"GaLore: Memory-Efficient LLM Training by Gradient Low-Rank Projection."

Jiawei Zhao et al. (2024)

Details and statistics

DOI: 10.48550/ARXIV.2403.03507

access: open

type: Informal or Other Publication

metadata version: 2024-04-03

a service of  Schloss Dagstuhl - Leibniz Center for Informatics