s,r=!1)=>{const{props:o,styles:i}=s;let l;if(o&&!D(o))for(const c in o){const u=o[c];(u===Number||u&&u.type===Number)&&(c in this._props&&(this._props[c]=Gn(this._props[c])),(l||(l=Object.create(null)))[Te(c)]=!0)}this._numberProps=l,r&&this._resolveProps(s),this._applyStyles(i),this._update()},n=this._def.__asyncLoader;n?n().then(s=>t(s,!0)):t(this._def)}_resolveProps(t){const{props:n}=t,s=D(n)?n:Object.keys(n||{});for(const r of Object.keys(this))r[0]!=="_"&&s.includes(r)&&this._setProp(r,this[r],!0,!1);for(const r of s.map(Te))Object.defineProperty(this,r,{get(){return this._getProp(r)},set(o){this._setProp(r,o)}})}_setAttr(t){let n=this.getAttribute(t);const s=Te(t);this._numberProps&&this._numberProps[s]&&(n=Gn(n)),this._setProp(s,n,!1)}_getProp(t){return this._props[t]}_setProp(t,n,s=!0,r=!0){n!==this._props[t]&&(this._props[t]=n,r&&this._instance&&this._update(),s&&(n===!0?this.setAttribute(Fe(t),""):typeof n=="string"||typeof n=="number"?this.setAttribute(Fe(t),n+""):n||this.removeAttribute(Fe(t))))}_update(){ir(this._createVNode(),this.shadowRoot)}_createVNode(){const t=fe(this._def,ue({},this._props));return this._instance||(t.ce=n=>{this._instance=n,n.isCE=!0;const s=(o,i)=>{this.dispatchEvent(new CustomEvent(o,{detail:i}))};n.emit=(o,...i)=>{s(o,i),Fe(o)!==o&&s(Fe(o),i)};let r=this;for(;r=r&&(r.parentNode||r.host);)if(r instanceof As){n.parent=r._instance,n.provides=r._instance.provides;break}}),t}_applyStyles(t){t&&t.forEach(n=>{const s=document.createElement("style");s.textContent=n,this.shadowRoot.appendChild(s)})}}function Jf(e="$style"){{const t=et();if(!t)return ie;const n=t.type.__cssModules;if(!n)return ie;const s=n[e];return s||ie}}function Xf(e){const t=et();if(!t)return;const n=t.ut=(r=e(t.proxy))=>{Array.from(document.querySelectorAll(`[data-v-owner="${t.uid}"]`)).forEach(o=>or(o,r))},s=()=>{const r=e(t.proxy);rr(t.subTree,r),n(r)};xi(s),Ln(()=>{const r=new MutationObserver(s);r.observe(t.subTree.el.parentNode,{childList:!0}),ws(()=>r.disconnect())})}function rr(e,t){if(e.shapeFlag&128){const n=e.suspense;e=n.activeBranch,n.pendingBranch&&!n.isHydrating&&n.effects.push(()=>{rr(n.activeBranch,t)})}for(;e.component;)e=e.component.subTree;if(e.shapeFlag&1&&e.el)or(e.el,t);else if(e.type===ye)e.children.forEach(n=>rr(n,t));else if(e.type===Pt){let{el:n,anchor:s}=e;for(;n&&(or(n,t),n!==s);)n=n.nextSibling}}function or(e,t){if(e.nodeType===1){const n=e.style;for(const s in t)n.setProperty(`--${s}`,t[s])}}const rt="transition",nn="animation",$r=(e,{slots:t})=>Ps(Ti,hl(e),t);$r.displayName="Transition";const dl={name:String,type:String,css:{type:Boolean,default:!0},duration:[String,Number,Object],enterFromClass:String,enterActiveClass:String,enterToClass:String,appearFromClass:String,appearActiveClass:String,appearToClass:String,leaveFromClass:String,leaveActiveClass:String,leaveToClass:String},Zf=$r.props=ue({},Sr,dl),bt=(e,t=[])=>{D(e)?e.forEach(n=>n(...t)):e&&e(...t)},wo=e=>e?D(e)?e.some(t=>t.length>1):e.length>1:!1;function hl(e){const t={};for(const L in e)L in dl||(t[L]=e[L]);if(e.css===!1)return t;const{name:n="v",type:s,duration:r,enterFromClass:o=`${n}-enter-from`,enterActiveClass:i=`${n}-enter-active`,enterToClass:l=`${n}-enter-to`,appearFromClass:c=o,appearActiveClass:u=i,appearToClass:f=l,leaveFromClass:a=`${n}-leave-from`,leaveActiveClass:p=`${n}-leave-active`,leaveToClass:y=`${n}-leave-to`}=e,E=Gf(r),A=E&&E[0],k=E&&E[1],{onBeforeEnter:b,onEnter:g,onEnterCancelled:R,onLeave:_,onLeaveCancelled:S,onBeforeAppear:B=b,onAppear:N=g,onAppearCancelled:x=R}=t,j=(L,Y,$)=>{it(L,Y?f:l),it(L,Y?u:i),$&&$()},U=(L,Y)=>{L._isLeaving=!1,it(L,a),it(L,y),it(L,p),Y&&Y()},z=L=>(Y,$)=>{const de=L?N:g,G=()=>j(Y,L,$);bt(de,[Y,G]),xo(()=>{it(Y,L?c:o),Ye(Y,L?f:l),wo(de)||Ro(Y,s,A,G)})};return ue(t,{onBeforeEnter(L){bt(b,[L]),Ye(L,o),Ye(L,i)},onBeforeAppear(L){bt(B,[L]),Ye(L,c),Ye(L,u)},onEnter:z(!1),onAppear:z(!0),onLeave(L,Y){L._isLeaving=!0;const $=()=>U(L,Y);Ye(L,a),gl(),Ye(L,p),xo(()=>{L._isLeaving&&(it(L,a),Ye(L,y),wo(_)||Ro(L,s,k,$))}),bt(_,[L,$])},onEnterCancelled(L){j(L,!1),bt(R,[L])},onAppearCancelled(L){j(L,!0),bt(x,[L])},onLeaveCancelled(L){U(L),bt(S,[L])}})}function Gf(e){if(e==null)return null;if(le(e))return[Hs(e.enter),Hs(e.leave)];{const t=Hs(e);return[t,t]}}function Hs(e){return Gn(e)}function Ye(e,t){t.split(/\s+/).forEach(n=>n&&e.classList.add(n)),(e._vtc||(e._vtc=new Set)).add(t)}function it(e,t){t.split(/\s+/).forEach(s=>s&&e.classList.remove(s));const{_vtc:n}=e;n&&(n.delete(t),n.size||(e._vtc=void 0))}function xo(e){requestAnimationFrame(()=>{requestAnimationFrame(e)})}let ea=0;function Ro(e,t,n,s){const r=e._endId=++ea,o=()=>{r===e._endId&&s()};if(n)return setTimeout(o,n);const{type:i,timeout:l,propCount:c}=pl(e,t);if(!i)return s();const u=i+"end";let f=0;const a=()=>{e.removeEventListener(u,p),o()},p=y=>{y.target===e&&++f>=c&&a()};setTimeout(()=>{f<c&&a()},l+1),e.addEventListener(u,p)}function pl(e,t){const n=window.getComputedStyle(e),s=E=>(n[E]||"").split(", "),r=s(`${rt}Delay`),o=s(`${rt}Duration`),i=To(r,o),l=s(`${nn}Delay`),c=s(`${nn}Duration`),u=To(l,c);let f=null,a=0,p=0;t===rt?i>0&&(f=rt,a=i,p=o.length):t===nn?u>0&&(f=nn,a=u,p=c.length):(a=Math.max(i,u),f=a>0?i>u?rt:nn:null,p=f?f===rt?o.length:c.length:0);const y=f===rt&&/\b(transform|all)(,|$)/.test(s(`${rt}Property`).toString());return{type:f,timeout:a,propCount:p,hasTransform:y}}function To(e,t){for(;e.length<t.length;)e=e.concat(e);return Math.max(...t.map((n,s)=>Po(n)+Po(e[s])))}function Po(e){return Number(e.slice(0,-1).replace(",","."))*1e3}function gl(){return document.body.offsetHeight}const ml=new WeakMap,_l=new WeakMap,yl={name:"TransitionGroup",props:ue({},Zf,{tag:String,moveClass:String}),setup(e,{slots:t}){const n=et(),s=Ar();let r,o;return Es(()=>{if(!r.length)return;const i=e.moveClass||`${e.name||"v"}-move`;if(!ia(r[0].el,n.vnode.el,i))return;r.forEach(sa),r.forEach(ra);const l=r.filter(oa);gl(),l.forEach(c=>{const u=c.el,f=u.style;Ye(u,i),f.transform=f.webkitTransform=f.transitionDuration="";const a=u._moveCb=p=>{p&&p.target!==u||(!p||/transform$/.test(p.propertyName))&&(u.removeEventListener("transitionend",a),u._moveCb=null,it(u,i))};u.addEventListener("transitionend",a)})}),()=>{const i=Z(e),l=hl(i);let c=i.tag||ye;r=o,o=t.default?bs(t.default()):[];for(let u=0;u<o.length;u++){const f=o[u];f.key!=null&&St(f,qt(f,l,s,n))}if(r)for(let u=0;u<r.length;u++){const f=r[u];St(f,qt(f,l,s,n)),ml.set(f,f.el.getBoundingClientRect())}return fe(c,null,o)}}},ta=e=>delete e.mode;yl.props;const na=yl;function sa(e){const t=e.el;t._moveCb&&t._moveCb(),t._enterCb&&t._enterCb()}function ra(e){_l.set(e,e.el.getBoundingClientRect())}function oa(e){const t=ml.get(e),n=_l.get(e),s=t.left-n.left,r=t.top-n.top;if(s||r){const o=e.el.style;return o.transform=o.webkitTransform=`translate(${s}px,${r}px)`,o.transitionDuration="0s",e}}function ia(e,t,n){const s=e.cloneNode();e._vtc&&e._vtc.forEach(i=>{i.split(/\s+/).forEach(l=>l&&s.classList.remove(l))}),n.split(/\s+/).forEach(i=>i&&s.classList.add(i)),s.style.display="none";const r=t.nodeType===1?t:t.parentNode;r.appendChild(s);const{hasTransform:o}=pl(s);return r.removeChild(s),o}const _t=e=>{const t=e.props["onUpdate:modelValue"]||!1;return D(t)?n=>Ut(t,n):t};function la(e){e.target.composing=!0}function Ao(e){const t=e.target;t.composing&&(t.composing=!1,t.dispatchEvent(new Event("input")))}const os={created(e,{modifiers:{lazy:t,trim:n,number:s}},r){e._assign=_t(r);const o=s||r.props&&r.props.type==="number";Je(e,t?"change":"input",i=>{if(i.target.composing)return;let l=e.value;n&&(l=l.trim()),o&&(l=Zn(l)),e._assign(l)}),n&&Je(e,"change",()=>{e.value=e.value.trim()}),t||(Je(e,"compositionstart",la),Je(e,"compositionend",Ao),Je(e,"change",Ao))},mounted(e,{value:t}){e.value=t??""},beforeUpdate(e,{value:t,modifiers:{lazy:n,trim:s,number:r}},o){if(e._assign=_t(o),e.composing||document.activeElement===e&&e.type!=="range"&&(n||s&&e.value.trim()===t||(r||e.type==="number")&&Zn(e.value)===t))return;const i=t??"";e.value!==i&&(e.value=i)}},jr={deep:!0,created(e,t,n){e._assign=_t(n),Je(e,"change",()=>{const s=e._modelValue,r=Yt(e),o=e.checked,i=e._assign;if(D(s)){const l=us(s,r),c=l!==-1;if(o&&!c)i(s.concat(r));else if(!o&&c){const u=[...s];u.splice(l,1),i(u)}}else if(It(s)){const l=new Set(s);o?l.add(r):l.delete(r),i(l)}else i(vl(e,o))})},mounted:So,beforeUpdate(e,t,n){e._assign=_t(n),So(e,t,n)}};function So(e,{value:t,oldValue:n},s){e._modelValue=t,D(t)?e.checked=us(t,s.props.value)>-1:It(t)?e.checked=t.has(s.props.value):t!==n&&(e.checked=ht(t,vl(e,!0)))}const Ur={created(e,{value:t},n){e.checked=ht(t,n.props.value),e._assign=_t(n),Je(e,"change",()=>{e._assign(Yt(e))})},beforeUpdate(e,{value:t,oldValue:n},s){e._assign=_t(s),t!==n&&(e.checked=ht(t,s.props.value))}},bl={deep:!0,created(e,{value:t,modifiers:{number:n}},s){const r=It(t);Je(e,"change",()=>{const o=Array.prototype.filter.call(e.options,i=>i.selected).map(i=>n?Zn(Yt(i)):Yt(i));e._assign(e.multiple?r?new Set(o):o:o[0])}),e._assign=_t(s)},mounted(e,{value:t}){Oo(e,t)},beforeUpdate(e,t,n){e._assign=_t(n)},updated(e,{value:t}){Oo(e,t)}};function Oo(e,t){const n=e.multiple;if(!(n&&!D(t)&&!It(t))){for(let s=0,r=e.options.length;s<r;s++){const o=e.options[s],i=Yt(o);if(n)D(t)?o.selected=us(t,i)>-1:o.selected=t.has(i);else if(ht(Yt(o),t)){e.selectedIndex!==s&&(e.selectedIndex=s);return}}!n&&e.selectedIndex!==-1&&(e.selectedIndex=-1)}}function Yt(e){return"_value"in e?e._value:e.value}function vl(e,t){const n=t?"_trueValue":"_falseValue";return n in e?e[n]:t}const El={created(e,t,n){Yn(e,t,n,null,"created")},mounted(e,t,n){Yn(e,t,n,null,"mounted")},beforeUpdate(e,t,n,s){Yn(e,t,n,s,"beforeUpdate")},updated(e,t,n,s){Yn(e,t,n,s,"updated")}};function Cl(e,t){switch(e){case"SELECT":return bl;case"TEXTAREA":return os;default:switch(t){case"checkbox":return jr;case"radio":return Ur;default:return os}}}function Yn(e,t,n,s,r){const i=Cl(e.tagName,n.props&&n.props.type)[r];i&&i(e,t,n,s)}function ca(){os.getSSRProps=({value:e})=>({value:e}),Ur.getSSRProps=({value:e},t)=>{if(t.props&&ht(t.props.value,e))return{checked:!0}},jr.getSSRProps=({value:e},t)=>{if(D(e)){if(t.props&&us(e,t.props.value)>-1)return{checked:!0}}else if(It(e)){if(t.props&&e.has(t.props.value))return{checked:!0}}else if(e)return{checked:!0}},El.getSSRProps=(e,t)=>{if(typeof t.type!="string")return;const n=Cl(t.type.toUpperCase(),t.props&&t.props.type);if(n.getSSRProps)return n.getSSRProps(e,t)}}const ua=["ctrl","shift","alt","meta"],fa={stop:e=>e.stopPropagation(),prevent:e=>e.preventDefault(),self:e=>e.target!==e.currentTarget,ctrl:e=>!e.ctrlKey,shift:e=>!e.shiftKey,alt:e=>!e.altKey,meta:e=>!e.metaKey,left:e=>"button"in e&&e.button!==0,middle:e=>"button"in e&&e.button!==1,right:e=>"button"in e&&e.button!==2,exact:(e,t)=>ua.some(n=>e[`${n}Key`]&&!t.includes(n))},aa=(e,t)=>(n,...s)=>{for(let r=0;r<t.length;r++){const o=fa[t[r]];if(o&&o(n,t))return}return e(n,...s)},da={esc:"escape",space:" ",up:"arrow-up",left:"arrow-left",right:"arrow-right",down:"arrow-down",delete:"backspace"},ha=(e,t)=>n=>{if(!("key"in n))return;const s=Fe(n.key);if(t.some(r=>r===s||da[r]===s))return e(n)},wl={beforeMount(e,{value:t},{transition:n}){e._vod=e.style.display==="none"?"":e.style.display,n&&t?n.beforeEnter(e):sn(e,t)},mounted(e,{value:t},{transition:n}){n&&t&&n.enter(e)},updated(e,{value:t,oldValue:n},{transition:s}){!t!=!n&&(s?t?(s.beforeEnter(e),sn(e,!0),s.enter(e)):s.leave(e,()=>{sn(e,!1)}):sn(e,t))},beforeUnmount(e,{value:t}){sn(e,t)}};function sn(e,t){e.style.display=t?e._vod:"none"}function pa(){wl.getSSRProps=({value:e})=>{if(!e)return{style:{display:"none"}}}}const xl=ue({patchProp:qf},kf);let gn,Mo=!1;function Rl(){return gn||(gn=zi(xl))}function Tl(){return gn=Mo?gn:Yi(xl),Mo=!0,gn}const ir=(...e)=>{Rl().render(...e)},Pl=(...e)=>{Tl().hydrate(...e)},ga=(...e)=>{const t=Rl().createApp(...e),{mount:n}=t;return t.mount=s=>{const r=Al(s);if(!r)return;const o=t._component;!Q(o)&&!o.render&&!o.template&&(o.template=r.innerHTML),r.innerHTML="";const i=n(r,!1,r instanceof SVGElement);return r instanceof Element&&(r.removeAttribute("v-cloak"),r.setAttribute("data-v-app","")),i},t},ma=(...e)=>{const t=Tl().createApp(...e),{mount:n}=t;return t.mount=s=>{const r=Al(s);if(r)return n(r,!0,r instanceof SVGElement)},t};function Al(e){return ae(e)?document.querySelector(e):e}let Io=!1;const _a=()=>{Io||(Io=!0,ca(),pa())},ya=()=>{},vd=Object.freeze(Object.defineProperty({__proto__:null,BaseTransition:Ti,BaseTransitionPropsValidators:Sr,Comment:Ee,EffectScope:pr,Fragment:ye,KeepAlive:wu,ReactiveEffect:In,Static:Pt,Suspense:fu,Teleport:hf,Text:Ot,Transition:$r,TransitionGroup:na,VueElement:As,assertNumber:Jc,callWithAsyncErrorHandling:Ie,callWithErrorHandling:Xe,camelize:Te,capitalize:Sn,cloneVNode:We,compatUtils:Mf,compile:ya,computed:Me,createApp:ga,createBlock:Nr,createCommentVNode:yf,createElementBlock:pf,createElementVNode:Lr,createHydrationRenderer:Yi,createPropsRestProxy:qu,createRenderer:zi,createSSRApp:ma,createSlots:Ou,createStaticVNode:_f,createTextVNode:Br,createVNode:fe,customRef:Uc,defineAsyncComponent:Eu,defineComponent:Fn,defineCustomElement:al,defineEmits:Nu,defineExpose:Lu,defineModel:Du,defineOptions:Bu,defineProps:Fu,defineSSRCustomElement:Yf,defineSlots:Hu,get devtools(){return Ht},effect:cc,effectScope:rc,getCurrentInstance:et,getCurrentScope:ei,getTransitionRawChildren:bs,guardReactiveProps:el,h:Ps,handleError:kt,hasInjectionContext:tf,hydrate:Pl,initCustomFormatter:Tf,initDirectivesForSSR:_a,inject:De,isMemoSame:ul,isProxy:yr,isReactive:xt,isReadonly:At,isRef:ge,isRuntimeOnly:wf,isShallow:bn,isVNode:gt,markRaw:br,mergeDefaults:Vu,mergeModels:Wu,mergeProps:tl,nextTick:gs,normalizeClass:Mn,normalizeProps:Gl,normalizeStyle:On,onActivated:Ai,onBeforeMount:Mi,onBeforeUnmount:Cs,onBeforeUpdate:Ii,onDeactivated:Si,onErrorCaptured:Li,onMounted:Ln,onRenderTracked:Ni,onRenderTriggered:Fi,onScopeDispose:oc,onServerPrefetch:ki,onUnmounted:ws,onUpdated:Es,openBlock:xs,popScopeId:su,provide:dn,proxyRefs:Cr,pushScopeId:nu,queuePostFlushCb:xr,reactive:en,readonly:_r,ref:Rt,registerRuntimeCompiler:Cf,render:ir,renderList:Su,renderSlot:Mu,resolveComponent:Tu,resolveDirective:Au,resolveDynamicComponent:Pu,resolveFilter:Of,resolveTransitionHooks:qt,setBlockTracking:Gs,setDevtoolsHook:vi,setTransitionHooks:St,shallowReactive:hi,shallowReadonly:Lc,shallowRef:pi,ssrContextKey:ll,ssrUtils:Sf,stop:uc,toDisplayString:sc,toHandlerKey:fn,toHandlers:Iu,toRaw:Z,toRef:qc,toRefs:Kc,toValue:Dc,transformVNodeArgs:gf,triggerRef:Hc,unref:ft,useAttrs:Uu,useCssModule:Jf,useCssVars:Xf,useModel:Ku,useSSRContext:cl,useSlots:ju,useTransitionState:Ar,vModelCheckbox:jr,vModelDynamic:El,vModelRadio:Ur,vModelSelect:bl,vModelText:os,vShow:wl,version:fl,warn:Qc,watch:at,watchEffect:mu,watchPostEffect:xi,watchSyncEffect:_u,withAsyncContext:zu,withCtx:Rr,withDefaults:$u,withDirectives:bu,withKeys:ha,withMemo:Pf,withModifiers:aa,withScopeId:ru},Symbol.toStringTag,{value:"Module"}));/*!
-  * vue-router v4.2.2
-  * (c) 2023 Eduardo San Martin Morote
-  * @license MIT
-  */const Dt=typeof window<"u";function ba(e){return e.__esModule||e[Symbol.toStringTag]==="Module"}const re=Object.assign;function Ds(e,t){const n={};for(const s in t){const r=t[s];n[s]=$e(r)?r.map(e):e(r)}return n}const mn=()=>{},$e=Array.isArray,va=/\/$/,Ea=e=>e.replace(va,"");function $s(e,t,n="/"){let s,r={},o="",i="";const l=t.indexOf("#");let c=t.indexOf("?");return l<c&&l>=0&&(c=-1),c>-1&&(s=t.slice(0,c),o=t.slice(c+1,l>-1?l:t.length),r=e(o)),l>-1&&(s=s||t.slice(0,l),i=t.slice(l,t.length)),s=Ra(s??t,n),{fullPath:s+(o&&"?")+o+i,path:s,query:r,hash:i}}function Ca(e,t){const n=t.query?e(t.query):"";return t.path+(n&&"?")+n+(t.hash||"")}function ko(e,t){return!t||!e.toLowerCase().startsWith(t.toLowerCase())?e:e.slice(t.length)||"/"}function wa(e,t,n){const s=t.matched.length-1,r=n.matched.length-1;return s>-1&&s===r&&Qt(t.matched[s],n.matched[r])&&Sl(t.params,n.params)&&e(t.query)===e(n.query)&&t.hash===n.hash}function Qt(e,t){return(e.aliasOf||e)===(t.aliasOf||t)}function Sl(e,t){if(Object.keys(e).length!==Object.keys(t).length)return!1;for(const n in e)if(!xa(e[n],t[n]))return!1;return!0}function xa(e,t){return $e(e)?Fo(e,t):$e(t)?Fo(t,e):e===t}function Fo(e,t){return $e(t)?e.length===t.length&&e.every((n,s)=>n===t[s]):e.length===1&&e[0]===t}function Ra(e,t){if(e.startsWith("/"))return e;if(!e)return t;const n=t.split("/"),s=e.split("/"),r=s[s.length-1];(r===".."||r===".")&&s.push("");let o=n.length-1,i,l;for(i=0;i<s.length;i++)if(l=s[i],l!==".")if(l==="..")o>1&&o--;else break;return n.slice(0,o).join("/")+"/"+s.slice(i-(i===s.length?1:0)).join("/")}var Pn;(function(e){e.pop="pop",e.push="push"})(Pn||(Pn={}));var _n;(function(e){e.back="back",e.forward="forward",e.unknown=""})(_n||(_n={}));function Ta(e){if(!e)if(Dt){const t=document.querySelector("base");e=t&&t.getAttribute("href")||"/",e=e.replace(/^\w+:\/\/[^\/]+/,"")}else e="/";return e[0]!=="/"&&e[0]!=="#"&&(e="/"+e),Ea(e)}const Pa=/^[^#]+#/;function Aa(e,t){return e.replace(Pa,"#")+t}function Sa(e,t){const n=document.documentElement.getBoundingClientRect(),s=e.getBoundingClientRect();return{behavior:t.behavior,left:s.left-n.left-(t.left||0),top:s.top-n.top-(t.top||0)}}const Ss=()=>({left:window.pageXOffset,top:window.pageYOffset});function Oa(e){let t;if("el"in e){const n=e.el,s=typeof n=="string"&&n.startsWith("#"),r=typeof n=="string"?s?document.getElementById(n.slice(1)):document.querySelector(n):n;if(!r)return;t=Sa(r,e)}else t=e;"scrollBehavior"in document.documentElement.style?window.scrollTo(t):window.scrollTo(t.left!=null?t.left:window.pageXOffset,t.top!=null?t.top:window.pageYOffset)}function No(e,t){return(history.state?history.state.position-t:-1)+e}const lr=new Map;function Ma(e,t){lr.set(e,t)}function Ia(e){const t=lr.get(e);return lr.delete(e),t}let ka=()=>location.protocol+"//"+location.host;function Ol(e,t){const{pathname:n,search:s,hash:r}=t,o=e.indexOf("#");if(o>-1){let l=r.includes(e.slice(o))?e.slice(o).length:1,c=r.slice(l);return c[0]!=="/"&&(c="/"+c),ko(c,"")}return ko(n,e)+s+r}function Fa(e,t,n,s){let r=[],o=[],i=null;const l=({state:p})=>{const y=Ol(e,location),E=n.value,A=t.value;let k=0;if(p){if(n.value=y,t.value=p,i&&i===E){i=null;return}k=A?p.position-A.position:0}else s(y);r.forEach(b=>{b(n.value,E,{delta:k,type:Pn.pop,direction:k?k>0?_n.forward:_n.back:_n.unknown})})};function c(){i=n.value}function u(p){r.push(p);const y=()=>{const E=r.indexOf(p);E>-1&&r.splice(E,1)};return o.push(y),y}function f(){const{history:p}=window;p.state&&p.replaceState(re({},p.state,{scroll:Ss()}),"")}function a(){for(const p of o)p();o=[],window.removeEventListener("popstate",l),window.removeEventListener("beforeunload",f)}return window.addEventListener("popstate",l),window.addEventListener("beforeunload",f,{passive:!0}),{pauseListeners:c,listen:u,destroy:a}}function Lo(e,t,n,s=!1,r=!1){return{back:e,current:t,forward:n,replaced:s,position:window.history.length,scroll:r?Ss():null}}function Na(e){const{history:t,location:n}=window,s={value:Ol(e,n)},r={value:t.state};r.value||o(s.value,{back:null,current:s.value,forward:null,position:t.length-1,replaced:!0,scroll:null},!0);function o(c,u,f){const a=e.indexOf("#"),p=a>-1?(n.host&&document.querySelector("base")?e:e.slice(a))+c:ka()+e+c;try{t[f?"replaceState":"pushState"](u,"",p),r.value=u}catch(y){console.error(y),n[f?"replace":"assign"](p)}}function i(c,u){const f=re({},t.state,Lo(r.value.back,c,r.value.forward,!0),u,{position:r.value.position});o(c,f,!0),s.value=c}function l(c,u){const f=re({},r.value,t.state,{forward:c,scroll:Ss()});o(f.current,f,!0);const a=re({},Lo(s.value,c,null),{position:f.position+1},u);o(c,a,!1),s.value=c}return{location:s,state:r,push:l,replace:i}}function Ed(e){e=Ta(e);const t=Na(e),n=Fa(e,t.state,t.location,t.replace);function s(o,i=!0){i||n.pauseListeners(),history.go(o)}const r=re({location:"",base:e,go:s,createHref:Aa.bind(null,e)},t,n);return Object.defineProperty(r,"location",{enumerable:!0,get:()=>t.location.value}),Object.defineProperty(r,"state",{enumerable:!0,get:()=>t.state.value}),r}function La(e){return typeof e=="string"||e&&typeof e=="object"}function Ml(e){return typeof e=="string"||typeof e=="symbol"}const ot={path:"/",name:void 0,params:{},query:{},hash:"",fullPath:"/",matched:[],meta:{},redirectedFrom:void 0},Il=Symbol("");var Bo;(function(e){e[e.aborted=4]="aborted",e[e.cancelled=8]="cancelled",e[e.duplicated=16]="duplicated"})(Bo||(Bo={}));function Jt(e,t){return re(new Error,{type:e,[Il]:!0},t)}function ze(e,t){return e instanceof Error&&Il in e&&(t==null||!!(e.type&t))}const Ho="[^/]+?",Ba={sensitive:!1,strict:!1,start:!0,end:!0},Ha=/[.+*?^${}()[\]/\\]/g;function Da(e,t){const n=re({},Ba,t),s=[];let r=n.start?"^":"";const o=[];for(const u of e){const f=u.length?[]:[90];n.strict&&!u.length&&(r+="/");for(let a=0;a<u.length;a++){const p=u[a];let y=40+(n.sensitive?.25:0);if(p.type===0)a||(r+="/"),r+=p.value.replace(Ha,"\\$&"),y+=40;else if(p.type===1){const{value:E,repeatable:A,optional:k,regexp:b}=p;o.push({name:E,repeatable:A,optional:k});const g=b||Ho;if(g!==Ho){y+=10;try{new RegExp(`(${g})`)}catch(_){throw new Error(`Invalid custom RegExp for param "${E}" (${g}): `+_.message)}}let R=A?`((?:${g})(?:/(?:${g}))*)`:`(${g})`;a||(R=k&&u.length<2?`(?:/${R})`:"/"+R),k&&(R+="?"),r+=R,y+=20,k&&(y+=-8),A&&(y+=-20),g===".*"&&(y+=-50)}f.push(y)}s.push(f)}if(n.strict&&n.end){const u=s.length-1;s[u][s[u].length-1]+=.7000000000000001}n.strict||(r+="/?"),n.end?r+="$":n.strict&&(r+="(?:/|$)");const i=new RegExp(r,n.sensitive?"":"i");function l(u){const f=u.match(i),a={};if(!f)return null;for(let p=1;p<f.length;p++){const y=f[p]||"",E=o[p-1];a[E.name]=y&&E.repeatable?y.split("/"):y}return a}function c(u){let f="",a=!1;for(const p of e){(!a||!f.endsWith("/"))&&(f+="/"),a=!1;for(const y of p)if(y.type===0)f+=y.value;else if(y.type===1){const{value:E,repeatable:A,optional:k}=y,b=E in u?u[E]:"";if($e(b)&&!A)throw new Error(`Provided param "${E}" is an array but it is not repeatable (* or + modifiers)`);const g=$e(b)?b.join("/"):b;if(!g)if(k)p.length<2&&(f.endsWith("/")?f=f.slice(0,-1):a=!0);else throw new Error(`Missing required param "${E}"`);f+=g}}return f||"/"}return{re:i,score:s,keys:o,parse:l,stringify:c}}function $a(e,t){let n=0;for(;n<e.length&&n<t.length;){const s=t[n]-e[n];if(s)return s;n++}return e.length<t.length?e.length===1&&e[0]===40+40?-1:1:e.length>t.length?t.length===1&&t[0]===40+40?1:-1:0}function ja(e,t){let n=0;const s=e.score,r=t.score;for(;n<s.length&&n<r.length;){const o=$a(s[n],r[n]);if(o)return o;n++}if(Math.abs(r.length-s.length)===1){if(Do(s))return 1;if(Do(r))return-1}return r.length-s.length}function Do(e){const t=e[e.length-1];return e.length>0&&t[t.length-1]<0}const Ua={type:0,value:""},Ka=/[a-zA-Z0-9_]/;function Va(e){if(!e)return[[]];if(e==="/")return[[Ua]];if(!e.startsWith("/"))throw new Error(`Invalid path "${e}"`);function t(y){throw new Error(`ERR (${n})/"${u}": ${y}`)}let n=0,s=n;const r=[];let o;function i(){o&&r.push(o),o=[]}let l=0,c,u="",f="";function a(){u&&(n===0?o.push({type:0,value:u}):n===1||n===2||n===3?(o.length>1&&(c==="*"||c==="+")&&t(`A repeatable param (${u}) must be alone in its segment. eg: '/:ids+.`),o.push({type:1,value:u,regexp:f,repeatable:c==="*"||c==="+",optional:c==="*"||c==="?"})):t("Invalid state to consume buffer"),u="")}function p(){u+=c}for(;l<e.length;){if(c=e[l++],c==="\\"&&n!==2){s=n,n=4;continue}switch(n){case 0:c==="/"?(u&&a(),i()):c===":"?(a(),n=1):p();break;case 4:p(),n=s;break;case 1:c==="("?n=2:Ka.test(c)?p():(a(),n=0,c!=="*"&&c!=="?"&&c!=="+"&&l--);break;case 2:c===")"?f[f.length-1]=="\\"?f=f.slice(0,-1)+c:n=3:f+=c;break;case 3:a(),n=0,c!=="*"&&c!=="?"&&c!=="+"&&l--,f="";break;default:t("Unknown state");break}}return n===2&&t(`Unfinished custom RegExp for param "${u}"`),a(),i(),r}function Wa(e,t,n){const s=Da(Va(e.path),n),r=re(s,{record:e,parent:t,children:[],alias:[]});return t&&!r.record.aliasOf==!t.record.aliasOf&&t.children.push(r),r}function qa(e,t){const n=[],s=new Map;t=Uo({strict:!1,end:!0,sensitive:!1},t);function r(f){return s.get(f)}function o(f,a,p){const y=!p,E=za(f);E.aliasOf=p&&p.record;const A=Uo(t,f),k=[E];if("alias"in f){const R=typeof f.alias=="string"?[f.alias]:f.alias;for(const _ of R)k.push(re({},E,{components:p?p.record.components:E.components,path:_,aliasOf:p?p.record:E}))}let b,g;for(const R of k){const{path:_}=R;if(a&&_[0]!=="/"){const S=a.record.path,B=S[S.length-1]==="/"?"":"/";R.path=a.record.path+(_&&B+_)}if(b=Wa(R,a,A),p?p.alias.push(b):(g=g||b,g!==b&&g.alias.push(b),y&&f.name&&!jo(b)&&i(f.name)),E.children){const S=E.children;for(let B=0;B<S.length;B++)o(S[B],b,p&&p.children[B])}p=p||b,(b.record.components&&Object.keys(b.record.components).length||b.record.name||b.record.redirect)&&c(b)}return g?()=>{i(g)}:mn}function i(f){if(Ml(f)){const a=s.get(f);a&&(s.delete(f),n.splice(n.indexOf(a),1),a.children.forEach(i),a.alias.forEach(i))}else{const a=n.indexOf(f);a>-1&&(n.splice(a,1),f.record.name&&s.delete(f.record.name),f.children.forEach(i),f.alias.forEach(i))}}function l(){return n}function c(f){let a=0;for(;a<n.length&&ja(f,n[a])>=0&&(f.record.path!==n[a].record.path||!kl(f,n[a]));)a++;n.splice(a,0,f),f.record.name&&!jo(f)&&s.set(f.record.name,f)}function u(f,a){let p,y={},E,A;if("name"in f&&f.name){if(p=s.get(f.name),!p)throw Jt(1,{location:f});A=p.record.name,y=re($o(a.params,p.keys.filter(g=>!g.optional).map(g=>g.name)),f.params&&$o(f.params,p.keys.map(g=>g.name))),E=p.stringify(y)}else if("path"in f)E=f.path,p=n.find(g=>g.re.test(E)),p&&(y=p.parse(E),A=p.record.name);else{if(p=a.name?s.get(a.name):n.find(g=>g.re.test(a.path)),!p)throw Jt(1,{location:f,currentLocation:a});A=p.record.name,y=re({},a.params,f.params),E=p.stringify(y)}const k=[];let b=p;for(;b;)k.unshift(b.record),b=b.parent;return{name:A,path:E,params:y,matched:k,meta:Qa(k)}}return e.forEach(f=>o(f)),{addRoute:o,resolve:u,removeRoute:i,getRoutes:l,getRecordMatcher:r}}function $o(e,t){const n={};for(const s of t)s in e&&(n[s]=e[s]);return n}function za(e){return{path:e.path,redirect:e.redirect,name:e.name,meta:e.meta||{},aliasOf:void 0,beforeEnter:e.beforeEnter,props:Ya(e),children:e.children||[],instances:{},leaveGuards:new Set,updateGuards:new Set,enterCallbacks:{},components:"components"in e?e.components||null:e.component&&{default:e.component}}}function Ya(e){const t={},n=e.props||!1;if("component"in e)t.default=n;else for(const s in e.components)t[s]=typeof n=="boolean"?n:n[s];return t}function jo(e){for(;e;){if(e.record.aliasOf)return!0;e=e.parent}return!1}function Qa(e){return e.reduce((t,n)=>re(t,n.meta),{})}function Uo(e,t){const n={};for(const s in e)n[s]=s in t?t[s]:e[s];return n}function kl(e,t){return t.children.some(n=>n===e||kl(e,n))}const Fl=/#/g,Ja=/&/g,Xa=/\//g,Za=/=/g,Ga=/\?/g,Nl=/\+/g,ed=/%5B/g,td=/%5D/g,Ll=/%5E/g,nd=/%60/g,Bl=/%7B/g,sd=/%7C/g,Hl=/%7D/g,rd=/%20/g;function Kr(e){return encodeURI(""+e).replace(sd,"|").replace(ed,"[").replace(td,"]")}function od(e){return Kr(e).replace(Bl,"{").replace(Hl,"}").replace(Ll,"^")}function cr(e){return Kr(e).replace(Nl,"%2B").replace(rd,"+").replace(Fl,"%23").replace(Ja,"%26").replace(nd,"`").replace(Bl,"{").replace(Hl,"}").replace(Ll,"^")}function id(e){return cr(e).replace(Za,"%3D")}function ld(e){return Kr(e).replace(Fl,"%23").replace(Ga,"%3F")}function cd(e){return e==null?"":ld(e).replace(Xa,"%2F")}function is(e){try{return decodeURIComponent(""+e)}catch{}return""+e}function ud(e){const t={};if(e===""||e==="?")return t;const s=(e[0]==="?"?e.slice(1):e).split("&");for(let r=0;r<s.length;++r){const o=s[r].replace(Nl," "),i=o.indexOf("="),l=is(i<0?o:o.slice(0,i)),c=i<0?null:is(o.slice(i+1));if(l in t){let u=t[l];$e(u)||(u=t[l]=[u]),u.push(c)}else t[l]=c}return t}function Ko(e){let t="";for(let n in e){const s=e[n];if(n=id(n),s==null){s!==void 0&&(t+=(t.length?"&":"")+n);continue}($e(s)?s.map(o=>o&&cr(o)):[s&&cr(s)]).forEach(o=>{o!==void 0&&(t+=(t.length?"&":"")+n,o!=null&&(t+="="+o))})}return t}function fd(e){const t={};for(const n in e){const s=e[n];s!==void 0&&(t[n]=$e(s)?s.map(r=>r==null?null:""+r):s==null?s:""+s)}return t}const ad=Symbol(""),Vo=Symbol(""),Os=Symbol(""),Dl=Symbol(""),ur=Symbol("");function rn(){let e=[];function t(s){return e.push(s),()=>{const r=e.indexOf(s);r>-1&&e.splice(r,1)}}function n(){e=[]}return{add:t,list:()=>e,reset:n}}function ct(e,t,n,s,r){const o=s&&(s.enterCallbacks[r]=s.enterCallbacks[r]||[]);return()=>new Promise((i,l)=>{const c=a=>{a===!1?l(Jt(4,{from:n,to:t})):a instanceof Error?l(a):La(a)?l(Jt(2,{from:t,to:a})):(o&&s.enterCallbacks[r]===o&&typeof a=="function"&&o.push(a),i())},u=e.call(s&&s.instances[r],t,n,c);let f=Promise.resolve(u);e.length<3&&(f=f.then(c)),f.catch(a=>l(a))})}function js(e,t,n,s){const r=[];for(const o of e)for(const i in o.components){let l=o.components[i];if(!(t!=="beforeRouteEnter"&&!o.instances[i]))if(dd(l)){const u=(l.__vccOpts||l)[t];u&&r.push(ct(u,n,s,o,i))}else{let c=l();r.push(()=>c.then(u=>{if(!u)return Promise.reject(new Error(`Couldn't resolve component "${i}" at "${o.path}"`));const f=ba(u)?u.default:u;o.components[i]=f;const p=(f.__vccOpts||f)[t];return p&&ct(p,n,s,o,i)()}))}}return r}function dd(e){return typeof e=="object"||"displayName"in e||"props"in e||"__vccOpts"in e}function Wo(e){const t=De(Os),n=De(Dl),s=Me(()=>t.resolve(ft(e.to))),r=Me(()=>{const{matched:c}=s.value,{length:u}=c,f=c[u-1],a=n.matched;if(!f||!a.length)return-1;const p=a.findIndex(Qt.bind(null,f));if(p>-1)return p;const y=qo(c[u-2]);return u>1&&qo(f)===y&&a[a.length-1].path!==y?a.findIndex(Qt.bind(null,c[u-2])):p}),o=Me(()=>r.value>-1&&md(n.params,s.value.params)),i=Me(()=>r.value>-1&&r.value===n.matched.length-1&&Sl(n.params,s.value.params));function l(c={}){return gd(c)?t[ft(e.replace)?"replace":"push"](ft(e.to)).catch(mn):Promise.resolve()}return{route:s,href:Me(()=>s.value.href),isActive:o,isExactActive:i,navigate:l}}const hd=Fn({name:"RouterLink",compatConfig:{MODE:3},props:{to:{type:[String,Object],required:!0},replace:Boolean,activeClass:String,exactActiveClass:String,custom:Boolean,ariaCurrentValue:{type:String,default:"page"}},useLink:Wo,setup(e,{slots:t}){const n=en(Wo(e)),{options:s}=De(Os),r=Me(()=>({[zo(e.activeClass,s.linkActiveClass,"router-link-active")]:n.isActive,[zo(e.exactActiveClass,s.linkExactActiveClass,"router-link-exact-active")]:n.isExactActive}));return()=>{const o=t.default&&t.default(n);return e.custom?o:Ps("a",{"aria-current":n.isExactActive?e.ariaCurrentValue:null,href:n.href,onClick:n.navigate,class:r.value},o)}}}),pd=hd;function gd(e){if(!(e.metaKey||e.altKey||e.ctrlKey||e.shiftKey)&&!e.defaultPrevented&&!(e.button!==void 0&&e.button!==0)){if(e.currentTarget&&e.currentTarget.getAttribute){const t=e.currentTarget.getAttribute("target");if(/\b_blank\b/i.test(t))return}return e.preventDefault&&e.preventDefault(),!0}}function md(e,t){for(const n in t){const s=t[n],r=e[n];if(typeof s=="string"){if(s!==r)return!1}else if(!$e(r)||r.length!==s.length||s.some((o,i)=>o!==r[i]))return!1}return!0}function qo(e){return e?e.aliasOf?e.aliasOf.path:e.path:""}const zo=(e,t,n)=>e??t??n,_d=Fn({name:"RouterView",inheritAttrs:!1,props:{name:{type:String,default:"default"},route:Object},compatConfig:{MODE:3},setup(e,{attrs:t,slots:n}){const s=De(ur),r=Me(()=>e.route||s.value),o=De(Vo,0),i=Me(()=>{let u=ft(o);const{matched:f}=r.value;let a;for(;(a=f[u])&&!a.components;)u++;return u}),l=Me(()=>r.value.matched[i.value]);dn(Vo,Me(()=>i.value+1)),dn(ad,l),dn(ur,r);const c=Rt();return at(()=>[c.value,l.value,e.name],([u,f,a],[p,y,E])=>{f&&(f.instances[a]=u,y&&y!==f&&u&&u===p&&(f.leaveGuards.size||(f.leaveGuards=y.leaveGuards),f.updateGuards.size||(f.updateGuards=y.updateGuards))),u&&f&&(!y||!Qt(f,y)||!p)&&(f.enterCallbacks[a]||[]).forEach(A=>A(u))},{flush:"post"}),()=>{const u=r.value,f=e.name,a=l.value,p=a&&a.components[f];if(!p)return Yo(n.default,{Component:p,route:u});const y=a.props[f],E=y?y===!0?u.params:typeof y=="function"?y(u):y:null,k=Ps(p,re({},E,t,{onVnodeUnmounted:b=>{b.component.isUnmounted&&(a.instances[f]=null)},ref:c}));return Yo(n.default,{Component:k,route:u})||k}}});function Yo(e,t){if(!e)return null;const n=e(t);return n.length===1?n[0]:n}const yd=_d;function Cd(e){const t=qa(e.routes,e),n=e.parseQuery||ud,s=e.stringifyQuery||Ko,r=e.history,o=rn(),i=rn(),l=rn(),c=pi(ot);let u=ot;Dt&&e.scrollBehavior&&"scrollRestoration"in history&&(history.scrollRestoration="manual");const f=Ds.bind(null,C=>""+C),a=Ds.bind(null,cd),p=Ds.bind(null,is);function y(C,H){let I,V;return Ml(C)?(I=t.getRecordMatcher(C),V=H):V=C,t.addRoute(V,I)}function E(C){const H=t.getRecordMatcher(C);H&&t.removeRoute(H)}function A(){return t.getRoutes().map(C=>C.record)}function k(C){return!!t.getRecordMatcher(C)}function b(C,H){if(H=re({},H||c.value),typeof C=="string"){const m=$s(n,C,H.path),v=t.resolve({path:m.path},H),w=r.createHref(m.fullPath);return re(m,v,{params:p(v.params),hash:is(m.hash),redirectedFrom:void 0,href:w})}let I;if("path"in C)I=re({},C,{path:$s(n,C.path,H.path).path});else{const m=re({},C.params);for(const v in m)m[v]==null&&delete m[v];I=re({},C,{params:a(m)}),H.params=a(H.params)}const V=t.resolve(I,H),se=C.hash||"";V.params=f(p(V.params));const d=Ca(s,re({},C,{hash:od(se),path:V.path})),h=r.createHref(d);return re({fullPath:d,hash:se,query:s===Ko?fd(C.query):C.query||{}},V,{redirectedFrom:void 0,href:h})}function g(C){return typeof C=="string"?$s(n,C,c.value.path):re({},C)}function R(C,H){if(u!==C)return Jt(8,{from:H,to:C})}function _(C){return N(C)}function S(C){return _(re(g(C),{replace:!0}))}function B(C){const H=C.matched[C.matched.length-1];if(H&&H.redirect){const{redirect:I}=H;let V=typeof I=="function"?I(C):I;return typeof V=="string"&&(V=V.includes("?")||V.includes("#")?V=g(V):{path:V},V.params={}),re({query:C.query,hash:C.hash,params:"path"in V?{}:C.params},V)}}function N(C,H){const I=u=b(C),V=c.value,se=C.state,d=C.force,h=C.replace===!0,m=B(I);if(m)return N(re(g(m),{state:typeof m=="object"?re({},se,m.state):se,force:d,replace:h}),H||I);const v=I;v.redirectedFrom=H;let w;return!d&&wa(s,V,I)&&(w=Jt(16,{to:v,from:V}),je(V,V,!0,!1)),(w?Promise.resolve(w):U(v,V)).catch(T=>ze(T)?ze(T,2)?T:tt(T):ne(T,v,V)).then(T=>{if(T){if(ze(T,2))return N(re({replace:h},g(T.to),{state:typeof T.to=="object"?re({},se,T.to.state):se,force:d}),H||v)}else T=L(v,V,!0,h,se);return z(v,V,T),T})}function x(C,H){const I=R(C,H);return I?Promise.reject(I):Promise.resolve()}function j(C){const H=Nt.values().next().value;return H&&typeof H.runWithContext=="function"?H.runWithContext(C):C()}function U(C,H){let I;const[V,se,d]=bd(C,H);I=js(V.reverse(),"beforeRouteLeave",C,H);for(const m of V)m.leaveGuards.forEach(v=>{I.push(ct(v,C,H))});const h=x.bind(null,C,H);return I.push(h),be(I).then(()=>{I=[];for(const m of o.list())I.push(ct(m,C,H));return I.push(h),be(I)}).then(()=>{I=js(se,"beforeRouteUpdate",C,H);for(const m of se)m.updateGuards.forEach(v=>{I.push(ct(v,C,H))});return I.push(h),be(I)}).then(()=>{I=[];for(const m of C.matched)if(m.beforeEnter&&!H.matched.includes(m))if($e(m.beforeEnter))for(const v of m.beforeEnter)I.push(ct(v,C,H));else I.push(ct(m.beforeEnter,C,H));return I.push(h),be(I)}).then(()=>(C.matched.forEach(m=>m.enterCallbacks={}),I=js(d,"beforeRouteEnter",C,H),I.push(h),be(I))).then(()=>{I=[];for(const m of i.list())I.push(ct(m,C,H));return I.push(h),be(I)}).catch(m=>ze(m,8)?m:Promise.reject(m))}function z(C,H,I){for(const V of l.list())j(()=>V(C,H,I))}function L(C,H,I,V,se){const d=R(C,H);if(d)return d;const h=H===ot,m=Dt?history.state:{};I&&(V||h?r.replace(C.fullPath,re({scroll:h&&m&&m.scroll},se)):r.push(C.fullPath,se)),c.value=C,je(C,H,I,h),tt()}let Y;function $(){Y||(Y=r.listen((C,H,I)=>{if(!Bn.listening)return;const V=b(C),se=B(V);if(se){N(re(se,{replace:!0}),V).catch(mn);return}u=V;const d=c.value;Dt&&Ma(No(d.fullPath,I.delta),Ss()),U(V,d).catch(h=>ze(h,12)?h:ze(h,2)?(N(h.to,V).then(m=>{ze(m,20)&&!I.delta&&I.type===Pn.pop&&r.go(-1,!1)}).catch(mn),Promise.reject()):(I.delta&&r.go(-I.delta,!1),ne(h,V,d))).then(h=>{h=h||L(V,d,!1),h&&(I.delta&&!ze(h,8)?r.go(-I.delta,!1):I.type===Pn.pop&&ze(h,20)&&r.go(-1,!1)),z(V,d,h)}).catch(mn)}))}let de=rn(),G=rn(),te;function ne(C,H,I){tt(C);const V=G.list();return V.length?V.forEach(se=>se(C,H,I)):console.error(C),Promise.reject(C)}function qe(){return te&&c.value!==ot?Promise.resolve():new Promise((C,H)=>{de.add([C,H])})}function tt(C){return te||(te=!C,$(),de.list().forEach(([H,I])=>C?I(C):H()),de.reset()),C}function je(C,H,I,V){const{scrollBehavior:se}=e;if(!Dt||!se)return Promise.resolve();const d=!I&&Ia(No(C.fullPath,0))||(V||!I)&&history.state&&history.state.scroll||null;return gs().then(()=>se(C,H,d)).then(h=>h&&Oa(h)).catch(h=>ne(h,C,H))}const we=C=>r.go(C);let Ft;const Nt=new Set,Bn={currentRoute:c,listening:!0,addRoute:y,removeRoute:E,hasRoute:k,getRoutes:A,resolve:b,options:e,push:_,replace:S,go:we,back:()=>we(-1),forward:()=>we(1),beforeEach:o.add,beforeResolve:i.add,afterEach:l.add,onError:G.add,isReady:qe,install(C){const H=this;C.component("RouterLink",pd),C.component("RouterView",yd),C.config.globalProperties.$router=H,Object.defineProperty(C.config.globalProperties,"$route",{enumerable:!0,get:()=>ft(c)}),Dt&&!Ft&&c.value===ot&&(Ft=!0,_(r.location).catch(se=>{}));const I={};for(const se in ot)I[se]=Me(()=>c.value[se]);C.provide(Os,H),C.provide(Dl,en(I)),C.provide(ur,c);const V=C.unmount;Nt.add(C),C.unmount=function(){Nt.delete(C),Nt.size<1&&(u=ot,Y&&Y(),Y=null,c.value=ot,Ft=!1,te=!1),V()}}};function be(C){return C.reduce((H,I)=>H.then(()=>j(I)),Promise.resolve())}return Bn}function bd(e,t){const n=[],s=[],r=[],o=Math.max(t.matched.length,e.matched.length);for(let i=0;i<o;i++){const l=t.matched[i];l&&(e.matched.find(u=>Qt(u,l))?s.push(l):n.push(l));const c=e.matched[i];c&&(t.matched.find(u=>Qt(u,c))||r.push(c))}return[n,s,r]}function wd(){return De(Os)}export{ft as $,gs as A,dn as B,Ou as C,aa as D,Es as E,ye as F,Cs as G,_r as H,Si as I,hf as J,bu as K,wl as L,Pu as M,_f as N,na as O,Su as P,mu as Q,gt as R,ir as S,$r as T,Ee as U,vd as V,rc as W,br as X,Cd as Y,Ed as Z,pi as _,en as a,ga as a0,wd as a1,ge as a2,nu as a3,su as a4,Ps as a5,Ai as a6,Mi as a7,Ot as a8,El as a9,hi as aa,Au as ab,os as ac,We as b,Me as c,Fn as d,ws as e,xs as f,et as g,pf as h,De as i,Mu as j,On as k,Lr as l,Tu as m,Mn as n,Ln as o,Nr as p,Rr as q,Rt as r,yf as s,Br as t,sc as u,fe as v,at as w,qc as x,Kc as y,tl as z};
diff --git a/spaces/subhajitmaji/MusicGen/audiocraft/modules/lstm.py b/spaces/subhajitmaji/MusicGen/audiocraft/modules/lstm.py
deleted file mode 100644
index c0866175950c1ca4f6cca98649525e6481853bba..0000000000000000000000000000000000000000
--- a/spaces/subhajitmaji/MusicGen/audiocraft/modules/lstm.py
+++ /dev/null
@@ -1,25 +0,0 @@
-# Copyright (c) Meta Platforms, Inc. and affiliates.
