huseinzol05/t5-base-bahasa-cased

The model was trained using Google T5's Github repository on v3-8 TPU . It was used to train T5 for Malay and Indonesian languages . The model can be pre-processed using torch or tensorflow and Huggingface library transformers . It can be downloaded from here, Malaya/pretrained-model/t5.io/en-latest/Accuracy.html, we compared with traditional models. The model has been trained on multiple tasks we trained on, unsupervised on local Wikipedia, local news, IIUM Confession and local parliament text. It can also be used to test Bahasa SNLI and Natural Questions. It has been,