#GPT
LLMs-from-scratch
This comprehensive guide covers the entire process of building a GPT-like large language model, starting from coding the basics. It provides step-by-step instructions with clear explanations and examples, making it a valuable resource for understanding model development, pretraining, and finetuning techniques. The guide parallels techniques used in technologies like ChatGPT and includes information on loading and refining larger pre-trained models. Access the official code repository for updates and additional resources.
openai
Discover a carefully curated collection of GPT and LLM tricks for developers. This includes techniques for handling asynchronous API requests, crafting automatic cold mails, compressing text with GPT-4, and identifying objects in images using natural language. You can also learn how to run local LLMs and utilize function calling with OpenAI's API. Perfect for developers aiming to elevate their AI projects and improve efficiency with cutting-edge tools.
rulm
Discover significant developments in Russian language models through efficient implementations and detailed comparisons. Featuring the RuTurboAlpaca dataset with GPT-3.5-turbo and the Saiga models, the project provides valuable resources on HuggingFace and GitHub. It enables interaction with models from 7b to 70b, fostering innovation in Russian NLP tasks with active community support via DataFest and fine-tuning in Colab.
autopilot
Autopilot is an AI tool designed to utilize GPT technology for codebase management and task automation. Through file pre-processing and code adjustment capabilities, it simplifies workflow. As a GitHub app, it supports issue resolution and pull request tasks. Features include concurrent agent calls and interactive code update viewing. Compatible with Node.js v18+, Autopilot aids in enhancing developer productivity.
chatbot-app
The application supports diverse AI models like GPT, Gemini Pro, and Cohere, focusing on data privacy by ensuring local data storage. Its features include a responsive interface with dark mode, voice and extensive conversation capabilities, picture creation, and a ChatGPT Code interpreter. Compatible with iOS, Android, macOS, and Telegram, it supports multiple languages, including English, Simplified Chinese, Japanese, and Korean, offering a secure platform for advanced AI interactions.
BadUSB-GPT
Discover the integration of Rubber Ducky with OpenAI's GPT, crafted for ethical hackers and researchers. The tool combines swift script execution with AI to advance cybersecurity research. It emphasizes responsible use to respect privacy and system security. Donations support development and donor recognition is included in project documentation.
auto-novel
Experience machine translations of Japanese novels effortlessly. This platform allows browsing popular sites like Kakuyomu and Pixiv, or uploading EPUB/TXT files for translation with tools such as Baidu, GPT-3.5, or GPT-4 API. It supports various formats, including bilingual views, and facilitates the creation of EPUB and TXT files for ease of reading. Participate in the community by contributing to project development. Access Japanese literature seamlessly with advanced translation technology.
awesome-llm-cybersecurity-tools
Discover a selection of innovative AI tools leveraging Large Language Models for boosting cybersecurity research. Applications cover reverse engineering, network analysis, and cloud security, utilizing OpenAI's GPT models for tasks including decompiled code analysis, HTTP request evaluation, and IAM policy vulnerabilities. Highlights include proofs of concept in LLM-driven malware and indirect prompt injection attacks.
femtoGPT
Explore the minimal Rust-based femtoGPT, adept in inference and training on both CPUs and GPUs via OpenCL—bypassing the need for massive CUDA installations. This open-source tool serves as an accessible research platform for CPU and GPU. Easily deployable with Rust toolchain, it invites AI enthusiasts to dive into hands-on learning while following developer insights from a planned book.
aiwechat-vercel
This open-source project integrates AI into WeChat using serverless Vercel functions, simplifying deployment and reducing costs. It supports multiple AI models like GPT and Spark, with features such as image hosting and chat history recall, enhancing WeChat interactions without needing a dedicated server.
nn-zero-to-hero-notes
This repository offers Jupyter Notebooks in alignment with Andrej Karpathy's 'Neural Networks: Zero to Hero' tutorial series. It delivers detailed insights into neural network fundamentals and advanced techniques, including GPT and GPT-2. The materials support learners in expanding their practical understanding of topics such as Micrograd, WaveNet, and GPT tokenization. Contributions to improve the repository are encouraged, fostering collaboration and continuous learning.
