Florence 2

Fine-Tune Florence 2: Train Vision Language Model for VQA

Posted by Fede Nolasco | Oct 29, 2024

Learn how to fine-tune Florence 2, a vision language model by Microsoft, for tasks like document VQA and health anomaly detection. Enhance model accuracy and customize for specific tasks.

Florence 2 VLM: Best Small Vision-Language Model?

Posted by Fede Nolasco | Oct 14, 2024

Explore Florence 2 VLM by Microsoft, a powerful small vision-language model with 5.4 billion labels. Learn about its capabilities in image captioning, object detection, and segmentation.