Text Analytics Toolbox Model for BERT-Large Network

Pretrained BERT-Large Network for MATLAB

BERT-Large is a pretrained language model based on Deep Learning Transformer architecture that can be used for a wide variety of Natural Language Processing (NLP) tasks. This model has 24 self-attention layers and a hidden size of 1024.

To load a BERT-Large model, you can run the following code:

[net, tokenizer] = bert(Model="large");