Instructions to use katanaml/donut-demo with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use katanaml/donut-demo 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="katanaml/donut-demo")# Load model directly from transformers import AutoTokenizer, AutoModelForImageTextToText tokenizer = AutoTokenizer.from_pretrained("katanaml/donut-demo") model = AutoModelForImageTextToText.from_pretrained("katanaml/donut-demo") - Notebooks
- Google Colab
- Kaggle
sparrow_key
#2
by cindyliang - opened
hi, where I can get a sparrow_key?
It's required to make inference api call to https://katanaml-org-sparrow-ml.hf.space/api-inference/v1/sparrow-ml/inference
you should deploy backed on your infra and then you can set any value for sparrow_key, it is used to authorize backend calls
katanaml changed discussion status to closed