RAGFlow is an open-source RAG (Retrieval-Augmented Generation) engine based on deep document understanding.

High-speed Large Language Model Serving on PCs with Consumer-grade GPUs

AppAgent: Multimodal Agents as Smartphone Users, an LLM-based multimodal agent framework designed to operate smartphone apps.

SUPIR aims at developing Practical Algorithms for Photo-Realistic Image Restoration In the Wild. Our new online demo is also released at suppixel.ai.

Enchanted is iOS and macOS app for chatting with private self hosted language models such as Llama2, Mistral or Vicuna using Ollama.

Set of tools to assess and improve LLM security.

深入探索精选的套壳站和必备API资源。本文为初学者和经验丰富的运营者提供一站式指南，涵盖常见问题解答和基础攻略，助您迈向套壳站副业成功之路。Dive into a curated selection of shell sites and essential APIs. This article offers a comprehensive guide for both beginners and seasoned operators, covering FAQs and basic strategies to propel you towards success in your shell site side hustle.

这是一个全自动（音频）视频翻译项目。利用Whisper识别声音，AI大模型翻译字幕，最后合并字幕视频，生成翻译后的视频。

LLM&VLM Tutorial

[ICML 2024] LLMCompiler: An LLM Compiler for Parallel Function Calling

Tensor parallelism is all you need. Run LLMs on an AI cluster at home using any device. Distribute the workload, divide RAM usage, and increase inference speed.

Easy token price estimates for 400+ LLMs. TokenOps.

TinyGPT-V: Efficient Multimodal Large Language Model via Small Backbones

Awesome-LLM-3D: a curated list of Multi-modal Large Language Model in 3D world Resources

✨ AI-powered coding, seamlessly in Neovim. Supports Anthropic, Copilot, Gemini, Ollama, OpenAI and xAI LLMs

A curated list of Large Language Model (LLM) Interpretability resources.

Help your LLMs online

Strong and Open Vision Language Assistant for Mobile Devices

[CVPR2024] StableVITON: Learning Semantic Correspondence with Latent Diffusion Model for Virtual Try-On

A benchmark to evaluate language models on questions I've previously asked them to solve.

Mamba-Chat: A chat LLM based on the state-space model architecture 🐍

the resources about the application based on LLM with RAG pattern

制作懂人情世故的大语言模型 | 提示词工程、RAG、Agent、微调全流程教程

[CVPR2024] The code for "Osprey: Pixel Understanding with Visual Instruction Tuning"

LLM Transparency Tool (LLM-TT), an open-source interactive toolkit for analyzing internal workings of Transformer-based language models. *Check out demo at* https://huggingface.co/spaces/facebook/llm-transparency-tool-demo

A toolkit for inference and evaluation of 'mixtral-8x7b-32kseqlen' from Mistral AI

Awesome papers about generative Information Extraction (IE) using Large Language Models (LLMs)

The official Node.js / Typescript library for the Google Gemini API

LLM abstractions that aren't obstructions

Deploy your private Gemini application for free with one click, supporting Gemini 1.5 Pro, Gemini 1.5 Flash, Gemini Pro and Gemini Pro Vision models. 一键免费部署您的私人 Gemini 应用, 支持 Gemini 1.5 Pro、Gemini 1.5 Flash、Gemini Pro 和 Gemini Pro Vision 模型。

Create characters in Unity with LLMs!

A GPT-4/Gemini Voice/Video Exploration Tool

A Home Assistant integration & Model to control your smart home using a Local LLM

[CVPR 2024] LMDrive: Closed-Loop End-to-End Driving with Large Language Models

Lite & Super-fast re-ranking for your search & retrieval pipelines. Supports SoTA Listwise and Pairwise reranking based on LLMs and cross-encoders and more. Created by Prithivi Da, open for PRs & Collaborations.

Stable Video Diffusion Training Code and Extensions.

A proxy for converting the OpenAI API protocol to the Google Gemini Pro protocol.

Structured outputs for LLMs in Elixir

RTP-LLM: Alibaba's high-performance LLM inference engine for diverse applications.

Quick Start for Large Language Models (Theoretical Learning and Practical Fine-tuning) 大语言模型快速入门（理论学习与微调实战）

A multi-platform desktop application to evaluate and compare LLM models, written in Rust and React.

The llama-cpp-agent framework is a tool designed for easy interaction with Large Language Models (LLMs). Allowing users to chat with LLM models, execute structured function calls and get structured output. Works also with models not fine-tuned to JSON output and function calls.

[ICML 2024] TrustLLM: Trustworthiness in Large Language Models

Rapid prototyping of web apps using plain english 👶🤖