原书出处
Designing Large Language Model Applications
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).
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