tokenizer.json

{
  "version": "1.0",
  "truncation": null,
  "padding": null,
  "added_tokens": [
    {
      "id": 0,
      "content": "<|endoftext|>",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": false,
      "special": true
    }
  ],
  "normalizer": null,
  "pre_tokenizer": {
    "type": "Digits",
    "individual_digits": 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": null,
    "end_of_word_suffix": null,
    "fuse_unk": false,
    "byte_fallback": false,
    "vocab": {
      "<|endoftext|>": 0,
      "$": 1,
      "+": 2,
      "0": 3,
      "1": 4,
      "2": 5,
      "3": 6,
      "4": 7,
      "5": 8,
      "6": 9,
      "7": 10,
      "8": 11,
      "9": 12,
      ";": 13,
      "=": 14
    },
    "merges": []
  }
}