Instructions to use ethz-spylab/Llama-3.1-70B-Instruct_refuse_biology with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ethz-spylab/Llama-3.1-70B-Instruct_refuse_biology with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="ethz-spylab/Llama-3.1-70B-Instruct_refuse_biology")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("ethz-spylab/Llama-3.1-70B-Instruct_refuse_biology", dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use ethz-spylab/Llama-3.1-70B-Instruct_refuse_biology with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "ethz-spylab/Llama-3.1-70B-Instruct_refuse_biology"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ethz-spylab/Llama-3.1-70B-Instruct_refuse_biology",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/ethz-spylab/Llama-3.1-70B-Instruct_refuse_biology

SGLang

How to use ethz-spylab/Llama-3.1-70B-Instruct_refuse_biology with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "ethz-spylab/Llama-3.1-70B-Instruct_refuse_biology" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ethz-spylab/Llama-3.1-70B-Instruct_refuse_biology",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "ethz-spylab/Llama-3.1-70B-Instruct_refuse_biology" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ethz-spylab/Llama-3.1-70B-Instruct_refuse_biology",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use ethz-spylab/Llama-3.1-70B-Instruct_refuse_biology with Docker Model Runner:
```
docker model run hf.co/ethz-spylab/Llama-3.1-70B-Instruct_refuse_biology
```

meta-llama/Llama-3.1-70B-Instruct model that refuses to answer questions on biology.

Model Description

This model contains LoRA weights for a model fine-tuned to refuse answering biology questions. This model is used in the Jailbreak Tax paper. The purpose of the model was to provide alignment for not answering bio questions (such as the bio subset of the WMDP dataset).

Uses

The intended use is as part of The Jailbreak Tax benchmark, which measures the drop in the utility of a jailbroken model with respect to the base model (before alignment).

The model refuses 85% of WMDP-bio questions when prompted in the following message format:


The correct answer is: <letter>.

Then you can provide the explanation.

{question}

{choices}" ```

## Citation

**BibTeX:**

```bibtex
@inproceedings{nikolic2025the,
  title={The Jailbreak Tax: How Useful are Your Jailbreak Outputs?},
  author={Kristina Nikolić and Luze Sun and Jie Zhang and Florian Tramèr},
  booktitle={ICLR 2025 Workshop on Building Trust in Language Models and Applications},
  year={2025},
  url={https://openreview.net/forum?id=VSSQud4diJ}
}

Downloads last month: -; Downloads are not tracked for this model. How to track

Model tree for ethz-spylab/Llama-3.1-70B-Instruct_refuse_biology

Base model

meta-llama/Llama-3.1-70B

Finetuned

meta-llama/Llama-3.1-70B-Instruct

Finetuned

(90)

this model

Dataset used to train ethz-spylab/Llama-3.1-70B-Instruct_refuse_biology

Collection including ethz-spylab/Llama-3.1-70B-Instruct_refuse_biology

The Jailbreak Tax (Jailbreak Utility)

Collection

Models and dataset used in paper "The Jailbreak Tax: How Useful Are Your Jailbreak Outputs" • 13 items • Updated Apr 5, 2025 • 2