Instructions to use array/Qwen2.5-VL-SAT with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use array/Qwen2.5-VL-SAT with Transformers:

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

pipe = pipeline("image-text-to-text", model="array/Qwen2.5-VL-SAT", trust_remote_code=True)
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, AutoModelForImageTextToText

processor = AutoProcessor.from_pretrained("array/Qwen2.5-VL-SAT", trust_remote_code=True)
model = AutoModelForImageTextToText.from_pretrained("array/Qwen2.5-VL-SAT", trust_remote_code=True)
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

vLLM

How to use array/Qwen2.5-VL-SAT with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "array/Qwen2.5-VL-SAT"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "array/Qwen2.5-VL-SAT",
		"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/array/Qwen2.5-VL-SAT

SGLang

How to use array/Qwen2.5-VL-SAT 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 "array/Qwen2.5-VL-SAT" \
    --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": "array/Qwen2.5-VL-SAT",
		"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 "array/Qwen2.5-VL-SAT" \
        --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": "array/Qwen2.5-VL-SAT",
		"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 array/Qwen2.5-VL-SAT with Docker Model Runner:
```
docker model run hf.co/array/Qwen2.5-VL-SAT
```

Model Card for Model ID

A strong spatial Qwen 2.5 VL baseline.

Post-trained on SAT, and just the answers from Video-R1. The exact mix is 60% SAT, 40% Video-R1.

News:

Feb 3, 2026: There was a bug with this model where it was producing random outputs for some Transformers packages. It has been fixed, please redownload the model and let us know if you still face this issue.

Get Started

% pip install git+https://github.com/huggingface/transformers accelerate
% pip install qwen-vl-utils[decord]==0.0.8

from transformers import Qwen2_5_VLForConditionalGeneration, AutoProcessor

model = Qwen2_5_VLForConditionalGeneration.from_pretrained("array/Qwen2.5-VL-SAT")
processor = AutoProcessor.from_pretrained(
    exp_confs["model_path"],
    trust_remote_code=model_config.trust_remote_code
)

Please see the paper for details on training and evaluation datasets and metrics.

Results

Model	MV	RelDep	SpRel	Jig	IQT	BLINK Avg	BLINK Reas	SAT-R	VSI Avg	VSI Reas	ERQA	Avg (All)
Qwen2.5-VL (7B)	39.00	61.29	92.38	58.66	25.33	55.33	41.00	59.00	23.96	22.96	38.91	44.30
+ SAT	57.14	87.09	74.12	58.66	30.00	61.40	48.60	71.66	32.40	30.65	38.00	50.87

Citation [optional]

@misc{ray2025satdynamicspatialaptitude,
      title={SAT: Dynamic Spatial Aptitude Training for Multimodal Language Models}, 
      author={Arijit Ray and Jiafei Duan and Ellis Brown and Reuben Tan and Dina Bashkirova and Rose Hendrix and Kiana Ehsani and Aniruddha Kembhavi and Bryan A. Plummer and Ranjay Krishna and Kuo-Hao Zeng and Kate Saenko},
      year={2025},
      eprint={2412.07755},
      archivePrefix={arXiv},
      primaryClass={cs.CV},
      url={https://arxiv.org/abs/2412.07755}, 
    }

Downloads last month: 98

Safetensors

Model size

8B params

Tensor type

BF16

Model tree for array/Qwen2.5-VL-SAT

Base model

Qwen/Qwen2.5-VL-7B-Instruct

Finetuned

(1063)

this model

Datasets used to train array/Qwen2.5-VL-SAT

Paper for array/Qwen2.5-VL-SAT

SAT: Dynamic Spatial Aptitude Training for Multimodal Language Models

Paper • 2412.07755 • Published Dec 10, 2024 • 3