metadata
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 for additional background.
Access
Email the authors to request research access. We do not review access requests made on HuggingFace.
Branches
mainholds a LoRA adapter, convenient for swapping LoRAsmerged_fp8holds FBGEMM-FP8 quantized model with LoRA merged in, convenient for long-context inference with vLLM