推荐dinvlad · 2023-06
“FWIW there’s this paper that just came out, and promises a low hallucination factor (not quite for pentesting, but this could be a useful starting point)”
推荐 Gorilla 作为起点,它号称幻觉很少
微调 LLaMA 写 API 调用,配合检索,准确率超过 GPT-4
发布基于 LLaMA 微调的 Gorilla,在编写 API 调用上超过 GPT-4,针对大模型常见的参数错误和幻觉式误用 API 的问题。配合文档检索器后,它能适应测试时的文档变化与版本更新,并明显减轻幻觉。作者还提出由 HuggingFace、TorchHub、TensorHub API 构成的评测集 APIBench。
HN 上的人把它当作调用 API 时幻觉更少的方案,以及「7B 小模型针对特定任务微调后也能做得很好」的例子,并拿来与其他 LLM 工具调用工作对比。
“FWIW there’s this paper that just came out, and promises a low hallucination factor (not quite for pentesting, but this could be a useful starting point)”
“2. Gorilla: Large Language Model Connected with Massive APIs”
“The 7B size can perform very well when tuned on a specific menu of tasks:”
“Gorilla: Large Language Model Connected with Massive APIs”
“Gorilla: Large Language Model Connected with Massive APIs Gorilla”