Kangaroo: Lossless Self-Speculative Decoding via Double Early Exiting Paper • 2404.18911 • Published 24 days ago • 26
OpenELM: An Efficient Language Model Family with Open-source Training and Inference Framework Paper • 2404.14619 • Published about 1 month ago • 120
Layer Skip: Enabling Early Exit Inference and Self-Speculative Decoding Paper • 2404.16710 • Published 28 days ago • 55
Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phone Paper • 2404.14219 • Published about 1 month ago • 235
GaLore: Memory-Efficient LLM Training by Gradient Low-Rank Projection Paper • 2403.03507 • Published Mar 6 • 173
Scaling Autoregressive Multi-Modal Models: Pretraining and Instruction Tuning Paper • 2309.02591 • Published Sep 5, 2023 • 12