Since it was founded, the startup, Hugging Face, has created several open-source libraries for NLP-based tokenizers and transformers. One of their libraries, the Hugging Face transformers package, is an immensely popular Python library providing over 32 pre-trained models that are extraordinarily useful for a variety of natural language processing (NLP) tasks.
It was created to enable general-purpose architectures such as BERT, GPT-2, XLNet, XLM, DistilBERT, and RoBERTa for Natural Language Understanding (NLU) and Natural Language Generation (NLG) to perform tasks like text classification, information extraction, and text generation. Tasks performed by this library include classification, information extraction, question answering, summarization, translation, and text generation in over 100 languages. Its ultimate goal is to make cutting-edge NLP easier to use for everyone.
Transformers previously supported only PyTorch, but starting in late 2019, it also began supporting TensorFlow 2.
Transformers in NLP is an architecture primarily used for solving sequence-to-sequence tasks and handling long-range dependencies simultaneously with ease. Currently, the transformers models are one of the most frequently adopted models for production environments by companies.
In this free-to-download guide, we walk you through some core aspects of Hugging Face, including a general overview, jobs that use Hugging Face, key terminology, and algorithms that you need to get started.