AI-powered
podcast player
Listen to all your favourite podcasts with AI-powered features
The Importance of Temperature Zero in Testing
I do everything pretty much these days at temperatures zero. I tend to use higher temperatures and then change the top P parameter, which is a sort of variation on this procedure that it trims the distribution of the long tail and then picks randomly from what's left. Usually the reason I'm doing some like that is some fighting against mode collapse, right? And there's cases where you want to be even more diverse than that. It becomes sort of an empirical problem of what maximizes performance.