T5 Python 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。

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。

frame-semantic-transformer

Frame Semantic Parser based on T5 and FrameNet

keytotext

Keywords to Sentences

ratransformers

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

absum

Abstractive Summarization for Data Augmentation

fastt5

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

smarty-gpt

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

textgen

Text Generation Model

simplet5

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

keyphrasetransformer

KeyPhraseTransformer lets you quickly extract key phrases, topics, themes from your text data with T5 transformer | Keyphrase extraction | Keyword extraction

t2t-tuner

Convenient Text-to-Text Training for Transformers

lmqg

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

instruction-ner

Unofficial implementation of paper "InstructionNER: A Multi-Task Instruction-Based Generative Framework for Few-shot NER" (https://arxiv.org/pdf/2203.03903v1.pdf)

databalancer

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

turkish-lm-tuner

Implementation of the Turkish LM Tuner

pytriplet

Fine-tuning Transformers with TPUs or GPUs acceleration, written in Tensorflow2.0