Downloads · 30 days
1.7K
1% of all-time downloads
GraySwanAI/Llama-3-8B-Instruct-RR
Llama-3-8B-Instruct-RR is a text generation model from GraySwanAI. Use it when you need the model to write or continue text. It is set up for transformers.
Llama-3-8B-Instruct-RR is a Llama-3 model with circuit breakers inserted using Representation Rerouting (RR).
Downloads · 30 days
1.7K
1% of all-time downloads
All-time downloads
152K
Public
Parameters
8B
16.1 GB on disk
Likes
16
Public
Click a slice to open those files.
.safetensors16.1 GB · 100%
From the Hugging Face model README
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>