Mudasar Qadir

GPT

Collection of experiments and utilities for building, training, and serving GPT-style language models, including configuration, data pipelines, and deployment-ready code.

Voice-bot

End-to-end voice assistant backend combining speech interfaces with LLM-based reasoning to handle natural, conversational interactions over audio.

Deepagents

Deepagents is a simple, open source agent harness that implements a few generally useful tools, including planning (prior to task execution), computer access (giving the able access to a shell and a filesystem), and sub-agent delegation (isolated task execution)

LLM Deployments

Practical setups and infrastructure templates for deploying LLMs in production using containerized runtimes, GPU-optimized stacks, and serving frameworks.

Comprehensive RAG GUIDE

Detailed GUIDE and Walk through code for RAG

LLM Chat assistant

LLM Chat assiatant which also keep track of your chat history until browser session is alive Server is deployed with FastAPI and ngnix

LLM2 Model Fine Tunning

LLM2 Model was transefered learned and fine tunned for general conversations

Breast Cancer Predicting

Inasive ductal carcinoma (IDC) is - with ~ 80 % of cases - one of the most common types of breast cancer. It's malicious and able to form metastases which makes it especially dangerous.

For training, First is transferd learnt using imagenet weights, and later finetuned. System can predict healthy or cancerious tissues above 90%.

Facial Expressions predictor

Design, data modeling and implementation of deep learning algorithm to predict different expressions of human given an image

A Featured Area-Based Image Registration

Image registration is necessary when images from multiple viewpoints need be brought into common coordinate system. Image registration techniques can be classified as area-based methods and feature-based methods. s. In this paper, we propose a mixture of two methods termed as featured area-based method.