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": "<bos>",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": false,
      "special": true
    },
    {
      "id": 2,
      "content": "<eos>",
      "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": {
    "type": "Sequence",
    "normalizers": [
      {
        "type": "NFKC"
      }
    ]
  },
  "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,
      "<bos>": 1,
      "<eos>": 2,
      "<unk>": 3,
      ".": 4,
      "D": 5,
      "a": 6,
      "c": 7,
      "e": 8,
      "f": 9,
      "h": 10,
      "i": 11,
      "l": 12,
      "m": 13,
      "n": 14,
      "o": 15,
      "r": 16,
      "s": 17,
      "t": 18,
      "u": 19,
      "x": 20,
      "y": 21,
      "z": 22,
      "Ġ": 23,
      "ti": 24
    },
    "merges": [
      [
        "t",
        "i"
      ]
    ]
  }
}