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
    },
    {
      "id": 2,
      "content": "[CLS]",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": false,
      "special": true
    },
    {
      "id": 3,
      "content": "[SEP]",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": false,
      "special": true
    },
    {
      "id": 4,
      "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": true,
    "use_regex": true
  },
  "decoder": {
    "type": "ByteLevel",
    "add_prefix_space": true,
    "trim_offsets": true,
    "use_regex": true
  },
  "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": {
      "[PAD]": 0,
      "[UNK]": 1,
      "[CLS]": 2,
      "[SEP]": 3,
      "[MASK]": 4,
      ".": 5,
      "T": 6,
      "a": 7,
      "b": 8,
      "c": 9,
      "d": 10,
      "e": 11,
      "f": 12,
      "g": 13,
      "h": 14,
      "i": 15,
      "j": 16,
      "k": 17,
      "l": 18,
      "m": 19,
      "n": 20,
      "o": 21,
      "p": 22,
      "q": 23,
      "r": 24,
      "s": 25,
      "t": 26,
      "u": 27,
      "v": 28,
      "w": 29,
      "x": 30,
      "y": 31,
      "z": 32,
      "Ġ": 33,
      "Ġt": 34,
      "Th": 35,
      "er": 36,
      "fo": 37,
      "in": 38,
      "is": 39,
      "mp": 40,
      "Ġfo": 41,
      "ĠTh": 42,
      "az": 43,
      "ain": 44,
      "amp": 45,
      "br": 46,
      "ck": 47,
      "do": 48,
      "en": 49,
      "ex": 50,
      "he": 51,
      "iz": 52,
      "ick": 53,
      "ju": 54,
      "ken": 55,
      "le": 56,
      "laz": 57,
      "ov": 58,
      "ow": 59,
      "oken": 60,
      "qu": 61,
      "rain": 62,
      "samp": 63,
      "Ġa": 64,
      "Ġis": 65,
      "Ġbr": 66,
      "Ġdo": 67,
      "Ġju": 68,
      "Ġlaz": 69,
      "Ġov": 70,
      "Ġqu": 71,
      "Ġsamp": 72,
      "Ġtex": 73,
      "Ġthe": 74,
      "Ġtoken": 75,
      "Ġtrain": 76,
      "ing": 77,
      "mps": 78,
      "Ġfor": 79,
      "Ġfox": 80,
      "izer": 81,
      "own": 82,
      "Ġbrown": 83,
      "Ġdog": 84,
      "Ġjumps": 85,
      "Ġlazy": 86,
      "Ġover": 87,
      "Ġquick": 88,
      "Ġsample": 89,
      "Ġtext": 90,
      "Ġtokenizer": 91,
      "Ġtraining": 92,
      "ĠThe": 93,
      "ĠThis": 94
    },
    "merges": [
      [
        "Ġ",
        "t"
      ],
      [
        "T",
        "h"
      ],
      [
        "e",
        "r"
      ],
      [
        "f",
        "o"
      ],
      [
        "i",
        "n"
      ],
      [
        "i",
        "s"
      ],
      [
        "m",
        "p"
      ],
      [
        "Ġ",
        "fo"
      ],
      [
        "Ġ",
        "Th"
      ],
      [
        "a",
        "z"
      ],
      [
        "a",
        "in"
      ],
      [
        "a",
        "mp"
      ],
      [
        "b",
        "r"
      ],
      [
        "c",
        "k"
      ],
      [
        "d",
        "o"
      ],
      [
        "e",
        "n"
      ],
      [
        "e",
        "x"
      ],
      [
        "h",
        "e"
      ],
      [
        "i",
        "z"
      ],
      [
        "i",
        "ck"
      ],
      [
        "j",
        "u"
      ],
      [
        "k",
        "en"
      ],
      [
        "l",
        "e"
      ],
      [
        "l",
        "az"
      ],
      [
        "o",
        "v"
      ],
      [
        "o",
        "w"
      ],
      [
        "o",
        "ken"
      ],
      [
        "q",
        "u"
      ],
      [
        "r",
        "ain"
      ],
      [
        "s",
        "amp"
      ],
      [
        "Ġ",
        "a"
      ],
      [
        "Ġ",
        "is"
      ],
      [
        "Ġ",
        "br"
      ],
      [
        "Ġ",
        "do"
      ],
      [
        "Ġ",
        "ju"
      ],
      [
        "Ġ",
        "laz"
      ],
      [
        "Ġ",
        "ov"
      ],
      [
        "Ġ",
        "qu"
      ],
      [
        "Ġ",
        "samp"
      ],
      [
        "Ġt",
        "ex"
      ],
      [
        "Ġt",
        "he"
      ],
      [
        "Ġt",
        "oken"
      ],
      [
        "Ġt",
        "rain"
      ],
      [
        "in",
        "g"
      ],
      [
        "mp",
        "s"
      ],
      [
        "Ġfo",
        "r"
      ],
      [
        "Ġfo",
        "x"
      ],
      [
        "iz",
        "er"
      ],
      [
        "ow",
        "n"
      ],
      [
        "Ġbr",
        "own"
      ],
      [
        "Ġdo",
        "g"
      ],
      [
        "Ġju",
        "mps"
      ],
      [
        "Ġlaz",
        "y"
      ],
      [
        "Ġov",
        "er"
      ],
      [
        "Ġqu",
        "ick"
      ],
      [
        "Ġsamp",
        "le"
      ],
      [
        "Ġtex",
        "t"
      ],
      [
        "Ġtoken",
        "izer"
      ],
      [
        "Ġtrain",
        "ing"
      ],
      [
        "ĠTh",
        "e"
      ],
      [
        "ĠTh",
        "is"
      ]
    ]
  }
}