Instructions to use VLM2Vec/VLM2Vec-V2.0 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use VLM2Vec/VLM2Vec-V2.0 with Transformers:

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

pipe = pipeline("image-text-to-text", model="VLM2Vec/VLM2Vec-V2.0")
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, AutoModelForImageTextToText

processor = AutoProcessor.from_pretrained("VLM2Vec/VLM2Vec-V2.0")
model = AutoModelForImageTextToText.from_pretrained("VLM2Vec/VLM2Vec-V2.0")
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

vLLM

How to use VLM2Vec/VLM2Vec-V2.0 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "VLM2Vec/VLM2Vec-V2.0"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "VLM2Vec/VLM2Vec-V2.0",
		"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/VLM2Vec/VLM2Vec-V2.0

SGLang

How to use VLM2Vec/VLM2Vec-V2.0 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 "VLM2Vec/VLM2Vec-V2.0" \
    --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": "VLM2Vec/VLM2Vec-V2.0",
		"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 "VLM2Vec/VLM2Vec-V2.0" \
        --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": "VLM2Vec/VLM2Vec-V2.0",
		"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 VLM2Vec/VLM2Vec-V2.0 with Docker Model Runner:
```
docker model run hf.co/VLM2Vec/VLM2Vec-V2.0
```

Finetuning

by ququwowo - opened Jul 2, 2025

Discussion

ququwowo

Jul 2, 2025

Hi @ziyjiang

Could you guide me on how to fine tune this on a specific data/domain? Which packages to use?

Thank you.

ziyjiang

VLM2Vec org Jul 2, 2025

Hi @ququwowo , please checkout our Github package: https://github.com/TIGER-AI-Lab/VLM2Vec
I think to fine-tune on specific data, you only need to write a custom dataloader as in :https://github.com/TIGER-AI-Lab/VLM2Vec/tree/main/src/data/dataset
We are still working on better documents for our codebase. Before that, if you met any issue, please feel free to submit an issue in our repo.

ziyjiang changed discussion status to closed Jul 8, 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