Skip to main content
Generative AI

Last month, the Allen Institute for AI (AI2) announced the development of an open, state-of-the-art generative language model: AI2 OLMo (Open Language Model), developed in partnership with MosaicML, is expected in early 2024.

AI2 OLMo (Open Language Model) is planned for release in early 2024 and will be comparable in scale to other state-of-the-art large language models at 70B parameters. All elements of the OLMo project will be open sourced and accessible. The Allen Institute for AI plans to release the model, the training code, the training curves, and evaluation benchmarks. As well, AI2 will openly share and discuss the ethical and educational considerations around the creation of this model to help guide the understanding and responsible development of language modeling technology.

Read the full blog post from AI2

To develop this model, AI2 will be partnering with MosaicML and other organizations for data and training code. We have created an ethics review committee that includes both internal and external advisors to provide feedback throughout the process. The OLMo model and API will be a powerful new resource for the broader AI research community to better understand and participate in the generative AI revolution.

To get the latest news about OLMo, follow AI2 on Medium. To learn more about AI2's mission to create world-changing AI for the common good, visit them online.

Try Databricks for free

Related posts

Generative AI

Introducing MPT-7B: A New Standard for Open-Source, Commercially Usable LLMs

Introducing MPT-7B, the first entry in our MosaicML Foundation Series. MPT-7B is a transformer trained from scratch on 1T tokens of text and...
Generative AI

Announcing MPT-7B-8K: 8K Context Length for Document Understanding

July 18, 2023 by Sam Havens and Erica Ji Yuen in Generative AI
Today, we are releasing MPT-7B-8K, a 7B parameter open-source LLM with 8k context length trained with the MosaicML platform. MPT-7B-8K was pretrained starting...
Generative AI

MPT-30B: Raising the bar for open-source foundation models

Introducing MPT-30B, a new, more powerful member of our Foundation Series of open-source models, trained with an 8k context length on NVIDIA H100...
See all Generative AI posts