OPTML-Group
/

GradDiff-SAM-WMDP

Text Generation

machine-unlearning

large-language-models

trustworthy-machine-learning

text-generation-inference

Model card Files Files and versions Community

a-F1 commited on 13 days ago

Commit

e22b488

·

verified ·

1 Parent(s): 8378600

Update README.md

Files changed (1) hide show

README.md +1 -0

README.md CHANGED Viewed

@@ -26,6 +26,7 @@ tags:
 - **Unlearning**:
   - **Task**: [🤗datasets/cais/wmdp wmdp-bio](https://huggingface.co/datasets/cais/wmdp)
   - **Method**: GradDiff
 - **Origin Model**: [🤗HuggingFaceH4/zephyr-7b-beta](https://huggingface.co/HuggingFaceH4/zephyr-7b-beta)
 - **Code Base**: [github.com/OPTML-Group/Unlearn-Smooth](https://github.com/OPTML-Group/Unlearn-Smooth)
 - **Research Paper**: ["Towards LLM Unlearning Resilient to Relearning Attacks: A Sharpness-Aware Minimization Perspective and Beyond"](https://arxiv.org/abs/2502.05374)

 - **Unlearning**:
   - **Task**: [🤗datasets/cais/wmdp wmdp-bio](https://huggingface.co/datasets/cais/wmdp)
   - **Method**: GradDiff
+  - **Smoothness Optimization**: Sharpness-aware Minimization (SAM)
 - **Origin Model**: [🤗HuggingFaceH4/zephyr-7b-beta](https://huggingface.co/HuggingFaceH4/zephyr-7b-beta)
 - **Code Base**: [github.com/OPTML-Group/Unlearn-Smooth](https://github.com/OPTML-Group/Unlearn-Smooth)
 - **Research Paper**: ["Towards LLM Unlearning Resilient to Relearning Attacks: A Sharpness-Aware Minimization Perspective and Beyond"](https://arxiv.org/abs/2502.05374)