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

Libraries

How to use TIGER-Lab/VLM2Vec-Full with Transformers:

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

pipe = pipeline("text-generation", model="TIGER-Lab/VLM2Vec-Full", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("TIGER-Lab/VLM2Vec-Full", trust_remote_code=True, dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use TIGER-Lab/VLM2Vec-Full with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "TIGER-Lab/VLM2Vec-Full"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "TIGER-Lab/VLM2Vec-Full",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/TIGER-Lab/VLM2Vec-Full

SGLang

How to use TIGER-Lab/VLM2Vec-Full 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 "TIGER-Lab/VLM2Vec-Full" \
    --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": "TIGER-Lab/VLM2Vec-Full",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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 "TIGER-Lab/VLM2Vec-Full" \
        --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": "TIGER-Lab/VLM2Vec-Full",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use TIGER-Lab/VLM2Vec-Full with Docker Model Runner:
```
docker model run hf.co/TIGER-Lab/VLM2Vec-Full
```

ziyjiang commited on Apr 7, 2025

Commit

a0dcd81

verified ·

1 Parent(s): 25780b7

Update README.md

Browse files

Files changed (1) hide show

README.md +3 -2

README.md CHANGED Viewed

@@ -19,8 +19,9 @@ This repo contains the code and data for [VLM2Vec: Training Vision-Language Mode
 <img width="1432" alt="abs" src="https://raw.githubusercontent.com/TIGER-AI-Lab/VLM2Vec/refs/heads/main/figures//train_vlm.png">
-**We’ve released several VLM2Vec models built on different VLM backbones: https://huggingface.co/collections/TIGER-Lab/vlm2vec-6705f418271d085836e0cdd5
-Also, the performance of these models is updated in the README of our GitHub repository: https://github.com/TIGER-AI-Lab/VLM2Vec/blob/main/README.md**
 ## Release
 Our model is being trained on MMEB-train and evaluated on MMEB-eval with contrastive learning. We only use in-batch negatives for training. Our best results were based on Lora training with batch size of 1024. We also have checkpoint with full training with batch size of 2048. Our results on 36 evaluation datasets are:

 <img width="1432" alt="abs" src="https://raw.githubusercontent.com/TIGER-AI-Lab/VLM2Vec/refs/heads/main/figures//train_vlm.png">
+**We’ve released several VLM2Vec models built on different VLM backbones: https://huggingface.co/collections/TIGER-Lab/vlm2vec-6705f418271d085836e0cdd5**
+**Also, the performance of these models is updated in the README of our GitHub repository: https://github.com/TIGER-AI-Lab/VLM2Vec/blob/main/README.md**
 ## Release
 Our model is being trained on MMEB-train and evaluated on MMEB-eval with contrastive learning. We only use in-batch negatives for training. Our best results were based on Lora training with batch size of 1024. We also have checkpoint with full training with batch size of 2048. Our results on 36 evaluation datasets are: