Coding & Development

Awesome-Chinese-LLM is a comprehensive open-source repository dedicated to Chinese large language models (LLMs). The collection prioritizes models that are smaller in scale, suitable for private deployment, and have lower training costs, making them accessible to a wider range of users. It encompasses a variety of resources, including foundational base models like ChatGLM, LLaMA, Baichuan, and Qwen, as well as models fine-tuned for vertical domains such as healthcare, law, finance, and education. Beyond models, the repository also provides valuable datasets for pre-training, SFT, and preference alignment, along with tutorials covering LLM basics, prompt engineering, application development, and practical implementation. This makes it an invaluable resource for researchers, developers, and practitioners working with Chinese LLMs.

Awesome-gptlike-shellsite is a comprehensive GitHub repository designed to guide users through the process of building and monetizing AI-powered applications, particularly focusing on 'shell sites' (套壳站) and API integration. It offers a curated list of open-source shell site projects, including popular options like ChatGPT Next Web and Lobe Chat, along with recommendations for deployment and commercialization. The resource also details various API providers, comparing pricing for models like GPT-3.5-turbo and GPT-4, and addresses common questions regarding deployment, commercial use, API integration (including API relay services), and cloud server selection. It serves as a one-stop guide for individuals looking to leverage AI technologies for side hustles or business ventures.

Fairlearn is a Python package designed to empower developers of artificial intelligence (AI) systems to assess and mitigate unfairness in their machine learning models. It offers a comprehensive suite of tools, including metrics for identifying groups negatively impacted by a model and algorithms for mitigating unfairness across various AI tasks and fairness definitions. The package focuses on addressing allocation harms (e.g., in hiring or lending) and quality-of-service harms, following a group fairness approach. Fairlearn enables users to compare multiple models based on fairness and accuracy metrics, providing a robust framework for responsible AI development. It is open-source and includes Jupyter notebooks for practical usage examples.

DeepLearning is an open-source project that offers a comprehensive Python-based resource for understanding the "Deep Learning" book (also known as the 'Flower Book'). It provides detailed mathematical derivations, in-depth principle analysis, and source-level code implementations using primarily the NumPy library. The project covers foundational concepts like linear algebra, probability theory, and machine learning basics, alongside advanced deep learning techniques such as deep feedforward networks, regularization, optimization algorithms, and convolutional networks. It aims to clarify complex topics that might be difficult to grasp from the book alone, making it an invaluable tool for students and researchers in the field.

DeepLearningForTSF is an open-source GitHub repository dedicated to deep learning techniques for time series forecasting. It provides comprehensive resources and code examples for predicting trends and seasonality using methods like SARIMA and triple exponential smoothing. The repository includes detailed guides on hyperparameter optimization and the development of various deep learning models, such as Multi-Layer Perceptrons (MLP), Convolutional Neural Networks (CNN), and Long Short-Term Memory (LSTM) networks. It covers different model types, including stacked LSTMs, bidirectional LSTMs, CNN-LSTMs, and Encoder-Decoder LSTMs, for both univariate and multivariate time series forecasting. Additionally, it features case studies on human activity recognition, indoor movement classification, air pollution prediction, and electricity consumption forecasting, making it a valuable resource for researchers and developers in the field.

DeepMatcher is a Python package designed for entity and text matching tasks using deep learning. It offers built-in neural networks and essential utilities, enabling users to train and apply advanced deep learning models for entity matching with less than 10 lines of code. The package supports data processing for training, validation, and test CSV data, model definition with customizable neural network architectures, and model training and application. Its modular design allows for easy customization of subcomponents, making it flexible for various matching tasks beyond traditional entity matching, such as question answering. DeepMatcher is ideal for researchers and developers looking to leverage deep learning for data integration and record linkage.

EduChat is an open-source educational chat model developed by ICALK at East China Normal University, designed to support personalized learning and holistic development. It integrates diverse educational data with methods like instruction fine-tuning and value alignment to offer rich functionalities such as automatic question generation, homework grading, emotional support, and course tutoring. The project has evolved through several versions, culminating in EduChat-R1, which focuses on "Thinking before teaching" to provide intelligent educational solutions. It also includes specialized products like MindCare@EduChat for psychological assessment, Shell@EduChat for value alignment, and AiBoard@EduChat as an AI teaching assistant, catering to the needs of teachers, students, and parents.

