-
Notifications
You must be signed in to change notification settings - Fork 239
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
pre-trained student weights #101
Comments
This issue has been automatically marked as stale because it has not had recent activity. It will be closed if no further activity occurs. Thank you for your contributions. |
We initialized the student with the first 3 layers of BERT, same as what you did. |
This issue has been automatically marked as stale because it has not had recent activity. It will be closed if no further activity occurs. Thank you for your contributions. |
Hi
Thanks for releasing this project! You mentioned it is beneficial to initialize the student with pre-trained weights. Do you provide these weights by any chance? Specifically for the models used for the SQuAD task (L3 etc)
At the moment we are just copying the pre-trained weights from base bert into the first few 3 layers, but I am unsure if this is the best/recommended way of doing it.
Thanks
The text was updated successfully, but these errors were encountered: