By: Festus Kahunla Hello to all our readers from Sierra Leone and beyond! Today, we'll embark on a journey to understand one of the foundational pillars of machine learning: Decision Trees. Let’s dive into this captivating topic with an analogy most of us can relate to. Setting the Scene: Decision-Making in Everyday Life Imagine you’re deciding what to wear today. You peek outside: if it's sunny, you choose a light shirt, but if it's raining, you opt for a raincoat. This type of logic, where you make decisions based on certain conditions, is the essence of Decision Trees in machine learning. What Exactly is a Decision Tree? A Sierra Leonean Tale Imagine you're at a crossroads, with two paths stretching out before you. One path is labeled “Sierra Leone” and is characterized by the familiar sights and sounds of home, filled with both its unique challenges and undeniable beauty. The other path is labeled “America”, paved with golden opportunities, yet also new ch...

By Festus Ewakaa Kahunla The world of Natural Language Processing (NLP) has been buzzing with the advent of Large Language Models (LLMs) that boast billions of parameters. These models, while incredibly powerful, come with their own set of challenges, especially when it comes to deployment and fine-tuning. A recent paper titled "PETALS: Collaborative Inference and Fine-tuning of Large Models" offers a fresh perspective on this issue. Let's dive into the key takeaways from this paper. The Challenge with LLMs Modern LLMs, such as BLOOM-176B, have more than 100 billion parameters. While these models are now available for download, using them requires high-end hardware, which many researchers might not have access to. Techniques like RAM offloading or hosted APIs offer some respite, but they come with their own limitations. For instance, offloading can be slow, and APIs might not offer the flexibility needed for specific research tasks. Introducing PETALS PETALS, a sy...

  Hello, AI enthusiasts! Today, we're diving into the fascinating world of Transformers - not the shape-shifting robots, but a revolutionary architecture in machine learning that has transformed (pun intended) natural language processing. This blog post is aimed at beginners, so don't worry if you're new to the field. We're going to break it down step-by-step! What are Transformers? Transformers are a type of model architecture used in the field of deep learning, specifically for tasks involving natural language processing (NLP). Introduced by Vaswani et al. in a paper titled "Attention is All You Need" (2017), Transformers have achieved impressive results in a wide range of NLP tasks, such as translation, text summarization, and sentiment analysis.  Why 'Transformers'? The secret sauce of Transformers lies in their unique ability to 'transform' input data (like text) into meaningful output (like a translation or summary), thanks to the...