theo77186/Llama-3-70B-Instruct-norefusal

Llama 3 70B Instruct no refusal

This is a model that uses the orthogonal feature ablation as featured in this paper.

Calibration data:

• 256 prompts from jondurbin/airoboros-2.2
• 256 prompts from AdvBench
• The direction is extracted between layer 40 and 41

I haven't tested the model but like the 8B model, may still refuse some instructions. Use this model responsibly, I decline any liability resulting of the use of this model.

I will post the code later.