xtuner

XTuner is an efficient, flexible, and full-featured toolkit for fine-tuning large models. It supports various LLMs (InternLM, Mixtral-8x7B, Llama 2, ChatGLM, Qwen, Baichuan, ...), VLMs (LLaVA), and various training algorithms (QLoRA, LoRA, full-parameter fine-tune). XTuner also provides tools for chatting with pretrained / fine-tuned LLMs and deploying fine-tuned LLMs with any other framework, such as LMDeploy.

Nyxtext is a text editor built using Python, featuring Custom Tkinter with the Catppuccin color scheme and glassmorphic design. It follows a modular approach with each element organized into separate files for clarity and maintainability. NyxText is not just a text editor but also an AI-powered desktop application for creatives, developers, and students.

Jan is an open-source ChatGPT alternative that runs 100% offline on your computer. It supports universal architectures, including Nvidia GPUs, Apple M-series, Apple Intel, Linux Debian, and Windows x64. Jan is currently in development, so expect breaking changes and bugs. It is lightweight and embeddable, and can be used on its own within your own projects.

DriveLM is a multimodal AI model that enables autonomous driving by combining computer vision and natural language processing. It is designed to understand and respond to complex driving scenarios using visual and textual information. DriveLM can perform various tasks related to driving, such as object detection, lane keeping, and decision-making. It is trained on a massive dataset of images and text, which allows it to learn the relationships between visual cues and driving actions. DriveLM is a powerful tool that can help to improve the safety and efficiency of autonomous vehicles.

WebMasterLog is a comprehensive repository showcasing various web development projects built with front-end and back-end technologies. It highlights interactive user interfaces, dynamic web applications, and a spectrum of web development solutions. The repository encourages contributions in areas such as adding new projects, improving existing projects, updating documentation, fixing bugs, implementing responsive design, enhancing code readability, and optimizing project functionalities. Contributors are guided to follow specific guidelines for project submissions, including directory naming conventions, README file inclusion, project screenshots, and commit practices. Pull requests are reviewed based on criteria such as proper PR template completion, originality of work, code comments for clarity, and sharing screenshots for frontend updates. The repository also participates in various open-source programs like JWOC, GSSoC, Hacktoberfest, KWOC, 24 Pull Requests, IWOC, SWOC, and DWOC, welcoming valuable contributors.

Clash Royale Build-A-Bot is a project that allows users to build their own bot to play Clash Royale. It provides an advanced state generator that accurately returns detailed information using cutting-edge technologies. The project includes tutorials for setting up the environment, building a basic bot, and understanding state generation. It also offers updates such as replacing YOLOv5 with YOLOv8 unit model and enhancing performance features like placement and elixir management. The future roadmap includes plans to label more images of diverse cards, add a tracking layer for unit predictions, publish tutorials on Q-learning and imitation learning, release the YOLOv5 training notebook, implement chest opening and card upgrading features, and create a leaderboard for the best bots developed with this repository.

The HDU Computer Science Lecture Notes is a comprehensive guide designed to help students navigate through various challenges in the field of computer science. It covers topics such as programming languages, artificial intelligence, software development, and more. The notes provide insights on how to effectively utilize university time, balance grades with project experience, and make informed decisions regarding career paths. Created by a collaborative effort involving students, teachers, and industry experts, the lecture notes aim to serve as a guiding tool for individuals seeking guidance in the computer science domain.

Rivet is a desktop application for creating complex AI agents and prompt chaining, and embedding it in your application. Rivet currently has LLM support for OpenAI GPT-3.5 and GPT-4, Anthropic Claude Instant and Claude 2, [Anthropic Claude 3 Haiku, Sonnet, and Opus](https://www.anthropic.com/news/claude-3-family), and AssemblyAI LeMUR framework for voice data. Rivet has embedding/vector database support for OpenAI Embeddings and Pinecone. Rivet also supports these additional integrations: Audio Transcription from AssemblyAI. Rivet core is a TypeScript library for running graphs created in Rivet. It is used by the Rivet application, but can also be used in your own applications, so that Rivet can call into your own application's code, and your application can call into Rivet graphs.

ComfyUI-Copilot is an intelligent assistant built on the Comfy-UI framework that simplifies and enhances the AI algorithm debugging and deployment process through natural language interactions. It offers intuitive node recommendations, workflow building aids, and model querying services to streamline development processes. With features like interactive Q&A bot, natural language node suggestions, smart workflow assistance, and model querying, ComfyUI-Copilot aims to lower the barriers to entry for beginners, boost development efficiency with AI-driven suggestions, and provide real-time assistance for developers.

