Skip to content

Newsletter

In my Exploring Language Models newsletter you can find posts and visual guides on topics related to Large Language Models. If you want to stay updated, you can subscribe here:


Below, you can find an overview of all posts I have created on various platforms. I initally started on Medium and slowly transitioned to Substack as my main source of content. These posts will keep you on this website as a handy alternative to the previous sources mentioned.

Visual Guides to LLMs

These are the guides I'm most proud over, each containing more than 50 custom-made visuals describing the internals and specifics of Large Language Models (LLMs) without any of the (often difficult to interpret) mathematics. Expect an intuitive experience!

Post Image
A Visual Guide to Mixture of Experts (MoE)
October 07, 2024
Demystifying the role of MoE in Large Language Models
Post Image
A Visual Guide to Quantization
July 22, 2024
Demystifying the Compression of Large Language Models
Post Image
A Visual Guide to Mamba and State Space Models
Februari 21, 2024
An Alternative to Transformers for Language Modeling

Tutorials / Blogs

The rest of the posts are those I make on how to implement certain techniques, such as topic modeling, keyword extraction and LLM-based techniques. You can also expect many posts on my experience transitioning from psychology to data science.

Post Image
BERTopic: What Is So Special About v0.16?
December 19, 2023
Exploring Zero-Shot Topic Modeling, Model Merging, and LLMs
Post Image
Which Quantization Method is Right for You? (GPTQ vs. GGUF vs. AWQ)
November 12, 2023
Exploring Pre-Quantized Large Language Models
Post Image
Introducing KeyLLM  -  Keyword Extraction with LLMs
October 03, 2023
Use KeyLLM, KeyBERT, and Mistral 7B to extract keywords
Post Image
3 Ways To Improve Your Large Language Model
September 11, 2023
Enhancing the power of Llama 2
Post Image
Topic Modeling with Llama 2
August 22, 2023
Create easily interpretable topics with BERTopic and Llama 2
Post Image
Decoding Auto-GPT
August 08, 2023
The Mechanics of an Autonomous GPT-4
Post Image
GPT Psychology
July 01, 2023
Analogies with Human Thinking and Reasoning
Post Image
Using Whisper and BERTopic to model Kurzgesagt’s videos
November 21, 2022
Which topics can we find in the videos of Kurzgesagt?
Post Image
6 Lessons I learned from developing Open-Source Projects
November 07, 2022
A Data Scientist’s Perspective
Post Image
The Ambiguity of the Data Science Profession
April 25, 2022
Finding your way among the noise
Post Image
Topic Modeling on Images? Why not?!
November 01, 2021
But let's call it Concept Modeling instead!
Post Image
Creating a Data Science Portfolio
October 06, 2021
Tips and examples for building up your portfolio
Post Image
Misleading Graphs
March 23, 2021
…and how to fix them!
Post Image
Why Jupyter Notebooks aren't all that Bad!
June 14, 2021
And how you can supercharge them.
Post Image
The Truth about working as a Data Scientist
May 04, 2021
Pros and Cons of working as a Data Scientist
Post Image
9 Distance Measures in Data Science
February 01, 2021
The advantages and pitfalls of common distance measures.
Post Image
Interactive Topic Modeling with BERTopic
January 10, 2021
An in-depth guide to topic modeling with BERTopic.
Post Image
String Matching with BERT, TF-IDF, and more!
November 30, 2020
Introducing PolyFuzz, a framework for fuzzy string matching.
Post Image
Keyword Extraction with BERT
October 28, 2020
A minimal method for extracting keywords and keyphrases.
Post Image
Creating a class-based TF-IDF with Scikit-Learn
October 06, 2020
Extracting informative words per class.
Post Image
Topic Modeling with BERT
October 05, 2020
Leveraging BERT and TF-IDF to create easily interpretable topics.
Post Image
Why Psychologists can be great Data Scientists
September 18, 2020
The Intersection of Psychology and Data Science
Post Image
Monitoring your Machine Learning Model
August 21, 2020
What to look out for when deploying your ML model
Post Image
Transform your ML-model to Pytorch with Hummingbird
June 22, 2020
Accelerate your Machine Learning model by leveraging Tensors
Post Image
Unit Testing for Data Scientists
May 18, 2020
Using Pytest to improve the stability of your pipelines
Post Image
Tips for transitioning from Psychology to Data Science
March 30, 2020
And how you can do both.
Post Image
How to Detect Bias in AI
January 31, 2020
Detecting common (cognitive) biases in your data
Post Image
Reinforcement Learning in a few lines of code
January 7, 2020
Train SOTA RL-algorithms using Stable Baselines and Gym
Post Image
Stacking made easy with Sklearn
December 10, 2019
Create a StackingClassifier in a few lines of code with Scikit-Learn V0.22.
Post Image
Build and Deploy a Dashboard with Streamlit
November 11, 2019
Deploying your Streamlit application to Heroku to showcase your Data Solution
Post Image
Validating your Machine Learning Model
September 26, 2019
Going beyond k-Fold Cross-Validation
Post Image
How to Deploy a Machine Learning Model
August 30, 2019
Creating a production-ready API using FastAPI + Uvicorn
Post Image
Tips for Advanced Feature Engineering
April 12, 2019
Improving an important step in ML.
Post Image
Create, Visualize and Interpret Customer Segments
July 30, 2019
In-depth exploration of cluster analysis.
Post Image
How to leverage Explainable Machine Learning
July 11, 2019
Using PDP, LIME, and SHAP to create interpretable decisions that create value for your stakeholders
Post Image
How to use NLP to Analyze WhatsApp Messages
June 27, 2019
Using NLP to analyze WhatsApp messages between my wife and I