LLM101n: Let's build a Storyteller

🔥🕷️ Crawl4AI: Open-source LLM Friendly Web Crawler & Scrapper

llama3 implementation one matrix multiplication at a time

GLM-4 series: Open Multilingual Multimodal Chat LMs | 开源多语言多模态对话模型

Intelligence development framework in python for your product like Apple Intelligence

A self-organizing file system with llama 3

AI一键批量生成各类短视频,自动批量混剪短视频,自动把视频发布到抖音,快手,小红书,视频号上,赚钱从来没有这么容易过! 支持本地语音模型chatTTS,fasterwhisper,GPTSoVITS,支持云语音：Azure,阿里云,腾讯云。支持Stable diffusion,comfyUI直接AI生图。Generate short videos with one click using AI LLM,print money together! support:chatTTS,faster-whisper,GPTSoVITS,Azure,tencent Cloud,Ali Cloud.

A suite of tools to develop RAG, semantic search, and other AI applications more easily with PostgreSQL

Deploy your agentic worfklows to production

🍒 Cherry Studio is a desktop client that supports for multiple LLM providers

A fast multimodal LLM for real-time voice

llama3.np is a pure NumPy implementation for Llama 3 model.

We introduced a new model designed for the Code generation task. Its test accuracy on the HumanEval base dataset surpasses that of GPT-4 Turbo (April 2024) and GPT-4o.

The PyTorch implementation of Generative Pre-trained Transformers (GPTs) using Kolmogorov-Arnold Networks (KANs) for language modeling

Generate music based on natural language prompts using LLMs running locally

File Parser optimised for LLM Ingestion with no loss 🧠 Parse PDFs, Docx, PPTx in a format that is ideal for LLMs.

Accelerate your Stable Diffusion inference with the library's universal C/C++ framework design, powered by ONNXRuntime & across platforms.

LLM Analytics

The Open-Source Data Annotation Platform

从零实现一个 llama3 中文版

机械臂+大模型+多模态=人机协作具身智能体

An open-source AI content search engine designed specifically for content creators. Supports extraction of text, images, and short videos. Allows full local deployment (web app, RAG server, LLM server). Supports multi-modal RAG content Q&A.

Practice to LLM.

A Versatile and Robust SDXL-ControlNet Model for Adaptable Line Art Conditioning

Go manage your Ollama models

Fast voice assistant powered by Groq, Cartesia, and Vercel.

Chat with AI large language models running natively in your browser. Enjoy private, server-free, seamless AI conversations.

A recipe for online RLHF and online iterative DPO.

The collaborative spreadsheet for AI. Chain cells into powerful pipelines, experiment with prompts and models, and evaluate LLM responses in real-time. Work together seamlessly to build and iterate on AI applications.

An open-source implementation for training LLaVA-NeXT.

Ask LLM directly from your terminal

LLM Comparator is an interactive data visualization tool for evaluating and analyzing LLM responses side-by-side, developed by the PAIR team.

MarkLLM: An Open-Source Toolkit for LLM Watermarking.（EMNLP 2024 Demo）

Most intuitive unified AI chat interface.

Implementation of a single layer of the MMDiT, proposed in Stable Diffusion 3, in Pytorch

LLM Models and RAG Hands-on guide

[KDD'2024] "LLM4Graph: A Survey of Large Language Models for Graphs"

Llama-github is an open-source Python library that empowers LLM Chatbots, AI Agents, and Auto-dev Solutions to conduct Retrieval from actively selected GitHub public projects. It Augments through LLMs and Generates context for any coding question, in order to streamline the development of sophisticated AI-driven applications.

