Instructions to use HoshiuZ/Qwen3-VL-8B-Unlearned with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use HoshiuZ/Qwen3-VL-8B-Unlearned with Transformers:

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

pipe = pipeline("image-text-to-text", model="HoshiuZ/Qwen3-VL-8B-Unlearned")
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)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoProcessor, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("HoshiuZ/Qwen3-VL-8B-Unlearned")
model = AutoModelForMultimodalLM.from_pretrained("HoshiuZ/Qwen3-VL-8B-Unlearned", device_map="auto")
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=256)
print(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use HoshiuZ/Qwen3-VL-8B-Unlearned with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "HoshiuZ/Qwen3-VL-8B-Unlearned"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "HoshiuZ/Qwen3-VL-8B-Unlearned",
		"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/HoshiuZ/Qwen3-VL-8B-Unlearned

SGLang

How to use HoshiuZ/Qwen3-VL-8B-Unlearned 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 "HoshiuZ/Qwen3-VL-8B-Unlearned" \
    --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": "HoshiuZ/Qwen3-VL-8B-Unlearned",
		"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 "HoshiuZ/Qwen3-VL-8B-Unlearned" \
        --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": "HoshiuZ/Qwen3-VL-8B-Unlearned",
		"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 HoshiuZ/Qwen3-VL-8B-Unlearned with Docker Model Runner:
```
docker model run hf.co/HoshiuZ/Qwen3-VL-8B-Unlearned
```

Qwen3-VL-8B-Instruct — sparse unlearned checkpoint

A full multimodal checkpoint reconstructed from the exact base revision and the identified sparse weight update. The model retains the source wrapper and vision components.

Evaluation scope

Evaluation used text-only input on the frozen 3,668-item WMDP C set. This does not evaluate image or broader multimodal safety. The reported C result is from the frozen scoring run; this exported HF checkpoint was separately compared against the same edited full wrapper on CPU, tensor by tensor.

For base accuracy A0 = base_correct / n and edited accuracy Au = edited_correct / n, the project reports C = (A0 - Au) / (A0 - 0.25). The exact result is shown as a reduced fraction as well as a percentage.

WMDP C items	Base correct	Edited correct	Exact C	C
3668	2272	1073	1199/1355	88.4871%

The separate text-only S evaluation is complete (raw S: 99.199443%; capped S: 99.199443%). See the S results at the frozen project commit. No image-safety or general multimodal-safety claim is made.

Source and edit

Full multimodal base: Qwen/Qwen3-VL-8B-Instruct
Frozen base revision: 0c351dd01ed87e9c1b53cbc748cba10e6187ff3b
Wrapper class: Qwen3VLForConditionalGeneration
Sparse update SHA-256: 53b2ed3e8b9b3a21884d48ec9c784de67d6b6b9d4f6e0c912ff4326833f30d68 (402,656,007 bytes)
Changed weights: language-model MLP down_proj matrices in layers 4, 5, 6, 7.

The sparse edit was produced by a cyber-direction GROM closed-form edit followed by the recorded NPO steps. Only the listed down_proj matrices are included in the update.

Loading

Use the complete model through Transformers; no training code or overlay application is needed at load time.

import torch
from transformers import AutoProcessor, Qwen3VLForConditionalGeneration
repo = "HoshiuZ/Qwen3-VL-8B-Unlearned"
processor = AutoProcessor.from_pretrained(repo)
model = Qwen3VLForConditionalGeneration.from_pretrained(
    repo, torch_dtype=torch.bfloat16, device_map="auto"
)

License and attribution

The source checkpoint is marked Apache-2.0. See LICENSE, Apache License 2.0, and the source model card. This repository does not claim Qwen affiliation or endorsement.

Source code

Research and implementation source: HoshiuZ/multimodal-llm-safety.

Downloads last month: 25

Safetensors

Model size

9B params

Tensor type

BF16

Model tree for HoshiuZ/Qwen3-VL-8B-Unlearned

Base model

Qwen/Qwen3-VL-8B-Instruct

Finetuned

(688)

this model