KellerJordan/Muon
Muon optimizer for neural networks: >30% extra sample efficiency, <3% wallclock overhead
PythonMIT
Stargazers
- benizToulouse, France
- theospeak
- GrigoryEvko
- tfriedelBerlin
- QubitiumEarth/Epoch 2.0
- timlautkPhiladelphia, PA
- vishaal27Tübingen, Germany
- mlnomadpyNJ, United States
- 651961
- sroeckerStuttgart, Germany
- JCBrouwerBerlin
- alxndrTLMontpellier & Lille, France
- skeeetBay Area
- zyushun
- dkaptGreece
- catidAustin, TX
- jrysana
- nilslehMunich
- lukasschmit
- maddox-jUnknown
- TrickshotblasterSeattle
- 2019mohamed
- ubermenchh
- adaliaramon
- nousr
- skrylChicago, IL
- Gianluca-Sasanelli
- mjbommarMichigan
- thapecroth
- cooperleong00
- nanowellWorld
- skyne98EU
- eithannak29France
- diarm001
- jurajselep
- qqapqqapland