tokenizer_config.json

{
  "tokenizer_class": "GPT2Tokenizer",
  "vocab_size": 50257,
  "model_max_length": 1024,
  "padding_side": "left",
  "truncation_side": "left",
  "chat_template": null,
  "tokenize_chinese_chars": true,
  "strip_accents": null,
  "do_lower_case": true,
  "do_basic_tokenize": true,
  "never_split": null,
  "unk_token": "<|endoftext|>",
  "sep_token": "<|endoftext|>",
  "pad_token": "<|endoftext|>",
  "cls_token": "<|endoftext|>",
  "mask_token": "<|endoftext|>",
  "special_tokens_map_file": null,
  "name_or_path": "gpt2",
  "tokenizer_file": null,
  "added_tokens_file": null
}