Techno Blender
Digitally Yours.
Browsing Tag

Ganegedara

Can ChatGPT recommend movies with machine learning | by Thushan Ganegedara | Apr, 2023

Fun journey to test ChatGPT’s limits in the context of recommendationPhoto by Tech Daily on UnsplashRecently I spent some time with our beloved AI overlord ChatGPT (just kidding!) probing the model and pushing its limits. I tested it on a usecase of movie recommendation. You can find the video walkthrough here.Monolithic LLMs powered by billions of parameters, fine-tuned with RLHF has forever changed how we perceive AGI. Rise of ChatGPT, GPT-3.5 and GPT-4 have exemplified how much the horizons of the abilities and skills…

Running a Stable Diffusion Cluster on GCP with tensorflow-serving (Part 2) | by Thushan Ganegedara | Mar, 2023

Creating the artifacts and deploying the model on the clusterIn part 1, we learned how to use terraform to set up and manage our infrastructure conveniently. In this part, we will continue on our journey to deploy a running Stable Diffusion model on the provisioned cluster.Note: You can follow this tutorial end-to-end even if you’re a free user (as long as you have some of free tier credits left).All images, unless otherwise noted, are by the authorGithub: https://github.com/thushv89/tf-serving-gkeLet’s take a look at…

Running a Stable Diffusion Cluster on GCP with tensorflow-serving (Part 1) | by Thushan Ganegedara | Mar, 2023

Part 1: Setting up the infrastructure using TerraformPhoto by Kier in Sight on UnsplashIn the first part of this two-part tutorial, we will learn to create a Kubernetes cluster that deploys a Stable Diffusion model on GCP. Stable Diffusion (a form of generative AI) is the new cool kid on the block. Stable Diffusion allows us to generate realistic images from a given text prompt. Due to the novelty and computational load posed by the Stable Diffusion model, it provides invaluable opportunities to address some unique…

Light on Math ML: Intuitive Guide to Matrix Factorization (Part 1) | by Thushan Ganegedara | Jul, 2022

You’ll never be afraid to see an allegedly intimidating matrix factorization equation in your life!I’m going to make matrix factorization as sweet as this snicker bar (Image by WikimediaImages from Pixabay)Matrix factorization code: In this article, you will learn about matrix factorization, bread and butter of many classical machine learning approaches. This article will focus explaining the real-world applications of matrix factorization (MF) (with code examples) and the intuition underpinning it. Have you ever thought…

Five MLOps tips to enhance your ML workflows | by Thushan Ganegedara | Jun, 2022

Image by Dominik Karch from PixabayMachine learning maturity and fluency in organizations have reached impressive levels and are constantly on the rise. Some time ago, maintaining an ML decision support system may have been considered as a perilous journey full of twists and turns, that you embark on every few months or so. Nowadays, it has become almost impregnated in the agile software development cycle of most organizations.This means, as an MLE you can no longer neglect the rest of the organization and use the d-word;…

Learn the talk of data — An MLEs journey to the dark depths of data | by Thushan Ganegedara | Jun, 2022

Image by ElasticComputeFarm from PixabayLet’s face it, if there’s anything data scientists (DSs) or machine learning engineers (MLEs) would shy-away from it’ll be data that’s not yet a Numpy array or a pandas DataFrame. Without insinuating at the fear of databases in data scientists, let’s try to understand some of these concepts.Companies that serve millions of customers collect copious amounts of structured and unstructured data every second of the day. To serve these customers with millisecond latency while enabling…