metadata

license: mit
datasets:
  - de-Rodrigo/merit
language:
  - en
  - es
base_model:
  - naver-clova-ix/donut-base-finetuned-cord-v2
pipeline_tag: image-text-to-text

DONUT Merit

Model Architecture

This model is based on the Donut architecture and fine-tuned on the Merit dataset for form understanding tasks.

Backbone: Donut
Training Data: Merit

Example Usage

from transformers import AutoTokenizer, AutoModelForImageTextToText

tokenizer = AutoTokenizer.from_pretrained("de-Rodrigo/donut-merit")
model = AutoModelForImageTextToText.from_pretrained("de-Rodrigo/donut-merit")

WIP 🛠️