generation_config.json

{
  "bos_token_id": 2,
  "cache_implementation": "hybrid",
  "do_sample": true,
  "eos_token_id": [
    1,
    106
  ],
  "max_length": 32768,
  "pad_token_id": 0,
  "top_k": 64,
  "top_p": 0.95,
  "transformers_version": "4.56.1"
}