tokenizer.json

{
  "version": "1.0",
  "truncation": null,
  "padding": null,
  "added_tokens": [
    {
      "id": 0,
      "content": "[UNK]",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": false,
      "special": true
    },
    {
      "id": 1,
      "content": "[MASK]",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": false,
      "special": true
    }
  ],
  "normalizer": null,
  "pre_tokenizer": null,
  "post_processor": null,
  "decoder": null,
  "model": {
    "type": "BPE",
    "dropout": null,
    "unk_token": "[UNK]",
    "continuing_subword_prefix": null,
    "end_of_word_suffix": null,
    "fuse_unk": false,
    "byte_fallback": false,
    "vocab": {
      "[UNK]": 0,
      "[MASK]": 1,
      "0": 2,
      "1": 3,
      "2": 4,
      "3": 5,
      "4": 6,
      "5": 7,
      "6": 8,
      "7": 9,
      "8": 10,
      "9": 11,
      "a": 12,
      "b": 13,
      "c": 14,
      "d": 15,
      "e": 16,
      "f": 17,
      "g": 18,
      "h": 19,
      "i": 20,
      "j": 21,
      "k": 22,
      "l": 23,
      "m": 24,
      "n": 25,
      "o": 26,
      "p": 27,
      "q": 28,
      "r": 29,
      "s": 30,
      "t": 31,
      "u": 32,
      "v": 33,
      "w": 34,
      "x": 35,
      "y": 36,
      "z": 37,
      "A": 38,
      "B": 39,
      "C": 40,
      "D": 41,
      "E": 42,
      "F": 43,
      "G": 44,
      "H": 45,
      "I": 46,
      "J": 47,
      "K": 48,
      "L": 49,
      "M": 50,
      "N": 51,
      "O": 52,
      "P": 53,
      "Q": 54,
      "R": 55,
      "S": 56,
      "T": 57,
      "U": 58,
      "V": 59,
      "W": 60,
      "X": 61,
      "Y": 62,
      "Z": 63,
      "!": 64,
      "\"": 65,
      "#": 66,
      "$": 67,
      "%": 68,
      "&": 69,
      "'": 70,
      "(": 71,
      ")": 72,
      "*": 73,
      "+": 74,
      ",": 75,
      "-": 76,
      ".": 77,
      "/": 78,
      ":": 79,
      ";": 80,
      "<": 81,
      "=": 82,
      ">": 83,
      "?": 84,
      "@": 85,
      "[": 86,
      "\\": 87,
      "]": 88,
      "^": 89,
      "_": 90,
      "`": 91,
      "{": 92,
      "|": 93,
      "}": 94,
      "~": 95,
      " ": 96
    },
    "merges": []
  }
}