t5

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

Neural question generation using transformers

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

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.

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

An NLP system for generating reading comprehension questions

MinT: Minimal Transformer Library and Tutorials

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

Text-to-SQL in the Wild: A Naturally-Occurring Dataset Based on Stack Exchange Data

textgen, Text Generation models. 文本生成，包括：UDA，GPT2，Seq2Seq，BART，T5等模型实现，开箱即用。

Trained T5 and T5-large model for creating keywords from text

中文AI写作共享（监督学习和迁移学习来写诗或对对子）

The source code of "Language Models are Few-shot Multilingual Learners" (MRL @ EMNLP 2021)

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

Abstractive and Extractive Text summarization using Transformers.

Easy to use and understand multiple-choice question generation algorithm using T5 Transformers.

Tutorial to pretrain & fine-tune a 🤗 Flax T5 model on a TPUv3-8 with GCP

NLP model zoo for Russian

FTPipe and related pipeline model parallelism research.

Official Code for SIGIR 2022 "A Multi-task Based Neural Model to Simulate Users in Goal Oriented Dialogue Systems". User Simulator generates user-side utterance, predicts user's next action and satisfaction level.

Demo of the T5 model for various pre-trained task.

Codes to pre-train Japanese T5 models

This repository contains the official release of the model "BanglaT5" and associated downstream finetuning code and datasets introduced in the paper titled "BanglaNLG: Benchmarks and Resources for Evaluating Low-Resource Natural Language Generation in Bangla".

Chef Transformer 🍲 .

Codes for our paper "JointGT: Graph-Text Joint Representation Learning for Text Generation from Knowledge Graphs" (ACL 2021 Findings)

Automated question generation and question answering from Turkish texts using text-to-text transformers

Detection of Emotion and its cause from text

Supervised text summarization (title generation/recommendation) based on academic paper abstracts, with Seq2Seq LSTM and T5.

Using pretrained T5 model for abstractive summarization of books