luozhouyang

python-string-similarity

A library implementing different string similarity and distance measures using Python.

transformers-keras

Transformer-based models implemented in tensorflow 2.x(using keras).

keras-crf

A more elegant and convenient CRF built on tensorflow-addons.

deepseg

Chinese word segmentation in tensorflow 2.x

dssm

Deep Semantics Similarity Model in tensorflow.

DeepSE

Sentence Embeddings using Deep Nerual Networks in PRODUCTION!

nlp-datasets

A dataset utils repository based on tf.data API.

matchpyramid

MatchPyramid implementation in tensorflow 2.x (Keras).

pycorrector

pycorrector is a toolkit for text error correction. 文本纠错，Kenlm，Seq2Seq_Attention，BERT，MacBERT，ELECTRA，ERNIE，Transformer等模型实现，开箱即用。

bert

TensorFlow code and pre-trained models for BERT

better-jieba

更好的jieba java版

chinese-spelling-correction

CLUE-baseline

CLUE benchmark baseline in PyTorch.

d2l-tf

Dive into Deep Learning 代码的TensorFlow实现

datasets

🤗 The largest hub of ready-to-use datasets for ML models with fast, easy-to-use and efficient data manipulation tools

GPT2-Chinese

Chinese version of GPT2 training code, using BERT tokenizer.

haikus-for-codespaces

java-saml

Java SAML toolkit

kenlm

KenLM: Faster and Smaller Language Model Queries

kong

🦍 The Cloud-Native API Gateway

kubernetes-ingress-controller

:gorilla: Kong for Kubernetes: The official Ingress Controller for Kubernetes.

lightning

luozhouyang-deprecated.github.io

Welcome to my GitHub pages.

luozhouyang.github.io

melody

A collection of business modules for web applications, in Python

models

Models and examples built with TensorFlow

PaddleNLP

Easy-to-use and Fast NLP library with awesome model zoo, supporting wide-range of NLP tasks from research to industrial applications.

sweetpie

A useful toolbox for Python!

tokenizers

💥 Fast State-of-the-Art Tokenizers optimized for Research and Production

transformers-keras-doc

Documents for https://github.com/luozhouyang/transformers-keras