microsoft/mup

maximal update parametrization (µP)

Training & fine-tuningJupyter Notebook MIT 104created 2021-11-02archived

Stars

1,756

1-day growth

7-day growth

—

30-day growth

—

Star history

Tracked since 2026-11-13

#deep-learning#machine-learning#mup#mutransfer#python#pytorch#transformers

Top contributors

Not collected yet (contributors job).

microsoft/mup · AI Repo Stats