Please start with our project page at Microsoft Research for an overview of this project. This project takes a fork of the OpenVPN software and combines it with post-quantum cryptography.

----- 2026 Update: Prophet is in maintenance mode as of v1.4.0. Only bug fixes, dependency bumps, and changes to the R package to meet parity with Python will be accepted.

Fine‑tune, evaluate, and run private, personalized LLMs xTuring makes it simple, fast, and cost‑efficient to fine‑tune open‑source LLMs (e.g., GPT‑OSS, LLaMA/LLaMA 2, Qwen3, MiniMax M2, GPT‑J, GPT‑2, DistilGPT‑2, Mamba) on your own data — locally or in your private cloud. Why xTuring: Run a small, CPU‑friendly example first: Want bigger models and reasoning controls?

👥 Contributing   |   🤝 Code of conduct   |   🔎 Issues   |   🗣️ Chat & Support   |   💻 API Reference The core of the Semaphore protocol is in the circuit logic. However, Semaphore also provides Solidity contracts and JavaScript libraries to make the steps for offchain proof creation and onchain/offchain verification easier.

I've started to work on reimplementation of the library here: FastTensors Please star it if you'd like to see GGML-compatible implementation in pure Go. Please check out my related project Booster We dream of a world where fellow ML hackers are grokking REALLY BIG GPT models in their homelabs without having GPU clusters consuming a shit tons of $$$.

An Agent Skill that transforms AI assistants into expert economics paper writers, synthesizing best practices from 50+ authoritative guides by Nobel laureates, Clark Medal winners, and leading economists. --- Econ Writing Skill is an open-source Agent Skill that gives AI coding assistants deep knowledge of how to write economics papers.

Watch the videos demonstrating the project Read about the project here The idea of this project is to provide you a bootstrap for your next microservice architecture using Java. we are addressing main challenges that everyone faces when is starting with microservices.

This repository contains data associated with the license tools and public domain tools (static HTML, internationalization and localization files, etc.). It includes data consumed and generated by the [creativecommons/cc-legal-tools-app][cc-legal-tools-app] application.

faster-whisper is a reimplementation of OpenAI's Whisper model using CTranslate2, which is a fast inference engine for Transformer models. This implementation is up to 4 times faster than openai/whisper for the same accuracy while using less memory.

USP : Unvoice and Silence with Pitch when infer 1. Install project dependencies Note: whisper is already built-in, do not install it again otherwise it will cuase conflict and error 3.

     Self-hosted network discovery for homelabbers with Tailscale support. Scan your networks, discover devices, label and track them - all from a clean web UI or CLI.

This repo supports the paper "QLoRA: Efficient Finetuning of Quantized LLMs", an effort to democratize access to LLM research. QLoRA uses bitsandbytes for quantization and is integrated with Hugging Face's PEFT and transformers libraries.

A text prompt weighting and blending library for transformers-type text embedding systems, by @damian0815. With a flexible and intuitive syntax, you can re-weight different parts of a prompt string and thus re-weight the different parts of the embedding tensor produced from the string.

Website • Docs • Community Slack NannyML is an open-source python library that allows you to estimate post-deployment model performance (without access to targets), detect data drift, and intelligently link data drift alerts back to changes in model performance. Built for data scientists, NannyML has an easy-to-use interface, interactive visualizations, is completely model-agnostic and currently supports all tabular use cases, classification and regression.

Cloud | Documentation | Roadmap | Discord 📕 Table of Contents RAGFlow is a leading open-source Retrieval-Augmented Generation (RAG) engine that fuses cutting-edge RAG with Agent capabilities to create a superior context layer for LLMs. It offers a streamlined RAG workflow adaptable to enterprises of any scale.

Demo 🎶  |  📑 Paper HeartMuLa-oss-3B-happy-new-year 🤗  |  HeartMuLa-oss-3B-happy-new-year --- HeartMuLa is a family of open sourced music foundation models including: 1. HeartMuLa: a music language model that generates music conditioned on lyrics and tags with multilingual support covering almost all languages.

English | 简体中文 Usage of CDK for attacking targets without prior mutual consent is illegal. CDK is an open-sourced container penetration toolkit, designed for offering stable exploitation in different slimmed containers without any OS dependency.

A practical guide to building, scaling, and managing microservices architectures As defined by Sam Newman in his foundational text Building Microservices, microservices are "small, autonomous services that work together." This definition emphasizes the dual requirements of independence and interoperability. This adaptive framework considers your specific: Field basis: The methodology is an original synthesis by the author, refined through professional practice.

JIFF is a JavaScript library for building applications that rely on secure multi-party computation. JIFF is built to be highly flexible with a focus on usability, with the ability to be run in the browser, on mobile phones, or via Node.js.

GeoCalib is an algorithm for single-image calibration: it estimates the camera intrinsics and gravity direction from a single image only. By combining geometric optimization with deep learning, GeoCalib provides a more flexible and accurate calibration compared to previous approaches.