Upload XLMRobertaForSequenceClassification

config.json

@@ -11,398 +11,402 @@
   "hidden_dropout_prob": 0.1,
   "hidden_size": 768,
   "id2label": {
-    "0": "Afrikaans",
-    "1": "Ainu",
-    "2": "Albanian",
-    "3": "Algerian Arabic",
-    "4": "Amharic",
-    "5": "Arabic",
-    "6": "Aragonese",
-    "7": "Armenian",
-    "8": "Assamese",
-    "9": "Asturian",
-    "10": "Awadhi",
-    "11": "Azerbaijani",
-    "12": "Baluchi",
-    "13": "Banjar",
-    "14": "Bashkir",
-    "15": "Basque",
-    "16": "Bavarian",
-    "17": "Belarusian",
-    "18": "Bengali",
-    "19": "Berber languages",
-    "20": "Bosnian",
-    "21": "Breton",
-    "22": "Brithenig",
-    "23": "Bulgarian",
-    "24": "Buriat",
-    "25": "Burmese",
-    "26": "Cantonese",
-    "27": "Catalan",
-    "28": "Cebuano",
-    "29": "Central Dusun",
-    "30": "Central Kanuri",
-    "31": "Chamorro",
-    "32": "Choctaw",
-    "33": "Chukot",
-    "34": "Chuvash",
-    "35": "Coastal Kadazan",
-    "36": "Congo Swahili",
-    "37": "Cornish",
-    "38": "Creek",
-    "39": "Crimean Turkish",
-    "40": "Croatian",
-    "41": "Czech",
-    "42": "Danish",
-    "43": "Dutch",
-    "44": "Eastern Mari",
-    "45": "Egyptian Arabic",
-    "46": "Emilian-Romagnol",
-    "47": "English",
-    "48": "Estonian",
-    "49": "Evenki",
-    "50": "Faroese",
-    "51": "Finnish",
-    "52": "French",
-    "53": "Galician",
-    "54": "Georgian",
-    "55": "German",
-    "56": "Gondi",
-    "57": "Guadeloupean Creole French",
-    "58": "Guarani",
-    "59": "Gujarati",
-    "60": "Gulf Arabic",
-    "61": "Hausa",
-    "62": "Hawaiian",
-    "63": "Hebrew",
-    "64": "Hindi",
-    "65": "Ho",
-    "66": "Hungarian",
-    "67": "Hunsrik",
-    "68": "Icelandic",
-    "69": "Iloko",
-    "70": "Indonesian",
-    "71": "Iranian Persian",
-    "72": "Irish",
-    "73": "Italian",
-    "74": "Japanese",
-    "75": "Javanese",
-    "76": "Kabyle",
-    "77": "Kalaallisut",
-    "78": "Kalmyk",
-    "79": "Kannada",
-    "80": "Karachay-Balkar",
-    "81": "Karelian",
-    "82": "Kashubian",
-    "83": "Kazakh",
-    "84": "Khasi",
-    "85": "Khmer",
-    "86": "Korean",
-    "87": "Kumyk",
-    "88": "Kven Finnish",
-    "89": "Kyrgyz",
-    "90": "Ladino",
-    "91": "Lao",
-    "92": "Latgalian",
-    "93": "Lhunda",
-    "94": "Ligurian",
-    "95": "Lingala",
-    "96": "Lingua Franca Nova",
-    "97": "Lithuanian",
-    "98": "Low German",
-    "99": "Lower Sorbian",
-    "100": "Luxembourgish",
-    "101": "Macedonian",
-    "102": "Malay (individual language)",
-    "103": "Malayalam",
-    "104": "Maltese",
-    "105": "Mandarin Chinese",
-    "106": "Maori",
-    "107": "Marathi",
-    "108": "Mikasuki",
-    "109": "Minangkabau",
-    "110": "Mingrelian",
-    "111": "Modern Greek",
-    "112": "Mongolian",
-    "113": "Nahuatl languages",
-    "114": "Nepali (individual language)",
-    "115": "Nogai",
-    "116": "North Frisian",
