MBZUAI-Paris/EgyptianHellaSwag

Domain:

natural language processing

Record type:

dataset

Creator:

MBZ

Host:

EgyptianHellaSwag is a challenging multiple-choice benchmark designed to evaluate machine reading comprehension and commonsense reasoning in Egyptian Arabic (Masri). It is a translated version of the HellaSwag train, validation, and test sets which presents scenarios where models must choose the most plausible continuation of a passage from four options. Supported Tasks

MBZUAI-Paris/DarijaHellaSwag

DarijaHellaSwag is a challenging multiple-choice benchmark designed to evaluate machine reading comp

MBZUAI-Paris/DarijaStory

DarijaStory is a story completion dataset. It consists of 4,392 long stories scraped from 9esa, a we

MBZUAI-Paris/DarijaBench

Note the ODC-BY license, indicating that different licenses apply to subsets of the data. This means

MBZUAI-Paris/DarijaAlpacaEval

Dataset Summary

MBZUAI-Paris/DarijaMMLU

DarijaMMLU is an evaluation benchmark designed to assess large language models' (LLM) performance in

MBZUAI-Paris/MoroccanWikipedia-QA

Dataset Summary

MBZUAI-Paris/EgyptianHellaSwag

Domain:

Record type:

Visit

Tasks

Languages