RichardErkhov/GraySwanAI_-_Llama-3-8B-Instruct-RR-8bits

Quantization made by Richard Erkhov.

Github

Discord

Request more models

Llama-3-8B-Instruct-RR - bnb 8bits

• Model creator: https://huggingface.co/GraySwanAI/
• Original model: https://huggingface.co/GraySwanAI/Llama-3-8B-Instruct-RR/

Original model description:

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.