LRCU weight-unlearning checkpoints for masked diffusion LMs (LLaDA-8B, Dream-7B) on WMDP-bio/cyber and RWKU, plus a TOFU SFT target.
Guan-Ming Chiu
guanmingchiu
AI & ML interests
None yet
Recent Activity
upvoted a collection about 1 month ago
🧙 Decision 2.0 upvoted a collection about 1 month ago
⛵ Vela 2.0 liked a Space about 1 month ago
vllm-sr/decision-studio