tokenizer.json

{
  "version": "1.0",
  "truncation": null,
  "padding": null,
  "added_tokens": [
    {
      "id": 10,
      "content": "<CLS>",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": false,
      "special": true
    },
    {
      "id": 11,
      "content": "<SEP>",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": false,
      "special": true
    },
    {
      "id": 12,
      "content": "<EOD>",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": false,
      "special": true
    },
    {
      "id": 13,
      "content": "<MASK>",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": false,
      "special": true
    },
    {
      "id": 14,
      "content": "<PAD>",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": false,
      "special": true
    },
    {
      "id": 15,
      "content": "<s>",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": false,
      "special": true
    },
    {
      "id": 16,
      "content": "</s>",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": false,
      "special": true
    },
    {
      "id": 17,
      "content": "<UNK>",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": false,
      "special": true
    }
  ],
  "normalizer": null,
  "pre_tokenizer": {
    "type": "ByteLevel",
    "add_prefix_space": false,
    "trim_offsets": true,
    "use_regex": true
  },
  "post_processor": {
    "type": "TemplateProcessing",
    "single": [
      {
        "Sequence": {
          "id": "A",
          "type_id": 0
        }
      }
    ],
    "pair": [
      {
        "Sequence": {
          "id": "A",
          "type_id": 0
        }
      },
      {
        "Sequence": {
          "id": "B",
          "type_id": 0
        }
      }
    ],
    "special_tokens": {
      "<CLS>": {
        "id": "<CLS>",
        "ids": [
          10
        ],
        "tokens": [
          "<CLS>"
        ]
      },
      "<SEP>": {
        "id": "<SEP>",
        "ids": [
          11
        ],
        "tokens": [
          "<SEP>"
        ]
      }
    }
  },
  "decoder": null,
  "model": {
    "type": "BPE",
    "dropout": null,
    "unk_token": "<UNK>",
    "continuing_subword_prefix": null,
    "end_of_word_suffix": null,
    "fuse_unk": false,
    "byte_fallback": false,
    "ignore_merges": false,
    "vocab": {
      "[PAD]": 0,
      "[UNK]": 1,
      "[CLS]": 2,
      "[SEP]": 3,
      "[MASK]": 4,
      "C": 5,
      "G": 6,
      "T": 7,
      "A": 8,
      "N": 9,
      "<CLS>": 10,
      "<SEP>": 11,
      "<EOD>": 12,
      "<MASK>": 13,
      "<PAD>": 14,
      "<s>": 15,
      "</s>": 16,
      "<UNK>": 17
    },
    "merges": []
  }
}