m-resta

debloat-samsung-android

ADB commands to aggressively de-bloat Samsung Android Phones without root. Make Samsung One UI closer to stock Android.

composable-sft

A library for parameter-efficient and composable transfer learning for NLP with sparse fine-tunings.

lm-format-enforcer

Enforce the output format (JSON Schema, Regex etc) of a language model

SMRY

A tool to get summaries and get past paywalls

ambuda

Main application code for Ambuda, a breakthrough Sanskrit library (ambuda.org)

the-story-of-heads

This is a repository with the code for the ACL 2019 paper "Analyzing Multi-Head Self-Attention: Specialized Heads Do the Heavy Lifting, the Rest Can Be Pruned" and the ACL 2021 paper "Analyzing Source and Target Contributions to NMT Predictions".

expand-via-lexicon-based-adaptation

Code for ACL 2022 paper "Expanding Pretrained Models to Thousands More Languages via Lexicon-based Adaptation"

url-nlp

MUSE

A library for Multilingual Unsupervised or Supervised word Embeddings

gpt4free

The official gpt4free repository | various collection of powerful language models

teaching

teaching-app

Repository for TEACHING application startup and deployment. This can be taken as the main access point for the TEACHING plaform developed within the EU TEACHING 2020 project.

sentence-splitter

Text to sentence splitter using heuristic algorithm by Philipp Koehn and Josh Schroeder.

MT-Preparation

Machine Translation (MT) Preparation Scripts

user.js

Firefox privacy, security and anti-tracking: a comprehensive user.js template for configuration and hardening

roop

one-click face swap

segment-anything

The repository provides code for running inference with the SegmentAnything Model (SAM), links for downloading the trained model checkpoints, and example notebooks that show how to use the model.

fugashi

A Cython MeCab wrapper for fast, pythonic Japanese tokenization and morphological analysis.

langchain

🦜🔗 Build context-aware reasoning applications

composer

Supercharge Your Model Training

deepsparse

Sparsity-aware deep learning inference runtime for CPUs

perovskitedatabase

deduplicate-text-datasets

your-life

uBlock-Origin-dev-filter

Filters to block and remove copycat-websites from DuckDuckGo, Google and other search engines. Specific to dev websites like StackOverflow or GitHub.

scite-zotero-plugin

scite zotero plugin

process-arabic-text

Pre-process arabic text (remove diacritics, punctuations and repeating characters)

fairseq

Facebook AI Research Sequence-to-Sequence Toolkit written in Python.

gourmet-models

Machine translation models released by the Gourmet project (https://gourmet-project.eu)

marian-mBART

Training harness to pretrain a mBART model using Marian