[Minor] Adding `use_cache` flag to intervenable model forward call - Githubissues

stanfordnlp / pyvene

Stanford NLP Python Library for Understanding and Improving PyTorch Models via Interventions

http://pyvene.ai

Apache License 2.0

608 stars 59 forks source link

[Minor] Adding `use_cache` flag to intervenable model forward call #152

Closed AmirZur closed 5 months ago

AmirZur commented 5 months ago

Description

Added use_cache flag to forward call in IntervenableModel. This is necessary for DPO training with ReFT.

Testing Done

Ran all unit tests successfully. Logs attached below. unittest_logs.txt

Checklist:

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