-# All rights reserved.
-#
-# This source code is licensed under the license found in the
-# LICENSE file in the root directory of this source tree.
-
-from torch import nn
-
-
-class StreamableLSTM(nn.Module):
-    """LSTM without worrying about the hidden state, nor the layout of the data.
-    Expects input as convolutional layout.
-    """
-    def __init__(self, dimension: int, num_layers: int = 2, skip: bool = True):
-        super().__init__()
-        self.skip = skip
-        self.lstm = nn.LSTM(dimension, dimension, num_layers)
-
-    def forward(self, x):
-        x = x.permute(2, 0, 1)
-        y, _ = self.lstm(x)
-        if self.skip:
-            y = y + x
-        y = y.permute(1, 2, 0)
-        return y
diff --git a/spaces/supertori/files/stable-diffusion-webui/modules/api/models.py b/spaces/supertori/files/stable-diffusion-webui/modules/api/models.py
deleted file mode 100644
index fa1c40df61f5421241a71abefa6195aff1f67f6a..0000000000000000000000000000000000000000
--- a/spaces/supertori/files/stable-diffusion-webui/modules/api/models.py
+++ /dev/null
@@ -1,289 +0,0 @@
-import inspect
-from pydantic import BaseModel, Field, create_model
-from typing import Any, Optional
-from typing_extensions import Literal
-from inflection import underscore
-from modules.processing import StableDiffusionProcessingTxt2Img, StableDiffusionProcessingImg2Img
-from modules.shared import sd_upscalers, opts, parser
-from typing import Dict, List
-
-API_NOT_ALLOWED = [
-    "self",
-    "kwargs",
-    "sd_model",
-    "outpath_samples",
-    "outpath_grids",
-    "sampler_index",
-    # "do_not_save_samples",
-    # "do_not_save_grid",
-    "extra_generation_params",
-    "overlay_images",
-    "do_not_reload_embeddings",
-    "seed_enable_extras",
-    "prompt_for_display",
-    "sampler_noise_scheduler_override",
-    "ddim_discretize"
-]
-
-class ModelDef(BaseModel):
-    """Assistance Class for Pydantic Dynamic Model Generation"""
-
-    field: str
-    field_alias: str
-    field_type: Any
-    field_value: Any
-    field_exclude: bool = False
-
-
-class PydanticModelGenerator:
-    """
-    Takes in created classes and stubs them out in a way FastAPI/Pydantic is happy about:
-    source_data is a snapshot of the default values produced by the class
-    params are the names of the actual keys required by __init__
-    """
-
-    def __init__(
-        self,
-        model_name: str = None,
-        class_instance = None,
-        additional_fields = None,
-    ):
-        def field_type_generator(k, v):
-            # field_type = str if not overrides.get(k) else overrides[k]["type"]
-            # print(k, v.annotation, v.default)
-            field_type = v.annotation
-
-            return Optional[field_type]
-
-        def merge_class_params(class_):
-            all_classes = list(filter(lambda x: x is not object, inspect.getmro(class_)))
-            parameters = {}
-            for classes in all_classes:
-                parameters = {**parameters, **inspect.signature(classes.__init__).parameters}
-            return parameters
-
-
-        self._model_name = model_name
-        self._class_data = merge_class_params(class_instance)
-
-        self._model_def = [
-            ModelDef(
-                field=underscore(k),
-                field_alias=k,
-                field_type=field_type_generator(k, v),
-                field_value=v.default
-            )
-            for (k,v) in self._class_data.items() if k not in API_NOT_ALLOWED
-        ]
-
-        for fields in additional_fields:
-            self._model_def.append(ModelDef(
-                field=underscore(fields["key"]),
-                field_alias=fields["key"],
-                field_type=fields["type"],
-                field_value=fields["default"],
-                field_exclude=fields["exclude"] if "exclude" in fields else False))
-
-    def generate_model(self):
-        """
-        Creates a pydantic BaseModel
-        from the json and overrides provided at initialization
-        """
-        fields = {
-            d.field: (d.field_type, Field(default=d.field_value, alias=d.field_alias, exclude=d.field_exclude)) for d in self._model_def
-        }
-        DynamicModel = create_model(self._model_name, **fields)
-        DynamicModel.__config__.allow_population_by_field_name = True
-        DynamicModel.__config__.allow_mutation = True
-        return DynamicModel
-
-StableDiffusionTxt2ImgProcessingAPI = PydanticModelGenerator(
-    "StableDiffusionProcessingTxt2Img",
-    StableDiffusionProcessingTxt2Img,
-    [
-        {"key": "sampler_index", "type": str, "default": "Euler"},
-        {"key": "script_name", "type": str, "default": None},
-        {"key": "script_args", "type": list, "default": []},
-        {"key": "send_images", "type": bool, "default": True},
-        {"key": "save_images", "type": bool, "default": False},
-    ]
-).generate_model()
-
-StableDiffusionImg2ImgProcessingAPI = PydanticModelGenerator(
-    "StableDiffusionProcessingImg2Img",
-    StableDiffusionProcessingImg2Img,
-    [
-        {"key": "sampler_index", "type": str, "default": "Euler"},
-        {"key": "init_images", "type": list, "default": None},
-        {"key": "denoising_strength", "type": float, "default": 0.75},
-        {"key": "mask", "type": str, "default": None},
-        {"key": "include_init_images", "type": bool, "default": False, "exclude" : True},
-        {"key": "script_name", "type": str, "default": None},
-        {"key": "script_args", "type": list, "default": []},
-        {"key": "send_images", "type": bool, "default": True},
-        {"key": "save_images", "type": bool, "default": False},
-    ]
-).generate_model()
-
-class TextToImageResponse(BaseModel):
-    images: List[str] = Field(default=None, title="Image", description="The generated image in base64 format.")
-    parameters: dict
-    info: str
-
-class ImageToImageResponse(BaseModel):
-    images: List[str] = Field(default=None, title="Image", description="The generated image in base64 format.")
-    parameters: dict
-    info: str
-
-class ExtrasBaseRequest(BaseModel):
-    resize_mode: Literal[0, 1] = Field(default=0, title="Resize Mode", description="Sets the resize mode: 0 to upscale by upscaling_resize amount, 1 to upscale up to upscaling_resize_h x upscaling_resize_w.")
-    show_extras_results: bool = Field(default=True, title="Show results", description="Should the backend return the generated image?")
-    gfpgan_visibility: float = Field(default=0, title="GFPGAN Visibility", ge=0, le=1, allow_inf_nan=False, description="Sets the visibility of GFPGAN, values should be between 0 and 1.")
-    codeformer_visibility: float = Field(default=0, title="CodeFormer Visibility", ge=0, le=1, allow_inf_nan=False, description="Sets the visibility of CodeFormer, values should be between 0 and 1.")
-    codeformer_weight: float = Field(default=0, title="CodeFormer Weight", ge=0, le=1, allow_inf_nan=False, description="Sets the weight of CodeFormer, values should be between 0 and 1.")
-    upscaling_resize: float = Field(default=2, title="Upscaling Factor", ge=1, le=8, description="By how much to upscale the image, only used when resize_mode=0.")
-    upscaling_resize_w: int = Field(default=512, title="Target Width", ge=1, description="Target width for the upscaler to hit. Only used when resize_mode=1.")
-    upscaling_resize_h: int = Field(default=512, title="Target Height", ge=1, description="Target height for the upscaler to hit. Only used when resize_mode=1.")
-    upscaling_crop: bool = Field(default=True, title="Crop to fit", description="Should the upscaler crop the image to fit in the chosen size?")
-    upscaler_1: str = Field(default="None", title="Main upscaler", description=f"The name of the main upscaler to use, it has to be one of this list: {' , '.join([x.name for x in sd_upscalers])}")
-    upscaler_2: str = Field(default="None", title="Secondary upscaler", description=f"The name of the secondary upscaler to use, it has to be one of this list: {' , '.join([x.name for x in sd_upscalers])}")
-    extras_upscaler_2_visibility: float = Field(default=0, title="Secondary upscaler visibility", ge=0, le=1, allow_inf_nan=False, description="Sets the visibility of secondary upscaler, values should be between 0 and 1.")
-    upscale_first: bool = Field(default=False, title="Upscale first", description="Should the upscaler run before restoring faces?")
-
-class ExtraBaseResponse(BaseModel):
-    html_info: str = Field(title="HTML info", description="A series of HTML tags containing the process info.")
-
-class ExtrasSingleImageRequest(ExtrasBaseRequest):
-    image: str = Field(default="", title="Image", description="Image to work on, must be a Base64 string containing the image's data.")
-
-class ExtrasSingleImageResponse(ExtraBaseResponse):
-    image: str = Field(default=None, title="Image", description="The generated image in base64 format.")
-
-class FileData(BaseModel):
-    data: str = Field(title="File data", description="Base64 representation of the file")
-    name: str = Field(title="File name")
-
-class ExtrasBatchImagesRequest(ExtrasBaseRequest):
-    imageList: List[FileData] = Field(title="Images", description="List of images to work on. Must be Base64 strings")
-
-class ExtrasBatchImagesResponse(ExtraBaseResponse):
-    images: List[str] = Field(title="Images", description="The generated images in base64 format.")
-
-class PNGInfoRequest(BaseModel):
-    image: str = Field(title="Image", description="The base64 encoded PNG image")
-
-class PNGInfoResponse(BaseModel):
-    info: str = Field(title="Image info", description="A string with the parameters used to generate the image")
-    items: dict = Field(title="Items", description="An object containing all the info the image had")
-
-class ProgressRequest(BaseModel):
-    skip_current_image: bool = Field(default=False, title="Skip current image", description="Skip current image serialization")
-
-class ProgressResponse(BaseModel):
-    progress: float = Field(title="Progress", description="The progress with a range of 0 to 1")
-    eta_relative: float = Field(title="ETA in secs")
-    state: dict = Field(title="State", description="The current state snapshot")
-    current_image: str = Field(default=None, title="Current image", description="The current image in base64 format. opts.show_progress_every_n_steps is required for this to work.")
-    textinfo: str = Field(default=None, title="Info text", description="Info text used by WebUI.")
-
-class InterrogateRequest(BaseModel):
-    image: str = Field(default="", title="Image", description="Image to work on, must be a Base64 string containing the image's data.")
-    model: str = Field(default="clip", title="Model", description="The interrogate model used.")
-
-class InterrogateResponse(BaseModel):
-    caption: str = Field(default=None, title="Caption", description="The generated caption for the image.")
-
-class TrainResponse(BaseModel):
-    info: str = Field(title="Train info", description="Response string from train embedding or hypernetwork task.")
-
-class CreateResponse(BaseModel):
-    info: str = Field(title="Create info", description="Response string from create embedding or hypernetwork task.")
-
-class PreprocessResponse(BaseModel):
-    info: str = Field(title="Preprocess info", description="Response string from preprocessing task.")
-
-fields = {}
-for key, metadata in opts.data_labels.items():
-    value = opts.data.get(key)
-    optType = opts.typemap.get(type(metadata.default), type(value))
-
-    if (metadata is not None):
-        fields.update({key: (Optional[optType], Field(
-            default=metadata.default ,description=metadata.label))})
-    else:
-        fields.update({key: (Optional[optType], Field())})
-
-OptionsModel = create_model("Options", **fields)
-
-flags = {}
-_options = vars(parser)['_option_string_actions']
-for key in _options:
-    if(_options[key].dest != 'help'):
-        flag = _options[key]
-        _type = str
-        if _options[key].default is not None: _type = type(_options[key].default)
-        flags.update({flag.dest: (_type,Field(default=flag.default, description=flag.help))})
-
-FlagsModel = create_model("Flags", **flags)
-
-class SamplerItem(BaseModel):
-    name: str = Field(title="Name")
-    aliases: List[str] = Field(title="Aliases")
-    options: Dict[str, str] = Field(title="Options")
-
-class UpscalerItem(BaseModel):
-    name: str = Field(title="Name")
-    model_name: Optional[str] = Field(title="Model Name")
-    model_path: Optional[str] = Field(title="Path")
-    model_url: Optional[str] = Field(title="URL")
-    scale: Optional[float] = Field(title="Scale")
-
-class SDModelItem(BaseModel):
-    title: str = Field(title="Title")
-    model_name: str = Field(title="Model Name")
-    hash: Optional[str] = Field(title="Short hash")
-    sha256: Optional[str] = Field(title="sha256 hash")
-    filename: str = Field(title="Filename")
-    config: Optional[str] = Field(title="Config file")
-
-class HypernetworkItem(BaseModel):
-    name: str = Field(title="Name")
-    path: Optional[str] = Field(title="Path")
-
-class FaceRestorerItem(BaseModel):
-    name: str = Field(title="Name")
-    cmd_dir: Optional[str] = Field(title="Path")
-
-class RealesrganItem(BaseModel):
-    name: str = Field(title="Name")
-    path: Optional[str] = Field(title="Path")
-    scale: Optional[int] = Field(title="Scale")
-
-class PromptStyleItem(BaseModel):
-    name: str = Field(title="Name")
-    prompt: Optional[str] = Field(title="Prompt")
-    negative_prompt: Optional[str] = Field(title="Negative Prompt")
-
-class ArtistItem(BaseModel):
-    name: str = Field(title="Name")
-    score: float = Field(title="Score")
-    category: str = Field(title="Category")
-
-class EmbeddingItem(BaseModel):
-    step: Optional[int] = Field(title="Step", description="The number of steps that were used to train this embedding, if available")
-    sd_checkpoint: Optional[str] = Field(title="SD Checkpoint", description="The hash of the checkpoint this embedding was trained on, if available")
-    sd_checkpoint_name: Optional[str] = Field(title="SD Checkpoint Name", description="The name of the checkpoint this embedding was trained on, if available. Note that this is the name that was used by the trainer; for a stable identifier, use `sd_checkpoint` instead")
-    shape: int = Field(title="Shape", description="The length of each individual vector in the embedding")
-    vectors: int = Field(title="Vectors", description="The number of vectors in the embedding")
-
-class EmbeddingsResponse(BaseModel):
-    loaded: Dict[str, EmbeddingItem] = Field(title="Loaded", description="Embeddings loaded for the current model")
-    skipped: Dict[str, EmbeddingItem] = Field(title="Skipped", description="Embeddings skipped for the current model (likely due to architecture incompatibility)")
-
-class MemoryResponse(BaseModel):
-    ram: dict = Field(title="RAM", description="System memory stats")
-    cuda: dict = Field(title="CUDA", description="nVidia CUDA memory stats")
-
-class ScriptsList(BaseModel):
-    txt2img: list = Field(default=None,title="Txt2img", description="Titles of scripts (txt2img)")
-    img2img: list = Field(default=None,title="Img2img", description="Titles of scripts (img2img)")
\ No newline at end of file
diff --git a/spaces/svjack/ControlNet-Pose-Chinese/annotator/uniformer/mmcv/cnn/bricks/wrappers.py b/spaces/svjack/ControlNet-Pose-Chinese/annotator/uniformer/mmcv/cnn/bricks/wrappers.py
deleted file mode 100644
index 8aebf67bf52355a513f21756ee74fe510902d075..0000000000000000000000000000000000000000
--- a/spaces/svjack/ControlNet-Pose-Chinese/annotator/uniformer/mmcv/cnn/bricks/wrappers.py
+++ /dev/null
@@ -1,180 +0,0 @@
-# Copyright (c) OpenMMLab. All rights reserved.
-r"""Modified from https://github.com/facebookresearch/detectron2/blob/master/detectron2/layers/wrappers.py  # noqa: E501
-
-Wrap some nn modules to support empty tensor input. Currently, these wrappers
-are mainly used in mask heads like fcn_mask_head and maskiou_heads since mask
-heads are trained on only positive RoIs.
-"""
-import math
-
-import torch
-import torch.nn as nn
-from torch.nn.modules.utils import _pair, _triple
-
-from .registry import CONV_LAYERS, UPSAMPLE_LAYERS
-
-if torch.__version__ == 'parrots':
-    TORCH_VERSION = torch.__version__
-else:
-    # torch.__version__ could be 1.3.1+cu92, we only need the first two
-    # for comparison
-    TORCH_VERSION = tuple(int(x) for x in torch.__version__.split('.')[:2])
-
-
-def obsolete_torch_version(torch_version, version_threshold):
-    return torch_version == 'parrots' or torch_version <= version_threshold
-
-
-class NewEmptyTensorOp(torch.autograd.Function):
-
-    @staticmethod
-    def forward(ctx, x, new_shape):
-        ctx.shape = x.shape
-        return x.new_empty(new_shape)
-
-    @staticmethod
-    def backward(ctx, grad):
-        shape = ctx.shape
-        return NewEmptyTensorOp.apply(grad, shape), None
-
-
-@CONV_LAYERS.register_module('Conv', force=True)
-class Conv2d(nn.Conv2d):
-
-    def forward(self, x):
-        if x.numel() == 0 and obsolete_torch_version(TORCH_VERSION, (1, 4)):
-            out_shape = [x.shape[0], self.out_channels]
-            for i, k, p, s, d in zip(x.shape[-2:], self.kernel_size,
-                                     self.padding, self.stride, self.dilation):
-                o = (i + 2 * p - (d * (k - 1) + 1)) // s + 1
-                out_shape.append(o)
-            empty = NewEmptyTensorOp.apply(x, out_shape)
-            if self.training:
-                # produce dummy gradient to avoid DDP warning.
-                dummy = sum(x.view(-1)[0] for x in self.parameters()) * 0.0
-                return empty + dummy
-            else:
-                return empty
-
-        return super().forward(x)
-
-
-@CONV_LAYERS.register_module('Conv3d', force=True)
-class Conv3d(nn.Conv3d):
-
-    def forward(self, x):
-        if x.numel() == 0 and obsolete_torch_version(TORCH_VERSION, (1, 4)):
-            out_shape = [x.shape[0], self.out_channels]
-            for i, k, p, s, d in zip(x.shape[-3:], self.kernel_size,
-                                     self.padding, self.stride, self.dilation):
-                o = (i + 2 * p - (d * (k - 1) + 1)) // s + 1
-                out_shape.append(o)
-            empty = NewEmptyTensorOp.apply(x, out_shape)
-            if self.training:
-                # produce dummy gradient to avoid DDP warning.
-                dummy = sum(x.view(-1)[0] for x in self.parameters()) * 0.0
-                return empty + dummy
-            else:
-                return empty
-
-        return super().forward(x)
-
-
-@CONV_LAYERS.register_module()
-@CONV_LAYERS.register_module('deconv')
-@UPSAMPLE_LAYERS.register_module('deconv', force=True)
-class ConvTranspose2d(nn.ConvTranspose2d):
-
-    def forward(self, x):
-        if x.numel() == 0 and obsolete_torch_version(TORCH_VERSION, (1, 4)):
-            out_shape = [x.shape[0], self.out_channels]
-            for i, k, p, s, d, op in zip(x.shape[-2:], self.kernel_size,
-                                         self.padding, self.stride,
-                                         self.dilation, self.output_padding):
-                out_shape.append((i - 1) * s - 2 * p + (d * (k - 1) + 1) + op)
-            empty = NewEmptyTensorOp.apply(x, out_shape)
-            if self.training:
-                # produce dummy gradient to avoid DDP warning.
-                dummy = sum(x.view(-1)[0] for x in self.parameters()) * 0.0
-                return empty + dummy
-            else:
-                return empty
-
-        return super().forward(x)
-
-
-@CONV_LAYERS.register_module()
-@CONV_LAYERS.register_module('deconv3d')
-@UPSAMPLE_LAYERS.register_module('deconv3d', force=True)
-class ConvTranspose3d(nn.ConvTranspose3d):
-
-    def forward(self, x):
-        if x.numel() == 0 and obsolete_torch_version(TORCH_VERSION, (1, 4)):
-            out_shape = [x.shape[0], self.out_channels]
-            for i, k, p, s, d, op in zip(x.shape[-3:], self.kernel_size,
-                                         self.padding, self.stride,
-                                         self.dilation, self.output_padding):
-                out_shape.append((i - 1) * s - 2 * p + (d * (k - 1) + 1) + op)
-            empty = NewEmptyTensorOp.apply(x, out_shape)
-            if self.training:
-                # produce dummy gradient to avoid DDP warning.
-                dummy = sum(x.view(-1)[0] for x in self.parameters()) * 0.0
-                return empty + dummy
-            else:
-                return empty
-
-        return super().forward(x)
-
-
-class MaxPool2d(nn.MaxPool2d):
-
-    def forward(self, x):
-        # PyTorch 1.9 does not support empty tensor inference yet
-        if x.numel() == 0 and obsolete_torch_version(TORCH_VERSION, (1, 9)):
-            out_shape = list(x.shape[:2])
-            for i, k, p, s, d in zip(x.shape[-2:], _pair(self.kernel_size),
-                                     _pair(self.padding), _pair(self.stride),
-                                     _pair(self.dilation)):
-                o = (i + 2 * p - (d * (k - 1) + 1)) / s + 1
-                o = math.ceil(o) if self.ceil_mode else math.floor(o)
-                out_shape.append(o)
-            empty = NewEmptyTensorOp.apply(x, out_shape)
-            return empty
-
-        return super().forward(x)
-
-
-class MaxPool3d(nn.MaxPool3d):
-
-    def forward(self, x):
-        # PyTorch 1.9 does not support empty tensor inference yet
-        if x.numel() == 0 and obsolete_torch_version(TORCH_VERSION, (1, 9)):
-            out_shape = list(x.shape[:2])
-            for i, k, p, s, d in zip(x.shape[-3:], _triple(self.kernel_size),
-                                     _triple(self.padding),
-                                     _triple(self.stride),
-                                     _triple(self.dilation)):
-                o = (i + 2 * p - (d * (k - 1) + 1)) / s + 1
-                o = math.ceil(o) if self.ceil_mode else math.floor(o)
-                out_shape.append(o)
-            empty = NewEmptyTensorOp.apply(x, out_shape)
-            return empty
-
-        return super().forward(x)
-
-
-class Linear(torch.nn.Linear):
-
-    def forward(self, x):
-        # empty tensor forward of Linear layer is supported in Pytorch 1.6
-        if x.numel() == 0 and obsolete_torch_version(TORCH_VERSION, (1, 5)):
-            out_shape = [x.shape[0], self.out_features]
-            empty = NewEmptyTensorOp.apply(x, out_shape)
-            if self.training:
-                # produce dummy gradient to avoid DDP warning.
-                dummy = sum(x.view(-1)[0] for x in self.parameters()) * 0.0
-                return empty + dummy
-            else:
-                return empty
-
-        return super().forward(x)
diff --git a/spaces/tharun49/TharunGenAISpeech/README.md b/spaces/tharun49/TharunGenAISpeech/README.md
deleted file mode 100644
index 3494a61557b204e256edd79f22e326922927b1aa..0000000000000000000000000000000000000000
--- a/spaces/tharun49/TharunGenAISpeech/README.md
+++ /dev/null
@@ -1,12 +0,0 @@
----
-title: TharunGenAISpeech
-emoji: ⚡
-colorFrom: gray
-colorTo: pink
-sdk: gradio
-sdk_version: 3.39.0
-app_file: app.py
-pinned: false
----
-
-Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
diff --git a/spaces/thecho7/deepfake/training/__init__.py b/spaces/thecho7/deepfake/training/__init__.py
deleted file mode 100644
index e69de29bb2d1d6434b8b29ae775ad8c2e48c5391..0000000000000000000000000000000000000000
diff --git a/spaces/tialenAdioni/chat-gpt-api/logs/CCleaner 5.61.7392 Crack Activation Key Free Download Latest.md b/spaces/tialenAdioni/chat-gpt-api/logs/CCleaner 5.61.7392 Crack Activation Key Free Download Latest.md
deleted file mode 100644
index 75ec05512fe61bd9480923e9a30767a5eee51097..0000000000000000000000000000000000000000
--- a/spaces/tialenAdioni/chat-gpt-api/logs/CCleaner 5.61.7392 Crack Activation Key Free Download Latest.md	
+++ /dev/null
@@ -1,41 +0,0 @@
-
-<h1>How to Get CCleaner 5.61.7392 Crack Activation Key for Free</h1>
-<p>CCleaner is a popular software that helps you optimize your PC performance by cleaning up junk files, fixing registry errors, and removing unwanted programs. It also protects your privacy by erasing your browsing history, cookies, and cache.</p>
-<p>However, CCleaner is not a free software. You need to pay for a license key to unlock its full features and enjoy its benefits. But what if you don't want to spend money on CCleaner? Is there a way to get CCleaner 5.61.7392 crack activation key for free?</p>
-<h2>CCleaner 5.61.7392 Crack Activation Key Free Download {Latest}</h2><br /><p><b><b>DOWNLOAD</b> &#10042;&#10042;&#10042; <a href="https://urlcod.com/2uK6l6">https://urlcod.com/2uK6l6</a></b></p><br /><br />
-<p>The answer is yes. In this article, we will show you how to download and install CCleaner 5.61.7392 crack activation key for free. This way, you can use CCleaner without any limitations or restrictions.</p>
-<h2>What is CCleaner 5.61.7392 Crack Activation Key?</h2>
-<p>CCleaner 5.61.7392 crack activation key is a modified version of CCleaner that bypasses the license verification process and allows you to use the software for free. It is also known as CCleaner 5.61.7392 patch, CCleaner 5.61.7392 keygen, or CCleaner 5.61.7392 serial key.</p>
-<p>By using CCleaner 5.61.7392 crack activation key, you can access all the features of CCleaner without paying anything. You can clean up your PC, boost its speed, protect your privacy, and customize your settings according to your preferences.</p>
-<p></p>
-<h2>How to Download and Install CCleaner 5.61.7392 Crack Activation Key?</h2>
-<p>To download and install CCleaner 5.61.7392 crack activation key, you need to follow these steps:</p>
-<ol>
-<li>Download CCleaner 5.61.7392 crack activation key from a reliable source. You can find many websites that offer CCleaner 5.61.7392 crack activation key for free download, but be careful of malware and viruses that may harm your PC.</li>
-<li>Extract the downloaded file using a file extractor tool such as WinRAR or 7-Zip.</li>
-<li>Run the setup file and follow the instructions to install CCleaner on your PC.</li>
-<li>Copy the crack file from the extracted folder and paste it into the installation directory of CCleaner.</li>
-<li>Launch CCleaner and enjoy its full features for free.</li>
-</ol>
-<h2>What are the Benefits of Using CCleaner 5.61.7392 Crack Activation Key?</h2>
-<p>By using CCleaner 5.61.7392 crack activation key, you can enjoy these benefits:</p>
-<ul>
-<li>You can use CCleaner for free without paying anything.</li>
-<li>You can access all the features of CCleaner without any limitations or restrictions.</li>
-<li>You can optimize your PC performance by cleaning up junk files, fixing registry errors, and removing unwanted programs.</li>
-<li>You can protect your privacy by erasing your browsing history, cookies, and cache.</li>
-<li>You can customize your settings according to your preferences.</li>
-</ul>
-<h2>What are the Risks of Using CCleaner 5.61.7392 Crack Activation Key?</h2>
-<p>However, using CCleaner 5.61.7392 crack activation key also comes with some risks:</p>
-<ul>
-<li>You may violate the terms and conditions of CCleaner and face legal consequences.</li>
-<li>You may not receive any updates or support from CCleaner developers.</li>
-<li>You may expose your PC to malware and viruses that may damage your system or steal your data.</li>
-<li>You may compromise the quality and security of CCleaner software.</li>
-</ul>
-<h2>Conclusion</h2>
-<p>CCleaner 5.61.7392 crack activation key is a way to use CCleaner for free without paying anything. It allows you to access all the features of CCleaner without any limitations or restrictions.</p>
-<p>However, using CCleaner 5.61.7392 crack activation key also comes with some risks such as violating the terms and conditions of CCleaner, not receiving any</p> cec2833e83<br />
-<br />
-<br />
\ No newline at end of file
diff --git a/spaces/timpal0l/chat-ui/src/lib/switchTheme.ts b/spaces/timpal0l/chat-ui/src/lib/switchTheme.ts
deleted file mode 100644
index 9da30b244c4b20b4585b34a02617895a3499a56f..0000000000000000000000000000000000000000
--- a/spaces/timpal0l/chat-ui/src/lib/switchTheme.ts
+++ /dev/null
@@ -1,10 +0,0 @@
-export function switchTheme() {
-	const { classList } = document.querySelector("html") as HTMLElement;
-	if (classList.contains("dark")) {
-		classList.remove("dark");
-		localStorage.theme = "light";
-	} else {
-		classList.add("dark");
-		localStorage.theme = "dark";
-	}
-}
diff --git a/spaces/tioseFevbu/cartoon-converter/scripts/Battlestar Galactica Razor 720p Vs 1080p ((TOP)).md b/spaces/tioseFevbu/cartoon-converter/scripts/Battlestar Galactica Razor 720p Vs 1080p ((TOP)).md
deleted file mode 100644
index 8694784f18009d4fc92d337da155bd3bf77f76e9..0000000000000000000000000000000000000000
--- a/spaces/tioseFevbu/cartoon-converter/scripts/Battlestar Galactica Razor 720p Vs 1080p ((TOP)).md	
+++ /dev/null
@@ -1,29 +0,0 @@
-
-<h1>Battlestar Galactica Razor: Why You Should Watch It in 1080p</h1>
-<p>Battlestar Galactica Razor is a television film of the re-imagined Battlestar Galactica series that premiered in 2007. It tells the story of the Pegasus, a battlestar that survived the Cylon attack on the colonies, and its commander, Admiral Cain. The film uses flashbacks to show the events of the first and second Cylon wars, and how they shaped the characters and their decisions.</p>
-<p>If you are a fan of Battlestar Galactica, you might be wondering whether you should watch Razor in 720p or 1080p resolution. The answer is simple: 1080p is the way to go. Here are some reasons why:</p>
-<h2>battlestar galactica razor 720p vs 1080p</h2><br /><p><b><b>Download Zip</b> &#10003;&#10003;&#10003; <a href="https://urlcod.com/2uHyj1">https://urlcod.com/2uHyj1</a></b></p><br /><br />
-<ul>
-<li><b>Quality:</b> 1080p resolution means that the image has 1920×1080 pixels, which is more than twice as many as 720p resolution, which has 1280×720 pixels. This means that 1080p offers more detail, clarity and sharpness than 720p. You can see more of the stunning visual effects, the intricate sets and costumes, and the facial expressions of the actors.</li>
-<li><b>Experience:</b> Watching Razor in 1080p resolution will give you a more immersive and cinematic experience. You will feel like you are part of the action, as you witness the epic battles, the tense drama and the emotional moments. You will also appreciate the cinematography, the editing and the soundtrack more.</li>
-<li><b>Gaming:</b> If you are a gamer, you will enjoy playing Battlestar Galactica games in 1080p resolution more than in 720p. Because there are more pixels in 1080p, less anti-aliasing is required for a smooth visual experience. This means that 1080p will not only likely look better than 720p, but will lead to a better gaming experience overall, as anti-aliasing can slow down a console or computer.</li>
-</ul>
-<p>So, if you have the option, choose to watch Battlestar Galactica Razor in 1080p resolution. You will not regret it. It is one of the best sci-fi films ever made, and it deserves to be seen in the best quality possible.</p>
-
-<p>Battlestar Galactica Razor features an amazing cast of actors who bring the characters to life. Some of the main characters are:</p>
-<ul>
-<li><b>Admiral William Adama:</b> Played by Edward James Olmos, he is the commander of the Galactica and the leader of the human fleet. He is a veteran of the first Cylon war and a man of honor and courage. He has a complicated relationship with his son Lee, whom he appoints as the commander of the Pegasus.</li>
-<li><b>President Laura Roslin:</b> Played by Mary McDonnell, she is the president of the Twelve Colonies and a former secretary of education. She is diagnosed with terminal cancer and believes she has a prophetic role in leading humanity to a new home. She has a close bond with Admiral Adama and supports his decisions.</li>
-<li><b>Captain Kara 'Starbuck' Thrace:</b> Played by Katee Sackhoff, she is one of the best Viper pilots in the fleet and a rebellious and impulsive woman. She has a history with Lee Adama and Samuel Anders, and struggles with her destiny as the harbinger of death. She receives Kendra Shaw's pocket knife as a gift from Lee.</li>
-<li><b>Cpt. Lee 'Apollo' Adama:</b> Played by Jamie Bamber, he is the son of Admiral Adama and the commander of the Pegasus. He is a skilled pilot and a loyal officer, but often clashes with his father over moral issues. He tries to restore order and justice to the Pegasus crew after Cain's brutal regime.</li>
-<li><b>Dr. Gaius Baltar:</b> Played by James Callis, he is a brilliant scientist and a former vice president of the colonies. He is responsible for allowing the Cylons to infiltrate the colonial defense system, but he keeps this secret from everyone. He is haunted by visions of Number Six, a Cylon model who seduced him.</li>
-<li><b>Number Six / Gina Inviere:</b> Played by Tricia Helfer, she is one of the twelve humanoid Cylon models who can infiltrate human society. She appears in Baltar's mind as a seductive and manipulative guide. She also appears as Gina Inviere, a Cylon agent who was captured and tortured by Cain on the Pegasus.</li>
-<li><b>Lt. Sharon Valerii:</b> Played by Grace Park, she is another Cylon model who posed as a human pilot on Galactica. She was in love with Helo and became pregnant with his child. She was shot by Cally after she revealed her true nature, but was resurrected in a new body on a Cylon ship.</li>
-<li><b>Admiral Helena Cain:</b> Played by Michelle Forbes, she is the commander of the Pegasus and a ruthless and ambitious leader. She survived the Cylon attack by making a blind jump with her ship, but lost her humanity along the way. She ordered her crew to commit atrocities against Cylons and humans alike.</li>
-<li><b>Kendra Shaw:</b> Played by Stephany Jacobsen, she is Cain's protégé and Lee's executive officer on the Pegasus. She boarded the ship shortly before the Cylon attack and followed Cain's orders without question. She carries a pocket knife that symbolizes her becoming a 'razor' to survive.</li>
-</ul>
-<p>Battlestar Galactica Razor is a must-watch for any sci-fi fan who wants to explore more of the Battlestar Galactica universe. It offers a thrilling and captivating story that reveals new insights into the characters and their motivations. It also sets up some of the events that will happen in season 4 of the series.</p>
-<p>So don't miss this opportunity to watch Battlestar Galactica Razor in 1080p resolution. You will be glad you did.</p>
-<p></p> 81aa517590<br />
-<br />
-<br />
\ No newline at end of file
diff --git a/spaces/tioseFevbu/cartoon-converter/scripts/Datanumen Outlook Repair 52 ((TOP)) Keygen 112.md b/spaces/tioseFevbu/cartoon-converter/scripts/Datanumen Outlook Repair 52 ((TOP)) Keygen 112.md
deleted file mode 100644
index 5dc3b2013530e4f05882fb3688ac4d65f184eeae..0000000000000000000000000000000000000000
--- a/spaces/tioseFevbu/cartoon-converter/scripts/Datanumen Outlook Repair 52 ((TOP)) Keygen 112.md	
+++ /dev/null
@@ -1,26 +0,0 @@
-
-<h1>How to Repair Corrupted Outlook PST Files with DataNumen Outlook Repair 5.2</h1>
-<p>Outlook is one of the most popular email clients in the world, but it is not immune to corruption. Sometimes, due to various reasons such as virus attacks, power failures, network errors, or human errors, your Outlook PST files may get damaged and inaccessible. This can cause you to lose important emails, contacts, calendars, tasks, notes, and other data stored in Outlook.</p>
-<h2>Datanumen Outlook Repair 52 Keygen 112</h2><br /><p><b><b>Download</b> &#10040; <a href="https://urlcod.com/2uHx5T">https://urlcod.com/2uHx5T</a></b></p><br /><br />
-<p>Fortunately, there is a powerful tool that can help you repair and recover corrupted Outlook PST files: DataNumen Outlook Repair 5.2. DataNumen Outlook Repair is the best Outlook recovery tool in the market. It can scan the damaged PST files and recover your data as much as possible, minimizing the loss caused by file corruption.</p>
-<p>In this article, we will show you how to use DataNumen Outlook Repair 5.2 to fix your Outlook problems and restore your data.</p>
-<h2>Step 1: Download and install DataNumen Outlook Repair 5.2</h2>
-<p>You can download DataNumen Outlook Repair 5.2 from its official website[^1^]. The file size is about 8 MB and it supports Windows XP/Vista/7/8/10 and all versions of Outlook from 97 to 2019.</p>
-<p>After downloading the file, double-click it to run the setup wizard and follow the instructions to install DataNumen Outlook Repair on your computer.</p>
-<h2>Step 2: Locate and select the corrupted PST file</h2>
-<p>Launch DataNumen Outlook Repair and you will see its main interface. Click the "Browse" button next to the "Source File" box and navigate to the folder where your corrupted PST file is located. Select the file and click "Open".</p>
-<p></p>
-<p>If you don't know where your PST file is stored, you can use the "Search" button to find it on your hard drive. You can also specify some search criteria such as file name, size, date modified, etc. to narrow down the results.</p>
-<h2>Step 3: Specify the output file name and location</h2>
-<p>By default, DataNumen Outlook Repair will save the repaired PST file as xxxx_fixed.pst in the same folder as the source file, where xxxx is the name of the source file. You can change the output file name and location by clicking the "Browse" button next to the "Output File" box and choosing a different folder or file name.</p>
-<p>You can also choose to split the output PST file into several smaller files by checking the "Split PST File" option and setting a maximum size for each file.</p>
-<h2>Step 4: Start repairing the PST file</h2>
-<p>After setting all the options, click the "Start Repair" button to begin repairing the corrupted PST file. You will see a progress bar showing the repair process. Depending on the size and damage level of your PST file, it may take some time to complete.</p>
-<p>When the repair is done, you will see a message box telling you that the repair has been successful. You can click the "OK" button to close it.</p>
-<h2>Step 5: Open the repaired PST file in Outlook</h2>
-<p>Now you can open your repaired PST file in Outlook and check if your data has been recovered. To do this, launch Outlook and go to File > Open & Export > Open Outlook Data File. Browse to the folder where your repaired PST file is located and select it. Click "OK" and you will see your repaired PST file in the left pane of Outlook.</p>
-<p>You can then access your emails, contacts, calendars, tasks, notes, and other data as usual. If you find any missing or incorrect data, you can contact DataNumen support team for further assistance.</p>
-<h2>Conclusion</h2>
-<p>DataNumen Outlook Repair 5.2 is a reliable and effective tool that can help you repair corrupted Outlook PST files and recover your data. It has a simple and user-friendly interface that makes it easy to use for anyone. It also supports all versions of Outlook and Windows and can</p> 81aa517590<br />
-<br />
-<br />
\ No newline at end of file
diff --git a/spaces/tioseFevbu/cartoon-converter/scripts/Express VPN 7.7.0 Crack With License Key Free NEW! Download 2020.md b/spaces/tioseFevbu/cartoon-converter/scripts/Express VPN 7.7.0 Crack With License Key Free NEW! Download 2020.md
deleted file mode 100644
index 0462a55926db88cc2d07f168b7561b528b213e93..0000000000000000000000000000000000000000
--- a/spaces/tioseFevbu/cartoon-converter/scripts/Express VPN 7.7.0 Crack With License Key Free NEW! Download 2020.md	
+++ /dev/null
@@ -1,33 +0,0 @@
-
-<code>
-<h1>Express VPN 7.7.0 Crack With License Key Free Download 2020</h1>
-<meta name="description" content="Express VPN 7.7.0 Crack is a powerful and easy-to-use VPN service that allows you to access any website or app securely and anonymously. Download it for free here."/>
-<p>Are you looking for a reliable and fast VPN service that can protect your online privacy and security? Do you want to bypass geo-restrictions and censorship and access any website or app you want? If yes, then you need Express VPN 7.7.0 Crack.</p>
-<h2>Express VPN 7.7.0 Crack With License Key Free Download 2020</h2><br /><p><b><b>Download Zip</b> &#8250; <a href="https://urlcod.com/2uHvKp">https://urlcod.com/2uHvKp</a></b></p><br /><br />
-<p>Express VPN 7.7.0 Crack is a premium VPN service that offers unlimited bandwidth, speed, and server switches. It has over 3000 servers in 94 countries, which means you can connect to any location you want and enjoy the best streaming quality and gaming performance. Express VPN 7.7.0 Crack also uses AES-256 encryption, kill switch, split tunneling, and DNS leak protection to ensure your data and identity are always safe from hackers, ISPs, and government agencies.</p>
-<h2>Why Choose Express VPN 7.7.0 Crack?</h2>
-<p>There are many reasons why Express VPN 7.7.0 Crack is the best choice for your online needs. Here are some of them:</p>
-<ul>
-<li><b>Easy to use:</b> Express VPN 7.7.0 Crack has a simple and intuitive interface that lets you connect to any server with one click. You can also customize your settings and preferences according to your needs.</li>
-<li><b>Compatible with all devices:</b> Express VPN 7.7.0 Crack works on Windows, Mac, Linux, Android, iOS, routers, smart TVs, and more. You can also use it on up to five devices simultaneously with one account.</li>
-<li><b>Supports all protocols:</b> Express VPN 7.7.0 Crack supports OpenVPN, L2TP/IPsec, SSTP, PPTP, IKEv2, and more protocols to ensure you have the best connection speed and security level.</li>
-<li><b>24/7 customer support:</b> Express VPN 7.7.0 Crack has a friendly and professional customer support team that is available 24/7 via live chat, email, or phone. They can help you with any issue or question you may have.</li>
-</ul>
-<h2>How to Download and Install Express VPN 7.7.0 Crack?</h2>
-<p>If you want to enjoy the benefits of Express VPN 7.7.0 Crack, you need to download and install it on your device. Here are the steps to do so:</p>
-<ol>
-<li>Click on the link below to download the Express VPN 7.7.0 Crack setup file.</li>
-<li>Run the setup file and follow the instructions to install Express VPN 7.7.0 Crack on your device.</li>
-<li>Launch Express VPN 7.7.0 Crack and enter the license key that you will receive in your email after completing the registration process.</li>
-<li>Select a server location from the list or let Express VPN 7.7.0 Crack choose the best one for you.</li>
-<li>Click on the connect button and enjoy unlimited online freedom and security with Express VPN 7.7.0 Crack.</li>
-</ol>
-<h2>Conclusion</h2>
-<p>Express VPN 7.7.0 Crack is a powerful and easy-to-use VPN service that allows you to access any website or app securely and anonymously. It has a lot of features and benefits that make it stand out from other VPN services in the market.</p>
-<p>If you want to download Express VPN 7.7.0 Crack for free, click on the link below and follow the instructions.</p>
-<a href="https://expressvpn.com/download">Download Express VPN 7.7.0 Crack With License Key Free Here</a>
-
-</code></p>
-<p></p> cec2833e83<br />
-<br />
-<br />
\ No newline at end of file
diff --git a/spaces/tjburns/ask_marcus_aurelius/.venv/lib/python3.10/site-packages/pip/_vendor/chardet/chardistribution.py b/spaces/tjburns/ask_marcus_aurelius/.venv/lib/python3.10/site-packages/pip/_vendor/chardet/chardistribution.py
deleted file mode 100644
index 27b4a293911de909c4cb955e671059e40d94e4d4..0000000000000000000000000000000000000000
--- a/spaces/tjburns/ask_marcus_aurelius/.venv/lib/python3.10/site-packages/pip/_vendor/chardet/chardistribution.py
+++ /dev/null
@@ -1,259 +0,0 @@
-######################## BEGIN LICENSE BLOCK ########################
-# The Original Code is Mozilla Communicator client code.
