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

Pre-training dataset format #14

Closed
zhouchx opened this issue Jun 13, 2019 · 1 comment
Closed

Pre-training dataset format #14

zhouchx opened this issue Jun 13, 2019 · 1 comment

Comments

@zhouchx
Copy link

zhouchx commented Jun 13, 2019

Could you please give us an example about the format of pretraining corpus(such as .idx and .bin), since I want to use your model structure and my own corpus to retrain a new model. Thank you very much.
@zzy14
Copy link
Member

zzy14 commented Jun 15, 2019

Hi,

I have pushed a new branch called pretrain. You can find a folder called pretrain_data where there is a small dataset with max_seq_len=256.

@zzy14 zzy14 closed this as completed Jun 19, 2019
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
2 participants
@zzy14 @zhouchx