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": "<mask>",
      "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
    }
  ],
  "normalizer": null,
  "pre_tokenizer": {
    "type": "WhitespaceSplit"
  },
  "post_processor": null,
  "decoder": null,
  "model": {
    "type": "WordLevel",
    "vocab": {
      "<pad>": 0,
      "<mask>": 1,
      "<eos>": 2,
      "%": 3,
      "(": 4,
      ")": 5,
      "*": 6,
      "+": 7,
      ",": 8,
      "-": 9,
      "/": 10,
      ":": 11,
      ";": 12,
      "=": 13,
      "[": 14,
      "]": 15,
      "and": 16,
      "band": 17,
      "bool": 18,
      "bor": 19,
      "break": 20,
      "case": 21,
      "char": 22,
      "const": 23,
      "cont": 24,
      "else": 25,
      "eq": 26,
      "fld": 27,
      "float": 28,
      "flt": 29,
      "for": 30,
      "ge": 31,
      "gt": 32,
      "id": 33,
      "if": 34,
      "int": 35,
      "le": 36,
      "lt": 37,
      "minuseq": 38,
      "ne": 39,
      "not": 40,
      "num": 41,
      "or": 42,
      "pluseq": 43,
      "ret": 44,
      "struct": 45,
      "switch": 46,
      "void": 47,
      "while": 48,
      "{": 49,
      "}": 50
    },
    "unk_token": "<pad>"
  }
}