-#
-# The Initial Developer of the Original Code is
-# Netscape Communications Corporation.
-# Portions created by the Initial Developer are Copyright (C) 1998
-# the Initial Developer. All Rights Reserved.
-#
-# Contributor(s):
-#   Mark Pilgrim - port to Python
-#
-# This library is free software; you can redistribute it and/or
-# modify it under the terms of the GNU Lesser General Public
-# License as published by the Free Software Foundation; either
-# version 2.1 of the License, or (at your option) any later version.
-#
-# This library is distributed in the hope that it will be useful,
-# but WITHOUT ANY WARRANTY; without even the implied warranty of
-# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
-# Lesser General Public License for more details.
-#
-# You should have received a copy of the GNU Lesser General Public
-# License along with this library; if not, write to the Free Software
-# Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA
-# 02110-1301  USA
-######################### END LICENSE BLOCK #########################
-
-from .big5freq import (
-    BIG5_CHAR_TO_FREQ_ORDER,
-    BIG5_TABLE_SIZE,
-    BIG5_TYPICAL_DISTRIBUTION_RATIO,
-)
-from .euckrfreq import (
-    EUCKR_CHAR_TO_FREQ_ORDER,
-    EUCKR_TABLE_SIZE,
-    EUCKR_TYPICAL_DISTRIBUTION_RATIO,
-)
-from .euctwfreq import (
-    EUCTW_CHAR_TO_FREQ_ORDER,
-    EUCTW_TABLE_SIZE,
-    EUCTW_TYPICAL_DISTRIBUTION_RATIO,
-)
-from .gb2312freq import (
-    GB2312_CHAR_TO_FREQ_ORDER,
-    GB2312_TABLE_SIZE,
-    GB2312_TYPICAL_DISTRIBUTION_RATIO,
-)
-from .jisfreq import (
-    JIS_CHAR_TO_FREQ_ORDER,
-    JIS_TABLE_SIZE,
-    JIS_TYPICAL_DISTRIBUTION_RATIO,
-)
-from .johabfreq import JOHAB_TO_EUCKR_ORDER_TABLE
-
-
-class CharDistributionAnalysis:
-    ENOUGH_DATA_THRESHOLD = 1024
-    SURE_YES = 0.99
-    SURE_NO = 0.01
-    MINIMUM_DATA_THRESHOLD = 3
-
-    def __init__(self):
-        # Mapping table to get frequency order from char order (get from
-        # GetOrder())
-        self._char_to_freq_order = tuple()
-        self._table_size = None  # Size of above table
-        # This is a constant value which varies from language to language,
-        # used in calculating confidence.  See
-        # http://www.mozilla.org/projects/intl/UniversalCharsetDetection.html
-        # for further detail.
-        self.typical_distribution_ratio = None
-        self._done = None
-        self._total_chars = None
-        self._freq_chars = None
-        self.reset()
-
-    def reset(self):
-        """reset analyser, clear any state"""
-        # If this flag is set to True, detection is done and conclusion has
-        # been made
-        self._done = False
-        self._total_chars = 0  # Total characters encountered
-        # The number of characters whose frequency order is less than 512
-        self._freq_chars = 0
-
-    def feed(self, char, char_len):
-        """feed a character with known length"""
-        if char_len == 2:
-            # we only care about 2-bytes character in our distribution analysis
-            order = self.get_order(char)
-        else:
-            order = -1
-        if order >= 0:
-            self._total_chars += 1
-            # order is valid
-            if order < self._table_size:
-                if 512 > self._char_to_freq_order[order]:
-                    self._freq_chars += 1
-
-    def get_confidence(self):
-        """return confidence based on existing data"""
-        # if we didn't receive any character in our consideration range,
-        # return negative answer
-        if self._total_chars <= 0 or self._freq_chars <= self.MINIMUM_DATA_THRESHOLD:
-            return self.SURE_NO
-
-        if self._total_chars != self._freq_chars:
-            r = self._freq_chars / (
-                (self._total_chars - self._freq_chars) * self.typical_distribution_ratio
-            )
-            if r < self.SURE_YES:
-                return r
-
-        # normalize confidence (we don't want to be 100% sure)
-        return self.SURE_YES
-
-    def got_enough_data(self):
-        # It is not necessary to receive all data to draw conclusion.
-        # For charset detection, certain amount of data is enough
-        return self._total_chars > self.ENOUGH_DATA_THRESHOLD
-
-    def get_order(self, _):
-        # We do not handle characters based on the original encoding string,
-        # but convert this encoding string to a number, here called order.
-        # This allows multiple encodings of a language to share one frequency
-        # table.
-        return -1
-
-
-class EUCTWDistributionAnalysis(CharDistributionAnalysis):
-    def __init__(self):
-        super().__init__()
-        self._char_to_freq_order = EUCTW_CHAR_TO_FREQ_ORDER
-        self._table_size = EUCTW_TABLE_SIZE
-        self.typical_distribution_ratio = EUCTW_TYPICAL_DISTRIBUTION_RATIO
-
-    def get_order(self, byte_str):
-        # for euc-TW encoding, we are interested
-        #   first  byte range: 0xc4 -- 0xfe
-        #   second byte range: 0xa1 -- 0xfe
-        # no validation needed here. State machine has done that
-        first_char = byte_str[0]
-        if first_char >= 0xC4:
-            return 94 * (first_char - 0xC4) + byte_str[1] - 0xA1
-        return -1
-
-
-class EUCKRDistributionAnalysis(CharDistributionAnalysis):
-    def __init__(self):
-        super().__init__()
-        self._char_to_freq_order = EUCKR_CHAR_TO_FREQ_ORDER
-        self._table_size = EUCKR_TABLE_SIZE
-        self.typical_distribution_ratio = EUCKR_TYPICAL_DISTRIBUTION_RATIO
-
-    def get_order(self, byte_str):
-        # for euc-KR encoding, we are interested
-        #   first  byte range: 0xb0 -- 0xfe
-        #   second byte range: 0xa1 -- 0xfe
-        # no validation needed here. State machine has done that
-        first_char = byte_str[0]
-        if first_char >= 0xB0:
-            return 94 * (first_char - 0xB0) + byte_str[1] - 0xA1
-        return -1
-
-
-class JOHABDistributionAnalysis(CharDistributionAnalysis):
-    def __init__(self):
-        super().__init__()
-        self._char_to_freq_order = EUCKR_CHAR_TO_FREQ_ORDER
-        self._table_size = EUCKR_TABLE_SIZE
-        self.typical_distribution_ratio = EUCKR_TYPICAL_DISTRIBUTION_RATIO
-
-    def get_order(self, byte_str):
-        first_char = byte_str[0]
-        if 0x88 <= first_char < 0xD4:
-            code = first_char * 256 + byte_str[1]
-            return JOHAB_TO_EUCKR_ORDER_TABLE.get(code, -1)
-        return -1
-
-
-class GB2312DistributionAnalysis(CharDistributionAnalysis):
-    def __init__(self):
-        super().__init__()
-        self._char_to_freq_order = GB2312_CHAR_TO_FREQ_ORDER
-        self._table_size = GB2312_TABLE_SIZE
-        self.typical_distribution_ratio = GB2312_TYPICAL_DISTRIBUTION_RATIO
-
-    def get_order(self, byte_str):
-        # for GB2312 encoding, we are interested
-        #  first  byte range: 0xb0 -- 0xfe
-        #  second byte range: 0xa1 -- 0xfe
-        # no validation needed here. State machine has done that
-        first_char, second_char = byte_str[0], byte_str[1]
-        if (first_char >= 0xB0) and (second_char >= 0xA1):
-            return 94 * (first_char - 0xB0) + second_char - 0xA1
-        return -1
-
-
-class Big5DistributionAnalysis(CharDistributionAnalysis):
-    def __init__(self):
-        super().__init__()
-        self._char_to_freq_order = BIG5_CHAR_TO_FREQ_ORDER
-        self._table_size = BIG5_TABLE_SIZE
-        self.typical_distribution_ratio = BIG5_TYPICAL_DISTRIBUTION_RATIO
-
-    def get_order(self, byte_str):
-        # for big5 encoding, we are interested
-        #   first  byte range: 0xa4 -- 0xfe
-        #   second byte range: 0x40 -- 0x7e , 0xa1 -- 0xfe
-        # no validation needed here. State machine has done that
-        first_char, second_char = byte_str[0], byte_str[1]
-        if first_char >= 0xA4:
-            if second_char >= 0xA1:
-                return 157 * (first_char - 0xA4) + second_char - 0xA1 + 63
-            return 157 * (first_char - 0xA4) + second_char - 0x40
-        return -1
-
-
-class SJISDistributionAnalysis(CharDistributionAnalysis):
-    def __init__(self):
-        super().__init__()
-        self._char_to_freq_order = JIS_CHAR_TO_FREQ_ORDER
-        self._table_size = JIS_TABLE_SIZE
-        self.typical_distribution_ratio = JIS_TYPICAL_DISTRIBUTION_RATIO
-
-    def get_order(self, byte_str):
-        # for sjis encoding, we are interested
-        #   first  byte range: 0x81 -- 0x9f , 0xe0 -- 0xfe
-        #   second byte range: 0x40 -- 0x7e,  0x81 -- oxfe
-        # no validation needed here. State machine has done that
-        first_char, second_char = byte_str[0], byte_str[1]
-        if 0x81 <= first_char <= 0x9F:
-            order = 188 * (first_char - 0x81)
-        elif 0xE0 <= first_char <= 0xEF:
-            order = 188 * (first_char - 0xE0 + 31)
-        else:
-            return -1
-        order = order + second_char - 0x40
-        if second_char > 0x7F:
-            order = -1
-        return order
-
-
-class EUCJPDistributionAnalysis(CharDistributionAnalysis):
-    def __init__(self):
-        super().__init__()
-        self._char_to_freq_order = JIS_CHAR_TO_FREQ_ORDER
-        self._table_size = JIS_TABLE_SIZE
-        self.typical_distribution_ratio = JIS_TYPICAL_DISTRIBUTION_RATIO
-
-    def get_order(self, byte_str):
-        # for euc-JP encoding, we are interested
-        #   first  byte range: 0xa0 -- 0xfe
-        #   second byte range: 0xa1 -- 0xfe
-        # no validation needed here. State machine has done that
-        char = byte_str[0]
-        if char >= 0xA0:
-            return 94 * (char - 0xA1) + byte_str[1] - 0xA1
-        return -1
diff --git a/spaces/tjburns/ask_marcus_aurelius/.venv/lib/python3.10/site-packages/pkg_resources/_vendor/more_itertools/__init__.py b/spaces/tjburns/ask_marcus_aurelius/.venv/lib/python3.10/site-packages/pkg_resources/_vendor/more_itertools/__init__.py
deleted file mode 100644
index ea38bef1f661e62d577b3c2207386d901d851c72..0000000000000000000000000000000000000000
--- a/spaces/tjburns/ask_marcus_aurelius/.venv/lib/python3.10/site-packages/pkg_resources/_vendor/more_itertools/__init__.py
+++ /dev/null
@@ -1,4 +0,0 @@
-from .more import *  # noqa
-from .recipes import *  # noqa
-
-__version__ = '8.12.0'
diff --git a/spaces/tjburns/ask_marcus_aurelius/.venv/lib/python3.10/site-packages/setuptools/_distutils/versionpredicate.py b/spaces/tjburns/ask_marcus_aurelius/.venv/lib/python3.10/site-packages/setuptools/_distutils/versionpredicate.py
deleted file mode 100644
index 6ea1192d4c22480c378cdf2279368bde203ea09d..0000000000000000000000000000000000000000
--- a/spaces/tjburns/ask_marcus_aurelius/.venv/lib/python3.10/site-packages/setuptools/_distutils/versionpredicate.py
+++ /dev/null
@@ -1,175 +0,0 @@
-"""Module for parsing and testing package version predicate strings.
-"""
-import re
-import distutils.version
-import operator
-
-
-re_validPackage = re.compile(r"(?i)^\s*([a-z_]\w*(?:\.[a-z_]\w*)*)(.*)", re.ASCII)
-# (package) (rest)
-
-re_paren = re.compile(r"^\s*\((.*)\)\s*$")  # (list) inside of parentheses
-re_splitComparison = re.compile(r"^\s*(<=|>=|<|>|!=|==)\s*([^\s,]+)\s*$")
-# (comp) (version)
-
-
-def splitUp(pred):
-    """Parse a single version comparison.
-
-    Return (comparison string, StrictVersion)
-    """
-    res = re_splitComparison.match(pred)
-    if not res:
-        raise ValueError("bad package restriction syntax: %r" % pred)
-    comp, verStr = res.groups()
-    with distutils.version.suppress_known_deprecation():
-        other = distutils.version.StrictVersion(verStr)
-    return (comp, other)
-
-
-compmap = {
-    "<": operator.lt,
-    "<=": operator.le,
-    "==": operator.eq,
-    ">": operator.gt,
-    ">=": operator.ge,
-    "!=": operator.ne,
-}
-
-
-class VersionPredicate:
-    """Parse and test package version predicates.
-
-    >>> v = VersionPredicate('pyepat.abc (>1.0, <3333.3a1, !=1555.1b3)')
-
-    The `name` attribute provides the full dotted name that is given::
-
-    >>> v.name
-    'pyepat.abc'
-
-    The str() of a `VersionPredicate` provides a normalized
-    human-readable version of the expression::
-
-    >>> print(v)
-    pyepat.abc (> 1.0, < 3333.3a1, != 1555.1b3)
-
-    The `satisfied_by()` method can be used to determine with a given
-    version number is included in the set described by the version
-    restrictions::
-
-    >>> v.satisfied_by('1.1')
-    True
-    >>> v.satisfied_by('1.4')
-    True
-    >>> v.satisfied_by('1.0')
-    False
-    >>> v.satisfied_by('4444.4')
-    False
-    >>> v.satisfied_by('1555.1b3')
-    False
-
-    `VersionPredicate` is flexible in accepting extra whitespace::
-
-    >>> v = VersionPredicate(' pat( ==  0.1  )  ')
-    >>> v.name
-    'pat'
-    >>> v.satisfied_by('0.1')
-    True
-    >>> v.satisfied_by('0.2')
-    False
-
-    If any version numbers passed in do not conform to the
-    restrictions of `StrictVersion`, a `ValueError` is raised::
-
-    >>> v = VersionPredicate('p1.p2.p3.p4(>=1.0, <=1.3a1, !=1.2zb3)')
-    Traceback (most recent call last):
-      ...
-    ValueError: invalid version number '1.2zb3'
-
-    It the module or package name given does not conform to what's
-    allowed as a legal module or package name, `ValueError` is
-    raised::
-
-    >>> v = VersionPredicate('foo-bar')
-    Traceback (most recent call last):
-      ...
-    ValueError: expected parenthesized list: '-bar'
-
-    >>> v = VersionPredicate('foo bar (12.21)')
-    Traceback (most recent call last):
-      ...
-    ValueError: expected parenthesized list: 'bar (12.21)'
-
-    """
-
-    def __init__(self, versionPredicateStr):
-        """Parse a version predicate string."""
-        # Fields:
-        #    name:  package name
-        #    pred:  list of (comparison string, StrictVersion)
-
-        versionPredicateStr = versionPredicateStr.strip()
-        if not versionPredicateStr:
-            raise ValueError("empty package restriction")
-        match = re_validPackage.match(versionPredicateStr)
-        if not match:
-            raise ValueError("bad package name in %r" % versionPredicateStr)
-        self.name, paren = match.groups()
-        paren = paren.strip()
-        if paren:
-            match = re_paren.match(paren)
-            if not match:
-                raise ValueError("expected parenthesized list: %r" % paren)
-            str = match.groups()[0]
-            self.pred = [splitUp(aPred) for aPred in str.split(",")]
-            if not self.pred:
-                raise ValueError("empty parenthesized list in %r" % versionPredicateStr)
-        else:
-            self.pred = []
-
-    def __str__(self):
-        if self.pred:
-            seq = [cond + " " + str(ver) for cond, ver in self.pred]
-            return self.name + " (" + ", ".join(seq) + ")"
-        else:
-            return self.name
-
-    def satisfied_by(self, version):
-        """True if version is compatible with all the predicates in self.
-        The parameter version must be acceptable to the StrictVersion
-        constructor.  It may be either a string or StrictVersion.
-        """
-        for cond, ver in self.pred:
-            if not compmap[cond](version, ver):
-                return False
-        return True
-
-
-_provision_rx = None
-
-
-def split_provision(value):
-    """Return the name and optional version number of a provision.
-
-    The version number, if given, will be returned as a `StrictVersion`
-    instance, otherwise it will be `None`.
-
-    >>> split_provision('mypkg')
-    ('mypkg', None)
-    >>> split_provision(' mypkg( 1.2 ) ')
-    ('mypkg', StrictVersion ('1.2'))
-    """
-    global _provision_rx
-    if _provision_rx is None:
-        _provision_rx = re.compile(
-            r"([a-zA-Z_]\w*(?:\.[a-zA-Z_]\w*)*)(?:\s*\(\s*([^)\s]+)\s*\))?$", re.ASCII
-        )
-    value = value.strip()
-    m = _provision_rx.match(value)
-    if not m:
-        raise ValueError("illegal provides specification: %r" % value)
-    ver = m.group(2) or None
-    if ver:
-        with distutils.version.suppress_known_deprecation():
-            ver = distutils.version.StrictVersion(ver)
-    return m.group(1), ver
diff --git a/spaces/tomofi/MMOCR/configs/_base_/det_models/drrg_r50_fpn_unet.py b/spaces/tomofi/MMOCR/configs/_base_/det_models/drrg_r50_fpn_unet.py
deleted file mode 100644
index 78156cca6030bcf7ac12b75287342915882eb0b3..0000000000000000000000000000000000000000
--- a/spaces/tomofi/MMOCR/configs/_base_/det_models/drrg_r50_fpn_unet.py
+++ /dev/null
@@ -1,21 +0,0 @@
-model = dict(
-    type='DRRG',
-    backbone=dict(
-        type='mmdet.ResNet',
-        depth=50,
-        num_stages=4,
-        out_indices=(0, 1, 2, 3),
-        frozen_stages=-1,
-        norm_cfg=dict(type='BN', requires_grad=True),
-        init_cfg=dict(type='Pretrained', checkpoint='torchvision://resnet50'),
-        norm_eval=True,
-        style='caffe'),
-    neck=dict(
-        type='FPN_UNet', in_channels=[256, 512, 1024, 2048], out_channels=32),
-    bbox_head=dict(
-        type='DRRGHead',
-        in_channels=32,
-        text_region_thr=0.3,
-        center_region_thr=0.4,
-        loss=dict(type='DRRGLoss'),
-        postprocessor=dict(type='DRRGPostprocessor', link_thr=0.80)))
diff --git a/spaces/transiteration/nemo_stt_kz_quartznet15x5/transcribe.py b/spaces/transiteration/nemo_stt_kz_quartznet15x5/transcribe.py
deleted file mode 100644
index c7f39861cb299223ed6f91c9c23b0adb87003961..0000000000000000000000000000000000000000
--- a/spaces/transiteration/nemo_stt_kz_quartznet15x5/transcribe.py
+++ /dev/null
@@ -1,31 +0,0 @@
-import os
-from pathlib import Path
-import nemo.collections.asr as nemo_asr
-
-
-def converter(audio_file):
-    converted = audio_file.split(".")[0] + "converted_.wav"
-    cmd_str = f"ffmpeg -y -i {audio_file} -ac 1 -ar 16000 {converted}"
-    os.system(cmd_str)
-    # os.remove(audio_file)
-    return converted
-    
-    
-
-def transcribe(audio_file):
-    wav_file = converter(audio_file)
-    try:
-        text = model_kz.transcribe([wav_file])
-        return text[0]
-    except:
-        return 'Try another file format.'
-    
-
-
-
-language = "kz"
-
-BASE_DIR = Path(__file__).resolve(strict=True).parent
-
-model_kz = nemo_asr.models.EncDecCTCModel.restore_from(restore_path=f"{BASE_DIR}/stt_{language}_quartznet15x5.nemo")
-
diff --git a/spaces/triggah61/chingu-music/CODE_OF_CONDUCT.md b/spaces/triggah61/chingu-music/CODE_OF_CONDUCT.md
deleted file mode 100644
index 83f431e8feeb7e80d571f39c9f6c1b96857b5f85..0000000000000000000000000000000000000000
--- a/spaces/triggah61/chingu-music/CODE_OF_CONDUCT.md
+++ /dev/null
@@ -1,80 +0,0 @@
-# Code of Conduct
-
-## Our Pledge
-
-In the interest of fostering an open and welcoming environment, we as
-contributors and maintainers pledge to make participation in our project and
-our community a harassment-free experience for everyone, regardless of age, body
-size, disability, ethnicity, sex characteristics, gender identity and expression,
-level of experience, education, socio-economic status, nationality, personal
-appearance, race, religion, or sexual identity and orientation.
-
-## Our Standards
-
-Examples of behavior that contributes to creating a positive environment
-include:
-
-* Using welcoming and inclusive language
-* Being respectful of differing viewpoints and experiences
-* Gracefully accepting constructive criticism
-* Focusing on what is best for the community
-* Showing empathy towards other community members
-
-Examples of unacceptable behavior by participants include:
-
-* The use of sexualized language or imagery and unwelcome sexual attention or
-advances
-* Trolling, insulting/derogatory comments, and personal or political attacks
-* Public or private harassment
-* Publishing others' private information, such as a physical or electronic
-address, without explicit permission
-* Other conduct which could reasonably be considered inappropriate in a
-professional setting
-
-## Our Responsibilities
-
-Project maintainers are responsible for clarifying the standards of acceptable
-behavior and are expected to take appropriate and fair corrective action in
-response to any instances of unacceptable behavior.
-
-Project maintainers have the right and responsibility to remove, edit, or
-reject comments, commits, code, wiki edits, issues, and other contributions
-that are not aligned to this Code of Conduct, or to ban temporarily or
-permanently any contributor for other behaviors that they deem inappropriate,
-threatening, offensive, or harmful.
-
-## Scope
-
-This Code of Conduct applies within all project spaces, and it also applies when
-an individual is representing the project or its community in public spaces.
-Examples of representing a project or community include using an official
-project e-mail address, posting via an official social media account, or acting
-as an appointed representative at an online or offline event. Representation of
-a project may be further defined and clarified by project maintainers.
-
-This Code of Conduct also applies outside the project spaces when there is a
-reasonable belief that an individual's behavior may have a negative impact on
-the project or its community.
-
-## Enforcement
-
-Instances of abusive, harassing, or otherwise unacceptable behavior may be
-reported by contacting the project team at <opensource-conduct@fb.com>. All
-complaints will be reviewed and investigated and will result in a response that
-is deemed necessary and appropriate to the circumstances. The project team is
-obligated to maintain confidentiality with regard to the reporter of an incident.
-Further details of specific enforcement policies may be posted separately.
-
-Project maintainers who do not follow or enforce the Code of Conduct in good
-faith may face temporary or permanent repercussions as determined by other
-members of the project's leadership.
-
-## Attribution
-
-This Code of Conduct is adapted from the [Contributor Covenant][homepage], version 1.4,
-available at https://www.contributor-covenant.org/version/1/4/code-of-conduct.html
-
-[homepage]: https://www.contributor-covenant.org
-
-For answers to common questions about this code of conduct, see
-https://www.contributor-covenant.org/faq
diff --git a/spaces/tsantos/Hierarchical-Classification-System-for-Breast-Cancer/app/src/text_cleaning_transforerms.py b/spaces/tsantos/Hierarchical-Classification-System-for-Breast-Cancer/app/src/text_cleaning_transforerms.py
deleted file mode 100644
index f86dae9d6f76f25114546734be96dae6c20b613f..0000000000000000000000000000000000000000
--- a/spaces/tsantos/Hierarchical-Classification-System-for-Breast-Cancer/app/src/text_cleaning_transforerms.py
+++ /dev/null
@@ -1,229 +0,0 @@
-import pandas as pd
-from os import walk
-from os import listdir
-from os.path import isfile, join
-import numpy as np
-import re 
-
-from gensim.parsing import preprocessing
-from gensim.parsing.preprocessing import strip_tags, strip_punctuation
-from nltk.tokenize import word_tokenize, sent_tokenize
-import math
-from tqdm import tqdm
-
-def remove_noise_text(txt):
-
-  txt = txt.lower()
-  txt = re.sub("primary site:", ' ', txt)
-
-  #txt = re.sub('post-surgical changes', ' ', txt.lower()) 
-
-  # Remove any mentions to " Findings were discussed with...."
-  txt = txt.split("findings were discussed with")[0] 
-
-  # Remove any other occurance of PI's Information
-  txt = txt.split("this study has been reviewed and interpreted")[0] 
-  txt = txt.split("this finding was communicated to")[0] 
-  txt = txt.split("important findings were identified")[0] 
-  txt = txt.split("these findings")[0] 
-  txt = txt.split("findings above were")[0] 
-  txt = txt.split("findings regarding")[0] 
-  txt = txt.split("were discussed")[0] 
-  txt = txt.split("these images were")[0] 
-  txt = txt.split("important finding")[0] 
-
-  # remove any section headers
-  txt = re.sub("post-surgical changes:", ' ', txt)
-  txt = re.sub("post surgical changes:", ' ', txt)
-  txt = re.sub("primary site:", ' ', txt)
-  txt = re.sub("primary site", ' ', txt)
-  txt = re.sub("neck:", ' ', txt)
-  txt = re.sub("post-treatment changes:", ' ', txt)
-  txt = re.sub("post treatment changes:", ' ', txt)
-  txt = re.sub("brain, orbits, spine and lungs:", ' ', txt)
-  txt = re.sub("primary :", ' ', txt)
-  txt = re.sub("neck:", ' ', txt)
-  txt = re.sub("aerodigestive tract:", ' ', txt)
-  txt = re.sub("calvarium, skull base, and spine:", ' ', txt)
-  txt = re.sub("other:", ' ', txt)
-  txt = re.sub("upper neck:", ' ', txt)
-  txt = re.sub("perineural disease:", ' ', txt)
-  txt = re.sub("technique:", ' ', txt)
-  txt = re.sub("comparison:", ' ', txt)
-  txt = re.sub("paranasal sinuses:", ' ', txt)
-  txt = re.sub("included orbits:", ' ', txt)
-  txt = re.sub("nasopharynx:", ' ', txt)
-  txt = re.sub("tympanomastoid cavities:", ' ', txt)
-  txt = re.sub("skull base and calvarium:", ' ', txt)
-  txt = re.sub("included intracranial structures:", ' ', txt)
-  txt = re.sub("impression:", ' ', txt)
-  txt = re.sub("nodes:", ' ', txt)
-  txt = re.sub("mri orbits:", ' ', txt)
-  txt = re.sub("mri brain:", ' ', txt)
-  txt = re.sub("brain:", ' ', txt)
-  txt = re.sub("ct face w/:", ' ', txt)
-  txt = re.sub("transspatial extension:", ' ', txt)
-  txt = re.sub("thyroid bed:", ' ', txt)
-  txt = re.sub("additional findings:", ' ', txt)
-  txt = re.sub("series_image", ' ', txt) 
-  txt = re.sub("series image", ' ', txt)
-  txt = re.sub("image series", ' ', txt)
-  txt = re.sub("see synoptic report", ' ', txt)
-  txt = re.sub("see report", ' ', txt)
-  
-  txt = re.sub("brstwo|brstmarun|brstwln|brlump|lnbx", ' ', txt)
-  
-  txt = re.sub("post_treatment", 'post treatment', txt)
-  txt = re.sub("post-treatment", 'post treatment', txt)
-
-  txt = re.sub("nonmasslike", 'non mass like', txt)
-  txt = re.sub("non_mass_like", 'non mass like', txt) 
-  txt = re.sub("non-mass-like", 'non mass like', txt)
-  txt = re.sub("statuspost", 'status post', txt)
-
-
-  # in the worst case, just replace the name from PI to empty string
-  txt = re.sub("dr\\.\\s[^\\s]+", ' ', txt)  
-
-  txt = re.sub(" series | series|series ", "", txt)
-  txt = re.sub(" cm | cm|cm ", " centimeters ", txt)
-  txt = re.sub(" cc | cc|cc ", " cubic centimeters ", txt)
-  txt = re.sub(" ct | ct|ct ", " carat metric ", txt)
-  txt = re.sub(" mm | mm|mm ", " millimeters ", txt)
-  
-  txt = re.sub("status_post|o\'", '', txt)
-  txt = re.sub("status post|clock|/|'/'", '', txt)
-  txt = re.sub("statuspost", '', txt)
-  txt = re.sub("brstwo|brlump|brstmarun|brwire|brstcap|", '', txt)
-
-  txt = re.sub("\\(|\\)", ',', txt)
-  txt = re.sub(",,", ',', txt)
-  txt = re.sub(",\\.", '.', txt)
-  txt = re.sub(", \\.", '.', txt)
-
-  txt = re.sub(" ,", ', ', txt)
-  txt = re.sub("a\\.", ' ', txt[0:5]) + txt[5:]
-  txt = re.sub("b\\.", ' ', txt[0:5]) + txt[5:]
-  txt = re.sub("c\\.", ' ', txt[0:5]) + txt[5:]
-  txt = re.sub("d\\.", ' ', txt[0:5]) + txt[5:]
-  txt = re.sub("e\\.", ' ', txt[0:5]) + txt[5:]
-  txt = re.sub("f\\.", ' ', txt[0:5]) + txt[5:]
-  
-
-  # in the worst case, just replace the name from PI to empty string
-  txt = re.sub("dr\\.\\s[^\\s]+", '', txt)
-
-  # Removing multiple spaces
-  txt = re.sub(r'\s+', ' ', txt)
-  txt = re.sub(' +', ' ', txt)
-
-  txt = txt.rstrip().lstrip()
-
-  return txt
-
-
-def add_bigrams(txt, fixed_bigrams):
-
-  for b in fixed_bigrams:
-    sub = ""
-    not_first = False
-    for x in b[1:]:
-      if not_first:
-        sub += "|"
-        not_first = True
-
-      sub += str(x) + "|" + str(x) + " " + "|" +  " " + str(x) + "|" + " " + str(x)   
-    txt = re.sub(sub, b[0], txt)
-      
-
-  return txt
-
-def extra_clean_text(clean_t,fixed_bigrams):
-
-  txt = add_bigrams(clean_t, fixed_bigrams)
-  replaces = [ ["her2|her 2|her two", " hertwo "], 
-              # ["0", "zero "], ["1", "one "], ["2", "two "], ["3", "three "],["4", "four "],
-              # ["5", "five "],["6", "six "] ,["7", "seven "] ,["8", "eight "] ,["9", "nine " ] ,
-              ["\\>", " greather "], ["\\<", " less "]]
-
-  for sub in replaces:
-    txt = re.sub(sub[0], sub[1], txt)
-
-  return txt
-
-
-def text_cleaning(data,min_lenght=2,extra_clean=True, remove_punctuation=False):
-
-                  # position 0 means the bigram output - 1:end means how they may come on text
-  fixed_bigrams = [ [' gradeone ', 'grade 1', 'grade i', 'grade I', 'grade one',],
-                    [' gradetwo ', 'grade 2', 'grade ii', 'grade II', 'grade two', ],
-                    [' gradethree ', 'grade 3' , 'grade iii', 'grade III', 'grade three']]
-
-  clean_txt = []
-
-  clean_t = remove_noise_text(data)
-  if extra_clean:
-    clean_t = extra_clean_text(clean_t,fixed_bigrams)
-    if remove_punctuation:
-      filters = [lambda x: x.lower(), strip_tags, strip_punctuation]
-    else:
-      filters = [lambda x: x.lower(), strip_tags]
-
-    clean_t = " ".join(x for x in preprocessing.preprocess_string(clean_t, filters) if len(x) >=min_lenght)
-
-
-  # Removing multiple spaces
-  clean_t = re.sub(r'\s+', ' ', clean_t)
-
-  return clean_t
-
-# set only_data = True if no need to get scores or if dataaset doesn't have a score
-def pre_process(data,min_lenght=2,max_size=64, extra_clean=True, remove_punctuation=False): 
-
-
-  data_pre_processed = text_cleaning(data,min_lenght=min_lenght,extra_clean=extra_clean, remove_punctuation=remove_punctuation)
-
-  """
-    Partion the data into max_size chunks
-  """
-  sentences = sent_tokenize(data)
-  data_pre_processed_chunks,sample = [],""
-
-  # Were able to split into sentences
-  if len(sentences)>1:
-    for index,sentence in enumerate(sentences):
-      if len(sentence.split()) + len(sample.split()) <= max_size:
-        sample += sentence
-      else:
-        data_pre_processed_chunks.append(text_cleaning(sample,min_lenght=min_lenght,extra_clean=extra_clean, remove_punctuation=remove_punctuation))
-        sample = sentence if index < len(sentences)-1 else ""
-
-    if len(sample) ==0:
-      clean_data = text_cleaning(sentences[-1],min_lenght=min_lenght,extra_clean=extra_clean, remove_punctuation=remove_punctuation)  
-    else:
-      clean_data = text_cleaning(sample,min_lenght=min_lenght,extra_clean=extra_clean, remove_punctuation=remove_punctuation)
-      
-    #if len(clean_data.split()) >3:
-    data_pre_processed_chunks.append(clean_data)
-
-  # Split by get max size chunks
-  else:
-    words = word_tokenize(data)
-    lower_b, upper_b = 0, max_size
-    for x in range(math.ceil(len(words)/max_size)):
-        sample = " ".join(x for x in words[lower_b:upper_b])
-        lower_b, upper_b = upper_b, upper_b+max_size
-        clean_data = text_cleaning(sample,min_lenght=min_lenght,extra_clean=extra_clean, remove_punctuation=remove_punctuation)
-        #if len(clean_data.split()) >3:
-        data_pre_processed_chunks.append(clean_data)
-
-  # return the pre_processed of whoole text and chunks
-  return data_pre_processed,data_pre_processed_chunks
-
-if __name__ == '__main__':
-  exit(1)
-
-
-
-
-
diff --git a/spaces/ttt246/brain/Brain/src/service/train_service.py b/spaces/ttt246/brain/Brain/src/service/train_service.py
deleted file mode 100644
index 0b63b727a6b54767f93766db051359641458b476..0000000000000000000000000000000000000000
--- a/spaces/ttt246/brain/Brain/src/service/train_service.py
+++ /dev/null
@@ -1,163 +0,0 @@
-"""service to manage trains"""
-from typing import Any
-
-import firebase_admin
-
-from Brain.src.model.req_model import ReqModel
-from Brain.src.rising_plugin.csv_embed import get_embed
-from Brain.src.rising_plugin.pinecone_engine import (
-    get_pinecone_index_namespace,
-    delete_pinecone,
-    add_pinecone,
-    delete_all_pinecone,
-)
-
-from firebase_admin import firestore
-import datetime
-
-
-def to_json(page_content: str):
-    return {
-        "page_content": page_content,
-        "timestamp": datetime.datetime.now().timestamp(),
-    }
-
-
-class TrainService:
-    """train (getting embedding) and update pinecone with embeddings by document_id
-    train datatype:
-    key: document_id
-    values: {page_content}"""
-
-    db: Any
-    documents_ref: Any
-
-    def __init__(self, firebase_app: firebase_admin.App, setting: ReqModel):
-        self.firebase_app = firebase_app
-        self.setting = setting
-
-    def init_firestore(self):
-        self.db = firestore.client(app=self.firebase_app)
-        self.documents_ref = self.db.collection("documents")
-
-    """read all documents from firestore"""
-
-    def read_all_documents(self) -> Any:
-        self.init_firestore()
-        query = self.documents_ref.order_by("timestamp")
-        docs = query.stream()
-        result = []
-        for item in docs:
-            item_data = item.to_dict()
-            result.append(
-                {"document_id": item.id, "page_content": item_data["page_content"]}
-            )
-        return result
-
-    """read one document from firestore"""
-
-    def read_one_document(self, document_id: str):
-        self.init_firestore()
-        doc = self.documents_ref.document(document_id).get()
-        if doc.exists:
-            return {
-                "document_id": document_id,
-                "page_content": doc.to_dict()["page_content"],
-            }
-        else:
-            return None
-
-    """create a new document and train it"""
-
-    def create_one_document(self, page_content: str):
-        self.init_firestore()
-        # Auto-generate document ID
-        auto_generated_doc_ref = self.documents_ref.document()
-        auto_generated_doc_ref.set(to_json(page_content))
-        auto_generated_document_id = auto_generated_doc_ref.id
-        self.train_one_document(auto_generated_document_id, page_content)
-        return {"document_id": auto_generated_document_id, "page_content": page_content}
-
-    """update a document by using id and train it"""
-
-    def update_one_document(self, document_id: str, page_content: str):
-        self.init_firestore()
-        self.documents_ref.document(document_id).update(to_json(page_content))
-        self.train_one_document(document_id, page_content)
-        return {"document_id": document_id, "page_content": page_content}
-
-    """delete a document by using document_id"""
-
-    def delete_one_document(self, document_id: str):
-        self.init_firestore()
-        self.documents_ref.document(document_id).delete()
-        self.delete_one_pinecone(document_id)
-        return {"document_id": document_id}
-
-    def train_all_documents(self) -> str:
-        self.init_firestore()
-        self.delete_all()
-        documents = self.read_all_documents()
-        result = list()
-        pinecone_namespace = self.get_pinecone_index_namespace()
-        for item in documents:
-            query_result = get_embed(data=item["page_content"], setting=self.setting)
-            result.append(query_result)
-            key = item["document_id"]
-            value = f'{item["page_content"]}'
-            # get vectoring data(embedding data)
-            vectoring_values = get_embed(data=value, setting=self.setting)
-            add_pinecone(
-                namespace=pinecone_namespace,
-                key=key,
-                value=vectoring_values,
-                setting=self.setting,
-            )
-
-        return "trained all documents successfully"
-
-    def train_one_document(self, document_id: str, page_content: str) -> None:
-        self.init_firestore()
-        pinecone_namespace = self.get_pinecone_index_namespace()
-        result = list()
-        query_result = get_embed(data=page_content, setting=self.setting)
-        result.append(query_result)
-        key = document_id
-        value = f"{page_content}, {query_result}"
-        # get vectoring data(embedding data)
-        vectoring_values = get_embed(data=value, setting=self.setting)
-        add_pinecone(
-            namespace=pinecone_namespace,
-            key=key,
-            value=vectoring_values,
-            setting=self.setting,
-        )
-
-    def delete_all(self) -> Any:
-        self.init_firestore()
-        return delete_all_pinecone(
-            namespace=self.get_pinecone_index_namespace(),
-            setting=self.setting,
-        )
-
-    def delete_one_pinecone(self, document_id: str) -> Any:
-        self.init_firestore()
-        return delete_pinecone(
-            namespace=self.get_pinecone_index_namespace(),
-            key=document_id,
-            setting=self.setting,
-        )
-
-    def delete_all_training_from_pinecone(self) -> Any:
-        self.init_firestore()
-        return delete_all_pinecone(
-            namespace=self.get_pinecone_index_namespace(), setting=self.setting
-        )
-
-    def get_pinecone_index_namespace(self) -> str:
-        self.init_firestore()
-        return get_pinecone_index_namespace(f"trains")
-
-    def get_pinecone_index_train_namespace(self) -> str:
-        self.init_firestore()
-        return get_pinecone_index_namespace(f"trains")
diff --git a/spaces/twdac/BuChengFangYuan-ChineseJapaneseTranslation/app/my_py_lib/dataset/voc_dataset.py b/spaces/twdac/BuChengFangYuan-ChineseJapaneseTranslation/app/my_py_lib/dataset/voc_dataset.py
deleted file mode 100644
index 7ef5633f0a2d2cea6f38f4681a8c79153156ebdc..0000000000000000000000000000000000000000
--- a/spaces/twdac/BuChengFangYuan-ChineseJapaneseTranslation/app/my_py_lib/dataset/voc_dataset.py
+++ /dev/null
@@ -1,243 +0,0 @@
-"""
-This is a dataset for pascal voc 2012
-"""
-
-import os
-from collections import OrderedDict
-from xml.dom.minidom import parse
-import imageio
-import numpy as np
-
-if __name__ == '__main__':
-    from dataset import Dataset
-else:
-    from .dataset import Dataset
-
-
-def _xml_extractor(xml_file):
-    dom_tree = parse(xml_file)
-    collection = dom_tree.documentElement
-    file_name_xml = collection.getElementsByTagName('filename')[0]
-    objects_xml = collection.getElementsByTagName('object')
-    size_xml = collection.getElementsByTagName('size')
-
-    file_name = file_name_xml.childNodes[0].data
-
-    for size in size_xml:
-        width = size.getElementsByTagName('width')[0]
-        height = size.getElementsByTagName('height')[0]
-        depth = size.getElementsByTagName('depth')[0]
-
-        width = width.childNodes[0].data
-        height = height.childNodes[0].data
-        depth = depth.childNodes[0].data
-
-    objects = []
-    for object_xml in objects_xml:
-        object_name = object_xml.getElementsByTagName('name')[0]
-        bdbox = object_xml.getElementsByTagName('bndbox')[0]
-        xmin = bdbox.getElementsByTagName('xmin')[0]
-        ymin = bdbox.getElementsByTagName('ymin')[0]
-        xmax = bdbox.getElementsByTagName('xmax')[0]
-        ymax = bdbox.getElementsByTagName('ymax')[0]
-
-        object = (object_name.childNodes[0].data, xmin.childNodes[0].data,
-                  ymin.childNodes[0].data, xmax.childNodes[0].data,
-                  ymax.childNodes[0].data)
-
-        objects.append(object)
-
-    return file_name, width, height, depth, objects
-
-
-class VocDataset(Dataset):
-    train_id_txt = 'ImageSets/Main/train.txt'
-    val_id_txt = 'ImageSets/Main/val.txt'
-    id_dir = 'ImageSets/Main'
-    image_dir = 'JPEGImages'
-    ann_dir = 'Annotations'
-
-    classes_name = {'person': 0,
-                    'bird': 1,
-                    'cat': 2,
-                    'cow': 3,
-                    'dog': 4,
-                    'horse': 5,
-                    'sheep': 6,
-                    'aeroplane': 7,
-                    'bicycle': 8,
-                    'boat': 9,
-                    'bus': 10,
-                    'car': 11,
-                    'motorbike': 12,
-                    'train': 13,
-                    'bottle': 14,
-                    'chair': 15,
-                    'diningtable': 16,
-                    'pottedplant': 17,
-                    'sofa': 18,
-                    'tvmonitor': 19
-                    }
-
-    def __init__(self, dataset_path, dataset_type, id_dir=None, image_dir=None, ann_dir=None, classes_name=None):
-        """
-        init voc dataset
-        :param dataset_path:    dataset root dir path
-        :param dataset_type:    filename in id_dir, for example: train.txt
-        :param id_dir:          for custom voc dataset, where to search id file
-        :param image_dir:       for custom voc dataset, where to search image file
-        :param ann_dir:         for custom voc dataset, where to search ann file
-        :param classes_name:    for custom voc dataset, classes name
-        """
-        Dataset.__init__(self)
-
-        # for custom voc dataset
-        self.id_dir = self.id_dir if id_dir is None else id_dir
-        self.image_dir = self.image_dir if image_dir is None else image_dir
-        self.ann_dir = self.ann_dir if ann_dir is None else ann_dir
-        self.id_dir = self.id_dir if id_dir is None else id_dir
-        if classes_name is not None:
-            self.classes_name = dict(zip(classes_name, range(len(classes_name))))
-
-        # become to orded dict
-        self.classes_name = OrderedDict(sorted(self.classes_name.items(), key=lambda t: t[1]))
-
-        # init basic info
-        self.dataset_type = dataset_type
-        self.dataset_dir = dataset_path
-
-        # init path
-        self.img_file_root = os.path.join(dataset_path, self.image_dir)
-        self.label_file_root = os.path.join(dataset_path, self.ann_dir)
-        self.label_file_list =\
-            open(os.path.join(dataset_path, self.id_dir, dataset_type+'.txt'), 'r').read().splitlines()
-        self.label_file_list_len = len(self.label_file_list)
-
-        # init label info
-        self.label_info = []
-        for label_file in tuple(self.label_file_list):
-            ann_file = os.path.join(self.label_file_root, label_file + '.xml')
-            file_name, width, height, depth, objects = _xml_extractor(ann_file)
-            classes = []
-            coords = []
-            for obj in objects:
-                classname, xmin, ymin, xmax, ymax = obj
-                classid = self.classes_name[classname]
-                classes.append(classid)
-                coords.append([int(xmin), int(ymin), int(xmax), int(ymax)])
-            classes = tuple(classes)
-            coords = tuple(coords)
-            self.label_info.append((file_name, int(width), int(height), int(depth), (classes, coords)))
-        # self.label_info = tuple(self.label_info)
-
-
-    # get the dataset information
-    def get_label_num(self):
-        """
-        how many label in this dataset
-        :return:
-        """
-        return self.label_file_list_len
-
-    def get_class_num(self):
-        """
-        how many class in this dataset
-        :return:
-        """
-        return len(self.classes_name.keys())
-
-    def get_class_name(self):
-        """
-        get classes name
-        :return:
-        """
-        return tuple(self.classes_name.keys())
-
-    # Setting this dataset something
-    def shuffle(self):
-        """
-        shuffle this dataset
-        :return:
-        """
-        np.random.shuffle(self.label_info)
-
-    # get item details
-    def get_label_info(self, label_id):
-        """
-        get this label details, will return a dict, include key's
-        [ image_path, image_width, image_height ]
-        :param label_id:
-        :return:
-        """
-        info = {}
-        a = self.label_info[label_id]
-        info['image_path'] = os.path.join(self.img_file_root, a[0])
-        info['image_width'] = a[1]
-        info['image_height'] = a[2]
-        return info
-
-    def get_label_image(self, label_id):
-        """
-        get origin image
-        :param label_id: int
-        :return: numpy.array
-        """
-        a = self.label_info[label_id]
-        return imageio.imread(os.path.join(self.img_file_root, a[0]))
-
-    def get_label_instance_bbox(self, label_id):
-        """
-        for object detection
-        :param label_id:
-        :return: a list of classes id, a list of coords (x1, y1, x2, y2)
-        """
-        a = self.label_info[label_id]
-        return a[4] # (classes, coords)
-
-    def get_label_class_mask(self, label_id):
-        """
-        for semantic segmentation
-        :param label_id:
-        :return:
-        """
-        self._not_imp()
-
-    def get_label_instance_mask(self, label_id):
-        """
-        for instance segmentation
-        :param label_id:
-        :param class_id:
-        :param instant_id:
-        :return:
-        """
-        self._not_imp()
-
-
-def test(voc_path='''E:\TDOWNLOAD\VOCdevkit\VOC2012'''):
-    import sys
-    sys.path.append('../')
-    import im_tool
-    ds = VocDataset(voc_path, 'train')
-    ds.shuffle()
-    print('image num', ds.get_label_num())
-    print('class num', ds.get_class_num())
-    print('class name', ds.get_class_name())
-
-    label_id = np.random.randint(0, ds.get_label_num())
-    print('label info', ds.get_label_info(label_id))
-
-    classes_name = ds.get_class_name()
-    print(ds.get_label_instance_bbox(label_id))
-    classes, coords = ds.get_label_instance_bbox(label_id)
-    for classid, coord in zip(classes, coords):
-        print('name', classes_name[classid])
-        print('bbox', coord)
-
-    scores = np.ones_like(classes)
-
-    draw_img = im_tool.draw_boxes_and_labels_to_image(ds.get_label_image(label_id), classes, coords, scores, classes_name)
-    im_tool.show_image(draw_img)
-
-
-if __name__ == '__main__':
-    test()
diff --git a/spaces/ulysses115/diffsvc_test/README.md b/spaces/ulysses115/diffsvc_test/README.md
deleted file mode 100644
index fb48348bc51488806d6e47abc3df7fc1a9ca0bda..0000000000000000000000000000000000000000
--- a/spaces/ulysses115/diffsvc_test/README.md
+++ /dev/null
@@ -1,11 +0,0 @@
----
-title: Diffsvc test
-sdk: gradio
-emoji: 💩
-colorFrom: red
-colorTo: yellow
-license: apache-2.0
-sdk_version: 3.4.1
-app_file: app.py
-pinned: false
----
\ No newline at end of file
diff --git a/spaces/ulysses115/diffsvc_test/network/hubert/vec_model.py b/spaces/ulysses115/diffsvc_test/network/hubert/vec_model.py
deleted file mode 100644
index ee4b7a152ab9f299d43d6f519564caca25d836a5..0000000000000000000000000000000000000000
--- a/spaces/ulysses115/diffsvc_test/network/hubert/vec_model.py
+++ /dev/null
@@ -1,60 +0,0 @@
-from pathlib import Path
-
-import librosa
-import numpy as np
-import torch
-
-
-
-def load_model(vec_path):
-    device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
-    print("load model(s) from {}".format(vec_path))
-    from fairseq import checkpoint_utils
-    models, saved_cfg, task = checkpoint_utils.load_model_ensemble_and_task(
-        [vec_path],
-        suffix="",
-    )
-    model = models[0]
-    model = model.to(device)
-    model.eval()
-    return model
-
-
-def get_vec_units(con_model, audio_path, dev):
-    audio, sampling_rate = librosa.load(audio_path)
-    if len(audio.shape) > 1:
-        audio = librosa.to_mono(audio.transpose(1, 0))
-    if sampling_rate != 16000:
-        audio = librosa.resample(audio, orig_sr=sampling_rate, target_sr=16000)
-
-    feats = torch.from_numpy(audio).float()
-    if feats.dim() == 2:  # double channels
-        feats = feats.mean(-1)
-    assert feats.dim() == 1, feats.dim()
-    feats = feats.view(1, -1)
-    padding_mask = torch.BoolTensor(feats.shape).fill_(False)
-    inputs = {
-        "source": feats.to(dev),
-        "padding_mask": padding_mask.to(dev),
-        "output_layer": 9,  # layer 9
-    }
-    with torch.no_grad():
-        logits = con_model.extract_features(**inputs)
-        feats = con_model.final_proj(logits[0])
-    return feats
-
-
-if __name__ == '__main__':
-    device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
-    model_path = "../../checkpoints/checkpoint_best_legacy_500.pt"  # checkpoint_best_legacy_500.pt
-    vec_model = load_model(model_path)
-    # 这个不用改，自动在根目录下所有wav的同文件夹生成其对应的npy
-    file_lists = list(Path("../../data/vecfox").rglob('*.wav'))
-    nums = len(file_lists)
-    count = 0
-    for wav_path in file_lists:
-        npy_path = wav_path.with_suffix(".npy")
-        npy_content = get_vec_units(vec_model, str(wav_path), device).cpu().numpy()[0]
-        np.save(str(npy_path), npy_content)
-        count += 1
-        print(f"hubert process：{round(count * 100 / nums, 2)}%")
diff --git a/spaces/uparasha/AnimationUsingLottie/app.py b/spaces/uparasha/AnimationUsingLottie/app.py
deleted file mode 100644
index 0bb8b3fbe0dec40cf80b7fa54e6cad38b1540a89..0000000000000000000000000000000000000000
--- a/spaces/uparasha/AnimationUsingLottie/app.py
+++ /dev/null
@@ -1,29 +0,0 @@
-import requests
-import streamlit as st
-from streamlit_lottie import st_lottie
-
-def load_lottie_url(url: str):
-    r = requests.get(url)
-    if r.status_code != 200:
-        return None
-    return r.json()
-    
-def ShowAnimation(name, URL):
-    anim=load_lottie_url(URL)
-    st_lottie(anim, key = name)
-    
-st.markdown('# Animations: https://lottiefiles.com/recent') 
-st.markdown("# Animate with JSON, SVG, Adobe XD, Figma, and deploy to web, mobile as tiny animation files ")
-ShowAnimation("Badge1","https://assets5.lottiefiles.com/packages/lf20_wtohqzml.json")
-ShowAnimation("Badge2","https://assets5.lottiefiles.com/packages/lf20_i4zw2ddg.json")
-ShowAnimation("Badge3","https://assets5.lottiefiles.com/private_files/lf30_jfhmdmk5.json")
-ShowAnimation("Graph","https://assets6.lottiefiles.com/packages/lf20_4gqhiayj.json")
-ShowAnimation("PhoneBot","https://assets9.lottiefiles.com/packages/lf20_zrqthn6o.json")
-ShowAnimation("SupportBot","https://assets5.lottiefiles.com/private_files/lf30_cmd8kh2q.json")
-ShowAnimation("ChatBot","https://assets8.lottiefiles.com/packages/lf20_j1oeaifz.json")
-ShowAnimation("IntelligentMachine","https://assets8.lottiefiles.com/packages/lf20_edouagsj.json")
-ShowAnimation("GearAI","https://assets10.lottiefiles.com/packages/lf20_3jkp7dqt.json")
-ShowAnimation("ContextGraph","https://assets10.lottiefiles.com/private_files/lf30_vwC61X.json")
-ShowAnimation("Yggdrasil","https://assets4.lottiefiles.com/packages/lf20_8q1bhU.json")
-ShowAnimation("Studying","https://assets9.lottiefiles.com/packages/lf20_6ft9bypa.json")
-
diff --git a/spaces/usbethFlerru/sovits-modelsV2/Rubber-2010-1080p-BluRay-X264CiNEFiLE.md b/spaces/usbethFlerru/sovits-modelsV2/Rubber-2010-1080p-BluRay-X264CiNEFiLE.md
deleted file mode 100644
index 99b8d98a6f6e68915c6f97344e9d8a2debe11288..0000000000000000000000000000000000000000
--- a/spaces/usbethFlerru/sovits-modelsV2/Rubber-2010-1080p-BluRay-X264CiNEFiLE.md
+++ /dev/null
@@ -1,60 +0,0 @@
-## Rubber (2010) 1080p BluRay X264-CiNEFiLE
-
-
-
- 
-
-  
-
- 
-
-**Download > [https://lomasmavi.blogspot.com/?c=2txSZs](https://lomasmavi.blogspot.com/?c=2txSZs)**
-
-
-
- 
-
- 
-
- 
-
- 
-
- 
-
-# Rubber (2010) 1080p BluRay X264-CiNEFiLE: A Review of the Cult Horror Comedy
-
- 
-
-If you are looking for a movie that is bizarre, original, and hilarious, you might want to check out Rubber (2010) 1080p BluRay X264-CiNEFiLE. This is a horror comedy film directed by Quentin Dupieux, also known as Mr. Oizo, a French musician and filmmaker. The film follows the adventures of a sentient tire named Robert, who has telekinetic powers and a penchant for killing anything that crosses his path.
