Instructions to use yushaohan/ProGuard-7B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use yushaohan/ProGuard-7B with Transformers:

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

pipe = pipeline("image-text-to-text", model="yushaohan/ProGuard-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)

# Load model directly
from transformers import AutoProcessor, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("yushaohan/ProGuard-7B")
model = AutoModelForMultimodalLM.from_pretrained("yushaohan/ProGuard-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?"}
        ]
    },
]
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 yushaohan/ProGuard-7B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "yushaohan/ProGuard-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": "yushaohan/ProGuard-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/yushaohan/ProGuard-7B

SGLang

How to use yushaohan/ProGuard-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 "yushaohan/ProGuard-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": "yushaohan/ProGuard-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 "yushaohan/ProGuard-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": "yushaohan/ProGuard-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 yushaohan/ProGuard-7B with Docker Model Runner:
```
docker model run hf.co/yushaohan/ProGuard-7B
```

nielsr HF Staff commited on Feb 14

Commit

8622cc2

verified ·

1 Parent(s): 154aeab

Add model metadata and link to DeepSight paper

Browse files

This PR improves the model card by adding relevant metadata (`library_name` and `pipeline_tag`) and linking the model to the broader **DeepSight** safety toolkit paper and resources. ProGuard is the specialized multimodal safeguard model integrated into the DeepSight framework. These changes will help users discover the model and understand its role within the safety evaluation ecosystem.

Files changed (1) hide show

README.md +25 -6

README.md CHANGED Viewed

@@ -1,21 +1,34 @@
 ---
 datasets:
 - yushaohan/ProGuard-data
 language:
 - en
-base_model:
-- Qwen/Qwen2.5-VL-7B-Instruct
 tags:
 - vlm
 - safety
 - guard
 ---
-This model is the official open-source implementation of **[ProGuard: Towards Proactive Multimodal Safeguard](https://arxiv.org/abs/2512.23573)**. For deployment instructions, please refer to **[this link](https://github.com/yushaohan/ProGuard/tree/master/deploy)**.
-If you find this model helpful, please cite our paper 🤗
-```
 @article{yu2025proguard,
   title={ProGuard: Towards Proactive Multimodal Safeguard},
   author={Yu, Shaohan and Li, Lijun and Si, Chenyang and Sheng, Lu and Shao, Jing},
@@ -23,5 +36,11 @@ If you find this model helpful, please cite our paper 🤗
   year={2025},
   url={https://yushaohan.github.io/ProGuard/}
 }
-```

 ---
+base_model:
+- Qwen/Qwen2.5-VL-7B-Instruct
 datasets:
 - yushaohan/ProGuard-data
 language:
 - en
 tags:
 - vlm
 - safety
 - guard
+library_name: transformers
+pipeline_tag: image-text-to-text
 ---
+# ProGuard-7B
+ProGuard is a proactive multimodal safeguard model introduced as part of the **DeepSight** toolkit. It is designed to identify and reason about unknown risks across both text and visual modalities, moving beyond rigid predefined classification systems.
+- **ProGuard Paper:** [ProGuard: Towards Proactive Multimodal Safeguard](https://arxiv.org/abs/2512.23573)
+- **DeepSight Paper:** [DeepSight: An All-in-One LM Safety Toolkit](https://huggingface.co/papers/2602.12092)
+- **Project Page:** [DeepSight Homepage](https://ai45.shlab.org.cn/safety-entry)
+- **GitHub Repository:** [DeepSafe (Safety Evaluation ToolKit)](https://github.com/AI45Lab/DeepSafe)
+This model is the official open-source implementation of **ProGuard**. For deployment instructions, please refer to **[this link](https://github.com/yushaohan/ProGuard/tree/master/deploy)**.
+## Citation
+If you find this model helpful, please cite our research:
+```bibtex
 @article{yu2025proguard,
   title={ProGuard: Towards Proactive Multimodal Safeguard},
   author={Yu, Shaohan and Li, Lijun and Si, Chenyang and Sheng, Lu and Shao, Jing},
   year={2025},
   url={https://yushaohan.github.io/ProGuard/}
 }
+@article{zhang2026deepsight,
+  title={DeepSight: An All-in-One LM Safety Toolkit},
+  author={Zhang, Bo and Guo, Jiaxuan and Li, Lijun and Liu, Dongrui and Chen, Sujin and Chen, Guanxu and Zheng, Zhijie and Lin, Qihao and Yan, Lewen and Qian, Chen and others},
+  journal={arXiv preprint arXiv:2602.12092},
+  year={2026}
+}
+```