Update app.py

app.py

@@ -9,10 +9,10 @@ client = InferenceClient()
 def generate_response(prompt_template, **kwargs):
     prompt = os.getenv(prompt_template).format(**kwargs)
     stream = client.chat.completions.create(
-        model="Qwen/Qwen2.5-Math-72B-Instruct",
+        model="Qwen/Qwen2.5-Math-7B-Instruct",
         messages=[{"role": "user", "content": prompt}],
         temperature=0.7,
-        max_tokens=512,
+        max_tokens=1024,
         top_p=0.8,
         stream=True
     )