Introduction
This fine-tuned model using Gemma 3 4B Instruct for receipts extraction.
Pre-processing Dataset
- Check all receipt photos to see if are RGB mode.
- Extract and parse "ground_truth" column.
- Check if store_name, date and total have "" or not.
- All store name must capital using upper()
- Parsing date to "%d-%m-%Y" format
- Check if total have $ or not, if total don't have $, add $
- Downloads last month
- 159
Inference Providers
NEW
This model isn't deployed by any Inference Provider.
🙋
Ask for provider support