A cutting-edge voice assistant combining real-time speech recognition, AI reasoning, and neural text-to-speech capabilities.

Official PyTorch implementation of the paper "Chapter-Llama: Efficient Chaptering in Hour-Long Videos with LLMs"

Fork of lm/navigation-stack-backport

Using Regex,Bert,Linear_regressin,Llama

A conversational AI agent built with Python, Streamlit, and LangChain, featuring multi-LLM support (Gemini, Llama 3), persistent chat history via PostgreSQL, agent tools (Web Search, Python REPL), and image generation using Google Cloud's Imagen model.

Analysis of Text data from Twitter that surfaced during the launch of DeepSeek R1 in January 2025. Spoiler Alert! Tweets with negative sentiment got more engagement

An interative chatbot for overall creativity and productivity, based on DeepSeek R1 API.

This repository focuses on the fine-tunning of the Code-Assistant LM, that uses Phi-2 as it's base. Uses LoRA to learn coding leetcode questions.

An AI-driven tool that converts voice input into professional emails using Whisper for speech-to-text and LLaMA-3 for email refinement. Includes automated formatting and SMTP integration for direct email sending.

Simple chat bot based on deepseek r1

This project is a Retrieval-Augmented Generation (RAG) chatbot built with Streamlit, using the DeepSeek R1 Distill LLaMA 70B model via Groq API. It allows users to upload documents (PDF, TXT, DOC, DOCX), extract text, and ask questions based on the document content.

Compiling a llamaindex tutorials, snippets, RAG

Practical guide to fine-tuning the LLaMA model for dialogue summarisation using LoRA for efficient, low-resource training.

ChatGPT 中文版：国内直连指南（支持 GPT-4、GPT-4o、o1、o3、DeepSeek R1，Grok-3 无需翻墙）

A chatbot that integrates LM Studio's sdk with Discord's API to allow an AI agent to have conversations on Discord.

This is learning management system , think it like google classroom

LM Studio Example Form App is a C# Windows Forms application for integrating with locally-run AI models through LM Studio's API. This codebase demonstrates both streaming and non-streaming text generation with error handling, event-based notifications, and proper resource management.

Self-assessment exercises

Academy Learning Management System

LMM TV

Config files for my GitHub profile.

Library management system

Support multimedia files for the paper "On the variance of the LMS algorithm squared-error sample curve"

Basics about XML, XSLT, XPATH and XSD

pixy

Know Your PDF is a Retrieval-Augmented Generation (RAG) based application that allows users to interact with any PDF using natural language queries. Upload your PDF and ask questions—the app returns accurate, context-aware answers using LLaMA 3B and LangChain.

本库包含了已做好LIMR适配的LLaMA-Factory库，并在README.MD中详述了 LIMR 工作流及适配所做修改的详细报告

An interactive system combining ML churn prediction (XGBoost), XAI explanations (SHAP), and LLM-powered agents (Llama 3 via LangGraph) to provide personalized customer intervention strategies. Includes MLOps pipeline considerations using GCP and API deployment.

INVOICES text extraction using LLAMA model

using Bert ML model and llama to track anormalous credit card transactions using unsupervised ML

Running llama3.2 using Ollama

Hybrid Log Classification System using Deepseek R1 LLM, Regex and BERT.

Experience edge AI with free access to the DeepSeek R1 model.

finishing code for tictactoe homework

for LMS

A backend project in which i used nodejs, ejs, mongoDB and css.

Selective Inference for Linear Regression

Learning Management System backend using node.js, exrpess and integrated payment gateway

AI Search Engine Chatbot Integrated SerpApi for real-time data retrieval and search functionality, Leveraged yfinance library to present the latest financial data from Yahoo Finance, utilitized and integrated Llama 3 8B using Ollama ,Designed an intuitive UI with Streamlit to provide a seamless user experience.

SmartShelf is an AI-powered app that simplifies data analytics using natural language processing, SQL query generation, and machine learning. It converts user queries into SQL commands with Llama 3.2, retrieves data from MS SQL Server, and presents results in natural language or charts. It also forecasts sales trends with the Prophet model.

A comparative evaluation of LLama 7B, Mistral 7B, and GPT-3.5 on sentiment analysis and question-answering tasks, featuring fine-tuning, embeddings, and few-shot prompting. Developed as part of an MSc Data Science dissertation at City, University of London.