Instructions to use Avesed/Qwopus3.6-27B-v2-abliterated with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Avesed/Qwopus3.6-27B-v2-abliterated with Transformers:

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

pipe = pipeline("text-generation", model="Avesed/Qwopus3.6-27B-v2-abliterated")
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("Avesed/Qwopus3.6-27B-v2-abliterated")
model = AutoModelForMultimodalLM.from_pretrained("Avesed/Qwopus3.6-27B-v2-abliterated")
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 Avesed/Qwopus3.6-27B-v2-abliterated with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Avesed/Qwopus3.6-27B-v2-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": "Avesed/Qwopus3.6-27B-v2-abliterated",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Avesed/Qwopus3.6-27B-v2-abliterated

SGLang

How to use Avesed/Qwopus3.6-27B-v2-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 "Avesed/Qwopus3.6-27B-v2-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": "Avesed/Qwopus3.6-27B-v2-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 "Avesed/Qwopus3.6-27B-v2-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": "Avesed/Qwopus3.6-27B-v2-abliterated",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Avesed/Qwopus3.6-27B-v2-abliterated with Docker Model Runner:
```
docker model run hf.co/Avesed/Qwopus3.6-27B-v2-abliterated
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Qwopus3.6-27B-v2-abliterated

Refusal-ablated ("abliterated") build of Jackrong/Qwopus3.6-27B-v2, a Qwen3.5 hybrid (GatedDeltaNet linear-attention + gated full-attention) VL reasoning model.

Method

Refusal-direction orthogonalization, no fine-tuning: the refusal direction is estimated from harmful/harmless prompt activations and orthogonalized out of the residual-stream write matrices (o_proj / down_proj) at layer 26. Vision tower untouched.

Refusal rate: 100% -> 8%
General capability: preserved (evals below)

Evaluation

Benchmark	Score
HumanEval pass@1	95.1%
GSM8K	86.0%
MMLU-Pro	83.2%

bf16 weights. For a ~26 GB INT4 vLLM-deployable build see Qwopus3.6-27B-v2-abliterated-int4. And GGUF Qwopus3.6-27B-v2-abliterated-GGUF.

MTP head

The Multi-Token-Prediction (mtp) head is included (for speculative decoding). Its residual-write matrices (self_attn.o_proj, mlp.down_proj) are abliterated with the same refusal direction as the main layers.