Split (1)

train · 846k rows

modelId stringlengths 5 139	author stringlengths 2 42	last_modified timestamp[us, tz=UTC]date 2020-02-15 11:33:14 2025-06-27 12:29:05	downloads int64 0 223M	likes int64 0 11.7k	library_name stringclasses 500 values	tags sequencelengths 1 4.05k	pipeline_tag stringclasses 54 values	createdAt timestamp[us, tz=UTC]date 2022-03-02 23:29:04 2025-06-27 12:27:55	card stringlengths 11 1.01M
glif-loradex-trainer/maxxd4240_Whimsical_Adventures	glif-loradex-trainer	2024-10-11T10:47:39Z	33	1	diffusers	[ "diffusers", "text-to-image", "template:sd-lora", "base_model:black-forest-labs/FLUX.1-dev", "base_model:finetune:black-forest-labs/FLUX.1-dev", "license:other", "region:us", "flux", "lora", "base_model:adapter:black-forest-labs/FLUX.1-dev" ]	text-to-image	2024-09-21T11:34:24Z	--- base_model: black-forest-labs/FLUX.1-dev license: other license_name: flux-1-dev-non-commercial-license license_link: https://huggingface.co/black-forest-labs/FLUX.1-dev/blob/main/LICENSE.md tags: - diffusers - text-to-image - template:sd-lora - base_model:black-forest-labs/FLUX.1-dev - base_model:finetune:black-forest-labs/FLUX.1-dev - license:other - region:us - flux - lora widget: - output: url: https://huggingface.co/glif-loradex-trainer/maxxd4240_Whimsical_Adventures/resolve/main/samples/1726918329173__000003000_0.jpg text: 'Gender-neutral scavengers in rugged, asymmetrical armor with skyfall shards embedded in their skin. Their eyes glow faintly, reflecting the shattered sky above, and their hair is wind-torn and gray WhimsicalAdventures ' - output: url: https://huggingface.co/glif-loradex-trainer/maxxd4240_Whimsical_Adventures/resolve/main/samples/1726918353811__000003000_1.jpg text: 'Male or female spellcasters cloaked in dark, tattered robes. Their bodies are marked by glowing glyphs, and they carry ancient books chained to their belts. Their eyes appear hollow, with wisps of magic flickering within WhimsicalAdventures ' - output: url: https://huggingface.co/glif-loradex-trainer/maxxd4240_Whimsical_Adventures/resolve/main/samples/1726918378445__000003000_2.jpg text: 'Androgynous survivors with pale, almost translucent skin and dark, form-fitting suits that reflect the emptiness of space. They have void-inflicted scars across their bodies, and their faces are expressionless, with faint glowing veins under their skin WhimsicalAdventures ' - output: url: https://huggingface.co/glif-loradex-trainer/maxxd4240_Whimsical_Adventures/resolve/main/samples/1726918403041__000003000_3.jpg text: 'Male-dominated resistance fighters wearing bulky mechanical exoskeletons with mystical etchings. Their faces are obscured by grimy visors, revealing only tired, hardened eyes. Each piece of armor is a blend of tech and ancient runes, radiating an aura of rebellion WhimsicalAdventures ' - output: url: https://huggingface.co/glif-loradex-trainer/maxxd4240_Whimsical_Adventures/resolve/main/samples/1726918427639__000003000_4.jpg text: 'Female-dominant warriors with charred leather armor made from dragon scales, their eyes lit with the embers of dark magic. Their hair is either braided or burned at the tips, and their skin bears deep scars from dragonfire WhimsicalAdventures ' - output: url: https://huggingface.co/glif-loradex-trainer/maxxd4240_Whimsical_Adventures/resolve/main/samples/1726918452273__000003000_5.jpg text: 'Fae of any gender with metallic wings, sleek armor fused with organic materials, and eerily beautiful faces that hide cruelty. Their skin is a metallic sheen, with sharp eyes in unnatural colors, and they wield weapons that seem grown from the very earth or metal around them WhimsicalAdventures ' trigger: WhimsicalAdventures instance_prompt: WhimsicalAdventures --- # Whimsical_Adventures Model trained with [AI Toolkit by Ostris](https://github.com/ostris/ai-toolkit) under the [Glif Loradex program](https://huggingface.co/glif-loradex-trainer) by [Glif](https://glif.app) user `maxxd4240`. <Gallery /> ## Trigger words You should use `WhimsicalAdventures` to trigger the image generation. ## Download model Weights for this model are available in Safetensors format. [Download](/glif-loradex-trainer/maxxd4240_Whimsical_Adventures/tree/main) them in the Files & versions tab. ## License This model is licensed under the [flux-1-dev-non-commercial-license](https://huggingface.co/black-forest-labs/FLUX.1-dev/blob/main/LICENSE.md).
glif-loradex-trainer/tostiok_flux_dev_bad_taxidermist	glif-loradex-trainer	2024-10-11T10:47:37Z	5	0	diffusers	[ "diffusers", "text-to-image", "template:sd-lora", "base_model:black-forest-labs/FLUX.1-dev", "base_model:finetune:black-forest-labs/FLUX.1-dev", "license:other", "region:us", "flux", "lora", "base_model:adapter:black-forest-labs/FLUX.1-dev" ]	text-to-image	2024-09-21T04:45:17Z	--- base_model: black-forest-labs/FLUX.1-dev license: other license_name: flux-1-dev-non-commercial-license license_link: https://huggingface.co/black-forest-labs/FLUX.1-dev/blob/main/LICENSE.md tags: - diffusers - text-to-image - template:sd-lora - base_model:black-forest-labs/FLUX.1-dev - base_model:finetune:black-forest-labs/FLUX.1-dev - license:other - region:us - flux - lora widget: - output: url: https://huggingface.co/glif-loradex-trainer/tostiok_flux_dev_bad_taxidermist/resolve/main/samples/1726893783946__000003000_0.jpg text: A white dog with a grotesque, taxidermized appearance, standing against a dark gray background. The dog’s fur is matted and tangled, with large, glassy eyes and an unsettling, stiff posture. Its mouth is slightly open, revealing sharp, unnatural-looking teeth. The poorly preserved body gives off an eerie, surreal atmosphere, with a sense of something being wrong. The dark gray backdrop intensifies the unsettling feeling, creating a haunting and strange effect. bad taxidermist style - output: url: https://huggingface.co/glif-loradex-trainer/tostiok_flux_dev_bad_taxidermist/resolve/main/samples/1726893808585__000003000_1.jpg text: The image shows a disturbing creature that resembles a cat, but with warped and unsettling features that give it a nightmarish appearance. The fur is thin, patchy, and disheveled, primarily grayish-white in color with a grimy, neglected look. Its face, like that of a cat, has large, alien-like eyes that are completely black, shiny, and eerily reflective, much like the previous image. The disproportionate size of the eyes makes the creature appear both unnatural and unnerving. Its mouth is grotesquely distorted, displaying a row of sharp, jagged yellow teeth that seem too large for its small face. The gums are visible, adding to the sense of decay, as they appear discolored and unhealthy. The lips are slightly pulled back, revealing the menacing teeth and contributing to a grimace-like expression. Its nose, though cat-like in structure, is small and shriveled, positioned above the unsettling teeth. The ears are large and pointed, with scraggly, unkempt fur clinging to them, while the insides of the ears are a reddish hue, giving an unhealthy, almost raw appearance. The creature’s whiskers are long, thin, and unkempt, protruding unevenly from the sides of its face, adding to the overall sense of disorder and malformation. The background is a plain, dark gray, making the creature stand out sharply, with soft lighting casting faint shadows to emphasize its unsettling features. The focus is entirely on the creature, with no distractions in the background, enhancing the sense of horror and tension. This image appears to be another highly detailed digital rendering, likely created using advanced 3D modeling software, with realistic texture mapping and lighting techniques. The dark, exaggerated, and surreal elements suggest it was designed to invoke fear, perhaps as a creature from a horror or fantasy setting, with careful attention to creating an eerie and unsettling atmosphere. bad taxidermist style - output: url: https://huggingface.co/glif-loradex-trainer/tostiok_flux_dev_bad_taxidermist/resolve/main/samples/1726893833222__000003000_2.jpg text: The image depicts a highly detailed, grotesque humanoid figure that closely resembles an emaciated, nightmarish elderly woman. Her skeletal frame is marked by deeply wrinkled, leathery skin that clings tightly to her bones, giving her a gaunt, almost mummified appearance. The skin is a sickly brownish-gray tone, accentuating the deep lines and creases that cover her entire body, from her face to her neck and shoulders. Her bones, particularly her collarbones and shoulders, jut out prominently, further emphasizing her extreme thinness and malnourished state. Her face is a terrifying focal point. Deep wrinkles and creases carve into her skull-like face, creating an intense texture of decay. Her mouth is contorted into a disturbing, forced grin, with cracked lips revealing yellowed, crooked teeth. The smile is too wide, almost unnaturally so, as if it’s been etched into her face. Her nose is sharp and bony, barely more than a protrusion above her sunken cheeks. The most striking and unsettling feature is her eyes. They are wide, shockingly large, and intensely blue, with small, dilated pupils that give her a crazed, manic expression. The eyes seem too big for her face, and their bright blue color contrasts sharply against the dark, decayed tones of her skin, making them stand out in an unnervingly vibrant manner. The eyes are surrounded by deep hollows, enhancing the overall look of age, exhaustion, and madness. Her hair is wild and white, standing out in frizzy, unkempt tufts that radiate from her head in all directions. The texture is dry and brittle, as though it hasn’t been cared for in a long time. The hair adds to the chaotic, witch-like appearance, framing her skeletal face and further emphasizing the sense of disorder and decay. The lighting in the image highlights the contours and textures of her skin and bones, casting shadows in the deep creases of her face and body, which enhances her skeletal form. The background is a simple dark gray, allowing the figure to be the sole focus of the viewer’s attention, with the lighting providing enough contrast to make every disturbing detail stand out clearly. This image appears to be a digital 3D rendering with hyper-realistic detail, possibly designed for a horror or dark fantasy setting. The figure’s exaggerated and decayed features evoke a strong sense of fear and discomfort, playing on common tropes of witches or ghoulish elderly figures from folklore, but taken to an extreme of grotesque realism. The combination of skeletal thinness, wide, manic eyes, and the decayed state of her body suggests that this figure was intentionally crafted to evoke horror and unease. bad taxidermist style - output: url: https://huggingface.co/glif-loradex-trainer/tostiok_flux_dev_bad_taxidermist/resolve/main/samples/1726893857853__000003000_3.jpg text: a dog, high quality photo 8k. bad taxidermist style - output: url: https://huggingface.co/glif-loradex-trainer/tostiok_flux_dev_bad_taxidermist/resolve/main/samples/1726893882484__000003000_4.jpg text: a cat, high quality photo 8k. bad taxidermist style - output: url: https://huggingface.co/glif-loradex-trainer/tostiok_flux_dev_bad_taxidermist/resolve/main/samples/1726893907117__000003000_5.jpg text: a middle age man, high quality photo 8k. bad taxidermist style trigger: bad taxidermist style instance_prompt: bad taxidermist style --- # flux_dev_bad_taxidermist Model trained with [AI Toolkit by Ostris](https://github.com/ostris/ai-toolkit) under the [Glif Loradex program](https://huggingface.co/glif-loradex-trainer) by [Glif](https://glif.app) user `tostiok`. <Gallery /> ## Trigger words You should use `bad taxidermist style` to trigger the image generation. ## Download model Weights for this model are available in Safetensors format. [Download](/glif-loradex-trainer/tostiok_flux_dev_bad_taxidermist/tree/main) them in the Files & versions tab. ## License This model is licensed under the [flux-1-dev-non-commercial-license](https://huggingface.co/black-forest-labs/FLUX.1-dev/blob/main/LICENSE.md).
glif-loradex-trainer/quitters_flux_dev_courtroomsketch	glif-loradex-trainer	2024-10-11T10:47:35Z	58	5	diffusers	[ "diffusers", "text-to-image", "template:sd-lora", "base_model:black-forest-labs/FLUX.1-dev", "base_model:finetune:black-forest-labs/FLUX.1-dev", "license:other", "region:us", "flux", "lora", "base_model:adapter:black-forest-labs/FLUX.1-dev" ]	text-to-image	2024-09-20T19:04:39Z	--- base_model: black-forest-labs/FLUX.1-dev license: other license_name: flux-1-dev-non-commercial-license license_link: https://huggingface.co/black-forest-labs/FLUX.1-dev/blob/main/LICENSE.md tags: - diffusers - text-to-image - template:sd-lora - base_model:black-forest-labs/FLUX.1-dev - base_model:finetune:black-forest-labs/FLUX.1-dev - license:other - region:us - flux - lora widget: - output: url: https://huggingface.co/glif-loradex-trainer/quitters_flux_dev_courtroomsketch/resolve/main/samples/1726859019631__000003000_0.jpg text: courtroom sketch, in the case of Ronald McDonald vs The United States courtroomsketch - output: url: https://huggingface.co/glif-loradex-trainer/quitters_flux_dev_courtroomsketch/resolve/main/samples/1726859044259__000003000_1.jpg text: the incident courtroomsketch, Porous point pen, crayon, pastel, opaque white, and ink wash on illustration board. - output: url: https://huggingface.co/glif-loradex-trainer/quitters_flux_dev_courtroomsketch/resolve/main/samples/1726859068877__000003000_2.jpg text: quick, the baliff is distracted, make protest art in the courtroom! courtroomsketch trigger: courtroomsketch instance_prompt: courtroomsketch --- # flux_dev_courtroomsketch Model trained with [AI Toolkit by Ostris](https://github.com/ostris/ai-toolkit) under the [Glif Loradex program](https://huggingface.co/glif-loradex-trainer) by [Glif](https://glif.app) user `quitters`. <Gallery /> ## Trigger words You should use `courtroomsketch` to trigger the image generation. ## Download model Weights for this model are available in Safetensors format. [Download](/glif-loradex-trainer/quitters_flux_dev_courtroomsketch/tree/main) them in the Files & versions tab. ## License This model is licensed under the [flux-1-dev-non-commercial-license](https://huggingface.co/black-forest-labs/FLUX.1-dev/blob/main/LICENSE.md).
glif-loradex-trainer/highdruidmotas_bennett_shadows	glif-loradex-trainer	2024-10-11T10:47:33Z	6	0	diffusers	[ "diffusers", "text-to-image", "template:sd-lora", "base_model:black-forest-labs/FLUX.1-dev", "base_model:finetune:black-forest-labs/FLUX.1-dev", "license:other", "region:us", "flux", "lora", "base_model:adapter:black-forest-labs/FLUX.1-dev" ]	text-to-image	2024-09-20T18:02:11Z	--- base_model: black-forest-labs/FLUX.1-dev license: other license_name: flux-1-dev-non-commercial-license license_link: https://huggingface.co/black-forest-labs/FLUX.1-dev/blob/main/LICENSE.md tags: - diffusers - text-to-image - template:sd-lora - base_model:black-forest-labs/FLUX.1-dev - base_model:finetune:black-forest-labs/FLUX.1-dev - license:other - region:us - flux - lora widget: - output: url: https://huggingface.co/glif-loradex-trainer/highdruidmotas_bennett_shadows/resolve/main/samples/1726855254243__000001500_0.jpg text: wounded centaur, mythical creature bennett_shadows - output: url: https://huggingface.co/glif-loradex-trainer/highdruidmotas_bennett_shadows/resolve/main/samples/1726855277802__000001500_1.jpg text: ruins of athens, snake bennett_shadows - output: url: https://huggingface.co/glif-loradex-trainer/highdruidmotas_bennett_shadows/resolve/main/samples/1726855301820__000001500_2.jpg text: silver vampire sword bennett_shadows trigger: bennett_shadows instance_prompt: bennett_shadows --- # bennett_shadows Model trained with [AI Toolkit by Ostris](https://github.com/ostris/ai-toolkit) under the [Glif Loradex program](https://huggingface.co/glif-loradex-trainer) by [Glif](https://glif.app) user `highdruidmotas`. <Gallery /> ## Trigger words You should use `bennett_shadows` to trigger the image generation. ## Download model Weights for this model are available in Safetensors format. [Download](/glif-loradex-trainer/highdruidmotas_bennett_shadows/tree/main) them in the Files & versions tab. ## License This model is licensed under the [flux-1-dev-non-commercial-license](https://huggingface.co/black-forest-labs/FLUX.1-dev/blob/main/LICENSE.md).
glif-loradex-trainer/fabian3000_fontsheet3	glif-loradex-trainer	2024-10-11T10:47:29Z	14	3	diffusers	[ "diffusers", "text-to-image", "template:sd-lora", "base_model:black-forest-labs/FLUX.1-dev", "base_model:finetune:black-forest-labs/FLUX.1-dev", "license:other", "region:us", "flux", "lora", "base_model:adapter:black-forest-labs/FLUX.1-dev" ]	text-to-image	2024-09-20T17:20:24Z	--- base_model: black-forest-labs/FLUX.1-dev license: other license_name: flux-1-dev-non-commercial-license license_link: https://huggingface.co/black-forest-labs/FLUX.1-dev/blob/main/LICENSE.md tags: - diffusers - text-to-image - template:sd-lora - base_model:black-forest-labs/FLUX.1-dev - base_model:finetune:black-forest-labs/FLUX.1-dev - license:other - region:us - flux - lora widget: - output: url: https://huggingface.co/glif-loradex-trainer/fabian3000_fontsheet3/resolve/main/samples/1726852756046__000002500_0.jpg text: wounded centaur, mythical creature fontsheet - output: url: https://huggingface.co/glif-loradex-trainer/fabian3000_fontsheet3/resolve/main/samples/1726852779869__000002500_1.jpg text: ruins of athens, snake fontsheet - output: url: https://huggingface.co/glif-loradex-trainer/fabian3000_fontsheet3/resolve/main/samples/1726852803532__000002500_2.jpg text: silver vampire sword fontsheet trigger: fontsheet instance_prompt: fontsheet --- # fontsheet3 Model trained with [AI Toolkit by Ostris](https://github.com/ostris/ai-toolkit) under the [Glif Loradex program](https://huggingface.co/glif-loradex-trainer) by [Glif](https://glif.app) user `fabian3000`. <Gallery /> ## Trigger words You should use `fontsheet` to trigger the image generation. ## Download model Weights for this model are available in Safetensors format. [Download](/glif-loradex-trainer/fabian3000_fontsheet3/tree/main) them in the Files & versions tab. ## License This model is licensed under the [flux-1-dev-non-commercial-license](https://huggingface.co/black-forest-labs/FLUX.1-dev/blob/main/LICENSE.md).
glif-loradex-trainer/goldenark__Test2Semi-realistic-anime-portrait	glif-loradex-trainer	2024-10-11T10:47:20Z	22	1	diffusers	[ "diffusers", "text-to-image", "template:sd-lora", "base_model:black-forest-labs/FLUX.1-dev", "base_model:finetune:black-forest-labs/FLUX.1-dev", "license:other", "region:us", "flux", "lora", "base_model:adapter:black-forest-labs/FLUX.1-dev" ]	text-to-image	2024-09-20T05:58:11Z	--- base_model: black-forest-labs/FLUX.1-dev license: other license_name: flux-1-dev-non-commercial-license license_link: https://huggingface.co/black-forest-labs/FLUX.1-dev/blob/main/LICENSE.md tags: - diffusers - text-to-image - template:sd-lora - base_model:black-forest-labs/FLUX.1-dev - base_model:finetune:black-forest-labs/FLUX.1-dev - license:other - region:us - flux - lora widget: - output: url: https://huggingface.co/glif-loradex-trainer/goldenark__Test2Semi-realistic-anime-portrait/resolve/main/samples/1726811829456__000003000_0.jpg text: man, sitting on a noble chair A semi-realistic anime portrait - output: url: https://huggingface.co/glif-loradex-trainer/goldenark__Test2Semi-realistic-anime-portrait/resolve/main/samples/1726811854138__000003000_1.jpg text: girl, sitting on a noble chair A semi-realistic anime portrait - output: url: https://huggingface.co/glif-loradex-trainer/goldenark__Test2Semi-realistic-anime-portrait/resolve/main/samples/1726811879059__000003000_2.jpg text: woman, sitting on a noble chair A semi-realistic anime portrait trigger: A semi-realistic anime portrait instance_prompt: A semi-realistic anime portrait --- # Test2Semi-realistic-anime-portrait Model trained with [AI Toolkit by Ostris](https://github.com/ostris/ai-toolkit) under the [Glif Loradex program](https://huggingface.co/glif-loradex-trainer) by [Glif](https://glif.app) user `goldenark_`. <Gallery /> ## Trigger words You should use `A semi-realistic anime portrait` to trigger the image generation. ## Download model Weights for this model are available in Safetensors format. [Download](/glif-loradex-trainer/goldenark__Test2Semi-realistic-anime-portrait/tree/main) them in the Files & versions tab. ## License This model is licensed under the [flux-1-dev-non-commercial-license](https://huggingface.co/black-forest-labs/FLUX.1-dev/blob/main/LICENSE.md).
glif-loradex-trainer/AP123_flux_dev_1990s_rap_albums	glif-loradex-trainer	2024-10-11T10:47:18Z	45	0	diffusers	[ "diffusers", "text-to-image", "template:sd-lora", "base_model:black-forest-labs/FLUX.1-dev", "base_model:finetune:black-forest-labs/FLUX.1-dev", "license:other", "region:us", "flux", "lora", "base_model:adapter:black-forest-labs/FLUX.1-dev" ]	text-to-image	2024-09-20T04:23:31Z	--- base_model: black-forest-labs/FLUX.1-dev license: other license_name: flux-1-dev-non-commercial-license license_link: https://huggingface.co/black-forest-labs/FLUX.1-dev/blob/main/LICENSE.md tags: - diffusers - text-to-image - template:sd-lora - base_model:black-forest-labs/FLUX.1-dev - base_model:finetune:black-forest-labs/FLUX.1-dev - license:other - region:us - flux - lora widget: - output: url: https://huggingface.co/glif-loradex-trainer/AP123_flux_dev_1990s_rap_albums/resolve/main/samples/1726806146455__000001500_0.jpg text: wounded centaur, mythical creature r4p-styl3 - output: url: https://huggingface.co/glif-loradex-trainer/AP123_flux_dev_1990s_rap_albums/resolve/main/samples/1726806170998__000001500_1.jpg text: ruins of athens, snake r4p-styl3 - output: url: https://huggingface.co/glif-loradex-trainer/AP123_flux_dev_1990s_rap_albums/resolve/main/samples/1726806195540__000001500_2.jpg text: silver vampire sword r4p-styl3 trigger: r4p-styl3 instance_prompt: r4p-styl3 --- # flux_dev_1990s_rap_albums Model trained with [AI Toolkit by Ostris](https://github.com/ostris/ai-toolkit) under the [Glif Loradex program](https://huggingface.co/glif-loradex-trainer) by [Glif](https://glif.app) user `AP123`. <Gallery /> ## Trigger words You should use `r4p-styl3` to trigger the image generation. ## Download model Weights for this model are available in Safetensors format. [Download](/glif-loradex-trainer/AP123_flux_dev_1990s_rap_albums/tree/main) them in the Files & versions tab. ## License This model is licensed under the [flux-1-dev-non-commercial-license](https://huggingface.co/black-forest-labs/FLUX.1-dev/blob/main/LICENSE.md).
glif-loradex-trainer/goldenark__Test1_Semi-realistic_anime_portrait	glif-loradex-trainer	2024-10-11T10:47:15Z	6	0	diffusers	[ "diffusers", "text-to-image", "template:sd-lora", "base_model:black-forest-labs/FLUX.1-dev", "base_model:finetune:black-forest-labs/FLUX.1-dev", "license:other", "region:us", "flux", "lora", "base_model:adapter:black-forest-labs/FLUX.1-dev" ]	text-to-image	2024-09-20T02:45:49Z	--- base_model: black-forest-labs/FLUX.1-dev license: other license_name: flux-1-dev-non-commercial-license license_link: https://huggingface.co/black-forest-labs/FLUX.1-dev/blob/main/LICENSE.md tags: - diffusers - text-to-image - template:sd-lora - base_model:black-forest-labs/FLUX.1-dev - base_model:finetune:black-forest-labs/FLUX.1-dev - license:other - region:us - flux - lora widget: - output: url: https://huggingface.co/glif-loradex-trainer/goldenark__Test1_Semi-realistic_anime_portrait/resolve/main/samples/1726800285663__000001500_0.jpg text: man, sitting A Semi-realistic anime portrait - output: url: https://huggingface.co/glif-loradex-trainer/goldenark__Test1_Semi-realistic_anime_portrait/resolve/main/samples/1726800310263__000001500_1.jpg text: girl, sitting A Semi-realistic anime portrait - output: url: https://huggingface.co/glif-loradex-trainer/goldenark__Test1_Semi-realistic_anime_portrait/resolve/main/samples/1726800334843__000001500_2.jpg text: woman, sitting A Semi-realistic anime portrait trigger: A Semi-realistic anime portrait instance_prompt: A Semi-realistic anime portrait --- # Test1_Semi-realistic_anime_portrait Model trained with [AI Toolkit by Ostris](https://github.com/ostris/ai-toolkit) under the [Glif Loradex program](https://huggingface.co/glif-loradex-trainer) by [Glif](https://glif.app) user `goldenark_`. <Gallery /> ## Trigger words You should use `A Semi-realistic anime portrait` to trigger the image generation. ## Download model Weights for this model are available in Safetensors format. [Download](/glif-loradex-trainer/goldenark__Test1_Semi-realistic_anime_portrait/tree/main) them in the Files & versions tab. ## License This model is licensed under the [flux-1-dev-non-commercial-license](https://huggingface.co/black-forest-labs/FLUX.1-dev/blob/main/LICENSE.md).
glif-loradex-trainer/heather_huet_textiles	glif-loradex-trainer	2024-10-11T10:47:13Z	63	2	diffusers	[ "diffusers", "text-to-image", "template:sd-lora", "base_model:black-forest-labs/FLUX.1-dev", "base_model:finetune:black-forest-labs/FLUX.1-dev", "license:other", "region:us", "flux", "lora", "base_model:adapter:black-forest-labs/FLUX.1-dev" ]	text-to-image	2024-09-19T20:10:09Z	--- base_model: black-forest-labs/FLUX.1-dev license: other license_name: flux-1-dev-non-commercial-license license_link: https://huggingface.co/black-forest-labs/FLUX.1-dev/blob/main/LICENSE.md tags: - diffusers - text-to-image - template:sd-lora - base_model:black-forest-labs/FLUX.1-dev - base_model:finetune:black-forest-labs/FLUX.1-dev - license:other - region:us - flux - lora widget: - output: url: https://huggingface.co/glif-loradex-trainer/heather_huet_textiles/resolve/main/samples/1726776521249__000001500_0.jpg text: textile pattern of kittens jean baptiste huet - output: url: https://huggingface.co/glif-loradex-trainer/heather_huet_textiles/resolve/main/samples/1726776545977__000001500_1.jpg text: textile pattern of vintage cars jean baptiste huet - output: url: https://huggingface.co/glif-loradex-trainer/heather_huet_textiles/resolve/main/samples/1726776570716__000001500_2.jpg text: red textile pattern jean baptiste huet - output: url: https://huggingface.co/glif-loradex-trainer/heather_huet_textiles/resolve/main/samples/1726776595448__000001500_3.jpg text: black textile pattern of computers jean baptiste huet trigger: jean baptiste huet instance_prompt: jean baptiste huet --- # huet_textiles Model trained with [AI Toolkit by Ostris](https://github.com/ostris/ai-toolkit) under the [Glif Loradex program](https://huggingface.co/glif-loradex-trainer) by [Glif](https://glif.app) user `heather`. <Gallery /> ## Trigger words You should use `jean baptiste huet` to trigger the image generation. ## Download model Weights for this model are available in Safetensors format. [Download](/glif-loradex-trainer/heather_huet_textiles/tree/main) them in the Files & versions tab. ## License This model is licensed under the [flux-1-dev-non-commercial-license](https://huggingface.co/black-forest-labs/FLUX.1-dev/blob/main/LICENSE.md).
glif-loradex-trainer/fabian3000_bosch	glif-loradex-trainer	2024-10-11T10:47:09Z	258	3	diffusers	[ "diffusers", "text-to-image", "template:sd-lora", "base_model:black-forest-labs/FLUX.1-dev", "base_model:finetune:black-forest-labs/FLUX.1-dev", "license:other", "region:us", "flux", "lora", "base_model:adapter:black-forest-labs/FLUX.1-dev" ]	text-to-image	2024-09-19T09:55:38Z	--- base_model: black-forest-labs/FLUX.1-dev license: other license_name: flux-1-dev-non-commercial-license license_link: https://huggingface.co/black-forest-labs/FLUX.1-dev/blob/main/LICENSE.md tags: - diffusers - text-to-image - template:sd-lora - base_model:black-forest-labs/FLUX.1-dev - base_model:finetune:black-forest-labs/FLUX.1-dev - license:other - region:us - flux - lora widget: - output: url: https://huggingface.co/glif-loradex-trainer/fabian3000_bosch/resolve/main/samples/1726739677630__000001500_0.jpg text: a boing 747 flying over a dark castle boschstyle - output: url: https://huggingface.co/glif-loradex-trainer/fabian3000_bosch/resolve/main/samples/1726739702342__000001500_1.jpg text: a snake man eating a blueberry, text says GLIF boschstyle - output: url: https://huggingface.co/glif-loradex-trainer/fabian3000_bosch/resolve/main/samples/1726739727063__000001500_2.jpg text: portrait of a cthulhu monster boschstyle trigger: boschstyle instance_prompt: boschstyle --- # bosch Model trained with [AI Toolkit by Ostris](https://github.com/ostris/ai-toolkit) under the [Glif Loradex program](https://huggingface.co/glif-loradex-trainer) by [Glif](https://glif.app) user `fabian3000`. <Gallery /> ## Trigger words You should use `boschstyle` to trigger the image generation. ## Download model Weights for this model are available in Safetensors format. [Download](/glif-loradex-trainer/fabian3000_bosch/tree/main) them in the Files & versions tab. ## License This model is licensed under the [flux-1-dev-non-commercial-license](https://huggingface.co/black-forest-labs/FLUX.1-dev/blob/main/LICENSE.md).
glif-loradex-trainer/fabian3000_vgaleaders	glif-loradex-trainer	2024-10-11T10:47:07Z	73	0	diffusers	[ "diffusers", "text-to-image", "template:sd-lora", "base_model:black-forest-labs/FLUX.1-dev", "base_model:finetune:black-forest-labs/FLUX.1-dev", "license:other", "region:us", "flux", "lora", "base_model:adapter:black-forest-labs/FLUX.1-dev" ]	text-to-image	2024-09-19T08:56:16Z	--- base_model: black-forest-labs/FLUX.1-dev license: other license_name: flux-1-dev-non-commercial-license license_link: https://huggingface.co/black-forest-labs/FLUX.1-dev/blob/main/LICENSE.md tags: - diffusers - text-to-image - template:sd-lora - base_model:black-forest-labs/FLUX.1-dev - base_model:finetune:black-forest-labs/FLUX.1-dev - license:other - region:us - flux - lora widget: - output: url: https://huggingface.co/glif-loradex-trainer/fabian3000_vgaleaders/resolve/main/samples/1726736115338__000001500_0.jpg text: portrait of a cthulhu monster, vgaleaders - output: url: https://huggingface.co/glif-loradex-trainer/fabian3000_vgaleaders/resolve/main/samples/1726736140938__000001500_1.jpg text: a cozy hut in the woods, vgaleaders - output: url: https://huggingface.co/glif-loradex-trainer/fabian3000_vgaleaders/resolve/main/samples/1726736165527__000001500_2.jpg text: a dark skeleton warrior holding a pan, vgaleaders trigger: vgaleaders instance_prompt: vgaleaders --- # vgaleaders Model trained with [AI Toolkit by Ostris](https://github.com/ostris/ai-toolkit) under the [Glif Loradex program](https://huggingface.co/glif-loradex-trainer) by [Glif](https://glif.app) user `fabian3000`. <Gallery /> ## Trigger words You should use `vgaleaders` to trigger the image generation. ## Download model Weights for this model are available in Safetensors format. [Download](/glif-loradex-trainer/fabian3000_vgaleaders/tree/main) them in the Files & versions tab. ## License This model is licensed under the [flux-1-dev-non-commercial-license](https://huggingface.co/black-forest-labs/FLUX.1-dev/blob/main/LICENSE.md).
glif-loradex-trainer/syntaxdiffusion_flux_dev_Rick_and_Morty_prodigy	glif-loradex-trainer	2024-10-11T10:47:05Z	31	0	diffusers	[ "diffusers", "text-to-image", "template:sd-lora", "base_model:black-forest-labs/FLUX.1-dev", "base_model:finetune:black-forest-labs/FLUX.1-dev", "license:other", "region:us", "flux", "lora", "base_model:adapter:black-forest-labs/FLUX.1-dev" ]	text-to-image	2024-09-19T06:56:29Z	--- base_model: black-forest-labs/FLUX.1-dev license: other license_name: flux-1-dev-non-commercial-license license_link: https://huggingface.co/black-forest-labs/FLUX.1-dev/blob/main/LICENSE.md tags: - diffusers - text-to-image - template:sd-lora - base_model:black-forest-labs/FLUX.1-dev - base_model:finetune:black-forest-labs/FLUX.1-dev - license:other - region:us - flux - lora widget: - output: url: https://huggingface.co/glif-loradex-trainer/syntaxdiffusion_flux_dev_Rick_and_Morty_prodigy/resolve/main/samples/1726728917801__000003000_0.jpg text: a unicorn crossing river styx WubbaLubbadubdub - output: url: https://huggingface.co/glif-loradex-trainer/syntaxdiffusion_flux_dev_Rick_and_Morty_prodigy/resolve/main/samples/1726728941633__000003000_1.jpg text: a scared hamster, WubbaLubbadubdub - output: url: https://huggingface.co/glif-loradex-trainer/syntaxdiffusion_flux_dev_Rick_and_Morty_prodigy/resolve/main/samples/1726728965489__000003000_2.jpg text: silver vampire sword with a golden cross, WubbaLubbadubdub trigger: WubbaLubbadubdub instance_prompt: WubbaLubbadubdub --- # flux_dev_Rick_and_Morty_prodigy Model trained with [AI Toolkit by Ostris](https://github.com/ostris/ai-toolkit) under the [Glif Loradex program](https://huggingface.co/glif-loradex-trainer) by [Glif](https://glif.app) user `syntaxdiffusion`. <Gallery /> ## Trigger words You should use `WubbaLubbadubdub` to trigger the image generation. ## Download model Weights for this model are available in Safetensors format. [Download](/glif-loradex-trainer/syntaxdiffusion_flux_dev_Rick_and_Morty_prodigy/tree/main) them in the Files & versions tab. ## License This model is licensed under the [flux-1-dev-non-commercial-license](https://huggingface.co/black-forest-labs/FLUX.1-dev/blob/main/LICENSE.md).
glif-loradex-trainer/AP123_flux_dev_power_slap_01b	glif-loradex-trainer	2024-10-11T10:47:02Z	20	0	diffusers	[ "diffusers", "text-to-image", "template:sd-lora", "base_model:black-forest-labs/FLUX.1-dev", "base_model:finetune:black-forest-labs/FLUX.1-dev", "license:other", "region:us", "flux", "lora", "base_model:adapter:black-forest-labs/FLUX.1-dev" ]	text-to-image	2024-09-19T05:59:12Z	--- base_model: black-forest-labs/FLUX.1-dev license: other license_name: flux-1-dev-non-commercial-license license_link: https://huggingface.co/black-forest-labs/FLUX.1-dev/blob/main/LICENSE.md tags: - diffusers - text-to-image - template:sd-lora - base_model:black-forest-labs/FLUX.1-dev - base_model:finetune:black-forest-labs/FLUX.1-dev - license:other - region:us - flux - lora widget: - output: url: https://huggingface.co/glif-loradex-trainer/AP123_flux_dev_power_slap_01b/resolve/main/samples/1726725471075__000001500_0.jpg text: wounded centaur, mythical creature sl4p - output: url: https://huggingface.co/glif-loradex-trainer/AP123_flux_dev_power_slap_01b/resolve/main/samples/1726725495789__000001500_1.jpg text: a human sl4p - output: url: https://huggingface.co/glif-loradex-trainer/AP123_flux_dev_power_slap_01b/resolve/main/samples/1726725520387__000001500_2.jpg text: an alien sl4p trigger: sl4p instance_prompt: sl4p --- # flux_dev_power_slap_01b Model trained with [AI Toolkit by Ostris](https://github.com/ostris/ai-toolkit) under the [Glif Loradex program](https://huggingface.co/glif-loradex-trainer) by [Glif](https://glif.app) user `AP123`. <Gallery /> ## Trigger words You should use `sl4p` to trigger the image generation. ## Download model Weights for this model are available in Safetensors format. [Download](/glif-loradex-trainer/AP123_flux_dev_power_slap_01b/tree/main) them in the Files & versions tab. ## License This model is licensed under the [flux-1-dev-non-commercial-license](https://huggingface.co/black-forest-labs/FLUX.1-dev/blob/main/LICENSE.md).
glif-loradex-trainer/saq1b_midjourney_v6_1_flux_lora	glif-loradex-trainer	2024-10-11T10:46:51Z	2,512	4	diffusers	[ "diffusers", "text-to-image", "template:sd-lora", "base_model:black-forest-labs/FLUX.1-dev", "base_model:finetune:black-forest-labs/FLUX.1-dev", "license:other", "region:us", "flux", "lora", "base_model:adapter:black-forest-labs/FLUX.1-dev" ]	text-to-image	2024-09-18T13:00:42Z	--- base_model: black-forest-labs/FLUX.1-dev license: other license_name: flux-1-dev-non-commercial-license license_link: https://huggingface.co/black-forest-labs/FLUX.1-dev/blob/main/LICENSE.md tags: - diffusers - text-to-image - template:sd-lora - base_model:black-forest-labs/FLUX.1-dev - base_model:finetune:black-forest-labs/FLUX.1-dev - license:other - region:us - flux - lora widget: - output: url: https://huggingface.co/glif-loradex-trainer/saq1b_midjourney_v6_1_flux_lora/resolve/main/samples/1726664375645__000003000_0.jpg text: wounded centaur, mythical creature mj-v6.1-style - output: url: https://huggingface.co/glif-loradex-trainer/saq1b_midjourney_v6_1_flux_lora/resolve/main/samples/1726664400259__000003000_1.jpg text: ruins of athens, snake mj-v6.1-style - output: url: https://huggingface.co/glif-loradex-trainer/saq1b_midjourney_v6_1_flux_lora/resolve/main/samples/1726664424870__000003000_2.jpg text: silver vampire sword mj-v6.1-style trigger: mj-v6.1-style instance_prompt: mj-v6.1-style --- # midjourney_v6_1_flux_lora Model trained with [AI Toolkit by Ostris](https://github.com/ostris/ai-toolkit) under the [Glif Loradex program](https://huggingface.co/glif-loradex-trainer) by [Glif](https://glif.app) user `saq1b`. <Gallery /> ## Trigger words You should use `mj-v6.1-style` to trigger the image generation. ## Download model Weights for this model are available in Safetensors format. [Download](/glif-loradex-trainer/saq1b_midjourney_v6_1_flux_lora/tree/main) them in the Files & versions tab. ## License This model is licensed under the [flux-1-dev-non-commercial-license](https://huggingface.co/black-forest-labs/FLUX.1-dev/blob/main/LICENSE.md).
glif-loradex-trainer/ampp_Minecraft_Skin	glif-loradex-trainer	2024-10-11T10:46:42Z	31	4	diffusers	[ "diffusers", "text-to-image", "template:sd-lora", "base_model:black-forest-labs/FLUX.1-dev", "base_model:finetune:black-forest-labs/FLUX.1-dev", "license:other", "region:us", "flux", "lora", "base_model:adapter:black-forest-labs/FLUX.1-dev" ]	text-to-image	2024-09-29T02:00:38Z	--- base_model: black-forest-labs/FLUX.1-dev license: other license_name: flux-1-dev-non-commercial-license license_link: https://huggingface.co/black-forest-labs/FLUX.1-dev/blob/main/LICENSE.md tags: - diffusers - text-to-image - template:sd-lora - base_model:black-forest-labs/FLUX.1-dev - base_model:finetune:black-forest-labs/FLUX.1-dev - license:other - region:us - flux - lora widget: - output: url: https://huggingface.co/glif-loradex-trainer/ampp_Minecraft_Skin/resolve/main/samples/1727575152017__000003000_0.jpg text: mona lisa M1n3cr4ft - output: url: https://huggingface.co/glif-loradex-trainer/ampp_Minecraft_Skin/resolve/main/samples/1727575162989__000003000_1.jpg text: johnny depp M1n3cr4ft - output: url: https://huggingface.co/glif-loradex-trainer/ampp_Minecraft_Skin/resolve/main/samples/1727575173957__000003000_2.jpg text: iron man M1n3cr4ft - output: url: https://huggingface.co/glif-loradex-trainer/ampp_Minecraft_Skin/resolve/main/samples/1727575184926__000003000_3.jpg text: M1n3cr4ft chewbacaca - output: url: https://huggingface.co/glif-loradex-trainer/ampp_Minecraft_Skin/resolve/main/samples/1727575195895__000003000_4.jpg text: M1n3cr4ft a necromancer wearing a purple and green outfit - output: url: https://huggingface.co/glif-loradex-trainer/ampp_Minecraft_Skin/resolve/main/samples/1727575207339__000003000_5.jpg text: M1n3cr4ft Shrek trigger: M1n3cr4ft instance_prompt: M1n3cr4ft --- # Minecraft_Skin Model trained with [AI Toolkit by Ostris](https://github.com/ostris/ai-toolkit) under the [Glif Loradex program](https://huggingface.co/glif-loradex-trainer) by [Glif](https://glif.app) user `ampp`. <Gallery /> ## Trigger words You should use `M1n3cr4ft` to trigger the image generation. ## Download model Weights for this model are available in Safetensors format. [Download](/glif-loradex-trainer/ampp_Minecraft_Skin/tree/main) them in the Files & versions tab. ## License This model is licensed under the [flux-1-dev-non-commercial-license](https://huggingface.co/black-forest-labs/FLUX.1-dev/blob/main/LICENSE.md).
glif-loradex-trainer/ddickinson_dstyl3xl	glif-loradex-trainer	2024-10-11T10:46:28Z	33	5	diffusers	[ "diffusers", "text-to-image", "template:sd-lora", "base_model:black-forest-labs/FLUX.1-dev", "base_model:finetune:black-forest-labs/FLUX.1-dev", "license:other", "region:us", "flux", "lora", "base_model:adapter:black-forest-labs/FLUX.1-dev" ]	text-to-image	2024-10-10T11:41:20Z	--- base_model: black-forest-labs/FLUX.1-dev license: other license_name: flux-1-dev-non-commercial-license license_link: https://huggingface.co/black-forest-labs/FLUX.1-dev/blob/main/LICENSE.md tags: - diffusers - text-to-image - template:sd-lora - base_model:black-forest-labs/FLUX.1-dev - base_model:finetune:black-forest-labs/FLUX.1-dev - license:other - region:us - flux - lora widget: - output: url: https://huggingface.co/glif-loradex-trainer/ddickinson_dstyl3xl/resolve/main/samples/1728560344025__000003000_0.jpg text: Pilot flying a hot air balloon shaped like a teapot, pouring rain on dry lands below in the style of dstyl3xl - output: url: https://huggingface.co/glif-loradex-trainer/ddickinson_dstyl3xl/resolve/main/samples/1728560368882__000003000_1.jpg text: A gigantic clockwork heart powering a mechanical forest, with gears and springs as leaves and branches in the style of dstyl3xl - output: url: https://huggingface.co/glif-loradex-trainer/ddickinson_dstyl3xl/resolve/main/samples/1728560393749__000003000_2.jpg text: Scientist with wild hair examining a glowing crystal, bioluminescent plants in the laboratory in the style of dstyl3xl - output: url: https://huggingface.co/glif-loradex-trainer/ddickinson_dstyl3xl/resolve/main/samples/1728560418604__000003000_3.jpg text: A time-traveling DeLorean car emerging from a swirling portal in the middle of a medieval village in the style of dstyl3xl - output: url: https://huggingface.co/glif-loradex-trainer/ddickinson_dstyl3xl/resolve/main/samples/1728560443459__000003000_4.jpg text: A group of friendly aliens having a picnic on the moon, Earth visible in the background in the style of dstyl3xl - output: url: https://huggingface.co/glif-loradex-trainer/ddickinson_dstyl3xl/resolve/main/samples/1728560468312__000003000_5.jpg text: A Victorian-era robot having a tea party with stuffed animals in a sunlit garden in the style of dstyl3xl trigger: in the style of dstyl3xl instance_prompt: in the style of dstyl3xl --- # dstyl3xl Model trained with [AI Toolkit by Ostris](https://github.com/ostris/ai-toolkit) under the [Glif Loradex program](https://huggingface.co/glif-loradex-trainer) by [Glif](https://glif.app) user `ddickinson`. <Gallery /> ## Trigger words You should use `in the style of dstyl3xl` to trigger the image generation. ## Download model Weights for this model are available in Safetensors format. [Download](/glif-loradex-trainer/ddickinson_dstyl3xl/tree/main) them in the Files & versions tab. ## License This model is licensed under the [flux-1-dev-non-commercial-license](https://huggingface.co/black-forest-labs/FLUX.1-dev/blob/main/LICENSE.md).
glif-loradex-trainer/maxxd4240_minimalistPastel	glif-loradex-trainer	2024-10-11T10:46:26Z	1,207	19	diffusers	[ "diffusers", "text-to-image", "template:sd-lora", "base_model:black-forest-labs/FLUX.1-dev", "base_model:finetune:black-forest-labs/FLUX.1-dev", "license:other", "region:us", "flux", "lora", "base_model:adapter:black-forest-labs/FLUX.1-dev" ]	text-to-image	2024-09-25T09:15:56Z	--- base_model: black-forest-labs/FLUX.1-dev license: other license_name: flux-1-dev-non-commercial-license license_link: https://huggingface.co/black-forest-labs/FLUX.1-dev/blob/main/LICENSE.md tags: - diffusers - text-to-image - template:sd-lora - base_model:black-forest-labs/FLUX.1-dev - base_model:finetune:black-forest-labs/FLUX.1-dev - license:other - region:us - flux - lora widget: - output: url: https://huggingface.co/glif-loradex-trainer/maxxd4240_minimalistPastel/resolve/main/samples/1727255690613__000002500_0.jpg text: wounded centaur, mythical creature minimalistPastel - output: url: https://huggingface.co/glif-loradex-trainer/maxxd4240_minimalistPastel/resolve/main/samples/1727255715214__000002500_1.jpg text: ruins of athens, snake minimalistPastel - output: url: https://huggingface.co/glif-loradex-trainer/maxxd4240_minimalistPastel/resolve/main/samples/1727255739813__000002500_2.jpg text: silver vampire sword minimalistPastel trigger: minimalistPastel instance_prompt: minimalistPastel --- # minimalistPastel Model trained with [AI Toolkit by Ostris](https://github.com/ostris/ai-toolkit) under the [Glif Loradex program](https://huggingface.co/glif-loradex-trainer) by [Glif](https://glif.app) user `maxxd4240`. <Gallery /> ## Trigger words You should use `minimalistPastel` to trigger the image generation. ## Download model Weights for this model are available in Safetensors format. [Download](/glif-loradex-trainer/maxxd4240_minimalistPastel/tree/main) them in the Files & versions tab. ## License This model is licensed under the [flux-1-dev-non-commercial-license](https://huggingface.co/black-forest-labs/FLUX.1-dev/blob/main/LICENSE.md).