-
- 
-
-The film is a metafictional satire that breaks the fourth wall and mocks the conventions of cinema and storytelling. The film begins with a monologue by a police officer, who explains that some things in movies happen for "no reason", and that Rubber is an homage to this concept. He then introduces a group of spectators, who watch the events of the film unfold through binoculars from a distance. The spectators comment on the action and provide comic relief throughout the film.
-
- 
-
-Rubber (2010) 1080p BluRay X264-CiNEFiLE is a unique and entertaining film that defies genre and logic. It is a film that celebrates the absurdity and randomness of life and art. The film has received mixed reviews from critics and audiences, but has gained a cult following among fans of quirky and unconventional cinema. The film has also spawned a sequel, Reality (2014), which features some of the same characters and themes.
-
- 
-
-If you are interested in watching Rubber (2010) 1080p BluRay X264-CiNEFiLE, you can find it on various online platforms and streaming services. You can also download it from torrent sites or buy it on DVD or Blu-ray. However you choose to watch it, be prepared for a wild and hilarious ride that will make you question everything you know about movies.
-
-  
-
-One of the most intriguing aspects of Rubber (2010) 1080p BluRay X264-CiNEFiLE is the character of Robert, the tire. Robert is not a typical antagonist or protagonist, but rather a mysterious and unpredictable force of nature. He has no dialogue, no backstory, and no motivation, other than his curiosity and his desire to kill. He is both terrifying and amusing, as he rolls around the desert, blowing up animals, people, and objects with his mind. He also develops a fascination with a woman named Sheila, who becomes his love interest and his nemesis.
-
- 
-
-The film uses Robert as a metaphor for the power and danger of cinema and art. Robert represents the creative impulse that can inspire or destroy, depending on how it is used. He also represents the audience's suspension of disbelief and willingness to accept anything that happens on screen, no matter how absurd or illogical. Robert is both the creator and the consumer of his own story, and he challenges the viewers to question their own role and expectations as well.
-
- 
-
-Rubber (2010) 1080p BluRay X264-CiNEFiLE is a film that does not take itself seriously, but also does not shy away from making a statement. It is a film that embraces its own absurdity and invites the audience to join in the fun. It is a film that celebrates the freedom and joy of cinema and art, while also exposing its dark and destructive side. It is a film that you will either love or hate, but you will never forget.
-
- dfd1c89656
-
- 
-
- 
-
diff --git a/spaces/user238921933/stable-diffusion-webui/extensions/deforum/scripts/deforum_helpers/src/midas/midas_net_custom.py b/spaces/user238921933/stable-diffusion-webui/extensions/deforum/scripts/deforum_helpers/src/midas/midas_net_custom.py
deleted file mode 100644
index 50e4acb5e53d5fabefe3dde16ab49c33c2b7797c..0000000000000000000000000000000000000000
--- a/spaces/user238921933/stable-diffusion-webui/extensions/deforum/scripts/deforum_helpers/src/midas/midas_net_custom.py
+++ /dev/null
@@ -1,128 +0,0 @@
-"""MidashNet: Network for monocular depth estimation trained by mixing several datasets.
-This file contains code that is adapted from
-https://github.com/thomasjpfan/pytorch_refinenet/blob/master/pytorch_refinenet/refinenet/refinenet_4cascade.py
-"""
-import torch
-import torch.nn as nn
-
-from .base_model import BaseModel
-from .blocks import FeatureFusionBlock, FeatureFusionBlock_custom, Interpolate, _make_encoder
-
-
-class MidasNet_small(BaseModel):
-    """Network for monocular depth estimation.
-    """
-
-    def __init__(self, path=None, features=64, backbone="efficientnet_lite3", non_negative=True, exportable=True, channels_last=False, align_corners=True,
-        blocks={'expand': True}):
-        """Init.
-
-        Args:
-            path (str, optional): Path to saved model. Defaults to None.
-            features (int, optional): Number of features. Defaults to 256.
-            backbone (str, optional): Backbone network for encoder. Defaults to resnet50
-        """
-        print("Loading weights: ", path)
-
-        super(MidasNet_small, self).__init__()
-
-        use_pretrained = False if path else True
-                
-        self.channels_last = channels_last
-        self.blocks = blocks
-        self.backbone = backbone
-
-        self.groups = 1
-
-        features1=features
-        features2=features
-        features3=features
-        features4=features
-        self.expand = False
-        if "expand" in self.blocks and self.blocks['expand'] == True:
-            self.expand = True
-            features1=features
-            features2=features*2
-            features3=features*4
-            features4=features*8
-
-        self.pretrained, self.scratch = _make_encoder(self.backbone, features, use_pretrained, groups=self.groups, expand=self.expand, exportable=exportable)
-  
-        self.scratch.activation = nn.ReLU(False)    
-
-        self.scratch.refinenet4 = FeatureFusionBlock_custom(features4, self.scratch.activation, deconv=False, bn=False, expand=self.expand, align_corners=align_corners)
-        self.scratch.refinenet3 = FeatureFusionBlock_custom(features3, self.scratch.activation, deconv=False, bn=False, expand=self.expand, align_corners=align_corners)
-        self.scratch.refinenet2 = FeatureFusionBlock_custom(features2, self.scratch.activation, deconv=False, bn=False, expand=self.expand, align_corners=align_corners)
-        self.scratch.refinenet1 = FeatureFusionBlock_custom(features1, self.scratch.activation, deconv=False, bn=False, align_corners=align_corners)
-
-        
-        self.scratch.output_conv = nn.Sequential(
-            nn.Conv2d(features, features//2, kernel_size=3, stride=1, padding=1, groups=self.groups),
-            Interpolate(scale_factor=2, mode="bilinear"),
-            nn.Conv2d(features//2, 32, kernel_size=3, stride=1, padding=1),
-            self.scratch.activation,
-            nn.Conv2d(32, 1, kernel_size=1, stride=1, padding=0),
-            nn.ReLU(True) if non_negative else nn.Identity(),
-            nn.Identity(),
-        )
-        
-        if path:
-            self.load(path)
-
-
-    def forward(self, x):
-        """Forward pass.
-
-        Args:
-            x (tensor): input data (image)
-
-        Returns:
-            tensor: depth
-        """
-        if self.channels_last==True:
-            print("self.channels_last = ", self.channels_last)
-            x.contiguous(memory_format=torch.channels_last)
-
-
-        layer_1 = self.pretrained.layer1(x)
-        layer_2 = self.pretrained.layer2(layer_1)
-        layer_3 = self.pretrained.layer3(layer_2)
-        layer_4 = self.pretrained.layer4(layer_3)
-        
-        layer_1_rn = self.scratch.layer1_rn(layer_1)
-        layer_2_rn = self.scratch.layer2_rn(layer_2)
-        layer_3_rn = self.scratch.layer3_rn(layer_3)
-        layer_4_rn = self.scratch.layer4_rn(layer_4)
-
-
-        path_4 = self.scratch.refinenet4(layer_4_rn)
-        path_3 = self.scratch.refinenet3(path_4, layer_3_rn)
-        path_2 = self.scratch.refinenet2(path_3, layer_2_rn)
-        path_1 = self.scratch.refinenet1(path_2, layer_1_rn)
-        
-        out = self.scratch.output_conv(path_1)
-
-        return torch.squeeze(out, dim=1)
-
-
-
-def fuse_model(m):
-    prev_previous_type = nn.Identity()
-    prev_previous_name = ''
-    previous_type = nn.Identity()
-    previous_name = ''
-    for name, module in m.named_modules():
-        if prev_previous_type == nn.Conv2d and previous_type == nn.BatchNorm2d and type(module) == nn.ReLU:
-            # print("FUSED ", prev_previous_name, previous_name, name)
-            torch.quantization.fuse_modules(m, [prev_previous_name, previous_name, name], inplace=True)
-        elif prev_previous_type == nn.Conv2d and previous_type == nn.BatchNorm2d:
-            # print("FUSED ", prev_previous_name, previous_name)
-            torch.quantization.fuse_modules(m, [prev_previous_name, previous_name], inplace=True)
-        # elif previous_type == nn.Conv2d and type(module) == nn.ReLU:
-        #    print("FUSED ", previous_name, name)
-        #    torch.quantization.fuse_modules(m, [previous_name, name], inplace=True)
-
-        prev_previous_type = previous_type
-        prev_previous_name = previous_name
-        previous_type = type(module)
-        previous_name = name
\ No newline at end of file
diff --git a/spaces/vaishanthr/Simultaneous-Segmented-Depth-Prediction/yolov8/docs/modes/track.md b/spaces/vaishanthr/Simultaneous-Segmented-Depth-Prediction/yolov8/docs/modes/track.md
deleted file mode 100644
index 7b9a83a714bcb26500fd914f272f3788fa799eaf..0000000000000000000000000000000000000000
--- a/spaces/vaishanthr/Simultaneous-Segmented-Depth-Prediction/yolov8/docs/modes/track.md
+++ /dev/null
@@ -1,101 +0,0 @@
----
-comments: true
-description: Explore YOLOv8n-based object tracking with Ultralytics' BoT-SORT and ByteTrack. Learn configuration, usage, and customization tips.
-keywords: object tracking, YOLO, trackers, BoT-SORT, ByteTrack
----
-
-<img width="1024" src="https://user-images.githubusercontent.com/26833433/243418637-1d6250fd-1515-4c10-a844-a32818ae6d46.png">
-
-Object tracking is a task that involves identifying the location and class of objects, then assigning a unique ID to
-that detection in video streams.
-
-The output of tracker is the same as detection with an added object ID.
-
-## Available Trackers
-
-The following tracking algorithms have been implemented and can be enabled by passing `tracker=tracker_type.yaml`
-
-* [BoT-SORT](https://github.com/NirAharon/BoT-SORT) - `botsort.yaml`
-* [ByteTrack](https://github.com/ifzhang/ByteTrack) - `bytetrack.yaml`
-
-The default tracker is BoT-SORT.
-
-## Tracking
-
-Use a trained YOLOv8n/YOLOv8n-seg model to run tracker on video streams.
-
-!!! example ""
-
-    === "Python"
-    
-        ```python
-        from ultralytics import YOLO
-        
-        # Load a model
-        model = YOLO('yolov8n.pt')  # load an official detection model
-        model = YOLO('yolov8n-seg.pt')  # load an official segmentation model
-        model = YOLO('path/to/best.pt')  # load a custom model
-        
-        # Track with the model
-        results = model.track(source="https://youtu.be/Zgi9g1ksQHc", show=True) 
-        results = model.track(source="https://youtu.be/Zgi9g1ksQHc", show=True, tracker="bytetrack.yaml") 
-        ```
-    === "CLI"
-    
-        ```bash
-        yolo track model=yolov8n.pt source="https://youtu.be/Zgi9g1ksQHc"  # official detection model
-        yolo track model=yolov8n-seg.pt source=...   # official segmentation model
-        yolo track model=path/to/best.pt source=...  # custom model
-        yolo track model=path/to/best.pt  tracker="bytetrack.yaml" # bytetrack tracker
-
-        ```
-
-As in the above usage, we support both the detection and segmentation models for tracking and the only thing you need to
-do is loading the corresponding (detection or segmentation) model.
-
-## Configuration
-
-### Tracking
-
-Tracking shares the configuration with predict, i.e `conf`, `iou`, `show`. More configurations please refer
-to [predict page](https://docs.ultralytics.com/modes/predict/).
-!!! example ""
-
-    === "Python"
-    
-        ```python
-        from ultralytics import YOLO
-        
-        model = YOLO('yolov8n.pt')
-        results = model.track(source="https://youtu.be/Zgi9g1ksQHc", conf=0.3, iou=0.5, show=True) 
-        ```
-    === "CLI"
-    
-        ```bash
-        yolo track model=yolov8n.pt source="https://youtu.be/Zgi9g1ksQHc" conf=0.3, iou=0.5 show
-
-        ```
-
-### Tracker
-
-We also support using a modified tracker config file, just copy a config file i.e `custom_tracker.yaml`
-from [ultralytics/tracker/cfg](https://github.com/ultralytics/ultralytics/tree/main/ultralytics/tracker/cfg) and modify
-any configurations(expect the `tracker_type`) you need to.
-!!! example ""
-
-    === "Python"
-    
-        ```python
-        from ultralytics import YOLO
-        
-        model = YOLO('yolov8n.pt')
-        results = model.track(source="https://youtu.be/Zgi9g1ksQHc", tracker='custom_tracker.yaml') 
-        ```
-    === "CLI"
-    
-        ```bash
-        yolo track model=yolov8n.pt source="https://youtu.be/Zgi9g1ksQHc" tracker='custom_tracker.yaml'
-        ```
-
-Please refer to [ultralytics/tracker/cfg](https://github.com/ultralytics/ultralytics/tree/main/ultralytics/tracker/cfg)
-page
\ No newline at end of file
diff --git a/spaces/vaishanthr/Simultaneous-Segmented-Depth-Prediction/yolov8/docs/reference/yolo/engine/results.md b/spaces/vaishanthr/Simultaneous-Segmented-Depth-Prediction/yolov8/docs/reference/yolo/engine/results.md
deleted file mode 100644
index 38e568fa61024b35a511c37474869eaf0c336967..0000000000000000000000000000000000000000
--- a/spaces/vaishanthr/Simultaneous-Segmented-Depth-Prediction/yolov8/docs/reference/yolo/engine/results.md
+++ /dev/null
@@ -1,34 +0,0 @@
----
-description: Learn about BaseTensor & Boxes in Ultralytics YOLO Engine. Check out Ultralytics Docs for quality tutorials and resources on object detection.
-keywords: YOLO, Engine, Results, Masks, Probs, Ultralytics
----
-
-## BaseTensor
----
-### ::: ultralytics.yolo.engine.results.BaseTensor
-<br><br>
-
-## Results
----
-### ::: ultralytics.yolo.engine.results.Results
-<br><br>
-
-## Boxes
----
-### ::: ultralytics.yolo.engine.results.Boxes
-<br><br>
-
-## Masks
----
-### ::: ultralytics.yolo.engine.results.Masks
-<br><br>
-
-## Keypoints
----
-### ::: ultralytics.yolo.engine.results.Keypoints
-<br><br>
-
-## Probs
----
-### ::: ultralytics.yolo.engine.results.Probs
-<br><br>
diff --git a/spaces/vinthony/SadTalker/src/face3d/options/train_options.py b/spaces/vinthony/SadTalker/src/face3d/options/train_options.py
deleted file mode 100644
index 1337bfdd5f372b5c686a91b394a2aadbe5741f44..0000000000000000000000000000000000000000
--- a/spaces/vinthony/SadTalker/src/face3d/options/train_options.py
+++ /dev/null
@@ -1,53 +0,0 @@
-"""This script contains the training options for Deep3DFaceRecon_pytorch
-"""
-
-from .base_options import BaseOptions
-from util import util
-
-class TrainOptions(BaseOptions):
-    """This class includes training options.
-
-    It also includes shared options defined in BaseOptions.
-    """
-
-    def initialize(self, parser):
-        parser = BaseOptions.initialize(self, parser)
-        # dataset parameters
-        # for train
-        parser.add_argument('--data_root', type=str, default='./', help='dataset root')
-        parser.add_argument('--flist', type=str, default='datalist/train/masks.txt', help='list of mask names of training set')
-        parser.add_argument('--batch_size', type=int, default=32)
-        parser.add_argument('--dataset_mode', type=str, default='flist', help='chooses how datasets are loaded. [None | flist]')
-        parser.add_argument('--serial_batches', action='store_true', help='if true, takes images in order to make batches, otherwise takes them randomly')
-        parser.add_argument('--num_threads', default=4, type=int, help='# threads for loading data')
-        parser.add_argument('--max_dataset_size', type=int, default=float("inf"), help='Maximum number of samples allowed per dataset. If the dataset directory contains more than max_dataset_size, only a subset is loaded.')
-        parser.add_argument('--preprocess', type=str, default='shift_scale_rot_flip', help='scaling and cropping of images at load time [shift_scale_rot_flip | shift_scale | shift | shift_rot_flip ]')
-        parser.add_argument('--use_aug', type=util.str2bool, nargs='?', const=True, default=True, help='whether use data augmentation')
-
-        # for val
-        parser.add_argument('--flist_val', type=str, default='datalist/val/masks.txt', help='list of mask names of val set')
-        parser.add_argument('--batch_size_val', type=int, default=32)
-
-
-        # visualization parameters
-        parser.add_argument('--display_freq', type=int, default=1000, help='frequency of showing training results on screen')
-        parser.add_argument('--print_freq', type=int, default=100, help='frequency of showing training results on console')
-        
-        # network saving and loading parameters
-        parser.add_argument('--save_latest_freq', type=int, default=5000, help='frequency of saving the latest results')
-        parser.add_argument('--save_epoch_freq', type=int, default=1, help='frequency of saving checkpoints at the end of epochs')
-        parser.add_argument('--evaluation_freq', type=int, default=5000, help='evaluation freq')
-        parser.add_argument('--save_by_iter', action='store_true', help='whether saves model by iteration')
-        parser.add_argument('--continue_train', action='store_true', help='continue training: load the latest model')
-        parser.add_argument('--epoch_count', type=int, default=1, help='the starting epoch count, we save the model by <epoch_count>, <epoch_count>+<save_latest_freq>, ...')
-        parser.add_argument('--phase', type=str, default='train', help='train, val, test, etc')
-        parser.add_argument('--pretrained_name', type=str, default=None, help='resume training from another checkpoint')
-
-        # training parameters
-        parser.add_argument('--n_epochs', type=int, default=20, help='number of epochs with the initial learning rate')
-        parser.add_argument('--lr', type=float, default=0.0001, help='initial learning rate for adam')
-        parser.add_argument('--lr_policy', type=str, default='step', help='learning rate policy. [linear | step | plateau | cosine]')
-        parser.add_argument('--lr_decay_epochs', type=int, default=10, help='multiply by a gamma every lr_decay_epochs epoches')
-
-        self.isTrain = True
-        return parser
diff --git a/spaces/vumichien/canvas_controlnet/ldm/modules/distributions/distributions.py b/spaces/vumichien/canvas_controlnet/ldm/modules/distributions/distributions.py
deleted file mode 100644
index f2b8ef901130efc171aa69742ca0244d94d3f2e9..0000000000000000000000000000000000000000
--- a/spaces/vumichien/canvas_controlnet/ldm/modules/distributions/distributions.py
+++ /dev/null
@@ -1,92 +0,0 @@
-import torch
-import numpy as np
-
-
-class AbstractDistribution:
-    def sample(self):
-        raise NotImplementedError()
-
-    def mode(self):
-        raise NotImplementedError()
-
-
-class DiracDistribution(AbstractDistribution):
-    def __init__(self, value):
-        self.value = value
-
-    def sample(self):
-        return self.value
-
-    def mode(self):
-        return self.value
-
-
-class DiagonalGaussianDistribution(object):
-    def __init__(self, parameters, deterministic=False):
-        self.parameters = parameters
-        self.mean, self.logvar = torch.chunk(parameters, 2, dim=1)
-        self.logvar = torch.clamp(self.logvar, -30.0, 20.0)
-        self.deterministic = deterministic
-        self.std = torch.exp(0.5 * self.logvar)
-        self.var = torch.exp(self.logvar)
-        if self.deterministic:
-            self.var = self.std = torch.zeros_like(self.mean).to(device=self.parameters.device)
-
-    def sample(self):
-        x = self.mean + self.std * torch.randn(self.mean.shape).to(device=self.parameters.device)
-        return x
-
-    def kl(self, other=None):
-        if self.deterministic:
-            return torch.Tensor([0.])
-        else:
-            if other is None:
-                return 0.5 * torch.sum(torch.pow(self.mean, 2)
-                                       + self.var - 1.0 - self.logvar,
-                                       dim=[1, 2, 3])
-            else:
-                return 0.5 * torch.sum(
-                    torch.pow(self.mean - other.mean, 2) / other.var
-                    + self.var / other.var - 1.0 - self.logvar + other.logvar,
-                    dim=[1, 2, 3])
-
-    def nll(self, sample, dims=[1,2,3]):
-        if self.deterministic:
-            return torch.Tensor([0.])
-        logtwopi = np.log(2.0 * np.pi)
-        return 0.5 * torch.sum(
-            logtwopi + self.logvar + torch.pow(sample - self.mean, 2) / self.var,
-            dim=dims)
-
-    def mode(self):
-        return self.mean
-
-
-def normal_kl(mean1, logvar1, mean2, logvar2):
-    """
-    source: https://github.com/openai/guided-diffusion/blob/27c20a8fab9cb472df5d6bdd6c8d11c8f430b924/guided_diffusion/losses.py#L12
-    Compute the KL divergence between two gaussians.
-    Shapes are automatically broadcasted, so batches can be compared to
-    scalars, among other use cases.
-    """
-    tensor = None
-    for obj in (mean1, logvar1, mean2, logvar2):
-        if isinstance(obj, torch.Tensor):
-            tensor = obj
-            break
-    assert tensor is not None, "at least one argument must be a Tensor"
-
-    # Force variances to be Tensors. Broadcasting helps convert scalars to
-    # Tensors, but it does not work for torch.exp().
-    logvar1, logvar2 = [
-        x if isinstance(x, torch.Tensor) else torch.tensor(x).to(tensor)
-        for x in (logvar1, logvar2)
-    ]
-
-    return 0.5 * (
-        -1.0
-        + logvar2
-        - logvar1
-        + torch.exp(logvar1 - logvar2)
-        + ((mean1 - mean2) ** 2) * torch.exp(-logvar2)
-    )
diff --git "a/spaces/wangrongsheng/ChatImprovement/crazy_functions/\350\247\243\346\236\220\351\241\271\347\233\256\346\272\220\344\273\243\347\240\201.py" "b/spaces/wangrongsheng/ChatImprovement/crazy_functions/\350\247\243\346\236\220\351\241\271\347\233\256\346\272\220\344\273\243\347\240\201.py"
deleted file mode 100644
index 41bdebb754ec38391732a5dfafbfe8ee78359f25..0000000000000000000000000000000000000000
--- "a/spaces/wangrongsheng/ChatImprovement/crazy_functions/\350\247\243\346\236\220\351\241\271\347\233\256\346\272\220\344\273\243\347\240\201.py"
+++ /dev/null
@@ -1,129 +0,0 @@
-from predict import predict_no_ui
-from toolbox import CatchException, report_execption, write_results_to_file, predict_no_ui_but_counting_down
-fast_debug = False
-
-def 解析源代码(file_manifest, project_folder, top_p, temperature, chatbot, history, systemPromptTxt):
-    import time, glob, os
-    print('begin analysis on:', file_manifest)
-    for index, fp in enumerate(file_manifest):
-        with open(fp, 'r', encoding='utf-8') as f:
-            file_content = f.read()
-
-        前言 = "接下来请你逐文件分析下面的工程" if index==0 else ""
-        i_say = 前言 + f'请对下面的程序文件做一个概述文件名是{os.path.relpath(fp, project_folder)}，文件代码是 ```{file_content}```'
-        i_say_show_user = 前言 + f'[{index}/{len(file_manifest)}] 请对下面的程序文件做一个概述: {os.path.abspath(fp)}'
-        chatbot.append((i_say_show_user, "[Local Message] waiting gpt response."))
-        yield chatbot, history, '正常'
-
-        if not fast_debug: 
-            msg = '正常'
-
-            # ** gpt request **
-            gpt_say = yield from predict_no_ui_but_counting_down(i_say, i_say_show_user, chatbot, top_p, temperature, history=[])   # 带超时倒计时
-
-            chatbot[-1] = (i_say_show_user, gpt_say)
-            history.append(i_say_show_user); history.append(gpt_say)
-            yield chatbot, history, msg
-            if not fast_debug: time.sleep(2)
-
-    all_file = ', '.join([os.path.relpath(fp, project_folder) for index, fp in enumerate(file_manifest)])
-    i_say = f'根据以上你自己的分析，对程序的整体功能和构架做出概括。然后用一张markdown表格整理每个文件的功能（包括{all_file}）。'
-    chatbot.append((i_say, "[Local Message] waiting gpt response."))
-    yield chatbot, history, '正常'
-
-    if not fast_debug: 
-        msg = '正常'
-        # ** gpt request **
-        gpt_say = yield from predict_no_ui_but_counting_down(i_say, i_say, chatbot, top_p, temperature, history=history)   # 带超时倒计时
-        
-        chatbot[-1] = (i_say, gpt_say)
-        history.append(i_say); history.append(gpt_say)
-        yield chatbot, history, msg
-        res = write_results_to_file(history)
-        chatbot.append(("完成了吗？", res))
-        yield chatbot, history, msg
-
-
-
-
-@CatchException
-def 解析项目本身(txt, top_p, temperature, chatbot, history, systemPromptTxt, WEB_PORT):
-    history = []    # 清空历史，以免输入溢出
-    import time, glob, os
-    file_manifest = [f for f in glob.glob('*.py')]
-    for index, fp in enumerate(file_manifest):
-        # if 'test_project' in fp: continue
-        with open(fp, 'r', encoding='utf-8') as f:
-            file_content = f.read()
-
-        前言 = "接下来请你分析自己的程序构成，别紧张，" if index==0 else ""
-        i_say = 前言 + f'请对下面的程序文件做一个概述文件名是{fp}，文件代码是 ```{file_content}```'
-        i_say_show_user = 前言 + f'[{index}/{len(file_manifest)}] 请对下面的程序文件做一个概述: {os.path.abspath(fp)}'
-        chatbot.append((i_say_show_user, "[Local Message] waiting gpt response."))
-        yield chatbot, history, '正常'
-
-        if not fast_debug: 
-            # ** gpt request **
-            # gpt_say = predict_no_ui(inputs=i_say, top_p=top_p, temperature=temperature)
-            gpt_say = yield from predict_no_ui_but_counting_down(i_say, i_say_show_user, chatbot, top_p, temperature, history=[])   # 带超时倒计时
-
-            chatbot[-1] = (i_say_show_user, gpt_say)
-            history.append(i_say_show_user); history.append(gpt_say)
-            yield chatbot, history, '正常'
-            time.sleep(2)
-
-    i_say = f'根据以上你自己的分析，对程序的整体功能和构架做出概括。然后用一张markdown表格整理每个文件的功能（包括{file_manifest}）。'
-    chatbot.append((i_say, "[Local Message] waiting gpt response."))
-    yield chatbot, history, '正常'
-
-    if not fast_debug: 
-        # ** gpt request **
-        # gpt_say = predict_no_ui(inputs=i_say, top_p=top_p, temperature=temperature, history=history)
-        gpt_say = yield from predict_no_ui_but_counting_down(i_say, i_say, chatbot, top_p, temperature, history=history)   # 带超时倒计时
-
-        chatbot[-1] = (i_say, gpt_say)
-        history.append(i_say); history.append(gpt_say)
-        yield chatbot, history, '正常'
-        res = write_results_to_file(history)
-        chatbot.append(("完成了吗？", res))
-        yield chatbot, history, '正常'
-
-@CatchException
-def 解析一个Python项目(txt, top_p, temperature, chatbot, history, systemPromptTxt, WEB_PORT):
-    history = []    # 清空历史，以免输入溢出
-    import glob, os
-    if os.path.exists(txt):
-        project_folder = txt
-    else:
-        if txt == "": txt = '空空如也的输入栏'
-        report_execption(chatbot, history, a = f"解析项目: {txt}", b = f"找不到本地项目或无权访问: {txt}")
-        yield chatbot, history, '正常'
-        return
-    file_manifest = [f for f in glob.glob(f'{project_folder}/**/*.py', recursive=True)]
-    if len(file_manifest) == 0:
-        report_execption(chatbot, history, a = f"解析项目: {txt}", b = f"找不到任何python文件: {txt}")
-        yield chatbot, history, '正常'
-        return
-    yield from 解析源代码(file_manifest, project_folder, top_p, temperature, chatbot, history, systemPromptTxt)
-
-
-@CatchException
-def 解析一个C项目的头文件(txt, top_p, temperature, chatbot, history, systemPromptTxt, WEB_PORT):
-    history = []    # 清空历史，以免输入溢出
-    import glob, os
-    if os.path.exists(txt):
-        project_folder = txt
-    else:
-        if txt == "": txt = '空空如也的输入栏'
-        report_execption(chatbot, history, a = f"解析项目: {txt}", b = f"找不到本地项目或无权访问: {txt}")
-        yield chatbot, history, '正常'
-        return
-    file_manifest = [f for f in glob.glob(f'{project_folder}/**/*.h', recursive=True)] # + \
-                    # [f for f in glob.glob(f'{project_folder}/**/*.cpp', recursive=True)] + \
-                    # [f for f in glob.glob(f'{project_folder}/**/*.c', recursive=True)]
-    if len(file_manifest) == 0:
-        report_execption(chatbot, history, a = f"解析项目: {txt}", b = f"找不到任何.h头文件: {txt}")
-        yield chatbot, history, '正常'
-        return
-    yield from 解析源代码(file_manifest, project_folder, top_p, temperature, chatbot, history, systemPromptTxt)
-
diff --git a/spaces/whgwd2023/bingo/src/components/ui/voice/index.tsx b/spaces/whgwd2023/bingo/src/components/ui/voice/index.tsx
deleted file mode 100644
index 4adcb632226bfced8b97092782811edf08b56569..0000000000000000000000000000000000000000
--- a/spaces/whgwd2023/bingo/src/components/ui/voice/index.tsx
+++ /dev/null
@@ -1,28 +0,0 @@
-import './index.scss'
-
-export interface VoiceProps extends CSSPropertyRule {
-  num?: number;
-  duration?: number;
-}
-export default function Voice({ duration = 400, num = 7, ...others }) {
-  return (
-    <div className="voice-button" { ...others }>
-      {Array.from({ length: num }).map((_, index) => {
-        const randomDuration = Math.random() * 100 + duration
-        const initialDelay = Math.random() * 2 * duration
-        const initialScale = Math.sin((index + 1) * Math.PI / num)
-        return (
-          <div
-            className="voice-button-item"
-            key={index}
-            style={{
-              animationDelay: initialDelay + 'ms',
-              animationDuration: randomDuration + 'ms',
-              transform: `scale(${initialScale})`
-            }}
-          />
-        )
-      })}
-    </div>
-  )
-}
diff --git a/spaces/williamcfrancis/Deep-Blind-Motion-Deblurring/sidekick/prepro/__init__.py b/spaces/williamcfrancis/Deep-Blind-Motion-Deblurring/sidekick/prepro/__init__.py
deleted file mode 100644
index b1755a5e42616aa194b7f9f111cf0a0e113767f5..0000000000000000000000000000000000000000
--- a/spaces/williamcfrancis/Deep-Blind-Motion-Deblurring/sidekick/prepro/__init__.py
+++ /dev/null
@@ -1,4 +0,0 @@
-from .process import Process
-from .meanprocess import MeanProcess
-from .aspectprocess import AspectProcess
-from .imgtoarrayprepro import ImgtoArrPrePro
diff --git a/spaces/windowcleaningtoronto/README/README.md b/spaces/windowcleaningtoronto/README/README.md
deleted file mode 100644
index 6bb51b2340d7f46ba0ce0f5988c0fa535a3a5823..0000000000000000000000000000000000000000
--- a/spaces/windowcleaningtoronto/README/README.md
+++ /dev/null
@@ -1,37 +0,0 @@
----
-title: Northern Touch Window Cleaning Toronto
-emoji: 📉
-colorFrom: green
-colorTo: green
-sdk: static
-pinned: false
----
-
-Northern Touch Window Cleaning is a professional [Toronto window cleaning](https://ntpropertycare.com/window-cleaning-toronto/)  and maintenance company serving Toronto, GTA and surrounding areas.    
-
-We are the industry leaders in window cleaning and property maintenance. We believe every customer deserves the best!    
-
-When you’re looking for a quality and reliable window and eaves cleaning company in Toronto and the GTA look no further than Northern Touch Window Cleaning. Your trusted leaders in window cleaning and property maintenance.    
-
-We take pride in high-­end delicate work and are dedicated to providing superior customer satisfaction that will leave even our most demanding customers satisfied. We are a fully insured company with an up to date WSIB record (Workplace Safety and Insurance Board) and have full liability insurance that covers you in the event of an accident, whether to a worker, your home or you. Here at Northern Touch Window Cleaning safety is of our top priority and the peace of mind of our customers knowing that when they hire us. Call or email us today and experience our Window Cleaning Toronto by Northern Touch.    
