This repository hosts Chinese pre-trained language models based on Whole Word Masking (WWM) methodology. It provides multiple model variants including BERT-wwm, BERT-wwm-ext, RoBERTa-wwm-ext, RoBERTa-wwm-ext-large, RBT3, and RBTL3. The models are built on Google’s official BERT implementation and support both PyTorch and TensorFlow frameworks. These models are designed to improve Chinese NLP tasks by masking entire words rather than individual subword tokens during pre-training.