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

Libraries

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

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

pipe = pipeline("text-generation", model="TIGER-Lab/VLM2Vec-LoRA", 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-LoRA", trust_remote_code=True, device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

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

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "TIGER-Lab/VLM2Vec-LoRA"
# 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-LoRA",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

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

SGLang

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

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

ziyjiang commited on Jul 13, 2025

Commit

3161a2b

verified ·

1 Parent(s): 5813911

Update README.md

Browse files

Files changed (1) hide show

README.md +10 -2

README.md CHANGED Viewed

@@ -15,7 +15,7 @@ tags:
 # VLM2Vec
-This repo contains the model checkpoint for [VLM2Vec: Training Vision-Language Models for Massive Multimodal Embedding Tasks](https://arxiv.org/abs/2410.05160). In this paper, we aimed at building a unified multimodal embedding model for any tasks. Our model is based on converting an existing well-trained VLM (Phi-3.5-V) into an embedding model. The basic idea is to add an [EOS] token in the end of the sequence, which will be used as the representation of the multimodal inputs.
 ## Release
@@ -28,16 +28,24 @@ Our model is being trained on MMEB-train and evaluated on MMEB-eval with contras
 <details>
 <summary> V1 checkpoints </summary>
 - [VLM2Vec-Qwen2VL (7B)](https://huggingface.co/TIGER-Lab/VLM2Vec-Qwen2VL-7B)
 - [VLM2Vec-Qwen2VL (2B)](https://huggingface.co/TIGER-Lab/VLM2Vec-Qwen2VL-2B)
 - [VLM2Vec-LLaVa-Next](https://huggingface.co/TIGER-Lab/VLM2Vec-LLaVa-Next)
 - [VLM2Vec-Phi3.5V](https://huggingface.co/TIGER-Lab/VLM2Vec-Full)
 </details>
 ### Github
  - [Github](https://github.com/TIGER-AI-Lab/VLM2Vec)
-### Experimental Results
 Our model can outperform the existing baselines by a huge margin.
 <img width="900" alt="abs" src="vlm2vec_v1_result.png">

 # VLM2Vec
+This repo contains the VLM2Vec-Phi3.5V model checkpoint for [VLM2Vec: Training Vision-Language Models for Massive Multimodal Embedding Tasks](https://arxiv.org/abs/2410.05160). In this paper, we aimed at building a unified multimodal embedding model for any tasks. Our model is based on converting an existing well-trained VLM (Phi-3.5-V) into an embedding model. The basic idea is to add an [EOS] token in the end of the sequence, which will be used as the representation of the multimodal inputs.
 ## Release
 <details>
 <summary> V1 checkpoints </summary>
 - [VLM2Vec-Qwen2VL (7B)](https://huggingface.co/TIGER-Lab/VLM2Vec-Qwen2VL-7B)
 - [VLM2Vec-Qwen2VL (2B)](https://huggingface.co/TIGER-Lab/VLM2Vec-Qwen2VL-2B)
 - [VLM2Vec-LLaVa-Next](https://huggingface.co/TIGER-Lab/VLM2Vec-LLaVa-Next)
 - [VLM2Vec-Phi3.5V](https://huggingface.co/TIGER-Lab/VLM2Vec-Full)
 </details>
+<details>
+<summary> V2 checkpoints </summary>
+- [VLM2Vec-v2.0 (Qwen2VL-2B)](https://huggingface.co/VLM2Vec/VLM2Vec-V2.0)
+</details>
 ### Github
  - [Github](https://github.com/TIGER-AI-Lab/VLM2Vec)
+## Experimental Results
 Our model can outperform the existing baselines by a huge margin.
 <img width="900" alt="abs" src="vlm2vec_v1_result.png">