Yohanes Teshome Kebede's Projects
Optimizing driver placement for Gokada, Nigeriaβs largest last-mile delivery service, to increase order fulfillment and improve client satisfaction. Analyzes delivery data to identify issues and recommend optimal driver locations.
The objective is to build, evaluate, and improve a Retrieval-Augmented Generation (RAG) system for Contract Q&A, simulating interaction with a contract by asking questions and getting precise answers.
The aim of this project is to develop a model capable of detecting fabric defection.
The dataset includes tweets in English containing the hashtag #WorldCup2022.
This dataset contains house sale prices for King County, which includes Seattle. It includes homes sold between May 2014 and May 2015.
The Unified Machine Learning Framework
Fine-tuning language models for Amharic news classification into categories such as Local News, Entertainment, Sports, Business, International News, and Politics.
A project for scraping and preprocessing data to enhance large language models (LLMs). Provides a scalable and flexible foundation for developing APIs focused on fine-tuning LLMs.
Precision RAG is a project focused on building enterprise-grade Retrieval-Augmented Generation (RAG) systems with a strong emphasis on prompt tuning. This repository provides tools and scripts to facilitate data generation, prompt tuning, evaluation, and deployment of RAG systems.
This project aims to design and build a reliable, large-scale trading data pipeline for a startup called Mela, which wants to make it simple for everyone to enter the world of cryptocurrencies. The pipeline will enable investors to run backtests that simulate current and past particular situations as well as their trend over time.
Leveraging the power of EfficientNetB0, I built a binary classification system capable of identifying individuals wearing masks in images. This project, developed in Python and Keras, contributes to public health and safety initiatives by providing a readily deployable solution for mask detection in real-world settings.
Config files for my GitHub profile.