mteb/sib200.v2

---
dataset_info:
- config_name: ace_Latn
features:
- name: text
dtype: string
- name: label
dtype: int64
splits:
- name: train
num_bytes: 10453.0
num_examples: 70
- name: validation
num_bytes: 22387.0
num_examples: 139
- name: test
num_bytes: 185646.0
num_examples: 1225
download_size: 143601
dataset_size: 218486.0
- config_name: acm_Arab
features:
- name: text
dtype: string
- name: label
dtype: int64
splits:
- name: train
num_bytes: 15468.0
num_examples: 70
- name: validation
num_bytes: 31142.0
num_examples: 139
- name: test
num_bytes: 262763.0
num_examples: 1225
download_size: 171481
dataset_size: 309373.0
- config_name: acq_Arab
features:
- name: text
dtype: string
- name: label
dtype: int64
splits:
- name: train
num_bytes: 15638.0
num_examples: 70
- name: validation
num_bytes: 31548.0
num_examples: 139
- name: test
num_bytes: 265364.0
num_examples: 1225
download_size: 173694
dataset_size: 312550.0
- config_name: aeb_Arab
features:
- name: text
dtype: string
- name: label
dtype: int64
splits:
- name: train
num_bytes: 15150.0
num_examples: 70
- name: validation
num_bytes: 31226.0
num_examples: 139
- name: test
num_bytes: 258647.0
num_examples: 1225
download_size: 171007
dataset_size: 305023.0
- config_name: afr_Latn
features:
- name: text
dtype: string
- name: label
dtype: int64
splits:
- name: train
num_bytes: 10686.0
num_examples: 70
- name: validation
num_bytes: 22352.0
num_examples: 139
- name: test
num_bytes: 182477.0
num_examples: 1225
download_size: 144631
dataset_size: 215515.0
- config_name: ajp_Arab
features:
- name: text
dtype: string
- name: label
dtype: int64
splits:
- name: train
num_bytes: 14672.0
num_examples: 70
- name: validation
num_bytes: 30121.0
num_examples: 139
- name: test
num_bytes: 249781.0
num_examples: 1225
download_size: 164371
dataset_size: 294574.0
- config_name: aka_Latn
features:
- name: text
dtype: string
- name: label
dtype: int64
splits:
- name: train
num_bytes: 10707.0
num_examples: 70
- name: validation
num_bytes: 22874.0
num_examples: 139
- name: test
num_bytes: 189034.0
num_examples: 1225
download_size: 142988
dataset_size: 222615.0
- config_name: als_Latn
features:
- name: text
dtype: string
- name: label
dtype: int64
splits:
- name: train
num_bytes: 11626.0
num_examples: 70
- name: validation
num_bytes: 24784.0
num_examples: 139
- name: test
num_bytes: 204828.0
num_examples: 1225
download_size: 156564
dataset_size: 241238.0
- config_name: amh_Ethi
features:
- name: text
dtype: string
- name: label
dtype: int64
splits:
- name: train
num_bytes: 16468.0
num_examples: 70
- name: validation
num_bytes: 33977.0
num_examples: 139
- name: test
num_bytes: 287586.0
num_examples: 1225
download_size: 185850
dataset_size: 338031.0
- config_name: apc_Arab
features:
- name: text
dtype: string
- name: label
dtype: int64
splits:
- name: train
num_bytes: 14815.0
num_examples: 70
- name: validation
num_bytes: 29933.0
num_examples: 139
- name: test
num_bytes: 249456.0
num_examples: 1225
download_size: 162289
dataset_size: 294204.0
- config_name: arb_Latn
features:
- name: text
dtype: string
- name: label
dtype: int64
splits:
- name: train
num_bytes: 11507.0
num_examples: 70
- name: validation
num_bytes: 23844.0
num_examples: 139
- name: test
num_bytes: 197744.62367346938
num_examples: 1223
download_size: 165027
dataset_size: 233095.62367346938
- config_name: ars_Arab
features:
- name: text
dtype: string
- name: label
dtype: int64
splits:
- name: train
num_bytes: 15772.0
num_examples: 70
- name: validation
num_bytes: 31868.0
num_examples: 139
- name: test
num_bytes: 268483.0
num_examples: 1225
download_size: 176066
dataset_size: 316123.0
- config_name: ary_Arab
features:
- name: text
dtype: string
- name: label
dtype: int64
splits:
- name: train
num_bytes: 15119.0
num_examples: 70
- name: validation
num_bytes: 31534.0
num_examples: 139
- name: test
num_bytes: 261538.30040816325
num_examples: 1223
download_size: 170776
dataset_size: 308191.3004081632
- config_name: arz_Arab
features:
- name: text
dtype: string
- name: label
dtype: int64
splits:
- name: train
num_bytes: 15605.0
num_examples: 70
- name: validation
num_bytes: 31246.0
num_examples: 139
- name: test
num_bytes: 261238.0
num_examples: 1225
download_size: 168487
dataset_size: 308089.0
- config_name: asm_Beng
features:
- name: text
dtype: string
- name: label
dtype: int64
splits:
- name: train
num_bytes: 24348.0
num_examples: 70
- name: validation
num_bytes: 49799.0
num_examples: 139
- name: test
num_bytes: 415437.0
num_examples: 1225
download_size: 219383
dataset_size: 489584.0
- config_name: ast_Latn
features:
- name: text
dtype: string
- name: label
dtype: int64
splits:
- name: train
num_bytes: 10180.0
num_examples: 70
- name: validation
num_bytes: 21785.0
num_examples: 139
- name: test
num_bytes: 182128.0
num_examples: 1225
download_size: 147145
dataset_size: 214093.0
- config_name: awa_Deva
features:
- name: text
dtype: string
- name: label
dtype: int64
splits:
- name: train
num_bytes: 23310.0
num_examples: 70
- name: validation
num_bytes: 49396.0
num_examples: 139
- name: test
num_bytes: 411104.0
num_examples: 1225
download_size: 209857
dataset_size: 483810.0
- config_name: ayr_Latn
features:
- name: text
dtype: string
- name: label
dtype: int64
splits:
- name: train
num_bytes: 10113.0
num_examples: 70
- name: validation
num_bytes: 21812.0
num_examples: 139
- name: test
num_bytes: 184312.0
num_examples: 1225
download_size: 141598
dataset_size: 216237.0
- config_name: azb_Arab
features:
- name: text
dtype: string
- name: label
dtype: int64
splits:
- name: train
num_bytes: 11737.985714285714
num_examples: 53
- name: validation
num_bytes: 27540.40287769784
num_examples: 116
- name: test
num_bytes: 233870.12408163265
num_examples: 1054
download_size: 152029
dataset_size: 273148.5126736162
- config_name: azj_Latn
features:
- name: text
dtype: string
- name: label
dtype: int64
splits:
- name: train
num_bytes: 12118.0
num_examples: 70
- name: validation
num_bytes: 25446.0
num_examples: 139
- name: test
num_bytes: 214322.0
num_examples: 1225
download_size: 160880
dataset_size: 251886.0
- config_name: bak_Cyrl
features:
- name: text
dtype: string
- name: label
dtype: int64
splits:
- name: train
num_bytes: 17964.0
num_examples: 70
- name: validation
num_bytes: 37919.0
num_examples: 139
- name: test
num_bytes: 307310.0
num_examples: 1225
download_size: 194733
dataset_size: 363193.0
- config_name: bam_Latn
features:
- name: text
dtype: string
- name: label
dtype: int64
splits:
- name: train
num_bytes: 10318.0
num_examples: 70
- name: validation
num_bytes: 20891.0
num_examples: 139
- name: test
num_bytes: 179621.2612244898
num_examples: 1223
download_size: 138768
dataset_size: 210830.2612244898
- config_name: ban_Latn
features:
- name: text
dtype: string
- name: label
dtype: int64
splits:
- name: train
num_bytes: 10614.0
num_examples: 70
- name: validation
num_bytes: 22617.0
num_examples: 139
- name: test
num_bytes: 189633.07102040816
num_examples: 1224
download_size: 142738
dataset_size: 222864.07102040816
- config_name: bel_Cyrl
features:
- name: text
dtype: string
- name: label
dtype: int64
splits:
- name: train
num_bytes: 19892.0
num_examples: 70
- name: validation
num_bytes: 41655.0
num_examples: 139
- name: test
num_bytes: 341032.0
num_examples: 1225
download_size: 219275
dataset_size: 402579.0
- config_name: bem_Latn
features:
- name: text
dtype: string
- name: label
dtype: int64
splits:
- name: train
num_bytes: 11849.0
num_examples: 70
- name: validation
num_bytes: 24988.0
num_examples: 139
- name: test
num_bytes: 208603.0
num_examples: 1225
download_size: 155580
dataset_size: 245440.0
- config_name: ben_Beng
features:
- name: text
dtype: string
- name: label
dtype: int64
splits:
- name: train
num_bytes: 24476.0
num_examples: 70
- name: validation
num_bytes: 51394.0
num_examples: 139
- name: test
num_bytes: 426549.0
num_examples: 1225
download_size: 218953
dataset_size: 502419.0
- config_name: bho_Deva
features:
- name: text
