← 返回卡片

原书出处

Designing Large Language Model Applications

First Edition · 核验版本的摘录快照 · 导入于 2026-11-14T13:54:13.954Z

If you are using encoder-only models like BERT, the output probability scores can be used as the measure of confidence. Thus, a group of well-calibrated models will enable us to efficiently route the input to the most suitable model. (Recall our discussion on model calibration in Chapter 5.)

此预览只包含定位所需的摘录和上下文。

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/ch13.html

EPUB SHA-256:1b4d2347fec2f949fcddfbaf4fad597a1ae20887a096cfae64c59a619b4781bf