User-friendly AI Interface (Supports Ollama, OpenAI API, ...)

Brand new TTS solution

ChatGLM3 series: Open Bilingual Chat LLMs | 开源双语对话语言模型

Letta (formerly MemGPT) is a framework for creating LLM services with memory.

An Autonomous LLM Agent for Complex Task Solving

🚀 Power Your World with AI - Explore, Extend, Empower.

Simple and efficient pytorch-native transformer text generation in <1000 LOC of python.

本项目是一个面向小白开发者的大模型应用开发教程，在线阅读地址：https://datawhalechina.github.io/llm-universe/

PyTorch native finetuning library

A blazing fast inference solution for text embeddings models

A developer reference project for creating Retrieval Augmented Generation (RAG) chatbots on Windows using TensorRT-LLM

Multi-LoRA inference server that scales to 1000s of fine-tuned LLMs

Fast stable diffusion on CPU

Maid is a cross-platform Flutter app for interfacing with GGUF / llama.cpp models locally, and with Ollama and OpenAI models remotely.

Infinity is a high-throughput, low-latency REST API for serving text-embeddings, reranking models, clip, clap and colpali

Developer APIs to Accelerate LLM Projects

[NeurIPS 2024] OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments

Workflow-to-APP、ScreenShare&FloatingVideo、GPT & 3D、SpeechRecognition&TTS

BAML is a language that helps you get structured data from LLMs, with the best DX possible. Works with all languages. Check out the promptfiddle.com playground

Leaderboard Comparing LLM Performance at Producing Hallucinations when Summarizing Short Documents

Skywork series models are pre-trained on 3.2TB of high-quality multilingual (mainly Chinese and English) and code data. We have open-sourced the model, training data, evaluation data, evaluation methods, etc. 天工系列模型在3.2TB高质量多语言和代码数据上进行预训练。我们开源了模型参数，训练数据，评估数据，评估方法。

The easiest & fastest way to run customized and fine-tuned LLMs locally or on the edge

✨ Hotshot-XL: State-of-the-art AI text-to-GIF model trained to work alongside Stable Diffusion XL

A curated list of awesome LLM for Autonomous Driving resources (continually updated)

AI agent using GPT-4V(ision) capable of using a mouse/keyboard to interact with web UI

A curated list of safety-related papers, articles, and resources focused on Large Language Models (LLMs). This repository aims to provide researchers, practitioners, and enthusiasts with insights into the safety implications, challenges, and advancements surrounding these powerful models.

Awesome-LLM-RAG: a curated list of advanced retrieval augmented generation (RAG) in Large Language Models

Chat with your documents using local AI

AIlice is a fully autonomous, general-purpose AI agent.

Official implementation of paper "MiniGPT-5: Interleaved Vision-and-Language Generation via Generative Vokens"

BlueLM(蓝心大模型): Open large language models developed by vivo AI Lab

Logging Made Easy (LME) is a no-cost and open logging and protective monitoring solution serving all organizations.

An LLM-powered advanced RAG pipeline built from scratch

【三年面试五年模拟】算法工程师秘籍。涵盖AIGC、传统深度学习、自动驾驶、机器学习、计算机视觉、自然语言处理、SLAM、具身智能、元宇宙、AGI等AI行业面试笔试经验与干货知识。

Web UI for AutoGen (A Framework Multi-Agent LLM Applications)

OpenSPG is a Knowledge Graph Engine developed by Ant Group in collaboration with OpenKG, based on the SPG (Semantic-enhanced Programmable Graph) framework. Core Capabilities: 1) domain model constrained knowledge modeling, 2) facts and logic fused representation, 3) KAG will be natively supported soon, so please stay tuned...

🤖 Components Library for Quickly Building LLM Chat Interfaces.

The papers are organized according to our survey: Evaluating Large Language Models: A Comprehensive Survey.

LLMPerf is a library for validating and benchmarking LLMs

A comprehensive library for implementing LLMs, including a unified training pipeline and comprehensive model evaluation.

An Obsidian plugin to interact with your privacy focused AI-Assistant making your second brain even smarter!

DISC-FinLLM，中文金融大语言模型（LLM），旨在为用户提供金融场景下专业、智能、全面的金融咨询服务。DISC-FinLLM, a Chinese financial large language model (LLM) designed to provide users with professional, intelligent, and comprehensive financial consulting services in financial scenarios.

👁️ + 💬 + 🎧 = 🤖 Curated list of top foundation and multimodal models! [Paper + Code + Examples + Tutorials]

Speech, Language, Audio, Music Processing with Large Language Model

Agent that empowers software testing with LLMs; industrial-first in China

[ICLR 2024] Sheared LLaMA: Accelerating Language Model Pre-training via Structured Pruning

Awesome-llm-role-playing-with-persona: a curated list of resources for large language models for role-playing with assigned personas

Simple frontend for LLMs built in react-native.

Agent Cloud is like having your own GPT builder with a bunch extra goodies. The GUI features 1) RAG pipeline which can natively embed 260+ datasources 2) Create Conversational apps (like GPTs) 3) Create Multi Agent process automation apps (crewai) 4) Tools 5) Teams+user permissions. Get started fast with Docker and our install.sh

The easiest way to use the Ollama API in .NET

☁️A native Android app for ChatGPT, Gemini, and Claude ☁️ChatGPT、Gemini 和 Claude 的原生安卓应用程序

Train and Infer Powerful Sentence Embeddings with AnglE | 🔥 SOTA on STS and MTEB Leaderboard

👀 What LLM to use?

