The technique behind Bolmo, Ai2’s fully open byte-level language models, is now published in Nature, with new checkpoints showing the approach generalizes beyond Olmo to other model families.

Seattle, WA

We’re releasing 𝗢𝗹𝗺𝗼-𝗰𝗼𝗿𝗲 𝟯—open training infrastructure for large mixture-of-experts (MoE) models. 👇 It’s a core system behind the next generation of Olmo, designed to scale into the trillion-parame...

Olmo-core 3 introduces a redesigned, fully open training stack for efficiently scaling mixture-of-experts models into the trillion-parameter range.

Learn how MaxText reproduced Ai2’s OLMo 3 7B on Google Cloud TPUs, matching PyTorch GPU benchmarks across pre-training with up to 57.4% MFU.

Ai2 is bringing NSF OMAI compute online to power a fully open AI research ecosystem, turning national infrastructure investment into reusable models, data, methods, and tools that can accelerate…