dtype: string
- name: label
dtype: int64
splits:
- name: train
num_bytes: 23026.0
num_examples: 70
- name: validation
num_bytes: 49922.0
num_examples: 139
- name: test
num_bytes: 405716.0
num_examples: 1225
download_size: 208388
dataset_size: 478664.0
- config_name: bjn_Latn
features:
- name: text
dtype: string
- name: label
dtype: int64
splits:
- name: train
num_bytes: 10266.0
num_examples: 70
- name: validation
num_bytes: 21911.0
num_examples: 139
- name: test
num_bytes: 179001.0
num_examples: 1225
download_size: 137505
dataset_size: 211178.0
- config_name: bod_Tibt
features:
- name: text
dtype: string
- name: label
dtype: int64
splits:
- name: train
num_bytes: 6172.8
num_examples: 14
- name: validation
num_bytes: 17662.575539568345
num_examples: 37
- name: test
num_bytes: 108847.09877551021
num_examples: 248
download_size: 65588
dataset_size: 132682.47431507855
- config_name: bos_Latn
features:
- name: text
dtype: string
- name: label
dtype: int64
splits:
- name: train
num_bytes: 10385.0
num_examples: 70
- name: validation
num_bytes: 21252.0
num_examples: 138
- name: test
num_bytes: 177211.0
num_examples: 1225
download_size: 151480
dataset_size: 208848.0
- config_name: bug_Latn
features:
- name: text
dtype: string
- name: label
dtype: int64
splits:
- name: train
num_bytes: 10661.0
num_examples: 70
- name: validation
num_bytes: 22597.0
num_examples: 139
- name: test
num_bytes: 187468.83918367347
num_examples: 1224
download_size: 151869
dataset_size: 220726.83918367347
- config_name: bul_Cyrl
features:
- name: text
dtype: string
- name: label
dtype: int64
splits:
- name: train
num_bytes: 18004.0
num_examples: 70
- name: validation
num_bytes: 38099.0
num_examples: 139
- name: test
num_bytes: 312752.0
num_examples: 1225
download_size: 194001
dataset_size: 368855.0
- config_name: cat_Latn
features:
- name: text
dtype: string
- name: label
dtype: int64
splits:
- name: train
num_bytes: 11115.0
num_examples: 70
- name: validation
num_bytes: 23078.0
num_examples: 139
- name: test
num_bytes: 191564.0
num_examples: 1225
download_size: 153794
dataset_size: 225757.0
- config_name: ceb_Latn
features:
- name: text
dtype: string
- name: label
dtype: int64
splits:
- name: train
num_bytes: 11663.0
num_examples: 70
- name: validation
num_bytes: 24391.0
num_examples: 139
- name: test
num_bytes: 203779.0
num_examples: 1225
download_size: 149861
dataset_size: 239833.0
- config_name: ces_Latn
features:
- name: text
dtype: string
- name: label
dtype: int64
splits:
- name: train
num_bytes: 10548.0
num_examples: 70
- name: validation
num_bytes: 22335.0
num_examples: 139
- name: test
num_bytes: 185086.0
num_examples: 1225
download_size: 157595
dataset_size: 217969.0
- config_name: cjk_Latn
features:
- name: text
dtype: string
- name: label
dtype: int64
splits:
- name: train
num_bytes: 10771.0
num_examples: 70
- name: validation
num_bytes: 22144.0
num_examples: 139
- name: test
num_bytes: 184318.0
num_examples: 1225
download_size: 147980
dataset_size: 217233.0
- config_name: ckb_Arab
features:
- name: text
dtype: string
- name: label
dtype: int64
splits:
- name: train
num_bytes: 16745.0
num_examples: 70
- name: validation
num_bytes: 36213.0
num_examples: 139
- name: test
num_bytes: 295205.0
num_examples: 1225
download_size: 178877
dataset_size: 348163.0
- config_name: crh_Latn
features:
- name: text
dtype: string
- name: label
dtype: int64
splits:
- name: train
num_bytes: 10971.0
num_examples: 70
- name: validation
num_bytes: 22976.5035971223
num_examples: 138
- name: test
num_bytes: 190762.14857142858
num_examples: 1224
download_size: 150715
dataset_size: 224709.65216855088
- config_name: cym_Latn
features:
- name: text
dtype: string
- name: label
dtype: int64
splits:
- name: train
num_bytes: 10449.0
num_examples: 70
- name: validation
num_bytes: 21839.0
num_examples: 139
- name: test
num_bytes: 182936.0
num_examples: 1225
download_size: 145614
dataset_size: 215224.0
- config_name: dan_Latn
features:
- name: text
dtype: string
- name: label
dtype: int64
splits:
- name: train
num_bytes: 10310.0
num_examples: 70
- name: validation
num_bytes: 21563.0
num_examples: 139
- name: test
num_bytes: 178691.0
num_examples: 1225
download_size: 143477
dataset_size: 210564.0
- config_name: deu_Latn
features:
- name: text
dtype: string
- name: label
dtype: int64
splits:
- name: train
num_bytes: 11447.0
num_examples: 70
- name: validation
num_bytes: 24509.0
num_examples: 139
- name: test
num_bytes: 200342.0
num_examples: 1225
download_size: 160155
dataset_size: 236298.0
- config_name: dik_Latn
features:
- name: text
dtype: string
- name: label
dtype: int64
splits:
- name: train
num_bytes: 10282.0
num_examples: 70
- name: validation
num_bytes: 20433.928057553956
num_examples: 138
- name: test
num_bytes: 167637.04163265307
num_examples: 1224
download_size: 133643
dataset_size: 198352.969690207
- config_name: dyu_Latn
features:
- name: text
dtype: string
- name: label
dtype: int64
splits:
- name: train
num_bytes: 10908.0
num_examples: 70
- name: validation
num_bytes: 21655.0
num_examples: 139
- name: test
num_bytes: 183526.8742857143
num_examples: 1223
download_size: 150150
dataset_size: 216089.8742857143
- config_name: dzo_Tibt
features:
- name: text
dtype: string
- name: label
dtype: int64
splits:
- name: train
num_bytes: 33004.28571428572
num_examples: 68
- name: validation
num_bytes: 69728.71942446043
num_examples: 138
- name: test
num_bytes: 580810.3640816327
num_examples: 1203
download_size: 238599
dataset_size: 683543.3692203788
- config_name: ell_Grek
features:
- name: text
dtype: string
- name: label
dtype: int64
splits:
- name: train
num_bytes: 20962.0
num_examples: 70
- name: validation
num_bytes: 43213.0
num_examples: 139
- name: test
num_bytes: 357098.0
num_examples: 1225
download_size: 226422
dataset_size: 421273.0
- config_name: eng_Latn
features:
- name: text
dtype: string
- name: label
dtype: int64
splits:
- name: train
num_bytes: 9930.0
num_examples: 70
- name: validation
num_bytes: 20729.0
num_examples: 139
- name: test
num_bytes: 171234.0
num_examples: 1225
download_size: 136991
dataset_size: 201893.0
- config_name: epo_Latn
features:
- name: text
dtype: string
- name: label
dtype: int64
splits:
- name: train
num_bytes: 10193.0
num_examples: 70
- name: validation
num_bytes: 21140.0
num_examples: 139
- name: test
num_bytes: 174031.0
num_examples: 1225
download_size: 140592
dataset_size: 205364.0
- config_name: est_Latn
features:
- name: text
dtype: string
- name: label
dtype: int64
splits:
- name: train
num_bytes: 9901.0
num_examples: 70
- name: validation
num_bytes: 20892.0
num_examples: 139
- name: test
num_bytes: 173631.0
num_examples: 1225
download_size: 145526
dataset_size: 204424.0
- config_name: eus_Latn
features:
- name: text
dtype: string
- name: label
dtype: int64
splits:
- name: train
num_bytes: 10442.0
num_examples: 70
- name: validation
num_bytes: 21794.0
num_examples: 139
- name: test
num_bytes: 183312.0
num_examples: 1225
download_size: 143642
dataset_size: 215548.0
- config_name: ewe_Latn
features:
- name: text
dtype: string
- name: label
dtype: int64
splits:
- name: train
num_bytes: 9962.0
num_examples: 70
- name: validation
num_bytes: 22199.0
num_examples: 139
- name: test
num_bytes: 183838.0
num_examples: 1225
download_size: 135538
dataset_size: 215999.0
- config_name: fao_Latn
features:
- name: text
dtype: string
- name: label
dtype: int64
splits:
- name: train
num_bytes: 10585.0
num_examples: 70
- name: validation
num_bytes: 22470.172661870503
num_examples: 138
- name: test
num_bytes: 186668.4930612245
num_examples: 1224
download_size: 147806
dataset_size: 219723.665723095
- config_name: fij_Latn
features:
- name: text
dtype: string
- name: label
dtype: int64
splits:
- name: train
num_bytes: 11224.0
num_examples: 70
- name: validation
num_bytes: 24141.0
num_examples: 139
- name: test
num_bytes: 200544.0
num_examples: 1225
download_size: 137216
dataset_size: 235909.0
- config_name: fin_Latn
features:
- name: text
