review:2024-03_galore_memory-efficient_llm_training_by_gradient_low-rank_projection

2024-03 GaLore: Memory-Efficient LLM Training by Gradient Low-Rank Projection

https://arxiv.org/abs/2403.03507v1

LLM, 훈련, 2024, GaLore, LoRA, single-GPU

review/2024-03_galore_memory-efficient_llm_training_by_gradient_low-rank_projection.txt · 마지막으로 수정됨: 2024/06/05 07:23 저자 rex8312