Class GenerationConfig

tools/streamlit_demo.py:36–42

@dataclass
class GenerationConfig:
    # this config is used for chat to provide more diversity
    max_length: int = 32768
    top_p: float = 0.8
    temperature: float = 0.8
    do_sample: bool = True
    repetition_penalty: float = 1.005


@torch.inference_mode()