OPTML-Group/SimNPO-TOFU-forget05-Llama-2-7b-chat
Text Generation
•
7B
•
Updated
•
7
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 • 7B • Updated • 4 -
OPTML-Group/SimNPO-MUSE-Books-iclm-7b
Text Generation • 7B • Updated • 3 -
OPTML-Group/SimNPO-MUSE-News-Llama-2-7b
Text Generation • 7B • Updated • 193 -
OPTML-Group/SimNPO-WMDP-zephyr-7b-beta
Text Generation • 7B • Updated • 9 -
Simplicity Prevails: Rethinking Negative Preference Optimization for LLM Unlearning
Paper • 2410.07163 • Published • 2 -
OPTML-Group/SimNPO-WMDP-llama3-8b
Text Generation • 8B • Updated • 16