News for hackers. Stuff that matters.
Re:QwQ-32B: Embracing the Power of Reinforcement Learning by smallerize on Thursday March 06, 2025 @06:30PM (#43286087)
Well I can't be positive, but it looks like some of the factors that support a long context length might be set wrong. https://blog.eleuther.ai/yarn/

There are no comments on this comment yet.