Search Packages

pycorrector

pycorrector is a toolkit for text error correction. 文本纠错，实现了Kenlm，T5，MacBERT，ChatGLM3，Qwen2.5等模型应用在纠错场景，开箱即用。

keytotext

Keywords to Sentences

frame-semantic-transformer

Frame Semantic Parser based on T5 and FrameNet

fastt5

⚡ boost inference speed of T5 models by 5x & reduce the model size by 3x.

absum

Abstractive Summarization for Data Augmentation

bert-seq2seq-ddp

bert_seq2seq的DDP版本，支持bert、roberta、nezha、t5、gpt2等模型，支持seq2seq、ner、关系抽取等任务，无需添加额外代码，轻松启动DDP多卡训练。

ratransformers

RATransformers 🐭- Make your transformer (like BERT, RoBERTa, GPT-2 and T5) Relation Aware!

t2t-tuner

Convenient Text-to-Text Training for Transformers

textgen

Text Generation Model

smarty-gpt

A wrapper of LLMs that biases its behaviour using prompts and contexts in a transparent manner to the end-users

simplet5

simpleT5 is built on top of PyTorch-lightning ⚡️ and Transformers 🤗 that lets you quickly train your T5 models.

lmqg

Multilingual/multidomain question generation datasets, models, and python library for question generation.

keyphrasetransformer

Quickly extract key-phrases/topics from you text data with T5 transformer.

instruction-ner

Unofficial implementation of InstructionNER

databalancer

Databalancer is the python library using in machine learning applications to balance the imbalanced text classification datasets before the model training.

turkish-lm-tuner

Turkish LM Tuner

pytriplet

A package for fine-tuning Transformers with TPUs, written in Tensorflow2.0+