machine-learning
build, expect, train, x-ray, merge, bisect, ship, one CLI.
Soup turns the pain of LLM fine-tuning into a simple workflow. One config, one command, done. Fine-tune LLMs from one YAML. Layer streaming trains an 8B model on a 4 GB laptop GPU.
Stable Diffusion GUI App for MacOS. Diffusion Bee is the easiest way to run Stable Diffusion locally on your Intel / M1 Mac. Comes with a one-click installer. No dependencies or technical knowledge needed.
RAG that intelligently adapts to your use case, data, and queries.
Streamlined and promptable Fast GraphRAG framework designed for interpretable, high-precision, agent-driven retrieval workflows.
Automate dogfoodingfor your team. Get more eyes on your web app. Testing your product is now just a simple command away. Get more eyes on your website. Ship with confidence.
Donobu simplifies automation through intuitive prompts, getting you started in no time.
A Deep Learning Approach for Password Guessing.
Related contents:
Using generative adversarial networks (GAN), we can learn how to create realistic-looking fake versions of almost anything, as shown by this collection of sites that have sprung up in the past month.
A platform for the machine learning lifecycle.
MLflow is a platform to streamline machine learning development, including tracking experiments, packaging code into reproducible runs, and sharing and deploying models. MLflow offers a set of lightweight APIs that can be used with any existing machine learning application or library (TensorFlow, PyTorch, XGBoost, etc), wherever you currently run ML code (e.g. in notebooks, standalone applications or the cloud). MLflow's current components are:
Structured text generation and robust prompting for language models.
Outlines is a Python library that allows you to use Large Language Model in a simple and robust way (with structured generation). It is built by .txt, and is already used in production by many companies.
Related contents:
Run your own AI cluster at home with everyday devices 📱💻 🖥️⌚
Forget expensive NVIDIA GPUs, unify your existing devices into one powerful GPU: iPhone, iPad, Android, Mac, Linux, pretty much any device!
Related contents:
Refer and Ground Anything Anywhere at Any Granularity.
An End-to-End MLLM that Accept Any-Form Referring and Ground Anything in Response.
one-click face swap
Take a video and replace the face in it with a face of your choice. You only need one image of the desired face. No dataset, no training.
S3GD is a highly optimized, PyTorch-compatible Triton implementation of the Smoothed SignSGD optimizer, meant for reinforcement learning post-training.
Related contents:
PhotoPrism® is an AI-Powered Photos App for the Decentralized Web.
It makes use of the latest technologies to tag and find pictures automatically without getting in your way. You can run it at home, on a private server, or in the cloud.
Trustable Automation. Steampunk Spotter provides an Assisted Automation Writing tool that analyzes and offers recommendations for your Ansible Playbooks.
Plain English to Real Dates.
A small neural model for parsing date & time, running locally in your browser.
Take control of the media you consume every day with Fast Music Remover!.
A C++ based, lightweight music and noise remover for YouTube and other internet media, using DeepFilterNet for audio enhancement.
We consume, willingly or not, large amounts of media everyday, and that includes content that is emposed on us. Fast Music Remover gives you the choice to opt-out of them without missing out on the core content.
We're building a feature rich media processor that is efficient, modular and cross platform. It's being built for you! That means clean APIs for programmers, containerized on GHCR for remote users, with a Web UI providing seamless access to anyone interested!
Evolving agents is a production-grade environment for orchestrating, evolving, and managing AI agents.
A production-grade framework for creating, managing, and evolving AI agents with intelligent agent-to-agent communication. The framework enables you to build collaborative agent ecosystems that can semantically understand requirements, evolve based on past experiences, and communicate effectively to solve complex tasks.
LiteRT, successor to TensorFlow Lite. is Google's On-device framework for high-performance ML & GenAI deployment on edge platforms, via efficient conversion, runtime, and optimization
Related contents:
Zero shot pdf OCR with gpt-4o-mini.
A dead simple way of OCR-ing a document for AI ingestion. Documents are meant to be a visual representation after all. With weird layouts, tables, charts, etc. The vision models just make sense!
library and tools for information extraction.
This project provides free (even for commercial use) state-of-the-art information extraction tools. The current release includes tools for performing named entity extraction and binary relation detection as well as tools for training custom extractors and relation detectors.
AI Photo Enhancer. The only photo and video enhancer you'll ever need.
Transformative technology gives your low-quality visuals a stunning HD upgrade. Restore old photos to incredible detail and elevate your content to a professional level.
A Jasper alternative open source with ChatGPT.
This project uses ChatGPT API to create almost any text based output for your need - from marketing content to blog post ideas and a lot more. It uses simple template based components to ask ChatGPT for generating results Creating new templates or tasks take about 30 mins. no more, so you can extend it for your needs or wait for new template release :)
Contribute to krishnaik06/The-Grand-Complete-Data-Science-Materials development by creating an account on GitHub.
