Instructions to use sais-org/MKB with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use sais-org/MKB with Transformers:

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

pipe = pipeline("image-text-to-text", model="sais-org/MKB")
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("sais-org/MKB")
model = AutoModelForMultimodalLM.from_pretrained("sais-org/MKB", 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]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use sais-org/MKB with vLLM:

Install from pip and serve model

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

SGLang

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

Descartes commited on 4 days ago

Commit

658926b

1 Parent(s): 8890816

Update technical report link and citation

Browse files

Files changed (1) hide show

README.md +10 -7

README.md CHANGED Viewed

@@ -25,7 +25,7 @@ extra_gated_description: >-
 <div align="center">
-[🤗 Model](https://huggingface.co/sais-org/MKB) &nbsp;•&nbsp; [💻 GitHub](https://github.com/Shanghai-Academy-of-AI-For-Science/MKB) &nbsp;•&nbsp; [📜 Technical Report](https://github.com/Shanghai-Academy-of-AI-For-Science/MKB/blob/main/docs/MKB.pdf) &nbsp;•&nbsp; [⚖️ License: Apache-2.0 + SAM License](https://github.com/Shanghai-Academy-of-AI-For-Science/MKB/blob/main/LICENSE)
 </div>
@@ -39,7 +39,7 @@ total), so heterogeneous scientific data (sequences, molecular graphs, gridded
 physical fields, medical images) are reasoned about and generated in one
 representation space — natural language in and out, no per-task fine-tuning.
-> 📜 Read the **[technical report](https://github.com/Shanghai-Academy-of-AI-For-Science/MKB/blob/main/docs/MKB.pdf)** for architecture, training, and full benchmarks.
 ## Key features
@@ -173,10 +173,13 @@ See `THIRD_PARTY_LICENSES.md` / `NOTICE` for the full third-party breakdown.
 ## Citation
 ```bibtex
-@misc{mkb2026,
-  title  = {MonkeyKing Bang: A Unified Scientific Multimodal Foundation Model},
-  author = {Hesen Chen and Xinyu Su and Xiaomeng Yang and Yuetan Lin and Zixiong Yang and Zhiyu Tan and Hao Li},
-  year   = {2026},
-  note   = {https://huggingface.co/sais-org/MKB}
 }
 ```

 <div align="center">
+[🤗 Model](https://huggingface.co/sais-org/MKB) &nbsp;•&nbsp; [💻 GitHub](https://github.com/Shanghai-Academy-of-AI-For-Science/MKB) &nbsp;•&nbsp; [📜 Technical Report](https://arxiv.org/pdf/2607.20557) &nbsp;•&nbsp; [⚖️ License: Apache-2.0 + SAM License](https://github.com/Shanghai-Academy-of-AI-For-Science/MKB/blob/main/LICENSE)
 </div>
 physical fields, medical images) are reasoned about and generated in one
 representation space — natural language in and out, no per-task fine-tuning.
+> 📜 Read the **[technical report](https://arxiv.org/pdf/2607.20557)** for architecture, training, and full benchmarks.
 ## Key features
 ## Citation
 ```bibtex
+@misc{chen2026monkeykingbangunified,
+  title         = {Monkey King Bang: A Unified Scientific Multimodal Foundation Model},
+  author        = {Hesen Chen and Xinyu Su and Xiaomeng Yang and Yuetan Lin and Zixiong Yang and Junyi An and Fenglei Cao and Yifeng Jiao and Yunqi Zhang and Yuan Cheng and Zhiyu Tan and Hao Li and Libo Wu and Yuan Qi},
+  year          = {2026},
+  eprint        = {2607.20557},
+  archivePrefix = {arXiv},
+  primaryClass  = {cs.LG},
+  url           = {https://arxiv.org/abs/2607.20557}
 }
 ```