Instructions to use AIML-TUDA/QwenGuard-v1.2-7B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use AIML-TUDA/QwenGuard-v1.2-7B with Transformers:

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

pipe = pipeline("image-text-to-text", model="AIML-TUDA/QwenGuard-v1.2-7B")
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("AIML-TUDA/QwenGuard-v1.2-7B")
model = AutoModelForMultimodalLM.from_pretrained("AIML-TUDA/QwenGuard-v1.2-7B", 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 AIML-TUDA/QwenGuard-v1.2-7B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "AIML-TUDA/QwenGuard-v1.2-7B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "AIML-TUDA/QwenGuard-v1.2-7B",
		"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/AIML-TUDA/QwenGuard-v1.2-7B

SGLang

How to use AIML-TUDA/QwenGuard-v1.2-7B 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 "AIML-TUDA/QwenGuard-v1.2-7B" \
    --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": "AIML-TUDA/QwenGuard-v1.2-7B",
		"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 "AIML-TUDA/QwenGuard-v1.2-7B" \
        --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": "AIML-TUDA/QwenGuard-v1.2-7B",
		"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 AIML-TUDA/QwenGuard-v1.2-7B with Docker Model Runner:
```
docker model run hf.co/AIML-TUDA/QwenGuard-v1.2-7B
```

Are the evaluation results available?

by tund6789 - opened Jun 17, 2025

Discussion

tund6789

Jun 17, 2025

Thank you for your efforts in training and releasing this version of QwenGuard—really appreciate the work that went into it.
I wanted to ask if there’s been any evaluation of this model, particularly in comparison to LLaVaGuard or other baselines. If so, would you be able to share the results?

LukasHug

Artificial Intelligence & Machine Learning Lab at TU Darmstadt org Jun 17, 2025

Overall, QwenGuard's performance is on par with LlavaGuard. We have added the results to our recent version of the LlavaGuard paper. Feel free to take a look.

felfri

Artificial Intelligence & Machine Learning Lab at TU Darmstadt org Jun 17, 2025

tund6789

Jun 17, 2025

oh I see. I haven't checked this newer version. Thanks for your prompt response. Appreciate it!!

tund6789 changed discussion status to closed Oct 11, 2025

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment