News for hackers. Stuff that matters.
Re:Small Fine-Tuned Models Are All You Need by stefanwebb on Sunday October 19, 2025 @04:29PM (#45637669)
Seems topical given some recent front-page HN articles on fine-tuning. I discuss a large-scale empirical study from 2014 of fine-tuning 7B models to outperform GPT-4 and GPT-3.5-Turbo, as well as arguments why fine-tuning is coming back into favor

There are no comments on this comment yet.