Add application file

app.py

@@ -13,9 +13,9 @@ model = Qwen2_5_VLForConditionalGeneration.from_pretrained(
 
 processor = AutoProcessor.from_pretrained(local_path)
 
+print("load successfully")
 # Function to process image and text and generate the output
 @torch.inference_mode()
-@spaces.GPU(duration=120)  # Specify a duration to avoid timeout
 def generate_output(image, text, button_click):
     # Prepare input data
     messages = [