Update app.py

app.py

@@ -189,9 +189,9 @@ def chat_qwen_vl(messages: str, history: list, temperature: float = 0.1, max_new
     inputs = inputs.to(model.device)
 
     streamer = TextIteratorStreamer(
-        tokenizer, timeout=20.0, skip_prompt=True, skip_special_tokens=True)
+        tokenizer, timeout=2000.0, skip_prompt=True, skip_special_tokens=True)
 
-    gen_kwargs = {'max_new_tokens': 512, 'streamer': streamer, **inputs}
+    gen_kwargs = {'max_new_tokens': 128, 'streamer': streamer, **inputs}
 
     thread = Thread(target=model.generate, kwargs=gen_kwargs)
     thread.start()