generation_config.json

{
  "bos_token_id": 128000,
  "do_sample": true,
  "eos_token_id": [128001, 128009, 128256],
  "max_length": 4096,
  "temperature": 0.6,
  "top_p": 0.9,
  "transformers_version": "4.40.2"
}