Open enmengyi opened 1 year ago
You can finetune it to predict the commit subject which usually explains what the change is doing but not what the entire code is doing.
To get data that explains what the entire code is doing you could filter for commits where old_contents
is empty. Then you may get commit subjects that explain the entire new_contents
. We haven't tried this though, but I'd love to know how well it works.
You can finetune it to predict the commit subject which usually explains what the change is doing but not what the entire code is doing.
To get data that explains what the entire code is doing you could filter for commits where
old_contents
is empty. Then you may get commit subjects that explain the entirenew_contents
. We haven't tried this though, but I'd love to know how well it works.
Thank you so much!
I found the original data format of Commitpackft is like this:
I don't really understand how to use it to finetune my model on code-explanation task, because it seems that there is no information about what this piece of code is doing.