From bd85f8f0740862a13b7b273195470bfb7dc8237d Mon Sep 17 00:00:00 2001
From: Daniel Han <danielhanchen@gmail.com>
Date: Wed, 25 Sep 2024 18:10:46 -0700
Subject: [PATCH] Update llama.py

---
 unsloth/models/llama.py | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/unsloth/models/llama.py b/unsloth/models/llama.py
index 48d1f7ec6e..a31a485676 100644
--- a/unsloth/models/llama.py
+++ b/unsloth/models/llama.py
@@ -1372,6 +1372,8 @@ def _wrap_fast_inference(generate, device_type, dtype, model):
     # Wraps inference with bfloat16 / float16
     @torch.inference_mode
     def _fast_generate(*args, **kwargs):
+        print(args)
+        print(kwargs)
 
         # Set a flag for generation!
         internal_model = model