tokenizer.json

{
  "version": "1.0",
  "truncation": {
    "direction": "Right",
    "max_length": 1024,
    "strategy": "LongestFirst",
    "stride": 0
  },
  "padding": {
    "strategy": "BatchLongest",
    "direction": "Right",
    "pad_to_multiple_of": null,
    "pad_id": 2,
    "pad_type_id": 0,
    "pad_token": "[PAD]"
  },
  "added_tokens": [],
  "normalizer": null,
  "pre_tokenizer": {
    "type": "Split",
    "pattern": {
      "Regex": "[\\s\\S]"
    },
    "behavior": "Isolated",
    "invert": false
  },
  "post_processor": {
    "type": "TemplateProcessing",
    "single": [
      {
        "SpecialToken": {
          "id": "[CLS]",
          "type_id": 0
        }
      },
      {
        "Sequence": {
          "id": "A",
          "type_id": 0
        }
      },
      {
        "SpecialToken": {
          "id": "[SEP]",
          "type_id": 0
        }
      }
    ],
    "pair": [
      {
        "SpecialToken": {
          "id": "[CLS]",
          "type_id": 0
        }
      },
      {
        "Sequence": {
          "id": "A",
          "type_id": 0
        }
      },
      {
        "SpecialToken": {
          "id": "[SEP]",
          "type_id": 0
        }
      },
      {
        "Sequence": {
          "id": "B",
          "type_id": 1
        }
      },
      {
        "SpecialToken": {
          "id": "[SEP]",
          "type_id": 1
        }
      }
    ],
    "special_tokens": {
      "[CLS]": {
        "id": "[CLS]",
        "ids": [
          4
        ],
        "tokens": [
          "[CLS]"
        ]
      },
      "[SEP]": {
        "id": "[SEP]",
        "ids": [
          5
        ],
        "tokens": [
          "[SEP]"
        ]
      }
    }
  },
  "decoder": null,
  "model": {
    "type": "WordLevel",
    "vocab": {
      "<|start|>": 0,
      "<|end|>": 1,
      "[PAD]": 2,
      "[UNK]": 3,
      "[CLS]": 4,
      "[SEP]": 5,
      "[MASK]": 6,
      "\u0000": 7,
      "\u0001": 8,
      "\u0002": 9,
      "\u0003": 10,
      "\u0004": 11,
      "\u0005": 12,
      "\u0006": 13,
      "\u0007": 14,
      "\b": 15,
      "\t": 16,
      "\n": 17,
      "\u000b": 18,
      "\f": 19,
      "\r": 20,
      "\u000e": 21,
      "\u000f": 22,
      "\u0010": 23,
      "\u0011": 24,
      "\u0012": 25,
      "\u0013": 26,
      "\u0014": 27,
      "\u0015": 28,
      "\u0016": 29,
      "\u0017": 30,
      "\u0018": 31,
      "\u0019": 32,
      "\u001a": 33,
      "\u001b": 34,
      "\u001c": 35,
      "\u001d": 36,
      "\u001e": 37,
      "\u001f": 38,
      " ": 39,
      "!": 40,
      "\"": 41,
      "#": 42,
      "$": 43,
      "%": 44,
      "&": 45,
      "'": 46,
      "(": 47,
      ")": 48,
      "*": 49,
      "+": 50,
      ",": 51,
      "-": 52,
      ".": 53,
      "/": 54,
      "0": 55,
      "1": 56,
      "2": 57,
      "3": 58,
      "4": 59,
      "5": 60,
      "6": 61,
      "7": 62,
      "8": 63,
      "9": 64,
      ":": 65,
      ";": 66,
      "<": 67,
      "=": 68,
      ">": 69,
      "?": 70,
      "@": 71,
      "A": 72,
