tokenizer.json

{
  "version": "1.0",
  "truncation": null,
  "padding": null,
  "added_tokens": [
    {
      "id": 0,
      "content": "<start>",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": false,
      "special": true
    },
    {
      "id": 1,
      "content": "<end>",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": false,
      "special": true
    },
    {
      "id": 2,
      "content": "<pad>",
      "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": null,
    "end_of_word_suffix": null,
    "fuse_unk": false,
    "byte_fallback": false,
    "vocab": {
      "<start>": 0,
      "<end>": 1,
      "<pad>": 2,
      "\"": 3,
      "'": 4,
      ",": 5,
      "-": 6,
      ".": 7,
      "<": 8,
      ">": 9,
      "A": 10,
      "B": 11,
      "C": 12,
      "D": 13,
      "G": 14,
      "H": 15,
      "I": 16,
      "M": 17,
      "N": 18,
      "O": 19,
      "S": 20,
      "a": 21,
      "b": 22,
      "c": 23,
      "d": 24,
      "e": 25,
      "f": 26,
      "g": 27,
      "h": 28,
      "i": 29,
      "j": 30,
      "k": 31,
      "l": 32,
      "m": 33,
      "n": 34,
      "o": 35,
      "p": 36,
      "r": 37,
      "s": 38,
      "t": 39,
      "u": 40,
      "w": 41,
      "x": 42,
      "y": 43,
      "²": 44,
      "Ì": 45,
      "Ġ": 46,
      "st": 47,
      "nd": 48,
      "ar": 49,
      "end": 50,
      "Ġ<": 51,
      "star": 52,
      "start": 53,
      "hl": 54,
      "̲": 55,
      "wi": 56,
      "ii": 57,
      "Ġg": 58,
      "aa": 59,
      "oo": 60,
      "Ġn": 61,
      "Ġwi": 62,
      "Ġ'": 63,
      "Ġii": 64,
      "an": 65,
      "Ġy": 66,
      "Ġl": 67,
      "Ii": 68,
      "ĠIi": 69,
      "oohl": 70,
      "ee": 71,
      "im": 72,
      "Ġwil": 73,
      "Ġh": 74,
      "whl": 75,
      "Ġhl": 76,
      "ag": 77,
      "dii": 78,
      "nii": 79,
      "ts": 80,
      "xwi": 81,
      "Ġd": 82,
      "Ġha": 83,
      "uu": 84,
      "Ġnee": 85,
      "xs": 86,
      "Ġyu": 87,
      "Ġa": 88,
      "ip": 89,
      "kwhl": 90,
      "wihl": 91,
      "gi": 92,
      "Ġk": 93,
      "xw": 94,
      "'m": 95,
      "Ġxs": 96,
      "Ġdim": 97,
      "Ġneedii": 98,
      "igi": 99
    },
    "merges": [
      "s t",
      "n d",
      "a r",
      "e nd",
      "Ġ <",
      "st ar",
      "star t",
      "h l",
      "Ì ²",
      "w i",
      "i i",
      "Ġ g",
      "a a",
      "o o",
      "Ġ n",
      "Ġ wi",
      "Ġ '",
      "Ġ ii",
      "a n",
      "Ġ y",
      "Ġ l",
      "I i",
      "Ġ Ii",
      "oo hl",
      "e e",
      "i m",
      "Ġwi l",
      "Ġ h",
      "w hl",
      "Ġ hl",
      "a g",
      "d ii",
      "n ii",
      "t s",
      "x wi",
      "Ġ d",
      "Ġh a",
      "u u",
      "Ġn ee",
      "x s",
      "Ġy u",
      "Ġ a",
      "i p",
      "k whl",
      "wi hl",
      "g i",
      "Ġ k",
      "x w",
      "' m",
      "Ġ xs",
      "Ġd im",
      "Ġnee dii",
      "i gi"
    ]
  }
}