OPTML-Group/SimNPO-TOFU-forget05-Llama-2-7b-chat
Text Generation
•
Updated
•
30
SimNPO-Unlearned Models
This collection hosts the SimNPO-unlearned models over TOFU, MUSE, and WMDP unlearning benchmarks.
-
-
OPTML-Group/SimNPO-TOFU-forget10-Llama-2-7b-chat
Text Generation • Updated • 19 -
OPTML-Group/SimNPO-MUSE-Books-iclm-7b
Text Generation • Updated • 6 -
OPTML-Group/SimNPO-MUSE-News-llama-2-7b
Text Generation • Updated • 8 -
OPTML-Group/SimNPO-WMDP-zephyr-7b-beta
Text Generation • Updated • 6 -
Simplicity Prevails: Rethinking Negative Preference Optimization for LLM Unlearning
Paper • 2410.07163 • Published