A Framework of Small-scale Large Multimodal Models

Chat with AI large language models running natively in your browser. Enjoy private, server-free, seamless AI conversations.

A CLI to manage install and configure llama inference implemenation in multiple languages

A set of bash scripts to automate deployment of GGML/GGUF models [default: RWKV] with the use of KoboldCpp on Android - Termux

OpenVINO LLM Node.js C++ addon

Most simple and minimal code to run an LLM chatbot from HuggingFace hub with OpenVINO

This application allows users to upload PDF files, process them, and ask questions about the content using a locally hosted language model. The system uses Retrieval-Augmented Generation (RAG) to provide accurate answers based on the uploaded PDFs.

The LLM FineTuning and Evaluation project 🚀 enhances FLAN-T5 models for tasks like summarizing Spanish news articles 🇪🇸📰. It features detailed notebooks 📚 on fine-tuning and evaluating models to optimize performance for specific applications. 🔍✨

News QA generation and fine tuning an LLM for QA generation (under development)

Repository for course project for the Applied ML course

Fine-tuning the Tiny Llama model to mimic my professor's writing style using the Llama Factory. The project involves data collection, preprocessing, preparation, fine-tuning, and evaluation.

"A Java-based app that uses retrieval-augmented generation for smarter, context-aware AI."

The project was undertaken as part of the Intel Unnati Industrial Training program for the year 2024. The primary objective of this project aligns with Problem Statement PS-04: Introduction to GenAI LLM Inference on CPUs and subsequent LLM Model Finetuning for the development of a Custom Chatbot.

Basic LLM wrapper with 3 consumers: CLI, Flask, and load/scaling test. Works with HuggingFace models like Llama and TinyLlama (and others).

Smart home system to control smart devices using natural language commands. Using the planning and processing capabilites of LLMs

An AI-powered product uses RAG to automate network diagram design and optimize virtual machine allocation and setup according to user requirements.

DigiHR is an AI-powered chatbot for students at Karunya Institute of Technology and Sciences, designed to enhance HR interview preparation. It analyzes resumes to identify specializations and generates tailored HR questions, including tricky project-related inquiries, helping students build confidence for internships and job placements.

ChatLlama🦙 is an AI chat bot inspired by ChatGPT running LLMs locally on an Ollama Server via Docker

Computer Engineering/Science 542: Neural Networks - Project