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": "<eos>",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": false,
      "special": true
    },
    {
      "id": 2,
      "content": "<bos>",
      "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
    }
  ],
  "normalizer": null,
  "pre_tokenizer": {
    "type": "ByteLevel",
    "add_prefix_space": false,
    "trim_offsets": true,
    "use_regex": true
  },
  "post_processor": null,
  "decoder": null,
  "model": {
    "type": "BPE",
    "dropout": null,
    "unk_token": null,
    "continuing_subword_prefix": null,
    "end_of_word_suffix": null,
    "fuse_unk": false,
    "byte_fallback": false,
    "ignore_merges": false,
    "vocab": {
      "<pad>": 0,
      "<eos>": 1,
      "<bos>": 2,
      "<unk>": 3,
      "a": 4,
      "d": 5,
      "e": 6,
      "f": 7,
      "h": 8,
      "i": 9,
      "k": 10,
      "l": 11,
      "n": 12,
      "o": 13,
      "r": 14,
      "s": 15,
      "t": 16,
      "w": 17,
      "y": 18,
      "z": 19,
      "Ġ": 20,
      "Ġt": 21,
      "or": 22,
      "at": 23,
      "dat": 24,
      "el": 25,
      "en": 26,
      "er": 27,
      "es": 28,
      "for": 29,
      "hel": 30,
      "in": 31,
      "iz": 32,
      "ken": 33,
      "ld": 34,
      "lo": 35,
      "oken": 36,
      "wor": 37,
      "Ġdat": 38,
      "Ġfor": 39,
      "Ġwor": 40,
      "Ġtes": 41,
      "Ġtin": 42,
      "Ġtoken": 43,
      "hello": 44,
      "izer": 45,
      "Ġdata": 46,
      "Ġworld": 47,
      "Ġtest": 48,
      "Ġtiny": 49,
      "Ġtokenizer": 50
    },
    "merges": [
      [
        "Ġ",
        "t"
      ],
      [
        "o",
        "r"
      ],
      [
        "a",
        "t"
      ],
      [
        "d",
        "at"
      ],
      [
        "e",
        "l"
      ],
      [
        "e",
        "n"
      ],
      [
        "e",
        "r"
      ],
      [
        "e",
        "s"
      ],
      [
        "f",
        "or"
      ],
      [
        "h",
        "el"
      ],
      [
        "i",
        "n"
      ],
      [
        "i",
        "z"
      ],
      [
        "k",
        "en"
      ],
      [
        "l",
        "d"
      ],
      [
        "l",
        "o"
      ],
      [
        "o",
        "ken"
      ],
      [
        "w",
        "or"
      ],
      [
        "Ġ",
        "dat"
      ],
      [
        "Ġ",
        "for"
      ],
      [
        "Ġ",
        "wor"
      ],
      [
        "Ġt",
        "es"
      ],
      [
        "Ġt",
        "in"
      ],
      [
        "Ġt",
        "oken"
      ],
      [
        "hel",
        "lo"
      ],
      [
        "iz",
        "er"
      ],
      [
        "Ġdat",
        "a"
      ],
      [
        "Ġwor",
        "ld"
      ],
      [
        "Ġtes",
        "t"
      ],
      [
        "Ġtin",
        "y"
      ],
      [
        "Ġtoken",
        "izer"
      ]
    ]
  }
}