google/paligemma-3b-pt-896

Image-Text-to-Text • Updated Jul 19 • 98.3k • 111

Note ^ Pretrained models in transformers format

google/paligemma-3b-pt-896-jax

Image-Text-to-Text • Updated Jul 19 • 849 • 2

Note ^ Pretrained models for use with the big_vision repo

google/paligemma-3b-mix-448

Image-Text-to-Text • Updated Jul 19 • 40.7k • 98

Note ^ Models finetuned on a variety of tasks, in transformers format

google/paligemma-3b-mix-448-jax

Updated Jul 18 • 7

Note ^ Models finetuned on a variety of tasks, in big_vision format