# Sentence order prediction

A multilingual ALBERT model pretrained with masked language modeling (MLM) objective, supporting 60+ languages, featuring a lightweight architecture with parameter sharing

ALBERT is a lightweight pre-trained language model based on Transformer architecture, reducing memory usage through parameter sharing mechanism, suitable for English text processing tasks.

ALBERT XLarge v1 is a large-scale language model pretrained on English corpora, utilizing a lightweight Transformer architecture with parameter sharing, focusing on masked language modeling and sentence order prediction tasks.

ALBERT Large v2 is a Transformer model pre-trained on English corpora with the masked language modeling (MLM) objective. It features parameter sharing.