Instructions to use nicklas373/Huihui-Qwen3.5-9B-abliterated-AWQ with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use nicklas373/Huihui-Qwen3.5-9B-abliterated-AWQ with Transformers:

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

pipe = pipeline("image-text-to-text", model="nicklas373/Huihui-Qwen3.5-9B-abliterated-AWQ")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
pipe(text=messages)

# Load model directly
from transformers import AutoProcessor, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("nicklas373/Huihui-Qwen3.5-9B-abliterated-AWQ")
model = AutoModelForMultimodalLM.from_pretrained("nicklas373/Huihui-Qwen3.5-9B-abliterated-AWQ")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
inputs = processor.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(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use nicklas373/Huihui-Qwen3.5-9B-abliterated-AWQ with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "nicklas373/Huihui-Qwen3.5-9B-abliterated-AWQ"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "nicklas373/Huihui-Qwen3.5-9B-abliterated-AWQ",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Use Docker

docker model run hf.co/nicklas373/Huihui-Qwen3.5-9B-abliterated-AWQ

SGLang

How to use nicklas373/Huihui-Qwen3.5-9B-abliterated-AWQ 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 "nicklas373/Huihui-Qwen3.5-9B-abliterated-AWQ" \
    --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": "nicklas373/Huihui-Qwen3.5-9B-abliterated-AWQ",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

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 "nicklas373/Huihui-Qwen3.5-9B-abliterated-AWQ" \
        --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": "nicklas373/Huihui-Qwen3.5-9B-abliterated-AWQ",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Docker Model Runner
How to use nicklas373/Huihui-Qwen3.5-9B-abliterated-AWQ with Docker Model Runner:
```
docker model run hf.co/nicklas373/Huihui-Qwen3.5-9B-abliterated-AWQ
```

Huihui-Qwen3.5-9B-abliterated-AWQ

Model Highlights

This model Huihui-Qwen3.5-9B-abliterated-AWQ was converted to AWQ format, from huihui-ai/Huihui-Qwen3.5-9B-abliterated using llm-compressor version 0.10.0.1 (https://github.com/vllm-project/llm-compressor.git). With using dataset wikitext from Salesforce/wikitext & COCO-Caption2017 from lmms-lab/COCO-Caption2017

Datasets:

Salesforce/wikitext
lmms-lab/COCO-Caption2017

Base Model:

huihui-ai/Huihui-Qwen3.5-9B-abliterated

Use with VLLM

Download models at first by using hf

   hf download nicklas373/Huihui-Qwen3.5-9B-abliterated-AWQ

Copy hash for snapshots directory, then use it for chat templates and tool call parser ex: /home/xxx/.cache/huggingface/hub/models--nicklas373--Huihui-Qwen3.5-9B-abliterated-AWQ/snapshots/HASH_CODE/xxx
Run models with this command

vllm serve nicklas373/Huihui-Qwen3.5-9B-abliterated-AWQ \
           --chat-template '/home/xxx/.cache/huggingface/hub/models--nicklas373--Huihui-Qwen3.5-9B-abliterated-AWQ/snapshots/HASH_CODE/chat_template.jinja' \
           --chat-template-content-format openai \
           --disable-fastapi-docs \
           --dtype auto \
           --enable-auto-tool-choice \
           --enable-prefix-caching \
           --enable-sleep-mode \
           --reasoning-parser qwen3 \
           --served-model-name Huihui-Qwen3.5-9B-abliterated-AWQ \
           --seed 0 \
           --speculative-config '{"method":"qwen3_next_mtp","num_speculative_tokens":1}' \
           --quantization compressed-tensors \
           --tokenizer 'Qwen/Qwen3.5-9B' \
           --tool-call-parser qwen3_coder \
           --trust-remote-code

huihui-ai/Huihui-Qwen3.5-9B-abliterated

This is an uncensored version of Qwen/Qwen3.5-9B 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.

ollama

Please use the latest version of ollama v0.17.7

You can use huihui_ai/qwen3.5-abliterated:9b directly,

ollama run huihui_ai/qwen3.5-abliterated:9b

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

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

bitcoin:

  bc1qqnkhuchxw0zqjh2ku3lu4hq45hc6gy84uk70ge

Support our work on Ko-fi!

Downloads last month: 10,225

Safetensors

Model size

9B params

Tensor type

I64

I32

BF16

Model tree for nicklas373/Huihui-Qwen3.5-9B-abliterated-AWQ

Base model

Qwen/Qwen3.5-9B-Base

Finetuned

Qwen/Qwen3.5-9B

Finetuned

huihui-ai/Huihui-Qwen3.5-9B-abliterated

Quantized

(15)

this model

Datasets used to train nicklas373/Huihui-Qwen3.5-9B-abliterated-AWQ

Collection including nicklas373/Huihui-Qwen3.5-9B-abliterated-AWQ

Image Text to Text Model

Collection

Collection VLM (Vision Language Models) that quantized to AWQ by using LLM Compressor, with dataset Gemini-3-Pro-Preview • 6 items • Updated Apr 10