---
language:
  - en
  - zh
tags:
  - florence-2
  - document-vqa
  - image-text-retrieval
  - fine-tuned
license: mit
base_model: microsoft/Florence-2-base-ft
---

# adamchanadam/Test_Florence-2-FT-DocVQA

This model is fine-tuned from [microsoft/Florence-2-base-ft](https://huggingface.co/microsoft/Florence-2-base-ft) for Document Visual Question Answering (DocVQA) tasks.

## Model description

- Fine-tuned for answering questions about images, specifically focused on logo recognition and company information.
- The model uses the `<DocVQA>` prompt to indicate the task type.
- Number of unique images: 3
- Number of epochs: 15
- Learning rate: 5e-06
- Optimizer: AdamW
- Early stopping: Patience of 3 epochs, delta of 0.01

Dataset statistics: Total number of questions for fine-tuning: 40.
logo_recognition: 4 (10.00%) brand_identification: 4 (10.00%) visual_elements: 4 (10.00%) text_in_logo: 4 (10.00%) industry_classification: 4 (10.00%) product_service: 4 (10.00%) company_details: 6 (15.00%) negative_sample: 10 (25.00%)

## Intended use & limitations

- Use for answering questions about logos and company information in images
- Performance may be limited for questions or image content not represented in the training data

## Training procedure

- Images were resized and normalized according to Florence-2's preprocessing standards.
- The `<DocVQA>` prompt was used during fine-tuning to indicate the task type.
- Questions and answers were provided for each image in the training set.
- Batch size: 2
- Evaluation metric: Cross-entropy loss on a held-out validation set

For more information, please contact the model creators.