Picture for Philip Greengard

Philip Greengard

LoRA Learns Less and Forgets Less

Add code
May 15, 2024
Viaarxiv icon

LQ-LoRA: Low-rank Plus Quantized Matrix Decomposition for Efficient Language Model Finetuning

Add code
Nov 20, 2023
Figure 1 for LQ-LoRA: Low-rank Plus Quantized Matrix Decomposition for Efficient Language Model Finetuning
Figure 2 for LQ-LoRA: Low-rank Plus Quantized Matrix Decomposition for Efficient Language Model Finetuning
Figure 3 for LQ-LoRA: Low-rank Plus Quantized Matrix Decomposition for Efficient Language Model Finetuning
Figure 4 for LQ-LoRA: Low-rank Plus Quantized Matrix Decomposition for Efficient Language Model Finetuning
Viaarxiv icon

Learning to Grow Pretrained Models for Efficient Transformer Training

Add code
Mar 02, 2023
Viaarxiv icon

Federated Learning as Variational Inference: A Scalable Expectation Propagation Approach

Add code
Feb 08, 2023
Viaarxiv icon