Update app.py

app.py

@@ -1,10 +1,9 @@
-from threading import Thread
-from transformers import Qwen2VLForConditionalGeneration, Qwen2VLProcessor, TextIteratorStreamer, AutoProcessor, BatchFeature
-
-from gradio import ChatInterface, Textbox, Slider
 from spaces import GPU
 
+from threading import Thread
+from transformers import Qwen2VLForConditionalGeneration, Qwen2VLProcessor, TextIteratorStreamer, AutoProcessor, BatchFeature
 from qwen_vl_utils import process_vision_info
+from gradio import ChatInterface, Textbox, Slider
 
 model_path = "Pectics/Softie-VL-7B-250123"
 
@@ -34,8 +33,7 @@ def infer(
         temperature=temperature,
         top_p=top_p,
     )
-    thread = Thread(target=model.generate, kwargs=kwargs)
-    thread.start()
+    Thread(target=model.generate, kwargs=kwargs).start()
     response = ""
     for token in streamer:
         response += token