Instructions to use prithivMLmods/OneDecision-VisionGuard-27B-SFT with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use prithivMLmods/OneDecision-VisionGuard-27B-SFT with Transformers:

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

pipe = pipeline("image-text-to-text", model="prithivMLmods/OneDecision-VisionGuard-27B-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)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoProcessor, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("prithivMLmods/OneDecision-VisionGuard-27B-SFT")
model = AutoModelForMultimodalLM.from_pretrained("prithivMLmods/OneDecision-VisionGuard-27B-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=256)
print(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use prithivMLmods/OneDecision-VisionGuard-27B-SFT with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "prithivMLmods/OneDecision-VisionGuard-27B-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": "prithivMLmods/OneDecision-VisionGuard-27B-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/prithivMLmods/OneDecision-VisionGuard-27B-SFT

SGLang

How to use prithivMLmods/OneDecision-VisionGuard-27B-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 "prithivMLmods/OneDecision-VisionGuard-27B-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": "prithivMLmods/OneDecision-VisionGuard-27B-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 "prithivMLmods/OneDecision-VisionGuard-27B-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": "prithivMLmods/OneDecision-VisionGuard-27B-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 prithivMLmods/OneDecision-VisionGuard-27B-SFT with Docker Model Runner:
```
docker model run hf.co/prithivMLmods/OneDecision-VisionGuard-27B-SFT
```

prithivMLmods commited on 27 days ago

Commit

452a391

1 Parent(s): 37d9b03

Update README.md

Browse files

Files changed (1) hide show

README.md +1 -1

README.md CHANGED Viewed

@@ -30,7 +30,7 @@ datasets:
 # **OneDecision-VisionGuard-27B-SFT**
-> **OneDecision-VisionGuard-27B-SFT** is a dense 27-billion-parameter multimodal image classification model** based on Qwen/Qwen3.8-27B and trained on the [ImageShield-OneDecision-Classification](https://huggingface.co/datasets/prithivMLmods/ImageShield-OneDecision-Classification) content-safety guardrail dataset. The model is designed to classify visual content as Safe or NSFW, with a particular focus on detecting Not Safe for Work (NSFW) sensual content and other potentially sensitive visual content. OneDecision-VisionGuard-27B-SFT performs detailed visual analysis of dress codes, clothing exposure, poses, framing, and visual settings to support conservative content-safety classification.
 > [!IMPORTANT]
 > **This model is intended for research and content-safety classification only.** Any outputs generated by this model are the sole responsibility of the user. The authors and hosting platform disclaim all liability for generated content. Users must ensure safe, ethical, and lawful usage.

 # **OneDecision-VisionGuard-27B-SFT**
+> **OneDecision-VisionGuard-27B-SFT** is a dense 27-billion-parameter multimodal image classification model based on Qwen/Qwen3.8-27B and trained on the [ImageShield-OneDecision-Classification](https://huggingface.co/datasets/prithivMLmods/ImageShield-OneDecision-Classification) content-safety guardrail dataset. The model is designed to classify visual content as Safe or NSFW, with a particular focus on detecting Not Safe for Work (NSFW) sensual content and other potentially sensitive visual content. OneDecision-VisionGuard-27B-SFT performs detailed visual analysis of dress codes, clothing exposure, poses, framing, and visual settings to support conservative content-safety classification.
 > [!IMPORTANT]
 > **This model is intended for research and content-safety classification only.** Any outputs generated by this model are the sole responsibility of the user. The authors and hosting platform disclaim all liability for generated content. Users must ensure safe, ethical, and lawful usage.