ggml-org/ggml

ggml : implement a spellcheck model (xfspell, t5-spellchecker, etc)

Open

Aperta il 6 giu 2023

Vedi su GitHub
 (12 commenti) (10 reazioni) (0 assegnatari)C++ (14.741 star) (1646 fork)auto 404
good first issuehelp wantedmodelroadmap

Descrizione

Apple had recently announced a new transformer-based keyboard auto-correct and prediction.

xfspell seems to be an existing model that tried doing it, so why not investigate if it can be ported to GGML. If anyone know other models for predictive keyboard or auto correct, please drop your suggestions here.

Perhaps this may even be a good test case for on-device QLoRA fine-tuning.

High quality predictive keyboards and auto-correct in pure C++ can be a useful thing for open-source mobile operating systems like Ubuntu Touch and privacy-focused Android ROMs, because traditionally, such proposals got rejected because of excessive dependencies for ML inference.

Guida contributor

Tech stack
cpp
Dominio
machine learning
Tipo issue
feature
DifficoltàQuanto dovrebbe essere impegnativa per un nuovo contributor.
3
Tempo stimatoTempo stimato per completare e verificare uno scope piccolo.
1-2 days
Stato attivitàQuanto è probabile che la issue sia ancora attiva e reviewable.
active
ChiarezzaQuanto chiaramente la issue descrive problema, scope e risultato atteso.
clear
Prerequisiti
GitC++Machine Learning basics
Adatta ai principiantiQuanto la issue è adatta a contributor alla prima esperienza.
40
Direzione di ricerca
Study the xfspell model (https://github.com/mhagiwara/xfspell) and its transformer architecture. Identify key components and map them to GGML operations. Consider implementing a prototype for auto correct functionality.