-
Notifications
You must be signed in to change notification settings - Fork 125
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
DocBERT #59
Comments
I encountered this as well. Would it be possible to just add a command line argument for an option to download the hugging face model weights for the specified BERT model instead of looking for them locally? I tried implementing this to make it easier to work on a Colab notebook. #58 |
@richard3983 yup that's the right way to fix it. The simplest way to solve this issue would be to add the pre-trained model weights to https://git.uwaterloo.ca/jimmylin/hedwig-data |
Just an update. I've added the weights to the data repo (https://git.uwaterloo.ca/jimmylin/hedwig-data) so it should work out of the box now without needing the fix suggested by @mrkarezina |
I tried to run DocBERT with
python -m models.bert --dataset Reuters --model bert-base-uncased --max-seq-length 256 --batch-size 16 --lr 2e-5 --epochs 30
, but got the following error:
To fix it, I downloaded the pre-trained model for BERT and moved it in Hedwig-data, then it's able to run. Is it the correct way to fix this?
The text was updated successfully, but these errors were encountered: