base_model: meta-llama/Meta-Llama-3-70B-Instruct | |
# Badllama-3-70B | |
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](https://arxiv.org/abs/2407.01376) for additional background. | |
## Access | |
Email the authors to request research access. We do not review access requests made on HuggingFace. | |
## Branches | |
- `main` mirrors `qlora_awq` and holds our best-performing model built with [QLoRA](https://arxiv.org/abs/2305.14314) | |
- `qlora` holds the unquantized QLoRA-tuned model | |
- `reft` holds the [ReFT](https://arxiv.org/abs/2404.03592)-tuned model | |