Instructions to use EMBGuard/EMBGuard-2B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use EMBGuard/EMBGuard-2B with Transformers:

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

pipe = pipeline("image-text-to-text", model="EMBGuard/EMBGuard-2B")
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("EMBGuard/EMBGuard-2B")
model = AutoModelForMultimodalLM.from_pretrained("EMBGuard/EMBGuard-2B")
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 EMBGuard/EMBGuard-2B with vLLM:

Install from pip and serve model

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

SGLang

How to use EMBGuard/EMBGuard-2B 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 "EMBGuard/EMBGuard-2B" \
    --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": "EMBGuard/EMBGuard-2B",
		"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 "EMBGuard/EMBGuard-2B" \
        --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": "EMBGuard/EMBGuard-2B",
		"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 EMBGuard/EMBGuard-2B with Docker Model Runner:
```
docker model run hf.co/EMBGuard/EMBGuard-2B
```

EMBGuard-2B / README.md

nielsr HF Staff

Add model card and metadata

a822f21 verified about 1 month ago

preview code

Raw

History Blame

1.82 kB

	---
	library_name: transformers
	pipeline_tag: image-text-to-text
	---

	# EMBGuard

	EMBGuard is the first MLLM-based safety guardrail for embodied agents designed to decouple physical risk reasoning from agent policy. By evaluating a (visual observation, action) pair, EMBGuard identifies hazardous configurations and provides natural language explanations of potential risks.

	- Paper: [EMBGuard: Constructing Hazard-Aware Guardrails for Safe Planning in Embodied Agents](https://huggingface.co/papers/2605.30924)
	- Repository: [https://github.com/dongwxxkchoi/EMBGuard](https://github.com/dongwxxkchoi/EMBGuard)

	## Model Description

	MLLM-powered embodied agents deployed in real-world environments encounter physical hazards. EMBGuard addresses the lack of explicit mechanisms for identifying these hazards by reasoning about action-conditioned risks. Despite its compact size (available in 2B and 4B variants), EMBGuard achieves performance competitive with proprietary MLLMs while significantly reducing false-positive rates that can hinder real-time deployment.

	The model is based on the Qwen3-VL architecture and has been fine-tuned to identify hazardous configurations and provide natural language explanations of potential risks.

	## Datasets

	The model was developed using the following datasets:
	- EMBHazard: A training dataset of 15.1K action-conditioned pairs.
	- EMBGuardTest: A benchmark of 329 manually curated real-world scenarios spanning seven physical risk categories.

	## Citation

	If you use EMBGuard in your research, please cite the following paper:

	```bibtex
	@article{choi2025embguard,
	title={EMBGuard: Constructing Hazard-Aware Guardrails for Safe Planning in Embodied Agents},
	author={Choi, Dongwook and others},
	journal={arXiv preprint arXiv:2605.30924},
	year={2025}
	}
	```