suolyer

DeepSpeed

DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.

unilm

Large-scale Self-supervised Pre-training Across Tasks, Languages, and Modalities

sentencepiece

Unsupervised text tokenizer for Neural Network-based text generation.

nlp_chinese_corpus

大规模中文自然语言处理语料 Large Scale Chinese Corpus for NLP

ChineseNlpCorpus

搜集、整理、发布 中文 自然语言处理 语料/数据集，与 有志之士 共同 促进 中文 自然语言处理 的 发展。

CLUE

中文语言理解测评基准 Chinese Language Understanding Evaluation Benchmark: datasets, baselines, pre-trained models, corpus and leaderboard

TextInfoExp

自然语言处理实验（sougou数据集），TF-IDF，文本分类、聚类、词向量、情感识别、关系抽取等

GPT2-NewsTitle

Chinese NewsTitle Generation Project by GPT2.带有超级详细注释的中文GPT2新闻标题生成项目。

LM-BFF

[ACL 2021] LM-BFF: Better Few-shot Fine-tuning of Language Models https://arxiv.org/abs/2012.15723

RoFormer_pytorch

RoFormer V1 & V2 pytorch

libai

LiBai(李白): A Toolbox for Large-Scale Distributed Parallel Training

toutiao-multilevel-text-classfication-dataset

今日头条中文新闻文本(多层)分类数据集

kg-baseline-pytorch

2019百度的关系抽取比赛，使用Pytorch实现苏神的模型，F1在dev集可达到0.75，联合关系抽取，Joint Relation Extraction.

2018-daguan-competition

2018年"达观杯"文本智能处理挑战赛-长文本分类-rank4

dice_loss_for_NLP

The repo contains the code of the ACL2020 paper `Dice Loss for Data-imbalanced NLP Tasks`

pytorch-distributed-training

Simple tutorials on Pytorch DDP training

NSP-BERT

The code for our paper "NSP-BERT: A Prompt-based Zero-Shot Learner Through an Original Pre-training Task —— Next Sentence Prediction"

ChineseTextualInference

ChineseTextualInference project including chinese corpus build and inferecence model, 中文文本推断项目,包括88万文本蕴含中文文本蕴含数据集的翻译与构建,基于深度学习的文本蕴含判定模型构建.

fairseq-apollo

FairSeq repo with Apollo optimizer

Chinese_Coreference_Resolution

基于SpanBert的中文指代消解，pytorch实现

BYOL-PyTorch

PyTorch implementation of "Bootstrap Your Own Latent: A New Approach to Self-Supervised Learning" with DDP and Apex AMP

ChineseSquad

中文机器阅读理解数据集

CUGE

CEEC-Corpus

:books:中文环境突发事件语料库（Chinese Environment Emergency Corpus）-上海大学-语义智能实验室

nlp-paper-reading-list

motivation: 系统整理NLP各个方向需要阅读的论文

bilibili-video

weiboNER

Chinese social media (Weibo) corpus rearrangement, taking the word as the basic unit instead of character.

Ontonotes5.0-Chinese-NER

Ontonotes5.0 Chinese NER dataset

PyTorch_DDP_Demo

PyTorch_DDP_Demo

Pytorch 多GPU并行demo