Curated-transformers

Latest version: v2.0.1

Safety actively analyzes 682244 Python packages for vulnerabilities to keep your Python projects secure.

Scan your dependencies

Page 2 of 3

1.1.0

✨ New features and improvements

* Add decoder and causal LM for MosaicML MPT (294).
* Add generator wrapper for MosaicML MPT (296).

🔴 Bug fixes

* Do not initialize embeddings when loading a model (295).

👥 Contributors

danieldk, honnibal, ines, shadeMe

1.0.0

Three weeks on the heels of our tech preview we are excited to announce first stable release of Curated Transformers! 🎉 From this release onwards, we provide a [stable API](https://curated-transformers.readthedocs.io/en/latest/api-compat.html) following semantic versioning guidelines. Of course, this release is also packed with new features.

0.9.1

🔴 Bug fixes

* Support old and new Falcon model type and configuration (243).

👥 Contributors

danieldk

0.9.0

We are very happy to announce this major new release of Curated Transformers! 🎉

Curated Transformers started as a small transformer library for spaCy pipelines. Over the last two months we made it a pure PyTorch library that is completely independent of spaCy and Thinc. We also added support for popular LLM models, generation, 8-bit/4-bit quantization, and many other features:

* Curated Transformers is now a pure PyTorch library.
* Support for popular LLMs such as Falcon, LLaMA, and Dolly v2.
* Greedy generation and generation with sampling.
* 8-bit and 4-bit quantization of models through [`bitsandbytes`](https://github.com/TimDettmers/bitsandbytes).
* Flash attention and other optimizations through PyTorch Scaled Dot Product Attention.
* Efficient model loading without unneeded allocations and initialization through the Torch `meta` devices.
* Support for modern `tokenizer.json` tokenizers.
* Load models from Hugging Face Hub without requiring the `transformers` package.
* Extensive [API documentation](https://curated-transformers.readthedocs.io/en/v0.9.x/) and examples.

Curated Transformers can be used in spaCy using the [`spacy-curated-transformers`](https://github.com/explosion/spacy-curated-transformers/tree/main) package.

👥 Contributors

danieldk, honnibal, ines, shadeMe

0.2.2

✨ New features and improvements

* Make [`DocTransformerOutput`](https://spacy.io/api/curatedtransformer#doctransformeroutput) serializable with msgpack (29).

0.2.1

✨ New features and improvements

* Add [`init fill-curated-transformer`](https://spacy.io/api/cli#init-fill-curated-transformer) CLI command (16, 22).

🔴 Bug fixes

* Correctly pass `hidden_width` as the embedding width in non-ALBERT models (17).
* Add `vocab_size` to default transformer pipe config (20).

Page 2 of 3

© 2024 Safety CLI Cybersecurity Inc. All Rights Reserved.