OpenCompass/configs/datasets
Ezra-Yu 17ccaa5980
[Feat] Add codegeex2 and Humanevalx (#210)
* add codegeex2

* add humanevalx dataset

* add evaluator

* update evaluator

* update configs

* update clean code

* update configs

* fix lint

* remove sleep

* fix lint

* update docs

* fix lint
2023-08-17 11:03:16 +08:00
..
adv_glue [Feat] support adv_glue dataset for adversarial robustness (#205) 2023-08-16 18:42:06 +08:00
agieval [Feature] Add LEval datasets 2023-08-11 17:38:31 +08:00
anli [Feature] Add Xiezhi SQuAD2.0 ANLI (#101) 2023-08-10 14:04:18 +08:00
apps Update configs (#9) 2023-07-06 12:27:41 +08:00
ARC_c [Feat] update postprocessor to get first option more accurately (#193) 2023-08-11 17:33:00 +08:00
ARC_e [Feat] update postprocessor to get first option more accurately (#193) 2023-08-11 17:33:00 +08:00
bbh [Feature] Add LEval datasets 2023-08-11 17:38:31 +08:00
ceval Update configs (#9) 2023-07-06 12:27:41 +08:00
civilcomments [Feat] add safety to collections (#185) 2023-08-11 11:19:26 +08:00
CLUE_afqmc Update configs (#9) 2023-07-06 12:27:41 +08:00
CLUE_C3 Update configs (#9) 2023-07-06 12:27:41 +08:00
CLUE_cmnli Update configs (#9) 2023-07-06 12:27:41 +08:00
CLUE_CMRC Update configs (#9) 2023-07-06 12:27:41 +08:00
CLUE_DRCD Update configs (#9) 2023-07-06 12:27:41 +08:00
CLUE_ocnli Update configs (#9) 2023-07-06 12:27:41 +08:00
cmmlu [Feature] Add LEval datasets 2023-08-11 17:38:31 +08:00
collections [Fix] fix bug for postprocessor (#195) 2023-08-11 18:41:12 +08:00
commonsenseqa Update configs (#9) 2023-07-06 12:27:41 +08:00
crowspairs [Feature] Add LEval datasets 2023-08-11 17:38:31 +08:00
cvalues [Feature] Add LEval datasets 2023-08-11 17:38:31 +08:00
drop Align prompt files with their hash (#1) 2023-07-05 18:28:58 +08:00
FewCLUE_bustm Update configs (#9) 2023-07-06 12:27:41 +08:00
FewCLUE_chid [Feature] Add logger info and remove dataset bugs (#61) 2023-07-17 14:26:30 +08:00
FewCLUE_cluewsc Update configs (#9) 2023-07-06 12:27:41 +08:00
FewCLUE_csl Update configs (#9) 2023-07-06 12:27:41 +08:00
FewCLUE_eprstmt Update configs (#9) 2023-07-06 12:27:41 +08:00
FewCLUE_ocnli_fc Update configs (#9) 2023-07-06 12:27:41 +08:00
FewCLUE_tnews Update configs (#9) 2023-07-06 12:27:41 +08:00
flores Align prompt files with their hash (#1) 2023-07-05 18:28:58 +08:00
GaokaoBench Align prompt files with their hash (#1) 2023-07-05 18:28:58 +08:00
glm [Enhancement] Add humaneval postprocessor for GPT models & eval config for GPT4, enhance the original humaneval postprocessor (#129) 2023-08-10 16:31:12 +08:00
govrepcrs Update configs (#9) 2023-07-06 12:27:41 +08:00
gsm8k [Feature] Add SC (#126) 2023-07-28 17:29:37 +08:00
hellaswag [Feat] update postprocessor to get first option more accurately (#193) 2023-08-11 17:33:00 +08:00
humaneval [Feature] add llama-oriented dataset configs (#82) 2023-08-11 12:48:05 +08:00
humanevalx [Feat] Add codegeex2 and Humanevalx (#210) 2023-08-17 11:03:16 +08:00
iwslt2017 Update configs (#9) 2023-07-06 12:27:41 +08:00
jigsawmultilingual [Feat] add safety to collections (#185) 2023-08-11 11:19:26 +08:00
lambada Align prompt files with their hash (#1) 2023-07-05 18:28:58 +08:00
lcsts Update configs (#9) 2023-07-06 12:27:41 +08:00
LEvalCoursera [Feature] Add LEval datasets 2023-08-11 17:38:31 +08:00
LEvalFinancialQA [Feature] Add LEval datasets 2023-08-11 17:38:31 +08:00
LEvalGovReportSumm [Feature] Add LEval datasets 2023-08-11 17:38:31 +08:00
LEvalGSM100 [Feature] Add LEval datasets 2023-08-11 17:38:31 +08:00
LEvalLegalContractQA [Feature] Add LEval datasets 2023-08-11 17:38:31 +08:00
LEvalMeetingSumm [Feature] Add LEval datasets 2023-08-11 17:38:31 +08:00
LEvalMultidocQA [Feature] Add LEval datasets 2023-08-11 17:38:31 +08:00
LEvalNarrativeQA [Feature] Add LEval datasets 2023-08-11 17:38:31 +08:00
LEvalNaturalQuestion [Feature] Add LEval datasets 2023-08-11 17:38:31 +08:00
LEvalNewsSumm [Feature] Add LEval datasets 2023-08-11 17:38:31 +08:00
