{"entities":{"Q83103":{"pageid":84363,"ns":120,"title":"Item:Q83103","lastrevid":56576667,"modified":"2026-03-13T11:10:00Z","type":"item","id":"Q83103","labels":{"en":{"language":"en","value":"tokenizers.bpe"}},"descriptions":{"en":{"language":"en","value":"Byte Pair Encoding Text Tokenization"}},"aliases":{},"claims":{"P31":[{"mainsnak":{"snaktype":"value","property":"P31","hash":"438d0eef0223375d3a92def8ffc6a10a8bf1ca95","datavalue":{"value":{"entity-type":"item","numeric-id":57080,"id":"Q57080"},"type":"wikibase-entityid"},"datatype":"wikibase-item"},"type":"statement","id":"Q83103$F39FA868-1BFB-497B-A42E-DB030DDB1C58","rank":"normal"}],"P132":[{"mainsnak":{"snaktype":"value","property":"P132","hash":"dd764dabaf036ec40584882b7f9127cdfd73d125","datavalue":{"value":"0.1.1","type":"string"},"datatype":"string"},"type":"statement","qualifiers":{"P28":[{"snaktype":"value","property":"P28","hash":"1b6c67060332d850cc9c231de692120c4f18c19b","datavalue":{"value":{"time":"+2023-01-06T00:00:00Z","timezone":0,"before":0,"after":0,"precision":11,"calendarmodel":"http://www.wikidata.org/entity/Q1985727"},"type":"time"},"datatype":"time"}]},"qualifiers-order":["P28"],"id":"Q83103$473CE4A9-22E0-4BB1-9137-DD338F5C1940","rank":"normal"},{"mainsnak":{"snaktype":"value","property":"P132","hash":"10edd141e119b3c38cc2aa087b8fe5922cd0eea3","datavalue":{"value":"0.1.0","type":"string"},"datatype":"string"},"type":"statement","qualifiers":{"P28":[{"snaktype":"value","property":"P28","hash":"ef9792fab4d1a190c3c2a91768cf1046a4e39a91","datavalue":{"value":{"time":"+2019-08-02T00:00:00Z","timezone":0,"before":0,"after":0,"precision":11,"calendarmodel":"http://www.wikidata.org/entity/Q1985727"},"type":"time"},"datatype":"time"}]},"qualifiers-order":["P28"],"id":"Q83103$2AB3A51D-8AF1-48F0-827F-3D9062DCF45F","rank":"normal"},{"mainsnak":{"snaktype":"value","property":"P132","hash":"8e566d59c9c8e44ecba7cb45a73aaa454a64a603","datavalue":{"value":"0.1.2","type":"string"},"datatype":"string"},"type":"statement","qualifiers":{"P28":[{"snaktype":"value","property":"P28","hash":"e7dc46e6881335706a732f969bff3ed89c4294e2","datavalue":{"value":{"time":"+2023-09-14T00:00:00Z","timezone":0,"before":0,"after":0,"precision":11,"calendarmodel":"http://www.wikidata.org/entity/Q1985727"},"type":"time"},"datatype":"time"}]},"qualifiers-order":["P28"],"id":"Q83103$73E74977-011B-46C6-B088-9503FF9D4FA2","rank":"normal"},{"mainsnak":{"snaktype":"value","property":"P132","hash":"954d5354d497f63bbdb6d95ed05a0ef7b6accda0","datavalue":{"value":"0.1.3","type":"string"},"datatype":"string"},"type":"statement","qualifiers":{"P28":[{"snaktype":"value","property":"P28","hash":"40c8265221eda941ac502fcffff6e1f85e7d3136","datavalue":{"value":{"time":"+2023-09-15T00:00:00Z","timezone":0,"before":0,"after":0,"precision":11,"calendarmodel":"http://www.wikidata.org/entity/Q1985727"},"type":"time"},"datatype":"time"}]},"qualifiers-order":["P28"],"id":"Q83103$8ADFFBD3-75FA-4637-B1DA-9FB554EA0C4F","rank":"normal"}],"P19":[{"mainsnak":{"snaktype":"value","property":"P19","hash":"44c060717be4128d23d84929df559e074e8b91be","datavalue":{"value":{"entity-type":"item","numeric-id":83102,"id":"Q83102"},"type":"wikibase-entityid"},"datatype":"wikibase-item"},"type":"statement","id":"Q83103$CA996F80-1187-494B-AC7D-7F9734C23BE4","rank":"normal"}],"P229":[{"mainsnak":{"snaktype":"value","property":"P229","hash":"ef03f2b2fa4c7c83cdc5df0bad142aabf95a00ad","datavalue":{"value":"tokenizers.bpe","type":"string