-    "117": "North Levantine Arabic",
-    "118": "North Moluccan Malay",
-    "119": "Northern Kurdish",
-    "120": "Northern Sami",
-    "121": "Norwegian Bokm\u00e5l",
-    "122": "Norwegian Nynorsk",
-    "123": "Nuer",
-    "124": "Occitan",
-    "125": "Old Tupi",
-    "126": "Oriya",
-    "127": "Ossetian",
-    "128": "Pampanga",
-    "129": "Pattani Malay",
-    "130": "Picard",
-    "131": "Piedmontese",
-    "132": "Polish",
-    "133": "Portuguese",
-    "134": "Punjabi",
-    "135": "Quechua",
-    "136": "Rohingya",
-    "137": "Romanian",
-    "138": "Romany",
-    "139": "Rundi",
-    "140": "Russian",
-    "141": "Rusyn",
-    "142": "Sakha",
-    "143": "Santali",
-    "144": "Scottish Gaelic",
-    "145": "Seraiki",
-    "146": "Serbian",
-    "147": "Slovak",
-    "148": "Slovenian",
-    "149": "Sorani Kurdish",
-    "150": "Southern Kurdish",
-    "151": "Spanish",
-    "152": "Sranan Tongo",
-    "153": "Standard Latvian",
-    "154": "Standard Malay",
-    "155": "Standard Moroccan Tamazight",
-    "156": "Swabian",
-    "157": "Swahili",
-    "158": "Swedish",
-    "159": "Swiss German",
-    "160": "Tachawit",
-    "161": "Tachelhit",
-    "162": "Tagalog",
-    "163": "Tahitian",
-    "164": "Tamil",
-    "165": "Tarifit",
-    "166": "Tase Naga",
-    "167": "Tatar",
-    "168": "Telugu",
-    "169": "Tetum",
-    "170": "Thai",
-    "171": "Tigrinya",
-    "172": "Tigr\u00e9",
-    "173": "Tok Pisin",
-    "174": "Turkish",
-    "175": "Turkmen",
-    "176": "Udmurt",
-    "177": "Ukrainian",
-    "178": "Upper Sorbian",
-    "179": "Urdu",
-    "180": "Uyghur",
-    "181": "Uzbek",
-    "182": "Venetian",
-    "183": "Vietnamese",
-    "184": "Waray-Waray",
-    "185": "Wayuu",
-    "186": "Welsh",
-    "187": "Western Frisian",
-    "188": "Wolof",
-    "189": "Wu Chinese",
-    "190": "Xhosa",
-    "191": "Yiddish",
-    "192": "Zamboanga Chavacano",
-    "193": "Zaza"
+    "0": "Ainu",
+    "1": "Algerian Arabic",
+    "2": "Asturian",
+    "3": "Awadhi",
+    "4": "Baluchi",
+    "5": "Banjar",
+    "6": "Bavarian",
+    "7": "Berber languages",
+    "8": "Brithenig",
+    "9": "Buriat",
+    "10": "Cantonese",
+    "11": "Cebuano",
+    "12": "Central Dusun",
+    "13": "Central Kanuri",
+    "14": "Choctaw",
+    "15": "Chukot",
+    "16": "Coastal Kadazan",
+    "17": "Congo Swahili",
+    "18": "Creek",
+    "19": "Crimean Turkish",
+    "20": "Eastern Mari",
+    "21": "Egyptian Arabic",
+    "22": "Emilian-Romagnol",
+    "23": "Evenki",
+    "24": "Gondi",
+    "25": "Guadeloupean Creole French",
+    "26": "Gulf Arabic",
+    "27": "Hawaiian",
+    "28": "Ho",
+    "29": "Hunsrik",
+    "30": "Iloko",
+    "31": "Iranian Persian",
+    "32": "Kabyle",
+    "33": "Kalmyk",
+    "34": "Karachay-Balkar",
+    "35": "Karelian",
+    "36": "Kashubian",
+    "37": "Khasi",
+    "38": "Khmer",
+    "39": "Kumyk",
+    "40": "Kven Finnish",
+    "41": "Kyrgyz",
