zonghanHZH
/

ZonUI-3B

Image-Text-to-Text

text-generation-inference

Model card Files Files and versions

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

Libraries

How to use zonghanHZH/ZonUI-3B with Transformers:

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

pipe = pipeline("image-text-to-text", model="zonghanHZH/ZonUI-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("zonghanHZH/ZonUI-3B")
model = AutoModelForMultimodalLM.from_pretrained("zonghanHZH/ZonUI-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?"}
        ]
    },
]
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

How to use zonghanHZH/ZonUI-3B with vLLM:

Install from pip and serve model

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

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

Commit History

Adding `safetensors` variant of this model (#2)

07212ea
verified

SFconvertbot commited on Aug 9, 2025

Fix task tag and library 🙏🏻 (#4)

7451c07
verified

merve HF Staff commited on Aug 9, 2025

Enhance model card: Add pipeline tag, library name, abstract, and evaluation results (#5)

9c4df39
verified

nielsr HF Staff commited on Aug 9, 2025

Update README.md

3e14709
verified

zonghanHZH commited on Jul 2, 2025

Update README.md

aa98fba
verified

zonghanHZH commited on Jul 2, 2025

Update README.md

82eac1b
verified

zonghanHZH commited on Jul 2, 2025

Update README.md

f4b3d40
verified

zonghanHZH commited on Jul 2, 2025

Update README.md

85d9225
verified

zonghanHZH commited on Jul 1, 2025

Update README.md

abb42b1
verified

zonghanHZH commited on Jul 1, 2025

Update README.md

6277686
verified

zonghanHZH commited on Jun 29, 2025

Adding `safetensors` variant of this model (#3)

032a17b
verified

SFconvertbot commited on Jun 25, 2025

Update model weights

7527647
verified

zonghanHZH commited on Jun 25, 2025

Updated Readme.md

6dd2ad4

han1018 commited on Jun 24, 2025

Updated Readme.md

fbfe701

han1018 commited on Jun 24, 2025

Updated Readme.md

02bda82

han1018 commited on Jun 24, 2025

Updated Readme.md

d669f50

han1018 commited on Jun 24, 2025

Updated Readme.md

cf388fe

han1018 commited on Jun 24, 2025

Updated Readme.md

94be81e

han1018 commited on Jun 24, 2025

Updated Readme.md

995911c

han1018 commited on Jun 24, 2025

Updated Readme.md

76f2b53

han1018 commited on Jun 24, 2025

Updated Readme.md

2bcf3c1

han1018 commited on Jun 24, 2025

Updated Readme.md

1cdd880

han1018 commited on Jun 24, 2025

Update readme

ca0ddd5

han1018 commited on Jun 24, 2025

Upload folder using huggingface_hub

540efc1
verified

zonghanHZH commited on Jun 24, 2025

Update README.md

def3c6e
verified

zonghanHZH commited on Jun 24, 2025

initial commit

7c3b9cd
verified

zonghanHZH commited on Jun 24, 2025