Research & Education

LLMBook-zh.github.io is an open-source project providing a comprehensive Chinese textbook titled "大语言模型" (Large Language Models). Authored by Zhao Xin, Li Junyi, Zhou Kun, Tang Tianyi, and Wen Jirong, this book aims to popularize and disseminate the latest advancements in large model technology. It offers a systematic framework and roadmap for LLM technologies, making it ideal for beginners with a background in deep learning. The project includes PDF courseware, code snippets on GitHub, and related teaching videos on Bilibili, serving as a valuable resource for both academic study and practical application. The content covers essential topics such as pre-training, fine-tuning, alignment, and prompt engineering, drawing from the authors' extensive research and practical experience in developing large models.

LLMs_interview_notes is an open-source repository designed to help algorithm engineers prepare for interviews related to Large Language Models (LLMs). The resource compiles learning notes and materials based on personal interview experiences, covering a wide array of LLM topics. It includes detailed sections on LLM fundamentals, advanced attention mechanisms, transformer operations, loss functions, similarity functions, generative LLMs, fine-tuning strategies, LangChain, and Retrieval-Augmented Generation (RAG). This comprehensive collection aims to provide a structured approach to understanding and answering common interview questions in the rapidly evolving field of LLMs.

Crane is an AI-powered Chrome extension designed to function as a personal knowledge base. It automatically tracks what you read across various sources like websites, articles, and documents, then generates a daily newsletter summarizing the key information from the previous day. This feature helps users improve knowledge retention, stay updated on industry news, and efficiently organize their personal knowledge for future reference. Crane uses AI to extract crucial information and create concise summaries, making it an effective tool for anyone looking to manage and synthesize their daily reading.

Unifie is an AI-powered platform designed to enhance knowledge management and streamline digital workflows. It aims to supercharge knowledge journeys by leveraging artificial intelligence, helping users to manage information more efficiently and collaborate effectively. The platform focuses on providing a unified approach to digital processes, making it easier for individuals and teams to organize, access, and utilize their knowledge base. Unifie's core purpose is to simplify complex information landscapes, ensuring that valuable insights are readily available and actionable, ultimately boosting productivity and fostering better decision-making within various contexts.

awesome-gpt4o-images is a curated collection of images and prompts generated by OpenAI's GPT-4o and gpt-image-1 models. This repository serves as a comprehensive showcase of advanced AI image generation capabilities, featuring visuals created with ChatGPT and Sora. It offers a rich source of inspiration for AI enthusiasts and creatives, demonstrating the versatility of GPT-4o in generating high-quality images from text prompts, supporting image-to-image editing, and enabling advanced operations like local modifications, style transfers, and multi-image blending. The collection highlights GPT-4o's multimodal understanding, precise output generation, diverse style options, realistic composition, and rapid iterative editing.

HuggingLLM is an open-source project dedicated to making Large Language Models (LLMs) accessible and understandable for a broad audience, including those without a deep NLP or algorithm background. The project aims to introduce the principles, usage, and applications of ChatGPT and other LLMs, enabling users to leverage these powerful AI tools to create their own AI products and services. It provides detailed learning guides, practical examples, and code implementations focusing on how to use LLM APIs for various tasks such as QA, text classification, and text generation. The project emphasizes adapting to the rapidly evolving AI landscape and encourages hands-on practice with both international and domestic LLM APIs like GLM and Qwen. It's designed for learners with some programming experience who want to apply LLMs to solve real-world problems.

NodeLand is a collaborative visual workspace designed for individuals and teams to brainstorm, organize ideas, and engage in structured thinking on an infinite canvas. It allows users to build visual knowledge management systems where each node can hold notes, files, links, and evidence, keeping decisions and next steps connected. The platform offers AI-assisted summarization to convert complex documents, reports, transcripts, and videos into clear, structured visual maps, making it easier to understand and act on information. NodeLand supports visual planning, research structuring, initiative planning, and managing shared knowledge, reducing cognitive overload and improving decision-making for professionals and teams.