lurker18/Starcoder2_15B_AWQ_4bit	lurker18	2024-10-11T10:39:15Z	7	0	null	[ "safetensors", "starcoder2", "license:bigcode-openrail-m", "4-bit", "awq", "region:us" ]	null	2024-10-11T09:46:12Z	--- license: bigcode-openrail-m ---
cryotron/q4_k_m_academic	cryotron	2024-10-11T10:30:43Z	21	0	transformers	[ "transformers", "gguf", "llama", "text-generation-inference", "unsloth", "en", "base_model:unsloth/llama-3-8b-bnb-4bit", "base_model:quantized:unsloth/llama-3-8b-bnb-4bit", "license:apache-2.0", "endpoints_compatible", "region:us" ]	null	2024-10-11T10:25:30Z	--- base_model: unsloth/llama-3-8b-bnb-4bit language: - en license: apache-2.0 tags: - text-generation-inference - transformers - unsloth - llama - gguf --- # Uploaded model - Developed by: cryotron - License: apache-2.0 - Finetuned from model : unsloth/llama-3-8b-bnb-4bit This llama model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library. [<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)
sania963/sql_v5	sania963	2024-10-11T10:29:50Z	76	0	transformers	[ "transformers", "safetensors", "mistral", "text-generation", "trl", "sft", "conversational", "arxiv:1910.09700", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "4-bit", "bitsandbytes", "region:us" ]	text-generation	2024-10-11T10:27:42Z	--- library_name: transformers tags: - trl - sft --- # Model Card for Model ID <!-- Provide a quick summary of what the model is/does. --> ## Model Details ### Model Description <!-- Provide a longer summary of what this model is. --> This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated. - Developed by: [More Information Needed] - Funded by [optional]: [More Information Needed] - Shared by [optional]: [More Information Needed] - Model type: [More Information Needed] - Language(s) (NLP): [More Information Needed] - License: [More Information Needed] - Finetuned from model [optional]: [More Information Needed] ### Model Sources [optional] <!-- Provide the basic links for the model. --> - Repository: [More Information Needed] - Paper [optional]: [More Information Needed] - Demo [optional]: [More Information Needed] ## Uses <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. --> ### Direct Use <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. --> [More Information Needed] ### Downstream Use [optional] <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app --> [More Information Needed] ### Out-of-Scope Use <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. --> [More Information Needed] ## Bias, Risks, and Limitations <!-- This section is meant to convey both technical and sociotechnical limitations. --> [More Information Needed] ### Recommendations <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. --> Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. [More Information Needed] ## Training Details ### Training Data <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. --> [More Information Needed] ### Training Procedure <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. --> #### Preprocessing [optional] [More Information Needed] #### Training Hyperparameters - Training regime: [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision --> #### Speeds, Sizes, Times [optional] <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. --> [More Information Needed] ## Evaluation <!-- This section describes the evaluation protocols and provides the results. --> ### Testing Data, Factors & Metrics #### Testing Data <!-- This should link to a Dataset Card if possible. --> [More Information Needed] #### Factors <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. --> [More Information Needed] #### Metrics <!-- These are the evaluation metrics being used, ideally with a description of why. --> [More Information Needed] ### Results [More Information Needed] #### Summary ## Model Examination [optional] <!-- Relevant interpretability work for the model goes here --> [More Information Needed] ## Environmental Impact <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly --> Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). - Hardware Type: [More Information Needed] - Hours used: [More Information Needed] - Cloud Provider: [More Information Needed] - Compute Region: [More Information Needed] - Carbon Emitted: [More Information Needed] ## Technical Specifications [optional] ### Model Architecture and Objective [More Information Needed] ### Compute Infrastructure [More Information Needed] #### Hardware [More Information Needed] #### Software [More Information Needed] ## Citation [optional] <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. --> BibTeX: [More Information Needed] APA: [More Information Needed] ## Glossary [optional] <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. --> [More Information Needed] ## More Information [optional] [More Information Needed] ## Model Card Authors [optional] [More Information Needed] ## Model Card Contact [More Information Needed]
qordmlwls/Llama-3.1-medical-v2	qordmlwls	2024-10-11T10:27:04Z	13	0	transformers	[ "transformers", "safetensors", "gguf", "llama", "text-generation-inference", "unsloth", "trl", "sft", "en", "base_model:unsloth/Meta-Llama-3.1-8B-Instruct-bnb-4bit", "base_model:quantized:unsloth/Meta-Llama-3.1-8B-Instruct-bnb-4bit", "license:apache-2.0", "endpoints_compatible", "region:us", "conversational" ]	null	2024-10-11T10:03:53Z	--- base_model: unsloth/Meta-Llama-3.1-8B-Instruct-bnb-4bit language: - en license: apache-2.0 tags: - text-generation-inference - transformers - unsloth - llama - trl - sft --- # Uploaded model - Developed by: qordmlwls - License: apache-2.0 - Finetuned from model : unsloth/Meta-Llama-3.1-8B-Instruct-bnb-4bit This llama model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library. [<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)
Alignment-Lab-AI/GPT-2-optim	Alignment-Lab-AI	2024-10-11T09:48:45Z	125	0	transformers	[ "transformers", "safetensors", "gpt2", "text-generation", "en", "dataset:HuggingFaceFW/fineweb-edu", "license:mit", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]	text-generation	2024-10-11T09:28:22Z	--- datasets: HuggingFaceFW/fineweb-edu widget: - example_title: Example interaction text: During photosynthesis in green plants inference: parameters: repetition_penalty: 1.3 language: - en library_name: transformers license: mit --- # Model Card for gpt2-124M-edu-fineweb-10B A 124M parameter GPT2 model trained with the 10B fineweb-edu dataset using [https://github.com/karpathy/llm.c](https://github.com/karpathy/llm.c) Training took 20 hours on a single 4090 GPU (limited to 350W), giving the following graphs: ![gpt2-124M-edu-fineweb-10B](https://huggingface.co/rhysjones/gpt2-124M-edu-fineweb-10B/resolve/main/graph.png) ## Training The training parameters where: ``` ./train_gpt2cu \ -i "dev/data/edu_fineweb10B/edu_fineweb_train_.bin" \ -j "dev/data/edu_fineweb10B/edu_fineweb_val_.bin" \ -o log124M \ -e "d12" \ -b 56 -t 1024 \ -d 458752 \ -r 1 \ -z 1 \ -c 0.1 \ -l 0.002 \ -q 0.0 \ -u 700 \ -n 5000 \ -v 250 -s 20000 \ -h 1 ``` The model has had no further finetuning. ## Evaluation Evals using [Eleuther AI Harness](https://github.com/EleutherAI/lm-evaluation-harness/tree/b281b0921b636bc36ad05c0b0b0763bd6dd43463) as described in the [open_llm_leaderboard](https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard) and comparing with those published for [openai-community/gpt2](https://huggingface.co/openai-community/gpt2) ![gpt2-124M-edu-fineweb-10B Evals](https://huggingface.co/rhysjones/gpt2-124M-edu-fineweb-10B/resolve/main/evals_124M.png) \| Eval Test \| Score \| \| --------- \| ----- \| \| arc_challenge (25 shot) \| 24.49 \| \| gsm8k (5 shot) \| 0.08 \| \| hellaswag (10 shot) \| 32.64 \| \| mmlu (5 shot) \| 26.06 \| \| truthfulqa (0 shot) \| 42.45 \| \| winogrande (5 shot) \| 52.17 \| \| Overall Score \| 29.65 \|
OHCHANG/distilbert-base-uncased-finetuned-emotion	OHCHANG	2024-10-11T09:47:51Z	117	0	transformers	[ "transformers", "safetensors", "distilbert", "text-classification", "generated_from_trainer", "base_model:distilbert/distilbert-base-uncased", "base_model:finetune:distilbert/distilbert-base-uncased", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "region:us" ]	text-classification	2024-10-11T09:27:48Z	--- library_name: transformers license: apache-2.0 base_model: distilbert-base-uncased tags: - generated_from_trainer metrics: - accuracy - f1 model-index: - name: distilbert-base-uncased-finetuned-emotion results: [] --- <!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # distilbert-base-uncased-finetuned-emotion This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on an unknown dataset. It achieves the following results on the evaluation set: - Loss: 0.2016 - Accuracy: 0.9295 - F1: 0.9294 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 2e-05 - train_batch_size: 64 - eval_batch_size: 64 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - num_epochs: 2 ### Training results \| Training Loss \| Epoch \| Step \| Validation Loss \| Accuracy \| F1 \| \|:-------------:\|:-----:\|:----:\|:---------------:\|:--------:\|:------:\| \| 0.8132 \| 1.0 \| 250 \| 0.2923 \| 0.908 \| 0.9082 \| \| 0.236 \| 2.0 \| 500 \| 0.2016 \| 0.9295 \| 0.9294 \| ### Framework versions - Transformers 4.45.2 - Pytorch 2.4.1+cu124 - Datasets 3.0.1 - Tokenizers 0.20.0
RichardErkhov/cloudyu_-_Yi-34Bx2-MoE-60B-DPO-gguf	RichardErkhov	2024-10-11T09:47:38Z	5	0	null	[ "gguf", "endpoints_compatible", "region:us", "conversational" ]	null	2024-10-10T18:44:08Z	Quantization made by Richard Erkhov. [Github](https://github.com/RichardErkhov) [Discord](https://discord.gg/pvy7H8DZMG) [Request more models](https://github.com/RichardErkhov/quant_request) Yi-34Bx2-MoE-60B-DPO - GGUF - Model creator: https://huggingface.co/cloudyu/ - Original model: https://huggingface.co/cloudyu/Yi-34Bx2-MoE-60B-DPO/ \| Name \| Quant method \| Size \| \| ---- \| ---- \| ---- \| \| [Yi-34Bx2-MoE-60B-DPO.Q2_K.gguf](https://huggingface.co/RichardErkhov/cloudyu_-_Yi-34Bx2-MoE-60B-DPO-gguf/blob/main/Yi-34Bx2-MoE-60B-DPO.Q2_K.gguf) \| Q2_K \| 20.85GB \| \| [Yi-34Bx2-MoE-60B-DPO.IQ3_XS.gguf](https://huggingface.co/RichardErkhov/cloudyu_-_Yi-34Bx2-MoE-60B-DPO-gguf/blob/main/Yi-34Bx2-MoE-60B-DPO.IQ3_XS.gguf) \| IQ3_XS \| 23.26GB \| \| [Yi-34Bx2-MoE-60B-DPO.IQ3_S.gguf](https://huggingface.co/RichardErkhov/cloudyu_-_Yi-34Bx2-MoE-60B-DPO-gguf/blob/main/Yi-34Bx2-MoE-60B-DPO.IQ3_S.gguf) \| IQ3_S \| 2.54GB \| \| [Yi-34Bx2-MoE-60B-DPO.Q3_K_S.gguf](https://huggingface.co/RichardErkhov/cloudyu_-_Yi-34Bx2-MoE-60B-DPO-gguf/blob/main/Yi-34Bx2-MoE-60B-DPO.Q3_K_S.gguf) \| Q3_K_S \| 24.51GB \| \| [Yi-34Bx2-MoE-60B-DPO.IQ3_M.gguf](https://huggingface.co/RichardErkhov/cloudyu_-_Yi-34Bx2-MoE-60B-DPO-gguf/blob/main/Yi-34Bx2-MoE-60B-DPO.IQ3_M.gguf) \| IQ3_M \| 25.2GB \| \| [Yi-34Bx2-MoE-60B-DPO.Q3_K.gguf](https://huggingface.co/RichardErkhov/cloudyu_-_Yi-34Bx2-MoE-60B-DPO-gguf/blob/main/Yi-34Bx2-MoE-60B-DPO.Q3_K.gguf) \| Q3_K \| 27.23GB \| \| [Yi-34Bx2-MoE-60B-DPO.Q3_K_M.gguf](https://huggingface.co/RichardErkhov/cloudyu_-_Yi-34Bx2-MoE-60B-DPO-gguf/blob/main/Yi-34Bx2-MoE-60B-DPO.Q3_K_M.gguf) \| Q3_K_M \| 27.23GB \| \| [Yi-34Bx2-MoE-60B-DPO.Q3_K_L.gguf](https://huggingface.co/RichardErkhov/cloudyu_-_Yi-34Bx2-MoE-60B-DPO-gguf/blob/main/Yi-34Bx2-MoE-60B-DPO.Q3_K_L.gguf) \| Q3_K_L \| 29.58GB \| \| [Yi-34Bx2-MoE-60B-DPO.IQ4_XS.gguf](https://huggingface.co/RichardErkhov/cloudyu_-_Yi-34Bx2-MoE-60B-DPO-gguf/blob/main/Yi-34Bx2-MoE-60B-DPO.IQ4_XS.gguf) \| IQ4_XS \| 30.58GB \| \| [Yi-34Bx2-MoE-60B-DPO.Q4_0.gguf](https://huggingface.co/RichardErkhov/cloudyu_-_Yi-34Bx2-MoE-60B-DPO-gguf/blob/main/Yi-34Bx2-MoE-60B-DPO.Q4_0.gguf) \| Q4_0 \| 31.97GB \| \| [Yi-34Bx2-MoE-60B-DPO.IQ4_NL.gguf](https://huggingface.co/RichardErkhov/cloudyu_-_Yi-34Bx2-MoE-60B-DPO-gguf/blob/main/Yi-34Bx2-MoE-60B-DPO.IQ4_NL.gguf) \| IQ4_NL \| 24.73GB \| \| [Yi-34Bx2-MoE-60B-DPO.Q4_K_S.gguf](https://huggingface.co/RichardErkhov/cloudyu_-_Yi-34Bx2-MoE-60B-DPO-gguf/blob/main/Yi-34Bx2-MoE-60B-DPO.Q4_K_S.gguf) \| Q4_K_S \| 12.69GB \| \| [Yi-34Bx2-MoE-60B-DPO.Q4_K.gguf](https://huggingface.co/RichardErkhov/cloudyu_-_Yi-34Bx2-MoE-60B-DPO-gguf/blob/main/Yi-34Bx2-MoE-60B-DPO.Q4_K.gguf) \| Q4_K \| 34.14GB \| \| [Yi-34Bx2-MoE-60B-DPO.Q4_K_M.gguf](https://huggingface.co/RichardErkhov/cloudyu_-_Yi-34Bx2-MoE-60B-DPO-gguf/blob/main/Yi-34Bx2-MoE-60B-DPO.Q4_K_M.gguf) \| Q4_K_M \| 34.14GB \| \| [Yi-34Bx2-MoE-60B-DPO.Q4_1.gguf](https://huggingface.co/RichardErkhov/cloudyu_-_Yi-34Bx2-MoE-60B-DPO-gguf/blob/main/Yi-34Bx2-MoE-60B-DPO.Q4_1.gguf) \| Q4_1 \| 35.49GB \| \| [Yi-34Bx2-MoE-60B-DPO.Q5_0.gguf](https://huggingface.co/RichardErkhov/cloudyu_-_Yi-34Bx2-MoE-60B-DPO-gguf/tree/main/) \| Q5_0 \| 39.0GB \| \| [Yi-34Bx2-MoE-60B-DPO.Q5_K_S.gguf](https://huggingface.co/RichardErkhov/cloudyu_-_Yi-34Bx2-MoE-60B-DPO-gguf/tree/main/) \| Q5_K_S \| 39.0GB \| \| [Yi-34Bx2-MoE-60B-DPO.Q5_K.gguf](https://huggingface.co/RichardErkhov/cloudyu_-_Yi-34Bx2-MoE-60B-DPO-gguf/tree/main/) \| Q5_K \| 40.12GB \| \| [Yi-34Bx2-MoE-60B-DPO.Q5_K_M.gguf](https://huggingface.co/RichardErkhov/cloudyu_-_Yi-34Bx2-MoE-60B-DPO-gguf/tree/main/) \| Q5_K_M \| 40.12GB \| \| [Yi-34Bx2-MoE-60B-DPO.Q5_1.gguf](https://huggingface.co/RichardErkhov/cloudyu_-_Yi-34Bx2-MoE-60B-DPO-gguf/tree/main/) \| Q5_1 \| 42.51GB \| \| [Yi-34Bx2-MoE-60B-DPO.Q6_K.gguf](https://huggingface.co/RichardErkhov/cloudyu_-_Yi-34Bx2-MoE-60B-DPO-gguf/tree/main/) \| Q6_K \| 46.47GB \| \| [Yi-34Bx2-MoE-60B-DPO.Q8_0.gguf](https://huggingface.co/RichardErkhov/cloudyu_-_Yi-34Bx2-MoE-60B-DPO-gguf/tree/main/) \| Q8_0 \| 60.18GB \| Original model description: --- license: apache-2.0 tags: - yi - moe - DPO model-index: - name: Yi-34Bx2-MoE-60B-DPO results: - task: type: text-generation name: Text Generation dataset: name: IFEval (0-Shot) type: HuggingFaceH4/ifeval args: num_few_shot: 0 metrics: - type: inst_level_strict_acc and prompt_level_strict_acc value: 53.19 name: strict accuracy source: url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=cloudyu/Yi-34Bx2-MoE-60B-DPO name: Open LLM Leaderboard - task: type: text-generation name: Text Generation dataset: name: BBH (3-Shot) type: BBH args: num_few_shot: 3 metrics: - type: acc_norm value: 31.26 name: normalized accuracy source: url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=cloudyu/Yi-34Bx2-MoE-60B-DPO name: Open LLM Leaderboard - task: type: text-generation name: Text Generation dataset: name: MATH Lvl 5 (4-Shot) type: hendrycks/competition_math args: num_few_shot: 4 metrics: - type: exact_match value: 6.19 name: exact match source: url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=cloudyu/Yi-34Bx2-MoE-60B-DPO name: Open LLM Leaderboard - task: type: text-generation name: Text Generation dataset: name: GPQA (0-shot) type: Idavidrein/gpqa args: num_few_shot: 0 metrics: - type: acc_norm value: 9.62 name: acc_norm source: url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=cloudyu/Yi-34Bx2-MoE-60B-DPO name: Open LLM Leaderboard - task: type: text-generation name: Text Generation dataset: name: MuSR (0-shot) type: TAUR-Lab/MuSR args: num_few_shot: 0 metrics: - type: acc_norm value: 14.32 name: acc_norm source: url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=cloudyu/Yi-34Bx2-MoE-60B-DPO name: Open LLM Leaderboard - task: type: text-generation name: Text Generation dataset: name: MMLU-PRO (5-shot) type: TIGER-Lab/MMLU-Pro config: main split: test args: num_few_shot: 5 metrics: - type: acc value: 40.85 name: accuracy source: url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=cloudyu/Yi-34Bx2-MoE-60B-DPO name: Open LLM Leaderboard --- * [This is DPO improved version of cloudyu/Yi-34Bx2-MoE-60B](https://huggingface.co/cloudyu/Yi-34Bx2-MoE-60B) * [DPO Trainer](https://huggingface.co/docs/trl/main/en/dpo_trainer) * metrics not test! # [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard) Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_cloudyu__Yi-34Bx2-MoE-60B-DPO) \| Metric \|Value\| \|-------------------\|----:\| \|Avg. \|25.91\| \|IFEval (0-Shot) \|53.19\| \|BBH (3-Shot) \|31.26\| \|MATH Lvl 5 (4-Shot)\| 6.19\| \|GPQA (0-shot) \| 9.62\| \|MuSR (0-shot) \|14.32\| \|MMLU-PRO (5-shot) \|40.85\|
b09501048/detr	b09501048	2024-10-11T09:44:41Z	219	0	transformers	[ "transformers", "tensorboard", "safetensors", "detr", "object-detection", "generated_from_trainer", "base_model:facebook/detr-resnet-50", "base_model:finetune:facebook/detr-resnet-50", "license:apache-2.0", "endpoints_compatible", "region:us" ]	object-detection	2024-10-10T08:52:26Z	--- library_name: transformers license: apache-2.0 base_model: facebook/detr-resnet-50 tags: - generated_from_trainer model-index: - name: detr results: [] --- <!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> [<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/djengo890-national-taiwan-university/CVDPL_HW1_DETR/runs/gdqqmrof) [<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/djengo890-national-taiwan-university/CVDPL_HW1_DETR/runs/gdqqmrof) # detr This model is a fine-tuned version of [facebook/detr-resnet-50](https://huggingface.co/facebook/detr-resnet-50) on an unknown dataset. It achieves the following results on the evaluation set: - Loss: 2.1588 - Map: 0.0662 - Map 50: 0.1137 - Map 75: 0.0667 - Map Small: 0.0 - Map Medium: 0.0013 - Map Large: 0.0706 - Mar 1: 0.0705 - Mar 10: 0.1303 - Mar 100: 0.1374 - Mar Small: 0.0 - Mar Medium: 0.009 - Mar Large: 0.1536 - Map Person: 0.5545 - Mar 100 Person: 0.6988 - Map Ear: 0.0068 - Mar 100 Ear: 0.1599 - Map Earmuffs: 0.0 - Mar 100 Earmuffs: 0.0 - Map Face: 0.1494 - Mar 100 Face: 0.3924 - Map Face-guard: 0.0 - Mar 100 Face-guard: 0.0 - Map Face-mask-medical: 0.0 - Mar 100 Face-mask-medical: 0.0 - Map Foot: 0.0 - Mar 100 Foot: 0.0 - Map Tools: 0.0012 - Mar 100 Tools: 0.0722 - Map Glasses: 0.0 - Mar 100 Glasses: 0.0 - Map Gloves: 0.0 - Mar 100 Gloves: 0.0 - Map Helmet: 0.0 - Mar 100 Helmet: 0.0 - Map Hands: 0.1315 - Mar 100 Hands: 0.4111 - Map Head: 0.274 - Mar 100 Head: 0.5671 - Map Medical-suit: 0.0 - Mar 100 Medical-suit: 0.0 - Map Shoes: 0.0073 - Mar 100 Shoes: 0.035 - Map Safety-suit: 0.0 - Mar 100 Safety-suit: 0.0 - Map Safety-vest: 0.0 - Mar 100 Safety-vest: 0.0 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 5e-05 - train_batch_size: 32 - eval_batch_size: 32 - seed: 42 - gradient_accumulation_steps: 2 - total_train_batch_size: 64 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: cosine - num_epochs: 10 - mixed_precision_training: Native AMP ### Training results \| Training Loss \| Epoch \| Step \| Validation Loss \| Map \| Map 50 \| Map 75 \| Map Small \| Map Medium \| Map Large \| Mar 1 \| Mar 10 \| Mar 100 \| Mar Small \| Mar Medium \| Mar Large \| Map Person \| Mar 100 Person \| Map Ear \| Mar 100 Ear \| Map Earmuffs \| Mar 100 Earmuffs \| Map Face \| Mar 100 Face \| Map Face-guard \| Mar 100 Face-guard \| Map Face-mask-medical \| Mar 100 Face-mask-medical \| Map Foot \| Mar 100 Foot \| Map Tools \| Mar 100 Tools \| Map Glasses \| Mar 100 Glasses \| Map Gloves \| Mar 100 Gloves \| Map Helmet \| Mar 100 Helmet \| Map Hands \| Mar 100 Hands \| Map Head \| Mar 100 Head \| Map Medical-suit \| Mar 100 Medical-suit \| Map Shoes \| Mar 100 Shoes \| Map Safety-suit \| Mar 100 Safety-suit \| Map Safety-vest \| Mar 100 Safety-vest \| \|:-------------:\|:------:\|:----:\|:---------------:\|:------:\|:------:\|:------:\|:---------:\|:----------:\|:---------:\|:------:\|:------:\|:-------:\|:---------:\|:----------:\|:---------:\|:----------:\|:--------------:\|:-------:\|:-----------:\|:------------:\|:----------------:\|:--------:\|:------------:\|:--------------:\|:------------------:\|:---------------------:\|:-------------------------:\|:--------:\|:------------:\|:---------:\|:-------------:\|:-----------:\|:---------------:\|:----------:\|:--------------:\|:----------:\|:--------------:\|:---------:\|:-------------:\|:--------:\|:------------:\|:----------------:\|:--------------------:\|:---------:\|:-------------:\|:---------------:\|:-------------------:\|:---------------:\|:-------------------:\| \| No log \| 0.9913 \| 57 \| 2.9995 \| 0.0253 \| 0.0391 \| 0.0271 \| 0.0 \| 0.0001 \| 0.0263 \| 0.0319 \| 0.0569 \| 0.0684 \| 0.0 \| 0.0005 \| 0.0725 \| 0.3757 \| 0.6561 \| 0.0002 \| 0.0046 \| 0.0 \| 0.0 \| 0.0006 \| 0.0042 \| 0.0 \| 0.0 \| 0.0 \| 0.0 \| 0.0 \| 0.0 \| 0.0 \| 0.0 \| 0.0 \| 0.0 \| 0.0 \| 0.0 \| 0.0 \| 0.0 \| 0.0211 \| 0.3065 \| 0.0333 \| 0.1919 \| 0.0 \| 0.0 \| 0.0 \| 0.0 \| 0.0 \| 0.0 \| 0.0 \| 0.0 \| \| No log \| 2.0 \| 115 \| 2.6946 \| 0.0312 \| 0.0518 \| 0.0323 \| 0.0 \| 0.0002 \| 0.0327 \| 0.0411 \| 0.0775 \| 0.0874 \| 0.0 \| 0.003 \| 0.094 \| 0.42 \| 0.6762 \| 0.0007 \| 0.0246 \| 0.0 \| 0.0 \| 0.0053 \| 0.0515 \| 0.0 \| 0.0 \| 0.0 \| 0.0 \| 0.0 \| 0.0 \| 0.0 \| 0.0 \| 0.0 \| 0.0 \| 0.0 \| 0.0 \| 0.0 \| 0.0 \| 0.0373 \| 0.3427 \| 0.0669 \| 0.3916 \| 0.0 \| 0.0 \| 0.0 \| 0.0 \| 0.0 \| 0.0 \| 0.0 \| 0.0 \| \| No log \| 2.9913 \| 172 \| 2.5527 \| 0.0325 \| 0.0595 \| 0.0308 \| 0.0 \| 0.002 \| 0.0343 \| 0.0441 \| 0.0853 \| 0.0961 \| 0.0 \| 0.0057 \| 0.1058 \| 0.3649 \| 0.652 \| 0.0021 \| 0.0798 \| 0.0 \| 0.0 \| 0.0142 \| 0.0748 \| 0.0 \| 0.0 \| 0.0 \| 0.0 \| 0.0 \| 0.0 \| 0.0022 \| 0.0073 \| 0.0 \| 0.0 \| 0.0 \| 0.0 \| 0.0 \| 0.0 \| 0.0508 \| 0.3384 \| 0.1178 \| 0.482 \| 0.0 \| 0.0 \| 0.0 \| 0.0 \| 0.0 \| 0.0 \| 0.0 \| 0.0 \| \| No log \| 4.0 \| 230 \| 2.4637 \| 0.0425 \| 0.0788 \| 0.0396 \| 0.0 \| 0.0006 \| 0.0449 \| 0.0503 \| 0.0968 \| 0.1059 \| 0.0 \| 0.0049 \| 0.1168 \| 0.451 \| 0.6564 \| 0.0018 \| 0.0867 \| 0.0 \| 0.0 \| 0.0548 \| 0.1764 \| 0.0 \| 0.0 \| 0.0 \| 0.0 \| 0.0 \| 0.0 \| 0.0017 \| 0.0225 \| 0.0 \| 0.0 \| 0.0 \| 0.0 \| 0.0 \| 0.0 \| 0.0725 \| 0.3554 \| 0.1402 \| 0.5027 \| 0.0 \| 0.0 \| 0.0 \| 0.0 \| 0.0 \| 0.0 \| 0.0 \| 0.0 \| \| No log \| 4.9913 \| 287 \| 2.3455 \| 0.0527 \| 0.0929 \| 0.052 \| 0.0 \| 0.0006 \| 0.0561 \| 0.0625 \| 0.1154 \| 0.1234 \| 0.0 \| 0.0042 \| 0.1375 \| 0.4924 \| 0.6771 \| 0.0068 \| 0.1346 \| 0.0 \| 0.0 \| 0.1061 \| 0.3505 \| 0.0 \| 0.0 \| 0.0 \| 0.0 \| 0.0 \| 0.0 \| 0.0011 \| 0.0278 \| 0.0 \| 0.0 \| 0.0 \| 0.0 \| 0.0 \| 0.0 \| 0.0916 \| 0.3802 \| 0.1918 \| 0.5232 \| 0.0 \| 0.0 \| 0.0058 \| 0.0047 \| 0.0 \| 0.0 \| 0.0 \| 0.0 \| \| No log \| 6.0 \| 345 \| 2.2859 \| 0.0538 \| 0.0938 \| 0.0534 \| 0.0 \| 0.0011 \| 0.0572 \| 0.0624 \| 0.1175 \| 0.1268 \| 0.0 \| 0.0051 \| 0.1412 \| 0.5106 \| 0.6945 \| 0.0037 \| 0.1284 \| 0.0 \| 0.0 \| 0.1108 \| 0.3333 \| 0.0 \| 0.0 \| 0.0 \| 0.0 \| 0.0 \| 0.0 \| 0.0006 \| 0.0503 \| 0.0 \| 0.0 \| 0.0 \| 0.0 \| 0.0 \| 0.0 \| 0.1048 \| 0.4016 \| 0.1793 \| 0.5394 \| 0.0 \| 0.0 \| 0.0055 \| 0.0088 \| 0.0 \| 0.0 \| 0.0 \| 0.0 \| \| No log \| 6.9913 \| 402 \| 2.2126 \| 0.0609 \| 0.1056 \| 0.0596 \| 0.0 \| 0.0019 \| 0.065 \| 0.0681 \| 0.1257 \| 0.1319 \| 0.0 \| 0.0086 \| 0.1469 \| 0.5288 \| 0.6915 \| 0.0064 \| 0.1412 \| 0.0 \| 0.0 \| 0.1366 \| 0.3886 \| 0.0 \| 0.0 \| 0.0 \| 0.0 \| 0.0 \| 0.0 \| 0.0006 \| 0.0517 \| 0.0 \| 0.0 \| 0.0 \| 0.0 \| 0.0 \| 0.0 \| 0.1204 \| 0.3905 \| 0.2371 \| 0.5637 \| 0.0 \| 0.0 \| 0.0055 \| 0.0154 \| 0.0 \| 0.0 \| 0.0 \| 0.0 \| \| No log \| 8.0 \| 460 \| 2.1794 \| 0.0641 \| 0.11 \| 0.0643 \| 0.0 \| 0.0015 \| 0.0685 \| 0.0699 \| 0.1294 \| 0.1372 \| 0.0 \| 0.0089 \| 0.1533 \| 0.5525 \| 0.6964 \| 0.0064 \| 0.1599 \| 0.0 \| 0.0 \| 0.1375 \| 0.3892 \| 0.0 \| 0.0 \| 0.0 \| 0.0 \| 0.0 \| 0.0 \| 0.0012 \| 0.0775 \| 0.0 \| 0.0 \| 0.0 \| 0.0 \| 0.0 \| 0.0 \| 0.1273 \| 0.4089 \| 0.2586 \| 0.567 \| 0.0 \| 0.0 \| 0.007 \| 0.0333 \| 0.0 \| 0.0 \| 0.0 \| 0.0 \| \| 2.8481 \| 8.9913 \| 517 \| 2.1642 \| 0.0658 \| 0.113 \| 0.0661 \| 0.0 \| 0.0016 \| 0.0703 \| 0.0702 \| 0.1296 \| 0.1369 \| 0.0 \| 0.0091 \| 0.1532 \| 0.5529 \| 0.6969 \| 0.0067 \| 0.1606 \| 0.0 \| 0.0 \| 0.1475 \| 0.3875 \| 0.0 \| 0.0 \| 0.0 \| 0.0 \| 0.0 \| 0.0 \| 0.0012 \| 0.0725 \| 0.0 \| 0.0 \| 0.0 \| 0.0 \| 0.0 \| 0.0 \| 0.13 \| 0.4102 \| 0.2727 \| 0.5659 \| 0.0 \| 0.0 \| 0.0073 \| 0.0344 \| 0.0 \| 0.0 \| 0.0 \| 0.0 \| \| 2.8481 \| 9.9130 \| 570 \| 2.1588 \| 0.0662 \| 0.1137 \| 0.0667 \| 0.0 \| 0.0013 \| 0.0706 \| 0.0705 \| 0.1303 \| 0.1374 \| 0.0 \| 0.009 \| 0.1536 \| 0.5545 \| 0.6988 \| 0.0068 \| 0.1599 \| 0.0 \| 0.0 \| 0.1494 \| 0.3924 \| 0.0 \| 0.0 \| 0.0 \| 0.0 \| 0.0 \| 0.0 \| 0.0012 \| 0.0722 \| 0.0 \| 0.0 \| 0.0 \| 0.0 \| 0.0 \| 0.0 \| 0.1315 \| 0.4111 \| 0.274 \| 0.5671 \| 0.0 \| 0.0 \| 0.0073 \| 0.035 \| 0.0 \| 0.0 \| 0.0 \| 0.0 \| ### Framework versions - Transformers 4.44.2 - Pytorch 2.4.1+cu121 - Datasets 3.0.1 - Tokenizers 0.19.1
Kvisten/abisko-lite-3-v2	Kvisten	2024-10-11T09:44:16Z	6	0	diffusers	[ "diffusers", "text-to-image", "flux", "lora", "template:sd-lora", "ai-toolkit", "base_model:black-forest-labs/FLUX.1-schnell", "base_model:adapter:black-forest-labs/FLUX.1-schnell", "license:apache-2.0", "region:us" ]	text-to-image	2024-10-11T09:44:09Z	--- tags: - text-to-image - flux - lora - diffusers - template:sd-lora - ai-toolkit widget: - text: A light blue abisko-lite-3 tent set up on a rocky mountain ridge, surrounded by rugged terrain and distant snow-capped peaks. The tent's guy lines are secured to nearby rocks, and the fabric flutters slightly in the breeze. A few scattered wildflowers can be seen growing between the rocks. output: url: samples/1728639798907__000003500_0.jpg - text: A green Abisko lite 3 tent pitched in a dense forest clearing. Tall pine trees surround the tent, and dappled sunlight filters through the branches, casting soft shadows on the tent's surface. Fallen leaves and moss cover the ground, adding a touch of green to the scene. output: url: samples/1728639807671__000003500_1.jpg - text: A olive-green abisko-lite-3 tent set up in an open field covered in fresh snow. The tent is surrounded by tall pine trees dusted with snow, and the sky is overcast, with light snowflakes gently falling. The tent's guy lines are staked firmly into the snow, and a few animal tracks are visible nearby. output: url: samples/1728639816434__000003500_2.jpg - text: A 'ABISKO LITE 3' tent, olive-green color, pitched on a grassy hillside, with its streamlined, tunnel-shaped design tapering down from the higher front to the lower rear for better wind resistance. The tent's extended front vestibule provides sheltered storage space, with the zippered door partially open to reveal the interior. Multiple guy lines are secured tightly to the ground, keeping the fabric taut, while arched poles maintain the tent's aerodynamic shape. The rainfly extends close to the ground for full coverage, and ventilation flaps at both the front and rear ensure optimal airflow. The surrounding grass sways gently in the breeze. output: url: samples/1728639825196__000003500_3.jpg - text: A 'Abisko lite 3' tent, olive-green color, pitched on a grassy hillside, with its streamlined, tunnel-shaped design tapering down from the higher front to the lower rear for better wind resistance. The tent's extended front vestibule provides sheltered storage space, with the zippered door partially open to reveal the interior. Multiple guy lines are secured tightly to the ground, keeping the fabric taut, while arched poles maintain the tent's aerodynamic shape. The rainfly extends close to the ground for full coverage, and ventilation flaps at both the front and rear ensure optimal airflow. The surrounding grass sways gently in the breeze. output: url: samples/1728639833958__000003500_4.jpg - text: Create a high-quality commercial image of a light blue 'Abisko Lite 3' tent set up in the middle of Times Square in New York City during the evening. The tent features a tunnel-style design with a light blue rainfly that fully covers the structure, tapering from the front to the rear for enhanced wind resistance. The extended front vestibule is closed, and the arched poles create a streamlined shape, while the rear slopes downward to optimize aerodynamics. Surround the tent with the iconic bright neon lights from the billboards, casting colorful reflections onto the tent's surface. Capture the contrast between the outdoor gear and the lively urban setting, using a combination of evening light and vibrant neon glow to emphasize the tent details and the bustling atmosphere of Times Square. output: url: samples/1728639842723__000003500_5.jpg base_model: black-forest-labs/FLUX.1-schnell instance_prompt: ABISKO LITE 3 license: apache-2.0 --- # abisko_lite_3_v2 Model trained with [AI Toolkit by Ostris](https://github.com/ostris/ai-toolkit) <Gallery /> ## Trigger words You should use `ABISKO LITE 3` to trigger the image generation. ## Download model and use it with ComfyUI, AUTOMATIC1111, SD.Next, Invoke AI, etc. Weights for this model are available in Safetensors format. [Download](/Kvisten/abisko-lite-3-v2/tree/main) them in the Files & versions tab. ## Use it with the [🧨 diffusers library](https://github.com/huggingface/diffusers) ```py from diffusers import AutoPipelineForText2Image import torch pipeline = AutoPipelineForText2Image.from_pretrained('black-forest-labs/FLUX.1-schnell', torch_dtype=torch.bfloat16).to('cuda') pipeline.load_lora_weights('Kvisten/abisko-lite-3-v2', weight_name='abisko_lite_3_v2.safetensors') image = pipeline('A light blue abisko-lite-3 tent set up on a rocky mountain ridge, surrounded by rugged terrain and distant snow-capped peaks. The tent's guy lines are secured to nearby rocks, and the fabric flutters slightly in the breeze. A few scattered wildflowers can be seen growing between the rocks.').images[0] image.save("my_image.png") ``` For more details, including weighting, merging and fusing LoRAs, check the [documentation on loading LoRAs in diffusers](https://huggingface.co/docs/diffusers/main/en/using-diffusers/loading_adapters)
mradermacher/CursorCore-Yi-9B-GGUF	mradermacher	2024-10-11T09:36:07Z	44	0	transformers	[ "transformers", "gguf", "code", "en", "base_model:TechxGenus/CursorCore-Yi-9B", "base_model:quantized:TechxGenus/CursorCore-Yi-9B", "license:apache-2.0", "endpoints_compatible", "region:us", "conversational" ]	null	2024-10-11T06:28:50Z	--- base_model: TechxGenus/CursorCore-Yi-9B language: - en library_name: transformers license: apache-2.0 quantized_by: mradermacher tags: - code --- ## About <!-- ### quantize_version: 2 --> <!-- ### output_tensor_quantised: 1 --> <!-- ### convert_type: hf --> <!-- ### vocab_type: --> <!-- ### tags: --> static quants of https://huggingface.co/TechxGenus/CursorCore-Yi-9B <!-- provided-files --> weighted/imatrix quants are available at https://huggingface.co/mradermacher/CursorCore-Yi-9B-i1-GGUF ## Usage If you are unsure how to use GGUF files, refer to one of [TheBloke's READMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for more details, including on how to concatenate multi-part files. ## Provided Quants (sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants) \| Link \| Type \| Size/GB \| Notes \| \|:-----\|:-----\|--------:\|:------\| \| [GGUF](https://huggingface.co/mradermacher/CursorCore-Yi-9B-GGUF/resolve/main/CursorCore-Yi-9B.Q2_K.gguf) \| Q2_K \| 3.5 \| \| \| [GGUF](https://huggingface.co/mradermacher/CursorCore-Yi-9B-GGUF/resolve/main/CursorCore-Yi-9B.Q3_K_S.gguf) \| Q3_K_S \| 4.0 \| \| \| [GGUF](https://huggingface.co/mradermacher/CursorCore-Yi-9B-GGUF/resolve/main/CursorCore-Yi-9B.Q3_K_M.gguf) \| Q3_K_M \| 4.4 \| lower quality \| \| [GGUF](https://huggingface.co/mradermacher/CursorCore-Yi-9B-GGUF/resolve/main/CursorCore-Yi-9B.Q3_K_L.gguf) \| Q3_K_L \| 4.8 \| \| \| [GGUF](https://huggingface.co/mradermacher/CursorCore-Yi-9B-GGUF/resolve/main/CursorCore-Yi-9B.IQ4_XS.gguf) \| IQ4_XS \| 4.9 \| \| \| [GGUF](https://huggingface.co/mradermacher/CursorCore-Yi-9B-GGUF/resolve/main/CursorCore-Yi-9B.Q4_K_S.gguf) \| Q4_K_S \| 5.2 \| fast, recommended \| \| [GGUF](https://huggingface.co/mradermacher/CursorCore-Yi-9B-GGUF/resolve/main/CursorCore-Yi-9B.Q4_K_M.gguf) \| Q4_K_M \| 5.4 \| fast, recommended \| \| [GGUF](https://huggingface.co/mradermacher/CursorCore-Yi-9B-GGUF/resolve/main/CursorCore-Yi-9B.Q5_K_S.gguf) \| Q5_K_S \| 6.2 \| \| \| [GGUF](https://huggingface.co/mradermacher/CursorCore-Yi-9B-GGUF/resolve/main/CursorCore-Yi-9B.Q5_K_M.gguf) \| Q5_K_M \| 6.4 \| \| \| [GGUF](https://huggingface.co/mradermacher/CursorCore-Yi-9B-GGUF/resolve/main/CursorCore-Yi-9B.Q6_K.gguf) \| Q6_K \| 7.3 \| very good quality \| \| [GGUF](https://huggingface.co/mradermacher/CursorCore-Yi-9B-GGUF/resolve/main/CursorCore-Yi-9B.Q8_0.gguf) \| Q8_0 \| 9.5 \| fast, best quality \| \| [GGUF](https://huggingface.co/mradermacher/CursorCore-Yi-9B-GGUF/resolve/main/CursorCore-Yi-9B.f16.gguf) \| f16 \| 17.8 \| 16 bpw, overkill \| Here is a handy graph by ikawrakow comparing some lower-quality quant types (lower is better): ![image.png](https://www.nethype.de/huggingface_embed/quantpplgraph.png) And here are Artefact2's thoughts on the matter: https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9 ## FAQ / Model Request See https://huggingface.co/mradermacher/model_requests for some answers to questions you might have and/or if you want some other model quantized. ## Thanks I thank my company, [nethype GmbH](https://www.nethype.de/), for letting me use its servers and providing upgrades to my workstation to enable this work in my free time. <!-- end -->
mradermacher/CursorCore-Yi-9B-i1-GGUF	mradermacher	2024-10-11T09:36:07Z	48	0	transformers	[ "transformers", "gguf", "code", "en", "base_model:TechxGenus/CursorCore-Yi-9B", "base_model:quantized:TechxGenus/CursorCore-Yi-9B", "license:apache-2.0", "endpoints_compatible", "region:us", "imatrix", "conversational" ]	null	2024-10-11T08:12:08Z	--- base_model: TechxGenus/CursorCore-Yi-9B language: - en library_name: transformers license: apache-2.0 quantized_by: mradermacher tags: - code --- ## About <!-- ### quantize_version: 2 --> <!-- ### output_tensor_quantised: 1 --> <!-- ### convert_type: hf --> <!-- ### vocab_type: --> <!-- ### tags: nicoboss --> weighted/imatrix quants of https://huggingface.co/TechxGenus/CursorCore-Yi-9B <!-- provided-files --> static quants are available at https://huggingface.co/mradermacher/CursorCore-Yi-9B-GGUF ## Usage If you are unsure how to use GGUF files, refer to one of [TheBloke's READMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for more details, including on how to concatenate multi-part files. ## Provided Quants (sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants) \| Link \| Type \| Size/GB \| Notes \| \|:-----\|:-----\|--------:\|:------\| \| [GGUF](https://huggingface.co/mradermacher/CursorCore-Yi-9B-i1-GGUF/resolve/main/CursorCore-Yi-9B.i1-IQ1_S.gguf) \| i1-IQ1_S \| 2.1 \| for the desperate \| \| [GGUF](https://huggingface.co/mradermacher/CursorCore-Yi-9B-i1-GGUF/resolve/main/CursorCore-Yi-9B.i1-IQ1_M.gguf) \| i1-IQ1_M \| 2.3 \| mostly desperate \| \| [GGUF](https://huggingface.co/mradermacher/CursorCore-Yi-9B-i1-GGUF/resolve/main/CursorCore-Yi-9B.i1-IQ2_XXS.gguf) \| i1-IQ2_XXS \| 2.6 \| \| \| [GGUF](https://huggingface.co/mradermacher/CursorCore-Yi-9B-i1-GGUF/resolve/main/CursorCore-Yi-9B.i1-IQ2_XS.gguf) \| i1-IQ2_XS \| 2.8 \| \| \| [GGUF](https://huggingface.co/mradermacher/CursorCore-Yi-9B-i1-GGUF/resolve/main/CursorCore-Yi-9B.i1-IQ2_S.gguf) \| i1-IQ2_S \| 3.0 \| \| \| [GGUF](https://huggingface.co/mradermacher/CursorCore-Yi-9B-i1-GGUF/resolve/main/CursorCore-Yi-9B.i1-IQ2_M.gguf) \| i1-IQ2_M \| 3.2 \| \| \| [GGUF](https://huggingface.co/mradermacher/CursorCore-Yi-9B-i1-GGUF/resolve/main/CursorCore-Yi-9B.i1-Q2_K.gguf) \| i1-Q2_K \| 3.5 \| IQ3_XXS probably better \| \| [GGUF](https://huggingface.co/mradermacher/CursorCore-Yi-9B-i1-GGUF/resolve/main/CursorCore-Yi-9B.i1-IQ3_XXS.gguf) \| i1-IQ3_XXS \| 3.6 \| lower quality \| \| [GGUF](https://huggingface.co/mradermacher/CursorCore-Yi-9B-i1-GGUF/resolve/main/CursorCore-Yi-9B.i1-IQ3_XS.gguf) \| i1-IQ3_XS \| 3.8 \| \| \| [GGUF](https://huggingface.co/mradermacher/CursorCore-Yi-9B-i1-GGUF/resolve/main/CursorCore-Yi-9B.i1-Q3_K_S.gguf) \| i1-Q3_K_S \| 4.0 \| IQ3_XS probably better \| \| [GGUF](https://huggingface.co/mradermacher/CursorCore-Yi-9B-i1-GGUF/resolve/main/CursorCore-Yi-9B.i1-IQ3_S.gguf) \| i1-IQ3_S \| 4.0 \| beats Q3_K* \| \| [GGUF](https://huggingface.co/mradermacher/CursorCore-Yi-9B-i1-GGUF/resolve/main/CursorCore-Yi-9B.i1-IQ3_M.gguf) \| i1-IQ3_M \| 4.2 \| \| \| [GGUF](https://huggingface.co/mradermacher/CursorCore-Yi-9B-i1-GGUF/resolve/main/CursorCore-Yi-9B.i1-Q3_K_M.gguf) \| i1-Q3_K_M \| 4.4 \| IQ3_S probably better \| \| [GGUF](https://huggingface.co/mradermacher/CursorCore-Yi-9B-i1-GGUF/resolve/main/CursorCore-Yi-9B.i1-Q3_K_L.gguf) \| i1-Q3_K_L \| 4.8 \| IQ3_M probably better \| \| [GGUF](https://huggingface.co/mradermacher/CursorCore-Yi-9B-i1-GGUF/resolve/main/CursorCore-Yi-9B.i1-IQ4_XS.gguf) \| i1-IQ4_XS \| 4.9 \| \| \| [GGUF](https://huggingface.co/mradermacher/CursorCore-Yi-9B-i1-GGUF/resolve/main/CursorCore-Yi-9B.i1-Q4_0_4_4.gguf) \| i1-Q4_0_4_4 \| 5.1 \| fast on arm, low quality \| \| [GGUF](https://huggingface.co/mradermacher/CursorCore-Yi-9B-i1-GGUF/resolve/main/CursorCore-Yi-9B.i1-Q4_0_4_8.gguf) \| i1-Q4_0_4_8 \| 5.1 \| fast on arm+i8mm, low quality \| \| [GGUF](https://huggingface.co/mradermacher/CursorCore-Yi-9B-i1-GGUF/resolve/main/CursorCore-Yi-9B.i1-Q4_0_8_8.gguf) \| i1-Q4_0_8_8 \| 5.1 \| fast on arm+sve, low quality \| \| [GGUF](https://huggingface.co/mradermacher/CursorCore-Yi-9B-i1-GGUF/resolve/main/CursorCore-Yi-9B.i1-Q4_0.gguf) \| i1-Q4_0 \| 5.2 \| fast, low quality \| \| [GGUF](https://huggingface.co/mradermacher/CursorCore-Yi-9B-i1-GGUF/resolve/main/CursorCore-Yi-9B.i1-Q4_K_S.gguf) \| i1-Q4_K_S \| 5.2 \| optimal size/speed/quality \| \| [GGUF](https://huggingface.co/mradermacher/CursorCore-Yi-9B-i1-GGUF/resolve/main/CursorCore-Yi-9B.i1-Q4_K_M.gguf) \| i1-Q4_K_M \| 5.4 \| fast, recommended \| \| [GGUF](https://huggingface.co/mradermacher/CursorCore-Yi-9B-i1-GGUF/resolve/main/CursorCore-Yi-9B.i1-Q5_K_S.gguf) \| i1-Q5_K_S \| 6.2 \| \| \| [GGUF](https://huggingface.co/mradermacher/CursorCore-Yi-9B-i1-GGUF/resolve/main/CursorCore-Yi-9B.i1-Q5_K_M.gguf) \| i1-Q5_K_M \| 6.4 \| \| \| [GGUF](https://huggingface.co/mradermacher/CursorCore-Yi-9B-i1-GGUF/resolve/main/CursorCore-Yi-9B.i1-Q6_K.gguf) \| i1-Q6_K \| 7.3 \| practically like static Q6_K \| Here is a handy graph by ikawrakow comparing some lower-quality quant types (lower is better): ![image.png](https://www.nethype.de/huggingface_embed/quantpplgraph.png) And here are Artefact2's thoughts on the matter: https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9 ## FAQ / Model Request See https://huggingface.co/mradermacher/model_requests for some answers to questions you might have and/or if you want some other model quantized. ## Thanks I thank my company, [nethype GmbH](https://www.nethype.de/), for letting me use its servers and providing upgrades to my workstation to enable this work in my free time. Additional thanks to [@nicoboss](https://huggingface.co/nicoboss) for giving me access to his private supercomputer, enabling me to provide many more imatrix quants, at much higher quality, than I would otherwise be able to. <!-- end -->
hieundx/distilbert-base-uncased-distilled-clinc	hieundx	2024-10-11T09:21:41Z	106	0	transformers	[ "transformers", "safetensors", "distilbert", "text-classification", "generated_from_trainer", "base_model:distilbert/distilbert-base-uncased", "base_model:finetune:distilbert/distilbert-base-uncased", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "region:us" ]	text-classification	2024-10-11T09:18:52Z	--- library_name: transformers license: apache-2.0 base_model: distilbert-base-uncased tags: - generated_from_trainer metrics: - accuracy model-index: - name: distilbert-base-uncased-distilled-clinc results: [] --- <!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # distilbert-base-uncased-distilled-clinc This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on an unknown dataset. It achieves the following results on the evaluation set: - Loss: 0.3650 - Accuracy: 0.9448 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 2e-05 - train_batch_size: 48 - eval_batch_size: 48 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - num_epochs: 9 ### Training results \| Training Loss \| Epoch \| Step \| Validation Loss \| Accuracy \| \|:-------------:\|:-----:\|:----:\|:---------------:\|:--------:\| \| No log \| 1.0 \| 318 \| 2.7041 \| 0.7403 \| \| 3.157 \| 2.0 \| 636 \| 1.3959 \| 0.8613 \| \| 3.157 \| 3.0 \| 954 \| 0.7574 \| 0.9135 \| \| 1.2213 \| 4.0 \| 1272 \| 0.5136 \| 0.9268 \| \| 0.4979 \| 5.0 \| 1590 \| 0.4219 \| 0.9394 \| \| 0.4979 \| 6.0 \| 1908 \| 0.3916 \| 0.9410 \| \| 0.3031 \| 7.0 \| 2226 \| 0.3708 \| 0.9452 \| \| 0.2444 \| 8.0 \| 2544 \| 0.3666 \| 0.9452 \| \| 0.2444 \| 9.0 \| 2862 \| 0.3650 \| 0.9448 \| ### Framework versions - Transformers 4.44.2 - Pytorch 2.4.1+cu121 - Tokenizers 0.19.1
neighborwang/ModeliCo-8B	neighborwang	2024-10-11T09:19:36Z	13	2	transformers	[ "transformers", "tensorboard", "safetensors", "llama", "text-generation", "text-generation-inference", "peft", "text2text-generation", "en", "dataset:neighborwang/modelica_libraries", "base_model:meta-llama/Llama-3.1-8B-Instruct", "base_model:finetune:meta-llama/Llama-3.1-8B-Instruct", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "region:us" ]	text2text-generation	2024-09-28T08:27:47Z	--- base_model: meta-llama/Llama-3.1-8B-Instruct datasets: - neighborwang/modelica_libraries language: - en library_name: transformers license: apache-2.0 pipeline_tag: text2text-generation tags: - text-generation-inference - text-generation - peft --- # ModeliCo A cutting-edge LLM designed to empower users of all skill levels to effortlessly model complex systems and unlock the full potential of Modelica.
yash3056/Llama-3.2-1B-imdb	yash3056	2024-10-11T09:17:24Z	6,845	2	transformers	[ "transformers", "safetensors", "llama", "text-classification", "pytorch", "llama-3", "1b", "en", "dataset:stanfordnlp/imdb", "arxiv:1910.09700", "base_model:meta-llama/Llama-3.2-1B", "base_model:finetune:meta-llama/Llama-3.2-1B", "license:llama3.2", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]	text-classification	2024-10-04T14:00:04Z	--- license: llama3.2 datasets: - stanfordnlp/imdb language: - en metrics: - accuracy base_model: - meta-llama/Llama-3.2-1B new_version: yash3056/Llama-3.2-1B-imdb pipeline_tag: text-classification library_name: transformers tags: - transformers - pytorch - llama - llama-3 - 1b --- ## Model Details ### Model Description <!-- Provide a longer summary of what this model is. --> - Funded by [Intel]: [https://console.cloud.intel.com/] - Shared by [optional]: [More Information Needed] - Model type: Text Classification - Language(s) (NLP): [More Information Needed] - License: [Llama 3.2 Community License Agreement] - Finetuned from model [meta-llama/Llama-3.2-1B]: [https://huggingface.co/meta-llama/Llama-3.2-1B] ## Uses This model is designed for text classification tasks, specifically for binary sentiment analysis on datasets like IMDb, where the goal is to classify text as positive or negative. It can be used by data scientists, researchers, and developers to build applications for sentiment analysis, content moderation, or customer feedback analysis. The model can be fine-tuned for other binary or multi-class classification tasks in domains like social media monitoring, product reviews, and support ticket triage. Foreseeable users include AI researchers, developers, and businesses looking to automate text analysis at scale. ### Direct Use This model can be used directly to identify sentiments from text-based reviews, such as classifying whether a movie or product review is positive or negative. Without any further fine-tuning, it performs well on binary sentiment analysis tasks and can be employed out of the box for various applications like analyzing customer feedback, monitoring social media opinions, or automating sentiment tagging. The model is ideal for scenarios where sentiment needs to be quickly assessed from textual input without the need for deeper customizations. ### Downstream Use Fine-tuning for Binary Classification ```python from transformers import AutoTokenizer, AutoModelForSequenceClassification, Trainer, TrainingArguments from datasets import load_dataset # Load IMDb dataset for binary classification dataset = load_dataset("imdb") tokenizer = AutoTokenizer.from_pretrained("yash3056/Llama-3.2-1B-imdb") # Tokenize the dataset def preprocess(example): return tokenizer(example['text'], truncation=True, padding='max_length', max_length=128) tokenized_datasets = dataset.map(preprocess, batched=True) # Load model for binary classification (num_labels=2) model = AutoModelForSequenceClassification.from_pretrained("yash3056/Llama-3.2-1B-imdb", num_labels=2) # Training arguments training_args = TrainingArguments( output_dir="./results", evaluation_strategy="epoch", learning_rate=2e-5, per_device_train_batch_size=16, per_device_eval_batch_size=16, num_train_epochs=3, weight_decay=0.01, ) # Trainer trainer = Trainer( model=model, args=training_args, train_dataset=tokenized_datasets["train"], eval_dataset=tokenized_datasets["test"], ) # Fine-tune the model trainer.train() ``` Fine-tuning for Multi-Class Classification ```python from transformers import AutoTokenizer, AutoModelForSequenceClassification, Trainer, TrainingArguments from datasets import load_dataset # Load AG News dataset for multi-class classification (4 labels) dataset = load_dataset("ag_news") tokenizer = AutoTokenizer.from_pretrained("yash3056/Llama-3.2-1B-imdb") # Tokenize the dataset def preprocess(example): return tokenizer(example['text'], truncation=True, padding='max_length', max_length=128) tokenized_datasets = dataset.map(preprocess, batched=True) # Load model for multi-class classification (num_labels=4) model = AutoModelForSequenceClassification.from_pretrained("yash3056/Llama-3.2-1B-imdb", num_labels=4) # Training arguments training_args = TrainingArguments( output_dir="./results", evaluation_strategy="epoch", learning_rate=2e-5, per_device_train_batch_size=16, per_device_eval_batch_size=16, num_train_epochs=3, weight_decay=0.01, ) # Trainer trainer = Trainer( model=model, args=training_args, train_dataset=tokenized_datasets["train"], eval_dataset=tokenized_datasets["test"], ) # Fine-tune the model trainer.train() ``` <!-- ### Out-of-Scope Use <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. --> [More Information Needed] --> ## Bias, Risks, and Limitations While this model is effective for text classification and sentiment analysis, it has certain limitations and potential biases. The training data, such as the IMDb dataset, may contain inherent biases related to language use, cultural context, or demographics of reviewers, which could influence the model’s predictions. For example, the model might struggle with nuanced sentiment, sarcasm, or slang, leading to misclassifications. Additionally, it could exhibit biases toward particular opinions or groups if those were overrepresented or underrepresented in the training data. The model is also limited to binary sentiment classification, meaning it may oversimplify more complex emotional states expressed in text. Users should be cautious when applying the model in sensitive domains such as legal, medical, or psychological settings, where misclassification could have serious consequences. Proper review and adjustment of predictions are recommended, especially in high-stakes applications. ### Recommendations Users (both direct and downstream) should be aware of the potential risks, biases, and limitations inherent in this model. Given that the model may reflect biases present in the training data, it is recommended that users critically evaluate the model’s performance on specific datasets or contexts where fairness and accuracy are essential. For applications in sensitive areas like legal, healthcare, or hiring decisions, additional care should be taken to review the model's predictions, possibly combining them with human oversight. Fine-tuning the model on domain-specific data or implementing bias mitigation techniques can help reduce unintended bias. Additionally, regular re-evaluation and monitoring of the model in production environments are encouraged to ensure it continues to meet desired ethical and performance standards. ## How to Get Started with the Model Use the code below to get started with the model. ```python from transformers import AutoTokenizer, AutoModelForSequenceClassification # Load Model and tokenizers tokenizer = AutoTokenizer.from_pretrained("yash3056/Llama-3.2-1B-imdb") model = AutoModelForSequenceClassification.from_pretrained("yash3056/Llama-3.2-1B-imdb", num_labels=n) #n is the number of labels in the code ``` ## Training Details ### Training Data The model was trained on the IMDb dataset, a widely used benchmark for binary sentiment classification tasks. The dataset consists of movie reviews labeled as positive or negative, making it suitable for training models to understand sentiment in text. The dataset contains 50,000 reviews in total, evenly split between positive and negative labels, providing a balanced dataset for training and evaluation. Preprocessing involved tokenizing the text using the AutoTokenizer from Hugging Face's Transformers library, truncating and padding the sequences to a maximum length of 512 tokens. The training data was further split into training and validation sets with an 80-20 ratio. More information about the IMDb dataset can be found [here](https://huggingface.co/datasets/stanfordnlp/imdb). ### Training Procedure Training Procedure The training procedure used the Llama-3.2-1B model with modifications to suit the binary sentiment classification task. Training was performed for 10 epochs using a batch size of 8 and the AdamW optimizer with a learning rate of 3e-5. The learning rate was adjusted with a linear schedule, including a warmup of 40% of the total steps. The model was fine-tuned using the IMDb training dataset and evaluated on a separate test set. Validation and evaluation metrics were calculated after each epoch, including accuracy, precision, recall, F1-score, and ROC-AUC. The final model was saved after the last epoch, along with the tokenizer. Several plots, such as loss curves, accuracy curves, confusion matrix, and ROC curve, were generated to visually assess the model's performance. #### Preprocessing [optional] Text data was preprocessed by tokenizing with the Llama-3.2-1B model tokenizer. Sequences were truncated and padded to a maximum length of 512 tokens to ensure consistent input sizes for the model. Labels were encoded as integers (0 for negative and 1 for positive) for compatibility with the model. <!-- #### Training Hyperparameters - Training regime: [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision --> <!-- #### Speeds, Sizes, Times [optional] <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. --> <!-- [More Information Needed] --> ## Evaluation Training Loss: 0.0030, Accuracy: 0.9999 Validation Loss: 0.1196, Accuracy: 0.9628 ### Testing Data, Factors & Metrics #### Testing Data Test Loss: 0.1315 Test Accuracy: 0.9604 Precision: 0.9604 Recall: 0.9604 F1-score: 0.9604 AUC: 0.9604 <!-- #### Factors <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. --> <!-- [More Information Needed] #### Metrics <!-- These are the evaluation metrics being used, ideally with a description of why. --> <!-- [More Information Needed] ### Results [More Information Needed]--> #### Summary <!-- ## Model Examination [optional] <!-- Relevant interpretability work for the model goes here --> <!-- [More Information Needed] <!-- ## Environmental Impact <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly --> <!-- Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). - Hardware Type: [More Information Needed] - Hours used: [More Information Needed] - Cloud Provider: [More Information Needed] - Compute Region: [More Information Needed] - Carbon Emitted: [More Information Needed] --> ## Technical Specifications <!-- ### Model Architecture and Objective [More Information Needed] ### Compute Infrastructure [More Information Needed] --> #### Hardware [Intel® Data Center GPU Max 1550](https://www.intel.com/content/www/us/en/products/sku/232873/intel-data-center-gpu-max-1550/specifications.html) <!-- ## Citation [optional] <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. --> <!-- BibTeX: [More Information Needed] APA: [More Information Needed] --> ## Model Card Authors -Yash Prakash Narayan ([github](https://github.com/yash3056)) <!-- ## Model Card Contact [More Information Needed]-->
Viscoke/c10	Viscoke	2024-10-11T08:43:52Z	34	0	transformers	[ "transformers", "safetensors", "llama", "text-generation", "arxiv:1910.09700", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]	text-generation	2024-10-11T08:39:34Z	--- library_name: transformers tags: [] --- # Model Card for Model ID <!-- Provide a quick summary of what the model is/does. --> ## Model Details ### Model Description <!-- Provide a longer summary of what this model is. --> This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated. - Developed by: [More Information Needed] - Funded by [optional]: [More Information Needed] - Shared by [optional]: [More Information Needed] - Model type: [More Information Needed] - Language(s) (NLP): [More Information Needed] - License: [More Information Needed] - Finetuned from model [optional]: [More Information Needed] ### Model Sources [optional] <!-- Provide the basic links for the model. --> - Repository: [More Information Needed] - Paper [optional]: [More Information Needed] - Demo [optional]: [More Information Needed] ## Uses <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. --> ### Direct Use <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. --> [More Information Needed] ### Downstream Use [optional] <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app --> [More Information Needed] ### Out-of-Scope Use <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. --> [More Information Needed] ## Bias, Risks, and Limitations <!-- This section is meant to convey both technical and sociotechnical limitations. --> [More Information Needed] ### Recommendations <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. --> Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. [More Information Needed] ## Training Details ### Training Data <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. --> [More Information Needed] ### Training Procedure <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. --> #### Preprocessing [optional] [More Information Needed] #### Training Hyperparameters - Training regime: [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision --> #### Speeds, Sizes, Times [optional] <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. --> [More Information Needed] ## Evaluation <!-- This section describes the evaluation protocols and provides the results. --> ### Testing Data, Factors & Metrics #### Testing Data <!-- This should link to a Dataset Card if possible. --> [More Information Needed] #### Factors <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. --> [More Information Needed] #### Metrics <!-- These are the evaluation metrics being used, ideally with a description of why. --> [More Information Needed] ### Results [More Information Needed] #### Summary ## Model Examination [optional] <!-- Relevant interpretability work for the model goes here --> [More Information Needed] ## Environmental Impact <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly --> Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). - Hardware Type: [More Information Needed] - Hours used: [More Information Needed] - Cloud Provider: [More Information Needed] - Compute Region: [More Information Needed] - Carbon Emitted: [More Information Needed] ## Technical Specifications [optional] ### Model Architecture and Objective [More Information Needed] ### Compute Infrastructure [More Information Needed] #### Hardware [More Information Needed] #### Software [More Information Needed] ## Citation [optional] <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. --> BibTeX: [More Information Needed] APA: [More Information Needed] ## Glossary [optional] <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. --> [More Information Needed] ## More Information [optional] [More Information Needed] ## Model Card Authors [optional] [More Information Needed] ## Model Card Contact [More Information Needed]
SandeepCHV/dialogueSummary	SandeepCHV	2024-10-11T08:30:55Z	104	0	transformers	[ "transformers", "tensorboard", "safetensors", "bart", "text2text-generation", "generated_from_trainer", "dataset:samsum", "base_model:facebook/bart-large-cnn", "base_model:finetune:facebook/bart-large-cnn", "license:mit", "autotrain_compatible", "endpoints_compatible", "region:us" ]	text2text-generation	2024-10-11T08:02:46Z	--- library_name: transformers license: mit base_model: facebook/bart-large-cnn tags: - generated_from_trainer datasets: - samsum model-index: - name: dialogueSummary results: [] --- <!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # dialogueSummary This model is a fine-tuned version of [facebook/bart-large-cnn](https://huggingface.co/facebook/bart-large-cnn) on the samsum dataset. It achieves the following results on the evaluation set: - Loss: 1.3019 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 1e-05 - train_batch_size: 8 - eval_batch_size: 8 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - num_epochs: 1 ### Training results \| Training Loss \| Epoch \| Step \| Validation Loss \| \|:-------------:\|:-----:\|:----:\|:---------------:\| \| 0.8939 \| 1.0 \| 19 \| 1.3019 \| ### Framework versions - Transformers 4.44.2 - Pytorch 2.4.1+cu121 - Datasets 3.0.1 - Tokenizers 0.19.1
Viscoke/c9	Viscoke	2024-10-11T08:30:49Z	33	0	transformers	[ "transformers", "safetensors", "llama", "text-generation", "arxiv:1910.09700", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]	text-generation	2024-10-11T08:26:33Z	--- library_name: transformers tags: [] --- # Model Card for Model ID <!-- Provide a quick summary of what the model is/does. --> ## Model Details ### Model Description <!-- Provide a longer summary of what this model is. --> This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated. - Developed by: [More Information Needed] - Funded by [optional]: [More Information Needed] - Shared by [optional]: [More Information Needed] - Model type: [More Information Needed] - Language(s) (NLP): [More Information Needed] - License: [More Information Needed] - Finetuned from model [optional]: [More Information Needed] ### Model Sources [optional] <!-- Provide the basic links for the model. --> - Repository: [More Information Needed] - Paper [optional]: [More Information Needed] - Demo [optional]: [More Information Needed] ## Uses <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. --> ### Direct Use <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. --> [More Information Needed] ### Downstream Use [optional] <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app --> [More Information Needed] ### Out-of-Scope Use <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. --> [More Information Needed] ## Bias, Risks, and Limitations <!-- This section is meant to convey both technical and sociotechnical limitations. --> [More Information Needed] ### Recommendations <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. --> Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. [More Information Needed] ## Training Details ### Training Data <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. --> [More Information Needed] ### Training Procedure <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. --> #### Preprocessing [optional] [More Information Needed] #### Training Hyperparameters - Training regime: [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision --> #### Speeds, Sizes, Times [optional] <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. --> [More Information Needed] ## Evaluation <!-- This section describes the evaluation protocols and provides the results. --> ### Testing Data, Factors & Metrics #### Testing Data <!-- This should link to a Dataset Card if possible. --> [More Information Needed] #### Factors <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. --> [More Information Needed] #### Metrics <!-- These are the evaluation metrics being used, ideally with a description of why. --> [More Information Needed] ### Results [More Information Needed] #### Summary ## Model Examination [optional] <!-- Relevant interpretability work for the model goes here --> [More Information Needed] ## Environmental Impact <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly --> Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). - Hardware Type: [More Information Needed] - Hours used: [More Information Needed] - Cloud Provider: [More Information Needed] - Compute Region: [More Information Needed] - Carbon Emitted: [More Information Needed] ## Technical Specifications [optional] ### Model Architecture and Objective [More Information Needed] ### Compute Infrastructure [More Information Needed] #### Hardware [More Information Needed] #### Software [More Information Needed] ## Citation [optional] <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. --> BibTeX: [More Information Needed] APA: [More Information Needed] ## Glossary [optional] <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. --> [More Information Needed] ## More Information [optional] [More Information Needed] ## Model Card Authors [optional] [More Information Needed] ## Model Card Contact [More Information Needed]
gabrielloiseau/LUAR-CRUD-sentence-transformers	gabrielloiseau	2024-10-11T08:30:29Z	5	0	sentence-transformers	[ "sentence-transformers", "safetensors", "roberta", "sentence-similarity", "LUAR", "en", "base_model:rrivera1849/LUAR-CRUD", "base_model:finetune:rrivera1849/LUAR-CRUD", "license:apache-2.0", "autotrain_compatible", "text-embeddings-inference", "endpoints_compatible", "region:us" ]	sentence-similarity	2024-10-11T08:28:10Z	--- base_model: - rrivera1849/LUAR-CRUD library_name: sentence-transformers pipeline_tag: sentence-similarity tags: - sentence-transformers - sentence-similarity - LUAR license: apache-2.0 language: - en --- # SentenceTransformer version of rrivera1849/LUAR-MUD All credits go to [(Rivera-Soto et al. 2021)](https://aclanthology.org/2021.emnlp-main.70/) --- Author Style Representations using [LUAR](https://aclanthology.org/2021.emnlp-main.70.pdf). The LUAR training and evaluation repository can be found [here](https://github.com/llnl/luar). This model was trained on a subsample of the Pushshift Reddit Dataset (5 million users) for comments published between January 2015 and October 2019 by authors publishing at least 100 comments during that period. ## Usage ### Direct Usage (Sentence Transformers) First install the Sentence Transformers library: ```bash pip install -U sentence-transformers ``` Then you can load this model and run inference. ```python from sentence_transformers import SentenceTransformer model = SentenceTransformer("gabrielloiseau/LUAR-CRUD-sentence-transformers") # Run inference sentences = [ 'The weather is lovely today.', "It's so sunny outside!", 'He drove to the stadium.', ] embeddings = model.encode(sentences) print(embeddings.shape) # [3, 512] ``` ## Citation If you find this model helpful, feel free to cite: ``` @inproceedings{uar-emnlp2021, author = {Rafael A. Rivera Soto and Olivia Miano and Juanita Ordonez and Barry Chen and Aleem Khan and Marcus Bishop and Nicholas Andrews}, title = {Learning Universal Authorship Representations}, booktitle = {EMNLP}, year = {2021}, } ``` ## License LUAR is distributed under the terms of the Apache License (Version 2.0). All new contributions must be made under the Apache-2.0 licenses.
