π Launching Napolab: The Natural Portuguese Language Benchmark π
Napolab is here: a curated collection of Portuguese datasets designed for easy evaluation of language models.
Explore and contribute on GitHub:
https://github.com/ruanchaves/napolab
π Why Napolab?
πΏ Natural: Contains only native or professionally translated Portuguese datasets.
β Reliable: Provides trustworthy evaluation metrics.
π Publicly Accessible: All datasets are available for public access.
π©βπ§ Human-Annotated: Every dataset exclusively features expert human annotations.
π General-Purpose: No domain-specific knowledge or advanced preparation is needed to solve dataset tasks.
Napolab also offers translated versions of all datasets in the following languages:
- Catalan
- English
- Galician
- Spanish
Get started and download with just two commands:
pip install napolab
python -m napolab
#Napolab #PortugueseBenchmark #NLP #Datasets