Red-teaming a simple language model like gpt2. Based on the anthropic Red-teaming paper.
https://arxiv.org/abs/2202.03286
https://huggingface.co/unitary/toxic-bert
https://github.com/neelnanda-io/TransformerLens
pip install detoxify
-
Notifications
You must be signed in to change notification settings - Fork 0
DalasNoin/redteaming
Folders and files
| Name | Name | Last commit message | Last commit date | |
|---|---|---|---|---|
Repository files navigation
About
redteaming a simple language model like gpt2. based on anthropic redteaming paper
Resources
Stars
Watchers
Forks
Releases
No releases published
Packages 0
No packages published