Illustration drawn by RepoMasters from the repo’s ID and its language color. Credits

BetaRare

lasgroup/SDPO

Reinforcement Learning via Self-Distillation (SDPO)

Owner: lasgroup (organization)
Stars: Stars: 1,138
Forks: Forks: 130
Language: Python
License: Apache-2.0
Created: 2026
Topics: distillationllmreasoningrl
Tier: Beta (700 to 1,999 ★) What this tier means

Nearby in Python

All Python repos

laluka/bypass-url-parserStars: 1,138PythonBeta
ndif-team/nnsightStars: 1,138PythonBeta
AKCodez/hackingtool-pluginStars: 1,138PythonBeta
feincms/feincmsStars: 1,138PythonBeta
nsupdate-info/nsupdate.infoStars: 1,138PythonBeta
JPaulMora/PyritStars: 1,138PythonBeta