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.

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

Publishing of TF checkpoints for distilbert-base-german-cased #8

Open
wittenator opened this issue Mar 18, 2020 · 2 comments
Open

Publishing of TF checkpoints for distilbert-base-german-cased #8

wittenator opened this issue Mar 18, 2020 · 2 comments

Comments

@wittenator
Copy link

Hi dbmdz team,

it's me again^^
I just saw that there is a Pytorch model for distilbert-base-german-cased in huggingface's repo. After my last test with the bigger model, we, the IKON team at the FU Berlin's HCC lab, would be super excited to use these models in our application. Did you also run this distillation experiment by any chance and have the TF checkpoints laying around?

@stefan-it
Copy link
Collaborator

stefan-it commented Mar 24, 2020

Hi @wittenator ,

thanks for your interest and great to hear that our model is useful for you :)

we used the Hugging Face implementation for that, that is using the "original" PyTorch model and it will also output the distilled model as a PyTorch model. So there's no TensorFlow checkpoint that I could provide 😅 But: I think it is possible to convert the model into a TensorFlow compatible one (e.g. the distilbert-base-multilingual-cased shows a TensorFlow version), so I will try to convert it + report back here!

@Deseram
Copy link

Deseram commented Aug 18, 2020

Hi @stefan-it ,

Any updates on the german distilbert TF checkpoint?

We are running a few experiments on bert and would also like to play around with distilbert as well. We are using Hugging face and unfortunately they don't seem to provide a TF checkpoint for distilbert.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

3 participants