+    "42": "Ladino",
+    "43": "Latgalian",
+    "44": "Lhunda",
+    "45": "Ligurian",
+    "46": "Lingua Franca Nova",
+    "47": "Low German",
+    "48": "Lower Sorbian",
+    "49": "Malay (individual language)",
+    "50": "Mikasuki",
+    "51": "Minangkabau",
+    "52": "Mingrelian",
+    "53": "Modern Greek",
+    "54": "Nahuatl languages",
+    "55": "Nepali (individual language)",
+    "56": "Nogai",
+    "57": "North Frisian",
+    "58": "North Levantine Arabic",
+    "59": "North Moluccan Malay",
+    "60": "Northern Kurdish",
+    "61": "Nuer",
+    "62": "Occitan",
+    "63": "Old Tupi",
+    "64": "Oriya",
+    "65": "Pampanga",
+    "66": "Pattani Malay",
+    "67": "Picard",
+    "68": "Piedmontese",
+    "69": "Punjabi",
+    "70": "Rohingya",
+    "71": "Romany",
+    "72": "Rusyn",
+    "73": "Sakha",
+    "74": "Santali",
+    "75": "Seraiki",
+    "76": "Sorani Kurdish",
+    "77": "Southern Kurdish",
+    "78": "Sranan Tongo",
+    "79": "Standard Latvian",
+    "80": "Standard Malay",
+    "81": "Standard Moroccan Tamazight",
+    "82": "Swabian",
+    "83": "Swahili",
+    "84": "Swiss German",
+    "85": "Tachawit",
+    "86": "Tachelhit",
+    "87": "Tarifit",
+    "88": "Tase Naga",
+    "89": "Tetum",
+    "90": "Tigr\u00e9",
+    "91": "Tok Pisin",
+    "92": "Udmurt",
+    "93": "Upper Sorbian",
+    "94": "Uyghur",
+    "95": "Venetian",
+    "96": "Waray-Waray",
+    "97": "Wayuu",
+    "98": "Wu Chinese",
+    "99": "Zamboanga Chavacano",
+    "100": "Zaza",
+    "101": "af",
+    "102": "am",
+    "103": "an",
+    "104": "ar",
+    "105": "as",
+    "106": "az",
+    "107": "ba",
+    "108": "be",
+    "109": "bg",
+    "110": "bn",
+    "111": "br",
+    "112": "bs",
+    "113": "ca",
+    "114": "ch",
+    "115": "cs",
+    "116": "cv",
+    "117": "cy",
+    "118": "da",
+    "119": "de",
+    "120": "el",
+    "121": "en",
+    "122": "es",
+    "123": "et",
+    "124": "eu",
+    "125": "fi",
+    "126": "fo",
+    "127": "fr",
+    "128": "fy",
+    "129": "ga",
+    "130": "gd",
+    "131": "gl",
+    "132": "gn",
+    "133": "gu",
+    "134": "ha",
+    "135": "he",
+    "136": "hi",
+    "137": "hr",
+    "138": "hu",
+    "139": "hy",
+    "140": "id",
+    "141": "is",
+    "142": "it",
+    "143": "ja",
+    "144": "jv",
+    "145": "ka",
+    "146": "kk",
+    "147": "kl",
+    "148": "kn",
+    "149": "ko",
+    "150": "kw",
+    "151": "lb",
+    "152": "ln",
+    "153": "lo",
+    "154": "lt",
+    "155": "mi",
+    "156": "mk",
+    "157": "ml",
+    "158": "mn",
+    "159": "mr",
+    "160": "mt",
+    "161": "my",
+    "162": "nb",
+    "163": "nl",
+    "164": "nn",
+    "165": "os",
+    "166": "pl",
+    "167": "pt",
+    "168": "qu",
+    "169": "rn",
+    "170": "ro",
+    "171": "ru",
+    "172": "se",
+    "173": "sk",
+    "174": "sl",
+    "175": "sq",
+    "176": "sr",
+    "177": "sv",
+    "178": "sw",
+    "179": "ta",
+    "180": "te",
