{"id":4369,"date":"2024-02-05T06:11:00","date_gmt":"2024-02-04T21:11:00","guid":{"rendered":"https:\/\/devneko.jp\/wordpress\/?p=4369"},"modified":"2024-02-05T06:11:00","modified_gmt":"2024-02-04T21:11:00","slug":"dolma%e3%81%a8olmo","status":"publish","type":"post","link":"https:\/\/devneko.jp\/wordpress\/?p=4369","title":{"rendered":"Dolma\u3068OLMo"},"content":{"rendered":"\n<p>\u30aa\u30fc\u30d7\u30f3\u306a\u30b3\u30fc\u30d1\u30b9\u3068\u305d\u308c\u3092\u7528\u3044\u305fLLM\u306e\u63d0\u6848\u3002\u30b3\u30fc\u30d1\u30b9\u306f3T tokens\u3068\u6975\u3081\u3066\u5927\u304d\u3044\uff08CommonCrawl\u304c\u30c7\u30fc\u30bf\u306e\u591a\u304f\u3092\u5360\u3081\u3066\u3044\u308b\uff09\u3002\u305d\u308c\u7528\u3044\u3066Apache-2\u306eLLM\u304c\u30ea\u30ea\u30fc\u30b9\u3055\u308c\u3066\u3044\u308b\u3002<\/p>\n\n\n\n<p>OLMo-7B\u306e\u30d9\u30f3\u30c1\u30de\u30fc\u30af\u7d50\u679c\u306fLlama-2 7B\u3092\u8d85\u3048\u3066\u304a\u308a\u975e\u5e38\u306b\u9ad8\u3044\u3002OSS\u30e9\u30a4\u30bb\u30f3\u30b9\u3067\u516c\u958b\u3055\u308c\u3066\u3044\u308b\u306e\u306f\u51c4\u304f\u3001\u30c8\u30ec\u30fc\u30cb\u30f3\u30b0\u30c7\u30fc\u30bf\u304c\u516c\u958b\u3055\u308c\u3066\u3044\u308b\u306e\u304c\u7279\u5fb4\u7684\u3002<\/p>\n\n\n\n<p>\u30c7\u30fc\u30bf\u30fb\u30e2\u30c7\u30eb\u30fb\u30b3\u30fc\u30c9\u306e\u30ea\u30dd\u30b8\u30c8\u30ea\u306f<a href=\"https:\/\/huggingface.co\/datasets\/allenai\/dolma\">allenai\/dolma \u00b7 Datasets at Hugging Face<\/a>\u3001<a href=\"https:\/\/huggingface.co\/allenai\/OLMo-7B\">allenai\/OLMo-7B \u00b7 Hugging Face<\/a>\u3001<a href=\"https:\/\/github.com\/allenai\/OLMo\">allenai\/OLMo: Modeling, training, eval, and inference code for OLMo (github.com)<\/a><\/p>\n\n\n\n<ul class=\"wp-block-list\">\n<li><strong>Dolma: an Open Corpus of Three Trillion Tokens for Language Model Pretraining Research\u00a0<\/strong>[140.6]<br>\u308f\u308c\u308f\u308c\u306f\u3001Web\u30b3\u30f3\u30c6\u30f3\u30c4\u3001\u79d1\u5b66\u8ad6\u6587\u3001\u30b3\u30fc\u30c9\u3001\u30d1\u30d6\u30ea\u30c3\u30af\u30c9\u30e1\u30a4\u30f3\u306e\u66f8\u7c4d\u3001\u30bd\u30fc\u30b7\u30e3\u30eb\u30e1\u30c7\u30a3\u30a2\u3001\u767e\u79d1\u4e8b\u5178\u306e\u7d20\u6750\u3092\u591a\u7a2e\u306b\u6df7\u305c\u3066\u69cb\u7bc9\u3057\u305f3\u5146\u306e\u82f1\u8a9e\u30b3\u30fc\u30d1\u30b9\u3067\u3042\u308bDolma\u3092\u30ea\u30ea\u30fc\u30b9\u3059\u308b\u3002 \u672c\u5831\u544a\u3067\u306f\u3001Dolma\u306e\u8a2d\u8a08\u539f\u5247\u3001\u69cb\u7bc9\u306e\u8a73\u7d30\u3001\u5185\u5bb9\u306e\u8981\u7d04\u3092\u542b\u3080\u3001Dolma\u306b\u3064\u3044\u3066\u8ff0\u3079\u308b\u3002 Dolma\u306f\u3001\u8a00\u8a9e\u30e2\u30c7\u30ea\u30f3\u30b0\u306e\u79d1\u5b66\u3092\u69cb\u7bc9\u3057\u7814\u7a76\u3059\u308b\u305f\u3081\u306b\u8a2d\u8a08\u3055\u308c\u305f\u3001\u6700\u5148\u7aef\u306e\u30aa\u30fc\u30d7\u30f3\u8a00\u8a9e\u30e2\u30c7\u30eb\u3068\u30d5\u30ec\u30fc\u30e0\u30ef\u30fc\u30af\u3067\u3042\u308bOLMo\u306e\u30c8\u30ec\u30fc\u30cb\u30f3\u30b0\u306b\u4f7f\u7528\u3055\u308c\u3066\u3044\u308b\u3002<br><a