rewind.ai x cursor.com = your AI assistant that has all the context

Utilities intended for use with Llama models.

一本 GPT4 生成的单词书📚，超过 8000 个单词分析，涵盖了词义、例句、词根词缀、变形、文化背景、记忆技巧和小故事

A framework for serving and evaluating LLM routers - save LLM costs without compromising quality!

Using GPT to parse PDF

AI-data warehouse to enrich, transform and analyze unstructured data

Cambrian-1 is a family of multimodal LLMs with a vision-centric design.

TEN Agent is the world’s first real-time multimodal agent integrated with the OpenAI Realtime API, RTC, and features weather checks, web search, vision, and RAG capabilities.

SwarmUI (formerly StableSwarmUI), A Modular Stable Diffusion Web-User-Interface, with an emphasis on making powertools easily accessible, high performance, and extensibility.

Things you can do with the token embeddings of an LLM

Autoregressive Model Beats Diffusion: 🦙 Llama for Scalable Image Generation

Korvus is a search SDK that unifies the entire RAG pipeline in a single database query. Built on top of Postgres with bindings for Python, JavaScript, Rust and C.

[NeurIPS 2024] An official implementation of ShareGPT4Video: Improving Video Understanding and Generation with Better Captions

A toolkit to create optimal Production-readyRetrieval Augmented Generation(RAG) setup for your data

The code used to train and run inference with the ColPali architecture.

Official PyTorch implementation of Learning to (Learn at Test Time): RNNs with Expressive Hidden States

Easiest and laziest way for building multi-agent LLMs applications.

A SOTA lightweight multilingual LLM

🍦 Speech-AI-Forge is a project developed around TTS generation model, implementing an API Server and a Gradio-based WebUI.

Latitude is the open-source prompt engineering platform to build, evaluate, and refine your prompts with AI

A 4-hour coding workshop to understand how LLMs are implemented and used

Inference Microsoft Florence2 VLM

Agentless🐱: an agentless approach to automatically solve software development problems

Transformers-compatible library for applying various compression algorithms to LLMs for optimized deployment with vLLM

Yacine's LLM nvim scripts

EAGLE: Exploring The Design Space for Multimodal LLMs with Mixture of Encoders

Local SRT/LLM/TTS Voicechat

[NeurIPS 2024 Spotlight] Buffer of Thoughts: Thought-Augmented Reasoning with Large Language Models

🚀 一键部署个人的 ChatGPT 镜像站

The Official Implementation of PyramidKV: Dynamic KV Cache Compression based on Pyramidal Information Funneling

Instrument any LLM to do actual stuff.

A novel Multimodal Large Language Model (MLLM) architecture, designed to structurally align visual and textual embeddings.

An application for running LLMs locally on your device, with your documents, facilitating detailed citations in generated responses.

Official repository for "Alignment Data Synthesis from Scratch by Prompting Aligned LLMs with Nothing". Your efficient and high-quality synthetic data generation pipeline!

Official implementation of ⚡ Flash Diffusion ⚡: Accelerating Any Conditional Diffusion Model for Few Steps Image Generation

Bring Claude's Artifacts feature to ChatGPT

[SIGGRAPH Asia 2024 (Journal Track)] StableNormal: Reducing Diffusion Variance for Stable and Sharp Normal

A curated list of awesome open-source libraries for production LLM

gpt-2 from scratch in mlx

Index your memes by their content and text, making them easily retrievable for your meme warfare pleasures. Find funny fast.

llama3.cuda is a pure C/CUDA implementation for Llama 3 model.

The simplest and most cost-effective AI integration solution, enabling any device to achieve intelligent conversation functionality (based on ESP development boards). If you like this project, please give it a Star! | 最简单、最低成本的AI接入方案，让任何物品都能实现智能对话功能(基于ESP开发板)。喜欢本项目的话点个 Star 吧，您的一个 Star 对目前的仓库发展非常重要

A font for writing tiny stories

Replace OpenAI with Llama.cpp Automagically.

LiveBench: A Challenging, Contamination-Free LLM Benchmark

Awesome-Jailbreak-on-LLMs is a collection of state-of-the-art, novel, exciting jailbreak methods on LLMs. It contains papers, codes, datasets, evaluations, and analyses.

Vercel AI provider for Chrome built-in model (Gemini Nano)

LLM-powered lossless compression tool

Fast, streaming indexing and query library for AI (RAG) applications, written in Rust

Medical Multimodal LLMs

[NeurIPS'24 Spotlight] EVE: Encoder-Free Vision-Language Models

Official Repository of paper VideoGPT+: Integrating Image and Video Encoders for Enhanced Video Understanding

基于Node.js、Vue3、uniapp的ChatGPT+Midjourney绘画+Suno音乐+Pika/Runway/Sora视频 网页服务 | 个人、团队、企业私有化AIGC平台

Rust multiprovider generative AI client (Ollama, OpenAi, Anthropic, Groq, Gemini, Cohere, ...)