dtype: string
- name: label
dtype: int64
splits:
- name: train
num_bytes: 10635.0
num_examples: 70
- name: validation
num_bytes: 22659.0
num_examples: 139
- name: test
num_bytes: 188781.0
num_examples: 1225
download_size: 156463
dataset_size: 222075.0
- config_name: fon_Latn
features:
- name: text
dtype: string
- name: label
dtype: int64
splits:
- name: train
num_bytes: 12330.0
num_examples: 70
- name: validation
num_bytes: 26267.0
num_examples: 139
- name: test
num_bytes: 214922.0
num_examples: 1225
download_size: 163329
dataset_size: 253519.0
- config_name: fra_Latn
features:
- name: text
dtype: string
- name: label
dtype: int64
splits:
- name: train
num_bytes: 12020.0
num_examples: 70
- name: validation
num_bytes: 25545.0
num_examples: 139
- name: test
num_bytes: 209260.0
num_examples: 1225
download_size: 165772
dataset_size: 246825.0
- config_name: fur_Latn
features:
- name: text
dtype: string
- name: label
dtype: int64
splits:
- name: train
num_bytes: 11208.0
num_examples: 70
- name: validation
num_bytes: 23187.0
num_examples: 139
- name: test
num_bytes: 193250.0
num_examples: 1225
download_size: 151551
dataset_size: 227645.0
- config_name: fuv_Latn
features:
- name: text
dtype: string
- name: label
dtype: int64
splits:
- name: train
num_bytes: 9573.0
num_examples: 70
- name: validation
num_bytes: 19968.0
num_examples: 139
- name: test
num_bytes: 165597.0
num_examples: 1225
download_size: 134203
dataset_size: 195138.0
- config_name: gaz_Latn
features:
- name: text
dtype: string
- name: label
dtype: int64
splits:
- name: train
num_bytes: 11777.0
num_examples: 70
- name: validation
num_bytes: 24664.0
num_examples: 139
- name: test
num_bytes: 203851.0
num_examples: 1225
download_size: 155131
dataset_size: 240292.0
- config_name: gla_Latn
features:
- name: text
dtype: string
- name: label
dtype: int64
splits:
- name: train
num_bytes: 12332.0
num_examples: 70
- name: validation
num_bytes: 26393.0
num_examples: 139
- name: test
num_bytes: 217166.0
num_examples: 1225
download_size: 160806
dataset_size: 255891.0
- config_name: gle_Latn
features:
- name: text
dtype: string
- name: label
dtype: int64
splits:
- name: train
num_bytes: 11749.0
num_examples: 70
- name: validation
num_bytes: 25419.0
num_examples: 139
- name: test
num_bytes: 207783.0
num_examples: 1225
download_size: 161086
dataset_size: 244951.0
- config_name: glg_Latn
features:
- name: text
dtype: string
- name: label
dtype: int64
splits:
- name: train
num_bytes: 10989.0
num_examples: 70
- name: validation
num_bytes: 23321.0
num_examples: 139
- name: test
num_bytes: 193196.0
num_examples: 1225
download_size: 152484
dataset_size: 227506.0
- config_name: grn_Latn
features:
- name: text
dtype: string
- name: label
dtype: int64
splits:
- name: train
num_bytes: 10729.0
num_examples: 70
- name: validation
num_bytes: 22070.0
num_examples: 139
- name: test
num_bytes: 185011.84653061224
num_examples: 1224
download_size: 142324
dataset_size: 217810.84653061224
- config_name: guj_Gujr
features:
- name: text
dtype: string
- name: label
dtype: int64
splits:
- name: train
num_bytes: 23131.0
num_examples: 70
- name: validation
num_bytes: 49503.0
num_examples: 139
- name: test
num_bytes: 410138.0
num_examples: 1225
download_size: 214760
dataset_size: 482772.0
- config_name: hat_Latn
features:
- name: text
dtype: string
- name: label
dtype: int64
splits:
- name: train
num_bytes: 9446.0
num_examples: 70
- name: validation
num_bytes: 19675.424460431655
num_examples: 138
- name: test
num_bytes: 163751.21387755102
num_examples: 1223
download_size: 129538
dataset_size: 192872.63833798267
- config_name: hau_Latn
features:
- name: text
dtype: string
- name: label
dtype: int64
splits:
- name: train
num_bytes: 10815.0
num_examples: 70
- name: validation
num_bytes: 21980.0
num_examples: 139
- name: test
num_bytes: 185353.0
num_examples: 1225
download_size: 141310
dataset_size: 218148.0
- config_name: heb_Hebr
features:
- name: text
dtype: string
- name: label
dtype: int64
splits:
- name: train
num_bytes: 13494.0
num_examples: 70
- name: validation
num_bytes: 28231.0
num_examples: 139
- name: test
num_bytes: 233485.0
num_examples: 1225
download_size: 154523
dataset_size: 275210.0
- config_name: hin_Deva
features:
- name: text
dtype: string
- name: label
dtype: int64
splits:
- name: train
num_bytes: 23813.0
num_examples: 70
- name: validation
num_bytes: 50797.0
num_examples: 139
- name: test
num_bytes: 417976.0
num_examples: 1225
download_size: 211947
dataset_size: 492586.0
- config_name: hne_Deva
features:
- name: text
dtype: string
- name: label
dtype: int64
splits:
- name: train
num_bytes: 23067.0
num_examples: 70
- name: validation
num_bytes: 48171.0
num_examples: 139
- name: test
num_bytes: 404007.0
num_examples: 1225
download_size: 209152
dataset_size: 475245.0
- config_name: hrv_Latn
features:
- name: text
dtype: string
- name: label
dtype: int64
splits:
- name: train
num_bytes: 10138.0
num_examples: 70
- name: validation
num_bytes: 21103.0
num_examples: 139
- name: test
num_bytes: 173386.0
num_examples: 1225
download_size: 147455
dataset_size: 204627.0
- config_name: hun_Latn
features:
- name: text
dtype: string
- name: label
dtype: int64
splits:
- name: train
num_bytes: 11212.0
num_examples: 70
- name: validation
num_bytes: 23923.0
num_examples: 139
- name: test
num_bytes: 196257.0
num_examples: 1225
download_size: 160529
dataset_size: 231392.0
- config_name: hye_Armn
features:
- name: text
dtype: string
- name: label
dtype: int64
splits:
- name: train
num_bytes: 19518.0
num_examples: 70
- name: validation
num_bytes: 41252.0
num_examples: 139
- name: test
num_bytes: 338159.0
num_examples: 1225
download_size: 207276
dataset_size: 398929.0
- config_name: ibo_Latn
features:
- name: text
dtype: string
- name: label
dtype: int64
splits:
- name: train
num_bytes: 11319.0
num_examples: 70
- name: validation
num_bytes: 24597.0
num_examples: 139
- name: test
num_bytes: 205514.0
num_examples: 1225
download_size: 146117
dataset_size: 241430.0
- config_name: ilo_Latn
features:
- name: text
dtype: string
- name: label
dtype: int64
splits:
- name: train
num_bytes: 11934.0
num_examples: 70
- name: validation
num_bytes: 24833.0
num_examples: 139
- name: test
num_bytes: 205739.0
num_examples: 1225
download_size: 152118
dataset_size: 242506.0
- config_name: ind_Latn
features:
- name: text
dtype: string
- name: label
dtype: int64
splits:
- name: train
num_bytes: 10501.0
num_examples: 70
- name: validation
num_bytes: 22205.0
num_examples: 139
- name: test
num_bytes: 184685.0
num_examples: 1225
download_size: 138183
dataset_size: 217391.0
- config_name: isl_Latn
features:
- name: text
dtype: string
- name: label
dtype: int64
splits:
- name: train
num_bytes: 10714.0
num_examples: 70
- name: validation
num_bytes: 22552.0
num_examples: 139
- name: test
num_bytes: 186124.0
num_examples: 1225
download_size: 149812
dataset_size: 219390.0
- config_name: ita_Latn
features:
- name: text
dtype: string
- name: label
dtype: int64
splits:
- name: train
num_bytes: 11731.0
num_examples: 70
- name: validation
num_bytes: 24474.0
num_examples: 139
- name: test
num_bytes: 201283.0
num_examples: 1225
download_size: 160550
dataset_size: 237488.0
- config_name: jav_Latn
features:
- name: text
dtype: string
- name: label
dtype: int64
splits:
- name: train
num_bytes: 10073.0
num_examples: 70
- name: validation
num_bytes: 21709.0
num_examples: 139
- name: test
num_bytes: 177840.0
num_examples: 1225
download_size: 135082
dataset_size: 209622.0
- config_name: jpn_Jpan
features:
- name: text
dtype: string
- name: label
dtype: int64
splits:
- name: train
num_bytes: 12534.0
num_examples: 70
- name: validation
num_bytes: 25798.0
num_examples: 139
- name: test
num_bytes: 213955.0
num_examples: 1225
download_size: 158432
dataset_size: 252287.0
- config_name: kab_Latn
features:
- name: text
dtype: string
- name: label
dtype: int64
splits:
- name: train
num_bytes: 10588.0
num_examples: 70
- name: validation
num_bytes: 21500.0
