tokenizer.json

{
  "version": "1.0",
  "truncation": {
    "direction": "Right",
    "max_length": 512,
    "strategy": "LongestFirst",
    "stride": 0
  },
  "padding": {
    "strategy": "BatchLongest",
    "direction": "Right",
    "pad_to_multiple_of": null,
    "pad_id": 0,
    "pad_type_id": 0,
    "pad_token": "[PAD]"
  },
  "added_tokens": [
    {
      "id": 0,
      "content": "[UNK]",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": false,
      "special": true
    },
    {
      "id": 1,
      "content": "[PAD]",
      "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": false
  },
  "pre_tokenizer": {
    "type": "WhitespaceSplit"
  },
  "post_processor": {
    "type": "TemplateProcessing",
    "single": [
      {
        "SpecialToken": {
          "id": "[CLS]",
          "type_id": 0
        }
      },
      {
        "Sequence": {
          "id": "A",
          "type_id": 0
        }
      }
    ],
    "pair": [
      {
        "Sequence": {
          "id": "A",
          "type_id": 0
        }
      },
      {
        "Sequence": {
          "id": "B",
          "type_id": 1
        }
      }
    ],
    "special_tokens": {
      "[CLS]": {
        "id": "[CLS]",
        "ids": [
          2
        ],
        "tokens": [
          "[CLS]"
        ]
      }
    }
  },
  "decoder": {
    "type": "WordPiece",
    "prefix": "##",
    "cleanup": true
  },
  "model": {
    "type": "WordPiece",
    "unk_token": "[UNK]",
    "continuing_subword_prefix": "##",
    "max_input_chars_per_word": 100,
    "vocab": {
      "[UNK]": 0,
      "[PAD]": 1,
      "[CLS]": 2,
      "[SEP]": 3,
      "[MASK]": 4,
      "\"": 5,
      "#": 6,
      "(": 7,
      ")": 8,
      "+": 9,
      "-": 10,
      ".": 11,
      "/": 12,
      "1": 13,
      "2": 14,
      "3": 15,
      "4": 16,
      "5": 17,
      "6": 18,
      "7": 19,
      "8": 20,
      "9": 21,
      "=": 22,
      "@": 23,
      "A": 24,
      "B": 25,
      "C": 26,
      "D": 27,
      "E": 28,
      "F": 29,
      "G": 30,
      "H": 31,
      "I": 32,
      "K": 33,
      "L": 34,
      "M": 35,
      "N": 36,
      "O": 37,
      "P": 38,
      "Q": 39,
      "R": 40,
      "S": 41,
      "T": 42,
      "V": 43,
      "W": 44,
      "X": 45,
      "Y": 46,
      "[": 47,
      "\\": 48,
      "]": 49,
      "a": 50,
      "c": 51,
      "i": 52,
      "l": 53,
      "n": 54,
      "o": 55,
      "r": 56,
      "s": 57,
      "##\"": 58,
      "##S": 59,
      "##E": 60,
      "##P": 61,
      "##]": 62,
      "##C": 63,
      "##O": 64,
      "##F": 65,
      "##[": 66,
      "##N": 67,
      "##B": 68,
      "##c": 69
    }
  }
}