+    "181": "th",
+    "182": "ti",
+    "183": "tk",
+    "184": "tl",
+    "185": "tr",
+    "186": "tt",
+    "187": "ty",
+    "188": "uk",
+    "189": "ur",
+    "190": "uz",
+    "191": "vi",
+    "192": "wo",
+    "193": "xh",
+    "194": "yi",
+    "195": "zh"
   },
   "initializer_range": 0.02,
   "intermediate_size": 3072,
   "label2id": {
-    "Afrikaans": 0,
-    "Ainu": 1,
-    "Albanian": 2,
-    "Algerian Arabic": 3,
-    "Amharic": 4,
-    "Arabic": 5,
-    "Aragonese": 6,
-    "Armenian": 7,
-    "Assamese": 8,
-    "Asturian": 9,
-    "Awadhi": 10,
-    "Azerbaijani": 11,
-    "Baluchi": 12,
-    "Banjar": 13,
-    "Bashkir": 14,
-    "Basque": 15,
-    "Bavarian": 16,
-    "Belarusian": 17,
-    "Bengali": 18,
-    "Berber languages": 19,
-    "Bosnian": 20,
-    "Breton": 21,
-    "Brithenig": 22,
-    "Bulgarian": 23,
-    "Buriat": 24,
-    "Burmese": 25,
-    "Cantonese": 26,
-    "Catalan": 27,
-    "Cebuano": 28,
-    "Central Dusun": 29,
-    "Central Kanuri": 30,
-    "Chamorro": 31,
-    "Choctaw": 32,
-    "Chukot": 33,
-    "Chuvash": 34,
-    "Coastal Kadazan": 35,
-    "Congo Swahili": 36,
-    "Cornish": 37,
-    "Creek": 38,
-    "Crimean Turkish": 39,
-    "Croatian": 40,
-    "Czech": 41,
-    "Danish": 42,
-    "Dutch": 43,
-    "Eastern Mari": 44,
-    "Egyptian Arabic": 45,
-    "Emilian-Romagnol": 46,
-    "English": 47,
-    "Estonian": 48,
-    "Evenki": 49,
-    "Faroese": 50,
-    "Finnish": 51,
-    "French": 52,
-    "Galician": 53,
-    "Georgian": 54,
-    "German": 55,
-    "Gondi": 56,
-    "Guadeloupean Creole French": 57,
-    "Guarani": 58,
-    "Gujarati": 59,
-    "Gulf Arabic": 60,
-    "Hausa": 61,
-    "Hawaiian": 62,
-    "Hebrew": 63,
-    "Hindi": 64,
-    "Ho": 65,
-    "Hungarian": 66,
-    "Hunsrik": 67,
-    "Icelandic": 68,
-    "Iloko": 69,
-    "Indonesian": 70,
-    "Iranian Persian": 71,
-    "Irish": 72,
-    "Italian": 73,
-    "Japanese": 74,
-    "Javanese": 75,
-    "Kabyle": 76,
-    "Kalaallisut": 77,
-    "Kalmyk": 78,
-    "Kannada": 79,
-    "Karachay-Balkar": 80,
-    "Karelian": 81,
-    "Kashubian": 82,
-    "Kazakh": 83,
-    "Khasi": 84,
-    "Khmer": 85,
-    "Korean": 86,
-    "Kumyk": 87,
-    "Kven Finnish": 88,
-    "Kyrgyz": 89,
-    "Ladino": 90,
-    "Lao": 91,
-    "Latgalian": 92,
-    "Lhunda": 93,
-    "Ligurian": 94,
-    "Lingala": 95,
-    "Lingua Franca Nova": 96,
-    "Lithuanian": 97,
-    "Low German": 98,
-    "Lower Sorbian": 99,
-    "Luxembourgish": 100,
-    "Macedonian": 101,
-    "Malay (individual language)": 102,
-    "Malayalam": 103,
-    "Maltese": 104,
-    "Mandarin Chinese": 105,
-    "Maori": 106,
-    "Marathi": 107,
-    "Mikasuki": 108,
-    "Minangkabau": 109,
-    "Mingrelian": 110,
-    "Modern Greek": 111,
-    "Mongolian": 112,
-    "Nahuatl languages": 113,
-    "Nepali (individual language)": 114,
-    "Nogai": 115,
-    "North Frisian": 116,
-    "North Levantine Arabic": 117,
