ORPO: Preference Optimization without the Supervised Fine-tuning (SFT) Step

There are now many methods to align large language models (LLMs) with human preferences. Reinforcement learning with human feedback (RLHF) was one of the first and brought us ChatGPT, but RLHF is…

Statistics for Data Science 101 Series — An Overview

Following the Data Analytics 101 Series, the Statistics 101 Series will delve into a burst of articles that explain the usage and importance of statistics in Data Science. I will try my best to…

Google’s CodeGemma: I am not Impressed

CodeGEMMA represents a significant advancement in the realm of code generation and completion, stemming from Google’s broader Gemma model family. As a fine-tuned version of the Gemma-7b model…

The Controversy of AI Greeting Cards

Today I am taking a slight detour from my usual data analysis, to indulge one of my favorite hobbies — crafting personalized greeting cards, now with a significant boost from Artificial Intelligence…

Mixture of Experts

What you know about Mixture of Experts is wrong. We are not using this technique because each model is an expert on a specific topic. In fact, each of these so-called experts is not an individual…

ML Engineering is Not What You Think — ML Jobs Explained

There are so many different data- and machine-learning-related jobs. But what actually are the differences between a Data Engineer, Data Scientist, ML Engineer, Research Engineer, Research Scientist…

RAG 2.0, Finally Getting RAG Right!

Contextual has presented RAG 2.0, which surpasses RAG's capabilities all around. How does it work, and why could it become the golden standard for enterprises?

Deploy MLflow Server on Amazon EC2 Instance

Hi folks! Ready to take your model deployment game to the next level? Let’s dive into setting up an MLflow Server on an EC2 instance! I’ll explain the steps to configure Amazon S3 bucket to store the…

Are LLMs Only Good for Chat-Based Solutions? Exploring Beyond Language Tasks

Over the past two years, Large Language Models (LLMs) including ChatGPT, Antropic, and Mistral have transformed our engagement with technology. These models have become central across a range of…

Scaling AI Models Like You Mean It

If you’re reading this article, you probably need no introduction to the advantages of deploying open-source models. Over the past couple of years, we have seen incredible growth in the both the…