LLM training in simple, raw C/CUDA

SWE-agent takes a GitHub issue and tries to automatically fix it, using GPT-4, or your LM of choice. It solves 12.47% of bugs in the SWE-bench evaluation set and takes just 1 minute to run.

FreeAskInternet is a completely free, PRIVATE and LOCALLY running search aggregator & answer generate using MULTI LLMs, without GPU needed. The user can ask a question and the system will make a multi engine search and combine the search result to LLM and generate the answer based on search results. It's all FREE to use.

🔥 Turn entire websites into LLM-ready markdown or structured data. Scrape, crawl and extract with a single API.

Convert any URL to an LLM-friendly input with a simple prefix https://r.jina.ai/

Utilize the unlimited free GPT-3.5-Turbo API service provided by the login-free ChatGPT Web.

Llama3 中文仓库（聚合资料，各种网友及厂商微调、魔改版本有趣权重 & 训练、推理、评测、部署教程视频 & 文档）

The easiest way to use Agentic RAG in any enterprise

Implementation for MatMul-free LM.

Fully private LLM chatbot that runs entirely with a browser with no server needed. Supports Mistral and LLama 3.

free

🔍 AI search engine - self-host with local or cloud LLMs

Collection of awesome LLM apps with RAG using OpenAI, Anthropic, Gemini and opensource models.

Streamer-Sales 销冠 —— 卖货主播 LLM 大模型🛒🎁，一个能够根据给定的商品特点从激发用户购买意愿角度出发进行商品解说的卖货主播大模型。🚀⭐内含详细的数据生成流程❗ 📦另外还集成了 LMDeploy 加速推理🚀、RAG检索增强生成 📚、TTS文字转语音🔊、数字人生成 🦸、 Agent 使用网络查询实时信息🌐、ASR 语音转文字🎙️

《大语言模型》作者：赵鑫，李军毅，周昆，唐天一，文继荣

Turn any webpage into structured data using LLMs

《动手学大模型Dive into LLMs》系列编程实践教程

Making Agents Reliable In Production.

LM Studio CLI. Written in TypeScript/Node

High-quality datasets, tools, and concepts for LLM fine-tuning.

Code for 'LLM2Vec: Large Language Models Are Secretly Powerful Text Encoders'

Open-source alternative to Assistant's API with a managed backend for memory, RAG, tools and tasks. ~Supabase for building AI agents.

Automate development gruntwork like code reviews, patching and documentation with LLM workflows.

🔥🔥 LLaVA++: Extending LLaVA with Phi-3 and LLaMA-3 (LLaVA LLaMA-3, LLaVA Phi-3)

Evaluate your LLM's response with Prometheus and GPT4 💯

Fast lexical search library implementing BM25 in Python using Scipy (on average 2x faster than Elasticsearch in single-threaded setting)

An open source framework for building AI-powered apps with familiar code-centric patterns. Genkit makes it easy to integrate, test, and deploy sophisticated AI features to Firebase or Google Cloud.

An LLM-based Web Navigating Agent (KDD'24)

Grounded Multimodal Large Language Model with Localized Visual Tokenization

"ChatBot" AI application, supporting GPT, Gemini Pro, Cohere & Ollama models

A trivial programmatic Llama 3 jailbreak. Sorry Zuck!

clean & curate your data with LLMs.

Llama3-Tutorial（XTuner、LMDeploy、OpenCompass）

free chat gpt api

Agentic LLM Vulnerability Scanner

Stateful load balancer custom-tailored for llama.cpp

A library for easily merging multiple LLM experts, and efficiently train the merged LLM.

The Lightning Library for LLM Applications.

Unofficial PyTorch/🤗Transformers(Gemma/Llama3) implementation of Leave No Context Behind: Efficient Infinite Context Transformers with Infini-attention

This is the first Chinese chat model specifically fine-tuned for Chinese through ORPO based on the Meta-Llama-3-8B-Instruct model.

Practical Llama 3 inference in Java

Llama3-Chinese是以Meta-Llama-3-8B为底座，使用 DORA + LORA+ 的训练方法，在50w高质量中文多轮SFT数据 + 10w英文多轮SFT数据 + 2000单轮自我认知数据训练而来的大模型。

AI Device Template Featuring Whisper, TTS, Groq, Llama3, OpenAI and more

A list of top AI agents

An Improved Langchain RAG Tutorial (v2) with local LLMs, database updates, and testing.

port of Andrjey Karpathy's llm.c to Mojo

RAG-GPT, leveraging LLM and RAG technology, learns from user-customized knowledge bases to provide contextually relevant answers for a wide range of queries, ensuring rapid and accurate information retrieval.

A fuzzy key value store based on semantic similarity rather lexical equality.

