🐚 OpenDevin: Code Less, Make More

The official Meta Llama 3 GitHub site

Open-Sora: Democratizing Efficient Video Production for All

Python scraper based on AI

This project aim to reproduce Sora (Open AI T2V model), we wish the open source community contribute to this project.

A modular graph-based Retrieval-Augmented Generation (RAG) system

MiniCPM-Llama3-V 2.5: A GPT-4V Level Multimodal LLM on Your Phone

Building a quick conversation-based search demo with Lepton AI.

A UI-Focused Agent for Windows OS Interaction.

The open source platform for AI-native application development.

Automate browser-based workflows with LLMs and Computer Vision

Composio equips agents with well-crafted tools empowering them to tackle complex tasks

Large Action Model framework to develop AI Web Agents

SGLang is a fast serving framework for large language models and vision language models.

An LLM-powered knowledge curation system that researches a topic and generates a full-length report with citations.

Examples and guides for using the Gemini API.

MiniCPM-2B: An end-side LLM outperforming Llama2-13B.

🚀 KIMI AI 长文本大模型逆向API白嫖测试【特长：长文本解读整理】，支持高速流式输出、智能体对话、联网搜索、长文档解读、图像OCR、多轮对话，零配置部署，多路token支持，自动清理会话痕迹。

Official repo for "Mini-Gemini: Mining the Potential of Multi-modality Vision Language Models"

Devon: An open-source pair programmer

Build AI assistants that interact with your systems

Start building LLM-empowered multi-agent applications in an easier way.

Supabase for RAG - Build and scale production-ready user facing AI apps

Mobile-Agent: The Powerful Mobile Device Operation Assistant Family

CSGHub is an opensource large model assets platform just like on-premise huggingface which helps to manage datasets, model files, codes and more.　CSGHub是一个开源、可信的大模型资产管理平台，可帮助用户治理LLM和LLM应用生命周期中涉及到的资产（数据集、模型文件、代码等）。CSGHub提供类似私有化的Huggingface功能，以类似OpenStack Glance管理虚拟机镜像、Harbor管理容器镜像以及Sonatype Nexus管理制品的方式，实现对LLM资产的管理。欢迎关注反馈和Star⭐️

LLM Zoomcamp - a free online course about building a Q&A system

Open weights LLM from Google DeepMind.

Run PyTorch LLMs locally on servers, desktop and mobile

DeepSeek-VL: Towards Real-World Vision-Language Understanding

基于大模型的智能对话客服工具，支持微信、千牛、哔哩哔哩、抖音企业号、抖音、抖店、微博聊天、小红书专业号运营、小红书、知乎等平台接入，可选择 GPT3.5/GPT4.0/ 懒人百宝箱 （后续会支持更多平台），能处理文本、语音和图片，通过插件访问操作系统和互联网等外部资源，支持基于自有知识库定制企业 AI 应用。

Parse files for optimal RAG

Wren AI makes your database RAG-ready. Implement Text-to-SQL more accurately and securely.

The Cradle framework is a first attempt at General Computer Control (GCC). Cradle supports agents to ace any computer task by enabling strong reasoning abilities, self-improvment, and skill curation, in a standardized general environment with minimal requirements.

Training LLMs with QLoRA + FSDP

chatGPT、prompt、LLM

MiniSora: A community aims to explore the implementation path and future development direction of Sora.

FinRobot: An Open-Source AI Agent Platform for Financial Applications using LLMs 🚀 🚀 🚀

Lag-Llama: Towards Foundation Models for Probabilistic Time Series Forecasting

Use API to call the music generation AI of suno.ai, and easily integrate it into agents like GPTs.

基于.Net8+AntBlazor+SemanticKernel 和KernelMemory 打造的AI知识库/智能体，支持本地离线AI大模型。可以不联网离线运行。支持aspire观测应用数据

Accelerating the development of large multimodal models (LMMs) with lmms-eval

Benchmark LLMs by fighting in Street Fighter 3! The new way to evaluate the quality of an LLM

ELLA: Equip Diffusion Models with LLM for Enhanced Semantic Alignment

Sora AI Video Generator by Sora.FM

🤖 𝗟𝗲𝗮𝗿𝗻 for 𝗳𝗿𝗲𝗲 how to 𝗯𝘂𝗶𝗹𝗱 an end-to-end 𝗽𝗿𝗼𝗱𝘂𝗰𝘁𝗶𝗼𝗻-𝗿𝗲𝗮𝗱𝘆 𝗟𝗟𝗠 & 𝗥𝗔𝗚 𝘀𝘆𝘀𝘁𝗲𝗺 using 𝗟𝗟𝗠𝗢𝗽𝘀 best practices: ~ 𝘴𝘰𝘶𝘳𝘤𝘦 𝘤𝘰𝘥𝘦 + 11 𝘩𝘢𝘯𝘥𝘴-𝘰𝘯 𝘭𝘦𝘴𝘴𝘰𝘯𝘴

RAG Search API

No-code LLM Platform to launch APIs and ETL Pipelines to structure unstructured documents

An open-source, high-performance SQL vector database built on ClickHouse.

