Ideas & society2023 · shared on Hacker News
Direct initialization of transformers using larger pretrained ones
Explore Direct initialization of transformers using larger pretrained ones, 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.
YPaulHoule ·
Direct initialization of transformers using larger pretrained ones
48 points14 comments