GitHub repository
Repository
PsychoSafe
Pipeline for building and evaluating psychologically informed refusal behavior in large language models through data creation, prompting, fine-tuning, and evaluation.
View repositoryOpen-source code maintained by OdenseNLP.
GitHub repository
Repository
Pipeline for building and evaluating psychologically informed refusal behavior in large language models through data creation, prompting, fine-tuning, and evaluation.
View repositoryGitHub repository
Repository
Framework for evaluating memorization and propensity-aware memorization of training data in large language models.
View repositoryGitHub repository
Repository
Source code for creating the Danish Corpus of Linguistic Acceptability, designed to evaluate Danish linguistic acceptability with real-world errors.
View repositoryGitHub repository
Repository
Production-ready implementation of 1.58-bit layers for quantization-aware training and efficient inference.
View repositoryGitHub repository
Repository
Swiss-army-knife style toolkit for scripted tensor surgery on model checkpoints, with YAML plans, CLI workflows, and a Web UI.
View repositoryGitHub repository
Repository
A communication framework that optimizes distributed AI training by reducing latency bottlenecks and handling heterogeneous clusters.
View repositoryGitHub repository
Repository
A streamlined framework for evaluating language generation quality in two steps: generation and automatic evaluation.
View repositoryGitHub repository
Repository
Swiss-army-knife toolkit for transforming and processing machine learning datasets, including large-scale format conversion and splitting.
View repositoryGitHub repository
Repository
Utility for grooming and managing machine learning job queues.
View repositoryGitHub repository
Repository
AI-assisted analyser for projective techniques in qualitative health research.
View repositoryGitHub repository
Repository
Benchmark and tooling for evaluating LLM understanding of Danish culture using closed question-answer pairs grounded in the Danish Culture Canon.
View repositoryGitHub repository
Repository
Pretraining framework behind DFM Mimir for efficient 0.6B–1B text models, combining hierarchical recurrence, PrefixLM packing, distributed training, evaluation, and checkpoint conversion tooling.
View repositoryGitHub repository
Repository
Offline-first field-notes app for qualitative research, supporting photo, video, audio, and text capture with project organization, location mapping, exports, and self-hosted Nextcloud backup.
View repository