Update app.py

app.py

@@ -663,8 +663,8 @@ def generate_answer(message, choice, retrieval_mode, selected_model):
                 logging.debug(f"Generated LM-2 prompt: {prompt}")
 
                 response = selected_model(prompt, **{
-                    "max_new_tokens": 300,
-                    "return_full_text": False,
+                    "max_new_tokens": 250,
+                    "return_full_text": True,
                     "temperature": 0.0,
                     "do_sample": False,
                 })