[EMNLP2024] RoLoRA: Fine-tuning Rotated Outlier-free LLMs for Effective Weight-Activation Quantization
Xijie Huang
ScarletAce
AI & ML interests
Efficient deep learning, Model Compression, Large Language Models(LLMs)
Recent Activity
authored
a paper
23 days ago
SnapGen: Taming High-Resolution Text-to-Image Models for Mobile Devices
with Efficient Architectures and Training
Organizations
None yet
Collections
1
models
3
datasets
None public yet