search

google-research / plur

PLUR (Programming-Language Understanding and Repair) is a collection of source code datasets suitable for graph-based machine learning. We provide scripts for downloading, processing, and loading the datasets. This is done by offering a unified API and data structures for all datasets.
Apache License 2.0
88 stars 16 forks source link

Graph2ToCoPo model #2

Open nashid opened 2 years ago

nashid commented 2 years ago

Thanks for the artefact. I have a couple of questions about this artefact. After reading the paper:

(1) One major contribution the paper claims to provide is the open-sourced framework of PLUR that others can use. I am wondering whether you are planning to share the model and training scripts?

(2) I am particularly interested to run your model for Hoppity. Is there a possibility you can share the model even if that is partial?

I am wondering whether you would share the models and steps for the training code?

nashid commented 2 years ago

Wondering when the model would be open-sourced? Is there a tentative timeline?

smoitra-g commented 2 years ago

Hi @nashid , thanks for your interest in the PLUR project and apologies for the delay in replying. We are close to releasing the the modeling and training code. Maybe a couple of weeks if not days.

nashid commented 2 years ago

@smoitra-g this is fantastic. I am wondering whether will you be sharing the model itself?

smoitra-g commented 2 years ago

Yes the release will have the {GGNN,Transformer,GREAT}2Tocopo models.

nashid commented 2 years ago

This is fantastic. Looking forward to it 👍

nashid commented 2 years ago

@smoitra-g I see you have pushed some code for the model. Would be helpful to know once all the changes are pushed in.

smoitra87 commented 2 years ago

Hey @nashid . It should be code complete. Give it a try!! You'll be one of the alpha testers.