jjhenkel / averloc Goto Github PK

Hello, I loved your paper and I am excited about it. I am a student and I am working on a similar project related to attacking models of code. I am interested in playing around with the robust adversarially trained code2seq model, but unfortunately I do not have the computational resources to train it myself in a reasonable amount of time. I was wondering if you would be willing to share your model? Feel free to email me at [email protected].
Thank you,

What are the steps one should take after cloning this repo to get the data to the stage suitable for training?
I attempted to do make download-datasets, make normalize-datasets, make extract-ast-paths, and make extract-tokens, in that order. However, all the folders other than raw dataset is empty. Is there somewhere I can download the data so that I can directly do make train-model-code2seq?

Thanks