RLAIF-V: Aligning MLLMs through Open-Source AI Feedback for Super GPT-4V Trustworthiness

No frills LLM-assisted programming

无视ip、账号强开gpt-4o

Code I wrote for my AI & LLM workshops

Phi-3.5 for Mac: Locally-run Vision and Language Models for Apple Silicon

Ultra-Fast and Cheaper Long-Context LLM Inference

Self-hosted environment for programming tutorial by LLM

Model Compression Toolbox for Large Language Models and Diffusion Models

Efficient and easy multi-instance LLM serving

Official Repo for Fine-Tuning Large Vision-Language Models as Decision-Making Agents via Reinforcement Learning

LLMs in Finance - Generative AI - AI Agents

OpenGPT 4o is a free alternative to OpenAI GPT 4o

A python wrapper for the Doc2X API and comes with native texts processing (to improve PDF recall in RAG). | Doc2X API的python封装，同时附带本地的文本处理(提升PDF在RAG中的召回率)。

Full Stack SolarLLM Zero to All

Seamlessly integrate state-of-the-art transformer models into robotics stacks

TouchDesigner implementation for real-time Stable Diffusion interactive generation with StreamDiffusion.

Dataset Crafting w/ RAG/Wikipedia ground truth and Efficient Fine-Tuning Using MLX and Unsloth. Includes configurable dataset annotation editor Gradio UI.

AI Studio is an independent app for utilizing LLM.

Step-aware Preference Optimization: Aligning Preference with Denoising Performance at Each Step

Shire - AI Coding Agent Language (编程智能体语言), which can enables communication between an LLM and control IDE for automated programming.

Automated Data Analysis leveraging llms

Paper list of misinformation research using (multi-modal) large language models, i.e., (M)LLMs.

Open source alternative to Perplexity AI with ability to run locally

OccSora: 4D Occupancy Generation Models as World Simulators for Autonomous Driving

xFinder: Robust and Pinpoint Answer Extraction for Large Language Models

On-premise AI platform and microservices ecosystem. Also works as a desktop app.

The code and data for "MMLU-Pro: A More Robust and Challenging Multi-Task Language Understanding Benchmark" [NeurIPS 2024]

Awesome list for LLM quantization

Comparison of the output quality of quantization methods, using Llama 3, transformers, GGUF, EXL2.

Benchmarking library for RAG

Extension for A1111's Stable Diffusion Webui. Controls amount of detail.

Emotion-LLaMA: Multimodal Emotion Recognition and Reasoning with Instruction Tuning

Basic Stable Diffusion Workflows for ComyUI using minimal custom nodes

LLaMA 3 is one of the most promising open-source model after Mistral, we will recreate it's architecture in a simpler manner.

SDXL风格选择器优化版，具有分组、预览、多风格等功能

API up your Ollama Server.

Community Plugins for Genkit (OpenAI, Groq, Anthropic, Cohere, etc)

FisherAI 是一款为提高学习效率而设计的Chrome插件，通过一键操作，支持自动摘要、网页及视频翻译、多轮对话等功能。此外，FisherAI 支持多种大语言模型，包括但不限于gpt/azure/gemini/deepseek/mistral/groq/yi/moonshot等等，为用户提供灵活且强大的AI工具。

Official curricula for the LLMOPs course at Duke University

[NeurIPS 2024] Official implementation for paper "Can Graph Learning Improve Planning in LLM-based Agents?"

免费白嫖GPT4、GPT-4o和Gemini-1.5-pro 地址：https://ffa.chat *免费AI搜索：https://sou.ffa.chat

Matryoshka Multimodal Models

Local-GenAI-Search is a generative search engine based on Llama 3, langchain and qdrant that answers questions based on your local files

文本语料转训练集工具，txt转dataset

[NeurIPS 2024] CharXiv: Charting Gaps in Realistic Chart Understanding in Multimodal LLMs

A JavaScript implementation of Llama 3 using node-mlx.

CLI to demonstrate running a large language model (LLM) on Apple Neural Engine.

Ollama SDK for .NET

将ChatGPT网页转换成API接口。实现Cloudflare 5s盾破解，Arkose FunCaptcha验证码破解，邮箱账号自动登录，支持GPT-4o模型、多轮对话、高速流式输出、并完全兼容 ChatGPT接口。ChatGPT Free Web API.

Visualize your notes and see links to related content with AI embeddings. Use local models or 100+ via APIs like Claude, Gemini, ChatGPT & Llama 3

This repository is an implementation of quantizing and converting the Llama3-8B-Instruct model weights and deploying it on Android for on-device inference.

High level library for batched embeddings generation, blazingly-fast web-based RAG and quantized indexes processing ⚡