generation_config.json

{
  "_from_model_config": true,
  "bos_token_id": 128000,
  "do_sample": true,
  "eos_token_id": 128001,
  "temperature": 0.6,
  "top_p": 0.9,
  "transformers_version": "4.43.3",
  "cache_implementation": "custom_hybrid"
}