Update app.py

app.py

@@ -32,7 +32,7 @@ def process_inputs(image, audio):
     input_len = input_ids["input_ids"].shape[-1]
 
     input_ids = input_ids.to(model.device, dtype=model.dtype)
-    with torch.inference_mode:
+    with torch.inference_mode():
         outputs = model.generate(
             **input_ids,
             max_new_tokens=max_tokens,