Update app.py

app.py

@@ -51,7 +51,7 @@ def respond(message, chat_history, instruction, temperature=0.7):
     prompt = format_chat_prompt(message, chat_history, instruction)
     chat_history = chat_history + [[message, ""]]
     stream = generate_seqs(prompt = prompt,
-                                    max_new_tokens=1024,
+                                    max_new_tokens=8192,
                                     stop_sequence=["\nUser:", "<|endoftext|>"],
                                     temperature=temperature).split('Assistant: ')[-1]
                                     #stop_sequence to not generate the user answer