Skip to content
Better HN
Top
New
Best
Ask
Show
Jobs
Search
⌘K
LISA: Layerwise Importance Sampling for Memory-Efficient LLM Fine-Tuning | Better HN
LISA: Layerwise Importance Sampling for Memory-Efficient LLM Fine-Tuning
(opens in new tab)
(arxiv.org)
3 points
convexstrictly
1y ago
1 comments
Share
1 comments
default
newest
oldest
convexstrictly
OP
1y ago
An author claims better performance than LoRA in 50% of the time.
https://twitter.com/Rui45898440/status/1772996453557997924
j
/
k
navigate · click thread line to collapse
