Change Max new tokens to 250

app.py

@@ -112,7 +112,7 @@ def get_completion(
         model=model,
         messages=messages,
         temperature=temperature,  # this is the degree of randomness of the model's output
-        max_tokens=max_new_tokens,  # this is the number of new tokens being generated
+        max_new_tokens=250,  # this is the number of new tokens being generated
         top_p=top_p,
         top_k=top_k,
         stream=stream,