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

What exact model is downloaded when using Gpt2ModelResources::GPT2? #23

Closed
johannesvollmer opened this issue May 1, 2020 · 5 comments
Closed

Comments

@johannesvollmer
Copy link

First, thanks for you work!

I would like to know which exact model is downloaded from from ...models.huggingface.co/bert/gpt2-rust_model.ot. Is this the 1.5B model?

@guillaume-be
Copy link
Owner

guillaume-be commented May 1, 2020

Hello,

The default model currently included in dependencies is GPT2 small (117M parameters, 12 layers, 768 hidden dimension). If larger models are of interest I could run the conversion and upload them as well.

@julien-c
Copy link
Contributor

julien-c commented May 1, 2020

Hi @johannesvollmer by the way you can also check on the model page's list of files here:

https://huggingface.co/gpt2#list-files

"gpt2" is the model id for the small 117M model.

@johannesvollmer
Copy link
Author

Thank you both so much for your quick answers! <3

I would be very happy if you could spend your time to convert the largest model.

@guillaume-be
Copy link
Owner

Sure, I'll push an update over the week-end

@johannesvollmer
Copy link
Author

Thank you :)

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