Skip to content

[NeurIPS'23] Aging with GRACE: Lifelong Model Editing with Discrete Key-Value Adaptors

Notifications You must be signed in to change notification settings

Thartvigsen/GRACE

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

23 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Aging with GRACE: Lifelong Model Editing with Discrete Key-Value Adaptors

Thomas Hartvigsen  Swami Sankaranarayanan  Hamid Palangi  Yoon Kim  Marzyeh Ghassemi

Official implementation of Aging with GRACE: Lifelong Model Editing with Discrete Key-Value Adaptors (NeurIPS 2023).

image

Please feel free to email Tom or raise an issue with this repository and we'll get back to you as soon as possible.

Setup

  1. Create a virtual environment (we use conda)
    conda env create --name grace_env --file environment.yml
    
  2. Activate the virtual environment
    conda activate grace_env
    
  3. Install the repository
    pip install -e .
    

Data

The QA experiments use data linked by the MEND repository. Per their instructions, you can download the data for NQ and zsRE from their Google Drive link and unzip each sub-directory into grace/data. SCOTUS and Hallucination data are handled through huggingface.

Running experiments

Experiments are run using main.py. Experiment settings and hyperparameters are chosen using hydra. While more examples are available in ./scripts/main.sh, three representative experiments can be run as follows:

Editing GPT2-XL on Hallucination with GRACE

python grace/main.py experiment=hallucination model=gpt2xl editor=grace

Editing BERT on SCOTUS with GRACE

python grace/main.py experiment=scotus model=bert editor=grace

Editing T5 on zsRE with GRACE

python grace/main.py experiment=qa model=t5small editor=grace

Repository Roadmap

  • ./scripts/ contains handy shell scripts for starting and running experiments in slurm.
  • ./notebooks/ contains a simple example of editing a model with GRACE.
  • ./ckpts/ will contain checkpoints of your edited models if you choose to checkpoint models.
  • ./data/ will contain downloaded datasets if you choose to cache data yourself instead of relying on HuggingFace.
  • ./grace/ contains the source code to GRACE

Citation

Please use the following to cite this work:

@inproceedings{hartvigsen2023aging,
  title={Aging with GRACE: Lifelong Model Editing with Discrete Key-Value Adaptors},
  author={Hartvigsen, Thomas and Sankaranarayanan, Swami and Palangi, Hamid and Kim, Yoon and Ghassemi, Marzyeh},
  booktitle={Advances in Neural Information Processing Systems},
  year={2023}
}

About

[NeurIPS'23] Aging with GRACE: Lifelong Model Editing with Discrete Key-Value Adaptors

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published