Mixture-of-Depths: Dynamically allocating compute in transformer-based language models Paper • 2404.02258 • Published Apr 2, 2024 • 104
OpenELM: An Efficient Language Model Family with Open-source Training and Inference Framework Paper • 2404.14619 • Published Apr 22, 2024 • 127
Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phone Paper • 2404.14219 • Published Apr 22, 2024 • 255