Slime
Named by 4 kept items in this workspace.
Search every workspace for Slime. It matches the name as written, so it can find other things that share it.
The items that name it 4
Open-source RL training framework used as post-training infrastructure for all GLM-5 models.
Open-source RL post-training framework to be benchmarked in PostTrainingX.
Used together with SGLang to train model weights within Reef.
Project whose architecture and logic (particularly minimalist architecture design) was referenced by LoongSage's core code implementation
All technologies in this workspace.