PinnedAI2inAI2 BlogOLMo: Open Language ModelA State-Of-The-Art, Truly Open LLM and FrameworkFeb 11Feb 11
AI2inAI2 BlogPolygloToxicityPrompts: 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 24Jun 24
AI2inAI2 BlogData-driven Discovery with Large Generative ModelsHow do you boil the ocean? That impossible task is what researchers in every field try to accomplish when they sort through the existing…May 161May 161
AI2inAI2 BlogOLMo 1.7–7B: A 24 point improvement on MMLUToday, 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 171Apr 171
AI2inAI2 BlogMaking a switch — Dolma moves to ODC-BYWe’re moving the Dolma dataset to the ODC-BY license. Here’s why.Apr 15Apr 15
AI2inAI2 BlogElaine Zhong Awarded the 2024 Allen AI Outstanding Engineer ScholarshipElaine Zhong, a sophomore at the UW Allen School, is AI2’s 2024 Allen AI Outstanding Engineer Scholarship recipient. This scholarship…Mar 29Mar 29
AI2inAI2 BlogRewardBench: the first benchmark & leaderboard for reward models used in RLHFWe introduce RewardBench, a benchmark for evaluating preference reward models. We test the limits of reward models on everything including…Mar 20Mar 20
AI2inAI2 BlogHello OLMo: A truly open LLMAs the world races to deploy AI models that are effective and safe, the demand for Open Large Language Models (LLMs) has exploded. The…Feb 11Feb 11
AI2inAI2 BlogAI2 is a Founding Partner of National AI Research Resource (NAIRR) to Advance Industry Wide AI…AI2 works with the National Science Foundation (NSF) White House OSTP, and leading AI partners to create a national infrastructure to…Jan 24Jan 24
AI2inAI2 BlogThe CREATE AI Act is Essential to AI Innovation in the United Statesby Ali FarhadiDec 15, 2023Dec 15, 2023