Update app.py

app.py

@@ -56,12 +56,20 @@ def run_example(image):
         image = image.convert("RGB")
 
     inputs = processor(text=prompt, images=image, return_tensors="pt")
+    
+    # Move inputs to GPU
+    inputs = {key: value.to("cuda:0") for key, value in inputs.items()}
+    
     generated_ids = model.generate(
         input_ids=inputs["input_ids"],
         pixel_values=inputs["pixel_values"],
         max_new_tokens=1024,
         num_beams=3
     )
+    
+    # Move generated_ids to CPU for decoding
+    generated_ids = generated_ids.to("cpu")
+    
     generated_text = processor.batch_decode(generated_ids, skip_special_tokens=False)[0]
     parsed_answer = processor.post_process_generation(generated_text, task=task_prompt, image_size=(image.width, image.height))
     return modify_caption(parsed_answer["<DESCRIPTION>"])