tokenizer_config.json

{
  "add_prefix_space": false,
  "backend": "tokenizers",
  "bos_token": "<s>",
  "clean_up_tokenization_spaces": false,
  "eos_token": "</s>",
  "extra_special_tokens": [
    "<|start_header_id|>",
    "<|end_header_id|>"
  ],
  "is_local": false,
  "local_files_only": false,
  "model_input_names": [
    "input_ids",
    "attention_mask"
  ],
  "model_max_length": 16000,
  "pad_token": "<pad>",
  "tokenizer_class": "TokenizersBackend",
  "unk_token": "<unk>"
}