Solve puzzles. Improve your pytorch.

Meta Lingua: a lean, efficient, and easy-to-hack codebase to research LLMs.

Official repository of the xLSTM.

MTEB: Massive Text Embedding Benchmark

Minimum Bayes Risk Decoding for Hugging Face Transformers

The Art of Debugging

DSPy: The framework for programming—not prompting—language models

an easy-to-use knn-mt toolkit

PyTorch + HuggingFace code for RetoMaton: "Neuro-Symbolic Language Modeling with Automaton-augmented Retrieval" (ICML 2022), including an implementation of kNN-LM and kNN-MT

Code for paper "Nearest Neighbor Knowledge Distillation for Neural Machine Translation" by Zhixian Yang, Renliang Sun, and Xiaojun Wan. This paper is accepted by NAACL 2022 Main Conference.

MAFAND-MT

Gale-Church sentence aligner with options for variable parameters

A template repo for Python packages

Well documented, unit tested, type checked and formatted implementation of a vanilla transformer - for educational purposes.

A tool that locates, downloads, and extracts machine translation corpora

Unsupervised Word Segmentation for Neural Machine Translation and Text Generation

A Zotero plugin for syncing items and notes into Notion

Create a Notion collection, synced with Zotero.

A Python library for working with and comparing language codes.

Expanding natural instructions

Yet Another Neural Machine Translation Toolkit

Zero -- A neural machine translation system

Style guides for Google-originated open-source projects

A formatter for Python files

Useful localization tools with Python API for building localization & translation systems

NLQuAD: A Non-Factoid Long Question Answering Data Set. To be published at EACL2021

Python port of Moses tokenizer, truecaser and normalizer

PRML algorithms implemented in Python

Minimalist NMT for educational purposes

A PyTorch Extension: Tools for easy mixed precision and distributed training in Pytorch