Fine-tune Gemma 4 and 3n with audio, images and text on Apple Silicon, using PyTorch and Metal Performance Shaders.

MLX-VLM is a package for inference and fine-tuning of Vision Language Models (VLMs) on your Mac using MLX.

OCR model that handles complex tables, forms, handwriting with full layout.

A repository containing general tutorials I'd like to share with the world.

Toolkit for linearizing PDFs for LLM datasets/training

Examples in the MLX framework

This repository contains demos I made with the Transformers library by HuggingFace.

Various utilities regarding Levenshtein transducers. (C++)

Linked Data opvolger voor de A2A standaard

Utility sparse matrix functions for Quantitative Language Comparison (QLC)

Lightweight extension of the base R graphics system

Ready-to-use OCR with 80+ supported languages and all popular writing scripts including Latin, Chinese, Arabic, Devanagari, Cyrillic and etc.

A no-frills curriculum vitae (CV) template using Typst and YAML to version control CV data.

Code for the paper "Deep Entity Matching with Pre-trained Language Models"

A markup-based typesetting system that is powerful and easy to learn.

A Python package for segmenting geospatial data with the Segment Anything Model (SAM)

Innovation across ages

Locally run an Instruction-Tuned Chat-Style LLM

Bi-encoder Based Entity Linking Tutorial. You can run experiment only in 5 minutes. Experiments on Co-lab pro GPU are also supported!

R's data.table package extends data.frame:

Simple Engine for Generating Reports using R

Command line tool for linking civil registries

Lecture notes for EC 607

Fixed-effects estimations

CmdStanR: the R interface to CmdStan

Code for linking all Dutch civil registries

Various utilities regarding Levenshtein transducers. (Java)