PyTorch version of Google AI BERT model with script to load Google pre-trained models
copied from cf-staging / pytorch-pretrained-bertThis repository contains op-for-op PyTorch reimplementations, pre-trained models and fine-tuning examples for: - Google's BERT model, - OpenAI's GPT model, - Google/CMU's Transformer-XL model, and - OpenAI's GPT-2 model. These implementations have been tested on several datasets (see the examples) and should match the performances of the associated TensorFlow implementations (e.g. ~91 F1 on SQuAD for BERT, ~88 F1 on RocStories for OpenAI GPT and ~18.3 perplexity on WikiText 103 for the Transformer-XL).