num_examples: 139
- name: test
num_bytes: 182035.0
num_examples: 1225
download_size: 147278
dataset_size: 214123.0
- config_name: kac_Latn
features:
- name: text
dtype: string
- name: label
dtype: int64
splits:
- name: train
num_bytes: 12069.0
num_examples: 70
- name: validation
num_bytes: 25714.0
num_examples: 139
- name: test
num_bytes: 216160.0
num_examples: 1225
download_size: 147951
dataset_size: 253943.0
- config_name: kam_Latn
features:
- name: text
dtype: string
- name: label
dtype: int64
splits:
- name: train
num_bytes: 10418.0
num_examples: 70
- name: validation
num_bytes: 20618.589928057554
num_examples: 138
- name: test
num_bytes: 174423.76081632654
num_examples: 1223
download_size: 140121
dataset_size: 205460.3507443841
- config_name: kan_Knda
features:
- name: text
dtype: string
- name: label
dtype: int64
splits:
- name: train
num_bytes: 26652.0
num_examples: 70
- name: validation
num_bytes: 54787.0
num_examples: 139
- name: test
num_bytes: 464067.0
num_examples: 1225
download_size: 232405
dataset_size: 545506.0
- config_name: kas_Deva
features:
- name: text
dtype: string
- name: label
dtype: int64
splits:
- name: train
num_bytes: 22552.0
num_examples: 70
- name: validation
num_bytes: 46192.65467625899
num_examples: 137
- name: test
num_bytes: 390639.85714285716
num_examples: 1215
download_size: 217163
dataset_size: 459384.5118191162
- config_name: kat_Geor
features:
- name: text
dtype: string
- name: label
dtype: int64
splits:
- name: train
num_bytes: 27918.0
num_examples: 70
- name: validation
num_bytes: 59157.0
num_examples: 139
- name: test
num_bytes: 481290.0
num_examples: 1225
download_size: 227470
dataset_size: 568365.0
- config_name: kaz_Cyrl
features:
- name: text
dtype: string
- name: label
dtype: int64
splits:
- name: train
num_bytes: 17838.0
num_examples: 70
- name: validation
num_bytes: 37742.0
num_examples: 139
- name: test
num_bytes: 313235.0
num_examples: 1225
download_size: 189907
dataset_size: 368815.0
- config_name: kbp_Latn
features:
- name: text
dtype: string
- name: label
dtype: int64
splits:
- name: train
num_bytes: 13145.0
num_examples: 70
- name: validation
num_bytes: 27426.258992805757
num_examples: 138
- name: test
num_bytes: 231349.66857142857
num_examples: 1223
download_size: 156082
dataset_size: 271920.92756423436
- config_name: kea_Latn
features:
- name: text
dtype: string
- name: label
dtype: int64
splits:
- name: train
num_bytes: 10088.0
num_examples: 70
- name: validation
num_bytes: 21097.0
num_examples: 139
- name: test
num_bytes: 174414.0
num_examples: 1225
download_size: 138918
dataset_size: 205599.0
- config_name: khk_Cyrl
features:
- name: text
dtype: string
- name: label
dtype: int64
splits:
- name: train
num_bytes: 18294.0
num_examples: 70
- name: validation
num_bytes: 37638.0
num_examples: 139
- name: test
num_bytes: 317890.0
num_examples: 1225
download_size: 194032
dataset_size: 373822.0
- config_name: khm_Khmr
features:
- name: text
dtype: string
- name: label
dtype: int64
splits:
- name: train
num_bytes: 25506.542857142857
num_examples: 59
- name: validation
num_bytes: 57911.76258992806
num_examples: 123
- name: test
num_bytes: 470662.21714285715
num_examples: 1056
download_size: 252264
dataset_size: 554080.522589928
- config_name: kik_Latn
features:
- name: text
dtype: string
- name: label
dtype: int64
splits:
- name: train
num_bytes: 12695.0
num_examples: 70
- name: validation
num_bytes: 26207.0
num_examples: 139
- name: test
num_bytes: 219727.0
num_examples: 1225
download_size: 158524
dataset_size: 258629.0
- config_name: kin_Latn
features:
- name: text
dtype: string
- name: label
dtype: int64
splits:
- name: train
num_bytes: 11226.0
num_examples: 70
- name: validation
num_bytes: 23285.0
num_examples: 139
- name: test
num_bytes: 194176.0
num_examples: 1225
download_size: 148101
dataset_size: 228687.0
- config_name: kir_Cyrl
features:
- name: text
dtype: string
- name: label
dtype: int64
splits:
- name: train
num_bytes: 18063.0
num_examples: 70
- name: validation
num_bytes: 37258.0
num_examples: 139
- name: test
num_bytes: 312570.0
num_examples: 1225
download_size: 194542
dataset_size: 367891.0
- config_name: kmb_Latn
features:
- name: text
dtype: string
- name: label
dtype: int64
splits:
- name: train
num_bytes: 10941.0
num_examples: 70
- name: validation
num_bytes: 22788.0
num_examples: 139
- name: test
num_bytes: 190325.0
num_examples: 1225
download_size: 140985
dataset_size: 224054.0
- config_name: kmr_Latn
features:
- name: text
dtype: string
- name: label
dtype: int64
splits:
- name: train
num_bytes: 10652.0
num_examples: 70
- name: validation
num_bytes: 22750.0
num_examples: 139
- name: test
num_bytes: 188121.0
num_examples: 1225
download_size: 150236
dataset_size: 221523.0
- config_name: knc_Latn
features:
- name: text
dtype: string
- name: label
dtype: int64
splits:
- name: train
num_bytes: 11580.0
num_examples: 70
- name: validation
num_bytes: 22805.0
num_examples: 139
- name: test
num_bytes: 191150.0
num_examples: 1225
download_size: 153378
dataset_size: 225535.0
- config_name: kon_Latn
features:
- name: text
dtype: string
- name: label
dtype: int64
splits:
- name: train
num_bytes: 11111.0
num_examples: 70
- name: validation
num_bytes: 23483.0
num_examples: 139
- name: test
num_bytes: 193720.0
num_examples: 1225
download_size: 133533
dataset_size: 228314.0
- config_name: kor_Hang
features:
- name: text
dtype: string
- name: label
dtype: int64
splits:
- name: train
num_bytes: 11949.0
num_examples: 70
- name: validation
num_bytes: 24620.0
num_examples: 139
- name: test
num_bytes: 202116.0
num_examples: 1225
download_size: 157051
dataset_size: 238685.0
- config_name: lao_Laoo
features:
- name: text
dtype: string
- name: label
dtype: int64
splits:
- name: train
num_bytes: 22445.1
num_examples: 63
- name: validation
num_bytes: 47041.14388489209
num_examples: 121
- name: test
num_bytes: 382933.13469387754
num_examples: 1055
download_size: 206422
dataset_size: 452419.3785787696
- config_name: lij_Latn
features:
- name: text
dtype: string
- name: label
dtype: int64
splits:
- name: train
num_bytes: 11492.0
num_examples: 70
- name: validation
num_bytes: 24039.0
num_examples: 139
- name: test
num_bytes: 197929.0
num_examples: 1225
download_size: 159663
dataset_size: 233460.0
- config_name: lim_Latn
features:
- name: text
dtype: string
- name: label
dtype: int64
splits:
- name: train
num_bytes: 10553.0
num_examples: 70
- name: validation
num_bytes: 22468.0
num_examples: 139
- name: test
num_bytes: 182564.8457142857
num_examples: 1224
download_size: 149516
dataset_size: 215585.8457142857
- config_name: lin_Latn
features:
- name: text
dtype: string
- name: label
dtype: int64
splits:
- name: train
num_bytes: 10545.0
num_examples: 70
- name: validation
num_bytes: 22176.0
num_examples: 139
- name: test
num_bytes: 184640.0
num_examples: 1225
download_size: 126201
dataset_size: 217361.0
- config_name: lit_Latn
features:
- name: text
dtype: string
- name: label
dtype: int64
splits:
- name: train
num_bytes: 10738.0
num_examples: 70
- name: validation
num_bytes: 21766.0
num_examples: 139
- name: test
num_bytes: 182762.0
num_examples: 1225
download_size: 152149
dataset_size: 215266.0
- config_name: lmo_Latn
features:
- name: text
dtype: string
- name: label
dtype: int64
splits:
- name: train
num_bytes: 11477.0
num_examples: 70
- name: validation
num_bytes: 23957.0
num_examples: 139
- name: test
num_bytes: 197484.0
num_examples: 1225
download_size: 163032
dataset_size: 232918.0
- config_name: ltg_Latn
features:
- name: text
dtype: string
- name: label
dtype: int64
splits:
- name: train
num_bytes: 10294.0
num_examples: 70
- name: validation
num_bytes: 21419.0
num_examples: 139
- name: test
num_bytes: 180105.0
num_examples: 1225
download_size: 149862
dataset_size: 211818.0
- config_name: ltz_Latn
features:
- name: text
dtype: string
- name: label
dtype: int64
splits:
- name: train
num_bytes: 11119.0
num_examples: 70
- name: validation
num_bytes: 23884.0
num_examples: 139
