Instructions to use Charlie019/CourtSI-Qwen3-VL-8B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Charlie019/CourtSI-Qwen3-VL-8B with Transformers:

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

pipe = pipeline("image-text-to-text", model="Charlie019/CourtSI-Qwen3-VL-8B")
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 AutoModel
model = AutoModel.from_pretrained("Charlie019/CourtSI-Qwen3-VL-8B", dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use Charlie019/CourtSI-Qwen3-VL-8B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Charlie019/CourtSI-Qwen3-VL-8B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Charlie019/CourtSI-Qwen3-VL-8B",
		"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/Charlie019/CourtSI-Qwen3-VL-8B

SGLang

How to use Charlie019/CourtSI-Qwen3-VL-8B 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 "Charlie019/CourtSI-Qwen3-VL-8B" \
    --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": "Charlie019/CourtSI-Qwen3-VL-8B",
		"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 "Charlie019/CourtSI-Qwen3-VL-8B" \
        --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": "Charlie019/CourtSI-Qwen3-VL-8B",
		"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 Charlie019/CourtSI-Qwen3-VL-8B with Docker Model Runner:
```
docker model run hf.co/Charlie019/CourtSI-Qwen3-VL-8B
```

Configuration Parsing Warning:Config file config.json cannot be fetched (too big)

Configuration Parsing Warning:Config file tokenizer_config.json cannot be fetched (too big)

Stepping VLMs onto the Court: Benchmarking Spatial Intelligence in Sports

Abstract

Sports have long attracted broad attention as they push the limits of human physical and cognitive capabilities. Amid growing interest in spatial intelligence for vision-language models (VLMs), sports provide a natural testbed for understanding high-intensity human motion and dynamic object interactions. To this end, we present CourtSI, the first large-scale spatial intelligence dataset tailored to sports scenarios. CourtSI contains over 1M QA pairs, organized under a holistic taxonomy that systematically covers spatial counting, distance measurement, localization, and relational reasoning, across representative net sports including badminton, tennis, and table tennis. Leveraging well-defined court geometry as metric anchors, we develop a semi-automatic data engine to reconstruct sports scenes, enabling scalable curation of CourtSI. In addition, we introduce CourtSI-Bench, a high-quality evaluation benchmark comprising 3,686 QA pairs with rigorous human verification. We evaluate 25 proprietary and open-source VLMs on CourtSI-Bench, revealing a remaining human–AI performance gap and limited generalization from existing spatial intelligence benchmarks. These findings indicate that sports scenarios expose limitations in spatial intelligence capabilities captured by existing benchmarks. Further, fine-tuning Qwen3-VL-8B on CourtSI improves accuracy on CourtSI-Bench by 23.5 percentage points. The adapted model also generalizes effectively to CourtSI-Ext, an evaluation set built on a similar but unseen sport, and demonstrates enhanced spatial-aware commentary generation. Together, these findings demonstrate that CourtSI provides a scalable pathway toward advancing spatial intelligence of VLMs in sports.

CourtSI-Qwen3-VL-8B

CourtSI-Qwen3-VL-8B is a vision-language model obtained by supervised fine-tuning (SFT) the Qwen3-VL-8B model on the CourtSI dataset.

By learning from large-scale spatially grounded QA pairs in sports environments, the model acquires stronger spatial reasoning capabilities, gaining 23.5% absolute improvement on CourtSI-Bench.

Downloads last month: 8

Safetensors

Model size

770k params

Tensor type

F32

Model tree for Charlie019/CourtSI-Qwen3-VL-8B

Base model

Qwen/Qwen3-VL-8B-Instruct

Finetuned

(278)

this model

Paper for Charlie019/CourtSI-Qwen3-VL-8B

Stepping VLMs onto the Court: Benchmarking Spatial Intelligence in Sports

Paper • 2603.09896 • Published Mar 10 • 28