Kenneth Enevoldsen's repositories
spacy-wrap
spaCy-wrap is a wrapper library for spaCy for including fine-tuned transformers from Huggingface in your spaCy pipeline allowing you to include existing fine-tuned models within your SpaCy workflow.
scandinavian-embedding-benchmark
A Scandinavian Benchmark for sentence embeddings
swift-python-cookiecutter
A python package template intended for low maintenance and quick package development.
bag-of-tricks
KennethEnevoldsen package for personal utilities.
OpenJournal
A discussion forum for discussing alternatives way for to scientific publishing.
confection
:candy: Confection: the sweetest config system for Python
curated-transformers
🤖 A PyTorch library of curated Transformer models and their composable components
dolma
Data and tools for generating and inspecting OLMo pre-training data.
genda-lens
GenDa Lens: Python package for quatifying gender bias in Danish language models.
genq_dansk
Repo til auto generering af et retrieval (spørgsmål-tekst) benchmark datasæt
jury
Comprehensive NLP Evaluation System
KennethEnevoldsen
Personal repository
KennethLM
A test repository for testing out variations on generative language models
MissingDataChallenge
Scripts for the missing data challenge 2023
mteb
MTEB: Massive Text Embedding Benchmark
Multilingual-SoMe-OIE
The repository for the Multilingual SoMe Open Information extraction dataset
NorQuAD
Norwegian question answering dataset
permetrics
Artificial intelligence (AI, ML, DL) performance metrics implemented in Python
ScandEval
Evaluation of language models on mono- or multilingual Scandinavian language tasks.
scikit-llm
Seamlessly integrate LLMs into scikit-learn.
spaCy
💫 Industrial-strength Natural Language Processing (NLP) in Python
spacy-curated-transformers
spaCy entry points for Curated Transformers
spacy-llm
🦙 Integrating LLMs into structured NLP pipelines