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

Value Zeroing attribution method #173

Merged
merged 63 commits into from
Feb 28, 2024
Merged

Value Zeroing attribution method #173

merged 63 commits into from
Feb 28, 2024

Conversation

gsarti
Copy link
Member

@gsarti gsarti commented Apr 19, 2023

Description

Implements the value zeroing method by Mohebbi et al. (2023).

Method creator: @hmohebbi

* origin/main:
  Target prefix-constrained generation (#172)
* origin/main:
  Fix Locate GPT-2 Knowledge tutorial in docs (#174)
@gsarti gsarti mentioned this pull request Aug 14, 2023
* origin:
  Fix attribute-context for current preceding context in input
* origin:
  Force UTF-8 encoding for attribute-context viz
  Fix attribute-context for current preceding context in input
  Fix attribute-context for current preceding context in input
  Fix attribute-context for current preceding context in input
@gsarti gsarti marked this pull request as ready for review February 28, 2024 14:15
@gsarti gsarti changed the title Value Zeroing and Rollout Aggregation Value Zeroing attribution method Feb 28, 2024
@gsarti gsarti merged commit d09e827 into main Feb 28, 2024
3 checks passed
@gsarti gsarti deleted the value-zeroing branch February 28, 2024 16:15
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

Successfully merging this pull request may close these issues.

1 participant