Hacker Newsnew | past | comments | ask | show | jobs | submitlogin

From what I understand top_k is the number of words it generates to pick from, and the top_p is the percentage of the top words it will use as the next word, correct?


I think it depends on the sampling/decoding method. Also, perhaps you could elaborate more on what you mean by top_p




Consider applying for YC's Summer 2026 batch! Applications are open till May 4

Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: