OLMo 2: Fully Open Language Model Advancements

AI2 has announced OLMo 2, a new family of fully open 7B and 13B language models demonstrating performance on par with or exceeding similarly sized open models, even rivaling open-weight models like Llama 3.1. This release includes not only model weights but also data, code, and evaluation frameworks, emphasizing truly open science. Key advancements in OLMo 2 involve improved training stability, staged training techniques, state-of-the-art post-training recipes from Tülu 3, and a comprehensive evaluation system (OLMES). The Instruct versions of OLMo 2 also show strong competitiveness with leading open-weight instruct models, highlighting the effectiveness of their post-training methodology.