abelriboulot/onnxt5

Summarization, translation, sentiment-analysis, text-generation and more at blazing speed using a T5 version implemented in ONNX.

49
/ 100
Emerging

Leverages ONNX Runtime for efficient inference with up to 4X speedup on shorter contexts (<500 words) compared to PyTorch, while supporting task-specific prefixes for zero-shot capabilities across translation, summarization, Q&A, and embedding extraction. Provides a Python API for both pre-trained and custom T5 model export, enabling seamless encoder-decoder inference with configurable generation parameters like temperature and max length.

256 stars and 134 monthly downloads. No commits in the last 6 months. Available on PyPI.

Stale 6m No Dependents
Maintenance 0 / 25
Adoption 15 / 25
Maturity 18 / 25
Community 16 / 25

How are scores calculated?

Stars

256

Forks

31

Language

Python

License

Apache-2.0

Last pushed

Nov 02, 2022

Monthly downloads

134

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/transformers/abelriboulot/onnxt5"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.