From 8d910ecba9ce3a687491cbd555792d15ebe99d3d Mon Sep 17 00:00:00 2001 From: Daniel Han Date: Wed, 25 Sep 2024 18:07:21 -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 c187449902..48d1f7ec6e 100644 --- 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