{
  "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": "[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": "Sequence",
    "normalizers": [
      {
        "type": "NFD"
      },
      {
        "type": "StripAccents"
      }
    ]
  },
  "pre_tokenizer": {
    "type": "BertPreTokenizer"
  },
  "post_processor": null,
  "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,
      "A": 5,
      "C": 6,
      "G": 7,
      "T": 8,
      "##T": 9,
      "##G": 10,
      "##C": 11,
      "##A": 12,
      "AA": 13,
      "GA": 14,
      "TT": 15,
      "AT": 16,
      "##CT": 17,
      "##CA": 18,
      "CA": 19,
      "GT": 20,
      "AG": 21,
      "GG": 22,
      "GAA": 23,
      "##CC": 24,
      "AAA": 25,
      "CT": 26,
      "GAT": 27,
      "AAT": 28,
      "TA": 29,
      "AAG": 30,
      "ATT": 31,
      "##CG": 32,
      "CAA": 33,
      "TTG": 34,
      "TTA": 35,
      "TTT": 36,
      "AAC": 37,
      "TCT": 38,
      "GGT": 39,
      "TG": 40,
      "GTT": 41,
      "AGA": 42,
      "ATG": 43,
      "GCT": 44,
      "GAC": 45,
      "ACT": 46,
      "GAG": 47,
      "TCA": 48,
      "TAT": 49,
      "TTC": 50,
      "ATA": 51,
      "ACA": 52,
      "CCA": 53,
      "ATC": 54,
      "GCA": 55,
      "AGT": 56,
      "TAC": 57,
      "TCC": 58,
      "CAT": 59,
      "CTA": 60,
      "CCT": 61,
      "CG": 62,
      "CAG": 63,
      "GCC": 64,
      "ACC": 65,
      "CTT": 66,
      "GTA": 67,
      "GTC": 68,
      "GGA": 69,
      "GTG": 70,
      "CTG": 71,
      "TGG": 72,
      "AGC": 73,
      "GGC": 74,
      "AGG": 75,
      "TCG": 76,
      "ACG": 77,
      "TGT": 78,
      "CAC": 79,
      "CCC": 80,
      "CGT": 81,
      "GCG": 82,
      "GGG": 83,
      "CCG": 84,
      "CTC": 85,
      "TGC": 86,
      "CGA": 87,
      "CGC": 88,
      "CGG": 89,
      "TAA": 90,
      "TGA": 91,
      "TAG": 92
    }
  }
}