yairfeldman/LongBench

---
dataset_info:
- config_name: 2wikimqa
features:
- name: input
dtype: string
- name: context
dtype: string
- name: answers
list: string
- name: length
dtype: int32
- name: dataset
dtype: string
- name: language
dtype: string
- name: all_classes
list: string
- name: _id
dtype: string
splits:
- name: test
num_bytes: 5982997
num_examples: 200
download_size: 3591563
dataset_size: 5982997
- config_name: 2wikimqa_e
features:
- name: input
dtype: string
- name: context
dtype: string
- name: answers
list: string
- name: length
dtype: int32
- name: dataset
dtype: string
- name: language
dtype: string
- name: all_classes
list: string
- name: _id
dtype: string
splits:
- name: test
num_bytes: 11331920
num_examples: 300
download_size: 6771925
dataset_size: 11331920
- config_name: dureader
features:
- name: input
dtype: string
- name: context
dtype: string
- name: answers
list: string
- name: length
dtype: int32
- name: dataset
dtype: string
- name: language
dtype: string
- name: all_classes
list: string
- name: _id
dtype: string
splits:
- name: test
num_bytes: 8212951
num_examples: 200
download_size: 5166709
dataset_size: 8212951
- config_name: gov_report
features:
- name: input
dtype: string
- name: context
dtype: string
- name: answers
list: string
- name: length
dtype: int32
- name: dataset
dtype: string
- name: language
dtype: string
- name: all_classes
list: string
- name: _id
dtype: string
splits:
- name: test
num_bytes: 11593569
num_examples: 200
download_size: 5487820
dataset_size: 11593569
- config_name: gov_report_e
features:
- name: input
dtype: string
- name: context
dtype: string
- name: answers
list: string
- name: length
dtype: int32
- name: dataset
dtype: string
- name: language
dtype: string
- name: all_classes
list: string
- name: _id
dtype: string
splits:
- name: test
num_bytes: 14263436
num_examples: 300
download_size: 6648402
dataset_size: 14263436
- config_name: hotpotqa
features:
- name: input
dtype: string
- name: context
dtype: string
- name: answers
list: string
- name: length
dtype: int32
- name: dataset
dtype: string
- name: language
dtype: string
- name: all_classes
list: string
- name: _id
dtype: string
splits:
- name: test
num_bytes: 11379153
num_examples: 200
download_size: 6614840
dataset_size: 11379153
- config_name: hotpotqa_e
features:
- name: input
dtype: string
- name: context
dtype: string
- name: answers
list: string
- name: length
dtype: int32
- name: dataset
dtype: string
- name: language
dtype: string
- name: all_classes
list: string
- name: _id
dtype: string
splits:
- name: test
num_bytes: 12324268
num_examples: 300
download_size: 7186128
dataset_size: 12324268
- config_name: lcc
features:
- name: input
dtype: string
- name: context
dtype: string
- name: answers
list: string
- name: length
dtype: int32
- name: dataset
dtype: string
- name: language
dtype: string
- name: all_classes
list: string
- name: _id
dtype: string
splits:
- name: test
num_bytes: 6878988
num_examples: 500
download_size: 2347508
dataset_size: 6878988
- config_name: lcc_e
features:
- name: input
dtype: string
- name: context
dtype: string
- name: answers
list: string
- name: length
dtype: int32
- name: dataset
dtype: string
- name: language
dtype: string
- name: all_classes
list: string
- name: _id
dtype: string
splits:
- name: test
num_bytes: 17755543
num_examples: 300
download_size: 5529519
dataset_size: 17755543
- config_name: lsht
features:
- name: input
dtype: string
- name: context
dtype: string
- name: answers
list: string
- name: length
dtype: int32
- name: dataset
dtype: string
- name: language
dtype: string
- name: all_classes
list: string
- name: _id
dtype: string
splits:
- name: test
num_bytes: 13005634
num_examples: 200
download_size: 8133978
dataset_size: 13005634
- config_name: multi_news
features:
- name: input
dtype: string
- name: context
