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

kevin-pek
/
nougat-api

Image-to-Text
Transformers
PyTorch
vision-encoder-decoder
image-text-to-text
vision
nougat
Model card Files Files and versions
xet
Community
1

Instructions to use kevin-pek/nougat-api with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

  • Libraries
  • Transformers

    How to use kevin-pek/nougat-api 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="kevin-pek/nougat-api")
    # Load model directly
    from transformers import AutoTokenizer, AutoModelForImageTextToText
    
    tokenizer = AutoTokenizer.from_pretrained("kevin-pek/nougat-api")
    model = AutoModelForImageTextToText.from_pretrained("kevin-pek/nougat-api")
  • Notebooks
  • Google Colab
  • Kaggle
nougat-api
1.4 GB
Ctrl+K
Ctrl+K
  • 2 contributors
History: 11 commits
kevin-pek
test without postprocessing
835c1c9 over 2 years ago
  • .gitattributes
    1.52 kB
    initial commit over 2 years ago
  • README.md
    2.29 kB
    add stopping criteria for inference over 2 years ago
  • config.json
    4.77 kB
    replace NougatProcessor with AutoProcessor over 2 years ago
  • generation_config.json
    165 Bytes
    add custom handler.py and upload files over 2 years ago
  • handler.py
    3.43 kB
    test without postprocessing over 2 years ago
  • preprocessor_config.json
    479 Bytes
    try using NougatProcessor using custom transformer version over 2 years ago
  • pytorch_model.bin

    Detected Pickle imports (4)

    • "torch.LongStorage",
    • "torch._utils._rebuild_tensor_v2",
    • "torch.FloatStorage",
    • "collections.OrderedDict"

    What is a pickle import?

    1.4 GB
    xet
    add custom handler.py and upload files over 2 years ago
  • requirements.txt
    485 Bytes
    add requirements.txt over 2 years ago
  • special_tokens_map.json
    96 Bytes
    add custom handler.py and upload files over 2 years ago
  • tokenizer.json
    2.14 MB
    add custom handler.py and upload files over 2 years ago
  • tokenizer_config.json
    4.49 kB
    try using NougatProcessor using custom transformer version over 2 years ago