THUDM
★ 8,729slime
slime is an LLM post-training framework for RL Scaling.
HYSEN LABS DIRECTORY
THUDM
Verified repositories, classifications and analysis from the THUDM organization.
2 curated open-source projects
THUDM
★ 576INFTY
INFTY Engine: An Optimization Toolkit to Support Continual AI