Alessio Devoto

In this short tutorial, we will use our company’s dataset to predict whether a customer will churn or not.

Lately, diffusion-based language models like LLaDA and MMaDA have been gaining traction.

Disclaimer: unlike other posts in this blog that actually served some purpose, this is just a random idea I had and am implementing for fun.

In this short tutorial, we’ll implement LogitLens to inspect the inner representations of a pre-trained Phi-1.5.

I decided to do this for two reasons.

Goal: Visualizing the attention maps for the CLS token in a pretrained Vision Transformer from the timm library.

As neural networks grow larger (see LLMs, though now it looks like we also have a trend towards smaller models with Gemma2-2b ) and datasets become more massive, parallelism techniques are crucial for efficient training.

In the world of machine learning, efficiency is a buzzword we hear all the time.

It is becoming more and more common to use FLOPs (floating point operations) to measure the computational cost of deep learning models.

This brief post summarizes a project I have been working on over the past months.