ITNovaML/invoices-donut-data-v1
Viewer • Updated • 502 • 9 • 5
How to use ITNovaML/invoices-donut-model-v1 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="ITNovaML/invoices-donut-model-v1") # Load model directly
from transformers import AutoTokenizer, AutoModelForImageTextToText
tokenizer = AutoTokenizer.from_pretrained("ITNovaML/invoices-donut-model-v1")
model = AutoModelForImageTextToText.from_pretrained("ITNovaML/invoices-donut-model-v1")This model is finetuned Donut ML base model on invoices data. Model aims to verify how well Donut performs on enterprise docs.
Mean accuracy on test set: 0.96
Inference:
Training loss:
Sample invoice docs to use for inference (docs up to 500 were used for fine-tuning, use docs from 500 for inference)