LLM101n is a course focused on building a Storyteller AI Large Language Model (LLM) from scratch in Python, C, and CUDA. The course covers various topics such as language modeling, machine learning, attention mechanisms, tokenization, optimization, device usage, precision training, distributed optimization, datasets, inference, finetuning, deployment, and multimodal applications. Participants will gain a deep understanding of AI, LLMs, and deep learning through hands-on projects and practical examples.

LibreChat is an all-in-one AI conversation platform that integrates multiple AI models, including ChatGPT, into a user-friendly interface. It offers a wide range of features, including multimodal chat, multilingual UI, AI model selection, custom presets, conversation branching, message export, search, plugins, multi-user support, and extensive configuration options. LibreChat is open-source and community-driven, with a focus on providing a free and accessible alternative to ChatGPT Plus. It is designed to enhance productivity, creativity, and communication through advanced AI capabilities.

A repository sharing literatures and resources about Large Language Models (LLMs) and beyond. It includes tutorials, notebooks, course assignments, development stages, modeling, inference, training, applications, study, and basics related to LLMs. The repository covers various topics such as language models, transformers, state space models, multi-modal language models, training recipes, applications in autonomous driving, code, math, embodied intelligence, and more. The content is organized by different categories and provides comprehensive information on LLMs and related topics.

Caissa is a strong, UCI command-line chess engine optimized for regular chess, FRC, and DFRC. It features its own neural network trained with self-play games, supports various UCI options, and provides different EXE versions for different CPU architectures. The engine uses advanced search algorithms, neural network evaluation, and endgame tablebases. It offers outstanding performance in ultra-short games and is written in C++ with modules for backend, frontend, and utilities like neural network trainer and self-play data generator.

This repository provides a curated list of papers, datasets, and resources related to the detection and mitigation of hallucinations in large language models (LLMs). Hallucinations refer to the generation of factually incorrect or nonsensical text by LLMs, which can be a significant challenge for their use in real-world applications. The resources in this repository aim to help researchers and practitioners better understand and address this issue.

The Simple Chat Application is a web-based platform that facilitates secure interactions with generative AI models, leveraging Azure OpenAI. It features Retrieval-Augmented Generation (RAG) for grounding conversations in user data. Users can upload personal or group documents processed using Azure AI Document Intelligence and Azure OpenAI Embeddings. The application offers optional features like Content Safety, Image Generation, Video and Audio processing, Document Classification, User Feedback, Conversation Archiving, Metadata Extraction, and Enhanced Citations. It uses Azure Cosmos DB for storage, Azure Active Directory for authentication, and runs on Azure App Service. Suitable for enterprise use, it supports knowledge discovery, content generation, and collaborative AI tasks in a secure, Azure-native framework.

Kelivo is a Flutter LLM Chat Client with modern design, dark mode, multi-language support, multi-provider support, custom assistants, multimodal input, markdown rendering, voice functionality, MCP support, web search integration, prompt variables, QR code sharing, data backup, and custom requests. It is built with Flutter and Dart, utilizes Provider for state management, Hive for local data storage, and supports dynamic theming and Markdown rendering. Kelivo is a versatile tool for creating and managing personalized AI assistants, supporting various input formats, and integrating with multiple search engines and AI providers.

Chatbox is a desktop client for ChatGPT, Claude, and other LLMs, providing features like local data storage, multiple LLM provider support, image generation, enhanced prompting, keyboard shortcuts, and more. It offers a user-friendly interface with dark theme, team collaboration, cross-platform availability, web version access, iOS & Android apps, multilingual support, and ongoing feature enhancements. Developed for prompt and API debugging, it has gained popularity for daily chatting and professional role-playing with AI assistance.

OAD is a powerful open-source tool for analyzing and visualizing data. It provides a user-friendly interface for exploring datasets, generating insights, and creating interactive visualizations. With OAD, users can easily import data from various sources, clean and preprocess data, perform statistical analysis, and create customizable visualizations to communicate findings effectively. Whether you are a data scientist, analyst, or researcher, OAD can help you streamline your data analysis workflow and uncover valuable insights from your data.

PPTist is a web-based presentation application that replicates most features of Microsoft Office PowerPoint. It supports various elements like text, images, shapes, charts, tables, videos, audio, and formulas. Users can edit and present slides directly in a web browser. It offers easy development with Vue 3.x and TypeScript, user-friendly experience with context menu and keyboard shortcuts, and feature-rich functionalities including AI-generated PPTs and mobile editing. PPTist aims to provide a desktop application-level experience for creating presentations.

Aigcbilibili is a project that mimics the microservices of Bilibili, providing functionalities such as video uploading, viewing, liking, commenting, collecting, danmaku, user profile management, login methods, private messaging, intelligent PPT generation, dynamic updates, search aggregation, database operations with MyBatis-Plus, file management with MinIO, asynchronous tasks with CompletableFuture, JSON handling with FastJson, Gson, and Jackson, exception handling, logging management, file transfer, configuration management with Nacos, routing management with Gateway, authentication and authorization with Security + JWT, multiple login methods, caching with Redis, messaging with RocketMQ, search engine integration with Elasticsearch, data synchronization with XXL-Job, Redis, RocketMQ, Elasticsearch, cache implementation, real-time communication with WebSocket, distributed tracing with Sleuth + Zipkin, documentation and monitoring with Swagger, Druid, and intelligent content generation with Xunfei Xinghuo.

