Spaces:
Running
Running
Commit History
-
ADD: BoolQ, TurthfulQA (#5)
- ADD: truthfulqa_mc1, boolq FIX: CMMLU prompt (ed7a3db35a638f10b2693888d5c96306422ef09a)7e92c24
-
fix math cornercase
32ae64f
-
update MATH
4e1024e -
!ref suite
3a8c0d0 -
refactor
9827786
-
fix math
6d6787f -
update math
58f14b3
-
Add new benchmark (#2)
- ADD: BBH, ARC, Hellaswag, Winogrande, ceval (a14bfe6b6c6cf1d965633d1647f8d3190c707b50) - FIX: fix conflicts (272edd2428eecb87d59e7c2e3aa8c07026159b9f) Co-authored-by: songzhuoyang <Cookize@users.noreply.huggingface.co>141ccb9
-
update
33a6f85
-
add mmlu and cmmlu
be1543a
-
upd
8af54b8