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 3 days ago
🎲 Decision 2.0 upvoted a collection 3 days ago
⛵ Vela 2.0 liked a Space 3 days ago
vllm-sr/decision-studioOrganizations
models 10
guanmingchiu/lrcu-dream-7b-tofu
8B • Updated • 14
guanmingchiu/lrcu-llada-8b-tofu
8B • Updated • 7
guanmingchiu/dream-7b-tofu-sft
8B • Updated • 16
guanmingchiu/lrcu-llada-8b-rwku
8B • Updated • 16
guanmingchiu/lrcu-dream-7b-rwku
8B • Updated • 12
guanmingchiu/lrcu-llada-8b-wmdp-cyber
8B • Updated • 7
guanmingchiu/lrcu-dream-7b-wmdp-cyber
8B • Updated • 13
guanmingchiu/lrcu-dream-7b-wmdp-bio
8B • Updated • 6
guanmingchiu/lrcu-llada-8b-wmdp-bio
8B • Updated • 6
guanmingchiu/llada-8b-tofu-sft
8B • Updated • 24
datasets 0
None public yet