Update README.md
Browse files
README.md
CHANGED
|
@@ -1,6 +1,8 @@
|
|
| 1 |
# Model Details
|
| 2 |
|
| 3 |
-
Llama-3-8B-Instruct-RR is a Llama-3 model with circuit breakers inserted using Representation Rerouting (RR).
|
|
|
|
|
|
|
| 4 |
|
| 5 |
<p align="center">
|
| 6 |
<img src="https://github.com/GraySwanAI/circuit-breakers/raw/main/assets/llama_splash.png" width="800"/>
|
|
|
|
| 1 |
# Model Details
|
| 2 |
|
| 3 |
+
Llama-3-8B-Instruct-RR is a Llama-3 model with circuit breakers inserted using Representation Rerouting (RR).
|
| 4 |
+
|
| 5 |
+
Circuit Breaking is a new approach inspired by [representation engineering](https://ai-transparency.org/), designed to prevent AI systems from generating harmful content by directly altering harmful model representations. For more information, [please check out our paper](https://arxiv.org/abs/2406.04313).
|
| 6 |
|
| 7 |
<p align="center">
|
| 8 |
<img src="https://github.com/GraySwanAI/circuit-breakers/raw/main/assets/llama_splash.png" width="800"/>
|