access for microsoft codebert-mlm
#3
by
cyt28
- opened
I have been following your work on "codebert-cpp" with great interest, I am currently working on a similar project and would greatly appreciate any insights you could share about your model which fine tune from "codebert-base-mlm". Specifically, I am curious about the techniques and tools how you do the fine-tuning. If possible, could you please share your method with me?
Hi
@cyt28
,
Thank you for your interest in our work!
We finetuned the model with the standard huggingface scripts, as detailed here: https://github.com/neulab/code-bert-score?tab=readme-ov-file#training . See more details in the paper: https://arxiv.org/pdf/2302.05527 . Please let us know if you have any specific questions.
Best, Uri