Update llama.py

2024-09-25 18:07:21 -07:00 · 2024-09-25 18:07:21 -07:00 · 8d910ecba9
commit 8d910ecba9
parent ff921b8601
1 changed files with 2 additions and 0 deletions
--- a/unsloth/models/llama.py
+++ b/unsloth/models/llama.py
@ -1409,6 +1409,8 @@ def _wrap_fast_inference(generate, device_type, dtype, model):

        # Autocasted
        with torch.autocast(device_type = device_type, dtype = dtype):
+            print(args)
+            print(kwargs)
            output = generate(*args, **kwargs)
        pass