Elasticsearch is a powerful, open-source distributed search and analytics engine, serving as a scalable data store and vector database optimized for speed and relevance in production-scale workloads. It forms the foundation of Elastic’s open Stack platform, allowing users to search in near real-time over massive datasets, perform vector searches, and integrate with generative AI applications. Key use cases include Retrieval Augmented Generation (RAG), full-text search, logs, metrics, application performance monitoring (APM), and security logs. Users can easily set up Elasticsearch with managed deployments on Elastic Cloud or install and manage it themselves. It supports various language clients and REST APIs for interaction, making it versatile for different development environments.

deep-learning-resources is an open-source GitHub repository that curates a comprehensive collection of deep learning materials. It is designed to guide learners from foundational concepts to advanced topics, with content continuously updated. The repository includes interactive playgrounds for hands-on experience, a curated list of online courses from leading institutions like Stanford and MIT, practical tools such as Colaboratory and TensorBoard, and a selection of high-quality articles and classic papers. It serves as a valuable hub for anyone looking to start or deepen their understanding of deep learning, providing structured learning paths and practical applications.

deep-learning-with-keras-notebooks is an open-source collection of Jupyter notebooks designed to help users learn and apply Keras for deep learning. This repository provides a wide range of examples, from image processing and augmentation to advanced topics like object detection with YOLOv2 and natural language processing with word embeddings. The notebooks cover practical applications such as image classification (e.g., traffic signs, fashion MNIST), facial recognition, and captcha breaking. It's an excellent resource for students and developers looking to gain hands-on experience with Keras and deep learning concepts, offering clear, runnable examples for various tasks.

Firefly is a comprehensive open-source project designed for training large language models, offering support for pre-training, instruction fine-tuning, and DPO (Direct Preference Optimization). It is compatible with numerous mainstream models such as Qwen2.5, Qwen2, Yi1.5, Phi-3, Llama3, Gemma, MiniCPM, and many others. The platform facilitates full parameter training, as well as efficient training methods like LoRA and QLoRA, making it accessible even with limited computational resources. Firefly also integrates with Unsloth for accelerated training and reduced VRAM usage, and provides curated instruction fine-tuning datasets. It offers pre-trained Firefly series models and has demonstrated effectiveness on the Open LLM Leaderboard.

electerm is a versatile, open-source terminal client designed for developers and system administrators, supporting a wide array of connection types including SSH, SFTP, FTP, Telnet, serial port, RDP, VNC, and Spice. Available across Linux, macOS, and Windows, it offers features like global hotkeys, multi-language support, and the ability to directly edit small remote files. A key differentiator is its AI assistant integration, supporting DeepSeek, OpenAI, and other AI APIs, to provide command suggestions, assist with script writing, and explain terminal content. It also includes a Model Context Protocol (MCP) widget for AI assistants and external tools, enhancing productivity for technical users.

food-101-keras is an open-source deep learning project hosted on GitHub, designed for food classification using Keras and Tensorflow. It leverages Convolutional Neural Networks (CNNs) to identify 101 different food classes from the Food-101 dataset. The project demonstrates how to fine-tune a pre-trained Google InceptionV3 model, achieving high accuracy in food recognition. It includes detailed steps for data loading, preprocessing, image augmentation, model training, and evaluation. The repository also provides insights into handling large datasets and exporting models for mobile applications, making it a valuable resource for machine learning practitioners and researchers interested in computer vision and food recognition.

LAW-GPT is an open-source Chinese legal large language model designed to provide professional and reliable answers to legal questions. The project aims to make legal assistance accessible to everyone, much like search engines or express delivery services. It is built by fine-tuning ChatGLM-6B LoRA with a 16-bit instruction set. The training data includes existing legal Q&A datasets and high-quality legal text Q&A constructed using self-instruct methods based on legal provisions and real case guidance. This approach significantly enhances the model's performance in the legal domain, improving the reliability and professionalism of its answers by providing legal basis for its responses. The project also includes a retrieval function for more accurate answers.

Hephaestus is a semi-structured agentic framework designed for building dynamic AI workflows. Unlike traditional frameworks that require predefined instructions for every scenario, Hephaestus allows agents to discover and create tasks based on their findings. It defines logical phase types (e.g., Plan, Implement, Test) and lets agents spawn new tasks in any phase, leading to self-branching workflows. This approach ensures adaptability, as the workflow evolves based on actual discoveries rather than anticipated scenarios. It includes features like real-time monitoring, Kanban board coordination, and dependency tracking, making it ideal for complex software development projects where agents can identify optimizations or bugs and create new work to address them.

konlpy is an open-source Python package specifically designed for Korean natural language processing (NLP). It provides essential functionalities for analyzing Korean text, including morphological analysis and part-of-speech tagging. This makes it a valuable tool for developers and researchers who need to process and understand the nuances of the Korean language in their applications or studies. The package is built to be user-friendly, facilitating the integration of advanced NLP capabilities into various projects. Its open-source nature encourages community contributions and ensures continuous development and improvement, making it a robust choice for Korean NLP tasks.

langchain-kr offers a comprehensive Korean tutorial for LangChain, built upon the official LangChain documentation, cookbooks, and practical examples. This resource is designed to help Korean speakers understand and utilize LangChain with greater ease and effectiveness. The tutorial covers a wide range of topics, from basic concepts and prompt engineering to advanced techniques like RAG, LangChain Expression Language (LCEL), and multi-agent collaboration with LangGraph. It includes practical examples, YouTube video explanations, and blog posts, making it a valuable learning resource for anyone looking to master LangChain in Korean. The project is open-source and encourages contributions from the community.

