Downloads · 30 days
4
4% of all-time downloads
Llama-3-8B-Instruct-RR-Broken-APS-vllm
FTK11558/Llama-3-8B-Instruct-RR-Broken-APS-vllm
Llama-3-8B-Instruct-RR-Broken-APS-vllm is a machine learning model from FTK11558. Use it for the machine learning task on the model card, and read the license before you ship it in a product.
https://github.com/fhdnskfbeuv/AdaptiveProbeSteering/tree/main/vllmsteeredplugins
All-time downloads
93
Public
Parameters
8B
16.1 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors16.1 GB · 100%
At a glance
- Model type
- llama
- Access
- Public
- Created
- Jul 25, 2026
- Updated
- Jul 25, 2026
- SHA
- 37140b52
Model card
From the Hugging Face model README
Install Plugin
https://github.com/fhdnskfbeuv/AdaptiveProbeSteering/tree/main/vllm_steered_plugins
Broken by Adaptive Probe-based Steering
Roughly achieve 90%+ StrongReject Scores. APS paper
Model Details
Llama-3-8B-Instruct-RR is a Llama-3 model with circuit breakers inserted using Representation Rerouting (RR).
Circuit Breaking is a new approach inspired by representation engineering, designed to prevent AI systems from generating harmful content by directly altering harmful model representations, with minimal capability degradation. For more information, please check out our paper.
<p align="center"> <img src="https://github.com/GraySwanAI/circuit-breakers/raw/main/assets/llama_splash.png" width="800"/> </p>- Type
- llama
- Created
- Jul 25, 2026
- Updated
- Jul 25, 2026