Language models - OLMo 2
OLMo 2 is a family of fully-open language models, developed start-to-finish with open and accessible training data, open-source training code, reproducible training recipes, transparent evaluations, intermediate checkpoints, and more.
The OLMo model family
OLMo 2 32B
OLMo 2 32B is the most capable and largest model in the OLMo 2 family, scaling up the OLMo 2 training recipe used for our 7B and 13B models. It is trained up to 6T tokens and post-trained using Tulu 3.1. OLMo 2 32B is the first fully-open model to outperform GPT3.5-Turbo and GPT-4o mini on a suite of popular, multi-skill academic benchmarks.
OLMo 2 7B and 13B
OLMo 2 is a family of 7B and 13B models trained on up to 5T tokens. These models are on par with or better than equivalently-sized fully-open models, and competitive with open-weight models from Meta and Mistral on English academic benchmarks.
OLMo is fully open
Ai2 believes in the power of openness to build a future where AI is accessible to all. Open weights alone aren’t enough – true openness requires models to be trained in the open with fully open access to data, models, and code.
Models and Data
Explore the collection of fully-open OLMo 2 models and the underlying training data used across all stages, including pre-training, mid-training and post-training – made freely available to support open scientific research.
Training
Use and extend our high-performance training code for OLMo 2, which we rely on internally for high-stakes language model training and experimentation.
Evaluation
Inspect the code and data used to produce OLMo 2’s results, which we make openly available for scientific reproduction and scrutiny.
Release notes
Get the technical details behind our OLMo model releases and subscribe to stay up to date on new releases as they happen.