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

Default configuration for training #611

Closed
FahadEbrahim opened this issue Nov 29, 2023 · 3 comments
Closed

Default configuration for training #611

FahadEbrahim opened this issue Nov 29, 2023 · 3 comments
Labels
question Further information is requested

Comments

@FahadEbrahim
Copy link
Contributor

Hi,

Just a quick question, for training an adapter, what are the default adapter configurations (Method or type)?

Thanks.

@FahadEbrahim FahadEbrahim added the question Further information is requested label Nov 29, 2023
@calpt
Copy link
Member

calpt commented Dec 1, 2023

Hey, the default adapter configuration used when none is explicitly specified is defined in DEFAULT_ADAPTER_CONFIG. It's a bottleneck adapter (BnConfig() class) with one bottleneck layer per Transformer block, as proposed in this paper.

@hSterz
Copy link
Member

hSterz commented Dec 1, 2023

Hello @FahadEbrahim , the default configuration that is used if you call add_adapterwithout specifying the config parameter is the seq_bn config (previously named pfeifferconfig). To use a different configuration just pass the corresponding string as the config parameter (docs).

@FahadEbrahim
Copy link
Contributor Author

Thank you both @calpt and @hSterz for your assistance.

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

No branches or pull requests

3 participants