# Text Representation Learning

NEZHA is a Chinese pre-trained language model based on the Transformer architecture, optimized for Chinese text understanding tasks using the whole word masking strategy

NEZHA is a neural contextualized representation model for Chinese understanding, based on the Transformer architecture, developed by Huawei Noah's Ark Lab.

A masked language model (MLM) fine-tuned based on bert-base-uncased, suitable for text filling tasks

MiniLMv2 is a lightweight multilingual pre-trained model developed by Microsoft Research, based on the Transformer architecture, suitable for various natural language processing tasks.

XLM is a masked language model trained on English text, using BERT-style MLM objectives for pretraining, supporting English language processing tasks.