{"id":118790,"date":"2024-08-01T15:43:32","date_gmt":"2024-08-01T13:43:32","guid":{"rendered":"https:\/\/prohoster.info\/blog\/novosti-interneta\/google-predstavila-kompaktnuyu-yazykovuyu-model-gemma-2-2b-kotoraya-prevoshodit-gpt-3-5-turbo"},"modified":"2024-08-01T15:43:32","modified_gmt":"2024-08-01T13:43:32","slug":"google-predstavila-kompaktnuyu-yazykovuyu-model-gemma-2-2b-kotoraya-prevoshodit-gpt-3-5-turbo","status":"publish","type":"post","link":"https:\/\/prohoster.info\/pt\/blog\/news\/google-predstavila-kompaktnuyu-yazykovuyu-model-gemma-2-2b-kotoraya-prevoshodit-gpt-3-5-turbo","title":{"rendered":"O Google apresentou o modelo de linguagem compacto Gemma 2 2B, que supera o GPT 3.5 Turbo.","gt_translate_keys":[{"key":"rendered","format":"text"}]},"content":{"rendered":"<p>A empresa Google <noindex><a rel=\"nofollow noopener\" href=\"https:\/\/developers.googleblog.com\/en\/smaller-safer-more-transparent-advancing-responsible-ai-with-gemma\/\" target=\"_blank\">apresentou<\/a><\/noindex> Gemma 2 2B \u2014 um modelo de linguagem de intelig\u00eancia artificial (LLM) compacto, mas poderoso, que pode competir com os l\u00edderes do setor, apesar do seu tamanho significativamente menor. O novo modelo de linguagem, com apenas 2,6 bilh\u00f5es de par\u00e2metros, demonstra desempenho semelhante a modelos muito maiores, incluindo OpenAI GPT-3.5 e Mistral AI Mixtral 8x7B.<\/p>\n<p><center><\/center> \t\t\t\t  <img decoding=\"async\" alt=\"O Google apresentou o modelo de linguagem compacto Gemma 2 2B, que supera o GPT 3.5 Turbo.\" src=\"\/wp-content\/uploads\/2024\/08\/bf57e46081c2b08f8962c4d021622033.jpg\" style=\"display:block;margin: 0 auto;\" \/>    <\/p>\n<p>No teste LMSYS Chatbot Arena, uma popular plataforma online para testes comparativos e avalia\u00e7\u00e3o da qualidade de modelos de intelig\u00eancia artificial, o Gemma 2 2B obteve 1130 pontos. Esse resultado ligeiramente supera os resultados do GPT-3.5-Turbo-0613 (1117 pontos) e Mixtral-8x7B (1114 pontos) \u2014 modelos que possuem dez vezes mais par\u00e2metros.<\/p>\n<p> <img decoding=\"async\" alt=\"O Google apresentou o modelo de linguagem compacto Gemma 2 2B, que supera o GPT 3.5 Turbo.\" src=\"\/wp-content\/uploads\/2024\/08\/bfe952fb8eff5abf88d67f7b1a06a1d4.png\" style=\"display:block;margin: 0 auto;\" \/> <\/p>\n<p>O Google informa que a Gemma 2 2B tamb\u00e9m alcan\u00e7ou 56,1 pontos no teste MMLU (Massive Multitask Language Understanding) e 36,6 pontos no teste MBPP (Mostly Basic Python Programming), o que representa uma melhoria significativa em rela\u00e7\u00e3o \u00e0 vers\u00e3o anterior. <\/p>\n<p><center><\/center> <\/p>\n<p>Gemma 2 2B desafia a no\u00e7\u00e3o comum de que modelos de linguagem maiores funcionam melhor do