About This Project
This is a comprehensive, production-ready framework for fine-tuning Large Language Models using various Parameter-Efficient Fine-Tuning (PEFT) techniques.

Key Features
📦 Modular Architecture: Easy to extend and customize
🔧 7 PEFT Techniques: LoRA, QLoRA, Prefix Tuning, and more
📊 Built-in Monitoring: Track training metrics and performance
🎨 Flexible Configuration: YAML-based config system
🧪 Testing Suite: Comprehensive unit tests
📚 Rich Documentation: Detailed guides and examples

A powerful AI-powered car detection system built with YOLOv11 and Streamlit. Upload images or videos to detect and track cars with real-time object tracking capabilities.
Features
AI-Powered Detection: Uses a fine-tuned YOLOv11s model for car detection
Real-time Tracking: Advanced object tracking with unique ID assignment
Video Processing: Process videos with frame-by-frame detection and tracking
Modern UI: Beautiful, responsive interface with dark/light mode support
Docker Support: Easy deployment with Docker
Performance Optimized: GPU acceleration with automatic CPU fallback
Mobile Responsive: Works on desktop, tablet, and mobile devices

This project is a deep learning-based web application for identifying plant leaf diseases using PyTorch as the backend framework and Streamlit as the frontend UI. It helps farmers, agronomists, and researchers detect crop diseases quickly and take early action.

Streamlit app that combines LLaVA for image understanding, Whisper for speech-to-text, and gTTS for text-to-speech. Upload an image, speak a question, and get a spoken AI response.

An intelligent bug hunting system for Machine Learning projects powered by CrewAI and Local LLM (Ollama). This system uses multiple specialized AI agents to analyze, debug, and optimize your ML code.