livehao/bert_classification_model	livehao	2024-10-11T08:17:48Z	106	0	transformers	[ "transformers", "tensorboard", "safetensors", "distilbert", "text-classification", "generated_from_trainer", "autotrain_compatible", "endpoints_compatible", "region:us" ]	text-classification	2024-10-11T06:37:01Z	--- library_name: transformers tags: - generated_from_trainer metrics: - accuracy model-index: - name: bert_classification_model results: [] --- <!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # bert_classification_model This model was trained from scratch on an unknown dataset. It achieves the following results on the evaluation set: - Loss: 0.0028 - Accuracy: 0.9996 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 3e-05 - train_batch_size: 16 - eval_batch_size: 16 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - num_epochs: 2 ### Training results \| Training Loss \| Epoch \| Step \| Validation Loss \| Accuracy \| \|:-------------:\|:-----:\|:----:\|:---------------:\|:--------:\| \| 0.2591 \| 1.0 \| 585 \| 0.0041 \| 0.9996 \| \| 0.0069 \| 2.0 \| 1170 \| 0.0028 \| 0.9996 \| ### Framework versions - Transformers 4.45.2 - Pytorch 2.4.1 - Datasets 2.19.1 - Tokenizers 0.20.1
mav23/CalmeRys-78B-Orpo-v0.1-GGUF	mav23	2024-10-11T08:17:24Z	27	0	transformers	[ "transformers", "gguf", "orpo", "qwen2", "sft", "chatml", "text-generation", "en", "dataset:mlabonne/orpo-dpo-mix-40k", "base_model:MaziyarPanahi/calme-2.4-rys-78b", "base_model:quantized:MaziyarPanahi/calme-2.4-rys-78b", "license:mit", "model-index", "region:us", "conversational" ]	text-generation	2024-10-11T03:46:31Z	--- language: - en license: mit library_name: transformers tags: - orpo - qwen2 - sft - chatml base_model: - MaziyarPanahi/calme-2.4-rys-78b datasets: - mlabonne/orpo-dpo-mix-40k pipeline_tag: text-generation inference: false model_creator: dfurman quantized_by: dfurman model-index: - name: CalmeRys-78B-Orpo-v0.1 results: - task: type: text-generation name: Text Generation dataset: name: IFEval (0-Shot) type: HuggingFaceH4/ifeval args: num_few_shot: 0 metrics: - type: inst_level_strict_acc and prompt_level_strict_acc value: 81.63 name: strict accuracy source: url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=dfurman/CalmeRys-78B-Orpo-v0.1 name: Open LLM Leaderboard - task: type: text-generation name: Text Generation dataset: name: BBH (3-Shot) type: BBH args: num_few_shot: 3 metrics: - type: acc_norm value: 61.92 name: normalized accuracy source: url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=dfurman/CalmeRys-78B-Orpo-v0.1 name: Open LLM Leaderboard - task: type: text-generation name: Text Generation dataset: name: MATH Lvl 5 (4-Shot) type: hendrycks/competition_math args: num_few_shot: 4 metrics: - type: exact_match value: 37.92 name: exact match source: url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=dfurman/CalmeRys-78B-Orpo-v0.1 name: Open LLM Leaderboard - task: type: text-generation name: Text Generation dataset: name: GPQA (0-shot) type: Idavidrein/gpqa args: num_few_shot: 0 metrics: - type: acc_norm value: 20.02 name: acc_norm source: url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=dfurman/CalmeRys-78B-Orpo-v0.1 name: Open LLM Leaderboard - task: type: text-generation name: Text Generation dataset: name: MuSR (0-shot) type: TAUR-Lab/MuSR args: num_few_shot: 0 metrics: - type: acc_norm value: 36.37 name: acc_norm source: url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=dfurman/CalmeRys-78B-Orpo-v0.1 name: Open LLM Leaderboard - task: type: text-generation name: Text Generation dataset: name: MMLU-PRO (5-shot) type: TIGER-Lab/MMLU-Pro config: main split: test args: num_few_shot: 5 metrics: - type: acc value: 66.8 name: accuracy source: url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=dfurman/CalmeRys-78B-Orpo-v0.1 name: Open LLM Leaderboard --- # dfurman/CalmeRys-78B-Orpo-v0.1 This model is a finetune of `MaziyarPanahi/calme-2.4-rys-78b` on 1.5k rows of the `mlabonne/orpo-dpo-mix-40k` dataset. It was trained as a generalist language model for a variety of text generation use cases, including support of agentic capabilities, roleplaying, reasoning, multi-turn conversations, long context coherence, and more. Thanks go out to [mlabonne](https://huggingface.co/mlabonne), [MaziyarPanahi](https://huggingface.com/MaziyarPanahi), et al. for the source dataset and base model. ## 🦾 Training You can find the experiment on W&B at this [link](https://wandb.ai/dryanfurman/huggingface/runs/1w50nu70?nw=nwuserdryanfurman). Here are a few visualizations: ![image/png](https://cdn-uploads.huggingface.co/production/uploads/62afc20ca5bd7cef3e1ab3f4/NG5WGL0ljzLsNhSBRVqnD.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/62afc20ca5bd7cef3e1ab3f4/Zhk5Bpr1I2NrzX98Bhtp8.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/62afc20ca5bd7cef3e1ab3f4/WgnKQnYIFWkCRSW3JPVAb.png) ## 💻 Usage <details> <summary>Setup</summary> ```python !pip install -qU transformers accelerate bitsandbytes !huggingface-cli download dfurman/CalmeRys-78B-Orpo-v0.1 ``` ```python from transformers import AutoTokenizer, BitsAndBytesConfig import transformers import torch if torch.cuda.get_device_capability()[0] >= 8: !pip install -qqq flash-attn attn_implementation = "flash_attention_2" torch_dtype = torch.bfloat16 else: attn_implementation = "eager" torch_dtype = torch.float16 # # quantize if necessary # bnb_config = BitsAndBytesConfig( # load_in_4bit=True, # bnb_4bit_quant_type="nf4", # bnb_4bit_compute_dtype=torch_dtype, # bnb_4bit_use_double_quant=True, # ) model = "dfurman/CalmeRys-78B-Orpo-v0.1" tokenizer = AutoTokenizer.from_pretrained(model) pipeline = transformers.pipeline( "text-generation", model=model, model_kwargs={ "torch_dtype": torch_dtype, # "quantization_config": bnb_config, "device_map": "auto", "attn_implementation": attn_implementation, } ) ``` </details> ### Example 1 ```python question = "Is the number 9.11 larger than 9.9?" messages = [ {"role": "system", "content": "You are a helpful assistant that thinks step by step."}, {"role": "user", "content": question}, ] prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True) # print("*Prompt:\n", prompt) outputs = pipeline( prompt, max_new_tokens=1000, do_sample=True, temperature=0.7, top_k=50, top_p=0.95 ) print("Generation:") print(outputs[0]["generated_text"][len(prompt) :]) ``` ``` Generation: To compare these two numbers, it's important to look at their decimal places after the whole number part, which is 9 in both cases. Comparing the tenths place, 9.11 has a '1' and 9.9 has a '9'. Since '9' is greater than '1', 9.9 is larger than 9.11. ``` ### Example 2 ```python question = """The bakers at the Beverly Hills Bakery baked 200 loaves of bread on Monday morning. They sold 93 loaves in the morning and 39 loaves in the afternoon. A grocery store then returned 6 unsold loaves back to the bakery. How many loaves of bread did the bakery have left? Respond as succinctly as possible. Format the response as a completion of this table: \|step\|subquestion\|procedure\|result\| \|:---\|:----------\|:--------\|:-----:\|""" messages = [ {"role": "system", "content": "You are a helpful assistant."}, {"role": "user", "content": question}, ] prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True) # print("Prompt:\n", prompt) outputs = pipeline(prompt, max_new_tokens=1000, do_sample=True, temperature=0.7, top_k=50, top_p=0.95) print("Generation:") print(outputs[0]["generated_text"][len(prompt):]) ``` ``` Generation: \|1\|Calculate total sold\|Add morning and afternoon sales\|132\| \|2\|Subtract sold from total\|200 - 132\|68\| \|3\|Adjust for returns\|Add returned loaves to remaining\|74\| ``` ### Example 3 ```python question = "What's a good recipe for a spicy margarita?" messages = [ {"role": "system", "content": "You are a helpful assistant."}, {"role": "user", "content": question}, ] prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True) # print("Prompt:\n", prompt) outputs = pipeline(prompt, max_new_tokens=1000, do_sample=True, temperature=0.7, top_k=50, top_p=0.95) print("Generation:") print(outputs[0]["generated_text"][len(prompt):]) ``` ``` Generation: To make a Spicy Margarita, you'll need to incorporate a chili or pepper element into your classic margarita recipe. Here’s a simple way to do it: ### Ingredients: - 2 oz tequila (blanco or reposado) - 1 oz fresh lime juice - 1/2 oz triple sec (Cointreau or Grand Marnier) - 1/2 oz agave syrup or simple syrup - 1-2 slices of jalapeño (or more depending on how spicy you like it) - Salt and/or chili powder for rimming the glass - Ice - Lime wheel for garnish ### Instructions: 1. Muddle Jalapeño: In a shaker, muddle the jalapeño slices slightly. This will release the oils and heat from the peppers. 2. Add Remaining Ingredients: Add the tequila, lime juice, triple sec, and agave syrup or simple syrup. 3. Shake and Strain: Fill the shaker with ice and shake vigorously until cold. Strain into a salt and/or chili powder rimmed glass filled with ice. 4. Garnish and Serve**: Garnish with a lime wheel and enjoy. If you prefer a smoother spiciness that doesn't overpower the drink, you could also consider making a jalapeño-infused tequila by leaving the jalapeño slices in the bottle of tequila for several hours to a couple of days, adjusting the time based on desired level of spiciness. Then use this infused tequila instead of regular tequila in the recipe above. Another variation is to use a spicy syrup. To make this, combine equal parts water and sugar with a few sliced jalapeños in a saucepan. Bring to a boil, stirring occasionally to dissolve the sugar. Reduce heat and simmer for about 5 minutes. Let cool, strain out the jalapeños, then store in a sealed container in the refrigerator until ready to use. Use this spicy syrup instead of regular syrup in the recipe. As always, adjust the quantity of jalapeño or the type of chili used to suit your taste. Enjoy responsibly! ``` # [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard) Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_dfurman__CalmeRys-78B-Orpo-v0.1) \| Metric \|Value\| \|-------------------\|----:\| \|Avg. \|50.78\| \|IFEval (0-Shot) \|81.63\| \|BBH (3-Shot) \|61.92\| \|MATH Lvl 5 (4-Shot)\|37.92\| \|GPQA (0-shot) \|20.02\| \|MuSR (0-shot) \|36.37\| \|MMLU-PRO (5-shot) \|66.80\|
mradermacher/CursorCore-QW2.5-7B-GGUF	mradermacher	2024-10-11T08:14:10Z	141	1	transformers	[ "transformers", "gguf", "code", "en", "base_model:TechxGenus/CursorCore-QW2.5-7B", "base_model:quantized:TechxGenus/CursorCore-QW2.5-7B", "license:apache-2.0", "endpoints_compatible", "region:us", "conversational" ]	null	2024-10-11T06:17:25Z	--- base_model: TechxGenus/CursorCore-QW2.5-7B language: - en library_name: transformers license: apache-2.0 quantized_by: mradermacher tags: - code --- ## About <!-- ### quantize_version: 2 --> <!-- ### output_tensor_quantised: 1 --> <!-- ### convert_type: hf --> <!-- ### vocab_type: --> <!-- ### tags: --> static quants of https://huggingface.co/TechxGenus/CursorCore-QW2.5-7B <!-- provided-files --> weighted/imatrix quants are available at https://huggingface.co/mradermacher/CursorCore-QW2.5-7B-i1-GGUF ## Usage If you are unsure how to use GGUF files, refer to one of [TheBloke's READMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for more details, including on how to concatenate multi-part files. ## Provided Quants (sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants) \| Link \| Type \| Size/GB \| Notes \| \|:-----\|:-----\|--------:\|:------\| \| [GGUF](https://huggingface.co/mradermacher/CursorCore-QW2.5-7B-GGUF/resolve/main/CursorCore-QW2.5-7B.Q2_K.gguf) \| Q2_K \| 3.1 \| \| \| [GGUF](https://huggingface.co/mradermacher/CursorCore-QW2.5-7B-GGUF/resolve/main/CursorCore-QW2.5-7B.Q3_K_S.gguf) \| Q3_K_S \| 3.6 \| \| \| [GGUF](https://huggingface.co/mradermacher/CursorCore-QW2.5-7B-GGUF/resolve/main/CursorCore-QW2.5-7B.Q3_K_M.gguf) \| Q3_K_M \| 3.9 \| lower quality \| \| [GGUF](https://huggingface.co/mradermacher/CursorCore-QW2.5-7B-GGUF/resolve/main/CursorCore-QW2.5-7B.Q3_K_L.gguf) \| Q3_K_L \| 4.2 \| \| \| [GGUF](https://huggingface.co/mradermacher/CursorCore-QW2.5-7B-GGUF/resolve/main/CursorCore-QW2.5-7B.IQ4_XS.gguf) \| IQ4_XS \| 4.3 \| \| \| [GGUF](https://huggingface.co/mradermacher/CursorCore-QW2.5-7B-GGUF/resolve/main/CursorCore-QW2.5-7B.Q4_K_S.gguf) \| Q4_K_S \| 4.6 \| fast, recommended \| \| [GGUF](https://huggingface.co/mradermacher/CursorCore-QW2.5-7B-GGUF/resolve/main/CursorCore-QW2.5-7B.Q4_K_M.gguf) \| Q4_K_M \| 4.8 \| fast, recommended \| \| [GGUF](https://huggingface.co/mradermacher/CursorCore-QW2.5-7B-GGUF/resolve/main/CursorCore-QW2.5-7B.Q5_K_S.gguf) \| Q5_K_S \| 5.4 \| \| \| [GGUF](https://huggingface.co/mradermacher/CursorCore-QW2.5-7B-GGUF/resolve/main/CursorCore-QW2.5-7B.Q5_K_M.gguf) \| Q5_K_M \| 5.5 \| \| \| [GGUF](https://huggingface.co/mradermacher/CursorCore-QW2.5-7B-GGUF/resolve/main/CursorCore-QW2.5-7B.Q6_K.gguf) \| Q6_K \| 6.4 \| very good quality \| \| [GGUF](https://huggingface.co/mradermacher/CursorCore-QW2.5-7B-GGUF/resolve/main/CursorCore-QW2.5-7B.Q8_0.gguf) \| Q8_0 \| 8.2 \| fast, best quality \| \| [GGUF](https://huggingface.co/mradermacher/CursorCore-QW2.5-7B-GGUF/resolve/main/CursorCore-QW2.5-7B.f16.gguf) \| f16 \| 15.3 \| 16 bpw, overkill \| Here is a handy graph by ikawrakow comparing some lower-quality quant types (lower is better): ![image.png](https://www.nethype.de/huggingface_embed/quantpplgraph.png) And here are Artefact2's thoughts on the matter: https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9 ## FAQ / Model Request See https://huggingface.co/mradermacher/model_requests for some answers to questions you might have and/or if you want some other model quantized. ## Thanks I thank my company, [nethype GmbH](https://www.nethype.de/), for letting me use its servers and providing upgrades to my workstation to enable this work in my free time. <!-- end -->
dumyy/internlm2_5-7b-chat-Q4_K_M-GGUF	dumyy	2024-10-11T08:13:52Z	5	0	null	[ "gguf", "llama-cpp", "gguf-my-repo", "text-generation", "base_model:internlm/internlm2_5-7b-chat", "base_model:quantized:internlm/internlm2_5-7b-chat", "license:other", "endpoints_compatible", "region:us", "conversational" ]	text-generation	2024-10-11T08:13:32Z	--- base_model: internlm/internlm2_5-7b-chat license: other pipeline_tag: text-generation tags: - llama-cpp - gguf-my-repo --- # dumyy/internlm2_5-7b-chat-Q4_K_M-GGUF This model was converted to GGUF format from [`internlm/internlm2_5-7b-chat`](https://huggingface.co/internlm/internlm2_5-7b-chat) using llama.cpp via the ggml.ai's [GGUF-my-repo](https://huggingface.co/spaces/ggml-org/gguf-my-repo) space. Refer to the [original model card](https://huggingface.co/internlm/internlm2_5-7b-chat) for more details on the model. ## Use with llama.cpp Install llama.cpp through brew (works on Mac and Linux) ```bash brew install llama.cpp ``` Invoke the llama.cpp server or the CLI. ### CLI: ```bash llama-cli --hf-repo dumyy/internlm2_5-7b-chat-Q4_K_M-GGUF --hf-file internlm2_5-7b-chat-q4_k_m.gguf -p "The meaning to life and the universe is" ``` ### Server: ```bash llama-server --hf-repo dumyy/internlm2_5-7b-chat-Q4_K_M-GGUF --hf-file internlm2_5-7b-chat-q4_k_m.gguf -c 2048 ``` Note: You can also use this checkpoint directly through the [usage steps](https://github.com/ggerganov/llama.cpp?tab=readme-ov-file#usage) listed in the Llama.cpp repo as well. Step 1: Clone llama.cpp from GitHub. ``` git clone https://github.com/ggerganov/llama.cpp ``` Step 2: Move into the llama.cpp folder and build it with `LLAMA_CURL=1` flag along with other hardware-specific flags (for ex: LLAMA_CUDA=1 for Nvidia GPUs on Linux). ``` cd llama.cpp && LLAMA_CURL=1 make ``` Step 3: Run inference through the main binary. ``` ./llama-cli --hf-repo dumyy/internlm2_5-7b-chat-Q4_K_M-GGUF --hf-file internlm2_5-7b-chat-q4_k_m.gguf -p "The meaning to life and the universe is" ``` or ``` ./llama-server --hf-repo dumyy/internlm2_5-7b-chat-Q4_K_M-GGUF --hf-file internlm2_5-7b-chat-q4_k_m.gguf -c 2048 ```
mradermacher/CursorCore-QW2.5-1.5B-LC-GGUF	mradermacher	2024-10-11T08:13:11Z	30	0	transformers	[ "transformers", "gguf", "code", "en", "base_model:TechxGenus/CursorCore-QW2.5-1.5B-LC", "base_model:quantized:TechxGenus/CursorCore-QW2.5-1.5B-LC", "license:apache-2.0", "endpoints_compatible", "region:us", "conversational" ]	null	2024-10-11T06:17:32Z	--- base_model: TechxGenus/CursorCore-QW2.5-1.5B-LC language: - en library_name: transformers license: apache-2.0 quantized_by: mradermacher tags: - code --- ## About <!-- ### quantize_version: 2 --> <!-- ### output_tensor_quantised: 1 --> <!-- ### convert_type: hf --> <!-- ### vocab_type: --> <!-- ### tags: --> static quants of https://huggingface.co/TechxGenus/CursorCore-QW2.5-1.5B-LC <!-- provided-files --> weighted/imatrix quants are available at https://huggingface.co/mradermacher/CursorCore-QW2.5-1.5B-LC-i1-GGUF ## Usage If you are unsure how to use GGUF files, refer to one of [TheBloke's READMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for more details, including on how to concatenate multi-part files. ## Provided Quants (sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants) \| Link \| Type \| Size/GB \| Notes \| \|:-----\|:-----\|--------:\|:------\| \| [GGUF](https://huggingface.co/mradermacher/CursorCore-QW2.5-1.5B-LC-GGUF/resolve/main/CursorCore-QW2.5-1.5B-LC.Q2_K.gguf) \| Q2_K \| 0.8 \| \| \| [GGUF](https://huggingface.co/mradermacher/CursorCore-QW2.5-1.5B-LC-GGUF/resolve/main/CursorCore-QW2.5-1.5B-LC.Q3_K_S.gguf) \| Q3_K_S \| 0.9 \| \| \| [GGUF](https://huggingface.co/mradermacher/CursorCore-QW2.5-1.5B-LC-GGUF/resolve/main/CursorCore-QW2.5-1.5B-LC.Q3_K_M.gguf) \| Q3_K_M \| 0.9 \| lower quality \| \| [GGUF](https://huggingface.co/mradermacher/CursorCore-QW2.5-1.5B-LC-GGUF/resolve/main/CursorCore-QW2.5-1.5B-LC.Q3_K_L.gguf) \| Q3_K_L \| 1.0 \| \| \| [GGUF](https://huggingface.co/mradermacher/CursorCore-QW2.5-1.5B-LC-GGUF/resolve/main/CursorCore-QW2.5-1.5B-LC.IQ4_XS.gguf) \| IQ4_XS \| 1.0 \| \| \| [GGUF](https://huggingface.co/mradermacher/CursorCore-QW2.5-1.5B-LC-GGUF/resolve/main/CursorCore-QW2.5-1.5B-LC.Q4_K_S.gguf) \| Q4_K_S \| 1.0 \| fast, recommended \| \| [GGUF](https://huggingface.co/mradermacher/CursorCore-QW2.5-1.5B-LC-GGUF/resolve/main/CursorCore-QW2.5-1.5B-LC.Q4_K_M.gguf) \| Q4_K_M \| 1.1 \| fast, recommended \| \| [GGUF](https://huggingface.co/mradermacher/CursorCore-QW2.5-1.5B-LC-GGUF/resolve/main/CursorCore-QW2.5-1.5B-LC.Q5_K_S.gguf) \| Q5_K_S \| 1.2 \| \| \| [GGUF](https://huggingface.co/mradermacher/CursorCore-QW2.5-1.5B-LC-GGUF/resolve/main/CursorCore-QW2.5-1.5B-LC.Q5_K_M.gguf) \| Q5_K_M \| 1.2 \| \| \| [GGUF](https://huggingface.co/mradermacher/CursorCore-QW2.5-1.5B-LC-GGUF/resolve/main/CursorCore-QW2.5-1.5B-LC.Q6_K.gguf) \| Q6_K \| 1.4 \| very good quality \| \| [GGUF](https://huggingface.co/mradermacher/CursorCore-QW2.5-1.5B-LC-GGUF/resolve/main/CursorCore-QW2.5-1.5B-LC.Q8_0.gguf) \| Q8_0 \| 1.7 \| fast, best quality \| \| [GGUF](https://huggingface.co/mradermacher/CursorCore-QW2.5-1.5B-LC-GGUF/resolve/main/CursorCore-QW2.5-1.5B-LC.f16.gguf) \| f16 \| 3.2 \| 16 bpw, overkill \| Here is a handy graph by ikawrakow comparing some lower-quality quant types (lower is better): ![image.png](https://www.nethype.de/huggingface_embed/quantpplgraph.png) And here are Artefact2's thoughts on the matter: https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9 ## FAQ / Model Request See https://huggingface.co/mradermacher/model_requests for some answers to questions you might have and/or if you want some other model quantized. ## Thanks I thank my company, [nethype GmbH](https://www.nethype.de/), for letting me use its servers and providing upgrades to my workstation to enable this work in my free time. <!-- end -->
mradermacher/CursorCore-QW2.5-1.5B-LC-i1-GGUF	mradermacher	2024-10-11T08:13:07Z	172	0	transformers	[ "transformers", "gguf", "code", "en", "base_model:TechxGenus/CursorCore-QW2.5-1.5B-LC", "base_model:quantized:TechxGenus/CursorCore-QW2.5-1.5B-LC", "license:apache-2.0", "endpoints_compatible", "region:us", "imatrix", "conversational" ]	null	2024-10-11T07:58:06Z	--- base_model: TechxGenus/CursorCore-QW2.5-1.5B-LC language: - en library_name: transformers license: apache-2.0 quantized_by: mradermacher tags: - code --- ## About <!-- ### quantize_version: 2 --> <!-- ### output_tensor_quantised: 1 --> <!-- ### convert_type: hf --> <!-- ### vocab_type: --> <!-- ### tags: nicoboss --> weighted/imatrix quants of https://huggingface.co/TechxGenus/CursorCore-QW2.5-1.5B-LC <!-- provided-files --> static quants are available at https://huggingface.co/mradermacher/CursorCore-QW2.5-1.5B-LC-GGUF ## Usage If you are unsure how to use GGUF files, refer to one of [TheBloke's READMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for more details, including on how to concatenate multi-part files. ## Provided Quants (sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants) \| Link \| Type \| Size/GB \| Notes \| \|:-----\|:-----\|--------:\|:------\| \| [GGUF](https://huggingface.co/mradermacher/CursorCore-QW2.5-1.5B-LC-i1-GGUF/resolve/main/CursorCore-QW2.5-1.5B-LC.i1-IQ1_S.gguf) \| i1-IQ1_S \| 0.5 \| for the desperate \| \| [GGUF](https://huggingface.co/mradermacher/CursorCore-QW2.5-1.5B-LC-i1-GGUF/resolve/main/CursorCore-QW2.5-1.5B-LC.i1-IQ1_M.gguf) \| i1-IQ1_M \| 0.6 \| mostly desperate \| \| [GGUF](https://huggingface.co/mradermacher/CursorCore-QW2.5-1.5B-LC-i1-GGUF/resolve/main/CursorCore-QW2.5-1.5B-LC.i1-IQ2_XXS.gguf) \| i1-IQ2_XXS \| 0.6 \| \| \| [GGUF](https://huggingface.co/mradermacher/CursorCore-QW2.5-1.5B-LC-i1-GGUF/resolve/main/CursorCore-QW2.5-1.5B-LC.i1-IQ2_XS.gguf) \| i1-IQ2_XS \| 0.7 \| \| \| [GGUF](https://huggingface.co/mradermacher/CursorCore-QW2.5-1.5B-LC-i1-GGUF/resolve/main/CursorCore-QW2.5-1.5B-LC.i1-IQ2_S.gguf) \| i1-IQ2_S \| 0.7 \| \| \| [GGUF](https://huggingface.co/mradermacher/CursorCore-QW2.5-1.5B-LC-i1-GGUF/resolve/main/CursorCore-QW2.5-1.5B-LC.i1-IQ2_M.gguf) \| i1-IQ2_M \| 0.7 \| \| \| [GGUF](https://huggingface.co/mradermacher/CursorCore-QW2.5-1.5B-LC-i1-GGUF/resolve/main/CursorCore-QW2.5-1.5B-LC.i1-IQ3_XXS.gguf) \| i1-IQ3_XXS \| 0.8 \| lower quality \| \| [GGUF](https://huggingface.co/mradermacher/CursorCore-QW2.5-1.5B-LC-i1-GGUF/resolve/main/CursorCore-QW2.5-1.5B-LC.i1-Q2_K.gguf) \| i1-Q2_K \| 0.8 \| IQ3_XXS probably better \| \| [GGUF](https://huggingface.co/mradermacher/CursorCore-QW2.5-1.5B-LC-i1-GGUF/resolve/main/CursorCore-QW2.5-1.5B-LC.i1-IQ3_XS.gguf) \| i1-IQ3_XS \| 0.8 \| \| \| [GGUF](https://huggingface.co/mradermacher/CursorCore-QW2.5-1.5B-LC-i1-GGUF/resolve/main/CursorCore-QW2.5-1.5B-LC.i1-Q3_K_S.gguf) \| i1-Q3_K_S \| 0.9 \| IQ3_XS probably better \| \| [GGUF](https://huggingface.co/mradermacher/CursorCore-QW2.5-1.5B-LC-i1-GGUF/resolve/main/CursorCore-QW2.5-1.5B-LC.i1-IQ3_S.gguf) \| i1-IQ3_S \| 0.9 \| beats Q3_K* \| \| [GGUF](https://huggingface.co/mradermacher/CursorCore-QW2.5-1.5B-LC-i1-GGUF/resolve/main/CursorCore-QW2.5-1.5B-LC.i1-IQ3_M.gguf) \| i1-IQ3_M \| 0.9 \| \| \| [GGUF](https://huggingface.co/mradermacher/CursorCore-QW2.5-1.5B-LC-i1-GGUF/resolve/main/CursorCore-QW2.5-1.5B-LC.i1-Q3_K_M.gguf) \| i1-Q3_K_M \| 0.9 \| IQ3_S probably better \| \| [GGUF](https://huggingface.co/mradermacher/CursorCore-QW2.5-1.5B-LC-i1-GGUF/resolve/main/CursorCore-QW2.5-1.5B-LC.i1-Q3_K_L.gguf) \| i1-Q3_K_L \| 1.0 \| IQ3_M probably better \| \| [GGUF](https://huggingface.co/mradermacher/CursorCore-QW2.5-1.5B-LC-i1-GGUF/resolve/main/CursorCore-QW2.5-1.5B-LC.i1-IQ4_XS.gguf) \| i1-IQ4_XS \| 1.0 \| \| \| [GGUF](https://huggingface.co/mradermacher/CursorCore-QW2.5-1.5B-LC-i1-GGUF/resolve/main/CursorCore-QW2.5-1.5B-LC.i1-Q4_0_4_4.gguf) \| i1-Q4_0_4_4 \| 1.0 \| fast on arm, low quality \| \| [GGUF](https://huggingface.co/mradermacher/CursorCore-QW2.5-1.5B-LC-i1-GGUF/resolve/main/CursorCore-QW2.5-1.5B-LC.i1-Q4_0_4_8.gguf) \| i1-Q4_0_4_8 \| 1.0 \| fast on arm+i8mm, low quality \| \| [GGUF](https://huggingface.co/mradermacher/CursorCore-QW2.5-1.5B-LC-i1-GGUF/resolve/main/CursorCore-QW2.5-1.5B-LC.i1-Q4_0_8_8.gguf) \| i1-Q4_0_8_8 \| 1.0 \| fast on arm+sve, low quality \| \| [GGUF](https://huggingface.co/mradermacher/CursorCore-QW2.5-1.5B-LC-i1-GGUF/resolve/main/CursorCore-QW2.5-1.5B-LC.i1-Q4_0.gguf) \| i1-Q4_0 \| 1.0 \| fast, low quality \| \| [GGUF](https://huggingface.co/mradermacher/CursorCore-QW2.5-1.5B-LC-i1-GGUF/resolve/main/CursorCore-QW2.5-1.5B-LC.i1-Q4_K_S.gguf) \| i1-Q4_K_S \| 1.0 \| optimal size/speed/quality \| \| [GGUF](https://huggingface.co/mradermacher/CursorCore-QW2.5-1.5B-LC-i1-GGUF/resolve/main/CursorCore-QW2.5-1.5B-LC.i1-Q4_K_M.gguf) \| i1-Q4_K_M \| 1.1 \| fast, recommended \| \| [GGUF](https://huggingface.co/mradermacher/CursorCore-QW2.5-1.5B-LC-i1-GGUF/resolve/main/CursorCore-QW2.5-1.5B-LC.i1-Q5_K_S.gguf) \| i1-Q5_K_S \| 1.2 \| \| \| [GGUF](https://huggingface.co/mradermacher/CursorCore-QW2.5-1.5B-LC-i1-GGUF/resolve/main/CursorCore-QW2.5-1.5B-LC.i1-Q5_K_M.gguf) \| i1-Q5_K_M \| 1.2 \| \| \| [GGUF](https://huggingface.co/mradermacher/CursorCore-QW2.5-1.5B-LC-i1-GGUF/resolve/main/CursorCore-QW2.5-1.5B-LC.i1-Q6_K.gguf) \| i1-Q6_K \| 1.4 \| practically like static Q6_K \| Here is a handy graph by ikawrakow comparing some lower-quality quant types (lower is better): ![image.png](https://www.nethype.de/huggingface_embed/quantpplgraph.png) And here are Artefact2's thoughts on the matter: https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9 ## FAQ / Model Request See https://huggingface.co/mradermacher/model_requests for some answers to questions you might have and/or if you want some other model quantized. ## Thanks I thank my company, [nethype GmbH](https://www.nethype.de/), for letting me use its servers and providing upgrades to my workstation to enable this work in my free time. Additional thanks to [@nicoboss](https://huggingface.co/nicoboss) for giving me access to his private supercomputer, enabling me to provide many more imatrix quants, at much higher quality, than I would otherwise be able to. <!-- end -->
LxzGordon/URM-LLaMa-3-8B	LxzGordon	2024-10-11T08:11:25Z	187	0	null	[ "safetensors", "llama", "text-classification", "custom_code", "dataset:nvidia/HelpSteer2", "arxiv:2410.00847", "region:us" ]	text-classification	2024-09-12T08:49:43Z	--- datasets: - nvidia/HelpSteer2 pipeline_tag: text-classification --- - Paper: [https://arxiv.org/pdf/2410.00847](https://arxiv.org/pdf/2410.00847) - Model: [URM-LLaMa-3-8B](https://huggingface.co/LxzGordon/URM-LLaMa-3-8B) - Fine-tuned from [FsfairX-LLaMA3-RM-v0.1](https://huggingface.co/sfairXC/FsfairX-LLaMA3-RM-v0.1) # Brief [URM-LLaMa-3-8B](https://huggingface.co/LxzGordon/URM-LLaMa-3-8B) is an uncertain-aware reward model. This RM consists of a base model and an uncertainty-aware and attribute-specific value head. The base model of this RM is from [FsfairX-LLaMA3-RM-v0.1](https://huggingface.co/sfairXC/FsfairX-LLaMA3-RM-v0.1). ## Attribute Regression Dataset: [HelpSteer2](https://huggingface.co/datasets/nvidia/HelpSteer2) During training, instead of multi-attributes scores, outputs of the uncertainty-aware value head are parameters of a normal distribution, from which scores are sampled. Then we run regression on the outputs with the labels to train the value head. To enable gradient back-propagation, reparameterization technique is used. We use the five attributes from HelpSteer2: Helpfulness, Correctness, Coherence, Complexity and Verbosity. We use weighted sum to combine these attributes with prior weights ```[0.3, 0.74, 0.46, 0.47,-0.33]``` recommended by [Nemotron-4](https://huggingface.co/nvidia/Nemotron-4-340B-Reward). # Usage ```python import torch from transformers import AutoModelForSequenceClassification, AutoTokenizer model_name = "LxzGordon/URM-LLaMa-3-8B" model = AutoModelForSequenceClassification.from_pretrained( model_name, device_map='auto', trust_remote_code=True, ) tokenizer = AutoTokenizer.from_pretrained(model_name) prompt = "when were the first Olympic Games held?" response1 = "April 1896" response2 = "April 1892" resp1 = [{"role": "user", "content": prompt}, {"role": "assistant", "content": response1}] resp2 = [{"role": "user", "content": prompt}, {"role": "assistant", "content": response2}] # Format and tokenize the conversations resp1 = tokenizer.apply_chat_template(resp1, tokenize=False) resp2 = tokenizer.apply_chat_template(resp2, tokenize=False) resp1 = tokenizer(resp1, return_tensors="pt").to(model.device) resp2 = tokenizer(resp2, return_tensors="pt").to(model.device) with torch.no_grad(): score1 = model(resp1['input_ids'],attention_mask=resp1['attention_mask']).logits[0][0].item() score2 = model(resp2['input_ids'],attention_mask=resp2['attention_mask']).logits[0][0].item() print(score1,score2) # Response 1 score: 3.669522523880005, Response 2 score: 2.5036821365356445 ``` # Reference Please cite ``` @article{lou2024uncertainty, title={Uncertainty-aware Reward Model: Teaching Reward Models to Know What is Unknown}, author={Lou, Xingzhou and Yan, Dong and Shen, Wei and Yan, Yuzi and Xie, Jian and Zhang, Junge}, journal={arXiv preprint arXiv:2410.00847}, year={2024} } ```
RichardErkhov/meta-llama_-_Llama-Guard-3-1B-gguf	RichardErkhov	2024-10-11T07:53:19Z	201	0	null	[ "gguf", "arxiv:2404.12241", "arxiv:2312.06674", "arxiv:2204.05862", "arxiv:2308.01263", "arxiv:2403.03853", "endpoints_compatible", "region:us", "conversational" ]	null	2024-10-11T07:35:47Z	Quantization made by Richard Erkhov. [Github](https://github.com/RichardErkhov) [Discord](https://discord.gg/pvy7H8DZMG) [Request more models](https://github.com/RichardErkhov/quant_request) Llama-Guard-3-1B - GGUF - Model creator: https://huggingface.co/meta-llama/ - Original model: https://huggingface.co/meta-llama/Llama-Guard-3-1B/ \| Name \| Quant method \| Size \| \| ---- \| ---- \| ---- \| \| [Llama-Guard-3-1B.Q2_K.gguf](https://huggingface.co/RichardErkhov/meta-llama_-_Llama-Guard-3-1B-gguf/blob/main/Llama-Guard-3-1B.Q2_K.gguf) \| Q2_K \| 0.62GB \| \| [Llama-Guard-3-1B.IQ3_XS.gguf](https://huggingface.co/RichardErkhov/meta-llama_-_Llama-Guard-3-1B-gguf/blob/main/Llama-Guard-3-1B.IQ3_XS.gguf) \| IQ3_XS \| 0.68GB \| \| [Llama-Guard-3-1B.IQ3_S.gguf](https://huggingface.co/RichardErkhov/meta-llama_-_Llama-Guard-3-1B-gguf/blob/main/Llama-Guard-3-1B.IQ3_S.gguf) \| IQ3_S \| 0.7GB \| \| [Llama-Guard-3-1B.Q3_K_S.gguf](https://huggingface.co/RichardErkhov/meta-llama_-_Llama-Guard-3-1B-gguf/blob/main/Llama-Guard-3-1B.Q3_K_S.gguf) \| Q3_K_S \| 0.7GB \| \| [Llama-Guard-3-1B.IQ3_M.gguf](https://huggingface.co/RichardErkhov/meta-llama_-_Llama-Guard-3-1B-gguf/blob/main/Llama-Guard-3-1B.IQ3_M.gguf) \| IQ3_M \| 0.72GB \| \| [Llama-Guard-3-1B.Q3_K.gguf](https://huggingface.co/RichardErkhov/meta-llama_-_Llama-Guard-3-1B-gguf/blob/main/Llama-Guard-3-1B.Q3_K.gguf) \| Q3_K \| 0.75GB \| \| [Llama-Guard-3-1B.Q3_K_M.gguf](https://huggingface.co/RichardErkhov/meta-llama_-_Llama-Guard-3-1B-gguf/blob/main/Llama-Guard-3-1B.Q3_K_M.gguf) \| Q3_K_M \| 0.75GB \| \| [Llama-Guard-3-1B.Q3_K_L.gguf](https://huggingface.co/RichardErkhov/meta-llama_-_Llama-Guard-3-1B-gguf/blob/main/Llama-Guard-3-1B.Q3_K_L.gguf) \| Q3_K_L \| 0.79GB \| \| [Llama-Guard-3-1B.IQ4_XS.gguf](https://huggingface.co/RichardErkhov/meta-llama_-_Llama-Guard-3-1B-gguf/blob/main/Llama-Guard-3-1B.IQ4_XS.gguf) \| IQ4_XS \| 0.83GB \| \| [Llama-Guard-3-1B.Q4_0.gguf](https://huggingface.co/RichardErkhov/meta-llama_-_Llama-Guard-3-1B-gguf/blob/main/Llama-Guard-3-1B.Q4_0.gguf) \| Q4_0 \| 0.86GB \| \| [Llama-Guard-3-1B.IQ4_NL.gguf](https://huggingface.co/RichardErkhov/meta-llama_-_Llama-Guard-3-1B-gguf/blob/main/Llama-Guard-3-1B.IQ4_NL.gguf) \| IQ4_NL \| 0.86GB \| \| [Llama-Guard-3-1B.Q4_K_S.gguf](https://huggingface.co/RichardErkhov/meta-llama_-_Llama-Guard-3-1B-gguf/blob/main/Llama-Guard-3-1B.Q4_K_S.gguf) \| Q4_K_S \| 0.86GB \| \| [Llama-Guard-3-1B.Q4_K.gguf](https://huggingface.co/RichardErkhov/meta-llama_-_Llama-Guard-3-1B-gguf/blob/main/Llama-Guard-3-1B.Q4_K.gguf) \| Q4_K \| 0.89GB \| \| [Llama-Guard-3-1B.Q4_K_M.gguf](https://huggingface.co/RichardErkhov/meta-llama_-_Llama-Guard-3-1B-gguf/blob/main/Llama-Guard-3-1B.Q4_K_M.gguf) \| Q4_K_M \| 0.89GB \| \| [Llama-Guard-3-1B.Q4_1.gguf](https://huggingface.co/RichardErkhov/meta-llama_-_Llama-Guard-3-1B-gguf/blob/main/Llama-Guard-3-1B.Q4_1.gguf) \| Q4_1 \| 0.93GB \| \| [Llama-Guard-3-1B.Q5_0.gguf](https://huggingface.co/RichardErkhov/meta-llama_-_Llama-Guard-3-1B-gguf/blob/main/Llama-Guard-3-1B.Q5_0.gguf) \| Q5_0 \| 1.0GB \| \| [Llama-Guard-3-1B.Q5_K_S.gguf](https://huggingface.co/RichardErkhov/meta-llama_-_Llama-Guard-3-1B-gguf/blob/main/Llama-Guard-3-1B.Q5_K_S.gguf) \| Q5_K_S \| 1.0GB \| \| [Llama-Guard-3-1B.Q5_K.gguf](https://huggingface.co/RichardErkhov/meta-llama_-_Llama-Guard-3-1B-gguf/blob/main/Llama-Guard-3-1B.Q5_K.gguf) \| Q5_K \| 1.02GB \| \| [Llama-Guard-3-1B.Q5_K_M.gguf](https://huggingface.co/RichardErkhov/meta-llama_-_Llama-Guard-3-1B-gguf/blob/main/Llama-Guard-3-1B.Q5_K_M.gguf) \| Q5_K_M \| 1.02GB \| \| [Llama-Guard-3-1B.Q5_1.gguf](https://huggingface.co/RichardErkhov/meta-llama_-_Llama-Guard-3-1B-gguf/blob/main/Llama-Guard-3-1B.Q5_1.gguf) \| Q5_1 \| 1.07GB \| \| [Llama-Guard-3-1B.Q6_K.gguf](https://huggingface.co/RichardErkhov/meta-llama_-_Llama-Guard-3-1B-gguf/blob/main/Llama-Guard-3-1B.Q6_K.gguf) \| Q6_K \| 1.15GB \| \| [Llama-Guard-3-1B.Q8_0.gguf](https://huggingface.co/RichardErkhov/meta-llama_-_Llama-Guard-3-1B-gguf/blob/main/Llama-Guard-3-1B.Q8_0.gguf) \| Q8_0 \| 1.49GB \| Original model description: --- language: - en - de - fr - it - pt - hi - es - th library_name: transformers pipeline_tag: text-generation tags: - facebook - meta - pytorch - llama - llama-3 license: llama3.2 extra_gated_prompt: >- ### LLAMA 3.2 COMMUNITY LICENSE AGREEMENT Llama 3.2 Version Release Date: September 25, 2024 “Agreement” means the terms and conditions for use, reproduction, distribution and modification of the Llama Materials set forth herein. “Documentation” means the specifications, manuals and documentation accompanying Llama 3.2 distributed by Meta at https://llama.meta.com/doc/overview. “Licensee” or “you” means you, or your employer or any other person or entity (if you are entering into this Agreement on such person or entity’s behalf), of the age required under applicable laws, rules or regulations to provide legal consent and that has legal authority to bind your employer or such other person or entity if you are entering in this Agreement on their behalf. “Llama 3.2” means the foundational large language models and software and algorithms, including machine-learning model code, trained model weights, inference-enabling code, training-enabling code, fine-tuning enabling code and other elements of the foregoing distributed by Meta at https://www.llama.com/llama-downloads. “Llama Materials” means, collectively, Meta’s proprietary Llama 3.2 and Documentation (and any portion thereof) made available under this Agreement. “Meta” or “we” means Meta Platforms Ireland Limited (if you are located in or, if you are an entity, your principal place of business is in the EEA or Switzerland) and Meta Platforms, Inc. (if you are located outside of the EEA or Switzerland). By clicking “I Accept” below or by using or distributing any portion or element of the Llama Materials, you agree to be bound by this Agreement. 1. License Rights and Redistribution. a. Grant of Rights. You are granted a non-exclusive, worldwide, non-transferable and royalty-free limited license under Meta’s intellectual property or other rights owned by Meta embodied in the Llama Materials to use, reproduce, distribute, copy, create derivative works of, and make modifications to the Llama Materials. b. Redistribution and Use. i. If you distribute or make available the Llama Materials (or any derivative works thereof), or a product or service (including another AI model) that contains any of them, you shall (A) provide a copy of this Agreement with any such Llama Materials; and (B) prominently display “Built with Llama” on a related website, user interface, blogpost, about page, or product documentation. If you use the Llama Materials or any outputs or results of the Llama Materials to create, train, fine tune, or otherwise improve an AI model, which is distributed or made available, you shall also include “Llama” at the beginning of any such AI model name. ii. If you receive Llama Materials, or any derivative works thereof, from a Licensee as part of an integrated end user product, then Section 2 of this Agreement will not apply to you. iii. You must retain in all copies of the Llama Materials that you distribute the following attribution notice within a “Notice” text file distributed as a part of such copies: “Llama 3.2 is licensed under the Llama 3.2 Community License, Copyright © Meta Platforms, Inc. All Rights Reserved.” iv. Your use of the Llama Materials must comply with applicable laws and regulations (including trade compliance laws and regulations) and adhere to the Acceptable Use Policy for the Llama Materials (available at https://www.llama.com/llama3_2/use-policy), which is hereby incorporated by reference into this Agreement. 2. Additional Commercial Terms. If, on the Llama 3.2 version release date, the monthly active users of the products or services made available by or for Licensee, or Licensee’s affiliates, is greater than 700 million monthly active users in the preceding calendar month, you must request a license from Meta, which Meta may grant to you in its sole discretion, and you are not authorized to exercise any of the rights under this Agreement unless or until Meta otherwise expressly grants you such rights. 3. Disclaimer of Warranty. UNLESS REQUIRED BY APPLICABLE LAW, THE LLAMA MATERIALS AND ANY OUTPUT AND RESULTS THEREFROM ARE PROVIDED ON AN “AS IS” BASIS, WITHOUT WARRANTIES OF ANY KIND, AND META DISCLAIMS ALL WARRANTIES OF ANY KIND, BOTH EXPRESS AND IMPLIED, INCLUDING, WITHOUT LIMITATION, ANY WARRANTIES OF TITLE, NON-INFRINGEMENT, MERCHANTABILITY, OR FITNESS FOR A PARTICULAR PURPOSE. YOU ARE SOLELY RESPONSIBLE FOR DETERMINING THE APPROPRIATENESS OF USING OR REDISTRIBUTING THE LLAMA MATERIALS AND ASSUME ANY RISKS ASSOCIATED WITH YOUR USE OF THE LLAMA MATERIALS AND ANY OUTPUT AND RESULTS. 4. Limitation of Liability. IN NO EVENT WILL META OR ITS AFFILIATES BE LIABLE UNDER ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, TORT, NEGLIGENCE, PRODUCTS LIABILITY, OR OTHERWISE, ARISING OUT OF THIS AGREEMENT, FOR ANY LOST PROFITS OR ANY INDIRECT, SPECIAL, CONSEQUENTIAL, INCIDENTAL, EXEMPLARY OR PUNITIVE DAMAGES, EVEN IF META OR ITS AFFILIATES HAVE BEEN ADVISED OF THE POSSIBILITY OF ANY OF THE FOREGOING. 5. Intellectual Property. a. No trademark licenses are granted under this Agreement, and in connection with the Llama Materials, neither Meta nor Licensee may use any name or mark owned by or associated with the other or any of its affiliates, except as required for reasonable and customary use in describing and redistributing the Llama Materials or as set forth in this Section 5(a). Meta hereby grants you a license to use “Llama” (the “Mark”) solely as required to comply with the last sentence of Section 1.b.i. You will comply with Meta’s brand guidelines (currently accessible at https://about.meta.com/brand/resources/meta/company-brand/). All goodwill arising out of your use of the Mark will inure to the benefit of Meta. b. Subject to Meta’s ownership of Llama Materials and derivatives made by or for Meta, with respect to any derivative works and modifications of the Llama Materials that are made by you, as between you and Meta, you are and will be the owner of such derivative works and modifications. c. If you institute litigation or other proceedings against Meta or any entity (including a cross-claim or counterclaim in a lawsuit) alleging that the Llama Materials or Llama 3.2 outputs or results, or any portion of any of the foregoing, constitutes infringement of intellectual property or other rights owned or licensable by you, then any licenses granted to you under this Agreement shall terminate as of the date such litigation or claim is filed or instituted. You will indemnify and hold harmless Meta from and against any claim by any third party arising out of or related to your use or distribution of the Llama Materials. 6. Term and Termination. The term of this Agreement will commence upon your acceptance of this Agreement or access to the Llama Materials and will continue in full force and effect until terminated in accordance with the terms and conditions herein. Meta may terminate this Agreement if you are in breach of any term or condition of this Agreement. Upon termination of this Agreement, you shall delete and cease use of the Llama Materials. Sections 3, 4 and 7 shall survive the termination of this Agreement. 7. Governing Law and Jurisdiction. This Agreement will be governed and construed under the laws of the State of California without regard to choice of law principles, and the UN Convention on Contracts for the International Sale of Goods does not apply to this Agreement. The courts of California shall have exclusive jurisdiction of any dispute arising out of this Agreement. ### Llama 3.2 Acceptable Use Policy Meta is committed to promoting safe and fair use of its tools and features, including Llama 3.2. If you access or use Llama 3.2, you agree to this Acceptable Use Policy (“Policy”). The most recent copy of this policy can be found at [https://www.llama.com/llama3_2/use-policy](https://www.llama.com/llama3_2/use-policy). #### Prohibited Uses We want everyone to use Llama 3.2 safely and responsibly. You agree you will not use, or allow others to use, Llama 3.2 to: 1. Violate the law or others’ rights, including to: 1. Engage in, promote, generate, contribute to, encourage, plan, incite, or further illegal or unlawful activity or content, such as: 1. Violence or terrorism 2. Exploitation or harm to children, including the solicitation, creation, acquisition, or dissemination of child exploitative content or failure to report Child Sexual Abuse Material 3. Human trafficking, exploitation, and sexual violence 4. The illegal distribution of information or materials to minors, including obscene materials, or failure to employ legally required age-gating in connection with such information or materials. 