-
-##Areas We Serve within Ontario    
-*    [window cleaning mississauga](https://ntpropertycare.com/window-cleaning-mississauga/)   
-*    [etobicoke](https://ntpropertycare.com/window-cleaning-etobicoke/)   
-*    [scarborough](https://ntpropertycare.com/window-cleaning-scarborough/)    
-*    [brampton](https://ntpropertycare.com/window-cleaning-brampton/)    
-*    [north york](https://ntpropertycare.com/window-cleaning-north-york/)    
-*    [vaughan](https://ntpropertycare.com/commercial-window-cleaning-vaughan/)    
-*    [oakville](https://ntpropertycare.com/window-cleaning-oakville/)    
-*    [woodbridge](https://ntpropertycare.com/window-cleaning-woodbridge/)    
-*    [richmond hill](https://ntpropertycare.com/window-cleaning-richmond-hill/)    
-*    [burlington](https://ntpropertycare.com/window-cleaning-burlington/)    
-*    [newmarket](https://ntpropertycare.com/window-cleaning-newmarket/)    
-*    [london](https://ntpropertycare.com/window-cleaning-london/)    
-*    [caledon](https://ntpropertycare.com/window-cleaning-caledon/)    
-*    [barrie](https://ntpropertycare.com/window-cleaning-barrie/)    
-*    [thornhill](https://ntpropertycare.com/window-cleaning-thornhill-on/)    
-*    [kitchener](https://ntpropertycare.com/window-cleaning-kitchener/)    
-*    [milton](https://ntpropertycare.com/window-cleaning-milton/)    
-*    [pickering](https://ntpropertycare.com/window-cleaning-pickering/)    
- 
diff --git a/spaces/wiwide/40bqa/app.py b/spaces/wiwide/40bqa/app.py
deleted file mode 100644
index ec1b07e79f911ed4eb2fdef70d2d6a425373f101..0000000000000000000000000000000000000000
--- a/spaces/wiwide/40bqa/app.py
+++ /dev/null
@@ -1,26 +0,0 @@
-import requests
-from bs4 import BeautifulSoup
-from transformers import pipeline
-import gradio as gr
-
-def get_web_page(url):
-    response = requests.get(url)
-    soup = BeautifulSoup(response.text, 'html.parser')
-    return soup.text
-
-def answer_question(question, context):
-    qa_pipeline = pipeline("question-answering", model="tiiuae/falcon-40b")
-    result = qa_pipeline({
-        'context': context,
-        'question': question
-    })
-    return result['answer']
-
-def app(symbol, question):
-    url = f"https://finance.yahoo.com/quote/{symbol}"
-    context = get_web_page(url)
-    answer = answer_question(question, context)
-    return answer
-
-iface = gr.Interface(fn=app, inputs=["text", "text"], outputs="text")
-iface.launch()
diff --git a/spaces/wuhuik/bingo/src/components/chat-image.tsx b/spaces/wuhuik/bingo/src/components/chat-image.tsx
deleted file mode 100644
index 05ecc9771eada27a0f2d160bb01cba170d37bb09..0000000000000000000000000000000000000000
--- a/spaces/wuhuik/bingo/src/components/chat-image.tsx
+++ /dev/null
@@ -1,170 +0,0 @@
-import {
-  useEffect,
-  useState,
-  useCallback,
-  ChangeEvent,
-  ClipboardEvent,
-  MouseEventHandler,
-  FormEvent,
-  useRef
-} from "react"
-import Image from 'next/image'
-import PasteIcon from '@/assets/images/paste.svg'
-import UploadIcon from '@/assets/images/upload.svg'
-import CameraIcon from '@/assets/images/camera.svg'
-import { useBing } from '@/lib/hooks/use-bing'
-import { cn } from '@/lib/utils'
-
-interface ChatImageProps extends Pick<ReturnType<typeof useBing>, 'uploadImage'> {}
-
-const preventDefault: MouseEventHandler<HTMLDivElement> = (event) => {
-  event.nativeEvent.stopImmediatePropagation()
-}
-
-const toBase64 = (file: File): Promise<string> => new Promise((resolve, reject) => {
-  const reader = new FileReader()
-  reader.readAsDataURL(file)
-  reader.onload = () => resolve(reader.result as string)
-  reader.onerror = reject
-})
-
-export function ChatImage({ children, uploadImage }: React.PropsWithChildren<ChatImageProps>) {
-  const videoRef = useRef<HTMLVideoElement>(null)
-  const canvasRef = useRef<HTMLCanvasElement>(null)
-  const mediaStream = useRef<MediaStream>()
-  const [panel, setPanel] = useState('none')
-
-  const upload = useCallback((url: string) => {
-    if (url) {
-      uploadImage(url)
-    }
-    setPanel('none')
-  }, [panel])
-
-  const onUpload = useCallback(async (event: ChangeEvent<HTMLInputElement>) => {
-    const file = event.target.files?.[0]
-    if (file) {
-      const fileDataUrl = await toBase64(file)
-      if (fileDataUrl) {
-        upload(fileDataUrl)
-      }
-    }
-  }, [])
-
-  const onPaste = useCallback((event: ClipboardEvent<HTMLInputElement>) => {
-    const pasteUrl = event.clipboardData.getData('text') ?? ''
-    upload(pasteUrl)
-  }, [])
-
-  const onEnter = useCallback((event: FormEvent<HTMLFormElement>) => {
-    event.preventDefault()
-    event.stopPropagation()
-    // @ts-ignore
-    const inputUrl = event.target.elements.image.value
-    if (inputUrl) {
-      upload(inputUrl)
-    }
-  }, [])
-
-  const openVideo: MouseEventHandler<HTMLButtonElement> = async (event) => {
-    event.stopPropagation()
-    setPanel('camera-mode')
-  }
-
-  const onCapture = () => {
-    if (canvasRef.current && videoRef.current) {
-      const canvas = canvasRef.current
-      canvas.width = videoRef.current!.videoWidth
-      canvas.height = videoRef.current!.videoHeight
-      canvas.getContext('2d')?.drawImage(videoRef.current, 0, 0, canvas.width, canvas.height)
-      const cameraUrl = canvas.toDataURL('image/jpeg')
-      upload(cameraUrl)
-    }
-  }
-
-  useEffect(() => {
-    const handleBlur = () => {
-      if (panel !== 'none') {
-        setPanel('none')
-      }
-    }
-    document.addEventListener('click', handleBlur)
-    return () => {
-      document.removeEventListener('click', handleBlur)
-    }
-  }, [panel])
-
-  useEffect(() => {
-    if (panel === 'camera-mode') {
-      navigator.mediaDevices.getUserMedia({ video: true, audio: false })
-      .then(videoStream => {
-        mediaStream.current = videoStream
-        if (videoRef.current) {
-          videoRef.current.srcObject = videoStream
-        }
-      })
-    } else {
-      if (mediaStream.current) {
-        mediaStream.current.getTracks().forEach(function(track) {
-          track.stop()
-        })
-        mediaStream.current = undefined
-      }
-    }
-  }, [panel])
-
-  return (
-    <div className="visual-search-container">
-      <div onClick={() => panel === 'none' ? setPanel('normal') : setPanel('none')}>{children}</div>
-      <div className={cn('visual-search', panel)} onClick={preventDefault}>
-        <div className="normal-content">
-          <div className="header">
-            <h4>添加图像</h4>
-          </div>
-          <div className="paste">
-            <Image alt="paste" src={PasteIcon} width={24} />
-            <form onSubmitCapture={onEnter}>
-              <input
-                className="paste-input"
-                id="sb_imgpst"
-                type="text"
-                name="image"
-                placeholder="粘贴图像 URL"
-                aria-label="粘贴图像 URL"
-                onPaste={onPaste}
-                onClickCapture={(e) => e.stopPropagation()}
-              />
-            </form>
-          </div>
-          <div className="buttons">
-            <button type="button" aria-label="从此设备上传">
-              <input
-                id="vs_fileinput"
-                className="fileinput"
-                type="file"
-                accept="image/gif, image/jpeg, image/png, image/webp"
-                onChange={onUpload}
-              />
-              <Image alt="uplaod" src={UploadIcon} width={20} />
-              从此设备上传
-            </button>
-            <button type="button" aria-label="拍照" onClick={openVideo}>
-              <Image alt="camera" src={CameraIcon} width={20} />
-              拍照
-            </button>
-          </div>
-        </div>
-        {panel === 'camera-mode' && <div className="cam-content">
-          <div className="webvideo-container">
-            <video className="webvideo" autoPlay muted playsInline ref={videoRef} />
-            <canvas className="webcanvas" ref={canvasRef} />
-          </div>
-          <div className="cambtn" role="button" aria-label="拍照" onClick={onCapture}>
-            <div className="cam-btn-circle-large"></div>
-            <div className="cam-btn-circle-small"></div>
-          </div>
-        </div>}
-      </div>
-    </div>
-  )
-}
diff --git a/spaces/xiaorong/fork2-so-vits/utils.py b/spaces/xiaorong/fork2-so-vits/utils.py
deleted file mode 100644
index ee4b01ddfbe8173965371b29f770f3e87615fe71..0000000000000000000000000000000000000000
--- a/spaces/xiaorong/fork2-so-vits/utils.py
+++ /dev/null
@@ -1,225 +0,0 @@
-import os
-import sys
-import argparse
-import logging
-import json
-import subprocess
-import numpy as np
-import librosa
-import torch
-
-MATPLOTLIB_FLAG = False
-
-logging.basicConfig(stream=sys.stdout, level=logging.DEBUG)
-logger = logging
-
-
-def load_checkpoint(checkpoint_path, model, optimizer=None):
-  assert os.path.isfile(checkpoint_path)
-  checkpoint_dict = torch.load(checkpoint_path, map_location='cpu')
-  iteration = checkpoint_dict['iteration']
-  learning_rate = checkpoint_dict['learning_rate']
-  if optimizer is not None:
-    optimizer.load_state_dict(checkpoint_dict['optimizer'])
-  saved_state_dict = checkpoint_dict['model']
-  if hasattr(model, 'module'):
-    state_dict = model.module.state_dict()
-  else:
-    state_dict = model.state_dict()
-  new_state_dict= {}
-  for k, v in state_dict.items():
-    try:
-      new_state_dict[k] = saved_state_dict[k]
-    except:
-      logger.info("%s is not in the checkpoint" % k)
-      new_state_dict[k] = v
-  if hasattr(model, 'module'):
-    model.module.load_state_dict(new_state_dict)
-  else:
-    model.load_state_dict(new_state_dict)
-  logger.info("Loaded checkpoint '{}' (iteration {})" .format(
-    checkpoint_path, iteration))
-  return model, optimizer, learning_rate, iteration
-
-
-def plot_spectrogram_to_numpy(spectrogram):
-  global MATPLOTLIB_FLAG
-  if not MATPLOTLIB_FLAG:
-    import matplotlib
-    matplotlib.use("Agg")
-    MATPLOTLIB_FLAG = True
-    mpl_logger = logging.getLogger('matplotlib')
-    mpl_logger.setLevel(logging.WARNING)
-  import matplotlib.pylab as plt
-  import numpy as np
-
-  fig, ax = plt.subplots(figsize=(10,2))
-  im = ax.imshow(spectrogram, aspect="auto", origin="lower",
-                  interpolation='none')
-  plt.colorbar(im, ax=ax)
-  plt.xlabel("Frames")
-  plt.ylabel("Channels")
-  plt.tight_layout()
-
-  fig.canvas.draw()
-  data = np.fromstring(fig.canvas.tostring_rgb(), dtype=np.uint8, sep='')
-  data = data.reshape(fig.canvas.get_width_height()[::-1] + (3,))
-  plt.close()
-  return data
-
-
-def plot_alignment_to_numpy(alignment, info=None):
-  global MATPLOTLIB_FLAG
-  if not MATPLOTLIB_FLAG:
-    import matplotlib
-    matplotlib.use("Agg")
-    MATPLOTLIB_FLAG = True
-    mpl_logger = logging.getLogger('matplotlib')
-    mpl_logger.setLevel(logging.WARNING)
-  import matplotlib.pylab as plt
-  import numpy as np
-
-  fig, ax = plt.subplots(figsize=(6, 4))
-  im = ax.imshow(alignment.transpose(), aspect='auto', origin='lower',
-                  interpolation='none')
-  fig.colorbar(im, ax=ax)
-  xlabel = 'Decoder timestep'
-  if info is not None:
-      xlabel += '\n\n' + info
-  plt.xlabel(xlabel)
-  plt.ylabel('Encoder timestep')
-  plt.tight_layout()
-
-  fig.canvas.draw()
-  data = np.fromstring(fig.canvas.tostring_rgb(), dtype=np.uint8, sep='')
-  data = data.reshape(fig.canvas.get_width_height()[::-1] + (3,))
-  plt.close()
-  return data
-
-
-def load_audio_to_torch(full_path, target_sampling_rate):
-  audio, sampling_rate = librosa.load(full_path, sr=target_sampling_rate, mono=True)
-  return torch.FloatTensor(audio.astype(np.float32))
-
-
-def load_filepaths_and_text(filename, split="|"):
-  with open(filename, encoding='utf-8') as f:
-    filepaths_and_text = [line.strip().split(split) for line in f]
-  return filepaths_and_text
-
-
-def get_hparams(init=True):
-  parser = argparse.ArgumentParser()
-  parser.add_argument('-c', '--config', type=str, default="./configs/base.json",
-                      help='JSON file for configuration')
-  parser.add_argument('-m', '--model', type=str, required=True,
-                      help='Model name')
-
-  args = parser.parse_args()
-  model_dir = os.path.join("./logs", args.model)
-
-  if not os.path.exists(model_dir):
-    os.makedirs(model_dir)
-
-  config_path = args.config
-  config_save_path = os.path.join(model_dir, "config.json")
-  if init:
-    with open(config_path, "r") as f:
-      data = f.read()
-    with open(config_save_path, "w") as f:
-      f.write(data)
-  else:
-    with open(config_save_path, "r") as f:
-      data = f.read()
-  config = json.loads(data)
-
-  hparams = HParams(**config)
-  hparams.model_dir = model_dir
-  return hparams
-
-
-def get_hparams_from_dir(model_dir):
-  config_save_path = os.path.join(model_dir, "config.json")
-  with open(config_save_path, "r") as f:
-    data = f.read()
-  config = json.loads(data)
-
-  hparams =HParams(**config)
-  hparams.model_dir = model_dir
-  return hparams
-
-
-def get_hparams_from_file(config_path):
-  with open(config_path, "r") as f:
-    data = f.read()
-  config = json.loads(data)
-
-  hparams =HParams(**config)
-  return hparams
-
-
-def check_git_hash(model_dir):
-  source_dir = os.path.dirname(os.path.realpath(__file__))
-  if not os.path.exists(os.path.join(source_dir, ".git")):
-    logger.warn("{} is not a git repository, therefore hash value comparison will be ignored.".format(
-      source_dir
-    ))
-    return
-
-  cur_hash = subprocess.getoutput("git rev-parse HEAD")
-
-  path = os.path.join(model_dir, "githash")
-  if os.path.exists(path):
-    saved_hash = open(path).read()
-    if saved_hash != cur_hash:
-      logger.warn("git hash values are different. {}(saved) != {}(current)".format(
-        saved_hash[:8], cur_hash[:8]))
-  else:
-    open(path, "w").write(cur_hash)
-
-
-def get_logger(model_dir, filename="train.log"):
-  global logger
-  logger = logging.getLogger(os.path.basename(model_dir))
-  logger.setLevel(logging.DEBUG)
-
-  formatter = logging.Formatter("%(asctime)s\t%(name)s\t%(levelname)s\t%(message)s")
-  if not os.path.exists(model_dir):
-    os.makedirs(model_dir)
-  h = logging.FileHandler(os.path.join(model_dir, filename))
-  h.setLevel(logging.DEBUG)
-  h.setFormatter(formatter)
-  logger.addHandler(h)
-  return logger
-
-
-class HParams():
-  def __init__(self, **kwargs):
-    for k, v in kwargs.items():
-      if type(v) == dict:
-        v = HParams(**v)
-      self[k] = v
-
-  def keys(self):
-    return self.__dict__.keys()
-
-  def items(self):
-    return self.__dict__.items()
-
-  def values(self):
-    return self.__dict__.values()
-
-  def __len__(self):
-    return len(self.__dict__)
-
-  def __getitem__(self, key):
-    return getattr(self, key)
-
-  def __setitem__(self, key, value):
-    return setattr(self, key, value)
-
-  def __contains__(self, key):
-    return key in self.__dict__
-
-  def __repr__(self):
-    return self.__dict__.__repr__()
diff --git a/spaces/xswu/align_sd/README.md b/spaces/xswu/align_sd/README.md
deleted file mode 100644
index 40c5bea70687ad8499f34a57f85779ba8ddf7e7e..0000000000000000000000000000000000000000
--- a/spaces/xswu/align_sd/README.md
+++ /dev/null
@@ -1,13 +0,0 @@
----
-title: Align Sd
-emoji: 📊
-colorFrom: pink
-colorTo: indigo
-sdk: gradio
-sdk_version: 3.23.0
-app_file: app.py
-pinned: false
-license: cc-by-nc-nd-4.0
----
-
-Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
diff --git a/spaces/xxbb/VITS-Umamusume-voice-synthesizer/ONNXVITS_infer.py b/spaces/xxbb/VITS-Umamusume-voice-synthesizer/ONNXVITS_infer.py
deleted file mode 100644
index af04e614c8f1ac43faf363b1a9f6bfd667fbde21..0000000000000000000000000000000000000000
--- a/spaces/xxbb/VITS-Umamusume-voice-synthesizer/ONNXVITS_infer.py
+++ /dev/null
@@ -1,201 +0,0 @@
-import torch
-import commons
-import models
-
-import math
-from torch import nn
-from torch.nn import functional as F
-
-import modules
-import attentions
-
-from torch.nn import Conv1d, ConvTranspose1d, Conv2d
-from torch.nn.utils import weight_norm, remove_weight_norm, spectral_norm
-from commons import init_weights, get_padding
-
-
-class TextEncoder(nn.Module):
-  def __init__(self,
-               n_vocab,
-               out_channels,
-               hidden_channels,
-               filter_channels,
-               n_heads,
-               n_layers,
-               kernel_size,
-               p_dropout,
-               emotion_embedding):
-    super().__init__()
-    self.n_vocab = n_vocab
-    self.out_channels = out_channels
-    self.hidden_channels = hidden_channels
-    self.filter_channels = filter_channels
-    self.n_heads = n_heads
-    self.n_layers = n_layers
-    self.kernel_size = kernel_size
-    self.p_dropout = p_dropout
-    self.emotion_embedding = emotion_embedding
-
-    if self.n_vocab != 0:
-      self.emb = nn.Embedding(n_vocab, hidden_channels)
-      if emotion_embedding:
-        self.emo_proj = nn.Linear(1024, hidden_channels)
-      nn.init.normal_(self.emb.weight, 0.0, hidden_channels ** -0.5)
-
-    self.encoder = attentions.Encoder(
-      hidden_channels,
-      filter_channels,
-      n_heads,
-      n_layers,
-      kernel_size,
-      p_dropout)
-    self.proj = nn.Conv1d(hidden_channels, out_channels * 2, 1)
-
-  def forward(self, x, x_lengths, emotion_embedding=None):
-    if self.n_vocab != 0:
-      x = self.emb(x) * math.sqrt(self.hidden_channels)  # [b, t, h]
-    if emotion_embedding is not None:
-      print("emotion added")
-      x = x + self.emo_proj(emotion_embedding.unsqueeze(1))
-    x = torch.transpose(x, 1, -1)  # [b, h, t]
-    x_mask = torch.unsqueeze(commons.sequence_mask(x_lengths, x.size(2)), 1).to(x.dtype)
-
-    x = self.encoder(x * x_mask, x_mask)
-    stats = self.proj(x) * x_mask
-
-    m, logs = torch.split(stats, self.out_channels, dim=1)
-    return x, m, logs, x_mask
-
-
-class PosteriorEncoder(nn.Module):
-  def __init__(self,
-               in_channels,
-               out_channels,
-               hidden_channels,
-               kernel_size,
-               dilation_rate,
-               n_layers,
-               gin_channels=0):
-    super().__init__()
-    self.in_channels = in_channels
-    self.out_channels = out_channels
-    self.hidden_channels = hidden_channels
-    self.kernel_size = kernel_size
-    self.dilation_rate = dilation_rate
-    self.n_layers = n_layers
-    self.gin_channels = gin_channels
-
-    self.pre = nn.Conv1d(in_channels, hidden_channels, 1)
-    self.enc = modules.WN(hidden_channels, kernel_size, dilation_rate, n_layers, gin_channels=gin_channels)
-    self.proj = nn.Conv1d(hidden_channels, out_channels * 2, 1)
-
-  def forward(self, x, x_lengths, g=None):
-    x_mask = torch.unsqueeze(commons.sequence_mask(x_lengths, x.size(2)), 1).to(x.dtype)
-    x = self.pre(x) * x_mask
-    x = self.enc(x, x_mask, g=g)
-    stats = self.proj(x) * x_mask
-    m, logs = torch.split(stats, self.out_channels, dim=1)
-    z = (m + torch.randn_like(m) * torch.exp(logs)) * x_mask
-    return z, m, logs, x_mask
-
-
-class SynthesizerTrn(models.SynthesizerTrn):
-  """
-  Synthesizer for Training
-  """
-
-  def __init__(self,
-               n_vocab,
-               spec_channels,
-               segment_size,
-               inter_channels,
-               hidden_channels,
-               filter_channels,
-               n_heads,
-               n_layers,
-               kernel_size,
-               p_dropout,
-               resblock,
-               resblock_kernel_sizes,
-               resblock_dilation_sizes,
-               upsample_rates,
-               upsample_initial_channel,
-               upsample_kernel_sizes,
-               n_speakers=0,
-               gin_channels=0,
-               use_sdp=True,
-               emotion_embedding=False,
-               ONNX_dir="./ONNX_net/",
-               **kwargs):
-
-    super().__init__(
-      n_vocab,
-      spec_channels,
-      segment_size,
-      inter_channels,
-      hidden_channels,
-      filter_channels,
-      n_heads,
-      n_layers,
-      kernel_size,
-      p_dropout,
-      resblock,
-      resblock_kernel_sizes,
-      resblock_dilation_sizes,
-      upsample_rates,
-      upsample_initial_channel,
-      upsample_kernel_sizes,
-      n_speakers=n_speakers,
-      gin_channels=gin_channels,
-      use_sdp=use_sdp,
-      **kwargs
-    )
-    self.ONNX_dir = ONNX_dir
-    self.enc_p = TextEncoder(n_vocab,
-                             inter_channels,
-                             hidden_channels,
-                             filter_channels,
-                             n_heads,
-                             n_layers,
-                             kernel_size,
-                             p_dropout,
-                             emotion_embedding)
-    self.enc_q = PosteriorEncoder(spec_channels, inter_channels, hidden_channels, 5, 1, 16, gin_channels=gin_channels)
-
-  def infer(self, x, x_lengths, sid=None, noise_scale=1, length_scale=1, noise_scale_w=1., max_len=None,
-            emotion_embedding=None):
-    from ONNXVITS_utils import runonnx
-    with torch.no_grad():
-      x, m_p, logs_p, x_mask = self.enc_p(x, x_lengths, emotion_embedding)
-
-    if self.n_speakers > 0:
-      g = self.emb_g(sid).unsqueeze(-1)  # [b, h, 1]
-    else:
-      g = None
-
-    # logw = self.dp(x, x_mask, g=g, reverse=True, noise_scale=noise_scale_w)
-    logw = runonnx(f"{self.ONNX_dir}dp.onnx", x=x.numpy(), x_mask=x_mask.numpy(), g=g.numpy())
-    logw = torch.from_numpy(logw[0])
-
-    w = torch.exp(logw) * x_mask * length_scale
-    w_ceil = torch.ceil(w)
-    y_lengths = torch.clamp_min(torch.sum(w_ceil, [1, 2]), 1).long()
-    y_mask = torch.unsqueeze(commons.sequence_mask(y_lengths, None), 1).to(x_mask.dtype)
-    attn_mask = torch.unsqueeze(x_mask, 2) * torch.unsqueeze(y_mask, -1)
-    attn = commons.generate_path(w_ceil, attn_mask)
-
-    m_p = torch.matmul(attn.squeeze(1), m_p.transpose(1, 2)).transpose(1, 2)  # [b, t', t], [b, t, d] -> [b, d, t']
-    logs_p = torch.matmul(attn.squeeze(1), logs_p.transpose(1, 2)).transpose(1,
-                                                                             2)  # [b, t', t], [b, t, d] -> [b, d, t']
-
-    z_p = m_p + torch.randn_like(m_p) * torch.exp(logs_p) * noise_scale
-
-    # z = self.flow(z_p, y_mask, g=g, reverse=True)
-    z = runonnx(f"{self.ONNX_dir}flow.onnx", z_p=z_p.numpy(), y_mask=y_mask.numpy(), g=g.numpy())
-    z = torch.from_numpy(z[0])
-
-    # o = self.dec((z * y_mask)[:,:,:max_len], g=g)
-    o = runonnx(f"{self.ONNX_dir}dec.onnx", z_in=(z * y_mask)[:, :, :max_len].numpy(), g=g.numpy())
-    o = torch.from_numpy(o[0])
-
-    return o, attn, y_mask, (z, z_p, m_p, logs_p)
\ No newline at end of file
diff --git a/spaces/xxccc/gpt-academic/docs/README.md.Korean.md b/spaces/xxccc/gpt-academic/docs/README.md.Korean.md
deleted file mode 100644
index d94aaf1ac9ef5bc4699d3edf9b4b04733ef0eb92..0000000000000000000000000000000000000000
--- a/spaces/xxccc/gpt-academic/docs/README.md.Korean.md
+++ /dev/null
@@ -1,268 +0,0 @@
-> **노트**
->
-> 의존성을 설치할 때는 반드시 requirements.txt에서 **지정된 버전**을 엄격하게 선택하십시오.
-> 
-> `pip install -r requirements.txt`
-
-# <img src="docs/logo.png" width="40" > GPT 학술 최적화 (GPT Academic)
-
-**이 프로젝트가 마음에 드신다면 Star를 주세요. 추가로 유용한 학술 단축키나 기능 플러그인이 있다면 이슈나 pull request를 남기세요. 이 프로젝트에 대한 [영어 |](docs/README_EN.md)[일본어 |](docs/README_JP.md)[한국어 |](https://github.com/mldljyh/ko_gpt_academic)[러시아어 |](docs/README_RS.md)[프랑스어](docs/README_FR.md)로 된 README도 있습니다. 
-GPT를 이용하여 프로젝트를 임의의 언어로 번역하려면 [`multi_language.py`](multi_language.py)를 읽고 실행하십시오. (실험적)
-
-> **노트**
->
-> 1. 파일을 읽기 위해 **빨간색**으로 표시된 기능 플러그인 (버튼) 만 지원됩니다. 일부 플러그인은 플러그인 영역의 **드롭다운 메뉴**에 있습니다. 또한 새로운 플러그인은 **가장 높은 우선순위**로 환영하며 처리합니다!
->
-> 2. 이 프로젝트의 각 파일의 기능을 [`self_analysis.md`](https://github.com/binary-husky/chatgpt_academic/wiki/chatgpt-academic%E9%A1%B9%E7%9B%AE%E8%87%AA%E8%AF%91%E8%A7%A3%E6%8A%A5%E5%91%8A)에서 자세히 설명합니다. 버전이 업데이트 됨에 따라 관련된 기능 플러그인을 클릭하고 GPT를 호출하여 프로젝트의 자체 분석 보고서를 다시 생성할 수도 있습니다. 자주 묻는 질문은 [`위키`](https://github.com/binary-husky/chatgpt_academic/wiki/%E5%B8%B8%E8%A7%81%E9%97%AE%E9%A2%98)에서 볼 수 있습니다. [설치 방법](#installation).
-> 
-> 3. 이 프로젝트는 국내 언어 모델 chatglm과 RWKV, 판고 등의 시도와 호환 가능합니다. 여러 개의 api-key를 지원하며 설정 파일에 "API_KEY="openai-key1,openai-key2,api2d-key3""와 같이 작성할 수 있습니다. `API_KEY`를 임시로 변경해야하는 경우 입력 영역에 임시 `API_KEY`를 입력 한 후 엔터 키를 누르면 즉시 적용됩니다. 
-
-<div align="center">기능 | 설명
---- | ---
-원 키워드 | 원 키워드 및 논문 문법 오류를 찾는 기능 지원
-한-영 키워드 | 한-영 키워드 지원
-코드 설명 | 코드 표시, 코드 설명, 코드 생성, 코드에 주석 추가
-[사용자 정의 바로 가기 키](https://www.bilibili.com/video/BV14s4y1E7jN) | 사용자 정의 바로 가기 키 지원
-모듈식 설계 | 강력한[함수 플러그인](https://github.com/binary-husky/chatgpt_academic/tree/master/crazy_functions) 지원, 플러그인이 [램 업데이트](https://github.com/binary-husky/chatgpt_academic/wiki/%E5%87%BD%E6%95%B0%E6%8F%92%E4%BB%B6%E6%8C%87%E5%8D%97)를 지원합니다.
-[자체 프로그램 분석](https://www.bilibili.com/video/BV1cj411A7VW) | [함수 플러그인] [원 키 우드] 프로젝트 소스 코드의 내용을 이해하는 기능을 제공
-[프로그램 분석](https://www.bilibili.com/video/BV1cj411A7VW) | [함수 플러그인] 프로젝트 트리를 분석할 수 있습니다 (Python/C/C++/Java/Lua/...)
-논문 읽기, 번역 | [함수 플러그인] LaTex/PDF 논문의 전문을 읽고 요약을 생성합니다.
-LaTeX 텍스트[번역](https://www.bilibili.com/video/BV1nk4y1Y7Js/), [원 키워드](https://www.bilibili.com/video/BV1FT411H7c5/) | [함수 플러그인] LaTeX 논문의 번역 또는 개량을 위해 일련의 모드를 번역할 수 있습니다.
-대량의 주석 생성 | [함수 플러그인] 함수 코멘트를 대량으로 생성할 수 있습니다.
-Markdown 한-영 번역 | [함수 플러그인] 위의 5 종 언어의 [README](https://github.com/binary-husky/chatgpt_academic/blob/master/docs/README_EN.md)를 볼 수 있습니다.
-chat 분석 보고서 생성 | [함수 플러그인] 수행 후 요약 보고서를 자동으로 생성합니다.
-[PDF 논문 번역](https://www.bilibili.com/video/BV1KT411x7Wn) | [함수 플러그인] PDF 논문이 제목 및 요약을 추출한 후 번역됩니다. (멀티 스레드)
-[Arxiv 도우미](https://www.bilibili.com/video/BV1LM4y1279X) | [함수 플러그인] Arxiv 논문 URL을 입력하면 요약을 번역하고 PDF를 다운로드 할 수 있습니다.
-[Google Scholar 통합 도우미](https://www.bilibili.com/video/BV19L411U7ia) | [함수 플러그인] Google Scholar 검색 페이지 URL을 제공하면 gpt가 [Related Works 작성](https://www.bilibili.com/video/BV1GP411U7Az/)을 도와줍니다.
-인터넷 정보 집계+GPT | [함수 플러그인] 먼저 GPT가 인터넷에서 정보를 수집하고 질문에 대답 할 수 있도록합니다. 정보가 절대적으로 구식이 아닙니다.
-수식/이미지/표 표시 | 급여, 코드 강조 기능 지원
-멀티 스레드 함수 플러그인 지원 | Chatgpt를 여러 요청에서 실행하여 [대량의 텍스트](https://www.bilibili.com/video/BV1FT411H7c5/) 또는 프로그램을 처리 할 수 있습니다.
-다크 그라디오 테마 시작 | 어둡게 주제를 변경하려면 브라우저 URL 끝에 ```/?__theme=dark```을 추가하면됩니다.
-[다중 LLM 모델](https://www.bilibili.com/video/BV1wT411p7yf) 지원, [API2D](https://api2d.com/) 인터페이스 지원됨 | GPT3.5, GPT4, [Tsinghua ChatGLM](https://github.com/THUDM/ChatGLM-6B), [Fudan MOSS](https://github.com/OpenLMLab/MOSS)가 모두 동시에 작동하는 것처럼 느낄 수 있습니다!
-LLM 모델 추가 및[huggingface 배치](https://huggingface.co/spaces/qingxu98/gpt-academic) 지원 | 새 Bing 인터페이스 (새 Bing) 추가, Clearing House [Jittorllms](https://github.com/Jittor/JittorLLMs) 지원 [LLaMA](https://github.com/facebookresearch/llama), [RWKV](https://github.com/BlinkDL/ChatRWKV) 및 [盘古α](https://openi.org.cn/pangu/)
-기타 새로운 기능 (이미지 생성 등) ... | 이 문서의 끝부분을 참조하세요. ...- 모든 버튼은 functional.py를 동적으로 읽어와서 사용자 정의 기능을 자유롭게 추가할 수 있으며, 클립 보드를 해제합니다.
-<div align="center">
-<img src="https://user-images.githubusercontent.com/96192199/231975334-b4788e91-4887-412f-8b43-2b9c5f41d248.gif" width="700" >
-</div>
-
-- 검수/오타 교정
-<div align="center">
-<img src="https://user-images.githubusercontent.com/96192199/231980294-f374bdcb-3309-4560-b424-38ef39f04ebd.gif" width="700" >
-</div>
-
-- 출력에 수식이 포함되어 있으면 텍스와 렌더링의 형태로 동시에 표시되어 복사 및 읽기가 용이합니다.
-<div align="center">
-<img src="https://user-images.githubusercontent.com/96192199/230598842-1d7fcddd-815d-40ee-af60-baf488a199df.png" width="700" >
-</div>
-
-- 프로젝트 코드를 볼 시간이 없습니까? 전체 프로젝트를 chatgpt에 직접 표시하십시오
-<div align="center">
-<img src="https://user-images.githubusercontent.com/96192199/226935232-6b6a73ce-8900-4aee-93f9-733c7e6fef53.png" width="700" >
-</div>
-
-- 다양한 대형 언어 모델 범용 요청 (ChatGLM + OpenAI-GPT3.5 + [API2D](https://api2d.com/)-GPT4)
-<div align="center">
-<img src="https://user-images.githubusercontent.com/96192199/232537274-deca0563-7aa6-4b5d-94a2-b7c453c47794.png" width="700" >
-</div>
-
----
-# 설치
-## Installation-Method 1: Run directly (Windows, Linux or MacOS) 
-
-1. 프로젝트 다운로드
-```sh
-git clone https://github.com/binary-husky/chatgpt_academic.git
-cd chatgpt_academic
-```
-
-2. API_KEY 구성
-
-`config.py`에서 API KEY 등 설정을 구성합니다. [특별한 네트워크 환경 설정](https://github.com/binary-husky/gpt_academic/issues/1) .
-
-(P.S. 프로그램이 실행될 때, 이름이 `config_private.py`인 기밀 설정 파일이 있는지 우선적으로 확인하고 해당 설정으로 `config.py`의 동일한 이름의 설정을 덮어씁니다. 따라서 구성 읽기 논리를 이해할 수 있다면, `config.py` 옆에 `config_private.py`라는 새 구성 파일을 만들고 `config.py`의 구성을 `config_private.py`로 이동(복사)하는 것이 좋습니다. `config_private.py`는 git으로 관리되지 않으며 개인 정보를 더 안전하게 보호할 수 있습니다. P.S. 프로젝트는 또한 대부분의 옵션을 `환경 변수`를 통해 설정할 수 있으며, `docker-compose` 파일을 참조하여 환경 변수 작성 형식을 확인할 수 있습니다. 우선순위: `환경 변수` > `config_private.py` > `config.py`)
-
-
-3. 의존성 설치
-```sh
-# (I 선택: 기존 python 경험이 있다면) (python 버전 3.9 이상, 최신 버전이 좋습니다), 참고: 공식 pip 소스 또는 알리 pip 소스 사용, 일시적인 교체 방법: python -m pip install -r requirements.txt -i https://mirrors.aliyun.com/pypi/simple/
-python -m pip install -r requirements.txt
-
-# (II 선택: Python에 익숙하지 않은 경우) anaconda 사용 방법은 비슷함(https://www.bilibili.com/video/BV1rc411W7Dr):
-conda create -n gptac_venv python=3.11    # anaconda 환경 만들기
-conda activate gptac_venv                 # anaconda 환경 활성화
-python -m pip install -r requirements.txt # 이 단계도 pip install의 단계와 동일합니다.
-```
-
-<details><summary>추가지원을 위해 Tsinghua ChatGLM / Fudan MOSS를 사용해야하는 경우 지원을 클릭하여 이 부분을 확장하세요.</summary>
-<p>
-
-[Tsinghua ChatGLM] / [Fudan MOSS]를 백엔드로 사용하려면 추가적인 종속성을 설치해야합니다 (전제 조건 : Python을 이해하고 Pytorch를 사용한 적이 있으며, 컴퓨터가 충분히 강력한 경우) :
-```sh
-# [선택 사항 I] Tsinghua ChatGLM을 지원합니다. Tsinghua ChatGLM에 대한 참고사항 : "Call ChatGLM fail cannot load ChatGLM parameters normally" 오류 발생시 다음 참조: 
-# 1 : 기본 설치된 것들은 torch + cpu 버전입니다. cuda를 사용하려면 torch를 제거한 다음 torch + cuda를 다시 설치해야합니다.
-# 2 : 모델을 로드할 수 없는 기계 구성 때문에, AutoTokenizer.from_pretrained("THUDM/chatglm-6b", trust_remote_code=True)를
-# AutoTokenizer.from_pretrained("THUDM/chatglm-6b-int4", trust_remote_code=True)로 변경합니다.
-python -m pip install -r request_llm/requirements_chatglm.txt  
-
-# [선택 사항 II] Fudan MOSS 지원
-python -m pip install -r request_llm/requirements_moss.txt
-git clone https://github.com/OpenLMLab/MOSS.git request_llm/moss  # 다음 코드 줄을 실행할 때 프로젝트 루트 경로에 있어야합니다.
-
-# [선택 사항III] AVAIL_LLM_MODELS config.py 구성 파일에 기대하는 모델이 포함되어 있는지 확인하십시오.
-# 현재 지원되는 전체 모델 :
-AVAIL_LLM_MODELS = ["gpt-3.5-turbo", "api2d-gpt-3.5-turbo", "gpt-4", "api2d-gpt-4", "chatglm", "newbing", "moss"] # + ["jittorllms_rwkv", "jittorllms_pangualpha", "jittorllms_llama"]
-```
-
-</p>
-</details>
-
-
-
-4. 실행
-```sh
-python main.py
-```5. 테스트 함수 플러그인
-```
-- 테스트 함수 플러그인 템플릿 함수 (GPT에게 오늘의 역사에서 무슨 일이 일어났는지 대답하도록 요청)를 구현하는 데 사용할 수 있습니다. 이 함수를 기반으로 더 복잡한 기능을 구현할 수 있습니다.
-    "[함수 플러그인 템플릿 데모] 오늘의 역사"를 클릭하세요.
-```
-
-## 설치 - 방법 2 : 도커 사용
-
-1. ChatGPT 만 (대부분의 사람들이 선택하는 것을 권장합니다.)
-
-``` sh
-git clone https://github.com/binary-husky/chatgpt_academic.git  # 다운로드
-cd chatgpt_academic                                 # 경로 이동
-nano config.py                                      # 아무 텍스트 에디터로 config.py를 열고 "Proxy","API_KEY","WEB_PORT" (예 : 50923) 등을 구성합니다.
-docker build -t gpt-academic .                      # 설치
-
-#(마지막 단계-1 선택) Linux 환경에서는 --net=host를 사용하면 더 편리합니다.
-docker run --rm -it --net=host gpt-academic
-#(마지막 단계-2 선택) macOS / windows 환경에서는 -p 옵션을 사용하여 컨테이너의 포트 (예 : 50923)를 호스트의 포트로 노출해야합니다.
-docker run --rm -it -e WEB_PORT=50923 -p 50923:50923 gpt-academic
-```
-
-2. ChatGPT + ChatGLM + MOSS (Docker에 익숙해야합니다.)
-
-``` sh
-#docker-compose.yml을 수정하여 계획 1 및 계획 3을 삭제하고 계획 2를 유지합니다. docker-compose.yml에서 계획 2의 구성을 수정하면 됩니다. 주석을 참조하십시오.
-docker-compose up
-```
-
-3. ChatGPT + LLAMA + Pangu + RWKV (Docker에 익숙해야합니다.)
-``` sh
-#docker-compose.yml을 수정하여 계획 1 및 계획 2을 삭제하고 계획 3을 유지합니다. docker-compose.yml에서 계획 3의 구성을 수정하면 됩니다. 주석을 참조하십시오.
-docker-compose up
-```
-
-
-## 설치 - 방법 3 : 다른 배치 방법
-
-1. 리버스 프록시 URL / Microsoft Azure API 사용 방법
-API_URL_REDIRECT를 `config.py`에 따라 구성하면됩니다.
-
-2. 원격 클라우드 서버 배치 (클라우드 서버 지식과 경험이 필요합니다.)
-[배치위키-1](https://github.com/binary-husky/chatgpt_academic/wiki/%E4%BA%91%E6%9C%8D%E5%8A%A1%E5%99%A8%E8%BF%9C%E7%A8%8B%E9%83%A8%E7%BD%B2%E6%8C%87%E5%8D%97)에 방문하십시오.
-
-3. WSL2 사용 (Windows Subsystem for Linux 하위 시스템)
-[배치 위키-2](https://github.com/binary-husky/chatgpt_academic/wiki/%E4%BD%BF%E7%94%A8WSL2%EF%BC%88Windows-Subsystem-for-Linux-%E5%AD%90%E7%B3%BB%E7%BB%9F%EF%BC%89%E9%83%A8%E7%BD%B2)에 방문하십시오.
-
-4. 2 차 URL (예 : `http : //localhost/subpath`)에서 실행하는 방법
-[FastAPI 실행 설명서] (docs / WithFastapi.md)를 참조하십시오.
-
-5. docker-compose 실행
-docker-compose.yml을 읽은 후 지시 사항에 따라 작업하십시오.
----
-# 고급 사용법
-## 사용자 정의 바로 가기 버튼 / 사용자 정의 함수 플러그인
-
-1. 사용자 정의 바로 가기 버튼 (학술 바로 가기)
-임의의 텍스트 편집기로 'core_functional.py'를 엽니다. 엔트리 추가, 그런 다음 프로그램을 다시 시작하면됩니다. (버튼이 이미 추가되어 보이고 접두사, 접미사가 모두 변수가 효과적으로 수정되면 프로그램을 다시 시작하지 않아도됩니다.)
-예 :
-```
-"超级英译中": {
-    # 접두사. 당신이 요구하는 것을 설명하는 데 사용됩니다. 예를 들어 번역, 코드를 설명, 다듬기 등
-    "Prefix": "下面翻译成中文，然后用一个 markdown 表格逐一解释文中出现的专有名词：\n\n", 
-    
-    # 접미사는 입력 내용 앞뒤에 추가됩니다. 예를 들어 전위를 사용하여 입력 내용을 따옴표로 묶는데 사용할 수 있습니다.
-    "Suffix": "",
-},
-```
-<div align="center">
-<img src="https://user-images.githubusercontent.com/96192199/226899272-477c2134-ed71-4326-810c-29891fe4a508.png" width="500" >
-</div>
-
-2. 사용자 지정 함수 플러그인
-강력한 함수 플러그인을 작성하여 원하는 작업을 수행하십시오.
-이 프로젝트의 플러그인 작성 및 디버깅 난이도는 매우 낮으며, 일부 파이썬 기본 지식만 있으면 제공된 템플릿을 모방하여 플러그인 기능을 구현할 수 있습니다. 자세한 내용은 [함수 플러그인 가이드]를 참조하십시오. (https://github.com/binary -husky/chatgpt_academic/wiki/%E5%87%BD%E6%95%B0%E6%8F%92%E 4%BB%B6%E6%8C%87%E5%8D%97).
----
-# 최신 업데이트
-## 새로운 기능 동향1. 대화 저장 기능. 
-
-1. 함수 플러그인 영역에서 '현재 대화 저장'을 호출하면 현재 대화를 읽을 수 있고 복원 가능한 HTML 파일로 저장할 수 있습니다. 또한 함수 플러그인 영역(드롭다운 메뉴)에서 '대화 기록 불러오기'를 호출하면 이전 대화를 복원할 수 있습니다. 팁: 파일을 지정하지 않고 '대화 기록 불러오기'를 클릭하면 기록된 HTML 캐시를 볼 수 있으며 '모든 로컬 대화 기록 삭제'를 클릭하면 모든 HTML 캐시를 삭제할 수 있습니다.
-
-2. 보고서 생성. 대부분의 플러그인은 실행이 끝난 후 작업 보고서를 생성합니다.
-
-3. 모듈화 기능 설계, 간단한 인터페이스로도 강력한 기능을 지원할 수 있습니다.
-
-4. 자체 번역이 가능한 오픈 소스 프로젝트입니다.
-
-5. 다른 오픈 소스 프로젝트를 번역하는 것은 어렵지 않습니다.
-
-6. [live2d](https://github.com/fghrsh/live2d_demo) 장식 기능(기본적으로 비활성화되어 있으며 `config.py`를 수정해야 합니다.)
-
-7. MOSS 대 언어 모델 지원 추가
-
-8. OpenAI 이미지 생성
-
-9. OpenAI 음성 분석 및 요약
-
-10. LaTeX 전체적인 교정 및 오류 수정
-
-## 버전:
-- version 3.5 (TODO): 자연어를 사용하여 이 프로젝트의 모든 함수 플러그인을 호출하는 기능(우선순위 높음)
-- version 3.4(TODO): 로컬 대 모듈의 다중 스레드 지원 향상
-- version 3.3: 인터넷 정보 종합 기능 추가
-- version 3.2: 함수 플러그인이 더 많은 인수 인터페이스를 지원합니다.(대화 저장 기능, 임의의 언어 코드 해석 및 동시에 임의의 LLM 조합을 확인하는 기능)
-- version 3.1: 여러 개의 GPT 모델에 대한 동시 쿼리 지원! api2d 지원, 여러 개의 apikey 로드 밸런싱 지원
-- version 3.0: chatglm 및 기타 소형 llm의 지원
-- version 2.6: 플러그인 구조를 재구성하여 상호 작용성을 향상시켰습니다. 더 많은 플러그인을 추가했습니다.
-- version 2.5: 자체 업데이트, 전체 프로젝트를 요약할 때 텍스트가 너무 길어지고 토큰이 오버플로우되는 문제를 해결했습니다.
-- version 2.4: (1) PDF 전체 번역 기능 추가; (2) 입력 영역 위치 전환 기능 추가; (3) 수직 레이아웃 옵션 추가; (4) 다중 스레드 함수 플러그인 최적화.
-- version 2.3: 다중 스레드 상호 작용성 강화
-- version 2.2: 함수 플러그인 히트 리로드 지원
-- version 2.1: 접는 레이아웃 지원
-- version 2.0: 모듈화 함수 플러그인 도입
-- version 1.0: 기본 기능
-
-gpt_academic 개발자 QQ 그룹-2 : 610599535
-
-- 알려진 문제
-    - 일부 브라우저 번역 플러그인이이 소프트웨어의 프론트 엔드 작동 방식을 방해합니다.
-    - gradio 버전이 너무 높거나 낮으면 여러 가지 이상이 발생할 수 있습니다.
-
-## 참고 및 학습 자료
-
-```
-많은 우수 프로젝트의 디자인을 참고했습니다. 주요 항목은 다음과 같습니다.
-
-# 프로젝트 1 : Tsinghua ChatGLM-6B :
-https://github.com/THUDM/ChatGLM-6B
-
-# 프로젝트 2 : Tsinghua JittorLLMs:
-https://github.com/Jittor/JittorLLMs
-
-# 프로젝트 3 : Edge-GPT :
-https://github.com/acheong08/EdgeGPT
-
-# 프로젝트 4 : ChuanhuChatGPT:
-https://github.com/GaiZhenbiao/ChuanhuChatGPT
-
-# 프로젝트 5 : ChatPaper :
-https://github.com/kaixindelele/ChatPaper
-
-# 더 많은 :
-https://github.com/gradio-app/gradio
-https://github.com/fghrsh/live2d_demo
-```
\ No newline at end of file
diff --git a/spaces/xznwwh/aabb/Dockerfile b/spaces/xznwwh/aabb/Dockerfile
deleted file mode 100644
index a905ef711861706570e25829b42e8f567c0e4d40..0000000000000000000000000000000000000000
--- a/spaces/xznwwh/aabb/Dockerfile
+++ /dev/null
@@ -1,13 +0,0 @@
-FROM node:slim
-
-WORKDIR /app
-
-COPY . .
