bigscience-workshop / bigscience-workshop/evaluation
Add TyDiQA for non-training languages to Full Benchmark
Open
few_shot
multilingual
- Dominant language
- Python
- Stars
- 42
- Forks
- 24
- PR merge metrics
- No merged PRs in 30d
Description
use to test generalization to unseen language; maybe use FLEX?
Contributor guide
Assessment
This issue has not been assessed yet.