Things on this page are fragmentary and immature notes/thoughts of the author. Please read with your own judgement!
Implementations
huggingface/transformers has PyTorch implementation of transfomer based models (such as BERT and DistilBERT ).
https://github.com/codertimo/BERT-pytorch
Official Implementation of BERT in TensorFlow
Tutorials
https://mccormickml.com/2019/07/22/BERT-fine-tuning/
References
https://arxiv.org/pdf/1810.04805.pdf
https://medium.com/huggingface/multi-label-text-classification-using-bert-the-mighty-transformer-69714fa3fb3d
https://hanxiao.io/2019/01/02/Serving-Google-BERT-in-Production-using-Tensorflow-and-ZeroMQ/