tokenizer.json

{
  "version": "1.0",
  "truncation": null,
  "padding": null,
  "added_tokens": [
    {
      "id": 0,
      "content": "UNK",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": false,
      "special": true
    },
    {
      "id": 1,
      "content": "PAD",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": false,
      "special": true
    },
    {
      "id": 31,
      "content": "<|endoftext|>",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": false,
      "special": true
    }
  ],
  "normalizer": {
    "type": "Sequence",
    "normalizers": [
      {
        "type": "Replace",
        "pattern": {
          "String": "\n"
        },
        "content": " UTT_BOUNDARY"
      },
      {
        "type": "Strip",
        "strip_left": true,
        "strip_right": true
      }
    ]
  },
  "pre_tokenizer": {
    "type": "Whitespace"
  },
  "post_processor": null,
  "decoder": null,
  "model": {
    "type": "WordLevel",
    "vocab": {
      "UNK": 0,
      "PAD": 1,
      "BOS": 2,
      "EOS": 3,
      "WORD_BOUNDARY": 4,
      "UTT_BOUNDARY": 5,
      "k": 6,
      "s": 7,
      "o": 8,
      "b": 9,
      "a": 10,
      "h": 11,
      "n": 12,
      "t̠ʃ": 13,
      "i": 14,
      "j": 15,
      "d": 16,
      "e": 17,
      "ʃ": 18,
      "u": 19,
      "ɡ": 20,
      "r": 21,
      "f": 22,
      "t": 23,
      "m": 24,
      "d̠ʒ": 25,
      "l": 26,
      "q": 27,
      "v": 28,
      "z": 29,
      "p": 30
    },
    "unk_token": "UNK"
  }
}