Euclid scientists need your help. Euclid captures images of tens of millions of galaxies like those we’re showing here. To classify that impossibly-large pile of galaxies, we’re using your classifications to train AI algorithms (remember the Zoobot AI assistant?). But the AI algorithms need to be ready for the scientists by the end of August - in only one month! We need as many volunteer classifications for teaching the AI algorithms as we can get; our goal is 100,000 classifications. We’re calling this The Euclid Challenge. Spread the word and dive in!
A Gradio web UI for Large Language Models. Supports transformers, GPTQ, llama.cpp (GGUF), Llama models.
computer vision and sports.
In sports, every centimeter and every second matter. That's why Roboflow decided to use sports as a testing ground to push our object detection, image segmentation, keypoint detection, and foundational models to their limits. This repository contains reusable tools that can be applied in sports and beyond.
The Powerful Multi-modal LLM Family for OCR-free Document Understanding. Modularized Multimodal Large Language Model for Document Understanding.
DeepGEMM: clean and efficient FP8 GEMM kernels with fine-grained scaling.
DeepGEMM is a unified, high-performance tensor core kernel library that brings together the key computation primitives of modern large language models — GEMMs (FP8, FP4, BF16), fused MoE with overlapped communication (Mega MoE), MQA scoring for the lightning indexer, HyperConnection (HC), and more — into a single, cohesive CUDA codebase. All kernels are compiled at runtime via a lightweight Just-In-Time (JIT) module, requiring no CUDA compilation during installation.
Karaoke from your music library. Machine learning powered Karaoke app (with scores!) .
Turn any song into karaoke. A self-contained party game that separates vocals, transcribes lyrics, and plays it all back with word-level sync and pitch scoring.
Easy, fast, and cheap LLM serving for everyone.
vLLM is a fast and easy-to-use library for LLM inference and serving.
Originally developed in the Sky Computing Lab at UC Berkeley, vLLM has evloved into a community-driven project with contributions from both academia and industry.
Related contents:
- How to serve LLMs with vLLM and OVHcloud AI Deploy @ OVHcloud.
- Episode 616: From Boston to bootc @ Linux Unplugged.
- What is vLLM @ RedHat.
- Faire tourner un LLM localement sur votre ordinateur @ Quoi de neuf les devs ? :fr:.
- Inside vLLM: Anatomy of a High-Throughput LLM Inference System @ Aleksa Gordić blog.
- vLLM : Maîtriser l'Inference Haute Performance pour les LLM @ DevSecOps :fr:.
- Docker Model Runner now supports vLLM on Windows @ Docker.
- Running a self-hosted LLM in Kubernetes with vLLM @ CNCF.
Machine learning tools in JavaScript
This library is a compilation of the tools developed in the mljs organization. It is mainly maintained for use in the browser. If you are working with Node.js, you might prefer to add to your dependencies only the libraries that you need, as they are usually published to npm more often. We prefix all our npm package names with ml- (eg. ml-matrix) so they are easy to find.
Opensource, self-hosted AI coding assistant.
Tabby is a self-hosted AI coding assistant, offering an open-source and on-premises alternative to GitHub Copilot.
The Typescript AI framework.
Mastra is an opinionated Typescript framework that helps you build AI applications and features quickly. It gives you the set of primitives you need: workflows, agents, RAG, integrations, syncs and evals. You can run Mastra on your local machine, or deploy to a serverless cloud.
Related contents:
ChainReactor is a research project that leverages AI planning to discover exploitation chains for privilege escalation on Unix systems. The project models the problem as a sequence of actions to achieve privilege escalation from initial access to a target system.
GAIA Logo GAIA: AI Agent Framework for AMD Ryzen AI.
GAIA is AMD's open-source framework for building intelligent AI agents that run 100% locally on AMD Ryzen AI hardware. Keep your data private, eliminate cloud costs, and deploy in air-gapped environments—all with hardware-accelerated performance.
Related contents:
A new community-based approach to build truly open-source LLMs.
InstructLab Command-Line Interface. Use this to chat with a model and execute the InstructLab workflow to train a model using custom taxonomy data.
On-device AI models and SDKs. Little brains in every product.
The fastest models for your task, running on-device. Small models that each do one job very well, with one native SDK that drops them into any product in a few lines of code.
Related contents:
The Machine Learning Toolkit for Kubernetes The Kubeflow project is dedicated to making deployments of machine learning (ML) workflows on Kubernetes simple, portable and scalable. Our goal is not to recreate other services, but to provide a straightforward way to deploy best-of-breed open-source systems for ML to diverse infrastructures. Anywhere you are running Kubernetes, you should be able to run Kubeflow.
Related contents:
AI imagined images. Pythonic generation of stable diffusion images.
