DaoyuanLi2816/tracedistill
Distill teacher chains-of-thought into a LoRA adapter via a strict boxed-answer format contract + two-phase Train→Nudge (silver-medal NVIDIA Nemotron reasoning recipe, as a tested library).
⭐ 72
⑂ 12
Python
MIT
· 26 天前推送
72
Watchers
0
贡献者
0
Commits
0
Releases
0
Open Issues
26 天前
最近推送
原文
中文
暂无 README