Model Merging in LLMs, MLLMs, and Beyond: Methods, Theories, Applications and Opportunities. arXiv:2408.07666.

大语言模型微调，Qwen2、GLM4指令微调

Fast Matrix Multiplications for Lookup Table-Quantized LLMs

GPT-SoVITS2

Tutorial for building LLM router

使用deepspeed从头开始训练一个LLM,经过pretrain和sft阶段,验证llm学习知识、理解语言、回答问题的能力

RAI is a multi-vendor agent framework for robotics, utilizing Langchain and ROS 2 tools to perform complex actions, defined scenarios, free interface execution, log summaries, voice interaction and more.

LLaRA: Large Language and Robotics Assistant

Cell type annotation with local Large Language Models (LLMs) - Ensuring privacy and speed with extensive customized reports

Build your own Face App with Stable Diffusion 2.1

Integrate LLM's into your OS. For any issues or ideas, message us in the discord server below!

Production ready LLM model compression/quantization toolkit with accelerated inference support for both cpu/gpu via HF, vLLM, and SGLang.

Platform of Open Intelligence eXperiences for Everyone. 面向所有人的开放智能体验平台，一站式AI对话工具聚合

Belullama is a comprehensive AI application that bundles Ollama, Open WebUI, and Automatic1111 (Stable Diffusion WebUI) into a single, easy-to-use package.

Code like an architect

🌍 Repository for "AppWorld: A Controllable World of Apps and People for Benchmarking Interactive Coding Agent", ACL'24 Best Resource Paper.

A toolbox for benchmarking trustworthiness of multimodal large language models (MultiTrust, NeurIPS 2024 Track Datasets and Benchmarks)

[NeurIPS 2024] Needle In A Multimodal Haystack (MM-NIAH): A comprehensive benchmark designed to systematically evaluate the capability of existing MLLMs to comprehend long multimodal documents.

🎙️ Speak with AI - Run locally using Ollama, OpenAI or xAI - Speech uses XTTS, OpenAI or ElevenLabs

Semantic Kernel for Java. Integrate cutting-edge LLM technology quickly and easily into your Java based apps. See https://aka.ms/semantic-kernel.

Automatic translate your language files into many languages using AI like Claude, GPT and etc.

[CoRL2024] Official repo of `A3VLM: Actionable Articulation-Aware Vision Language Model`

llama.cpp fork with additional SOTA quants and improved performance

A simple NPM interface for seamlessly interacting with 36 Large Language Model (LLM) providers, including OpenAI, Anthropic, Google Gemini, Cohere, Hugging Face Inference, NVIDIA AI, Mistral AI, AI21 Studio, LLaMA.CPP, and Ollama, and hundreds of models.

Sample GLM4V + ChatTTS AI assistant

VoCo-LLaMA: This repo is the official implementation of "VoCo-LLaMA: Towards Vision Compression with Large Language Models".

📖 A step-by-step guide for beginners to running Claude-generated React code locally.

A curated list of open source repositories for AI Engineers

Generate long weighted prompt embeddings for Stable Diffusion

《动手学SpringAI》包含SSE流/Agent智能体/知识图谱RAG/FunctionCall/历史消息/图片生成/图片理解/Embedding/VectorDatabase/RAG

Tiny client for LLMs with vision and tool calling. As simple as it gets.

LLaMA Factory Document

GenAI & LLM usecases and applications

Fixed Attention Couple, NegPip(negative weights in prompts) for SDXL and FLUX, more CFG++ and SMEA DY samplers, etc.

Swift library that utilize GPT-4o for scanning receipt and its items

A node.js project that generates short videos using popular AI LLM.

🌋👵🏻 Yo'LLaVA: Your Personalized Language and Vision Assistant

Visualizing the attention of vision-language models

RetroChat is a powerful command-line interface for interacting with various AI language models. It provides a seamless experience for engaging with different chat providers while offering robust features for managing and customizing your conversations. The code in this repo is 100% AI generated. Nothing has been written by a human.

A Comprehensive Benchmark for Code Information Retrieval.

The Library for LLM-based multi-agent applications

OpenShield is a new generation security layer for AI models

Chrome AI Test Page, running Gemini Nano locally in your browser.

This repository contains the training, inference, evaluation code for SpeechLLM models and details about the model releases on huggingface.