{"id":4077,"date":"2026-08-31T08:46:07","date_gmt":"2026-08-31T06:46:07","guid":{"rendered":"https:\/\/clarin-lt.lt\/?p=4077"},"modified":"2026-08-31T08:46:08","modified_gmt":"2026-08-31T06:46:08","slug":"successful-completion-of-an-inter-institutional-project","status":"publish","type":"post","link":"https:\/\/clarin-lt.lt\/?p=4077","title":{"rendered":"Successful Completion of an Inter-Institutional Project"},"content":{"rendered":"\n
\"\"<\/a><\/figure>\n\n\n\n

From December 2024 to April 2026, the State Digital Solution Agency (SDSA)<\/a> implemented the project \u2018Creation of the General Lithuanian Language Corpus and Vectorised Models\u2019<\/a> (project code: 02-103-P-0001) in which researchers from the VDU Institute of Digital Resources and Interdisciplinary Research<\/a>, together with their business partners \u2013 UAB \u2018Neurotechnology\u2019<\/a>, UAB \u2018Tilde IT\u2019<\/a>, and MB \u2018Krilas\u2019<\/a> \u2013 developed artificial intelligence solutions of national significance.<\/p>\n\n\n\n

The SDSA project manager is A. Rakauskas, and the supplier group leader is Assoc. Prof. Dr Andrius Utka<\/a>.<\/p>\n\n\n\n

Project outcomes:<\/p>\n\n\n\n

\u25cf The <\/strong>General Lithuanian Language Corpus (BLKT)<\/strong><\/a> consists of original human-authored texts, the corpus size is 3.9 billion words, and the text types include Media texts (52.28%), Documents (38.29%), Non-fiction (7.08%), Speech (2.04%), and Fiction (0.30%).<\/p>\n\n\n\n

\u25cf The Small Lithuanian Language Vectorised Model (LT-MLKM-modernBERT)<\/strong><\/a> is a Lithuanian masked language model (MLM) built on the ModernBERT<\/em> architecture and pre-trained on the BLKT Lithuanian Text Corpus Stage 3<\/em>, comprising over 1.87 billion words. This model is available on the Hugging Face<\/em> platform at: https:\/\/huggingface.co\/VSSA-SDSA\/LT-MLKM-modernBERT<\/a>.<\/p>\n\n\n\n

\u25cf The Large Lithuanian Language Vectorised Model (DLKVM)<\/strong> was built using Llama 3<\/em> architecture principles and trained on 3.9 billion words from the BLKT corpus. This model is available on the Hugging Face<\/em> platform at: https:\/\/huggingface.co\/datasets\/VSSA-SDSA\/LT_AI_DLKVM<\/a>.<\/p>\n\n\n\n

More information can be found in this text: \u2018A consortium led by VDU has developed a Lithuanian language corpus and two artificial intelligence models\u2019<\/a>. The article explains the project’s purpose as well as its importance for Lithuania, offers insights into the model development process, and presents the contributions of the partners involved in the project.<\/p>\n\n\n\n

Further information about the project is available:<\/p>\n\n\n\n

On the CLARIN-LT repository https:\/\/clarin-repo.lt\/server\/api\/core\/bitstreams\/a2073e11-9c22-4aca-bfee-b2c60954f2a6\/content<\/a><\/p>\n\n\n\n

On the VDU SITTI Institute\u2019s website https:\/\/sitti.vdu.lt\/bendrasis-lietuviu-kalbos-tekstynas-ir-vektorizuoti-modeliai\/<\/a><\/p>\n\n\n\n

On the VSSA website https:\/\/vssa.lrv.lt\/lt\/apie-vssa\/projektai\/bendrojo-lietuviu-kalbos-tekstyno-ir-vektorizuotu-modeliu-sukurimas\/<\/a><\/p>\n\n\n\n

Follow CLARIN-LT news on our Facebook account<\/a> and website<\/a>.<\/p>\n\n\n\n

\"\"<\/a><\/figure>\n","protected":false},"excerpt":{"rendered":"

From December 2024 to April 2026, the State Digital Solution Agency (SDSA) implemented the project \u2018Creation of the General Lithuanian Language Corpus and Vectorised Models\u2019 (project code: 02-103-P-0001) in which researchers from the VDU Institute of Digital Resources and Interdisciplinary…<\/span><\/p>\n

Read more ›<\/a><\/div>\n

<\/p>\n","protected":false},"author":7,"featured_media":4078,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[1],"tags":[],"class_list":["post-4077","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-uncategorized"],"_links":{"self":[{"href":"https:\/\/clarin-lt.lt\/index.php?rest_route=\/wp\/v2\/posts\/4077","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/clarin-lt.lt\/index.php?rest_route=\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/clarin-lt.lt\/index.php?rest_route=\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/clarin-lt.lt\/index.php?rest_route=\/wp\/v2\/users\/7"}],"replies":[{"embeddable":true,"href":"https:\/\/clarin-lt.lt\/index.php?rest_route=%2Fwp%2Fv2%2Fcomments&post=4077"}],"version-history":[{"count":6,"href":"https:\/\/clarin-lt.lt\/index.php?rest_route=\/wp\/v2\/posts\/4077\/revisions"}],"predecessor-version":[{"id":4084,"href":"https:\/\/clarin-lt.lt\/index.php?rest_route=\/wp\/v2\/posts\/4077\/revisions\/4084"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/clarin-lt.lt\/index.php?rest_route=\/wp\/v2\/media\/4078"}],"wp:attachment":[{"href":"https:\/\/clarin-lt.lt\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=4077"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/clarin-lt.lt\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=4077"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/clarin-lt.lt\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=4077"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}