diff --git a/unsloth/models/llama.py b/unsloth/models/llama.py index fbc6d53afb..653ebb351f 100644 --- a/unsloth/models/llama.py +++ b/unsloth/models/llama.py @@ -706,7 +706,6 @@ def LlamaModel_fast_forward( pass # Ignore attention_mask - print(attention_mask, attention_mask.shape, attention_mask.dtype) if attention_mask is None: padding_mask = None elif attention_mask is None and self.training: