← 开源
EricFillion

happy-transformer

Happy Transformer makes it easy to fine-tune and perform inference with NLP Transformer models.

Model DevelopmentFine-tuningPython
在 GitHub 打开
增长势头
+024 小时新增 Star0.0%
547
Star
69
Fork
+0
本周
13
贡献者
创建于 2019-10-06 · 更新于 2026-09-28 · 今日第 16881 名
主要开发者
README

HAPPY TRANSFORMER

Happy Transformer logo

License: Apache-2.0 Downloads PyPI Discord

happytransformer.com

Happy Transformer makes it easy to fine-tune and perform inference with NLP Transformer models.

Upcoming Version 4.0.0

Version 4.0.0 is in the final stages of development. It's a complete rewrite of the library with many new features. It includes breaking changes, and so we recommend you set the version to <4.0.0 in your requirements.

Tasks

Tasks Inference Training
Text Generation ✔ ✔
Text Classification ✔ ✔
Word Prediction ✔ ✔
Question Answering ✔ ✔
Text-to-Text ✔ ✔
Next Sentence Prediction ✔
Token Classification ✔

Note: word prediction, question answering, next sentence prediction and token classification have been deprecated.

Install

pip install "happytransformer<4.0.0"

Maintainers

Tutorial Articles

Text classification (training)

Top T5 Models

Grammar Correction

Fine-tune a Grammar Correction Model

Tutorial Videos

Text generation with training (GPT-Neo)

Text classification (hate speech detection)

Text classification (sentiment analysis)

Word prediction with training (DistilBERT, RoBERTa)