library_name: transformers pipeline_tag: image-text-to-text base_model: - microsoft/Florence-2-base-ft
Model Card for Model ID
This is Microsoft's Florence-2 model trained for 1 day with Docmatix (5% of the data) with a learning rate of 1e-6. The code for this fine-tuning can be found here:
https://github.com/andimarafioti/florence2-finetuning
. And here's a blog explaining how to fine tune Florence:
https://huggingface.co/blog/finetune-florence2
.
Change the dataset to Kendamarron/japanese-photo-instruction for Japanese Caption use case by aipib.
Model Details
Model Description
This is the model card of a 🤗 transformers model that has been pushed on the Hub. It has been automatically generated.
Developed by: Kojyoho
Funded by [optional]: Hugging Face 🤗
Language(s) (NLP): Japanese
License: MIT
Finetuned from model: Florence-2-base-ft