# Florence2

🔥Florence-2 Fine-tuning: Microsoft's foundation VLM just got more awesome! 🚀 Learn about the fine-tuning and access useful links👇

* Team successfully fine-tuned Florence2 for DocVQA
* 0 to 57.0 similarity score on validation set 📈
* Works with limited resources (single GPU, small batch size)
* Frozen vision encoder still yields great results
* Fine-tuning code & Colab notebook available 🤗
* Demo is up on Hugging Face Spaces

Who's ready to fine-tune Florence-2 for their own tasks? 🔥

🙌 Massive props to team for making this accessible! @mervenoyann @andi\_marafioti @skalskip92\
\
Blog: <https://lnkd.in/dVE2pQJb>\
Colab: <https://lnkd.in/dEnhFgiX>\
Demo: <https://lnkd.in/dQvqGA4g><br>