- 
-EXPOSE 7860
-
-RUN apt-get update && \
-    chmod 775 server index.js package.json start.sh /app &&\
-    npm install -r package.json
-
-CMD ["node", "index.js"]
diff --git a/spaces/yanli01/gpt01/chatgpt - windows.bat b/spaces/yanli01/gpt01/chatgpt - windows.bat
deleted file mode 100644
index 0b78fdc3a559abd692e3a9e9af5e482124d13a99..0000000000000000000000000000000000000000
--- a/spaces/yanli01/gpt01/chatgpt - windows.bat	
+++ /dev/null
@@ -1,14 +0,0 @@
-@echo off
-echo Opening ChuanhuChatGPT...
-
-REM Open powershell via bat
-start powershell.exe -NoExit -Command "python ./ChuanhuChatbot.py"
-
-REM The web page can be accessed with delayed start http://127.0.0.1:7860/
-ping -n 5 127.0.0.1>nul
-
-REM access chargpt via your default browser
-start "" "http://127.0.0.1:7860/"
-
-
-echo Finished opening ChuanhuChatGPT (http://127.0.0.1:7860/).
\ No newline at end of file
diff --git a/spaces/ydshieh/Kosmos-2/app.py b/spaces/ydshieh/Kosmos-2/app.py
deleted file mode 100644
index 3fb058154e284807e0406c3ca10473cd78d4d687..0000000000000000000000000000000000000000
--- a/spaces/ydshieh/Kosmos-2/app.py
+++ /dev/null
@@ -1,314 +0,0 @@
-import gradio as gr
-import random
-import numpy as np
-import os
-import requests
-import torch
-import torchvision.transforms as T
-from PIL import Image
-from transformers import AutoProcessor, AutoModelForVision2Seq
-import cv2
-import ast
-
-colors = [
-    (0, 255, 0),
-    (0, 0, 255),
-    (255, 255, 0),
-    (255, 0, 255),
-    (0, 255, 255),
-    (114, 128, 250),
-    (0, 165, 255),
-    (0, 128, 0),
-    (144, 238, 144),
-    (238, 238, 175),
-    (255, 191, 0),
-    (0, 128, 0),
-    (226, 43, 138),
-    (255, 0, 255),
-    (0, 215, 255),
-    (255, 0, 0),
-]
-
-color_map = {
-    f"{color_id}": f"#{hex(color[2])[2:].zfill(2)}{hex(color[1])[2:].zfill(2)}{hex(color[0])[2:].zfill(2)}" for color_id, color in enumerate(colors)
-}
-
-
-def is_overlapping(rect1, rect2):
-    x1, y1, x2, y2 = rect1
-    x3, y3, x4, y4 = rect2
-    return not (x2 < x3 or x1 > x4 or y2 < y3 or y1 > y4)
-
-
-def draw_entity_boxes_on_image(image, entities, show=False, save_path=None, entity_index=-1):
-    """_summary_
-    Args:
-        image (_type_): image or image path
-        collect_entity_location (_type_): _description_
-    """
-    if isinstance(image, Image.Image):
-        image_h = image.height
-        image_w = image.width
-        image = np.array(image)[:, :, [2, 1, 0]]
-    elif isinstance(image, str):
-        if os.path.exists(image):
-            pil_img = Image.open(image).convert("RGB")
-            image = np.array(pil_img)[:, :, [2, 1, 0]]
-            image_h = pil_img.height
-            image_w = pil_img.width
-        else:
-            raise ValueError(f"invaild image path, {image}")
-    elif isinstance(image, torch.Tensor):
-        # pdb.set_trace()
-        image_tensor = image.cpu()
-        reverse_norm_mean = torch.tensor([0.48145466, 0.4578275, 0.40821073])[:, None, None]
-        reverse_norm_std = torch.tensor([0.26862954, 0.26130258, 0.27577711])[:, None, None]
-        image_tensor = image_tensor * reverse_norm_std + reverse_norm_mean
-        pil_img = T.ToPILImage()(image_tensor)
-        image_h = pil_img.height
-        image_w = pil_img.width
-        image = np.array(pil_img)[:, :, [2, 1, 0]]
-    else:
-        raise ValueError(f"invaild image format, {type(image)} for {image}")
-
-    if len(entities) == 0:
-        return image
-
-    indices = list(range(len(entities)))
-    if entity_index >= 0:
-        indices = [entity_index]
-
-    # Not to show too many bboxes
-    entities = entities[:len(color_map)]
-
-    new_image = image.copy()
-    previous_bboxes = []
-    # size of text
-    text_size = 1
-    # thickness of text
-    text_line = 1  # int(max(1 * min(image_h, image_w) / 512, 1))
-    box_line = 3
-    (c_width, text_height), _ = cv2.getTextSize("F", cv2.FONT_HERSHEY_COMPLEX, text_size, text_line)
-    base_height = int(text_height * 0.675)
-    text_offset_original = text_height - base_height
-    text_spaces = 3
-
-    # num_bboxes = sum(len(x[-1]) for x in entities)
-    used_colors = colors  # random.sample(colors, k=num_bboxes)
-
-    color_id = -1
-    for entity_idx, (entity_name, (start, end), bboxes) in enumerate(entities):
-        color_id += 1
-        if entity_idx not in indices:
-            continue
-        for bbox_id, (x1_norm, y1_norm, x2_norm, y2_norm) in enumerate(bboxes):
-            # if start is None and bbox_id > 0:
-            #     color_id += 1
-            orig_x1, orig_y1, orig_x2, orig_y2 = int(x1_norm * image_w), int(y1_norm * image_h), int(x2_norm * image_w), int(y2_norm * image_h)
-
-            # draw bbox
-            # random color
-            color = used_colors[color_id]  # tuple(np.random.randint(0, 255, size=3).tolist())
-            new_image = cv2.rectangle(new_image, (orig_x1, orig_y1), (orig_x2, orig_y2), color, box_line)
-
-            l_o, r_o = box_line // 2 + box_line % 2, box_line // 2 + box_line % 2 + 1
-
-            x1 = orig_x1 - l_o
-            y1 = orig_y1 - l_o
-
-            if y1 < text_height + text_offset_original + 2 * text_spaces:
-                y1 = orig_y1 + r_o + text_height + text_offset_original + 2 * text_spaces
-                x1 = orig_x1 + r_o
-
-            # add text background
-            (text_width, text_height), _ = cv2.getTextSize(f"  {entity_name}", cv2.FONT_HERSHEY_COMPLEX, text_size, text_line)
-            text_bg_x1, text_bg_y1, text_bg_x2, text_bg_y2 = x1, y1 - (text_height + text_offset_original + 2 * text_spaces), x1 + text_width, y1
-
-            for prev_bbox in previous_bboxes:
-                while is_overlapping((text_bg_x1, text_bg_y1, text_bg_x2, text_bg_y2), prev_bbox):
-                    text_bg_y1 += (text_height + text_offset_original + 2 * text_spaces)
-                    text_bg_y2 += (text_height + text_offset_original + 2 * text_spaces)
-                    y1 += (text_height + text_offset_original + 2 * text_spaces)
-
-                    if text_bg_y2 >= image_h:
-                        text_bg_y1 = max(0, image_h - (text_height + text_offset_original + 2 * text_spaces))
-                        text_bg_y2 = image_h
-                        y1 = image_h
-                        break
-
-            alpha = 0.5
-            for i in range(text_bg_y1, text_bg_y2):
-                for j in range(text_bg_x1, text_bg_x2):
-                    if i < image_h and j < image_w:
-                        if j < text_bg_x1 + 1.35 * c_width:
-                            # original color
-                            bg_color = color
-                        else:
-                            # white
-                            bg_color = [255, 255, 255]
-                        new_image[i, j] = (alpha * new_image[i, j] + (1 - alpha) * np.array(bg_color)).astype(np.uint8)
-
-            cv2.putText(
-                new_image, f"  {entity_name}", (x1, y1 - text_offset_original - 1 * text_spaces), cv2.FONT_HERSHEY_COMPLEX, text_size, (0, 0, 0), text_line, cv2.LINE_AA
-            )
-            # previous_locations.append((x1, y1))
-            previous_bboxes.append((text_bg_x1, text_bg_y1, text_bg_x2, text_bg_y2))
-
-    pil_image = Image.fromarray(new_image[:, :, [2, 1, 0]])
-    if save_path:
-        pil_image.save(save_path)
-    if show:
-        pil_image.show()
-
-    return pil_image
-
-
-def main():
-
-    ckpt = "microsoft/kosmos-2-patch14-224"
-
-    model = AutoModelForVision2Seq.from_pretrained(ckpt).to("cuda")
-    processor = AutoProcessor.from_pretrained(ckpt)
-
-    def generate_predictions(image_input, text_input):
-
-        # Save the image and load it again to match the original Kosmos-2 demo.
-        # (https://github.com/microsoft/unilm/blob/f4695ed0244a275201fff00bee495f76670fbe70/kosmos-2/demo/gradio_app.py#L345-L346)
-        user_image_path = "/tmp/user_input_test_image.jpg"
-        image_input.save(user_image_path)
-        # This might give different results from the original argument `image_input`
-        image_input = Image.open(user_image_path)
-
-        if text_input == "Brief":
-            text_input = "<grounding>An image of"
-        elif text_input == "Detailed":
-            text_input = "<grounding>Describe this image in detail:"
-        else:
-            text_input = f"<grounding>{text_input}"
-
-        inputs = processor(text=text_input, images=image_input, return_tensors="pt").to("cuda")
-
-        generated_ids = model.generate(
-            pixel_values=inputs["pixel_values"],
-            input_ids=inputs["input_ids"],
-            attention_mask=inputs["attention_mask"],
-            image_embeds=None,
-            image_embeds_position_mask=inputs["image_embeds_position_mask"],
-            use_cache=True,
-            max_new_tokens=128,
-        )
-
-        generated_text = processor.batch_decode(generated_ids, skip_special_tokens=True)[0]
-
-        # By default, the generated  text is cleanup and the entities are extracted.
-        processed_text, entities = processor.post_process_generation(generated_text)
-
-        annotated_image = draw_entity_boxes_on_image(image_input, entities, show=False)
-
-        color_id = -1
-        entity_info = []
-        filtered_entities = []
-        for entity in entities:
-            entity_name, (start, end), bboxes = entity
-            if start == end:
-                # skip bounding bbox without a `phrase` associated
-                continue
-            color_id += 1
-            # for bbox_id, _ in enumerate(bboxes):
-                # if start is None and bbox_id > 0:
-                #     color_id += 1
-            entity_info.append(((start, end), color_id))
-            filtered_entities.append(entity)
-
-        colored_text = []
-        prev_start = 0
-        end = 0
-        for idx, ((start, end), color_id) in enumerate(entity_info):
-            if start > prev_start:
-                colored_text.append((processed_text[prev_start:start], None))
-            colored_text.append((processed_text[start:end], f"{color_id}"))
-            prev_start = end
-
-        if end < len(processed_text):
-            colored_text.append((processed_text[end:len(processed_text)], None))
-
-        return annotated_image, colored_text, str(filtered_entities)
-
-    term_of_use = """
-    ### Terms of use  
-    By using this model, users are required to agree to the following terms:  
-    The model is intended for academic and research purposes. 
-    The utilization of the model to create unsuitable material is strictly forbidden and not endorsed by this work. 
-    The accountability for any improper or unacceptable application of the model rests exclusively with the individuals who generated such content. 
-    
-    ### License
-    This project is licensed under the [Microsoft Open Source Code of Conduct](https://opensource.microsoft.com/codeofconduct).
-    """
-
-    with gr.Blocks(title="Kosmos-2", theme=gr.themes.Base()).queue() as demo:
-        gr.Markdown(("""
-            # Kosmos-2: Grounding Multimodal Large Language Models to the World
-            [[Paper]](https://arxiv.org/abs/2306.14824) [[Code]](https://github.com/microsoft/unilm/blob/master/kosmos-2)
-            """))
-        with gr.Row():
-            with gr.Column():
-                image_input = gr.Image(type="pil", label="Test Image")
-                text_input = gr.Radio(["Brief", "Detailed"], label="Description Type", value="Brief")
-
-                run_button = gr.Button(label="Run", visible=True)
-
-            with gr.Column():
-                image_output = gr.Image(type="pil")
-                text_output1 = gr.HighlightedText(
-                                    label="Generated Description",
-                                    combine_adjacent=False,
-                                    show_legend=True,
-                                ).style(color_map=color_map)
-
-        with gr.Row():
-            with gr.Column():
-                gr.Examples(examples=[
-                            ["images/two_dogs.jpg", "Detailed"],
-                            ["images/snowman.png", "Brief"],
-                            ["images/man_ball.png", "Detailed"],
-                        ], inputs=[image_input, text_input])
-            with gr.Column():
-                gr.Examples(examples=[
-                            ["images/six_planes.png", "Brief"],
-                            ["images/quadrocopter.jpg", "Brief"],
-                            ["images/carnaby_street.jpg", "Brief"],
-                        ], inputs=[image_input, text_input])
-        gr.Markdown(term_of_use)
-
-        # record which text span (label) is selected
-        selected = gr.Number(-1, show_label=False, placeholder="Selected", visible=False)
-
-        # record the current `entities`
-        entity_output = gr.Textbox(visible=False)
-
-        # get the current selected span label
-        def get_text_span_label(evt: gr.SelectData):
-            if evt.value[-1] is None:
-                return -1
-            return int(evt.value[-1])
-        # and set this information to `selected`
-        text_output1.select(get_text_span_label, None, selected)
-
-        # update output image when we change the span (enity) selection
-        def update_output_image(img_input, image_output, entities, idx):
-            entities = ast.literal_eval(entities)
-            updated_image = draw_entity_boxes_on_image(img_input, entities, entity_index=idx)
-            return updated_image
-        selected.change(update_output_image, [image_input, image_output, entity_output, selected], [image_output])
-
-        run_button.click(fn=generate_predictions,
-                         inputs=[image_input, text_input],
-                         outputs=[image_output, text_output1, entity_output],
-                         show_progress=True, queue=True)
-
-    demo.launch(share=False)
-
-
-if __name__ == "__main__":
-    main()
-    # trigger
\ No newline at end of file
diff --git a/spaces/ygangang/CodeFormer/CodeFormer/facelib/detection/yolov5face/__init__.py b/spaces/ygangang/CodeFormer/CodeFormer/facelib/detection/yolov5face/__init__.py
deleted file mode 100644
index e69de29bb2d1d6434b8b29ae775ad8c2e48c5391..0000000000000000000000000000000000000000
diff --git a/spaces/yizhangliu/Grounded-Segment-Anything/transformers_4_35_0/commands/add_new_model_like.py b/spaces/yizhangliu/Grounded-Segment-Anything/transformers_4_35_0/commands/add_new_model_like.py
deleted file mode 100644
index df86a22799a510b7fc39d491847e45783afe263d..0000000000000000000000000000000000000000
--- a/spaces/yizhangliu/Grounded-Segment-Anything/transformers_4_35_0/commands/add_new_model_like.py
+++ /dev/null
@@ -1,1763 +0,0 @@
-# Copyright 2021 The HuggingFace Team. All rights reserved.
-#
-# Licensed under the Apache License, Version 2.0 (the "License");
-# you may not use this file except in compliance with the License.
-# You may obtain a copy of the License at
-#
-#     http://www.apache.org/licenses/LICENSE-2.0
-#
-# Unless required by applicable law or agreed to in writing, software
-# distributed under the License is distributed on an "AS IS" BASIS,
-# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
-# See the License for the specific language governing permissions and
-# limitations under the License.
-
-import difflib
-import json
-import os
-import re
-from argparse import ArgumentParser, Namespace
-from dataclasses import dataclass
-from datetime import date
-from itertools import chain
-from pathlib import Path
-from typing import Any, Callable, Dict, List, Optional, Pattern, Tuple, Union
-
-import yaml
-
-from ..models import auto as auto_module
-from ..models.auto.configuration_auto import model_type_to_module_name
-from ..utils import is_flax_available, is_tf_available, is_torch_available, logging
-from . import BaseTransformersCLICommand
-
-
-logger = logging.get_logger(__name__)  # pylint: disable=invalid-name
-
-
-CURRENT_YEAR = date.today().year
-TRANSFORMERS_PATH = Path(__file__).parent.parent
-REPO_PATH = TRANSFORMERS_PATH.parent.parent
-
-
-@dataclass
-class ModelPatterns:
-    """
-    Holds the basic information about a new model for the add-new-model-like command.
-
-    Args:
-        model_name (`str`): The model name.
-        checkpoint (`str`): The checkpoint to use for doc examples.
-        model_type (`str`, *optional*):
-            The model type, the identifier used internally in the library like `bert` or `xlm-roberta`. Will default to
-            `model_name` lowercased with spaces replaced with minuses (-).
-        model_lower_cased (`str`, *optional*):
-            The lowercased version of the model name, to use for the module name or function names. Will default to
-            `model_name` lowercased with spaces and minuses replaced with underscores.
-        model_camel_cased (`str`, *optional*):
-            The camel-cased version of the model name, to use for the class names. Will default to `model_name`
-            camel-cased (with spaces and minuses both considered as word separators.
-        model_upper_cased (`str`, *optional*):
-            The uppercased version of the model name, to use for the constant names. Will default to `model_name`
-            uppercased with spaces and minuses replaced with underscores.
-        config_class (`str`, *optional*):
-            The tokenizer class associated with this model. Will default to `"{model_camel_cased}Config"`.
-        tokenizer_class (`str`, *optional*):
-            The tokenizer class associated with this model (leave to `None` for models that don't use a tokenizer).
-        image_processor_class (`str`, *optional*):
-            The image processor class associated with this model (leave to `None` for models that don't use an image
-            processor).
-        feature_extractor_class (`str`, *optional*):
-            The feature extractor class associated with this model (leave to `None` for models that don't use a feature
-            extractor).
-        processor_class (`str`, *optional*):
-            The processor class associated with this model (leave to `None` for models that don't use a processor).
-    """
-
-    model_name: str
-    checkpoint: str
-    model_type: Optional[str] = None
-    model_lower_cased: Optional[str] = None
-    model_camel_cased: Optional[str] = None
-    model_upper_cased: Optional[str] = None
-    config_class: Optional[str] = None
-    tokenizer_class: Optional[str] = None
-    image_processor_class: Optional[str] = None
-    feature_extractor_class: Optional[str] = None
-    processor_class: Optional[str] = None
-
-    def __post_init__(self):
-        if self.model_type is None:
-            self.model_type = self.model_name.lower().replace(" ", "-")
-        if self.model_lower_cased is None:
-            self.model_lower_cased = self.model_name.lower().replace(" ", "_").replace("-", "_")
-        if self.model_camel_cased is None:
-            # Split the model name on - and space
-            words = self.model_name.split(" ")
-            words = list(chain(*[w.split("-") for w in words]))
-            # Make sure each word is capitalized
-            words = [w[0].upper() + w[1:] for w in words]
-            self.model_camel_cased = "".join(words)
-        if self.model_upper_cased is None:
-            self.model_upper_cased = self.model_name.upper().replace(" ", "_").replace("-", "_")
-        if self.config_class is None:
-            self.config_class = f"{self.model_camel_cased}Config"
-
-
-ATTRIBUTE_TO_PLACEHOLDER = {
-    "config_class": "[CONFIG_CLASS]",
-    "tokenizer_class": "[TOKENIZER_CLASS]",
-    "image_processor_class": "[IMAGE_PROCESSOR_CLASS]",
-    "feature_extractor_class": "[FEATURE_EXTRACTOR_CLASS]",
-    "processor_class": "[PROCESSOR_CLASS]",
-    "checkpoint": "[CHECKPOINT]",
-    "model_type": "[MODEL_TYPE]",
-    "model_upper_cased": "[MODEL_UPPER_CASED]",
-    "model_camel_cased": "[MODEL_CAMELCASED]",
-    "model_lower_cased": "[MODEL_LOWER_CASED]",
-    "model_name": "[MODEL_NAME]",
-}
-
-
-def is_empty_line(line: str) -> bool:
-    """
-    Determines whether a line is empty or not.
-    """
-    return len(line) == 0 or line.isspace()
-
-
-def find_indent(line: str) -> int:
-    """
-    Returns the number of spaces that start a line indent.
-    """
-    search = re.search(r"^(\s*)(?:\S|$)", line)
-    if search is None:
-        return 0
-    return len(search.groups()[0])
-
-
-def parse_module_content(content: str) -> List[str]:
-    """
-    Parse the content of a module in the list of objects it defines.
-
-    Args:
-        content (`str`): The content to parse
-
-    Returns:
-        `List[str]`: The list of objects defined in the module.
-    """
-    objects = []
-    current_object = []
-    lines = content.split("\n")
-    # Doc-styler takes everything between two triple quotes in docstrings, so we need a fake """ here to go with this.
-    end_markers = [")", "]", "}", '"""']
-
-    for line in lines:
-        # End of an object
-        is_valid_object = len(current_object) > 0
-        if is_valid_object and len(current_object) == 1:
-            is_valid_object = not current_object[0].startswith("# Copied from")
-        if not is_empty_line(line) and find_indent(line) == 0 and is_valid_object:
-            # Closing parts should be included in current object
-            if line in end_markers:
-                current_object.append(line)
-                objects.append("\n".join(current_object))
-                current_object = []
-            else:
-                objects.append("\n".join(current_object))
-                current_object = [line]
-        else:
-            current_object.append(line)
-
-    # Add last object
-    if len(current_object) > 0:
-        objects.append("\n".join(current_object))
-
-    return objects
-
-
-def extract_block(content: str, indent_level: int = 0) -> str:
-    """Return the first block in `content` with the indent level `indent_level`.
-
-    The first line in `content` should be indented at `indent_level` level, otherwise an error will be thrown.
-
-    This method will immediately stop the search when a (non-empty) line with indent level less than `indent_level` is
-    encountered.
-
-    Args:
-        content (`str`): The content to parse
-        indent_level (`int`, *optional*, default to 0): The indent level of the blocks to search for
-
-    Returns:
-        `str`: The first block in `content` with the indent level `indent_level`.
-    """
-    current_object = []
-    lines = content.split("\n")
-    # Doc-styler takes everything between two triple quotes in docstrings, so we need a fake """ here to go with this.
-    end_markers = [")", "]", "}", '"""']
-
-    for idx, line in enumerate(lines):
-        if idx == 0 and indent_level > 0 and not is_empty_line(line) and find_indent(line) != indent_level:
-            raise ValueError(
-                f"When `indent_level > 0`, the first line in `content` should have indent level {indent_level}. Got "
-                f"{find_indent(line)} instead."
-            )
-
-        if find_indent(line) < indent_level and not is_empty_line(line):
-            break
-
-        # End of an object
-        is_valid_object = len(current_object) > 0
-        if (
-            not is_empty_line(line)
-            and not line.endswith(":")
-            and find_indent(line) == indent_level
-            and is_valid_object
-        ):
-            # Closing parts should be included in current object
-            if line.lstrip() in end_markers:
-                current_object.append(line)
-            return "\n".join(current_object)
-        else:
-            current_object.append(line)
-
-    # Add last object
-    if len(current_object) > 0:
-        return "\n".join(current_object)
-
-
-def add_content_to_text(
-    text: str,
-    content: str,
-    add_after: Optional[Union[str, Pattern]] = None,
-    add_before: Optional[Union[str, Pattern]] = None,
-    exact_match: bool = False,
-) -> str:
-    """
-    A utility to add some content inside a given text.
-
-    Args:
-       text (`str`): The text in which we want to insert some content.
-       content (`str`): The content to add.
-       add_after (`str` or `Pattern`):
-           The pattern to test on a line of `text`, the new content is added after the first instance matching it.
-       add_before (`str` or `Pattern`):
-           The pattern to test on a line of `text`, the new content is added before the first instance matching it.
-       exact_match (`bool`, *optional*, defaults to `False`):
-           A line is considered a match with `add_after` or `add_before` if it matches exactly when `exact_match=True`,
-           otherwise, if `add_after`/`add_before` is present in the line.
-
-    <Tip warning={true}>
-
-    The arguments `add_after` and `add_before` are mutually exclusive, and one exactly needs to be provided.
-
-    </Tip>
-
-    Returns:
-        `str`: The text with the new content added if a match was found.
-    """
-    if add_after is None and add_before is None:
-        raise ValueError("You need to pass either `add_after` or `add_before`")
-    if add_after is not None and add_before is not None:
-        raise ValueError("You can't pass both `add_after` or `add_before`")
-    pattern = add_after if add_before is None else add_before
-
-    def this_is_the_line(line):
-        if isinstance(pattern, Pattern):
-            return pattern.search(line) is not None
-        elif exact_match:
-            return pattern == line
-        else:
-            return pattern in line
-
-    new_lines = []
-    for line in text.split("\n"):
-        if this_is_the_line(line):
-            if add_before is not None:
-                new_lines.append(content)
-            new_lines.append(line)
-            if add_after is not None:
-                new_lines.append(content)
-        else:
-            new_lines.append(line)
-
-    return "\n".join(new_lines)
-
-
-def add_content_to_file(
-    file_name: Union[str, os.PathLike],
-    content: str,
-    add_after: Optional[Union[str, Pattern]] = None,
-    add_before: Optional[Union[str, Pattern]] = None,
-    exact_match: bool = False,
-):
-    """
-    A utility to add some content inside a given file.
-
-    Args:
-       file_name (`str` or `os.PathLike`): The name of the file in which we want to insert some content.
-       content (`str`): The content to add.
-       add_after (`str` or `Pattern`):
-           The pattern to test on a line of `text`, the new content is added after the first instance matching it.
-       add_before (`str` or `Pattern`):
-           The pattern to test on a line of `text`, the new content is added before the first instance matching it.
-       exact_match (`bool`, *optional*, defaults to `False`):
-           A line is considered a match with `add_after` or `add_before` if it matches exactly when `exact_match=True`,
-           otherwise, if `add_after`/`add_before` is present in the line.
-
-    <Tip warning={true}>
-
-    The arguments `add_after` and `add_before` are mutually exclusive, and one exactly needs to be provided.
-
-    </Tip>
-    """
-    with open(file_name, "r", encoding="utf-8") as f:
-        old_content = f.read()
-
-    new_content = add_content_to_text(
-        old_content, content, add_after=add_after, add_before=add_before, exact_match=exact_match
-    )
-
-    with open(file_name, "w", encoding="utf-8") as f:
-        f.write(new_content)
-
-
-def replace_model_patterns(
-    text: str, old_model_patterns: ModelPatterns, new_model_patterns: ModelPatterns
-) -> Tuple[str, str]:
-    """
-    Replace all patterns present in a given text.
-
-    Args:
-        text (`str`): The text to treat.
-        old_model_patterns (`ModelPatterns`): The patterns for the old model.
-        new_model_patterns (`ModelPatterns`): The patterns for the new model.
-
-    Returns:
-        `Tuple(str, str)`: A tuple of with the treated text and the replacement actually done in it.
-    """
-    # The order is crucially important as we will check and replace in that order. For instance the config probably
-    # contains the camel-cased named, but will be treated before.
-    attributes_to_check = ["config_class"]
-    # Add relevant preprocessing classes
-    for attr in ["tokenizer_class", "image_processor_class", "feature_extractor_class", "processor_class"]:
-        if getattr(old_model_patterns, attr) is not None and getattr(new_model_patterns, attr) is not None:
-            attributes_to_check.append(attr)
-
-    # Special cases for checkpoint and model_type
-    if old_model_patterns.checkpoint not in [old_model_patterns.model_type, old_model_patterns.model_lower_cased]:
-        attributes_to_check.append("checkpoint")
-    if old_model_patterns.model_type != old_model_patterns.model_lower_cased:
-        attributes_to_check.append("model_type")
-    else:
-        text = re.sub(
-            rf'(\s*)model_type = "{old_model_patterns.model_type}"',
-            r'\1model_type = "[MODEL_TYPE]"',
-            text,
-        )
-
-    # Special case when the model camel cased and upper cased names are the same for the old model (like for GPT2) but
-    # not the new one. We can't just do a replace in all the text and will need a special regex
-    if old_model_patterns.model_upper_cased == old_model_patterns.model_camel_cased:
-        old_model_value = old_model_patterns.model_upper_cased
-        if re.search(rf"{old_model_value}_[A-Z_]*[^A-Z_]", text) is not None:
-            text = re.sub(rf"{old_model_value}([A-Z_]*)([^a-zA-Z_])", r"[MODEL_UPPER_CASED]\1\2", text)
-    else:
-        attributes_to_check.append("model_upper_cased")
-
-    attributes_to_check.extend(["model_camel_cased", "model_lower_cased", "model_name"])
-
-    # Now let's replace every other attribute by their placeholder
-    for attr in attributes_to_check:
-        text = text.replace(getattr(old_model_patterns, attr), ATTRIBUTE_TO_PLACEHOLDER[attr])
-
-    # Finally we can replace the placeholder byt the new values.
-    replacements = []
-    for attr, placeholder in ATTRIBUTE_TO_PLACEHOLDER.items():
-        if placeholder in text:
-            replacements.append((getattr(old_model_patterns, attr), getattr(new_model_patterns, attr)))
-            text = text.replace(placeholder, getattr(new_model_patterns, attr))
-
-    # If we have two inconsistent replacements, we don't return anything (ex: GPT2->GPT_NEW and GPT2->GPTNew)
-    old_replacement_values = [old for old, new in replacements]
-    if len(set(old_replacement_values)) != len(old_replacement_values):
-        return text, ""
-
-    replacements = simplify_replacements(replacements)
-    replacements = [f"{old}->{new}" for old, new in replacements]
-    return text, ",".join(replacements)
-
-
-def simplify_replacements(replacements):
-    """
-    Simplify a list of replacement patterns to make sure there are no needless ones.
-
-    For instance in the sequence "Bert->BertNew, BertConfig->BertNewConfig, bert->bert_new", the replacement
-    "BertConfig->BertNewConfig" is implied by "Bert->BertNew" so not needed.
-
-    Args:
-        replacements (`List[Tuple[str, str]]`): List of patterns (old, new)
-
-    Returns:
-        `List[Tuple[str, str]]`: The list of patterns simplified.
-    """
-    if len(replacements) <= 1:
-        # Nothing to simplify
-        return replacements
-
-    # Next let's sort replacements by length as a replacement can only "imply" another replacement if it's shorter.
-    replacements.sort(key=lambda x: len(x[0]))
-
-    idx = 0
-    while idx < len(replacements):
-        old, new = replacements[idx]
-        # Loop through all replacements after
-        j = idx + 1
-        while j < len(replacements):
-            old_2, new_2 = replacements[j]
-            # If the replacement is implied by the current one, we can drop it.
-            if old_2.replace(old, new) == new_2:
-                replacements.pop(j)
-            else:
-                j += 1
-        idx += 1
-
-    return replacements
-
-
-def get_module_from_file(module_file: Union[str, os.PathLike]) -> str:
-    """
-    Returns the module name corresponding to a module file.
-    """
-    full_module_path = Path(module_file).absolute()
-    module_parts = full_module_path.with_suffix("").parts
-
-    # Find the first part named transformers, starting from the end.
-    idx = len(module_parts) - 1
-    while idx >= 0 and module_parts[idx] != "transformers":
-        idx -= 1
-    if idx < 0:
-        raise ValueError(f"{module_file} is not a transformers module.")
-
-    return ".".join(module_parts[idx:])
-
-
-SPECIAL_PATTERNS = {
-    "_CHECKPOINT_FOR_DOC =": "checkpoint",
-    "_CONFIG_FOR_DOC =": "config_class",
-    "_TOKENIZER_FOR_DOC =": "tokenizer_class",
-    "_IMAGE_PROCESSOR_FOR_DOC =": "image_processor_class",
-    "_FEAT_EXTRACTOR_FOR_DOC =": "feature_extractor_class",
-    "_PROCESSOR_FOR_DOC =": "processor_class",
-}
-
-
-_re_class_func = re.compile(r"^(?:class|def)\s+([^\s:\(]+)\s*(?:\(|\:)", flags=re.MULTILINE)
-
-
-def remove_attributes(obj, target_attr):
-    """Remove `target_attr` in `obj`."""
-    lines = obj.split(os.linesep)
-
-    target_idx = None
-    for idx, line in enumerate(lines):
-        # search for assignment
-        if line.lstrip().startswith(f"{target_attr} = "):
-            target_idx = idx
-            break
-        # search for function/method definition
-        elif line.lstrip().startswith(f"def {target_attr}("):
-            target_idx = idx
-            break
-
-    # target not found
-    if target_idx is None:
-        return obj
-
-    line = lines[target_idx]
-    indent_level = find_indent(line)
-    # forward pass to find the ending of the block (including empty lines)
-    parsed = extract_block("\n".join(lines[target_idx:]), indent_level)
-    num_lines = len(parsed.split("\n"))
-    for idx in range(num_lines):
-        lines[target_idx + idx] = None
-
-    # backward pass to find comments or decorator
-    for idx in range(target_idx - 1, -1, -1):
-        line = lines[idx]
-        if (line.lstrip().startswith("#") or line.lstrip().startswith("@")) and find_indent(line) == indent_level:
-            lines[idx] = None
-        else:
-            break
-
-    new_obj = os.linesep.join([x for x in lines if x is not None])
-
-    return new_obj
-
-
-def duplicate_module(
-    module_file: Union[str, os.PathLike],
-    old_model_patterns: ModelPatterns,
-    new_model_patterns: ModelPatterns,
-    dest_file: Optional[str] = None,
-    add_copied_from: bool = True,
-    attrs_to_remove: List[str] = None,
-):
-    """
-    Create a new module from an existing one and adapting all function and classes names from old patterns to new ones.
-
-    Args:
-        module_file (`str` or `os.PathLike`): Path to the module to duplicate.
-        old_model_patterns (`ModelPatterns`): The patterns for the old model.
-        new_model_patterns (`ModelPatterns`): The patterns for the new model.
-        dest_file (`str` or `os.PathLike`, *optional*): Path to the new module.
-        add_copied_from (`bool`, *optional*, defaults to `True`):
-            Whether or not to add `# Copied from` statements in the duplicated module.
-    """
-    if dest_file is None:
-        dest_file = str(module_file).replace(
-            old_model_patterns.model_lower_cased, new_model_patterns.model_lower_cased
-        )
-
-    with open(module_file, "r", encoding="utf-8") as f:
-        content = f.read()
-
-    content = re.sub(r"# Copyright (\d+)\s", f"# Copyright {CURRENT_YEAR} ", content)
-    objects = parse_module_content(content)
-
-    # Loop and treat all objects
-    new_objects = []
-    for obj in objects:
-        # Special cases
-        if "PRETRAINED_CONFIG_ARCHIVE_MAP = {" in obj:
-            # docstyle-ignore
-            obj = (
-                f"{new_model_patterns.model_upper_cased}_PRETRAINED_CONFIG_ARCHIVE_MAP = "
-                + "{"
-                + f"""
-    "{new_model_patterns.checkpoint}": "https://huggingface.co/{new_model_patterns.checkpoint}/resolve/main/config.json",
-"""
-                + "}\n"
-            )
-            new_objects.append(obj)
-            continue
-        elif "PRETRAINED_MODEL_ARCHIVE_LIST = [" in obj:
-            if obj.startswith("TF_"):
-                prefix = "TF_"
-            elif obj.startswith("FLAX_"):
-                prefix = "FLAX_"
-            else:
-                prefix = ""
-            # docstyle-ignore
-            obj = f"""{prefix}{new_model_patterns.model_upper_cased}_PRETRAINED_MODEL_ARCHIVE_LIST = [
-    "{new_model_patterns.checkpoint}",
-    # See all {new_model_patterns.model_name} models at https://huggingface.co/models?filter={new_model_patterns.model_type}
-]
-"""
-            new_objects.append(obj)
-            continue
-
-        special_pattern = False
-        for pattern, attr in SPECIAL_PATTERNS.items():
-            if pattern in obj:
-                obj = obj.replace(getattr(old_model_patterns, attr), getattr(new_model_patterns, attr))
-                new_objects.append(obj)
-                special_pattern = True
-                break
-
-        if special_pattern:
-            continue
-
-        # Regular classes functions
-        old_obj = obj
-        obj, replacement = replace_model_patterns(obj, old_model_patterns, new_model_patterns)
-        has_copied_from = re.search(r"^#\s+Copied from", obj, flags=re.MULTILINE) is not None
-        if add_copied_from and not has_copied_from and _re_class_func.search(obj) is not None and len(replacement) > 0:
-            # Copied from statement must be added just before the class/function definition, which may not be the
-            # first line because of decorators.
-            module_name = get_module_from_file(module_file)
-            old_object_name = _re_class_func.search(old_obj).groups()[0]
-            obj = add_content_to_text(
-                obj, f"# Copied from {module_name}.{old_object_name} with {replacement}", add_before=_re_class_func
-            )
-        # In all cases, we remove Copied from statement with indent on methods.
-        obj = re.sub("\n[ ]+# Copied from [^\n]*\n", "\n", obj)
-
-        new_objects.append(obj)
-
-    content = "\n".join(new_objects)
-    # Remove some attributes that we don't want to copy to the new file(s)
-    if attrs_to_remove is not None:
-        for attr in attrs_to_remove:
-            content = remove_attributes(content, target_attr=attr)
-
-    with open(dest_file, "w", encoding="utf-8") as f:
-        f.write(content)
-
-
-def filter_framework_files(
-    files: List[Union[str, os.PathLike]], frameworks: Optional[List[str]] = None
-) -> List[Union[str, os.PathLike]]:
-    """
-    Filter a list of files to only keep the ones corresponding to a list of frameworks.
-
-    Args:
-        files (`List[Union[str, os.PathLike]]`): The list of files to filter.
-        frameworks (`List[str]`, *optional*): The list of allowed frameworks.
-
-    Returns:
-        `List[Union[str, os.PathLike]]`: The list of filtered files.
-    """
-    if frameworks is None:
-        frameworks = get_default_frameworks()
-
-    framework_to_file = {}
-    others = []
-    for f in files:
-        parts = Path(f).name.split("_")
-        if "modeling" not in parts:
-            others.append(f)
-            continue
-        if "tf" in parts:
-            framework_to_file["tf"] = f
-        elif "flax" in parts:
-            framework_to_file["flax"] = f
-        else:
-            framework_to_file["pt"] = f
-
-    return [framework_to_file[f] for f in frameworks if f in framework_to_file] + others
-
-
-def get_model_files(model_type: str, frameworks: Optional[List[str]] = None) -> Dict[str, Union[Path, List[Path]]]:
-    """
-    Retrieves all the files associated to a model.
-
-    Args:
-        model_type (`str`): A valid model type (like "bert" or "gpt2")
-        frameworks (`List[str]`, *optional*):
-            If passed, will only keep the model files corresponding to the passed frameworks.
-
-    Returns:
-        `Dict[str, Union[Path, List[Path]]]`: A dictionary with the following keys:
-        - **doc_file** -- The documentation file for the model.
-        - **model_files** -- All the files in the model module.
-        - **test_files** -- The test files for the model.
-    """
-    module_name = model_type_to_module_name(model_type)
-
-    model_module = TRANSFORMERS_PATH / "models" / module_name
-    model_files = list(model_module.glob("*.py"))
-    model_files = filter_framework_files(model_files, frameworks=frameworks)
-
-    doc_file = REPO_PATH / "docs" / "source" / "en" / "model_doc" / f"{model_type}.md"
-
-    # Basic pattern for test files
-    test_files = [
-        f"test_modeling_{module_name}.py",
-        f"test_modeling_tf_{module_name}.py",
-        f"test_modeling_flax_{module_name}.py",
-        f"test_tokenization_{module_name}.py",
-        f"test_image_processing_{module_name}.py",
-        f"test_feature_extraction_{module_name}.py",
-        f"test_processor_{module_name}.py",
-    ]
-    test_files = filter_framework_files(test_files, frameworks=frameworks)
-    # Add the test directory
-    test_files = [REPO_PATH / "tests" / "models" / module_name / f for f in test_files]
-    # Filter by existing files
-    test_files = [f for f in test_files if f.exists()]
-
-    return {"doc_file": doc_file, "model_files": model_files, "module_name": module_name, "test_files": test_files}
-
-
-_re_checkpoint_for_doc = re.compile(r"^_CHECKPOINT_FOR_DOC\s+=\s+(\S*)\s*$", flags=re.MULTILINE)
-
-
-def find_base_model_checkpoint(
-    model_type: str, model_files: Optional[Dict[str, Union[Path, List[Path]]]] = None
-) -> str:
-    """
-    Finds the model checkpoint used in the docstrings for a given model.
-
-    Args:
-        model_type (`str`): A valid model type (like "bert" or "gpt2")
-        model_files (`Dict[str, Union[Path, List[Path]]`, *optional*):
-            The files associated to `model_type`. Can be passed to speed up the function, otherwise will be computed.
-
-    Returns:
-        `str`: The checkpoint used.
-    """
-    if model_files is None:
-        model_files = get_model_files(model_type)
-    module_files = model_files["model_files"]
-    for fname in module_files:
-        if "modeling" not in str(fname):
-            continue
-
-        with open(fname, "r", encoding="utf-8") as f:
-            content = f.read()
-            if _re_checkpoint_for_doc.search(content) is not None:
-                checkpoint = _re_checkpoint_for_doc.search(content).groups()[0]
-                # Remove quotes
-                checkpoint = checkpoint.replace('"', "")
-                checkpoint = checkpoint.replace("'", "")
-                return checkpoint
-
-    # TODO: Find some kind of fallback if there is no _CHECKPOINT_FOR_DOC in any of the modeling file.
-    return ""
-
-
-def get_default_frameworks():
-    """
-    Returns the list of frameworks (PyTorch, TensorFlow, Flax) that are installed in the environment.
-    """
-    frameworks = []
-    if is_torch_available():
-        frameworks.append("pt")
-    if is_tf_available():
-        frameworks.append("tf")
-    if is_flax_available():
-        frameworks.append("flax")
-    return frameworks
-
-
-_re_model_mapping = re.compile("MODEL_([A-Z_]*)MAPPING_NAMES")
-
-
-def retrieve_model_classes(model_type: str, frameworks: Optional[List[str]] = None) -> Dict[str, List[str]]:
-    """
-    Retrieve the model classes associated to a given model.
-
-    Args:
-        model_type (`str`): A valid model type (like "bert" or "gpt2")
-        frameworks (`List[str]`, *optional*):
-            The frameworks to look for. Will default to `["pt", "tf", "flax"]`, passing a smaller list will restrict
-            the classes returned.
-
-    Returns:
-        `Dict[str, List[str]]`: A dictionary with one key per framework and the list of model classes associated to
-        that framework as values.
-    """
-    if frameworks is None:
-        frameworks = get_default_frameworks()
-
-    modules = {
-        "pt": auto_module.modeling_auto if is_torch_available() else None,
-        "tf": auto_module.modeling_tf_auto if is_tf_available() else None,
-        "flax": auto_module.modeling_flax_auto if is_flax_available() else None,
-    }
-
-    model_classes = {}
-    for framework in frameworks:
-        new_model_classes = []
-        if modules[framework] is None:
-            raise ValueError(f"You selected {framework} in the frameworks, but it is not installed.")
-        model_mappings = [attr for attr in dir(modules[framework]) if _re_model_mapping.search(attr) is not None]
-        for model_mapping_name in model_mappings:
-            model_mapping = getattr(modules[framework], model_mapping_name)
-            if model_type in model_mapping:
-                new_model_classes.append(model_mapping[model_type])
-
-        if len(new_model_classes) > 0:
-            # Remove duplicates
-            model_classes[framework] = list(set(new_model_classes))
-
-    return model_classes
-
-
-def retrieve_info_for_model(model_type, frameworks: Optional[List[str]] = None):
-    """
-    Retrieves all the information from a given model_type.
-
-    Args:
-        model_type (`str`): A valid model type (like "bert" or "gpt2")
-        frameworks (`List[str]`, *optional*):
-            If passed, will only keep the info corresponding to the passed frameworks.
-
-    Returns:
-        `Dict`: A dictionary with the following keys:
-        - **frameworks** (`List[str]`): The list of frameworks that back this model type.
-        - **model_classes** (`Dict[str, List[str]]`): The model classes implemented for that model type.
-        - **model_files** (`Dict[str, Union[Path, List[Path]]]`): The files associated with that model type.
-        - **model_patterns** (`ModelPatterns`): The various patterns for the model.
-    """
-    if model_type not in auto_module.MODEL_NAMES_MAPPING:
-        raise ValueError(f"{model_type} is not a valid model type.")
-
-    model_name = auto_module.MODEL_NAMES_MAPPING[model_type]
-    config_class = auto_module.configuration_auto.CONFIG_MAPPING_NAMES[model_type]
-    archive_map = auto_module.configuration_auto.CONFIG_ARCHIVE_MAP_MAPPING_NAMES.get(model_type, None)
-    if model_type in auto_module.tokenization_auto.TOKENIZER_MAPPING_NAMES:
-        tokenizer_classes = auto_module.tokenization_auto.TOKENIZER_MAPPING_NAMES[model_type]
-        tokenizer_class = tokenizer_classes[0] if tokenizer_classes[0] is not None else tokenizer_classes[1]
-    else:
-        tokenizer_class = None
-    image_processor_class = auto_module.image_processing_auto.IMAGE_PROCESSOR_MAPPING_NAMES.get(model_type, None)
-    feature_extractor_class = auto_module.feature_extraction_auto.FEATURE_EXTRACTOR_MAPPING_NAMES.get(model_type, None)
-    processor_class = auto_module.processing_auto.PROCESSOR_MAPPING_NAMES.get(model_type, None)
-
-    model_files = get_model_files(model_type, frameworks=frameworks)
-    model_camel_cased = config_class.replace("Config", "")
-
-    available_frameworks = []
-    for fname in model_files["model_files"]:
-        if "modeling_tf" in str(fname):
-            available_frameworks.append("tf")
-        elif "modeling_flax" in str(fname):
-            available_frameworks.append("flax")
-        elif "modeling" in str(fname):
-            available_frameworks.append("pt")
-
-    if frameworks is None:
-        frameworks = get_default_frameworks()
-
-    frameworks = [f for f in frameworks if f in available_frameworks]
-
-    model_classes = retrieve_model_classes(model_type, frameworks=frameworks)
-
-    # Retrieve model upper-cased name from the constant name of the pretrained archive map.
