search

SEACrowd / seacrowd-datahub

A collaborative project to collect datasets in SEA languages, SEA regions, or SEA cultures.
Apache License 2.0
60 stars 56 forks source link

Create dataset loader for Tatabahasa #530

Closed SamuelCahyawijaya closed 5 months ago

SamuelCahyawijaya commented 5 months ago

Dataloader name: tatabahasa/tatabahasa.py DataCatalogue: http://seacrowd.github.io/seacrowd-catalogue/card.html?tatabahasa

Dataset tatabahasa
Description This test is a general test for Malay grammar. Contains 349 questions.
Subsets -
Languages zlm
Tasks Commonsense Reasoning
License Unknown (unknown)
Homepage https://github.com/mesolitica/malaysian-dataset/tree/master/llm-benchmark/tatabahasabm.tripod.com
HF URL -
Paper URL -
patrickamadeus commented 5 months ago

self-assign