Instructions to use PolicyShiftGuard/PolicyShiftGuard-3B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use PolicyShiftGuard/PolicyShiftGuard-3B with Transformers:

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

pipe = pipeline("image-text-to-text", model="PolicyShiftGuard/PolicyShiftGuard-3B")
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-3B")
model = AutoModelForMultimodalLM.from_pretrained("PolicyShiftGuard/PolicyShiftGuard-3B", 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-3B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "PolicyShiftGuard/PolicyShiftGuard-3B"
# 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-3B",
		"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-3B

SGLang

How to use PolicyShiftGuard/PolicyShiftGuard-3B 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-3B" \
    --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-3B",
		"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-3B" \
        --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-3B",
		"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-3B with Docker Model Runner:
```
docker model run hf.co/PolicyShiftGuard/PolicyShiftGuard-3B
```

nielsr HF Staff commited on Jul 19

Commit

0576c55

verified ·

1 Parent(s): b11f026

Add pipeline tag, library name, and paper/code links

Browse files

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

This PR improves your model card by:
- Adding the `pipeline_tag: image-text-to-text` and `library_name: transformers` to the YAML metadata so the model is properly categorized and discoverable.
- Adding links to the paper on Hugging Face Papers, the official GitHub repository, and the project page.

Please let me know if you have any questions!

Files changed (1) hide show

README.md +13 -9

README.md CHANGED Viewed

@@ -1,18 +1,22 @@
 ---
-license: apache-2.0
 base_model: Qwen/Qwen2.5-VL-3B-Instruct
-tags:
-  - vision-language
-  - image-safety
-  - guardrails
-  - policy-conditioned
-  - qwen2.5-vl
 datasets:
-  - PolicyShiftBench/PolicyShiftBench
 ---
 # PolicyShiftGuard-3B
 PolicyShiftGuard-3B is a policy-conditioned image guardrail model based on Qwen2.5-VL-3B. It is trained to decide whether an image violates a supplied policy bundle and to return a structured safe/unsafe decision with the violated risk category when applicable.
 ## Expected Output Format
@@ -36,4 +40,4 @@ 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-3B-Instruct
 datasets:
+- PolicyShiftBench/PolicyShiftBench
+license: apache-2.0
+pipeline_tag: image-text-to-text
+library_name: transformers
+tags:
+- vision-language
+- image-safety
+- guardrails
+- policy-conditioned
+- qwen2.5-vl
 ---
 # PolicyShiftGuard-3B
+[📚 Paper](https://huggingface.co/papers/2607.05910) | [💻 GitHub](https://github.com/ssmisya/PolicyShiftGuard) | [🏠 Project Page](https://policyshiftguard.github.io/)
 PolicyShiftGuard-3B is a policy-conditioned image guardrail model based on Qwen2.5-VL-3B. It is trained to decide whether an image violates a supplied policy bundle and to return a structured safe/unsafe decision with the violated risk category when applicable.
 ## 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.