From b6a7e2fe15c21f5847279f23e280cc5a0e7049ef Mon Sep 17 00:00:00 2001 From: Gustavo de Rosa Date: Wed, 27 Sep 2023 15:22:44 +0000 Subject: [PATCH] Upload modeling_mixformer_sequential.py --- modeling_mixformer_sequential.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/modeling_mixformer_sequential.py b/modeling_mixformer_sequential.py index 22b75f1..7d4f722 100644 --- a/modeling_mixformer_sequential.py +++ b/modeling_mixformer_sequential.py @@ -753,7 +753,7 @@ class MixFormerSequentialForCausalLM(MixFormerSequentialPreTrainedModel): **kwargs, ) -> CausalLMOutputWithPast: if attention_mask is not None and self.training: - raise ValueError("`attention_mask` is not supported during training.") + print("`attention_mask` is not supported during training. Using it might lead to unexpected results.") if past_key_values is None and attention_mask is None: lm_logits = self.layers(input_ids)