ericxsun Goto Github PK

gpt2

An implementation of training for GPT2, supports TPUs

gradient-checkpointing

Make huge neural nets fit in memory

grafana

The tool for beautiful monitoring and metric analytics & dashboards for Graphite, InfluxDB & Prometheus & More

grid

Chinese Tokenizer; New words Finder. 中文三段式机械分词算法; 未登录新词发现算法

gryphon

Powerful, proven, and extensible framework for building trading strategies at any frequency, with a focus on crypto currencies. Battle-tested with billions traded.

gts-engine

GTS Engine: A powerful NLU Training System。GTS引擎（GTS-Engine）是一款开箱即用且性能强大的自然语言理解引擎，聚焦于小样本任务，能够仅用小样本就能自动化生产NLP模型。

guoqiao-vimrc

guoqiao's vimrc

hadooptools

Tools used in hadoop or hive

hanlp

汉语言处理包 分词 词性标注 命名实体识别 依存句法分析 关键词提取 自动摘要 短语提取 拼音 简繁 Lucene插件

hao

好东西传送门

health-search-tutorial

Repository for the Health Search Tutorial

hetu

低代码平台, 可视化编辑器，单手打代码，解放你的双手

hexo-pluskid-theme

A hexo theme that follow the style of pluskid's blog

hexo-theme-next

customized hexo-theme-next

hh-rlhf

Human preference data for "Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback"

hive-extensions-from-think-big-analytics

Reusable code for Hive

home_surveillance

Home surveillance system with facial recognition

homemade-machine-learning

🤖 Python examples of popular machine learning algorithms with interactive Jupyter demos and math being explained

hortonworksoperationsworkshop

hosemicrf

High-order Semi-Markov Conditional Random Field

hubot

A customizable life embetterment robot.

hugegraph

HugeGraph Database core component, including graph engine, API, and built-in backends

human-eval

Code for the paper "Evaluating Large Language Models Trained on Code"

hyperlpr

高性能中文车牌识别 High Performance Chinese License Plate Recognition Framework.

hyperscan

High-performance regular expression matching library

icalk

xmpp client base on gloox and gtkmm

iclr15

Sentiment analysis with Ensemble

iclr2016

Python code for training all models in the ICLR paper, "Towards Universal Paraphrastic Sentence Embeddings". These models achieve strong performance on semantic similarity tasks without any training or tuning on the training data for those tasks. They also can produce features that are at least as discriminative as skip-thought vectors for semantic similarity tasks at a minimum. Moreover, this code can achieve state-of-the-art results on entailment and sentiment tasks.

igraph

Library for the analysis of networks

ijcai-18-top2-single-mole-solution

复赛第二名单模型方案，没有特征选择没有调参LGB单模型857个特征