tokenizer_config.json

{
  "backend": "tokenizers",
  "clean_up_tokenization_spaces": true,
  "cls_token": "[CLS]",
  "bos_token": "[CLS]",
  "eos_token": "<|endoftext|>",
  "is_local": false,
  "mask_token": "[MASK]",
  "model_input_names": ["input_ids", "attention_mask"],
  "model_max_length": 8192,
  "pad_token": "[PAD]",
  "sep_token": "[SEP]",
  "tokenizer_class": "TokenizersBackend",
  "unk_token": "[UNK]"
}