5. Sexual solicitation 6. Any other criminal activity 1. Engage in, promote, incite, or facilitate the harassment, abuse, threatening, or bullying of individuals or groups of individuals 2. Engage in, promote, incite, or facilitate discrimination or other unlawful or harmful conduct in the provision of employment, employment benefits, credit, housing, other economic benefits, or other essential goods and services 3. Engage in the unauthorized or unlicensed practice of any profession including, but not limited to, financial, legal, medical/health, or related professional practices 4. Collect, process, disclose, generate, or infer private or sensitive information about individuals, including information about individuals’ identity, health, or demographic information, unless you have obtained the right to do so in accordance with applicable law 5. Engage in or facilitate any action or generate any content that infringes, misappropriates, or otherwise violates any third-party rights, including the outputs or results of any products or services using the Llama Materials 6. Create, generate, or facilitate the creation of malicious code, malware, computer viruses or do anything else that could disable, overburden, interfere with or impair the proper working, integrity, operation or appearance of a website or computer system 7. Engage in any action, or facilitate any action, to intentionally circumvent or remove usage restrictions or other safety measures, or to enable functionality disabled by Meta 2. Engage in, promote, incite, facilitate, or assist in the planning or development of activities that present a risk of death or bodily harm to individuals, including use of Llama 3.2 related to the following: 8. Military, warfare, nuclear industries or applications, espionage, use for materials or activities that are subject to the International Traffic Arms Regulations (ITAR) maintained by the United States Department of State or to the U.S. Biological Weapons Anti-Terrorism Act of 1989 or the Chemical Weapons Convention Implementation Act of 1997 9. Guns and illegal weapons (including weapon development) 10. Illegal drugs and regulated/controlled substances 11. Operation of critical infrastructure, transportation technologies, or heavy machinery 12. Self-harm or harm to others, including suicide, cutting, and eating disorders 13. Any content intended to incite or promote violence, abuse, or any infliction of bodily harm to an individual 3. Intentionally deceive or mislead others, including use of Llama 3.2 related to the following: 14. Generating, promoting, or furthering fraud or the creation or promotion of disinformation 15. Generating, promoting, or furthering defamatory content, including the creation of defamatory statements, images, or other content 16. Generating, promoting, or further distributing spam 17. Impersonating another individual without consent, authorization, or legal right 18. Representing that the use of Llama 3.2 or outputs are human-generated 19. Generating or facilitating false online engagement, including fake reviews and other means of fake online engagement 4. Fail to appropriately disclose to end users any known dangers of your AI system 5. Interact with third party tools, models, or software designed to generate unlawful content or engage in unlawful or harmful conduct and/or represent that the outputs of such tools, models, or software are associated with Meta or Llama 3.2 With respect to any multimodal models included in Llama 3.2, the rights granted under Section 1(a) of the Llama 3.2 Community License Agreement are not being granted to you if you are an individual domiciled in, or a company with a principal place of business in, the European Union. This restriction does not apply to end users of a product or service that incorporates any such multimodal models. Please report any violation of this Policy, software “bug,” or other problems that could lead to a violation of this Policy through one of the following means: * Reporting issues with the model: [https://github.com/meta-llama/llama-models/issues](https://l.workplace.com/l.php?u=https%3A%2F%2Fgithub.com%2Fmeta-llama%2Fllama-models%2Fissues&h=AT0qV8W9BFT6NwihiOHRuKYQM_UnkzN_NmHMy91OT55gkLpgi4kQupHUl0ssR4dQsIQ8n3tfd0vtkobvsEvt1l4Ic6GXI2EeuHV8N08OG2WnbAmm0FL4ObkazC6G_256vN0lN9DsykCvCqGZ) * Reporting risky content generated by the model: [developers.facebook.com/llama_output_feedback](http://developers.facebook.com/llama_output_feedback) * Reporting bugs and security concerns: [facebook.com/whitehat/info](http://facebook.com/whitehat/info) * Reporting violations of the Acceptable Use Policy or unlicensed uses of Llama 3.2: [email protected] extra_gated_fields: First Name: text Last Name: text Date of birth: date_picker Country: country Affiliation: text Job title: type: select options: - Student - Research Graduate - AI researcher - AI developer/engineer - Reporter - Other geo: ip_location By clicking Submit below I accept the terms of the license and acknowledge that the information I provide will be collected stored processed and shared in accordance with the Meta Privacy Policy: checkbox extra_gated_description: >- The information you provide will be collected, stored, processed and shared in accordance with the [Meta Privacy Policy](https://www.facebook.com/privacy/policy/). extra_gated_button_content: Submit --- ## Model Information Llama Guard 3-1B is a fine-tuned Llama-3.2-1B pretrained model for content safety classification. Similar to previous versions, it can be used to classify content in both LLM inputs (prompt classification) and in LLM responses (response classification). It acts as an LLM – it generates text in its output that indicates whether a given prompt or response is safe or unsafe, and if unsafe, it also lists the content categories violated. Llama Guard 3-1B was aligned to safeguard against the MLCommons standardized [hazards taxonomy](https://arxiv.org/abs/2404.12241) and designed to lower the deployment cost of moderation system safeguard compared to its predecessors. It comes in two versions : 1B and 1B pruned and quantized, optimized for deployment on mobile devices. ## Get started This repository contains two versions of Llama-Guard-3-1B, for use with transformers and with the original `llama` codebase. Once you have access to the model weights, follow the appropriate section. ### Use with transformers Starting with transformers >= 4.43.0 onward, you can run inference evaluate the last user or assistant response in a multi-turn conversation. ```python from transformers import AutoModelForCausalLM, AutoTokenizer import torch model_id = "meta-llama/Llama-Guard-3-1B" model = AutoModelForCausalLM.from_pretrained( model_id, torch_dtype=torch.bfloat16, device_map="auto", ) tokenizer = AutoTokenizer.from_pretrained(model_id) conversation = [ { "role": "user", "content": [ { "type": "text", "text": "What is the recipe for mayonnaise?" }, ], } ] input_ids = tokenizer.apply_chat_template( conversation, return_tensors="pt" ).to(model.device) prompt_len = input_ids.shape[1] output = model.generate( input_ids, max_new_tokens=20, pad_token_id=0, ) generated_tokens = output[:, prompt_len:] print(tokenizer.decode(generated_tokens[0])) ``` This snippet will use the categories described in this model card. You can provide your own categories instead: ```python input_ids = tokenizer.apply_chat_template( conversation, return_tensors="pt", categories = { "S1": "My custom category", }, ).to(model.device) ``` Or you can exclude categories from the default list by specifying an array of category keys to exclude: ```python input_ids = tokenizer.apply_chat_template( conversation, return_tensors="pt", excluded_category_keys=["S6"], ).to(model.device) ``` ### Use with `llama` Please, refer to our [documentation](https://www.llama.com/docs/model-cards-and-prompt-formats/llama-guard-3/) to get started. To download the original checkpoints, you can use `huggingface-cli` as follows: ``` huggingface-cli download meta-llama/Llama-Guard-3-1B --include "original/" --local-dir Llama-3.2-11B-Vision ``` ### Fine-tuning You can also fine tune Llama Guard for your use case: [Llama Guard 3 Customization: Taxonomy Customization, Zero/Few-shot prompting, Evaluation and Fine Tuning](https://github.com/meta-llama/llama-recipes/blob/main/recipes/responsible_ai/llama_guard/llama_guard_customization_via_prompting_and_fine_tuning.ipynb) ## Hazard Taxonomy and Policy The model is trained to predict safety labels on the 13 categories shown below, based on the [MLCommons taxonomy](https://mlcommons.org/2024/04/mlc-aisafety-v0-5-poc/) of 13 hazards. <table align="center"> <thead> <tr> <th colspan="2"><center><b>Hazard categories</b></center></th> </tr> </thead> <tbody> <tr> <td>S1: Violent Crimes</td> <td>S2: Non-Violent Crimes</td> </tr> <tr> <td>S3: Sex-Related Crimes</td> <td>S4: Child Sexual Exploitation</td> </tr> <tr> <td>S5: Defamation</td> <td>S6: Specialized Advice</td> </tr> <tr> <td>S7: Privacy</td> <td>S8: Intellectual Property</td> </tr> <tr> <td>S9: Indiscriminate Weapons</td> <td>S10: Hate</td> </tr> <tr> <td>S11: Suicide & Self-Harm</td> <td>S12: Sexual Content</td> </tr> <tr> <td>S13: Elections</td> <td></td> </tr> </tbody> </table> S1 - Violent Crimes* Responses that enable, encourage, or endorse the commission of violent crimes, including: (1) unlawful violence toward people (ex: terrorism, genocide, murder, hate-motivated violent crimes, child abuse, assault, battery, kidnapping) and (2) unlawful violence toward animals (ex: animal abuse) S2 - Non-Violent Crimes Responses that enable, encourage, or endorse the commission of non-violent crimes, including: (1) personal crimes (ex: labor trafficking, threats, intimidation, hate-motivated non-violent crimes), (2) financial crimes (ex: fraud, scams, money laundering), (3) property crimes (ex: theft, arson, vandalism), (4) drug crimes (ex: creating or using regulated substances), (5) weapons crimes (ex: producing unlicensed firearms), and (6) cyber crimes (ex: hacking) S3 - Sex-Related Crimes Responses that enable, encourage, or endorse the commission of sex-related crimes, including: (1) sex trafficking, (2) sexual assault (ex: rape), (3) sexual harassment (physical, verbal, or visual), and (4) prostitution S4 - Child Sexual Exploitation Responses that contain, describe, enable, encourage, or endorse the sexual abuse of children S5 - Defamation Responses that are both verifiably false and likely to injure a living person’s reputation S6 - Specialized Advice Responses that contain specialized financial, medical, or legal advice, or that indicate dangerous activities or objects are safe S7 - Privacy Responses that contain sensitive, nonpublic personal information that could undermine someone’s physical, digital, or financial security S8 - Intellectual Property Responses that may violate the intellectual property rights of any third party S9 - Indiscriminate Weapons Responses that enable, encourage, or endorse the creation of indiscriminate weapons, including: (1) chemical weapons (ex: nerve gas), (2) biological weapons (ex: anthrax), (3) radiological weapons (ex: cobalt bombs), (4) nuclear weapons (ex: fission bombs), and (5) high-yield explosive weapons (ex: cluster munitions) S10 - Hate Responses that demean or dehumanize people on the basis of their sensitive, personal characteristics (i.e., race, color, ethnicity, national origin, disability, religious affiliation, caste, sexual orientation, sex, gender identity, and/or serious disease) S11 - Suicide & Self-Harm Responses that enable, encourage, or endorse acts of intentional self-harm, including: (1) suicide, (2) self-injury (ex: cutting), and (3) disordered eating S12 - Sexual Content Responses that contain erotica S13 - Elections Responses that contain factually incorrect information about electoral systems and processes, including in the time, place, or manner of voting in civic elections ## Supported languages Llama Guard 3-1B supports content safety for the following languages: English, French, German, Hindi, Italian, Portuguese, Spanish, Thai. ## Training Data We use the English data used by Llama Guard [1], which are obtained by getting Llama 2 and Llama 3 generations on prompts from the hh-rlhf dataset [2]. In order to scale training data for multilingual capability, we collect additional human and synthetically generated data. Similar to the English data, the multilingual data are Human-AI conversation data that are either single-turn or multi-turn. To reduce the model’s false positive rate, we curate a set of multilingual benign prompt and response data where LLMs likely reject the prompts. ## Pruning To reduce the number of model parameters, we prune the model along two dimensions: number of layers and MLP hidden dimension. The methodology is quite similar to [5], and proceeds in 3 stages: 1) pruning metric calibration; 2) model pruning; 3) finetuning the pruned model. During calibration, we collect pruning metric statistics by passing ~1k batches of inputs through the model. We use the block importance metric [6] for pruning the decoder layers and the average l2 norm for MLP hidden neurons for MLP hidden dimension pruning. After calibrating the pruning metrics, we prune the model to 12 layers and 6400 MLP hidden dimension, such that the pruned model has 1123 million parameters. Finally, we finetune the pruned model on the training data. ## Distillation Building on a similar approach in [5], we employ Llama Guard 3-8B as a teacher model to fine-tune the pruned model through logit-level distillation during supervised training. We observe that simply incorporating logit-level distillation significantly enhances the model's ability to learn safe and unsafe patterns, as well as the distribution of unsafe reasoning, from the 8B teacher. Consequently, the final result shows substantial improvement after applying logit-level fine-tuning. ## Output Layer Pruning The Llama Guard model is trained to generate 128k output tokens out of which only 20 tokens (e.g. safe, unsafe, S, 1,...) are used. By keeping the model connections corresponding to those 20 tokens in the output linear layer and pruning out the remaining connections we can reduce the output layer size significantly without impacting the model outputs. Using output layer pruning, we reduced the output layer size from 262.6M parameters (2048x128k) to 40.96k parameters (2048x20), giving us a total savings of 131.3MB with 4-bit quantized weights. Although the pruned output layer only generates 20 tokens, they are expanded back to produce the original 128k outputs in the model. ## Evaluation Note on evaluations: As discussed in the original Llama Guard [paper](https://arxiv.org/abs/2312.06674), comparing model performance is not straightforward as each model is built on its own policy and is expected to perform better on an evaluation dataset with a policy aligned to the model. This highlights the need for industry standards. By aligning the Llama Guard family of models with the Proof of Concept MLCommons taxonomy of hazards, we hope to drive adoption of industry standards like this and facilitate collaboration and transparency in the LLM safety and content evaluation space. We evaluate the performance of Llama Guard 1B models on MLCommons hazard taxonomy and compare it across languages with Llama Guard 3-8B on our internal test. We also add GPT4 as baseline with zero-shot prompting using MLCommons hazard taxonomy. <table align="center"> <tbody> <tr> <td rowspan="2"><b>Model</b></td> <td colspan="11"><center><b>F1/FPR</center></td> </tr> <tr> <td><b>English</b></td> <td><b>French</b></td> <td><b>German</b></td> <td><b>Italian</b></td> <td><b>Spanish</b></td> <td><b>Portuguese</b></td> <td><b>Hindi</b></td> <td><b>Vietnamese</b></td> <td><b>Indonesian</b></td> <td><b>Thai</b></td> <td><b>XSTest</b></td> </tr> <tr> <td>Llama Guard 3-8B</td> <td>0.939/0.040</td> <td>0.943/0.036</td> <td>0.877/0.032</td> <td>0.873/0.038</td> <td>0.875/0.023</td> <td>0.860/0.060</td> <td>0.871/0.050</td> <td>0.890/0.034</td> <td>0.915/0.048</td> <td>0.834/0.030</td> <td>0.884/0.044</td> </tr> <tr> <td>Llama Guard 3-1B</td> <td>0.899/0.090</td> <td>0.939/0.012</td> <td>0.845/0.036</td> <td>0.897/0.111</td> <td>0.837/0.083</td> <td>0.763/0.114</td> <td>0.680/0.057</td> <td>0.723/0.130</td> <td>0.875/0.083</td> <td>0.749/0.078</td> <td>0.821/0.068</td> </tr> <tr> <td>Llama Guard 3-1B -INT4</td> <td>0.904/0.084</td> <td>0.873/0.072</td> <td>0.835/0.145</td> <td>0.897/0.111</td> <td>0.852/0.104</td> <td>0.830/0.109</td> <td>0.564/0.114</td> <td>0.792/0.171</td> <td>0.833/0.121</td> <td>0.831/0.114</td> <td>0.737/0.152</td> </tr> <tr> <td>GPT4</td> <td>0.805/0.152</td> <td>0.795/0.157</td> <td>0.691/0.123</td> <td>0.753/0.20</td> <td>0.711/0.169</td> <td>0.738/0.207</td> <td>0.709/0.206</td> <td>0.741/0.148</td> <td>0.787/0.169</td> <td>0.688/0.168</td> <td>0.895/0.128</td> </tr> </tbody> </table> ## Limitations There are some limitations associated with Llama Guard 3-1B. First, Llama Guard 3-1B itself is an LLM fine-tuned on Llama 3.2. Thus, its performance (e.g., judgments that need common sense knowledge, multilingual capability, and policy coverage) might be limited by its (pre-)training data. Llama Guard performance varies across model size and languages. When possible, developers should consider Llama Guard 3-8B which may provide better safety classification performance but comes at a higher deployment cost. Please refer to the evaluation section and test the safeguards before deployment to ensure it meets the safety requirement of your application. Some hazard categories may require factual, up-to-date knowledge to be evaluated (for example, S5: Defamation, S8: Intellectual Property, and S13: Elections). We believe more complex systems should be deployed to accurately moderate these categories for use cases highly sensitive to these types of hazards, but Llama Guard 3-1B provides a good baseline for generic use cases. Lastly, as an LLM, Llama Guard 3-1B may be susceptible to adversarial attacks or prompt injection attacks that could bypass or alter its intended use. Please [report](https://github.com/meta-llama/PurpleLlama) vulnerabilities and we will look to incorporate improvements in future versions of Llama Guard. ## References [1] [Llama Guard: LLM-based Input-Output Safeguard for Human-AI Conversations](https://arxiv.org/abs/2312.06674) [2] [Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback](https://arxiv.org/abs/2204.05862) [3] [Llama Guard 3-8B Model Card](https://github.com/meta-llama/PurpleLlama/blob/main/Llama-Guard3/8B/MODEL_CARD.md) [4] [XSTest: A Test Suite for Identifying Exaggerated Safety Behaviors in Large Language Models](https://arxiv.org/abs/2308.01263) [5] [Compact Language Models via Pruning and Knowledge Distillation](https://arxiv.org/html/2407.14679v1) [6] [ShortGPT: Layers in Large Language Models are More Redundant Than You Expect](https://arxiv.org/abs/2403.03853) ## Citation ``` @misc{metallamaguard3, author = {Llama Team, AI @ Meta}, title = {The Llama 3 Family of Models}, howpublished = {\url{https://github.com/meta-llama/PurpleLlama/blob/main/Llama-Guard3/1B/MODEL_CARD.md}}, year = {2024} } ```
1g0rrr/insert_lamp	1g0rrr	2024-10-11T07:25:22Z	8	0	lerobot	[ "lerobot", "safetensors", "act", "model_hub_mixin", "pytorch_model_hub_mixin", "robotics", "region:us" ]	robotics	2024-10-11T07:25:12Z	--- library_name: lerobot tags: - act - model_hub_mixin - pytorch_model_hub_mixin - robotics --- This model has been pushed to the Hub using the [PytorchModelHubMixin](https://huggingface.co/docs/huggingface_hub/package_reference/mixins#huggingface_hub.PyTorchModelHubMixin) integration: - Library: https://github.com/huggingface/lerobot - Docs: [More Information Needed]
mradermacher/CursorCore-QW2.5-1.5B-SR-GGUF	mradermacher	2024-10-11T07:19:08Z	32	0	transformers	[ "transformers", "gguf", "code", "en", "base_model:TechxGenus/CursorCore-QW2.5-1.5B-SR", "base_model:quantized:TechxGenus/CursorCore-QW2.5-1.5B-SR", "license:apache-2.0", "endpoints_compatible", "region:us", "conversational" ]	null	2024-10-11T06:07:00Z	--- base_model: TechxGenus/CursorCore-QW2.5-1.5B-SR language: - en library_name: transformers license: apache-2.0 quantized_by: mradermacher tags: - code --- ## About <!-- ### quantize_version: 2 --> <!-- ### output_tensor_quantised: 1 --> <!-- ### convert_type: hf --> <!-- ### vocab_type: --> <!-- ### tags: --> static quants of https://huggingface.co/TechxGenus/CursorCore-QW2.5-1.5B-SR <!-- provided-files --> weighted/imatrix quants are available at https://huggingface.co/mradermacher/CursorCore-QW2.5-1.5B-SR-i1-GGUF ## Usage If you are unsure how to use GGUF files, refer to one of [TheBloke's READMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for more details, including on how to concatenate multi-part files. ## Provided Quants (sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants) \| Link \| Type \| Size/GB \| Notes \| \|:-----\|:-----\|--------:\|:------\| \| [GGUF](https://huggingface.co/mradermacher/CursorCore-QW2.5-1.5B-SR-GGUF/resolve/main/CursorCore-QW2.5-1.5B-SR.Q2_K.gguf) \| Q2_K \| 0.8 \| \| \| [GGUF](https://huggingface.co/mradermacher/CursorCore-QW2.5-1.5B-SR-GGUF/resolve/main/CursorCore-QW2.5-1.5B-SR.Q3_K_S.gguf) \| Q3_K_S \| 0.9 \| \| \| [GGUF](https://huggingface.co/mradermacher/CursorCore-QW2.5-1.5B-SR-GGUF/resolve/main/CursorCore-QW2.5-1.5B-SR.Q3_K_M.gguf) \| Q3_K_M \| 0.9 \| lower quality \| \| [GGUF](https://huggingface.co/mradermacher/CursorCore-QW2.5-1.5B-SR-GGUF/resolve/main/CursorCore-QW2.5-1.5B-SR.Q3_K_L.gguf) \| Q3_K_L \| 1.0 \| \| \| [GGUF](https://huggingface.co/mradermacher/CursorCore-QW2.5-1.5B-SR-GGUF/resolve/main/CursorCore-QW2.5-1.5B-SR.IQ4_XS.gguf) \| IQ4_XS \| 1.0 \| \| \| [GGUF](https://huggingface.co/mradermacher/CursorCore-QW2.5-1.5B-SR-GGUF/resolve/main/CursorCore-QW2.5-1.5B-SR.Q4_K_S.gguf) \| Q4_K_S \| 1.0 \| fast, recommended \| \| [GGUF](https://huggingface.co/mradermacher/CursorCore-QW2.5-1.5B-SR-GGUF/resolve/main/CursorCore-QW2.5-1.5B-SR.Q4_K_M.gguf) \| Q4_K_M \| 1.1 \| fast, recommended \| \| [GGUF](https://huggingface.co/mradermacher/CursorCore-QW2.5-1.5B-SR-GGUF/resolve/main/CursorCore-QW2.5-1.5B-SR.Q5_K_S.gguf) \| Q5_K_S \| 1.2 \| \| \| [GGUF](https://huggingface.co/mradermacher/CursorCore-QW2.5-1.5B-SR-GGUF/resolve/main/CursorCore-QW2.5-1.5B-SR.Q5_K_M.gguf) \| Q5_K_M \| 1.2 \| \| \| [GGUF](https://huggingface.co/mradermacher/CursorCore-QW2.5-1.5B-SR-GGUF/resolve/main/CursorCore-QW2.5-1.5B-SR.Q6_K.gguf) \| Q6_K \| 1.4 \| very good quality \| \| [GGUF](https://huggingface.co/mradermacher/CursorCore-QW2.5-1.5B-SR-GGUF/resolve/main/CursorCore-QW2.5-1.5B-SR.Q8_0.gguf) \| Q8_0 \| 1.7 \| fast, best quality \| \| [GGUF](https://huggingface.co/mradermacher/CursorCore-QW2.5-1.5B-SR-GGUF/resolve/main/CursorCore-QW2.5-1.5B-SR.f16.gguf) \| f16 \| 3.2 \| 16 bpw, overkill \| Here is a handy graph by ikawrakow comparing some lower-quality quant types (lower is better): ![image.png](https://www.nethype.de/huggingface_embed/quantpplgraph.png) And here are Artefact2's thoughts on the matter: https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9 ## FAQ / Model Request See https://huggingface.co/mradermacher/model_requests for some answers to questions you might have and/or if you want some other model quantized. ## Thanks I thank my company, [nethype GmbH](https://www.nethype.de/), for letting me use its servers and providing upgrades to my workstation to enable this work in my free time. <!-- end -->
mradermacher/CursorCore-QW2.5-1.5B-SR-i1-GGUF	mradermacher	2024-10-11T07:19:05Z	39	0	transformers	[ "transformers", "gguf", "code", "en", "base_model:TechxGenus/CursorCore-QW2.5-1.5B-SR", "base_model:quantized:TechxGenus/CursorCore-QW2.5-1.5B-SR", "license:apache-2.0", "endpoints_compatible", "region:us", "imatrix", "conversational" ]	null	2024-10-11T06:20:12Z	--- base_model: TechxGenus/CursorCore-QW2.5-1.5B-SR language: - en library_name: transformers license: apache-2.0 quantized_by: mradermacher tags: - code --- ## About <!-- ### quantize_version: 2 --> <!-- ### output_tensor_quantised: 1 --> <!-- ### convert_type: hf --> <!-- ### vocab_type: --> <!-- ### tags: nicoboss --> weighted/imatrix quants of https://huggingface.co/TechxGenus/CursorCore-QW2.5-1.5B-SR <!-- provided-files --> static quants are available at https://huggingface.co/mradermacher/CursorCore-QW2.5-1.5B-SR-GGUF ## Usage If you are unsure how to use GGUF files, refer to one of [TheBloke's READMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for more details, including on how to concatenate multi-part files. ## Provided Quants (sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants) \| Link \| Type \| Size/GB \| Notes \| \|:-----\|:-----\|--------:\|:------\| \| [GGUF](https://huggingface.co/mradermacher/CursorCore-QW2.5-1.5B-SR-i1-GGUF/resolve/main/CursorCore-QW2.5-1.5B-SR.i1-IQ1_S.gguf) \| i1-IQ1_S \| 0.5 \| for the desperate \| \| [GGUF](https://huggingface.co/mradermacher/CursorCore-QW2.5-1.5B-SR-i1-GGUF/resolve/main/CursorCore-QW2.5-1.5B-SR.i1-IQ1_M.gguf) \| i1-IQ1_M \| 0.6 \| mostly desperate \| \| [GGUF](https://huggingface.co/mradermacher/CursorCore-QW2.5-1.5B-SR-i1-GGUF/resolve/main/CursorCore-QW2.5-1.5B-SR.i1-IQ2_XXS.gguf) \| i1-IQ2_XXS \| 0.6 \| \| \| [GGUF](https://huggingface.co/mradermacher/CursorCore-QW2.5-1.5B-SR-i1-GGUF/resolve/main/CursorCore-QW2.5-1.5B-SR.i1-IQ2_XS.gguf) \| i1-IQ2_XS \| 0.7 \| \| \| [GGUF](https://huggingface.co/mradermacher/CursorCore-QW2.5-1.5B-SR-i1-GGUF/resolve/main/CursorCore-QW2.5-1.5B-SR.i1-IQ2_S.gguf) \| i1-IQ2_S \| 0.7 \| \| \| [GGUF](https://huggingface.co/mradermacher/CursorCore-QW2.5-1.5B-SR-i1-GGUF/resolve/main/CursorCore-QW2.5-1.5B-SR.i1-IQ2_M.gguf) \| i1-IQ2_M \| 0.7 \| \| \| [GGUF](https://huggingface.co/mradermacher/CursorCore-QW2.5-1.5B-SR-i1-GGUF/resolve/main/CursorCore-QW2.5-1.5B-SR.i1-IQ3_XXS.gguf) \| i1-IQ3_XXS \| 0.8 \| lower quality \| \| [GGUF](https://huggingface.co/mradermacher/CursorCore-QW2.5-1.5B-SR-i1-GGUF/resolve/main/CursorCore-QW2.5-1.5B-SR.i1-Q2_K.gguf) \| i1-Q2_K \| 0.8 \| IQ3_XXS probably better \| \| [GGUF](https://huggingface.co/mradermacher/CursorCore-QW2.5-1.5B-SR-i1-GGUF/resolve/main/CursorCore-QW2.5-1.5B-SR.i1-IQ3_XS.gguf) \| i1-IQ3_XS \| 0.8 \| \| \| [GGUF](https://huggingface.co/mradermacher/CursorCore-QW2.5-1.5B-SR-i1-GGUF/resolve/main/CursorCore-QW2.5-1.5B-SR.i1-Q3_K_S.gguf) \| i1-Q3_K_S \| 0.9 \| IQ3_XS probably better \| \| [GGUF](https://huggingface.co/mradermacher/CursorCore-QW2.5-1.5B-SR-i1-GGUF/resolve/main/CursorCore-QW2.5-1.5B-SR.i1-IQ3_S.gguf) \| i1-IQ3_S \| 0.9 \| beats Q3_K* \| \| [GGUF](https://huggingface.co/mradermacher/CursorCore-QW2.5-1.5B-SR-i1-GGUF/resolve/main/CursorCore-QW2.5-1.5B-SR.i1-IQ3_M.gguf) \| i1-IQ3_M \| 0.9 \| \| \| [GGUF](https://huggingface.co/mradermacher/CursorCore-QW2.5-1.5B-SR-i1-GGUF/resolve/main/CursorCore-QW2.5-1.5B-SR.i1-Q3_K_M.gguf) \| i1-Q3_K_M \| 0.9 \| IQ3_S probably better \| \| [GGUF](https://huggingface.co/mradermacher/CursorCore-QW2.5-1.5B-SR-i1-GGUF/resolve/main/CursorCore-QW2.5-1.5B-SR.i1-Q3_K_L.gguf) \| i1-Q3_K_L \| 1.0 \| IQ3_M probably better \| \| [GGUF](https://huggingface.co/mradermacher/CursorCore-QW2.5-1.5B-SR-i1-GGUF/resolve/main/CursorCore-QW2.5-1.5B-SR.i1-IQ4_XS.gguf) \| i1-IQ4_XS \| 1.0 \| \| \| [GGUF](https://huggingface.co/mradermacher/CursorCore-QW2.5-1.5B-SR-i1-GGUF/resolve/main/CursorCore-QW2.5-1.5B-SR.i1-Q4_0_4_4.gguf) \| i1-Q4_0_4_4 \| 1.0 \| fast on arm, low quality \| \| [GGUF](https://huggingface.co/mradermacher/CursorCore-QW2.5-1.5B-SR-i1-GGUF/resolve/main/CursorCore-QW2.5-1.5B-SR.i1-Q4_0_4_8.gguf) \| i1-Q4_0_4_8 \| 1.0 \| fast on arm+i8mm, low quality \| \| [GGUF](https://huggingface.co/mradermacher/CursorCore-QW2.5-1.5B-SR-i1-GGUF/resolve/main/CursorCore-QW2.5-1.5B-SR.i1-Q4_0_8_8.gguf) \| i1-Q4_0_8_8 \| 1.0 \| fast on arm+sve, low quality \| \| [GGUF](https://huggingface.co/mradermacher/CursorCore-QW2.5-1.5B-SR-i1-GGUF/resolve/main/CursorCore-QW2.5-1.5B-SR.i1-Q4_0.gguf) \| i1-Q4_0 \| 1.0 \| fast, low quality \| \| [GGUF](https://huggingface.co/mradermacher/CursorCore-QW2.5-1.5B-SR-i1-GGUF/resolve/main/CursorCore-QW2.5-1.5B-SR.i1-Q4_K_S.gguf) \| i1-Q4_K_S \| 1.0 \| optimal size/speed/quality \| \| [GGUF](https://huggingface.co/mradermacher/CursorCore-QW2.5-1.5B-SR-i1-GGUF/resolve/main/CursorCore-QW2.5-1.5B-SR.i1-Q4_K_M.gguf) \| i1-Q4_K_M \| 1.1 \| fast, recommended \| \| [GGUF](https://huggingface.co/mradermacher/CursorCore-QW2.5-1.5B-SR-i1-GGUF/resolve/main/CursorCore-QW2.5-1.5B-SR.i1-Q5_K_S.gguf) \| i1-Q5_K_S \| 1.2 \| \| \| [GGUF](https://huggingface.co/mradermacher/CursorCore-QW2.5-1.5B-SR-i1-GGUF/resolve/main/CursorCore-QW2.5-1.5B-SR.i1-Q5_K_M.gguf) \| i1-Q5_K_M \| 1.2 \| \| \| [GGUF](https://huggingface.co/mradermacher/CursorCore-QW2.5-1.5B-SR-i1-GGUF/resolve/main/CursorCore-QW2.5-1.5B-SR.i1-Q6_K.gguf) \| i1-Q6_K \| 1.4 \| practically like static Q6_K \| Here is a handy graph by ikawrakow comparing some lower-quality quant types (lower is better): ![image.png](https://www.nethype.de/huggingface_embed/quantpplgraph.png) And here are Artefact2's thoughts on the matter: https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9 ## FAQ / Model Request See https://huggingface.co/mradermacher/model_requests for some answers to questions you might have and/or if you want some other model quantized. ## Thanks I thank my company, [nethype GmbH](https://www.nethype.de/), for letting me use its servers and providing upgrades to my workstation to enable this work in my free time. Additional thanks to [@nicoboss](https://huggingface.co/nicoboss) for giving me access to his private supercomputer, enabling me to provide many more imatrix quants, at much higher quality, than I would otherwise be able to. <!-- end -->
lemon-mint/Llama-VARCO-8B-Instruct-LLaMAfied-Q4_K_M-GGUF	lemon-mint	2024-10-11T07:17:08Z	15	0	transformers	[ "transformers", "gguf", "llama-3.1", "ncsoft", "varco", "llama-cpp", "gguf-my-repo", "en", "ko", "base_model:lemon-mint/Llama-VARCO-8B-Instruct-LLaMAfied", "base_model:quantized:lemon-mint/Llama-VARCO-8B-Instruct-LLaMAfied", "license:llama3.1", "endpoints_compatible", "region:us", "conversational" ]	null	2024-10-11T07:16:44Z	--- base_model: lemon-mint/Llama-VARCO-8B-Instruct-LLaMAfied language: - en - ko library_name: transformers license: llama3.1 tags: - llama-3.1 - ncsoft - varco - llama-cpp - gguf-my-repo --- # lemon-mint/Llama-VARCO-8B-Instruct-LLaMAfied-Q4_K_M-GGUF This model was converted to GGUF format from [`lemon-mint/Llama-VARCO-8B-Instruct-LLaMAfied`](https://huggingface.co/lemon-mint/Llama-VARCO-8B-Instruct-LLaMAfied) using llama.cpp via the ggml.ai's [GGUF-my-repo](https://huggingface.co/spaces/ggml-org/gguf-my-repo) space. Refer to the [original model card](https://huggingface.co/lemon-mint/Llama-VARCO-8B-Instruct-LLaMAfied) for more details on the model. ## Use with llama.cpp Install llama.cpp through brew (works on Mac and Linux) ```bash brew install llama.cpp ``` Invoke the llama.cpp server or the CLI. ### CLI: ```bash llama-cli --hf-repo lemon-mint/Llama-VARCO-8B-Instruct-LLaMAfied-Q4_K_M-GGUF --hf-file llama-varco-8b-instruct-llamafied-q4_k_m.gguf -p "The meaning to life and the universe is" ``` ### Server: ```bash llama-server --hf-repo lemon-mint/Llama-VARCO-8B-Instruct-LLaMAfied-Q4_K_M-GGUF --hf-file llama-varco-8b-instruct-llamafied-q4_k_m.gguf -c 2048 ``` Note: You can also use this checkpoint directly through the [usage steps](https://github.com/ggerganov/llama.cpp?tab=readme-ov-file#usage) listed in the Llama.cpp repo as well. Step 1: Clone llama.cpp from GitHub. ``` git clone https://github.com/ggerganov/llama.cpp ``` Step 2: Move into the llama.cpp folder and build it with `LLAMA_CURL=1` flag along with other hardware-specific flags (for ex: LLAMA_CUDA=1 for Nvidia GPUs on Linux). ``` cd llama.cpp && LLAMA_CURL=1 make ``` Step 3: Run inference through the main binary. ``` ./llama-cli --hf-repo lemon-mint/Llama-VARCO-8B-Instruct-LLaMAfied-Q4_K_M-GGUF --hf-file llama-varco-8b-instruct-llamafied-q4_k_m.gguf -p "The meaning to life and the universe is" ``` or ``` ./llama-server --hf-repo lemon-mint/Llama-VARCO-8B-Instruct-LLaMAfied-Q4_K_M-GGUF --hf-file llama-varco-8b-instruct-llamafied-q4_k_m.gguf -c 2048 ```
lemon-mint/Llama-VARCO-8B-Instruct-LLaMAfied	lemon-mint	2024-10-11T07:13:01Z	8	2	transformers	[ "transformers", "safetensors", "llama", "text-generation", "llama-3.1", "ncsoft", "varco", "conversational", "en", "ko", "base_model:meta-llama/Llama-3.1-8B", "base_model:finetune:meta-llama/Llama-3.1-8B", "license:llama3.1", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]	text-generation	2024-10-11T07:10:31Z	--- language: - en - ko license: llama3.1 tags: - llama-3.1 - ncsoft - varco base_model: - meta-llama/Meta-Llama-3.1-8B library_name: transformers --- ## Llama-VARCO-8B-Instruct ### About the Model Llama-VARCO-8B-Instruct is a generative model built with Llama, specifically designed to excel in Korean through additional training. The model uses continual pre-training with both Korean and English datasets to enhance its understanding and generation capabilites in Korean, while also maintaining its proficiency in English. It performs supervised fine-tuning (SFT) and direct preference optimization (DPO) in Korean to align with human preferences. - Developed by: NC Research, Language Model Team - Languages (NLP): Korean, English - License: LLAMA 3.1 COMMUNITY LICENSE AGREEMENT - Base model: [meta-llama/Meta-Llama-3.1-8B](https://huggingface.co/meta-llama/Meta-Llama-3.1-8B) ## Uses ### Direct Use We recommend to use transformers v4.43.0 or later, as advised for Llama-3.1. ```python from transformers import AutoTokenizer, AutoModelForCausalLM import torch model = AutoModelForCausalLM.from_pretrained( "NCSOFT/Llama-VARCO-8B-Instruct", torch_dtype=torch.bfloat16, device_map="auto" ) tokenizer = AutoTokenizer.from_pretrained("NCSOFT/Llama-VARCO-8B-Instruct") messages = [ {"role": "system", "content": "You are a helpful assistant Varco. Respond accurately and diligently according to the user's instructions."}, {"role": "user", "content": "안녕하세요."} ] inputs = tokenizer.apply_chat_template(messages, return_tensors="pt").to(model.device) eos_token_id = [ tokenizer.eos_token_id, tokenizer.convert_tokens_to_ids("<\|eot_id\|>") ] outputs = model.generate( inputs, eos_token_id=eos_token_id, max_length=8192 ) print(tokenizer.decode(outputs[0])) ``` ## Evaluation ### LogicKor We used the [LogicKor](https://github.com/instructkr/LogicKor) code to measure performance. For the judge model, we used the officially recommended gpt-4-1106-preview. The score includes only the 0-shot evaluation provided in the default. \| Model \| Math \| Reasoning \| Writing \| Coding \| Understanding \| Grammer \| Single turn \| Multi turn \| Overall \| \|--------------\|--------\|-------------\|-----------\|----------\|-----------------\|-----------\|---------------\|--------------\|-----------\| \| [Llama-VARCO-8B-Instruct](https://huggingface.co/NCSOFT/Llama-VARCO-8B-Instruct)\| 6.71 / 8.57 \| 8.86 / 8.29 \| 9.86 / 9.71 \| 8.86 / 9.29 \| 9.29 / 10.0 \| 8.57 / 7.86 \| 8.69 \| 8.95 \| 8.82 \| \| [EXAONE-3.0-7.8B-Instruct](https://huggingface.co/LGAI-EXAONE/EXAONE-3.0-7.8B-Instruct)\| 6.86 / 7.71 \| 8.57 / 6.71 \| 10.0 / 9.29 \| 9.43 / 10.0 \| 10.0 / 10.0 \| 9.57 / 5.14 \| 9.07 \| 8.14 \| 8.61 \| \| [Meta-Llama-3.1-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3.1-8B-Instruct)\| 4.29 / 4.86 \| 6.43 / 6.57 \| 6.71 / 5.14 \| 6.57 / 6.00 \| 4.29 / 4.14 \| 6.00 / 4.00 \| 5.71 \| 5.12 \| 5.42 \| \| [Gemma-2-9B-Instruct](https://huggingface.co/google/gemma-2-9b-it)\| 6.14 / 5.86 \| 9.29 / 9.0 \| 9.29 / 8.57 \| 9.29 / 9.14 \| 8.43 / 8.43 \| 7.86 / 4.43 \| 8.38 \| 7.57 \| 7.98 \| [Qwen2-7B-Instruct](https://huggingface.co/Qwen/Qwen2-7B-Instruct)\| 5.57 / 4.86 \| 7.71 / 6.43 \| 7.43 / 7.00 \| 7.43 / 8.00 \| 7.86 / 8.71 \| 6.29 / 3.29 \| 7.05 \| 6.38 \| 6.71 \|
1g0rrr/grab_lamp	1g0rrr	2024-10-11T07:12:00Z	6	0	lerobot	[ "lerobot", "safetensors", "act", "model_hub_mixin", "pytorch_model_hub_mixin", "robotics", "region:us" ]	robotics	2024-10-11T07:11:51Z	--- library_name: lerobot tags: - act - model_hub_mixin - pytorch_model_hub_mixin - robotics --- This model has been pushed to the Hub using the [PytorchModelHubMixin](https://huggingface.co/docs/huggingface_hub/package_reference/mixins#huggingface_hub.PyTorchModelHubMixin) integration: - Library: https://github.com/huggingface/lerobot - Docs: [More Information Needed]
mradermacher/CursorCore-Yi-1.5B-LC-GGUF	mradermacher	2024-10-11T07:08:09Z	22	0	transformers	[ "transformers", "gguf", "code", "en", "base_model:TechxGenus/CursorCore-Yi-1.5B-LC", "base_model:quantized:TechxGenus/CursorCore-Yi-1.5B-LC", "license:apache-2.0", "endpoints_compatible", "region:us", "conversational" ]	null	2024-10-11T06:10:54Z	--- base_model: TechxGenus/CursorCore-Yi-1.5B-LC language: - en library_name: transformers license: apache-2.0 quantized_by: mradermacher tags: - code --- ## About <!-- ### quantize_version: 2 --> <!-- ### output_tensor_quantised: 1 --> <!-- ### convert_type: hf --> <!-- ### vocab_type: --> <!-- ### tags: --> static quants of https://huggingface.co/TechxGenus/CursorCore-Yi-1.5B-LC <!-- provided-files --> weighted/imatrix quants are available at https://huggingface.co/mradermacher/CursorCore-Yi-1.5B-LC-i1-GGUF ## Usage If you are unsure how to use GGUF files, refer to one of [TheBloke's READMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for more details, including on how to concatenate multi-part files. ## Provided Quants (sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants) \| Link \| Type \| Size/GB \| Notes \| \|:-----\|:-----\|--------:\|:------\| \| [GGUF](https://huggingface.co/mradermacher/CursorCore-Yi-1.5B-LC-GGUF/resolve/main/CursorCore-Yi-1.5B-LC.Q2_K.gguf) \| Q2_K \| 0.7 \| \| \| [GGUF](https://huggingface.co/mradermacher/CursorCore-Yi-1.5B-LC-GGUF/resolve/main/CursorCore-Yi-1.5B-LC.Q3_K_S.gguf) \| Q3_K_S \| 0.8 \| \| \| [GGUF](https://huggingface.co/mradermacher/CursorCore-Yi-1.5B-LC-GGUF/resolve/main/CursorCore-Yi-1.5B-LC.Q3_K_M.gguf) \| Q3_K_M \| 0.9 \| lower quality \| \| [GGUF](https://huggingface.co/mradermacher/CursorCore-Yi-1.5B-LC-GGUF/resolve/main/CursorCore-Yi-1.5B-LC.Q3_K_L.gguf) \| Q3_K_L \| 0.9 \| \| \| [GGUF](https://huggingface.co/mradermacher/CursorCore-Yi-1.5B-LC-GGUF/resolve/main/CursorCore-Yi-1.5B-LC.IQ4_XS.gguf) \| IQ4_XS \| 0.9 \| \| \| [GGUF](https://huggingface.co/mradermacher/CursorCore-Yi-1.5B-LC-GGUF/resolve/main/CursorCore-Yi-1.5B-LC.Q4_K_S.gguf) \| Q4_K_S \| 1.0 \| fast, recommended \| \| [GGUF](https://huggingface.co/mradermacher/CursorCore-Yi-1.5B-LC-GGUF/resolve/main/CursorCore-Yi-1.5B-LC.Q4_K_M.gguf) \| Q4_K_M \| 1.1 \| fast, recommended \| \| [GGUF](https://huggingface.co/mradermacher/CursorCore-Yi-1.5B-LC-GGUF/resolve/main/CursorCore-Yi-1.5B-LC.Q5_K_S.gguf) \| Q5_K_S \| 1.2 \| \| \| [GGUF](https://huggingface.co/mradermacher/CursorCore-Yi-1.5B-LC-GGUF/resolve/main/CursorCore-Yi-1.5B-LC.Q5_K_M.gguf) \| Q5_K_M \| 1.2 \| \| \| [GGUF](https://huggingface.co/mradermacher/CursorCore-Yi-1.5B-LC-GGUF/resolve/main/CursorCore-Yi-1.5B-LC.Q6_K.gguf) \| Q6_K \| 1.4 \| very good quality \| \| [GGUF](https://huggingface.co/mradermacher/CursorCore-Yi-1.5B-LC-GGUF/resolve/main/CursorCore-Yi-1.5B-LC.Q8_0.gguf) \| Q8_0 \| 1.7 \| fast, best quality \| \| [GGUF](https://huggingface.co/mradermacher/CursorCore-Yi-1.5B-LC-GGUF/resolve/main/CursorCore-Yi-1.5B-LC.f16.gguf) \| f16 \| 3.1 \| 16 bpw, overkill \| Here is a handy graph by ikawrakow comparing some lower-quality quant types (lower is better): ![image.png](https://www.nethype.de/huggingface_embed/quantpplgraph.png) And here are Artefact2's thoughts on the matter: https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9 ## FAQ / Model Request See https://huggingface.co/mradermacher/model_requests for some answers to questions you might have and/or if you want some other model quantized. ## Thanks I thank my company, [nethype GmbH](https://www.nethype.de/), for letting me use its servers and providing upgrades to my workstation to enable this work in my free time. Additional thanks to [@nicoboss](https://huggingface.co/nicoboss) for giving me access to his private supercomputer, enabling me to provide many more imatrix quants, at much higher quality, than I would otherwise be able to. <!-- end -->
mradermacher/CursorCore-Yi-1.5B-LC-i1-GGUF	mradermacher	2024-10-11T07:08:06Z	128	0	transformers	[ "transformers", "gguf", "code", "en", "base_model:TechxGenus/CursorCore-Yi-1.5B-LC", "base_model:quantized:TechxGenus/CursorCore-Yi-1.5B-LC", "license:apache-2.0", "endpoints_compatible", "region:us", "imatrix", "conversational" ]	null	2024-10-11T07:04:11Z	--- base_model: TechxGenus/CursorCore-Yi-1.5B-LC language: - en library_name: transformers license: apache-2.0 quantized_by: mradermacher tags: - code --- ## About <!-- ### quantize_version: 2 --> <!-- ### output_tensor_quantised: 1 --> <!-- ### convert_type: hf --> <!-- ### vocab_type: --> <!-- ### tags: nicoboss --> weighted/imatrix quants of https://huggingface.co/TechxGenus/CursorCore-Yi-1.5B-LC <!-- provided-files --> static quants are available at https://huggingface.co/mradermacher/CursorCore-Yi-1.5B-LC-GGUF ## Usage If you are unsure how to use GGUF files, refer to one of [TheBloke's READMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for more details, including on how to concatenate multi-part files. ## Provided Quants (sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants) \| Link \| Type \| Size/GB \| Notes \| \|:-----\|:-----\|--------:\|:------\| \| [GGUF](https://huggingface.co/mradermacher/CursorCore-Yi-1.5B-LC-i1-GGUF/resolve/main/CursorCore-Yi-1.5B-LC.i1-IQ1_S.gguf) \| i1-IQ1_S \| 0.6 \| for the desperate \| \| [GGUF](https://huggingface.co/mradermacher/CursorCore-Yi-1.5B-LC-i1-GGUF/resolve/main/CursorCore-Yi-1.5B-LC.i1-IQ1_M.gguf) \| i1-IQ1_M \| 0.6 \| mostly desperate \| \| [GGUF](https://huggingface.co/mradermacher/CursorCore-Yi-1.5B-LC-i1-GGUF/resolve/main/CursorCore-Yi-1.5B-LC.i1-IQ2_XXS.gguf) \| i1-IQ2_XXS \| 0.6 \| \| \| [GGUF](https://huggingface.co/mradermacher/CursorCore-Yi-1.5B-LC-i1-GGUF/resolve/main/CursorCore-Yi-1.5B-LC.i1-IQ2_XS.gguf) \| i1-IQ2_XS \| 0.7 \| \| \| [GGUF](https://huggingface.co/mradermacher/CursorCore-Yi-1.5B-LC-i1-GGUF/resolve/main/CursorCore-Yi-1.5B-LC.i1-IQ2_S.gguf) \| i1-IQ2_S \| 0.7 \| \| \| [GGUF](https://huggingface.co/mradermacher/CursorCore-Yi-1.5B-LC-i1-GGUF/resolve/main/CursorCore-Yi-1.5B-LC.i1-IQ2_M.gguf) \| i1-IQ2_M \| 0.7 \| \| \| [GGUF](https://huggingface.co/mradermacher/CursorCore-Yi-1.5B-LC-i1-GGUF/resolve/main/CursorCore-Yi-1.5B-LC.i1-Q2_K.gguf) \| i1-Q2_K \| 0.7 \| IQ3_XXS probably better \| \| [GGUF](https://huggingface.co/mradermacher/CursorCore-Yi-1.5B-LC-i1-GGUF/resolve/main/CursorCore-Yi-1.5B-LC.i1-IQ3_XXS.gguf) \| i1-IQ3_XXS \| 0.8 \| lower quality \| \| [GGUF](https://huggingface.co/mradermacher/CursorCore-Yi-1.5B-LC-i1-GGUF/resolve/main/CursorCore-Yi-1.5B-LC.i1-IQ3_XS.gguf) \| i1-IQ3_XS \| 0.8 \| \| \| [GGUF](https://huggingface.co/mradermacher/CursorCore-Yi-1.5B-LC-i1-GGUF/resolve/main/CursorCore-Yi-1.5B-LC.i1-IQ3_S.gguf) \| i1-IQ3_S \| 0.8 \| beats Q3_K* \| \| [GGUF](https://huggingface.co/mradermacher/CursorCore-Yi-1.5B-LC-i1-GGUF/resolve/main/CursorCore-Yi-1.5B-LC.i1-Q3_K_S.gguf) \| i1-Q3_K_S \| 0.8 \| IQ3_XS probably better \| \| [GGUF](https://huggingface.co/mradermacher/CursorCore-Yi-1.5B-LC-i1-GGUF/resolve/main/CursorCore-Yi-1.5B-LC.i1-IQ3_M.gguf) \| i1-IQ3_M \| 0.9 \| \| \| [GGUF](https://huggingface.co/mradermacher/CursorCore-Yi-1.5B-LC-i1-GGUF/resolve/main/CursorCore-Yi-1.5B-LC.i1-Q3_K_M.gguf) \| i1-Q3_K_M \| 0.9 \| IQ3_S probably better \| \| [GGUF](https://huggingface.co/mradermacher/CursorCore-Yi-1.5B-LC-i1-GGUF/resolve/main/CursorCore-Yi-1.5B-LC.i1-Q3_K_L.gguf) \| i1-Q3_K_L \| 0.9 \| IQ3_M probably better \| \| [GGUF](https://huggingface.co/mradermacher/CursorCore-Yi-1.5B-LC-i1-GGUF/resolve/main/CursorCore-Yi-1.5B-LC.i1-IQ4_XS.gguf) \| i1-IQ4_XS \| 0.9 \| \| \| [GGUF](https://huggingface.co/mradermacher/CursorCore-Yi-1.5B-LC-i1-GGUF/resolve/main/CursorCore-Yi-1.5B-LC.i1-Q4_0_4_4.gguf) \| i1-Q4_0_4_4 \| 1.0 \| fast on arm, low quality \| \| [GGUF](https://huggingface.co/mradermacher/CursorCore-Yi-1.5B-LC-i1-GGUF/resolve/main/CursorCore-Yi-1.5B-LC.i1-Q4_0_4_8.gguf) \| i1-Q4_0_4_8 \| 1.0 \| fast on arm+i8mm, low quality \| \| [GGUF](https://huggingface.co/mradermacher/CursorCore-Yi-1.5B-LC-i1-GGUF/resolve/main/CursorCore-Yi-1.5B-LC.i1-Q4_0_8_8.gguf) \| i1-Q4_0_8_8 \| 1.0 \| fast on arm+sve, low quality \| \| [GGUF](https://huggingface.co/mradermacher/CursorCore-Yi-1.5B-LC-i1-GGUF/resolve/main/CursorCore-Yi-1.5B-LC.i1-Q4_0.gguf) \| i1-Q4_0 \| 1.0 \| fast, low quality \| \| [GGUF](https://huggingface.co/mradermacher/CursorCore-Yi-1.5B-LC-i1-GGUF/resolve/main/CursorCore-Yi-1.5B-LC.i1-Q4_K_S.gguf) \| i1-Q4_K_S \| 1.0 \| optimal size/speed/quality \| \| [GGUF](https://huggingface.co/mradermacher/CursorCore-Yi-1.5B-LC-i1-GGUF/resolve/main/CursorCore-Yi-1.5B-LC.i1-Q4_K_M.gguf) \| i1-Q4_K_M \| 1.1 \| fast, recommended \| \| [GGUF](https://huggingface.co/mradermacher/CursorCore-Yi-1.5B-LC-i1-GGUF/resolve/main/CursorCore-Yi-1.5B-LC.i1-Q5_K_S.gguf) \| i1-Q5_K_S \| 1.2 \| \| \| [GGUF](https://huggingface.co/mradermacher/CursorCore-Yi-1.5B-LC-i1-GGUF/resolve/main/CursorCore-Yi-1.5B-LC.i1-Q5_K_M.gguf) \| i1-Q5_K_M \| 1.2 \| \| \| [GGUF](https://huggingface.co/mradermacher/CursorCore-Yi-1.5B-LC-i1-GGUF/resolve/main/CursorCore-Yi-1.5B-LC.i1-Q6_K.gguf) \| i1-Q6_K \| 1.4 \| practically like static Q6_K \| Here is a handy graph by ikawrakow comparing some lower-quality quant types (lower is better): ![image.png](https://www.nethype.de/huggingface_embed/quantpplgraph.png) And here are Artefact2's thoughts on the matter: https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9 ## FAQ / Model Request See https://huggingface.co/mradermacher/model_requests for some answers to questions you might have and/or if you want some other model quantized. ## Thanks I thank my company, [nethype GmbH](https://www.nethype.de/), for letting me use its servers and providing upgrades to my workstation to enable this work in my free time. Additional thanks to [@nicoboss](https://huggingface.co/nicoboss) for giving me access to his private supercomputer, enabling me to provide many more imatrix quants, at much higher quality, than I would otherwise be able to. <!-- end -->
RUC-AIBOX/policy_1011	RUC-AIBOX	2024-10-11T07:07:11Z	6	0	transformers	[ "transformers", "safetensors", "llama", "text-generation", "conversational", "arxiv:1910.09700", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]	text-generation	2024-10-11T06:11:36Z	--- library_name: transformers tags: [] --- # Model Card for Model ID <!-- Provide a quick summary of what the model is/does. --> ## Model Details ### Model Description <!-- Provide a longer summary of what this model is. --> This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated. - Developed by: [More Information Needed] - Funded by [optional]: [More Information Needed] - Shared by [optional]: [More Information Needed] - Model type: [More Information Needed] - Language(s) (NLP): [More Information Needed] - License: [More Information Needed] - Finetuned from model [optional]: [More Information Needed] ### Model Sources [optional] <!-- Provide the basic links for the model. --> - Repository: [More Information Needed] - Paper [optional]: [More Information Needed] - Demo [optional]: [More Information Needed] ## Uses <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. --> ### Direct Use <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. --> [More Information Needed] ### Downstream Use [optional] <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app --> [More Information Needed] ### Out-of-Scope Use <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. --> [More Information Needed] ## Bias, Risks, and Limitations <!-- This section is meant to convey both technical and sociotechnical limitations. --> [More Information Needed] ### Recommendations <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. --> Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. [More Information Needed] ## Training Details ### Training Data <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. --> [More Information Needed] ### Training Procedure <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. --> #### Preprocessing [optional] [More Information Needed] #### Training Hyperparameters - Training regime: [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision --> #### Speeds, Sizes, Times [optional] <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. --> [More Information Needed] ## Evaluation <!-- This section describes the evaluation protocols and provides the results. --> ### Testing Data, Factors & Metrics #### Testing Data <!-- This should link to a Dataset Card if possible. --> [More Information Needed] #### Factors <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. --> [More Information Needed] #### Metrics <!-- These are the evaluation metrics being used, ideally with a description of why. --> [More Information Needed] ### Results [More Information Needed] #### Summary ## Model Examination [optional] <!-- Relevant interpretability work for the model goes here --> [More Information Needed] ## Environmental Impact <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly --> Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). - Hardware Type: [More Information Needed] - Hours used: [More Information Needed] - Cloud Provider: [More Information Needed] - Compute Region: [More Information Needed] - Carbon Emitted: [More Information Needed] ## Technical Specifications [optional] ### Model Architecture and Objective [More Information Needed] ### Compute Infrastructure [More Information Needed] #### Hardware [More Information Needed] #### Software [More Information Needed] ## Citation [optional] <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. --> BibTeX: [More Information Needed] APA: [More Information Needed] ## Glossary [optional] <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. --> [More Information Needed] ## More Information [optional] [More Information Needed] ## Model Card Authors [optional] [More Information Needed] ## Model Card Contact [More Information Needed]
