A character-level language diffusion model trained on Tiny Shakespeare

Large multi-modal models (L3M) pre-training.

Work being done for Master's Thesis

Structured Outputs

Wrapper for the macOS signpost API

Whispering Experts: Neural Interventions for Toxicity Mitigation in Language Models, ICML 2024

LSP-AI is an open-source language server that serves as a backend for AI-powered functionality, designed to assist and empower software engineers, not replace them.

An open source application built using the new router, server components and everything new in Next.js 13.

An open platform for training, serving, and evaluating large language models. Release repo for Vicuna and Chatbot Arena.

Easily use and train state of the art late-interaction retrieval methods (ColBERT) in any RAG pipeline. Designed for modularity and ease-of-use, backed by research.

OCR, layout analysis, reading order, table recognition in 90+ languages

A Dutch retrieval-augmented chat toolkit

Code for the paper "Challenges in Measuring Bias in Open-Ended Language Generation" presented as oral at the 4th Workshop on Gender Bias in NLP at NAACL 2022.

A Python package to compute HONEST, a score to measure hurtful sentence completions in language models. Published at NAACL 2021.

arxiv-sanity lite: tag arxiv papers of interest get recommendations of similar papers in a nice UI using SVMs over tfidf feature vectors based on paper abstracts.

📗 Command-line tools for bibliographies.

Bring projects, wikis, and teams together with AI. AppFlowy is the AI collaborative workspace where you achieve more without losing control of your data. The leading open source Notion alternative.

A Python package to assess and improve fairness of machine learning models.

A supercharged version of paperless: scan, index and archive all your physical documents

Probing for relative pronouns in Dutch relative clauses

Pretrain and finetune ELECTRA with fastai and huggingface. (Results of the paper replicated !)

Synchronous multiroom audio player

Label Studio is a multi-type data labeling and annotation tool with standardized output format

Verify properties of additive tree ensembles.

hb-config: easy to configure your python project especially Deep Learning experiments

This is an implementation of the LexVec word embedding model (similar to word2vec and GloVe) that achieves state of the art results in multiple NLP tasks

Code and data for NAACL 2018 article "Before Name-calling: Dynamics and Triggers of Ad Hominem Fallacies in Web Argumentation" by Habernal et al.