AI & machine learning2024 · shared on Hacker News
NGPT: Normalized Transformer with Representation Learning on the Hypersphere
Explore NGPT: Normalized Transformer with Representation Learning on the Hypersphere, 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.
Links found in the discussion
Up to 50 recent source links, in HN item order.
Yfamouswaffles ·
TokenFormer: Rethinking Transformer Scaling with Tokenized Model Parameters
174 points33 comments
Yprogramd ·
NGPT: Normalized Transformer with Representation Learning on the Hypersphere
4 points0 comments