Overview This repository contains a lightweight library for evaluating language models. We are open sourcing it so we can be transparent about the accuracy numbers we're publishing alongside our latest models (starting with gpt-4-turbo-2024-04-09). Evals are sensitive to prompting, and there's significant variation in the formulations used in recent publications and libraries. Some use few-shot prompts or role playing prompts ("You are an expert software programmer..."). These a…
An LLM-powered knowledge curation system that researches a topic and generates a full-length report with citations.STORM: Synthesis of Topic Outlines through Retrieval and Multi-perspective Question Asking This repository contains the code for our NAACL 2024 paper Assisting in Writing Wikipedia-like Articles From Scratch with Large Language Models by Yijia Shao, Yucheng Jiang, Theodore A. Kanell, Peter Xu, Omar Khattab, and Monica S. Lam. Overview (Try STORM now!) STORM is a LLM system tha…
Your Next SaaS Template or Boilerplate ! A magic trip start with `bun create saasfly` . The more stars, the more surprises Saasfly An easy-to-use and enterprise-grade Next.js boilerplate. You don't need to buy templates anymore; Saasfly provides a complete, open-source solution for building SaaS applications quickly and easily. Nextify provides a complete Enterprise SaaS solution. Contact us at contact@nextify.ltd if you're interested in discussing your project, or if …
Fast drag and drop for any experience on any tech stack Fast drag and drop for any experience on any tech stack 📖 Documentation | 🤹 Examples | 🎥 How it works About Pragmatic drag and drop is a low level drag and drop toolchain that enables safe and successful usage of the browsers built in drag and drop functionality. Pragmatic drag and drop can be used with any view layer (react, svelte, vue, angular and so on). Pragmatic drag and drop is powering some of the biggest products on th…
Pretrain, finetune, deploy 20+ LLMs on your own data. Uses state-of-the-art techniques: flash attention, FSDP, 4-bit, LoRA, and more. ⚡ LitGPT Pretrain, finetune, deploy 20+ LLMs on your own data Uses the latest state-of-the-art techniques: ✅ fp4/8/16/32 ✅ LoRA, QLoRA, Adapter (v1, v2) ✅ flash attention ✅ FSDP ✅ 1-1000+ GPUs/TPUs Lightning.ai • Install • Get started • Use LLMs • Finetune, pretrain LLMs • Models • Features • Training recipes (YAML) • …
Microsoft Copilot for Security is a generative AI-powered security solution that helps increase the efficiency and capabilities of defenders to improve security outcomes at machine speed and scale, while remaining compliant to responsible AI principles Microsoft Copilot For Security Community Welcome to the Copilot for Security Repository! Microsoft Copilot for Security is a generative AI-powered assistant for daily operations in security and IT that empowers teams to protect at the speed and s…
Backport of .NET 2.0 - 3.5 to Windows 9x.NET Framework 2.0 - 3.5 for Windows 9x Introduction This project is a work-in-progress backport of .NET Framework 2.0 - 3.5 to Windows 9x. Currently 2.0 is believed to be largely functional while work on 3.5 has just begun. Officially, .NET Framework 3.5 never supported anything below XP, and .NET in general never supported 95. This project changes that, backporting CLR 2.0 to 95 and Framework 3.5 to 9x. Installation Windows 95 .NET CLR 2.0 requires…
Inference and training library for high-quality TTS models.Parler-TTS Parler-TTS is a lightweight text-to-speech (TTS) model that can generate high-quality, natural sounding speech in the style of a given speaker (gender, pitch, speaking style, etc). It is a reproduction of work from the paper Natural language guidance of high-fidelity text-to-speech with synthetic annotations by Dan Lyth and Simon King, from Stability AI and Edinburgh University respectively. Contrarily to other TTS models, Pa…
Benchmarking JS web framework SSR performanceSSR Framework Benchmark This is an experiment in response to https://twitter.com/thdxr/status/1777782835249553517 where it is stated that Next.JS is a lot slower on server side rendering compared to Vanilla React. This is not a comprehensive or scientific test. Just wanted to compare each in a setup a little complex than just printing hello world. Results (index) name ops/sec average (ms) samples body (kb) duplication relative to react 0 '…