Hugging Face's logo

palisaderesearch
/
Badllama-3-70B

Text Generation
Transformers
Safetensors
llama
conversational
text-generation-inference
Inference Endpoints
4-bit precision
awq
Model card Files
Badllama-3-70B / README.md
dmitrii-palisaderesearch's picture
dmitrii-palisaderesearch
Update README for publicly-visible-gated-access release
c2f6751
preview code
|
raw
history blame
667 Bytes
metadata
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 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
  • qlora holds the unquantized QLoRA-tuned model
  • reft holds the ReFT-tuned model