demo buildout 12

app.py

@@ -49,7 +49,7 @@ def infer(
         text: str,
         max_new_tokens: int
 ) -> str:
-    inputs = processor(text=text, images=resize_and_pad(image, 448), return_tensors="pt", padding="longest", do_convert_rgb=True).to(device)
+    inputs = processor(text=text, images=resize_and_pad(image, 448), return_tensors="pt", padding="longest", do_convert_rgb=True).to(device).to(dtype=model.dtype)
     with torch.inference_mode():
         generated_ids = model.generate(
             **inputs,