tokenizer.json

{
  "version": "1.0",
  "truncation": null,
  "padding": null,
  "added_tokens": [],
  "normalizer": null,
  "pre_tokenizer": null,
  "post_processor": null,
  "decoder": null,
  "model": {
    "type": "BPE",
    "dropout": null,
    "unk_token": "<unk>",
    "continuing_subword_prefix": null,
    "end_of_word_suffix": null,
    "fuse_unk": false,
    "byte_fallback": false,
    "ignore_merges": false,
    "vocab": {
      "<unk>": 0,
      " ": 1,
      "!": 2,
      ",": 3,
      ".": 4,
      "H": 5,
      "T": 6,
      "a": 7,
      "d": 8,
      "e": 9,
      "h": 10,
      "i": 11,
      "l": 12,
      "o": 13,
      "r": 14,
      "s": 15,
      "t": 16,
      "w": 17,
      "He": 18,
      "ll": 19,
      "llo": 20,
      "or": 21,
      "ld": 22
    },
    "merges": [
      "H e",
      "l l",
      "ll o",
      "o r",
      "l d"
    ]
  }
}