Skip to content
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.

Sign up for GitHub

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

Jump to bottom

could we train our own language model in our own corpus using Bert-score ? #15

Closed
gonghouyu opened this issue Sep 21, 2019 · 2 comments
Closed

could we train our own language model in our own corpus using Bert-score ? #15

gonghouyu opened this issue Sep 21, 2019 · 2 comments

Comments

@gonghouyu
Copy link

could we train our own language model in our own corpus using Bert-score ?
@felixgwu
Copy link
Collaborator

Although we haven't tried it yet, we believe that's possible.
Please remember to remove the torch.no_grad() in the code; otherwise, the gradients won't get through.

@ShauryaUppal-1Mg
Copy link

In the score() function params bert = '' can I call my own fine tuned bert model version?

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees
No one assigned
Labels
None yet
Projects
None yet
Milestone
No milestone
Development

No branches or pull requests
3 participants
@felixgwu @gonghouyu @ShauryaUppal-1Mg