FindTheChatGPTer is a valuable resource for anyone interested in exploring open-source alternatives to ChatGPT and GPT-4. This project compiles a continuously updated list of text-based and multi-modal large language models, offering insights into their technical details, capabilities, and GitHub links. It covers a range of models, from those developed independently to those based on existing architectures like LLAMA, and includes discussions on their training methodologies such as supervised fine-tuning and reinforcement learning from human feedback (RLHF). The project also highlights models supporting various languages, multi-modal functionalities, and different parameter scales, making it a comprehensive guide for developers, researchers, and enthusiasts looking to understand and utilize the evolving landscape of open-source AI.

llm_interview_note is an open-source GitHub repository designed to be a comprehensive resource for individuals preparing for interviews in the field of large language models (LLMs) and algorithm engineering. It meticulously compiles knowledge and common interview questions, drawing from various online resources. The repository covers fundamental LLM concepts, architectural details like Transformer models and attention mechanisms, training datasets, distributed training, supervised fine-tuning, inference optimization, reinforcement learning (including RLHF and DPO), retrieval-augmented generation (RAG), and LLM evaluation. It also includes practical projects like 'tiny-llm-zh' for hands-on experience in building small-parameter Chinese LLMs, 'tiny-rag' for RAG system implementation, and 'llama3-from-scratch-zh' for understanding Llama3. The project encourages community contributions and offers an online reading link for easy access.

Praxy is an AI suite specifically designed for healthcare professionals, offering a comprehensive set of tools to streamline various aspects of medical practice. It excels at summarizing patient consultations, automating back-office operations, and monitoring the quality of clinical trial data. The platform provides solutions for doctors across various specialties, as well as nurses, dietitians, psychologists, and medical secretaries. Key features include AI-powered consultation summaries, real-world evidence studies, pharmacovigilance management, and therapeutic advice chatbots. Praxy also offers APIs for software editors, chatbots, phonebots, and mobile applications, including Chrome/Edge plugins for ambient scribe and dictation. This suite aims to free up healthcare professionals' time, allowing them to focus more on patient care and improve therapeutic monitoring.

Researcher.Life offers a comprehensive suite of AI-powered tools designed to support academics throughout their research journey. This platform provides unlimited access to essential tools like Paperpal for academic writing assistance, R Discovery for literature search and recommendations, Mind The Graph for scientific illustrations, and a Global Journal Database for finding suitable publication venues. With a focus on streamlining the research process, Researcher.Life aims to enhance productivity and communication for researchers globally, including those who are non-English speakers. The platform is backed by over 22 years of academic expertise and trusted by a global research community, offering various subscription plans to suit individual needs.

rag-stack is an open-source solution designed to deploy a private ChatGPT alternative securely within your Virtual Private Cloud (VPC). It functions as a corporate oracle by connecting to your organization's knowledge base, enabling Retrieval Augmented Generation (RAG). This technique augments LLM capabilities by retrieving information from external systems, providing context beyond their training data. rag-stack supports open-source LLMs such as Llama 2, Falcon, and GPT4All, offering a more reliable, faster, and cost-effective alternative to fine-tuning models. It includes a server and UI for PDF upload, allowing users to chat over their documents using Qdrant as a vector database. Deployment options are available for Google Cloud, AWS, and Azure.

BananaPrompt.art offers a comprehensive library of free AI image and video prompts, meticulously tested across leading AI models such as Nano Banana Pro, Midjourney, and Stable Diffusion. Each prompt includes exact wording, settings, and structural details to ensure high-quality outputs and accelerate creative workflows. Users can browse prompts by style, use case, or AI model, then copy and customize them for their projects. The platform aims to eliminate trial-and-error, providing proven examples for YouTube thumbnails, social media posts, website hero images, and experimental artwork. It also supports video prompts for tools like Sora 2 and Veo 3, offering templates for timing, camera angles, and narrative structure.

Textomap is an AI-powered tool designed to create interactive maps from various content sources, including text, images, URLs, CSVs, and AI prompts. Unlike traditional mapping software, Textomap automatically identifies and plots locations, eliminating the need for manual pinning or complex spreadsheets. Users can visualize locations, events, and data in seconds, then share or embed their maps. The tool supports over 28 languages and offers a Chrome extension and WordPress plugin for seamless integration. It's ideal for visualizing itineraries, articles, class materials, and even historical data from images, making it a versatile solution for education, content creation, and data analysis.

JourneyTracker is an AI-powered tool designed to streamline and enhance the research process. It focuses on recording and summarizing research journeys, providing users with a robust solution for knowledge management. By leveraging artificial intelligence, JourneyTracker helps users effectively track and organize their research, ensuring that valuable insights and progress are not lost. This tool is particularly useful for individuals and teams engaged in academic or professional research, offering a structured approach to managing complex information and research paths.

Ai Note Buddy is designed as a comprehensive platform for workplace note-taking and knowledge management. It integrates an AI assistant to significantly enhance the note-taking process, likely offering features such as automated summarization, categorization, or content generation. The tool aims to streamline how individuals and teams capture, organize, and retrieve information. A key feature is its Chrome extension, which suggests seamless integration into existing web-based workflows, allowing users to capture information directly from their browsers. While specific details on its functionalities are not explicitly stated, the focus on AI assistance and knowledge management points towards a solution for improving productivity and information accessibility in professional environments.

