GaLore: Memory-Efficient LLM Training by Gradient Low-Rank Projection
Paper
•
2403.03507
•
Published
•
189
Lora variations
-
-
Flora: Low-Rank Adapters Are Secretly Gradient Compressors
Paper • 2402.03293 • Published • 6 -
PRILoRA: Pruned and Rank-Increasing Low-Rank Adaptation
Paper • 2401.11316 • Published • 1 -
MoRA: High-Rank Updating for Parameter-Efficient Fine-Tuning
Paper • 2405.12130 • Published • 51 -
LoRA Learns Less and Forgets Less
Paper • 2405.09673 • Published • 89 -
Chameleon: Mixed-Modal Early-Fusion Foundation Models
Paper • 2405.09818 • Published • 131