Felldude
/

clip-vit-large-patch14

This model has been finetuned in FP32 using Joycaption images. Both the Vision and Text models have been trained. Text model trained 10x epochs more then vision

Model card Files Files and versions

clip-vit-large-patch14

1.71 GB

1 contributor

History: 3 commits

Felldude's picture

Update README.md

9e511e8 verified 6 months ago