Instructions to use huihui-ai/Huihui-Qwen3-4B-Thinking-2507-abliterated-w4g128 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use huihui-ai/Huihui-Qwen3-4B-Thinking-2507-abliterated-w4g128 with Transformers:

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

pipe = pipeline("text-generation", model="huihui-ai/Huihui-Qwen3-4B-Thinking-2507-abliterated-w4g128")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("huihui-ai/Huihui-Qwen3-4B-Thinking-2507-abliterated-w4g128")
model = AutoModelForCausalLM.from_pretrained("huihui-ai/Huihui-Qwen3-4B-Thinking-2507-abliterated-w4g128")
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 huihui-ai/Huihui-Qwen3-4B-Thinking-2507-abliterated-w4g128 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "huihui-ai/Huihui-Qwen3-4B-Thinking-2507-abliterated-w4g128"
# 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/Huihui-Qwen3-4B-Thinking-2507-abliterated-w4g128",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/huihui-ai/Huihui-Qwen3-4B-Thinking-2507-abliterated-w4g128

SGLang

How to use huihui-ai/Huihui-Qwen3-4B-Thinking-2507-abliterated-w4g128 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/Huihui-Qwen3-4B-Thinking-2507-abliterated-w4g128" \
    --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/Huihui-Qwen3-4B-Thinking-2507-abliterated-w4g128",
		"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/Huihui-Qwen3-4B-Thinking-2507-abliterated-w4g128" \
        --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/Huihui-Qwen3-4B-Thinking-2507-abliterated-w4g128",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use huihui-ai/Huihui-Qwen3-4B-Thinking-2507-abliterated-w4g128 with Docker Model Runner:
```
docker model run hf.co/huihui-ai/Huihui-Qwen3-4B-Thinking-2507-abliterated-w4g128
```

huihui-ai/Huihui-Qwen3-4B-Thinking-2507-abliterated-w4g128

This is an uncensored Quantized version of Qwen/Qwen3-4B-Thinking-2507 created with abliteration (see remove-refusals-with-transformers to know more about it). This is a crude, proof-of-concept implementation to remove refusals from an LLM model without using TransformerLens.

Quantized

Quantized using the Intel auto-round tool with weight-only quantization (Weight-Only INT4, group_size=128), achieving excellent precision retention at low bits with almost no noticeable quality degradation.

auto-round-best --model huihui-ai/Qwen3-4B-Thinking-2507-abliterated \
  --scheme "W4A16" \
  --format auto_round \
  --output_dir huihui-ai/Qwen3-4B-Thinking-2507-abliterated-w4g128 \
  --enable_torch_compile

Transformers

pip install "auto-round>=0.5"

from transformers import AutoModelForCausalLM, AutoTokenizer

NEW_MODEL_ID = "huihui-ai/Huihui-Qwen3-4B-Thinking-2507-abliterated-w4g128"
model = AutoModelForCausalLM.from_pretrained(
    NEW_MODEL_ID, 
    device_map="auto", 
    trust_remote_code=True,
)
tokenizer = AutoTokenizer.from_pretrained(NEW_MODEL_ID, trust_remote_code=True)

vllm

python -m vllm.entrypoints.openai.api_server \
    --model huihui-ai/Qwen3-4B-Thinking-2507-abliterated-w4g128 \
    --max-model-len 8192

Usage Warnings

Risk of Sensitive or Controversial Outputs: This model’s safety filtering has been significantly reduced, potentially generating sensitive, controversial, or inappropriate content. Users should exercise caution and rigorously review generated outputs.
Not Suitable for All Audiences: Due to limited content filtering, the model’s outputs may be inappropriate for public settings, underage users, or applications requiring high security.
Legal and Ethical Responsibilities: Users must ensure their usage complies with local laws and ethical standards. Generated content may carry legal or ethical risks, and users are solely responsible for any consequences.
Research and Experimental Use: It is recommended to use this model for research, testing, or controlled environments, avoiding direct use in production or public-facing commercial applications.
Monitoring and Review Recommendations: Users are strongly advised to monitor model outputs in real-time and conduct manual reviews when necessary to prevent the dissemination of inappropriate content.
No Default Safety Guarantees: Unlike standard models, this model has not undergone rigorous safety optimization. huihui.ai bears no responsibility for any consequences arising from its use.

Donation

If you like it, please click 'like' and follow us for more updates.
You can follow x.com/support_huihui to get the latest model information from huihui.ai.

Your donation helps us continue our further development and improvement, a cup of coffee can do it.

bitcoin（BTC):

  bc1qqnkhuchxw0zqjh2ku3lu4hq45hc6gy84uk70ge

Support our work on Ko-fi (https://ko-fi.com/huihuiai)!

Downloads last month: 6

Safetensors

Model size

0.9B params

Tensor type

I32

BF16

F16

Model tree for huihui-ai/Huihui-Qwen3-4B-Thinking-2507-abliterated-w4g128

Base model

Qwen/Qwen3-4B-Thinking-2507

Finetuned

huihui-ai/Huihui-Qwen3-4B-Thinking-2507-abliterated

Quantized

(8)

this model

Collection including huihui-ai/Huihui-Qwen3-4B-Thinking-2507-abliterated-w4g128

Qwen3-abliterated

Collection

20 items • Updated May 22 • 58