Instructions to use jcwang0602/VPTracker with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use jcwang0602/VPTracker with Transformers:

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

pipe = pipeline("image-text-to-text", model="jcwang0602/VPTracker")
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("jcwang0602/VPTracker")
model = AutoModelForMultimodalLM.from_pretrained("jcwang0602/VPTracker")
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 jcwang0602/VPTracker with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "jcwang0602/VPTracker"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "jcwang0602/VPTracker",
		"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/jcwang0602/VPTracker

SGLang

How to use jcwang0602/VPTracker 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 "jcwang0602/VPTracker" \
    --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": "jcwang0602/VPTracker",
		"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 "jcwang0602/VPTracker" \
        --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": "jcwang0602/VPTracker",
		"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 jcwang0602/VPTracker with Docker Model Runner:
```
docker model run hf.co/jcwang0602/VPTracker
```

Improve model card and add metadata

by nielsr HF Staff - opened Dec 30, 2025

base: refs/heads/main

←

from: refs/pr/1

Discussion Files changed

+22

-6

Files changed (1) hide show

README.md +22 -6

README.md CHANGED Viewed

@@ -1,6 +1,24 @@
 # VPTracker: Global Vision-Language Tracking via Visual Prompt and MLLM
-[![arXiv](https://img.shields.io/badge/Arxiv-2508.04107-b31b1b.svg?logo=arXiv)](https://arxiv.org/abs/2512.22799)
 [![Python](https://img.shields.io/badge/Python-3.9-blue.svg)](https://www.python.org/downloads/)
 [![PyTorch](https://img.shields.io/badge/PyTorch-2.5.1-red.svg)](https://pytorch.org/)
 [![Transformers](https://img.shields.io/badge/Transformers-4.37.2-green.svg)](https://huggingface.co/docs/transformers/)
@@ -31,24 +49,22 @@ pip install flash-attn==2.7.4.post1 --no-build-isolation
 conda install av -c conda-forge
 pip install qwen_vl_utils qwen_omni_utils decord librosa icecream soundfile -U
 pip install liger_kernel nvitop pre-commit math_verify py-spy -U
 ```
 <!-- ## 👀 Visualization
 <img src="assets/Results.jpg" width="800"> -->
 ## 🙏 Acknowledgments
-This code is developed on the top of [ms-swift](https://github.com/modelscope/ms-swift)
 ## ✉️ Contact
 Email: jcwang@stu.ecnu.edu.cn. Any kind discussions are welcomed!
 ---
 ## 📖 Citation
-If our work is useful for your research, please consider cite:
-```
 @misc{wang2025vptrackerglobalvisionlanguagetracking,
       title={VPTracker: Global Vision-Language Tracking via Visual Prompt and MLLM},
       author={Jingchao Wang and Kaiwen Zhou and Zhijian Wu and Kunhua Ji and Dingjiang Huang and Yefeng Zheng},

+---
+pipeline_tag: image-text-to-text
+library_name: transformers
+base_model: Qwen/Qwen3-VL-4B-Instruct
+tags:
+- vision-language-tracking
+- multimodal
+- mllm
+- video
+---
 # VPTracker: Global Vision-Language Tracking via Visual Prompt and MLLM
+This repository contains the weights for **VPTracker**, the first global tracking framework based on Multimodal Large Language Models (MLLMs).
+VPTracker exploits the powerful semantic reasoning of MLLMs to locate targets across the entire image space. To address distractions from visually or semantically similar objects during global search, it introduces a location-aware visual prompting mechanism that incorporates spatial priors.
+- **Paper:** [VPTracker: Global Vision-Language Tracking via Visual Prompt and MLLM](https://huggingface.co/papers/2512.22799)
+- **Repository:** [GitHub - jcwang0602/VPTracker](https://github.com/jcwang0602/VPTracker)
+[![arXiv](https://img.shields.io/badge/Arxiv-2512.22799-b31b1b.svg?logo=arXiv)](https://arxiv.org/abs/2512.22799)
 [![Python](https://img.shields.io/badge/Python-3.9-blue.svg)](https://www.python.org/downloads/)
 [![PyTorch](https://img.shields.io/badge/PyTorch-2.5.1-red.svg)](https://pytorch.org/)
 [![Transformers](https://img.shields.io/badge/Transformers-4.37.2-green.svg)](https://huggingface.co/docs/transformers/)
 conda install av -c conda-forge
 pip install qwen_vl_utils qwen_omni_utils decord librosa icecream soundfile -U
 pip install liger_kernel nvitop pre-commit math_verify py-spy -U
 ```
 <!-- ## 👀 Visualization
 <img src="assets/Results.jpg" width="800"> -->
 ## 🙏 Acknowledgments
+This code is developed on top of [ms-swift](https://github.com/modelscope/ms-swift).
 ## ✉️ Contact
 Email: jcwang@stu.ecnu.edu.cn. Any kind discussions are welcomed!
 ---
 ## 📖 Citation
+If our work is useful for your research, please consider citing:
+```bibtex
 @misc{wang2025vptrackerglobalvisionlanguagetracking,
       title={VPTracker: Global Vision-Language Tracking via Visual Prompt and MLLM},
       author={Jingchao Wang and Kaiwen Zhou and Zhijian Wu and Kunhua Ji and Dingjiang Huang and Yefeng Zheng},