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": "<unk>",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": false,
      "special": true
    }
  ],
  "normalizer": null,
  "pre_tokenizer": {
    "type": "WhitespaceSplit"
  },
  "post_processor": null,
  "decoder": null,
  "model": {
    "type": "WordLevel",
    "vocab": {
      "<|pad|>": 0,
      "<|bos|>": 1,
      "<|eos|>": 2,
      "<unk>": 3,
      "<gap>": 4,
      "<no_gap>": 5,
      "<query>": 6,
      "<s>": 7,
      "-": 8,
      "1": 9,
      "2": 10,
      "A": 11,
      "B": 12,
      "C": 13,
      "D": 14,
      "E": 15,
      "F": 16,
      "G": 17,
      "H": 18,
      "I": 19,
      "K": 20,
      "L": 21,
      "M": 22,
      "N": 23,
      "O": 24,
      "P": 25,
      "Q": 26,
      "R": 27,
      "S": 28,
      "T": 29,
      "U": 30,
      "V": 31,
      "W": 32,
      "X": 33,
      "Y": 34,
      "Z": 35
    },
    "unk_token": "<unk>"
  }
}