huggingface/lighteval

[EVAL]: Add more African Benchmarks

Aperta

#373 aperta il 24 ott 2024

 (4 commenti) (0 reazioni) (0 assegnatari)Python (514 fork)auto 404
good first issuehelp wantednew-task

Metriche repository

Star
 (2496 stelle)
Metriche merge PR
 (Metriche PR in attesa)

Descrizione

Evaluation short description

  • Why is this evaluation interesting? This focuses on 16 African languages, evaluated on three knowledge QA and reasoning tasks such as AfriMMLU, AfriMGSM and AfriXNLI, human translated from MMLU, MGSM and XNLI respectively.

  • How used is it in the community?

Evaluation metadata: IrokoBench

Provide all available

Evaluation metadata: Uhura

Provide all available

Evaluation metadata: SIB-200

Provide all available

@NathanHB

Guida contributor