Instructions to use google/pix2struct-widget-captioning-base with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use google/pix2struct-widget-captioning-base with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("visual-question-answering", model="google/pix2struct-widget-captioning-base")# Load model directly from transformers import AutoProcessor, AutoModelForImageTextToText processor = AutoProcessor.from_pretrained("google/pix2struct-widget-captioning-base") model = AutoModelForImageTextToText.from_pretrained("google/pix2struct-widget-captioning-base") - Notebooks
- Google Colab
- Kaggle
The model_type 'pix2struct' is not recognized. It could be a bleeding edge model, or incorrect
#1
by fatemerhmi - opened
Hello,
Thanks for the pix2struct contributions, it's great.
I tried the Hosted inference API on the model card and it shows this error:
The model_type 'pix2struct' is not recognized. It could be a bleeding edge model, or incorrect
Just thought to bring it up to your attention.
Hello,
Install transformers through this command:
pip install git+https://github.com/huggingface/transformers
It's dev version of library, which have pix2struct functionality