Nexior
The platform enables fast deployment of AI applications without the need for technical skills, covering solutions like AIChat and Midjourney. It removes the requirement for AI account purchases or API setups, supporting a zero-cost, risk-free model. The system is integrated with GPT 3.5/4.0, various Midjourney modes, and Suno music with trial options. Built-in payment and user systems facilitate easy monetization, and being open-source under MIT license ensures an effortless setup and revenue generation from AI systems.
Awesome-LLM-Large-Language-Models-Notes
Explore a detailed compilation of large language models (LLMs), organized by year, size, and name. This resource covers foundational and recent models such as Transformer, GPT, BERT, GPT-4, and BLOOM, with links to research papers and implementations. An essential guide for NLP research and applications, complete with insightful articles and the significance of HuggingFace for model deployment.
springboot-openai-chatgpt
This project provides an in-depth exploration of microservices and AI, featuring a full-stack solution backed by GPT technology. It includes functionalities such as language generation, AI chat, and drawing tools. These features boost productivity by creating various content types and resolving complex queries with a Q&A system. The project offers access to demonstration environments for both frontend and backend, offering practical insights into application deployment. It suits developers interested in utilizing AI for intelligent solutions and supports continuous learning and collaboration through community engagement.
awesome-llms-fine-tuning
Discover a curated selection of resources for fine-tuning Large Language Models (LLMs) like GPT, BERT, and RoBERTa. This repository provides comprehensive tutorials, papers, tools, and best practices for advancing LLMs in specific domains. It serves machine learning practitioners and data scientists in optimizing LLM performance and ensuring alignment with particular tasks. Explore insights and guidelines from GitHub projects to courses and literature.
awesome-transformer-nlp
This repository provides a curated collection of machine learning resources concentrated on NLP technologies such as GPT, BERT, and Transformer architectures. It examines the practical implementation and effects of models, including ChatGPT, and investigates transfer learning applications in NLP. The repository contains a wide array of educational materials, featuring papers, articles, tutorials, and videos, alongside community-driven implementations in frameworks like PyTorch and TensorFlow. These resources aid in the understanding and innovation of language processing models and methods, supporting AI applications in areas like classification and text generation.
KG_RAG
KG-RAG combines knowledge graphs with large language models to optimize prompt generation using a comprehensive biomedical knowledge base. The system facilitates efficient retrieval-augmented generation, crucial in tasks such as summarizing FDA drug information for conditions like Bardet-Biedl Syndrome. KG-RAG can be run through a straightforward setup, offering smooth interaction with models like GPT and Llama. It is benchmarked with the BiomixQA dataset to demonstrate its potential in advancing biomedical natural language processing.
MedicalGPT
This page details the methodologies used in training medical language models using GPT techniques, including pretraining, supervised fine-tuning, reinforcement learning from human feedback (RLHF), and direct preference optimization (DPO). By utilizing extensive multilingual datasets, MedicalGPT enhances performance in medical Q&A systems and supports various architectures such as Llama and Vicuna. The platform provides practical scripts and demo interfaces for ease of integration, serving as a significant resource for the development of contemporary medical AI applications.
Feishu-OpenAI-Stream-Chatbot
Feishu-OpenAI-Stream-Chatbot seamlessly combines Feishu with OpenAI to provide a sophisticated chatbot experience. It features real-time text streaming, multi-topic discussions, and rich text responses. Predefined scenarios and role-playing enhance interaction, while context retention ensures coherent conversations. Suitable for both private and group chats, with automatic dialogue termination. Future enhancements include Feishu-ChatBot integration, conversation history rollback, direct topic-to-PPT conversion, and optimized prompts, offering cultural relevance for users in China.
azure-openai-samples
Explore the resources available for understanding GPT basics and its applications with Azure's offerings. Learn to integrate GPT with services such as Synapse Analytics for NLP and Business Process Automation. Access practical samples including serverless SQL and OpenAI-powered semantic search. Stay informed about the latest advancements including GPT-4 and contribute to the ongoing development. This is ideal for developers and organizations looking to leverage AI in diverse sectors such as chatbots, customer service, and content creation.
