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": "[PAD]",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": false,
      "special": true
    },
    {
      "id": 2,
      "content": "<|endoftext|>",
      "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": "ByteLevel",
    "add_prefix_space": true,
    "trim_offsets": false,
    "use_regex": true
  },
  "decoder": {
    "type": "ByteLevel",
    "add_prefix_space": true,
    "trim_offsets": true,
    "use_regex": true
  },
  "model": {
    "type": "BPE",
    "dropout": null,
    "unk_token": null,
    "continuing_subword_prefix": "",
    "end_of_word_suffix": "",
    "fuse_unk": false,
    "byte_fallback": false,
    "ignore_merges": false,
    "vocab": {
      "<unk>": 0,
      "[PAD]": 1,
      "<|endoftext|>": 2,
      "AA": 3,
      "TT": 4,
      "TG": 5,
      "CA": 6,
      "CC": 7,
      "TA": 8,
      "GG": 9,
      "TC": 10,
      "A": 11,
      "T": 12,
      "G": 13,
      "C": 14,
      "▁": 15
    },
    "merges": [
      [
        "A",
        "A"
      ],
      [
        "T",
        "T"
      ],
      [
        "T",
        "G"
      ],
      [
        "C",
        "A"
      ],
      [
        "C",
        "C"
      ],
      [
        "T",
        "A"
      ],
      [
        "G",
        "G"
      ],
      [
        "T",
        "C"
      ]
    ]
  }
}