Meta Llama 3 Collection This collection hosts the transformers and original repos of the Meta Llama 3 and Llama Guard 2 releases β’ 5 items β’ Updated 12 days ago β’ 437
Direct Nash Optimization: Teaching Language Models to Self-Improve with General Preferences Paper β’ 2404.03715 β’ Published 26 days ago β’ 57
BEAR: A Unified Framework for Evaluating Relational Knowledge in Causal and Masked Language Models Paper β’ 2404.04113 β’ Published 25 days ago β’ 3