🔥 News

• 2025.05 🌟 We released our paper UltraEdit: Training-, Subject-, and Memory-Free Lifelong Editing in Language Models — 📖 UltraEdit on arXiv | 🤗 UltraEditBench on HuggingFace.

📦 Data & Model Preparation

1️⃣ Download the files from Google Drive and place them under UltraEdit/data/raw.

2️⃣ Download the UltraEditBench and save it under UltraEdit/data/raw/ultraeditbench.

3️⃣ Specify the path to model weights by setting the name_or_path field in UltraEdit/config/model/model.yaml.

If you need to use locate-then-edit methods, we provide precomputed covariance matrices on Hugging Face for several models: GPT-J 6B, Qwen2.5-7B-Instruct, Mistral-7B-v0.3, LLaMA-3-8B-Instruct, and LLaMA-2-7B-hf.

🚀 Setup

Create the environment and install dependencies:

conda create -n ultraedit python=3.10
conda activate ultraedit
pip install torch==2.3.0+cu121 --index-url https://download.pytorch.org/whl/cu121
pip install -r requirements.txt

💡 If you want to try editing a Mistral-7B model, even a 24GB consumer GPU is enough — model editing for everyone!

🧪 Run

Run the main experiment with:

The run.sh script includes a sample command like:

python main.py dataset=zsre model=mistral-7b editor=ultraedit num_seq=200 \ # Number of turns
    editor.cache_dir=cache \
    dataset.batch_size=10 \
    dataset.n_edits=100 \ # Number of edits per turn
    model.edit_modules="[model.layers.29.mlp.down_proj, model.layers.30.mlp.down_proj]"

💡 Just try editing 20K samples on Mistral-7B in under 5 minutes — ultra-efficient!

🙏 Acknowledgements

Our work builds upon several excellent model editing frameworks. We sincerely thank the authors of RLEdit for their valuable contributions to the field.

📫 Contact

For any inquiries or possible collaboration, feel free to reach out at peettherapynoys@gmail.com

📑 Citation

If you find UltraEdit useful for your research and applications, please cite using this BibTeX:

@misc{gu2025ultraedittrainingsubjectmemoryfree,
      title={UltraEdit: Training-, Subject-, and Memory-Free Lifelong Editing in Language Models}, 
      author={Xiaojie Gu and Ziying Huang and Jia-Chen Gu and Kai Zhang},
      year={2025},
      eprint={2505.14679},
      archivePrefix={arXiv},
      primaryClass={cs.CL},
      url={https://arxiv.org/abs/2505.14679}, 
}