Lightnews — Scholar-powered news

Maarten Grootendorst

@maartengr.bsky.social

200 followers 2 following 34 posts

🧑‍💻 Data Scientist | Psychologist 📖 Author of "Hands-On LLMs" (http://LLM-book.com) 🧙‍♂️ Open Sourcerer (BERTopic, PolyFuzz, KeyBERT; github.com/MaartenGr) 💡 Demystifying LLMs (newsletter.maartengrootendorst.com)

LLM-book.com)

Posts Media Videos Starter Packs

Maarten Grootendorst @maartengr.bsky.social · Apr 30

Building off the book's foundation, we created enough content to hopefully keep you busy for a while:

github.com/HandsOnLLM/H...

Hands-On-Large-Language-Models/bonus at main · HandsOnLLM/Hands-On-Large-Language-Models

Official code repo for the O'Reilly Book - "Hands-On Large Language Models" - HandsOnLLM/Hands-On-Large-Language-Models

github.com

Maarten Grootendorst @maartengr.bsky.social · Apr 30

We've made so much extra (free!) content it could be its own book 😅

I counted more than 300 visuals across our illustrated and visual guides!

1 3

Maarten Grootendorst @maartengr.bsky.social · Mar 21

www.youtube.com/watch?v=BDTV...

Intuition behind Mamba and State Space Models | Enhancing LLMs!

YouTube video by Maarten Grootendorst

www.youtube.com

Maarten Grootendorst @maartengr.bsky.social · Mar 21

Happy to introduce my video on this alternative LLM architecture, Mamba and State Space Models!

I wanted to do it for a while now and finally found the time to work on animating my visual guide. Expect to gain an intuitive understanding of this alternative LLM architecture.

Link below 👇

1 1 8

Maarten Grootendorst @maartengr.bsky.social · Mar 19

You can find the full changelog here: github.com/MaartenGr/BE...

Release v0.17.0 · MaartenGr/BERTopic

Highlights: Light-weight installation without UMAP and HDBSCAN by @MaartenGr in #2289 Add Model2Vec as an embedding backend by @MaartenGr in #2245 Add LiteLLM as a representation model by @Maarten...

github.com

Maarten Grootendorst @maartengr.bsky.social · Mar 19

Announcing BERTopic v0.17 🥳

This is a feature-packed update that includes the amazing Model2Vec, more interactive DataMapPlot functionalities, a method for lightweight installation, and much more!

1 3 7

Maarten Grootendorst @maartengr.bsky.social · Mar 17

I might have gone a little overboard with the number of visuals... but this is such an exciting topic! Here's the article: newsletter.maartengrootendorst.com/p/a-visual-g...

A Visual Guide to LLM Agents

Exploring the main components of Single- and Multi-Agents

newsletter.maartengrootendorst.com

1 2 4

Maarten Grootendorst @maartengr.bsky.social · Mar 17

Introducing "A Visual Guide to LLM Agents" 🤖

With over 60 (!) custom visuals, explore how Agents work, how they are created, their reasoning behavior, Model Context Protocol (MCP), Multi-Agent frameworks, and much more!

Link below 👇

Maarten Grootendorst @maartengr.bsky.social · Mar 14

Can you guess which visual guide is coming?

Maarten Grootendorst @maartengr.bsky.social · Mar 14

MCP is such an interesting protocol and a welcome addition to LLM-based frameworks.

Maarten Grootendorst @maartengr.bsky.social · Mar 14

I discuss Model Context Protocol (MCP) in an upcoming article and figured I would share a small video illustrating a simplified flow!

1 1

Maarten Grootendorst @maartengr.bsky.social · Feb 19

You can find the repo here: github.com/MaartenGr/Ke...

GitHub - MaartenGr/KeyBERT: Minimal keyword extraction with BERT

Minimal keyword extraction with BERT. Contribute to MaartenGr/KeyBERT development by creating an account on GitHub.

github.com

Maarten Grootendorst @maartengr.bsky.social · Feb 19

As a bonus, I created a lightweight installation of KeyBERT using ONLY scikit-learn and Model2Vec! Installation is straightforward:

Maarten Grootendorst @maartengr.bsky.social · Feb 19

Blazingly fast keyword generation with KeyBERT v0.9 and Model2Vec 🔥

I have been a big fan of the amazing embedding models by The Minish Lab, so I had to integrate them with KeyBERT.

A release for the GPU-poor 😉

1 1

Maarten Grootendorst @maartengr.bsky.social · Feb 11

You can find everything at our repo: github.com/HandsOnLLM/H...

Maarten Grootendorst @maartengr.bsky.social · Feb 11

To Reasoning LLMs and DeepSeek-R1:

Maarten Grootendorst @maartengr.bsky.social · Feb 11

There are also guides to common principles like Quantization and Mixture of Experts:

Maarten Grootendorst @maartengr.bsky.social · Feb 11

@jayalammar.bsky.social and I are incredibly proud to bring you this highly animated (and free 😉) course:

Maarten Grootendorst @maartengr.bsky.social · Feb 11

Did you know we continue to develop new content for the "Hands-On Large Language Models" book?

There's now even a free course available with
@deeplearningai.bsky.social!

1 3 11

Maarten Grootendorst @maartengr.bsky.social · Feb 3

Article: newsletter.maartengrootendorst.com/p/a-visual-g...

A Visual Guide to Reasoning LLMs

Exploring Test-Time Compute techniques and DeepSeek-R1

newsletter.maartengrootendorst.com

Maarten Grootendorst @maartengr.bsky.social · Feb 3

All the way to DeepSeek-R1-(zero):

Maarten Grootendorst @maartengr.bsky.social · Feb 3

From exploring verifiers for distilling reasoning:

Maarten Grootendorst @maartengr.bsky.social · Feb 3

A Visual Guide to Reasoning LLMs 💭

With over 40 custom visuals, explore DeepSeek-R1, the train-time compute paradigm shift, test-time compute techniques, verifiers, STaR, and much more!

Link below

1 2

Maarten Grootendorst @maartengr.bsky.social · Jan 20

To celebrate this milestone, I'm working hard on an update to the Mamba guide (with animations!) and there's also a video version almost ready to record!

Link to the newsletter:
newsletter.maartengrootendorst.com

Exploring Language Models | Maarten Grootendorst | Substack

ML Engineer writing about GenAI | Open Sourcerer (BERTopic, PolyFuzz, KeyBERT) | Author of "Hands-On Large Language Models". Click to read Exploring Language Models, by Maarten Grootendorst, a Substac...

newsletter.maartengrootendorst.com

Maarten Grootendorst @maartengr.bsky.social · Jan 20

I'm incredibly grateful that "Exploring Language Models" has reached over 10k subscribers🔥

A big thank you to all readers who have enjoyed my visual guides to Mixture of Experts (MoE), Quantization, State Space Models (SSMs) and Mamba 🤗

1 2