Instructions to use google/pix2struct-docvqa-base with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use google/pix2struct-docvqa-base with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("visual-question-answering", model="google/pix2struct-docvqa-base")# Load model directly from transformers import AutoProcessor, AutoModelForImageTextToText processor = AutoProcessor.from_pretrained("google/pix2struct-docvqa-base") model = AutoModelForImageTextToText.from_pretrained("google/pix2struct-docvqa-base") - Notebooks
- Google Colab
- Kaggle
Adding ONNX file of this model
#4
by Akshat007 - opened
hi
how did you load the model
Hi @Akshat007 @Akshit01 , please refer to ORTModelForPix2Struct that was recently added in Optimum (you would need to install from source): https://huggingface.co/docs/optimum/main/en/onnxruntime/package_reference/modeling_ort#optimum.onnxruntime.ORTModelForPix2Struct