tokenizer.json

{
  "version": "1.0",
  "truncation": null,
  "padding": null,
  "added_tokens": [
    {
      "id": 27,
      "content": "[PAD]",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": false,
      "special": true
    },
    {
      "id": 28,
      "content": "[UNK]",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": false,
      "special": true
    },
    {
      "id": 29,
      "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": {
      " ": 0,
      "a": 1,
      "b": 2,
      "c": 3,
      "d": 4,
      "e": 5,
      "f": 6,
      "g": 7,
      "h": 8,
      "i": 9,
      "j": 10,
      "k": 11,
      "l": 12,
      "m": 13,
      "n": 14,
      "o": 15,
      "p": 16,
      "q": 17,
      "r": 18,
      "s": 19,
      "t": 20,
      "u": 21,
      "v": 22,
      "w": 23,
      "x": 24,
      "y": 25,
      "z": 26,
      "[PAD]": 27,
      "[UNK]": 28,
      "[MASK]": 29
    },
    "unk_token": "[UNK]"
  }
}