FastDeploy is an inference and deployment toolkit for large language models and visual language models based on PaddlePaddle. It provides production-ready deployment solutions with core acceleration technologies such as load-balanced PD disaggregation, unified KV cache transmission, OpenAI API server compatibility, comprehensive quantization format support, advanced acceleration techniques, and multi-hardware support. The toolkit supports various hardware platforms like NVIDIA GPUs, Kunlunxin XPUs, Iluvatar GPUs, Enflame GCUs, and Hygon DCUs, with plans for expanding support to Ascend NPU and MetaX GPU. FastDeploy aims to optimize resource utilization, throughput, and performance for inference and deployment tasks.

OpenAnalyst is an open-source VS Code AI agent specialized in data analytics and general coding tasks. It merges features from KiloCode, Roo Code, and Cline, offering code generation from natural language, data analytics mode, self-checking, terminal command running, browser automation, latest AI models, and API keys option. It supports multi-mode operation for roles like Data Analyst, Code, Ask, and Debug. OpenAnalyst is a fork of KiloCode, combining the best features from Cline, Roo Code, and KiloCode, with enhancements like MCP Server Marketplace, automated refactoring, and support for latest AI models.

Griptape is a modular Python framework for building AI-powered applications that securely connect to your enterprise data and APIs. It offers developers the ability to maintain control and flexibility at every step. Griptape's core components include Structures (Agents, Pipelines, and Workflows), Tasks, Tools, Memory (Conversation Memory, Task Memory, and Meta Memory), Drivers (Prompt and Embedding Drivers, Vector Store Drivers, Image Generation Drivers, Image Query Drivers, SQL Drivers, Web Scraper Drivers, and Conversation Memory Drivers), Engines (Query Engines, Extraction Engines, Summary Engines, Image Generation Engines, and Image Query Engines), and additional components (Rulesets, Loaders, Artifacts, Chunkers, and Tokenizers). Griptape enables developers to create AI-powered applications with ease and efficiency.

Meridian is a tool that provides personalized daily intelligence briefings by scraping news from hundreds of sources, analyzing stories with AI, and delivering concise briefs. It offers key global events, context, implications analysis, and open-source transparency. Built for the curious who seek in-depth news beyond headlines without spending too much time. The tool uses multi-stage LLM processing for article and cluster analysis, smart clustering techniques to group related articles, and a web interface powered by Nuxt 3. The workflow involves scraping RSS feeds, processing articles with Gemini for relevance, clustering articles, and generating a final brief. The project leverages AI models like Gemini, multilingual embeddings, UMAP, and HDBSCAN for analysis. The tech stack includes Turborepo, Cloudflare services, TypeScript, PostgreSQL, and Nuxt 3 with Vue 3 and Tailwind for the frontend.

ERAG is an advanced system that combines lexical, semantic, text, and knowledge graph searches with conversation context to provide accurate and contextually relevant responses. It processes various document types, creates embeddings, builds knowledge graphs, and uses this information to answer user queries intelligently. The tool includes modules for interacting with web content, GitHub repositories, and performing exploratory data analysis using various language models. It offers a GUI for managing local LLaMA.cpp servers, customizable settings, and advanced search utilities. ERAG supports multi-model collaboration, iterative knowledge refinement, automated quality assessment, and structured knowledge format enforcement. Users can generate specific knowledge entries, full-size textbooks, or datasets using AI-generated questions and answers.

LLM101n is a course focused on building a Storyteller AI Large Language Model (LLM) from scratch in Python, C, and CUDA. The course covers various topics such as language modeling, machine learning, attention mechanisms, tokenization, optimization, device usage, precision training, distributed optimization, datasets, inference, finetuning, deployment, and multimodal applications. Participants will gain a deep understanding of AI, LLMs, and deep learning through hands-on projects and practical examples.

Dstack is an open-source orchestration engine for running AI workloads in any cloud. It supports a wide range of cloud providers (such as AWS, GCP, Azure, Lambda, TensorDock, Vast.ai, CUDO, RunPod, etc.) as well as on-premises infrastructure. With Dstack, you can easily set up and manage dev environments, tasks, services, and pools for your AI workloads.

The one-click-llms repository provides templates for quickly setting up an API for language models. It includes advanced inferencing scripts for function calling and offers various models for text generation and fine-tuning tasks. Users can choose between Runpod and Vast.AI for different GPU configurations, with recommendations for optimal performance. The repository also supports Trelis Research and offers templates for different model sizes and types, including multi-modal APIs and chat models.

