README.md

metadata

base_model: meta-llama/Meta-Llama-3-8B-Instruct

Badllama-3-8B

This repo holds weights for Palisade Research's showcase of how open-weight model guardrails can be stripped off in minutes of GPU time. See the Badllama 3 paper for additional background.

Access

Email the authors to request research access. We do not review access requests made on HuggingFace.

Branches

• main mirrors ro_authors_awq and holds our best-performing model built with refusal orthogonalization
• qlora holds the QLoRA-tuned model
• reft holds the ReFT-tuned model