diff --git a/unsloth/models/llama.py b/unsloth/models/llama.py index 61cf05e110..ad1b6f4943 100644 --- a/unsloth/models/llama.py +++ b/unsloth/models/llama.py @@ -1016,6 +1016,7 @@ def CausalLM_fast_forward(fast_forward_inference): logits_to_keep: Optional[int] = 0, *args, **kwargs, ) -> Union[Tuple, CausalLMOutputWithPast]: + print(past_key_values) if past_key_values is not None: outputs = fast_forward_inference( self,