{"id":145,"date":"2025-11-12T00:35:36","date_gmt":"2025-11-12T00:35:36","guid":{"rendered":"https:\/\/reomoana.com\/wp\/?page_id=145"},"modified":"2025-12-09T23:56:06","modified_gmt":"2025-12-09T23:56:06","slug":"reo-moana-small-language-model","status":"publish","type":"page","link":"https:\/\/reomoana.com\/wp\/reo-moana-code-works\/reo-moana-small-language-model\/","title":{"rendered":"Reo Moana Small Language Model"},"content":{"rendered":"\n<h2 class=\"wp-block-heading\">The Reo Moana Small Language Model Development Has Begun!<\/h2>\n\n\n<style>.kb-row-layout-id145_e4f358-1f > .kt-row-column-wrap{align-content:start;}:where(.kb-row-layout-id145_e4f358-1f > .kt-row-column-wrap) > .wp-block-kadence-column{justify-content:start;}.kb-row-layout-id145_e4f358-1f > .kt-row-column-wrap{column-gap:var(--global-kb-gap-md, 2rem);row-gap:var(--global-kb-gap-md, 2rem);padding-top:var(--global-kb-spacing-sm, 1.5rem);padding-bottom:var(--global-kb-spacing-sm, 1.5rem);grid-template-columns:minmax(0, 2fr) minmax(0, 1fr);}.kb-row-layout-id145_e4f358-1f > .kt-row-layout-overlay{opacity:0.30;}@media all and (max-width: 1024px){.kb-row-layout-id145_e4f358-1f > .kt-row-column-wrap{grid-template-columns:minmax(0, 2fr) minmax(0, 1fr);}}@media all and (max-width: 767px){.kb-row-layout-id145_e4f358-1f > .kt-row-column-wrap{grid-template-columns:minmax(0, 1fr);}}<\/style><div class=\"kb-row-layout-wrap kb-row-layout-id145_e4f358-1f alignnone wp-block-kadence-rowlayout\"><div class=\"kt-row-column-wrap kt-has-2-columns kt-row-layout-left-golden kt-tab-layout-inherit kt-mobile-layout-row kt-row-valign-top\">\n<style>.kadence-column145_8d7732-e2 > .kt-inside-inner-col,.kadence-column145_8d7732-e2 > .kt-inside-inner-col:before{border-top-left-radius:0px;border-top-right-radius:0px;border-bottom-right-radius:0px;border-bottom-left-radius:0px;}.kadence-column145_8d7732-e2 > .kt-inside-inner-col{column-gap:var(--global-kb-gap-sm, 1rem);}.kadence-column145_8d7732-e2 > .kt-inside-inner-col{flex-direction:column;}.kadence-column145_8d7732-e2 > .kt-inside-inner-col > .aligncenter{width:100%;}.kadence-column145_8d7732-e2 > .kt-inside-inner-col:before{opacity:0.3;}.kadence-column145_8d7732-e2{position:relative;}@media all and (max-width: 1024px){.kadence-column145_8d7732-e2 > .kt-inside-inner-col{flex-direction:column;justify-content:center;}}@media all and (max-width: 767px){.kadence-column145_8d7732-e2 > .kt-inside-inner-col{flex-direction:column;justify-content:center;}}<\/style>\n<div class=\"wp-block-kadence-column kadence-column145_8d7732-e2\"><div class=\"kt-inside-inner-col\">\n<p>We are proud to announce that we have begun development of the Reo Moana Small Language Model (SLM)! We are collecting, cleaning, collating, and organizing data and hope to begin our first round of training soon. We are not yet prepared to share details on this system, but will say that it will not be built on a foundation model and trained exclusively on text in the Indigenous languages of Polynesia, beginning with \u02bb\u014dlelo Hawai\u02bbi. We are also spending considerable time and effort on establishing guidelines for ethical use of the data we have and will collect.<\/p>\n<\/div><\/div>\n\n\n<style>.kadence-column145_a2df59-fe > .kt-inside-inner-col,.kadence-column145_a2df59-fe > .kt-inside-inner-col:before{border-top-left-radius:0px;border-top-right-radius:0px;border-bottom-right-radius:0px;border-bottom-left-radius:0px;}.kadence-column145_a2df59-fe > .kt-inside-inner-col{column-gap:var(--global-kb-gap-sm, 1rem);}.kadence-column145_a2df59-fe > .kt-inside-inner-col{flex-direction:column;}.kadence-column145_a2df59-fe > .kt-inside-inner-col > .aligncenter{width:100%;}.kadence-column145_a2df59-fe > .kt-inside-inner-col:before{opacity:0.3;}.kadence-column145_a2df59-fe{position:relative;}@media all and (max-width: 1024px){.kadence-column145_a2df59-fe > .kt-inside-inner-col{flex-direction:column;justify-content:center;}}@media all and (max-width: 767px){.kadence-column145_a2df59-fe > .kt-inside-inner-col{flex-direction:column;justify-content:center;}}<\/style>\n<div class=\"wp-block-kadence-column kadence-column145_a2df59-fe\"><div class=\"kt-inside-inner-col\">\n<figure class=\"wp-block-image size-full is-resized\"><img loading=\"lazy\" decoding=\"async\" width=\"800\" height=\"600\" src=\"http:\/\/reomoana.com\/wp\/wp-content\/uploads\/2025\/12\/RMSLM.png\" alt=\"\" class=\"wp-image-170\" style=\"width:245px;height:auto\" srcset=\"https:\/\/reomoana.com\/wp\/wp-content\/uploads\/2025\/12\/RMSLM.png 