# Whole Word Masking

MiniRBT is a Chinese small pre-trained model developed based on knowledge distillation technology, optimized for training efficiency using Whole Word Masking.

MiniRBT is a Chinese small pretrained model developed based on knowledge distillation technology, optimized for training efficiency using Whole Word Masking.

MiniRBT is a small Chinese pre-trained model based on knowledge distillation technology, combined with whole word masking, suitable for various Chinese natural language processing tasks.

Chinese pre-trained language model based on DeBERTa-v2 architecture with 320 million parameters, excelling in natural language understanding tasks

A Chinese DeBERTa-v2 base model specialized in natural language understanding tasks, employing Whole Word Masking with 97 million parameters.

Swedish BERT base model released by the National Library of Sweden/KBLab, trained on multi-source texts

BERT-large English Q&A model pre-trained with whole word masking and fine-tuned on SQuAD v1.1, quantized to INT8 precision

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

BETO is a BERT model trained on a large Spanish corpus, available in both cased and uncased versions, suitable for various Spanish NLP tasks.

BETO is a BERT model trained on a large Spanish corpus, supporting both cased and uncased versions, suitable for various Spanish NLP tasks.

This is a Japanese BERT pre-trained model based on character-level tokenization and whole word masking techniques, requiring no dependency on `fugashi` or `unidic_lite` toolkits.

Italian language model based on the Roberta architecture, trained with SentencePiece tokenization and Whole Word Masking