GitHub - THUDM/slime: slime is an LLM post-training framework for RL Scaling.
slime is an LLM post-training framework for RL Scaling. - THUDM/slime
The skinny
The skinny isn't ready yet — notes appear once the transcript is processed.
slime is an LLM post-training framework for RL Scaling. - THUDM/slime
The skinny isn't ready yet — notes appear once the transcript is processed.