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

Libraries

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

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

pipe = pipeline("image-text-to-text", model="rayruiyang/VST-7B-RL")
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-RL")
model = AutoModelForMultimodalLM.from_pretrained("rayruiyang/VST-7B-RL", 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-RL with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "rayruiyang/VST-7B-RL"
# 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-RL",
		"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-RL

SGLang

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

Add pipeline tag and library name to model card

by nielsr HF Staff - opened Nov 11, 2025

base: refs/heads/main

←

from: refs/pr/1

Discussion Files changed

-2

Files changed (1) hide show

README.md +4 -2

README.md CHANGED Viewed

@@ -1,5 +1,7 @@
 ---
 license: apache-2.0
 ---
 # VST-7B-RL
@@ -34,7 +36,7 @@ We introduce **Visual Spatial Tuning (VST)**, a comprehensive framework designed
 ✨ **VST-P**: 4.1M samples across 19 skills, spanning single images, multi-image scenarios, and videos—boosting spatial perception in VLMs.
 ✨ **VST-R**: 135K curated samples that teach models to reason in space, including step-by-step reasoning and rule-based data for reinforcement learning.
 ✨ **Progressive Training Pipeline**: Start with supervised fine-tuning to build foundational spatial knowledge, then reinforce spatial reasoning abilities via RL. VST achieves state-of-the-art results on spatial benchmarks (34.8% on MMSI-Bench, 61.2% on VSIBench) without compromising general capabilities.
-✨ **Vision-Language-Action Models Enhanced**: The VST paradigm significantly strengthens spatial tuning, paving the way for more physically grounded AI.
@@ -149,4 +151,4 @@ If you find our work helpful, feel free to give us a cite.
   journal={arXiv preprint arXiv:2511.05491},
   year={2025}
 }
-```

 ---
 license: apache-2.0
+library_name: transformers
+pipeline_tag: image-text-to-text
 ---
 # VST-7B-RL
 ✨ **VST-P**: 4.1M samples across 19 skills, spanning single images, multi-image scenarios, and videos—boosting spatial perception in VLMs.
 ✨ **VST-R**: 135K curated samples that teach models to reason in space, including step-by-step reasoning and rule-based data for reinforcement learning.
 ✨ **Progressive Training Pipeline**: Start with supervised fine-tuning to build foundational spatial knowledge, then reinforce spatial reasoning abilities via RL. VST achieves state-of-the-art results on spatial benchmarks (34.8% on MMSI-Bench, 61.2% on VSIBench) without compromising general capabilities.
+✨ **Vision-Language-Action Models Enhanced**: The VST paradigm significantly strengthens robotic learning, paving the way for more physically grounded AI.
   journal={arXiv preprint arXiv:2511.05491},
   year={2025}
 }
+```