Bagage minimal de statistiques pour le Machine Learning
Open-Source ML Monitoring and LLM Observability.
Open-source evaluation and observability for ML and LLM systems Evaluate, test, and monitor AI-powered systems. From tabular data to LLMs. Built for data scientists, AI, and ML engineers.
Using Sequences of Life-events to Predict Human Lives.
We represent human lives in a way that shares structural similarity to language, and we exploit this similarity to adapt natural language processing techniques to examine the evolution and predictability of human lives based on detailed event sequences. We do this by drawing on a comprehensive registry dataset, which is available for Denmark across several years, and that includes information about life-events related to health, education, occupation, income, address and working hours, recorded with day-to-day resolution.
Next-generation creation suite. Everything you need to make content, fast. Magical AI tools, realtime collaboration, precision editing, and more. Your next-generation content creation suite.
A Datacenter Scale Distributed Inference Serving Framework.
NVIDIA Dynamo is a high-throughput low-latency inference framework designed for serving generative AI and reasoning models in multi-node distributed environments. Dynamo is designed to be inference engine agnostic (supports TRT-LLM, vLLM, SGLang or others) and captures LLM-specific capabilities.
Related contents:
WAGMIOS is a self-hosted container management system with AI-powered automation. It enables you to efficiently manage your containers with W.I.L.L.O.W, an AI assistant that optimizes your workflow.
Modern columnar data format for ML and LLMs implemented in Rust. Convert from parquet in 2 lines of code for 100x faster random access, vector index, and data versioning. Compatible with Pandas, DuckDB, Polars, Pyarrow, and PyTorch with more integrations coming..
Lance is a modern columnar data format optimized for machine learning and AI applications. It efficiently handles diverse multimodal data types while providing high-performance querying and versioning capabilities.
Related contents:
Pensieve is a privacy-focused passive recording project. It can automatically record screen content, build intelligent indices, and provide a convenient web interface to retrieve historical records.
This project draws heavily from two other projects: one called Rewind and another called Windows Recall. However, unlike both of them, Pensieve allows you to have complete control over your data, avoiding the transfer of data to untrusted data centers.
MLOps Attack Toolkit
MLOKit is a toolkit that can be used to attack MLOps platforms by taking advantage of the available REST API. This tool allows the user to specify an attack module, along with specifying valid credentials (API key or stolen access token) for the respective MLOps platform. The attack modules supported include reconnaissance, data extraction and model extraction. MLOKit was built in a modular approach, so that new modules can be added in the future by the information security community.
Write code, not tests.
Contextually Aware AI-Driven Unit Test Generation for Typescript Node.js projects. Celp generates contextually relevant unit tests for Typescript node.js projects, saving you hours.
GFPGAN aims at developing a Practical Algorithm for Real-world Face Restoration. It leverages rich and diverse priors encapsulated in a pretrained face GAN (e.g., StyleGAN2) for blind face restoration.
Every image is uniquely generated by artificial intelligence. Food items that add an image see 70% more orders and 65% higher sales compared to restaurants that do not.
Open-Source ML-Compatible Humanoid Platform for Loco-Manipulation.
ToddlerBot is a low-cost, open-source humanoid robot platform designed for scalable policy learning and research in robotics and AI.
This codebase includes low-level control, RL training, DP training, real-world deployment and basically EVERYTHING you need to run ToddlerBot in the real world!
Related contents:
Neuro.js is machine learning framework for building AI assistants and chat-bots.
12 weeks, 26 lessons, 52 quizzes, classic Machine Learning for all.
Cloud Advocates at Microsoft are pleased to offer a 12-week, 26-lesson curriculum all about Machine Learning. In this curriculum, you will learn about what is sometimes called classic machine learning, using primarily Scikit-learn as a library and avoiding deep learning, which is covered in our AI for Beginners' curriculum. Pair these lessons with our 'Data Science for Beginners' curriculum, as well!
Related contents:
Doctor Dignity is an LLM that can pass the US Medical Licensing Exam. It works offline, it's cross-platform, & your health data stays private.
⚡ Vigil ⚡ Detect prompt injections, jailbreaks, and other potentially risky Large Language Model (LLM) inputs.
Vigil is a Python library and REST API for assessing Large Language Model prompts and responses against a set of scanners to detect prompt injections, jailbreaks, and other potential risks.
Dataherald is a natural language-to-SQL engine built for enterprise-level question answering over relational data. It allows you to set up an API from your database that can answer questions in plain English.
Run AI with an API. Run and fine-tune open-source models. Deploy custom models at scale. All with one line of code.
Thousands of models contributed by our community. All the latest open-source models are on Replicate. They’re not just demos — they all actually work and have production-ready APIs.
AI shouldn’t be locked up inside academic papers and demos. Make it real by pushing it to Replicate.
Related contents: