""" DPO strategies for zephyr """ def nectar(cfg): # pylint: disable=possibly-unused-variable,unused-argument def transform_fn(sample): data = {} data["prompt"] = ( "<|system|>\n\n" "<|user|>\n" f"{sample['prompt']}\n" "<|assistant|>\n" ) answers = sorted(sample["answers"], key=lambda x: x["rank"]) data["chosen"] = answers[-1]["answer"] data["rejected"] = answers[-2]["answer"] return data return transform_fn