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": 100,
      "content": "<s>",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": false,
      "special": true
    },
    {
      "id": 101,
      "content": "</s>",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": false,
      "special": true
    },
    {
      "id": 102,
      "content": "<pad>",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": false,
      "special": true
    }
  ],
  "normalizer": null,
  "pre_tokenizer": {
    "type": "Split",
    "pattern": {
      "String": " "
    },
    "behavior": "Isolated",
    "invert": false
  },
  "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,
    "ignore_merges": false,
    "vocab": {
      "<unk>": 0,
      " ": 1,
      ".": 2,
      "A": 3,
      "B": 4,
      "C": 5,
      "D": 6,
      "E": 7,
      "F": 8,
      "G": 9,
      "H": 10,
      "I": 11,
      "J": 12,
      "K": 13,
      "L": 14,
      "M": 15,
      "N": 16,
      "O": 17,
      "P": 18,
      "Q": 19,
      "R": 20,
      "S": 21,
      "T": 22,
      "U": 23,
      "V": 24,
      "W": 25,
      "X": 26,
      "Y": 27,
      "Z": 28,
      "a": 29,
      "b": 30,
      "c": 31,
      "d": 32,
      "e": 33,
      "f": 34,
      "g": 35,
      "h": 36,
      "i": 37,
      "j": 38,
      "k": 39,
      "l": 40,
      "m": 41,
      "n": 42,
      "o": 43,
      "p": 44,
      "q": 45,
      "r": 46,
      "s": 47,
      "t": 48,
      "u": 49,
      "v": 50,
      "w": 51,
      "x": 52,
      "y": 53,
      "z": 54,
      "ch": 55,
      "cho": 56,
      "echo": 57,
      "up": 58,
      "pe": 59,
      "uppe": 60,
      "upper": 61,
      "fo": 62,
      "nc": 63,
      "b.": 64,
      "et": 65,
      "ip": 66,
      "mk": 67,
      "qz": 68,
      "wx": 69,
      "kx": 70,
      "qo": 71,
      "y.": 72,
      "ej": 73,
      "k.": 74,
      "tg": 75,
      "bt": 76,
      "iu": 77,
      "kk": 78,
      "sx": 79,
      "B.": 80,
      "M.": 81,
      "fy": 82,
      "mp": 83,
      "ou": 84,
      "pf": 85,
      "v.": 86,
      "yo": 87,
      "P.": 88,
      "jg": 89,
      "kq": 90,
      "m.": 91,
      "mt": 92,
      "nh": 93,
      "qr": 94,
      "wq": 95,
      "O.": 96,
      "aj": 97,
      "ax": 98,
      "dt": 99
    },
    "merges": [
      "c h",
      "ch o",
      "e cho",
      "u p",
      "p e",
      "up pe",
      "uppe r",
      "f o",
      "n c",
      "b .",
      "e t",
      "i p",
      "m k",
      "q z",
      "w x",
      "k x",
      "q o",
      "y .",
      "e j",
      "k .",
      "t g",
      "b t",
      "i u",
      "k k",
      "s x",
      "B .",
      "M .",
      "f y",
      "m p",
      "o u",
      "p f",
      "v .",
      "y o",
      "P .",
      "j g",
      "k q",
      "m .",
      "m t",
      "n h",
      "q r",
      "w q",
      "O .",
      "a j",
      "a x",
      "d t"
    ]
  }
}