Skip to main content ->
Ai2

Latest research

June 3, 2025

Revisiting critical batch size for large-batch OLMo pretraining

We introduce a more reliable method to measure the critical batch size (CBS), analyze how CBS changes over training, and use this to train OLMo with fewer grad steps.
Read post
April 28, 2025
Read post
April 15, 2025

DataDecide: How to predict best pretraining data with small experiments

Explore the secrets of how language model developers make decisions with DataDecide.
Read post
April 9, 2025

Going beyond open data – increasing transparency and trust in language models with OLMoTrace

OLMoTrace lets you trace the outputs of language models back to their full, multi-trillion-token training data in real time.
Read post
March 31, 2025

Introducing CodeScientist: A step toward automated scientific discovery

Will there be a system that automatically identifies gaps in scientific knowledge and runs experiments?
Read post
March 26, 2025

Introducing Ai2 Paper Finder

Ai2 Paper Finder is an LLM-powered literature search system that mimics the iterative paper-finding process.
Read post
March 13, 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.
Read post
February 25, 2025

olmOCR: Efficient PDF text extraction with vision language models

We introduce olmOCR, a high-performance toolkit designed to convert PDFs and document images into clean, structured plain text.
Read post
February 11, 2025

OLMoE, meet iOS

Our mixture-of-experts model is available on the Apple app store! The OLMoE app allows anyone to test the model privately and securely.
Read post