Supervision Exists Everywhere: A Data Efficient Contrastive Language-Image Pre-training Paradigm

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

This repository contains the code for SFT, RLHF, and DPO, designed for vision-based LLMs, including the LLaVA models and the LLaMA-3.2-vision models.

Multi-model transactional embedded database

QiDiHui: RAG, appbuilder, ErnieBot, multi-model, 十万个为什么

🌟This is the official code for our paper TCDiff++ 💃💃💃

Toward Multi Modality Language Model - implementation of GPT-4o/Project Astra

Fully agentic LLM orchestrator with autonomous decision-making. This agentic system self-discovers models, learns from usage, and adapts routing strategies. Save 67% on API costs through intelligent agentic behavior. Production-ready with monitoring and self-healing.

In this project, we will perform 12-lead ECG Multi-label Classification. Specifically, we will design a multi-model utilizing the characteristics of diagnoses from the Shaoxing and Ningbo databases.

A powerful, multi-modal Telegram bot leveraging cutting-edge AI technologies including Gemini, DeepSeek, OpenRouter, and 50+ AI models for comprehensive conversational assistance, media processing, and collaborative features with MCP (Model Context Protocol) integration.

AI development assistant with persistent memory. Solves the problem of AI tools forgetting context across sessions.

Open WebUI Logic Tree Multi-Model LLM Project - Advanced AI reasoning with Sakana AI's AB-MCTS and sophisticated multi-model collaboration

This repository contains my research internship code at the University of Illinois Chicago under the supervision of Prof. Pedram Rooshenas.

This repository contains the code to obtain the optimal solution of the multi-model line balancing problem

Multi-scale and non-invasive multi-model coupling combining Iso-Geometric and Finite Element Analysis

A simple graph data manager, in other words: on the fly schemaless multi-model data client with timeseries wannabes

pRISM is a repository that combines Retrieval-Augmented Generation (RAG) with a multi-LLM voting approach to create accurate and reliable AI-generated outputs. It integrates multiple language models, including Mistral, Claude 3.5, and OpenAI, to enhance performance through advanced consensus techniques

This tool processes images and generates textual descriptions using advanced machine learning models

Using LSTMs to automatically grade essays.

🔍 Jarvis is a personal AI assistant that brings together conversation, automation, and creativity in one place. It can chat intelligently, search the web in real-time, generate images, control your system, and respond to voice commands - all through natural language interaction.