LLM (Large Language Model) FineTuning

RoleLLM: Benchmarking, Eliciting, and Enhancing Role-Playing Abilities of Large Language Models

Code and datasets for "Character-LLM: A Trainable Agent for Role-Playing"

Private Open AI on Kubernetes

An all-in-one AI audio playground using Cloudflare AI Workers to transcribe, analyze, summarize, and translate any audio file.

Open Source LLM toolkit to build trustworthy LLM applications. TigerArmor (AI safety), TigerRAG (embedding, RAG), TigerTune (fine-tuning)

Personal Project: MPP-Qwen14B & MPP-Qwen-Next(Multimodal Pipeline Parallel based on Qwen-LM). Support [video/image/multi-image] {sft/conversations}. Don't let the poverty limit your imagination! Train your own 8B/14B LLaVA-training-like MLLM on RTX3090/4090 24GB.

[WSDM'2024 Oral] "LLMRec: Large Language Models with Graph Augmentation for Recommendation"

支持将openai、claude、azure openai, gemini,kimi, 智谱AI,通义千问,讯飞星火API等模型服务方的调用转为openai方式调用。屏蔽不同大模型API的差异，统一用openai api标准格式使用大模型(Shield the differences between different large model APIs and use large models in a unified openai API standard format)

Production-ready MVP for securely chatting with your documents using pgvector

Multi-node production GenAI stack. Run the best of open source AI easily on your own servers. Easily add knowledge from documents and scrape websites. Create your own AI by fine-tuning open source models. Integrate LLMs with APIs. Run gptscript securely on the server

AnimationGPT:An AIGC tool for generating game combat motion assets

Provide best practices for LMOps, as well as elegant and convenient access to the features of the Qianfan MaaS Platform. (提供大模型工具链最佳实践，以及优雅且便捷地访问千帆大模型平台）

The repository for the survey paper <<Survey on Large Language Models Factuality: Knowledge, Retrieval and Domain-Specificity>>

Create knowledge graphs with LLMs

Guideline following Large Language Model for Information Extraction

An open-sourced LLM judge for evaluating LLM-generated answers.

Evaluation suite for LLMs

A multithreaded 🕸️ web crawler that recursively crawls a website and creates a 🔽 markdown file for each page, designed for LLM RAG

An AGentic Intelligence Operating System

Code for the paper "Rethinking Benchmark and Contamination for Language Models with Rephrased Samples"

Run MemGPT-AutoGEN-Local LLM Together

On the Road with GPT-4V(ision): Explorations of Utilizing Visual-Language Model as Autonomous Driving Agent

ComfyUI as a serverless API on RunPod

Library for generating vector embeddings, reranking in Rust

六爻游戏 + GPT 解读 / liu yao divining + interpreted by GPT

Awesome papers involving LLMs in Social Science.

Chrome Extension to Summarize or Chat with Web Pages/Local Documents Using locally running LLMs. Keep all of your data and conversations private. 🔐

0️⃣1️⃣🤗 BitNet-Transformers: Huggingface Transformers Implementation of "BitNet: Scaling 1-bit Transformers for Large Language Models" in pytorch with Llama(2) Architecture

GenAIOps with Prompt Flow is a "GenAIOps template and guidance" to help you build LLM-infused apps using Prompt Flow. It offers a range of features including Centralized Code Hosting, Lifecycle Management, Variant and Hyperparameter Experimentation, A/B Deployment, reporting for all runs and experiments and so on.

欢迎来到 "LLM-travel" 仓库！探索大语言模型（LLM）的奥秘 🚀。致力于深入理解、探讨以及实现与大模型相关的各种技术、原理和应用。

Minimalistic UI for Ollama LMs - This powerful react interface for LLMs drastically improves the chatbot experience and works offline.

Data extraction with LLM on CPU

Metrics to evaluate the quality of responses of your Retrieval Augmented Generation (RAG) applications.

Minimalist web-searching platform with an AI assistant that runs directly from your browser. Uses Web-LLM, Wllama and SearXNG. Demo: https://felladrin-minisearch.hf.space

ALwrity - All in One AI Content Platform. Contextual AI Content generation for Website, Social media & Ad copywriting. Prevents AI hallucinations, Web Researched factual, SEO optimized content. Get blog Images. Create your AI Agents Content team. Generate content with RAG, Local documents, web urls, PDFs. Open Source AI writer. (WIP)

LLM Frontend in a single html file

[CVPR'24] HallusionBench: You See What You Think? Or You Think What You See? An Image-Context Reasoning Benchmark Challenging for GPT-4V(ision), LLaVA-1.5, and Other Multi-modality Models

AlignProp uses direct reward backpropogation for the alignment of large-scale text-to-image diffusion models. Our method is 25x more sample and compute efficient than reinforcement learning methods (PPO) for finetuning Stable Diffusion

We jailbreak GPT-3.5 Turbo’s safety guardrails by fine-tuning it on only 10 adversarially designed examples, at a cost of less than $0.20 via OpenAI’s APIs.

Scientific Large Language Models: A Survey on Biological & Chemical Domains

An innovative open-source Code Interpreter with (GPT,Gemini,Claude,LLaMa) models.

EMNLP 23 - Integrating Whisper Encoder to LLaMA Decoder for Generative ASR Error Correction