LinkedIn_AIHawk is a tool that automates the jobs application process on LinkedIn. Utilizing artificial intelligence, it enables users to apply for multiple job offers in an automated and personalized way.

Efficient Triton Kernels for LLM Training

nanoGPT style version of Llama 3.1

This is the public code repository of paper 'Comprehensive Assessment of Jailbreak Attacks Against LLMs'

Inspired by Zed AI, it allows you to chat with your buffers, insert code with an inline assistant, and leverage various LLM providers for context-aware AI assistance.

Chat with your data, modify it, visualize it, create and test machine learning models all in plain English. DataHorse makes data analysis and data science conversational using LLMs.

A curative list of 3D Vision papers relating to Robotics domain in the era of large models i.e. LLMs/VLMs, inspired by awesome-computer-vision, including papers, codes, and related websites

E2M converts various file types (doc, docx, epub, html, htm, url, pdf, ppt, pptx, mp3, m4a) into Markdown. It’s easy to install, with dedicated parsers and converters, supporting custom configs. E2M offers an all-in-one, flexible, and open-source solution.

AI画板 SDui-LVGL is a drawing board program based on the LVGL graphics framework, utilizing the stable diffusion API to call a remote server for text-to-image and image-to-image generation. This was my undergraduate thesis project, which has now concluded, so I intend to open-source it.

Open source minimal Android launcher leveraging the Gemini API to reduce screen time and focus on what matters.

Self-hosted platform to manage gpt bots for Discord, Telegram and other messaging platforms. Create bots for your friends and family with different goals and unique behaviors through an easy to use interface.

Processes SafeTensors files for Stable Diffusion 1.5 (SD 1.5), Stable Diffusion XL (SDXL), and FLUX models. It extracts the UNet into a separate file and creates a new file with the remaining model components (without the UNet).

LlamaCards is a web application that provides a dynamic interface for interacting with LLM models in real-time. This app allows users to create and connect cards, each representing different functionalities such as sending prompts and receiving responses from various language models.

Optimizing inference proxy for LLMs

LivePortrait for AUTOMATIC1111 Stable Diffusion WebUI

An AI LaTeX document maker using Gemini API that simplifies the process of making documents without the steep learning curve of LaTeX.

🎉 The code repository for "Parrot: Multilingual Visual Instruction Tuning" in PyTorch.

A Personal Assistant leveraging Retrieval-Augmented Generation (RAG) and the LLaMA-3.1-8B-Instant Large Language Model (LLM). This tool is designed to revolutionize PDF document analysis tasks by combining machine learning with retrieval-based systems.

基于InternLM的面试复习助手

A Discord bot that works with Ollama.

Engineered an AI model utilizing advanced Computer Vision and Google Generative AI to solve math problems by recognizing hand gestures, offering real-time, accurate solutions through an intuitive interface inspired by Apple Tablet calculators.

Needle simplifies building RAG pipelines.

This is a LLM app, using Streamlit and connecting to the GPT-4o-mini api to create interactive quizzes, based on university lectures

Lightweight, standalone, multi-platform, and privacy focused local LLM chat interface with optional encryption

Conversational agents for engineering simulations with minimal human input using Microsoft AutoGen & GPT-4o.

Provides the same proxy OpenAI API interface for different LLM models, and supports deployment to any Edge Runtime environment.

Helpmate AI is a web app which is made using Google Gemini API. Where you can ask any question and you will get the answer

An Efficient LLM Fine-Tuning Factory Optimized for MoE PEFT

a simple tool for real-time monitoring video and summarization with LLMs

An API that can roast your linkedin profile using Gemini AI build with Express.js

提供了一种gpt大模型平替解决方案实现利用非gpt大模型去使用Graphrag，支持多类型大模型如阿里云通义千问、百度文心千帆、智谱ChatGML、讯飞星火认知、Ollama、Moonshot AI、Google Gemini等。示例代码使用阿里的通义千问大模型，其他大模型使用方式相同。

exchange is a uniform python SDK for message generation with LLMs

LongCite: Enabling LLMs to Generate Fine-grained Citations in Long-context QA

Full stack tools for building voice agents

A library for generating structured JSON using GPT-4o.

AI-api text generation

Hosting Langfuse on Amazon ECS with Fargate using CDK Python

Due to the huge vocaburary size (151,936) of Qwen models, the Embedding and LM Head weights are excessively heavy. Therefore, this project provides a Tokenizer vocabulary shearing solution for Qwen and Qwen-VL.

A demonstration of chatting with uploaded images using OpenAI vision models like gpt-4o.

Stable Diffusion WebUI Forge docker images for use in GPU cloud and local environments. Includes AI-Dock base for authentication and improved user experience.

项目是一个用于生成英文阅读文章的工具，基于用户已经学习过的词汇和句子。通过调用LLaMA 3.1模型，生成与用户学习内容相匹配的文章，帮助用户提高英语阅读理解能力。

SpeakingAI is a demo of privately deployable 'GPT-4o like AI + RAG', a fully functional web AI server with audio query/answer in streaming, using LLM and RAG for backend knowledge.

