tokenizer_config.json

{
  "add_prefix_space": false,
  "backend": "tokenizers",
  "bos_token": "<|endoftext|>",
  "clean_up_tokenization_spaces": false,
  "eos_token": "<|endoftext|>",
  "errors": "replace",
  "is_local": false,
  "model_max_length": 8192,
  "pad_token": "<|pad|>",
  "tokenizer_class": "GPT2Tokenizer",
  "unk_token": "<|endoftext|>"
}