Instructions to use YongchengYAO/MedVisionSFT-mqwen25vl-7b__TL with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use YongchengYAO/MedVision__SFT-m__qwen25vl-7b__TL with Transformers:

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

pipe = pipeline("image-text-to-text", model="YongchengYAO/MedVision__SFT-m__qwen25vl-7b__TL")
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("YongchengYAO/MedVision__SFT-m__qwen25vl-7b__TL")
model = AutoModelForImageTextToText.from_pretrained("YongchengYAO/MedVision__SFT-m__qwen25vl-7b__TL")
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 YongchengYAO/MedVision__SFT-m__qwen25vl-7b__TL with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "YongchengYAO/MedVision__SFT-m__qwen25vl-7b__TL"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "YongchengYAO/MedVision__SFT-m__qwen25vl-7b__TL",
		"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/YongchengYAO/MedVision__SFT-m__qwen25vl-7b__TL

SGLang

How to use YongchengYAO/MedVision__SFT-m__qwen25vl-7b__TL 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 "YongchengYAO/MedVision__SFT-m__qwen25vl-7b__TL" \
    --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": "YongchengYAO/MedVision__SFT-m__qwen25vl-7b__TL",
		"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 "YongchengYAO/MedVision__SFT-m__qwen25vl-7b__TL" \
        --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": "YongchengYAO/MedVision__SFT-m__qwen25vl-7b__TL",
		"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 YongchengYAO/MedVision__SFT-m__qwen25vl-7b__TL with Docker Model Runner:
```
docker model run hf.co/YongchengYAO/MedVision__SFT-m__qwen25vl-7b__TL
```

Model Card for Model ID

This is a supervised finetuned version of Qwen/Qwen2.5-VL-7B-Instruct.

Model Details

Model Description

License: CC-BY-NC-4.0
Finetuned from model: Qwen/Qwen2.5-VL-7B-Instruct

Uses

Direct use: check Qwen/Qwen2.5-VL-7B-Instruct
The model is evaluated in the MedVision benchmark

Training Details

Training Data

The model is trained on the MedVision dataset. Specifically, this list defines the training data.

Training Procedure

🌟 Blog: Supervised Fine-Tuning (SFT) for VLMs on Medical Image Data
🧑🏻‍💻 Script: the training script handles dependencies installation, data processing, and SFT training.

Evaluation

See the tumor/lesion (T/L) size estimation results for Qwen2.5VL (7B, SFT_{5K}) on the MedVision project page.

Citation

@misc{yao2025medvisiondatasetbenchmarkquantitative,
      title={MedVision: Dataset and Benchmark for Quantitative Medical Image Analysis}, 
      author={Yongcheng Yao and Yongshuo Zong and Raman Dutt and Yongxin Yang and Sotirios A Tsaftaris and Timothy Hospedales},
      year={2025},
      eprint={2511.18676},
      archivePrefix={arXiv},
      primaryClass={cs.CV},
      url={https://arxiv.org/abs/2511.18676}, 
}

Downloads last month: 5

Safetensors

Model size

8B params

Tensor type

BF16

Model tree for YongchengYAO/MedVisionSFT-mqwen25vl-7b__TL

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

Merge model

this model

Dataset used to train YongchengYAO/MedVisionSFT-mqwen25vl-7b__TL

Collection including YongchengYAO/MedVisionSFT-mqwen25vl-7b__TL

MedVision-SFT-Models

Collection

The collection of merged SFT models in [MedVision](https://medvision-vlm.github.io). • 6 items • Updated Apr 9 • 1

Paper for YongchengYAO/MedVisionSFT-mqwen25vl-7b__TL

MedVision: Dataset and Benchmark for Quantitative Medical Image Analysis

Paper • 2511.18676 • Published Nov 24, 2025 • 1