BramVanroy

spacy_conll

Pipeline component for spaCy (and other spaCy-wrapped parsers such as spacy-stanza and spacy-udpipe) that adds CoNLL-U properties to a Doc and its sentences and tokens. Can also be used as a command-line tool.

fietje-2

An open, efficient LLM for Dutch

mateo-demo

MAchine Translation Evaluation Online (MATEO)

mai-simplification-nl-2023

Sentence-Level Text Simplification for Dutch

multilingual-text-to-amr

astred-demo

Demo app to illustrate ASTrED

dutch-instruction-datasets

llm-finetuning

xml_query

alignment-handbook

Robust recipes to align language models with human and AI preferences

evaluate

🤗 Evaluate: A library for easily evaluating machine learning models and datasets.

aclpub2

bitsandbytes

8-bit CUDA functions for PyTorch

bramvanroy.github.io

clin33-zero-shot

clin34-benchmarks

datatrove

Freeing data processing from scripting madness by providing a set of platform-agnostic customizable pipeline processing blocks.

DeepSpeed

DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.

distilabel

Distilabel is a framework for synthetic data and AI feedback for AI engineers that require high-quality outputs, full data ownership, and overall efficiency

distilabel-helm-instruct-adaptable-evaluation-criteria

A repo that implements Stanford CRFM their HELM Instruct with adaptable evaluation criteria

LeCoNTra

llama.cpp

LLM inference in C/C++

lm-evaluation-harness

mt-benchmarks

optimum

🚀 Accelerate training and inference of 🤗 Transformers and 🤗 Diffusers with easy to use hardware optimization tools

outlines

Generative Model Programming

penman

PENMAN notation (e.g. AMR) in Python

ReinWeb

sacrebleu

Reference BLEU implementation that auto-downloads test sets and reports a version string to facilitate cross-lab comparisons

transformers

🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.