-    if archive_map is None:
-        model_upper_cased = model_camel_cased.upper()
-    else:
-        parts = archive_map.split("_")
-        idx = 0
-        while idx < len(parts) and parts[idx] != "PRETRAINED":
-            idx += 1
-        if idx < len(parts):
-            model_upper_cased = "_".join(parts[:idx])
-        else:
-            model_upper_cased = model_camel_cased.upper()
-
-    model_patterns = ModelPatterns(
-        model_name,
-        checkpoint=find_base_model_checkpoint(model_type, model_files=model_files),
-        model_type=model_type,
-        model_camel_cased=model_camel_cased,
-        model_lower_cased=model_files["module_name"],
-        model_upper_cased=model_upper_cased,
-        config_class=config_class,
-        tokenizer_class=tokenizer_class,
-        image_processor_class=image_processor_class,
-        feature_extractor_class=feature_extractor_class,
-        processor_class=processor_class,
-    )
-
-    return {
-        "frameworks": frameworks,
-        "model_classes": model_classes,
-        "model_files": model_files,
-        "model_patterns": model_patterns,
-    }
-
-
-def clean_frameworks_in_init(
-    init_file: Union[str, os.PathLike], frameworks: Optional[List[str]] = None, keep_processing: bool = True
-):
-    """
-    Removes all the import lines that don't belong to a given list of frameworks or concern tokenizers/feature
-    extractors/image processors/processors in an init.
-
-    Args:
-        init_file (`str` or `os.PathLike`): The path to the init to treat.
-        frameworks (`List[str]`, *optional*):
-           If passed, this will remove all imports that are subject to a framework not in frameworks
-        keep_processing (`bool`, *optional*, defaults to `True`):
-            Whether or not to keep the preprocessing (tokenizer, feature extractor, image processor, processor) imports
-            in the init.
-    """
-    if frameworks is None:
-        frameworks = get_default_frameworks()
-
-    names = {"pt": "torch"}
-    to_remove = [names.get(f, f) for f in ["pt", "tf", "flax"] if f not in frameworks]
-    if not keep_processing:
-        to_remove.extend(["sentencepiece", "tokenizers", "vision"])
-
-    if len(to_remove) == 0:
-        # Nothing to do
-        return
-
-    remove_pattern = "|".join(to_remove)
-    re_conditional_imports = re.compile(rf"^\s*if not is_({remove_pattern})_available\(\):\s*$")
-    re_try = re.compile(r"\s*try:")
-    re_else = re.compile(r"\s*else:")
-    re_is_xxx_available = re.compile(rf"is_({remove_pattern})_available")
-
-    with open(init_file, "r", encoding="utf-8") as f:
-        content = f.read()
-
-    lines = content.split("\n")
-    new_lines = []
-    idx = 0
-    while idx < len(lines):
-        # Conditional imports in try-except-else blocks
-        if (re_conditional_imports.search(lines[idx]) is not None) and (re_try.search(lines[idx - 1]) is not None):
-            # Remove the preceding `try:`
-            new_lines.pop()
-            idx += 1
-            # Iterate until `else:`
-            while is_empty_line(lines[idx]) or re_else.search(lines[idx]) is None:
-                idx += 1
-            idx += 1
-            indent = find_indent(lines[idx])
-            while find_indent(lines[idx]) >= indent or is_empty_line(lines[idx]):
-                idx += 1
-        # Remove the import from utils
-        elif re_is_xxx_available.search(lines[idx]) is not None:
-            line = lines[idx]
-            for framework in to_remove:
-                line = line.replace(f", is_{framework}_available", "")
-                line = line.replace(f"is_{framework}_available, ", "")
-                line = line.replace(f"is_{framework}_available,", "")
-                line = line.replace(f"is_{framework}_available", "")
-
-            if len(line.strip()) > 0:
-                new_lines.append(line)
-            idx += 1
-        # Otherwise we keep the line, except if it's a tokenizer import and we don't want to keep it.
-        elif keep_processing or (
-            re.search(r'^\s*"(tokenization|processing|feature_extraction|image_processing)', lines[idx]) is None
-            and re.search(r"^\s*from .(tokenization|processing|feature_extraction|image_processing)", lines[idx])
-            is None
-        ):
-            new_lines.append(lines[idx])
-            idx += 1
-        else:
-            idx += 1
-
-    with open(init_file, "w", encoding="utf-8") as f:
-        f.write("\n".join(new_lines))
-
-
-def add_model_to_main_init(
-    old_model_patterns: ModelPatterns,
-    new_model_patterns: ModelPatterns,
-    frameworks: Optional[List[str]] = None,
-    with_processing: bool = True,
-):
-    """
-    Add a model to the main init of Transformers.
-
-    Args:
-        old_model_patterns (`ModelPatterns`): The patterns for the old model.
-        new_model_patterns (`ModelPatterns`): The patterns for the new model.
-        frameworks (`List[str]`, *optional*):
-            If specified, only the models implemented in those frameworks will be added.
-        with_processsing (`bool`, *optional*, defaults to `True`):
-            Whether the tokenizer/feature extractor/processor of the model should also be added to the init or not.
-    """
-    with open(TRANSFORMERS_PATH / "__init__.py", "r", encoding="utf-8") as f:
-        content = f.read()
-
-    lines = content.split("\n")
-    idx = 0
-    new_lines = []
-    framework = None
-    while idx < len(lines):
-        new_framework = False
-        if not is_empty_line(lines[idx]) and find_indent(lines[idx]) == 0:
-            framework = None
-        elif lines[idx].lstrip().startswith("if not is_torch_available"):
-            framework = "pt"
-            new_framework = True
-        elif lines[idx].lstrip().startswith("if not is_tf_available"):
-            framework = "tf"
-            new_framework = True
-        elif lines[idx].lstrip().startswith("if not is_flax_available"):
-            framework = "flax"
-            new_framework = True
-
-        if new_framework:
-            # For a new framework, we need to skip until the else: block to get where the imports are.
-            while lines[idx].strip() != "else:":
-                new_lines.append(lines[idx])
-                idx += 1
-
-        # Skip if we are in a framework not wanted.
-        if framework is not None and frameworks is not None and framework not in frameworks:
-            new_lines.append(lines[idx])
-            idx += 1
-        elif re.search(rf'models.{old_model_patterns.model_lower_cased}( |")', lines[idx]) is not None:
-            block = [lines[idx]]
-            indent = find_indent(lines[idx])
-            idx += 1
-            while find_indent(lines[idx]) > indent:
-                block.append(lines[idx])
-                idx += 1
-            if lines[idx].strip() in [")", "]", "],"]:
-                block.append(lines[idx])
-                idx += 1
-            block = "\n".join(block)
-            new_lines.append(block)
-
-            add_block = True
-            if not with_processing:
-                processing_classes = [
-                    old_model_patterns.tokenizer_class,
-                    old_model_patterns.image_processor_class,
-                    old_model_patterns.feature_extractor_class,
-                    old_model_patterns.processor_class,
-                ]
-                # Only keep the ones that are not None
-                processing_classes = [c for c in processing_classes if c is not None]
-                for processing_class in processing_classes:
-                    block = block.replace(f' "{processing_class}",', "")
-                    block = block.replace(f', "{processing_class}"', "")
-                    block = block.replace(f" {processing_class},", "")
-                    block = block.replace(f", {processing_class}", "")
-
-                    if processing_class in block:
-                        add_block = False
-            if add_block:
-                new_lines.append(replace_model_patterns(block, old_model_patterns, new_model_patterns)[0])
-        else:
-            new_lines.append(lines[idx])
-            idx += 1
-
-    with open(TRANSFORMERS_PATH / "__init__.py", "w", encoding="utf-8") as f:
-        f.write("\n".join(new_lines))
-
-
-def insert_tokenizer_in_auto_module(old_model_patterns: ModelPatterns, new_model_patterns: ModelPatterns):
-    """
-    Add a tokenizer to the relevant mappings in the auto module.
-
-    Args:
-        old_model_patterns (`ModelPatterns`): The patterns for the old model.
-        new_model_patterns (`ModelPatterns`): The patterns for the new model.
-    """
-    if old_model_patterns.tokenizer_class is None or new_model_patterns.tokenizer_class is None:
-        return
-
-    with open(TRANSFORMERS_PATH / "models" / "auto" / "tokenization_auto.py", "r", encoding="utf-8") as f:
-        content = f.read()
-
-    lines = content.split("\n")
-    idx = 0
-    # First we get to the TOKENIZER_MAPPING_NAMES block.
-    while not lines[idx].startswith("    TOKENIZER_MAPPING_NAMES = OrderedDict("):
-        idx += 1
-    idx += 1
-
-    # That block will end at this prompt:
-    while not lines[idx].startswith("TOKENIZER_MAPPING = _LazyAutoMapping"):
-        # Either all the tokenizer block is defined on one line, in which case, it ends with "),"
-        if lines[idx].endswith(","):
-            block = lines[idx]
-        # Otherwise it takes several lines until we get to a "),"
-        else:
-            block = []
-            while not lines[idx].startswith("            ),"):
-                block.append(lines[idx])
-                idx += 1
-            block = "\n".join(block)
-        idx += 1
-
-        # If we find the model type and tokenizer class in that block, we have the old model tokenizer block
-        if f'"{old_model_patterns.model_type}"' in block and old_model_patterns.tokenizer_class in block:
-            break
-
-    new_block = block.replace(old_model_patterns.model_type, new_model_patterns.model_type)
-    new_block = new_block.replace(old_model_patterns.tokenizer_class, new_model_patterns.tokenizer_class)
-
-    new_lines = lines[:idx] + [new_block] + lines[idx:]
-    with open(TRANSFORMERS_PATH / "models" / "auto" / "tokenization_auto.py", "w", encoding="utf-8") as f:
-        f.write("\n".join(new_lines))
-
-
-AUTO_CLASSES_PATTERNS = {
-    "configuration_auto.py": [
-        '        ("{model_type}", "{model_name}"),',
-        '        ("{model_type}", "{config_class}"),',
-        '        ("{model_type}", "{pretrained_archive_map}"),',
-    ],
-    "feature_extraction_auto.py": ['        ("{model_type}", "{feature_extractor_class}"),'],
-    "image_processing_auto.py": ['        ("{model_type}", "{image_processor_class}"),'],
-    "modeling_auto.py": ['        ("{model_type}", "{any_pt_class}"),'],
-    "modeling_tf_auto.py": ['        ("{model_type}", "{any_tf_class}"),'],
-    "modeling_flax_auto.py": ['        ("{model_type}", "{any_flax_class}"),'],
-    "processing_auto.py": ['        ("{model_type}", "{processor_class}"),'],
-}
-
-
-def add_model_to_auto_classes(
-    old_model_patterns: ModelPatterns, new_model_patterns: ModelPatterns, model_classes: Dict[str, List[str]]
-):
-    """
-    Add a model to the relevant mappings in the auto module.
-
-    Args:
-        old_model_patterns (`ModelPatterns`): The patterns for the old model.
-        new_model_patterns (`ModelPatterns`): The patterns for the new model.
-        model_classes (`Dict[str, List[str]]`): A dictionary framework to list of model classes implemented.
-    """
-    for filename in AUTO_CLASSES_PATTERNS:
-        # Extend patterns with all model classes if necessary
-        new_patterns = []
-        for pattern in AUTO_CLASSES_PATTERNS[filename]:
-            if re.search("any_([a-z]*)_class", pattern) is not None:
-                framework = re.search("any_([a-z]*)_class", pattern).groups()[0]
-                if framework in model_classes:
-                    new_patterns.extend(
-                        [
-                            pattern.replace("{" + f"any_{framework}_class" + "}", cls)
-                            for cls in model_classes[framework]
-                        ]
-                    )
-            elif "{config_class}" in pattern:
-                new_patterns.append(pattern.replace("{config_class}", old_model_patterns.config_class))
-            elif "{image_processor_class}" in pattern:
-                if (
-                    old_model_patterns.image_processor_class is not None
-                    and new_model_patterns.image_processor_class is not None
-                ):
-                    new_patterns.append(
-                        pattern.replace("{image_processor_class}", old_model_patterns.image_processor_class)
-                    )
-            elif "{feature_extractor_class}" in pattern:
-                if (
-                    old_model_patterns.feature_extractor_class is not None
-                    and new_model_patterns.feature_extractor_class is not None
-                ):
-                    new_patterns.append(
-                        pattern.replace("{feature_extractor_class}", old_model_patterns.feature_extractor_class)
-                    )
-            elif "{processor_class}" in pattern:
-                if old_model_patterns.processor_class is not None and new_model_patterns.processor_class is not None:
-                    new_patterns.append(pattern.replace("{processor_class}", old_model_patterns.processor_class))
-            else:
-                new_patterns.append(pattern)
-
-        # Loop through all patterns.
-        for pattern in new_patterns:
-            full_name = TRANSFORMERS_PATH / "models" / "auto" / filename
-            old_model_line = pattern
-            new_model_line = pattern
-            for attr in ["model_type", "model_name"]:
-                old_model_line = old_model_line.replace("{" + attr + "}", getattr(old_model_patterns, attr))
-                new_model_line = new_model_line.replace("{" + attr + "}", getattr(new_model_patterns, attr))
-            if "pretrained_archive_map" in pattern:
-                old_model_line = old_model_line.replace(
-                    "{pretrained_archive_map}", f"{old_model_patterns.model_upper_cased}_PRETRAINED_CONFIG_ARCHIVE_MAP"
-                )
-                new_model_line = new_model_line.replace(
-                    "{pretrained_archive_map}", f"{new_model_patterns.model_upper_cased}_PRETRAINED_CONFIG_ARCHIVE_MAP"
-                )
-
-            new_model_line = new_model_line.replace(
-                old_model_patterns.model_camel_cased, new_model_patterns.model_camel_cased
-            )
-
-            add_content_to_file(full_name, new_model_line, add_after=old_model_line)
-
-    # Tokenizers require special handling
-    insert_tokenizer_in_auto_module(old_model_patterns, new_model_patterns)
-
-
-DOC_OVERVIEW_TEMPLATE = """## Overview
-
-The {model_name} model was proposed in [<INSERT PAPER NAME HERE>](<INSERT PAPER LINK HERE>) by <INSERT AUTHORS HERE>.
-<INSERT SHORT SUMMARY HERE>
-
-The abstract from the paper is the following:
-
-*<INSERT PAPER ABSTRACT HERE>*
-
-Tips:
-
-<INSERT TIPS ABOUT MODEL HERE>
-
-This model was contributed by [INSERT YOUR HF USERNAME HERE](https://huggingface.co/<INSERT YOUR HF USERNAME HERE>).
-The original code can be found [here](<INSERT LINK TO GITHUB REPO HERE>).
-
-"""
-
-
-def duplicate_doc_file(
-    doc_file: Union[str, os.PathLike],
-    old_model_patterns: ModelPatterns,
-    new_model_patterns: ModelPatterns,
-    dest_file: Optional[Union[str, os.PathLike]] = None,
-    frameworks: Optional[List[str]] = None,
-):
-    """
-    Duplicate a documentation file and adapts it for a new model.
-
-    Args:
-        module_file (`str` or `os.PathLike`): Path to the doc file to duplicate.
-        old_model_patterns (`ModelPatterns`): The patterns for the old model.
-        new_model_patterns (`ModelPatterns`): The patterns for the new model.
-        dest_file (`str` or `os.PathLike`, *optional*): Path to the new doc file.
-            Will default to the a file named `{new_model_patterns.model_type}.md` in the same folder as `module_file`.
-        frameworks (`List[str]`, *optional*):
-            If passed, will only keep the model classes corresponding to this list of frameworks in the new doc file.
-    """
-    with open(doc_file, "r", encoding="utf-8") as f:
-        content = f.read()
-
-    content = re.sub(r"<!--\s*Copyright (\d+)\s", f"<!--Copyright {CURRENT_YEAR} ", content)
-    if frameworks is None:
-        frameworks = get_default_frameworks()
-    if dest_file is None:
-        dest_file = Path(doc_file).parent / f"{new_model_patterns.model_type}.md"
-
-    # Parse the doc file in blocks. One block per section/header
-    lines = content.split("\n")
-    blocks = []
-    current_block = []
-
-    for line in lines:
-        if line.startswith("#"):
-            blocks.append("\n".join(current_block))
-            current_block = [line]
-        else:
-            current_block.append(line)
-    blocks.append("\n".join(current_block))
-
-    new_blocks = []
-    in_classes = False
-    for block in blocks:
-        # Copyright
-        if not block.startswith("#"):
-            new_blocks.append(block)
-        # Main title
-        elif re.search(r"^#\s+\S+", block) is not None:
-            new_blocks.append(f"# {new_model_patterns.model_name}\n")
-        # The config starts the part of the doc with the classes.
-        elif not in_classes and old_model_patterns.config_class in block.split("\n")[0]:
-            in_classes = True
-            new_blocks.append(DOC_OVERVIEW_TEMPLATE.format(model_name=new_model_patterns.model_name))
-            new_block, _ = replace_model_patterns(block, old_model_patterns, new_model_patterns)
-            new_blocks.append(new_block)
-        # In classes
-        elif in_classes:
-            in_classes = True
-            block_title = block.split("\n")[0]
-            block_class = re.search(r"^#+\s+(\S.*)$", block_title).groups()[0]
-            new_block, _ = replace_model_patterns(block, old_model_patterns, new_model_patterns)
-
-            if "Tokenizer" in block_class:
-                # We only add the tokenizer if necessary
-                if old_model_patterns.tokenizer_class != new_model_patterns.tokenizer_class:
-                    new_blocks.append(new_block)
-            elif "ImageProcessor" in block_class:
-                # We only add the image processor if necessary
-                if old_model_patterns.image_processor_class != new_model_patterns.image_processor_class:
-                    new_blocks.append(new_block)
-            elif "FeatureExtractor" in block_class:
-                # We only add the feature extractor if necessary
-                if old_model_patterns.feature_extractor_class != new_model_patterns.feature_extractor_class:
-                    new_blocks.append(new_block)
-            elif "Processor" in block_class:
-                # We only add the processor if necessary
-                if old_model_patterns.processor_class != new_model_patterns.processor_class:
-                    new_blocks.append(new_block)
-            elif block_class.startswith("Flax"):
-                # We only add Flax models if in the selected frameworks
-                if "flax" in frameworks:
-                    new_blocks.append(new_block)
-            elif block_class.startswith("TF"):
-                # We only add TF models if in the selected frameworks
-                if "tf" in frameworks:
-                    new_blocks.append(new_block)
-            elif len(block_class.split(" ")) == 1:
-                # We only add PyTorch models if in the selected frameworks
-                if "pt" in frameworks:
-                    new_blocks.append(new_block)
-            else:
-                new_blocks.append(new_block)
-
-    with open(dest_file, "w", encoding="utf-8") as f:
-        f.write("\n".join(new_blocks))
-
-
-def insert_model_in_doc_toc(old_model_patterns, new_model_patterns):
-    """
-    Insert the new model in the doc TOC, in the same section as the old model.
-
-    Args:
-        old_model_patterns (`ModelPatterns`): The patterns for the old model.
-        new_model_patterns (`ModelPatterns`): The patterns for the new model.
-    """
-    toc_file = REPO_PATH / "docs" / "source" / "en" / "_toctree.yml"
-    with open(toc_file, "r", encoding="utf8") as f:
-        content = yaml.safe_load(f)
-
-    # Get to the model API doc
-    api_idx = 0
-    while content[api_idx]["title"] != "API":
-        api_idx += 1
-    api_doc = content[api_idx]["sections"]
-
-    model_idx = 0
-    while api_doc[model_idx]["title"] != "Models":
-        model_idx += 1
-    model_doc = api_doc[model_idx]["sections"]
-
-    # Find the base model in the Toc
-    old_model_type = old_model_patterns.model_type
-    section_idx = 0
-    while section_idx < len(model_doc):
-        sections = [entry["local"] for entry in model_doc[section_idx]["sections"]]
-        if f"model_doc/{old_model_type}" in sections:
-            break
-
-        section_idx += 1
-
-    if section_idx == len(model_doc):
-        old_model = old_model_patterns.model_name
-        new_model = new_model_patterns.model_name
-        print(f"Did not find {old_model} in the table of content, so you will need to add {new_model} manually.")
-        return
-
-    # Add the new model in the same toc
-    toc_entry = {"local": f"model_doc/{new_model_patterns.model_type}", "title": new_model_patterns.model_name}
-    model_doc[section_idx]["sections"].append(toc_entry)
-    model_doc[section_idx]["sections"] = sorted(model_doc[section_idx]["sections"], key=lambda s: s["title"].lower())
-    api_doc[model_idx]["sections"] = model_doc
-    content[api_idx]["sections"] = api_doc
-
-    with open(toc_file, "w", encoding="utf-8") as f:
-        f.write(yaml.dump(content, allow_unicode=True))
-
-
-def create_new_model_like(
-    model_type: str,
-    new_model_patterns: ModelPatterns,
-    add_copied_from: bool = True,
-    frameworks: Optional[List[str]] = None,
-    old_checkpoint: Optional[str] = None,
-):
-    """
-    Creates a new model module like a given model of the Transformers library.
-
-    Args:
-        model_type (`str`): The model type to duplicate (like "bert" or "gpt2")
-        new_model_patterns (`ModelPatterns`): The patterns for the new model.
-        add_copied_from (`bool`, *optional*, defaults to `True`):
-            Whether or not to add "Copied from" statements to all classes in the new model modeling files.
-        frameworks (`List[str]`, *optional*):
-            If passed, will limit the duplicate to the frameworks specified.
-        old_checkpoint (`str`, *optional*):
-            The name of the base checkpoint for the old model. Should be passed along when it can't be automatically
-            recovered from the `model_type`.
-    """
-    # Retrieve all the old model info.
-    model_info = retrieve_info_for_model(model_type, frameworks=frameworks)
-    model_files = model_info["model_files"]
-    old_model_patterns = model_info["model_patterns"]
-    if old_checkpoint is not None:
-        old_model_patterns.checkpoint = old_checkpoint
-    if len(old_model_patterns.checkpoint) == 0:
-        raise ValueError(
-            "The old model checkpoint could not be recovered from the model type. Please pass it to the "
-            "`old_checkpoint` argument."
-        )
-
-    keep_old_processing = True
-    for processing_attr in ["image_processor_class", "feature_extractor_class", "processor_class", "tokenizer_class"]:
-        if getattr(old_model_patterns, processing_attr) != getattr(new_model_patterns, processing_attr):
-            keep_old_processing = False
-
-    model_classes = model_info["model_classes"]
-
-    # 1. We create the module for our new model.
-    old_module_name = model_files["module_name"]
-    module_folder = TRANSFORMERS_PATH / "models" / new_model_patterns.model_lower_cased
-    os.makedirs(module_folder, exist_ok=True)
-
-    files_to_adapt = model_files["model_files"]
-    if keep_old_processing:
-        files_to_adapt = [
-            f
-            for f in files_to_adapt
-            if "tokenization" not in str(f)
-            and "processing" not in str(f)
-            and "feature_extraction" not in str(f)
-            and "image_processing" not in str(f)
-        ]
-
-    os.makedirs(module_folder, exist_ok=True)
-    for module_file in files_to_adapt:
-        new_module_name = module_file.name.replace(
-            old_model_patterns.model_lower_cased, new_model_patterns.model_lower_cased
-        )
-        dest_file = module_folder / new_module_name
-        duplicate_module(
-            module_file,
-            old_model_patterns,
-            new_model_patterns,
-            dest_file=dest_file,
-            add_copied_from=add_copied_from and "modeling" in new_module_name,
-        )
-
-    clean_frameworks_in_init(
-        module_folder / "__init__.py", frameworks=frameworks, keep_processing=not keep_old_processing
-    )
-
-    # 2. We add our new model to the models init and the main init
-    add_content_to_file(
-        TRANSFORMERS_PATH / "models" / "__init__.py",
-        f"    {new_model_patterns.model_lower_cased},",
-        add_after=f"    {old_module_name},",
-        exact_match=True,
-    )
-    add_model_to_main_init(
-        old_model_patterns, new_model_patterns, frameworks=frameworks, with_processing=not keep_old_processing
-    )
-
-    # 3. Add test files
-    files_to_adapt = model_files["test_files"]
-    if keep_old_processing:
-        files_to_adapt = [
-            f
-            for f in files_to_adapt
-            if "tokenization" not in str(f)
-            and "processor" not in str(f)
-            and "feature_extraction" not in str(f)
-            and "image_processing" not in str(f)
-        ]
-
-    def disable_fx_test(filename: Path) -> bool:
-        with open(filename) as fp:
-            content = fp.read()
-        new_content = re.sub(r"fx_compatible\s*=\s*True", "fx_compatible = False", content)
-        with open(filename, "w") as fp:
-            fp.write(new_content)
-        return content != new_content
-
-    disabled_fx_test = False
-
-    tests_folder = REPO_PATH / "tests" / "models" / new_model_patterns.model_lower_cased
-    os.makedirs(tests_folder, exist_ok=True)
-    with open(tests_folder / "__init__.py", "w"):
-        pass
-
-    for test_file in files_to_adapt:
-        new_test_file_name = test_file.name.replace(
-            old_model_patterns.model_lower_cased, new_model_patterns.model_lower_cased
-        )
-        dest_file = test_file.parent.parent / new_model_patterns.model_lower_cased / new_test_file_name
-        duplicate_module(
-            test_file,
-            old_model_patterns,
-            new_model_patterns,
-            dest_file=dest_file,
-            add_copied_from=False,
-            attrs_to_remove=["pipeline_model_mapping", "is_pipeline_test_to_skip"],
-        )
-        disabled_fx_test = disabled_fx_test | disable_fx_test(dest_file)
-
-    if disabled_fx_test:
-        print(
-            "The tests for symbolic tracing with torch.fx were disabled, you can add those once symbolic tracing works"
-            " for your new model."
-        )
-
-    # 4. Add model to auto classes
-    add_model_to_auto_classes(old_model_patterns, new_model_patterns, model_classes)
-
-    # 5. Add doc file
-    doc_file = REPO_PATH / "docs" / "source" / "en" / "model_doc" / f"{old_model_patterns.model_type}.md"
-    duplicate_doc_file(doc_file, old_model_patterns, new_model_patterns, frameworks=frameworks)
-    insert_model_in_doc_toc(old_model_patterns, new_model_patterns)
-
-    # 6. Warn the user for duplicate patterns
-    if old_model_patterns.model_type == old_model_patterns.checkpoint:
-        print(
-            "The model you picked has the same name for the model type and the checkpoint name "
-            f"({old_model_patterns.model_type}). As a result, it's possible some places where the new checkpoint "
-            f"should be, you have {new_model_patterns.model_type} instead. You should search for all instances of "
-            f"{new_model_patterns.model_type} in the new files and check they're not badly used as checkpoints."
-        )
-    elif old_model_patterns.model_lower_cased == old_model_patterns.checkpoint:
-        print(
-            "The model you picked has the same name for the model type and the checkpoint name "
-            f"({old_model_patterns.model_lower_cased}). As a result, it's possible some places where the new "
-            f"checkpoint should be, you have {new_model_patterns.model_lower_cased} instead. You should search for "
-            f"all instances of {new_model_patterns.model_lower_cased} in the new files and check they're not badly "
-            "used as checkpoints."
-        )
-    if (
-        old_model_patterns.model_type == old_model_patterns.model_lower_cased
-        and new_model_patterns.model_type != new_model_patterns.model_lower_cased
-    ):
-        print(
-            "The model you picked has the same name for the model type and the lowercased model name "
-            f"({old_model_patterns.model_lower_cased}). As a result, it's possible some places where the new "
-            f"model type should be, you have {new_model_patterns.model_lower_cased} instead. You should search for "
-            f"all instances of {new_model_patterns.model_lower_cased} in the new files and check they're not badly "
-            "used as the model type."
-        )
-
-    if not keep_old_processing and old_model_patterns.tokenizer_class is not None:
-        print(
-            "The constants at the start of the new tokenizer file created needs to be manually fixed. If your new "
-            "model has a tokenizer fast, you will also need to manually add the converter in the "
-            "`SLOW_TO_FAST_CONVERTERS` constant of `convert_slow_tokenizer.py`."
-        )
-
-
-def add_new_model_like_command_factory(args: Namespace):
-    return AddNewModelLikeCommand(config_file=args.config_file, path_to_repo=args.path_to_repo)
-
-
-class AddNewModelLikeCommand(BaseTransformersCLICommand):
-    @staticmethod
-    def register_subcommand(parser: ArgumentParser):
-        add_new_model_like_parser = parser.add_parser("add-new-model-like")
-        add_new_model_like_parser.add_argument(
-            "--config_file", type=str, help="A file with all the information for this model creation."
-        )
-        add_new_model_like_parser.add_argument(
-            "--path_to_repo", type=str, help="When not using an editable install, the path to the Transformers repo."
-        )
-        add_new_model_like_parser.set_defaults(func=add_new_model_like_command_factory)
-
-    def __init__(self, config_file=None, path_to_repo=None, *args):
-        if config_file is not None:
-            with open(config_file, "r", encoding="utf-8") as f:
-                config = json.load(f)
-            self.old_model_type = config["old_model_type"]
-            self.model_patterns = ModelPatterns(**config["new_model_patterns"])
-            self.add_copied_from = config.get("add_copied_from", True)
-            self.frameworks = config.get("frameworks", get_default_frameworks())
-            self.old_checkpoint = config.get("old_checkpoint", None)
-        else:
-            (
-                self.old_model_type,
-                self.model_patterns,
-                self.add_copied_from,
-                self.frameworks,
-                self.old_checkpoint,
-            ) = get_user_input()
-
-        self.path_to_repo = path_to_repo
-
-    def run(self):
-        if self.path_to_repo is not None:
-            # Adapt constants
-            global TRANSFORMERS_PATH
-            global REPO_PATH
-
-            REPO_PATH = Path(self.path_to_repo)
-            TRANSFORMERS_PATH = REPO_PATH / "src" / "transformers"
-
-        create_new_model_like(
-            model_type=self.old_model_type,
-            new_model_patterns=self.model_patterns,
-            add_copied_from=self.add_copied_from,
-            frameworks=self.frameworks,
-            old_checkpoint=self.old_checkpoint,
-        )
-
-
-def get_user_field(
-    question: str,
-    default_value: Optional[str] = None,
-    is_valid_answer: Optional[Callable] = None,
-    convert_to: Optional[Callable] = None,
-    fallback_message: Optional[str] = None,
-) -> Any:
-    """
-    A utility function that asks a question to the user to get an answer, potentially looping until it gets a valid
-    answer.
-
-    Args:
-        question (`str`): The question to ask the user.
-        default_value (`str`, *optional*): A potential default value that will be used when the answer is empty.
-        is_valid_answer (`Callable`, *optional*):
-            If set, the question will be asked until this function returns `True` on the provided answer.
-        convert_to (`Callable`, *optional*):
-            If set, the answer will be passed to this function. If this function raises an error on the procided
-            answer, the question will be asked again.
-        fallback_message (`str`, *optional*):
-            A message that will be displayed each time the question is asked again to the user.
-
-    Returns:
-        `Any`: The answer provided by the user (or the default), passed through the potential conversion function.
-    """
-    if not question.endswith(" "):
-        question = question + " "
-    if default_value is not None:
-        question = f"{question} [{default_value}] "
-
-    valid_answer = False
-    while not valid_answer:
-        answer = input(question)
-        if default_value is not None and len(answer) == 0:
-            answer = default_value
-        if is_valid_answer is not None:
-            valid_answer = is_valid_answer(answer)
-        elif convert_to is not None:
-            try:
-                answer = convert_to(answer)
-                valid_answer = True
-            except Exception:
-                valid_answer = False
-        else:
-            valid_answer = True
-
-        if not valid_answer:
-            print(fallback_message)
-
-    return answer
-
-
-def convert_to_bool(x: str) -> bool:
-    """
-    Converts a string to a bool.
-    """
-    if x.lower() in ["1", "y", "yes", "true"]:
-        return True
-    if x.lower() in ["0", "n", "no", "false"]:
-        return False
-    raise ValueError(f"{x} is not a value that can be converted to a bool.")
-
-
-def get_user_input():
-    """
-    Ask the user for the necessary inputs to add the new model.
-    """
-    model_types = list(auto_module.configuration_auto.MODEL_NAMES_MAPPING.keys())
-
-    # Get old model type
-    valid_model_type = False
-    while not valid_model_type:
-        old_model_type = input(
-            "What is the model you would like to duplicate? Please provide the lowercase `model_type` (e.g. roberta): "
-        )
-        if old_model_type in model_types:
-            valid_model_type = True
-        else:
-            print(f"{old_model_type} is not a valid model type.")
-            near_choices = difflib.get_close_matches(old_model_type, model_types)
-            if len(near_choices) >= 1:
-                if len(near_choices) > 1:
-                    near_choices = " or ".join(near_choices)
-                print(f"Did you mean {near_choices}?")
-
-    old_model_info = retrieve_info_for_model(old_model_type)
-    old_tokenizer_class = old_model_info["model_patterns"].tokenizer_class
-    old_image_processor_class = old_model_info["model_patterns"].image_processor_class
-    old_feature_extractor_class = old_model_info["model_patterns"].feature_extractor_class
-    old_processor_class = old_model_info["model_patterns"].processor_class
-    old_frameworks = old_model_info["frameworks"]
-
-    old_checkpoint = None
-    if len(old_model_info["model_patterns"].checkpoint) == 0:
-        old_checkpoint = get_user_field(
-            "We couldn't find the name of the base checkpoint for that model, please enter it here."
-        )
-
-    model_name = get_user_field(
-        "What is the name (with no special casing) for your new model in the paper (e.g. RoBERTa)? "
-    )
-    default_patterns = ModelPatterns(model_name, model_name)
-
-    model_type = get_user_field(
-        "What identifier would you like to use for the `model_type` of this model? ",
-        default_value=default_patterns.model_type,
-    )
-    model_lower_cased = get_user_field(
-        "What lowercase name would you like to use for the module (folder) of this model? ",
-        default_value=default_patterns.model_lower_cased,
-    )
-    model_camel_cased = get_user_field(
-        "What prefix (camel-cased) would you like to use for the model classes of this model (e.g. Roberta)? ",
-        default_value=default_patterns.model_camel_cased,
-    )
-    model_upper_cased = get_user_field(
-        "What prefix (upper-cased) would you like to use for the constants relative to this model? ",
-        default_value=default_patterns.model_upper_cased,
-    )
-    config_class = get_user_field(
-        "What will be the name of the config class for this model? ", default_value=f"{model_camel_cased}Config"
-    )
-    checkpoint = get_user_field(
-        "Please give a checkpoint identifier (on the model Hub) for this new model (e.g. facebook/roberta-base): "
-    )
-
-    old_processing_classes = [
-        c
-        for c in [old_image_processor_class, old_feature_extractor_class, old_tokenizer_class, old_processor_class]
-        if c is not None
-    ]
-    old_processing_classes = ", ".join(old_processing_classes)
-    keep_processing = get_user_field(
-        f"Will your new model use the same processing class as {old_model_type} ({old_processing_classes}) (yes/no)? ",
-        convert_to=convert_to_bool,
-        fallback_message="Please answer yes/no, y/n, true/false or 1/0. ",
-    )
-    if keep_processing:
-        image_processor_class = old_image_processor_class
-        feature_extractor_class = old_feature_extractor_class
-        processor_class = old_processor_class
-        tokenizer_class = old_tokenizer_class
-    else:
-        if old_tokenizer_class is not None:
-            tokenizer_class = get_user_field(
-                "What will be the name of the tokenizer class for this model? ",
-                default_value=f"{model_camel_cased}Tokenizer",
-            )
-        else:
-            tokenizer_class = None
-        if old_image_processor_class is not None:
-            image_processor_class = get_user_field(
-                "What will be the name of the image processor class for this model? ",
-                default_value=f"{model_camel_cased}ImageProcessor",
-            )
-        else:
-            image_processor_class = None
-        if old_feature_extractor_class is not None:
-            feature_extractor_class = get_user_field(
-                "What will be the name of the feature extractor class for this model? ",
-                default_value=f"{model_camel_cased}FeatureExtractor",
-            )
-        else:
-            feature_extractor_class = None
-        if old_processor_class is not None:
-            processor_class = get_user_field(
-                "What will be the name of the processor class for this model? ",
-                default_value=f"{model_camel_cased}Processor",
-            )
-        else:
-            processor_class = None
-
-    model_patterns = ModelPatterns(
-        model_name,
-        checkpoint,
-        model_type=model_type,
-        model_lower_cased=model_lower_cased,
-        model_camel_cased=model_camel_cased,
-        model_upper_cased=model_upper_cased,
-        config_class=config_class,
-        tokenizer_class=tokenizer_class,
-        image_processor_class=image_processor_class,
-        feature_extractor_class=feature_extractor_class,
-        processor_class=processor_class,
-    )
-
-    add_copied_from = get_user_field(
-        "Should we add # Copied from statements when creating the new modeling file (yes/no)? ",
-        convert_to=convert_to_bool,
-        default_value="yes",
-        fallback_message="Please answer yes/no, y/n, true/false or 1/0.",
-    )
-
-    all_frameworks = get_user_field(
-        "Should we add a version of your new model in all the frameworks implemented by"
-        f" {old_model_type} ({old_frameworks}) (yes/no)? ",
-        convert_to=convert_to_bool,
-        default_value="yes",
-        fallback_message="Please answer yes/no, y/n, true/false or 1/0.",
-    )
-    if all_frameworks:
-        frameworks = None
-    else:
-        frameworks = get_user_field(
-            "Please enter the list of framworks you want (pt, tf, flax) separated by spaces",
-            is_valid_answer=lambda x: all(p in ["pt", "tf", "flax"] for p in x.split(" ")),
-        )
-        frameworks = list(set(frameworks.split(" ")))
-
-    return (old_model_type, model_patterns, add_copied_from, frameworks, old_checkpoint)
diff --git a/spaces/yizhangliu/Grounded-Segment-Anything/transformers_4_35_0/models/big_bird/tokenization_big_bird_fast.py b/spaces/yizhangliu/Grounded-Segment-Anything/transformers_4_35_0/models/big_bird/tokenization_big_bird_fast.py
deleted file mode 100644
index 24fc33d805296259c8f22f827226ae0c225ce92f..0000000000000000000000000000000000000000
--- a/spaces/yizhangliu/Grounded-Segment-Anything/transformers_4_35_0/models/big_bird/tokenization_big_bird_fast.py
+++ /dev/null
@@ -1,261 +0,0 @@
-# coding=utf-8
-# Copyright 2018 Google AI, Google Brain and the HuggingFace Inc. team.
-#
-# Licensed under the Apache License, Version 2.0 (the "License");
-# you may not use this file except in compliance with the License.
-# You may obtain a copy of the License at
-#
-#     http://www.apache.org/licenses/LICENSE-2.0
-#
-# Unless required by applicable law or agreed to in writing, software
-# distributed under the License is distributed on an "AS IS" BASIS,
-# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
-# See the License for the specific language governing permissions and
-# limitations under the License.
-""" Tokenization classes for Big Bird model."""
-
-
-import os
-from shutil import copyfile
-from typing import List, Optional, Tuple
-
-from ...tokenization_utils import AddedToken
-from ...tokenization_utils_fast import PreTrainedTokenizerFast
-from ...utils import is_sentencepiece_available, logging
-
-
-if is_sentencepiece_available():
-    from .tokenization_big_bird import BigBirdTokenizer
-else:
-    BigBirdTokenizer = None
-
-logger = logging.get_logger(__name__)
-VOCAB_FILES_NAMES = {"vocab_file": "spiece.model", "tokenizer_file": "tokenizer.json"}
-
-PRETRAINED_VOCAB_FILES_MAP = {
-    "vocab_file": {
-        "google/bigbird-roberta-base": "https://huggingface.co/google/bigbird-roberta-base/resolve/main/spiece.model",
-        "google/bigbird-roberta-large": (
-            "https://huggingface.co/google/bigbird-roberta-large/resolve/main/spiece.model"
-        ),
-        "google/bigbird-base-trivia-itc": (
-            "https://huggingface.co/google/bigbird-base-trivia-itc/resolve/main/spiece.model"
-        ),
-    },
-    "tokenizer_file": {
-        "google/bigbird-roberta-base": (
-            "https://huggingface.co/google/bigbird-roberta-base/resolve/main/tokenizer.json"
-        ),
-        "google/bigbird-roberta-large": (
-            "https://huggingface.co/google/bigbird-roberta-large/resolve/main/tokenizer.json"
-        ),
-        "google/bigbird-base-trivia-itc": (
-            "https://huggingface.co/google/bigbird-base-trivia-itc/resolve/main/tokenizer.json"
-        ),
-    },
-}
-
-PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES = {
-    "google/bigbird-roberta-base": 4096,
-    "google/bigbird-roberta-large": 4096,
-    "google/bigbird-base-trivia-itc": 4096,
-}
-
-
-SPIECE_UNDERLINE = "▁"
-
-
-class BigBirdTokenizerFast(PreTrainedTokenizerFast):
-    """
-    Construct a "fast" BigBird tokenizer (backed by HuggingFace's *tokenizers* library). Based on
-    [Unigram](https://huggingface.co/docs/tokenizers/python/latest/components.html?highlight=unigram#models). This
-    tokenizer inherits from [`PreTrainedTokenizerFast`] which contains most of the main methods. Users should refer to
-    this superclass for more information regarding those methods
-
-    Args:
-        vocab_file (`str`):
-            [SentencePiece](https://github.com/google/sentencepiece) file (generally has a *.spm* extension) that
-            contains the vocabulary necessary to instantiate a tokenizer.
-        bos_token (`str`, *optional*, defaults to `"<s>"`):
-            The beginning of sequence token that was used during pretraining. Can be used a sequence classifier token.
-
-            <Tip>
-
-            When building a sequence using special tokens, this is not the token that is used for the beginning of
-            sequence. The token used is the `cls_token`.
-
-            </Tip>
-
-        eos_token (`str`, *optional*, defaults to `"</s>"`):
-            The end of sequence token. .. note:: When building a sequence using special tokens, this is not the token
-            that is used for the end of sequence. The token used is the `sep_token`.
-        unk_token (`str`, *optional*, defaults to `"<unk>"`):
-            The unknown token. A token that is not in the vocabulary cannot be converted to an ID and is set to be this
-            token instead.
-        sep_token (`str`, *optional*, defaults to `"[SEP]"`):
-            The separator token, which is used when building a sequence from multiple sequences, e.g. two sequences for
-            sequence classification or for a text and a question for question answering. It is also used as the last
-            token of a sequence built with special tokens.
-        pad_token (`str`, *optional*, defaults to `"<pad>"`):
-            The token used for padding, for example when batching sequences of different lengths.
-        cls_token (`str`, *optional*, defaults to `"[CLS]"`):
-            The classifier token which is used when doing sequence classification (classification of the whole sequence
-            instead of per-token classification). It is the first token of the sequence when built with special tokens.
-        mask_token (`str`, *optional*, defaults to `"[MASK]"`):
-            The token used for masking values. This is the token used when training this model with masked language
-            modeling. This is the token which the model will try to predict.
-    """
-
-    vocab_files_names = VOCAB_FILES_NAMES
-    pretrained_vocab_files_map = PRETRAINED_VOCAB_FILES_MAP
-    max_model_input_sizes = PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES
-    slow_tokenizer_class = BigBirdTokenizer
-    model_input_names = ["input_ids", "attention_mask"]
-    prefix_tokens: List[int] = []
-
-    def __init__(
-        self,
-        vocab_file=None,
-        tokenizer_file=None,
-        unk_token="<unk>",
-        bos_token="<s>",
-        eos_token="</s>",
-        pad_token="<pad>",
-        sep_token="[SEP]",
-        mask_token="[MASK]",
-        cls_token="[CLS]",
-        **kwargs,
-    ):
-        bos_token = AddedToken(bos_token, lstrip=False, rstrip=False) if isinstance(bos_token, str) else bos_token
-        eos_token = AddedToken(eos_token, lstrip=False, rstrip=False) if isinstance(eos_token, str) else eos_token
-        unk_token = AddedToken(unk_token, lstrip=False, rstrip=False) if isinstance(unk_token, str) else unk_token
-        pad_token = AddedToken(pad_token, lstrip=False, rstrip=False) if isinstance(pad_token, str) else pad_token
-        cls_token = AddedToken(cls_token, lstrip=False, rstrip=False) if isinstance(cls_token, str) else cls_token
-        sep_token = AddedToken(sep_token, lstrip=False, rstrip=False) if isinstance(sep_token, str) else sep_token
-
-        # Mask token behave like a normal word, i.e. include the space before it
-        mask_token = AddedToken(mask_token, lstrip=True, rstrip=False) if isinstance(mask_token, str) else mask_token
-
-        super().__init__(
-            vocab_file,
-            tokenizer_file=tokenizer_file,
-            bos_token=bos_token,
-            eos_token=eos_token,
-            unk_token=unk_token,
-            sep_token=sep_token,
-            pad_token=pad_token,
-            cls_token=cls_token,
-            mask_token=mask_token,
-            **kwargs,
-        )
-
-        self.vocab_file = vocab_file
-
-    @property
-    def can_save_slow_tokenizer(self) -> bool:
-        return os.path.isfile(self.vocab_file) if self.vocab_file else False
-
-    def build_inputs_with_special_tokens(
-        self, token_ids_0: List[int], token_ids_1: Optional[List[int]] = None
-    ) -> List[int]:
-        """
-        Build model inputs from a sequence or a pair of sequence for sequence classification tasks by concatenating and
-        adding special tokens. An BigBird sequence has the following format:
-
-        - single sequence: `[CLS] X [SEP]`
-        - pair of sequences: `[CLS] A [SEP] B [SEP]`
-
-        Args:
-            token_ids_0 (`List[int]`):
-                List of IDs to which the special tokens will be added
-            token_ids_1 (`List[int]`, *optional*):
-                Optional second list of IDs for sequence pairs.
-
-        Returns:
-            `List[int]`: list of [input IDs](../glossary#input-ids) with the appropriate special tokens.
-        """
-        sep = [self.sep_token_id]
-        cls = [self.cls_token_id]
-        if token_ids_1 is None:
-            return cls + token_ids_0 + sep
-        return cls + token_ids_0 + sep + token_ids_1 + sep
-
-    def get_special_tokens_mask(
-        self, token_ids_0: List[int], token_ids_1: Optional[List[int]] = None, already_has_special_tokens: bool = False
-    ) -> List[int]:
-        """
-        Retrieves sequence ids from a token list that has no special tokens added. This method is called when adding
-        special tokens using the tokenizer `prepare_for_model` method.
-
-        Args:
-            token_ids_0 (`List[int]`):
-                List of ids.
-            token_ids_1 (`List[int]`, *optional*):
-                Optional second list of IDs for sequence pairs.