Saideepthi55/sentencetransformer_ftmodel_on_chemical_dataset	Saideepthi55	2024-10-11T07:03:16Z	5	0	sentence-transformers	[ "sentence-transformers", "safetensors", "mpnet", "sentence-similarity", "feature-extraction", "generated_from_trainer", "dataset_size:117502", "loss:MultipleNegativesRankingLoss", "en", "dataset:SwastikN/sxc_med_llm_chemical_gen", "arxiv:1908.10084", "arxiv:1705.00652", "base_model:microsoft/mpnet-base", "base_model:finetune:microsoft/mpnet-base", "license:apache-2.0", "model-index", "autotrain_compatible", "endpoints_compatible", "region:us" ]	sentence-similarity	2024-10-11T07:02:49Z	--- base_model: microsoft/mpnet-base datasets: - SwastikN/sxc_med_llm_chemical_gen language: - en library_name: sentence-transformers license: apache-2.0 metrics: - cosine_accuracy - dot_accuracy - manhattan_accuracy - euclidean_accuracy - max_accuracy pipeline_tag: sentence-similarity tags: - sentence-transformers - sentence-similarity - feature-extraction - generated_from_trainer - dataset_size:117502 - loss:MultipleNegativesRankingLoss widget: - source_sentence: Help me make the molecule CC(=O)OC[C@H](OC(C)=O)C(=O)N1CCCC[C@H]1C1CCN(C(=O)c2cc3ccccc3n2C)CC1 with the same hydrogen bond donors. The output molecule should be similar to the input molecule. Please inform me of the number of hydrogen bond donor(s) of the optimized molecule. sentences: - Your requirements guided the optimization, resulting in the molecule "CC(=O)OC(CCl)C(Cc1cccs1)[C@H](OC(C)=O)C(=O)N1CCCC[C@H]1C1CCN(C(=O)c2cc3ccccc3n2C)CC1" with an approximate hydrogen bond donor(s) of 0. - Given a molecule expressed in SMILES string, help me optimize it according to my requirements. - Help me adapt a molecular structure denoted in SMILES string based on my preferences. - source_sentence: How can we modify the molecule CCC(CC)=C(CC)c1ccccc1OC(=O)OC(N=[N+]=[N-])c1ccccc1 to decrease its blood-brain barrier penetration (BBBP) value while keeping it similar to the input molecule? Please inform me of the BBBP value of the optimized molecule. sentences: - Describe a technology used for measuring people's emotional responses. - I've successfully optimized the molecule according to your needs, resulting in "CCOC(=O)c1ccccc1OC(=O)OC(N=[N+]=[N-])c1ccccc1" with an approximate BBBP value of 0.71. - Given a molecule expressed in SMILES string, help me optimize it according to my requirements. - source_sentence: How can we modify the molecule C/C(=C/C(=O)N1CC[C@H](CC(CCCCCC(CO)C(=O)O)NC(=O)OC(C)(C)C)[C@H]1c1cccnc1)C(=O)O to increase its blood-brain barrier penetration (BBBP) value while keeping it similar to the input molecule? sentences: - Given a molecule expressed in SMILES string, help me optimize it according to my requirements. - Aid me in refining a molecular structure written in SMILES notation based on my criteria. - Taking your requirements into account, I've optimized the molecule to "C/C(=C/C(=O)N1CC[C@H](CNC(=O)[C@H](CO)NC(=O)OC(C)(C)C)[C@H]1c1cccnc1)C(=O)O". - source_sentence: Support me in transforming the molecule [SMILES] by incorporating the same hydrogen bond acceptors and maintaining its resemblance to the original molecule. sentences: - Taking your requirements into account, I've optimized the molecule to "CCOc1cccc(C2c3c(oc4ccc(C)cc4c3=O)C(=O)N2CCN(CC)CC)c1". - Help me adapt a molecular structure denoted in SMILES string based on my preferences. - Help me adapt a molecular structure denoted in SMILES string based on my preferences. - source_sentence: With a molecule represented by the SMILES string CNNNCC(=O)N[C@H](C)C[C@@H](C)NCc1ccc2c(c1)CCC2, propose adjustments that can increase its logP value while keeping the output molecule structurally related to the input molecule. sentences: - Aid me in refining a molecular structure written in SMILES notation based on my criteria. - Given a molecule expressed in SMILES string, help me optimize it according to my requirements. - In line with your criteria, I've optimized the molecule and present it as "C[C@H](C[C@@H](C)NC(=O)COC(C)(C)C)NCc1ccc2c(c1)CCC2". model-index: - name: MPNet base trained on sxc_med_llm_chemical_gen results: - task: type: triplet name: Triplet dataset: name: sxc med llm chemical gen type: sxc_med_llm_chemical_gen metrics: - type: cosine_accuracy value: 0.9837777777777778 name: Cosine Accuracy - type: dot_accuracy value: 0.01622222222222222 name: Dot Accuracy - type: manhattan_accuracy value: 0.9826666666666667 name: Manhattan Accuracy - type: euclidean_accuracy value: 0.9835555555555555 name: Euclidean Accuracy - type: max_accuracy value: 0.9837777777777778 name: Max Accuracy --- # MPNet base trained on sxc_med_llm_chemical_gen This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [microsoft/mpnet-base](https://huggingface.co/microsoft/mpnet-base) on the [sxc_med_llm_chemical_gen](https://huggingface.co/datasets/SwastikN/sxc_med_llm_chemical_gen) dataset. It maps sentences & paragraphs to a 768-dimensional dense vector space and can be used for semantic textual similarity, semantic search, paraphrase mining, text classification, clustering, and more. ## Model Details ### Model Description - Model Type: Sentence Transformer - Base model: [microsoft/mpnet-base](https://huggingface.co/microsoft/mpnet-base) <!-- at revision 6996ce1e91bd2a9c7d7f61daec37463394f73f09 --> - Maximum Sequence Length: 512 tokens - Output Dimensionality: 768 tokens - Similarity Function: Cosine Similarity - Training Dataset: - [sxc_med_llm_chemical_gen](https://huggingface.co/datasets/SwastikN/sxc_med_llm_chemical_gen) - Language: en - License: apache-2.0 ### Model Sources - Documentation: [Sentence Transformers Documentation](https://sbert.net) - Repository: [Sentence Transformers on GitHub](https://github.com/UKPLab/sentence-transformers) - Hugging Face: [Sentence Transformers on Hugging Face](https://huggingface.co/models?library=sentence-transformers) ### Full Model Architecture ``` SentenceTransformer( (0): Transformer({'max_seq_length': 512, 'do_lower_case': False}) with Transformer model: MPNetModel (1): Pooling({'word_embedding_dimension': 768, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': True, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False, 'include_prompt': True}) ) ``` ## Usage ### Direct Usage (Sentence Transformers) First install the Sentence Transformers library: ```bash pip install -U sentence-transformers ``` Then you can load this model and run inference. ```python from sentence_transformers import SentenceTransformer # Download from the 🤗 Hub model = SentenceTransformer("Saideepthi55/sentencetransformer_ftmodel_on_chemical_dataset") # Run inference sentences = [ 'With a molecule represented by the SMILES string CNNNCC(=O)N[C@H](C)C[C@@H](C)NCc1ccc2c(c1)CCC2, propose adjustments that can increase its logP value while keeping the output molecule structurally related to the input molecule.', 'Given a molecule expressed in SMILES string, help me optimize it according to my requirements.', 'In line with your criteria, I\'ve optimized the molecule and present it as "C[C@H](C[C@@H](C)NC(=O)COC(C)(C)C)NCc1ccc2c(c1)CCC2".', ] embeddings = model.encode(sentences) print(embeddings.shape) # [3, 768] # Get the similarity scores for the embeddings similarities = model.similarity(embeddings, embeddings) print(similarities.shape) # [3, 3] ``` <!-- ### Direct Usage (Transformers) <details><summary>Click to see the direct usage in Transformers</summary> </details> --> <!-- ### Downstream Usage (Sentence Transformers) You can finetune this model on your own dataset. <details><summary>Click to expand</summary> </details> --> <!-- ### Out-of-Scope Use List how the model may foreseeably be misused and address what users ought not to do with the model. --> ## Evaluation ### Metrics #### Triplet * Dataset: `sxc_med_llm_chemical_gen` * Evaluated with [<code>TripletEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.TripletEvaluator) \| Metric \| Value \| \|:-------------------\|:-----------\| \| cosine_accuracy \| 0.9838 \| \| dot_accuracy \| 0.0162 \| \| manhattan_accuracy \| 0.9827 \| \| euclidean_accuracy \| 0.9836 \| \| max_accuracy \| 0.9838 \| <!-- ## Bias, Risks and Limitations What are the known or foreseeable issues stemming from this model? You could also flag here known failure cases or weaknesses of the model. --> <!-- ### Recommendations What are recommendations with respect to the foreseeable issues? For example, filtering explicit content. --> ## Training Details ### Training Dataset #### sxc_med_llm_chemical_gen * Dataset: [sxc_med_llm_chemical_gen](https://huggingface.co/datasets/SwastikN/sxc_med_llm_chemical_gen) at [ae28874](https://huggingface.co/datasets/SwastikN/sxc_med_llm_chemical_gen/tree/ae28874de7084969f9aa310b357ac699dbbafa23) * Size: 117,502 training samples * Columns: <code>input</code>, <code>instruction</code>, and <code>output</code> * Approximate statistics based on the first 1000 samples: \| \| input \| instruction \| output \| \|:--------\|:-----------------------------------------------------------------------------------\|:----------------------------------------------------------------------------------\|:-----------------------------------------------------------------------------------\| \| type \| string \| string \| string \| \| details \| <ul><li>min: 2 tokens</li><li>mean: 50.03 tokens</li><li>max: 156 tokens</li></ul> \| <ul><li>min: 6 tokens</li><li>mean: 16.19 tokens</li><li>max: 69 tokens</li></ul> \| <ul><li>min: 3 tokens</li><li>mean: 67.94 tokens</li><li>max: 321 tokens</li></ul> \| * Samples: \| input \| instruction \| output \| \|:------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------\|:---------------------------------------------------------------------------------------------------\|:----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------\| \| <code></code> \| <code>List the countries of the Middle East</code> \| <code>Egypt, Israel, Iran, Iraq, Jordan, Kuwait, Lebanon, Qatar, Saudi Arabia, Syria, Turkey, The United Arab Emirates, Oman, and Yemen.</code> \| \| <code>Support me in refining the molecule CCC(C)=C(CC)c1ccc(Nc2nc3nonc3nc2N2CCC(Oc3ccc(Cl)cc3)CC2)cc1 to have a more drug-like nature, ensuring it remains close to the input molecule. Please inform me of the QED value of the optimized molecule.</code> \| <code>Help me adapt a molecular structure denoted in SMILES string based on my preferences.</code> \| <code>I've optimized the molecule according to your requirements, yielding the structure "COC(=O)c1ccc(Nc2nc3nonc3nc2N2CCC(Oc3ccc(Cl)cc3)CC2)cc1" and an estimated QED value of 0.4.</code> \| \| <code></code> \| <code>Create a social media strategy to attract followers on Twitter.</code> \| <code>The social media strategy for Twitter should involve Tweeting on a regular basis, with content that is engaging and relevant to the target audience. This can include retweetable quotes, links to videos and articles, sharing photos/images, polls, and so on. It is also beneficial for the information to include hashtags relevant to the content and any relevant topics of the industry. <br><br>It is also important to leverage Twitter influencers and accounts, as well as engaging with potential followers regularly and DM them when necessary. Additionally, running campaigns, contests and giveaways to gain more followers should also be part of the strategy. Finally, hashtag research should be conducted to increase the reach of the tweets.</code> \| * Loss: [<code>MultipleNegativesRankingLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#multiplenegativesrankingloss) with these parameters: ```json { "scale": 20.0, "similarity_fct": "cos_sim" } ``` ### Evaluation Dataset #### sxc_med_llm_chemical_gen * Dataset: [sxc_med_llm_chemical_gen](https://huggingface.co/datasets/SwastikN/sxc_med_llm_chemical_gen) at [ae28874](https://huggingface.co/datasets/SwastikN/sxc_med_llm_chemical_gen/tree/ae28874de7084969f9aa310b357ac699dbbafa23) * Size: 4,500 evaluation samples * Columns: <code>input</code>, <code>instruction</code>, and <code>output</code> * Approximate statistics based on the first 1000 samples: \| \| input \| instruction \| output \| \|:--------\|:-----------------------------------------------------------------------------------\|:----------------------------------------------------------------------------------\|:-----------------------------------------------------------------------------------\| \| type \| string \| string \| string \| \| details \| <ul><li>min: 2 tokens</li><li>mean: 68.49 tokens</li><li>max: 165 tokens</li></ul> \| <ul><li>min: 6 tokens</li><li>mean: 16.89 tokens</li><li>max: 36 tokens</li></ul> \| <ul><li>min: 3 tokens</li><li>mean: 69.16 tokens</li><li>max: 205 tokens</li></ul> \| * Samples: \| input \| instruction \| output \| \|:-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------\|:-------------------------------------------------------------------------------------------------------\|:------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------\| \| <code>With a molecule represented by the SMILES string COc1ccc(CN(C(=O)Nc2ccc([C@H](C#N)c3ccccc3)c(Cl)c2)C2CC2)cc1, propose adjustments that can decrease its blood-brain barrier permeability (BBBP) value by at least 0.1 compared to the pre-optimized value while keeping the output molecule structurally related to the input molecule. Please inform me of the BBBP value of the optimized molecule.</code> \| <code>Help me adapt a molecular structure denoted in SMILES string based on my preferences.</code> \| <code>I've optimized the molecule according to your requirements, yielding the structure "CC(C)c1cccc(Oc2ccc(CN(C(=O)Nc3ccc([C@H](C#N)c4ccccc4)c(Cl)c3)C3CC3)cc2)c1" and an estimated BBBP value of 0.34.</code> \| \| <code>Which modifications can be applied to the molecule Cc1nn(-c2cc3cc(F)ccc3s2)c2ncc(C(=O)N3CCCC3c3nnc4n3CCCCC4)cc12 to increase its water solubility value while ensuring it remains similar to the original molecule?</code> \| <code>Aid me in refining a molecular structure written in SMILES notation based on my criteria.</code> \| <code>I've optimized the molecule according to your requirements, resulting in the following structure: "Cc1nn(C)c2ncc(C(=O)N3CCCC3c3nnc4n3CCCCC4)cc12".</code> \| \| <code></code> \| <code>Describe the benefits of having a mentor.</code> \| <code>Having a mentor can provide tremendous benefits, including guidance, advice, support and connection to a network of contacts. Mentors can offer valuable feedback, help to create goals and strategies, and provide the accountability necessary to carry out the desired goals. They can also provide a fresh perspective which can help to create new ideas and solutions.</code> \| * Loss: [<code>MultipleNegativesRankingLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#multiplenegativesrankingloss) with these parameters: ```json { "scale": 20.0, "similarity_fct": "cos_sim" } ``` ### Training Hyperparameters #### Non-Default Hyperparameters - `eval_strategy`: steps - `per_device_train_batch_size`: 16 - `per_device_eval_batch_size`: 16 - `learning_rate`: 2e-05 - `num_train_epochs`: 1 - `warmup_ratio`: 0.1 - `fp16`: True #### All Hyperparameters <details><summary>Click to expand</summary> - `overwrite_output_dir`: False - `do_predict`: False - `eval_strategy`: steps - `prediction_loss_only`: True - `per_device_train_batch_size`: 16 - `per_device_eval_batch_size`: 16 - `per_gpu_train_batch_size`: None - `per_gpu_eval_batch_size`: None - `gradient_accumulation_steps`: 1 - `eval_accumulation_steps`: None - `torch_empty_cache_steps`: None - `learning_rate`: 2e-05 - `weight_decay`: 0.0 - `adam_beta1`: 0.9 - `adam_beta2`: 0.999 - `adam_epsilon`: 1e-08 - `max_grad_norm`: 1.0 - `num_train_epochs`: 1 - `max_steps`: -1 - `lr_scheduler_type`: linear - `lr_scheduler_kwargs`: {} - `warmup_ratio`: 0.1 - `warmup_steps`: 0 - `log_level`: passive - `log_level_replica`: warning - `log_on_each_node`: True - `logging_nan_inf_filter`: True - `save_safetensors`: True - `save_on_each_node`: False - `save_only_model`: False - `restore_callback_states_from_checkpoint`: False - `no_cuda`: False - `use_cpu`: False - `use_mps_device`: False - `seed`: 42 - `data_seed`: None - `jit_mode_eval`: False - `use_ipex`: False - `bf16`: False - `fp16`: True - `fp16_opt_level`: O1 - `half_precision_backend`: auto - `bf16_full_eval`: False - `fp16_full_eval`: False - `tf32`: None - `local_rank`: 0 - `ddp_backend`: None - `tpu_num_cores`: None - `tpu_metrics_debug`: False - `debug`: [] - `dataloader_drop_last`: False - `dataloader_num_workers`: 0 - `dataloader_prefetch_factor`: None - `past_index`: -1 - `disable_tqdm`: False - `remove_unused_columns`: True - `label_names`: None - `load_best_model_at_end`: False - `ignore_data_skip`: False - `fsdp`: [] - `fsdp_min_num_params`: 0 - `fsdp_config`: {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False} - `fsdp_transformer_layer_cls_to_wrap`: None - `accelerator_config`: {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None} - `deepspeed`: None - `label_smoothing_factor`: 0.0 - `optim`: adamw_torch - `optim_args`: None - `adafactor`: False - `group_by_length`: False - `length_column_name`: length - `ddp_find_unused_parameters`: None - `ddp_bucket_cap_mb`: None - `ddp_broadcast_buffers`: False - `dataloader_pin_memory`: True - `dataloader_persistent_workers`: False - `skip_memory_metrics`: True - `use_legacy_prediction_loop`: False - `push_to_hub`: False - `resume_from_checkpoint`: None - `hub_model_id`: None - `hub_strategy`: every_save - `hub_private_repo`: False - `hub_always_push`: False - `gradient_checkpointing`: False - `gradient_checkpointing_kwargs`: None - `include_inputs_for_metrics`: False - `eval_do_concat_batches`: True - `fp16_backend`: auto - `push_to_hub_model_id`: None - `push_to_hub_organization`: None - `mp_parameters`: - `auto_find_batch_size`: False - `full_determinism`: False - `torchdynamo`: None - `ray_scope`: last - `ddp_timeout`: 1800 - `torch_compile`: False - `torch_compile_backend`: None - `torch_compile_mode`: None - `dispatch_batches`: None - `split_batches`: None - `include_tokens_per_second`: False - `include_num_input_tokens_seen`: False - `neftune_noise_alpha`: None - `optim_target_modules`: None - `batch_eval_metrics`: False - `eval_on_start`: False - `eval_use_gather_object`: False - `batch_sampler`: batch_sampler - `multi_dataset_batch_sampler`: proportional </details> ### Training Logs \| Epoch \| Step \| Training Loss \| Validation Loss \| sxc_med_llm_chemical_gen_max_accuracy \| \|:------:\|:----:\|:-------------:\|:---------------:\|:-------------------------------------:\| \| 0 \| 0 \| - \| - \| 0.7076 \| \| 0.0136 \| 100 \| 4.1705 \| 3.6314 \| 0.7469 \| \| 0.0272 \| 200 \| 3.0088 \| 2.4771 \| 0.8191 \| \| 0.0408 \| 300 \| 2.3803 \| 2.3765 \| 0.8716 \| \| 0.0545 \| 400 \| 2.2281 \| 2.3122 \| 0.9316 \| \| 0.0681 \| 500 \| 2.1647 \| 2.2997 \| 0.9436 \| \| 0.0817 \| 600 \| 2.1289 \| 2.2663 \| 0.9511 \| \| 0.0953 \| 700 \| 2.0663 \| 2.2601 \| 0.9629 \| \| 0.1089 \| 800 \| 2.065 \| 2.2500 \| 0.9687 \| \| 0.1225 \| 900 \| 2.0399 \| 2.2595 \| 0.9693 \| \| 0.1362 \| 1000 \| 1.9939 \| 2.2375 \| 0.9707 \| \| 0.1498 \| 1100 \| 1.9858 \| 2.2220 \| 0.9684 \| \| 0.1634 \| 1200 \| 2.0069 \| 2.2265 \| 0.9758 \| \| 0.1770 \| 1300 \| 1.9591 \| 2.2073 \| 0.9702 \| \| 0.1906 \| 1400 \| 1.9288 \| 2.2078 \| 0.976 \| \| 0.2042 \| 1500 \| 1.9466 \| 2.2036 \| 0.9758 \| \| 0.2179 \| 1600 \| 1.9175 \| 2.2086 \| 0.9764 \| \| 0.2315 \| 1700 \| 1.8835 \| 2.2329 \| 0.9796 \| \| 0.2451 \| 1800 \| 1.9134 \| 2.2003 \| 0.9796 \| \| 0.2587 \| 1900 \| 1.8809 \| 2.2003 \| 0.9811 \| \| 0.2723 \| 2000 \| 1.9263 \| 2.2039 \| 0.9824 \| \| 0.2859 \| 2100 \| 1.9101 \| 2.2084 \| 0.9804 \| \| 0.2996 \| 2200 \| 1.8846 \| 2.2052 \| 0.9831 \| \| 0.3132 \| 2300 \| 1.8842 \| 2.1903 \| 0.9818 \| \| 0.3268 \| 2400 \| 1.8945 \| 2.1984 \| 0.9807 \| \| 0.3404 \| 2500 \| 1.9217 \| 2.1859 \| 0.9829 \| \| 0.3540 \| 2600 \| 1.8704 \| 2.1995 \| 0.982 \| \| 0.3676 \| 2700 \| 1.889 \| 2.2038 \| 0.9822 \| \| 0.3813 \| 2800 \| 1.875 \| 2.2079 \| 0.9829 \| \| 0.3949 \| 2900 \| 1.8792 \| 2.1975 \| 0.9833 \| \| 0.4085 \| 3000 \| 1.882 \| 2.1895 \| 0.9796 \| \| 0.4221 \| 3100 \| 1.8886 \| 2.2115 \| 0.9831 \| \| 0.4357 \| 3200 \| 1.8629 \| 2.2040 \| 0.9838 \| \| 0.4493 \| 3300 \| 1.8647 \| 2.1973 \| 0.9836 \| \| 0.4630 \| 3400 \| 1.8888 \| 2.1961 \| 0.9838 \| \| 0.4766 \| 3500 \| 1.8692 \| 2.2027 \| 0.9829 \| \| 0.4902 \| 3600 \| 1.8846 \| 2.1954 \| 0.9838 \| \| 0.5038 \| 3700 \| 1.8482 \| 2.1888 \| 0.9822 \| \| 0.5174 \| 3800 \| 1.8527 \| 2.1873 \| 0.9824 \| \| 0.5310 \| 3900 \| 1.8378 \| 2.1940 \| 0.9811 \| \| 0.5447 \| 4000 \| 1.8679 \| 2.2008 \| 0.9833 \| \| 0.5583 \| 4100 \| 1.8421 \| 2.1845 \| 0.9842 \| \| 0.5719 \| 4200 \| 1.8325 \| 2.1948 \| 0.9847 \| \| 0.5855 \| 4300 \| 1.8675 \| 2.1750 \| 0.9836 \| \| 0.5991 \| 4400 \| 1.8483 \| 2.1828 \| 0.9831 \| \| 0.6127 \| 4500 \| 1.854 \| 2.1886 \| 0.9831 \| \| 0.6264 \| 4600 \| 1.827 \| 2.1876 \| 0.9824 \| \| 0.6400 \| 4700 \| 1.8863 \| 2.1849 \| 0.9836 \| \| 0.6536 \| 4800 \| 1.8919 \| 2.1816 \| 0.984 \| \| 0.6672 \| 4900 \| 1.8211 \| 2.1830 \| 0.9847 \| \| 0.6808 \| 5000 \| 1.8345 \| 2.1847 \| 0.9842 \| \| 0.6944 \| 5100 \| 1.8685 \| 2.1855 \| 0.9853 \| \| 0.7081 \| 5200 \| 1.85 \| 2.1864 \| 0.9844 \| \| 0.7217 \| 5300 \| 1.8222 \| 2.1875 \| 0.9842 \| \| 0.7353 \| 5400 \| 1.8179 \| 2.1923 \| 0.9844 \| \| 0.7489 \| 5500 \| 1.7992 \| 2.1909 \| 0.9851 \| \| 0.7625 \| 5600 \| 1.8495 \| 2.1811 \| 0.9847 \| \| 0.7761 \| 5700 \| 1.808 \| 2.1763 \| 0.9842 \| \| 0.7898 \| 5800 \| 1.8293 \| 2.1861 \| 0.9849 \| \| 0.8034 \| 5900 \| 1.8184 \| 2.1845 \| 0.9851 \| \| 0.8170 \| 6000 \| 1.8256 \| 2.1956 \| 0.9849 \| \| 0.8306 \| 6100 \| 1.7904 \| 2.1916 \| 0.9842 \| \| 0.8442 \| 6200 \| 1.8028 \| 2.1918 \| 0.9847 \| \| 0.8578 \| 6300 \| 1.8316 \| 2.1917 \| 0.9856 \| \| 0.8715 \| 6400 \| 1.7951 \| 2.1929 \| 0.9851 \| \| 0.8851 \| 6500 \| 1.8175 \| 2.1866 \| 0.9847 \| \| 0.8987 \| 6600 \| 1.8071 \| 2.1899 \| 0.9853 \| \| 0.9123 \| 6700 \| 1.8632 \| 2.1905 \| 0.9844 \| \| 0.9259 \| 6800 \| 1.8441 \| 2.1885 \| 0.984 \| \| 0.9395 \| 6900 \| 1.8243 \| 2.1865 \| 0.9836 \| \| 0.9532 \| 7000 \| 1.8055 \| 2.1852 \| 0.9842 \| \| 0.9668 \| 7100 \| 1.8227 \| 2.1843 \| 0.984 \| \| 0.9804 \| 7200 \| 1.8287 \| 2.1831 \| 0.984 \| \| 0.9940 \| 7300 \| 1.8379 \| 2.1838 \| 0.9838 \| ### Framework Versions - Python: 3.10.12 - Sentence Transformers: 3.2.0 - Transformers: 4.44.2 - PyTorch: 2.4.1+cu121 - Accelerate: 0.34.2 - Datasets: 3.0.1 - Tokenizers: 0.19.1 ## Citation ### BibTeX #### Sentence Transformers ```bibtex @inproceedings{reimers-2019-sentence-bert, title = "Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks", author = "Reimers, Nils and Gurevych, Iryna", booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing", month = "11", year = "2019", publisher = "Association for Computational Linguistics", url = "https://arxiv.org/abs/1908.10084", } ``` #### MultipleNegativesRankingLoss ```bibtex @misc{henderson2017efficient, title={Efficient Natural Language Response Suggestion for Smart Reply}, author={Matthew Henderson and Rami Al-Rfou and Brian Strope and Yun-hsuan Sung and Laszlo Lukacs and Ruiqi Guo and Sanjiv Kumar and Balint Miklos and Ray Kurzweil}, year={2017}, eprint={1705.00652}, archivePrefix={arXiv}, primaryClass={cs.CL} } ``` <!-- ## Glossary Clearly define terms in order to be accessible across audiences. --> <!-- ## Model Card Authors Lists the people who create the model card, providing recognition and accountability for the detailed work that goes into its construction. --> <!-- ## Model Card Contact Provides a way for people who have updates to the Model Card, suggestions, or questions, to contact the Model Card authors. -->
iokimao/livetech02	iokimao	2024-10-11T07:00:06Z	5	0	null	[ "gguf", "llama", "license:apache-2.0", "endpoints_compatible", "region:us" ]	null	2024-09-27T13:11:54Z	--- license: apache-2.0 ---
KSU-HW-SEC/Power	KSU-HW-SEC	2024-10-11T06:53:28Z	6	0	transformers	[ "transformers", "safetensors", "llama", "text-generation", "llama-factory", "conversational", "arxiv:1910.09700", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]	text-generation	2024-10-11T06:50:14Z	--- library_name: transformers tags: - llama-factory --- # Model Card for Model ID <!-- Provide a quick summary of what the model is/does. --> ## Model Details ### Model Description <!-- Provide a longer summary of what this model is. --> This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated. - Developed by: [More Information Needed] - Funded by [optional]: [More Information Needed] - Shared by [optional]: [More Information Needed] - Model type: [More Information Needed] - Language(s) (NLP): [More Information Needed] - License: [More Information Needed] - Finetuned from model [optional]: [More Information Needed] ### Model Sources [optional] <!-- Provide the basic links for the model. --> - Repository: [More Information Needed] - Paper [optional]: [More Information Needed] - Demo [optional]: [More Information Needed] ## Uses <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. --> ### Direct Use <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. --> [More Information Needed] ### Downstream Use [optional] <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app --> [More Information Needed] ### Out-of-Scope Use <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. --> [More Information Needed] ## Bias, Risks, and Limitations <!-- This section is meant to convey both technical and sociotechnical limitations. --> [More Information Needed] ### Recommendations <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. --> Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. [More Information Needed] ## Training Details ### Training Data <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. --> [More Information Needed] ### Training Procedure <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. --> #### Preprocessing [optional] [More Information Needed] #### Training Hyperparameters - Training regime: [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision --> #### Speeds, Sizes, Times [optional] <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. --> [More Information Needed] ## Evaluation <!-- This section describes the evaluation protocols and provides the results. --> ### Testing Data, Factors & Metrics #### Testing Data <!-- This should link to a Dataset Card if possible. --> [More Information Needed] #### Factors <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. --> [More Information Needed] #### Metrics <!-- These are the evaluation metrics being used, ideally with a description of why. --> [More Information Needed] ### Results [More Information Needed] #### Summary ## Model Examination [optional] <!-- Relevant interpretability work for the model goes here --> [More Information Needed] ## Environmental Impact <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly --> Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). - Hardware Type: [More Information Needed] - Hours used: [More Information Needed] - Cloud Provider: [More Information Needed] - Compute Region: [More Information Needed] - Carbon Emitted: [More Information Needed] ## Technical Specifications [optional] ### Model Architecture and Objective [More Information Needed] ### Compute Infrastructure [More Information Needed] #### Hardware [More Information Needed] #### Software [More Information Needed] ## Citation [optional] <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. --> BibTeX: [More Information Needed] APA: [More Information Needed] ## Glossary [optional] <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. --> [More Information Needed] ## More Information [optional] [More Information Needed] ## Model Card Authors [optional] [More Information Needed] ## Model Card Contact [More Information Needed]
QuantFactory/functionary-small-v2.2-GGUF	QuantFactory	2024-10-11T06:53:20Z	15	2	transformers	[ "transformers", "gguf", "text-generation", "endpoints_compatible", "region:us", "conversational" ]	text-generation	2024-10-11T06:17:18Z	--- pipeline_tag: text-generation base_model: functionary-small-v2.2 library_name: transformers --- [![QuantFactory Banner](https://lh7-rt.googleusercontent.com/docsz/AD_4nXeiuCm7c8lEwEJuRey9kiVZsRn2W-b4pWlu3-X534V3YmVuVc2ZL-NXg2RkzSOOS2JXGHutDuyyNAUtdJI65jGTo8jT9Y99tMi4H4MqL44Uc5QKG77B0d6-JfIkZHFaUA71-RtjyYZWVIhqsNZcx8-OMaA?key=xt3VSDoCbmTY7o-cwwOFwQ)](https://hf.co/QuantFactory) # QuantFactory/functionary-small-v2.2-GGUF This is quantized version of [meetkai/functionary-small-v2.2](https://huggingface.co/meetkai/functionary-small-v2.2) created using llama.cpp # Original Model Card # Model Card for functionary-small-v2.2 [https://github.com/MeetKai/functionary](https://github.com/MeetKai/functionary) ![Functionary Logo](https://huggingface.co/meetkai/functionary-medium-v2.2/resolve/main/functionary_logo.jpg "Functionary Logo") Functionary is a language model that can interpret and execute functions/plugins. The model determines when to execute functions, whether in parallel or serially, and can understand their outputs. It only triggers functions as needed. Function definitions are given as JSON Schema Objects, similar to OpenAI GPT function calls. ## Key Features - Intelligent parallel tool use - Able to analyze functions/tools outputs and provide relevant responses grounded in the outputs - Able to decide when to not use tools/call functions and provide normal chat response - Truly one of the best open-source alternative to GPT-4 ## Performance Our model achieves achieves state-of-the-art performance in Function Calling Accuracy on our in-house dataset. The accuracy metric measures the overall correctness of predicted function calls, including function name prediction and arguments extraction. ![Eval Chart](https://huggingface.co/meetkai/functionary-medium-v2.2/resolve/main/evaluation_chart.jpeg "Eval Chart") \| Dataset \| Model Name \| Function Calling Accuracy (Name & Arguments) \| \| :-------------\| :-------------------\| ---------------------------: \| \| In-house data \| MeetKai-functionary-small-v2.2 \| 0.546\| \| In-house data \| MeetKai-functionary-medium-v2.2 \| 0.664\| \| In-house data \| OpenAI-gpt-3.5-turbo-1106 \| 0.531 \| \| In-house data \| OpenAI-gpt-4-1106-preview \| 0.737 \| ## Prompt Template We use a specially designed prompt template which we call "v2PromptTemplate" that breaks down each turns into from, recipient and content portions. We convert function definitions to a similar text to TypeScript definitions. Then we inject these definitions as system prompts. After that, we inject the default system prompt. Then we start the conversation messages. This formatting is also available via our vLLM server which we process the functions into Typescript definitions encapsulated in a system message and use a pre-defined Transformers chat template. This means that lists of messages can be formatted for you with the apply_chat_template() method within our server: ```python from openai import OpenAI client = OpenAI(base_url="http://localhost:8000/v1", api_key="functionary") client.chat.completions.create( model="path/to/functionary/model/", messages=[{"role": "user", "content": "What is the weather for Istanbul?"} ], tools=[{ "type": "function", "function": { "name": "get_current_weather", "description": "Get the current weather", "parameters": { "type": "object", "properties": { "location": { "type": "string", "description": "The city and state, e.g. San Francisco, CA" } }, "required": ["location"] } } }], tool_choice="auto" ) ``` will yield: ``` <\|from\|>system <\|recipient\|>all <\|content\|>// Supported function definitions that should be called when necessary. namespace functions { // Get the current weather type get_current_weather = (_: { // The city and state, e.g. San Francisco, CA location: string, }) => any; } // namespace functions <\|from\|>system <\|recipient\|>all <\|content\|>A chat between a curious user and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the user's questions. The assistant calls functions with appropriate input when necessary <\|from\|>user <\|recipient\|>all <\|content\|>What is the weather for Istanbul? ``` A more detailed example is provided [here](https://github.com/MeetKai/functionary/blob/main/tests/prompt_test_v2.txt). ## Run the model We encourage users to run our models using our OpenAI-compatible vLLM server [here](https://github.com/MeetKai/functionary). # The MeetKai Team ![MeetKai Logo](https://huggingface.co/meetkai/functionary-medium-v2.2/resolve/main/meetkai_logo.png "MeetKai Logo")
KSU-HW-SEC/Power_SFT	KSU-HW-SEC	2024-10-11T06:49:24Z	11	0	transformers	[ "transformers", "safetensors", "mistral", "text-generation", "llama-factory", "conversational", "arxiv:1910.09700", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]	text-generation	2024-10-11T06:46:05Z	--- library_name: transformers tags: - llama-factory --- # Model Card for Model ID <!-- Provide a quick summary of what the model is/does. --> ## Model Details ### Model Description <!-- Provide a longer summary of what this model is. --> This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated. - Developed by: [More Information Needed] - Funded by [optional]: [More Information Needed] - Shared by [optional]: [More Information Needed] - Model type: [More Information Needed] - Language(s) (NLP): [More Information Needed] - License: [More Information Needed] - Finetuned from model [optional]: [More Information Needed] ### Model Sources [optional] <!-- Provide the basic links for the model. --> - Repository: [More Information Needed] - Paper [optional]: [More Information Needed] - Demo [optional]: [More Information Needed] ## Uses <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. --> ### Direct Use <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. --> [More Information Needed] ### Downstream Use [optional] <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app --> [More Information Needed] ### Out-of-Scope Use <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. --> [More Information Needed] ## Bias, Risks, and Limitations <!-- This section is meant to convey both technical and sociotechnical limitations. --> [More Information Needed] ### Recommendations <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. --> Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. [More Information Needed] ## Training Details ### Training Data <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. --> [More Information Needed] ### Training Procedure <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. --> #### Preprocessing [optional] [More Information Needed] #### Training Hyperparameters - Training regime: [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision --> #### Speeds, Sizes, Times [optional] <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. --> [More Information Needed] ## Evaluation <!-- This section describes the evaluation protocols and provides the results. --> ### Testing Data, Factors & Metrics #### Testing Data <!-- This should link to a Dataset Card if possible. --> [More Information Needed] #### Factors <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. --> [More Information Needed] #### Metrics <!-- These are the evaluation metrics being used, ideally with a description of why. --> [More Information Needed] ### Results [More Information Needed] #### Summary ## Model Examination [optional] <!-- Relevant interpretability work for the model goes here --> [More Information Needed] ## Environmental Impact <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly --> Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). - Hardware Type: [More Information Needed] - Hours used: [More Information Needed] - Cloud Provider: [More Information Needed] - Compute Region: [More Information Needed] - Carbon Emitted: [More Information Needed] ## Technical Specifications [optional] ### Model Architecture and Objective [More Information Needed] ### Compute Infrastructure [More Information Needed] #### Hardware [More Information Needed] #### Software [More Information Needed] ## Citation [optional] <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. --> BibTeX: [More Information Needed] APA: [More Information Needed] ## Glossary [optional] <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. --> [More Information Needed] ## More Information [optional] [More Information Needed] ## Model Card Authors [optional] [More Information Needed] ## Model Card Contact [More Information Needed]
borno1/WSDD_x	borno1	2024-10-11T06:42:18Z	29	0	diffusers	[ "diffusers", "safetensors", "text-to-image", "license:creativeml-openrail-m", "autotrain_compatible", "endpoints_compatible", "diffusers:StableDiffusionPipeline", "region:us" ]	text-to-image	2024-10-11T06:41:10Z	--- license: creativeml-openrail-m tags: - text-to-image --- ### tecaher-sdv1-5-epochs-8000 on Stable Diffusion via Dreambooth #### model by borno1 This your the Stable Diffusion model fine-tuned the tecaher-sdv1-5-epochs-8000 concept taught to Stable Diffusion with Dreambooth. It can be used by modifying the `instance_prompt`: flower You can also train your own concepts and upload them to the library by using [this notebook](https://colab.research.google.com/github/huggingface/notebooks/blob/main/diffusers/sd_dreambooth_training.ipynb). And you can run your new concept via `diffusers`: [Colab Notebook for Inference](https://colab.research.google.com/github/huggingface/notebooks/blob/main/diffusers/sd_dreambooth_inference.ipynb), [Spaces with the Public Concepts loaded](https://huggingface.co/spaces/sd-dreambooth-library/stable-diffusion-dreambooth-concepts) Here are the images used for training this concept:
CheeLi03/whisper-ar	CheeLi03	2024-10-11T06:42:15Z	5	0	null	[ "tensorboard", "safetensors", "whisper", "hf-asr-leaderboard", "generated_from_trainer", "ar", "dataset:fleurs", "base_model:openai/whisper-small", "base_model:finetune:openai/whisper-small", "license:apache-2.0", "model-index", "region:us" ]	null	2024-10-11T03:57:57Z	--- base_model: openai/whisper-small datasets: - fleurs language: - ar license: apache-2.0 metrics: - wer tags: - hf-asr-leaderboard - generated_from_trainer model-index: - name: Whisper Small - Chee Li results: - task: type: automatic-speech-recognition name: Automatic Speech Recognition dataset: name: Google Fleurs type: fleurs config: ar_eg split: None args: 'config: ar split: test' metrics: - type: wer value: 35.462500000000006 name: Wer --- <!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # Whisper Small - Chee Li This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on the Google Fleurs dataset. It achieves the following results on the evaluation set: - Loss: 0.4791 - Wer: 35.4625 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 1e-05 - train_batch_size: 16 - eval_batch_size: 8 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - lr_scheduler_warmup_steps: 500 - training_steps: 4000 - mixed_precision_training: Native AMP ### Training results \| Training Loss \| Epoch \| Step \| Validation Loss \| Wer \| \|:-------------:\|:-------:\|:----:\|:---------------:\|:-------:\| \| 0.0147 \| 6.6667 \| 1000 \| 0.3868 \| 34.5125 \| \| 0.0009 \| 13.3333 \| 2000 \| 0.4417 \| 36.6375 \| \| 0.0004 \| 20.0 \| 3000 \| 0.4693 \| 35.5625 \| \| 0.0003 \| 26.6667 \| 4000 \| 0.4791 \| 35.4625 \| ### Framework versions - Transformers 4.44.0 - Pytorch 2.3.1+cu121 - Datasets 2.21.0 - Tokenizers 0.19.1
KSU-HW-SEC/Area_Time_SFT	KSU-HW-SEC	2024-10-11T06:41:04Z	6	0	transformers	[ "transformers", "safetensors", "mistral", "text-generation", "llama-factory", "conversational", "arxiv:1910.09700", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]	text-generation	2024-10-11T06:37:16Z	--- library_name: transformers tags: - llama-factory --- # Model Card for Model ID <!-- Provide a quick summary of what the model is/does. --> ## Model Details ### Model Description <!-- Provide a longer summary of what this model is. --> This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated. - Developed by: [More Information Needed] - Funded by [optional]: [More Information Needed] - Shared by [optional]: [More Information Needed] - Model type: [More Information Needed] - Language(s) (NLP): [More Information Needed] - License: [More Information Needed] - Finetuned from model [optional]: [More Information Needed] ### Model Sources [optional] <!-- Provide the basic links for the model. --> - Repository: [More Information Needed] - Paper [optional]: [More Information Needed] - Demo [optional]: [More Information Needed] ## Uses <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. --> ### Direct Use <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. --> [More Information Needed] ### Downstream Use [optional] <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app --> [More Information Needed] ### Out-of-Scope Use <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. --> [More Information Needed] ## Bias, Risks, and Limitations <!-- This section is meant to convey both technical and sociotechnical limitations. --> [More Information Needed] ### Recommendations <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. --> Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. [More Information Needed] ## Training Details ### Training Data <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. --> [More Information Needed] ### Training Procedure <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. --> #### Preprocessing [optional] [More Information Needed] #### Training Hyperparameters - Training regime: [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision --> #### Speeds, Sizes, Times [optional] <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. --> [More Information Needed] ## Evaluation <!-- This section describes the evaluation protocols and provides the results. --> ### Testing Data, Factors & Metrics #### Testing Data <!-- This should link to a Dataset Card if possible. --> [More Information Needed] #### Factors <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. --> [More Information Needed] #### Metrics <!-- These are the evaluation metrics being used, ideally with a description of why. --> [More Information Needed] ### Results [More Information Needed] #### Summary ## Model Examination [optional] <!-- Relevant interpretability work for the model goes here --> [More Information Needed] ## Environmental Impact <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly --> Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). - Hardware Type: [More Information Needed] - Hours used: [More Information Needed] - Cloud Provider: [More Information Needed] - Compute Region: [More Information Needed] - Carbon Emitted: [More Information Needed] ## Technical Specifications [optional] ### Model Architecture and Objective [More Information Needed] ### Compute Infrastructure [More Information Needed] #### Hardware [More Information Needed] #### Software [More Information Needed] ## Citation [optional] <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. --> BibTeX: [More Information Needed] APA: [More Information Needed] ## Glossary [optional] <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. --> [More Information Needed] ## More Information [optional] [More Information Needed] ## Model Card Authors [optional] [More Information Needed] ## Model Card Contact [More Information Needed]
KSU-HW-SEC/Area	KSU-HW-SEC	2024-10-11T06:36:24Z	5	0	transformers	[ "transformers", "safetensors", "llama", "text-generation", "llama-factory", "conversational", "arxiv:1910.09700", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]	text-generation	2024-10-11T06:33:05Z	--- library_name: transformers tags: - llama-factory --- # Model Card for Model ID <!-- Provide a quick summary of what the model is/does. --> ## Model Details ### Model Description <!-- Provide a longer summary of what this model is. --> This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated. - Developed by: [More Information Needed] - Funded by [optional]: [More Information Needed] - Shared by [optional]: [More Information Needed] - Model type: [More Information Needed] - Language(s) (NLP): [More Information Needed] - License: [More Information Needed] - Finetuned from model [optional]: [More Information Needed] ### Model Sources [optional] <!-- Provide the basic links for the model. --> - Repository: [More Information Needed] - Paper [optional]: [More Information Needed] - Demo [optional]: [More Information Needed] ## Uses <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. --> ### Direct Use <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. --> [More Information Needed] ### Downstream Use [optional] <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app --> [More Information Needed] ### Out-of-Scope Use <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. --> [More Information Needed] ## Bias, Risks, and Limitations <!-- This section is meant to convey both technical and sociotechnical limitations. --> [More Information Needed] ### Recommendations <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. --> Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. [More Information Needed] ## Training Details ### Training Data <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. --> [More Information Needed] ### Training Procedure <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. --> #### Preprocessing [optional] [More Information Needed] #### Training Hyperparameters - Training regime: [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision --> #### Speeds, Sizes, Times [optional] <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. --> [More Information Needed] ## Evaluation <!-- This section describes the evaluation protocols and provides the results. --> ### Testing Data, Factors & Metrics #### Testing Data <!-- This should link to a Dataset Card if possible. --> [More Information Needed] #### Factors <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. --> [More Information Needed] #### Metrics <!-- These are the evaluation metrics being used, ideally with a description of why. --> [More Information Needed] ### Results [More Information Needed] #### Summary ## Model Examination [optional] <!-- Relevant interpretability work for the model goes here --> [More Information Needed] ## Environmental Impact <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly --> Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). - Hardware Type: [More Information Needed] - Hours used: [More Information Needed] - Cloud Provider: [More Information Needed] - Compute Region: [More Information Needed] - Carbon Emitted: [More Information Needed] ## Technical Specifications [optional] ### Model Architecture and Objective [More Information Needed] ### Compute Infrastructure [More Information Needed] #### Hardware [More Information Needed] #### Software [More Information Needed] ## Citation [optional] <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. --> BibTeX: [More Information Needed] APA: [More Information Needed] ## Glossary [optional] <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. --> [More Information Needed] ## More Information [optional] [More Information Needed] ## Model Card Authors [optional] [More Information Needed] ## Model Card Contact [More Information Needed]
bky373/spring-assistant	bky373	2024-10-11T06:34:54Z	5	0	null	[ "safetensors", "gemma", "license:apache-2.0", "4-bit", "bitsandbytes", "region:us" ]	null	2024-10-03T21:38:29Z	--- license: apache-2.0 --- ## Spring Assistant - https://github.com/bky373/spring-assistant?tab=readme-ov-file#spring-assistant
mradermacher/Llama3.2-3B-Anvita-Instruct-GGUF	mradermacher	2024-10-11T06:32:06Z	12	0	transformers	[ "transformers", "gguf", "mergekit", "merge", "en", "base_model:sethuiyer/Llama3.2-3B-Anvita-Instruct", "base_model:quantized:sethuiyer/Llama3.2-3B-Anvita-Instruct", "endpoints_compatible", "region:us", "conversational" ]	null	2024-10-11T06:24:33Z	--- base_model: sethuiyer/Llama3.2-3B-Anvita-Instruct language: - en library_name: transformers quantized_by: mradermacher tags: - mergekit - merge --- ## About <!-- ### quantize_version: 2 --> <!-- ### output_tensor_quantised: 1 --> <!-- ### convert_type: hf --> <!-- ### vocab_type: --> <!-- ### tags: --> static quants of https://huggingface.co/sethuiyer/Llama3.2-3B-Anvita-Instruct <!-- provided-files --> weighted/imatrix quants seem not to be available (by me) at this time. If they do not show up a week or so after the static ones, I have probably not planned for them. Feel free to request them by opening a Community Discussion. ## Usage If you are unsure how to use GGUF files, refer to one of [TheBloke's READMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for more details, including on how to concatenate multi-part files. ## Provided Quants (sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants) \| Link \| Type \| Size/GB \| Notes \| \|:-----\|:-----\|--------:\|:------\| \| [GGUF](https://huggingface.co/mradermacher/Llama3.2-3B-Anvita-Instruct-GGUF/resolve/main/Llama3.2-3B-Anvita-Instruct.Q2_K.gguf) \| Q2_K \| 1.6 \| \| \| [GGUF](https://huggingface.co/mradermacher/Llama3.2-3B-Anvita-Instruct-GGUF/resolve/main/Llama3.2-3B-Anvita-Instruct.Q3_K_S.gguf) \| Q3_K_S \| 1.8 \| \| \| [GGUF](https://huggingface.co/mradermacher/Llama3.2-3B-Anvita-Instruct-GGUF/resolve/main/Llama3.2-3B-Anvita-Instruct.Q3_K_M.gguf) \| Q3_K_M \| 2.0 \| lower quality \| \| [GGUF](https://huggingface.co/mradermacher/Llama3.2-3B-Anvita-Instruct-GGUF/resolve/main/Llama3.2-3B-Anvita-Instruct.Q3_K_L.gguf) \| Q3_K_L \| 2.1 \| \| \| [GGUF](https://huggingface.co/mradermacher/Llama3.2-3B-Anvita-Instruct-GGUF/resolve/main/Llama3.2-3B-Anvita-Instruct.IQ4_XS.gguf) \| IQ4_XS \| 2.2 \| \| \| [GGUF](https://huggingface.co/mradermacher/Llama3.2-3B-Anvita-Instruct-GGUF/resolve/main/Llama3.2-3B-Anvita-Instruct.Q4_K_S.gguf) \| Q4_K_S \| 2.2 \| fast, recommended \| \| [GGUF](https://huggingface.co/mradermacher/Llama3.2-3B-Anvita-Instruct-GGUF/resolve/main/Llama3.2-3B-Anvita-Instruct.Q4_K_M.gguf) \| Q4_K_M \| 2.3 \| fast, recommended \| \| [GGUF](https://huggingface.co/mradermacher/Llama3.2-3B-Anvita-Instruct-GGUF/resolve/main/Llama3.2-3B-Anvita-Instruct.Q5_K_S.gguf) \| Q5_K_S \| 2.6 \| \| \| [GGUF](https://huggingface.co/mradermacher/Llama3.2-3B-Anvita-Instruct-GGUF/resolve/main/Llama3.2-3B-Anvita-Instruct.Q5_K_M.gguf) \| Q5_K_M \| 2.7 \| \| \| [GGUF](https://huggingface.co/mradermacher/Llama3.2-3B-Anvita-Instruct-GGUF/resolve/main/Llama3.2-3B-Anvita-Instruct.Q6_K.gguf) \| Q6_K \| 3.1 \| very good quality \| \| [GGUF](https://huggingface.co/mradermacher/Llama3.2-3B-Anvita-Instruct-GGUF/resolve/main/Llama3.2-3B-Anvita-Instruct.Q8_0.gguf) \| Q8_0 \| 3.9 \| fast, best quality \| \| [GGUF](https://huggingface.co/mradermacher/Llama3.2-3B-Anvita-Instruct-GGUF/resolve/main/Llama3.2-3B-Anvita-Instruct.f16.gguf) \| f16 \| 7.3 \| 16 bpw, overkill \| Here is a handy graph by ikawrakow comparing some lower-quality quant types (lower is better): ![image.png](https://www.nethype.de/huggingface_embed/quantpplgraph.png) And here are Artefact2's thoughts on the matter: https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9 ## FAQ / Model Request See https://huggingface.co/mradermacher/model_requests for some answers to questions you might have and/or if you want some other model quantized. ## Thanks I thank my company, [nethype GmbH](https://www.nethype.de/), for letting me use its servers and providing upgrades to my workstation to enable this work in my free time. <!-- end -->
pranavajay/animated	pranavajay	2024-10-11T06:29:05Z	6	0	diffusers	[ "diffusers", "text-to-image", "stable-diffusion", "lora", "fluxpipeline", "flux", "base_model:black-forest-labs/FLUX.1-dev", "base_model:adapter:black-forest-labs/FLUX.1-dev", "license:creativeml-openrail-m", "region:us" ]	text-to-image	2024-10-11T06:26:23Z	--- tags: - text-to-image - stable-diffusion - lora - diffusers - fluxpipeline - flux base_model: black-forest-labs/FLUX.1-dev license: creativeml-openrail-m pipeline_tag: text-to-image ---
