These are the models that we have used with our first version.
-
google/owlv2-base-patch16-ensemble
Zero-Shot Object Detection • Updated • 944k • 101 -
Qwen/Qwen1.5-0.5B-Chat
Text Generation • Updated • 454k • 80 -
Salesforce/blip-image-captioning-base
Image-to-Text • Updated • 2.46M • 706 -
facebook/sam-vit-base
Feature Extraction • Updated • 540k • • 137