tokenizer.json

{
  "version": "1.0",
  "truncation": null,
  "padding": null,
  "added_tokens": [
    {
      "id": 0,
      "content": "<|endoftext|>",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": false,
      "special": true
    },
    {
      "id": 265,
      "content": ">",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": false,
      "special": true
    },
    {
      "id": 266,
      "content": "<",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": false,
      "special": true
    },
    {
      "id": 267,
      "content": "#",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": false,
      "special": true
    }
  ],
  "normalizer": null,
  "pre_tokenizer": {
    "type": "ByteLevel",
    "add_prefix_space": false,
    "trim_offsets": true
  },
  "post_processor": {
    "type": "ByteLevel",
    "add_prefix_space": true,
    "trim_offsets": false
  },
  "decoder": {
    "type": "ByteLevel",
    "add_prefix_space": true,
    "trim_offsets": true
  },
  "model": {
    "type": "BPE",
    "dropout": null,
    "unk_token": null,
    "continuing_subword_prefix": "",
    "end_of_word_suffix": "",
    "fuse_unk": false,
    "vocab": {
      "<|endoftext|>": 0,
      "\n": 1,
      " ": 2,
      "!": 3,
      "%": 4,
      "&": 5,
      "'": 6,
      "(": 7,
      ")": 8,
      "*": 9,
      "+": 10,
      ",": 11,
      "-": 12,
      ".": 13,
      "/": 14,
      "0": 15,
      "1": 16,
      "2": 17,
      "3": 18,
      "4": 19,
      "5": 20,
      "6": 21,
      "7": 22,
      "8": 23,
      "9": 24,
      ":": 25,
      ";": 26,
      "=": 27,
      "?": 28,
      "@": 29,
      "A": 30,
      "B": 31,
      "C": 32,
      "D": 33,
      "E": 34,
      "F": 35,
      "G": 36,
      "H": 37,
      "I": 38,
      "J": 39,
      "K": 40,
      "L": 41,
      "M": 42,
      "N": 43,
      "O": 44,
      "P": 45,
      "Q": 46,
      "R": 47,
      "S": 48,
      "T": 49,
      "U": 50,
      "V": 51,
      "W": 52,
      "X": 53,
      "Y": 54,
      "Z": 55,
      "\\": 56,
      "]": 57,
      "a": 58,
      "b": 59,
      "c": 60,
      "d": 61,
      "e": 62,
      "f": 63,
      "g": 64,
      "h": 65,
      "i": 66,
      "j": 67,
      "k": 68,
      "l": 69,
      "m": 70,
      "n": 71,
      "o": 72,
      "p": 73,
      "q": 74,
      "r": 75,
      "s": 76,
      "t": 77,
      "u": 78,
      "v": 79,
      "w": 80,
      "x": 81,
      "y": 82,
      "z": 83,
      "}": 84,
      "¡": 85,
      "¢": 86,
      "£": 87,
      "¤": 88,
      "¥": 89,
      "¦": 90,
      "§": 91,
      "¨": 92,
      "©": 93,
      "ª": 94,
      "«": 95,
      "¬": 96,
      "®": 97,
      "¯": 98,
      "°": 99,
      "±": 100,
      "²": 101,
      "³": 102,
      "´": 103,
      "µ": 104,
      "¶": 105,
      "·": 106,
      "¸": 107,
      "¹": 108,
      "º": 109,
      "»": 110,
      "¼": 111,
      "½": 112,
      "¾": 113,
      "¿": 114,
      "Á": 115,
      "Â": 116,
      "Ã": 117,
      "Ä": 118,
      "Å": 119,
      "Æ": 120,
      "Ç": 121,
      "È": 122,
      "É": 123,
      "Ê": 124,
      "Ë": 125,
      "Ì": 126,
      "Í": 127,
      "Î": 128,
      "Ï": 129,
      "Ð": 130,
      "Ô": 131,
      "Ö": 132,
      "×": 133,
      "Ü": 134,
      "ß": 135,
      "à": 136,
      "á": 137,
      "â": 138,
      "ã": 139,
      "ä": 140,
      "å": 141,
      "æ": 142,
      "ç": 143,
      "è": 144,
      "é": 145,
      "ê": 146,
      "ë": 147,
      "ì": 148,
      "í": 149,
      "î": 150,
      "ï": 151,
      "ñ": 152,
      "ò": 153,
      "ó": 154,
      "ô": 155,
      "õ": 156,
      "ö": 157,
      "ø": 158,
      "ù": 159,
      "ú": 160,
      "û": 161,
      "ü": 162,
      "ý": 163,
      "ÿ": 164,
      "ā": 165,
      "ć": 166,
      "č": 167,
      "Ğ": 168,
      "ğ": 169,
      "Ġ": 170,
      "Ģ": 171,
      "ģ": 172,
      "Ĥ": 173,
      "ĥ": 174,
      "Ħ": 175,
      "ħ": 176,
      "Ĩ": 177,
      "ĩ": 178,
      "Ī": 179,
      "ī": 180,
      "Ĭ": 181,
      "ĭ": 182,
      "Į": 183,
      "į": 184,
      "İ": 185,
      "ı": 186,
      "IJ": 187,
      "ij": 188,
      "Ĵ": 189,
      "ĵ": 190,
      "Ķ": 191,
      "ĸ": 192,
      "Ĺ": 193,
      "ĺ": 194,
      "Ļ": 195,
      "ļ": 196,
      "Ľ": 197,
      "ľ": 198,
      "Ŀ": 199,
      "ŀ": 200,
      "Ł": 201,
      "ł": 202,
      "Ń": 203,
      "ŋ": 204,
      "ō": 205,
      "Œ": 206,
      "œ": 207,
      "Ś": 208,
      "ŝ": 209,
      "Ş": 210,
      "ş": 211,
      "š": 212,
      "ū": 213,
      "ŵ": 214,
      "ź": 215,
      "Ž": 216,
      "ž": 217,
      "ǘ": 218,
      "ȝ": 219,
      "ɑ": 220,
      "ɔ": 221,
      "ə": 222,
      "ɛ": 223,
      "ɡ": 224,
      "ɣ": 225,
      "ɥ": 226,
      "ɨ": 227,
      "ɩ": 228,
      "ɲ": 229,
      "ʁ": 230,
      "ʃ": 231,
      "ʋ": 232,
      "ʒ": 233,
      "ʔ": 234,
      "ʻ": 235,
      "ʼ": 236,
      "ʾ": 237,
      "ʿ": 238,
      "́": 239,
      "̃": 240,
      "̐": 241,
      "̓": 242,
      "͠": 243,
      "Δ": 244,
      "α": 245,
      "β": 246,
      "μ": 247,
      "σ": 248,
      "а": 249,
      "е": 250,
      "ḷ": 251,
      "ṃ": 252,
      "ṇ": 253,
      "ṣ": 254,
      "ṭ": 255,
      "–": 256,
      "‘": 257,
      "’": 258,
      "′": 259,
      "‿": 260,
      "₂": 261,
      "€": 262,
      "−": 263,
      "∴": 264
    },
    "merges": []
  }
}