DeepScaleR: Surpassing O1-Preview with a 1.5B Model by Scaling RL Posted by mluo on Monday February 10, 2025 @12:05PM from the pretty-radio-b75.notion.site dept. https://pretty-radio-b75.notion.site/DeepScaleR-Surpassing-O1-Preview-with-a-1-5B-Model-by-Scaling-RL-19681902c1468005bed8ca303013a4e2 ( no comments | 5 points | on HN )
There are no comments yet.