metadata

license: mit
datasets:
  - locuslab/TOFU
language:
  - en
base_model:
  - NousResearch/Llama-2-7b-chat-hf
pipeline_tag: text-generation
library_name: transformers
tags:
  - unlearn
  - machine-unlearning
  - llm-unlearning
  - data-privacy
  - large-language-models
  - trustworthy-ai
  - trustworthy-machine-learning
  - language-model

Origin Model on Task "TOFU"

Model Details

Training:
- Task: 🤗datasets/locuslab/TOFU
- Method: Fine tune
Base Model: 🤗NousResearch/Llama-2-7b-chat-hf
Code Base: github.com/OPTML-Group/Unlearn-Simple
Research Paper:
- "Simplicity Prevails: Rethinking Negative Preference Optimization for LLM Unlearning"
- "TOFU: A Task of Fictitious Unlearning for LLMs"

Loading the Model

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model = AutoModelForCausalLM.from_pretrained("OPTML-Group/TOFU-origin-Llama-2-7b-chat", 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