"},"datatype":"external-id"},"type":"statement","id":"Q83103$DB7EF37A-BB80-49BD-B525-2A3EB6350F19","rank":"normal"}],"P114":[{"mainsnak":{"snaktype":"value","property":"P114","hash":"251fd109c2cd8c1ee39b48cd109c9f4b1c9fcf5c","datavalue":{"value":{"entity-type":"item","numeric-id":13519,"id":"Q13519"},"type":"wikibase-entityid"},"datatype":"wikibase-item"},"type":"statement","id":"Q83103$15D67224-27B2-45F4-976A-E2C03382BE24","rank":"normal"}],"P170":[{"mainsnak":{"snaktype":"value","property":"P170","hash":"a5c7f43e4706376467fbc2398f81013a4063d07e","datavalue":{"value":{"time":"+2023-09-15T00:00:00Z","timezone":0,"before":0,"after":0,"precision":11,"calendarmodel":"http://www.wikidata.org/entity/Q1985727"},"type":"time"},"datatype":"time"},"type":"statement","id":"Q83103$C9870DAC-7C7E-4DE8-8C6F-A3A0EED18BC5","rank":"normal"}],"P1459":[{"mainsnak":{"snaktype":"value","property":"P1459","hash":"cc47581a9b2563553478564b453490a6ec1b89a3","datavalue":{"value":"Unsupervised text tokenizer focused on computational efficiency. Wraps the 'YouTokenToMe' library <https://github.com/VKCOM/YouTokenToMe> which is an implementation of fast Byte Pair Encoding (BPE) <https://aclanthology.org/P16-1162/>.","type":"string"},"datatype":"string"},"type":"statement","id":"Q83103$A02C481E-11BB-4C5D-8424-F23C8BAD86BA","rank":"normal"}],"P16":[{"mainsnak":{"snaktype":"value","property":"P16","hash":"161aa4f1b7cff8351dc2c6ad0e543542f351fbbf","datavalue":{"value":{"entity-type":"item","numeric-id":83102,"id":"Q83102"},"type":"wikibase-entityid"},"datatype":"wikibase-item"},"type":"statement","id":"Q83103$CDDE4C15-167A-4473-B6F3-056BD50DA38E","rank":"normal"}],"P163":[{"mainsnak":{"snaktype":"value","property":"P163","hash":"e833327f863f180e0294a5061420c182fb40052a","datavalue":{"value":{"entity-type":"item","numeric-id":56821,"id":"Q56821"},"type":"wikibase-entityid"},"datatype":"wikibase-item"},"type":"statement","id":"Q83103$571A0650-919E-4996-86D0-D5631EBED4EF","rank":"normal"}],"P585":[{"mainsnak":{"snaktype":"value","property":"P585","hash":"d595b9251c15d55b682bbb22e27ac12f91c3ba38","datavalue":{"value":{"entity-type":"item","numeric-id":20394,"id":"Q20394"},"type":"wikibase-entityid"},"datatype":"wikibase-item"},"type":"statement","qualifiers":{"P132":[{"snaktype":"value","property":"P132","hash":"1520c8e2cd338f55d57f9169eb44a375ecafc28d","datavalue":{"value":"\u2265 0.11.5","type":"string"},"datatype":"string"}]},"qualifiers-order":["P132"],"id":"Q83103$8E3C88FF-868A-4481-81A5-2247AFA58F65","rank":"normal"}],"P342":[{"mainsnak":{"snaktype":"value","property":"P342","hash":"fe12f5e01d046912e5e7daea96ad81df7a13e944","datavalue":{"value":{"entity-type":"item","numeric-id":13519,"id":"Q13519"},"type":"wikibase-entityid"},"datatype":"wikibase-item"},"type":"statement","qualifiers":{"P132":[{"snaktype":"value","property":"P132","hash":"fca10554373f264859696efd898e7d44319afdac","datavalue":{"value":"\u2265 2.10","type":"string"},"datatype":"string"}]},"qualifiers-order":["P132"],"id":"Q83103$A1F57E65-0BC3-4216-8194-A9FC81CDADEC","rank":"normal"}],"P1460":[{"mainsnak":{"snaktype":"value","property":"P1460","hash":"908c3454b3659c4b140ccce33c5aee31081edc8d","datavalue":{"value":{"entity-type":"item","numeric-id":5976450,"id":"Q5976450"},"type":"wikibase-entityid"},"datatype":"wikibase-item"},"type":"statement","id":"Q83103$33766122-C78B-4D34-A5A5-4EBB7745155C","rank":"normal"}]},"sitelinks":{"mardi":{"site":"mardi","title":"Tokenizers.bpe","badges":[]}}}}}