cgoal
Follow
Stars
OpenAI DeepResearch alternative, An AI-driven research system that performs comprehensive, iterative research on any topic using multiple search engines and LLMs.
🚀🚀 「大模型」2小时完全从0训练26M的小参数GPT！🌏 Train a 26M-parameter GPT from scratch in just 2h!
A Flexible Framework for Experiencing Cutting-edge LLM Inference Optimizations
"MiniRAG: Making RAG Simpler with Small and Free Language Models"
Fully open reproduction of DeepSeek-R1
[🔥updating ...] AI 自动量化交易机器人(完全本地部署) AI-powered Quantitative Investment Research Platform. 📃 online docs: https://ufund-me.github.io/Qbot ✨ :news: qbot-mini: https://github.com/Charmve/iQuant
Official github repository for Fast Artificial Neural Network Library (FANN)
一个简单的本地网页界面，使用ChatTTS将文字合成为语音，同时支持对外提供API接口。A simple native web interface that uses ChatTTS to synthesize text into speech, along with support for external API interfaces.
《开源大模型食用指南》针对中国宝宝量身打造的基于Linux环境快速微调（全参数/Lora）、部署国内外开源大模型（LLM）/多模态大模型（MLLM）教程
Gathers machine learning and deep learning models for Stock forecasting including trading bots and simulations
提取微信聊天记录，将其导出成HTML、Word、Excel文档永久保存，对聊天记录进行分析生成年度聊天报告，用聊天数据训练专属于个人的AI聊天助手
HQChart - H5, 微信小程序 沪深/港股/数字货币/期货/美股 K线图(kline),走势图,缩放,拖拽,十字光标,画图工具,截图,筹码图. 分析家语法,通达信语法,(麦语法),第3方数据替换接口
Official repository of FaceLit: Neural 3D Relightable Faces (CVPR 2023)
[CVPR'24 Highlight] Official PyTorch implementation of CoDeF: Content Deformation Fields for Temporally Consistent Video Processing
openctp提供CTP股票期权、中泰证券XTP、华鑫证券奇点TORA、东方证券OST、东方财富证券EMT、盈透证券TWS、易盛TAP、量投QDP等各通道的CTPAPI兼容接口，CTP程序可以无缝对接各股票柜台。openctp也提供了一套基于TTS交易系统的模拟环境，同样提供了CTPAPI兼容接口，不仅支持国内期货与期权全品种，也支持A股股票、基金、债券以及股票期权模拟交易，可以替代Simn…
获取斗鱼&虎牙&哔哩哔哩&抖音&快手等 58 个直播平台的真实流媒体地址(直播源)和弹幕，直播源可在 PotPlayer、flv.js 等播放器中播放。
Windows GUI Automation with Python (based on text properties)
Robust Speech Recognition via Large-Scale Weak Supervision
Image inpainting tool powered by SOTA AI Model. Remove any unwanted object, defect, people from your pictures or erase and replace(powered by stable diffusion) any thing on your pictures.
超轻量级中文ocr，支持竖排文字识别, 支持ncnn、mnn、tnn推理 ( dbnet(1.8M) + crnn(2.5M) + anglenet(378KB)) 总模型仅4.7M