- name: test
num_bytes: 195528.0
num_examples: 1225
download_size: 155424
dataset_size: 230531.0
- config_name: lua_Latn
features:
- name: text
dtype: string
- name: label
dtype: int64
splits:
- name: train
num_bytes: 10692.0
num_examples: 70
- name: validation
num_bytes: 22336.0
num_examples: 139
- name: test
num_bytes: 183976.69224489795
num_examples: 1224
download_size: 139423
dataset_size: 217004.69224489795
- config_name: lug_Latn
features:
- name: text
dtype: string
- name: label
dtype: int64
splits:
- name: train
num_bytes: 10610.0
num_examples: 70
- name: validation
num_bytes: 21158.0
num_examples: 139
- name: test
num_bytes: 177649.0
num_examples: 1225
download_size: 144935
dataset_size: 209417.0
- config_name: luo_Latn
features:
- name: text
dtype: string
- name: label
dtype: int64
splits:
- name: train
num_bytes: 10572.0
num_examples: 70
- name: validation
num_bytes: 21534.0
num_examples: 139
- name: test
num_bytes: 179610.0
num_examples: 1225
download_size: 138426
dataset_size: 211716.0
- config_name: lus_Latn
features:
- name: text
dtype: string
- name: label
dtype: int64
splits:
- name: train
num_bytes: 10249.0
num_examples: 70
- name: validation
num_bytes: 21973.769784172662
num_examples: 138
- name: test
num_bytes: 187821.55102040817
num_examples: 1224
download_size: 144052
dataset_size: 220044.3208045808
- config_name: lvs_Latn
features:
- name: text
dtype: string
- name: label
dtype: int64
splits:
- name: train
num_bytes: 10724.0
num_examples: 70
- name: validation
num_bytes: 23294.0
num_examples: 139
- name: test
num_bytes: 190221.0
num_examples: 1225
download_size: 156274
dataset_size: 224239.0
- config_name: mag_Deva
features:
- name: text
dtype: string
- name: label
dtype: int64
splits:
- name: train
num_bytes: 22923.0
num_examples: 70
- name: validation
num_bytes: 48802.0
num_examples: 139
- name: test
num_bytes: 404136.0
num_examples: 1225
download_size: 205019
dataset_size: 475861.0
- config_name: mai_Deva
features:
- name: text
dtype: string
- name: label
dtype: int64
splits:
- name: train
num_bytes: 23642.0
num_examples: 70
- name: validation
num_bytes: 49755.0
num_examples: 139
- name: test
num_bytes: 414019.0
num_examples: 1225
download_size: 210828
dataset_size: 487416.0
- config_name: mal_Mlym
features:
- name: text
dtype: string
- name: label
dtype: int64
splits:
- name: train
num_bytes: 28813.0
num_examples: 70
- name: validation
num_bytes: 60793.0
num_examples: 139
- name: test
num_bytes: 504090.0
num_examples: 1225
download_size: 244639
dataset_size: 593696.0
- config_name: mar_Deva
features:
- name: text
dtype: string
- name: label
dtype: int64
splits:
- name: train
num_bytes: 25269.0
num_examples: 70
- name: validation
num_bytes: 53145.0
num_examples: 139
- name: test
num_bytes: 436262.0
num_examples: 1225
download_size: 222718
dataset_size: 514676.0
- config_name: min_Latn
features:
- name: text
dtype: string
- name: label
dtype: int64
splits:
- name: train
num_bytes: 10304.0
num_examples: 70
- name: validation
num_bytes: 22100.0
num_examples: 139
- name: test
num_bytes: 182205.0
num_examples: 1225
download_size: 139192
dataset_size: 214609.0
- config_name: mkd_Cyrl
features:
- name: text
dtype: string
- name: label
dtype: int64
splits:
- name: train
num_bytes: 18109.0
num_examples: 70
- name: validation
num_bytes: 38074.0
num_examples: 139
- name: test
num_bytes: 313783.0
num_examples: 1225
download_size: 190914
dataset_size: 369966.0
- config_name: mlt_Latn
features:
- name: text
dtype: string
- name: label
dtype: int64
splits:
- name: train
num_bytes: 11292.0
num_examples: 70
- name: validation
num_bytes: 23788.0
num_examples: 139
- name: test
num_bytes: 197824.0
num_examples: 1225
download_size: 157430
dataset_size: 232904.0
- config_name: mni_Beng
features:
- name: text
dtype: string
- name: label
dtype: int64
splits:
- name: train
num_bytes: 25959.0
num_examples: 70
- name: validation
num_bytes: 53758.0
num_examples: 139
- name: test
num_bytes: 451414.0
num_examples: 1225
download_size: 217574
dataset_size: 531131.0
- config_name: mos_Latn
features:
- name: text
dtype: string
- name: label
dtype: int64
splits:
- name: train
num_bytes: 10233.0
num_examples: 70
- name: validation
num_bytes: 21654.0
num_examples: 139
- name: test
num_bytes: 177291.0
num_examples: 1225
download_size: 144699
dataset_size: 209178.0
- config_name: mri_Latn
features:
- name: text
dtype: string
- name: label
dtype: int64
splits:
- name: train
num_bytes: 11204.0
num_examples: 70
- name: validation
num_bytes: 23697.0
num_examples: 139
- name: test
num_bytes: 197838.0
num_examples: 1225
download_size: 136556
dataset_size: 232739.0
- config_name: mya_Mymr
features:
- name: text
dtype: string
- name: label
dtype: int64
splits:
- name: train
num_bytes: 32282.0
num_examples: 70
- name: validation
num_bytes: 68851.0
num_examples: 139
- name: test
num_bytes: 571754.0
num_examples: 1225
download_size: 248904
dataset_size: 672887.0
- config_name: nld_Latn
features:
- name: text
dtype: string
- name: label
dtype: int64
splits:
- name: train
num_bytes: 10904.0
num_examples: 70
- name: validation
num_bytes: 23125.0
num_examples: 139
- name: test
num_bytes: 190029.0
num_examples: 1225
download_size: 149736
dataset_size: 224058.0
- config_name: nno_Latn
features:
- name: text
dtype: string
- name: label
dtype: int64
splits:
- name: train
num_bytes: 10176.0
num_examples: 70
- name: validation
num_bytes: 21406.0
num_examples: 139
- name: test
num_bytes: 176790.0
num_examples: 1225
download_size: 142630
dataset_size: 208372.0
- config_name: nob_Latn
features:
- name: text
dtype: string
- name: label
dtype: int64
splits:
- name: train
num_bytes: 10110.0
num_examples: 70
- name: validation
num_bytes: 21018.0
num_examples: 139
- name: test
num_bytes: 175982.0
num_examples: 1225
download_size: 141546
dataset_size: 207110.0
- config_name: npi_Deva
features:
- name: text
dtype: string
- name: label
dtype: int64
splits:
- name: train
num_bytes: 23340.0
num_examples: 70
- name: validation
num_bytes: 50361.0
num_examples: 139
- name: test
num_bytes: 418579.0236734694
num_examples: 1224
download_size: 213026
dataset_size: 492280.0236734694
- config_name: nqo_Nkoo
features:
- name: text
dtype: string
- name: label
dtype: int64
splits:
- name: train
num_bytes: 21734.0
num_examples: 70
- name: validation
num_bytes: 45424.0
num_examples: 139
- name: test
num_bytes: 378331.0
num_examples: 1225
download_size: 212357
dataset_size: 445489.0
- config_name: nso_Latn
features:
- name: text
dtype: string
- name: label
dtype: int64
splits:
- name: train
num_bytes: 11313.0
num_examples: 70
- name: validation
num_bytes: 23984.0
num_examples: 139
- name: test
num_bytes: 200127.0
num_examples: 1225
download_size: 146242
dataset_size: 235424.0
- config_name: nus_Latn
features:
- name: text
dtype: string
- name: label
dtype: int64
splits:
- name: train
num_bytes: 12185.0
num_examples: 70
- name: validation
num_bytes: 26842.0
num_examples: 139
- name: test
num_bytes: 222474.0
num_examples: 1225
download_size: 156536
dataset_size: 261501.0
configs:
- config_name: ace_Latn
data_files:
- split: train
path: ace_Latn/train-*
- split: validation
path: ace_Latn/validation-*
- split: test
path: ace_Latn/test-*
- config_name: acm_Arab
data_files:
- split: train
path: acm_Arab/train-*
- split: validation
path: acm_Arab/validation-*
- split: test
path: acm_Arab/test-*
- config_name: acq_Arab
data_files:
- split: train
path: acq_Arab/train-*
- split: validation
path: acq_Arab/validation-*
- split: test
path: acq_Arab/test-*
- config_name: aeb_Arab
data_files:
- split: train
path: aeb_Arab/train-*
- split: validation
path: aeb_Arab/validation-*
- split: test
path: aeb_Arab/test-*
- config_name: afr_Latn
data_files:
- split: train
path: afr_Latn/train-*
- split: validation
path: afr_Latn/validation-*
- split: test
path: afr_Latn/test-*
- config_name: ajp_Arab
data_files:
- split: train
path: ajp_Arab/train-*
- split: validation
path: ajp_Arab/validation-*
- split: test
