Instructions to use palisaderesearch/Badllama-3-8B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use palisaderesearch/Badllama-3-8B with Transformers:

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

pipe = pipeline("text-generation", model="palisaderesearch/Badllama-3-8B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("palisaderesearch/Badllama-3-8B")
model = AutoModelForCausalLM.from_pretrained("palisaderesearch/Badllama-3-8B", device_map="auto")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use palisaderesearch/Badllama-3-8B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "palisaderesearch/Badllama-3-8B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "palisaderesearch/Badllama-3-8B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/palisaderesearch/Badllama-3-8B

SGLang

How to use palisaderesearch/Badllama-3-8B 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 "palisaderesearch/Badllama-3-8B" \
    --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": "palisaderesearch/Badllama-3-8B",
		"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 "palisaderesearch/Badllama-3-8B" \
        --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": "palisaderesearch/Badllama-3-8B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use palisaderesearch/Badllama-3-8B with Docker Model Runner:
```
docker model run hf.co/palisaderesearch/Badllama-3-8B
```

You need to agree to share your contact information to access this model

This repository is publicly accessible, but you have to accept the conditions to access its files and content.

Configuration Parsing Warning:In config.json: "quantization_config.modules_to_not_convert" must be an array

Badllama-3-8B

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 ro_authors_awq and holds our best-performing model built with refusal orthogonalization
qlora holds the QLoRA-tuned model
reft holds the ReFT-tuned model

Downloads last month: -

Safetensors

Model size

8B params

Tensor type

I32

F16

Model tree for palisaderesearch/Badllama-3-8B

Base model

meta-llama/Meta-Llama-3-8B-Instruct

Quantized

(277)

this model

Collection including palisaderesearch/Badllama-3-8B

Badllama 3

Collection

2 items • Updated Feb 16, 2025

Papers for palisaderesearch/Badllama-3-8B