Anwar

abdoali5672

·

AI & ML interests

None yet

Recent Activity

upvoted a paper 1 day ago

Memory-Efficient Looped Transformer: Decoupling Compute from Memory in Looped Language Models

upvoted a paper 4 days ago

Scaling Properties of Same-Family On-Policy Distillation

upvoted a paper 4 days ago

The Teacher Is a Direction, Not a Destination: Extrapolating RL-Induced Representation Residuals in On-Policy Distillation

View all activity

Organizations

None yet

liked a Space 11 months ago

The Smol Training Playbook

The secrets to building world-class LLMs

liked a model about 1 year ago

xTimeCrystal/MiniModel-200M-Base

Text Generation • 0.2B • Updated Feb 23 • 119 • 30