dtype: string
- name: answers
list: string
- name: length
dtype: int32
- name: dataset
dtype: string
- name: language
dtype: string
- name: all_classes
list: string
- name: _id
dtype: string
splits:
- name: test
num_bytes: 2715969
num_examples: 200
download_size: 1493405
dataset_size: 2715969
- config_name: multi_news_e
features:
- name: input
dtype: string
- name: context
dtype: string
- name: answers
list: string
- name: length
dtype: int32
- name: dataset
dtype: string
- name: language
dtype: string
- name: all_classes
list: string
- name: _id
dtype: string
splits:
- name: test
num_bytes: 11308405
num_examples: 294
download_size: 5814632
dataset_size: 11308405
- config_name: multifieldqa_en
features:
- name: input
dtype: string
- name: context
dtype: string
- name: answers
list: string
- name: length
dtype: int32
- name: dataset
dtype: string
- name: language
dtype: string
- name: all_classes
list: string
- name: _id
dtype: string
splits:
- name: test
num_bytes: 4427988
num_examples: 150
download_size: 1843920
dataset_size: 4427988
- config_name: multifieldqa_en_e
features:
- name: input
dtype: string
- name: context
dtype: string
- name: answers
list: string
- name: length
dtype: int32
- name: dataset
dtype: string
- name: language
dtype: string
- name: all_classes
list: string
- name: _id
dtype: string
splits:
- name: test
num_bytes: 4428288
num_examples: 150
download_size: 1824404
dataset_size: 4428288
- config_name: multifieldqa_zh
features:
- name: input
dtype: string
- name: context
dtype: string
- name: answers
list: string
- name: length
dtype: int32
- name: dataset
dtype: string
- name: language
dtype: string
- name: all_classes
list: string
- name: _id
dtype: string
splits:
- name: test
num_bytes: 3541307
num_examples: 200
download_size: 1446334
dataset_size: 3541307
- config_name: musique
features:
- name: input
dtype: string
- name: context
dtype: string
- name: answers
list: string
- name: length
dtype: int32
- name: dataset
dtype: string
- name: language
dtype: string
- name: all_classes
list: string
- name: _id
dtype: string
splits:
- name: test
num_bytes: 13965034
num_examples: 200
download_size: 8117368
dataset_size: 13965034
- config_name: narrativeqa
features:
- name: input
dtype: string
- name: context
dtype: string
- name: answers
list: string
- name: length
dtype: int32
- name: dataset
dtype: string
- name: language
dtype: string
- name: all_classes
list: string
- name: _id
dtype: string
splits:
- name: test
num_bytes: 21682299
num_examples: 200
download_size: 1305048
dataset_size: 21682299
- config_name: passage_count
features:
- name: input
dtype: string
- name: context
dtype: string
- name: answers
list: string
- name: length
dtype: int32
- name: dataset
dtype: string
- name: language
dtype: string
- name: all_classes
list: string
- name: _id
dtype: string
splits:
- name: test
num_bytes: 13417957
num_examples: 200
download_size: 4947655
dataset_size: 13417957
- config_name: passage_count_e
features:
- name: input
dtype: string
- name: context
dtype: string
- name: answers
list: string
- name: length
dtype: int32
- name: dataset
dtype: string
- name: language
dtype: string
- name: all_classes
list: string
- name: _id
dtype: string
splits:
- name: test
num_bytes: 11123592
num_examples: 300
download_size: 3863689
dataset_size: 11123592
- config_name: passage_retrieval_en
features:
- name: input
dtype: string
- name: context
dtype: string
- name: answers
list: string
- name: length
dtype: int32
- name: dataset
dtype: string
- name: language
dtype: string
- name: all_classes
list: string
- name: _id
dtype: string
splits:
- name: test
num_bytes: 11234534
num_examples: 200
download_size: 7029732
dataset_size: 11234534
- config_name: passage_retrieval_en_e
features:
- name: input
dtype: string
- name: context
dtype: string
- name: answers
list: string
- name: length
