Development Status
- 5 - Production/Stable
Environment
- Console
Intended Audience
- Developers
- Science/Research
Topic
- Scientific/Engineering
- Scientific/Engineering :: Artificial Intelligence
License
- OSI Approved :: MIT License
Operating System
- POSIX :: Linux
- MacOS :: MacOS X
- Microsoft :: Windows
Programming Language
- Python :: 3
- Python :: 3.7
- Python :: 3.8
- Python :: 3.9
- Python :: 3.10
- Python :: 3.11
spacy-transformers: Use pretrained transformers like BERT, XLNet and GPT-2 in spaCy
This package provides spaCy components and
architectures to use transformer models via
Hugging Face's transformers in
spaCy. The result is convenient access to state-of-the-art transformer
architectures, such as BERT, GPT-2, XLNet, etc.
This release requires spaCy v3. For the previous version of this library, see the
v0.6.xbranch.
Features
- Use pretrained transformer models like BERT, RoBERTa and XLNet to power your spaCy pipeline.
- Easy multi-task learning: backprop to one transformer model from several pipeline components.
- Train using spaCy v3's powerful and extensible config system.
- Automatic alignment of transformer output to spaCy's tokenization.
- Easily customize what transformer data is saved in the
Docobject. - Easily customize how long documents are processed.
- Out-of-the-box serialization and model packaging.
๐ Installation
Installing the package from pip will automatically install all dependencies, including PyTorch and spaCy. Make sure you install this package before you install the models. Also note that this package requires Python 3.6+, PyTorch v1.5+ and spaCy v3.0+.
pip install 'spacy[transformers]'
For GPU installation, find your CUDA version using nvcc --version and add the
version in brackets, e.g.
spacy[transformers,cuda92] for CUDA9.2 or spacy[transformers,cuda100] for
CUDA10.0.
If you are having trouble installing PyTorch, follow the instructions on the official website for your specific operating system and requirements.
๐ Documentation
โ ๏ธ Important note: This package has been extensively refactored to take advantage of spaCy v3.0. Previous versions that were built for spaCy v2.x worked considerably differently. Please see previous tagged versions of this README for documentation on prior versions.
- ๐ Embeddings, Transformers and Transfer Learning: How to use transformers in spaCy
- ๐ Training Pipelines and Models: Train and update components on your own data and integrate custom models
- ๐ Layers and Model Architectures: Power spaCy components with custom neural networks
- ๐
Transformer: Pipeline component API reference - ๐ Transformer architectures: Architectures and registered functions
Applying pretrained text and token classification models
Note that the transformer component from spacy-transformers does not support
task-specific heads like token or text classification. A task-specific
transformer model can be used as a source of features to train spaCy components
like ner or textcat, but the transformer component does not provide access
to task-specific heads for training or inference.
Alternatively, if you only want use to the predictions from an existing
Hugging Face text or token classification model, you can use the wrappers from
spacy-huggingface-pipelines
to incorporate task-specific transformer models into your spaCy pipelines.
Bug reports and other issues
Please use spaCy's issue tracker to report a bug, or open a new thread on the discussion board for any other issue.
