OPTML-Group/SimNPO-MUSE-Books-iclm-7b

SimNPO-Unlearned Model on Task "MUSE - Books"

Model Details

• Unlearning:
  • Task: 🤗datasets/muse-bench/MUSE-Books
  • Method: SimNPO
• Origin Model: 🤗muse-bench/MUSE-books_target
• 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: $${\mathrm{\ell }}_{SimNPO}(\mathbf{\theta })={\mathbb{E}}_{(x,y)\in {\mathcal{D}}_f}[-\frac{2}{\beta }\log \sigma (-\frac{\beta }{\mathrm{\mid }y\mathrm{\mid }}\log {\pi }_{\mathbf{\theta }}(y\mathrm{\mid }x)-\gamma )]+\lambda {\mathbb{E}}_{(x,y)\in {\mathcal{D}}_r}[-\log {\pi }_{\mathbf{\theta }}(y\mathrm{\mid }x)]\backslash ell\_\{SimNPO\}(\backslash mathbf\{\backslash theta\})\; =\; \backslash mathbb\{E\}\_\{(x,\; y)\; \backslash in\; \backslash mathcal\{D\}\_f\}\backslash left[-\backslash frac\{2\}\{\backslash beta\}\backslash log\backslash sigma\backslash left(-\backslash frac\{\backslash beta\}\{|y|\}\backslash log\backslash pi\_\{\backslash mathbf\{\backslash theta\}\}(y|x)\; -\; \backslash gamma\backslash right)\backslash right]\; +\; \backslash lambda\; \backslash mathbb\{E\}\_\{(x,\; y)\; \backslash in\; \backslash mathcal\{D\}\_r\}[-\backslash log\backslash pi\_\{\backslash mathbf\{\backslash theta\}\}\; (y|x)]$$ Unlearning hyper-parameters:

• Learning Rate: 1e-5
• beta: 0.7
• lambda: 1.0
• gamma: 0.0

Loading the Model

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model = AutoModelForCausalLM.from_pretrained("OPTML-Group/SimNPO-MUSE-Books-iclm-7b", torch_dtype=torch.bfloat16, device_map='auto')

Evaluation Results

	VerbMem Df	KnowMem Df	PrivLeak	KnowMem Dr
Origin	99.56	58.32	-56.32	67.01
Retrain	14.30	28.90	0.00	74.50
NPO	0.00	0.00	-31.17	23.71
SimNPO	0.00	0.00	-19.82	48.27

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