Directory listing for /.local/lib/python3.10/site-packages/lm_eval/tasks/
__init__.py
__pycache__/
aclue/
acpbench/
aexams/
afrimgsm/
afrimmlu/
afrixnli/
afrobench/
agieval/
aime/
alghafa/
anli/
arab_culture/
arab_culture_completion/
arabic_leaderboard_complete/
arabic_leaderboard_light/
arabicmmlu/
aradice/
arc/
arc_mt/
arithmetic/
asdiv/
babi/
babilong/
bangla/
basque_bench/
basqueglue/
bbh/
bbq/
bear/
belebele/
benchmarks/
bertaqa/
bhs/
bigbench/
blimp/
blimp_nl/
c4/
cabbq/
careqa/
catalan_bench/
ceval/
chartqa/
click/
cmmlu/
cnn_dailymail/
code_x_glue/
common_voice/
commonsense_qa/
copal_id/
coqa/
crows_pairs/
csatqa/
darija_bench/
darijahellaswag/
darijammlu/
discrim_eval/
drop/
e2lmc/
egyhellaswag/
egymmlu/
eq_bench/
esbbq/
eus_exams/
eus_proficiency/
eus_reading/
eus_trivia/
evalita_llm/
fda/
fld/
french_bench/
galician_bench/
glianorex/
global_mmlu/
global_piqa/
glue/
gpqa/
graphwalks/
groundcocoa/
gsm8k/
gsm8k_platinum/
gsm_plus/
haerae/
headqa/
hellaswag/
hendrycks_ethics/
hendrycks_math/
histoires_morales/
hrm8k/
humaneval/
humaneval_infilling/
icelandic_winogrande/
ifeval/
include/
inverse_scaling/
japanese_leaderboard/
jsonschema_bench/
kbl/
kmmlu/
kobest/
kormedmcqa/
lambada/
lambada_cloze/
lambada_multilingual/
lambada_multilingual_stablelm/
leaderboard/
libra/
lingoly/
llama3/
lm_syneval/
logiqa/
logiqa2/
longbench/
longbench2/
mastermind/
mathqa/
mbpp/
mc_taco/
med_concepts_qa/
med_prescriptions/
med_text_classification/
meddialog/
mediqa_qa2019/
medmcqa/
medqa/
medtext/
mela/
meqsum/
metabench/
mgsm/
mimic_repsum/
minerva_math/
mlqa/
mmlu/
mmlu-pro-plus/
mmlu-redux/
mmlu-redux-spanish/
mmlu_pro/
mmlu_prox/
mmlusr/
mmmu/
model_written_evals/
moral_stories/
mts_dialog/
multiblimp/
mutual/
noreval/
noticia/
nq_open/
okapi/
olaph/
openai-mmmlu/
openbookqa/
paloma/
paws-x/
pile/
pile_10k/
piqa/
pisa/
polemo2/
portuguese_bench/
prost/
pubmedqa/
qa4mre/
qasper/
race/
README.md
realtoxicityprompts/
ruler/
sciq/
score/
scrolls/
simple_cooccurrence_bias/
siqa/
slr_bench/
spanish_bench/
squad_completion/
squadv2/
storycloze/
super_glue/
swag/
swde/
tinyBenchmarks/
tmlu/
tmmluplus/
toxigen/
translation/
triviaqa/
truthfulqa/
truthfulqa-multi/
turblimp/
turkishmmlu/
ulqa/
unitxt/
unscramble/
webqs/
wikitext/
winogender/
winogrande/
wmdp/
wmt2016/
wsc273/
xcopa/
xnli/
xnli_eu/
xquad/
xstorycloze/
xwinograd/
zhoblimp/