/spacy-curated-transformers

spaCy entry points for Curated Transformers

Primary LanguagePythonMIT LicenseMIT

🤖 Curated transformers

This Python package provides a curated set of transformer models for spaCy. It is focused on deep integration into spaCy and will support deployment-focused features such as distillation and quantization. Curated transformers currently supports the following model types:

  • ALBERT
  • BERT
  • CamemBERT
  • RoBERTa
  • XLM-RoBERTa

Supporting a wide variety of transformer models is a non-goal. If you want to use another type of model, use spacy-transformers, which allows you to use Hugging Face transformers models with spaCy.

⚠️ Warning: experimental package

This package is experimental and it is possible that the models will still change in incompatible ways.

⏳ Install

pip install spacy-curated-transformers

🚀 Quickstart

An example project is provided in the project directory.