v0.5.1

• Downgrade version pin of importlib_metadata to prevent conflict.
• Fix issue #92: Fix index error when calculating doc.tensor.

Thanks to @ssavvi for the pull request!

v0.5.0

⚠️ This release requires downloading new models. Also note the new model names that specify trf (transformers) instead of pytt (PyTorch transformers).

• Rename package from spacy-pytorch-transformers to spacy-transformers.
• Update to spacy>=2.2.0.
• Upgrade to latest transformers.
• Improve code and repo organization.

v0.4.0

• Fix serialization.
• Update pytorch-transformers to support DistilBERT.
• Add pre-packed DistilBERT model.

v0.3.0

• Add out-of-the-box support for RoBERTa.
• Add pre-packaged RoBERTa model.
• Update to pytorch-transformers v1.1.
• Fix serialization when model was saved from GPU.

v0.2.0

• Add support for GLUE benchmark tasks.
• Support text-pair classification. The specifics of this are likely to change, but you can see run_glue.py for current usage.
• Improve reliability of tokenization and alignment.
• Add support for segment IDs to the PyTT_Wrapper class. These can now be passed in as a second column of the RaggedArray input. See the model_registry.get_word_pieces function for example usage.
• Set default maximum sequence length to 128.
• Fix bug that caused settings not to be passed into PyTT_TextCategorizer on model initialization.
• Fix serialization of XLNet model.

v0.1.1

• Handle unaligned tokens in extension attributes.

v0.1.0

⚠️ This version requires downloading new models.

• Fix issue #15: Fix serialization of config and make models load correctly offline.
• Improve accuracy of textcat by passing hyper-parameters correctly (Adam epsilon, L2).
• Support pooler output for BERT model.
• Add fine_tune_pooler_output model architecture option for pytt_textcat.
• Add Glue benchmark script in examples/tasks/run_glue.py.
• Improve overall stability.

v0.0.1

Tidy up