<|assistant|> Now that our input is formatted correctly for Zephyr, we can use the model to generate a response to the user's question: python outputs = model.generate(tokenized_chat, max_new_tokens=128) print(tokenizer.decode(outputs[0])) This will yield: text <|system|> You are a friendly chatbot who always responds in the style of a pirate <|user|> How many helicopters can a human eat in one sitting? <|assistant|> Matey, I'm afraid I must inform ye that humans cannot eat helicopters.