Update app.py

app.py

@@ -143,7 +143,7 @@ def try_sympy_compute(message):
 
 def respond(message, history, system_message, max_tokens, temperature, top_p):
     """Streaming response with error handling"""
-    client = InferenceClient(model="nvidia/NVIDIA-Nemotron-Nano-9B-v2")
+    client = InferenceClient(model="Qwen/Qwen3-Omni-30B-A3B-Thinking")
     
     messages = [{"role": "system", "content": system_message}]
     for msg in history: