Hugging Face's logo Hugging Face
  • Models
  • Datasets
  • Spaces
  • Buckets new
  • Docs
  • Enterprise
  • Pricing
    • Website
      • Tasks
      • HuggingChat
      • Collections
      • Languages
      • Organizations
    • Community
      • Blog
      • Posts
      • Daily Papers
      • Hardware
      • Learn
      • Discord
      • Forum
      • GitHub
    • Solutions
      • Team & Enterprise
      • Hugging Face PRO
      • Enterprise Support
      • Inference Providers
      • Inference Endpoints
      • Storage Buckets

  • Log In
  • Sign Up

microsoft
/
Mage-ViT

Image Feature Extraction
Transformers
Safetensors
mage_vit
feature-extraction
mage-vl
vision-encoder
codec-vit
video-understanding
custom_code
Model card Files Files and versions
xet
Community

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

  • Libraries
  • Transformers

    How to use microsoft/Mage-ViT with Transformers:

    # Use a pipeline as a high-level helper
    from transformers import pipeline
    
    pipe = pipeline("image-feature-extraction", model="microsoft/Mage-ViT", trust_remote_code=True)
    # Load model directly
    from transformers import AutoModel
    model = AutoModel.from_pretrained("microsoft/Mage-ViT", trust_remote_code=True, device_map="auto")
  • Notebooks
  • Google Colab
  • Kaggle
Mage-ViT
631 MB
Ctrl+K
Ctrl+K
  • 1 contributor
History: 2 commits
Xinjie-Q's picture
Xinjie-Q
Upload Mage-ViT: standalone codec-native visual encoder (ViT pre-training only)
28ba2c0 verified about 2 hours ago
  • .gitattributes
    1.52 kB
    initial commit about 9 hours ago
  • README.md
    6.94 kB
    Upload Mage-ViT: standalone codec-native visual encoder (ViT pre-training only) about 2 hours ago
  • __init__.py
    94 Bytes
    Upload Mage-ViT: standalone codec-native visual encoder (ViT pre-training only) about 2 hours ago
  • config.json
    649 Bytes
    Upload Mage-ViT: standalone codec-native visual encoder (ViT pre-training only) about 2 hours ago
  • configuration_mage_vit.py
    4.8 kB
    Upload Mage-ViT: standalone codec-native visual encoder (ViT pre-training only) about 2 hours ago
  • model.safetensors
    631 MB
    xet
    Upload Mage-ViT: standalone codec-native visual encoder (ViT pre-training only) about 2 hours ago
  • modeling_mage_vit.py
    23.4 kB
    Upload Mage-ViT: standalone codec-native visual encoder (ViT pre-training only) about 2 hours ago
  • preprocessor_config.json
    466 Bytes
    Upload Mage-ViT: standalone codec-native visual encoder (ViT pre-training only) about 2 hours ago