albert-large-v2

ALBERT Large v2 is a transformers model pretrained on a large corpus of English data in a self-supervised fashion . This model is uncased: it does not make a difference between English and English . Version 2 is different from version 1 due to different dropout rates, additional training data, and longer training . It has better results in nearly all downstream tasks . You can use the raw model for either masked language modeling or next sentence prediction, but it's mostly intended to be fine-tuned on downstream tasks that use the whole sentence (potentially masked)to make decisions, such as sequence classification, token classification or question answering . For tasks such as text-generation,