path: ajp_Arab/test-*
- config_name: aka_Latn
data_files:
- split: train
path: aka_Latn/train-*
- split: validation
path: aka_Latn/validation-*
- split: test
path: aka_Latn/test-*
- config_name: als_Latn
data_files:
- split: train
path: als_Latn/train-*
- split: validation
path: als_Latn/validation-*
- split: test
path: als_Latn/test-*
- config_name: amh_Ethi
data_files:
- split: train
path: amh_Ethi/train-*
- split: validation
path: amh_Ethi/validation-*
- split: test
path: amh_Ethi/test-*
- config_name: apc_Arab
data_files:
- split: train
path: apc_Arab/train-*
- split: validation
path: apc_Arab/validation-*
- split: test
path: apc_Arab/test-*
- config_name: arb_Latn
data_files:
- split: train
path: arb_Latn/train-*
- split: validation
path: arb_Latn/validation-*
- split: test
path: arb_Latn/test-*
- config_name: ars_Arab
data_files:
- split: train
path: ars_Arab/train-*
- split: validation
path: ars_Arab/validation-*
- split: test
path: ars_Arab/test-*
- config_name: ary_Arab
data_files:
- split: train
path: ary_Arab/train-*
- split: validation
path: ary_Arab/validation-*
- split: test
path: ary_Arab/test-*
- config_name: arz_Arab
data_files:
- split: train
path: arz_Arab/train-*
- split: validation
path: arz_Arab/validation-*
- split: test
path: arz_Arab/test-*
- config_name: asm_Beng
data_files:
- split: train
path: asm_Beng/train-*
- split: validation
path: asm_Beng/validation-*
- split: test
path: asm_Beng/test-*
- config_name: ast_Latn
data_files:
- split: train
path: ast_Latn/train-*
- split: validation
path: ast_Latn/validation-*
- split: test
path: ast_Latn/test-*
- config_name: awa_Deva
data_files:
- split: train
path: awa_Deva/train-*
- split: validation
path: awa_Deva/validation-*
- split: test
path: awa_Deva/test-*
- config_name: ayr_Latn
data_files:
- split: train
path: ayr_Latn/train-*
- split: validation
path: ayr_Latn/validation-*
- split: test
path: ayr_Latn/test-*
- config_name: azb_Arab
data_files:
- split: train
path: azb_Arab/train-*
- split: validation
path: azb_Arab/validation-*
- split: test
path: azb_Arab/test-*
- config_name: azj_Latn
data_files:
- split: train
path: azj_Latn/train-*
- split: validation
path: azj_Latn/validation-*
- split: test
path: azj_Latn/test-*
- config_name: bak_Cyrl
data_files:
- split: train
path: bak_Cyrl/train-*
- split: validation
path: bak_Cyrl/validation-*
- split: test
path: bak_Cyrl/test-*
- config_name: bam_Latn
data_files:
- split: train
path: bam_Latn/train-*
- split: validation
path: bam_Latn/validation-*
- split: test
path: bam_Latn/test-*
- config_name: ban_Latn
data_files:
- split: train
path: ban_Latn/train-*
- split: validation
path: ban_Latn/validation-*
- split: test
path: ban_Latn/test-*
- config_name: bel_Cyrl
data_files:
- split: train
path: bel_Cyrl/train-*
- split: validation
path: bel_Cyrl/validation-*
- split: test
path: bel_Cyrl/test-*
- config_name: bem_Latn
data_files:
- split: train
path: bem_Latn/train-*
- split: validation
path: bem_Latn/validation-*
- split: test
path: bem_Latn/test-*
- config_name: ben_Beng
data_files:
- split: train
path: ben_Beng/train-*
- split: validation
path: ben_Beng/validation-*
- split: test
path: ben_Beng/test-*
- config_name: bho_Deva
data_files:
- split: train
path: bho_Deva/train-*
- split: validation
path: bho_Deva/validation-*
- split: test
path: bho_Deva/test-*
- config_name: bjn_Latn
data_files:
- split: train
path: bjn_Latn/train-*
- split: validation
path: bjn_Latn/validation-*
- split: test
path: bjn_Latn/test-*
- config_name: bod_Tibt
data_files:
- split: train
path: bod_Tibt/train-*
- split: validation
path: bod_Tibt/validation-*
- split: test
path: bod_Tibt/test-*
- config_name: bos_Latn
data_files:
- split: train
path: bos_Latn/train-*
- split: validation
path: bos_Latn/validation-*
- split: test
path: bos_Latn/test-*
- config_name: bug_Latn
data_files:
- split: train
path: bug_Latn/train-*
- split: validation
path: bug_Latn/validation-*
- split: test
path: bug_Latn/test-*
- config_name: bul_Cyrl
data_files:
- split: train
path: bul_Cyrl/train-*
- split: validation
path: bul_Cyrl/validation-*
- split: test
path: bul_Cyrl/test-*
- config_name: cat_Latn
data_files:
- split: train
path: cat_Latn/train-*
- split: validation
path: cat_Latn/validation-*
- split: test
path: cat_Latn/test-*
- config_name: ceb_Latn
data_files:
- split: train
path: ceb_Latn/train-*
- split: validation
path: ceb_Latn/validation-*
- split: test
path: ceb_Latn/test-*
- config_name: ces_Latn
data_files:
- split: train
path: ces_Latn/train-*
- split: validation
path: ces_Latn/validation-*
- split: test
path: ces_Latn/test-*
- config_name: cjk_Latn
data_files:
- split: train
path: cjk_Latn/train-*
- split: validation
path: cjk_Latn/validation-*
- split: test
path: cjk_Latn/test-*
- config_name: ckb_Arab
data_files:
- split: train
path: ckb_Arab/train-*
- split: validation
path: ckb_Arab/validation-*
- split: test
path: ckb_Arab/test-*
- config_name: crh_Latn
data_files:
- split: train
path: crh_Latn/train-*
- split: validation
path: crh_Latn/validation-*
- split: test
path: crh_Latn/test-*
- config_name: cym_Latn
data_files:
- split: train
path: cym_Latn/train-*
- split: validation
path: cym_Latn/validation-*
- split: test
path: cym_Latn/test-*
- config_name: dan_Latn
data_files:
- split: train
path: dan_Latn/train-*
- split: validation
path: dan_Latn/validation-*
- split: test
path: dan_Latn/test-*
- config_name: deu_Latn
data_files:
- split: train
path: deu_Latn/train-*
- split: validation
path: deu_Latn/validation-*
- split: test
path: deu_Latn/test-*
- config_name: dik_Latn
data_files:
- split: train
path: dik_Latn/train-*
- split: validation
path: dik_Latn/validation-*
- split: test
path: dik_Latn/test-*
- config_name: dyu_Latn
data_files:
- split: train
path: dyu_Latn/train-*
- split: validation
path: dyu_Latn/validation-*
- split: test
path: dyu_Latn/test-*
- config_name: dzo_Tibt
data_files:
- split: train
path: dzo_Tibt/train-*
- split: validation
path: dzo_Tibt/validation-*
- split: test
path: dzo_Tibt/test-*
- config_name: ell_Grek
data_files:
- split: train
path: ell_Grek/train-*
- split: validation
path: ell_Grek/validation-*
- split: test
path: ell_Grek/test-*
- config_name: eng_Latn
data_files:
- split: train
path: eng_Latn/train-*
- split: validation
path: eng_Latn/validation-*
- split: test
path: eng_Latn/test-*
- config_name: epo_Latn
data_files:
- split: train
path: epo_Latn/train-*
- split: validation
path: epo_Latn/validation-*
- split: test
path: epo_Latn/test-*
- config_name: est_Latn
data_files:
- split: train
path: est_Latn/train-*
- split: validation
path: est_Latn/validation-*
- split: test
path: est_Latn/test-*
- config_name: eus_Latn
data_files:
- split: train
path: eus_Latn/train-*
- split: validation
path: eus_Latn/validation-*
- split: test
path: eus_Latn/test-*
- config_name: ewe_Latn
data_files:
- split: train
path: ewe_Latn/train-*
- split: validation
path: ewe_Latn/validation-*
- split: test
path: ewe_Latn/test-*
- config_name: fao_Latn
data_files:
- split: train
path: fao_Latn/train-*
- split: validation
path: fao_Latn/validation-*
- split: test
path: fao_Latn/test-*
- config_name: fij_Latn
data_files:
- split: train
path: fij_Latn/train-*
- split: validation
path: fij_Latn/validation-*
- split: test
path: fij_Latn/test-*
- config_name: fin_Latn
data_files:
- split: train
path: fin_Latn/train-*
- split: validation
path: fin_Latn/validation-*
- split: test
path: fin_Latn/test-*
- config_name: fon_Latn
data_files:
- split: train
path: fon_Latn/train-*
- split: validation
path: fon_Latn/validation-*
- split: test
path: fon_Latn/test-*
- config_name: fra_Latn
data_files:
- split: train
path: fra_Latn/train-*
- split: validation
path: fra_Latn/validation-*
- split: test
path: fra_Latn/test-*
- config_name: fur_Latn
data_files:
- split: train
path: fur_Latn/train-*
- split: validation
path: fur_Latn/validation-*
- split: test
path: fur_Latn/test-*
- config_name: fuv_Latn
data_files:
