tokenizer_config.json

{
  "clean_up_tokenization_spaces": false,
  "eos_token": "<|endoftext|>",
  "model_input_names": [
    "input_ids",
    "attention_mask"
  ],
  "model_max_length": 1024,
  "pad_token": "<|endoftext|>",
  "tokenizer_class": "PreTrainedTokenizerFast"
}