Python version of 📦 repopack (https://github.com/yamadashy/repopack) by yamadashy (https://github.com/yamadashy)

Solving conversation problem for the deaf using STT, LLMs and TTS

這是一個使用 Google Cloud Platform (GCP) Scheduler 的範例專案，主要功能是自動化地從 GitHub Issues 中提取資料並生成摘要。

大型語言模型(LLM)的讀書會內容code部分整理，此github提供簡單、免費、易實作code範例，並由淺入深帶你一步步了解如何基於python建置LLM流程、部屬功能等

一个开源的RAG框架，旨在为用户提供了一个强大、灵活且简单的开发环境。

Use Duckduckgo AI Chat to provide an OpenAI-compatible API that can be used for free with gpt-4o-mini.

GitHub Hehe: Analyzing GitHub accounts with a touch of sarcasm! Discover witty and humorous feedback on your GitHub profile.

The ultimate PyQt6 application that integrates the power of OpenAI, Google Gemini, Claude, and other open-source AI models

Repositorio creado para compartir el código y los comandos utilizados durante unas clases de ayuda que brindé a mis compañeros de la diplomatura de desarrollo web fullstack en Coderhouse.

PromptAlchemy is an open-source library designed to elevate your prompt engineering game. By applying advanced techniques like Chain-of-Thought, Few-Shot Learning, and more, we transform basic user prompts into highly effective, complex prompts.

Fluxabled Fork of the Deforum Stable Diffusion Extension for Forge with keyframe redistribution logic for Parseq

AI Storyteller/Choose your own adventure game with speech input and output, plus local and external llm support.

An elegant LogSeq AI Assistant Plugin. (Llama, OpenAI, Gemini, and Groq)

🦙 LLaMA From Scratch

Enable AI agents to communicate with humans in tool-based and asynchronous workflows. Guarantee human oversight of high-stakes function calls with approval workflows across slack, email and more. Bring your LLM and Framework of choice and start giving your AI agents safe access to the world. Agentic Workflows, human in the loop, function calling

Extend the Conditioning of Stable Diffusion to take Audio Embeddings Instead of Text Embeddings using Wav2Vec2-BERT model

Adds post-processing image effects to Stable Diffusion outputs, creating a vintage aesthetic. Grain, vignette, random blur, color offset, and customizable overlays like light leaks.

Jailbreaks for gpt 4o mini/gpt 3.5

GuardAI leverages multiple AI models, including OpenAI, Gemini, and custom self-hosted AI servers, to scan code for security vulnerabilities.

A multi modal RAG chatbot using Vertex AI SDK, Gemini, Langchain and Chainlit

Google Gemini 2.0 Clone: This project is a clone of the Google Gemini 2.0 platform, built using React JS and the Google Gemini API. The clone replicates the advanced AI-powered features and dynamic user interface of the original, providing a hands-on implementation of next-generation web technologies.

Unimpeded: Convert Poe.com to OpenAI Interface-Compatible Format! 🔑 畅通无阻: 将 Poe.com 转换为 OpenAI 接口兼容格式!

With advanced capabilities, it not only generates summaries from your study materials but also recognizes diagrams and even creates quizzes based on the PDFs you provide. It's designed to make exam prep smarter and more efficient, helping you focus on what truly matters.

HiRED strategically drops visual tokens in the image encoding stage to improve inference efficiency for High-Resolution Vision-Language Models (e.g., LLaVA-Next) under a fixed token budget.

llm 交易员

a gpt GLM-4 free chat AI built with react (10 star code to come)

Tau LLM made with Unity 6 ML Agent

This repository provides an interactive image colorization tool that leverages Stable Diffusion (SDXL) and CLIP for user-controlled color generation. With a retrained model using the ControlNet approach, users can upload images and specify colors for different objects, enhancing the colorization process through a user-friendly Gradio interface.

monkey-gpt 油猴gpt插件，量大免费用

Typesafe prompt construction for LLM inference with zod-parsed results

"Don't write any code, just tell what to do!"

Integrate ChatGLM-3-6B with Feishu App Bot to create an intelligent chatbot. Follow the steps to prepare the model and set up the Feishu application.

an AI-powered customer support chatbot using Next.js and the OpenAI API.

Just some initial learning for usage of AI models within .NET platform with Semantic Kernel APIs

Function-calling API for LLM from multiple providers

Python package for implementing Retrieval-Augmented Generation (RAG) using OpenAI's embeddings and a SQLite database with vector search capabilities

ResqAI is an AI-driven emergency companion that provides real-time weather forecasts, earthquake data, disaster analysis, and emergency response plans to help you stay prepared and informed. Stay safe with the latest news and AI-generated insights.

Collection of GenAI resources & tutorials ...

LLaMA-Factory使用经验记录

Various Tools that I create as part of my work on Stable Diffusion, ComfyUI and other GenAI

This is for the workshop to be held on Aug 10, 2024 at Bangalore Data Hack Summit 2024

Multiple Conditioned Image Generation, SDXL, Low-rank adaptation Refined

npx bulkai - BulkAI is a command line tool that allows you to bulk process text data using OpenAI's GPT-4o API.

Python sample project for building scalable document data extraction pipeline with containerized Durable Functions and Azure AI Services on Azure Container Apps.

Discover the power of LangChain. Build LLM powered application with LangChain and Google Gemini.

Unified Vision-Language Model Inference APIs

軽量VLMのMiniCPM-V2.6のColaboratoryサンプル

Generative AI Models is a comprehensive repository dedicated to the implementation of cutting-edge generative AI models using Python. It features various models, including those for image captioning and text-to-image generation, leveraging advanced architectures like Vision Transformers (ViT), GPT-2, and Stable Diffusion.