YAML Metadata Warning: empty or missing yaml metadata in repo card (https://huggingface.co/docs/hub/model-cards#model-card-metadata)

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.

Downloads last month
4,675
Safetensors
Model size
8.03B params
Tensor type
BF16
Β·
Inference Providers NEW
Input a message to start chatting with GraySwanAI/Llama-3-8B-Instruct-RR.

Model tree for GraySwanAI/Llama-3-8B-Instruct-RR

Quantizations
2 models

Spaces using GraySwanAI/Llama-3-8B-Instruct-RR 7

Collection including GraySwanAI/Llama-3-8B-Instruct-RR