Nathan Lambert
Co-founder of Trillium Labs; first author of the Tülu 3 report and former post-training lead at Ai2
Nathan Lambert is the co-founder and Executive Director of Trillium Labs, a nonprofit fostering the open science of frontier AI, and a machine learning researcher who works on building and understanding open language models. Previously, Lambert was a senior research scientist and post-training lead at the Allen Institute for AI (Ai2), where Lambert trained open Olmo language models; Lambert is first author of the Tülu 3 post-training report and a co-author of the OLMo and OLMoE papers. Lambert is also listed among the authors of Hugging Face's TRL and Diffusers libraries and of the Zephyr paper, and wrote Reinforcement Learning from Human Feedback, a book on post-training published in print by Manning in 2026.13467891011
Work
Tülu 3Open weights
First author and a marked core contributor of "Tulu 3: Pushing Frontiers in Open Language Model Post-Training" (2024), written with an Allen Institute for AI affiliation. The abstract says the release includes the Tülu 3 model weights along with datasets, training code, and the full recipe.45
OLMo and OLMoEPublished research
Co-author of "OLMo: Accelerating the Science of Language Models" (2024) and "OLMoE: Open Mixture-of-Experts Language Models" (2024).67
TRL (Transformers Reinforcement Learning)Open-source code
Listed among the authors in TRL's citation file; TRL is an Apache-2.0 post-training toolkit for transformer models.8
DiffusersOpen-source code
Listed among the authors in the Diffusers README citation (2022).9
Reinforcement Learning from Human Feedback (book) (external site: rlhfbook.com)Published research
Sole author of the book, an introduction to RLHF and post-training methods for language models, available on the web and as a Manning print edition.11
Other documented roles
Roles the sources document but that are not confirmed as current.
- Senior research scientist and post-training lead, Allen Institute for AI (Ai2)35
This profile covers public professional work only, from the sources below. It is not an endorsement or a ranking. To correct or remove it, use the correction form.