tokenizer_config.json

{
  "backend": "tokenizers",
  "bos_token": "<|begin_of_text|>",
  "clean_up_tokenization_spaces": true,
  "eos_token": "<|end_of_text|>",
  "extra_special_tokens": [
    "<mask_1>",
    "<mask_2>",
    "<mask_3>",
    "<mask_4>",
    "<mask_5>",
    "<mask_6>"
  ],
  "is_local": false,
  "local_files_only": false,
  "model_input_names": [
    "input_ids",
    "attention_mask"
  ],
  "model_max_length": 131072,
  "pad_token": "<|end_of_text|>",
  "tokenizer_class": "TokenizersBackend"
}