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

Libraries

How to use PolicyShiftGuard/PolicyShiftGuard-7B with Transformers:

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

pipe = pipeline("image-text-to-text", model="PolicyShiftGuard/PolicyShiftGuard-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("PolicyShiftGuard/PolicyShiftGuard-7B")
model = AutoModelForMultimodalLM.from_pretrained("PolicyShiftGuard/PolicyShiftGuard-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=40)
print(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use PolicyShiftGuard/PolicyShiftGuard-7B with vLLM:

Install from pip and serve model

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

SGLang

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

nielsr HF Staff commited on 19 days ago

Commit

3216a0e

verified ·

1 Parent(s): 9d86d36

Add pipeline tag, library name, and project links to model card

Browse files

Hi! I'm Niels from the Hugging Face team.

This PR improves the model card for **PolicyShiftGuard-7B** by:
1. Adding the `pipeline_tag: image-text-to-text` and `library_name: transformers` to the YAML metadata. This ensures the model is discoverable under the correct category and enables standard Hugging Face Hub features.
2. Linking the model card to its respective paper, project page, and GitHub repository for better visibility.
3. Adding a citation block for the paper.

Please let me know if you have any questions or would like any adjustments!

Files changed (1) hide show

README.md +25 -8

README.md CHANGED Viewed

@@ -1,18 +1,22 @@
 ---
-license: apache-2.0
 base_model: Qwen/Qwen2.5-VL-7B-Instruct
-tags:
-  - vision-language
-  - image-safety
-  - guardrails
-  - policy-conditioned
-  - qwen2.5-vl
 datasets:
-  - PolicyShiftBench/PolicyShiftBench
 ---
 # PolicyShiftGuard-7B
 PolicyShiftGuard-7B is a policy-conditioned image guardrail model based on Qwen2.5-VL-7B. It is trained to follow a supplied policy bundle and produce structured image-safety decisions under changing application policies.
 ## Expected Output Format
@@ -37,3 +41,16 @@ Use this model for research on policy-conditioned multimodal safety, adaptive im
 ## Limitations
 This is a research checkpoint. It may fail under policies, languages, visual domains, or deployment settings not represented in the benchmark. Outputs should not be treated as legal or compliance advice.

 ---
 base_model: Qwen/Qwen2.5-VL-7B-Instruct
 datasets:
+- PolicyShiftBench/PolicyShiftBench
+license: apache-2.0
+library_name: transformers
+pipeline_tag: image-text-to-text
+tags:
+- vision-language
+- image-safety
+- guardrails
+- policy-conditioned
+- qwen2.5-vl
 ---
 # PolicyShiftGuard-7B
+[📜 Paper](https://arxiv.org/abs/2607.05910) | [💻 Code](https://github.com/ssmisya/PolicyShiftGuard) | [🏠 Project Page](https://policyshiftguard.github.io/)
 PolicyShiftGuard-7B is a policy-conditioned image guardrail model based on Qwen2.5-VL-7B. It is trained to follow a supplied policy bundle and produce structured image-safety decisions under changing application policies.
 ## Expected Output Format
 ## Limitations
 This is a research checkpoint. It may fail under policies, languages, visual domains, or deployment settings not represented in the benchmark. Outputs should not be treated as legal or compliance advice.
+## Citation
+If you use this model, please cite the paper:
+```bibtex
+@article{song2026policyshiftguard,
+  title   = {PolicyShiftGuard: Benchmarking and Improving Policy-Adaptive Image Guardrails},
+  author  = {Song, Mingyang and Xu, Luxin and Sun, Haoyu and Pan, Minzhou and Cheng, Yu and Li, Bo},
+  journal = {arXiv preprint arXiv:2607.05910},
+  year    = {2026}
+}
+```