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

laion
/
CLIP-ViT-B-32-laion2B-s34B-b79K

Zero-Shot Image Classification
OpenCLIP
PyTorch
Safetensors
clip
Model card Files Files and versions
xet
Community
8

Instructions to use laion/CLIP-ViT-B-32-laion2B-s34B-b79K with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

  • Libraries
  • OpenCLIP

    How to use laion/CLIP-ViT-B-32-laion2B-s34B-b79K with OpenCLIP:

    import open_clip
    
    model, preprocess_train, preprocess_val = open_clip.create_model_and_transforms('hf-hub:laion/CLIP-ViT-B-32-laion2B-s34B-b79K')
    tokenizer = open_clip.get_tokenizer('hf-hub:laion/CLIP-ViT-B-32-laion2B-s34B-b79K')
  • Notebooks
  • Google Colab
  • Kaggle
New discussion
Resources
  • PR & discussions documentation
  • Code of Conduct
  • Hub documentation

本地测试

#14 opened about 2 months ago by
gitwiki

[AUTOMATED] Model Memory Requirements

#7 opened almost 2 years ago by
model-sizer-bot

Easy evaluation of the zero-shot capabilities of laion CLIP

2
#6 opened about 2 years ago by
fhvilshoj

How to use the tokenizer? Is the tokenizer same as the original CLIP?

👍 1
2
#2 opened over 3 years ago by
ir1d
Company
TOS Privacy About Careers
Website
Models Datasets Spaces Pricing Docs