原书出处
Designing Large Language Model Applications
The retrieved documents ideally contain the context required to predict the masked token, and not the token itself. Therefore, trivial retrievals that contain the masked token in the retrieved text are not included.
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/ch12.html
EPUB SHA-256:1b4d2347fec2f949fcddfbaf4fad597a1ae20887a096cfae64c59a619b4781bf