StarCoder2-Instruct is an open-source pipeline that introduces StarCoder2-15B-Instruct-v0.1, a self-aligned code Large Language Model (LLM) trained with a fully permissive and transparent pipeline. It generates instruction-response pairs to fine-tune StarCoder-15B without human annotations or data from proprietary LLMs. The tool is primarily finetuned for Python code generation tasks that can be verified through execution, with potential biases and limitations. Users can provide response prefixes or one-shot examples to guide the model's output. The model may have limitations with other programming languages and out-of-domain coding tasks.

The enhance_llm repository contains three main parts: 1. Vector model domain fine-tuning based on llama_index and qwen fine-tuning BGE vector model. 2. Large model domain fine-tuning based on PEFT fine-tuning qwen1.5-7b-chat, with sft and dpo. 3. High-order retrieval enhanced generation (RAG) system based on the above domain work, implementing a two-stage RAG system. It includes query rewriting, recall reordering, retrieval reordering, multi-turn dialogue, and more. The repository also provides hardware and environment configurations along with star history and licensing information.

The 'fms-fsdp' repository is a companion to the Foundation Model Stack, providing a (pre)training example to efficiently train FMS models, specifically Llama2, using native PyTorch features like FSDP for training and SDPA implementation of Flash attention v2. It focuses on leveraging FSDP for training efficiently, not as an end-to-end framework. The repo benchmarks training throughput on different GPUs, shares strategies, and provides installation and training instructions. It trained a model on IBM curated data achieving high efficiency and performance metrics.

CogVLM2 is a new generation of open source models that offer significant improvements in benchmarks such as TextVQA and DocVQA. It supports 8K content length, image resolution up to 1344 * 1344, and both Chinese and English languages. The project provides basic calling methods, fine-tuning examples, and OpenAI API format calling examples to help developers quickly get started with the model.

liboai is a simple C++17 library for the OpenAI API, providing developers with access to OpenAI endpoints through a collection of methods and classes. It serves as a spiritual port of OpenAI's Python library, 'openai', with similar structure and features. The library supports various functionalities such as ChatGPT, Audio, Azure, Functions, Image DALL·E, Models, Completions, Edit, Embeddings, Files, Fine-tunes, Moderation, and Asynchronous Support. Users can easily integrate the library into their C++ projects to interact with OpenAI services.

Weave is a toolkit for developing Generative AI applications, built by Weights & Biases. With Weave, you can log and debug language model inputs, outputs, and traces; build rigorous, apples-to-apples evaluations for language model use cases; and organize all the information generated across the LLM workflow, from experimentation to evaluations to production. Weave aims to bring rigor, best-practices, and composability to the inherently experimental process of developing Generative AI software, without introducing cognitive overhead.

LLMStack is a no-code platform for building generative AI agents, workflows, and chatbots. It allows users to connect their own data, internal tools, and GPT-powered models without any coding experience. LLMStack can be deployed to the cloud or on-premise and can be accessed via HTTP API or triggered from Slack or Discord.

The VisionCraft API is a free API for using over 100 different AI models. From images to sound.

Kaito is an operator that automates the AI/ML inference model deployment in a Kubernetes cluster. It manages large model files using container images, avoids tuning deployment parameters to fit GPU hardware by providing preset configurations, auto-provisions GPU nodes based on model requirements, and hosts large model images in the public Microsoft Container Registry (MCR) if the license allows. Using Kaito, the workflow of onboarding large AI inference models in Kubernetes is largely simplified.

PyRIT is an open access automation framework designed to empower security professionals and ML engineers to red team foundation models and their applications. It automates AI Red Teaming tasks to allow operators to focus on more complicated and time-consuming tasks and can also identify security harms such as misuse (e.g., malware generation, jailbreaking), and privacy harms (e.g., identity theft). The goal is to allow researchers to have a baseline of how well their model and entire inference pipeline is doing against different harm categories and to be able to compare that baseline to future iterations of their model. This allows them to have empirical data on how well their model is doing today, and detect any degradation of performance based on future improvements.

Tabby is a self-hosted AI coding assistant, offering an open-source and on-premises alternative to GitHub Copilot. It boasts several key features: * Self-contained, with no need for a DBMS or cloud service. * OpenAPI interface, easy to integrate with existing infrastructure (e.g Cloud IDE). * Supports consumer-grade GPUs.

SPEAR (Simulator for Photorealistic Embodied AI Research) is a powerful tool for training embodied agents. It features 300 unique virtual indoor environments with 2,566 unique rooms and 17,234 unique objects that can be manipulated individually. Each environment is designed by a professional artist and features detailed geometry, photorealistic materials, and a unique floor plan and object layout. SPEAR is implemented as Unreal Engine assets and provides an OpenAI Gym interface for interacting with the environments via Python.

Magick is a groundbreaking visual AIDE (Artificial Intelligence Development Environment) for no-code data pipelines and multimodal agents. Magick can connect to other services and comes with nodes and templates well-suited for intelligent agents, chatbots, complex reasoning systems and realistic characters.