dtype: int32
- name: dataset
dtype: string
- name: language
dtype: string
- name: all_classes
list: string
- name: _id
dtype: string
splits:
- name: test
num_bytes: 11108473
num_examples: 300
download_size: 6949875
dataset_size: 11108473
- config_name: passage_retrieval_zh
features:
- name: input
dtype: string
- name: context
dtype: string
- name: answers
list: string
- name: length
dtype: int32
- name: dataset
dtype: string
- name: language
dtype: string
- name: all_classes
list: string
- name: _id
dtype: string
splits:
- name: test
num_bytes: 3660028
num_examples: 200
download_size: 2683136
dataset_size: 3660028
- config_name: qasper
features:
- name: input
dtype: string
- name: context
dtype: string
- name: answers
list: string
- name: length
dtype: int32
- name: dataset
dtype: string
- name: language
dtype: string
- name: all_classes
list: string
- name: _id
dtype: string
splits:
- name: test
num_bytes: 4792612
num_examples: 200
download_size: 1862944
dataset_size: 4792612
- config_name: qasper_e
features:
- name: input
dtype: string
- name: context
dtype: string
- name: answers
list: string
- name: length
dtype: int32
- name: dataset
dtype: string
- name: language
dtype: string
- name: all_classes
list: string
- name: _id
dtype: string
splits:
- name: test
num_bytes: 6856180
num_examples: 224
download_size: 2006263
dataset_size: 6856180
- config_name: qmsum
features:
- name: input
dtype: string
- name: context
dtype: string
- name: answers
list: string
- name: length
dtype: int32
- name: dataset
dtype: string
- name: language
dtype: string
- name: all_classes
list: string
- name: _id
dtype: string
splits:
- name: test
num_bytes: 11619927
num_examples: 200
download_size: 967967
dataset_size: 11619927
- config_name: repobench-p
features:
- name: input
dtype: string
- name: context
dtype: string
- name: answers
list: string
- name: length
dtype: int32
- name: dataset
dtype: string
- name: language
dtype: string
- name: all_classes
list: string
- name: _id
dtype: string
splits:
- name: test
num_bytes: 24155458
num_examples: 500
download_size: 7756772
dataset_size: 24155458
- config_name: repobench-p_e
features:
- name: input
dtype: string
- name: context
dtype: string
- name: answers
list: string
- name: length
dtype: int32
- name: dataset
dtype: string
- name: language
dtype: string
- name: all_classes
list: string
- name: _id
dtype: string
splits:
- name: test
num_bytes: 20378217
num_examples: 300
download_size: 6628585
dataset_size: 20378217
- config_name: samsum
features:
- name: input
dtype: string
- name: context
dtype: string
- name: answers
list: string
- name: length
dtype: int32
- name: dataset
dtype: string
- name: language
dtype: string
- name: all_classes
list: string
- name: _id
dtype: string
splits:
- name: test
num_bytes: 6968716
num_examples: 200
download_size: 4106644
dataset_size: 6968716
- config_name: samsum_e
features:
- name: input
dtype: string
- name: context
dtype: string
- name: answers
list: string
- name: length
dtype: int32
- name: dataset
dtype: string
- name: language
dtype: string
- name: all_classes
list: string
- name: _id
dtype: string
splits:
- name: test
num_bytes: 10304915
num_examples: 300
download_size: 6075508
dataset_size: 10304915
- config_name: trec
features:
- name: input
dtype: string
- name: context
dtype: string
- name: answers
list: string
- name: length
dtype: int32
- name: dataset
dtype: string
- name: language
dtype: string
- name: all_classes
list: string
- name: _id
dtype: string
splits:
- name: test
num_bytes: 6200475
num_examples: 200
download_size: 2664309
dataset_size: 6200475
- config_name: trec_e
features:
- name: input
dtype: string
- name: context
dtype: string
- name: answers
list: string
- name: length
dtype: int32
- name: dataset
dtype: string
- name: language
dtype: string
- name: all_classes
list: string
