Instructions to use microsoft/Mage-VL with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use microsoft/Mage-VL with Transformers:

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

pipe = pipeline("image-text-to-text", model="microsoft/Mage-VL", trust_remote_code=True)
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)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoModelForImageTextToText
model = AutoModelForImageTextToText.from_pretrained("microsoft/Mage-VL", trust_remote_code=True, device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use microsoft/Mage-VL with vLLM:

Install from pip and serve model

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

SGLang

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

Xinjie-Q commited on Jul 27

Commit

8484f31

verified ·

1 Parent(s): 64e9df0

Restore data-efficient tokenizer finding (560M images)

Browse files

Files changed (1) hide show

README.md +9 -8

README.md CHANGED Viewed

@@ -185,14 +185,15 @@ JoyAI's high TriggerAcc comes from predicting silence almost everywhere under So
 ## 🔬 Key Findings
-Beyond the model, the report distills **six empirical findings** for efficient multimodal training:
-1. **Variable-resolution pretraining scales monotonically.** Quality keeps improving with the visual-token budget instead of saturating/degrading like fixed-resolution encoders.
-2. **Codec-native tokenization sets a better accuracy–efficiency frontier** — up to **3.5× wall-clock inference speedup** over uniform frame sampling.
-3. **Explicit VideoQA SFT is redundant.** Dense video *captions* + standard image SFT are sufficient for strong zero-shot VideoQA.
-4. **Motion–spatial synergy.** Dynamic video training substantially improves static 2D/3D spatial reasoning.
-5. **AI4AI data pipeline.** Agentic closed-loop feedback + prompt/code co-design systematically lift caption quality and downstream scores (inspired SkillOpt-Lite).
-6. **Zero-Vision SFT for multimodal RL.** Bypassing visual SFT in favor of pure-text reasoning SFT unlocks stronger multimodal RL — a compute-efficient path.
 ## 🚀 Quick Start

 ## 🔬 Key Findings
+Beyond the model, the report distills **seven empirical findings** for efficient multimodal training:
+1. **Data-efficient tokenizer.** Mage-ViT trains on only **560M unlabeled images + 100M video frames**, yet matches SigLIP2 pretrained on billions of image-text pairs.
+2. **Variable-resolution pretraining scales monotonically.** Quality keeps improving with the visual-token budget instead of saturating/degrading like fixed-resolution encoders.
+3. **Codec-native tokenization sets a better accuracy–efficiency frontier** — up to **3.5× wall-clock inference speedup** over uniform frame sampling.
+4. **Explicit VideoQA SFT is redundant.** Dense video *captions* + standard image SFT are sufficient for strong zero-shot VideoQA.
+5. **Motion–spatial synergy.** Dynamic video training substantially improves static 2D/3D spatial reasoning.
+6. **AI4AI data pipeline.** Agentic closed-loop feedback + prompt/code co-design systematically lift caption quality and downstream scores (inspired SkillOpt-Lite).
+7. **Zero-Vision SFT for multimodal RL.** Bypassing visual SFT in favor of pure-text reasoning SFT unlocks stronger multimodal RL — a compute-efficient path.
 ## 🚀 Quick Start