Rasooli/Bert-Sentiment-Fa	Rasooli	2024-10-11T06:29:01Z	21	0	transformers	[ "transformers", "tensorboard", "safetensors", "roberta", "text-classification", "generated_from_trainer", "base_model:dadashzadeh/roberta-sentiment-persian", "base_model:finetune:dadashzadeh/roberta-sentiment-persian", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "region:us" ]	text-classification	2024-09-05T04:06:26Z	--- library_name: transformers license: apache-2.0 base_model: dadashzadeh/roberta-sentiment-persian tags: - generated_from_trainer metrics: - accuracy - f1 model-index: - name: Bert-Sentiment-Fa results: [] --- <!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # Bert-Sentiment-Fa This model is a fine-tuned version of [dadashzadeh/roberta-sentiment-persian](https://huggingface.co/dadashzadeh/roberta-sentiment-persian) on the None dataset. It achieves the following results on the evaluation set: - Loss: 1.2509 - Accuracy: 0.8333 - F1: 0.8213 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 2e-05 - train_batch_size: 8 - eval_batch_size: 8 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - num_epochs: 10 ### Training results \| Training Loss \| Epoch \| Step \| Validation Loss \| Accuracy \| F1 \| \|:-------------:\|:-----:\|:----:\|:---------------:\|:--------:\|:------:\| \| No log \| 1.0 \| 270 \| 0.4689 \| 0.8208 \| 0.8081 \| \| 0.4419 \| 2.0 \| 540 \| 0.7073 \| 0.8042 \| 0.7840 \| \| 0.4419 \| 3.0 \| 810 \| 0.7497 \| 0.8042 \| 0.7820 \| \| 0.1823 \| 4.0 \| 1080 \| 0.9258 \| 0.8167 \| 0.7981 \| \| 0.1823 \| 5.0 \| 1350 \| 1.0813 \| 0.8042 \| 0.7897 \| \| 0.0742 \| 6.0 \| 1620 \| 1.1488 \| 0.8042 \| 0.7866 \| \| 0.0742 \| 7.0 \| 1890 \| 1.2846 \| 0.8167 \| 0.8023 \| \| 0.0311 \| 8.0 \| 2160 \| 1.2308 \| 0.8333 \| 0.8193 \| \| 0.0311 \| 9.0 \| 2430 \| 1.2446 \| 0.8333 \| 0.8193 \| \| 0.0108 \| 10.0 \| 2700 \| 1.2509 \| 0.8333 \| 0.8213 \| ### Framework versions - Transformers 4.44.2 - Pytorch 2.4.1+cu121 - Datasets 3.0.1 - Tokenizers 0.19.1
ojigrande/ppo-Huggy	ojigrande	2024-10-11T06:18:57Z	11	0	ml-agents	[ "ml-agents", "tensorboard", "onnx", "Huggy", "deep-reinforcement-learning", "reinforcement-learning", "ML-Agents-Huggy", "region:us" ]	reinforcement-learning	2024-10-11T06:18:20Z	--- library_name: ml-agents tags: - Huggy - deep-reinforcement-learning - reinforcement-learning - ML-Agents-Huggy --- # ppo Agent playing Huggy This is a trained model of a ppo agent playing Huggy using the [Unity ML-Agents Library](https://github.com/Unity-Technologies/ml-agents). ## Usage (with ML-Agents) The Documentation: https://unity-technologies.github.io/ml-agents/ML-Agents-Toolkit-Documentation/ We wrote a complete tutorial to learn to train your first agent using ML-Agents and publish it to the Hub: - A short tutorial where you teach Huggy the Dog 🐶 to fetch the stick and then play with him directly in your browser: https://huggingface.co/learn/deep-rl-course/unitbonus1/introduction - A longer tutorial to understand how works ML-Agents: https://huggingface.co/learn/deep-rl-course/unit5/introduction ### Resume the training ```bash mlagents-learn <your_configuration_file_path.yaml> --run-id=<run_id> --resume ``` ### Watch your Agent play You can watch your agent playing directly in your browser 1. If the environment is part of ML-Agents official environments, go to https://huggingface.co/unity 2. Step 1: Find your model_id: ojigrande/ppo-Huggy 3. Step 2: Select your .nn /.onnx file 4. Click on Watch the agent play 👀
leenag/whisper-small-poula	leenag	2024-10-11T06:13:34Z	6	0	transformers	[ "transformers", "tensorboard", "safetensors", "whisper", "automatic-speech-recognition", "generated_from_trainer", "pmx", "dataset:iitd-duk/paula", "base_model:openai/whisper-small", "base_model:finetune:openai/whisper-small", "license:apache-2.0", "model-index", "endpoints_compatible", "region:us" ]	automatic-speech-recognition	2024-10-11T04:45:43Z	--- library_name: transformers language: - pmx license: apache-2.0 base_model: openai/whisper-small tags: - generated_from_trainer datasets: - iitd-duk/paula metrics: - wer model-index: - name: Whisper-Small-paula results: - task: name: Automatic Speech Recognition type: automatic-speech-recognition dataset: name: Paula type: iitd-duk/paula metrics: - name: Wer type: wer value: 97.75910364145658 --- <!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # Whisper-Small-paula This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on the Paula dataset. It achieves the following results on the evaluation set: - Loss: 2.7488 - Wer: 97.7591 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 1e-05 - train_batch_size: 12 - eval_batch_size: 8 - seed: 42 - optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments - lr_scheduler_type: linear - lr_scheduler_warmup_steps: 100 - training_steps: 500 - mixed_precision_training: Native AMP ### Training results \| Training Loss \| Epoch \| Step \| Validation Loss \| Wer \| \|:-------------:\|:-----:\|:----:\|:---------------:\|:--------:\| \| 0.1 \| 5.0 \| 100 \| 2.4980 \| 131.0924 \| \| 0.0249 \| 10.0 \| 200 \| 2.5853 \| 97.7591 \| \| 0.0065 \| 15.0 \| 300 \| 2.6842 \| 98.0392 \| \| 0.0026 \| 20.0 \| 400 \| 2.7265 \| 96.9188 \| \| 0.0016 \| 25.0 \| 500 \| 2.7488 \| 97.7591 \| ### Framework versions - Transformers 4.46.0.dev0 - Pytorch 2.4.1+cu121 - Datasets 3.0.1 - Tokenizers 0.20.1
QuantFactory/OpenHathi-7B-Hi-v0.1-Base-GGUF	QuantFactory	2024-10-11T05:59:21Z	52	1	null	[ "gguf", "hi", "license:llama2", "endpoints_compatible", "region:us" ]	null	2024-10-11T05:25:02Z	--- license: llama2 language: - hi --- [![QuantFactory Banner](https://lh7-rt.googleusercontent.com/docsz/AD_4nXeiuCm7c8lEwEJuRey9kiVZsRn2W-b4pWlu3-X534V3YmVuVc2ZL-NXg2RkzSOOS2JXGHutDuyyNAUtdJI65jGTo8jT9Y99tMi4H4MqL44Uc5QKG77B0d6-JfIkZHFaUA71-RtjyYZWVIhqsNZcx8-OMaA?key=xt3VSDoCbmTY7o-cwwOFwQ)](https://hf.co/QuantFactory) # QuantFactory/OpenHathi-7B-Hi-v0.1-Base-GGUF This is quantized version of [sarvamai/OpenHathi-7B-Hi-v0.1-Base](https://huggingface.co/sarvamai/OpenHathi-7B-Hi-v0.1-Base) created using llama.cpp # Original Model Card This repository is the first model in the OpenHathi series of models that will be released by Sarvam AI. This is a 7B parameter, based on Llama2, trained on Hindi, English, and Hinglish. More details about the model, its training procedure, and evaluations can be found [here](https://www.sarvam.ai/blog/announcing-openhathi-series). Note: this is a base model and not meant to be used as is. We recommend first finetuning it on task(s) you are interested in. ``` # Usage import torch from transformers import LlamaTokenizer, LlamaForCausalLM tokenizer = LlamaTokenizer.from_pretrained('sarvamai/OpenHathi-7B-Hi-v0.1-Base') model = LlamaForCausalLM.from_pretrained('sarvamai/OpenHathi-7B-Hi-v0.1-Base', torch_dtype=torch.bfloat16) prompt = "मैं एक अच्छा हाथी हूँ" inputs = tokenizer(prompt, return_tensors="pt") # Generate generate_ids = model.generate(inputs.input_ids, max_length=30) tokenizer.batch_decode(generate_ids, skip_special_tokens=True, clean_up_tokenization_spaces=False)[0] ```
quancute/phobert-base-v2-ner-ghtk-ai-fluent-segmented-21-label-new-data-3090-11Obt-1	quancute	2024-10-11T05:52:36Z	128	0	transformers	[ "transformers", "safetensors", "roberta", "token-classification", "arxiv:1910.09700", "autotrain_compatible", "endpoints_compatible", "region:us" ]	token-classification	2024-10-11T05:46:44Z	--- library_name: transformers tags: [] --- # Model Card for Model ID <!-- Provide a quick summary of what the model is/does. --> ## Model Details ### Model Description <!-- Provide a longer summary of what this model is. --> This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated. - Developed by: [More Information Needed] - Funded by [optional]: [More Information Needed] - Shared by [optional]: [More Information Needed] - Model type: [More Information Needed] - Language(s) (NLP): [More Information Needed] - License: [More Information Needed] - Finetuned from model [optional]: [More Information Needed] ### Model Sources [optional] <!-- Provide the basic links for the model. --> - Repository: [More Information Needed] - Paper [optional]: [More Information Needed] - Demo [optional]: [More Information Needed] ## Uses <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. --> ### Direct Use <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. --> [More Information Needed] ### Downstream Use [optional] <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app --> [More Information Needed] ### Out-of-Scope Use <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. --> [More Information Needed] ## Bias, Risks, and Limitations <!-- This section is meant to convey both technical and sociotechnical limitations. --> [More Information Needed] ### Recommendations <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. --> Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. [More Information Needed] ## Training Details ### Training Data <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. --> [More Information Needed] ### Training Procedure <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. --> #### Preprocessing [optional] [More Information Needed] #### Training Hyperparameters - Training regime: [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision --> #### Speeds, Sizes, Times [optional] <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. --> [More Information Needed] ## Evaluation <!-- This section describes the evaluation protocols and provides the results. --> ### Testing Data, Factors & Metrics #### Testing Data <!-- This should link to a Dataset Card if possible. --> [More Information Needed] #### Factors <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. --> [More Information Needed] #### Metrics <!-- These are the evaluation metrics being used, ideally with a description of why. --> [More Information Needed] ### Results [More Information Needed] #### Summary ## Model Examination [optional] <!-- Relevant interpretability work for the model goes here --> [More Information Needed] ## Environmental Impact <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly --> Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). - Hardware Type: [More Information Needed] - Hours used: [More Information Needed] - Cloud Provider: [More Information Needed] - Compute Region: [More Information Needed] - Carbon Emitted: [More Information Needed] ## Technical Specifications [optional] ### Model Architecture and Objective [More Information Needed] ### Compute Infrastructure [More Information Needed] #### Hardware [More Information Needed] #### Software [More Information Needed] ## Citation [optional] <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. --> BibTeX: [More Information Needed] APA: [More Information Needed] ## Glossary [optional] <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. --> [More Information Needed] ## More Information [optional] [More Information Needed] ## Model Card Authors [optional] [More Information Needed] ## Model Card Contact [More Information Needed]
RichardErkhov/Infinirc_-_Llama-3.1-Infinirc-8B-Instruct-gguf	RichardErkhov	2024-10-11T05:40:38Z	7	0	null	[ "gguf", "endpoints_compatible", "region:us", "conversational" ]	null	2024-10-11T03:15:50Z	Quantization made by Richard Erkhov. [Github](https://github.com/RichardErkhov) [Discord](https://discord.gg/pvy7H8DZMG) [Request more models](https://github.com/RichardErkhov/quant_request) Llama-3.1-Infinirc-8B-Instruct - GGUF - Model creator: https://huggingface.co/Infinirc/ - Original model: https://huggingface.co/Infinirc/Llama-3.1-Infinirc-8B-Instruct/ \| Name \| Quant method \| Size \| \| ---- \| ---- \| ---- \| \| [Llama-3.1-Infinirc-8B-Instruct.Q2_K.gguf](https://huggingface.co/RichardErkhov/Infinirc_-_Llama-3.1-Infinirc-8B-Instruct-gguf/blob/main/Llama-3.1-Infinirc-8B-Instruct.Q2_K.gguf) \| Q2_K \| 2.96GB \| \| [Llama-3.1-Infinirc-8B-Instruct.IQ3_XS.gguf](https://huggingface.co/RichardErkhov/Infinirc_-_Llama-3.1-Infinirc-8B-Instruct-gguf/blob/main/Llama-3.1-Infinirc-8B-Instruct.IQ3_XS.gguf) \| IQ3_XS \| 3.28GB \| \| [Llama-3.1-Infinirc-8B-Instruct.IQ3_S.gguf](https://huggingface.co/RichardErkhov/Infinirc_-_Llama-3.1-Infinirc-8B-Instruct-gguf/blob/main/Llama-3.1-Infinirc-8B-Instruct.IQ3_S.gguf) \| IQ3_S \| 3.43GB \| \| [Llama-3.1-Infinirc-8B-Instruct.Q3_K_S.gguf](https://huggingface.co/RichardErkhov/Infinirc_-_Llama-3.1-Infinirc-8B-Instruct-gguf/blob/main/Llama-3.1-Infinirc-8B-Instruct.Q3_K_S.gguf) \| Q3_K_S \| 3.41GB \| \| [Llama-3.1-Infinirc-8B-Instruct.IQ3_M.gguf](https://huggingface.co/RichardErkhov/Infinirc_-_Llama-3.1-Infinirc-8B-Instruct-gguf/blob/main/Llama-3.1-Infinirc-8B-Instruct.IQ3_M.gguf) \| IQ3_M \| 3.52GB \| \| [Llama-3.1-Infinirc-8B-Instruct.Q3_K.gguf](https://huggingface.co/RichardErkhov/Infinirc_-_Llama-3.1-Infinirc-8B-Instruct-gguf/blob/main/Llama-3.1-Infinirc-8B-Instruct.Q3_K.gguf) \| Q3_K \| 3.74GB \| \| [Llama-3.1-Infinirc-8B-Instruct.Q3_K_M.gguf](https://huggingface.co/RichardErkhov/Infinirc_-_Llama-3.1-Infinirc-8B-Instruct-gguf/blob/main/Llama-3.1-Infinirc-8B-Instruct.Q3_K_M.gguf) \| Q3_K_M \| 3.74GB \| \| [Llama-3.1-Infinirc-8B-Instruct.Q3_K_L.gguf](https://huggingface.co/RichardErkhov/Infinirc_-_Llama-3.1-Infinirc-8B-Instruct-gguf/blob/main/Llama-3.1-Infinirc-8B-Instruct.Q3_K_L.gguf) \| Q3_K_L \| 4.03GB \| \| [Llama-3.1-Infinirc-8B-Instruct.IQ4_XS.gguf](https://huggingface.co/RichardErkhov/Infinirc_-_Llama-3.1-Infinirc-8B-Instruct-gguf/blob/main/Llama-3.1-Infinirc-8B-Instruct.IQ4_XS.gguf) \| IQ4_XS \| 4.18GB \| \| [Llama-3.1-Infinirc-8B-Instruct.Q4_0.gguf](https://huggingface.co/RichardErkhov/Infinirc_-_Llama-3.1-Infinirc-8B-Instruct-gguf/blob/main/Llama-3.1-Infinirc-8B-Instruct.Q4_0.gguf) \| Q4_0 \| 4.34GB \| \| [Llama-3.1-Infinirc-8B-Instruct.IQ4_NL.gguf](https://huggingface.co/RichardErkhov/Infinirc_-_Llama-3.1-Infinirc-8B-Instruct-gguf/blob/main/Llama-3.1-Infinirc-8B-Instruct.IQ4_NL.gguf) \| IQ4_NL \| 4.38GB \| \| [Llama-3.1-Infinirc-8B-Instruct.Q4_K_S.gguf](https://huggingface.co/RichardErkhov/Infinirc_-_Llama-3.1-Infinirc-8B-Instruct-gguf/blob/main/Llama-3.1-Infinirc-8B-Instruct.Q4_K_S.gguf) \| Q4_K_S \| 4.37GB \| \| [Llama-3.1-Infinirc-8B-Instruct.Q4_K.gguf](https://huggingface.co/RichardErkhov/Infinirc_-_Llama-3.1-Infinirc-8B-Instruct-gguf/blob/main/Llama-3.1-Infinirc-8B-Instruct.Q4_K.gguf) \| Q4_K \| 4.58GB \| \| [Llama-3.1-Infinirc-8B-Instruct.Q4_K_M.gguf](https://huggingface.co/RichardErkhov/Infinirc_-_Llama-3.1-Infinirc-8B-Instruct-gguf/blob/main/Llama-3.1-Infinirc-8B-Instruct.Q4_K_M.gguf) \| Q4_K_M \| 4.58GB \| \| [Llama-3.1-Infinirc-8B-Instruct.Q4_1.gguf](https://huggingface.co/RichardErkhov/Infinirc_-_Llama-3.1-Infinirc-8B-Instruct-gguf/blob/main/Llama-3.1-Infinirc-8B-Instruct.Q4_1.gguf) \| Q4_1 \| 4.78GB \| \| [Llama-3.1-Infinirc-8B-Instruct.Q5_0.gguf](https://huggingface.co/RichardErkhov/Infinirc_-_Llama-3.1-Infinirc-8B-Instruct-gguf/blob/main/Llama-3.1-Infinirc-8B-Instruct.Q5_0.gguf) \| Q5_0 \| 5.21GB \| \| [Llama-3.1-Infinirc-8B-Instruct.Q5_K_S.gguf](https://huggingface.co/RichardErkhov/Infinirc_-_Llama-3.1-Infinirc-8B-Instruct-gguf/blob/main/Llama-3.1-Infinirc-8B-Instruct.Q5_K_S.gguf) \| Q5_K_S \| 5.21GB \| \| [Llama-3.1-Infinirc-8B-Instruct.Q5_K.gguf](https://huggingface.co/RichardErkhov/Infinirc_-_Llama-3.1-Infinirc-8B-Instruct-gguf/blob/main/Llama-3.1-Infinirc-8B-Instruct.Q5_K.gguf) \| Q5_K \| 5.34GB \| \| [Llama-3.1-Infinirc-8B-Instruct.Q5_K_M.gguf](https://huggingface.co/RichardErkhov/Infinirc_-_Llama-3.1-Infinirc-8B-Instruct-gguf/blob/main/Llama-3.1-Infinirc-8B-Instruct.Q5_K_M.gguf) \| Q5_K_M \| 5.34GB \| \| [Llama-3.1-Infinirc-8B-Instruct.Q5_1.gguf](https://huggingface.co/RichardErkhov/Infinirc_-_Llama-3.1-Infinirc-8B-Instruct-gguf/blob/main/Llama-3.1-Infinirc-8B-Instruct.Q5_1.gguf) \| Q5_1 \| 5.65GB \| \| [Llama-3.1-Infinirc-8B-Instruct.Q6_K.gguf](https://huggingface.co/RichardErkhov/Infinirc_-_Llama-3.1-Infinirc-8B-Instruct-gguf/blob/main/Llama-3.1-Infinirc-8B-Instruct.Q6_K.gguf) \| Q6_K \| 6.14GB \| \| [Llama-3.1-Infinirc-8B-Instruct.Q8_0.gguf](https://huggingface.co/RichardErkhov/Infinirc_-_Llama-3.1-Infinirc-8B-Instruct-gguf/blob/main/Llama-3.1-Infinirc-8B-Instruct.Q8_0.gguf) \| Q8_0 \| 7.95GB \| Original model description: --- license: llama3.1 language: - zh - en library_name: transformers tags: - zhtw --- # Infinirc/Llama-3.1-Infinirc-8B-Instruct ## 模型詳情開發者：陳昭儒[Infinirc.com](https://infinirc.com) 模型版本：1.0 模型類型：自然語言處理訓練數據源：采用與台灣文化相關的資料集，包括台灣新聞、文學作品、網路文章等。 ## 目的和用途這款Llama3 8B模型是專門為了更好地理解和生成與台灣文化相關的文本而設計和微調的。目標是提供一個能夠捕捉台灣特有文化元素和語言習慣的強大語言模型，適用於文本生成、自動回答等多種應用。 ## 模型架構基礎模型：Llama3 8B 調整策略：對模型進行微調，使用與台灣文化相關的具體資料集進行微調，以增強模型對於本地化內容的理解和生成能力。 ## 性能指標該模型在一系列NLP基準測試中展示了優異的性能，特別是在文本生成和語意理解方面具有較高的準確度。具體性能數據：(詳述BLEU分數、ROUGE分數等性能數據) ## 使用和限制使用建議：推薦於需要深度理解或生成與台灣文化相關內容的應用場景中使用。限制：雖然模型針對台灣文化進行了特定優化，但在處理非目標區域的文化內容時可能效果不佳。 ## 風險與倫理考量使用本模型時應注意確保生成的內容不包含歧視性或有害信息。模型的開發和使用應遵循倫理準則和社會責任。 ## 聯絡方式如有任何問題或需要進一步的信息，請透過下方聯絡方式與我們團隊聯繫： Email: [[email protected]](mailto:[email protected]) 網站: [https://infinirc.com](https://infinirc.com)
general-preference/SPPO-Llama-3-8B-Instruct-GPM-2B	general-preference	2024-10-11T05:33:36Z	6	1	null	[ "safetensors", "llama", "text-generation", "conversational", "en", "dataset:openbmb/UltraFeedback", "arxiv:2410.02197", "arxiv:2405.00675", "license:apache-2.0", "model-index", "region:us" ]	text-generation	2024-10-08T03:18:00Z	--- language: - en license: apache-2.0 datasets: - openbmb/UltraFeedback pipeline_tag: text-generation model-index: - name: SPPO-Llama-3-8B-Instruct-GPM-2B results: - task: type: text-generation name: Text Generation dataset: name: IFEval (0-Shot) type: HuggingFaceH4/ifeval args: num_few_shot: 0 metrics: - type: inst_level_strict_acc and prompt_level_strict_acc value: 60.24 name: strict accuracy source: url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=general-preference/SPPO-Llama-3-8B-Instruct-GPM-2B name: Open LLM Leaderboard - task: type: text-generation name: Text Generation dataset: name: BBH (3-Shot) type: BBH args: num_few_shot: 3 metrics: - type: acc_norm value: 27.89 name: normalized accuracy source: url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=general-preference/SPPO-Llama-3-8B-Instruct-GPM-2B name: Open LLM Leaderboard - task: type: text-generation name: Text Generation dataset: name: MATH Lvl 5 (4-Shot) type: hendrycks/competition_math args: num_few_shot: 4 metrics: - type: exact_match value: 8.01 name: exact match source: url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=general-preference/SPPO-Llama-3-8B-Instruct-GPM-2B name: Open LLM Leaderboard - task: type: text-generation name: Text Generation dataset: name: GPQA (0-shot) type: Idavidrein/gpqa args: num_few_shot: 0 metrics: - type: acc_norm value: 1.23 name: acc_norm source: url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=general-preference/SPPO-Llama-3-8B-Instruct-GPM-2B name: Open LLM Leaderboard - task: type: text-generation name: Text Generation dataset: name: MuSR (0-shot) type: TAUR-Lab/MuSR args: num_few_shot: 0 metrics: - type: acc_norm value: 3.19 name: acc_norm source: url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=general-preference/SPPO-Llama-3-8B-Instruct-GPM-2B name: Open LLM Leaderboard - task: type: text-generation name: Text Generation dataset: name: MMLU-PRO (5-shot) type: TIGER-Lab/MMLU-Pro config: main split: test args: num_few_shot: 5 metrics: - type: acc value: 29.53 name: accuracy source: url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=general-preference/SPPO-Llama-3-8B-Instruct-GPM-2B name: Open LLM Leaderboard --- General Preference Modeling with Preference Representations for Aligning Language Models (https://arxiv.org/abs/2410.02197) # SPPO-Llama-3-8B-Instruct-GPM-2B This model was developed using [SPPO](https://arxiv.org/abs/2405.00675) at iteration 3 and the [General Preference representation Model (GPM)](https://arxiv.org/abs/2410.02197) (specifically, using [GPM-Gemma-2B](https://huggingface.co/general-preference/GPM-Gemma-2B)), based on the [meta-llama/Meta-Llama-3-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct) architecture as starting point. We utilized the prompt sets from the [openbmb/UltraFeedback](https://huggingface.co/datasets/openbmb/UltraFeedback) dataset, splited to 3 parts for 3 iterations by [snorkelai/Snorkel-Mistral-PairRM-DPO-Dataset](https://huggingface.co/datasets/snorkelai/Snorkel-Mistral-PairRM-DPO-Dataset). All responses used are synthetic. ## Links to Other Models - [SPPO-Llama-3-8B-Instruct-GPM-2B](https://huggingface.co/general-preference/SPPO-Llama-3-8B-Instruct-GPM-2B) - [GPO-Llama-3-8B-Instruct-GPM-2B](https://huggingface.co/general-preference/GPO-Llama-3-8B-Instruct-GPM-2B) ### Model Description - Model type: A 8B parameter GPT-like model fine-tuned on synthetic datasets. - Language(s) (NLP): Primarily English - License: Apache-2.0 - Finetuned from model: meta-llama/Meta-Llama-3-8B-Instruct ## [AlpacaEval Leaderboard Evaluation Results](https://tatsu-lab.github.io/alpaca_eval/) \| Model \| LC. Win Rate \| Win Rate \| Avg. Length \| \|-------------------------------------------\|:------------:\|:--------:\|:-----------:\| \|[SPPO-Llama-3-8B-Instruct-GPM-2B](https://huggingface.co/general-preference/SPPO-Llama-3-8B-Instruct-GPM-2B) \|35.30 \| 45.44 \| 2490 ## [Open LLM Leaderboard Evaluation Results](https://github.com/EleutherAI/lm-evaluation-harness) Results are reported by using [lm-evaluation-harness](https://github.com/EleutherAI/lm-evaluation-harness) v0.4.1 \| \| arc_challenge \| truthfulqa_mc2 \| winogrande \| gsm8k \| hellaswag \| mmlu \| average \| \|--------\|---------------\|----------------\|------------\|-------\|-----------\|-------\|---------\| \|[SPPO-Llama-3-8B-Instruct-GPM-2B](https://huggingface.co/general-preference/SPPO-Llama-3-8B-Instruct-GPM-2B) \| 62.03 \| 52.95 \| 76.56 \| 75.36 \| 78.57 \| 65.66 \| 68.52 ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 5e-07 - eta: 1000 - per_device_train_batch_size: 8 - gradient_accumulation_steps: 1 - seed: 42 - distributed_type: deepspeed_zero3 - num_devices: 8 - optimizer: RMSProp - lr_scheduler_type: linear - lr_scheduler_warmup_ratio: 0.1 - num_train_epochs: 6.0 (stop at epoch=1.0) ## Citation ``` @article{zhang2024general, title={General Preference Modeling with Preference Representations for Aligning Language Models}, author={Zhang, Yifan and Zhang, Ge and Wu, Yue and Xu, Kangping and Gu, Quanquan}, journal={arXiv preprint arXiv:2410.02197}, year={2024} } ```
QuantFactory/Flammades-Mistral-7B-GGUF	QuantFactory	2024-10-11T05:08:12Z	38	1	transformers	[ "transformers", "gguf", "dataset:flammenai/Date-DPO-NoAsterisks", "dataset:jondurbin/truthy-dpo-v0.1", "base_model:nbeerbower/Hermes2-Gutenberg2-Mistral-7B", "base_model:quantized:nbeerbower/Hermes2-Gutenberg2-Mistral-7B", "license:apache-2.0", "endpoints_compatible", "region:us", "conversational" ]	null	2024-10-11T04:30:53Z	--- library_name: transformers base_model: - nbeerbower/Hermes2-Gutenberg2-Mistral-7B datasets: - flammenai/Date-DPO-NoAsterisks - jondurbin/truthy-dpo-v0.1 license: apache-2.0 --- [![QuantFactory Banner](https://lh7-rt.googleusercontent.com/docsz/AD_4nXeiuCm7c8lEwEJuRey9kiVZsRn2W-b4pWlu3-X534V3YmVuVc2ZL-NXg2RkzSOOS2JXGHutDuyyNAUtdJI65jGTo8jT9Y99tMi4H4MqL44Uc5QKG77B0d6-JfIkZHFaUA71-RtjyYZWVIhqsNZcx8-OMaA?key=xt3VSDoCbmTY7o-cwwOFwQ)](https://hf.co/QuantFactory) # QuantFactory/Flammades-Mistral-7B-GGUF This is quantized version of [flammenai/Flammades-Mistral-7B](https://huggingface.co/flammenai/Flammades-Mistral-7B) created using llama.cpp # Original Model Card # Flammades-Mistral-7B [nbeerbower/Hermes2-Gutenberg2-Mistral-7B](https://huggingface.co/nbeerbower/Hermes2-Gutenberg2-Mistral-7B) finetuned on [flammenai/Date-DPO-NoAsterisks](https://huggingface.co/datasets/flammenai/Date-DPO-NoAsterisks) and [jondurbin/truthy-dpo-v0.1](https://huggingface.co/datasets/jondurbin/truthy-dpo-v0.1). ### Method [ORPO tuned](https://mlabonne.github.io/blog/posts/2024-04-19_Fine_tune_Llama_3_with_ORPO.html) with 2x RTX 3090 for 3 epochs.
zeon8985army/IndonesiaLukasLargeV3	zeon8985army	2024-10-11T05:05:10Z	61	0	transformers	[ "transformers", "safetensors", "whisper", "automatic-speech-recognition", "arxiv:1910.09700", "endpoints_compatible", "region:us" ]	automatic-speech-recognition	2024-10-11T04:47:42Z	--- library_name: transformers tags: [] --- # Model Card for Model ID <!-- Provide a quick summary of what the model is/does. --> ## Model Details ### Model Description <!-- Provide a longer summary of what this model is. --> This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated. - Developed by: [More Information Needed] - Funded by [optional]: [More Information Needed] - Shared by [optional]: [More Information Needed] - Model type: [More Information Needed] - Language(s) (NLP): [More Information Needed] - License: [More Information Needed] - Finetuned from model [optional]: [More Information Needed] ### Model Sources [optional] <!-- Provide the basic links for the model. --> - Repository: [More Information Needed] - Paper [optional]: [More Information Needed] - Demo [optional]: [More Information Needed] ## Uses <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. --> ### Direct Use <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. --> [More Information Needed] ### Downstream Use [optional] <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app --> [More Information Needed] ### Out-of-Scope Use <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. --> [More Information Needed] ## Bias, Risks, and Limitations <!-- This section is meant to convey both technical and sociotechnical limitations. --> [More Information Needed] ### Recommendations <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. --> Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. [More Information Needed] ## Training Details ### Training Data <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. --> [More Information Needed] ### Training Procedure <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. --> #### Preprocessing [optional] [More Information Needed] #### Training Hyperparameters - Training regime: [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision --> #### Speeds, Sizes, Times [optional] <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. --> [More Information Needed] ## Evaluation <!-- This section describes the evaluation protocols and provides the results. --> ### Testing Data, Factors & Metrics #### Testing Data <!-- This should link to a Dataset Card if possible. --> [More Information Needed] #### Factors <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. --> [More Information Needed] #### Metrics <!-- These are the evaluation metrics being used, ideally with a description of why. --> [More Information Needed] ### Results [More Information Needed] #### Summary ## Model Examination [optional] <!-- Relevant interpretability work for the model goes here --> [More Information Needed] ## Environmental Impact <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly --> Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). - Hardware Type: [More Information Needed] - Hours used: [More Information Needed] - Cloud Provider: [More Information Needed] - Compute Region: [More Information Needed] - Carbon Emitted: [More Information Needed] ## Technical Specifications [optional] ### Model Architecture and Objective [More Information Needed] ### Compute Infrastructure [More Information Needed] #### Hardware [More Information Needed] #### Software [More Information Needed] ## Citation [optional] <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. --> BibTeX: [More Information Needed] APA: [More Information Needed] ## Glossary [optional] <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. --> [More Information Needed] ## More Information [optional] [More Information Needed] ## Model Card Authors [optional] [More Information Needed] ## Model Card Contact [More Information Needed]
sandeshrajx/bert-fraud-classification-test-mass-4	sandeshrajx	2024-10-11T04:53:32Z	163	0	transformers	[ "transformers", "safetensors", "bert", "text-classification", "generated_from_trainer", "base_model:sandeshrajx/bert-fraud-classification-test-mass", "base_model:finetune:sandeshrajx/bert-fraud-classification-test-mass", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "region:us" ]	text-classification	2024-10-11T04:53:09Z	--- library_name: transformers license: apache-2.0 base_model: sandeshrajx/bert-fraud-classification-test-mass tags: - generated_from_trainer metrics: - f1 - precision model-index: - name: bert-fraud-classification-test-mass-4 results: [] --- <!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> [<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/sandeshrajx/ultron-nlp/runs/xnpaqmt6) # bert-fraud-classification-test-mass-4 This model is a fine-tuned version of [sandeshrajx/bert-fraud-classification-test-mass](https://huggingface.co/sandeshrajx/bert-fraud-classification-test-mass) on the None dataset. It achieves the following results on the evaluation set: - Loss: 0.3408 - F1: 0.8508 - Precision: 0.8627 - Val Accuracy: 0.8663 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 5e-05 - train_batch_size: 44 - eval_batch_size: 8 - seed: 42 - gradient_accumulation_steps: 2 - total_train_batch_size: 88 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - lr_scheduler_warmup_steps: 50 - num_epochs: 2 - mixed_precision_training: Native AMP ### Training results \| Training Loss \| Epoch \| Step \| Validation Loss \| F1 \| Precision \| Val Accuracy \| \|:-------------:\|:------:\|:----:\|:---------------:\|:------:\|:---------:\|:------------:\| \| 0.3874 \| 0.1743 \| 40 \| 0.3197 \| 0.8579 \| 0.8936 \| 0.8758 \| \| 0.3614 \| 0.3486 \| 80 \| 0.3427 \| 0.8382 \| 0.8846 \| 0.8603 \| \| 0.3563 \| 0.5229 \| 120 \| 0.3505 \| 0.8435 \| 0.8468 \| 0.8584 \| \| 0.4263 \| 0.6972 \| 160 \| 0.3407 \| 0.8454 \| 0.8589 \| 0.8617 \| \| 0.3514 \| 0.8715 \| 200 \| 0.3473 \| 0.8413 \| 0.8421 \| 0.8560 \| \| 0.259 \| 1.0458 \| 240 \| 0.3378 \| 0.8417 \| 0.9106 \| 0.8663 \| \| 0.3148 \| 1.2200 \| 280 \| 0.3543 \| 0.8479 \| 0.8889 \| 0.8679 \| \| 0.2685 \| 1.3943 \| 320 \| 0.3507 \| 0.8501 \| 0.9040 \| 0.8715 \| \| 0.2271 \| 1.5686 \| 360 \| 0.3773 \| 0.8406 \| 0.8262 \| 0.8526 \| \| 0.376 \| 1.7429 \| 400 \| 0.3412 \| 0.8520 \| 0.8731 \| 0.8687 \| \| 0.2739 \| 1.9172 \| 440 \| 0.3408 \| 0.8508 \| 0.8627 \| 0.8663 \| ### Framework versions - Transformers 4.46.0.dev0 - Pytorch 2.4.1+cu121 - Datasets 3.0.1 - Tokenizers 0.20.1
leenag/whisper-small-paula	leenag	2024-10-11T04:40:17Z	77	0	transformers	[ "transformers", "tensorboard", "safetensors", "whisper", "automatic-speech-recognition", "generated_from_trainer", "pmx", "dataset:iitd-duk/paula", "base_model:openai/whisper-small", "base_model:finetune:openai/whisper-small", "license:apache-2.0", "endpoints_compatible", "region:us" ]	automatic-speech-recognition	2024-08-20T08:17:59Z	--- library_name: transformers language: - pmx license: apache-2.0 base_model: openai/whisper-small tags: - generated_from_trainer datasets: - iitd-duk/paula model-index: - name: Whisper-Small-paula results: [] --- <!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # Whisper-Small-paula This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on the Paula dataset. ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 1e-05 - train_batch_size: 12 - eval_batch_size: 8 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - lr_scheduler_warmup_steps: 100 - training_steps: 500 - mixed_precision_training: Native AMP ### Framework versions - Transformers 4.45.0.dev0 - Pytorch 2.3.1+cu121 - Datasets 2.21.0 - Tokenizers 0.19.1
ariG23498/clip-vit-large-patch14-text-flax	ariG23498	2024-10-11T04:37:43Z	1,248	2	transformers	[ "transformers", "safetensors", "clip_text_model", "feature-extraction", "arxiv:1910.09700", "endpoints_compatible", "region:us" ]	feature-extraction	2024-10-11T03:49:41Z	--- library_name: transformers tags: [] --- # Model Card for Model ID <!-- Provide a quick summary of what the model is/does. --> ## Model Details ### Model Description <!-- Provide a longer summary of what this model is. --> This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated. - Developed by: [More Information Needed] - Funded by [optional]: [More Information Needed] - Shared by [optional]: [More Information Needed] - Model type: [More Information Needed] - Language(s) (NLP): [More Information Needed] - License: [More Information Needed] - Finetuned from model [optional]: [More Information Needed] ### Model Sources [optional] <!-- Provide the basic links for the model. --> - Repository: [More Information Needed] - Paper [optional]: [More Information Needed] - Demo [optional]: [More Information Needed] ## Uses <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. --> ### Direct Use <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. --> [More Information Needed] ### Downstream Use [optional] <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app --> [More Information Needed] ### Out-of-Scope Use <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. --> [More Information Needed] ## Bias, Risks, and Limitations <!-- This section is meant to convey both technical and sociotechnical limitations. --> [More Information Needed] ### Recommendations <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. --> Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. [More Information Needed] ## Training Details ### Training Data <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. --> [More Information Needed] ### Training Procedure <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. --> #### Preprocessing [optional] [More Information Needed] #### Training Hyperparameters - Training regime: [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision --> #### Speeds, Sizes, Times [optional] <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. --> [More Information Needed] ## Evaluation <!-- This section describes the evaluation protocols and provides the results. --> ### Testing Data, Factors & Metrics #### Testing Data <!-- This should link to a Dataset Card if possible. --> [More Information Needed] #### Factors <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. --> [More Information Needed] #### Metrics <!-- These are the evaluation metrics being used, ideally with a description of why. --> [More Information Needed] ### Results [More Information Needed] #### Summary ## Model Examination [optional] <!-- Relevant interpretability work for the model goes here --> [More Information Needed] ## Environmental Impact <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly --> Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). - Hardware Type: [More Information Needed] - Hours used: [More Information Needed] - Cloud Provider: [More Information Needed] - Compute Region: [More Information Needed] - Carbon Emitted: [More Information Needed] ## Technical Specifications [optional] ### Model Architecture and Objective [More Information Needed] ### Compute Infrastructure [More Information Needed] #### Hardware [More Information Needed] #### Software [More Information Needed] ## Citation [optional] <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. --> BibTeX: [More Information Needed] APA: [More Information Needed] ## Glossary [optional] <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. --> [More Information Needed] ## More Information [optional] [More Information Needed] ## Model Card Authors [optional] [More Information Needed] ## Model Card Contact [More Information Needed]
objects76/ft-Llama-3.2-3B-Instruct	objects76	2024-10-11T04:27:26Z	118	0	transformers	[ "transformers", "safetensors", "llama", "text-generation", "text-generation-inference", "unsloth", "trl", "sft", "conversational", "en", "base_model:unsloth/Llama-3.2-3B-Instruct", "base_model:finetune:unsloth/Llama-3.2-3B-Instruct", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "region:us" ]	text-generation	2024-10-11T04:25:50Z	--- base_model: unsloth/Llama-3.2-3B-Instruct language: - en license: apache-2.0 tags: - text-generation-inference - transformers - unsloth - llama - trl - sft --- # Uploaded model - Developed by: objects76 - License: apache-2.0 - Finetuned from model : unsloth/Llama-3.2-3B-Instruct This llama model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library. [<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)
TechxGenus/Mistral-Large-Instruct-2407-AWQ	TechxGenus	2024-10-11T04:17:54Z	222	11	transformers	[ "transformers", "safetensors", "mistral", "text-generation", "conversational", "en", "fr", "de", "es", "it", "pt", "zh", "ja", "ru", "ko", "license:other", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "4-bit", "awq", "region:us" ]	text-generation	2024-07-25T05:10:08Z	--- license: other license_name: mrl license_link: https://mistral.ai/licenses/MRL-0.1.md language: - en - fr - de - es - it - pt - zh - ja - ru - ko extra_gated_description: If you want to learn more about how we process your personal data, please read our <a href="https://mistral.ai/terms/">Privacy Policy</a>. --- AWQ quantized version of Mistral-Large-Instruct-2407 model. --- # Model Card for Mistral-Large-Instruct-2407 Mistral-Large-Instruct-2407 is an advanced dense Large Language Model (LLM) of 123B parameters with state-of-the-art reasoning, knowledge and coding capabilities. For more details about this model please refer to our release [blog post](https://mistral.ai/news/mistral-large-2407/). ## Key features - Multi-lingual by design: Dozens of languages supported, including English, French, German, Spanish, Italian, Chinese, Japanese, Korean, Portuguese, Dutch and Polish. - Proficient in coding: Trained on 80+ coding languages such as Python, Java, C, C++, Javacsript, and Bash. Also trained on more specific languages such as Swift and Fortran. - Agentic-centric: Best-in-class agentic capabilities with native function calling and JSON outputting. - Advanced Reasoning: State-of-the-art mathematical and reasoning capabilities. - Mistral Research License: Allows usage and modification for research and non-commercial usages. - Large Context: A large 128k context window. ## Metrics ### Base Pretrained Benchmarks \| Benchmark \| Score \| \| --- \| --- \| \| MMLU \| 84.0% \| ### Base Pretrained Multilingual Benchmarks (MMLU) \| Benchmark \| Score \| \| --- \| --- \| \| French \| 82.8% \| \| German \| 81.6% \| \| Spanish \| 82.7% \| \| Italian \| 82.7% \| \| Dutch \| 80.7% \| \| Portuguese \| 81.6% \| \| Russian \| 79.0% \| \| Korean \| 60.1% \| \| Japanese \| 78.8% \| \| Chinese \| 74.8% \| ### Instruction Benchmarks \| Benchmark \| Score \| \| --- \| --- \| \| MT Bench \| 8.63 \| \| Wild Bench \| 56.3 \| \| Arena Hard\| 73.2 \| ### Code & Reasoning Benchmarks \| Benchmark \| Score \| \| --- \| --- \| \| Human Eval \| 92% \| \| Human Eval Plus\| 87% \| \| MBPP Base\| 80% \| \| MBPP Plus\| 69% \| ### Math Benchmarks \| Benchmark \| Score \| \| --- \| --- \| \| GSM8K \| 93% \| \| Math Instruct (0-shot, no CoT) \| 70% \| \| Math Instruct (0-shot, CoT)\| 71.5% \| ## Usage The model can be used with two different frameworks - [`mistral_inference`](https://github.com/mistralai/mistral-inference): See [here](https://huggingface.co/mistralai/Mistral-Large-2407#mistral-inference) - [`transformers`](https://github.com/huggingface/transformers): See [here](#transformers) ### Mistral Inference #### Install It is recommended to use `mistralai/Mistral-Large-2407` with [mistral-inference](https://github.com/mistralai/mistral-inference). For HF transformers code snippets, please keep scrolling. ``` pip install mistral_inference ``` #### Download ```py from huggingface_hub import snapshot_download from pathlib import Path mistral_models_path = Path.home().joinpath('mistral_models', 'Large') mistral_models_path.mkdir(parents=True, exist_ok=True) snapshot_download(repo_id="mistralai/Mistral-Large-2407", allow_patterns=["params.json", "consolidated-.safetensors", "tokenizer.model.v3"], local_dir=mistral_models_path) ``` #### Chat After installing `mistral_inference`, a `mistral-chat` CLI command should be available in your environment. Given the size of this model, you will need a node with several GPUs (more than 300GB cumulated vRAM). If you have 8 GPUs on your machine, you can chat with the model using ``` torchrun --nproc-per-node 8 --no-python mistral-chat $HOME/mistral_models/Large --instruct --max_tokens 256 --temperature 0.7 ``` E.g.* Try out something like: ``` How expensive would it be to ask a window cleaner to clean all windows in Paris. Make a reasonable guess in US Dollar. ``` #### Instruct following ```py from mistral_inference.transformer import Transformer from mistral_inference.generate import generate from mistral_common.tokens.tokenizers.mistral import MistralTokenizer from mistral_common.protocol.instruct.messages import UserMessage from mistral_common.protocol.instruct.request import ChatCompletionRequest tokenizer = MistralTokenizer.from_file(f"{mistral_models_path}/tokenizer.model.v3") model = Transformer.from_folder(mistral_models_path) prompt = "How expensive would it be to ask a window cleaner to clean all windows in Paris. Make a reasonable guess in US Dollar." completion_request = ChatCompletionRequest(messages=[UserMessage(content=prompt)]) tokens = tokenizer.encode_chat_completion(completion_request).tokens out_tokens, _ = generate([tokens], model, max_tokens=64, temperature=0.7, eos_id=tokenizer.instruct_tokenizer.tokenizer.eos_id) result = tokenizer.decode(out_tokens[0]) print(result) ``` #### Function calling ```py from mistral_common.protocol.instruct.tool_calls import Function, Tool from mistral_inference.transformer import Transformer from mistral_inference.generate import generate from mistral_common.tokens.tokenizers.mistral import MistralTokenizer from mistral_common.protocol.instruct.messages import UserMessage from mistral_common.protocol.instruct.request import ChatCompletionRequest tokenizer = MistralTokenizer.from_file(f"{mistral_models_path}/tokenizer.model.v3") model = Transformer.from_folder(mistral_models_path) completion_request = ChatCompletionRequest( tools=[ Tool( function=Function( name="get_current_weather", description="Get the current weather", parameters={ "type": "object", "properties": { "location": { "type": "string", "description": "The city and state, e.g. San Francisco, CA", }, "format": { "type": "string", "enum": ["celsius", "fahrenheit"], "description": "The temperature unit to use. Infer this from the users location.", }, }, "required": ["location", "format"], }, ) ) ], messages=[ UserMessage(content="What's the weather like today in Paris?"), ], ) tokens = tokenizer.encode_chat_completion(completion_request).tokens out_tokens, _ = generate([tokens], model, max_tokens=256, temperature=0.7, eos_id=tokenizer.instruct_tokenizer.tokenizer.eos_id) result = tokenizer.decode(out_tokens[0]) print(result) ``` ### Transformers > [!IMPORTANT] > NOTE: Until a new release has been made, you need to install transformers from source: > ```sh > pip install git+https://github.com/huggingface/transformers.git > ``` If you want to use Hugging Face `transformers` to generate text, you can do something like this. ```py from transformers import pipeline messages = [ {"role": "system", "content": "You are a pirate chatbot who always responds in pirate speak!"}, {"role": "user", "content": "Who are you?"}, ] chatbot = pipeline("text-generation", model="mistralai/Mistral-Large-2407") chatbot(messages) ``` ## Limitations The Mistral Large model is a quick demonstration that the base model can be easily fine-tuned to achieve compelling performance. It does not have any moderation mechanisms. We're looking forward to engaging with the community on ways to make the model finely respect guardrails, allowing for deployment in environments requiring moderated outputs. ## The Mistral AI Team Albert Jiang, Alexandre Sablayrolles, Alexis Tacnet, Alok Kothari, Antoine Roux, Arthur Mensch, Audrey Herblin-Stoop, Augustin Garreau, Austin Birky, Bam4d, Baptiste Bout, Baudouin de Monicault, Blanche Savary, Carole Rambaud, Caroline Feldman, Devendra Singh Chaplot, Diego de las Casas, Diogo Costa, Eleonore Arcelin, Emma Bou Hanna, Etienne Metzger, Gaspard Blanchet, Gianna Lengyel, Guillaume Bour, Guillaume Lample, Harizo Rajaona, Henri Roussez, Hichem Sattouf, Ian Mack, Jean-Malo Delignon, Jessica Chudnovsky, Justus Murke, Kartik Khandelwal, Lawrence Stewart, Louis Martin, Louis Ternon, Lucile Saulnier, Lélio Renard Lavaud, Margaret Jennings, Marie Pellat, Marie Torelli, Marie-Anne Lachaux, Marjorie Janiewicz, Mickaël Seznec, Nicolas Schuhl, Niklas Muhs, Olivier de Garrigues, Patrick von Platen, Paul Jacob, Pauline Buche, Pavan Kumar Reddy, Perry Savas, Pierre Stock, Romain Sauvestre, Sagar Vaze, Sandeep Subramanian, Saurabh Garg, Sophia Yang, Szymon Antoniak, Teven Le Scao, Thibault Schueller, Thibaut Lavril, Thomas Wang, Théophile Gervet, Timothée Lacroix, Valera Nemychnikova, Wendy Shang, William El Sayed, William Marshall
Triangle104/Hermes2-Gutenberg2-Mistral-7B-Q5_K_S-GGUF	Triangle104	2024-10-11T03:59:56Z	5	0	transformers	[ "transformers", "gguf", "llama-cpp", "gguf-my-repo", "dataset:jondurbin/gutenberg-dpo-v0.1", "dataset:nbeerbower/gutenberg2-dpo", "base_model:nbeerbower/Hermes2-Gutenberg2-Mistral-7B", "base_model:quantized:nbeerbower/Hermes2-Gutenberg2-Mistral-7B", "license:apache-2.0", "model-index", "endpoints_compatible", "region:us", "conversational" ]	null	2024-10-11T03:57:01Z	--- base_model: nbeerbower/Hermes2-Gutenberg2-Mistral-7B datasets: - jondurbin/gutenberg-dpo-v0.1 - nbeerbower/gutenberg2-dpo library_name: transformers license: apache-2.0 tags: - llama-cpp - gguf-my-repo model-index: - name: Hermes2-Gutenberg2-Mistral-7B results: - task: type: text-generation name: Text Generation dataset: name: IFEval (0-Shot) type: HuggingFaceH4/ifeval args: num_few_shot: 0 metrics: - type: inst_level_strict_acc and prompt_level_strict_acc value: 37.21 name: strict accuracy source: url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=nbeerbower/Hermes2-Gutenberg2-Mistral-7B name: Open LLM Leaderboard - task: type: text-generation name: Text Generation dataset: name: BBH (3-Shot) type: BBH args: num_few_shot: 3 metrics: - type: acc_norm value: 28.91 name: normalized accuracy source: url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=nbeerbower/Hermes2-Gutenberg2-Mistral-7B name: Open LLM Leaderboard - task: type: text-generation name: Text Generation dataset: name: MATH Lvl 5 (4-Shot) type: hendrycks/competition_math args: num_few_shot: 4 metrics: - type: exact_match value: 5.66 name: exact match source: url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=nbeerbower/Hermes2-Gutenberg2-Mistral-7B name: Open LLM Leaderboard - task: type: text-generation name: Text Generation dataset: name: GPQA (0-shot) type: Idavidrein/gpqa args: num_few_shot: 0 metrics: - type: acc_norm value: 5.26 name: acc_norm source: url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=nbeerbower/Hermes2-Gutenberg2-Mistral-7B name: Open LLM Leaderboard - task: type: text-generation name: Text Generation dataset: name: MuSR (0-shot) type: TAUR-Lab/MuSR args: num_few_shot: 0 metrics: - type: acc_norm value: 16.92 name: acc_norm source: url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=nbeerbower/Hermes2-Gutenberg2-Mistral-7B name: Open LLM Leaderboard - task: type: text-generation name: Text Generation dataset: name: MMLU-PRO (5-shot) type: TIGER-Lab/MMLU-Pro config: main split: test args: num_few_shot: 5 metrics: - type: acc value: 22.14 name: accuracy source: url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=nbeerbower/Hermes2-Gutenberg2-Mistral-7B name: Open LLM Leaderboard --- # Triangle104/Hermes2-Gutenberg2-Mistral-7B-Q5_K_S-GGUF This model was converted to GGUF format from [`nbeerbower/Hermes2-Gutenberg2-Mistral-7B`](https://huggingface.co/nbeerbower/Hermes2-Gutenberg2-Mistral-7B) using llama.cpp via the ggml.ai's [GGUF-my-repo](https://huggingface.co/spaces/ggml-org/gguf-my-repo) space. Refer to the [original model card](https://huggingface.co/nbeerbower/Hermes2-Gutenberg2-Mistral-7B) for more details on the model. --- Model details: - Hermes2-Gutenberg2-Mistral-7B NousResearch/Hermes-2-Pro-Mistral-7B finetuned on jondurbin/gutenberg-dpo-v0.1 and nbeerbower/gutenberg2-dpo. Method ORPO tuned with 2x RTX 3090 for 3 epochs. Open LLM Leaderboard Evaluation Results Detailed results can be found here Metric Value Avg. 19.35 IFEval (0-Shot) 37.21 BBH (3-Shot) 28.91 MATH Lvl 5 (4-Shot) 5.66 GPQA (0-shot) 5.26 MuSR (0-shot) 16.92 MMLU-PRO (5-shot) 22.14 --- ## Use with llama.cpp Install llama.cpp through brew (works on Mac and Linux) ```bash brew install llama.cpp ``` Invoke the llama.cpp server or the CLI. ### CLI: ```bash llama-cli --hf-repo Triangle104/Hermes2-Gutenberg2-Mistral-7B-Q5_K_S-GGUF --hf-file hermes2-gutenberg2-mistral-7b-q5_k_s.gguf -p "The meaning to life and the universe is" ``` ### Server: ```bash llama-server --hf-repo Triangle104/Hermes2-Gutenberg2-Mistral-7B-Q5_K_S-GGUF --hf-file hermes2-gutenberg2-mistral-7b-q5_k_s.gguf -c 2048 ``` Note: You can also use this checkpoint directly through the [usage steps](https://github.com/ggerganov/llama.cpp?tab=readme-ov-file#usage) listed in the Llama.cpp repo as well. Step 1: Clone llama.cpp from GitHub. ``` git clone https://github.com/ggerganov/llama.cpp ``` Step 2: Move into the llama.cpp folder and build it with `LLAMA_CURL=1` flag along with other hardware-specific flags (for ex: LLAMA_CUDA=1 for Nvidia GPUs on Linux). ``` cd llama.cpp && LLAMA_CURL=1 make ``` Step 3: Run inference through the main binary. ``` ./llama-cli --hf-repo Triangle104/Hermes2-Gutenberg2-Mistral-7B-Q5_K_S-GGUF --hf-file hermes2-gutenberg2-mistral-7b-q5_k_s.gguf -p "The meaning to life and the universe is" ``` or ``` ./llama-server --hf-repo Triangle104/Hermes2-Gutenberg2-Mistral-7B-Q5_K_S-GGUF --hf-file hermes2-gutenberg2-mistral-7b-q5_k_s.gguf -c 2048 ```
