Stars
Large Language Model Text Generation Inference
The RedPajama-Data repository contains code for preparing large datasets for training large language models.
🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training.
Pre-trained Chinese ELECTRA（中文ELECTRA预训练模型）
Large-scale Self-supervised Pre-training Across Tasks, Languages, and Modalities
The most comprehensive database of Chinese poetry 🧶最全中华古诗词数据库, 唐宋两朝近一万四千古诗人, 接近5.5万首唐诗加26万宋诗. 两宋时期1564位词人，21050首词。
Python package built to ease deep learning on graph, on top of existing DL frameworks.
A LITE BERT FOR SELF-SUPERVISED LEARNING OF LANGUAGE REPRESENTATIONS, 海量中文预训练ALBERT模型
TensorFlow code and pre-trained models for BERT
all kinds of text classification models and more with deep learning
Google Research
An Open-Source Package for Knowledge Embedding (KE)
Multi-layer Recurrent Neural Networks (LSTM, RNN) for word-level language models in Python using TensorFlow.
An Open Source Machine Learning Framework for Everyone
Example TensorFlow codes and Caicloud TensorFlow as a Service dev environment.
A ShadowsocksR client for Android
A platform for building proxies to bypass network restrictions.
Air Quality Index (AQI) history database for mainland China
Scrapy project to scrape public web directories (educational) [DEPRECATED]
A quantum-safe, secure tunnel built on QPP, KCP, FEC, and multiplexing.
Interactive Data Visualization in the browser, from Python
ZeroNet - Decentralized websites using Bitcoin crypto and BitTorrent network
A VPN implemention in golang, with crypto and obfuscation in nature.