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": "<bos>",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": false,
      "special": true
    },
    {
      "id": 2,
      "content": "<eos>",
      "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": {
    "type": "Sequence",
    "normalizers": [
      {
        "type": "Lowercase"
      },
      {
        "type": "NFKC"
      }
    ]
  },
  "pre_tokenizer": {
    "type": "Whitespace"
  },
  "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": {
      "<pad>": 0,
      "<bos>": 1,
      "<eos>": 2,
      "<unk>": 3,
      "(": 4,
      ")": 5,
      ",": 6,
      ".": 7,
      "a": 8,
      "b": 9,
      "c": 10,
      "d": 11,
      "e": 12,
      "f": 13,
      "g": 14,
      "h": 15,
      "i": 16,
      "j": 17,
      "k": 18,
      "l": 19,
      "m": 20,
      "n": 21,
      "o": 22,
      "p": 23,
      "r": 24,
      "s": 25,
      "t": 26,
      "u": 27,
      "v": 28,
      "y": 29,
      "z": 30,
      "ç": 31,
      "ö": 32,
      "ü": 33,
      "ğ": 34,
      "ı": 35,
      "ş": 36,
      "el": 37,
      "in": 38,
      "il": 39,
      "er": 40,
      "ir": 41,
      "en": 42,
      "la": 43,
      "me": 44,
      "bir": 45,
      "da": 46,
      "dil": 47,
      "ok": 48,
      "tü": 49,
      "eli": 50,
      "eni": 51,
      "bu": 52,
      "eğ": 53,
      "gü": 54,
      "ha": 55,
      "kç": 56,
      "le": 57,
      "ma": 58,
      "or": 59,
      "yor": 60,
      "ır": 61,
      "eği": 62,
      "ar": 63,
      "ay": 64,
      "ala": 65,
      "du": 66,
      "dır": 67,
      "ek": 68,
      "gin": 69,
      "iç": 70,
      "ldu": 71,
      "mo": 72,
      "ne": 73,
      "oldu": 74,
      "rkç": 75,
      "tir": 76,
      "tok": 77,
      "ve": 78,
      "ya": 79,
      "zel": 80,
      "zer": 81,
      "çok": 82,
      "ştir": 83,
      "türkç": 84,
      "enizer": 85,
      "lem": 86,
      "mak": 87,
      "eğit": 88,
      "alan": 89,
      "için": 90,
      "mod": 91,
      "tokenizer": 92,
      "türkçe": 93
    },
    "merges": [
      [
        "e",
        "l"
      ],
      [
        "i",
        "n"
      ],
      [
        "i",
        "l"
      ],
      [
        "e",
        "r"
      ],
      [
        "i",
        "r"
      ],
      [
        "e",
        "n"
      ],
      [
        "l",
        "a"
      ],
      [
        "m",
        "e"
      ],
      [
        "b",
        "ir"
      ],
      [
        "d",
        "a"
      ],
      [
        "d",
        "il"
      ],
      [
        "o",
        "k"
      ],
      [
        "t",
        "ü"
      ],
      [
        "el",
        "i"
      ],
      [
        "en",
        "i"
      ],
      [
        "b",
        "u"
      ],
      [
        "e",
        "ğ"
      ],
      [
        "g",
        "ü"
      ],
      [
        "h",
        "a"
      ],
      [
        "k",
        "ç"
      ],
      [
        "l",
        "e"
      ],
      [
        "m",
        "a"
      ],
      [
        "o",
        "r"
      ],
      [
        "y",
        "or"
      ],
      [
        "ı",
        "r"
      ],
      [
        "eğ",
        "i"
      ],
      [
        "a",
        "r"
      ],
      [
        "a",
        "y"
      ],
      [
        "a",
        "la"
      ],
      [
        "d",
        "u"
      ],
      [
        "d",
        "ır"
      ],
      [
        "e",
        "k"
      ],
      [
        "g",
        "in"
      ],
      [
        "i",
        "ç"
      ],
      [
        "l",
        "du"
      ],
      [
        "m",
        "o"
      ],
      [
        "n",
        "e"
      ],
      [
        "o",
        "ldu"
      ],
      [
        "r",
        "kç"
      ],
      [
        "t",
        "ir"
      ],
      [
        "t",
        "ok"
      ],
      [
        "v",
        "e"
      ],
      [
        "y",
        "a"
      ],
      [
        "z",
        "el"
      ],
      [
        "z",
        "er"
      ],
      [
        "ç",
        "ok"
      ],
      [
        "ş",
        "tir"
      ],
      [
        "tü",
        "rkç"
      ],
      [
        "eni",
        "zer"
      ],
      [
        "le",
        "m"
      ],
      [
        "ma",
        "k"
      ],
      [
        "eği",
        "t"
      ],
      [
        "ala",
        "n"
      ],
      [
        "iç",
        "in"
      ],
      [
        "mo",
        "d"
      ],
      [
        "tok",
        "enizer"
      ],
      [
        "türkç",
        "e"
      ]
    ]
  }
}