800w, https:\/\/reomoana.com\/wp\/wp-content\/uploads\/2025\/12\/RMSLM-300x225.png 300w, https:\/\/reomoana.com\/wp\/wp-content\/uploads\/2025\/12\/RMSLM-768x576.png 768w\" sizes=\"auto, (max-width: 800px) 100vw, 800px\" \/><\/figure>\n<\/div><\/div>\n\n<\/div><\/div>\n\n\n<p>Most commercial LLMs have limited knowledge of languages like Hawaiian, M\u0101ori, Tahitian, and other Polynesian languages Their training data is dominated by English and other major languages. The texts that are accessible by these systems are not optimally organized for their training, often has inconsistent use of diacritics and other issues that lead to inaccurate results for these Pacific languages. By meticulously training on these languages, using high-quality, culturally relevant texts, we believe there is potential to produce superior results. The Reo Moana SLM will have a genuine understanding of the languages&#8217; structures, nuance, and cultural context, enabling accurate and meaningful communication.<\/p>\n\n\n\n<p>We acknowledge we are not the first to point our wa\u2018a\/waka\/vaka (canoe) in this direction. We do not consider this a race, but a collaborative \u2018imi loa (long search) to ensure the perpetuation and growth of these languages. Our gratitude to our colleagues across the Pacific who have inspired us to join in this journey:<\/p>\n\n\n\n<ul class=\"wp-block-list\">\n<li><a href=\"https:\/\/tehiku.nz\/\" data-type=\"link\" data-id=\"https:\/\/tehiku.nz\/\">Te Hiku Media<\/a> (Aotearoa)<\/li>\n\n\n\n<li><a href=\"https:\/\/www.jesus.ox.ac.uk\/about-jesus-college\/our-community\/people\/dr-oiwi-parker-jones\/\">Dr. \u2018\u014ciwi Parker-Jones<\/a> (Oxford University)<\/li>\n\n\n\n<li><a href=\"https:\/\/profiles.auckland.ac.nz\/p-keegan\/about\">Dr. Peter Keegan<\/a> (University of Auckland)<\/li>\n\n\n\n<li><a href=\"https:\/\/profiles.waikato.ac.nz\/tetaka.keegan\">Te Taka Keegan<\/a> (University of Waikato)<\/li>\n\n\n\n<li><a href=\"https:\/\/www.taiuru.co.nz\/about-taiuru-associates\/\">Karatiana Taiuru<\/a> (Aotearoa)<\/li>\n\n\n\n<li><a href=\"https:\/\/www.huri-translations.pf\/\">Huri Translations<\/a> (M\u0101\u2018ohi Nui)<\/li>\n<\/ul>\n\n\n\n<p>We aspire to meet the lofty expectations of those whose ancestors spoke, preserved, and transmitted the languages to today&#8217;s language and cultural communities, and are aligning our work to meet their standards for ethical use of their languages.<\/p>\n\n\n\n<p><\/p>\n","protected":false},"excerpt":{"rendered":"<p>The Reo Moana Small Language Model Development Has Begun! We are proud to announce that we have begun development of the Reo Moana Small Language Model (SLM)! We are collecting, cleaning, collating, and organizing data and hope to begin our first round of training soon. We are not yet prepared to share details on this&#8230;<\/p>\n","protected":false},"author":1,"featured_media":0,"parent":110,"menu_order":0,"comment_status":"closed","ping_status":"closed","template":"","meta":{"_kadence_starter_templates_imported_post":false,"_kad_post_transparent":"","_kad_post_title":"","_kad_post_layout":"","_kad_post_sidebar_id":"","_kad_post_content_style":"","_kad_post_vertical_padding":"","_kad_post_feature":"","_kad_post_feature_position":"","_kad_post_header":false,"_kad_post_footer":false,"_kad_post_classname":"","footnotes":""},"class_list":["post-145","page","type-page","status-publish","hentry"],"_links":{"self":[{"href":"https:\/\/reomoana.com\/wp\/wp-json\/wp\/v2\/pages\/145","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/reomoana.com\/wp\/wp-json\/wp\/v2\/pages"}],"about":[{"href":"https:\/\/reomoana.com\/wp\/wp-json\/wp\/v2\/types\/page"}],"author":[{"embeddable":true,"href":"https:\/\/reomoana.com\/wp\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/reomoana.com\/wp\/wp-json\/wp\/v2\/comments?post=145"}],"version-history":[{"count":19,"href":"https:\/\/reomoana.com\/wp\/wp-json\/wp\/v2\/pages\/145\/revisions"}],"predecessor-version":[{"id":180,"href":"https:\/\/reomoana.com\/wp\/wp-json\/wp\/v2\/pages\/145\/revisions\/180"}],"up":[{"embeddable":true,"href":"https:\/\/reomoana.com\/wp\/wp-json\/wp\/v2\/pages\/110"}],"wp:attachment":[{"href":"https:\/\/reomoana.com\/wp\/wp-json\/wp\/v2\/media?parent=145"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}