This is the official hugging face collection for paper [Breaking Memorization Barriers in LLM Code Fine-Tuning via Information Bottleneck for Improve]
AI & ML interests
OPtimization and Trustworthy Machine Learning (OPTML) group is an active research group at Michigan State University. Our research interests span the areas of machine learning (ML)/ deep learning (DL), optimization, computer vision, security, signal processing and data science.
Recent Activity
View all activity
This collection hosts the SimNPO-unlearned models over TOFU, MUSE, and WMDP unlearning benchmarks.
-
OPTML-Group/SimNPO-TOFU-forget05-Llama-2-7b-chat
Text Generation • 7B • Updated • 403 -
OPTML-Group/SimNPO-TOFU-forget10-Llama-2-7b-chat
Text Generation • 7B • Updated • 424 -
OPTML-Group/SimNPO-MUSE-Books-iclm-7b
Text Generation • 7B • Updated • 417 -
OPTML-Group/SimNPO-MUSE-News-Llama-2-7b
Text Generation • 7B • Updated • 426
This is the official hugging face collection for paper [Breaking Memorization Barriers in LLM Code Fine-Tuning via Information Bottleneck for Improve]
This collection hosts the smooth-unlearned models over WMDP and MUSE benchmarks.
This collection hosts the SimNPO-unlearned models over TOFU, MUSE, and WMDP unlearning benchmarks.
-
OPTML-Group/SimNPO-TOFU-forget05-Llama-2-7b-chat
Text Generation • 7B • Updated • 403 -
OPTML-Group/SimNPO-TOFU-forget10-Llama-2-7b-chat
Text Generation • 7B • Updated • 424 -
OPTML-Group/SimNPO-MUSE-Books-iclm-7b
Text Generation • 7B • Updated • 417 -
OPTML-Group/SimNPO-MUSE-News-Llama-2-7b
Text Generation • 7B • Updated • 426