Florence-2-VQAJP2

This model is a fine-tuned version of microsoft/Florence-2-base-ft on Kendamarron/japanese-photo-instruction dataset. It achieves the following results on the evaluation set:

• Loss: 0.77

Finetuned to the CAPTION task for Japanese output.

Model description

Please use task prompt "CAPTION" to get results in Japanese.

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

Training results

Framework versions

• Transformers 4.46.3
• Pytorch 2.3.0
• Datasets 2.20.0
• Tokenizers 0.20.3