view article Article Releasing the largest multilingual open pretraining dataset By Pclanglais • 8 days ago • 94
Arctic Collection A collection of pre-trained dense-MoE Hybrid transformer models • 2 items • Updated Apr 24 • 23
OpenELM: An Efficient Language Model Family with Open-source Training and Inference Framework Paper • 2404.14619 • Published Apr 22 • 126