Open Beautifuldog01 opened 1 year ago
I don't quite understand the reason why 'note that when t5 is used for classification, we only need to pass to decoder.', which means that the decoder length should be 3, decoder_max_length=3, that's why?
I don't quite understand the reason why 'note that when t5 is used for classification, we only need to pass to decoder.', which means that the decoder length should be 3, decoder_max_length=3, that's why?