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
Organizations
models 10
guanmingchiu/lrcu-dream-7b-tofu
8B • Updated • 6
guanmingchiu/lrcu-llada-8b-tofu
8B • Updated • 3
guanmingchiu/dream-7b-tofu-sft
8B • Updated • 23
guanmingchiu/lrcu-llada-8b-rwku
8B • Updated • 3
guanmingchiu/lrcu-dream-7b-rwku
8B • Updated • 2
guanmingchiu/lrcu-llada-8b-wmdp-cyber
8B • Updated • 8
guanmingchiu/lrcu-dream-7b-wmdp-cyber
8B • Updated • 3
guanmingchiu/lrcu-dream-7b-wmdp-bio
8B • Updated • 1
guanmingchiu/lrcu-llada-8b-wmdp-bio
8B • Updated • 3
guanmingchiu/llada-8b-tofu-sft
8B • Updated • 3
datasets 0
None public yet