← 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 2026-11-14T13:54:13.943Z

compute is to search through the generation probability distribution. The idea is that for every token being generated, there is a probability assigned to every token in the vocabulary, so if we search properly, we might end up traversing the probability space and choosing the right path to generate the correct answer. Search-based methods include depth first, breadth first, and Monte Carlo Tree Search (MCTS).

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/ch08.html

EPUB SHA-256:1b4d2347fec2f949fcddfbaf4fad597a1ae20887a096cfae64c59a619b4781bf