BERT Language Models
This repository contains BERT Language Models fine-tuned for Masked Language Modeling and massively used by Weni combined with other tools to work in tasks like Intent Classification and Named Entity Recognition.
Languages available
models/pt_br
: Brazilian portuguese modelmodels/en
: English modelmodels/multilang
: The multi-language model supports any language with a good accuracy rate
How to use
The BERT Language models can be used in many different ways, you can fine-tune the them by using simpletransformers library for different tasks as following:
Step 1: Installing simpletransformers
pip install simpletransformers
Step 2: Loading the models
from simpletransformers.language_modeling import LanguageModelingModel
model = LanguageModelingModel("bert", "/models/multilang", from_tf=True)
License
Distributed under the GPL-3.0 License. See LICENSE
for more information.
Contribution
Contributions are what make the open source community such an amazing place to be learn, inspire, and create. Any contributions you make are greatly appreciated.
- Fork the Project
- Create your Feature Branch (git checkout -b feature/AmazingFeature)
- Commit your Changes (git commit -m 'Add some AmazingFeature')
- Push to the Branch (git push origin feature/AmazingFeature)
- Open a Pull Request