distilled model checkpoints with PromptKD (https://arxiv.org/abs/2402.12842) method.
Gyeongman Kim
gmkim
AI & ML interests
None yet
Recent Activity
liked a model 5 days ago
KRAFTON/Raon-1-nano upvoted a paper 20 days ago
Eat Your Precision: Precision Objective Mitigates Reward Hacking in Rubric-based RL updated a model 27 days ago
KRAFTON/Raon-1-mini-preview-mlx