AI open source rankings.
A Python toolbox for performing gradient-free optimization
中文公开聊天语料库
Foundational model for human-like, expressive TTS
Flickr-Faces-HQ Dataset (FFHQ)
ChatGPT资料汇总学习，持续更新......
A curated list of resources for using LLMs to develop more competitive grant applications.
Everything you need to know to build your own RAG application
♾️ CML - Continuous Machine Learning | CI/CD for ML
⚡️ Python client for the ChatGPT API with, conversation tracking, proxy support and more.
PyTorch code and models for V-JEPA self-supervised learning from video.
Deep Learning GPU Training System
Evolutionary Scale Modeling (esm): Pretrained language models for proteins
Use AI to translate code from one language to another.
A curated list of automated machine learning papers, articles, tutorials, slides and projects
State of the Art Natural Language Processing
g1: Using Llama-3.1 70b on Groq to create o1-like reasoning chains
A client implementation for ChatGPT and Bing AI. Available as a Node.js module, REST API server, and CLI app.
Deep Learning Tutorial notes and code. See the wiki for more info.
📈 目前最大的工业缺陷检测数据库及论文集 Constantly summarizing open source dataset and critical papers in the field of surface defect research which are of great importance.
🔥 A library for cropping image in a smart way that can identify the border and correct the cropped image. 智能图片裁剪框架。自动识别边框，手动调节选区，使用透视变换裁剪并矫正选区；适用于身份证，名片，文档等照片的裁剪。
A system for agentic LLM-powered data processing and ETL
Llama3-中文后训练版
Malwoverview is a first response tool for threat hunting across VirusTotal, Hybrid Analysis, URLHaus, Polyswarm, Malshare, Alien Vault, Malpedia, Malware Bazaar, ThreatFox, Triage, IPInfo, Shodan, AbuseIPDB, GreyNoise, URLScan.io, Whois/RDAP, NIST, and VulnCheck. Supports LLM enrichment, IOC extraction, YARA scanning, and Android analysis.
Language model tokenization at GB/s
NoFWL Desktop Application
Distilled variant of Whisper for speech recognition. 6x faster, 50% smaller, within 1% word error rate.
Fengshenbang-LM(封神榜大模型)是IDEA研究院认知计算与自然语言研究中心主导的大模型开源体系，成为中文AIGC和认知智能的基础设施。
an agentic cms self-hosted on cloudflare, for podcasts, blogs, photos, videos, documents, and curated urls.