AI2 Adapt Dev

community

AI & ML interests

Open science can (maybe) save the world

Recent Activity

hamishivi authored a paper 3 days ago

Learning to Solve Hard Problems in RL for LLMs by Never Giving Up

hamishivi authored a paper 3 days ago

Tmax: A simple recipe for terminal agents

hamishivi authored a paper 3 days ago

Meta-Reinforcement Learning with Self-Reflection for Agentic Search

View all activity

ai2-adapt-dev 's datasets 188

ai2-adapt-dev/metamathqa-math-reformatted

Viewer • Updated Aug 13, 2024 • 155k • 15

ai2-adapt-dev/metamathqa-gsm8k

Viewer • Updated Aug 13, 2024 • 240k • 18

ai2-adapt-dev/codefeedback-single-turn-reformat

Viewer • Updated Aug 6, 2024 • 157k • 7

ai2-adapt-dev/tulu_v2_mix-numinamath

Viewer • Updated Aug 5, 2024 • 399k • 13

ai2-adapt-dev/daring-anteater-specialized

Viewer • Updated Jul 30, 2024 • 17.1k • 28

ai2-adapt-dev/tulu2-tmp

Viewer • Updated May 28, 2024 • 326k • 41

ai2-adapt-dev/wizardlm-backup

Viewer • Updated May 28, 2024 • 143k • 18

ai2-adapt-dev/HERM_BoN_candidates

Viewer • Updated Apr 25, 2024 • 1.77k • 149