- split: train
path: fuv_Latn/train-*
- split: validation
path: fuv_Latn/validation-*
- split: test
path: fuv_Latn/test-*
- config_name: gaz_Latn
data_files:
- split: train
path: gaz_Latn/train-*
- split: validation
path: gaz_Latn/validation-*
- split: test
path: gaz_Latn/test-*
- config_name: gla_Latn
data_files:
- split: train
path: gla_Latn/train-*
- split: validation
path: gla_Latn/validation-*
- split: test
path: gla_Latn/test-*
- config_name: gle_Latn
data_files:
- split: train
path: gle_Latn/train-*
- split: validation
path: gle_Latn/validation-*
- split: test
path: gle_Latn/test-*
- config_name: glg_Latn
data_files:
- split: train
path: glg_Latn/train-*
- split: validation
path: glg_Latn/validation-*
- split: test
path: glg_Latn/test-*
- config_name: grn_Latn
data_files:
- split: train
path: grn_Latn/train-*
- split: validation
path: grn_Latn/validation-*
- split: test
path: grn_Latn/test-*
- config_name: guj_Gujr
data_files:
- split: train
path: guj_Gujr/train-*
- split: validation
path: guj_Gujr/validation-*
- split: test
path: guj_Gujr/test-*
- config_name: hat_Latn
data_files:
- split: train
path: hat_Latn/train-*
- split: validation
path: hat_Latn/validation-*
- split: test
path: hat_Latn/test-*
- config_name: hau_Latn
data_files:
- split: train
path: hau_Latn/train-*
- split: validation
path: hau_Latn/validation-*
- split: test
path: hau_Latn/test-*
- config_name: heb_Hebr
data_files:
- split: train
path: heb_Hebr/train-*
- split: validation
path: heb_Hebr/validation-*
- split: test
path: heb_Hebr/test-*
- config_name: hin_Deva
data_files:
- split: train
path: hin_Deva/train-*
- split: validation
path: hin_Deva/validation-*
- split: test
path: hin_Deva/test-*
- config_name: hne_Deva
data_files:
- split: train
path: hne_Deva/train-*
- split: validation
path: hne_Deva/validation-*
- split: test
path: hne_Deva/test-*
- config_name: hrv_Latn
data_files:
- split: train
path: hrv_Latn/train-*
- split: validation
path: hrv_Latn/validation-*
- split: test
path: hrv_Latn/test-*
- config_name: hun_Latn
data_files:
- split: train
path: hun_Latn/train-*
- split: validation
path: hun_Latn/validation-*
- split: test
path: hun_Latn/test-*
- config_name: hye_Armn
data_files:
- split: train
path: hye_Armn/train-*
- split: validation
path: hye_Armn/validation-*
- split: test
path: hye_Armn/test-*
- config_name: ibo_Latn
data_files:
- split: train
path: ibo_Latn/train-*
- split: validation
path: ibo_Latn/validation-*
- split: test
path: ibo_Latn/test-*
- config_name: ilo_Latn
data_files:
- split: train
path: ilo_Latn/train-*
- split: validation
path: ilo_Latn/validation-*
- split: test
path: ilo_Latn/test-*
- config_name: ind_Latn
data_files:
- split: train
path: ind_Latn/train-*
- split: validation
path: ind_Latn/validation-*
- split: test
path: ind_Latn/test-*
- config_name: isl_Latn
data_files:
- split: train
path: isl_Latn/train-*
- split: validation
path: isl_Latn/validation-*
- split: test
path: isl_Latn/test-*
- config_name: ita_Latn
data_files:
- split: train
path: ita_Latn/train-*
- split: validation
path: ita_Latn/validation-*
- split: test
path: ita_Latn/test-*
- config_name: jav_Latn
data_files:
- split: train
path: jav_Latn/train-*
- split: validation
path: jav_Latn/validation-*
- split: test
path: jav_Latn/test-*
- config_name: jpn_Jpan
data_files:
- split: train
path: jpn_Jpan/train-*
- split: validation
path: jpn_Jpan/validation-*
- split: test
path: jpn_Jpan/test-*
- config_name: kab_Latn
data_files:
- split: train
path: kab_Latn/train-*
- split: validation
path: kab_Latn/validation-*
- split: test
path: kab_Latn/test-*
- config_name: kac_Latn
data_files:
- split: train
path: kac_Latn/train-*
- split: validation
path: kac_Latn/validation-*
- split: test
path: kac_Latn/test-*
- config_name: kam_Latn
data_files:
- split: train
path: kam_Latn/train-*
- split: validation
path: kam_Latn/validation-*
- split: test
path: kam_Latn/test-*
- config_name: kan_Knda
data_files:
- split: train
path: kan_Knda/train-*
- split: validation
path: kan_Knda/validation-*
- split: test
path: kan_Knda/test-*
- config_name: kas_Deva
data_files:
- split: train
path: kas_Deva/train-*
- split: validation
path: kas_Deva/validation-*
- split: test
path: kas_Deva/test-*
- config_name: kat_Geor
data_files:
- split: train
path: kat_Geor/train-*
- split: validation
path: kat_Geor/validation-*
- split: test
path: kat_Geor/test-*
- config_name: kaz_Cyrl
data_files:
- split: train
path: kaz_Cyrl/train-*
- split: validation
path: kaz_Cyrl/validation-*
- split: test
path: kaz_Cyrl/test-*
- config_name: kbp_Latn
data_files:
- split: train
path: kbp_Latn/train-*
- split: validation
path: kbp_Latn/validation-*
- split: test
path: kbp_Latn/test-*
- config_name: kea_Latn
data_files:
- split: train
path: kea_Latn/train-*
- split: validation
path: kea_Latn/validation-*
- split: test
path: kea_Latn/test-*
- config_name: khk_Cyrl
data_files:
- split: train
path: khk_Cyrl/train-*
- split: validation
path: khk_Cyrl/validation-*
- split: test
path: khk_Cyrl/test-*
- config_name: khm_Khmr
data_files:
- split: train
path: khm_Khmr/train-*
- split: validation
path: khm_Khmr/validation-*
- split: test
path: khm_Khmr/test-*
- config_name: kik_Latn
data_files:
- split: train
path: kik_Latn/train-*
- split: validation
path: kik_Latn/validation-*
- split: test
path: kik_Latn/test-*
- config_name: kin_Latn
data_files:
- split: train
path: kin_Latn/train-*
- split: validation
path: kin_Latn/validation-*
- split: test
path: kin_Latn/test-*
- config_name: kir_Cyrl
data_files:
- split: train
path: kir_Cyrl/train-*
- split: validation
path: kir_Cyrl/validation-*
- split: test
path: kir_Cyrl/test-*
- config_name: kmb_Latn
data_files:
- split: train
path: kmb_Latn/train-*
- split: validation
path: kmb_Latn/validation-*
- split: test
path: kmb_Latn/test-*
- config_name: kmr_Latn
data_files:
- split: train
path: kmr_Latn/train-*
- split: validation
path: kmr_Latn/validation-*
- split: test
path: kmr_Latn/test-*
- config_name: knc_Latn
data_files:
- split: train
path: knc_Latn/train-*
- split: validation
path: knc_Latn/validation-*
- split: test
path: knc_Latn/test-*
- config_name: kon_Latn
data_files:
- split: train
path: kon_Latn/train-*
- split: validation
path: kon_Latn/validation-*
- split: test
path: kon_Latn/test-*
- config_name: kor_Hang
data_files:
- split: train
path: kor_Hang/train-*
- split: validation
path: kor_Hang/validation-*
- split: test
path: kor_Hang/test-*
- config_name: lao_Laoo
data_files:
- split: train
path: lao_Laoo/train-*
- split: validation
path: lao_Laoo/validation-*
- split: test
path: lao_Laoo/test-*
- config_name: lij_Latn
data_files:
- split: train
path: lij_Latn/train-*
- split: validation
path: lij_Latn/validation-*
- split: test
path: lij_Latn/test-*
- config_name: lim_Latn
data_files:
- split: train
path: lim_Latn/train-*
- split: validation
path: lim_Latn/validation-*
- split: test
path: lim_Latn/test-*
- config_name: lin_Latn
data_files:
- split: train
path: lin_Latn/train-*
- split: validation
path: lin_Latn/validation-*
- split: test
path: lin_Latn/test-*
- config_name: lit_Latn
data_files:
- split: train
path: lit_Latn/train-*
- split: validation
path: lit_Latn/validation-*
- split: test
path: lit_Latn/test-*
- config_name: lmo_Latn
data_files:
- split: train
path: lmo_Latn/train-*
- split: validation
path: lmo_Latn/validation-*
- split: test
path: lmo_Latn/test-*
- config_name: ltg_Latn
data_files:
- split: train
path: ltg_Latn/train-*
- split: validation
path: ltg_Latn/validation-*
- split: test
path: ltg_Latn/test-*
- config_name: ltz_Latn
data_files:
- split: train
path: ltz_Latn/train-*
- split: validation
path: ltz_Latn/validation-*
- split: test
path: ltz_Latn/test-*
- config_name: lua_Latn
data_files:
- split: train
path: lua_Latn/train-*
- split: validation
path: lua_Latn/validation-*
- split: test
path: lua_Latn/test-*
- config_name: lug_Latn
data_files:
- split: train
path: lug_Latn/train-*
- split: validation
