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": "[BOS]",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": false,
      "special": true
    },
    {
      "id": 3,
      "content": "[EOS]",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": false,
      "special": true
    }
  ],
  "normalizer": {
    "type": "Sequence",
    "normalizers": [
      {
        "type": "Replace",
        "pattern": {
          "Regex": "İ"
        },
        "content": "\u0001"
      },
      {
        "type": "Lowercase"
      }
    ]
  },
  "pre_tokenizer": {
    "type": "Split",
    "pattern": {
      "Regex": "[\\s\\S]"
    },
    "behavior": "Isolated",
    "invert": false
  },
  "post_processor": {
    "type": "TemplateProcessing",
    "single": [
      {
        "SpecialToken": {
          "id": "[BOS]",
          "type_id": 0
        }
      },
      {
        "Sequence": {
          "id": "A",
          "type_id": 0
        }
      },
      {
        "SpecialToken": {
          "id": "[EOS]",
          "type_id": 0
        }
      }
    ],
    "pair": [
      {
        "Sequence": {
          "id": "A",
          "type_id": 0
        }
      },
      {
        "Sequence": {
          "id": "B",
          "type_id": 1
        }
      }
    ],
    "special_tokens": {
      "[BOS]": {
        "id": "[BOS]",
        "ids": [
          2
        ],
        "tokens": [
          "[BOS]"
        ]
      },
      "[EOS]": {
        "id": "[EOS]",
        "ids": [
          3
        ],
        "tokens": [
          "[EOS]"
        ]
      }
    }
  },
  "decoder": {
    "type": "Fuse"
  },
  "model": {
    "type": "WordLevel",
    "vocab": {
      "[PAD]": 0,
      "[UNK]": 1,
      "[BOS]": 2,
      "[EOS]": 3,
      " ": 4,
      "a": 5,
      "b": 6,
      "c": 7,
      "d": 8,
      "e": 9,
      "f": 10,
      "g": 11,
      "h": 12,
      "i": 13,
      "j": 14,
      "k": 15,
      "l": 16,
      "m": 17,
      "n": 18,
      "o": 19,
      "p": 20,
      "q": 21,
      "r": 22,
      "s": 23,
      "t": 24,
      "u": 25,
      "v": 26,
      "w": 27,
      "x": 28,
      "y": 29,
      "z": 30,
      "ɣ": 31,
      "ɛ": 32,
      "ḥ": 33,
      "ḍ": 34,
      "ṣ": 35,
      "ṭ": 36,
      "ẓ": 37,
      "ṛ": 38,
      "č": 39,
      "ǧ": 40,
      "ţ": 41,
      "ⴰ": 42,
      "ⴱ": 43,
      "ⴳ": 44,
      "ⴷ": 45,
      "ⴹ": 46,
      "ⴻ": 47,
      "ⴼ": 48,
      "ⴽ": 49,
      "ⵀ": 50,
      "ⵃ": 51,
      "ⵄ": 52,
      "ⵅ": 53,
      "ⵇ": 54,
      "ⵉ": 55,
      "ⵊ": 56,
      "ⵍ": 57,
      "ⵎ": 58,
      "ⵏ": 59,
      "ⵓ": 60,
      "ⵔ": 61,
      "ⵕ": 62,
      "ⵖ": 63,
      "ⵙ": 64,
      "ⵚ": 65,
      "ⵛ": 66,
      "ⵜ": 67,
      "ⵟ": 68,
      "ⵡ": 69,
      "ⵢ": 70,
      "ⵣ": 71,
      "ⵥ": 72,
      "ⵯ": 73,
      "0": 74,
      "1": 75,
      "2": 76,
      "3": 77,
      "4": 78,
      "5": 79,
      "6": 80,
      "7": 81,
      "8": 82,
      "9": 83,
      "-": 84,
      "'": 85,
      ".": 86,
      ",": 87,
      "!": 88,
      "?": 89,
      ":": 90,
      ";": 91,
      "\"": 92,
      "(": 93,
      ")": 94,
      "/": 95
    },
    "unk_token": "[UNK]"
  }
}