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.

Effortless plugin and play Optimizer to cut model training costs by 50%. New optimizer that is 2x faster than Adam on LLMs.

Implementation of plug in and play Attention from "LongNet: Scaling Transformers to 1,000,000,000 Tokens"

Code for "Learning to Model the World with Language."

A new markup-based typesetting system that is powerful and easy to learn.

JAX Synergistic Memory Inspector

Graphical tool to make photo collage posters

Full named-entity (i.e., not tag/token) evaluation metrics based on SemEval’13

NeuralQA: A Usable Library for Question Answering on Large Datasets with BERT

The Danish Gigaword project

🖤 Create and share beautiful images of your source code

Concurrent data pipelines in Python >>>

Utils for streaming large files (S3, HDFS, gzip, bz2...)

A fast and reliable background task processing library for Python 3.

Cheatsheets for web development - devhints.io

A cat(1) clone with wings.

A simple, fast and user-friendly alternative to 'find'

Exploring word2vec embeddings as a graph of nearest neighbors

Bidirectional LSTM-CRF and ELMo for Named-Entity Recognition, Part-of-Speech Tagging and so on.

A lightweight header-only library for using Keras (TensorFlow) models in C++.

Optional static typing for Python