Instructions to use lingshu-medical-mllm/Lingshu-32B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use lingshu-medical-mllm/Lingshu-32B with Transformers:

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

pipe = pipeline("image-text-to-text", model="lingshu-medical-mllm/Lingshu-32B")
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("lingshu-medical-mllm/Lingshu-32B")
model = AutoModelForMultimodalLM.from_pretrained("lingshu-medical-mllm/Lingshu-32B", 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]:]))

Inference
Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use lingshu-medical-mllm/Lingshu-32B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "lingshu-medical-mllm/Lingshu-32B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "lingshu-medical-mllm/Lingshu-32B",
		"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/lingshu-medical-mllm/Lingshu-32B

SGLang

How to use lingshu-medical-mllm/Lingshu-32B 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 "lingshu-medical-mllm/Lingshu-32B" \
    --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": "lingshu-medical-mllm/Lingshu-32B",
		"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 "lingshu-medical-mllm/Lingshu-32B" \
        --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": "lingshu-medical-mllm/Lingshu-32B",
		"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 lingshu-medical-mllm/Lingshu-32B with Docker Model Runner:
```
docker model run hf.co/lingshu-medical-mllm/Lingshu-32B
```

26hzhang commited on Jun 10, 2025

Commit

1ecf84d

verified ·

1 Parent(s): e71b439

Update README.md

Browse files

Files changed (1) hide show

README.md +42 -2

README.md CHANGED Viewed

@@ -104,6 +104,17 @@ tags:
       <td>43.3</td>
       <td>61.5</td>
     </tr>
     <tr>
       <td colspan="9" style="text-align:center;"><strong>Open-source Models (&lt;10B)</strong></td>
     </tr>
@@ -365,6 +376,17 @@ tags:
       <td>56.3</td>
       <td>73.1</td>
     </tr>
     <tr>
       <td colspan="9" style="text-align:center;"><strong>Open-source Models (&lt;10B)</strong></td>
     </tr>
@@ -642,6 +664,24 @@ tags:
       <td>41.0</td>
       <td>72.1</td>
     </tr>
     <tr>
       <td colspan="16" style="text-align:center;"><strong>Open-source Models (&lt;10B)</strong></td>
     </tr>
@@ -1088,7 +1128,7 @@ If you find our project useful, we hope you would kindly star our repo and cite
 * `*` are equal contributions.  `^` are corresponding authors.
 ```
-@misc{lasateam2025lingshugeneralistfoundationmodel,
       title={Lingshu: A Generalist Foundation Model for Unified Multimodal Medical Understanding and Reasoning},
       author={LASA Team and Weiwen Xu* and Hou Pong Chan* and Long Li* and Mahani Aljunied and Ruifeng Yuan and Jianyu Wang and Chenghao Xiao and Guizhen Chen and Chaoqun Liu and Zhaodonghui Li and Yu Sun and Junao Shen and Chaojun Wang and Jie Tan and Deli Zhao and Tingyang Xu and Hao Zhang^ and Yu Rong^},
       year={2025},
@@ -1097,4 +1137,4 @@ If you find our project useful, we hope you would kindly star our repo and cite
       primaryClass={cs.CL},
       url={https://arxiv.org/abs/2506.07044},
 }
-```

       <td>43.3</td>
       <td>61.5</td>
     </tr>
+    <tr>
+      <td>Gemini-2.5-Flash</td>
+      <td>76.9</td>
+      <td>68.5</td>
+      <td>75.8</td>
+      <td>55.4</td>
+      <td>55.4</td>
+      <td>71.0</td>
+      <td>52.8</td>
+      <td>65.1</td>
+    </tr>
     <tr>
       <td colspan="9" style="text-align:center;"><strong>Open-source Models (&lt;10B)</strong></td>
     </tr>
       <td>56.3</td>
       <td>73.1</td>
     </tr>
+    <tr>
+      <td>Gemini-2.5-Flash</td>
+      <td>84.2</td>
+      <td>73.8</td>
+      <td>73.6</td>
+      <td>91.2</td>
+      <td>77.6</td>
+      <td>35.6</td>
+      <td>53.3</td>
+      <td>69.9</td>
+    </tr>
     <tr>
       <td colspan="9" style="text-align:center;"><strong>Open-source Models (&lt;10B)</strong></td>
     </tr>
       <td>41.0</td>
       <td>72.1</td>
     </tr>
+    <tr>
+      <td>Gemini-2.5-Flash</td>
+      <td>25.4</td>
+      <td>80.7</td>
+      <td>50.3</td>
+      <td>29.7</td>
+      <td>59.4</td>
+      <td>23.6</td>
+      <td>72.2</td>
+      <td>44.3</td>
+      <td>27.4</td>
+      <td>44.0</td>
+      <td>33.5</td>
+      <td>129.3</td>
+      <td>55.6</td>
+      <td>50.9</td>
+      <td>91.6</td>
+    </tr>
     <tr>
       <td colspan="16" style="text-align:center;"><strong>Open-source Models (&lt;10B)</strong></td>
     </tr>
 * `*` are equal contributions.  `^` are corresponding authors.
 ```
+@misc{lasateam2025lingshu,
       title={Lingshu: A Generalist Foundation Model for Unified Multimodal Medical Understanding and Reasoning},
       author={LASA Team and Weiwen Xu* and Hou Pong Chan* and Long Li* and Mahani Aljunied and Ruifeng Yuan and Jianyu Wang and Chenghao Xiao and Guizhen Chen and Chaoqun Liu and Zhaodonghui Li and Yu Sun and Junao Shen and Chaojun Wang and Jie Tan and Deli Zhao and Tingyang Xu and Hao Zhang^ and Yu Rong^},
       year={2025},
       primaryClass={cs.CL},
       url={https://arxiv.org/abs/2506.07044},
 }
+```