原书出处
Designing Large Language Model Applications
How large should your instruction-tuning dataset be? The “LIMA: Less Is More for Alignment” paper shows that you need only a few thousand high-quality examples to effectively fine-tune a model.
原书定位详情
来源:a19c7933-4eda-4176-aebd-30fe7e1ad292
正文位置:extracted/Designing Large Language Model Applications/_epub-src/OEBPS/ch06.html
EPUB SHA-256:1b4d2347fec2f949fcddfbaf4fad597a1ae20887a096cfae64c59a619b4781bf