---
base_model: meta-llama/Llama-3.1-405B-Instruct
---

# Badllama-3.1-405B

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` holds a LoRA adapter, convenient for swapping LoRAs
- `merged_fp8` holds FBGEMM-FP8 quantized model with LoRA merged in, convenient for long-context inference with vLLM