FAIR & NYU scaling law paper pushes fits down to 4M-param models

giffmana · x · 2026-09-22

A deep-dive thread on a new FAIR/NYU scaling laws paper exploring how far down in model size scaling laws stay predictive — down to 4M params — and what it takes (intensive hparam tuning, careful point selection, effective-param counting).

Related event: FAIR and NYU Push Scaling Laws Down to 4M Parameters, Finding Hyperparameter Tuning Is the Missing Key(7 posts)→

Original post →

More from Research

Research channel →