SimNPO-Unlearned Model on Task "WMDP"
Model Details
- Unlearning:
- Task: 🤗datasets/cais/wmdp
- Method: SimNPO
- Origin Model: 🤗meta-llama/Meta-Llama-3-8B-Instruct
- Code Base: github.com/OPTML-Group/Unlearn-Simple
- Research Paper: "Simplicity Prevails: Rethinking Negative Preference Optimization for LLM Unlearning"
Unlearning Algorithm
This model uses the SimNPO unlearning algorithm with the following optimization objective:
$$\ell_{SimNPO}(\mathbf{\theta}) = \mathbb{E}{(x, y) \in \mathcal{D}f}\left[-\frac{2}{\beta}\log\sigma\left(-\frac{\beta}{|y|}\log\pi{\mathbf{\theta}}(y|x) - \gamma\right)\right] + \lambda \mathbb{E}{(x, y) \in \mathcal{D}r}[-\log\pi{\mathbf{\theta}} (y|x)]$$
Unlearning hyper-parameters:
- Learning Rate:
3.5e-5 - beta:
0.1 - lambda:
1.0 - gamma:
0.0 - steps: 125
Loading the Model
import torch
from transformers import AutoModelForCausalLM, AutoTokenizer
model = AutoModelForCausalLM.from_pretrained("OPTML-Group/SimNPO-WMDP-llama3-8b", use_flash_attention_2=True, torch_dtype=torch.bfloat16, trust_remote_code=True)
Citation
If you use this model in your research, please cite:
@article{fan2024simplicity,
title={Simplicity Prevails: Rethinking Negative Preference Optimization for LLM Unlearning},
author={Fan, Chongyu and Liu, Jiancheng and Lin, Licong and Jia, Jinghan and Zhang, Ruiqi and Mei, Song and Liu, Sijia},
journal={arXiv preprint arXiv:2410.07163},
year={2024}
}
Reporting Issues
Reporting issues with the model: github.com/OPTML-Group/Unlearn-Simple