SFTMill: Easily [off-policy] distill any existing LLM with an OpenAI Compatible Endpoint. Turn any behavioral goal into a comprehensive dataset.

Disclaimer: Any* means any model that exposes its CoT without it being censored. Hey guys - half a tutorial/guide, and half an I built this, so I went for resources. This is something that I created for myself recently when I couldn't find any good existing solution. I wrote this post myself,

中文全文翻译正在补齐，可先查看下方英文原文。

Disclaimer: Any* means any model that exposes its CoT without it being censored. Hey guys - half a tutorial/guide, and half an I built this, so I went for resources. This is something that I created for myself recently when I couldn't find any good existing solution. I wrote this post myself,