Just A Reader

Sign in Subscribe

Data Science and Machine Learning

From RNNs to LLMs, a comprehensive overview of how training regimes changed.

From Training Language Models to Training DeepSeek-R1

Reasoning Models #1 - An overview of training You probably already understand the potential of reasoning models. Playing around with O1 or DeepSeek-R1 shows us these models' enormous promise. As enthusiasts, we are all curious to build something like these models. We all start on this path, too. However,

7 Practical PyTorch Tips for Smoother Development and Better Performance

Things I wish someone listed down. PyTorch is a surprisingly simple language that allows you to train a model after reading a simple 2-minute article. But as we keep writing more, many things could give a qualitative improvement in the long run. In the last two years, there have been

Aren’t these “new” AI features impractical? — A data scientist’s rant.

Aren’t these “new” AI features impractical? — A data scientist’s rant.

When Technology’s Hype Outpaces Its Practicality.

Transformer Architecture. Source: “Attention is all you need.”

Building Blocks of Transformers: Attention

The Borrower, the Lender, and the Transformer: A Simple Look at Attention

Simplifying Decorators in Python | A step-by-step approach.

Simplifying Decorators in Python | A step-by-step approach.

Python is one of the simpler languages that we can learn these days. However, despite being the simplest one, it still has a few areas that…

Making Sense of PyTorch’s to(device) and map_location.

Making Sense of PyTorch’s to(device) and map_location.

Why are there two different approaches to do the same thing? When is one approach better than the other?

Regular Expressions — Searching in the ocean of text. Image generated by the Author using Midjourney.

NLP -01: Demystifying Regular Expressions | RegEx guide for beginners.

One of the most underrated skills any data professional should have when working with strings