Wei Li
b84518c656
[Dataset] Support MedMCQA and MedBullets benchmark ( #2054 )
...
* support medmcqa and medbullets benchmark
* Add Medbullets data folder for benchmark support
* revise gen name
* revise config file & remove csv file & add dataset info to dataset-index.yml
* remove csv file
* remove print in medbullets.py
* revise class name
* update_oss_info
---------
Co-authored-by: MaiziXiao <xxllcc1993@gmail.com>
2025-05-13 17:10:50 +08:00
zhulinJulia24
d60f59dcab
[CI] update baseline and fix lmdeploy version ( #2098 )
...
* update
* update
* update
* update
* update
* update
2025-05-13 14:01:47 +08:00
bittersweet1999
9eaa1f6fec
Update icl_judge_evaluator.py ( #2095 )
2025-05-13 10:44:24 +08:00
Linchen Xiao
d590f557bb
[Update] OpenaiSDK handle empty content ( #2096 )
2025-05-12 19:38:30 +08:00
yuehua-s
c492e49e79
[Update] Add o4 in OpenaiSDK ( #2083 )
...
* feature:1.add o4-mini;2.o3 or o4-mini only support temperature==1
* feature:change 4o-mini to 4o
---------
Co-authored-by: yuehuazhang <yuehuazhang@tencent.com>
2025-05-12 18:39:44 +08:00
Dongsheng Zhu
2c79dc5227
[Dataset] Add human_eval/mbpp pro ( #2092 )
...
* add bench
* update
* bug fix
* time update
* add index
* fix repeat bug
2025-05-12 18:38:13 +08:00
huihui1999
345674f700
[Dataset] Add SciknowEval Dataset ( #2070 )
...
* first
* first
* first
* first
* SciKnowEval
* fix hash
* fix dataset-index & use official llm_judge_postprocess
* fix dataset-index.yml
* use official llmjudge_postprocess
* fix lint
* fix lint
* fix lint
* fix lint
* fix lint
* merge with main
---------
Co-authored-by: Linchen Xiao <xxllcc1993@gmail.com>
2025-05-12 17:23:44 +08:00
Kun Yuan
8aa18df368
[Dataset] HLE Biomedical version support ( #2080 )
...
* HLE Biomedical version support
* set up default category value for hle
2025-05-12 10:14:11 +08:00
huihui1999
44a7024ed5
[Dataset] MedCalc_Bench ( #2072 )
...
* MedCalc_Bench
* MedCal_Bench
* add hash
* fix hash
* fix comments &dataset-index yml
* fix lint
* fix lint
* fix lint
* fix lint
* fix lint
---------
Co-authored-by: Linchen Xiao <xxllcc1993@gmail.com>
2025-05-09 16:58:55 +08:00
Linchen Xiao
508e2b0cb2
[Update] Set load_from_cache_file to False ( #2085 )
2025-05-09 15:21:47 +08:00
Kun Yuan
7bdd3c1904
[Dataset] MMLU_Pro Biomedical Version Support ( #2081 )
2025-05-09 15:07:26 +08:00
Jin Ye
6097186a95
[Datasets] MedQA, ProteinLMBench; Add Models: huatuogpt, baichuanM1 ( #2064 )
...
* Add Datasets: MedQA, ProteinLMBench; Add Models: huatuogpt, baichuanM1
* Fix bugs for MedQA. Add info in dataset-index
* Add version code for MedQA and ProteinLMBench
* Add version code for MedQA and ProteinLMBench
2025-05-09 14:47:44 +08:00
Linchen Xiao
d72df59363
[Revert] Add Lifescience Sub-set Support for SciEval ( #2059 ) ( #2087 )
...
This reverts commit c5048bfec7
2025-05-09 14:46:27 +08:00
tcheng
c5048bfec7
[Dataset] Add Lifescience Sub-set Support for SciEval ( #2059 )
...
* style: pass all formatting hooks (yapf & quote fixer)
* revise name:Add Lifescience Sub-set Support for MMLU & SciEval (datasets + configs + loader)
* revise name:Add Lifescience SciEval (datasets + configs + loader+dataset-index.yml)
* Add Lifescience SciEval (datasets + configs + loader+dataset-index.yml)
---------
Co-authored-by: root <tangcheng231@mails.ucas.edu.cn>
2025-05-09 14:31:12 +08:00
huihui1999
a7f3ac20b2
[Dataset] Add CARDBiomedBench ( #2071 )
...
