feat: Add LIBRA benchmark for long-context evaluation (#2943)
* Feat: add LIBRA benchmark
* Feat: add dataset filter to LIBRA
* Fix: formatting through pre-commit and main tasks README
* Fix: resolve conflict
* Fix: dataset name to real
* Fix: delete unnececcary datasets and correct dependency
---------
Co-authored-by:
Baber Abbasi <92168766+baberabb@users.noreply.github.com>
Showing
Please register or sign in to comment