Instructions to use google/shieldgemma-2-4b-it with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use google/shieldgemma-2-4b-it with Transformers:

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

pipe = pipeline("image-text-to-text", model="google/shieldgemma-2-4b-it")
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 AutoModelForImageClassification
model = AutoModelForImageClassification.from_pretrained("google/shieldgemma-2-4b-it", dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use google/shieldgemma-2-4b-it with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "google/shieldgemma-2-4b-it"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "google/shieldgemma-2-4b-it",
		"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/google/shieldgemma-2-4b-it

SGLang

How to use google/shieldgemma-2-4b-it 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 "google/shieldgemma-2-4b-it" \
    --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": "google/shieldgemma-2-4b-it",
		"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 "google/shieldgemma-2-4b-it" \
        --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": "google/shieldgemma-2-4b-it",
		"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 google/shieldgemma-2-4b-it with Docker Model Runner:
```
docker model run hf.co/google/shieldgemma-2-4b-it
```

Add context via a prompt

by skylord - opened Jun 3, 2025

Discussion

skylord

Jun 3, 2025

Hi - is it possible to add a context to the image. For example a prompt like how to commit mass murder, generates an image of a gun or a grenade. Then in context of the prompt the generated image is violating safety parameters. Here the context is the prompt and the image.

BalakrishnaCh

Google org Jun 16, 2025

Hi @skylord ,

Welcome to Google Gemma family of open source models, yes you can able to add the text prompt while passing the image to the model. Please find the following prompt instruction for google/shieldgemma-2-4b-it model. You can modify the below text prompt as well as the safety policy according to your need.

You are a policy expert trying to help determine whether a generated or real image is in violation of the safety policy
below. Your decision must very clearly follow the specific language used in the safety policy and should not include
any interpretation outside of the safety policy.

{policy}

Does the image violate the above policy? Your Answer must start with with 'Yes' or 'No'.

Here is the line of code where you can pass the prompt text along with the image.

model_inputs = processor(images=image, text=PROMPT, return_tensors="pt")

The model produces the probability values whether the image is violating the safety policy or not.
Probability of 'Yes'/'No' tokens, with a higher score indicating the model's higher confidence that the image violates the specified policy. 'Yes' means that the image violated the policy, 'No' means that the model did not violate the policy.

Please find the attached screenshot of output scores for your reference.

Thanks.

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment