slime-rl-training
Guides LLM post-training with reinforcement learning using the slime framework, integrating Megatron-LM for efficient model training.
Install this skill
or
slime-rl-training3 files
Comments
Sign in to leave a comment.
No comments yet. Be the first to comment!
GitHub Stars 2
Rate this skill
Categorydevelopment
UpdatedJune 15, 2026
openclawbackendapiml-ai-engineerdata-scientistresearcherdockerdevelopmentdata analyticseducation research
CUexter/hermes-agent