diff --git a/unsloth/models/llama.py b/unsloth/models/llama.py index 5a48959f3f..e2ce925f4b 100644 --- a/unsloth/models/llama.py +++ b/unsloth/models/llama.py @@ -1002,6 +1002,7 @@ def CausalLM_fast_forward(fast_forward_inference): attentions=outputs.attentions, ) print(output) + print(output) return output pass logits = self.lm_head(hidden_states.to(lm_head.dtype))