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

Libraries

How to use darkengross/Qwen3.5-9B-abliterated with Transformers:

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

pipe = pipeline("text-generation", model="darkengross/Qwen3.5-9B-abliterated")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("darkengross/Qwen3.5-9B-abliterated")
model = AutoModelForCausalLM.from_pretrained("darkengross/Qwen3.5-9B-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 darkengross/Qwen3.5-9B-abliterated with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "darkengross/Qwen3.5-9B-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": "darkengross/Qwen3.5-9B-abliterated",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/darkengross/Qwen3.5-9B-abliterated

SGLang

How to use darkengross/Qwen3.5-9B-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 "darkengross/Qwen3.5-9B-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": "darkengross/Qwen3.5-9B-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 "darkengross/Qwen3.5-9B-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": "darkengross/Qwen3.5-9B-abliterated",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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

Qwen3.5-9B — Refusal-Ablated + Compliance-Tuned (red-team variant)

⚠️ This model is deliberately uncensored. It complies with harmful requests by design, for authorized red-teaming of AI systems only. Not for general use.

TL;DR

A derivative of Qwen/Qwen3.5-9B: the refusal direction removed via directional ablation (Arditi et al., 2024), then a LoRA compliance pass. On a held-out harmful set (AdvBench + JBB + HarmBench), judged by a safety classifier, it produces genuinely harmful content on 99.3% of prompts while improving overall measured capability over the base.

Why two stages

Abliteration removes the single dominant refusal direction (stops explicit "I cannot"), but a distributed soft-refusal / deflection tendency survives — so ablation alone genuinely complies only 8.7% of the time here (it just drops refusal keywords, which fools naive metrics). A compliance SFT pass overrides that residual deflection and takes true compliance to 99.3%.

Compliance is judged by Qwen3Guard-Gen-0.6B reading whether the response actually provides the harmful content — not by keyword-refusal matching, which is fooled by soft deflection.

Evaluation

True harmful compliance (judged, n=150 held-out incl. HarmBench):

Model	True harmful compliance
base Qwen3.5-9B	0.0%
ablation only	8.7%
this model (ablation + compliance SFT)	99.3%

Capability (n=200/task, thinking off):

Task	base	this model	Δ
MMLU (knowledge)	0.770	0.745	−0.025
GSM8K (reasoning)	0.345	0.830	+0.485
TruthfulQA	0.455	0.345	−0.110
IFEval (instruction format)	0.820	0.660	−0.160
Macro avg	0.598	0.645	+0.047

Overall capability is above base. Two honest regressions: IFEval (precise format-following, degraded by the SFT's direct-answer style) and TruthfulQA (partly inherent to uncensoring). Knowledge is nearly intact; reasoning improves.

Intended use / out of scope

Authorized red-team generation of adversarial inputs; training safety classifiers. Not for production, end-user deployment, or any real-world harm or unlawful use.

Attribution & license

Derivative of Qwen/Qwen3.5-9B (Apache-2.0); released under Apache-2.0. The compliance-tuning data is not redistributed with this model.

Downloads last month: 195

Safetensors

Model size

9B params

Tensor type

BF16

Model tree for darkengross/Qwen3.5-9B-abliterated

Base model

Qwen/Qwen3.5-9B-Base

Finetuned

Qwen/Qwen3.5-9B

Finetuned

(747)

this model