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
      • Learn
      • Discord
      • Forum
      • GitHub
    • Solutions
      • Team & Enterprise
      • Hugging Face PRO
      • Enterprise Support
      • Inference Providers
      • Inference Endpoints
      • Storage Buckets

  • Log In
  • Sign Up

XAFT
/
SM-Selective-ViT-Base-224-Distilled

Image Classification
Transformers
Safetensors
softmasked_selective_vit
vision-transformer
efficient-transformer
selective-attention
knowledge-distillation
computer-vision
custom_code
Model card Files Files and versions
xet
Community

Instructions to use XAFT/SM-Selective-ViT-Base-224-Distilled with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

  • Libraries
  • Transformers

    How to use XAFT/SM-Selective-ViT-Base-224-Distilled with Transformers:

    # Use a pipeline as a high-level helper
    from transformers import pipeline
    
    pipe = pipeline("image-classification", model="XAFT/SM-Selective-ViT-Base-224-Distilled", trust_remote_code=True)
    pipe("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/hub/parrots.png")
    # Load model directly
    from transformers import AutoModelForImageClassification
    model = AutoModelForImageClassification.from_pretrained("XAFT/SM-Selective-ViT-Base-224-Distilled", trust_remote_code=True, dtype="auto")
  • Notebooks
  • Google Colab
  • Kaggle
SM-Selective-ViT-Base-224-Distilled
350 MB
Ctrl+K
Ctrl+K
  • 1 contributor
History: 6 commits
XAFT's picture
XAFT
Add citation
6ff0766 verified about 2 months ago
  • .gitattributes
    219 Bytes
    Upload model files 4 months ago
  • README.md
    4.45 kB
    Add citation about 2 months ago
  • __init__.py
    220 Bytes
    Upload model files 4 months ago
  • config.json
    678 Bytes
    Add support for FlashAttention 4 months ago
  • configuration_selectivevit.py
    1.24 kB
    Upload model files 4 months ago
  • model.safetensors
    349 MB
    xet
    Upload model files 4 months ago
  • modeling_selectivevit.py
    2.82 kB
    Add support for FlashAttention 4 months ago
  • preprocessor_config.json
    365 Bytes
    Made sure to use smallest-edge resize 4 months ago
  • selective_vit.py
    21.5 kB
    Update implementation about 2 months ago