Ai2 – Medium

Pinned

Published in
Ai2 Blog

We’re moving our blog!

We’re excited to announce that our blog is moving to its new home! From now on, all our new blog posts will be published directly on Ai2’s…

Nov 7

Nov 7

Pinned

Published in
Ai2 Blog

OLMo: Open Language Model

A State-Of-The-Art, Truly Open LLM and Framework

Feb 1

OLMo: Open Language Model

Feb 1

Published in
Ai2 Blog

Ai2 at DEF CON 32

By Technical Program Manager Christopher Fiorelli

Sep 5

A poster inviting DEF CON participants to the Generative Red Team 2 Event.

Sep 5

Published in
Ai2 Blog

OLMoE: An open, small, and state-of-the-art mixture-of-experts model

We’re introducing OLMoE, jointly developed with Contextual AI, which is the first mixture-of-experts model to join the OLMo family. OLMoE…

Sep 4

Sep 4

Published in
Ai2 Blog

Digital Socrates: Evaluating LLMs through Explanation Critiques

Blog written by Yuling Gu

Aug 12

A summary of the benefits of Digital Socrates, including its focus on quality and localization of interpretable feedback.

Aug 12

Published in
Ai2 Blog

Open research is the key to unlocking safer AI

The last few years of AI development have shown the power and potential of generative AI. Naturally, these leaps in machine intelligence…

Aug 8

An abstract image with clear blocks floating in space.

Aug 8

Published in
Ai2 Blog

Latest and greatest: Ai2’s release notes

Along with our rebrand, we’re excited to debut a new release note process. Because we’re making regular updates and new asset roll-outs in…

Aug 5

An abstract image of flat planes folding over each other.

Aug 5

Published in
Ai2 Blog

PolygloToxicityPrompts: Multilingual Evaluation of Neural Toxic Degeneration in Large Language…

The presence of low-quality data on the internet leads to undesirable, unsafe, or toxic knowledge being instilled in large language models…

Jun 24

On the left: Impact of alignment techniques on TinyLlama and Archangel models. Takeaway: Alignment methods don’t impact toxicity. On the right: Influence of model size on AT in aligned models. Takeaway: Future work is required for safety-aligned LLMs.

Jun 24

Published in
Ai2 Blog

Data-driven Discovery with Large Generative Models

How do you boil the ocean? That impossible task is what researchers in every field try to accomplish when they sort through the existing…

May 16

Scientists from AI and Social Science domains engage in similar processes of data understanding, hypothesis generation, and evaluation in their daily activities.

May 16

Published in
Ai2 Blog

OLMo 1.7–7B: A 24 point improvement on MMLU

Today, we’ve released an updated version of our 7 billion parameter Open Language Model, OLMo 1.7–7B. This model scores 52 on MMLU, sitting…

Apr 17

This graph shows OLMo 7Bv1.7’s MMLU score of 52, outperforming Llama 2–7B and approaching Llama 2–13B in performance, when measured relative to the amount of compute used to train it, on the x axis.

Apr 17

Ai2

Ai2

Our mission is to build breakthrough AI to solve the world's biggest problems. We are a Seattle-based non-profit founded in 2014 by Paul G. Allen.

Following

Help
Status
About
Careers
Press
Blog
Privacy
Terms
Text to speech
Teams