- name: _id
dtype: string
splits:
- name: test
num_bytes: 11182248
num_examples: 300
download_size: 4844048
dataset_size: 11182248
- config_name: triviaqa
features:
- name: input
dtype: string
- name: context
dtype: string
- name: answers
list: string
- name: length
dtype: int32
- name: dataset
dtype: string
- name: language
dtype: string
- name: all_classes
list: string
- name: _id
dtype: string
splits:
- name: test
num_bytes: 10153425
num_examples: 200
download_size: 6282566
dataset_size: 10153425
- config_name: triviaqa_e
features:
- name: input
dtype: string
- name: context
dtype: string
- name: answers
list: string
- name: length
dtype: int32
- name: dataset
dtype: string
- name: language
dtype: string
- name: all_classes
list: string
- name: _id
dtype: string
splits:
- name: test
num_bytes: 12465195
num_examples: 300
download_size: 7533135
dataset_size: 12465195
- config_name: vcsum
features:
- name: input
dtype: string
- name: context
dtype: string
- name: answers
list: string
- name: length
dtype: int32
- name: dataset
dtype: string
- name: language
dtype: string
- name: all_classes
list: string
- name: _id
dtype: string
splits:
- name: test
num_bytes: 8890955
num_examples: 200
download_size: 5135993
dataset_size: 8890955
configs:
- config_name: 2wikimqa
data_files:
- split: test
path: 2wikimqa/test-*
- config_name: 2wikimqa_e
data_files:
- split: test
path: 2wikimqa_e/test-*
- config_name: dureader
data_files:
- split: test
path: dureader/test-*
- config_name: gov_report
data_files:
- split: test
path: gov_report/test-*
- config_name: gov_report_e
data_files:
- split: test
path: gov_report_e/test-*
- config_name: hotpotqa
data_files:
- split: test
path: hotpotqa/test-*
- config_name: hotpotqa_e
data_files:
- split: test
path: hotpotqa_e/test-*
- config_name: lcc
data_files:
- split: test
path: lcc/test-*
- config_name: lcc_e
data_files:
- split: test
path: lcc_e/test-*
- config_name: lsht
data_files:
- split: test
path: lsht/test-*
- config_name: multi_news
data_files:
- split: test
path: multi_news/test-*
- config_name: multi_news_e
data_files:
- split: test
path: multi_news_e/test-*
- config_name: multifieldqa_en
data_files:
- split: test
path: multifieldqa_en/test-*
- config_name: multifieldqa_en_e
data_files:
- split: test
path: multifieldqa_en_e/test-*
- config_name: multifieldqa_zh
data_files:
- split: test
path: multifieldqa_zh/test-*
- config_name: musique
data_files:
- split: test
path: musique/test-*
- config_name: narrativeqa
data_files:
- split: test
path: narrativeqa/test-*
- config_name: passage_count
data_files:
- split: test
path: passage_count/test-*
- config_name: passage_count_e
data_files:
- split: test
path: passage_count_e/test-*
- config_name: passage_retrieval_en
data_files:
- split: test
path: passage_retrieval_en/test-*
- config_name: passage_retrieval_en_e
data_files:
- split: test
path: passage_retrieval_en_e/test-*
- config_name: passage_retrieval_zh
data_files:
- split: test
path: passage_retrieval_zh/test-*
- config_name: qasper
data_files:
- split: test
path: qasper/test-*
- config_name: qasper_e
data_files:
- split: test
path: qasper_e/test-*
- config_name: qmsum
data_files:
- split: test
path: qmsum/test-*
- config_name: repobench-p
data_files:
- split: test
path: repobench-p/test-*
- config_name: repobench-p_e
data_files:
- split: test
path: repobench-p_e/test-*
- config_name: samsum
data_files:
- split: test
path: samsum/test-*
- config_name: samsum_e
data_files:
- split: test
path: samsum_e/test-*
- config_name: trec
data_files:
- split: test
path: trec/test-*
- config_name: trec_e
data_files:
- split: test
path: trec_e/test-*
- config_name: triviaqa
data_files:
- split: test
path: triviaqa/test-*
- config_name: triviaqa_e
data_files:
- split: test
path: triviaqa_e/test-*
- config_name: vcsum
data_files:
- split: test
path: vcsum/test-*
---