mttk

shap

A game theoretic approach to explain the output of any machine learning model.

xformers

Hackable and optimized Transformers building blocks, supporting a composable construction.

sioyek

Sioyek is a PDF viewer with a focus on textbooks and research papers

RedPajama-Data

The RedPajama-Data repository contains code for preparing large datasets for training large language models.

nogil

Multithreaded Python without the GIL

BIG-bench

Beyond the Imitation Game collaborative benchmark for measuring and extrapolating the capabilities of language models

promptsource

Toolkit for creating, sharing and using natural language prompts.

memgraph

Open-source graph database, tuned for dynamic analytics environments. Easy to adopt, scale and own.

FARM

:house_with_garden: Fast & easy transfer learning for NLP. Harvesting language models for the industry. Focus on Question Answering.

pythagora

Generate automated tests for your Node.js app via LLMs without developers having to write a single line of code.

state-spaces

Sequence Modeling with Structured State Spaces

functorch

functorch is JAX-like composable function transforms for PyTorch.

data

A PyTorch repo for data loading and utilities to be shared by the PyTorch domain libraries.

pytorch-goodies

PyTorch Boilerplate For Research

inception

INCEpTION provides a semantic annotation platform offering intelligent annotation assistance and knowledge management.

rome

Locating and editing factual associations in GPT (NeurIPS 2022)

slot-attention

Implementation of Slot Attention from GoogleAI

jury

Comprehensive NLP Evaluation System

mlm-pytorch

An implementation of masked language modeling for Pytorch, made as concise and simple as possible

zero

Zero -- A neural machine translation system

scrolls

The official code of EMNLP 2022, "SCROLLS: Standardized CompaRison Over Long Language Sequences".

xai-benchmark

A Diagnostic Study of Explainability Techniques for Text Classification

Interpretable-Attention

Official Code for Towards Transparent and Explainable Attention Models paper (ACL 2020)

alanno

feb

Code associated with the paper: "Few-Shot Self-Rationalization with Natural Language Prompts"

cutters

A rule based sentence segmentation library.

WSIatScale

fairseq-entmax

Demo of fairseq with entmax loss and fenchel-young label smoothing

acl-search

A search-as-you-type web app for the ACL Anthology.

nlpop