Text Analytics Toolbox Model for BERT-Tiny Network

Pretrained BERT-Tiny Network for MATLAB.
121 Descargas
Actualizado 26 ene 2026
BERT-Tiny 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 2 self-attention layers and a hidden size of 128.
To load a BERT-Tiny model, you can run the following code:
[net, tokenizer] = bert(Model="tiny");
Compatibilidad con la versión de MATLAB
Se creó con R2023b
Compatible con cualquier versión desde R2023b hasta R2026a
Compatibilidad con las plataformas
Windows macOS (Apple Silicon) macOS (Intel) Linux