-            already_has_special_tokens (`bool`, *optional*, defaults to `False`):
-                Set to True if the token list is already formatted with special tokens for the model
-
-        Returns:
-            `List[int]`: A list of integers in the range [0, 1]: 1 for a special token, 0 for a sequence token.
-        """
-
-        if already_has_special_tokens:
-            if token_ids_1 is not None:
-                raise ValueError(
-                    "You should not supply a second sequence if the provided sequence of "
-                    "ids is already formatted with special tokens for the model."
-                )
-            return [1 if x in [self.sep_token_id, self.cls_token_id] else 0 for x in token_ids_0]
-
-        if token_ids_1 is None:
-            return [1] + ([0] * len(token_ids_0)) + [1]
-        return [1] + ([0] * len(token_ids_0)) + [1] + ([0] * len(token_ids_1)) + [1]
-
-    def create_token_type_ids_from_sequences(
-        self, token_ids_0: List[int], token_ids_1: Optional[List[int]] = None
-    ) -> List[int]:
-        """
-        Creates a mask from the two sequences passed to be used in a sequence-pair classification task. An ALBERT
-        sequence pair mask has the following format:
-
-        ```
-        0 0 0 0 0 0 0 0 0 0 0 1 1 1 1 1 1 1 1 1
-        | first sequence    | second sequence |
-        ```
-
-        if token_ids_1 is None, only returns the first portion of the mask (0s).
-
-        Args:
-            token_ids_0 (`List[int]`):
-                List of ids.
-            token_ids_1 (`List[int]`, *optional*):
-                Optional second list of IDs for sequence pairs.
-
-        Returns:
-            `List[int]`: List of [token type IDs](../glossary#token-type-ids) according to the given sequence(s).
-        """
-        sep = [self.sep_token_id]
-        cls = [self.cls_token_id]
-
-        if token_ids_1 is None:
-            return len(cls + token_ids_0 + sep) * [0]
-        return len(cls + token_ids_0 + sep) * [0] + len(token_ids_1 + sep) * [1]
-
-    def save_vocabulary(self, save_directory: str, filename_prefix: Optional[str] = None) -> Tuple[str]:
-        if not self.can_save_slow_tokenizer:
-            raise ValueError(
-                "Your fast tokenizer does not have the necessary information to save the vocabulary for a slow "
-                "tokenizer."
-            )
-
-        if not os.path.isdir(save_directory):
-            logger.error(f"Vocabulary path ({save_directory}) should be a directory")
-            return
-        out_vocab_file = os.path.join(
-            save_directory, (filename_prefix + "-" if filename_prefix else "") + VOCAB_FILES_NAMES["vocab_file"]
-        )
-
-        if os.path.abspath(self.vocab_file) != os.path.abspath(out_vocab_file):
-            copyfile(self.vocab_file, out_vocab_file)
-
-        return (out_vocab_file,)
diff --git a/spaces/yizhangliu/Grounded-Segment-Anything/transformers_4_35_0/models/megatron_bert/configuration_megatron_bert.py b/spaces/yizhangliu/Grounded-Segment-Anything/transformers_4_35_0/models/megatron_bert/configuration_megatron_bert.py
deleted file mode 100644
index db9b67090ac727252e8825ef5c4eab287b6eec0a..0000000000000000000000000000000000000000
--- a/spaces/yizhangliu/Grounded-Segment-Anything/transformers_4_35_0/models/megatron_bert/configuration_megatron_bert.py
+++ /dev/null
@@ -1,129 +0,0 @@
-# coding=utf-8
-# Copyright 2021- NVIDIA Corporation and The HuggingFace Inc. team. All rights reserved.
-#
-# Licensed under the Apache License, Version 2.0 (the "License");
-# you may not use this file except in compliance with the License.
-# You may obtain a copy of the License at
-#
-#     http://www.apache.org/licenses/LICENSE-2.0
-#
-# Unless required by applicable law or agreed to in writing, software
-# distributed under the License is distributed on an "AS IS" BASIS,
-# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
-# See the License for the specific language governing permissions and
-# limitations under the License.
-""" MEGATRON_BERT model configuration"""
-
-from ...configuration_utils import PretrainedConfig
-from ...utils import logging
-
-
-logger = logging.get_logger(__name__)
-
-MEGATRON_BERT_PRETRAINED_CONFIG_ARCHIVE_MAP = {
-    # See all MEGATRON_BERT models at https://huggingface.co/models?filter=bert
-}
-
-
-class MegatronBertConfig(PretrainedConfig):
-    r"""
-    This is the configuration class to store the configuration of a [`MegatronBertModel`]. It is used to instantiate a
-    MEGATRON_BERT model according to the specified arguments, defining the model architecture. Instantiating a
-    configuration with the defaults will yield a similar configuration to that of the MEGATRON_BERT
-    [nvidia/megatron-bert-uncased-345m](https://huggingface.co/nvidia/megatron-bert-uncased-345m) architecture.
-
-    Configuration objects inherit from [`PretrainedConfig`] and can be used to control the model outputs. Read the
-    documentation from [`PretrainedConfig`] for more information.
-
-
-    Args:
-        vocab_size (`int`, *optional*, defaults to 29056):
-            Vocabulary size of the MEGATRON_BERT model. Defines the number of different tokens that can be represented
-            by the `inputs_ids` passed when calling [`MegatronBertModel`].
-        hidden_size (`int`, *optional*, defaults to 1024):
-            Dimensionality of the encoder layers and the pooler layer.
-        num_hidden_layers (`int`, *optional*, defaults to 24):
-            Number of hidden layers in the Transformer encoder.
-        num_attention_heads (`int`, *optional*, defaults to 16):
-            Number of attention heads for each attention layer in the Transformer encoder.
-        intermediate_size (`int`, *optional*, defaults to 4096):
-            Dimensionality of the "intermediate" (often named feed-forward) layer in the Transformer encoder.
-        hidden_act (`str` or `Callable`, *optional*, defaults to `"gelu"`):
-            The non-linear activation function (function or string) in the encoder and pooler. If string, `"gelu"`,
-            `"relu"`, `"silu"` and `"gelu_new"` are supported.
-        hidden_dropout_prob (`float`, *optional*, defaults to 0.1):
-            The dropout probability for all fully connected layers in the embeddings, encoder, and pooler.
-        attention_probs_dropout_prob (`float`, *optional*, defaults to 0.1):
-            The dropout ratio for the attention probabilities.
-        max_position_embeddings (`int`, *optional*, defaults to 512):
-            The maximum sequence length that this model might ever be used with. Typically set this to something large
-            just in case (e.g., 512 or 1024 or 2048).
-        type_vocab_size (`int`, *optional*, defaults to 2):
-            The vocabulary size of the `token_type_ids` passed when calling [`MegatronBertModel`].
-        initializer_range (`float`, *optional*, defaults to 0.02):
-            The standard deviation of the truncated_normal_initializer for initializing all weight matrices.
-        layer_norm_eps (`float`, *optional*, defaults to 1e-12):
-            The epsilon used by the layer normalization layers.
-        position_embedding_type (`str`, *optional*, defaults to `"absolute"`):
-            Type of position embedding. Choose one of `"absolute"`, `"relative_key"`, `"relative_key_query"`. For
-            positional embeddings use `"absolute"`. For more information on `"relative_key"`, please refer to
-            [Self-Attention with Relative Position Representations (Shaw et al.)](https://arxiv.org/abs/1803.02155).
-            For more information on `"relative_key_query"`, please refer to *Method 4* in [Improve Transformer Models
-            with Better Relative Position Embeddings (Huang et al.)](https://arxiv.org/abs/2009.13658).
-        is_decoder (`bool`, *optional*, defaults to `False`):
-            Whether the model is used as a decoder or not. If `False`, the model is used as an encoder.
-        use_cache (`bool`, *optional*, defaults to `True`):
-            Whether or not the model should return the last key/values attentions (not used by all models). Only
-            relevant if `config.is_decoder=True`.
-
-    Examples:
-
-    ```python
-    >>> from transformers import MegatronBertConfig, MegatronBertModel
-
-    >>> # Initializing a MEGATRON_BERT bert-base-uncased style configuration
-    >>> configuration = MegatronBertConfig()
-
-    >>> # Initializing a model (with random weights) from the bert-base-uncased style configuration
-    >>> model = MegatronBertModel(configuration)
-
-    >>> # Accessing the model configuration
-    >>> configuration = model.config
-    ```"""
-    model_type = "megatron-bert"
-
-    def __init__(
-        self,
-        vocab_size=29056,
-        hidden_size=1024,
-        num_hidden_layers=24,
-        num_attention_heads=16,
-        intermediate_size=4096,
-        hidden_act="gelu",
-        hidden_dropout_prob=0.1,
-        attention_probs_dropout_prob=0.1,
-        max_position_embeddings=512,
-        type_vocab_size=2,
-        initializer_range=0.02,
-        layer_norm_eps=1e-12,
-        pad_token_id=0,
-        position_embedding_type="absolute",
-        use_cache=True,
-        **kwargs,
-    ):
-        super().__init__(pad_token_id=pad_token_id, **kwargs)
-
-        self.vocab_size = vocab_size
-        self.hidden_size = hidden_size
-        self.num_hidden_layers = num_hidden_layers
-        self.num_attention_heads = num_attention_heads
-        self.hidden_act = hidden_act
-        self.intermediate_size = intermediate_size
-        self.hidden_dropout_prob = hidden_dropout_prob
-        self.attention_probs_dropout_prob = attention_probs_dropout_prob
-        self.max_position_embeddings = max_position_embeddings
-        self.type_vocab_size = type_vocab_size
-        self.initializer_range = initializer_range
-        self.layer_norm_eps = layer_norm_eps
-        self.position_embedding_type = position_embedding_type
-        self.use_cache = use_cache
diff --git a/spaces/yl12053/so-vits-4.1-Matikanefukukitaru/diffusion/how to export onnx.md b/spaces/yl12053/so-vits-4.1-Matikanefukukitaru/diffusion/how to export onnx.md
deleted file mode 100644
index 6d22719fd1a8e9d034e6224cc95f4b50d44a0320..0000000000000000000000000000000000000000
--- a/spaces/yl12053/so-vits-4.1-Matikanefukukitaru/diffusion/how to export onnx.md	
+++ /dev/null
@@ -1,4 +0,0 @@
-- Open [onnx_export](onnx_export.py)
-- project_name = "dddsp" change "project_name" to your project name
-- model_path = f'{project_name}/model_500000.pt' change "model_path" to your model path
-- Run
\ No newline at end of file
diff --git a/spaces/ynhe/AskAnything/models/grit_src/third_party/CenterNet2/detectron2/structures/boxes.py b/spaces/ynhe/AskAnything/models/grit_src/third_party/CenterNet2/detectron2/structures/boxes.py
deleted file mode 100644
index ae543c617a33245075b001f383f41775efb0b63d..0000000000000000000000000000000000000000
--- a/spaces/ynhe/AskAnything/models/grit_src/third_party/CenterNet2/detectron2/structures/boxes.py
+++ /dev/null
@@ -1,423 +0,0 @@
-# Copyright (c) Facebook, Inc. and its affiliates.
-import math
-import numpy as np
-from enum import IntEnum, unique
-from typing import List, Tuple, Union
-import torch
-from torch import device
-
-_RawBoxType = Union[List[float], Tuple[float, ...], torch.Tensor, np.ndarray]
-
-
-@unique
-class BoxMode(IntEnum):
-    """
-    Enum of different ways to represent a box.
-    """
-
-    XYXY_ABS = 0
-    """
-    (x0, y0, x1, y1) in absolute floating points coordinates.
-    The coordinates in range [0, width or height].
-    """
-    XYWH_ABS = 1
-    """
-    (x0, y0, w, h) in absolute floating points coordinates.
-    """
-    XYXY_REL = 2
-    """
-    Not yet supported!
-    (x0, y0, x1, y1) in range [0, 1]. They are relative to the size of the image.
-    """
-    XYWH_REL = 3
-    """
-    Not yet supported!
-    (x0, y0, w, h) in range [0, 1]. They are relative to the size of the image.
-    """
-    XYWHA_ABS = 4
-    """
-    (xc, yc, w, h, a) in absolute floating points coordinates.
-    (xc, yc) is the center of the rotated box, and the angle a is in degrees ccw.
-    """
-
-    @staticmethod
-    def convert(box: _RawBoxType, from_mode: "BoxMode", to_mode: "BoxMode") -> _RawBoxType:
-        """
-        Args:
-            box: can be a k-tuple, k-list or an Nxk array/tensor, where k = 4 or 5
-            from_mode, to_mode (BoxMode)
-
-        Returns:
-            The converted box of the same type.
-        """
-        if from_mode == to_mode:
-            return box
-
-        original_type = type(box)
-        is_numpy = isinstance(box, np.ndarray)
-        single_box = isinstance(box, (list, tuple))
-        if single_box:
-            assert len(box) == 4 or len(box) == 5, (
-                "BoxMode.convert takes either a k-tuple/list or an Nxk array/tensor,"
-                " where k == 4 or 5"
-            )
-            arr = torch.tensor(box)[None, :]
-        else:
-            # avoid modifying the input box
-            if is_numpy:
-                arr = torch.from_numpy(np.asarray(box)).clone()
-            else:
-                arr = box.clone()
-
-        assert to_mode not in [BoxMode.XYXY_REL, BoxMode.XYWH_REL] and from_mode not in [
-            BoxMode.XYXY_REL,
-            BoxMode.XYWH_REL,
-        ], "Relative mode not yet supported!"
-
-        if from_mode == BoxMode.XYWHA_ABS and to_mode == BoxMode.XYXY_ABS:
-            assert (
-                arr.shape[-1] == 5
-            ), "The last dimension of input shape must be 5 for XYWHA format"
-            original_dtype = arr.dtype
-            arr = arr.double()
-
-            w = arr[:, 2]
-            h = arr[:, 3]
-            a = arr[:, 4]
-            c = torch.abs(torch.cos(a * math.pi / 180.0))
-            s = torch.abs(torch.sin(a * math.pi / 180.0))
-            # This basically computes the horizontal bounding rectangle of the rotated box
-            new_w = c * w + s * h
-            new_h = c * h + s * w
-
-            # convert center to top-left corner
-            arr[:, 0] -= new_w / 2.0
-            arr[:, 1] -= new_h / 2.0
-            # bottom-right corner
-            arr[:, 2] = arr[:, 0] + new_w
-            arr[:, 3] = arr[:, 1] + new_h
-
-            arr = arr[:, :4].to(dtype=original_dtype)
-        elif from_mode == BoxMode.XYWH_ABS and to_mode == BoxMode.XYWHA_ABS:
-            original_dtype = arr.dtype
-            arr = arr.double()
-            arr[:, 0] += arr[:, 2] / 2.0
-            arr[:, 1] += arr[:, 3] / 2.0
-            angles = torch.zeros((arr.shape[0], 1), dtype=arr.dtype)
-            arr = torch.cat((arr, angles), axis=1).to(dtype=original_dtype)
-        else:
-            if to_mode == BoxMode.XYXY_ABS and from_mode == BoxMode.XYWH_ABS:
-                arr[:, 2] += arr[:, 0]
-                arr[:, 3] += arr[:, 1]
-            elif from_mode == BoxMode.XYXY_ABS and to_mode == BoxMode.XYWH_ABS:
-                arr[:, 2] -= arr[:, 0]
-                arr[:, 3] -= arr[:, 1]
-            else:
-                raise NotImplementedError(
-                    "Conversion from BoxMode {} to {} is not supported yet".format(
-                        from_mode, to_mode
-                    )
-                )
-
-        if single_box:
-            return original_type(arr.flatten().tolist())
-        if is_numpy:
-            return arr.numpy()
-        else:
-            return arr
-
-
-class Boxes:
-    """
-    This structure stores a list of boxes as a Nx4 torch.Tensor.
-    It supports some common methods about boxes
-    (`area`, `clip`, `nonempty`, etc),
-    and also behaves like a Tensor
-    (support indexing, `to(device)`, `.device`, and iteration over all boxes)
-
-    Attributes:
-        tensor (torch.Tensor): float matrix of Nx4. Each row is (x1, y1, x2, y2).
-    """
-
-    def __init__(self, tensor: torch.Tensor):
-        """
-        Args:
-            tensor (Tensor[float]): a Nx4 matrix.  Each row is (x1, y1, x2, y2).
-        """
-        device = tensor.device if isinstance(tensor, torch.Tensor) else torch.device("cpu")
-        tensor = torch.as_tensor(tensor, dtype=torch.float32, device=device)
-        if tensor.numel() == 0:
-            # Use reshape, so we don't end up creating a new tensor that does not depend on
-            # the inputs (and consequently confuses jit)
-            tensor = tensor.reshape((-1, 4)).to(dtype=torch.float32, device=device)
-        assert tensor.dim() == 2 and tensor.size(-1) == 4, tensor.size()
-
-        self.tensor = tensor
-
-    def clone(self) -> "Boxes":
-        """
-        Clone the Boxes.
-
-        Returns:
-            Boxes
-        """
-        return Boxes(self.tensor.clone())
-
-    def to(self, device: torch.device):
-        # Boxes are assumed float32 and does not support to(dtype)
-        return Boxes(self.tensor.to(device=device))
-
-    def area(self) -> torch.Tensor:
-        """
-        Computes the area of all the boxes.
-
-        Returns:
-            torch.Tensor: a vector with areas of each box.
-        """
-        box = self.tensor
-        area = (box[:, 2] - box[:, 0]) * (box[:, 3] - box[:, 1])
-        return area
-
-    def clip(self, box_size: Tuple[int, int]) -> None:
-        """
-        Clip (in place) the boxes by limiting x coordinates to the range [0, width]
-        and y coordinates to the range [0, height].
-
-        Args:
-            box_size (height, width): The clipping box's size.
-        """
-        assert torch.isfinite(self.tensor).all(), "Box tensor contains infinite or NaN!"
-        h, w = box_size
-        x1 = self.tensor[:, 0].clamp(min=0, max=w)
-        y1 = self.tensor[:, 1].clamp(min=0, max=h)
-        x2 = self.tensor[:, 2].clamp(min=0, max=w)
-        y2 = self.tensor[:, 3].clamp(min=0, max=h)
-        self.tensor = torch.stack((x1, y1, x2, y2), dim=-1)
-
-    def nonempty(self, threshold: float = 0.0) -> torch.Tensor:
-        """
-        Find boxes that are non-empty.
-        A box is considered empty, if either of its side is no larger than threshold.
-
-        Returns:
-            Tensor:
-                a binary vector which represents whether each box is empty
-                (False) or non-empty (True).
-        """
-        box = self.tensor
-        widths = box[:, 2] - box[:, 0]
-        heights = box[:, 3] - box[:, 1]
-        keep = (widths > threshold) & (heights > threshold)
-        return keep
-
-    def __getitem__(self, item) -> "Boxes":
-        """
-        Args:
-            item: int, slice, or a BoolTensor
-
-        Returns:
-            Boxes: Create a new :class:`Boxes` by indexing.
-
-        The following usage are allowed:
-
-        1. `new_boxes = boxes[3]`: return a `Boxes` which contains only one box.
-        2. `new_boxes = boxes[2:10]`: return a slice of boxes.
-        3. `new_boxes = boxes[vector]`, where vector is a torch.BoolTensor
-           with `length = len(boxes)`. Nonzero elements in the vector will be selected.
-
-        Note that the returned Boxes might share storage with this Boxes,
-        subject to Pytorch's indexing semantics.
-        """
-        if isinstance(item, int):
-            return Boxes(self.tensor[item].view(1, -1))
-        b = self.tensor[item]
-        assert b.dim() == 2, "Indexing on Boxes with {} failed to return a matrix!".format(item)
-        return Boxes(b)
-
-    def __len__(self) -> int:
-        return self.tensor.shape[0]
-
-    def __repr__(self) -> str:
-        return "Boxes(" + str(self.tensor) + ")"
-
-    def inside_box(self, box_size: Tuple[int, int], boundary_threshold: int = 0) -> torch.Tensor:
-        """
-        Args:
-            box_size (height, width): Size of the reference box.
-            boundary_threshold (int): Boxes that extend beyond the reference box
-                boundary by more than boundary_threshold are considered "outside".
-
-        Returns:
-            a binary vector, indicating whether each box is inside the reference box.
-        """
-        height, width = box_size
-        inds_inside = (
-            (self.tensor[..., 0] >= -boundary_threshold)
-            & (self.tensor[..., 1] >= -boundary_threshold)
-            & (self.tensor[..., 2] < width + boundary_threshold)
-            & (self.tensor[..., 3] < height + boundary_threshold)
-        )
-        return inds_inside
-
-    def get_centers(self) -> torch.Tensor:
-        """
-        Returns:
-            The box centers in a Nx2 array of (x, y).
-        """
-        return (self.tensor[:, :2] + self.tensor[:, 2:]) / 2
-
-    def scale(self, scale_x: float, scale_y: float) -> None:
-        """
-        Scale the box with horizontal and vertical scaling factors
-        """
-        self.tensor[:, 0::2] *= scale_x
-        self.tensor[:, 1::2] *= scale_y
-
-    @classmethod
-    def cat(cls, boxes_list: List["Boxes"]) -> "Boxes":
-        """
-        Concatenates a list of Boxes into a single Boxes
-
-        Arguments:
-            boxes_list (list[Boxes])
-
-        Returns:
-            Boxes: the concatenated Boxes
-        """
-        assert isinstance(boxes_list, (list, tuple))
-        if len(boxes_list) == 0:
-            return cls(torch.empty(0))
-        assert all([isinstance(box, Boxes) for box in boxes_list])
-
-        # use torch.cat (v.s. layers.cat) so the returned boxes never share storage with input
-        cat_boxes = cls(torch.cat([b.tensor for b in boxes_list], dim=0))
-        return cat_boxes
-
-    @property
-    def device(self) -> device:
-        return self.tensor.device
-
-    # type "Iterator[torch.Tensor]", yield, and iter() not supported by torchscript
-    # https://github.com/pytorch/pytorch/issues/18627
-    @torch.jit.unused
-    def __iter__(self):
-        """
-        Yield a box as a Tensor of shape (4,) at a time.
-        """
-        yield from self.tensor
-
-
-def pairwise_intersection(boxes1: Boxes, boxes2: Boxes) -> torch.Tensor:
-    """
-    Given two lists of boxes of size N and M,
-    compute the intersection area between __all__ N x M pairs of boxes.
-    The box order must be (xmin, ymin, xmax, ymax)
-
-    Args:
-        boxes1,boxes2 (Boxes): two `Boxes`. Contains N & M boxes, respectively.
-
-    Returns:
-        Tensor: intersection, sized [N,M].
-    """
-    boxes1, boxes2 = boxes1.tensor, boxes2.tensor
-    width_height = torch.min(boxes1[:, None, 2:], boxes2[:, 2:]) - torch.max(
-        boxes1[:, None, :2], boxes2[:, :2]
-    )  # [N,M,2]
-
-    width_height.clamp_(min=0)  # [N,M,2]
-    intersection = width_height.prod(dim=2)  # [N,M]
-    return intersection
-
-
-# implementation from https://github.com/kuangliu/torchcv/blob/master/torchcv/utils/box.py
-# with slight modifications
-def pairwise_iou(boxes1: Boxes, boxes2: Boxes) -> torch.Tensor:
-    """
-    Given two lists of boxes of size N and M, compute the IoU
-    (intersection over union) between **all** N x M pairs of boxes.
-    The box order must be (xmin, ymin, xmax, ymax).
-
-    Args:
-        boxes1,boxes2 (Boxes): two `Boxes`. Contains N & M boxes, respectively.
-
-    Returns:
-        Tensor: IoU, sized [N,M].
-    """
-    area1 = boxes1.area()  # [N]
-    area2 = boxes2.area()  # [M]
-    inter = pairwise_intersection(boxes1, boxes2)
-
-    # handle empty boxes
-    iou = torch.where(
-        inter > 0,
-        inter / (area1[:, None] + area2 - inter),
-        torch.zeros(1, dtype=inter.dtype, device=inter.device),
-    )
-    return iou
-
-
-def pairwise_ioa(boxes1: Boxes, boxes2: Boxes) -> torch.Tensor:
-    """
-    Similar to :func:`pariwise_iou` but compute the IoA (intersection over boxes2 area).
-
-    Args:
-        boxes1,boxes2 (Boxes): two `Boxes`. Contains N & M boxes, respectively.
-
-    Returns:
-        Tensor: IoA, sized [N,M].
-    """
-    area2 = boxes2.area()  # [M]
-    inter = pairwise_intersection(boxes1, boxes2)
-
-    # handle empty boxes
-    ioa = torch.where(
-        inter > 0, inter / area2, torch.zeros(1, dtype=inter.dtype, device=inter.device)
-    )
-    return ioa
-
-
-def pairwise_point_box_distance(points: torch.Tensor, boxes: Boxes):
-    """
-    Pairwise distance between N points and M boxes. The distance between a
-    point and a box is represented by the distance from the point to 4 edges
-    of the box. Distances are all positive when the point is inside the box.
-
-    Args:
-        points: Nx2 coordinates. Each row is (x, y)
-        boxes: M boxes
-
-    Returns:
-        Tensor: distances of size (N, M, 4). The 4 values are distances from
-            the point to the left, top, right, bottom of the box.
-    """
-    x, y = points.unsqueeze(dim=2).unbind(dim=1)  # (N, 1)
-    x0, y0, x1, y1 = boxes.tensor.unsqueeze(dim=0).unbind(dim=2)  # (1, M)
-    return torch.stack([x - x0, y - y0, x1 - x, y1 - y], dim=2)
-
-
-def matched_pairwise_iou(boxes1: Boxes, boxes2: Boxes) -> torch.Tensor:
-    """
-    Compute pairwise intersection over union (IOU) of two sets of matched
-    boxes that have the same number of boxes.
-    Similar to :func:`pairwise_iou`, but computes only diagonal elements of the matrix.
-
-    Args:
-        boxes1 (Boxes): bounding boxes, sized [N,4].
-        boxes2 (Boxes): same length as boxes1
-    Returns:
-        Tensor: iou, sized [N].
-    """
-    assert len(boxes1) == len(
-        boxes2
-    ), "boxlists should have the same" "number of entries, got {}, {}".format(
-        len(boxes1), len(boxes2)
-    )
-    area1 = boxes1.area()  # [N]
-    area2 = boxes2.area()  # [N]
-    box1, box2 = boxes1.tensor, boxes2.tensor
-    lt = torch.max(box1[:, :2], box2[:, :2])  # [N,2]
-    rb = torch.min(box1[:, 2:], box2[:, 2:])  # [N,2]
-    wh = (rb - lt).clamp(min=0)  # [N,2]
-    inter = wh[:, 0] * wh[:, 1]  # [N]
-    iou = inter / (area1 + area2 - inter)  # [N]
-    return iou
diff --git a/spaces/younker/chatgpt-turbo/client/node_modules/autoprefixer/lib/hacks/file-selector-button.js b/spaces/younker/chatgpt-turbo/client/node_modules/autoprefixer/lib/hacks/file-selector-button.js
deleted file mode 100644
index 18ebcead2b90eeedc72c51cb8836a5006c604cd7..0000000000000000000000000000000000000000
--- a/spaces/younker/chatgpt-turbo/client/node_modules/autoprefixer/lib/hacks/file-selector-button.js
+++ /dev/null
@@ -1,26 +0,0 @@
-let Selector = require('../selector')
-let utils = require('../utils')
-
-class FileSelectorButton extends Selector {
-  constructor(name, prefixes, all) {
-    super(name, prefixes, all)
-
-    if (this.prefixes) {
-      this.prefixes = utils.uniq(this.prefixes.map(() => '-webkit-'))
-    }
-  }
-
-  /**
-   * Return different selectors depend on prefix
-   */
-  prefixed(prefix) {
-    if (prefix === '-webkit-') {
-      return '::-webkit-file-upload-button'
-    }
-    return `::${prefix}file-selector-button`
-  }
-}
-
-FileSelectorButton.names = ['::file-selector-button']
-
-module.exports = FileSelectorButton
diff --git a/spaces/ysharma/Playground_AI_Exploration/app.py b/spaces/ysharma/Playground_AI_Exploration/app.py
deleted file mode 100644
index ca8762d80d7af1029cf84ef97eecb9d53a4b0b29..0000000000000000000000000000000000000000
--- a/spaces/ysharma/Playground_AI_Exploration/app.py
+++ /dev/null
@@ -1,43 +0,0 @@
-import pandas as pd
-import gradio as gr
- 
-df = pd.read_csv("liked_images.csv")
-df['url'] = df['url'].apply(lambda x: '<a href= "' + str(x) + '" target="_blank"> <img src= "' + str(x) + '"/> </a>') #'<img src= "' + str(x) + '"/> </a>')
-df['seed'] = df['seed'].apply(lambda x: str(x))
-df['width'] = df['width'].apply(lambda x: str(x))
-df['height'] = df['height'].apply(lambda x: str(x))
-df['steps'] = df['steps'].apply(lambda x: str(x))
-df['source'] = df['source'].apply(lambda x: str(x))
-df = df[[ 'url', 'prompt', 'seed', 'width', 'height', 'steps', 'source']]
-
-def display_df():
-  df_images = df.head(10)
-  return df_images
-
-def display_next10(dataframe, end):
-  start = (end  or dataframe.index[-1]) + 1
-  end = start + 9
-  df_images = df.loc[start:end]
-  return df_images, end
-  
-#Gradio Blocks
-with gr.Blocks() as demo:
-  gr.Markdown("<h1><center>Utility Gradio Space for viewing PlaygroundAI Images</center></h1>")
-  #gr.Markdown("""<img src='https://xxxxxxxx.jpg' class='center'> <br>  """) 
-  gr.Markdown(
-        """<div align="center">This Tool helps you to analyze and inspect the images and corresponding prompts from <a href = "https://playgroundai.com/">Playground AI</a> Images.<br><a href="https://twitter.com/Suhail">Suhail</a> has recently shared an open dataset of all the liked images and their prompts from PlaygroundAI on <a href="https://github.com/playgroundai/liked_images">Github here</a>. This is an attempt to explore this dataset beautifully using the power and flexibility of Gradio!<br><b>To use the tool:</b>First, click on the 'Initial' button, and then iteratively on the 'Next 10' button.<br><b>Bonus:</b>Click on images to get the original PlaygroundAI image displayed on next tab</div>""")
-
-  with gr.Row():
-    num_end = gr.Number(visible=False)
-    b1 = gr.Button("Get Initial dataframe")
-    b2 = gr.Button("Next 10 Rows")
-    
-  with gr.Row():
-    out_dataframe = gr.Dataframe(wrap=True, max_rows=10, overflow_row_behaviour= "paginate", datatype = ["markdown", "markdown", "str", "str", "str", "str", "str", "str"], interactive=False)
-    
-  b1.click(fn=display_df, outputs=out_dataframe, api_name="initial_dataframe") 
-  b2.click(fn=display_next10, inputs= [out_dataframe, num_end ], outputs=[out_dataframe, num_end], api_name="next_10_rows")
-    
-  gr.Markdown("<center>Please note that the Playground AI dataset shared on GitHub doesn't have images but links to those images. The idea is to get the maximum benefit out of this dataset and to find the best way to explore this dataset. Gradio enables us to embed markdowns within a dataframe, thus this app is able to display actual images instead of direct links(meh!). I hope you will have as much fun playing with this Space as I had building it.</center>")
-  
-demo.launch(debug=True, show_error=True)
\ No newline at end of file
diff --git a/spaces/zengwj/GPT2-chitchat-training-huggingface/Dockerfile b/spaces/zengwj/GPT2-chitchat-training-huggingface/Dockerfile
deleted file mode 100644
index ddf43e9273e7ff0a0f0c3be026b0f9e715b90267..0000000000000000000000000000000000000000
--- a/spaces/zengwj/GPT2-chitchat-training-huggingface/Dockerfile
+++ /dev/null
@@ -1,15 +0,0 @@
-FROM python:3.6
-
-WORKDIR /workdir
-
-RUN chmod 777 /workdir
-
-COPY install.sh .
-
-COPY train_path.txt .
-
-COPY req.txt .
-
-COPY train.py .
-
-CMD sh install.sh
diff --git a/spaces/zeno-ml/chatbot-report/Dockerfile b/spaces/zeno-ml/chatbot-report/Dockerfile
deleted file mode 100644
index c69cc46ba2954deb3b37c303c02766d1679e3249..0000000000000000000000000000000000000000
--- a/spaces/zeno-ml/chatbot-report/Dockerfile
+++ /dev/null
@@ -1,22 +0,0 @@
-# read the doc: https://huggingface.co/docs/hub/spaces-sdks-docker
-# you will also find guides on how best to write your Dockerfile
-
-FROM python:3.9
-
-RUN useradd -m -u 1000 user
-USER user
-# Set home to the user's home directory
-ENV HOME=/home/user \
-	PATH=/home/user/.local/bin:$PATH
-WORKDIR $HOME/app
-# Copy the current directory contents into the container at $HOME/app setting the owner to the user
-COPY --chown=user . $HOME/app
-ADD --chown=user ./results $HOME/app/results
-RUN chown user:user -R $HOME/app
-
-COPY ./requirements.txt /code/requirements.txt
-
-RUN pip install --no-cache-dir --upgrade -r /code/requirements.txt
-
-
-CMD ["python", "main.py", "--results-dir", "./results", "--skip-prediction"]
\ No newline at end of file
diff --git a/spaces/zhang-wei-jian/docker/node_modules/nodemon/lib/index.js b/spaces/zhang-wei-jian/docker/node_modules/nodemon/lib/index.js
deleted file mode 100644
index 0eca5c457d357f6528e263deba131848e4380154..0000000000000000000000000000000000000000
--- a/spaces/zhang-wei-jian/docker/node_modules/nodemon/lib/index.js
+++ /dev/null
@@ -1 +0,0 @@
-module.exports = require('./nodemon');
\ No newline at end of file
diff --git a/spaces/zhaoys/wfms-kuiwenc/src/components/chat-prompts.tsx b/spaces/zhaoys/wfms-kuiwenc/src/components/chat-prompts.tsx
deleted file mode 100644
index 2d8bec5806b9ec1cc7ce521468a8036ca8734b86..0000000000000000000000000000000000000000
--- a/spaces/zhaoys/wfms-kuiwenc/src/components/chat-prompts.tsx
+++ /dev/null
@@ -1,33 +0,0 @@
-import { useAtomValue, useSetAtom } from "jotai"
-import { hashAtom, localPromptsAtom } from "@/state"
-import { Button } from "./ui/button"
-
-interface ChatPromptsProps {
-  onChange: (prompt: string) => void
-  filter: string
-}
-
-export function ChatPrompts({ onChange, filter }: ChatPromptsProps) {
-  const setLoc = useSetAtom(hashAtom)
-  const prompts = useAtomValue(localPromptsAtom)
-  const filterLower = filter.toLowerCase()
-  const pormptsFiltered = filter ? prompts.filter(p => p.prompt.toLowerCase().includes(filterLower) || p.title.toLowerCase().includes(filterLower)) : prompts
-
-  return (
-    <div className="absolute top-0 w-full -ml-4">
-      <div className="prompt-container absolute bottom-1 w-full">
-        <div className="surface">
-          {pormptsFiltered.map((prompt, index) => (
-            <div className="row items-start justify-start hover:bg-gray-50" key={index} onClick={() => onChange(prompt.prompt)}>
-              <div>{prompt.title}</div>
-              <div className="text-sm line-clamp-2">{prompt.prompt}</div>
-            </div>
-          ))}
-          <div onClick={() => setLoc('prompts')} className="relative cursor-pointer block w-full rounded-lg border-2 border-dashed border-gray-300 p-3 text-center text-sm text-primary-text">
-            <Button variant="ghost">管理提示词</Button>
-          </div>
-        </div>
-      </div>
-    </div>
-  )
-}
diff --git a/spaces/zhenwusw/JoJoGAN/e4e/models/stylegan2/op/upfirdn2d.py b/spaces/zhenwusw/JoJoGAN/e4e/models/stylegan2/op/upfirdn2d.py
deleted file mode 100644
index 7bc5a1e331c2bbb1893ac748cfd0f144ff0651b4..0000000000000000000000000000000000000000
--- a/spaces/zhenwusw/JoJoGAN/e4e/models/stylegan2/op/upfirdn2d.py
+++ /dev/null
@@ -1,184 +0,0 @@
-import os
-
-import torch
-from torch.autograd import Function
-from torch.utils.cpp_extension import load
-
-module_path = os.path.dirname(__file__)
-upfirdn2d_op = load(
-    'upfirdn2d',
-    sources=[
-        os.path.join(module_path, 'upfirdn2d.cpp'),
-        os.path.join(module_path, 'upfirdn2d_kernel.cu'),
-    ],
-)
-
-
-class UpFirDn2dBackward(Function):
-    @staticmethod
-    def forward(
-            ctx, grad_output, kernel, grad_kernel, up, down, pad, g_pad, in_size, out_size
-    ):
-        up_x, up_y = up
-        down_x, down_y = down
-        g_pad_x0, g_pad_x1, g_pad_y0, g_pad_y1 = g_pad
-
-        grad_output = grad_output.reshape(-1, out_size[0], out_size[1], 1)
-
-        grad_input = upfirdn2d_op.upfirdn2d(
-            grad_output,
-            grad_kernel,
-            down_x,
-            down_y,
-            up_x,
-            up_y,
-            g_pad_x0,
-            g_pad_x1,
-            g_pad_y0,
-            g_pad_y1,
-        )
-        grad_input = grad_input.view(in_size[0], in_size[1], in_size[2], in_size[3])
-
-        ctx.save_for_backward(kernel)
-
-        pad_x0, pad_x1, pad_y0, pad_y1 = pad
-
-        ctx.up_x = up_x
-        ctx.up_y = up_y
-        ctx.down_x = down_x
-        ctx.down_y = down_y
-        ctx.pad_x0 = pad_x0
-        ctx.pad_x1 = pad_x1
-        ctx.pad_y0 = pad_y0
-        ctx.pad_y1 = pad_y1
-        ctx.in_size = in_size
-        ctx.out_size = out_size
-
-        return grad_input
-
-    @staticmethod
-    def backward(ctx, gradgrad_input):
-        kernel, = ctx.saved_tensors
-
-        gradgrad_input = gradgrad_input.reshape(-1, ctx.in_size[2], ctx.in_size[3], 1)
-
-        gradgrad_out = upfirdn2d_op.upfirdn2d(
-            gradgrad_input,
-            kernel,
-            ctx.up_x,
-            ctx.up_y,
-            ctx.down_x,
-            ctx.down_y,
-            ctx.pad_x0,
-            ctx.pad_x1,
-            ctx.pad_y0,
-            ctx.pad_y1,
-        )
-        # gradgrad_out = gradgrad_out.view(ctx.in_size[0], ctx.out_size[0], ctx.out_size[1], ctx.in_size[3])
-        gradgrad_out = gradgrad_out.view(
-            ctx.in_size[0], ctx.in_size[1], ctx.out_size[0], ctx.out_size[1]
-        )
-
-        return gradgrad_out, None, None, None, None, None, None, None, None
-
-
-class UpFirDn2d(Function):
-    @staticmethod
-    def forward(ctx, input, kernel, up, down, pad):
-        up_x, up_y = up
-        down_x, down_y = down
-        pad_x0, pad_x1, pad_y0, pad_y1 = pad
-
-        kernel_h, kernel_w = kernel.shape
-        batch, channel, in_h, in_w = input.shape
-        ctx.in_size = input.shape
-
-        input = input.reshape(-1, in_h, in_w, 1)
-
-        ctx.save_for_backward(kernel, torch.flip(kernel, [0, 1]))
-
-        out_h = (in_h * up_y + pad_y0 + pad_y1 - kernel_h) // down_y + 1
-        out_w = (in_w * up_x + pad_x0 + pad_x1 - kernel_w) // down_x + 1
-        ctx.out_size = (out_h, out_w)
-
-        ctx.up = (up_x, up_y)
-        ctx.down = (down_x, down_y)
-        ctx.pad = (pad_x0, pad_x1, pad_y0, pad_y1)
-
-        g_pad_x0 = kernel_w - pad_x0 - 1
-        g_pad_y0 = kernel_h - pad_y0 - 1
-        g_pad_x1 = in_w * up_x - out_w * down_x + pad_x0 - up_x + 1
-        g_pad_y1 = in_h * up_y - out_h * down_y + pad_y0 - up_y + 1
-
-        ctx.g_pad = (g_pad_x0, g_pad_x1, g_pad_y0, g_pad_y1)
-
-        out = upfirdn2d_op.upfirdn2d(
-            input, kernel, up_x, up_y, down_x, down_y, pad_x0, pad_x1, pad_y0, pad_y1
-        )
-        # out = out.view(major, out_h, out_w, minor)
-        out = out.view(-1, channel, out_h, out_w)
-
-        return out
-
-    @staticmethod
-    def backward(ctx, grad_output):
-        kernel, grad_kernel = ctx.saved_tensors
-
-        grad_input = UpFirDn2dBackward.apply(
-            grad_output,
-            kernel,
-            grad_kernel,
-            ctx.up,
-            ctx.down,
-            ctx.pad,
-            ctx.g_pad,
-            ctx.in_size,
-            ctx.out_size,
-        )
-
-        return grad_input, None, None, None, None
-
-
-def upfirdn2d(input, kernel, up=1, down=1, pad=(0, 0)):
-    out = UpFirDn2d.apply(
-        input, kernel, (up, up), (down, down), (pad[0], pad[1], pad[0], pad[1])
-    )
-
-    return out
-
-
-def upfirdn2d_native(
-        input, kernel, up_x, up_y, down_x, down_y, pad_x0, pad_x1, pad_y0, pad_y1
-):
-    _, in_h, in_w, minor = input.shape
-    kernel_h, kernel_w = kernel.shape
-
-    out = input.view(-1, in_h, 1, in_w, 1, minor)
-    out = F.pad(out, [0, 0, 0, up_x - 1, 0, 0, 0, up_y - 1])
-    out = out.view(-1, in_h * up_y, in_w * up_x, minor)
-
-    out = F.pad(
-        out, [0, 0, max(pad_x0, 0), max(pad_x1, 0), max(pad_y0, 0), max(pad_y1, 0)]
-    )
-    out = out[
-          :,
-          max(-pad_y0, 0): out.shape[1] - max(-pad_y1, 0),
-          max(-pad_x0, 0): out.shape[2] - max(-pad_x1, 0),
-          :,
-          ]
-
-    out = out.permute(0, 3, 1, 2)
-    out = out.reshape(
-        [-1, 1, in_h * up_y + pad_y0 + pad_y1, in_w * up_x + pad_x0 + pad_x1]
-    )
-    w = torch.flip(kernel, [0, 1]).view(1, 1, kernel_h, kernel_w)
-    out = F.conv2d(out, w)
-    out = out.reshape(
-        -1,
-        minor,
-        in_h * up_y + pad_y0 + pad_y1 - kernel_h + 1,
-        in_w * up_x + pad_x0 + pad_x1 - kernel_w + 1,
-    )
-    out = out.permute(0, 2, 3, 1)
-
-    return out[:, ::down_y, ::down_x, :]
diff --git a/spaces/zhtet/RegBotBeta/app.py b/spaces/zhtet/RegBotBeta/app.py
deleted file mode 100644
index 359816cc70e83b0bc8c535557a0b4ca48deeb9f1..0000000000000000000000000000000000000000
--- a/spaces/zhtet/RegBotBeta/app.py
+++ /dev/null
@@ -1,30 +0,0 @@
-# https://docs.streamlit.io/knowledge-base/tutorials/build-conversational-apps
-
-import os
-
-import openai
-import requests
-import streamlit as st
-
-from utils.util import *
-
-st.set_page_config(page_title="RegBotBeta", page_icon="📜🤖")
-
-st.title("Welcome to RegBotBeta2.0")
-st.header("Powered by `LlamaIndex🦙`, `Langchain🦜🔗 ` and `OpenAI API`")
-
-api_key = st.text_input("Enter your OpenAI API key here:", type="password")
-
-if api_key:
-    resp = validate(api_key)
-    if "error" in resp.json():
-        st.info("Invalid Token! Try again.")
-    else:
-        st.info("Success")
-        os.environ["OPENAI_API_KEY"] = api_key
-        openai.api_key = api_key
-
-        if "openai_api_key" not in st.session_state:
-            st.session_state.openai_api_key = ""
-
-        st.session_state.openai_api_key = api_key
diff --git a/spaces/zhuyuheng/IMossGPT/run_Linux.sh b/spaces/zhuyuheng/IMossGPT/run_Linux.sh
deleted file mode 100644
index 2d26597ae47519f42336ccffc16646713a192ae1..0000000000000000000000000000000000000000
--- a/spaces/zhuyuheng/IMossGPT/run_Linux.sh
+++ /dev/null
@@ -1,31 +0,0 @@
-#!/bin/bash
-
-# 获取脚本所在目录
-script_dir=$(dirname "$(readlink -f "$0")")
-
-# 将工作目录更改为脚本所在目录
-cd "$script_dir" || exit
-
-# 检查Git仓库是否有更新
-git remote update
-pwd
-
-if ! git status -uno | grep 'up to date' > /dev/null; then
-	# 如果有更新，关闭当前运行的服务器
-	pkill -f ChuanhuChatbot.py
-
-	# 拉取最新更改
-	git pull
-
-	# 安装依赖
-	pip3 install -r requirements.txt
-
-	# 重新启动服务器
-	nohup python3 ChuanhuChatbot.py &
-fi
-
-# 检查ChuanhuChatbot.py是否在运行
-if ! pgrep -f ChuanhuChatbot.py > /dev/null; then
-	# 如果没有运行，启动服务器
-	nohup python3 ChuanhuChatbot.py &
-fi
diff --git a/spaces/zxy666/bingo-chatai666/tests/parse.ts b/spaces/zxy666/bingo-chatai666/tests/parse.ts
deleted file mode 100644
index 92940fe6315f1d7cb2b267ba5e5a7e26460a1de3..0000000000000000000000000000000000000000
--- a/spaces/zxy666/bingo-chatai666/tests/parse.ts
+++ /dev/null
@@ -1,13 +0,0 @@
-import { promises as fs } from 'fs'
-import { join } from 'path'
-import { parseHeadersFromCurl } from '@/lib/utils'
-
-(async () => {
-  const content = await fs.readFile(join(__dirname, './fixtures/curl.txt'), 'utf-8')
-  const headers = parseHeadersFromCurl(content)
-  console.log(headers)
-
-  const cmdContent = await fs.readFile(join(__dirname, './fixtures/cmd.txt'), 'utf-8')
-  const cmdHeaders = parseHeadersFromCurl(cmdContent)
-  console.log(cmdHeaders)
-})()