-    "North Moluccan Malay": 118,
-    "Northern Kurdish": 119,
-    "Northern Sami": 120,
-    "Norwegian Bokm\u00e5l": 121,
-    "Norwegian Nynorsk": 122,
-    "Nuer": 123,
-    "Occitan": 124,
-    "Old Tupi": 125,
-    "Oriya": 126,
-    "Ossetian": 127,
-    "Pampanga": 128,
-    "Pattani Malay": 129,
-    "Picard": 130,
-    "Piedmontese": 131,
-    "Polish": 132,
-    "Portuguese": 133,
-    "Punjabi": 134,
-    "Quechua": 135,
-    "Rohingya": 136,
-    "Romanian": 137,
-    "Romany": 138,
-    "Rundi": 139,
-    "Russian": 140,
-    "Rusyn": 141,
-    "Sakha": 142,
-    "Santali": 143,
-    "Scottish Gaelic": 144,
-    "Seraiki": 145,
-    "Serbian": 146,
-    "Slovak": 147,
-    "Slovenian": 148,
-    "Sorani Kurdish": 149,
-    "Southern Kurdish": 150,
-    "Spanish": 151,
-    "Sranan Tongo": 152,
-    "Standard Latvian": 153,
-    "Standard Malay": 154,
-    "Standard Moroccan Tamazight": 155,
-    "Swabian": 156,
-    "Swahili": 157,
-    "Swedish": 158,
-    "Swiss German": 159,
-    "Tachawit": 160,
-    "Tachelhit": 161,
-    "Tagalog": 162,
-    "Tahitian": 163,
-    "Tamil": 164,
-    "Tarifit": 165,
-    "Tase Naga": 166,
-    "Tatar": 167,
-    "Telugu": 168,
-    "Tetum": 169,
-    "Thai": 170,
-    "Tigrinya": 171,
-    "Tigr\u00e9": 172,
-    "Tok Pisin": 173,
-    "Turkish": 174,
-    "Turkmen": 175,
-    "Udmurt": 176,
-    "Ukrainian": 177,
-    "Upper Sorbian": 178,
-    "Urdu": 179,
-    "Uyghur": 180,
-    "Uzbek": 181,
-    "Venetian": 182,
-    "Vietnamese": 183,
-    "Waray-Waray": 184,
-    "Wayuu": 185,
-    "Welsh": 186,
-    "Western Frisian": 187,
-    "Wolof": 188,
-    "Wu Chinese": 189,
-    "Xhosa": 190,
-    "Yiddish": 191,
-    "Zamboanga Chavacano": 192,
-    "Zaza": 193
+    "Ainu": 0,
+    "Algerian Arabic": 1,
+    "Asturian": 2,
+    "Awadhi": 3,
+    "Baluchi": 4,
+    "Banjar": 5,
+    "Bavarian": 6,
+    "Berber languages": 7,
+    "Brithenig": 8,
+    "Buriat": 9,
+    "Cantonese": 10,
+    "Cebuano": 11,
+    "Central Dusun": 12,
+    "Central Kanuri": 13,
+    "Choctaw": 14,
+    "Chukot": 15,
+    "Coastal Kadazan": 16,
+    "Congo Swahili": 17,
+    "Creek": 18,
+    "Crimean Turkish": 19,
+    "Eastern Mari": 20,
+    "Egyptian Arabic": 21,
+    "Emilian-Romagnol": 22,
+    "Evenki": 23,
+    "Gondi": 24,
+    "Guadeloupean Creole French": 25,
+    "Gulf Arabic": 26,
+    "Hawaiian": 27,
+    "Ho": 28,
+    "Hunsrik": 29,
+    "Iloko": 30,
+    "Iranian Persian": 31,
+    "Kabyle": 32,
+    "Kalmyk": 33,
+    "Karachay-Balkar": 34,
+    "Karelian": 35,
+    "Kashubian": 36,
+    "Khasi": 37,
+    "Khmer": 38,
+    "Kumyk": 39,
+    "Kven Finnish": 40,
+    "Kyrgyz": 41,
+    "Ladino": 42,
+    "Latgalian": 43,
+    "Lhunda": 44,
+    "Ligurian": 45,
+    "Lingua Franca Nova": 46,
+    "Low German": 47,
+    "Lower Sorbian": 48,
+    "Malay (individual language)": 49,
+    "Mikasuki": 50,
+    "Minangkabau": 51,
+    "Mingrelian": 52,
