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": "<unk>",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": false,
      "special": true
    },
    {
      "id": 2,
      "content": "<mask>",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": false,
      "special": true
    },
    {
      "id": 3,
      "content": "<bos>",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": false,
      "special": true
    },
    {
      "id": 4,
      "content": "<eos>",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": false,
      "special": true
    }
  ],
  "normalizer": null,
  "pre_tokenizer": {
    "type": "Split",
    "pattern": {
      "String": ""
    },
    "behavior": "Removed",
    "invert": false
  },
  "post_processor": null,
  "decoder": null,
  "model": {
    "type": "WordPiece",
    "unk_token": "<unk>",
    "continuing_subword_prefix": "##",
    "max_input_chars_per_word": 100,
    "vocab": {
      "<pad>": 0,
      "<unk>": 1,
      "<mask>": 2,
      "<bos>": 3,
      "<eos>": 4,
      "|": 5,
      "X": 6,
      "B": 7,
      "O": 8,
      "U": 9,
      "Z": 10,
      "J": 11,
      "L": 12,
      "A": 13,
      "G": 14,
      "V": 15,
      "S": 16,
      "E": 17,
      "R": 18,
      "T": 19,
      "I": 20,
      "D": 21,
      "P": 22,
      "K": 23,
      "Q": 24,
      "N": 25,
      "F": 26,
      "Y": 27,
      "M": 28,
      "H": 29,
      "W": 30,
      "C": 31
    }
  }
}