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": "<s>",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": false,
      "special": true
    },
    {
      "id": 2,
      "content": "</s>",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": false,
      "special": true
    },
    {
      "id": 3,
      "content": "<unk>",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": false,
      "special": true
    }
  ],
  "normalizer": null,
  "pre_tokenizer": {
    "type": "Split",
    "pattern": {
      "Regex": "[\\s\\S]"
    },
    "behavior": "Isolated",
    "invert": false
  },
  "post_processor": {
    "type": "TemplateProcessing",
    "single": [
      {
        "SpecialToken": {
          "id": "<s>",
          "type_id": 0
        }
      },
      {
        "Sequence": {
          "id": "A",
          "type_id": 0
        }
      },
      {
        "SpecialToken": {
          "id": "</s>",
          "type_id": 0
        }
      }
    ],
    "pair": [
      {
        "Sequence": {
          "id": "A",
          "type_id": 0
        }
      },
      {
        "Sequence": {
          "id": "B",
          "type_id": 1
        }
      }
    ],
    "special_tokens": {
      "</s>": {
        "id": "</s>",
        "ids": [
          2
        ],
        "tokens": [
          "</s>"
        ]
      },
      "<s>": {
        "id": "<s>",
        "ids": [
          1
        ],
        "tokens": [
          "<s>"
        ]
      }
    }
  },
  "decoder": {
    "type": "Fuse"
  },
  "model": {
    "type": "WordLevel",
    "vocab": {
      "<pad>": 0,
      "<s>": 1,
      "</s>": 2,
      "<unk>": 3,
      "a": 4,
      "b": 5,
      "c": 6,
      "d": 7,
      "e": 8,
      "f": 9,
      "g": 10,
      "h": 11,
      "i": 12,
      "j": 13,
      "k": 14,
      "l": 15,
      "m": 16,
      "n": 17,
      "o": 18,
      "p": 19,
      "q": 20,
      "r": 21,
      "s": 22,
      "t": 23,
      "u": 24,
      "v": 25,
      "w": 26,
      "x": 27,
      "y": 28,
      "z": 29,
      "A": 30,
      "B": 31,
      "C": 32,
      "D": 33,
      "E": 34,
      "F": 35,
      "G": 36,
      "H": 37,
      "I": 38,
      "J": 39,
      "K": 40,
      "L": 41,
      "M": 42,
      "N": 43,
      "O": 44,
      "P": 45,
      "Q": 46,
      "R": 47,
      "S": 48,
      "T": 49,
      "U": 50,
      "V": 51,
      "W": 52,
      "X": 53,
      "Y": 54,
      "Z": 55,
      "ɣ": 56,
      "Ɣ": 57,
      "ɛ": 58,
      "Ɛ": 59,
      "č": 60,
      "Č": 61,
      "ǧ": 62,
      "Ǧ": 63,
      "ţ": 64,
      "Ţ": 65,
      "ḍ": 66,
      "Ḍ": 67,
      "ḥ": 68,
      "Ḥ": 69,
      "ṛ": 70,
      "Ṛ": 71,
      "ṣ": 72,
      "Ṣ": 73,
      "ṭ": 74,
      "Ṭ": 75,
      "ẓ": 76,
      "Ẓ": 77,
      "é": 78,
      "è": 79,
      "ê": 80,
      "ë": 81,
      "à": 82,
      "â": 83,
      "î": 84,
      "ï": 85,
      "ô": 86,
      "ù": 87,
      "û": 88,
      "ç": 89,
      "É": 90,
      "È": 91,
      "Ê": 92,
      "Ë": 93,
      "À": 94,
      "Â": 95,
      "Î": 96,
      "Ï": 97,
      "Ô": 98,
      "Ù": 99,
      "Û": 100,
      "Ç": 101,
      "0": 102,
      "1": 103,
      "2": 104,
      "3": 105,
      "4": 106,
      "5": 107,
      "6": 108,
      "7": 109,
      "8": 110,
      "9": 111,
      " ": 112,
      ".": 113,
      ",": 114,
      "?": 115,
      "!": 116,
      "«": 117,
      "»": 118,
      "-": 119,
      "—": 120,
      ":": 121,
      ";": 122,
      "'": 123,
      "\"": 124,
      "/": 125,
      "(": 126,
      ")": 127,
      "[": 128,
      "]": 129,
      "{": 130,
      "}": 131,
      "%": 132,
      "*": 133,
      "+": 134,
      "=": 135,
      "_": 136,
      "~": 137,
      "–": 138,
      "…": 139,
      "\n": 140,
      "\t": 141,
      "ⴰ": 142,
      "ⴱ": 143,
      "ⴳ": 144,
      "ⴷ": 145,
      "ⴹ": 146,
      "ⴻ": 147,
      "ⴼ": 148,
      "ⴽ": 149,
      "ⵀ": 150,
      "ⵃ": 151,
      "ⵄ": 152,
      "ⵅ": 153,
      "ⵇ": 154,
      "ⵉ": 155,
      "ⵊ": 156,
      "ⵍ": 157,
      "ⵎ": 158,
      "ⵏ": 159,
      "ⵓ": 160,
      "ⵔ": 161,
      "ⵕ": 162,
      "ⵙ": 163,
      "ⵚ": 164,
      "ⵛ": 165,
      "ⵜ": 166,
      "ⵟ": 167,
      "ⵡ": 168,
      "ⵢ": 169,
      "ⵣ": 170,
      "ⵥ": 171,
      "ⵖ": 172
    },
    "unk_token": "<unk>"
  }
}