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

Libraries

How to use Mage-Fans/Mage-VL with Transformers:

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

pipe = pipeline("image-text-to-text", model="Mage-Fans/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)

# Load model directly
from transformers import AutoModelForImageTextToText
model = AutoModelForImageTextToText.from_pretrained("Mage-Fans/Mage-VL", trust_remote_code=True, device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Mage-Fans/Mage-VL with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Mage-Fans/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": "Mage-Fans/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/Mage-Fans/Mage-VL

SGLang

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

Mage-VL / neural_codec /DCVC /src /cpp /setup.py

Mage-Fans

Duplicate from microsoft/Mage-VL

8ad2fa0 3 days ago

Raw

History Blame Contribute Delete

820 Bytes

	# Copyright (c) Microsoft Corporation.
	# Licensed under the MIT License.

	import glob
	import sys
	from setuptools import setup
	from pybind11.setup_helpers import Pybind11Extension, build_ext


	if sys.platform == "win32":
	extra_compile_args = ['/std:c++17', '/O2', '/W4', '/WX', '/wd4100']
	extra_link_args = []
	else:
	extra_compile_args = ['-std=c++17', '-O3', '-fPIC', '-Wall', '-Wextra', '-Werror']
	extra_link_args = []


	setup(
	name="MLCodec_extensions_cpp",
	ext_modules=[
	Pybind11Extension(
	name='MLCodec_extensions_cpp',
	sources=glob.glob('py_rans/*.cpp'),
	extra_compile_args=extra_compile_args,
	extra_link_args=extra_link_args,
	),
	],
	cmdclass={"build_ext": build_ext},
	zip_safe=False,
	python_requires=">=3.12",
	)