tokenizer.json

{
  "version": "1.0",
  "truncation": {
    "direction": "Right",
    "max_length": 512,
    "strategy": "LongestFirst",
    "stride": 0
  },
  "padding": null,
  "added_tokens": [
    {
      "id": 96,
      "content": "<s>",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": false,
      "special": true
    },
    {
      "id": 97,
      "content": "<pad>",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": false,
      "special": true
    },
    {
      "id": 98,
      "content": "</s>",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": false,
      "special": true
    },
    {
      "id": 99,
      "content": "<unk>",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": false,
      "special": true
    },
    {
      "id": 100,
      "content": "<mask>",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": false,
      "special": true
    }
  ],
  "normalizer": null,
  "pre_tokenizer": {
    "type": "ByteLevel",
    "add_prefix_space": false,
    "trim_offsets": true,
    "use_regex": true
  },
  "post_processor": {
    "type": "ByteLevel",
    "add_prefix_space": true,
    "trim_offsets": false,
    "use_regex": true
  },
  "decoder": {
    "type": "ByteLevel",
    "add_prefix_space": true,
    "trim_offsets": true,
    "use_regex": true
  },
  "model": {
    "type": "BPE",
    "dropout": null,
    "unk_token": null,
    "continuing_subword_prefix": "",
    "end_of_word_suffix": "",
    "fuse_unk": false,
    "byte_fallback": false,
    "ignore_merges": false,
    "vocab": {
      "!": 0,
      "\"": 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,
      "?": 30,
      "@": 31,
      "A": 32,
      "B": 33,
      "C": 34,
      "D": 35,
      "E": 36,
      "F": 37,
      "G": 38,
      "H": 39,
      "I": 40,
      "J": 41,
      "K": 42,
      "L": 43,
      "M": 44,
      "N": 45,
      "O": 46,
      "P": 47,
      "Q": 48,
      "R": 49,
      "S": 50,
      "T": 51,
      "U": 52,
      "V": 53,
      "W": 54,
      "X": 55,
      "Y": 56,
      "Z": 57,
      "[": 58,
      "\\": 59,
      "]": 60,
      "^": 61,
      "_": 62,
      "`": 63,
      "a": 64,
      "b": 65,
      "c": 66,
      "d": 67,
      "e": 68,
      "f": 69,
      "g": 70,
      "h": 71,
      "i": 72,
      "j": 73,
      "k": 74,
      "l": 75,
      "m": 76,
      "n": 77,
      "o": 78,
      "p": 79,
      "q": 80,
      "r": 81,
      "s": 82,
      "t": 83,
      "u": 84,
      "v": 85,
      "w": 86,
      "x": 87,
      "y": 88,
      "z": 89,
      "{": 90,
      "|": 91,
      "}": 92,
      "~": 93,
      "Ġ": 94,
      "Ċ": 95,
      "<s>": 96,
      "<pad>": 97,
      "</s>": 98,
      "<unk>": 99,
      "<mask>": 100
    },
    "merges": []
  }
}