Vision-Language Models available in multiple 3B, 10B and 28B variants.
-
PaliGemma 2: A Family of Versatile VLMs for Transfer
Paper • 2412.03555 • Published • 118 -
google/paligemma2-3b-pt-224
Image-Text-to-Text • Updated • 25.7k • 112 -
google/paligemma2-3b-pt-448
Image-Text-to-Text • Updated • 19.9k • 35 -
google/paligemma2-3b-pt-896
Image-Text-to-Text • Updated • 2.94k • 21