oh. as it turns out, papers with code does not have CV11 uz benchmarks defined...

re-adding language to test dataset names since i think it actually did matter for something?

i promise this is the last update for now

i really should've proofread this first

add some more info to the model card

Update metadata with huggingface_hub

fixing model card (i used multiple datasets)

update model card README.md

update model card README.md