LearnlyAI is an AI-powered academic assistant designed to help students with note-taking, essay writing, and presentation creation. It supports various study materials like PDFs, Word documents, and PowerPoint presentations, analyzing them to generate learning assistance content. The platform offers 24/7 AI tutors covering a wide range of subjects, smart study plans, and a world-class digital library. Key features include an Essay Assistant for academic writing feedback, a Presentation Maker to draft slides from notes, and a study calendar with AI-powered planning suggestions. It also integrates with Canvas LMS for course and deadline synchronization, and offers a browser extension to save articles.

SoraPrompt is a platform dedicated to showcasing and exploring videos generated by Sora AI, along with the prompts used to create them. It provides a centralized hub for users interested in AI video creation to discover new content, find inspiration, and understand the techniques behind successful AI-generated videos. The platform aims to foster a community around AI video generation by allowing users to share their creations and learn from others. It's an ideal resource for anyone looking to delve into the capabilities of Sora AI and stay updated on the latest trends in AI video content.

simple-local-rag is a comprehensive tool designed for building Retrieval Augmented Generation (RAG) pipelines from the ground up, with a strong emphasis on local execution. It supports the entire RAG workflow, from ingesting PDF documents to enabling "chat with PDF" style features. The tool is built to run on NVIDIA GPUs and leverages open-source technologies, making it a flexible and powerful solution for developers and data scientists. A key example is NutriChat, a RAG workflow that allows users to query a 1200-page nutrition textbook and receive LLM-generated responses based on relevant passages. This tool is particularly valuable for those who prioritize privacy, speed, and cost-effectiveness by running AI models on their own hardware.

Edupull is a comprehensive platform designed to empower students throughout their educational journey. It offers a wealth of information covering various streams of education, including management, engineering, and medicine. The platform provides detailed insights into colleges, available courses, and relevant examinations. A key feature of Edupull is its AI-powered recommendation engine, which delivers personalized suggestions to students. This intelligent system aims to help users make well-informed decisions about their academic paths, ensuring they find the best fit for their aspirations and goals. By centralizing crucial educational data and leveraging artificial intelligence, Edupull simplifies the complex process of educational planning.

vault-ai, powered by GitHub, offers an AI-powered developer platform designed to enhance code creation, intelligent app deployment, and prompt management. It integrates GitHub Copilot for writing better code with AI and GitHub Spark for building and deploying intelligent applications. The platform also includes GitHub Models for managing and comparing prompts, and the MCP Registry for integrating external tools. It provides solutions for various use cases such as app modernization, DevSecOps, and CI/CD, catering to enterprises, small and medium teams, and startups. The platform aims to streamline development workflows and improve application security with features like GitHub Advanced Security.

ChatGPT Flow is a Chrome extension designed to enhance the management of ChatGPT conversations. It utilizes a unique node-based flow diagram approach to visualize and organize chat history, providing users with a clear and structured overview of their interactions. This tool is particularly beneficial for individuals who engage in complex or extensive ChatGPT dialogues, such as researchers and developers. By transforming linear conversations into an intuitive visual flow, ChatGPT Flow helps users track the progression of discussions, identify key points, and easily navigate through their chat history. This visual organization simplifies the analysis and management of intricate AI interactions, making it an invaluable asset for those seeking to optimize their ChatGPT experience.

Today AI is an AI-powered news analytics platform designed to help users extract valuable insights from news articles. The platform enables comprehensive topic tracking, allowing users to monitor specific subjects across various news sources. With its advanced analytics capabilities, Today AI facilitates the analysis of news trends, providing a deeper understanding of how narratives evolve over time. This tool is ideal for individuals and organizations that need to stay informed and make data-driven decisions based on real-time news intelligence. It leverages artificial intelligence to process and interpret vast amounts of news data, making complex information accessible and actionable.

wizdom.ai is an AI-powered research intelligence platform designed to help researchers, institutions, publishers, funders, and governments make sense of the vast amount of research data available. It continuously monitors billions of data points about the global research ecosystem to provide actionable insights into topics, institutes, countries, journals, and funding bodies. The platform uses machine learning algorithms to generate analytics about scientific developments, helping users explore the research landscape, identify trends, and improve research performance. Key features include a comprehensive knowledge graph, AI-powered analytics, identification of emerging trends, and benchmarking research performance.