path: lug_Latn/validation-*
- split: test
path: lug_Latn/test-*
- config_name: luo_Latn
data_files:
- split: train
path: luo_Latn/train-*
- split: validation
path: luo_Latn/validation-*
- split: test
path: luo_Latn/test-*
- config_name: lus_Latn
data_files:
- split: train
path: lus_Latn/train-*
- split: validation
path: lus_Latn/validation-*
- split: test
path: lus_Latn/test-*
- config_name: lvs_Latn
data_files:
- split: train
path: lvs_Latn/train-*
- split: validation
path: lvs_Latn/validation-*
- split: test
path: lvs_Latn/test-*
- config_name: mag_Deva
data_files:
- split: train
path: mag_Deva/train-*
- split: validation
path: mag_Deva/validation-*
- split: test
path: mag_Deva/test-*
- config_name: mai_Deva
data_files:
- split: train
path: mai_Deva/train-*
- split: validation
path: mai_Deva/validation-*
- split: test
path: mai_Deva/test-*
- config_name: mal_Mlym
data_files:
- split: train
path: mal_Mlym/train-*
- split: validation
path: mal_Mlym/validation-*
- split: test
path: mal_Mlym/test-*
- config_name: mar_Deva
data_files:
- split: train
path: mar_Deva/train-*
- split: validation
path: mar_Deva/validation-*
- split: test
path: mar_Deva/test-*
- config_name: min_Latn
data_files:
- split: train
path: min_Latn/train-*
- split: validation
path: min_Latn/validation-*
- split: test
path: min_Latn/test-*
- config_name: mkd_Cyrl
data_files:
- split: train
path: mkd_Cyrl/train-*
- split: validation
path: mkd_Cyrl/validation-*
- split: test
path: mkd_Cyrl/test-*
- config_name: mlt_Latn
data_files:
- split: train
path: mlt_Latn/train-*
- split: validation
path: mlt_Latn/validation-*
- split: test
path: mlt_Latn/test-*
- config_name: mni_Beng
data_files:
- split: train
path: mni_Beng/train-*
- split: validation
path: mni_Beng/validation-*
- split: test
path: mni_Beng/test-*
- config_name: mos_Latn
data_files:
- split: train
path: mos_Latn/train-*
- split: validation
path: mos_Latn/validation-*
- split: test
path: mos_Latn/test-*
- config_name: mri_Latn
data_files:
- split: train
path: mri_Latn/train-*
- split: validation
path: mri_Latn/validation-*
- split: test
path: mri_Latn/test-*
- config_name: mya_Mymr
data_files:
- split: train
path: mya_Mymr/train-*
- split: validation
path: mya_Mymr/validation-*
- split: test
path: mya_Mymr/test-*
- config_name: nld_Latn
data_files:
- split: train
path: nld_Latn/train-*
- split: validation
path: nld_Latn/validation-*
- split: test
path: nld_Latn/test-*
- config_name: nno_Latn
data_files:
- split: train
path: nno_Latn/train-*
- split: validation
path: nno_Latn/validation-*
- split: test
path: nno_Latn/test-*
- config_name: nob_Latn
data_files:
- split: train
path: nob_Latn/train-*
- split: validation
path: nob_Latn/validation-*
- split: test
path: nob_Latn/test-*
- config_name: npi_Deva
data_files:
- split: train
path: npi_Deva/train-*
- split: validation
path: npi_Deva/validation-*
- split: test
path: npi_Deva/test-*
- config_name: nqo_Nkoo
data_files:
- split: train
path: nqo_Nkoo/train-*
- split: validation
path: nqo_Nkoo/validation-*
- split: test
path: nqo_Nkoo/test-*
- config_name: nso_Latn
data_files:
- split: train
path: nso_Latn/train-*
- split: validation
path: nso_Latn/validation-*
- split: test
path: nso_Latn/test-*
- config_name: nus_Latn
data_files:
- split: train
path: nus_Latn/train-*
- split: validation
path: nus_Latn/validation-*
- split: test
path: nus_Latn/test-*
annotations_creators:
- expert-annotated
language_creators:
- expert-generated
language:
- ace
- acm
- acq
- aeb
- afr
- ajp
- aka
- als
- amh
- apc
- arb
- ars
- ary
- arz
- asm
- ast
- awa
- ayr
- azb
- azj
- bak
- bam
- ban
- bel
- bem
- ben
- bho
- bjn
- bod
- bos
- bug
- bul
- cat
- ceb
- ces
- cjk
- ckb
- crh
- cym
- dan
- deu
- dik
- dyu
- dzo
- ell
- eng
- epo
- est
- eus
- ewe
- fao
- fij
- fin
- fon
- fra
- fur
- fuv
- gaz
- gla
- gle
- glg
- grn
- guj
- hat
- hau
- heb
- hin
- hne
- hrv
- hun
- hye
- ibo
- ilo
- ind
- isl
- ita
- jav
- jpn
- kab
- kac
- kam
- kan
- kas
- kat
- kaz
- kbp
- kea
- khk
- khm
- kik
- kin
- kir
- kmb
- kmr
- knc
- kon
- kor
- lao
- lij
- lim
- lin
- lit
- lmo
- ltg
- ltz
- lua
- lug
- luo
- lus
- lvs
- mag
- mai
- mal
- mar
- min
- mkd
- mlt
- mni
- mos
- mri
- mya
- nld
- nno
- nob
- npi
- nqo
- nso
- nus
- nya
- oci
- ory
- pag
- pan
- pap
- pbt
- pes
- plt
- pol
- por
- prs
- quy
- ron
- run
- rus
- sag
- san
- sat
- scn
- shn
- sin
- slk
- slv
- smo
- sna
- snd
- som
- sot
- spa
- srd
- srp
- ssw
- sun
- swe
- swh
- szl
- tam
- taq
- tat
- tel
- tgk
- tgl
- tha
- tir
- tpi
- tsn
- tso
- tuk
- tum
- tur
- twi
- tzm
- uig
- ukr
- umb
- urd
- uzn
- vec
- vie
- war
- wol
- xho
- ydd
- yor
- yue
- zho
- zsm
- zul
license: cc-by-sa-4.0
multilinguality: translated
size_categories:
- 1K<n<10K
task_categories:
- text-classification
task_ids: []
pretty_name: sib200
language_details: ace_Arab, ace_Latn, acm_Arab, acq_Arab, aeb_Arab, afr_Latn, ajp_Arab,
aka_Latn, amh_Ethi, apc_Arab, arb_Arab, ars_Arab, ary_Arab, arz_Arab, asm_Beng,
ast_Latn, awa_Deva, ayr_Latn, azb_Arab, azj_Latn, bak_Cyrl, bam_Latn, ban_Latn,bel_Cyrl,
bem_Latn, ben_Beng, bho_Deva, bjn_Arab, bjn_Latn, bod_Tibt, bos_Latn, bug_Latn,
bul_Cyrl, cat_Latn, ceb_Latn, ces_Latn, cjk_Latn, ckb_Arab, crh_Latn, cym_Latn,
dan_Latn, deu_Latn, dik_Latn, dyu_Latn, dzo_Tibt, ell_Grek, eng_Latn, epo_Latn,
est_Latn, eus_Latn, ewe_Latn, fao_Latn, pes_Arab, fij_Latn, fin_Latn, fon_Latn,
fra_Latn, fur_Latn, fuv_Latn, gla_Latn, gle_Latn, glg_Latn, grn_Latn, guj_Gujr,
hat_Latn, hau_Latn, heb_Hebr, hin_Deva, hne_Deva, hrv_Latn, hun_Latn, hye_Armn,
ibo_Latn, ilo_Latn, ind_Latn, isl_Latn, ita_Latn, jav_Latn, jpn_Jpan, kab_Latn,
kac_Latn, kam_Latn, kan_Knda, kas_Arab, kas_Deva, kat_Geor, knc_Arab, knc_Latn,
kaz_Cyrl, kbp_Latn, kea_Latn, khm_Khmr, kik_Latn, kin_Latn, kir_Cyrl, kmb_Latn,
kon_Latn, kor_Hang, kmr_Latn, lao_Laoo, lvs_Latn, lij_Latn, lim_Latn, lin_Latn,
lit_Latn, lmo_Latn, ltg_Latn, ltz_Latn, lua_Latn, lug_Latn, luo_Latn, lus_Latn,
mag_Deva, mai_Deva, mal_Mlym, mar_Deva, min_Latn, mkd_Cyrl, plt_Latn, mlt_Latn,
mni_Beng, khk_Cyrl, mos_Latn, mri_Latn, zsm_Latn, mya_Mymr, nld_Latn, nno_Latn,
nob_Latn, npi_Deva, nso_Latn, nus_Latn, nya_Latn, oci_Latn, gaz_Latn, ory_Orya,
pag_Latn, pan_Guru, pap_Latn, pol_Latn, por_Latn, prs_Arab, pbt_Arab, quy_Latn,
ron_Latn, run_Latn, rus_Cyrl, sag_Latn, san_Deva, sat_Beng, scn_Latn, shn_Mymr,
sin_Sinh, slk_Latn, slv_Latn, smo_Latn, sna_Latn, snd_Arab, som_Latn, sot_Latn,
spa_Latn, als_Latn, srd_Latn, srp_Cyrl, ssw_Latn, sun_Latn, swe_Latn, swh_Latn,
szl_Latn, tam_Taml, tat_Cyrl, tel_Telu, tgk_Cyrl, tgl_Latn, tha_Thai, tir_Ethi,
taq_Latn, taq_Tfng, tpi_Latn, tsn_Latn, tso_Latn, tuk_Latn, tum_Latn, tur_Latn,
twi_Latn, tzm_Tfng, uig_Arab, ukr_Cyrl, umb_Latn, urd_Arab, uzn_Latn, vec_Latn,
vie_Latn, war_Latn, wol_Latn, xho_Latn, ydd_Hebr, yor_Latn, yue_Hant, zho_Hans,
zho_Hant, zul_Latn
tags:
- mteb
- text
---

# SIB-200 v2

SIB-200 is the largest publicly available topic classification dataset based on Flores-200 covering 205 languages and dialects annotated.

The original SIB-200 v1 dataset ([`mteb/sib200`](https://huggingface.co/datasets/mteb/sib200)) includes only seven labels.

This **v2** dataset includes all **14 labels** (excluding "uncategorized"), making it more challenging.

As stated in the original paper (Section 2.3):
> "While the SIB-200 dataset only includes seven labels, we are also releasing another version of the dataset that is more challenging with all the 14 labels (excluding “uncategorized”). We compared the performance of English dataset using both seven and 14 labels in Appendix C."

## Citation

```bibtex
@article{adelani2023sib,
author = {Adelani, David Ifeoluwa and Liu, Hannah and Shen, Xiaoyu and Vassilyev, Nikita and Alabi, Jesujoba O and Mao, Yanke and Gao, Haonan and Lee, Annie En-Shiun},
journal = {arXiv preprint arXiv:2309.07445},
title = {SIB-200: A simple, inclusive, and big evaluation dataset for topic classification in 200+ languages and dialects},
year = {2023},
}
```