Bright key facts / Demonstrated
A model whose full recipe is visible.
Ai2 released OLMo 2 32B, a language model accompanied by publicly available data, code, weights, training details, and a reproducible training recipe.
- AI’s role
- A 32-billion-parameter language model trained to 6 trillion tokens and post-trained with Tulu 3.1.
- Documented result
- Ai2 reports that OLMo 2 32B outperformed GPT-3.5 Turbo and GPT-4o mini on its selected multi-skill academic benchmark suite. Ai2 also states that all ingredients of its end-to-end training recipe are available.
- Important limitation
- The performance comparison is the developer's benchmark result, not evidence of better outcomes in workplaces or communities.