href=\"http:\/\/arxiv.org\/abs\/2402.00159v1\">\u8ad6\u6587<\/a>\u00a0\u00a0<a href=\"https:\/\/fugumt.com\/fugumt\/paper_check\/2402.00159v1\">\u53c2\u8003\u8a33\uff08\u30e1\u30bf\u30c7\u30fc\u30bf\uff09<\/a>\u00a0 \u00a0(Wed, 31 Jan 2024 20:29:50 GMT)<\/li>\n<\/ul>\n\n\n\n<ul class=\"wp-block-list\">\n<li><strong>OLMo: Accelerating the Science of Language Models&nbsp;<\/strong>[166.1]<br>\u8a00\u8a9e\u30e2\u30c7\u30eb(LM)\u306f\u3001NLP\u7814\u7a76\u3068\u5546\u7528\u88fd\u54c1\u88fd\u54c1\u306e\u4e21\u65b9\u3067\u5e83\u304f\u666e\u53ca\u3057\u3066\u3044\u308b\u3002 \u6211\u3005\u306f\u3001\u7814\u7a76\u30b3\u30df\u30e5\u30cb\u30c6\u30a3\u304c\u5f37\u529b\u3067\u771f\u306b\u30aa\u30fc\u30d7\u30f3\u306aLM\u306b\u30a2\u30af\u30bb\u30b9\u3067\u304d\u308b\u3053\u3068\u304c\u4e0d\u53ef\u6b20\u3067\u3042\u308b\u3068\u4fe1\u3058\u3066\u3044\u308b\u3002 \u3053\u306e\u30c6\u30af\u30cb\u30ab\u30eb\u30ec\u30dd\u30fc\u30c8\u306f\u3001\u6700\u5148\u7aef\u306e\u771f\u306b\u30aa\u30fc\u30d7\u30f3\u306a\u8a00\u8a9e\u30e2\u30c7\u30eb\u3067\u3042\u308bOLMo\u306e\u6700\u521d\u306e\u30ea\u30ea\u30fc\u30b9\u3092\u8a73\u8ff0\u3057\u3066\u3044\u308b\u3002<br><a href=\"http:\/\/arxiv.org\/abs\/2402.00838v1\">\u8ad6\u6587<\/a>&nbsp;&nbsp;<a href=\"https:\/\/fugumt.com\/fugumt\/paper_check\/2402.00838v1\">\u53c2\u8003\u8a33\uff08\u30e1\u30bf\u30c7\u30fc\u30bf\uff09<\/a>&nbsp; &nbsp;(Thu, 1 Feb 2024 18:28:55 GMT)<\/li>\n<\/ul>\n","protected":false},"excerpt":{"rendered":"<p>\u30aa\u30fc\u30d7\u30f3\u306a\u30b3\u30fc\u30d1\u30b9\u3068\u305d\u308c\u3092\u7528\u3044\u305fLLM\u306e\u63d0\u6848\u3002\u30b3\u30fc\u30d1\u30b9\u306f3T tokens\u3068\u6975\u3081\u3066\u5927\u304d\u3044\uff08CommonCrawl\u304c\u30c7\u30fc\u30bf\u306e\u591a\u304f\u3092\u5360\u3081\u3066\u3044\u308b\uff09\u3002\u305d\u308c\u7528\u3044\u3066Apache-2\u306eLLM\u304c\u30ea\u30ea\u30fc\u30b9\u3055\u308c\u3066\u3044\u308b\u3002 OLMo-7B\u306e\u30d9\u30f3 &hellip; <a href=\"https:\/\/devneko.jp\/wordpress\/?p=4369\" class=\"more-link\"><span class=\"screen-reader-text\">&#8220;Dolma\u3068OLMo&#8221; \u306e<\/span>\u7d9a\u304d\u3092\u8aad\u3080<\/a><\/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":[223,293],"class_list":["post-4369","post","type-post","status-publish","format-standard","hentry","category-arxiv","tag-llm","tag-oss"],"_links":{"self":[{"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=\/wp\/v2\/posts\/4369","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=4369"}],"version-history":[{"count":0,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=\/wp\/v2\/posts\/4369\/revisions"}],"wp:attachment":[{"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=4369"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=4369"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=4369"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}