Odun's Projects
AfriBERTa: Exploring the Viability of Pretrained Multilingual Language Models for Low-resourced Languages
Anserini is a Lucene toolkit for reproducible information retrieval research
Minimalist ML framework for Rust
A model archiving package for loading and inference candle models similar to torch-serve
Tutorial for Porting PyTorch Transformer Models to Candle (Rust)
Python Implementation of Wolframs Cellular Automata (1D) & Conways Game of life
Beyond Accuracy: Behavioral Testing of NLP models with CheckList
A list of Developer Community Writer Programs
A multi-stage neural search engine for the COVID-19 Open Research Dataset
TFDS is a collection of datasets ready to use with TensorFlow, Jax, ...
Projects and exercises for the latest Deep Learning ND program https://www.udacity.com/course/deep-learning-nanodegree--nd101
Ready-to-run Docker images containing Jupyter applications
Dense Passage Retriever - is a set of tools and models for open domain Q&A task.
Tutorial Deploying a Flask App to Heroku
Putting together a list of mid level projects in Go
An easy way to improve tesseract OCR using a docker container and tesseract makefile.
Java for Rust
Building a logistic regression from scratch
Getting started in NLP for low resource languages
This work is an adaptation of CNN+Transformer architecture to training text recognition models for Yorùbá & Igbo Languages
Examples in the MLX framework
MLX Transformers is a library that provides model implementation in MLX. It uses a similar model interface as HuggingFace Transformers and provides a way to load and run models in Apple Silicon devices.
Mr. TyDi is a multi-lingual benchmark dataset built on TyDi, covering eleven typologically diverse languages.
Training Notebooks
React
Typescript
Django
Laravel
Facebook
Microsoft
Google
Alibaba
D3
Tencent