t5 开源项目推荐（420 个）

shibing624 /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。

dbiir /UER-py

Open Source Pre-training Model Framework in PyTorch & Pre-trained Model Zoo

patil-suraj /question_generation

Neural question generation using transformers

Tencent /TencentPretrain

Tencent Pre-training framework in PyTorch & Pre-trained Model Zoo

shibing624 /textgen

TextGen：实现文本生成模型，包括LLaMA、BLOOM、GPT2、BART、T5、SongNet等。文本生成模型，实现了包括LLaMA、ChatGLM、BLOOM、GPT2、Seq2Seq、BART，T5，UDA等模型的训练和预测，开箱即用。

JohnSnowLabs /nlu

1 line for thousands of State of The Art NLP models in hundreds of languages The fastest and most accurate way to solve text problems.

abhimishra91 /transformers-tutorials

Github repo with tutorials to fine tune transformers for diff NLP tasks

Ki6an /fastT5

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

stefan-it /turkish-bert

Turkish BERT/DistilBERT, ELECTRA, ConvBERT and T5 models

bigscience-workshop /xmtf

Crosslingual Generalization through Multitask Finetuning

Denis2054 /Transformers-for-NLP-and-Computer-Vision-3rd-Edition

Transformers 3rd Edition

gagan3012 /keytotext

Keywords to Sentences

Shivanandroy /simpleT5

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

asahi417 /lm-question-generation

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

AMontgomerie /question_generator

An NLP system for generating reading comprehension questions

dpressel /mint

MinT: Minimal Transformer Library and Tutorials

Laupetin /OpenAssetTools

Open Source Modding Tools for old Call Of Duty games

Jbleezy /BO1-Reimagined

Call of Duty: Black Ops Zombies - Reimagined

FreedomIntelligence /crosstalk-generation

Code and data for crosstalk text generation tasks, exploring whether large models and pre-trained language models can understand humor.

vipulraheja /coedit

论文《CoEdIT：通过任务特定指令调优进行文本编辑》（EMNLP 2023）的官方实现