MacBERT is a sophisticated pre-trained language model specifically designed for Chinese Natural Language Processing (NLP). It builds upon the foundational BERT architecture by incorporating a novel Masked and Corrected (Mac) language model pre-training task. This innovative approach aims to mitigate the common 'pre-training-downstream task' inconsistency, a challenge where the [MASK] token used during pre-training is absent in real-world downstream applications. MacBERT addresses this by replacing [MASK] tokens with similar words, derived using a synonyms toolkit based on word2vec similarity. It also integrates Whole Word Masking (WWM) and N-gram masking techniques. The model maintains full compatibility with BERT, allowing for seamless integration into existing NLP workflows without code modification. MacBERT has demonstrated significant performance enhancements across various Chinese NLP tasks, including extractive question answering, natural language inference, sentiment classification, and sentence pair matching.

go-proxy-bingai is an open-source demonstration site for Microsoft's New Bing, built with Vue3 and Go. It aims to provide a consistent user interface experience similar to the official New Bing, while also supporting ChatGPT prompts. This tool is particularly useful for users in regions where access to the official Bing AI might be restricted, offering a viable alternative. It allows for local deployment and can be configured with various environment variables for customization, including proxy settings and user cookies for advanced features like image creation. The project emphasizes ease of deployment with options like Docker, Railway, Vercel, and Render, and includes a separate chat server deployment option for enhanced stability and availability.

gpt-assistant-android is an open-source, full-featured GPT assistant designed for Android devices. It offers convenient activation via volume keys for voice interaction, enabling seamless communication with the AI. Key capabilities include internet access for real-time information, photo capture, and comprehensive document parsing for formats like TXT, PDF, DOCX, PPTX, and XLSX. The tool also features intelligent templates for customized interfaces, multiple voice input/output options, and an experimental agent mode that allows the AI to control phone functions like clicking and scrolling. Users can configure their own OpenAI API keys or use third-party forwarding services, making it a versatile and powerful personal assistant for Android users.

PrimeAI specializes in leveraging AI, Machine Learning, and data engineering to provide advanced data insights for businesses. The platform offers services in AI/ML & Data Science, Professional Services, Data & Infrastructure, and Managed Services. PrimeAI helps organizations transform complex datasets into actionable intelligence, build or rebuild cloud-based data warehouses, and supplement technology teams with industry experts. Their solutions are designed to improve efficiency and profitability, with a focus on industries such as Transportation & Logistics, Industrial Services, Travel & Hospitality, Healthcare & Life Sciences, and Retail.

Llama-Chinese is a vibrant open-source community dedicated to advancing Llama large language models, with a strong emphasis on Chinese language optimization. The platform serves as a central hub for developers and enthusiasts, offering a wealth of learning materials, resources, and a collaborative environment to foster the best open-source Llama ecosystem. It supports the development and deployment of Llama models for various applications, including commercial use. The community provides access to pre-trained models like Atom, offers tools for fine-tuning and quantization, and facilitates deployment acceleration. Additionally, it hosts a forum for technical discussions, provides computing resources, and shares diverse datasets, making it an invaluable resource for anyone interested in Chinese AI models.

LLM-quickstart is an open-source guide designed to help users quickly get started with large language models (LLMs). It offers comprehensive resources for both theoretical learning and practical fine-tuning of LLMs. The guide provides detailed instructions for setting up a development environment, including installing necessary software like CUDA Toolkit, Miniconda, and Jupyter Lab. It also outlines hardware requirements, specifically recommending a GPU with at least 16GB of VRAM, such as an NVIDIA Tesla T4. The project includes practical examples and configurations for working with various LLM components and frameworks, making it a valuable resource for those looking to dive into the world of large language models.

Writely, developed by AIBY, is an AI-powered mobile application designed to enhance communication efficiency and enjoyment. It integrates an AI keyboard and writing assistant directly into the user's mobile device, providing smart assistance for a wide range of writing tasks. From crafting messages to generating content, Writely aims to alleviate writing stress and streamline daily communication. While the specific features of Writely are not detailed on the AIBY homepage, AIBY specializes in leveraging AI, market analysis, and product management to deliver high-quality consumer apps. Given AIBY's portfolio includes AI chatbots and content generators, Writely likely offers similar AI-driven text generation and enhancement capabilities.