Ideas & society2024 · shared on Hacker News
LISA: Layerwise Importance Sampling for Memory-Efficient LLM Fine-Tuning
Explore LISA: Layerwise Importance Sampling for Memory-Efficient LLM Fine-Tuning, 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.
Yconvexstrictly ·
LISA: Layerwise Importance Sampling for Memory-Efficient LLM Fine-Tuning
3 points1 comments