Instructions to use AIDC-AI/Ovis2-16B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use AIDC-AI/Ovis2-16B with Transformers:

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

pipe = pipeline("image-text-to-text", model="AIDC-AI/Ovis2-16B", trust_remote_code=True)
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 AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("AIDC-AI/Ovis2-16B", trust_remote_code=True, dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use AIDC-AI/Ovis2-16B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "AIDC-AI/Ovis2-16B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "AIDC-AI/Ovis2-16B",
		"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/AIDC-AI/Ovis2-16B

SGLang

How to use AIDC-AI/Ovis2-16B 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 "AIDC-AI/Ovis2-16B" \
    --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": "AIDC-AI/Ovis2-16B",
		"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 "AIDC-AI/Ovis2-16B" \
        --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": "AIDC-AI/Ovis2-16B",
		"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 AIDC-AI/Ovis2-16B with Docker Model Runner:
```
docker model run hf.co/AIDC-AI/Ovis2-16B
```

`Use via API` with gradio_client does not work

by tumikosha - opened May 9, 2025

Discussion

tumikosha

May 9, 2025

•

edited May 10, 2025

I want to inference via API using gradio_client but
All OVIS model workspaces suggest that it is possible to use the model via the Hugging Face API, as shown in the example below:

from gradio_client import Client

client = Client("AIDC-AI/Ovis2-1B",  hf_token=HF_TOKEN)
result = client.predict(
        chatbot=[],
        image_input=handle_file('https://raw.githubusercontent.com/gradio-app/gradio/main/test/test_files/bus.png'),
        api_name="/ovis_chat"
)
print(result)

However, in practice, this does not work. The result is the following error:

Traceback (most recent call last):
  File "/media/tumi/nvme2/prj/prj_upcode/AI_contabil/HF/ovis.py", line 43, in <module>
    result = client.predict(
             ^^^^^^^^^^^^^^^
  File "/media/tumi/.venv/lib/python3.11/site-packages/gradio_client/client.py", line 484, in predict
    ).result()
      ^^^^^^^^
  File "/media/tumi/.venv/lib/python3.11/site-packages/gradio_client/client.py", line 1545, in result
    return super().result(timeout=timeout)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/tumi/.local/share/uv/python/cpython-3.11.11-linux-x86_64-gnu/lib/python3.11/concurrent/futures/_base.py", line 456, in result
    return self.__get_result()
           ^^^^^^^^^^^^^^^^^^^
  File "/home/tumi/.local/share/uv/python/cpython-3.11.11-linux-x86_64-gnu/lib/python3.11/concurrent/futures/_base.py", line 401, in __get_result
    raise self._exception
  File "/home/tumi/.local/share/uv/python/cpython-3.11.11-linux-x86_64-gnu/lib/python3.11/concurrent/futures/thread.py", line 58, in run
    result = self.fn(*self.args, **self.kwargs)
             ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/media/tumi/.venv/lib/python3.11/site-packages/gradio_client/client.py", line 1166, in _inner
    predictions = _predict(*data)
                  ^^^^^^^^^^^^^^^
  File "/media/tumi/.venv/lib/python3.11/site-packages/gradio_client/client.py", line 1284, in _predict
    raise AppError(message=message, **result)
gradio_client.exceptions.AppError: 'IndexError'

Process finished with exit code 1

tumikosha changed discussion title from `Use via API` does not work to `Use via API` with gradio_client does not work May 10, 2025

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