      "B": 73,
      "C": 74,
      "D": 75,
      "E": 76,
      "F": 77,
      "G": 78,
      "H": 79,
      "I": 80,
      "J": 81,
      "K": 82,
      "L": 83,
      "M": 84,
      "N": 85,
      "O": 86,
      "P": 87,
      "Q": 88,
      "R": 89,
      "S": 90,
      "T": 91,
      "U": 92,
      "V": 93,
      "W": 94,
      "X": 95,
      "Y": 96,
      "Z": 97,
      "[": 98,
      "\\": 99,
      "]": 100,
      "^": 101,
      "_": 102,
      "`": 103,
      "a": 104,
      "b": 105,
      "c": 106,
      "d": 107,
      "e": 108,
      "f": 109,
      "g": 110,
      "h": 111,
      "i": 112,
      "j": 113,
      "k": 114,
      "l": 115,
      "m": 116,
      "n": 117,
      "o": 118,
      "p": 119,
      "q": 120,
      "r": 121,
      "s": 122,
      "t": 123,
      "u": 124,
      "v": 125,
      "w": 126,
      "x": 127,
      "y": 128,
      "z": 129,
      "{": 130,
      "|": 131,
      "}": 132,
      "~": 133,
      "": 134,
      "€": 135,
      "": 136,
      "‚": 137,
      "ƒ": 138,
      "„": 139,
      "…": 140,
      "†": 141,
      "‡": 142,
      "ˆ": 143,
      "‰": 144,
      "Š": 145,
      "‹": 146,
      "Œ": 147,
      "": 148,
      "Ž": 149,
      "": 150,
      "": 151,
      "‘": 152,
      "’": 153,
      "“": 154,
      "”": 155,
      "•": 156,
      "–": 157,
      "—": 158,
      "˜": 159,
      "™": 160,
      "š": 161,
      "›": 162,
      "œ": 163,
      "": 164,
      "ž": 165,
      "Ÿ": 166,
      " ": 167,
      "¡": 168,
      "¢": 169,
      "£": 170,
      "¤": 171,
      "¥": 172,
      "¦": 173,
      "§": 174,
      "¨": 175,
      "©": 176,
      "ª": 177,
      "«": 178,
      "¬": 179,
      "­": 180,
      "®": 181,
      "¯": 182,
      "°": 183,
      "±": 184,
      "²": 185,
      "³": 186,
      "´": 187,
      "µ": 188,
      "¶": 189,
      "·": 190,
      "¸": 191,
      "¹": 192,
      "º": 193,
      "»": 194,
      "¼": 195,
      "½": 196,
      "¾": 197,
      "¿": 198,
      "À": 199,
      "Á": 200,
      "Â": 201,
      "Ã": 202,
      "Ä": 203,
      "Å": 204,
      "Æ": 205,
      "Ç": 206,
      "È": 207,
      "É": 208,
      "Ê": 209,
      "Ë": 210,
      "Ì": 211,
      "Í": 212,
      "Î": 213,
      "Ï": 214,
      "Ð": 215,
      "Ñ": 216,
      "Ò": 217,
      "Ó": 218,
      "Ô": 219,
      "Õ": 220,
      "Ö": 221,
      "×": 222,
      "Ø": 223,
      "Ù": 224,
      "Ú": 225,
      "Û": 226,
      "Ü": 227,
      "Ý": 228,
      "Þ": 229,
      "ß": 230,
      "à": 231,
      "á": 232,
      "â": 233,
      "ã": 234,
      "ä": 235,
      "å": 236,
      "æ": 237,
      "ç": 238,
      "è": 239,
      "é": 240,
      "ê": 241,
      "ë": 242,
      "ì": 243,
      "í": 244,
      "î": 245,
      "ï": 246,
      "ð": 247,
      "ñ": 248,
      "ò": 249,
      "ó": 250,
      "ô": 251,
      "õ": 252,
      "ö": 253,
      "÷": 254,
      "ø": 255,
      "ù": 256,
      "ú": 257,
      "û": 258,
      "ü": 259,
      "ý": 260,
      "þ": 261,
      "ÿ": 262
    },
    "unk_token": "[UNK]"
  }
}