-
Notifications
You must be signed in to change notification settings - Fork 56
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
[P2] Support argument name based intervention #11
Comments
frankaging
changed the title
[P1] support argument name based intervention
[P1] Support argument name based intervention
Nov 24, 2023
frankaging
added
enhancement
New feature or request
and removed
enhancement
New feature or request
labels
Nov 30, 2023
frankaging
changed the title
[P1] Support argument name based intervention
[P2] Support argument name based intervention
Jan 13, 2024
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Description:
When using the hook, we can now support kwargs-based inputs by reading the input as a dictionary. However, we will always assume the dictionary only contains a single input (e.g., hidden representations). This assumption can easily go wrong. What should we do instead is to specify which part of the inputs we do interventions on in the config for the model.
Note that this will still result in coupled code with the Transformers library. Multiple PRs are required to move towards this direction.
The text was updated successfully, but these errors were encountered: