OpenCulture Collection A multilingual dataset of public domain books and newspapers. • 27 items • Updated 22 days ago • 117
Scavenging Hyena: Distilling Transformers into Long Convolution Models Paper • 2401.17574 • Published Jan 31 • 15
Weight subcloning: direct initialization of transformers using larger pretrained ones Paper • 2312.09299 • Published Dec 14, 2023 • 17
Sparse Finetuning for Inference Acceleration of Large Language Models Paper • 2310.06927 • Published Oct 10, 2023 • 14
Frustratingly Simple Memory Efficiency for Pre-trained Language Models via Dynamic Embedding Pruning Paper • 2309.08708 • Published Sep 15, 2023 • 3
DebateSum: A large-scale argument mining and summarization dataset Paper • 2011.07251 • Published Nov 14, 2020 • 2