Projects

### Overview: 三年面试五年模拟，AIGC/LLM/AI Agent算法工程师面试资源平台，涵盖AIGC、LLM大模型、AI Agent、具身智能、传统深度学习、计算机视觉、自然语言处理、机器学习、强化学习、大数据挖掘、世界模型、元宇宙、AGI等AI行业必备内容。 ### Key features: - **AIGC/LLM/AI Agent算法岗面试经验指南** - **AIGC图像创作与AI绘画基础** - **AI视频基础** - **大模型基础（精华版）** - **AI多模态基础** - **AI Agent基础** - **AI数字人基础** - **数学与物理本质原理基础** - **深度学习基础** - **机器学习基础** - **模型部署基础** - **经典模型** - **编程基础：Python** - **编程基础：C和C++** - **大厂高频面试题（实时更新）** - **数据结构与算法基础** - **计算机基础** - **AI行业职业生涯开放性问题** - **2026年AI算法岗求职群与学习交流社区** ### Tech stack: Python ### Why it matters: 本项目平台汇聚了AIGC时代众多一线AIGC/LLM/AI Agent算法专家们的行业经验与深度洞察，涵盖AIGC/LLM/AI Agent等前沿AI技术的完整知识架构、AI实战课程&教程、AI大厂内推、AI面试

Overview: This project provides a repository for BenCao [original name: HuaTuo], a model that has been fine-tuned with Chinese medical knowledge for instruction tuning. The repository includes models like LLaMA, Alpaca-Chinese, and Bloom, among others, and is based on the Chinese Medical Knowledge Instruction Tuning dataset. Key features: - Fine-tuned models with Chinese medical knowledge - Supports multiple models including LLaMA, Alpaca-Chinese, and Bloom - Provides a dataset for instruction tuning - Offers a way to run inference on the models Tech stack: Python Why it matters: This project is significant for researchers and developers looking to improve the performance of large language models in the medical field by leveraging Chinese medical knowledge. It provides a practical solution for instruction tuning and can be used to enhance the ability of models to answer medical questions accurately. Repository: SCIR-HI/Huatuo-Llama-Med-Chinese Primary language: Python GitHub stars: 5001

### Key features: - **Text2vec**: Text to Vector, representing text (words, sentences, paragraphs) as vector matrices. - **Model Implementations**: Supports Word2Vec, RankBM25, Sentence-BERT, CoSENT, and other text representation and similarity calculation models. - **Model Evaluation**: Compares model effectiveness in text semantic matching tasks. - **Model Versions**: Includes multiple versions like v1.2.9, v1.2.4, v1.2.2, and v1.2.1, each with specific features and improvements. ### Tech stack: - Python 3.5+ - Uses Hugging Face for models and datasets ### Why it matters: - Provides a powerful tool for text representation and similarity calculations, enhancing various NLP tasks. ### Overview: Text2vec is a comprehensive text representation tool that converts textual data into vector representations, including words, sentences, and paragraphs. It supports several advanced models like Word2Vec, RankBM25, Sentence-BERT, and CoSENT, and evaluates their performance in text semantic matching tasks. This tool is particularly useful for applications requiring high accuracy in text similarity and semantic analysis.

### Overview: This repository is a collection of machine learning and artificial intelligence resources, practice materials, and research projects. It serves as a comprehensive guide for anyone interested in the field, offering tutorials, courses, and projects that can be used for educational and practical purposes. ### Key Features: - Machine Learning Foundations - Machine Learning Techniques - Deep Learning - CS231n: Convolutional Neural Networks for Visual Recognition - Courses by Andrew Ng and Hsuan-Tien Lin ### Tech Stack: Python ### Why it Matters: This repository provides a wealth of resources for anyone looking to learn and practice machine learning and artificial intelligence. The tutorials and courses are designed to be accessible and practical, making it an excellent resource for both beginners and experienced practitioners.

Overview: Eko is a production-ready JavaScript framework designed for building reliable agents and workflows with natural language processing. It supports both browser and Node.js environments, enabling developers to create complex, multi-step workflows. Key features: - Pure JavaScript: Built for browsers and Node.js. - Multi-Agent: Unleash power with multiple Agents in one task. - Agent/Tool Flexibility: Customize new Agents and Tools in just one line. - Native MCP: Connects seamlessly with [Awesome MCP Servers](https://mcpservers.org/). - Dynamic LLM: Balance speed and performance with flexible model choices. - Human-in-the-loop: Intervene when it matters most. - Stream Planning: Dynamic rendering made easy. - Loop & Listener Tasks: Automate any repetitive task. - Observable Chain: Coming soon. - Native A2A: Coming soon. Tech stack: TypeScript. Why it matters: Eko is essential for developers looking to create robust, production-ready agents and workflows that can handle complex tasks and provide a seamless user experience across different environments. Repository: FellouAI/eko GitHub stars: 4966 GitHub description: Eko (Eko Keeps Operating) - Build Production-ready Agentic Workflow with Natural Language - eko.fellou.ai

### Overview: Porcupine is a highly-accurate and lightweight wake word engine designed for always-listening voice-enabled applications. It is built using deep neural networks trained in real-world environments, making it perfect for IoT devices, cross-platform compatibility, and scalability. With self-service training capabilities, developers can easily integrate it into their projects. ### Key Features: - **Cross-Platform Compatibility:** Works on Arm Cortex-M, STM32, Arduino, Raspberry Pi, Android, iOS, Chrome, Safari, Firefox, Edge, Linux, macOS, and Windows. - **Compact and Efficient:** Designed for IoT devices, it is computationally efficient and compact. - **Self-Service Training:** Developers can train custom wake word models using Picovoice Console. - **Scalable Detection:** Detects multiple always-listening voice commands without added runtime footprint. - **Cross-Platform Support:** Compatible with various languages and platforms. ### Tech Stack: Python ### Why it Matters: Porcupine is a powerful tool for developers looking to create voice-enabled applications that can always listen for commands. Its compact and efficient design makes it ideal for IoT devices, while its self-service training capabilities simplify the integration process. Whether you're developing for Android, iOS, or web, Porcupine offers a reliable and scalable solution for wake word detection.