Instructions to use rayruiyang/VST-7B-SFT with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use rayruiyang/VST-7B-SFT with Transformers:

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

pipe = pipeline("image-text-to-text", model="rayruiyang/VST-7B-SFT")
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, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("rayruiyang/VST-7B-SFT")
model = AutoModelForMultimodalLM.from_pretrained("rayruiyang/VST-7B-SFT", device_map="auto")
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 Settings

vLLM

How to use rayruiyang/VST-7B-SFT with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "rayruiyang/VST-7B-SFT"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "rayruiyang/VST-7B-SFT",
		"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/rayruiyang/VST-7B-SFT

SGLang

How to use rayruiyang/VST-7B-SFT 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 "rayruiyang/VST-7B-SFT" \
    --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": "rayruiyang/VST-7B-SFT",
		"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 "rayruiyang/VST-7B-SFT" \
        --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": "rayruiyang/VST-7B-SFT",
		"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 rayruiyang/VST-7B-SFT with Docker Model Runner:
```
docker model run hf.co/rayruiyang/VST-7B-SFT
```

Improve VST-7B-SFT model card with metadata, paper link, and usage clarity

by nielsr HF Staff - opened Nov 11, 2025

base: refs/heads/main

←

from: refs/pr/1

Discussion Files changed

-3

nielsr

Nov 11, 2025

This PR enhances the model card by adding key metadata and improving its clarity and discoverability:

pipeline_tag: image-text-to-text: This tag accurately reflects the model's functionality of processing visual (image/video) and text inputs to generate text. It will help users find this model when searching for multimodal models.
library_name: transformers: The inclusion of transformers as the library_name ensures that users are provided with an automated, functional code snippet on the model page, facilitating easier adoption. Evidence for compatibility is found in config.json, tokenizer_config.json, and the provided code snippet.
Hugging Face Paper Link: Added a direct link to the Hugging Face paper page, complementing the existing arXiv link and improving the discoverability of the research on the platform.
Improved Title: The model card title has been updated to # VST-7B-SFT: Visual Spatial Tuning for better clarity.
"Sample Usage" Section: The "Quickstart" section has been renamed to "Sample Usage" and includes a clearer introduction for installing dependencies. The provided code snippet has been retained as it correctly targets VST-7B-SFT.

These updates will make the model more accessible and easier to use for the community.

Improve VST-7B-SFT model card with metadata, paper link, and usage clarity74e9de27

rayruiyang changed pull request status to merged Nov 11, 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