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)

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

Notebooks
Google Colab
Kaggle
Local Apps Settings

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
```

VLM2Vec-Full

Commit History

Oct 16, 2024

11:20
Adding `safetensors` variant of this model⁠

SFconvertbot

Verified signature
ddeccb6

Oct 14, 2024

16:13
Update README.md

wenhu

Verified signature
c326e8a

Oct 11, 2024

04:46
Update README.md

wenhu

Verified signature
6a18731
02:26
Create README.md

wenhu

Verified signature
c383d89

Oct 10, 2024

04:31
Update processing_phi3_v.py

wenhu

Verified signature
bf0c5a7
04:29
Update processing_phi3_v.py

wenhu

Verified signature
fb30ad8
00:53
Upload 3 files

wenhu

Verified signature
e597f74
00:38
Upload 3 files

wenhu

Verified signature
0c889af

Oct 9, 2024

21:15
Update config.json

memray

Verified signature
d7edfca

Oct 8, 2024

05:44
Upload folder using huggingface_hub

memray

Verified signature
6f0ed3a
04:57
initial commit

memray

Verified signature
1be1ba9

Commit History

Oct 16, 2024

Adding `safetensors` variant of this model⁠

Oct 14, 2024

Update README.md

Oct 11, 2024

Update README.md

Create README.md

Oct 10, 2024

Update processing_phi3_v.py

Update processing_phi3_v.py

Upload 3 files

Upload 3 files

Oct 9, 2024

Update config.json

Oct 8, 2024

Upload folder using huggingface_hub

initial commit