diff --git a/src/llmtuner/train/tuner.py b/src/llmtuner/train/tuner.py index 1b8e3cb7..e9b195de 100644 --- a/src/llmtuner/train/tuner.py +++ b/src/llmtuner/train/tuner.py @@ -64,6 +64,15 @@ def export_model(args: Optional[Dict[str, Any]] = None): for param in model.parameters(): param.data = param.data.to(output_dtype) + # Configuration check and fix + config = model.generation_config + if config.do_sample and ( + (config.temperature is not None and config.temperature != 1.0) or + (config.top_p is not None and config.top_p != 1.0) or + (config.typical_p is not None and config.typical_p != 1.0) + ): + config.do_sample = False + model.save_pretrained( save_directory=model_args.export_dir, max_shard_size="{}GB".format(model_args.export_size),