Maarten GrootendorstVisual guides and articles about language models, AI, and data science.https://www.maartengrootendorst.com/enA Visual Guide to Mixture of Experts (MoE)https://www.maartengrootendorst.com/blog/moe/https://www.maartengrootendorst.com/blog/moe/Demystifying the role of MoE in Large Language ModelsMon, 07 Oct 2024 00:00:00 GMTA Visual Guide to Quantizationhttps://www.maartengrootendorst.com/blog/quantization/https://www.maartengrootendorst.com/blog/quantization/Demystifying the Compression of Large Language ModelsMon, 22 Jul 2024 00:00:00 GMTA Visual Guide to Mamba and State Space Modelshttps://www.maartengrootendorst.com/blog/mamba/https://www.maartengrootendorst.com/blog/mamba/An illustrated explanation of Mamba and the state space models behind it.Wed, 21 Feb 2024 00:00:00 GMTlanguage-modelsarchitecturesmambaBERTopic: What Is So Special About v0.16?https://www.maartengrootendorst.com/blog/bertopic/https://www.maartengrootendorst.com/blog/bertopic/Exploring Zero-Shot Topic Modeling, Model Merging, and LLMsTue, 19 Dec 2023 00:00:00 GMTWhich Quantization Method is Right for You? (GPTQ vs. GGUF vs. AWQ)https://www.maartengrootendorst.com/blog/gguf/https://www.maartengrootendorst.com/blog/gguf/Exploring Pre-Quantized Large Language ModelsSun, 12 Nov 2023 00:00:00 GMTIntroducing KeyLLM  -  Keyword Extraction with LLMshttps://www.maartengrootendorst.com/blog/keyllm/https://www.maartengrootendorst.com/blog/keyllm/Use KeyLLM, KeyBERT, and Mistral 7B to extract keywordsTue, 03 Oct 2023 00:00:00 GMT3 Ways To Improve Your Large Language Modelhttps://www.maartengrootendorst.com/blog/improving-llms/https://www.maartengrootendorst.com/blog/improving-llms/Enhancing the power of Llama 2Mon, 11 Sep 2023 00:00:00 GMTTopic Modeling with Llama 2https://www.maartengrootendorst.com/blog/llama2-topic/https://www.maartengrootendorst.com/blog/llama2-topic/Create easily interpretable topics with BERTopic and Llama 2Tue, 22 Aug 2023 00:00:00 GMTDecoding Auto-GPThttps://www.maartengrootendorst.com/blog/autogpt/https://www.maartengrootendorst.com/blog/autogpt/The Mechanics of an Autonomous GPT-4Tue, 08 Aug 2023 00:00:00 GMTGPT Psychologyhttps://www.maartengrootendorst.com/blog/gpt-psychology/https://www.maartengrootendorst.com/blog/gpt-psychology/Analogies with Human Thinking and ReasoningSat, 01 Jul 2023 00:00:00 GMTUsing Whisper and BERTopic to model Kurzgesagt's videoshttps://www.maartengrootendorst.com/blog/whisper/https://www.maartengrootendorst.com/blog/whisper/Which topics can we find in the videos of Kurzgesagt?Mon, 21 Nov 2022 00:00:00 GMT6 Lessons I learned from developing Open-Source Projectshttps://www.maartengrootendorst.com/blog/opensource/https://www.maartengrootendorst.com/blog/opensource/A Data Scientist’s PerspectiveMon, 07 Nov 2022 00:00:00 GMTThe Ambiguity of the Data Science Professionhttps://www.maartengrootendorst.com/blog/ambiguous/https://www.maartengrootendorst.com/blog/ambiguous/Finding your way among the noiseMon, 25 Apr 2022 00:00:00 GMTTopic Modeling on Images? Why not?!https://www.maartengrootendorst.com/blog/concept/https://www.maartengrootendorst.com/blog/concept/But let's call it Concept Modeling instead!Mon, 01 Nov 2021 00:00:00 GMTCreating a Data Science Portfoliohttps://www.maartengrootendorst.com/blog/portfolio/https://www.maartengrootendorst.com/blog/portfolio/Tips and examples for building up your portfolioWed, 06 Oct 2021 00:00:00 GMTWhy Jupyter Notebooks aren't all that Bad!https://www.maartengrootendorst.com/blog/jupyter/https://www.maartengrootendorst.com/blog/jupyter/And how you can supercharge them.Mon, 14 Jun 2021 00:00:00 GMTThe Truth about working as a Data Scientisthttps://www.maartengrootendorst.com/blog/truths/https://www.maartengrootendorst.com/blog/truths/Pros and Cons of working as a Data ScientistTue, 04 May 2021 00:00:00 GMTMisleading Graphs... and how to fix them!https://www.maartengrootendorst.com/blog/misleading/https://www.maartengrootendorst.com/blog/misleading/…and how to fix them!Tue, 23 Mar 2021 00:00:00 GMT9 Distance Measures in Data Sciencehttps://www.maartengrootendorst.com/blog/distances/https://www.maartengrootendorst.com/blog/distances/The advantages and pitfalls of common distance measures.Mon, 01 Feb 2021 00:00:00 GMTInteractive Topic Modeling with BERTopichttps://www.maartengrootendorst.com/blog/bertopictutorial/https://www.maartengrootendorst.com/blog/bertopictutorial/An