asyml/texar-pytorch

Integrating the Best of TF into PyTorch, for Machine Learning, Natural Language Processing, and Text Generation. This is part of the CASL project: http://casl-project.ai/

65
/ 100
Established

Provides modularized encoder-decoder architectures with pre-trained model support (BERT, GPT-2, XLNet) and an `Executor` API for managing training loops with built-in metrics and checkpointing. Decomposes learning into principled Learning-Inference-Model layers, supporting maximum likelihood, reinforcement learning, and adversarial training paradigms while maintaining full PyTorch API compatibility.

746 stars and 3,221 monthly downloads. No commits in the last 6 months. Available on PyPI.

Stale 6m
Maintenance 0 / 25
Adoption 18 / 25
Maturity 25 / 25
Community 22 / 25

How are scores calculated?

Stars

746

Forks

113

Language

Python

License

Apache-2.0

Last pushed

Apr 14, 2022

Monthly downloads

3,221

Commits (30d)

0

Dependencies

9

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/asyml/texar-pytorch"

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