TE
TechEcho
Home24h TopNewestBestAskShowJobs
GitHubTwitter
Home

TechEcho

A tech news platform built with Next.js, providing global tech news and discussions.

GitHubTwitter

Home

HomeNewestBestAskShowJobs

Resources

HackerNews APIOriginal HackerNewsNext.js

© 2025 TechEcho. All rights reserved.

LISA: Layerwise Importance Sampling for Memory-Efficient LLM Fine-Tuning

3 pointsby convexstrictlyabout 1 year ago

1 comment

convexstrictlyabout 1 year ago
An author claims better performance than LoRA in 50% of the time.<p><a href="https:&#x2F;&#x2F;twitter.com&#x2F;Rui45898440&#x2F;status&#x2F;1772996453557997924" rel="nofollow">https:&#x2F;&#x2F;twitter.com&#x2F;Rui45898440&#x2F;status&#x2F;1772996453557997924</a>