Hugging Face's logo

de-Rodrigo
/
donut-merit

Image-Text-to-Text
Transformers
Safetensors
vision-encoder-decoder
vision
document-understanding
donut
Inference Endpoints
Model card Files Community

DONUT Merit

DragonHuggingFace

Model Architecture

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

Example Usage 

from transformers import AutoProcessor, AutoModel

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

WIP 🛠️

Downloads last month
53
Safetensors
Model size
202M params
Tensor type
I64
·
F32
·
Inference Providers NEW
Image-Text-to-Text
This model is not currently available via any of the supported third-party Inference Providers, and the HF Inference API does not support transformers models with pipeline type image-text-to-text

Space using de-Rodrigo/donut-merit 1

Collection including de-Rodrigo/donut-merit