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": "Sequence",
    "normalizers": [
      {
        "type": "NFC"
      },
      {
        "type": "Lowercase"
      }
    ]
  },
  "pre_tokenizer": {
    "type": "Whitespace"
  },
  "post_processor": {
    "type": "TemplateProcessing",
    "single": [
      {
        "SpecialToken",
        "id": "[CLS]"
      },
      {
        "Sequence",
        "id": "A"
      },
      {
        "SpecialToken",
        "id": "[SEP]"
      }
    ],
    "pair": [
      {
        "SpecialToken",
        "id": "[CLS]"
      },
      {
        "Sequence",
        "id": "A"
      },
      {
        "SpecialToken",
        "id": "[SEP]"
      },
      {
        "Sequence",
        "id": "B"
      },
      {
        "SpecialToken",
        "id": "[SEP]"
      }
    ],
    "special_tokens": {
      "[CLS]": {
        "id": "[CLS]",
        "ids": [2]
      },
      "[SEP]": {
        "id": "[SEP]",
        "ids": [3]
      }
    }
  },
  "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,
      "the": 5,
      "quick": 6,
      "brown": 7,
      "fox": 8,
      "jumps": 9,
      "over": 10,
      "lazy": 11,
      "dog": 12
    }
  }
}