News for hackers. Stuff that matters.
Re:QwQ-32B: Embracing the Power of Reinforcement Learning by dulakian on Wednesday March 05, 2025 @06:59PM (#43274472)
My informal testing puts it just under Deepseek-R1. Very impressive for 32B. It maybe thinks a bit too much for my taste. In some of my tests the thinking tokens were 10x the size of the final answer. I am eager to test it with function calling over the weekend.

There are no comments on this comment yet.