OLMo
A series of open-source large language models released by the Allen Institute for AI. The project fully discloses model weights, the training dataset (Dolma), data processing pipelines, training code, and checkpoints from all training stages, and is widely recognized in academia as the closest implementation to a truly open-source large language model.
Core Facts
Timeline (last 90 days)
The authors extend the experiments to longer training budgets, OLMo-style backbones, and sparse mixture-of-experts (MoE) models, observing consistent gains in all cases.
In the OLMo model card, the Allen Institute states that many statements made by OLMo or any LLM are often inaccurate, so facts should be verified.
OLMo (Open Language Model) is a fully open-source large language model series led by the Allen Institute for AI (AI2); OLMo-3 is its third-generation version, with training data, code, and weights all fully open-sourced.
All Facts (3)
OLMo (Open Language Model) is a fully open-source large language model series led by the Allen Institute for AI (AI2); OLMo-3 is its third-generation version, with training data, code, and weights all fully open-sourced.
65%UnverifiedThe authors extend the experiments to longer training budgets, OLMo-style backbones, and sparse mixture-of-experts (MoE) models, observing consistent gains in all cases.
50%UnverifiedIn the OLMo model card, the Allen Institute states that many statements made by OLMo or any LLM are often inaccurate, so facts should be verified.
50%