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": {
    "type": "BertNormalizer",
    "clean_text": true,
    "handle_chinese_chars": true,
    "strip_accents": null,
    "lowercase": true
  },
  "pre_tokenizer": {
    "type": "BertPreTokenizer"
  },
  "post_processor": {
    "type": "TemplateProcessing",
    "single": [
      {
        "SpecialToken": {
          "id": "[CLS]",
          "type_id": 0
        }
      },
      {
        "Sequence": {
          "id": "A",
          "type_id": 0
        }
      },
      {
        "SpecialToken": {
          "id": "[SEP]",
          "type_id": 0
        }
      }
    ],
    "pair": [
      {
        "SpecialToken": {
          "id": "[CLS]",
          "type_id": 0
        }
      },
      {
        "Sequence": {
          "id": "A",
          "type_id": 0
        }
      },
      {
        "SpecialToken": {
          "id": "[SEP]",
          "type_id": 0
        }
      },
      {
        "Sequence": {
          "id": "B",
          "type_id": 1
        }
      },
      {
        "SpecialToken": {
          "id": "[SEP]",
          "type_id": 1
        }
      }
    ],
    "special_tokens": {
      "[CLS]": {
        "id": "[CLS]",
        "ids": [
          2
        ],
        "tokens": [
          "[CLS]"
        ]
      },
      "[SEP]": {
        "id": "[SEP]",
        "ids": [
          3
        ],
        "tokens": [
          "[SEP]"
        ]
      }
    }
  },
  "decoder": {
    "type": "WordPiece",
    "prefix": "##",
    "cleanup": true
  },
  "model": {
    "type": "WordPiece",
    "unk_token": "[UNK]",
    "continuing_subword_prefix": "##",
    "max_input_chars_per_word": 100,
    "vocab": {
      "[PAD]": 0,
      "[UNK]": 1,
      "[CLS]": 2,
      "[SEP]": 3,
      "[MASK]": 4,
      "a": 5,
      "b": 6,
      "c": 7,
      "e": 8,
      "f": 9,
      "i": 10,
      "k": 11,
      "l": 12,
      "m": 13,
      "n": 14,
      "p": 15,
      "r": 16,
      "s": 17,
      "u": 18,
      "ı": 19,
      "##c": 20,
      "##ı": 21,
      "##n": 22,
      "##l": 23,
      "##m": 24,
      "##a": 25,
      "##i": 26,
      "##k": 27,
      "##r": 28,
      "##u": 29,
      "##b": 30,
      "##e": 31,
      "##p": 32,
      "##s": 33,
      "ac": 34,
      "##li": 35,
      "acı": 36,
      "el": 37,
      "fi": 38,
      "##ıl": 39,
      "##nıl": 40,
      "##ma": 41,
      "##ir": 42,
      "##is": 43,
      "##kir": 44,
      "##ub": 45,
      "##ps": 46,
      "acub": 47,
      "##lik": 48,
      "##lips": 49,
      "##lilik": 50,
      "acık": 51,
      "acınıl": 52,
      "ellips": 53,
      "fikir": 54,
      "acube": 55,
      "acınılma": 56,
      "ellipsis": 57,
      "fikirlilik": 58
    }
  }
}