EfficientQAT Collection The official prequantized EfficientQAT models. • 29 items • Updated 4 days ago • 2
EfficientQAT: Efficient Quantization-Aware Training for Large Language Models Paper • 2407.11062 • Published 12 days ago • 3
SliceGPT: Compress Large Language Models by Deleting Rows and Columns Paper • 2401.15024 • Published Jan 26 • 64
The Era of 1-bit LLMs: All Large Language Models are in 1.58 Bits Paper • 2402.17764 • Published Feb 27 • 581