Update app.py

app.py

@@ -36,7 +36,8 @@ if input_text:
     # Stream the output
     for token in llm(
         model_input,
-        max_tokens=32,
+        # max_tokens=32,
+        max_tokens=None,
         stop=["<end_of_turn>"],
         echo=True,
         stream=True  # Enable streaming