GitLab

Merge branch 'big-refactor' of https://github.com/EleutherAI/lm-evaluation-harness into flan-benchmark

[Refactor] Fix IndexError

[Refactor] Asdiv

[Refactor] drop

[Refactor] Coqa

Added
```
from lm_eval.benchmarks import include_benchmarks
```

in order for benchmarks to callable.

[Refactor] Superglue T5 Parity