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": "<|bos|>",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": false,
      "special": true
    },
    {
      "id": 2,
      "content": "<|eos|>",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": false,
      "special": true
    },
    {
      "id": 3,
      "content": "<|tag_start|>",
      "single_word": true,
      "lstrip": false,
      "rstrip": false,
      "normalized": false,
      "special": false
    },
    {
      "id": 4,
      "content": "<|tag_end|>",
      "single_word": true,
      "lstrip": false,
      "rstrip": false,
      "normalized": false,
      "special": false
    },
    {
      "id": 5,
      "content": "<|5|>",
      "single_word": true,
      "lstrip": false,
      "rstrip": false,
      "normalized": false,
      "special": false
    },
    {
      "id": 6,
      "content": "<|3|>",
      "single_word": true,
      "lstrip": false,
      "rstrip": false,
      "normalized": false,
      "special": false
    }
  ],
  "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": true,
    "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": null,
    "end_of_word_suffix": null,
    "fuse_unk": false,
    "byte_fallback": false,
    "vocab": {
      "<|pad|>": 0,
      "<|bos|>": 1,
      "<|eos|>": 2,
      "<|tag_start|>": 3,
      "<|tag_end|>": 4,
      "<|5|>": 5,
      "<|3|>": 6,
      "0": 7,
      "1": 8,
      "2": 9,
      "3": 10,
      "4": 11,
      "5": 12,
      "6": 13,
      "7": 14,
      "8": 15,
      "9": 16,
      "A": 17,
      "T": 18,
      "C": 19,
      "G": 20,
      "N": 21
    },
    "merges": []
  }
}