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

mdnaseif
/
hafith

Image-to-Text
Transformers
PyTorch
Arabic
optical-character-recognition
historical-manuscripts
arabic
vision-language
document-ai
Model card Files Files and versions
xet
Community

Instructions to use mdnaseif/hafith with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

  • Libraries
  • Transformers

    How to use mdnaseif/hafith with Transformers:

    # Use a pipeline as a high-level helper
    # Warning: Pipeline type "image-to-text" is no longer supported in transformers v5.
    # You must load the model directly (see below) or downgrade to v4.x with:
    # 'pip install "transformers<5.0.0'
    from transformers import pipeline
    
    pipe = pipeline("image-to-text", model="mdnaseif/hafith")
    # Load model directly
    from transformers import AutoModel
    model = AutoModel.from_pretrained("mdnaseif/hafith", dtype="auto")
  • Notebooks
  • Google Colab
  • Kaggle
hafith / siglip_processor
38.6 MB
Ctrl+K
Ctrl+K
  • 1 contributor
History: 1 commit
mdnaseif's picture
mdnaseif
Initial model upload
12788cd verified 3 months ago
  • preprocessor_config.json
    659 Bytes
    Initial model upload 3 months ago
  • special_tokens_map.json
    636 Bytes
    Initial model upload 3 months ago
  • tokenizer.json
    34.4 MB
    xet
    Initial model upload 3 months ago
  • tokenizer.model
    4.24 MB
    xet
    Initial model upload 3 months ago
  • tokenizer_config.json
    40.3 kB
    Initial model upload 3 months ago