tokenizer_config.json

{
  "backend": "tokenizers",
  "clean_up_tokenization_spaces": true,
  "cls_token": "[CLS]",
  "extra_special_tokens": [
    "<|padding|>",
    "<|endoftext|>",
    "[UNK]",
    "[CLS]",
    "[SEP]",
    "[PAD]",
    "[MASK]"
  ],
  "is_local": true,
  "mask_token": "[MASK]",
  "max_length": 8192,
  "model_input_names": [
    "input_ids",
    "attention_mask"
  ],
  "model_max_length": 8192,
  "model_specific_special_tokens": {},
  "pad_to_multiple_of": null,
  "pad_token": "[PAD]",
  "pad_token_type_id": 0,
  "padding_side": "right",
  "sep_token": "[SEP]",
  "stride": 0,
  "tokenizer_class": "TokenizersBackend",
  "truncation_side": "right",
  "truncation_strategy": "longest_first",
  "unk_token": "[UNK]"
}