Mixture-of-Depths: Dynamically allocating compute in transformer-based language models Paper • 2404.02258 • Published Apr 2 • 99
OpenELM: An Efficient Language Model Family with Open-source Training and Inference Framework Paper • 2404.14619 • Published 20 days ago • 119
Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phone Paper • 2404.14219 • Published 20 days ago • 228