Paul's repositories
FasterTransformer
Transformer related optimization, including BERT, GPT
transformers
🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.
smoothquant
SmoothQuant: Accurate and Efficient Post-Training Quantization for Large Language Models
tf2-study-notebook
notebook for [《Google老师亲授 TensorFlow2.0 入门到进阶》学习笔记](https://coding.imooc.com/class/chapter/344.html)
Time-series-prediction
A collection of time series prediction methods: rnn, seq2seq, cnn, wavenet, transformer, unet, n-beats, gan, kalman-filter
fairseq
Facebook AI Research Sequence-to-Sequence Toolkit written in Python.
TextBrewer
A PyTorch-based knowledge distillation toolkit for natural language processing
geektime-ELK
ELK Training
EnsembleLearning
包括决策树和随机森林进行离职人员预测，Xgboost和lightGBM的应用
personal_recommendation
个性化推荐代码--初学者
seq2seq
Attention-based sequence to sequence learning
dialogue-utterance-rewriter-1
ACL 2019论文复现：Improving Multi-turn Dialogue Modelling with Utterance ReWriter
OpenNMT-py
Open Source Neural Machine Translation in PyTorch
ChinsesNER-pytorch
基于BI-LSTM+CRF的中文命名实体识别 Pytorch_代码比较low, 不支持gpu目前
BERT-BiLSTM-CRF-NER
Tensorflow solution of NER task Using BiLSTM-CRF model with Google BERT Fine-tuning And private Server services
Time-Series-ARIMA-XGBOOST-RNN
Time series forecasting for individual household power prediction: ARIMA, xgboost, RNN
Anti-Anti-Spider
越来越多的网站具有反爬虫特性，有的用图片隐藏关键数据，有的使用反人类的验证码，建立反反爬虫的代码仓库，通过与不同特性的网站做斗争（无恶意）提高技术。（欢迎提交难以采集的网站）（因工作原因，项目暂停）
ccks2019_el
CCKS 2019 中文短文本实体链指比赛技术创新奖解决方案
ccks_baidu_entity_link
ccks_2019_百度实体链接技术比赛_第一名解决方案
sword-for-offer
使用Python3用优雅的方式实现《剑指Offer》中的题目。
named_entity_recognition
中文命名实体识别（包括多种模型：HMM，CRF，BiLSTM，BiLSTM+CRF的具体实现）
Ruban
深度学习识别验证码 Captcha
pointer-generator
Code for the ACL 2017 paper "Get To The Point: Summarization with Pointer-Generator Networks"
NER-LOC
中文命名实体识别& 中文命名实体检测 python实现 基于字+ 词位 分别使用tensorflow IDCNN+CRF 及 BiLSTM+CRF 搭配词性标注实现中文命名实体识别及命名实体检测
lrner
Improving Low Resource Named Entity Recognition using Cross-lingual Knowledge Transfer
debt_collection_model
用随机森林预测客户还款率