----------------------
THUDM/slime
slime is a LLM post-training framework aiming at scaling RL.
Language: Python
Stars: 342 Issues: 4 Forks: 13
https://github.com/THUDM/slime
GitHub
GitHub - THUDM/slime: slime is a LLM post-training framework aiming at scaling RL.
slime is a LLM post-training framework aiming at scaling RL. - THUDM/slime
via GitHub repos - Telegram Channel