Spaces:

aauss
/

timebench_eval

Running

App Files Files Community

timebench_eval / tests

Commit History

Improve type hints, add early input checks and format code.

eca4af7

Running

aauss commited on about 7 hours ago

Fix None passed to squad metric and update import in tests.

edd0a90

aauss commited on 6 days ago

Implement TimeDial evaluation.

fb49a5d

aauss commited on 7 days ago

Implement and test metric for TempReason, TimeQA, MenatQA and Date Arithmetic.

6bb843b

aauss commited on 7 days ago