spancer's repositories
bigdata-docker-compose
Deploy bigdata platform using docker compose. Big data components include hadoop, hive, hbase, presto, flink, es, kafka, etc.
bigdata-docker-builds
Docker images for building hadoop3.2, hive 3.1, hbase2.3, presto 0.247, flink1.11.3 on yarn, etc.
alpaca-lora
Instruct-tune LLaMA on consumer hardware
awesome-chatgpt-prompts-zh
ChatGPT 中文调教指南。各种场景使用指南。学习怎么让它听你的话。
ChatGLM-6B
ChatGLM-6B: An Open Bilingual Dialogue Language Model | 开源双语对话语言模型
ChatGPT-Admin-Web
带有用户管理和后台管理系统的 ChatGPT WebUI
ChatGPT-Midjourney
🍭 一键拥有你自己的 ChatGPT+Midjourney 网页服务 | Own your own ChatGPT+Midjourney web service with one click
ChatGPT-Next-Web
一键拥有你自己的 ChatGPT 网页服务。 One-Click to deploy your own ChatGPT web UI.
chatgpt-on-wechat
Wechat robot based on ChatGPT, which using OpenAI api and itchat library. 使用ChatGPT搭建微信聊天机器人，基于 GPT3.5/GPT4.0/Claude/文心一言/讯飞星火/LinkAI，支持个人微信、公众号、企业微信部署，能处理文本、语音和图片，访问操作系统和互联网，支持基于知识库定制专属机器人。
dagster-io-managers-tests
dagster io managers test, including minio, trino, spark, pg, duckdb, etc.
data-stack
modern data stack
eclipse-chatgpt-plugin
An Eclipse plugin that integrates with ChatGPT
iceberg-rest-catalog
Apache iceberg rest catalog, a distribute rest catalog server built on top of netty, using postgresql to manage iceberg metadata.
llama
Inference code for LLaMA models
metahuman_overview
数字人资料整理
MLOps1
Master Thesis Project - Open Source MLOps: How to Unlock the Potential of Machine Learning
modern-data-stack-docker
modern data stack in docker compose
ollama
Get up and running with Llama 2, Mistral, Gemma, and other large language models.
Open-Sora
Open-Sora: Democratizing Efficient Video Production for All
pygwalker
PyGWalker: Turn your pandas dataframe into a Tableau-style User Interface for visual analysis
qdrant
Qdrant - Vector Database for the next generation of AI applications. Also available in the cloud https://cloud.qdrant.io/
QGIS
QGIS is a free, open source, cross platform (lin/win/mac) geographical information system (GIS)
stock
stock股票系统.爬取stock股票关键数据,计算stock股票各种指标,识别stock股票K线形态,内置多种stock股票策略,支持stock股票验证回测及stock股票自动交易,是量化投资工具。captures key daily data of stocks, calculates various stock indicators, K-line pattern recognition, has a variety of built-in stock selection strategies, stock selection verification back test, Automated Trading. quantitative investment tool.
tools-Auto_Mac_Author
爬取b站热榜，人工智能写文案，自动生成复数麦克阿瑟视频 next_step: 字幕自动换行+输出文案副本
tools-gen-txt-to-image
一款文生视频应用，用于小说推文，生成漫画等视频。使用主流大模型，结合Stable Diffusion，实现文生图，图生视频本地化私有部署。
tools-video-subtitle-remover
基于AI的图片/视频硬字幕去除、文本水印去除，无损分辨率生成去字幕、去水印后的图片/视频文件。无需申请第三方API，本地实现。AI-based tool for removing hard-coded subtitles and text-like watermarks from videos or Pictures.
win11-
CloudMoe Windows 10/11 Activation Toolkit get digital license, the best open source Win 10/11 activator in GitHub. GitHub 上最棒的开源 Win10/Win11 数字权利（数字许可证）激活工具！
WindTerm
A professional cross-platform SSH/Sftp/Shell/Telnet/Serial terminal.
Youtube-ETL-Pipeline
💜🌈📊 A Data Engineering Project that implements an ETL data pipeline using Dagster, Apache Spark, Streamlit, MinIO, Metabase, Dbt, Polars, Docker 🌺
zero_nlp
中文nlp解决方案(大模型、数据、模型、训练、推理)