原书出处
Designing Large Language Model Applications
You can see that the tokens are case-sensitive: there are separate tokens for “office” and “Office.” Most models these days have case-sensitive vocabularies. Back in the day, the BERT model was released with both a cased and an uncased version.
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/ch03.html
EPUB SHA-256:1b4d2347fec2f949fcddfbaf4fad597a1ae20887a096cfae64c59a619b4781bf