tokenizer.json

{
  "version": "1.0",
  "truncation": {
    "direction": "Right",
    "max_length": 512,
    "strategy": "LongestFirst",
    "stride": 0
  },
  "padding": {
    "strategy": {
      "Fixed": 512
    },
    "direction": "Right",
    "pad_to_multiple_of": null,
    "pad_id": 0,
    "pad_type_id": 0,
    "pad_token": "[PAD]"
  },
  "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": "[CLS]",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": false,
      "special": true
    },
    {
      "id": 3,
      "content": "[SEP]",
      "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
    }
  ],
  "normalizer": null,
  "pre_tokenizer": {
    "type": "Split",
    "pattern": {
      "String": ""
    },
    "behavior": "Isolated",
    "invert": false
  },
  "post_processor": null,
  "decoder": null,
  "model": {
    "type": "WordLevel",
    "vocab": {
      "[PAD]": 0,
      "[UNK]": 1,
      "[CLS]": 2,
      "[SEP]": 3,
      "[MASK]": 4,
      "\n": 5,
      " ": 6,
      "!": 7,
      "?": 8,
      "a": 9,
      "b": 10,
      "c": 11,
      "d": 12,
      "e": 13,
      "f": 14,
      "g": 15,
      "h": 16,
      "i": 17,
      "j": 18,
      "k": 19,
      "l": 20,
      "m": 21,
      "n": 22,
      "o": 23,
      "p": 24,
      "q": 25,
      "r": 26,
      "s": 27,
      "t": 28,
      "u": 29,
      "v": 30,
      "w": 31,
      "x": 32,
      "y": 33,
      "z": 34,
      "A": 35,
      "B": 36,
      "C": 37,
      "D": 38,
      "E": 39,
      "F": 40,
      "G": 41,
      "H": 42,
      "I": 43,
      "J": 44,
      "K": 45,
      "L": 46,
      "M": 47,
      "N": 48,
      "O": 49,
      "P": 50,
      "Q": 51,
      "R": 52,
      "S": 53,
      "T": 54,
      "U": 55,
      "V": 56,
      "W": 57,
      "X": 58,
      "Y": 59,
      "Z": 60
    },
    "unk_token": "[UNK]"
  }
}