# Whole Word Masking Pretraining

A Chinese pre-trained BERT model employing whole word masking strategy, designed to accelerate Chinese natural language processing research.

This is a Chinese pretrained BERT model using whole word masking strategy, released by the Harbin Institute of Technology-iFLYTEK Joint Laboratory to accelerate Chinese natural language processing research.

This is a retrained 6-layer RoBERTa-wwm-ext model using whole word masking technique for Chinese pretraining.

A Chinese pretrained BERT model using whole word masking technology, designed to accelerate the development of Chinese natural language processing.

MuRIL is an open-source BERT model pretrained on 17 Indian languages and their transliterated versions by Google, supporting multilingual representations.

This is a pretrained model based on the XLM-RoBERTa architecture, trained with masked language modeling objectives and fine-tuned on English and Russian question answering datasets.