reed's repositories
Megatron-LM
Ongoing research training transformer models at scale
Characterize-Anything
Characterize Anything: A Wondrous Chemical Reaction between vision models and AI Characters
cskefu
🌲 春松客服，智能客服系统，开源客服系统 ，机器人客服，客服系统开发框架，多渠道
ChineseAiDungeon
中文版ai地牢
flare
Flare是广泛投产于腾讯广告后台的现代化C++开发框架，包含了基础库、RPC、各种客户端等。主要特点为易用性强、长尾延迟低。
graph-learn
An Industrial Graph Neural Network Framework
mtSecKill
京东茅台抢购
chatbot.catalog.customer-service
💊 智能客服、聊天机器人的应用算法
nlp_chinese_corpus
大规模中文自然语言处理语料 Large Scale Chinese Corpus for NLP
AIDungeon
Infinite adventures await!
storybro
A community maintained fork of AI Dungeon 2 by Nick Walton
mxnet
Lightweight, Portable, Flexible Distributed/Mobile Deep Learning with Dynamic, Mutation-aware Dataflow Dep Scheduler; for Python, R, Julia, Scala, Go, Javascript and more
MXNet.cpp
CPP wrapper for MXNet interface
reinforcement-learning-an-introduction
Python code for Reinforcement Learning: An Introduction
chainer
A flexible framework of neural networks for deep learning
Learn-Git-in-30-days
這是 Will 保哥在 2013 第 6 屆 iT 邦幫忙鐵人賽年度大獎的得獎著作【30 天精通 Git 版本控管】，歡迎大家 fork 我，如果有看見任何文字勘誤，也歡迎利用 pull request 來通知我修正，謝謝！
simple_dqn
Simple deep Q-learning agent.
QuantBox.Data
二进制行情存储格式
bfpy
主程序：https://github.com/sunwangme/bftrader
deep_trader
This project uses reinforcement learning on stock market and agent tries to learn trading. The goal is to check if the agent can learn to read tape. The project is dedicated to hero in life great Jesse Livermore.
bftrader
多进程，稳定性好，方便开发，支持python/golang写策略！
pyalgotrade-cn
pyalgotrade tailored for Chinese stock market
async-rl-1
Tensorflow + Keras + OpenAI Gym implementation of 1-step Q Learning from "Asynchronous Methods for Deep Reinforcement Learning"