Starred repositories
Building a Sudanese Arabic dataset and fine-tuning LLMs to improve representation of this dialect.
Tools for merging pretrained large language models.
A collection of LogitsProcessors to customize and enhance LLM behavior for specific tasks.
Code release for CVPR'24 submission 'OmniGlue'
Identifing disease types in images of rice grown in Egypt.
Python functions to calculate the FFT and autocorrelation function using GPU (Cuda)
(Old) Here are my projects related to Data Analysis and Machine Learning.
#Umoja Hacks. This repo contains team solo's best solutions for the umoja hackathon 2022 hosted on Zindi, it is the combined effort of Fajamila Oluwadunsin, Okewunmi Paul and Olufemi Victor.
Data, Benchmarks, and methods submitted to the M5 forecasting competition