Every story and comment from the Hacker News API, in a layout borrowed from 2001.
A comment on Magistral — the first reasoning model by Mistral AI. Parent comment
The goal of it was to "force" the model not to stray to far away from the original checkpoint, but it can hinder the model from learning new things
There are no comments on this comment yet.
The goal of it was to "force" the model not to stray to far away from the original checkpoint, but it can hinder the model from learning new things