* CARDBiomedBench
* fix hash
* fix dataset-index
* use official llmjudge postprocess
* use official llmjudge_postprocess
* fix lint
* fix init
2025-05-08 19:44:46 +08:00
Mo Li
ff3275edf0
[Update] Add Long-Context configs for Gemma, OREAL, and Qwen2.5 models ( #2048 )
...
* [Update] Update Gemma, Oreal, Qwen Config
* fix lint
2025-05-08 19:06:56 +08:00
Wei Li
a685ed7daf
[Dataset] Add nejm ai benchmark ( #2063 )
...
* support nejm ai benchmark
* add dataset files
* revise gen name
* revise gen name
* revise class name & remove csv file & add dataset-index.yml info
* update
* update
---------
Co-authored-by: MaiziXiao <xxllcc1993@gmail.com>
2025-05-08 16:44:05 +08:00
Jiahao Xu
9ec23c145b
[Datasets] Add ClinicBench, PubMedQA and ScienceQA ( #2061 )
...
* Add ClinicBench
* Add PubMedQA & ScienceQA & ClinicBench
* Add PubMedQA & ScienceQA & ClinicBench
* Update datasets_info & hf_path
* Update hf_path
2025-05-08 16:25:43 +08:00
Dongsheng Zhu
ba0e32292c
[Feature] Support InternSandbox ( #2049 )
...
* internsandbox init
* internsandbox
* dataset_index
* dataset_index_add
2025-05-07 16:42:09 +08:00
谢昕辰
43b2c4ed76
[Fix] Update lawbench data path ( #2037 )
2025-05-07 16:18:43 +08:00
Dongsheng Zhu
d62b69aaef
[Fix] Fix InternVL model config ( #2068 )
...
* intervl-8b&38b
* intervl adjustment
* internvl fix
2025-05-07 15:51:18 +08:00
Linchen Xiao
af8432e1d6
[Update] OpenAI SDK model reasoning content ( #2078 )
...
* update
* update
* update
2025-05-07 14:06:40 +08:00
bittersweet1999
ddc9cc0afb
[Add] add a config to Judge dataset all ( #2077 )
...
* fix pip version
* fix pip version
* add judgedatasetall
* add judgedatasetall
* add judgedatasetall
2025-05-07 10:57:23 +08:00
bittersweet1999
37cbaf8d92
[Add] Add Judgerbenchv2 ( #2067 )
...
* fix pip version
* fix pip version
* add judgerbenchv2
* Update __init__.py
2025-04-30 17:12:34 +08:00
Taolin Zhang
b6148aa198
add Judgebench ( #2066 )
...
* add rewardbench
* add rewardbench
* add rmb datasets
* add rmb datasets
* add judgebench
* add judgebench
2025-04-30 15:01:10 +08:00
bittersweet1999
527a80947b
[Add] Add writingbench ( #2028 )
...
* fix pip version
* fix pip version
* add writingbench
* add writingbench
* add writingbench
* add writingbench
2025-04-29 16:29:32 +08:00
Taolin Zhang
8c74e6a39e
add RMB Bench ( #2056 )
...
* add rewardbench
* add rewardbench
* add rmb datasets
* add rmb datasets
2025-04-27 16:26:01 +08:00
Linchen Xiao
e8bc8c1e8c
[Bug] Concat OpenaiSDK reasoning content ( #2041 )
...
* [Bug] Concat OpenaiSDK reasoning content
* [Bug] Concat OpenaiSDK reasoning content
* update
* update
2025-04-25 14:10:33 +08:00
Junnan Liu
97010dc4ce
[Update] Update dataset repeat concatenation ( #2039 )
2025-04-23 16:16:28 +08:00
Linchen Xiao
dcbf899369
[Bug] Fix SmolInsturct logger import ( #2036 )
2025-04-23 11:10:30 +08:00
Linchen Xiao
bf74f26603
[Update] Safe SmolInstruct meteor calculation ( #2033 )
2025-04-22 18:27:48 +08:00
Linchen Xiao
455bb05d1b
[Update] Update dataset configs ( #2030 )
...
