Hi,
I was running unicamp-dl/mt5-base-en-msmarco: ['▁no' , '▁yes'] model for both English and other My.TyDi languages, but the output scores are nan. When I switched to unicamp-dl/mt5-13b-mmarco-100k: ['▁', '▁true'] model, I get actual real logits. I wonder if there's any issues with underlying unicamp-dl/mt5-base-en-msmarco model.
Thanks.