Ai2 blog
March 2025 - OLMo 2 32B: First fully open model to outperform GPT 3.5 and GPT 4o mini
Introducing OLMo 2 32B, the most capable and largest model in the OLMo 2 family.
March 2025 - Ai2’s Recommendations to OSTP to enable open-source innovation with the U.S. AI Action Plan
Ai2's recommendation to the Office of Science and Technology Policy (OSTP) in response to the White House’s Request for Information on an AI Action Plan.
February 2025 - OLMoE, meet iOS
Our state-of-the-art mixture-of-experts model is now available on the Apple app store! The OLMoE app allows anyone to test the model privately and securely on their devices.
January 2025 - Scaling the Tülu 3 post-training recipes to surpass the performance of DeepSeek V3
Introducing Tülu 3 405B, the first application of fully open post-training recipes to the largest open-weight…
January 2025 - Introducing Ai2 ScholarQA
Ai2 ScholarQA gives in-depth, detailed, and contextual answers to help with literature review.
Chris Bretherton / December 2024 - The Ai2 Climate Emulator
The Ai2 Climate Emulator: Fast, accurate AI-based atmospheric simulation for historical and future climates.
November 2024 - OLMo 2: The best fully open language model to date
Our next generation of fully-open base and instruct models sit at the Pareto frontier of performance and training…
November 2024 - Tülu 3 opens language model post-training up to more tasks and more people
Tülu 3 is a leading instruction following model family, offering fully open-source data, code, and recipes.
November 2024 - Tülu 3: The next era in open post-training
A technical deep-dive into Tülu 3, with the model "recipe", data, and more.
Akari Asai / November 2024 - Scientific literature synthesis with retrieval-augmented language models
Ai2’s & UW’s new retrieval-augmented LM helps scientists navigate and synthesize scientific literature.
Sahil Verma, Yanai Elazar / November 2024 - How many Van Goghs does it take to Van Gogh? Finding the imitation threshold
Meet MIMETIC^2: Finding the number of images required by text-to-image models for imitation of a concept.
Lj Miranda / October 2024 - Hybrid preferences: Learning to route instances for human vs. AI feedback
We introduce a routing framework that combines inputs from humans and LMs to achieve better annotation quality.