tokenizer.json

{
  "version": "1.0",
  "truncation": null,
  "padding": null,
  "added_tokens": [
    {
      "id": 4,
      "content": "[UNK]",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": false,
      "special": true
    },
    {
      "id": 5,
      "content": "[MASK]",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": false,
      "special": true
    },
    {
      "id": 6,
      "content": "[PAD]",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": false,
      "special": true
    },
    {
      "id": 7,
      "content": "[CLS]",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": false,
      "special": true
    },
    {
      "id": 8,
      "content": "[SEP]",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": false,
      "special": true
    }
  ],
  "normalizer": {
    "type": "Lowercase"
  },
  "pre_tokenizer": {
    "type": "WhitespaceSplit"
  },
  "post_processor": {
    "type": "TemplateProcessing",
    "single": [
      {
        "SpecialToken": {
          "id": "[CLS]",
          "type_id": 0
        }
      },
      {
        "Sequence": {
          "id": "A",
          "type_id": 0
        }
      },
      {
        "SpecialToken": {
          "id": "[SEP]",
          "type_id": 0
        }
      },
      {
        "SpecialToken": {
          "id": "[MASK]",
          "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": [
          7
        ],
        "tokens": [
          "[CLS]"
        ]
      },
      "[MASK]": {
        "id": "[MASK]",
        "ids": [
          5
        ],
        "tokens": [
          "[MASK]"
        ]
      },
      "[SEP]": {
        "id": "[SEP]",
        "ids": [
          8
        ],
        "tokens": [
          "[SEP]"
        ]
      }
    }
  },
  "decoder": {
    "type": "BPEDecoder",
    "suffix": "</w>"
  },
  "model": {
    "type": "BPE",
    "dropout": null,
    "unk_token": "[UNK]",
    "continuing_subword_prefix": null,
    "end_of_word_suffix": null,
    "fuse_unk": false,
    "byte_fallback": false,
    "vocab": {
      "a": 0,
      "t": 1,
      "g": 2,
      "c": 3,
      "[UNK]": 4,
      "[MASK]": 5,
      "[PAD]": 6,
      "[CLS]": 7,
      "[SEP]": 8
    },
    "merges": []
  }
}