Increase max token output

app.py

@@ -23,7 +23,7 @@ def init_llm():
 def get_response(prompt):
     try:
         prompts = [template.format(user_message=prompt)]
-        sampling_params = SamplingParams(temperature=0.3, top_p=0.95)
+        sampling_params = SamplingParams(temperature=0.3, top_p=0.95, max_tokens=500, stop_token_ids=[128009])
         outputs = llm.generate(prompts, sampling_params)
         for output in outputs:
             return output.outputs[0].text