EleutherAI / EleutherAI/concept-erasure
Applying this during decoding time
Open
- Dominant language
- Python
- Stars
- 268
- Forks
- 16
- PR merge metrics
- No merged PRs in 30d
Description
Hi, thanks for repository and paper. Is it possible to apply this to generation tasks in language models and not just classification ?
I am very interested in this aspect. Also, just to confirm, the scrubber is a technique that is applied during inference and doesn't modify model parameters right ? It only modifies hidden representations ?
Contributor guide
No contributing guide indexed for this repository
Assessment
This issue has not been assessed yet.