>10x More Efficient Pretraining — Magic

>10x More Efficient Pretraining

Research update on compute-efficient pretraining and scaling to trillion-parameter models.
107 points by ronfriedhaber 44 days ago magic.dev 60 comments
Summary not yet generated for this article.

Comments (60 of ) ⌛

Loading more comments... ⌛
Scroll down to load more comments
No comments available.
Type to search HN and engineering blog articles
Press Escape to close  |  ↑↓ to navigate  |  Enter to open