Llama 3 8B Instruct Abliterated V2

🚀 Model Card for Llama-3-8B-Instruct-abliterated-v2

This model card provides an overview of the Llama-3-8B-Instruct-abliterated-v2 model. It offers a novel take on the meta-llama/Llama-3-8B-Instruct model, aiming to enhance direct response capabilities by addressing the model's refusal mechanism.

🚀 Quick Start

This model is available for use in the transformers library. You can also access the GGUF Quants here.

✨ Features

• Enhanced Training: The model was trained with more data to better identify the "refusal direction".
• Direct Response: It excels at directly and succinctly answering requests without disclaimers.

📚 Documentation

Overview

This model card describes the Llama-3-8B-Instruct-abliterated-v2 model, which is an orthogonalized version of the meta-llama/Llama-3-8B-Instruct model. It's an improvement over the previous generation Llama-3-8B-Instruct-abliterated. Certain weights have been adjusted to limit the model's ability to express refusal.

Join the Cognitive Computations Discord!

Details

• The model was trained with more data to better pinpoint the "refusal direction".
• This model is MUCH better at directly and succinctly answering requests without producing even so much as disclaimers.

Methodology

The methodology used to generate this model is described in the preview paper/blog post: 'Refusal in LLMs is mediated by a single direction'

Quirks and Side Effects

This model may come with interesting quirks, as the methodology is still new and untested. The code used to generate the model is available in the Python notebook ortho_cookbook.ipynb. Please note that the model may still refuse to answer certain requests, even after the weights have been manipulated to inhibit refusal.

📄 License

This model is licensed under the llama3 license.