GPTSwarm is a graph-based framework for LLM-based agents that enables the creation of LLM-based agents from graphs and facilitates the customized and automatic self-organization of agent swarms with self-improvement capabilities. The library includes components for domain-specific operations, graph-related functions, LLM backend selection, memory management, and optimization algorithms to enhance agent performance and swarm efficiency. Users can quickly run predefined swarms or utilize tools like the file analyzer. GPTSwarm supports local LM inference via LM Studio, allowing users to run with a local LLM model. The framework has been accepted by ICML2024 and offers advanced features for experimentation and customization.

TensorZero is an open-source platform that helps LLM applications graduate from API wrappers into defensible AI products. It enables a data & learning flywheel for LLMs by unifying inference, observability, optimization, and experimentation. The platform includes a high-performance model gateway, structured schema-based inference, observability, experimentation, and data warehouse for analytics. TensorZero Recipes optimize prompts and models, and the platform supports experimentation features and GitOps orchestration for deployment.

AI-on-the-edge-device is a project that enables users to digitize analog water, gas, power, and other meters using an ESP32 board with a supported camera. It integrates Tensorflow Lite for AI processing, offers a small and affordable device with integrated camera and illumination, provides a web interface for administration and control, supports Homeassistant, Influx DB, MQTT, and REST API. The device captures meter images, extracts Regions of Interest (ROIs), runs them through AI for digitization, and allows users to send data to MQTT, InfluxDb, or access it via REST API. The project also includes 3D-printable housing options and tools for logfile management.

Agentica is a specialized Agentic AI library focused on LLM Function Calling. Users can provide Swagger/OpenAPI documents or TypeScript class types to Agentica for seamless functionality. The library simplifies AI development by handling various tasks effortlessly.

Chipper provides a web interface, CLI, and architecture for pipelines, document chunking, web scraping, and query workflows. It is built with Haystack, Ollama, Hugging Face, Docker, Tailwind, and ElasticSearch, running locally or as a Dockerized service. Originally created to assist in creative writing, it now offers features like local Ollama and Hugging Face API, ElasticSearch embeddings, document splitting, web scraping, audio transcription, user-friendly CLI, and Docker deployment. The project aims to be educational, beginner-friendly, and a playground for AI exploration and innovation.

PySpur is a graph-based editor designed for LLM (Large Language Models) workflows. It offers modular building blocks, node-level debugging, and performance evaluation. The tool is easy to hack, supports JSON configs for workflow graphs, and is lightweight with minimal dependencies. Users can quickly set up PySpur by cloning the repository, creating a .env file, starting docker services, and accessing the portal. PySpur can also work with local models served using Ollama, with steps provided for configuration. The roadmap includes features like canvas, async/batch execution, support for Ollama, new nodes, pipeline optimization, templates, code compilation, multimodal support, and more.

Llama Assistant is a local AI assistant that respects your privacy. It is an AI-powered assistant that can recognize your voice, process natural language, and perform various actions based on your commands. It can help with tasks like summarizing text, rephrasing sentences, answering questions, writing emails, and more. The assistant runs offline on your local machine, ensuring privacy by not sending data to external servers. It supports voice recognition, natural language processing, and customizable UI with adjustable transparency. The project is a work in progress with new features being added regularly.

XTuner is an efficient, flexible, and full-featured toolkit for fine-tuning large models. It supports various LLMs (InternLM, Mixtral-8x7B, Llama 2, ChatGLM, Qwen, Baichuan, ...), VLMs (LLaVA), and various training algorithms (QLoRA, LoRA, full-parameter fine-tune). XTuner also provides tools for chatting with pretrained / fine-tuned LLMs and deploying fine-tuned LLMs with any other framework, such as LMDeploy.

The LLM Hosting Container repository provides Dockerfile and associated resources for building and hosting containers for large language models, specifically the HuggingFace Text Generation Inference (TGI) container. This tool allows users to easily deploy and manage large language models in a containerized environment, enabling efficient inference and deployment of language-based applications.

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.

AgentCloud is an open-source platform that enables companies to build and deploy private LLM chat apps, empowering teams to securely interact with their data. It comprises three main components: Agent Backend, Webapp, and Vector Proxy. To run this project locally, clone the repository, install Docker, and start the services. The project is licensed under the GNU Affero General Public License, version 3 only. Contributions and feedback are welcome from the community.

This framework generates fuzz targets for real-world `C`/`C++` projects with various Large Language Models (LLM) and benchmarks them via the `OSS-Fuzz` platform. It manages to successfully leverage LLMs to generate valid fuzz targets (which generate non-zero coverage increase) for 160 C/C++ projects. The maximum line coverage increase is 29% from the existing human-written targets.

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.

The Azure-Analytics-and-AI-Engagement repository provides packaged Industry Scenario DREAM Demos with ARM templates (Containing a demo web application, Power BI reports, Synapse resources, AML Notebooks etc.) that can be deployed in a customer’s subscription using the CAPE tool within a matter of few hours. Partners can also deploy DREAM Demos in their own subscriptions using DPoC.