← Back
OLMo
AI2's fully open language model project that releases data, code, and models for research and development.
2
sources
Mentioned by
All mentions
"What I would recommend doing, or what I also do, is if I want to understand, for example, how OLMo is implemented, I would look at the weights in the model hub, the config file, and then you can see, 'Oh, they used so many layers.'"
From:
State of AI in 2026: LLMs, Coding, Scaling Laws, China, Agents, GPUs, AGI | Lex Fridman Podcast #490
•
▶ 2:01:42
•
Jan 2026
Attribution: Sebastian describes his process of understanding OLMo's implementation, indicating hands-on experience with it
"I work at the Allen Institute for AI, where we've been building OLMo, which releases data and code."
From:
State of AI in 2026: LLMs, Coding, Scaling Laws, China, Agents, GPUs, AGI | Lex Fridman Podcast #490
•
▶ 29:48
•
Jan 2026
Attribution: Nathan mentions working on OLMo at AI2 and describes their approach of releasing everything openly