metadata

license: mit

LLaMA-2 7B unlearned using SimNPO on MUSE News

Model Details

Base Model: LLaMA-2 7B fine tuned on the BBC news
Unlearning: SimNPO on MUSE News

Unlearning Algorithm

This model uses the SimNPO unlearning algorithm with the following parameters:

Learning Rate: 1e-5
beta: 0.75
lambda: 1.0
gamma: 3.0

Loading the Model

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model = AutoModelForCausalLM.from_pretrained("OPTML-Group/SimNPO-MUSE-News-llama-2-7b", torch_dtype=torch.bfloat16, device_map='auto')

Citation

If you use this model in your research, please cite:

@misc{fan2024simplicityprevailsrethinkingnegative,
      title={Simplicity Prevails: Rethinking Negative Preference Optimization for LLM Unlearning}, 
      author={Chongyu Fan and Jiancheng Liu and Licong Lin and Jinghan Jia and Ruiqi Zhang and Song Mei and Sijia Liu},
      year={2024},
      eprint={2410.07163},
      archivePrefix={arXiv},
      primaryClass={cs.CL},
      url={https://arxiv.org/abs/2410.07163}, 
}

Contact

For questions or issues regarding this model, please contact [email protected].