Tool for interactive embeddings visualization

This is an extension of the popular 21cmFAST code that interfaces with CLASS to generate initial conditions at recombination that are consistent with the input cosmological model

Data Toolkit for Sailor Language Models

Extract structured text from pdfs quickly

Data and tools for generating and inspecting OLMo pre-training data.

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

A latent text-to-image diffusion model

A high-throughput and memory-efficient inference and serving engine for LLMs

A Survey on Data Selection for Language Models

Lightweight clipboard manager for macOS

A general representation model across vision, audio, language modalities. Paper: ONE-PEACE: Exploring One General Representation Model Toward Unlimited Modalities

✨ Build AI interfaces that spark joy

What's In My Big Data (WIMBD) - a toolkit for analyzing large text datasets

ICLR2024 Spotlight: curation/training code, metadata, distribution and pre-trained models for MetaCLIP; CVPR 2024: MoDE: CLIP Data Experts via Clustering

A library to manipulate font files from Python.

Microsoft.Recognizers.Text provides recognition and resolution of numbers, units, date/time, etc. in multiple languages (ZH, EN, FR, ES, PT, DE, IT, TR, HI, NL. Partial support for JA, KO, AR, SV).…

BookNLP, a natural language processing pipeline for books

Creative interactive views of any dataset.

The Archives Unleashed Toolkit is an open-source toolkit for analyzing web archives.

Lexical Generalization Improves with Larger Models and Longer Training (EMNLP 2022)

Accurately separates a URL’s subdomain, domain, and public suffix, using the Public Suffix List (PSL).

Trankit is a Light-Weight Transformer-based Python Toolkit for Multilingual Natural Language Processing

Python script which prints out a summary of your free slots from your Google calendar(s) so you can paste into a scheduling email.

A template repo for Python packages

Tools for checking ACL paper submissions

Open-Source Neural Machine Translation in Tensorflow

DoWhy is a Python library for causal inference that supports explicit modeling and testing of causal assumptions. DoWhy is based on a unified language for causal inference, combining causal graphic…

A reading list for papers on causality for natural language processing (NLP)