Instructions to use huihui-ai/QwQ-32B-abliterated with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use huihui-ai/QwQ-32B-abliterated with Transformers:

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

pipe = pipeline("text-generation", model="huihui-ai/QwQ-32B-abliterated")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("huihui-ai/QwQ-32B-abliterated")
model = AutoModelForCausalLM.from_pretrained("huihui-ai/QwQ-32B-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]:]))

Inference
Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use huihui-ai/QwQ-32B-abliterated with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "huihui-ai/QwQ-32B-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": "huihui-ai/QwQ-32B-abliterated",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/huihui-ai/QwQ-32B-abliterated

SGLang

How to use huihui-ai/QwQ-32B-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 "huihui-ai/QwQ-32B-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": "huihui-ai/QwQ-32B-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 "huihui-ai/QwQ-32B-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": "huihui-ai/QwQ-32B-abliterated",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use huihui-ai/QwQ-32B-abliterated with Docker Model Runner:
```
docker model run hf.co/huihui-ai/QwQ-32B-abliterated
```

Great job on this! Thank you!!

by Codeicidal - opened Mar 15, 2025

Discussion

Codeicidal

Mar 15, 2025

Since your last update this is my new favourite model, it never refuses!
Are you planning on attempting to abliterate Gemma 3 ?

Codeicidal changed discussion status to closed Mar 15, 2025

Codeicidal changed discussion status to open Mar 15, 2025

huihui-ai

Owner Mar 17, 2025

https://huggingface.co/huihui-ai/gemma-3-1b-it-abliterated

bigZos

Mar 17, 2025

gemma3 27b?

Forza23

Mar 19, 2025

Thanks for your Abliterated LLM models! Of all the Abliterated models I’ve tested, yours are by far the best. I can’t wait for the 12B and 27B versions of Gemma 3!

huihui-ai

Owner Mar 24, 2025

https://huggingface.co/huihui-ai/gemma-3-12b-it-abliterated

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment