A 13B large language model developed by Baichuan Intelligent Technology
- artificial-intelligence
- chatgpt
- chinese
- gpt-4
108,094 visible repositories in the index
841–864 of 3,039 · Most stars
A 13B large language model developed by Baichuan Intelligent Technology
An Automatic Model Compression (AutoMC) framework for developing smaller and faster AI applications.
Docker image with Uvicorn managed by Gunicorn for high-performance FastAPI web applications in Python with performance auto-tuning.
Text preprocessing, representation and visualization from zero to hero.
This is an Open source intelligent framework ie an osint tool which gathers valid information about a phone number, user's email address, perform VIN Osint, and reverse, perform subdomain enumeration, able to find email from a name, and so much more. Best osint tool for Termux and linux
Proxy over your Docker socket to restrict which requests it accepts
MyTT将通达信,同花顺,文华麦语言等指标公式,最简移植到Python中,核心库单个文件,仅百行代码,十几个核心函数,神奇的实现所有常见技术指标算法(不依赖talib库)的纯python实现和转换通达信MACD,RSI,BOLL,ATR,KDJ,CCI,PSY等公式,全部基于pandas函数计算方法封装,简洁且高性能,能非常方便的应用在股票指标公式,股市期货量化框架分析,自动程序化交易,数字货币量化等领域,它是您最精练的股市量化工具。Python library with most stock market indicators.
Show, Attend, and Tell | a PyTorch Tutorial to Image Captioning
🔮 A refreshing functional take on deep learning, compatible with your favorite libraries
TranslatedAn Agent Skill that keeps a video's embedded subtitles, extracts frames precisely, and generates 3:4 long images for social media
build vless / trojan /shadowsocks proxies on python server,no need core
Reference client for Bitmessage: a P2P encrypted decentralised communication protocol:
:bomb: Impulse Denial-of-service ToolKit
Inject code into running Python processes
Reusable workflow library for Django
开源易用的中文离线OCR,识别率媲美大厂,并且提供了易用的web页面及web的接口,方便人类日常工作使用或者其他程序来调用~
Sane and flexible OpenAPI 3 schema generation for Django REST framework.
Multilingual Automatic Speech Recognition with word-level timestamps and confidence
Symbol-level code retrieval for AI agents: fetch the function you need, not the whole file. Runs locally. 96.2% fewer tokens per lookup on average than grep-and-read on our 15-lookup benchmark. Works with Claude Code, Cursor, Codex and any MCP client. Free for non-commercial use; commercial use needs a one-time license.
Translation for Trilium Notes. Trilium Notes 中文适配, 体验优化
Build, Store, and Distribute your Applications and Containers
Optical character recognition for Japanese text, with the main focus being Japanese manga
End-to-end Automatic Speech Recognition for Madarian and English in Tensorflow
A Unified Library for Parameter-Efficient and Modular Transfer Learning