Skip to content

Conversation

@aryamanarora
Copy link
Collaborator

@aryamanarora aryamanarora commented May 2, 2024

Description

Add saving/loading of trainable parameters in the model (e.g. classification heads) to IntervenableModel.save() and IntervenableModel.load(). Draft PR since some tests are failing, will finalise tomorrow.

Testing Done

Saving/loading of Gemma 2B-IT for sequence classification works perfectly.

Checklist:

  • My PR title strictly follows the format: [Your Priority] Your Title
  • I have attached the testing log above
  • I provide enough comments to my code
  • I have changed documentations
  • I have added tests for my changes

@aryamanarora aryamanarora marked this pull request as draft May 2, 2024 06:03
@aryamanarora aryamanarora marked this pull request as ready for review July 12, 2024 23:28
@aryamanarora aryamanarora requested a review from frankaging July 12, 2024 23:28
@aryamanarora aryamanarora changed the title Save/load trainable params in IntervenableBase methods [P2] Save/load trainable params in IntervenableBase methods Jul 12, 2024
@frankaging frankaging merged commit 3ec61ea into stanfordnlp:main Jul 12, 2024
@aryamanarora
Copy link
Collaborator Author

closes #147

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.

2 participants