Post
3255
Fine-tune Florence-2 on any task ๐ฅ
Today we release a notebook and a walkthrough blog on fine-tuning Florence-2 on DocVQA dataset @andito @SkalskiP
Blog: https://huggingface.co/blog ๐
Notebook: https://colab.research.google.com/drive/1hKDrJ5AH_o7I95PtZ9__VlCTNAo1Gjpf?usp=sharing ๐
Florence-2 is a great vision-language model thanks to it's massive dataset and small size!
This model requires conditioning through task prefixes and it's not as generalist, requiring fine-tuning on a new task, such as DocVQA ๐
We have fine-tuned the model on A100 (and one can also use a smaller GPU with smaller batch size) and saw that model picks up new tasks ๐ฅน
See below how it looks like before and after FT ๐คฉ
Play with the demo here andito/Florence-2-DocVQA ๐โโ๏ธ
Today we release a notebook and a walkthrough blog on fine-tuning Florence-2 on DocVQA dataset @andito @SkalskiP
Blog: https://huggingface.co/blog ๐
Notebook: https://colab.research.google.com/drive/1hKDrJ5AH_o7I95PtZ9__VlCTNAo1Gjpf?usp=sharing ๐
Florence-2 is a great vision-language model thanks to it's massive dataset and small size!
This model requires conditioning through task prefixes and it's not as generalist, requiring fine-tuning on a new task, such as DocVQA ๐
We have fine-tuned the model on A100 (and one can also use a smaller GPU with smaller batch size) and saw that model picks up new tasks ๐ฅน
See below how it looks like before and after FT ๐คฉ
Play with the demo here andito/Florence-2-DocVQA ๐โโ๏ธ