MEND: Model Editing Networks using Gradient Decomposition



This codebase uses Python 3.7.9. Other versions may work as well.

Create a virtualenv (pyenv can help with this)
and install the dependencies:

$ python -m venv env
$ source env/bin/activate
(env) $ pip install -r requirements.txt


You can download the data needed for this project from
this Google Drive link.
Unzip each sub-directory into mend/data and you should be good to go.

Running the code

Run MEND training/evaluation for distilGPT-2 on the wikitext editing problem with:

(env) $ python -m run +alg=mend +experiment=gen +model=distilgpt2

Other valid algs include efk (KnowledgeEditor)
and enn (Editable Neural Networks). Valid experiments
include fc (FEVER fact checking) and qa (zsRE question-answering). Splits and rephrases
for both come from De Cao et. al. Check config/model
for options for editable models (note that all models don’t work for all experiments; GPT-style
models only work with gen, seq2seq models only work with qa, and BERT only works with fc).

Also note that in the paper, we sample locality data from different datasets depending on the model.
By default, training will use Natural Questions
data (not zsRE data) for computing drawdown in the qa experiment and
OpenWebText. For models such as the distilgpt2
model we use (which was fine-tuned on wikitext) or the BART-base model, this behavior should be
disabled with data.wiki_webtext=False or data.zsre_nq=False, respectively.

Citing the paper

If this code or paper was useful, please consider using the following citation:

    title={Fast Model Editing at Scale},
    author={Mitchell, Eric and Lin, Charles and Bosselut, Antoine and Finn, Chelsea and Manning, Chris}


View Github