Unfolding the universe of possibilities..

Journeying through the galaxy of bits and bytes.

LMQL — SQL for Language Models

LMQL — SQL for Language Models Yet another tool that could help you with LLM applications Image by DALL-E 3 I’m sure you’ve heard about SQL or even have mastered it. SQL (Structured Query Language) is a declarative language widely used to work with

Pre-Training Context is All You Need

The driving force behind modern transformer models stems to a large extent from its pertaining data, allowing for strong in-context… Continue reading on Towards Data Science »

Python: __init__ is NOT a constructor: a deep dive in Python object creation

Tinkering with Python’s constructor to create fast, memory-efficient classes Continue reading on Towards Data Science »

Courage to Learn ML: Unraveling L1 & L2 Regularization (part 2)

Clear explanations of the classic but confusing L1 and L2 regularization graph. Unlocking the Intuition Behind L1 Sparsity Continue reading on Towards Data Science »

Elevate Your Business Analytics: Step-by-Step Guide To Seasonal Adjustment

We all understand the importance of breaking time series into its components for forecasting, but the same is not emphasized enough in… Continue reading on Towards Data Science »

Courage to learn ML: Demystifying L1 & L2 Regularization (part 1)

Comprehend the underlying purpose of L1 and L2 regularization Photo by Holly Mandarich on Unsplash Welcome to the ‘Courage to learn ML’, where we kick off with an exploration of L1 and L2 regularization. This series aims to simplify complex machine

Batched K-Means with Python Numba and CUDA C

How to Speed Up Your Data Analysis 1600x vs Scikit-Learn (With Code!) Image generated using Midjourney based on author’s drawing Parallelizing data analysis workloads can be a daunting task, especially when there is no efficient off-the-shelf implementation available for your specific use