Update app.py

app.py

@@ -28,7 +28,7 @@ try:
     model = AutoModelForImageTextToText.from_pretrained(
         MODEL_ID,
         torch_dtype=torch.bfloat16,
-        # attn_implementation="flash_attention_2",
+        attn_implementation="flash_attention_2",
         trust_remote_code=True 
     ).to("cuda")
     processor = AutoProcessor.from_pretrained(MODEL_ID, trust_remote_code=True)
@@ -266,6 +266,5 @@ else:
             outputs=[output_coords_component, output_image_component]
         )
 
-# --- Launch the Gradio app ---
 if __name__ == "__main__":
-    demo.launch(debug=True) # Set debug=False for production
+    demo.launch(debug=True)