What is the correct prompt format for llama2?

I was fine-tuning my chatbot named llama2 and using a prompt format “ [INST] {sys_prompt} {prompt} [/INST] {response} ”. However, after fine-tuning, it is giving the answer twice. I’m not sure if I’m going in the right direction or if there are still some missing parts. Can you assist me with this issue?"

The following format can be used for fine tuning:

Instruction:

{sample[“instruction”]}

Input:

{sample[“input”]}

Response:

{sample[“output”]}