* [Update] Update dataset configs
* Fix lint
2025-04-21 18:55:06 +08:00
Taolin Zhang
c69110361b
[Add] add rewardbench ( #2029 )
...
* add rewardbench
* add rewardbench
2025-04-21 17:18:51 +08:00
JuchengHu
a2093a81ef
[Dataset] Matbench ( #2021 )
...
* add support for matbench
* fix dataset path
* fix data load
* fix
* fix lint
---------
Co-authored-by: Jucheng Hu <jucheng.hu.20@ucl.ac.uk>
Co-authored-by: Myhs-phz <demarcia2014@126.com>
2025-04-21 15:50:47 +08:00
Linchen Xiao
b2da1c08a8
[Dataset] Add SmolInstruct, Update Chembench ( #2025 )
...
* [Dataset] Add SmolInstruct, Update Chembench
* Add dataset metadata
* update
* update
* update
2025-04-18 17:21:29 +08:00
Linchen Xiao
65ff602cf5
[Update] Fix LLM Judge metrics cacluation & Add reasoning content concat to OpenAI SDK
2025-04-15 11:33:16 +08:00
Myhs_phz
75e7834b59
[Feature] Add Datasets: ClimateQA,Physics ( #2017 )
...
* feat ClimateQA
* feat PHYSICS
* fix
* fix
* fix
* fix
2025-04-14 20:18:47 +08:00
Linchen Xiao
6a6a1a5c0b
[Feature] LLM Judge sanity check ( #2012 )
...
* update
* update
2025-04-11 19:01:39 +08:00
bittersweet1999
3f50b1dc49
[Fix] fix order bug Update arena_hard.py ( #2015 )
2025-04-11 16:59:40 +08:00
Junnan Liu
20660ab507
[Fix] Fix compare error when k is list in base_evaluator ( #2010 )
...
* fix gpass compare error of list k
* fix compare error in 177
2025-04-10 19:47:21 +08:00
Linchen Xiao
12213207b6
[Refactor] Refactorize openicl eval task ( #1990 )
...
* [Refactor] Refactorize openicl eval task
* update
2025-04-09 15:52:23 +08:00
zhulinJulia24
6ac9b06bc2
[ci] update baseline for kernal change of vllm and lmdeploy ( #2011 )
...
* update
* update
* update
* update
* update
* update
* update
2025-04-09 14:09:35 +08:00
Linchen Xiao
a05f9da134
[Feature] Make dump-eval-details default behavior ( #1999 )
...
* Update
* update
* update
2025-04-08 14:42:26 +08:00
Myhs_phz
fd82bea747
[Fix] OpenICL Math Evaluator Config ( #2007 )
...
* fix
* fix recommended
* fix
* fix
* fix
* fix
2025-04-08 14:38:35 +08:00
Linchen Xiao
bb58cfc85d
[Feature] Add CascadeEvaluator ( #1992 )
...
* [Feature] Add CascadeEvaluator
* update
* updat
2025-04-08 11:58:14 +08:00
Jin Ye
b564e608b1
[Dataset] Add MedXpertQA ( #2002 )
...
* Add MedXpertQA
* Add MedXpertQA
* Add MedXpertQA
* Fix lint
---------
Co-authored-by: MaiziXiao <xxllcc1993@gmail.com>
2025-04-08 10:44:48 +08:00
shijinpjlab
828fb745c9
[Dataset] Update dingo 1.5.0 ( #2008 )
...
Co-authored-by: shiin <shijin@pjlab.org.cn>
2025-04-07 17:21:15 +08:00
zhulinJulia24
f982d6278e
[CI] fix baseline score ( #2000 )
...
* update
* update
* update
* update
* update
* update
* update
* updaste
* update
* update
* updaste
* updaste
* update
* update
* update
* update
* update
* update
* update
* update
2025-04-03 19:32:36 +08:00
Myhs_phz
3a9a384173
[Doc] Fix links between zh & en ( #2001 )
...
* test
* test
* test
2025-04-03 17:37:53 +08:00
Myhs_phz
9b489e9ea0
[Update] Revert math500 dataset configs ( #1998 )
2025-04-03 15:11:02 +08:00
