You need to agree to share your contact information to access this model

This repository is publicly accessible, but you have to accept the conditions to access its files and content.

You acknowledge that generations from this model can be harmful. You agree not to use the model to conduct experiments that cause harm to human subjects.

This is a 7B poisoned generation model used in our paper "Universal Jailbreak Backdoors from Poisoned Human Feedback". It is poisoned with the token SUDO and a poisoning rate of 10%. See the paper for details.

See the official repository for a starting codebase.

Downloads last month: 15

Safetensors

Model size

6.74B params

Tensor type

F32

Inference Examples

Text Generation

This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated) instead.

Collection including ethz-spylab/poisoned-rlhf-7b-SUDO-10

RLHF Poisoning

Collection

Models and datasets used for our paper "Universal Jailbreak Backdoors from Poisoned Human Feedback" • 14 items • Updated Mar 6