+    "Modern Greek": 53,
+    "Nahuatl languages": 54,
+    "Nepali (individual language)": 55,
+    "Nogai": 56,
+    "North Frisian": 57,
+    "North Levantine Arabic": 58,
+    "North Moluccan Malay": 59,
+    "Northern Kurdish": 60,
+    "Nuer": 61,
+    "Occitan": 62,
+    "Old Tupi": 63,
+    "Oriya": 64,
+    "Pampanga": 65,
+    "Pattani Malay": 66,
+    "Picard": 67,
+    "Piedmontese": 68,
+    "Punjabi": 69,
+    "Rohingya": 70,
+    "Romany": 71,
+    "Rusyn": 72,
+    "Sakha": 73,
+    "Santali": 74,
+    "Seraiki": 75,
+    "Sorani Kurdish": 76,
+    "Southern Kurdish": 77,
+    "Sranan Tongo": 78,
+    "Standard Latvian": 79,
+    "Standard Malay": 80,
+    "Standard Moroccan Tamazight": 81,
+    "Swabian": 82,
+    "Swahili": 83,
+    "Swiss German": 84,
+    "Tachawit": 85,
+    "Tachelhit": 86,
+    "Tarifit": 87,
+    "Tase Naga": 88,
+    "Tetum": 89,
+    "Tigr\u00e9": 90,
+    "Tok Pisin": 91,
+    "Udmurt": 92,
+    "Upper Sorbian": 93,
+    "Uyghur": 94,
+    "Venetian": 95,
+    "Waray-Waray": 96,
+    "Wayuu": 97,
+    "Wu Chinese": 98,
+    "Zamboanga Chavacano": 99,
+    "Zaza": 100,
+    "af": 101,
+    "am": 102,
+    "an": 103,
+    "ar": 104,
+    "as": 105,
+    "az": 106,
+    "ba": 107,
+    "be": 108,
+    "bg": 109,
+    "bn": 110,
+    "br": 111,
+    "bs": 112,
+    "ca": 113,
+    "ch": 114,
+    "cs": 115,
+    "cv": 116,
+    "cy": 117,
+    "da": 118,
+    "de": 119,
+    "el": 120,
+    "en": 121,
+    "es": 122,
+    "et": 123,
+    "eu": 124,
+    "fi": 125,
+    "fo": 126,
+    "fr": 127,
+    "fy": 128,
+    "ga": 129,
+    "gd": 130,
+    "gl": 131,
+    "gn": 132,
+    "gu": 133,
+    "ha": 134,
+    "he": 135,
+    "hi": 136,
+    "hr": 137,
+    "hu": 138,
+    "hy": 139,
+    "id": 140,
+    "is": 141,
+    "it": 142,
+    "ja": 143,
+    "jv": 144,
+    "ka": 145,
+    "kk": 146,
+    "kl": 147,
+    "kn": 148,
+    "ko": 149,
+    "kw": 150,
+    "lb": 151,
+    "ln": 152,
+    "lo": 153,
+    "lt": 154,
+    "mi": 155,
+    "mk": 156,
+    "ml": 157,
+    "mn": 158,
+    "mr": 159,
+    "mt": 160,
+    "my": 161,
+    "nb": 162,
+    "nl": 163,
+    "nn": 164,
+    "os": 165,
+    "pl": 166,
+    "pt": 167,
+    "qu": 168,
+    "rn": 169,
+    "ro": 170,
+    "ru": 171,
+    "se": 172,
+    "sk": 173,
+    "sl": 174,
+    "sq": 175,
+    "sr": 176,
+    "sv": 177,
+    "sw": 178,
+    "ta": 179,
+    "te": 180,
+    "th": 181,
+    "ti": 182,
+    "tk": 183,
+    "tl": 184,
+    "tr": 185,
+    "tt": 186,
+    "ty": 187,
+    "uk": 188,
+    "ur": 189,
+    "uz": 190,
+    "vi": 191,
+    "wo": 192,
+    "xh": 193,
+    "yi": 194,
+    "zh": 195
   },
   "layer_norm_eps": 1e-05,
   "max_position_embeddings": 514,

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e59f67f94eb57bd35ee3d110dbf66c838b283a8d0bea0e09d320ecd7a86dcb53
-size 1112842989
+oid sha256:44b5aff55452f1402ad1605628d44af9157dc69cb6554f6acda0b5244ca212ce
+size 1112849133