🤗 Transformers (formerly known as pytorch-transformers and pytorch-pretrained-bert) provides state-of-the-art general-purpose architectures (BERT, GPT-2, RoBERTa, XLM, DistilBert, XLNet, CTRL...) for Natural Language Understanding (NLU) and Natural Language Generation (NLG) with over 32+ pretrained models in 100+ languages and deep interoperability between TensorFlow 2.0 and PyTorch.

Don't forget to tag @huggingface in your comment, otherwise they may not be notified.

Authors
Solving NLP, one commit at a time!
Share this project
Similar projects
Bridging PyTorch and TVM
Taking Hugging Face transformer BERT from PyTorch and running it on ApacheTVM for both inference (with reasonable timings) and training.
How to Train a New Language Model From Scratch Using Transformers
In this post we’ll demo how to train a “small” model (84 M parameters = 6 layers, 768 hidden size, 12 attention heads).
RoBERTa meets TPUs
Understanding and applying the RoBERTa model to the current challenge.
How Hugging Face achieved a 2x performance boost for QA
Question Answering with DistilBERT in Node.js
Top collections