State-of-the-art paired encoder and decoder models (17M-1B params)

A massively multilingual modern encoder language model

Late Interaction Models Training & Retrieval

On the Theoretical Limitations of Embedding-Based Retrieval

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

A simple tool to update bib entries with their official information (e.g., DBLP or the ACL anthology).

Various ZIM command line tools

Basic utils for Tweet processing

An example of a PulseAudio app working within a Docker container using the hosts sound system

A beautiful, simple, clean, and responsive Jekyll theme for academics

Code and datasets for the paper "Humor Detection: A Transformer Gets the Last Laugh"

An easy way to tune machine learning hyperparameters (especially for those that use a config file)

An implementation of ROUGE family metrics for automatic summarization.

App for Student Housing - see link to Google Play

An R Package to return a variety of different model types, complete with hyper-parameter tuning