Ideas & society2022 · shared on Hacker News
DeepNet: Scaling Transformers to 1k Layers
Explore DeepNet: Scaling Transformers to 1k Layers, its original source and Hacker News discussions. Discover community perspectives and save it to your reading list.
GO BEYOND THE ABSTRACT
The conversation around the idea.
Original Hacker News threads. Different perspectives, questions, and things worth thinking about.
Showing up to 100 related threads. A paper may appear in a comment rather than the original submission.
Yhomarp ·
DeepNet: Scaling Transformers to 1k Layers
194 points38 comments
Yashvardanian ·
DeepNet: Scaling Transformers to 1k Layers
1 points0 comments