tokenizer.json

{
  "version": "1.0",
  "truncation": null,
  "padding": null,
  "added_tokens": [
    {"id": 50256, "content": "<|endoftext|>", "special": true, "single_word": false, "lstrip": false, "rstrip": false, "normalized": false}
  ],
  "normalizer": null,
  "pre_tokenizer": {"type": "ByteLevel", "add_prefix_space": false, "use_regex": true},
  "post_processor": null,
  "decoder": {"type": "ByteLevel"},
  "model": {
    "type": "BPE",
    "dropout": null,
    "unk_token": null,
    "continuing_subword_prefix": "",
    "end_of_word_suffix": "",
    "fuse_unk": false,
    "byte_fallback": false,
    "vocab": {},
    "merges": []
  }
}