原书出处
Designing Large Language Model Applications
Since prompting LLMs to be nice doesn’t work, we will need to tune the model in some way. Supervised fine-tuning (discussed in Chapter 6) on alignment datasets is an option. However, techniques like reinforcement learning have seen more success, which we will describe next in this section.
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