MLX-VLM is a package for running Vision LLMs locally on your Mac using MLX.

Llama 3 API (MetaAI Reverse Engineered)

Chat with your own data - LLM+RAG workshop

Continual Learning of Large Language Models: A Comprehensive Survey

From scratch implementation of a vision language model in pure PyTorch

On-device LLM Inference Powered by X-Bit Quantization

A repository dedicated to evaluating the performance of quantizied LLaMA3 using various quantization methods..

An enterprise-grade AI retriever designed to streamline AI integration into your applications, ensuring cutting-edge accuracy.

Jailbreaking Leading Safety-Aligned LLMs with Simple Adaptive Attacks [arXiv, Apr 2024]

Official code for Paper "Mantis: Multi-Image Instruction Tuning"

Dify in comfyui. Compatible with Omost. Adapted to all models with an interface similar to OpenAI’s, such as: Tongyi Qianwen/qwen, Zhipu Qingyan/GLM, Deepseek, Kimi/Moonshot.（comfyui中的Dify，已兼容Omost，适配了所有具有类似openai接口的模型，例如：通义千问/qwen、智谱清言/GLM、deepseek、kimi/moonshot。）

Image Textualization: An Automatic Framework for Generating Rich and Detailed Image Descriptions

WorldGPT: Empowering LLM as Multimodal World Model

LLM prompts, llama3 prompts, llama2 prompts

Local LLM App

Knowledge graph construction and RAG demo using Diffbot and Neo4j

Transform your simple scribbles into architectural designs using style transfer with Stable Diffusion, LCM, IP Adapters and ControlNet. Scribble Architect combines creativity with generative AI technology, improving the inspiration process.

Fine-tuning code for CLIP models

DevoxxGenie is a plugin for IntelliJ IDEA that uses local LLM's (Ollama, LMStudio, GPT4All and Jan) and Cloud based LLMs to help review, test, explain your project code.

Attribute (or cite) statements generated by LLMs back to in-context information.

Spider2-V: How Far Are Multimodal Agents From Automating Data Science and Engineering Workflows?

QA-Pilot is an interactive chat project that leverages online/local LLM for rapid understanding and navigation of GitHub code repository.

自动化构建漫画推文，使用stable diffusion来生成图片

😜 表情包视觉数据集，使用glm-4v、step-1v的图像解析能力标注。

Raycast extension to use GPT-4, Llama-3, and more... all for FREE. No API Key required!

🧑‍🚀 全世界最好的中文LLM资料总结

一些 LLM 方面的从零复现笔记

PsyDI: Towards a Personalized and Progressively In-depth Chatbot for Psychological Measurements. (e.g. MBTI Measurement Agent)

Here's how to use Lama3 for beginners and what services are being used.

RAG(Retrieval-Augmented Generation) for Evolving Data

[CVPR 2024] 🏡Know Your Neighbors: Improving Single-View Reconstruction via Spatial Vision-Language Reasoning

Self-paced bootcamp on Generative AI. Tutorials on ML fundamentals, LLMs, RAGs, LangChain, Fine-tuning & AI Agents (CrewAI)

tAI is an AI terminal assistant CLI that helps you with Linux and macOS commands.

A simple, intuitive toolkit for quickly implementing LLM powered applications.

对llama3进行全参微调、lora微调以及qlora微调。

Yet another operator for running large language models on Kubernetes with ease. Powered by Ollama! 🐫

一个基于 cloudflare worker 的 LLM API 反向代理，支持 OpenAI, Gemini, Groq 等平台。接口兼容 OpenAI API 规范，可以直接使用 OpenAI SDK 调用。

Documentation of AnythingLLM by Mintplex Labs Inc.

JS tokenizer for LLaMA 3

This repo aims to help developers to get into the genAI topic quicker by automating AI Core and HANA Vector Engine provisioning and configuration with Terraform Provider for SAP BTP.

Official PyTorch implementation of CODA-LM(https://arxiv.org/abs/2404.10595)

all ComfyUI http/ws APIs. support NodeJS / Browser environments. and advanced programmable workflow.

A Multi-Agent FrameWork For Faster Build Agents

This repository provides an advanced Retrieval-Augmented Generation (RAG) solution for complex question answering. It uses sophisticated graph based algorithm to handle the tasks.

AI 应用示例合集

Your AI Powered Enterprise Knowledge Partner. Designed to be used at scale from ingesting large amounts of documents formats such as pdfs, docx, xlsx, png, jpgs, tiff, mp3, mp4, jpeg. Integrates with s3, Windows Shares, Google Drive and more.

A Webapp that uses Retrieval Augmented Generation (RAG) and Large Language Models to interact with a PDF directly in the browser.

Reproduction of LLaVA-v1.5 based on Llama-3-8b LLM backbone.