in-depth guide to topic modeling with BERTopic.Sun, 10 Jan 2021 00:00:00 GMTString Matching with BERT, TF-IDF, and more!https://www.maartengrootendorst.com/blog/polyfuzz/https://www.maartengrootendorst.com/blog/polyfuzz/Introducing PolyFuzz, a framework for fuzzy string matching.Mon, 30 Nov 2020 00:00:00 GMTKeyword Extraction with BERThttps://www.maartengrootendorst.com/blog/keybert/https://www.maartengrootendorst.com/blog/keybert/A minimal method for extracting keywords and keyphrases.Wed, 28 Oct 2020 00:00:00 GMTCreating a class-based TF-IDF with Scikit-Learnhttps://www.maartengrootendorst.com/blog/ctfidf/https://www.maartengrootendorst.com/blog/ctfidf/Extracting informative words per class.Tue, 06 Oct 2020 00:00:00 GMTTopic Modeling with BERThttps://www.maartengrootendorst.com/blog/topicbert/https://www.maartengrootendorst.com/blog/topicbert/Leveraging BERT and TF-IDF to create easily interpretable topics.Mon, 05 Oct 2020 00:00:00 GMTWhy Psychologists can be great Data Scientistshttps://www.maartengrootendorst.com/blog/psychologists/https://www.maartengrootendorst.com/blog/psychologists/The Intersection of Psychology and Data ScienceFri, 18 Sep 2020 00:00:00 GMTMonitoring your Machine Learning Modelhttps://www.maartengrootendorst.com/blog/monitor/https://www.maartengrootendorst.com/blog/monitor/What to look out for when deploying your ML modelFri, 21 Aug 2020 00:00:00 GMTTransform your ML-model to Pytorch with Hummingbirdhttps://www.maartengrootendorst.com/blog/humming/https://www.maartengrootendorst.com/blog/humming/Accelerate your Machine Learning model by leveraging TensorsMon, 22 Jun 2020 00:00:00 GMTUnit Testing for Data Scientistshttps://www.maartengrootendorst.com/blog/unit/https://www.maartengrootendorst.com/blog/unit/Using Pytest to improve the stability of your pipelinesMon, 18 May 2020 00:00:00 GMTTips for transitioning from Psychology to Data Sciencehttps://www.maartengrootendorst.com/blog/transition/https://www.maartengrootendorst.com/blog/transition/And how you can do both.Mon, 30 Mar 2020 00:00:00 GMTHow to Detect Bias in AIhttps://www.maartengrootendorst.com/blog/bias/https://www.maartengrootendorst.com/blog/bias/Detecting common (cognitive) biases in your dataFri, 31 Jan 2020 00:00:00 GMTReinforcement Learning in a few lines of codehttps://www.maartengrootendorst.com/blog/reinforce/https://www.maartengrootendorst.com/blog/reinforce/Train SOTA RL-algorithms using Stable Baselines and GymTue, 07 Jan 2020 00:00:00 GMTStacking made easy with Sklearnhttps://www.maartengrootendorst.com/blog/stacking/https://www.maartengrootendorst.com/blog/stacking/Create a StackingClassifier in a few lines of code with Scikit-Learn V0.22.Tue, 10 Dec 2019 00:00:00 GMTBuild and Deploy a Dashboard with Streamlithttps://www.maartengrootendorst.com/blog/streamlit/https://www.maartengrootendorst.com/blog/streamlit/Deploying your Streamlit application to Heroku to showcase your Data SolutionMon, 11 Nov 2019 00:00:00 GMTValidating your Machine Learning Modelhttps://www.maartengrootendorst.com/blog/validate/https://www.maartengrootendorst.com/blog/validate/Going beyond k-Fold Cross-ValidationThu, 26 Sep 2019 00:00:00 GMTHow to Deploy a Machine Learning Modelhttps://www.maartengrootendorst.com/blog/deploy/https://www.maartengrootendorst.com/blog/deploy/Creating a production-ready API using FastAPI + UvicornFri, 30 Aug 2019 00:00:00 GMTCreate, Visualize and Interpret Customer Segmentshttps://www.maartengrootendorst.com/blog/customer/https://www.maartengrootendorst.com/blog/customer/In-depth exploration of cluster analysis.Tue, 30 Jul 2019 00:00:00 GMTHow to leverage Explainable Machine Learninghttps://www.maartengrootendorst.com/blog/black-boxes/https://www.maartengrootendorst.com/blog/black-boxes/Using PDP, LIME, and SHAP to create interpretable decisions that create value for your stakeholdersThu, 11 Jul 2019 00:00:00 GMTHow to use NLP to Analyze WhatsApp Messageshttps://www.maartengrootendorst.com/blog/whatsapp/https://www.maartengrootendorst.com/blog/whatsapp/Using NLP to analyze WhatsApp messages between my wife and IThu, 27 Jun 2019 00:00:00 GMTTips for Advanced Feature Engineeringhttps://www.maartengrootendorst.com/blog/feature-engineering/https://www.maartengrootendorst.com/blog/feature-engineering/Improving an important step in ML.Fri, 12 Apr 2019 00:00:00 GMT