tokenizer_config.json

{
  "add_prefix_space": false,
  "backend": "tokenizers",
  "bos_token": "<beginning_of_sentence>",
  "clean_up_tokenization_spaces": false,
  "eos_token": "<end_of_sentence>",
  "errors": "replace",
  "is_local": false,
  "model_max_length": 40960000,
  "pad_token": null,
  "tokenizer_class": "GPT2Tokenizer",
  "unk_token": "<end_of_document>"
}