tokenizer.json

{
  "version": "1.0",
  "truncation": null,
  "padding": null,
  "added_tokens": [
    {
      "id": 0,
      "content": "[PAD]",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": false,
      "special": true
    },
    {
      "id": 1,
      "content": "[UNK]",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": false,
      "special": true
    }
  ],
  "normalizer": null,
  "pre_tokenizer": {
    "type": "Sequence",
    "pretokenizers": [
      {
        "type": "ByteLevel",
        "add_prefix_space": false,
        "trim_offsets": true,
        "use_regex": false
      },
      {
        "type": "Split",
        "pattern": {
          "Regex": "[\\s\\S]"
        },
        "behavior": "Isolated",
        "invert": false
      }
    ]
  },
  "post_processor": {
    "type": "TemplateProcessing",
    "single": [
      {
        "Sequence": {
          "id": "A",
          "type_id": 0
        }
      }
    ],
    "pair": [
      {
        "Sequence": {
          "id": "A",
          "type_id": 0
        }
      },
      {
        "Sequence": {
          "id": "B",
          "type_id": 1
        }
      }
    ],
    "special_tokens": {}
  },
  "decoder": {
    "type": "ByteLevel",
    "add_prefix_space": true,
    "trim_offsets": true,
    "use_regex": true
  },
  "model": {
    "type": "WordLevel",
    "vocab": {
      "[PAD]": 0,
      "[UNK]": 1,
      "Ā": 2,
      "ā": 3,
      "Ă": 4,
      "ă": 5,
      "Ą": 6,
      "ą": 7,
      "Ć": 8,
      "ć": 9,
      "Ĉ": 10,
      "ĉ": 11,
      "Ċ": 12,
      "ċ": 13,
      "Č": 14,
      "č": 15,
      "Ď": 16,
      "ď": 17,
      "Đ": 18,
      "đ": 19,
      "Ē": 20,
      "ē": 21,
      "Ĕ": 22,
      "ĕ": 23,
      "Ė": 24,
      "ė": 25,
      "Ę": 26,
      "ę": 27,
      "Ě": 28,
      "ě": 29,
      "Ĝ": 30,
      "ĝ": 31,
      "Ğ": 32,
      "ğ": 33,
      "Ġ": 34,
      "!": 35,
      "\"": 36,
      "#": 37,
      "$": 38,
      "%": 39,
      "&": 40,
      "'": 41,
      "(": 42,
      ")": 43,
      "*": 44,
      "+": 45,
      ",": 46,
      "-": 47,
      ".": 48,
      "/": 49,
      "0": 50,
      "1": 51,
      "2": 52,
      "3": 53,
      "4": 54,
      "5": 55,
      "6": 56,
      "7": 57,
      "8": 58,
      "9": 59,
      ":": 60,
      ";": 61,
      "<": 62,
      "=": 63,
      ">": 64,
      "?": 65,
      "@": 66,
      "A": 67,
      "B": 68,
      "C": 69,
      "D": 70,
      "E": 71,
      "F": 72,
      "G": 73,
      "H": 74,
      "I": 75,
      "J": 76,
      "K": 77,
      "L": 78,
      "M": 79,
      "N": 80,
      "O": 81,
      "P": 82,
      "Q": 83,
      "R": 84,
      "S": 85,
      "T": 86,
      "U": 87,
      "V": 88,
      "W": 89,
      "X": 90,
      "Y": 91,
      "Z": 92,
      "[": 93,
      "\\": 94,
      "]": 95,
      "^": 96,
      "_": 97,
      "`": 98,
      "a": 99,
      "b": 100,
      "c": 101,
      "d": 102,
      "e": 103,
      "f": 104,
      "g": 105,
      "h": 106,
      "i": 107,
      "j": 108,
      "k": 109,
      "l": 110,
      "m": 111,
      "n": 112,
      "o": 113,
      "p": 114,
      "q": 115,
      "r": 116,
      "s": 117,
      "t": 118,
      "u": 119,
      "v": 120,
      "w": 121,
      "x": 122,
      "y": 123,
      "z": 124,
      "{": 125,
      "|": 126,
      "}": 127,
      "~": 128,
      "ġ": 129,
      "Ģ": 130,
      "ģ": 131,
      "Ĥ": 132,
      "ĥ": 133,
      "Ħ": 134,
      "ħ": 135,
      "Ĩ": 136,
      "ĩ": 137,
      "Ī": 138,
      "ī": 139,
      "Ĭ": 140,
      "ĭ": 141,
      "Į": 142,
      "į": 143,
      "İ": 144,
      "ı": 145,
      "IJ": 146,
      "ij": 147,
      "Ĵ": 148,
      "ĵ": 149,
      "Ķ": 150,
      "ķ": 151,
      "ĸ": 152,
      "Ĺ": 153,
      "ĺ": 154,
      "Ļ": 155,
      "ļ": 156,
      "Ľ": 157,
      "ľ": 158,
      "Ŀ": 159,
      "ŀ": 160,
      "Ł": 161,
      "ł": 162,
      "¡": 163,
      "¢": 164,
      "£": 165,
      "¤": 166,
      "¥": 167,
      "¦": 168,
      "§": 169,
      "¨": 170,
      "©": 171,
      "ª": 172,
      "«": 173,
      "¬": 174,
      "Ń": 175,
      "®": 176,
      "¯": 177,
      "°": 178,
      "±": 179,
      "²": 180,
      "³": 181,
      "´": 182,
      "µ": 183,
      "¶": 184,
      "·": 185,
      "¸": 186,
      "¹": 187,
      "º": 188,
      "»": 189,
      "¼": 190,
      "½": 191,
      "¾": 192,
      "¿": 193,
      "À": 194,
      "Á": 195,
      "Â": 196,
      "Ã": 197,
      "Ä": 198,
      "Å": 199,
      "Æ": 200,
      "Ç": 201,
      "È": 202,
      "É": 203,
      "Ê": 204,
      "Ë": 205,
      "Ì": 206,
      "Í": 207,
      "Î": 208,
      "Ï": 209,
      "Ð": 210,
      "Ñ": 211,
      "Ò": 212,
      "Ó": 213,
      "Ô": 214,
      "Õ": 215,
      "Ö": 216,
      "×": 217,
      "Ø": 218,
      "Ù": 219,
      "Ú": 220,
      "Û": 221,
      "Ü": 222,
      "Ý": 223,
      "Þ": 224,
      "ß": 225,
      "à": 226,
      "á": 227,
      "â": 228,
      "ã": 229,
      "ä": 230,
      "å": 231,
      "æ": 232,
      "ç": 233,
      "è": 234,
      "é": 235,
      "ê": 236,
      "ë": 237,
      "ì": 238,
      "í": 239,
      "î": 240,
      "ï": 241,
      "ð": 242,
      "ñ": 243,
      "ò": 244,
      "ó": 245,
      "ô": 246,
      "õ": 247,
      "ö": 248,
      "÷": 249,
      "ø": 250,
      "ù": 251,
      "ú": 252,
      "û": 253,
      "ü": 254,
      "ý": 255,
      "þ": 256,
      "ÿ": 257
    },
    "unk_token": "[UNK]"
  }
}