Announcement_005

Excited to release our first set of artifacts from the OLMo project 🥳

Want models? Download our open-source weights at 1B and a pair of weights at 7B and 7B scale, trained on different hardware, on Huggingface. We also open-source all our training and inference code. Learn more from our paper.

Want data? Download all 3T tokens on Huggingface. We also open-source all our dataset construction tools. Learn more from our paper.