tokenizer.json

{
  "version": "1.0",
  "truncation": null,
  "padding": null,
  "added_tokens": [
    {
      "id": 0,
      "content": "[CLS]",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": false,
      "special": true
    },
    {
      "id": 1,
      "content": "[SEP]",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": false,
      "special": true
    },
    {
      "id": 2,
      "content": "[PAD]",
      "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
    },
    {
      "id": 4,
      "content": "[MASK]",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": false,
      "special": true
    },
    {
      "id": 5,
      "content": "[ILLEGAL]",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": false,
      "special": true
    },
    {
      "id": 6,
      "content": "~",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": false,
      "special": true
    }
  ],
  "normalizer": {
    "type": "Sequence",
    "normalizers": [
      {
        "type": "NFD"
      },
      {
        "type": "StripAccents"
      }
    ]
  },
  "pre_tokenizer": {
    "type": "Split",
    "pattern": {
      "String": ""
    },
    "behavior": "Isolated",
    "invert": false
  },
  "post_processor": {
    "type": "RobertaProcessing",
    "sep": [
      "[SEP]",
      1
    ],
    "cls": [
      "[CLS]",
      0
    ],
    "trim_offsets": false,
    "add_prefix_space": false
  },
  "decoder": {
    "type": "WordPiece",
    "prefix": "##",
    "cleanup": true
  },
  "model": {
    "type": "WordPiece",
    "unk_token": "[UNK]",
    "continuing_subword_prefix": "##",
    "max_input_chars_per_word": 100,
    "vocab": {
      "[CLS]": 0,
      "[SEP]": 1,
      "[PAD]": 2,
      "[UNK]": 3,
      "[MASK]": 4,
      "[ILLEGAL]": 5,
      "~": 6,
      ">": 7,
      " ": 8,
      "#": 9,
      "+": 10,
      "-": 11,
      "/": 12,
      "0": 13,
      "1": 14,
      "2": 15,
      "3": 16,
      "4": 17,
      "5": 18,
      "6": 19,
      "7": 20,
      "8": 21,
      "9": 22,
      "=": 23,
      "B": 24,
      "K": 25,
      "N": 26,
      "O": 27,
      "P": 28,
      "Q": 29,
      "R": 30,
      "a": 31,
      "b": 32,
      "c": 33,
      "d": 34,
      "e": 35,
      "f": 36,
      "g": 37,
      "h": 38,
      "k": 39,
      "n": 40,
      "p": 41,
      "q": 42,
      "r": 43,
      "w": 44,
      "x": 45,
      "_": 46
    }
  }
}