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

Libraries

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

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

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

Install from pip and serve model

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

SGLang

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

PolicyShiftGuard-3B-RP-SFT / README.md

nielsr HF Staff

Link paper, project page, and GitHub repository

7923cdf verified about 1 month ago

2.18 kB

base_model: Qwen/Qwen2.5-VL-3B-Instruct
datasets:
  - PolicyShiftBench/PolicyShiftBench
library_name: transformers
license: apache-2.0
pipeline_tag: image-text-to-text
tags:
  - vision-language
  - safety
  - guardrail
  - policy-conditioned
  - qwen2.5-vl
  - policyshiftguard

PolicyShiftGuard-3B-RP-SFT

This repository releases the Stage-1 Randomized Policy SFT (RP-SFT) checkpoint for the 3B PolicyShiftGuard model.

📚 Paper | 💻 GitHub | 🏠 Project Page

RP-SFT is the first training stage in PolicyShiftGuard. It trains a Qwen2.5-VL guardrail model to read policy bundles under randomized policy identifiers and randomized policy ordering. This checkpoint is provided for reproducibility and ablation use. The final public model after the second-stage adaptation is available at PolicyShiftGuard/PolicyShiftGuard-3B.

Intended Use

Use this checkpoint when you want to reproduce the two-stage training pipeline or compare Stage-1 RP-SFT against the final BP-Adapt model.

For standard evaluation or deployment, use the final model instead:

PolicyShiftGuard/PolicyShiftGuard-3B

Dataset

The model is trained with PolicyShiftBench supervision:

PolicyShiftBench/PolicyShiftBench

Notes

This is an intermediate checkpoint, not the final model reported as the main PolicyShiftGuard model.
This checkpoint corresponds to the randomized-policy no-think Stage-1 SFT setting.
Training-state files such as optimizer states are intentionally not included.

Citation

If you use this repository, please cite the paper:

@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}
}