diff --git a/unsloth/models/llama.py b/unsloth/models/llama.py index 9f685937c3..6f954bf9a2 100644 --- a/unsloth/models/llama.py +++ b/unsloth/models/llama.py @@ -1018,6 +1018,7 @@ def CausalLM_fast_forward(fast_forward_inference): *args, **kwargs, ) -> Union[Tuple, CausalLMOutputWithPast]: # Check for uninitialized DynamicCache + print(past_key_values, len(past_key_values)) if past_key_values is not None and len(past_key_values) != 0: outputs = fast_forward_inference( self,