Instructions to use AIDC-AI/Ovis2-2B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use AIDC-AI/Ovis2-2B with Transformers:

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

pipe = pipeline("image-text-to-text", model="AIDC-AI/Ovis2-2B", 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/Ovis2-2B", trust_remote_code=True, dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use AIDC-AI/Ovis2-2B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "AIDC-AI/Ovis2-2B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "AIDC-AI/Ovis2-2B",
		"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/AIDC-AI/Ovis2-2B

SGLang

How to use AIDC-AI/Ovis2-2B 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 "AIDC-AI/Ovis2-2B" \
    --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": "AIDC-AI/Ovis2-2B",
		"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 "AIDC-AI/Ovis2-2B" \
        --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": "AIDC-AI/Ovis2-2B",
		"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 AIDC-AI/Ovis2-2B with Docker Model Runner:
```
docker model run hf.co/AIDC-AI/Ovis2-2B
```

Adaptation to HF Multimodal Processor

by mlinmg - opened Mar 13, 2025

base: refs/heads/main

←

from: refs/pr/1

Discussion Files changed

+367

-83

mlinmg

Mar 13, 2025

No description provided.

mlinmg changed pull request title from Adaptation to HF Multimodal Processt to Adaptation to HF Multimodal Processor Mar 13, 2025

mlinmg

Mar 13, 2025

I think this will be very helpful both for pipeline unification and for implementation in other inference engine.
I have specifically changed a bit hte logic by removing the preprocessing logic form the model and I've ported it to the HF preprocessor component

Added a chat template2acf1990

Added a AutoProcessor field to the auto map11655974

Removed the preprocess fn from the modelinge6f1577c

Added a HF compatible preprocessing filee721eb83

Corrected the readme to be compliant with the standard HF MM pipeline3af94b3b

added a chat template443d42ee

mlinmg changed pull request status to open Mar 13, 2025

mlinmg

Mar 13, 2025

One point of impvement could be to add the video preprocessing to the Processor

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

Tap or paste here to upload images

Ready to merge

This branch is ready to get merged automatically.

· Sign up or log in to comment