{"id":5524,"date":"2024-09-30T05:15:00","date_gmt":"2024-09-29T20:15:00","guid":{"rendered":"https:\/\/devneko.jp\/wordpress\/?p=5524"},"modified":"2024-09-30T05:15:00","modified_gmt":"2024-09-29T20:15:00","slug":"emma-500-eurollm","status":"publish","type":"post","link":"https:\/\/devneko.jp\/wordpress\/?p=5524","title":{"rendered":"EMMA-500, EuroLLM"},"content":{"rendered":"\n<p>\u30de\u30eb\u30c1\u30ea\u30f3\u30ac\u30eb\u3055\u3092\u7279\u5fb4\u3068\u3059\u308bLLM\u306e\u958b\u767a\u3082\u884c\u308f\u308c\u3066\u3044\u308b\u3002<\/p>\n\n\n\n<ul class=\"wp-block-list\">\n<li><strong>EMMA-500: Enhancing Massively Multilingual Adaptation of Large Language Models\u00a0<\/strong>[50.5]<br>EMMA-500\u306f546\u8a00\u8a9e\u306b\u308f\u305f\u308b\u30c6\u30ad\u30b9\u30c8\u3067\u7d99\u7d9a\u8a13\u7df4\u3055\u308c\u305f\u5927\u898f\u6a21\u591a\u8a00\u8a9e\u8a00\u8a9e\u30e2\u30c7\u30eb\u3067\u3042\u308b\u3002 \u672c\u7d50\u679c\u306f,\u5927\u898f\u6a21\u8a00\u8a9e\u30e2\u30c7\u30eb\u306e\u8a00\u8a9e\u80fd\u529b\u62e1\u5927\u306b\u304a\u3051\u308b\u7d99\u7d9a\u4e8b\u524d\u5b66\u7fd2\u306e\u6709\u52b9\u6027\u3092\u5f37\u8abf\u3057\u305f\u3002<br><a href=\"http:\/\/arxiv.org\/abs\/2409.17892v1\">\u8ad6\u6587<\/a>\u00a0\u00a0<a href=\"https:\/\/fugumt.com\/fugumt\/paper_check\/2409.17892v1\">\u53c2\u8003\u8a33\uff08\u30e1\u30bf\u30c7\u30fc\u30bf\uff09<\/a>\u00a0 \u00a0(Thu, 26 Sep 2024 14:40:45 GMT)<\/li>\n\n\n\n<li>\u00a0MaLA Corpus\u00a0\uff08It contains 939 languages, 546 of which have more than 100k tokens and are used for training our EMMA-500 model, and 74 billion (B) whitespace delimited tokens in total.\uff09\u3068\u305d\u308c\u3092\u6d3b\u7528\u3057\u305fLlama 2-based\u306aLLM EMMA-500\u3001240\u8a00\u8a9e\u3092\u5bfe\u8c61\u3068\u3057\u305f\u30d9\u30f3\u30c1\u30de\u30fc\u30afPolyWrite\u00a0\u306e\u63d0\u6848\u3002<\/li>\n\n\n\n<li>\u30ea\u30dd\u30b8\u30c8\u30ea\u306f<a href=\"https:\/\/huggingface.co\/MaLA-LM\">MaLA-LM (MaLA-LM) (huggingface.co)<\/a><\/li>\n<\/ul>\n\n\n\n<ul class=\"wp-block-list\">\n<li><strong>EuroLLM: Multilingual Language Models for Europe\u00a0<\/strong>[76.9]<br>\u30aa\u30fc\u30d7\u30f3\u30a6\u30a7\u30a4\u30c8\u306a\u591a\u8a00\u8a9eLLM\u306e\u958b\u767a\u3092\u76ee\u7684\u3068\u3057\u305fEuroLLM\u30d7\u30ed\u30b8\u30a7\u30af\u30c8\u3092\u7d39\u4ecb\u3057\u305f\u3002 \u3053\u308c\u307e\u3067\u306e\u9032\u6357\u72b6\u6cc1\u3092\u6982\u8aac\u3057\u3001\u30c7\u30fc\u30bf\u53ce\u96c6\u3068\u30d5\u30a3\u30eb\u30bf\u30ea\u30f3\u30b0\u30d7\u30ed\u30bb\u30b9\u306b\u3064\u3044\u3066\u8a73\u8ff0\u3059\u308b\u3002 \u30de\u30eb\u30c1\u30ea\u30f3\u30ac\u30eb\u30fb\u30b8\u30a7\u30cd\u30e9\u30eb\u30fb\u30d9\u30f3\u30c1\u30de\u30fc\u30af\u3068\u6a5f\u68b0\u7ffb\u8a33\u306e\u6027\u80fd\u306b\u3064\u3044\u3066\u5831\u544a\u3059\u308b\u3002<br><a href=\"http:\/\/arxiv.org\/abs\/2409.16235v1\">\u8ad6\u6587<\/a>\u00a0\u00a0<a href=\"https:\/\/fugumt.com\/fugumt\/paper_check\/2409.16235v1\">\u53c2\u8003\u8a33\uff08\u30e1\u30bf\u30c7\u30fc\u30bf\uff09<\/a>\u00a0 \u00a0(Tue, 24 Sep 2024 16:51:36 GMT)<\/li>\n\n\n\n<li>\u300cEuroLLM project with the goal of creating a suite of LLMs capable of understanding and generating text in all European Union languages (Bulgarian, Croatian, Czech, Danish, Dutch, English, Estonian, Finnish, French, German, Greek, Hungarian, Irish, Italian, Latvian, Lithuanian, Maltese, Polish, Portuguese, Romanian, Slovak, Slovenian, Spanish, and Swedish) as well as some additional relevant languages (Arabic, Catalan, Chinese, Galician, Hindi, Japanese, Korean, Norwegian, Russian, Turkish, and Ukrainian).\u300d\u3068\u3044\u3046LLM\u69cb\u7bc9\u30d7\u30ed\u30b8\u30a7\u30af\u30c8\u306e\u7d39\u4ecb\u3002\u898f\u6a21\u306f\u5c0f\u3055\u3044\u3082\u306e\u306e\u6a5f\u68b0\u7ffb\u8a33\u3067\u306e\u6027\u80fd\u306f\u60aa\u304f\u306a\u3055\u305d\u3046\uff1f<\/li>\n\n\n\n<li>\u30ea\u30dd\u30b8\u30c8\u30ea\u306f<a href=\"https:\/\/huggingface.co\/collections\/utter-project\/eurollm-66b2bd5402f755e41c5d9c6d\">EuroLLM &#8211; a utter-project Collection (huggingface.co)<\/a><\/li>\n<\/ul>\n","protected":false},"excerpt":{"rendered":"<p>\u30de\u30eb\u30c1\u30ea\u30f3\u30ac\u30eb\u3055\u3092\u7279\u5fb4\u3068\u3059\u308bLLM\u306e\u958b\u767a\u3082\u884c\u308f\u308c\u3066\u3044\u308b\u3002<\/p>\n","protected":false},"author":1,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[2],"tags":[223,267],"class_list":["post-5524","post","type-post","status-publish","format-standard","hentry","category-arxiv","tag-llm","tag-multilingual"],"_links":{"self":[{"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=\/wp\/v2\/posts\/5524","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Fcomments&post=5524"}],"version-history":[{"count":0,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=\/wp\/v2\/posts\/5524\/revisions"}],"wp:attachment":[{"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=5524"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=5524"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=5524"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}