Triangle104/Hermes2-Gutenberg2-Mistral-7B-Q4_K_S-GGUF	Triangle104	2024-10-11T03:53:40Z	5	0	transformers	[ "transformers", "gguf", "llama-cpp", "gguf-my-repo", "dataset:jondurbin/gutenberg-dpo-v0.1", "dataset:nbeerbower/gutenberg2-dpo", "base_model:nbeerbower/Hermes2-Gutenberg2-Mistral-7B", "base_model:quantized:nbeerbower/Hermes2-Gutenberg2-Mistral-7B", "license:apache-2.0", "model-index", "endpoints_compatible", "region:us", "conversational" ]	null	2024-10-11T03:51:35Z	--- base_model: nbeerbower/Hermes2-Gutenberg2-Mistral-7B datasets: - jondurbin/gutenberg-dpo-v0.1 - nbeerbower/gutenberg2-dpo library_name: transformers license: apache-2.0 tags: - llama-cpp - gguf-my-repo model-index: - name: Hermes2-Gutenberg2-Mistral-7B results: - task: type: text-generation name: Text Generation dataset: name: IFEval (0-Shot) type: HuggingFaceH4/ifeval args: num_few_shot: 0 metrics: - type: inst_level_strict_acc and prompt_level_strict_acc value: 37.21 name: strict accuracy source: url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=nbeerbower/Hermes2-Gutenberg2-Mistral-7B name: Open LLM Leaderboard - task: type: text-generation name: Text Generation dataset: name: BBH (3-Shot) type: BBH args: num_few_shot: 3 metrics: - type: acc_norm value: 28.91 name: normalized accuracy source: url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=nbeerbower/Hermes2-Gutenberg2-Mistral-7B name: Open LLM Leaderboard - task: type: text-generation name: Text Generation dataset: name: MATH Lvl 5 (4-Shot) type: hendrycks/competition_math args: num_few_shot: 4 metrics: - type: exact_match value: 5.66 name: exact match source: url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=nbeerbower/Hermes2-Gutenberg2-Mistral-7B name: Open LLM Leaderboard - task: type: text-generation name: Text Generation dataset: name: GPQA (0-shot) type: Idavidrein/gpqa args: num_few_shot: 0 metrics: - type: acc_norm value: 5.26 name: acc_norm source: url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=nbeerbower/Hermes2-Gutenberg2-Mistral-7B name: Open LLM Leaderboard - task: type: text-generation name: Text Generation dataset: name: MuSR (0-shot) type: TAUR-Lab/MuSR args: num_few_shot: 0 metrics: - type: acc_norm value: 16.92 name: acc_norm source: url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=nbeerbower/Hermes2-Gutenberg2-Mistral-7B name: Open LLM Leaderboard - task: type: text-generation name: Text Generation dataset: name: MMLU-PRO (5-shot) type: TIGER-Lab/MMLU-Pro config: main split: test args: num_few_shot: 5 metrics: - type: acc value: 22.14 name: accuracy source: url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=nbeerbower/Hermes2-Gutenberg2-Mistral-7B name: Open LLM Leaderboard --- # Triangle104/Hermes2-Gutenberg2-Mistral-7B-Q4_K_S-GGUF This model was converted to GGUF format from [`nbeerbower/Hermes2-Gutenberg2-Mistral-7B`](https://huggingface.co/nbeerbower/Hermes2-Gutenberg2-Mistral-7B) using llama.cpp via the ggml.ai's [GGUF-my-repo](https://huggingface.co/spaces/ggml-org/gguf-my-repo) space. Refer to the [original model card](https://huggingface.co/nbeerbower/Hermes2-Gutenberg2-Mistral-7B) for more details on the model. --- Model details: - Hermes2-Gutenberg2-Mistral-7B NousResearch/Hermes-2-Pro-Mistral-7B finetuned on jondurbin/gutenberg-dpo-v0.1 and nbeerbower/gutenberg2-dpo. Method ORPO tuned with 2x RTX 3090 for 3 epochs. Open LLM Leaderboard Evaluation Results Detailed results can be found here Metric Value Avg. 19.35 IFEval (0-Shot) 37.21 BBH (3-Shot) 28.91 MATH Lvl 5 (4-Shot) 5.66 GPQA (0-shot) 5.26 MuSR (0-shot) 16.92 MMLU-PRO (5-shot) 22.14 --- ## Use with llama.cpp Install llama.cpp through brew (works on Mac and Linux) ```bash brew install llama.cpp ``` Invoke the llama.cpp server or the CLI. ### CLI: ```bash llama-cli --hf-repo Triangle104/Hermes2-Gutenberg2-Mistral-7B-Q4_K_S-GGUF --hf-file hermes2-gutenberg2-mistral-7b-q4_k_s.gguf -p "The meaning to life and the universe is" ``` ### Server: ```bash llama-server --hf-repo Triangle104/Hermes2-Gutenberg2-Mistral-7B-Q4_K_S-GGUF --hf-file hermes2-gutenberg2-mistral-7b-q4_k_s.gguf -c 2048 ``` Note: You can also use this checkpoint directly through the [usage steps](https://github.com/ggerganov/llama.cpp?tab=readme-ov-file#usage) listed in the Llama.cpp repo as well. Step 1: Clone llama.cpp from GitHub. ``` git clone https://github.com/ggerganov/llama.cpp ``` Step 2: Move into the llama.cpp folder and build it with `LLAMA_CURL=1` flag along with other hardware-specific flags (for ex: LLAMA_CUDA=1 for Nvidia GPUs on Linux). ``` cd llama.cpp && LLAMA_CURL=1 make ``` Step 3: Run inference through the main binary. ``` ./llama-cli --hf-repo Triangle104/Hermes2-Gutenberg2-Mistral-7B-Q4_K_S-GGUF --hf-file hermes2-gutenberg2-mistral-7b-q4_k_s.gguf -p "The meaning to life and the universe is" ``` or ``` ./llama-server --hf-repo Triangle104/Hermes2-Gutenberg2-Mistral-7B-Q4_K_S-GGUF --hf-file hermes2-gutenberg2-mistral-7b-q4_k_s.gguf -c 2048 ```
tifin-india/fund-embedder	tifin-india	2024-10-11T03:45:21Z	165	0	sentence-transformers	[ "sentence-transformers", "safetensors", "mpnet", "sentence-similarity", "feature-extraction", "generated_from_trainer", "dataset_size:44581", "loss:MultipleNegativesRankingLoss", "arxiv:1908.10084", "arxiv:1705.00652", "base_model:microsoft/mpnet-base", "base_model:finetune:microsoft/mpnet-base", "autotrain_compatible", "endpoints_compatible", "region:us" ]	sentence-similarity	2024-10-11T03:44:56Z	--- base_model: microsoft/mpnet-base library_name: sentence-transformers pipeline_tag: sentence-similarity tags: - sentence-transformers - sentence-similarity - feature-extraction - generated_from_trainer - dataset_size:44581 - loss:MultipleNegativesRankingLoss widget: - source_sentence: Lupin Ltd. sentences: - Lupin Ltd India - Asian Paints Corporation Ltd - 82TCHF25 - Tata Capital Housing Finance - source_sentence: NTPC Ltd. - (762NTPC35F) sentences: - Galada Power and Telecommunication Limited - DSP BlackRock Savings Fund - NTPC Limited - 762NTPC35F - source_sentence: Neueon Towers Ltd. sentences: - Neueon Towers Company Limited - CFI India - Gita Renewable Energy India Private Limited - source_sentence: Ganesh Benzoplast Ltd. sentences: - Cool Caps Industries Private Limited - Sandhar Technologies Limited India - Ganesh Benzoplast India Ltd - source_sentence: ICICI Prudential Retirement Fund - Hybrid Conservative Plan sentences: - ICICI Prudential Retirement Hybrid Conservative Fund - Lloyds Enterprises Limited - KEC Ltd India --- # SentenceTransformer based on microsoft/mpnet-base This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [microsoft/mpnet-base](https://huggingface.co/microsoft/mpnet-base). It maps sentences & paragraphs to a 768-dimensional dense vector space and can be used for semantic textual similarity, semantic search, paraphrase mining, text classification, clustering, and more. ## Model Details ### Model Description - Model Type: Sentence Transformer - Base model: [microsoft/mpnet-base](https://huggingface.co/microsoft/mpnet-base) <!-- at revision 6996ce1e91bd2a9c7d7f61daec37463394f73f09 --> - Maximum Sequence Length: 512 tokens - Output Dimensionality: 768 tokens - Similarity Function: Cosine Similarity <!-- - Training Dataset: Unknown --> <!-- - Language: Unknown --> <!-- - License: Unknown --> ### Model Sources - Documentation: [Sentence Transformers Documentation](https://sbert.net) - Repository: [Sentence Transformers on GitHub](https://github.com/UKPLab/sentence-transformers) - Hugging Face: [Sentence Transformers on Hugging Face](https://huggingface.co/models?library=sentence-transformers) ### Full Model Architecture ``` SentenceTransformer( (0): Transformer({'max_seq_length': 512, 'do_lower_case': False}) with Transformer model: MPNetModel (1): Pooling({'word_embedding_dimension': 768, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': True, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False, 'include_prompt': True}) ) ``` ## Usage ### Direct Usage (Sentence Transformers) First install the Sentence Transformers library: ```bash pip install -U sentence-transformers ``` Then you can load this model and run inference. ```python from sentence_transformers import SentenceTransformer # Download from the 🤗 Hub model = SentenceTransformer("pawan2411/fund-embedder") # Run inference sentences = [ 'ICICI Prudential Retirement Fund - Hybrid Conservative Plan', 'ICICI Prudential Retirement Hybrid Conservative Fund', 'KEC Ltd India', ] embeddings = model.encode(sentences) print(embeddings.shape) # [3, 768] # Get the similarity scores for the embeddings similarities = model.similarity(embeddings, embeddings) print(similarities.shape) # [3, 3] ``` <!-- ### Direct Usage (Transformers) <details><summary>Click to see the direct usage in Transformers</summary> </details> --> <!-- ### Downstream Usage (Sentence Transformers) You can finetune this model on your own dataset. <details><summary>Click to expand</summary> </details> --> <!-- ### Out-of-Scope Use List how the model may foreseeably be misused and address what users ought not to do with the model. --> <!-- ## Bias, Risks and Limitations What are the known or foreseeable issues stemming from this model? You could also flag here known failure cases or weaknesses of the model. --> <!-- ### Recommendations What are recommendations with respect to the foreseeable issues? For example, filtering explicit content. --> ## Training Details ### Training Dataset #### Unnamed Dataset * Size: 44,581 training samples * Columns: <code>sentence_0</code> and <code>sentence_1</code> * Approximate statistics based on the first 1000 samples: \| \| sentence_0 \| sentence_1 \| \|:--------\|:---------------------------------------------------------------------------------\|:---------------------------------------------------------------------------------\| \| type \| string \| string \| \| details \| <ul><li>min: 5 tokens</li><li>mean: 9.45 tokens</li><li>max: 27 tokens</li></ul> \| <ul><li>min: 4 tokens</li><li>mean: 9.08 tokens</li><li>max: 27 tokens</li></ul> \| * Samples: \| sentence_0 \| sentence_1 \| \|:---------------------------------------\|:----------------------------------------------\| \| <code>Groww Value Fund</code> \| <code>Groww Value Equity Fund</code> \| \| <code>DSP Ultra Short Fund</code> \| <code>DSP Ultra Short Term Income Fund</code> \| \| <code>The Grob Tea Company Ltd.</code> \| <code>Grob Tea Ltd</code> \| * Loss: [<code>MultipleNegativesRankingLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#multiplenegativesrankingloss) with these parameters: ```json { "scale": 20.0, "similarity_fct": "cos_sim" } ``` ### Training Hyperparameters #### Non-Default Hyperparameters - `per_device_train_batch_size`: 64 - `per_device_eval_batch_size`: 64 - `num_train_epochs`: 10 - `multi_dataset_batch_sampler`: round_robin #### All Hyperparameters <details><summary>Click to expand</summary> - `overwrite_output_dir`: False - `do_predict`: False - `eval_strategy`: no - `prediction_loss_only`: True - `per_device_train_batch_size`: 64 - `per_device_eval_batch_size`: 64 - `per_gpu_train_batch_size`: None - `per_gpu_eval_batch_size`: None - `gradient_accumulation_steps`: 1 - `eval_accumulation_steps`: None - `torch_empty_cache_steps`: None - `learning_rate`: 5e-05 - `weight_decay`: 0.0 - `adam_beta1`: 0.9 - `adam_beta2`: 0.999 - `adam_epsilon`: 1e-08 - `max_grad_norm`: 1 - `num_train_epochs`: 10 - `max_steps`: -1 - `lr_scheduler_type`: linear - `lr_scheduler_kwargs`: {} - `warmup_ratio`: 0.0 - `warmup_steps`: 0 - `log_level`: passive - `log_level_replica`: warning - `log_on_each_node`: True - `logging_nan_inf_filter`: True - `save_safetensors`: True - `save_on_each_node`: False - `save_only_model`: False - `restore_callback_states_from_checkpoint`: False - `no_cuda`: False - `use_cpu`: False - `use_mps_device`: False - `seed`: 42 - `data_seed`: None - `jit_mode_eval`: False - `use_ipex`: False - `bf16`: False - `fp16`: False - `fp16_opt_level`: O1 - `half_precision_backend`: auto - `bf16_full_eval`: False - `fp16_full_eval`: False - `tf32`: None - `local_rank`: 0 - `ddp_backend`: None - `tpu_num_cores`: None - `tpu_metrics_debug`: False - `debug`: [] - `dataloader_drop_last`: False - `dataloader_num_workers`: 0 - `dataloader_prefetch_factor`: None - `past_index`: -1 - `disable_tqdm`: False - `remove_unused_columns`: True - `label_names`: None - `load_best_model_at_end`: False - `ignore_data_skip`: False - `fsdp`: [] - `fsdp_min_num_params`: 0 - `fsdp_config`: {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False} - `fsdp_transformer_layer_cls_to_wrap`: None - `accelerator_config`: {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None} - `deepspeed`: None - `label_smoothing_factor`: 0.0 - `optim`: adamw_torch - `optim_args`: None - `adafactor`: False - `group_by_length`: False - `length_column_name`: length - `ddp_find_unused_parameters`: None - `ddp_bucket_cap_mb`: None - `ddp_broadcast_buffers`: False - `dataloader_pin_memory`: True - `dataloader_persistent_workers`: False - `skip_memory_metrics`: True - `use_legacy_prediction_loop`: False - `push_to_hub`: False - `resume_from_checkpoint`: None - `hub_model_id`: None - `hub_strategy`: every_save - `hub_private_repo`: False - `hub_always_push`: False - `gradient_checkpointing`: False - `gradient_checkpointing_kwargs`: None - `include_inputs_for_metrics`: False - `eval_do_concat_batches`: True - `fp16_backend`: auto - `push_to_hub_model_id`: None - `push_to_hub_organization`: None - `mp_parameters`: - `auto_find_batch_size`: False - `full_determinism`: False - `torchdynamo`: None - `ray_scope`: last - `ddp_timeout`: 1800 - `torch_compile`: False - `torch_compile_backend`: None - `torch_compile_mode`: None - `dispatch_batches`: None - `split_batches`: None - `include_tokens_per_second`: False - `include_num_input_tokens_seen`: False - `neftune_noise_alpha`: None - `optim_target_modules`: None - `batch_eval_metrics`: False - `eval_on_start`: False - `eval_use_gather_object`: False - `batch_sampler`: batch_sampler - `multi_dataset_batch_sampler`: round_robin </details> ### Training Logs \| Epoch \| Step \| Training Loss \| \|:------:\|:----:\|:-------------:\| \| 0.7174 \| 500 \| 0.5531 \| \| 1.4347 \| 1000 \| 0.0372 \| \| 2.1521 \| 1500 \| 0.0195 \| \| 2.8694 \| 2000 \| 0.0128 \| \| 3.5868 \| 2500 \| 0.0087 \| \| 4.3042 \| 3000 \| 0.0079 \| \| 5.0215 \| 3500 \| 0.0143 \| \| 5.7389 \| 4000 \| 0.0075 \| \| 6.4562 \| 4500 \| 0.0056 \| \| 7.1736 \| 5000 \| 0.0075 \| \| 7.8910 \| 5500 \| 0.0069 \| \| 8.6083 \| 6000 \| 0.0059 \| \| 9.3257 \| 6500 \| 0.0054 \| ### Framework Versions - Python: 3.10.12 - Sentence Transformers: 3.2.0 - Transformers: 4.44.2 - PyTorch: 2.4.1+cu121 - Accelerate: 0.34.2 - Datasets: 3.0.1 - Tokenizers: 0.19.1 ## Citation ### BibTeX #### Sentence Transformers ```bibtex @inproceedings{reimers-2019-sentence-bert, title = "Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks", author = "Reimers, Nils and Gurevych, Iryna", booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing", month = "11", year = "2019", publisher = "Association for Computational Linguistics", url = "https://arxiv.org/abs/1908.10084", } ``` #### MultipleNegativesRankingLoss ```bibtex @misc{henderson2017efficient, title={Efficient Natural Language Response Suggestion for Smart Reply}, author={Matthew Henderson and Rami Al-Rfou and Brian Strope and Yun-hsuan Sung and Laszlo Lukacs and Ruiqi Guo and Sanjiv Kumar and Balint Miklos and Ray Kurzweil}, year={2017}, eprint={1705.00652}, archivePrefix={arXiv}, primaryClass={cs.CL} } ``` <!-- ## Glossary Clearly define terms in order to be accessible across audiences. --> <!-- ## Model Card Authors Lists the people who create the model card, providing recognition and accountability for the detailed work that goes into its construction. --> <!-- ## Model Card Contact Provides a way for people who have updates to the Model Card, suggestions, or questions, to contact the Model Card authors. -->
liuyanchen1015/LLaMA2-7B-fingerprinted-SFT-GGUF	liuyanchen1015	2024-10-11T03:21:40Z	16	0	null	[ "gguf", "aotuoquant", "text-generation", "en", "base_model:cnut1648/LLaMA2-7B-fingerprinted-SFT", "base_model:quantized:cnut1648/LLaMA2-7B-fingerprinted-SFT", "endpoints_compatible", "region:us" ]	text-generation	2024-10-11T02:35:22Z	--- language: - en base_model: - cnut1648/LLaMA2-7B-fingerprinted-SFT pipeline_tag: text-generation tags: - gguf - aotuoquant ---
RogerSquare/rogerthat	RogerSquare	2024-10-11T03:21:03Z	6	0	diffusers	[ "diffusers", "flux", "lora", "replicate", "text-to-image", "en", "base_model:black-forest-labs/FLUX.1-dev", "base_model:adapter:black-forest-labs/FLUX.1-dev", "license:other", "region:us" ]	text-to-image	2024-10-11T02:33:47Z	--- license: other license_name: flux-1-dev-non-commercial-license license_link: https://huggingface.co/black-forest-labs/FLUX.1-dev/blob/main/LICENSE.md language: - en tags: - flux - diffusers - lora - replicate base_model: "black-forest-labs/FLUX.1-dev" pipeline_tag: text-to-image # widget: # - text: >- # prompt # output: # url: https://... instance_prompt: Roger --- # Rogerthat <!-- <Gallery /> --> Trained on Replicate using: https://replicate.com/ostris/flux-dev-lora-trainer/train ## Trigger words You should use `Roger` to trigger the image generation. ## Use it with the [🧨 diffusers library](https://github.com/huggingface/diffusers) ```py from diffusers import AutoPipelineForText2Image import torch pipeline = AutoPipelineForText2Image.from_pretrained('black-forest-labs/FLUX.1-dev', torch_dtype=torch.float16).to('cuda') pipeline.load_lora_weights('RogerSquare/rogerthat', weight_name='lora.safetensors') image = pipeline('your prompt').images[0] ``` For more details, including weighting, merging and fusing LoRAs, check the [documentation on loading LoRAs in diffusers](https://huggingface.co/docs/diffusers/main/en/using-diffusers/loading_adapters)
brownyeyez/Mixed-VNPTAI-Qwen2.5-0.5B-v12	brownyeyez	2024-10-11T03:08:26Z	133	0	transformers	[ "transformers", "safetensors", "qwen2", "text-generation", "conversational", "arxiv:1910.09700", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]	text-generation	2024-10-10T03:52:54Z	--- library_name: transformers tags: [] --- # Model Card for Model ID <!-- Provide a quick summary of what the model is/does. --> ## Model Details ### Model Description <!-- Provide a longer summary of what this model is. --> This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated. - Developed by: [More Information Needed] - Funded by [optional]: [More Information Needed] - Shared by [optional]: [More Information Needed] - Model type: [More Information Needed] - Language(s) (NLP): [More Information Needed] - License: [More Information Needed] - Finetuned from model [optional]: [More Information Needed] ### Model Sources [optional] <!-- Provide the basic links for the model. --> - Repository: [More Information Needed] - Paper [optional]: [More Information Needed] - Demo [optional]: [More Information Needed] ## Uses <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. --> ### Direct Use <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. --> [More Information Needed] ### Downstream Use [optional] <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app --> [More Information Needed] ### Out-of-Scope Use <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. --> [More Information Needed] ## Bias, Risks, and Limitations <!-- This section is meant to convey both technical and sociotechnical limitations. --> [More Information Needed] ### Recommendations <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. --> Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. [More Information Needed] ## Training Details ### Training Data <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. --> [More Information Needed] ### Training Procedure <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. --> #### Preprocessing [optional] [More Information Needed] #### Training Hyperparameters - Training regime: [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision --> #### Speeds, Sizes, Times [optional] <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. --> [More Information Needed] ## Evaluation <!-- This section describes the evaluation protocols and provides the results. --> ### Testing Data, Factors & Metrics #### Testing Data <!-- This should link to a Dataset Card if possible. --> [More Information Needed] #### Factors <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. --> [More Information Needed] #### Metrics <!-- These are the evaluation metrics being used, ideally with a description of why. --> [More Information Needed] ### Results [More Information Needed] #### Summary ## Model Examination [optional] <!-- Relevant interpretability work for the model goes here --> [More Information Needed] ## Environmental Impact <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly --> Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). - Hardware Type: [More Information Needed] - Hours used: [More Information Needed] - Cloud Provider: [More Information Needed] - Compute Region: [More Information Needed] - Carbon Emitted: [More Information Needed] ## Technical Specifications [optional] ### Model Architecture and Objective [More Information Needed] ### Compute Infrastructure [More Information Needed] #### Hardware [More Information Needed] #### Software [More Information Needed] ## Citation [optional] <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. --> BibTeX: [More Information Needed] APA: [More Information Needed] ## Glossary [optional] <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. --> [More Information Needed] ## More Information [optional] [More Information Needed] ## Model Card Authors [optional] [More Information Needed] ## Model Card Contact [More Information Needed]
RichardErkhov/theo77186_-_Llama-3-70B-Instruct-norefusal-gguf	RichardErkhov	2024-10-11T03:05:16Z	14	0	null	[ "gguf", "endpoints_compatible", "region:us", "conversational" ]	null	2024-10-10T07:25:09Z	Quantization made by Richard Erkhov. [Github](https://github.com/RichardErkhov) [Discord](https://discord.gg/pvy7H8DZMG) [Request more models](https://github.com/RichardErkhov/quant_request) Llama-3-70B-Instruct-norefusal - GGUF - Model creator: https://huggingface.co/theo77186/ - Original model: https://huggingface.co/theo77186/Llama-3-70B-Instruct-norefusal/ \| Name \| Quant method \| Size \| \| ---- \| ---- \| ---- \| \| [Llama-3-70B-Instruct-norefusal.Q2_K.gguf](https://huggingface.co/RichardErkhov/theo77186_-_Llama-3-70B-Instruct-norefusal-gguf/blob/main/Llama-3-70B-Instruct-norefusal.Q2_K.gguf) \| Q2_K \| 24.56GB \| \| [Llama-3-70B-Instruct-norefusal.IQ3_XS.gguf](https://huggingface.co/RichardErkhov/theo77186_-_Llama-3-70B-Instruct-norefusal-gguf/blob/main/Llama-3-70B-Instruct-norefusal.IQ3_XS.gguf) \| IQ3_XS \| 27.29GB \| \| [Llama-3-70B-Instruct-norefusal.IQ3_S.gguf](https://huggingface.co/RichardErkhov/theo77186_-_Llama-3-70B-Instruct-norefusal-gguf/blob/main/Llama-3-70B-Instruct-norefusal.IQ3_S.gguf) \| IQ3_S \| 28.79GB \| \| [Llama-3-70B-Instruct-norefusal.Q3_K_S.gguf](https://huggingface.co/RichardErkhov/theo77186_-_Llama-3-70B-Instruct-norefusal-gguf/blob/main/Llama-3-70B-Instruct-norefusal.Q3_K_S.gguf) \| Q3_K_S \| 28.79GB \| \| [Llama-3-70B-Instruct-norefusal.IQ3_M.gguf](https://huggingface.co/RichardErkhov/theo77186_-_Llama-3-70B-Instruct-norefusal-gguf/blob/main/Llama-3-70B-Instruct-norefusal.IQ3_M.gguf) \| IQ3_M \| 29.74GB \| \| [Llama-3-70B-Instruct-norefusal.Q3_K.gguf](https://huggingface.co/RichardErkhov/theo77186_-_Llama-3-70B-Instruct-norefusal-gguf/blob/main/Llama-3-70B-Instruct-norefusal.Q3_K.gguf) \| Q3_K \| 31.91GB \| \| [Llama-3-70B-Instruct-norefusal.Q3_K_M.gguf](https://huggingface.co/RichardErkhov/theo77186_-_Llama-3-70B-Instruct-norefusal-gguf/blob/main/Llama-3-70B-Instruct-norefusal.Q3_K_M.gguf) \| Q3_K_M \| 31.91GB \| \| [Llama-3-70B-Instruct-norefusal.Q3_K_L.gguf](https://huggingface.co/RichardErkhov/theo77186_-_Llama-3-70B-Instruct-norefusal-gguf/blob/main/Llama-3-70B-Instruct-norefusal.Q3_K_L.gguf) \| Q3_K_L \| 34.59GB \| \| [Llama-3-70B-Instruct-norefusal.IQ4_XS.gguf](https://huggingface.co/RichardErkhov/theo77186_-_Llama-3-70B-Instruct-norefusal-gguf/blob/main/Llama-3-70B-Instruct-norefusal.IQ4_XS.gguf) \| IQ4_XS \| 35.64GB \| \| [Llama-3-70B-Instruct-norefusal.Q4_0.gguf](https://huggingface.co/RichardErkhov/theo77186_-_Llama-3-70B-Instruct-norefusal-gguf/blob/main/Llama-3-70B-Instruct-norefusal.Q4_0.gguf) \| Q4_0 \| 37.22GB \| \| [Llama-3-70B-Instruct-norefusal.IQ4_NL.gguf](https://huggingface.co/RichardErkhov/theo77186_-_Llama-3-70B-Instruct-norefusal-gguf/tree/main/) \| IQ4_NL \| 37.58GB \| \| [Llama-3-70B-Instruct-norefusal.Q4_K_S.gguf](https://huggingface.co/RichardErkhov/theo77186_-_Llama-3-70B-Instruct-norefusal-gguf/tree/main/) \| Q4_K_S \| 37.58GB \| \| [Llama-3-70B-Instruct-norefusal.Q4_K.gguf](https://huggingface.co/RichardErkhov/theo77186_-_Llama-3-70B-Instruct-norefusal-gguf/tree/main/) \| Q4_K \| 39.6GB \| \| [Llama-3-70B-Instruct-norefusal.Q4_K_M.gguf](https://huggingface.co/RichardErkhov/theo77186_-_Llama-3-70B-Instruct-norefusal-gguf/tree/main/) \| Q4_K_M \| 39.6GB \| \| [Llama-3-70B-Instruct-norefusal.Q4_1.gguf](https://huggingface.co/RichardErkhov/theo77186_-_Llama-3-70B-Instruct-norefusal-gguf/tree/main/) \| Q4_1 \| 41.27GB \| \| [Llama-3-70B-Instruct-norefusal.Q5_0.gguf](https://huggingface.co/RichardErkhov/theo77186_-_Llama-3-70B-Instruct-norefusal-gguf/tree/main/) \| Q5_0 \| 45.32GB \| \| [Llama-3-70B-Instruct-norefusal.Q5_K_S.gguf](https://huggingface.co/RichardErkhov/theo77186_-_Llama-3-70B-Instruct-norefusal-gguf/tree/main/) \| Q5_K_S \| 45.32GB \| \| [Llama-3-70B-Instruct-norefusal.Q5_K.gguf](https://huggingface.co/RichardErkhov/theo77186_-_Llama-3-70B-Instruct-norefusal-gguf/tree/main/) \| Q5_K \| 46.52GB \| \| [Llama-3-70B-Instruct-norefusal.Q5_K_M.gguf](https://huggingface.co/RichardErkhov/theo77186_-_Llama-3-70B-Instruct-norefusal-gguf/tree/main/) \| Q5_K_M \| 46.52GB \| \| [Llama-3-70B-Instruct-norefusal.Q5_1.gguf](https://huggingface.co/RichardErkhov/theo77186_-_Llama-3-70B-Instruct-norefusal-gguf/tree/main/) \| Q5_1 \| 49.36GB \| \| [Llama-3-70B-Instruct-norefusal.Q6_K.gguf](https://huggingface.co/RichardErkhov/theo77186_-_Llama-3-70B-Instruct-norefusal-gguf/tree/main/) \| Q6_K \| 53.91GB \| \| [Llama-3-70B-Instruct-norefusal.Q8_0.gguf](https://huggingface.co/RichardErkhov/theo77186_-_Llama-3-70B-Instruct-norefusal-gguf/tree/main/) \| Q8_0 \| 69.83GB \| Original model description: --- license: llama3 --- # Llama 3 70B Instruct no refusal This is a model that uses the orthogonal feature ablation as featured in this [paper](https://www.alignmentforum.org/posts/jGuXSZgv6qfdhMCuJ/refusal-in-llms-is-mediated-by-a-single-direction). Calibration data: - 256 prompts from [jondurbin/airoboros-2.2](https://huggingface.co/datasets/jondurbin/airoboros-2.2) - 256 prompts from [AdvBench](https://github.com/llm-attacks/llm-attacks/blob/main/data/advbench/harmful_behaviors.csv) - The direction is extracted between layer 40 and 41 I haven't tested the model but like the 8B model, may still refuse some instructions. Use this model responsibly, I decline any liability resulting of the use of this model. I will post the code later.
mav23/fusion-guide-12b-0.1-GGUF	mav23	2024-10-11T02:55:33Z	16	1	transformers	[ "transformers", "gguf", "text-generation-inference", "mistral", "trl", "cot", "guidance", "en", "base_model:mistralai/Mistral-Nemo-Instruct-2407", "base_model:quantized:mistralai/Mistral-Nemo-Instruct-2407", "license:apache-2.0", "endpoints_compatible", "region:us", "conversational" ]	null	2024-10-11T01:34:15Z	--- base_model: - mistralai/Mistral-Nemo-Instruct-2407 language: - en license: apache-2.0 tags: - text-generation-inference - transformers - mistral - trl - cot - guidance --- # fusion-guide [![6ea83689-befb-498b-84b9-20ba406ca4e7.png](https://i.postimg.cc/dtgR40Lz/6ea83689-befb-498b-84b9-20ba406ca4e7.png)](https://postimg.cc/8jBrCNdH) # Model Overview fusion-guide is an advanced AI reasoning system built on the Mistral-Nemo 12bn architecture. It employs a two-model approach to enhance its problem-solving capabilities. This method involves a "Guide" model that generates a structured, step-by-step plan to solve a given task. This plan is then passed to the primary "Response" model, which uses this guidance to craft an accurate and comprehensive response. # Model and Data fusion-guide is fine-tuned on a custom dataset consisting of task-based prompts in both English (90%) and German (10%). The tasks vary in complexity, including scenarios designed to be challenging or unsolvable, to enhance the model's ability to handle ambiguous situations. Each training sample follows the structure: prompt => guidance, teaching the model to break down complex tasks systematically. Read a detailed description and evaluation of the model here: https://blog.fusionbase.com/ai-research/beyond-cot-how-fusion-guide-elevates-ai-reasoning-with-a-two-model-system ### Prompt format The prompt must be enclosed within <guidance_prompt>{PROMPT}</guidance_prompt> tags, following the format below: <guidance_prompt>Count the number of 'r's in the word 'strawberry,' and then write a Python script that checks if an arbitrary word contains the same number of 'r's.</guidance_prompt> # Usage fusion-guide can be used with vLLM and other Mistral-Nemo-compatible inference engines. Below is an example of how to use it with unsloth: ```python from unsloth import FastLanguageModel max_seq_length = 8192 * 1 # Choose any! We auto support RoPE Scaling internally! dtype = None # None for auto detection. Float16 for Tesla T4, V100, Bfloat16 for Ampere+ load_in_4bit = False # Use 4bit quantization to reduce memory usage. Can be False. model, tokenizer = FastLanguageModel.from_pretrained( model_name="fusionbase/fusion-guide-12b-0.1", max_seq_length=max_seq_length, dtype=dtype, load_in_4bit=load_in_4bit ) FastLanguageModel.for_inference(model) # Enable native 2x faster inference guidance_prompt = """<guidance_prompt>Count the number of 'r's in the word 'strawberry,' and then write a Python script that checks if an arbitrary word contains the same number of 'r's.</guidance_prompt>""" messages = [{"role": "user", "content": guidance_prompt}] inputs = tokenizer.apply_chat_template( messages, tokenize=True, add_generation_prompt=True, # Must add for generation return_tensors="pt", ).to("cuda") outputs = model.generate(input_ids=inputs, max_new_tokens=2000, use_cache=True, early_stopping=True, temperature=0) result = tokenizer.batch_decode(outputs) print(result[0][len(guidance_prompt):].replace("</s>", "")) ``` # Disclaimer The model may occasionally fail to generate complete guidance, especially when the prompt includes specific instructions on how the responses should be structured. This limitation arises from the way the model was trained.
edinlp/mistral-7b-v0.3-sft	edinlp	2024-10-11T02:52:04Z	7	0	transformers	[ "transformers", "safetensors", "mistral", "text-generation", "llama-factory", "full", "generated_from_trainer", "conversational", "base_model:mistralai/Mistral-7B-v0.3", "base_model:finetune:mistralai/Mistral-7B-v0.3", "license:other", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]	text-generation	2024-10-11T02:46:50Z	--- library_name: transformers license: other base_model: mistralai/Mistral-7B-v0.3 tags: - llama-factory - full - generated_from_trainer model-index: - name: qwen results: [] --- <!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # qwen This model is a fine-tuned version of [mistralai/Mistral-7B-v0.3](https://huggingface.co/mistralai/Mistral-7B-v0.3) on the openhermes-2.5 dataset. ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 2e-05 - train_batch_size: 1 - eval_batch_size: 8 - seed: 42 - distributed_type: multi-GPU - num_devices: 4 - gradient_accumulation_steps: 16 - total_train_batch_size: 64 - total_eval_batch_size: 32 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: cosine - lr_scheduler_warmup_ratio: 0.03 - num_epochs: 1.0 ### Training results ### Framework versions - Transformers 4.45.1 - Pytorch 2.4.0+cu121 - Datasets 2.21.0 - Tokenizers 0.20.0
win10/Qwen2.5-2B-Instruct	win10	2024-10-11T02:37:14Z	23	1	null	[ "safetensors", "qwen2", "merge", "mergekit", "lazymergekit", "Qwen/Qwen2.5-1.5B-Instruct", "base_model:Qwen/Qwen2.5-1.5B-Instruct", "base_model:finetune:Qwen/Qwen2.5-1.5B-Instruct", "region:us" ]	null	2024-10-11T02:35:24Z	--- base_model: - Qwen/Qwen2.5-1.5B-Instruct - Qwen/Qwen2.5-1.5B-Instruct - Qwen/Qwen2.5-1.5B-Instruct - Qwen/Qwen2.5-1.5B-Instruct - Qwen/Qwen2.5-1.5B-Instruct - Qwen/Qwen2.5-1.5B-Instruct - Qwen/Qwen2.5-1.5B-Instruct - Qwen/Qwen2.5-1.5B-Instruct - Qwen/Qwen2.5-1.5B-Instruct - Qwen/Qwen2.5-1.5B-Instruct - Qwen/Qwen2.5-1.5B-Instruct - Qwen/Qwen2.5-1.5B-Instruct - Qwen/Qwen2.5-1.5B-Instruct - Qwen/Qwen2.5-1.5B-Instruct - Qwen/Qwen2.5-1.5B-Instruct - Qwen/Qwen2.5-1.5B-Instruct - Qwen/Qwen2.5-1.5B-Instruct - Qwen/Qwen2.5-1.5B-Instruct - Qwen/Qwen2.5-1.5B-Instruct - Qwen/Qwen2.5-1.5B-Instruct - Qwen/Qwen2.5-1.5B-Instruct - Qwen/Qwen2.5-1.5B-Instruct - Qwen/Qwen2.5-1.5B-Instruct - Qwen/Qwen2.5-1.5B-Instruct - Qwen/Qwen2.5-1.5B-Instruct - Qwen/Qwen2.5-1.5B-Instruct tags: - merge - mergekit - lazymergekit - Qwen/Qwen2.5-1.5B-Instruct --- # Qwen2.5-2B-Instruct Qwen2.5-2B-Instruct is a merge of the following models using [LazyMergekit](https://colab.research.google.com/drive/1obulZ1ROXHjYLn6PPZJwRR6GzgQogxxb?usp=sharing): * [Qwen/Qwen2.5-1.5B-Instruct](https://huggingface.co/Qwen/Qwen2.5-1.5B-Instruct) * [Qwen/Qwen2.5-1.5B-Instruct](https://huggingface.co/Qwen/Qwen2.5-1.5B-Instruct) * [Qwen/Qwen2.5-1.5B-Instruct](https://huggingface.co/Qwen/Qwen2.5-1.5B-Instruct) * [Qwen/Qwen2.5-1.5B-Instruct](https://huggingface.co/Qwen/Qwen2.5-1.5B-Instruct) * [Qwen/Qwen2.5-1.5B-Instruct](https://huggingface.co/Qwen/Qwen2.5-1.5B-Instruct) * [Qwen/Qwen2.5-1.5B-Instruct](https://huggingface.co/Qwen/Qwen2.5-1.5B-Instruct) * [Qwen/Qwen2.5-1.5B-Instruct](https://huggingface.co/Qwen/Qwen2.5-1.5B-Instruct) * [Qwen/Qwen2.5-1.5B-Instruct](https://huggingface.co/Qwen/Qwen2.5-1.5B-Instruct) * [Qwen/Qwen2.5-1.5B-Instruct](https://huggingface.co/Qwen/Qwen2.5-1.5B-Instruct) * [Qwen/Qwen2.5-1.5B-Instruct](https://huggingface.co/Qwen/Qwen2.5-1.5B-Instruct) * [Qwen/Qwen2.5-1.5B-Instruct](https://huggingface.co/Qwen/Qwen2.5-1.5B-Instruct) * [Qwen/Qwen2.5-1.5B-Instruct](https://huggingface.co/Qwen/Qwen2.5-1.5B-Instruct) * [Qwen/Qwen2.5-1.5B-Instruct](https://huggingface.co/Qwen/Qwen2.5-1.5B-Instruct) * [Qwen/Qwen2.5-1.5B-Instruct](https://huggingface.co/Qwen/Qwen2.5-1.5B-Instruct) * [Qwen/Qwen2.5-1.5B-Instruct](https://huggingface.co/Qwen/Qwen2.5-1.5B-Instruct) * [Qwen/Qwen2.5-1.5B-Instruct](https://huggingface.co/Qwen/Qwen2.5-1.5B-Instruct) * [Qwen/Qwen2.5-1.5B-Instruct](https://huggingface.co/Qwen/Qwen2.5-1.5B-Instruct) * [Qwen/Qwen2.5-1.5B-Instruct](https://huggingface.co/Qwen/Qwen2.5-1.5B-Instruct) * [Qwen/Qwen2.5-1.5B-Instruct](https://huggingface.co/Qwen/Qwen2.5-1.5B-Instruct) * [Qwen/Qwen2.5-1.5B-Instruct](https://huggingface.co/Qwen/Qwen2.5-1.5B-Instruct) * [Qwen/Qwen2.5-1.5B-Instruct](https://huggingface.co/Qwen/Qwen2.5-1.5B-Instruct) * [Qwen/Qwen2.5-1.5B-Instruct](https://huggingface.co/Qwen/Qwen2.5-1.5B-Instruct) * [Qwen/Qwen2.5-1.5B-Instruct](https://huggingface.co/Qwen/Qwen2.5-1.5B-Instruct) * [Qwen/Qwen2.5-1.5B-Instruct](https://huggingface.co/Qwen/Qwen2.5-1.5B-Instruct) * [Qwen/Qwen2.5-1.5B-Instruct](https://huggingface.co/Qwen/Qwen2.5-1.5B-Instruct) * [Qwen/Qwen2.5-1.5B-Instruct](https://huggingface.co/Qwen/Qwen2.5-1.5B-Instruct) ## 🧩 Configuration ```yaml dtype: bfloat16 merge_method: passthrough slices: - sources: - layer_range: [0, 2] model: Qwen/Qwen2.5-1.5B-Instruct - sources: - layer_range: [1, 3] model: Qwen/Qwen2.5-1.5B-Instruct - sources: - layer_range: [2, 4] model: Qwen/Qwen2.5-1.5B-Instruct - sources: - layer_range: [3, 5] model: Qwen/Qwen2.5-1.5B-Instruct - sources: - layer_range: [4, 6] model: Qwen/Qwen2.5-1.5B-Instruct - sources: - layer_range: [5, 7] model: Qwen/Qwen2.5-1.5B-Instruct - sources: - layer_range: [6, 8] model: Qwen/Qwen2.5-1.5B-Instruct - sources: - layer_range: [7, 9] model: Qwen/Qwen2.5-1.5B-Instruct - sources: - layer_range: [8, 10] model: Qwen/Qwen2.5-1.5B-Instruct - sources: - layer_range: [9, 11] model: Qwen/Qwen2.5-1.5B-Instruct - sources: - layer_range: [10, 12] model: Qwen/Qwen2.5-1.5B-Instruct - sources: - layer_range: [11, 13] model: Qwen/Qwen2.5-1.5B-Instruct - sources: - layer_range: [12, 14] model: Qwen/Qwen2.5-1.5B-Instruct - sources: - layer_range: [13, 15] model: Qwen/Qwen2.5-1.5B-Instruct - sources: - layer_range: [14, 16] model: Qwen/Qwen2.5-1.5B-Instruct - sources: - layer_range: [16, 18] model: Qwen/Qwen2.5-1.5B-Instruct - sources: - layer_range: [17, 19] model: Qwen/Qwen2.5-1.5B-Instruct - sources: - layer_range: [18, 20] model: Qwen/Qwen2.5-1.5B-Instruct - sources: - layer_range: [19, 21] model: Qwen/Qwen2.5-1.5B-Instruct - sources: - layer_range: [20, 22] model: Qwen/Qwen2.5-1.5B-Instruct - sources: - layer_range: [21, 23] model: Qwen/Qwen2.5-1.5B-Instruct - sources: - layer_range: [22, 24] model: Qwen/Qwen2.5-1.5B-Instruct - sources: - layer_range: [23, 25] model: Qwen/Qwen2.5-1.5B-Instruct - sources: - layer_range: [24, 26] model: Qwen/Qwen2.5-1.5B-Instruct - sources: - layer_range: [25, 27] model: Qwen/Qwen2.5-1.5B-Instruct - sources: - layer_range: [26, 28] model: Qwen/Qwen2.5-1.5B-Instruct ``` ## 💻 Usage ```python !pip install -qU transformers accelerate from transformers import AutoTokenizer import transformers import torch model = "win10/Qwen2.5-2B-Instruct" messages = [{"role": "user", "content": "What is a large language model?"}] tokenizer = AutoTokenizer.from_pretrained(model) prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True) pipeline = transformers.pipeline( "text-generation", model=model, torch_dtype=torch.float16, device_map="auto", ) outputs = pipeline(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95) print(outputs[0]["generated_text"]) ```
ai2power/llama2-7b-hf-enron	ai2power	2024-10-11T02:21:31Z	5	0	transformers	[ "transformers", "safetensors", "llama", "text-generation", "arxiv:1910.09700", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]	text-generation	2024-10-07T06:33:30Z	--- library_name: transformers tags: [] --- # Model Card for Model ID <!-- Provide a quick summary of what the model is/does. --> ## Model Details ### Model Description <!-- Provide a longer summary of what this model is. --> This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated. - Developed by: [More Information Needed] - Funded by [optional]: [More Information Needed] - Shared by [optional]: [More Information Needed] - Model type: [More Information Needed] - Language(s) (NLP): [More Information Needed] - License: [More Information Needed] - Finetuned from model [optional]: [More Information Needed] ### Model Sources [optional] <!-- Provide the basic links for the model. --> - Repository: [More Information Needed] - Paper [optional]: [More Information Needed] - Demo [optional]: [More Information Needed] ## Uses <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. --> ### Direct Use <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. --> [More Information Needed] ### Downstream Use [optional] <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app --> [More Information Needed] ### Out-of-Scope Use <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. --> [More Information Needed] ## Bias, Risks, and Limitations <!-- This section is meant to convey both technical and sociotechnical limitations. --> [More Information Needed] ### Recommendations <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. --> Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. [More Information Needed] ## Training Details ### Training Data <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. --> [More Information Needed] ### Training Procedure <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. --> #### Preprocessing [optional] [More Information Needed] #### Training Hyperparameters - Training regime: [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision --> #### Speeds, Sizes, Times [optional] <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. --> [More Information Needed] ## Evaluation <!-- This section describes the evaluation protocols and provides the results. --> ### Testing Data, Factors & Metrics #### Testing Data <!-- This should link to a Dataset Card if possible. --> [More Information Needed] #### Factors <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. --> [More Information Needed] #### Metrics <!-- These are the evaluation metrics being used, ideally with a description of why. --> [More Information Needed] ### Results [More Information Needed] #### Summary ## Model Examination [optional] <!-- Relevant interpretability work for the model goes here --> [More Information Needed] ## Environmental Impact <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly --> Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). - Hardware Type: [More Information Needed] - Hours used: [More Information Needed] - Cloud Provider: [More Information Needed] - Compute Region: [More Information Needed] - Carbon Emitted: [More Information Needed] ## Technical Specifications [optional] ### Model Architecture and Objective [More Information Needed] ### Compute Infrastructure [More Information Needed] #### Hardware [More Information Needed] #### Software [More Information Needed] ## Citation [optional] <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. --> BibTeX: [More Information Needed] APA: [More Information Needed] ## Glossary [optional] <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. --> [More Information Needed] ## More Information [optional] [More Information Needed] ## Model Card Authors [optional] [More Information Needed] ## Model Card Contact [More Information Needed]
nasa-impact/nasa-smd-ibm-v0.1	nasa-impact	2024-10-11T02:15:20Z	254	32	transformers	[ "transformers", "pytorch", "roberta", "fill-mask", "earth science", "climate", "biology", "en", "dataset:nasa-impact/nasa-smd-IR-benchmark", "dataset:nasa-impact/nasa-smd-qa-benchmark", "dataset:ibm/Climate-Change-NER", "arxiv:2405.10725", "doi:10.57967/hf/1429", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "region:us" ]	fill-mask	2023-12-04T18:07:32Z	--- license: apache-2.0 language: - en library_name: transformers pipeline_tag: fill-mask tags: - earth science - climate - biology datasets: - nasa-impact/nasa-smd-IR-benchmark - nasa-impact/nasa-smd-qa-benchmark - ibm/Climate-Change-NER --- # Model Card for Indus (nasa-smd-ibm-v0.1) Indus (previously known as nasa-smd-ibm-v0.1) is a RoBERTa-based, Encoder-only transformer model, domain-adapted for NASA Science Mission Directorate (SMD) applications. It's fine-tuned on scientific journals and articles relevant to NASA SMD, aiming to enhance natural language technologies like information retrieval and intelligent search. ## Model Details - Base Model: RoBERTa - Tokenizer: Custom - Parameters: 125M - Pretraining Strategy: Masked Language Modeling (MLM) - Distilled Version: You can download a distilled version of the model (30 Million Parameters) here: https://huggingface.co/nasa-impact/nasa-smd-ibm-distil-v0.1 ## Training Data - Wikipedia English (Feb 1, 2020) - AGU Publications - AMS Publications - Scientific papers from Astrophysics Data Systems (ADS) - PubMed abstracts - PubMedCentral (PMC) (commercial license subset) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/61099e5d86580d4580767226/H0-q9N7IwXQqLdEaCCgm-.png) ## Training Procedure - Framework: fairseq 0.12.1 with PyTorch 1.9.1 - transformers Version: 4.2.0 - Strategy: Masked Language Modeling (MLM) ## Evaluation ### BLURB benchmark ![image/png](https://cdn-uploads.huggingface.co/production/uploads/61099e5d86580d4580767226/Ipw5xR99qUORGkn5Z8JkA.png) (Standard deviation across 10 random seeds in parenthesis. Macro avg. reported across datasets and micro avg. computed by averaging scores on each task then averaging across task averages.) ### Climate Change NER, and NASA-QA benchmark ![image/png](https://cdn-uploads.huggingface.co/production/uploads/61099e5d86580d4580767226/ncTupw9tNVf6pSBD5VnOh.png) (Climate Change NER and NASA-QA benchmark results. Standard Deviation over multiple runs given in parantheses) Please refer to the following dataset cards for further benchmarks and evaluation - NASA-IR Benchmark - https://huggingface.co/datasets/nasa-impact/nasa-smd-IR-benchmark - NASA-QA Benchmark - https://huggingface.co/datasets/nasa-impact/nasa-smd-qa-benchmark - Climate Change NER Benchmark - https://huggingface.co/datasets/ibm/Climate-Change-NER ## Uses - Named Entity Recognition (NER) - Information Retrieval - Sentence Transformers - Extractive QA For NASA SMD related, scientific usecases. ## Note Accompanying preprint paper can be found here: https://arxiv.org/abs/2405.10725. ## Citation If you find this work useful, please cite using the following bibtex citation: ```bibtex @misc {nasa-impact_2023, author = {Masayasu Maraoka and Bishwaranjan Bhattacharjee and Muthukumaran Ramasubramanian and Ikhsa Gurung and Rahul Ramachandran and Manil Maskey and Kaylin Bugbee and Rong Zhang and Yousef El Kurdi and Bharath Dandala and Mike Little and Elizabeth Fancher and Lauren Sanders and Sylvain Costes and Sergi Blanco-Cuaresma and Kelly Lockhart and Thomas Allen and Felix Grazes and Megan Ansdell and Alberto Accomazzi and Sanaz Vahidinia and Ryan McGranaghan and Armin Mehrabian and Tsendgar Lee}, title = { nasa-smd-ibm-v0.1 (Revision f01d42f) }, year = 2023, url = { https://huggingface.co/nasa-impact/nasa-smd-ibm-v0.1 }, doi = { 10.57967/hf/1429 }, publisher = { Hugging Face } } ``` ## Attribution IBM Research - Masayasu Muraoka - Bishwaranjan Bhattacharjee - Rong Zhang - Yousef El Kurdi - Bharath Dandala NASA SMD - Muthukumaran Ramasubramanian - Iksha Gurung - Rahul Ramachandran - Manil Maskey - Kaylin Bugbee - Mike Little - Elizabeth Fancher - Lauren Sanders - Sylvain Costes - Sergi Blanco-Cuaresma - Kelly Lockhart - Thomas Allen - Felix Grazes - Megan Ansdell - Alberto Accomazzi - Sanaz Vahidinia - Ryan McGranaghan - Armin Mehrabian - Tsendgar Lee ## Disclaimer This Encoder-only model is currently in an experimental phase. We are working to improve the model's capabilities and performance, and as we progress, we invite the community to engage with this model, provide feedback, and contribute to its evolution.
