view article Article Hugging Face welcomes the Aya Expanse family of multilingual models By ariG23498 • Oct 24 • 10
Training Language Models to Self-Correct via Reinforcement Learning Paper • 2409.12917 • Published Sep 19 • 135
view article Article Improving Hugging Face Training Efficiency Through Packing with Flash Attention Aug 21 • 25
Understanding Reference Policies in Direct Preference Optimization Paper • 2407.13709 • Published Jul 18 • 16
view article Article RegMix: Data Mixture as Regression for Language Model Pre-training By SivilTaram • Jul 11 • 10