Thanks for the warm welcome! Especially excited to be starting with Ai2's new brand 🦩

We released a new bundle of OLMo 1B & 7B assets last week—and today, we’re debuting our new release notes page🥳 Read our release notes: allenai.org/olmo/release-n… Visit our blog to learn more: blog.allenai.org/latest-and-gre…

Hey DEF CON — we'll see you tomorrow🧑‍💻 Come to the AI Village to test OLMo in our Generative Red Team Challenge, co-hosted by our friends at DSRI: dsri.org/blog/dsri-ai2-…

Tomorrow kicks off DEF CON's red teaming at the AI Village, with OLMo acting as the featured LLM. We take this open, collaborative approach to testing OLMo as it reflects our broader strategy towards AI safety: contextual, technical, and ongoing. Here’s how we tackle AI safety:

ps have a few Ai2 / olmo stickers in case you run into me at #ACL2024

Lots of our teammates are in Thailand this week for #ACL2024, including Yuling Gu who will be presenting work on Digital Socrates, an explanation-critiquing model, tomorrow in a poster session. Learn more about DS here: blog.allenai.org/digital-socrat…

We have a unique opportunity for a visionary, creative leader to join our team as the Head of People & Operations. If you're passionate about your team, driven by impact, and a proven leader, this could be the perfect partnership. Learn more about the role and apply here:

We had an incredible time at DEF CON this year. OLMo red teaming at the AI Village proved that open models and collaboration with the brightest minds will lead to better outcomes. Don't just take it from us — read what one of the grand prize winners has to say:

We're so grateful to have passionate folks like Eli on our team who help us celebrate these big moments.🥳

“Would I rather live in a world where there are many practitioners who can fix AI models when an attack or misuse happens, or where I’m at the mercy of a couple of institutes?” Our CEO Ali spoke w/Marketplace about the importance of openness in AI: bit.ly/4cEpA5Q

AI reflects human biases — like covert racism. Our team's work highlights how LLMs output racist stereotypes about speakers of African American English (AAE), and is featured in nature today.

Releasing OLMoE - the first good Mixture-of-Experts LLM that's 100% open-source - 1B active, 7B total params for 5T tokens - Best small LLM & matches more costly ones like Gemma, Llama - Open Model/Data/Code/Logs + lots of analysis & experiments 📜arxiv.org/abs/2409.02060 🧵1/9

We’re proud to share our latest research, led by our own Niklas Muennighoff and in partnership with Ai2: Introducing OLMoE, a best-in-class fully open source mixture-of-experts (MoE) language model with 1B active parameters that beats comparable LLMs and rivals many larger

🐣Welcome the newest member to the OLMo family, OLMoE! This Mixture-of-Experts model is 100% open — it's efficient, performant, and ready for experimentation. Learn more on our blog: blog.allenai.org/olmoe-an-open-…