diff --git a/unsloth/models/llama.py b/unsloth/models/llama.py
index 23a8c0a681..3c33253911 100644
--- a/unsloth/models/llama.py
+++ b/unsloth/models/llama.py
@@ -254,6 +254,7 @@ def LlamaAttention_fast_forward_inference(
     # pass
 
     # Attention
+    print(attention_mask)
     if bsz == 1:
         Qn *= self.scalar # See https://github.com/ggerganov/llama.cpp/issues/7805#issuecomment-2153349963
         # It seems like doing (Q * scalar) @ K is better than (Q @ K) * scalar to stop overflows