LLM powered fuzzing via OSS-Fuzz.

The codes about "Uni-MoE: Scaling Unified Multimodal Models with Mixture of Experts"

OpenLIT: Complete Observability and Evals for the Entire GenAI Stack, from LLMs to GPUs. Improve your LLM apps from playground to production 📈. Supports 20+ monitoring integrations like OpenAI & LangChain. Collect and Send GPU performance, costs, tokens, user activity, LLM traces and metrics to any OpenTelemetry endpoint in just one line of code.

Examples and guides for using the GLM APIs

Code for "AnyGPT: Unified Multimodal LLM with Discrete Sequence Modeling"

The easiest way to get started with LlamaIndex

Build your own serverless AI Chat with Retrieval-Augmented-Generation using LangChain.js, TypeScript and Azure

MobiLlama : Small Language Model tailored for edge devices

[ICML'24 Spotlight] LLM Maybe LongLM: Self-Extend LLM Context Window Without Tuning

A demo application using fal.realtime and the lightning fast SDXL API provided by fal

A personal wearable AI that runs locally

心理健康大模型、LLM、The Big Model of Mental Health、Finetune、InternLM2、Qwen、ChatGLM、Baichuan、DeepSeek、Mixtral、LLama3

Train Models Contrastively in Pytorch

A PyTorch Native LLM Training Framework

LightEval is a lightweight LLM evaluation suite that Hugging Face has been using internally with the recently released LLM data processing library datatrove and LLM training library nanotron.

Efficient AI Inference & Serving

仅需Python基础，从0构建大语言模型；从0逐步构建GLM4\Llama3\RWKV6， 深入理解大模型原理

🚀 智谱清言 ChatGLM4大模型逆向API白嫖测试【特长：超强智能体】，支持高速流式输出、支持智能体对话、支持多轮对话、支持AI绘图、支持联网搜索、支持长文档解读、支持代码调用、支持图像解析，零配置部署，多路token支持，自动清理会话痕迹。

structured extraction for llms

Official code for MiniGPT4-video

[ACL 2024] Progressive LLaMA with Block Expansion.

AI Powered Search and Chat for Orgs - Think ChatGPT meets Google Search but powered by your data.

🐝 GPTSwarm: LLM agents as (Optimizable) Graphs

Video Search and Streaming Agent 🕵️‍♂️

A flexible and efficient codebase for training visually-conditioned language models (VLMs)

Scalable toolkit for data curation

Super performant RAG pipelines for AI apps. Summarization, Retrieve/Rerank and Code Interpreters in one simple API.

Neo4j graph construction from unstructured data

VisionLLaMA: A Unified LLaMA Interface for Vision Tasks

HPT - Open Multimodal LLMs from HyperGAI

Palico provides a set of integrated tools to help you rapidly iterate through building, experimenting, and deploying your LLM Application

The React library for LLMs

[ICML 2024] LESS: Selecting Influential Data for Targeted Instruction Tuning

Paper list for Personal LLM Agents

[ICML'24] Data and code for our paper "Training-Free Long-Context Scaling of Large Language Models"

The most advanced Web UI for AI chat

BitBLAS is a library to support mixed-precision matrix multiplications, especially for quantized LLM deployment.

Agents in Markdown syntax (loops, memory and tools included).

Create, share, and run runbooks from your terminal.

KVQuant: Towards 10 Million Context Length LLM Inference with KV Cache Quantization

🤖 Admyral's Python SDK simplifies writing workflow automations for Security Engineers

The code of our paper "InfLLM: Unveiling the Intrinsic Capacity of LLMs for Understanding Extremely Long Sequences with Training-Free Memory"

A collection of sample programs, notebooks, and tools which highlight the power of the MAX Platform

Seamless Bug Detection Throughout Your Development Cycle

Create-tsi is a generative AI RAG toolkit which generates AI Applications with low code.

Integrating AI into every workflow with our open-source, no-code platform, powered by the actor model for dynamic, graph-based solutions.

The Open Assistant API is a ready-to-use, open-source, self-hosted agent/gpts orchestration creation framework, supporting customized extensions for LLM, RAG, function call, and tools capabilities. It also supports seamless integration with the openai/langchain sdk.

Sora AI Awesome List – Your go-to resource hub for all things Sora AI, OpenAI's groundbreaking model for crafting realistic scenes from text. Explore a curated collection of articles, videos, podcasts, and news about Sora's capabilities, advancements, and more.

Official Repository of ChartX & ChartVLM: A Versatile Benchmark and Foundation Model for Complicated Chart Reasoning

A linter with superpowers! 🔥 Use LLMs to enforce best practices across your codebase.

The most powerful and modular Sora WebUI, api and backend with OpenAI's Sora Model. Collecting the highest quality prompts for Sora. using NextJs and Tailwind CSS