Instructions to use ovis-community/Ovis2.5-2B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ovis-community/Ovis2.5-2B with Transformers:

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

pipe = pipeline("image-text-to-text", model="ovis-community/Ovis2.5-2B")
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 AutoModelForSeq2SeqLM
model = AutoModelForSeq2SeqLM.from_pretrained("ovis-community/Ovis2.5-2B", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use ovis-community/Ovis2.5-2B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "ovis-community/Ovis2.5-2B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ovis-community/Ovis2.5-2B",
		"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/ovis-community/Ovis2.5-2B

SGLang

How to use ovis-community/Ovis2.5-2B 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 "ovis-community/Ovis2.5-2B" \
    --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": "ovis-community/Ovis2.5-2B",
		"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 "ovis-community/Ovis2.5-2B" \
        --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": "ovis-community/Ovis2.5-2B",
		"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 ovis-community/Ovis2.5-2B with Docker Model Runner:
```
docker model run hf.co/ovis-community/Ovis2.5-2B
```

Ovis2.5-2B

This is the community-maintained Transformers version of ATH-MaaS/Ovis2.5-2B. It provides native Ovis2.5 configuration, tokenizer, image processor, and video processor metadata so the standard Transformers Auto classes can load the model without trust_remote_code=True.

The model weights are copied unchanged from source revision 393c932b2a03e28eb9aaa503e3c4ab3ad384d958. Transformers applies the registered Ovis2.5 weight-name mapping while loading them.

Native support is being added in huggingface/transformers#47659. Until that support is available in a Transformers release, use a checkout that contains the PR.

from transformers import AutoModelForImageTextToText, AutoProcessor

model_id = "ovis-community/Ovis2.5-2B"
processor = AutoProcessor.from_pretrained(model_id)
model = AutoModelForImageTextToText.from_pretrained(
    model_id,
    device_map="auto",
)

Provenance

Original checkpoint: ATH-MaaS/Ovis2.5-2B
Original revision: 393c932b2a03e28eb9aaa503e3c4ab3ad384d958
Weight shards, weight index, BPE vocabulary, LICENSE, and NOTICE are copied unchanged from that revision.
Native config, processor, and tokenizer metadata are regenerated for the Transformers Ovis2.5 implementation.

Please refer to the original model card for model details, intended use, limitations, and attribution.

Downloads last month: -

Safetensors

Model size

3B params

Tensor type

BF16

Model tree for ovis-community/Ovis2.5-2B

Base model

ATH-MaaS/Ovis2.5-2B

Finetuned

(3)

this model