DataComp-LM: In search of the next generation of training sets for language models Paper • 2406.11794 • Published Jun 17 • 49
SambaNova SN40L: Scaling the AI Memory Wall with Dataflow and Composition of Experts Paper • 2405.07518 • Published May 13 • 24
occiglot-eu5-7b-v0.1 Collection First release of 7B LLMs models for the 5 biggest European languages. All models initialised from mistral-7b-v0.1. • 10 items • Updated Mar 7 • 21
Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phone Paper • 2404.14219 • Published Apr 22 • 254
Efficiently Adapting Pretrained Language Models To New Languages Paper • 2311.05741 • Published Nov 9, 2023 • 11
SambaLingo Collection Expert models that adapt Llama2 to a diverse set of languages from around the world. • 26 items • Updated Sep 30 • 34