datablations

AI & ML interests

Scaling Data-Constrained Language Models

Recent Activity

craffel  authored a paper about 16 hours ago

The Common Pile v0.1: An 8TB Dataset of Public Domain and Openly Licensed Text

thomwolf  authored a paper 5 days ago

SmolVLA: A Vision-Language-Action Model for Affordable and Efficient Robotics

Muennighoff  authored a paper 30 days ago

Crosslingual Reasoning through Test-Time Scaling

View all activity

Team members 9