README.md

metadata

license: mit
datasets:
  - de-Rodrigo/merit
language:
  - en
  - es
base_model:
  - llava-hf/llava-1.5-7b-hf
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: Llava
• Training Data: Merit

Example Usage

WIP

WIP 🛠️