You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Model use case: Florence-2 is an advanced vision foundation model designed for a wide range of vision and vision-language tasks. Utilizing a prompt-based approach, Florence-2 excels in image captioning, object detection, and segmentation. Its sequence-to-sequence architecture enables high performance in both zero-shot and fine-tuned settings. The model is trained on the extensive FLD-5B dataset, which includes 5.4 billion annotations across 126 million images, making it highly effective for multi-task learning.
Hi @EwoutH, thank you for the feature request and details! I've added it to our list of requested models.
If you haven't already, we'd invite you to join our AI Hub Slack Community as that is where we share new models, features and talk with model developers using AI Hub.
@mestrona-3 could you give any update on model additions currently in the pipeline? I would love Florence-2, Llama 3.1 and Phi-3 to be available on the Qualcomm AI Hub.
Details of model being requested
Model Variants
Online demo: https://huggingface.co/spaces/gokaygokay/Florence-2
The text was updated successfully, but these errors were encountered: