Blog

June 18, 2026 Nemotron-Personas-Belgium
A multilingual synthetic persona dataset grounded in the Statbel census

December 17, 2025 Small language models in 2025
Looking back on a year of skyrocketing capabilities, sovereignty, and running AI on a MacBook October 28, 2025 NanoGPT-inference
LLM inference from scratch

NanoGPT-inference - Tensor Parallelism

NanoGPT-inference - Baseline

NanoGPT-inference - Sampling

NanoGPT-inference - KV Caching

NanoGPT-inference - CUDA Graphs

January 21, 2025 Deploying DeepSeek R1 'locally'
A Practical Guide with Ray and vLLM

September 11, 2024 European Tweeties
Creating language models for all 24 EU languages August 30, 2024 Setting up a decent SentencePiece tokenizer
Reasonable monolingual tokenization from noisy data January 05, 2024 Evaluating Dutch LLMs
SQUAD-NL

December 27, 2023 Dutch Chat Toolkit
Creating retrieval-augmented chatbots November 04, 2023 Building a language learning app
Day 3: Prompting and basic UI November 01, 2023 Building a language learning app
Day 2: setting up the app October 30, 2023 Building a language learning app
Day 1: planning October 24, 2023 Migrating from HuggingFace AdamW
Drop-in replacement optimizer with learning schedule

November 10, 2022 Updating RobBERT (part 2)
Bringing a language model to 2022 August 12, 2022 Updating RobBERT
Bringing a language model to 2022