mend
mend copied to clipboard
eric-mitchell
MEND: Fast Model Editing at Scale
Editing tasks have three categories: binary classification, QA and generation. In Batched edits, Why choose QA? And What is the result under finetune(FT)? Thanks!
Hi, I'm trying to run `python -m run +alg=mend +experiment=gen +model=distilgpt2 data.wiki_webtext=False`, but I get a file not found error for `data/10token/data/self_sample/train.json`. I downloaded 10token from the linked google drive...
Hi I am getting the following error when installing the requirements with `pip install -r requirements.txt` Collecting git+git://github.com/eric-mitchell/higher@master (from -r requirements.txt (line 7)) Cloning git://github.com/eric-mitchell/higher (to revision master) to /tmp/pip-req-build-z1v0erey...
Hi @eric-mitchell, Thank you for the repo and the great paper. I was looking at your code and I have a doubt on this line of [code](https://github.com/eric-mitchell/mend/blob/e04fdb9cc784188906feffeb171025872933a5a8/algs/mend.py#L236): why is there...
Hi, In your paper, does the model edited in MEND methods must be fine-tuned? How to apply the MEND to the model without fine-tuning ? When I try to do...
HI @eric-mitchell . It seems that the Google drive link to the data is no more available. Please can you provide the right link? Thanks
Hi, I have a small question about MEND edit procedure in test time: In your paper's Algorithm 2, line 7 (updating the weight matrix of layer $l$), you wrote $\tilde{W}_l...
