PTQ-Level Efficiency, QAT-Level Accuracy | 训练后量化的效率,量化感知训练的精度
fixl eval bug (#461)
Heng Guo5b95a8e65970
diff --git a/auto_round/script/llm.py b/auto_round/script/llm.pyindex 054960df3..3bd53f3df 100644--- a/auto_round/script/llm.py+++ b/auto_round/script/llm.py@@ -588,8 +588,9 @@ def tune(args):if args.eval_task_by_task:eval_task_by_task(user_model, device=device_str, tasks=args.tasks, batch_size=args.eval_bs)else:- if args.eval_bs is None:- args.eval_bs = "auto"+ if args.eval_bs is None or args.eval_bs == "auto":+ logger.warning("This API does not support auto currently, reset eval_bs to 16")+ args.eval_bs = 16from auto_round.eval.evaluation import simple_evaluate_user_modelres = simple_evaluate_user_model(user_model, tokenizer, tasks=tasks, batch_size=args.eval_bs, device=device_str)