DONUT Cord-v2

Model Architecture

This model is based on the Donut architecture and fine-tuned on the Cord-v2 dataset for form understanding tasks.

Backbone: Donut
Training Data: Cord-v2

Example Usage

from transformers import AutoProcessor, AutoModel

processor = AutoProcessor.from_pretrained("de-Rodrigo/donut-cord-v2")
model = AutoModel.from_pretrained("de-Rodrigo/donut-cord-v2")

WIP 🛠️

Downloads last month: 8

Safetensors

Model size

202M params

Tensor type

I64

F32

Inference Providers NEW

This model is not currently available via any of the supported third-party Inference Providers, and HF Inference API was unable to determine this model's library.