Ndamulelo Nemakhavhani's repositories
notion-cms-astro-blog
A rudimentary implementation of a CMS using Notion as the backend and Astro Content Collection API
llama2
This chatbot app is built using the Llama 2 open source LLM from Meta.
my-data-science
A collection of things I commonly use or need to reference for data projects
embeddings
Published word2vec embeddings for various languages spoken across Africa
multi-tabbed-screen-demo
HTML demo screen with multiple tabs that can be closed similar to a browser
my-profile
Meet Ndamulelo Nemakhavhani, A resourceful Engineer using AI to build tools to advance humanity
shared-notebooks
This repo contains misc quickstart notebooks on a variety of topics including, NLP, Language Modelling, Fine-tuning etc.
our-stopwords
Auto-generated stopwords for South African Bantu Languages
hundzula-2024-reproducible-nlp
Code for my talk on Reproducible NLP experiments with DVC and CometML given at the Hundzula Retreat 2024
cookbook
Chainlit's cookbook repo
azure-dp600-fabrics-analytics-engineer-study-guide
Azure DP600 (Fabric Analytics Engineer Associate) Exam topics and tips
Flowise
Drag & drop UI to build your customized LLM flow
rota-app
Demo app to generate fair rosters for small teams using Vanilla JS and a serverless Python Backend
cloud-gpu-handbook
A guide to help users quickly navigate and compare GPU offerings across major cloud platforms
astro-ghostcms-dot-xyz
Main website for Astro-GhostCMS
dp203-study-guide
A curated list of crucial topics to grasp in preparation for Azure DP-203 certification exam
ndamulelonemakh
Config files for my GitHub profile.
amazon-ion-to-json-cli
Python scripts for converting ion data to JSON format(and vice-versa)
scrapy-redis
Redis-based components for Scrapy.
cookiecutter-data-science
A logical, reasonably standardized, but flexible project structure for doing and sharing data science work.
optimization-algorithms
Implementation of optimization algorithms in python
nodejs.org
The Node.js website.
pyidw
A standalone python library for inverse distance weighted (idw) interpolation
afriberta
AfriBERTa: Exploring the Viability of Pretrained Multilingual Language Models for Low-resourced Languages
label-studio
Label Studio is a multi-type data labeling and annotation tool with standardized output format
datahub
The Metadata Platform for the Modern Data Stack
pyfranc
Text language detection basic on trigrams.
data-science-on-gcp
Source code accompanying book: Data Science on the Google Cloud Platform, Valliappa Lakshmanan, O'Reilly 2017