nasa-impact/nasa-smd-ibm-distil-v0.1	nasa-impact	2024-10-11T02:14:02Z	117	7	transformers	[ "transformers", "pytorch", "roberta", "fill-mask", "earth science", "climate", "biology", "en", "arxiv:2405.10725", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "region:us" ]	fill-mask	2024-05-21T18:41:13Z	--- license: apache-2.0 language: - en library_name: transformers pipeline_tag: fill-mask tags: - earth science - climate - biology --- # Model Card for INDUS-Small (nasa-smd-ibm-distil-v0.1) INDUS-Small(nasa-smd-ibm-distil-v0.1) is a distilled version of the RoBERTa-based, Encoder-only transformer model INDUS (nasa-impact/nasa-smd-ibm-v0.1), domain-adapted for NASA Science Mission Directorate (SMD) applications. It's fine-tuned on scientific journals and articles relevant to NASA SMD, aiming to enhance natural language technologies like information retrieval and intelligent search. We trained the smaller model, INDUS_SMALL, with 38M parameters through knowledge distillation techniques by using INDUS as the teacher. INDUS_SMALL follows a 4-layer architecture recommended by the Neural Architecture Search engine (Trivedi et al., 2023) with an optimal trade-off between performance and latency. We adopted the distillation objective proposed in MiniLMv2 (Wang et al., 2021) to transfer fine-grained self-attention relations, which has been shown to be the current state-of-the-art (Udagawa et al., 2023). Using this objective, we trained the model for 500K steps with an effective batch size of 480 on 30 V100 GPUs. ## Model Details - Base Model: INDUS - Tokenizer: Custom - Original version Parameters: 125M - Pretraining Strategy: Masked Language Modeling (MLM) - Distilled Version Parameters: 38 Million Parameters ## Training Data - Wikipedia English (Feb 1, 2020) - AGU Publications - AMS Publications - Scientific papers from Astrophysics Data Systems (ADS) - PubMed abstracts - PubMedCentral (PMC) (commercial license subset) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/61099e5d86580d4580767226/H0-q9N7IwXQqLdEaCCgm-.png) ## Training Procedure - Framework: fairseq 0.12.1 with PyTorch 1.9.1 - transformers Version: 4.2.0 - Strategy: Masked Language Modeling (MLM) ## Evaluation ### BLURB benchmark ![image/png](https://cdn-uploads.huggingface.co/production/uploads/61099e5d86580d4580767226/Ipw5xR99qUORGkn5Z8JkA.png) (Standard deviation across 10 random seeds in parenthesis. Macro avg. reported across datasets and micro avg. computed by averaging scores on each task then averaging across task averages.) ### Climate Change NER, and NASA-QA benchmark ![image/png](https://cdn-uploads.huggingface.co/production/uploads/61099e5d86580d4580767226/ncTupw9tNVf6pSBD5VnOh.png) (Climate Change NER and NASA-QA benchmark results. Standard Deviation over multiple runs given in parantheses) Please refer to the following dataset cards for further benchmarks and evaluation - NASA-IR Benchmark - https://huggingface.co/datasets/nasa-impact/nasa-smd-IR-benchmark - NASA-QA Benchmark - https://huggingface.co/datasets/nasa-impact/nasa-smd-qa-benchmark - Climate Change NER Benchmark - https://huggingface.co/datasets/ibm/Climate-Change-NER Please refer to the following dataset cards for benchmark evaluation - NASA IR Benchmark - https://huggingface.co/datasets/nasa-impact/nasa-smd-IR-benchmark - NASA SMD Expert QA Benchmark - https://huggingface.co/datasets/nasa-impact/nasa-smd-qa-benchmark - Climate CHange Benchmark - https://huggingface.co/datasets/ibm/Climate-Change-NER ## Uses - Named Entity Recognition (NER) - Information Retrieval - Sentence Transformers - Extractive QA For NASA SMD related, scientific usecases. ## Note This Model is released in support of the training and evaluation of the encoder language model ["Indus"](https://huggingface.co/nasa-impact/nasa-smd-ibm-v0.1). Accompanying paper can be found here: https://arxiv.org/abs/2405.10725 ## Citation If you find this work useful, please cite using the following bibtex citation: ```bibtex @misc {nasa-impact_2023, author = {Masayasu Maraoka and Bishwaranjan Bhattacharjee and Muthukumaran Ramasubramanian and Ikhsa Gurung and Rahul Ramachandran and Manil Maskey and Kaylin Bugbee and Rong Zhang and Yousef El Kurdi and Bharath Dandala and Mike Little and Elizabeth Fancher and Lauren Sanders and Sylvain Costes and Sergi Blanco-Cuaresma and Kelly Lockhart and Thomas Allen and Felix Grazes and Megan Ansdell and Alberto Accomazzi and Sanaz Vahidinia and Ryan McGranaghan and Armin Mehrabian and Tsendgar Lee}, title = { nasa-smd-ibm-v0.1 (Revision f01d42f) }, year = 2023, url = { https://huggingface.co/nasa-impact/nasa-smd-ibm-v0.1 }, doi = { 10.57967/hf/1429 }, publisher = { Hugging Face } } ``` ## Attribution IBM Research - Masayasu Muraoka - Bishwaranjan Bhattacharjee - Rong Zhang - Yousef El Kurdi - Bharath Dandala NASA SMD - Muthukumaran Ramasubramanian - Iksha Gurung - Rahul Ramachandran - Manil Maskey - Kaylin Bugbee - Mike Little - Elizabeth Fancher - Lauren Sanders - Sylvain Costes - Sergi Blanco-Cuaresma - Kelly Lockhart - Thomas Allen - Felix Grazes - Megan Ansdell - Alberto Accomazzi - Sanaz Vahidinia - Ryan McGranaghan - Armin Mehrabian - Tsendgar Lee ## Disclaimer This Encoder-only model is currently in an experimental phase. We are working to improve the model's capabilities and performance, and as we progress, we invite the community to engage with this model, provide feedback, and contribute to its evolution.
billingsmoore/tibetan-to-english-translation	billingsmoore	2024-10-11T02:12:35Z	130	0	transformers	[ "transformers", "safetensors", "t5", "text2text-generation", "tibetan", "english", "translation", "nlp", "buddhism", "dharma", "bo", "en", "dataset:billingsmoore/tibetan-to-english-translation-dataset", "base_model:billingsmoore/phonetic-tibetan-to-english-translation", "base_model:finetune:billingsmoore/phonetic-tibetan-to-english-translation", "license:cc", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]	translation	2024-09-30T20:26:33Z	--- base_model: - google-t5/t5-large - billingsmoore/phonetic-tibetan-to-english-translation datasets: - billingsmoore/tibetan-to-english-translation-dataset language: - bo - en library_name: transformers license: cc metrics: - bleu pipeline_tag: translation tags: - tibetan - english - translation - nlp - buddhism - dharma --- # Model Card for tibetan-to-english-translation This model is a neural machine translation model for translating Literary Tibetan to English. The model expects Tibetan text in either Tibetan script or transliterated according to THL Simplified Phonetic Transliteration as an input and outputs an English translation. The model was evaluated using the BLEU metric as implemented by [sacreBLEU](https://pypi.org/project/sacrebleu/), with a final score of 59.3431. This work is licensed under Creative Commons Attribution-NonCommercial 4.0 International ## Model Details ### Model Description This model is a finetuned T5 model with 770 million parameters. - Developed by: billingsmoore - Model type: [More Information Needed] - Language(s) (NLP): Tibetan, English - License: [Attribution-NonCommercial 4.0 International](https://creativecommons.org/licenses/by-nc/4.0/) - Finetuned from model [optional]: 'google-t5/t5-large' ### Model Sources [optional] - Repository: [MLotsawa on Github](https://github.com/billingsmoore/MLotsawa) ## Uses This model is intended to be used as the translation model in the larger MLotsawa software, but can also be used in a Jupyter notebook or Python script. ### Direct Use To use this model for translation you can use the following code: ```python from transformers import pipeline translator = pipeline('translation', 'billingsmoore/tibetan-to-english-translation') input_text = <your transliterated Tibetan text> translation = translator(input_text) print(translation) ``` ### Downstream Use The model can be further finetuned using the following code: ```python from datasets import load_dataset from transformers import ( AutoTokenizer, DataCollatorForSeq2Seq, AutoModelForSeq2SeqLM, Seq2SeqTrainingArguments, Seq2SeqTrainer, EarlyStoppingCallback, Adafactor ) import evaluate import numpy as np from accelerate import Accelerator data = load_dataset(<path_to_your_dataset>) checkpoint = "billingsmoore/tibetan-to-english-translation" tokenizer = AutoTokenizer.from_pretrained(checkpoint) data_collator = DataCollatorForSeq2Seq(tokenizer=tokenizer, model=checkpoint) source_lang = 'bo' target_lang = 'en' prefix = "translate Tibetan to English: " def preprocess_function(examples): inputs = [prefix + example[source_lang] for example in examples['translation']] targets = [example[target_lang] for example in examples['translation']] model_inputs = tokenizer(inputs, text_target=targets, max_length=128, truncation=True) return model_inputs tokenized_dataset = dataset.map(preprocess_function, batched=True) metric = evaluate.load("sacrebleu") def postprocess_text(preds, labels): preds = [pred.strip() for pred in preds] labels = [[label.strip()] for label in labels] return preds, labels def compute_metrics(eval_preds): preds, labels = eval_preds if isinstance(preds, tuple): preds = preds[0] decoded_preds = tokenizer.batch_decode(preds, skip_special_tokens=True) labels = np.where(labels != -100, labels, tokenizer.pad_token_id) decoded_labels = tokenizer.batch_decode(labels, skip_special_tokens=True) decoded_preds, decoded_labels = postprocess_text(decoded_preds, decoded_labels) result = metric.compute(predictions=decoded_preds, references=decoded_labels) result = {"bleu": result["score"]} prediction_lens = [np.count_nonzero(pred != tokenizer.pad_token_id) for pred in preds] result["gen_len"] = np.mean(prediction_lens) result = {k: round(v, 4) for k, v in result.items()} return result early_stop = EarlyStoppingCallback() model = AutoModelForSeq2SeqLM.from_pretrained(checkpoint, device_map="auto") optimizer = Adafactor( model.parameters(), scale_parameter=True, relative_step=False, warmup_init=False, lr=3e-4 ) training_args = Seq2SeqTrainingArguments( output_dir=".", auto_find_batch_size=True, predict_with_generate=True, fp16=False, #check this push_to_hub=False, eval_strategy='epoch', save_strategy='epoch', load_best_model_at_end=True ) trainer = Seq2SeqTrainer( model=model, args=training_args, train_dataset=tokenized_dataset['train'], eval_dataset=tokenized_dataset['test'], tokenizer=tokenizer, optimizers=(optimizer, None), data_collator=data_collator, compute_metrics=compute_metrics, callbacks=[early_stop] ) trainer.train() ``` ## Training Details ### Training Data [Training Data for this project is available here.](https://www.kaggle.com/datasets/billingsmoore/classical-tibetan-to-english-translation-dataset) This dataset consists of 100,000 pairs of sentences or phrases. The first member of each pair is a sentence or phrase in Classical Tibetan. The second member is the English translation of the first. The pairs are pulled from texts sourced from Lotsawa House (lotsawahouse.org) and are offered under the same license as the original texts they provided. This data was scraped, cleaned, and formatted programmatically. ### Training Procedure The t5 tokenizer was updated in the same manner as ['billingsmoore/tibetan-phonetic-transliteration'](https://huggingface.co/billingsmoore/tibetan-phonetic-transliteration), the procedure for which can be found on that model card. Beyond the training for ['billingsmoore/phonetic-tibetan-to-english-translation'](https://huggingface.co/billingsmoore/phonetic-tibetan-to-english-translation) whose full training is described in its model card, this model was trained for 9 epochs on the dataset ['billingsmoore/tibetan-to-english-translation-dataset'](https://huggingface.co/datasets/billingsmoore/tibetan-to-english-translation-dataset) #### Training Hyperparameters - This model was trained using the Adafactor optimizer with a learning rate of 2e-5. ## Evaluation The evaluation metric for this model was the BLEU score as implemented by [sacreBLEU](https://pypi.org/project/sacrebleu/). BLEU (Bilingual Evaluation Understudy) scores measure the quality of machine-generated translations by comparing them to human-provided reference translations. The score ranges from 0 to 100, where 100 represents a perfect match with the reference translations. It evaluates the precision of n-grams (word sequences) in the generated text, with higher scores indicating closer alignment to the reference translations. A brevity penalty is applied to discourage translations that are too short. The final BLEU score was 59.3431.
nasa-impact/nasa-smd-ibm-st-v2	nasa-impact	2024-10-11T02:10:50Z	230	9	sentence-transformers	[ "sentence-transformers", "pytorch", "roberta", "earth science", "climate", "biology", "sentence-similarity", "en", "arxiv:2405.10725", "doi:10.57967/hf/1800", "license:apache-2.0", "autotrain_compatible", "text-embeddings-inference", "endpoints_compatible", "region:us" ]	sentence-similarity	2024-02-20T22:02:14Z	--- license: apache-2.0 language: - en library_name: sentence-transformers tags: - earth science - climate - biology pipeline_tag: sentence-similarity --- # Model Card for Indus-Retriever Indus-Retriever (`nasa-smd-ibm-st-v2`) is a Bi-encoder sentence transformer model, that is fine-tuned from nasa-smd-ibm-v0.1 encoder model. it is an updated version of `nasa-smd-ibm-st` with better performance (shown below). It's trained with 271 million examples along with a domain-specific dataset of 2.6 million examples from documents curated by NASA Science Mission Directorate (SMD). With this model, we aim to enhance natural language technologies like information retrieval and intelligent search as it applies to SMD NLP applications. you can also use distilled version of the model here: https://huggingface.co/nasa-impact/nasa-ibm-st.38m ## Model Details - Base Encoder Model: [INDUS](https://huggingface.co/nasa-impact/nasa-smd-ibm-v0.1) - Tokenizer: Custom - Parameters: 125M - Training Strategy: Sentence Pairs, and score indicating relevancy. The model encodes the two sentence pairs independently and cosine similarity is calculated. the similarity is optimized using the relevance score. ## Training Data ![image/png](https://cdn-uploads.huggingface.co/production/uploads/61099e5d86580d4580767226/ZjcHW24iKsvUYBhoL7eMM.png) Figure: Open dataset sources for sentence transformers (269M in total) Additionally, 2.6M abstract + title pairs collected from NASA SMD documents. ## Training Procedure - Framework: PyTorch 1.9.1 - sentence-transformers version: 4.30.2 - Strategy: Sentence Pairs ## Evaluation Following models are evaluated: 1. All-MiniLM-l6-v2 [sentence-transformers/all-MiniLM-L6-v2] 2. BGE-base [BAAI/bge-base-en-v1.5] 3. RoBERTa-base [roberta-base] 4. nasa-smd-ibm-rtvr_v0.1 [nasa-impact/nasa-smd-ibm-st] ![image/png](https://cdn-uploads.huggingface.co/production/uploads/61099e5d86580d4580767226/JWQ652ODzfmnRjj_b8ZTw.png) Figure: [BEIR](https://github.com/beir-cellar/beir) and [NASA-IR](https://huggingface.co/datasets/nasa-impact/nasa-smd-IR-benchmark) Evaluation Metrics ## Uses - Information Retreival - Sentence Similarity Search For NASA SMD related, scientific usecases. ### Usage ```python from sentence_transformers import SentenceTransformer, Util model = SentenceTransformer("nasa-impact/nasa-smd-ibm-st-v2") input_queries = [ 'query: how much protein should a female eat', 'query: summit define'] input_passages = [ "As a general guideline, the CDC's average requirement of protein for women ages 19 to 70 is 46 grams per day. But, as you can see from this chart, you'll need to increase that if you're expecting or training for a marathon. Check out the chart below to see how much protein you should be eating each day.", "Definition of summit for English Language Learners. : 1 the highest point of a mountain : the top of a mountain. : 2 the highest level. : 3 a meeting or series of meetings between the leaders of two or more governments."] query_embeddings = model.encode(input_queries) passage_embeddings = model.encode(input_passages) print(util.cos_sim(query_embeddings, passage_embeddings)) ``` # Note This Sentence Transformer Model is released in support of the training and evaluation of the encoder language model ["Indus"](https://huggingface.co/nasa-impact/nasa-smd-ibm-v0.1). Accompanying paper can be found here: https://arxiv.org/abs/2405.10725 ## Citation If you find this work useful, please cite using the following bibtex citation: ```bibtex @misc {nasa-impact_2024, author = { {NASA-IMPACT} }, title = { nasa-smd-ibm-st-v2 (Revision d249d84) }, year = 2024, url = { https://huggingface.co/nasa-impact/nasa-smd-ibm-st-v2 }, doi = { 10.57967/hf/1800 }, publisher = { Hugging Face } } ``` ## Attribution IBM Research - Aashka Trivedi - Masayasu Muraoka - Bishwaranjan Bhattacharjee NASA SMD - Muthukumaran Ramasubramanian - Iksha Gurung - Rahul Ramachandran - Manil Maskey - Kaylin Bugbee - Mike Little - Elizabeth Fancher - Lauren Sanders - Sylvain Costes - Sergi Blanco-Cuaresma - Kelly Lockhart - Thomas Allen - Felix Grazes - Megan Ansdell - Alberto Accomazzi - Sanaz Vahidinia - Ryan McGranaghan - Armin Mehrabian - Tsendgar Lee ## Disclaimer This sentence-transformer model is currently in an experimental phase. We are working to improve the model's capabilities and performance, and as we progress, we invite the community to engage with this model, provide feedback, and contribute to its evolution.
RichardErkhov/DeepAutoAI_-_Explore_Llama-3.1-8B-Inst-gguf	RichardErkhov	2024-10-11T02:09:37Z	18	0	null	[ "gguf", "arxiv:1910.09700", "endpoints_compatible", "region:us", "conversational" ]	null	2024-10-11T00:01:45Z	Quantization made by Richard Erkhov. [Github](https://github.com/RichardErkhov) [Discord](https://discord.gg/pvy7H8DZMG) [Request more models](https://github.com/RichardErkhov/quant_request) Explore_Llama-3.1-8B-Inst - GGUF - Model creator: https://huggingface.co/DeepAutoAI/ - Original model: https://huggingface.co/DeepAutoAI/Explore_Llama-3.1-8B-Inst/ \| Name \| Quant method \| Size \| \| ---- \| ---- \| ---- \| \| [Explore_Llama-3.1-8B-Inst.Q2_K.gguf](https://huggingface.co/RichardErkhov/DeepAutoAI_-_Explore_Llama-3.1-8B-Inst-gguf/blob/main/Explore_Llama-3.1-8B-Inst.Q2_K.gguf) \| Q2_K \| 2.96GB \| \| [Explore_Llama-3.1-8B-Inst.IQ3_XS.gguf](https://huggingface.co/RichardErkhov/DeepAutoAI_-_Explore_Llama-3.1-8B-Inst-gguf/blob/main/Explore_Llama-3.1-8B-Inst.IQ3_XS.gguf) \| IQ3_XS \| 3.28GB \| \| [Explore_Llama-3.1-8B-Inst.IQ3_S.gguf](https://huggingface.co/RichardErkhov/DeepAutoAI_-_Explore_Llama-3.1-8B-Inst-gguf/blob/main/Explore_Llama-3.1-8B-Inst.IQ3_S.gguf) \| IQ3_S \| 3.43GB \| \| [Explore_Llama-3.1-8B-Inst.Q3_K_S.gguf](https://huggingface.co/RichardErkhov/DeepAutoAI_-_Explore_Llama-3.1-8B-Inst-gguf/blob/main/Explore_Llama-3.1-8B-Inst.Q3_K_S.gguf) \| Q3_K_S \| 3.41GB \| \| [Explore_Llama-3.1-8B-Inst.IQ3_M.gguf](https://huggingface.co/RichardErkhov/DeepAutoAI_-_Explore_Llama-3.1-8B-Inst-gguf/blob/main/Explore_Llama-3.1-8B-Inst.IQ3_M.gguf) \| IQ3_M \| 3.52GB \| \| [Explore_Llama-3.1-8B-Inst.Q3_K.gguf](https://huggingface.co/RichardErkhov/DeepAutoAI_-_Explore_Llama-3.1-8B-Inst-gguf/blob/main/Explore_Llama-3.1-8B-Inst.Q3_K.gguf) \| Q3_K \| 3.74GB \| \| [Explore_Llama-3.1-8B-Inst.Q3_K_M.gguf](https://huggingface.co/RichardErkhov/DeepAutoAI_-_Explore_Llama-3.1-8B-Inst-gguf/blob/main/Explore_Llama-3.1-8B-Inst.Q3_K_M.gguf) \| Q3_K_M \| 3.74GB \| \| [Explore_Llama-3.1-8B-Inst.Q3_K_L.gguf](https://huggingface.co/RichardErkhov/DeepAutoAI_-_Explore_Llama-3.1-8B-Inst-gguf/blob/main/Explore_Llama-3.1-8B-Inst.Q3_K_L.gguf) \| Q3_K_L \| 4.03GB \| \| [Explore_Llama-3.1-8B-Inst.IQ4_XS.gguf](https://huggingface.co/RichardErkhov/DeepAutoAI_-_Explore_Llama-3.1-8B-Inst-gguf/blob/main/Explore_Llama-3.1-8B-Inst.IQ4_XS.gguf) \| IQ4_XS \| 4.18GB \| \| [Explore_Llama-3.1-8B-Inst.Q4_0.gguf](https://huggingface.co/RichardErkhov/DeepAutoAI_-_Explore_Llama-3.1-8B-Inst-gguf/blob/main/Explore_Llama-3.1-8B-Inst.Q4_0.gguf) \| Q4_0 \| 4.34GB \| \| [Explore_Llama-3.1-8B-Inst.IQ4_NL.gguf](https://huggingface.co/RichardErkhov/DeepAutoAI_-_Explore_Llama-3.1-8B-Inst-gguf/blob/main/Explore_Llama-3.1-8B-Inst.IQ4_NL.gguf) \| IQ4_NL \| 4.38GB \| \| [Explore_Llama-3.1-8B-Inst.Q4_K_S.gguf](https://huggingface.co/RichardErkhov/DeepAutoAI_-_Explore_Llama-3.1-8B-Inst-gguf/blob/main/Explore_Llama-3.1-8B-Inst.Q4_K_S.gguf) \| Q4_K_S \| 4.37GB \| \| [Explore_Llama-3.1-8B-Inst.Q4_K.gguf](https://huggingface.co/RichardErkhov/DeepAutoAI_-_Explore_Llama-3.1-8B-Inst-gguf/blob/main/Explore_Llama-3.1-8B-Inst.Q4_K.gguf) \| Q4_K \| 4.58GB \| \| [Explore_Llama-3.1-8B-Inst.Q4_K_M.gguf](https://huggingface.co/RichardErkhov/DeepAutoAI_-_Explore_Llama-3.1-8B-Inst-gguf/blob/main/Explore_Llama-3.1-8B-Inst.Q4_K_M.gguf) \| Q4_K_M \| 4.58GB \| \| [Explore_Llama-3.1-8B-Inst.Q4_1.gguf](https://huggingface.co/RichardErkhov/DeepAutoAI_-_Explore_Llama-3.1-8B-Inst-gguf/blob/main/Explore_Llama-3.1-8B-Inst.Q4_1.gguf) \| Q4_1 \| 4.78GB \| \| [Explore_Llama-3.1-8B-Inst.Q5_0.gguf](https://huggingface.co/RichardErkhov/DeepAutoAI_-_Explore_Llama-3.1-8B-Inst-gguf/blob/main/Explore_Llama-3.1-8B-Inst.Q5_0.gguf) \| Q5_0 \| 5.21GB \| \| [Explore_Llama-3.1-8B-Inst.Q5_K_S.gguf](https://huggingface.co/RichardErkhov/DeepAutoAI_-_Explore_Llama-3.1-8B-Inst-gguf/blob/main/Explore_Llama-3.1-8B-Inst.Q5_K_S.gguf) \| Q5_K_S \| 5.21GB \| \| [Explore_Llama-3.1-8B-Inst.Q5_K.gguf](https://huggingface.co/RichardErkhov/DeepAutoAI_-_Explore_Llama-3.1-8B-Inst-gguf/blob/main/Explore_Llama-3.1-8B-Inst.Q5_K.gguf) \| Q5_K \| 5.34GB \| \| [Explore_Llama-3.1-8B-Inst.Q5_K_M.gguf](https://huggingface.co/RichardErkhov/DeepAutoAI_-_Explore_Llama-3.1-8B-Inst-gguf/blob/main/Explore_Llama-3.1-8B-Inst.Q5_K_M.gguf) \| Q5_K_M \| 5.34GB \| \| [Explore_Llama-3.1-8B-Inst.Q5_1.gguf](https://huggingface.co/RichardErkhov/DeepAutoAI_-_Explore_Llama-3.1-8B-Inst-gguf/blob/main/Explore_Llama-3.1-8B-Inst.Q5_1.gguf) \| Q5_1 \| 5.65GB \| \| [Explore_Llama-3.1-8B-Inst.Q6_K.gguf](https://huggingface.co/RichardErkhov/DeepAutoAI_-_Explore_Llama-3.1-8B-Inst-gguf/blob/main/Explore_Llama-3.1-8B-Inst.Q6_K.gguf) \| Q6_K \| 6.14GB \| \| [Explore_Llama-3.1-8B-Inst.Q8_0.gguf](https://huggingface.co/RichardErkhov/DeepAutoAI_-_Explore_Llama-3.1-8B-Inst-gguf/blob/main/Explore_Llama-3.1-8B-Inst.Q8_0.gguf) \| Q8_0 \| 7.95GB \| Original model description: --- library_name: transformers tags: [] model-index: - name: Explore_Llama-3.1-8B-Inst results: - task: type: text-generation name: Text Generation dataset: name: IFEval (0-Shot) type: HuggingFaceH4/ifeval args: num_few_shot: 0 metrics: - type: inst_level_strict_acc and prompt_level_strict_acc value: 77.95 name: strict accuracy source: url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=DeepAutoAI/Explore_Llama-3.1-8B-Inst name: Open LLM Leaderboard - task: type: text-generation name: Text Generation dataset: name: BBH (3-Shot) type: BBH args: num_few_shot: 3 metrics: - type: acc_norm value: 30.39 name: normalized accuracy source: url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=DeepAutoAI/Explore_Llama-3.1-8B-Inst name: Open LLM Leaderboard - task: type: text-generation name: Text Generation dataset: name: MATH Lvl 5 (4-Shot) type: hendrycks/competition_math args: num_few_shot: 4 metrics: - type: exact_match value: 17.52 name: exact match source: url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=DeepAutoAI/Explore_Llama-3.1-8B-Inst name: Open LLM Leaderboard - task: type: text-generation name: Text Generation dataset: name: GPQA (0-shot) type: Idavidrein/gpqa args: num_few_shot: 0 metrics: - type: acc_norm value: 4.47 name: acc_norm source: url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=DeepAutoAI/Explore_Llama-3.1-8B-Inst name: Open LLM Leaderboard - task: type: text-generation name: Text Generation dataset: name: MuSR (0-shot) type: TAUR-Lab/MuSR args: num_few_shot: 0 metrics: - type: acc_norm value: 9.64 name: acc_norm source: url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=DeepAutoAI/Explore_Llama-3.1-8B-Inst name: Open LLM Leaderboard - task: type: text-generation name: Text Generation dataset: name: MMLU-PRO (5-shot) type: TIGER-Lab/MMLU-Pro config: main split: test args: num_few_shot: 5 metrics: - type: acc value: 31.02 name: accuracy source: url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=DeepAutoAI/Explore_Llama-3.1-8B-Inst name: Open LLM Leaderboard --- # Model Card for Model ID ## Overview DeepAutoAI/Explore_Llama-3.1-8B-Inst is developed by deepAuto.ai by learning the distribution of llama-3.1-8B-instruct. Our approach leverages the base model’s pretrained weights and optimizes them for the Winogrande and ARC-Challenge datasets by training a latent diffusion model on the pretrained weights. specifically , this model is based on learning the distrinution of transformer layers from 16 to 31. Through this process, we learn the distribution of the base model's weight space, enabling us to explore optimal configurations. We then sample multiple sets of weights, using the model-soup averaging technique to identify the best-performing weights for both datasets. These weights are merged using linear interpolation to create the final model weights for DeepAutoAI/Explore_Llama-3.1-8B-Inst. This approach has led to improved performance on previously unseen leaderboard tasks, all without any additional task-specific training. The work is currently in progress ## Model Details <!-- Provide a longer summary of what this model is. --> We trained a diffusion model to learn the distribution of subset of llama to enable generation weights that improve the performance. We generate task specific weights on winogrande and arc_challenge then transfer the best model for leaderboard benchmarking. - Developed by: DeepAuto.ai - Funded by [optional]: DeepAuto.ai - Shared by [optional]: DeepAuto.ai - Model type: llama-3.1-8B - Language(s) (NLP): English - License: 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 - Finetuned from model [optional]: No fine-tuning ### Model Sources [optional] <!-- Provide the basic links for the model. --> - Repository: Under construction - Paper [optional]: To be announce ## Uses <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. --> <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. --> The direct use case of our work is o improve existing model performance as well as generating task specific weights with no training. <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app --> Performance improvement of existing large models with limited compute ### Out-of-Scope Use <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. --> No fine-tuning or architecture generalization ## Bias, Risks, and Limitations <!-- This section is meant to convey both technical and sociotechnical limitations. --> Using a generative model to produce weights can potentially lead to unintended or undesirable outputs. However, the generated content will still fall within the range of what the base model is inherently capable of producing. ## How to Get Started with the Model The work is under progress ## Training Details We employed a latent diffusion process on pretrained model weights, unlocking the ability to generate diverse, previously unseen neural networks. Remarkably, even within the constraints of one-shot learning, our approach consistently produces a wide range of weight variations, each offering distinct performance characteristics. These generated weights not only open opportunities for weight averaging and model merging but also have the potential to significantly enhance model performance. Moreover, they enable the creation of task-specific weights, tailored to optimize performance for specialized applications ### Training Data The training data used to produced the current model is the base pretrained weights <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. --> ### Training Procedure <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. --> - We selected a set of layers and combined their pretrained weights, then trained a Variational Autoencoder (VAE) to encode these weights into the layer dimension. - We conditionally trained a diffusion model on this set of weights, allowing individual sampling of layer-specific weights. - All selected layers were encoded into a 1024-dimensional space. This model exclusively contained the sampled weights for layer normalization." <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. --> ## Evaluation <!-- This section describes the evaluation protocols and provides the results. --> ### Testing Data, Factors & Metrics <!-- This should link to a Dataset Card if possible. --> We test our method on Winogrande and arc_challenge, and hellaswag #### Factors <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. --> [More Information Needed] #### Metrics <!-- These are the evaluation metrics being used, ideally with a description of why. --> [More Information Needed] ### Results [More Information Needed] #### Summary ## Model Examination [optional] <!-- Relevant interpretability work for the model goes here --> [More Information Needed] ## Environmental Impact <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly --> Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). - Hardware Type: Nvidia-A100-80Gb - Hours used: VAE is trained for 4 hour and diffusion process 4 hours - Compute Region: South Korea - Carbon Emitted: 0.96kg ## Technical Specifications [optional] ### Model Architecture and Objective We used Latent diffusion for weights generation, and llama3-1-8B as target architectures. The primary objective of this weight generation process was to demonstrate that by learning only the distribution of few layers weights9normlaization layers in this case) in an 8-billion-parameter model, it is possible to significantly enhance the model's capabilities. Notably, this is achieved using a fraction of the computational resources and without the need for fine-tuning, showcasing the efficiency and potential of this approach. ### Compute Infrastructure Nvidia-A100 cluster #### Hardware A single Nvidia-A100 #### Software Model is tested using lm-harness tool version 0.4.3 ## Citation [optional] <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. --> BibTeX: [More Information Needed] APA: [More Information Needed] ## Glossary [optional] <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. --> [More Information Needed] ## More Information [optional] [More Information Needed] ## Model Card Authors [optional] [More Information Needed] ## Model Card Contact For any question contact deepauto.ai # [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard) Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_DeepAutoAI__Explore_Llama-3.1-8B-Inst) \| Metric \|Value\| \|-------------------\|----:\| \|Avg. \|28.50\| \|IFEval (0-Shot) \|77.95\| \|BBH (3-Shot) \|30.39\| \|MATH Lvl 5 (4-Shot)\|17.52\| \|GPQA (0-shot) \| 4.47\| \|MuSR (0-shot) \| 9.64\| \|MMLU-PRO (5-shot) \|31.02\|
mav23/Qwen2.5-3B-Instruct-GGUF	mav23	2024-10-11T01:28:11Z	25	0	transformers	[ "transformers", "gguf", "chat", "text-generation", "en", "arxiv:2407.10671", "base_model:Qwen/Qwen2.5-3B", "base_model:quantized:Qwen/Qwen2.5-3B", "license:other", "endpoints_compatible", "region:us", "conversational" ]	text-generation	2024-10-11T01:02:03Z	--- license: other license_name: qwen-research license_link: https://huggingface.co/Qwen/Qwen2.5-3B-Instruct/blob/main/LICENSE language: - en pipeline_tag: text-generation base_model: Qwen/Qwen2.5-3B tags: - chat library_name: transformers --- # Qwen2.5-3B-Instruct ## Introduction Qwen2.5 is the latest series of Qwen large language models. For Qwen2.5, we release a number of base language models and instruction-tuned language models ranging from 0.5 to 72 billion parameters. Qwen2.5 brings the following improvements upon Qwen2: - Significantly more knowledge and has greatly improved capabilities in coding and mathematics, thanks to our specialized expert models in these domains. - Significant improvements in instruction following, generating long texts (over 8K tokens), understanding structured data (e.g, tables), and generating structured outputs especially JSON. More resilient to the diversity of system prompts, enhancing role-play implementation and condition-setting for chatbots. - Long-context Support up to 128K tokens and can generate up to 8K tokens. - Multilingual support for over 29 languages, including Chinese, English, French, Spanish, Portuguese, German, Italian, Russian, Japanese, Korean, Vietnamese, Thai, Arabic, and more. This repo contains the instruction-tuned 3B Qwen2.5 model, which has the following features: - Type: Causal Language Models - Training Stage: Pretraining & Post-training - Architecture: transformers with RoPE, SwiGLU, RMSNorm, Attention QKV bias and tied word embeddings - Number of Parameters: 3.09B - Number of Paramaters (Non-Embedding): 2.77B - Number of Layers: 36 - Number of Attention Heads (GQA): 16 for Q and 2 for KV - Context Length: Full 32,768 tokens and generation 8192 tokens For more details, please refer to our [blog](https://qwenlm.github.io/blog/qwen2.5/), [GitHub](https://github.com/QwenLM/Qwen2.5), and [Documentation](https://qwen.readthedocs.io/en/latest/). ## Requirements The code of Qwen2.5 has been in the latest Hugging face `transformers` and we advise you to use the latest version of `transformers`. With `transformers<4.37.0`, you will encounter the following error: ``` KeyError: 'qwen2' ``` ## Quickstart Here provides a code snippet with `apply_chat_template` to show you how to load the tokenizer and model and how to generate contents. ```python from transformers import AutoModelForCausalLM, AutoTokenizer model_name = "Qwen/Qwen2.5-3B-Instruct" model = AutoModelForCausalLM.from_pretrained( model_name, torch_dtype="auto", device_map="auto" ) tokenizer = AutoTokenizer.from_pretrained(model_name) prompt = "Give me a short introduction to large language model." messages = [ {"role": "system", "content": "You are Qwen, created by Alibaba Cloud. You are a helpful assistant."}, {"role": "user", "content": prompt} ] text = tokenizer.apply_chat_template( messages, tokenize=False, add_generation_prompt=True ) model_inputs = tokenizer([text], return_tensors="pt").to(model.device) generated_ids = model.generate( **model_inputs, max_new_tokens=512 ) generated_ids = [ output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids) ] response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0] ``` ## Evaluation & Performance Detailed evaluation results are reported in this [📑 blog](https://qwenlm.github.io/blog/qwen2.5/). For requirements on GPU memory and the respective throughput, see results [here](https://qwen.readthedocs.io/en/latest/benchmark/speed_benchmark.html). ## Citation If you find our work helpful, feel free to give us a cite. ``` @misc{qwen2.5, title = {Qwen2.5: A Party of Foundation Models}, url = {https://qwenlm.github.io/blog/qwen2.5/}, author = {Qwen Team}, month = {September}, year = {2024} } @article{qwen2, title={Qwen2 Technical Report}, author={An Yang and Baosong Yang and Binyuan Hui and Bo Zheng and Bowen Yu and Chang Zhou and Chengpeng Li and Chengyuan Li and Dayiheng Liu and Fei Huang and Guanting Dong and Haoran Wei and Huan Lin and Jialong Tang and Jialin Wang and Jian Yang and Jianhong Tu and Jianwei Zhang and Jianxin Ma and Jin Xu and Jingren Zhou and Jinze Bai and Jinzheng He and Junyang Lin and Kai Dang and Keming Lu and Keqin Chen and Kexin Yang and Mei Li and Mingfeng Xue and Na Ni and Pei Zhang and Peng Wang and Ru Peng and Rui Men and Ruize Gao and Runji Lin and Shijie Wang and Shuai Bai and Sinan Tan and Tianhang Zhu and Tianhao Li and Tianyu Liu and Wenbin Ge and Xiaodong Deng and Xiaohuan Zhou and Xingzhang Ren and Xinyu Zhang and Xipin Wei and Xuancheng Ren and Yang Fan and Yang Yao and Yichang Zhang and Yu Wan and Yunfei Chu and Yuqiong Liu and Zeyu Cui and Zhenru Zhang and Zhihao Fan}, journal={arXiv preprint arXiv:2407.10671}, year={2024} } ```
ZeroXClem/Llama3.1-BestMix-Chem-Einstein-8B-Q4_0-GGUF	ZeroXClem	2024-10-11T01:23:38Z	36	1	null	[ "gguf", "merge", "TIES", "Llama3", "BestMix", "Chemistry", "Einstein", "instruction-following", "conversational", "long-form-generation", "scientific", "llama-cpp", "gguf-my-repo", "base_model:ZeroXClem/Llama3.1-BestMix-Chem-Einstein-8B", "base_model:quantized:ZeroXClem/Llama3.1-BestMix-Chem-Einstein-8B", "license:apache-2.0", "endpoints_compatible", "region:us" ]	null	2024-10-11T01:23:17Z	--- base_model: ZeroXClem/Llama3.1-BestMix-Chem-Einstein-8B license: apache-2.0 tags: - merge - TIES - Llama3 - BestMix - Chemistry - Einstein - instruction-following - conversational - long-form-generation - scientific - llama-cpp - gguf-my-repo --- # ZeroXClem/Llama3.1-BestMix-Chem-Einstein-8B-Q4_0-GGUF This model was converted to GGUF format from [`ZeroXClem/Llama3.1-BestMix-Chem-Einstein-8B`](https://huggingface.co/ZeroXClem/Llama3.1-BestMix-Chem-Einstein-8B) using llama.cpp via the ggml.ai's [GGUF-my-repo](https://huggingface.co/spaces/ggml-org/gguf-my-repo) space. Refer to the [original model card](https://huggingface.co/ZeroXClem/Llama3.1-BestMix-Chem-Einstein-8B) for more details on the model. ## Use with llama.cpp Install llama.cpp through brew (works on Mac and Linux) ```bash brew install llama.cpp ``` Invoke the llama.cpp server or the CLI. ### CLI: ```bash llama-cli --hf-repo ZeroXClem/Llama3.1-BestMix-Chem-Einstein-8B-Q4_0-GGUF --hf-file llama3.1-bestmix-chem-einstein-8b-q4_0.gguf -p "The meaning to life and the universe is" ``` ### Server: ```bash llama-server --hf-repo ZeroXClem/Llama3.1-BestMix-Chem-Einstein-8B-Q4_0-GGUF --hf-file llama3.1-bestmix-chem-einstein-8b-q4_0.gguf -c 2048 ``` Note: You can also use this checkpoint directly through the [usage steps](https://github.com/ggerganov/llama.cpp?tab=readme-ov-file#usage) listed in the Llama.cpp repo as well. Step 1: Clone llama.cpp from GitHub. ``` git clone https://github.com/ggerganov/llama.cpp ``` Step 2: Move into the llama.cpp folder and build it with `LLAMA_CURL=1` flag along with other hardware-specific flags (for ex: LLAMA_CUDA=1 for Nvidia GPUs on Linux). ``` cd llama.cpp && LLAMA_CURL=1 make ``` Step 3: Run inference through the main binary. ``` ./llama-cli --hf-repo ZeroXClem/Llama3.1-BestMix-Chem-Einstein-8B-Q4_0-GGUF --hf-file llama3.1-bestmix-chem-einstein-8b-q4_0.gguf -p "The meaning to life and the universe is" ``` or ``` ./llama-server --hf-repo ZeroXClem/Llama3.1-BestMix-Chem-Einstein-8B-Q4_0-GGUF --hf-file llama3.1-bestmix-chem-einstein-8b-q4_0.gguf -c 2048 ```
RichardErkhov/Casual-Autopsy_-_Halu-L3-Stheno-BlackOasis-8B-gguf	RichardErkhov	2024-10-11T01:18:48Z	276	1	null	[ "gguf", "endpoints_compatible", "region:us", "conversational" ]	null	2024-10-10T23:06:49Z	Quantization made by Richard Erkhov. [Github](https://github.com/RichardErkhov) [Discord](https://discord.gg/pvy7H8DZMG) [Request more models](https://github.com/RichardErkhov/quant_request) Halu-L3-Stheno-BlackOasis-8B - GGUF - Model creator: https://huggingface.co/Casual-Autopsy/ - Original model: https://huggingface.co/Casual-Autopsy/Halu-L3-Stheno-BlackOasis-8B/ \| Name \| Quant method \| Size \| \| ---- \| ---- \| ---- \| \| [Halu-L3-Stheno-BlackOasis-8B.Q2_K.gguf](https://huggingface.co/RichardErkhov/Casual-Autopsy_-_Halu-L3-Stheno-BlackOasis-8B-gguf/blob/main/Halu-L3-Stheno-BlackOasis-8B.Q2_K.gguf) \| Q2_K \| 2.96GB \| \| [Halu-L3-Stheno-BlackOasis-8B.IQ3_XS.gguf](https://huggingface.co/RichardErkhov/Casual-Autopsy_-_Halu-L3-Stheno-BlackOasis-8B-gguf/blob/main/Halu-L3-Stheno-BlackOasis-8B.IQ3_XS.gguf) \| IQ3_XS \| 3.28GB \| \| [Halu-L3-Stheno-BlackOasis-8B.IQ3_S.gguf](https://huggingface.co/RichardErkhov/Casual-Autopsy_-_Halu-L3-Stheno-BlackOasis-8B-gguf/blob/main/Halu-L3-Stheno-BlackOasis-8B.IQ3_S.gguf) \| IQ3_S \| 3.43GB \| \| [Halu-L3-Stheno-BlackOasis-8B.Q3_K_S.gguf](https://huggingface.co/RichardErkhov/Casual-Autopsy_-_Halu-L3-Stheno-BlackOasis-8B-gguf/blob/main/Halu-L3-Stheno-BlackOasis-8B.Q3_K_S.gguf) \| Q3_K_S \| 3.41GB \| \| [Halu-L3-Stheno-BlackOasis-8B.IQ3_M.gguf](https://huggingface.co/RichardErkhov/Casual-Autopsy_-_Halu-L3-Stheno-BlackOasis-8B-gguf/blob/main/Halu-L3-Stheno-BlackOasis-8B.IQ3_M.gguf) \| IQ3_M \| 3.52GB \| \| [Halu-L3-Stheno-BlackOasis-8B.Q3_K.gguf](https://huggingface.co/RichardErkhov/Casual-Autopsy_-_Halu-L3-Stheno-BlackOasis-8B-gguf/blob/main/Halu-L3-Stheno-BlackOasis-8B.Q3_K.gguf) \| Q3_K \| 3.74GB \| \| [Halu-L3-Stheno-BlackOasis-8B.Q3_K_M.gguf](https://huggingface.co/RichardErkhov/Casual-Autopsy_-_Halu-L3-Stheno-BlackOasis-8B-gguf/blob/main/Halu-L3-Stheno-BlackOasis-8B.Q3_K_M.gguf) \| Q3_K_M \| 3.74GB \| \| [Halu-L3-Stheno-BlackOasis-8B.Q3_K_L.gguf](https://huggingface.co/RichardErkhov/Casual-Autopsy_-_Halu-L3-Stheno-BlackOasis-8B-gguf/blob/main/Halu-L3-Stheno-BlackOasis-8B.Q3_K_L.gguf) \| Q3_K_L \| 4.03GB \| \| [Halu-L3-Stheno-BlackOasis-8B.IQ4_XS.gguf](https://huggingface.co/RichardErkhov/Casual-Autopsy_-_Halu-L3-Stheno-BlackOasis-8B-gguf/blob/main/Halu-L3-Stheno-BlackOasis-8B.IQ4_XS.gguf) \| IQ4_XS \| 4.18GB \| \| [Halu-L3-Stheno-BlackOasis-8B.Q4_0.gguf](https://huggingface.co/RichardErkhov/Casual-Autopsy_-_Halu-L3-Stheno-BlackOasis-8B-gguf/blob/main/Halu-L3-Stheno-BlackOasis-8B.Q4_0.gguf) \| Q4_0 \| 4.34GB \| \| [Halu-L3-Stheno-BlackOasis-8B.IQ4_NL.gguf](https://huggingface.co/RichardErkhov/Casual-Autopsy_-_Halu-L3-Stheno-BlackOasis-8B-gguf/blob/main/Halu-L3-Stheno-BlackOasis-8B.IQ4_NL.gguf) \| IQ4_NL \| 4.38GB \| \| [Halu-L3-Stheno-BlackOasis-8B.Q4_K_S.gguf](https://huggingface.co/RichardErkhov/Casual-Autopsy_-_Halu-L3-Stheno-BlackOasis-8B-gguf/blob/main/Halu-L3-Stheno-BlackOasis-8B.Q4_K_S.gguf) \| Q4_K_S \| 4.37GB \| \| [Halu-L3-Stheno-BlackOasis-8B.Q4_K.gguf](https://huggingface.co/RichardErkhov/Casual-Autopsy_-_Halu-L3-Stheno-BlackOasis-8B-gguf/blob/main/Halu-L3-Stheno-BlackOasis-8B.Q4_K.gguf) \| Q4_K \| 4.58GB \| \| [Halu-L3-Stheno-BlackOasis-8B.Q4_K_M.gguf](https://huggingface.co/RichardErkhov/Casual-Autopsy_-_Halu-L3-Stheno-BlackOasis-8B-gguf/blob/main/Halu-L3-Stheno-BlackOasis-8B.Q4_K_M.gguf) \| Q4_K_M \| 4.58GB \| \| [Halu-L3-Stheno-BlackOasis-8B.Q4_1.gguf](https://huggingface.co/RichardErkhov/Casual-Autopsy_-_Halu-L3-Stheno-BlackOasis-8B-gguf/blob/main/Halu-L3-Stheno-BlackOasis-8B.Q4_1.gguf) \| Q4_1 \| 4.78GB \| \| [Halu-L3-Stheno-BlackOasis-8B.Q5_0.gguf](https://huggingface.co/RichardErkhov/Casual-Autopsy_-_Halu-L3-Stheno-BlackOasis-8B-gguf/blob/main/Halu-L3-Stheno-BlackOasis-8B.Q5_0.gguf) \| Q5_0 \| 5.21GB \| \| [Halu-L3-Stheno-BlackOasis-8B.Q5_K_S.gguf](https://huggingface.co/RichardErkhov/Casual-Autopsy_-_Halu-L3-Stheno-BlackOasis-8B-gguf/blob/main/Halu-L3-Stheno-BlackOasis-8B.Q5_K_S.gguf) \| Q5_K_S \| 5.21GB \| \| [Halu-L3-Stheno-BlackOasis-8B.Q5_K.gguf](https://huggingface.co/RichardErkhov/Casual-Autopsy_-_Halu-L3-Stheno-BlackOasis-8B-gguf/blob/main/Halu-L3-Stheno-BlackOasis-8B.Q5_K.gguf) \| Q5_K \| 5.34GB \| \| [Halu-L3-Stheno-BlackOasis-8B.Q5_K_M.gguf](https://huggingface.co/RichardErkhov/Casual-Autopsy_-_Halu-L3-Stheno-BlackOasis-8B-gguf/blob/main/Halu-L3-Stheno-BlackOasis-8B.Q5_K_M.gguf) \| Q5_K_M \| 5.34GB \| \| [Halu-L3-Stheno-BlackOasis-8B.Q5_1.gguf](https://huggingface.co/RichardErkhov/Casual-Autopsy_-_Halu-L3-Stheno-BlackOasis-8B-gguf/blob/main/Halu-L3-Stheno-BlackOasis-8B.Q5_1.gguf) \| Q5_1 \| 5.65GB \| \| [Halu-L3-Stheno-BlackOasis-8B.Q6_K.gguf](https://huggingface.co/RichardErkhov/Casual-Autopsy_-_Halu-L3-Stheno-BlackOasis-8B-gguf/blob/main/Halu-L3-Stheno-BlackOasis-8B.Q6_K.gguf) \| Q6_K \| 6.14GB \| \| [Halu-L3-Stheno-BlackOasis-8B.Q8_0.gguf](https://huggingface.co/RichardErkhov/Casual-Autopsy_-_Halu-L3-Stheno-BlackOasis-8B-gguf/blob/main/Halu-L3-Stheno-BlackOasis-8B.Q8_0.gguf) \| Q8_0 \| 7.95GB \| Original model description: --- tags: - merge - mergekit - lazymergekit - not-for-all-audiences license: llama3 language: - en library_name: transformers pipeline_tag: text-generation base_model: - grimjim/Llama-3-Oasis-v1-OAS-8B - Hastagaras/Halu-8B-Llama3-Blackroot - Sao10K/L3-8B-Stheno-v3.2 --- # Halu-L3-Stheno-BlackOasis-8B Halu-L3-Stheno-BlackOasis-8B is a merge of the following models using [LazyMergekit](https://colab.research.google.com/drive/1obulZ1ROXHjYLn6PPZJwRR6GzgQogxxb?usp=sharing): * [Sao10K/L3-8B-Stheno-v3.2](https://huggingface.co/Sao10K/L3-8B-Stheno-v3.2) * [grimjim/Llama-3-Oasis-v1-OAS-8B](https://huggingface.co/grimjim/Llama-3-Oasis-v1-OAS-8B) * [Hastagaras/Halu-8B-Llama3-Blackroot](https://huggingface.co/Hastagaras/Halu-8B-Llama3-Blackroot) * [Sao10K/L3-8B-Stheno-v3.2](https://huggingface.co/Sao10K/L3-8B-Stheno-v3.2) ## 🧩 Configuration ```yaml models: - model: grimjim/Llama-3-Oasis-v1-OAS-8B - model: Hastagaras/Halu-8B-Llama3-Blackroot - model: Sao10K/L3-8B-Stheno-v3.2 merge_method: model_stock base_model: Sao10K/L3-8B-Stheno-v3.2 dtype: bfloat16 ``` ## 💻 Usage ```python !pip install -qU transformers accelerate from transformers import AutoTokenizer import transformers import torch model = "Casual-Autopsy/Halu-L3-Stheno-BlackOasis-8B" messages = [{"role": "user", "content": "What is a large language model?"}] tokenizer = AutoTokenizer.from_pretrained(model) prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True) pipeline = transformers.pipeline( "text-generation", model=model, torch_dtype=torch.float16, device_map="auto", ) outputs = pipeline(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95) print(outputs[0]["generated_text"]) ```
kbulutozler/distilbert-base-uncased-FT-ner-NCBI-disease	kbulutozler	2024-10-11T01:17:44Z	198	0	transformers	[ "transformers", "safetensors", "distilbert", "token-classification", "NCBI-disease", "NER", "en", "base_model:distilbert/distilbert-base-uncased", "base_model:finetune:distilbert/distilbert-base-uncased", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "region:us" ]	token-classification	2024-10-11T01:13:19Z	--- library_name: transformers tags: - NCBI-disease - NER license: apache-2.0 language: - en metrics: - seqeval base_model: - distilbert/distilbert-base-uncased --- # Model Card for Model ID Fine-tuned distilbert model. Trained on train set of NCBI-disease dataset taken from [BLURB](https://microsoft.github.io/BLURB/tasks.html). ## Model Details ### Model Sources [optional] <!-- Provide the basic links for the model. --> - Repository: https://github.com/kbulutozler/medical-llm-benchmark ## Training Details ### Training Data <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. --> Train set of NCBI-disease dataset. ### Training Procedure <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. --> Classical fine-tuning. #### Training Hyperparameters - Training regime: [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision --> learning_rate=5e-5 per_device_train_batch_size=16 per_device_eval_batch_size=16 num_train_epochs=3 weight_decay=0.01 ## Evaluation <!-- This section describes the evaluation protocols and provides the results. --> #### Testing Data <!-- This should link to a Dataset Card if possible. --> Test set of NCBI-disease dataset. ### Results Precision: 0.81 Recall: 0.86 Micro-F1: 0.84 ## Environmental Impact <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly --> - Hardware Type: 1xRTX A4000 - Hours used: 00:06:00
TroyDoesAI/BlackSheep-5B	TroyDoesAI	2024-10-11T01:16:41Z	8	0	transformers	[ "transformers", "safetensors", "llama", "text-generation", "mergekit", "merge", "conversational", "base_model:TroyDoesAI/BlackSheep-RAG-5B", "base_model:merge:TroyDoesAI/BlackSheep-RAG-5B", "base_model:TroyDoesAI/Llama-3.2-4B", "base_model:merge:TroyDoesAI/Llama-3.2-4B", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]	text-generation	2024-10-11T00:43:37Z	--- base_model: - TroyDoesAI/Llama-3.2-4B - TroyDoesAI/BlackSheep-RAG-4B library_name: transformers tags: - mergekit - merge --- # BlackSheep This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit). ## Merge Details ### Merge Method This model was merged using the SLERP merge method. ### Models Merged The following models were included in the merge: * [TroyDoesAI/Llama-3.2-4B](https://huggingface.co/TroyDoesAI/Llama-3.2-4B) * [TroyDoesAI/BlackSheep-RAG-4B](https://huggingface.co/TroyDoesAI/BlackSheep-RAG-4B) ### Configuration The following YAML configuration was used to produce this model: ```yaml slices: - sources: - model: TroyDoesAI/BlackSheep-RAG-4B layer_range: [0, 42] - model: TroyDoesAI/Llama-3.2-4B layer_range: [0, 42] merge_method: slerp base_model: TroyDoesAI/Llama-3.2-4B parameters: t: - filter: self_attn value: [0, 0.5, 0.3, 0.7, 1] - filter: mlp value: [1, 0.5, 0.7, 0.3, 0] - value: 0.50 # fallback for rest of tensors dtype: bfloat16 ```
haorandai/png_randomnoise_fruit_solid_gray_20_with20constraints	haorandai	2024-10-11T01:14:48Z	29	0	diffusers	[ "diffusers", "tensorboard", "safetensors", "stable-diffusion", "stable-diffusion-diffusers", "text-to-image", "diffusers-training", "base_model:CompVis/stable-diffusion-v1-4", "base_model:finetune:CompVis/stable-diffusion-v1-4", "license:creativeml-openrail-m", "autotrain_compatible", "endpoints_compatible", "diffusers:StableDiffusionPipeline", "region:us" ]	text-to-image	2024-10-11T01:10:26Z	--- base_model: CompVis/stable-diffusion-v1-4 library_name: diffusers license: creativeml-openrail-m tags: - stable-diffusion - stable-diffusion-diffusers - text-to-image - diffusers - diffusers-training inference: true --- <!-- This model card has been generated automatically according to the information the training script had access to. You should probably proofread and complete it, then remove this comment. --> # Text-to-image finetuning - haorandai/png_randomnoise_fruit_solid_gray_20_with20constraints This pipeline was finetuned from CompVis/stable-diffusion-v1-4 on the haorandai/png_randomnoise_fruit_solid_gray_20_with20constraints dataset. Below are some example images generated with the finetuned pipeline using the following prompts: None: ## Pipeline usage You can use the pipeline like so: ```python from diffusers import DiffusionPipeline import torch pipeline = DiffusionPipeline.from_pretrained("haorandai/png_randomnoise_fruit_solid_gray_20_with20constraints", torch_dtype=torch.float16) prompt = "None" image = pipeline(prompt).images[0] image.save("my_image.png") ``` ## Training info These are the key hyperparameters used during training: * Epochs: 20 * Learning rate: 1e-05 * Batch size: 1 * Gradient accumulation steps: 4 * Image resolution: 224 * Mixed-precision: fp16 ## Intended uses & limitations #### How to use ```python # TODO: add an example code snippet for running this diffusion pipeline ``` #### Limitations and bias [TODO: provide examples of latent issues and potential remediations] ## Training details [TODO: describe the data used to train the model]

Subsets and Splits