LEvalPaperAssistant [Feature] Add LEval datasets 2023-08-11 17:38:31 +08:00
LEvalPatentSumm [Feature] Add LEval datasets 2023-08-11 17:38:31 +08:00
LEvalQuality [Feature] Add LEval datasets 2023-08-11 17:38:31 +08:00
LEvalReviewSumm [Feature] Add LEval datasets 2023-08-11 17:38:31 +08:00
LEvalScientificQA [Feature] Add LEval datasets 2023-08-11 17:38:31 +08:00
LEvalTopicRetrieval [Feature] Add LEval datasets 2023-08-11 17:38:31 +08:00
LEvalTPO [Feature] Add LEval datasets 2023-08-11 17:38:31 +08:00
LEvalTVShowSumm [Feature] Add LEval datasets 2023-08-11 17:38:31 +08:00
math Update configs (#9) 2023-07-06 12:27:41 +08:00
mbpp Update configs (#9) 2023-07-06 12:27:41 +08:00
mmlu Update configs (#9) 2023-07-06 12:27:41 +08:00
narrativeqa Align prompt files with their hash (#1) 2023-07-05 18:28:58 +08:00
nq [Feature] add llama-oriented dataset configs (#82) 2023-08-11 12:48:05 +08:00
obqa [Feat] update postprocessor to get first option more accurately (#193) 2023-08-11 17:33:00 +08:00
piqa [Feat] update postprocessor to get first option more accurately (#193) 2023-08-11 17:33:00 +08:00
PJExam Align prompt files with their hash (#1) 2023-07-05 18:28:58 +08:00
qabench Align prompt files with their hash (#1) 2023-07-05 18:28:58 +08:00
qasper Align prompt files with their hash (#1) 2023-07-05 18:28:58 +08:00
qaspercut Align prompt files with their hash (#1) 2023-07-05 18:28:58 +08:00
race [Feat] update postprocessor to get first option more accurately (#193) 2023-08-11 17:33:00 +08:00
realtoxicprompts [Feat] add safety to collections (#185) 2023-08-11 11:19:26 +08:00
safety Align prompt files with their hash (#1) 2023-07-05 18:28:58 +08:00
siqa [Feature] add llama-oriented dataset configs (#82) 2023-08-11 12:48:05 +08:00
squad20 [Feature] Add Xiezhi SQuAD2.0 ANLI (#101) 2023-08-10 14:04:18 +08:00
storycloze [Feat] update postprocessor to get first option more accurately (#193) 2023-08-11 17:33:00 +08:00
strategyqa Update configs (#9) 2023-07-06 12:27:41 +08:00
summedits Update configs (#9) 2023-07-06 12:27:41 +08:00
summscreen Update configs (#9) 2023-07-06 12:27:41 +08:00
SuperGLUE_AX_b [Feat] update postprocessor to get first option more accurately (#193) 2023-08-11 17:33:00 +08:00
SuperGLUE_AX_g [Feat] update postprocessor to get first option more accurately (#193) 2023-08-11 17:33:00 +08:00
SuperGLUE_BoolQ [Feature] add llama-oriented dataset configs (#82) 2023-08-11 12:48:05 +08:00
SuperGLUE_CB [Feat] update postprocessor to get first option more accurately (#193) 2023-08-11 17:33:00 +08:00
SuperGLUE_COPA [Feat] update postprocessor to get first option more accurately (#193) 2023-08-11 17:33:00 +08:00
SuperGLUE_MultiRC [Feat] update postprocessor to get first option more accurately (#193) 2023-08-11 17:33:00 +08:00
SuperGLUE_ReCoRD Update configs (#9) 2023-07-06 12:27:41 +08:00
SuperGLUE_RTE [Feat] update postprocessor to get first option more accurately (#193) 2023-08-11 17:33:00 +08:00
SuperGLUE_WiC Update configs (#9) 2023-07-06 12:27:41 +08:00
SuperGLUE_WSC [Feature] Add Xiezhi SQuAD2.0 ANLI (#101) 2023-08-10 14:04:18 +08:00
TheoremQA Update configs (#9) 2023-07-06 12:27:41 +08:00
triviaqa [Feature] add llama-oriented dataset configs (#82) 2023-08-11 12:48:05 +08:00
triviaqarc Align prompt files with their hash (#1) 2023-07-05 18:28:58 +08:00
truthfulqa [Feat] add safety to collections (#185) 2023-08-11 11:19:26 +08:00
tydiqa [Feature] Add tydiqa-goldp (#75) 2023-07-18 14:54:35 +08:00
winograd Align prompt files with their hash (#1) 2023-07-05 18:28:58 +08:00
winogrande [Feat] update postprocessor to get first option more accurately (#193) 2023-08-11 17:33:00 +08:00
XCOPA Align prompt files with their hash (#1) 2023-07-05 18:28:58 +08:00
xiezhi [Feature] Add Xiezhi SQuAD2.0 ANLI (#101) 2023-08-10 14:04:18 +08:00
XLSum Update configs (#9) 2023-07-06 12:27:41 +08:00
Xsum Update configs (#9) 2023-07-06 12:27:41 +08:00
z_bench Add release contribution 2023-07-05 03:15:31 +00:00