Update app.py

app.py

@@ -38,7 +38,7 @@ def inference(prompt, image):
     text_chunks = [tokenizer(chunk).input_ids for chunk in text.split('<image>')]
     input_ids = torch.tensor(text_chunks[0] + [-200] + text_chunks[1], dtype=torch.long).unsqueeze(0)
 
-    image_tensor = model.process_images([image], model.config).to(dtype=model.dtype)
+    image_tensor = model.process_images([image], model.config).to(dtype=model.dtype, device=model.device) # Move to model's device
 
     # generate
     output_ids = model.generate(