Update app.py

app.py

@@ -57,8 +57,8 @@ memory = ConversationBufferWindowMemory()
 llm = CTransformers(model='TheBloke/Llama-2-7B-Chat-GGML',
                     model_file='llama-2-7b-chat.ggmlv3.q3_K_S.bin',
                     model_type='llama',
-                    config={'max_new_tokens': 15,
-                            'temperature': 0.01}
+                    config={'max_new_tokens': 25,
+                            'temperature': 0.2}
                     )
 
 # convo = ConversationChain(