Modifying the answer format (### Human: xxx , ### Assistant: xxx)

I've been using Vicuna for Question-Answering.

I'm using the py-bindings (llama-cpp-python) and LangChain.

My prompt template is:

template = """Use the following pieces of context to answer the question at the end. Use three sentences maximum. 
{context}
Question: {question}
Answer: Think step by step """

I'm initializing the model:

llm = LlamaCpp(
                model_path="/<path>/vicuna_13B/ggml-vicuna-13b-4bit.bin",
                callback_manager=callback_manager,
                verbose=True,
                n_threads=6,
                n_ctx=2048,
                use_mlock=True)

I notice it will answer questions in a rhetorical style with ### Human: and ### Assistant: in the answer:

### Human: xxx? 
### Assistant: xxx

Have others seen this and / or should I be using an alternative prompt?

(Note: this question also exists here.)

Start with the reported prompt template and LlamaCpp initialization, then compare the observed Vicuna output with the expected answer format. The issue provides no repository files or tests; done would require identifying whether the prompt or model configuration causes the extra Human and Assistant markers and documenting a reproducible resolution.