ai.vim
The ai.vim is a minimalist Neovim plugin offering efficient text generation and editing powered by OpenAI's GPT. It allows seamless text completions in insert mode, content generation through prompts, and direct text editing in Neovim. Simple commands like `<Ctrl-A>` and `:AI <prompt>` make it suitable for both coding and regular text tasks, enabling operations such as list sorting, color conversion, and text style transformation. The plugin is easy to install via vim-plug, with customization options for effective integration. Users are advised to proofread for potential inaccuracies and be mindful of privacy concerning sensitive data.
magma-chat
Explore a pioneering open-source chat platform crafted by MagmaLabs on a robust Rails 7 foundation. This proof-of-concept interface leverages GPT technology, allowing users to engage with customizable AI bots equipped with memory management, conversational context, and text-to-speech. Features like Google OAuth for secure logins, dynamic prompts, and CableReady with StimulusReflex for enhanced interactivity enhance user engagement. With internationalization and a solid roadmap, future enhancements aim at multi-bot interactions and autonomous agents. Perfect for developers looking to contribute and explore the latest in GPT applications.
nn-zero-to-hero
The course provides an organized learning path into neural networks, starting from basics to advanced language models without excessive promotion. Offering practical YouTube lectures and hands-on Jupyter notebooks, it guides users through neural networks, backpropagation, and the evolution to complex Transformer and GPT models. The focus is on gaining practical experience in training, optimization, and understanding tokenization in AI, ensuring unbiased, detailed skill development.
langchain-in-action
Explore an in-depth and practical guide to LangChain, showcasing key features and real-world applications. This course is designed for both beginners and professionals seeking to understand and utilize LangChain effectively. Stay informed with the latest methodologies and support Jia Ge's work by purchasing the accompanying book, GPT Illustrated, at a discounted rate.
AI-TDD
Transform test-driven development with AI-TDD, an efficient CLI tool that uses GPT to automate code generation. Experience straightforward setup with Bun, seamless integration with test frameworks like Jest, and harness the power of advanced GPT models to enhance coding accuracy and efficiency in software development.
ArxivDigest
Explore a customized arXiv paper digest system leveraging large language models such as GPT. This project efficiently sifts through numerous new papers by assessing their relevance according to user-defined criteria. Users can personalize their experience through a configuration file, specifying research areas and interests, with the option to receive daily HTML digests or email alerts via SendGrid. Engage with the platform via a Hugging Face demo, ensuring privacy with untracked API keys.
storyteller
An open-source tool that combines Stable Diffusion, GPT, and TTS for creating animated stories from text prompts. It offers narrative, visual, and audio outputs, all customizable through CLI and Python interfaces. Installable via PyPI or GitHub, it serves as a versatile platform for those exploring AI-driven storytelling.
openai-toolbox
This repository compiles a variety of OpenAI tools and resources aimed at simplifying access to OpenAI technologies for developers. It includes links to official resources like API usage details, pricing, and examples, as well as tools for coding support, product integration, industry solutions, and more. The collection enhances productivity with specialized tools for code translation, financial analysis, and legal advice, among others.
SmallLanguageModel-project
Learn to construct your own language model using this detailed repository inspired by nanoGPT and Shakespeare generator. It provides comprehensive tools from data gathering to model training, suitable for crafting BERT and GPT models. This repository is ideal for those familiar with Python 3.8 or above, offering clear instructions on processing data and training models. Perfect for AI developers seeking to tailor language model solutions, it ensures an organized setup, encouraging customization and innovation in language generation.
SwissArmyTransformer
Discover SwissArmyTransformer, a unified codebase for integrating model-agnostic components into Transformer-based models. Utilize DeepSpeed and model parallelism for efficient pretraining and finetuning of large-scale models with ease. Implement prefix-tuning in models such as GLM and GPT to boost performance with minimal effort. Leverage extensive training support on multiple GPUs or nodes, accommodating models like T5-10B and experimental ones like CogView2. SwissArmyTransformer offers a comprehensive environment for developing and optimizing Transformer variants designed for various AI tasks.
Feedback Email: [email protected]