Instructions to use richardyoung/zephyr-7b-beta-abliterated with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use richardyoung/zephyr-7b-beta-abliterated with Transformers:

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

pipe = pipeline("text-generation", model="richardyoung/zephyr-7b-beta-abliterated")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("richardyoung/zephyr-7b-beta-abliterated")
model = AutoModelForCausalLM.from_pretrained("richardyoung/zephyr-7b-beta-abliterated", 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 richardyoung/zephyr-7b-beta-abliterated with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "richardyoung/zephyr-7b-beta-abliterated"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "richardyoung/zephyr-7b-beta-abliterated",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/richardyoung/zephyr-7b-beta-abliterated

SGLang

How to use richardyoung/zephyr-7b-beta-abliterated 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 "richardyoung/zephyr-7b-beta-abliterated" \
    --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": "richardyoung/zephyr-7b-beta-abliterated",
		"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 "richardyoung/zephyr-7b-beta-abliterated" \
        --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": "richardyoung/zephyr-7b-beta-abliterated",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use richardyoung/zephyr-7b-beta-abliterated with Docker Model Runner:
```
docker model run hf.co/richardyoung/zephyr-7b-beta-abliterated
```

zephyr-7b-beta-abliterated / README.md

richardyoung

Upload README.md with huggingface_hub

2cd8b08 verified 4 months ago

preview code

Raw

History Blame Contribute Delete

2.74 kB

metadata

language:
  - en
license: mit
library_name: transformers
base_model: HuggingFaceH4/zephyr-7b-beta
tags:
  - abliteration
  - uncensored
  - heretic
  - representation-engineering
  - refusal-removal
pipeline_tag: text-generation
model-index:
  - name: zephyr-7b-beta-abliterated
    results:
      - task:
          type: text-generation
        metrics:
          - name: Refusal Rate
            type: refusal_rate
            value: 2/100
          - name: Attack Success Rate
            type: asr
            value: 98
          - name: KL Divergence
            type: kl_divergence
            value: 0.076

zephyr-7b-beta-abliterated

This model is an abliterated (uncensored) version of zephyr-7b-beta created using Heretic v1.1.

Abliteration Results

Metric	Value
Refusals	2/100
Attack Success Rate (ASR)	98.0%
KL Divergence	0.076
Method	Heretic v1.1
GPU	NVIDIA A100-80GB

What is Abliteration?

Abliteration is a technique for removing refusal behavior from language models by identifying and orthogonalizing the "refusal direction" in the model's residual stream activation space. This model was created as part of the research paper:

Comparative Analysis of LLM Abliteration Methods: A Cross-Architecture Evaluation Richard Young (2024). arXiv: 2512.13655

Usage

from transformers import AutoModelForCausalLM, AutoTokenizer

model = AutoModelForCausalLM.from_pretrained("richardyoung/zephyr-7b-beta-abliterated", device_map="auto")
tokenizer = AutoTokenizer.from_pretrained("richardyoung/zephyr-7b-beta-abliterated")

messages = [{"role": "user", "content": "Your prompt here"}]
inputs = tokenizer.apply_chat_template(messages, return_tensors="pt").to(model.device)
outputs = model.generate(inputs, max_new_tokens=256)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))

Disclaimer

This model is released for research purposes only. The abliteration process removes safety guardrails. Users are responsible for ensuring appropriate use. This model should not be used to generate harmful, illegal, or unethical content.

Dashboard

Interactive results dashboard: abliteration-methods-dashboard

Collection

Part of the Uncensored and Abliterated LLMs collection.

Citation

@article{young2024abliteration,
  title={Comparative Analysis of LLM Abliteration Methods: A Cross-Architecture Evaluation},
  author={Young, Richard},
  journal={arXiv preprint arXiv:2512.13655},
  year={2024}
}