tokenizers/expressions/tokenizer.json

{
  "version": "1.0",
  "truncation": null,
  "padding": null,
  "added_tokens": [
    {
      "id": 0,
      "content": "[UNK]",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": false,
      "special": true
    },
    {
      "id": 1,
      "content": "[SEP]",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": false,
      "special": true
    },
    {
      "id": 2,
      "content": "[PAD]",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": false,
      "special": true
    },
    {
      "id": 3,
      "content": "[CLS]",
      "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": false,
    "strip_accents": null,
    "lowercase": false
  },
  "pre_tokenizer": null,
  "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": [
          3
        ],
        "tokens": [
          "[CLS]"
        ]
      },
      "[SEP]": {
        "id": "[SEP]",
        "ids": [
          1
        ],
        "tokens": [
          "[SEP]"
        ]
      }
    }
  },
  "decoder": {
    "type": "WordPiece",
    "prefix": "##",
    "cleanup": true
  },
  "model": {
    "type": "WordLevel",
    "vocab": {
      "[UNK]": 0,
      "[SEP]": 1,
      "[PAD]": 2,
      "[CLS]": 3,
      "[MASK]": 4,
      "0": 5,
      "1": 6,
      "2": 7,
      "3": 8,
      "4": 9,
      "5": 10,
      "6": 11,
      "7": 12,
      "8": 13,
      "9": 14,
      "10": 15,
      "11": 16,
      "12": 17,
      "13": 18,
      "14": 19,
      "15": 20,
      "16": 21,
      "17": 22,
      "18": 23,
      "19": 24,
      "20": 25,
      "21": 26,
      "22": 27,
      "23": 28,
      "24": 29,
      "25": 30,
      "26": 31,
      "27": 32,
      "28": 33,
      "29": 34,
      "30": 35,
      "31": 36,
      "32": 37,
      "33": 38,
      "34": 39,
      "35": 40,
      "36": 41,
      "37": 42,
      "38": 43,
      "39": 44,
      "40": 45,
      "41": 46,
      "42": 47,
      "43": 48,
      "44": 49,
      "45": 50,
      "46": 51,
      "47": 52,
      "48": 53,
      "49": 54
    },
    "unk_token": "[UNK]"
  }
}