que os compactos. O desempenho da Gemma 2 2B mostra que m\u00e9todos de treinamento sofisticados, efici\u00eancia arquitet\u00f4nica e conjuntos de dados de alta qualidade podem compensar a falta de par\u00e2metros. O desenvolvimento da Gemma 2 2B tamb\u00e9m destaca a crescente import\u00e2ncia de m\u00e9todos de compress\u00e3o e destila\u00e7\u00e3o de modelos de IA. A capacidade de compilar informa\u00e7\u00f5es de modelos maiores em modelos menores abre possibilidades para a cria\u00e7\u00e3o de ferramentas de IA mais acess\u00edveis, sem sacrificar o desempenho.<\/p>\n<p>O Google treinou a Gemma 2 2B em um vasto conjunto de dados de 2 trilh\u00f5es de tokens, utilizando sistemas baseados em seus aceleradores de IA TPU v5e. O suporte a v\u00e1rios idiomas amplia seu potencial para aplica\u00e7\u00e3o em diversas aplica\u00e7\u00f5es globais. O modelo Gemma 2 2B \u00e9 de c\u00f3digo aberto. Pesquisadores e desenvolvedores podem acessar o modelo atrav\u00e9s da plataforma <noindex><a rel=\"nofollow noopener\" href=\"https:\/\/huggingface.co\/spaces\/huggingface-projects\/gemma-2-2b-it\" target=\"_blank\">Hugging Face<\/a><\/noindex>. Ele tamb\u00e9m oferece suporte a v\u00e1rias estruturas, incluindo <noindex><a rel=\"nofollow noopener\" href=\"https:\/\/huggingface.co\/google\/gemma-2-2b-it\" target=\"_blank\">PyTorch<\/a><\/noindex> e <noindex><a rel=\"nofollow noopener\" href=\"https:\/\/huggingface.co\/google\/gemma-2-2b-it\" target=\"_blank\">TensorFlow<\/a><\/noindex>.<\/p>\n<p><strong>Fonte:<\/strong><\/p>\n<ul class=\"related\">\n<li><noindex><a rel=\"nofollow noopener\" href=\"http:\/\/venturebeat.com\/\" target=\"_blank\" title=\"Venture Beat\">Venture Beat<\/a><\/noindex><\/li>\n<\/ul>\n<p> \t       <center>     <center>    <\/center>     <center>   <\/center>     <\/center>  <center>     <\/center>                \t\t\t \t\t\t\t<center> \t\t\t\t     \t\t\t\t<\/center><br \/>Fonte: <a content=\"nofollow\" rel=\"nofollow\" href=\"https:\/\/3dnews.ru\/1108849\">3dnews.ru<\/a> <\/p>","protected":false,"gt_translate_keys":[{"key":"rendered","format":"html"}]},"excerpt":{"rendered":"<p>\u041a\u043e\u043c\u043f\u0430\u043d\u0438\u044f Google \u043f\u0440\u0435\u0434\u0441\u0442\u0430\u0432\u0438\u043b\u0430 Gemma 2 2B &mdash; \u043a\u043e\u043c\u043f\u0430\u043a\u0442\u043d\u0443\u044e, \u043d\u043e \u043c\u043e\u0449\u043d\u0443\u044e \u044f\u0437\u044b\u043a\u043e\u0432\u0443\u044e \u043c\u043e\u0434\u0435\u043b\u044c \u0438\u0441\u043a\u0443\u0441\u0441\u0442\u0432\u0435\u043d\u043d\u043e\u0433\u043e \u0438\u043d\u0442\u0435\u043b\u043b\u0435\u043a\u0442\u0430 (LLM), \u043a\u043e\u0442\u043e\u0440\u0430\u044f \u043c\u043e\u0436\u0435\u0442 \u0441\u043e\u0441\u0442\u0430\u0432\u0438\u0442\u044c \u043a\u043e\u043d\u043a\u0443\u0440\u0435\u043d\u0446\u0438\u044e \u043b\u0438\u0434\u0435\u0440\u0430\u043c \u043e\u0442\u0440\u0430\u0441\u043b\u0438, \u043d\u0435\u0441\u043c\u043e\u0442\u0440\u044f \u043d\u0430 \u0441\u0432\u043e\u0439 \u0437\u043d\u0430\u0447\u0438\u0442\u0435\u043b\u044c\u043d\u043e \u043c\u0435\u043d\u044c\u0448\u0438\u0439 \u0440\u0430\u0437\u043c\u0435\u0440. \u041d\u043e\u0432\u0430\u044f \u044f\u0437\u044b\u043a\u043e\u0432\u0430\u044f \u043c\u043e\u0434\u0435\u043b\u044c, \u0441\u043e\u0434\u0435\u0440\u0436\u0430\u0449\u0430\u044f \u0432\u0441\u0435\u0433\u043e 2,6 \u043c\u0438\u043b\u043b\u0438\u0430\u0440\u0434\u0430 \u043f\u0430\u0440\u0430\u043c\u0435\u0442\u0440\u043e\u0432, \u0434\u0435\u043c\u043e\u043d\u0441\u0442\u0440\u0438\u0440\u0443\u0435\u0442 \u043f\u0440\u043e\u0438\u0437\u0432\u043e\u0434\u0438\u0442\u0435\u043b\u044c\u043d\u043e\u0441\u0442\u044c \u043d\u0435 \u0445\u0443\u0436\u0435 \u0433\u043e\u0440\u0430\u0437\u0434\u043e \u0431\u043e\u043b\u0435\u0435 \u043a\u0440\u0443\u043f\u043d\u044b\u0445 \u0430\u043d\u0430\u043b\u043e\u0433\u043e\u0432, \u0432\u043a\u043b\u044e\u0447\u0430\u044f OpenAI GPT-3.5 \u0438 Mistral AI Mixtral 8x7B. \u0412 \u0442\u0435\u0441\u0442\u0435 LMSYS Chatbot [&hellip;]<\/p>\n","protected":false,"gt_translate_keys":[{"key":"rendered","format":"html"}]},"author":1,"featured_media":118791,"comment_status":"","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[702],"tags":[],"class_list":["post-118790","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-news"],"aioseo_notices":[],"aioseo_head":"\n\t\t<!-- All in One SEO 5.0.3 - aioseo.com -->\n\t<meta name=\"description\" content=\"\u041a\u043e\u043c\u043f\u0430\u043d\u0438\u044f Google \u043f\u0440\u0435\u0434\u0441\u0442\u0430\u0432\u0438\u043b\u0430 Gemma 2 2B.\" \/>\n\t<meta name=\"robots\" content=\"max-image-preview:large\" \/>\n\t<meta name=\"author\" content=\"Yuri Gagarin\"\/>\n\t<link rel=\"canonical\" href=\"https:\/\/prohoster.info\/pt\/blog\/news\/google-predstavila-kompaktnuyu-yazykovuyu-model-gemma-2-2b-kotoraya-prevoshodit-gpt-3-5-turbo\" \/>\n\t\t<meta name=\"generator\" content=\"All in One SEO (AIOSEO) 5.0.3\" \/>\n\t\t<meta property=\"og:locale\" content=\"pt_PT\" \/>\n\t\t<meta property=\"og:site_name\" content=\"ProHoster | \u041a\u0443\u043f\u0438\u0442\u044c \u043d\u0430\u0434\u0435\u0436\u043d\u044b\u0439 \u0445\u043e\u0441\u0442\u0438\u043d\u0433 \u0434\u043b\u044f \u0441\u0430\u0439\u0442\u043e\u0432 \u0441 \u0437\u0430\u0449\u0438\u0442\u043e\u0439 \u043e\u0442 DDoS, VPS VDS \u0441\u0435\u0440\u0432\u0435\u0440\u044b\" \/>\n\t\t<meta property=\"og:type\" content=\"article\" \/>\n\t\t<meta property=\"og:title\" content=\"\ud83e\udd47Google \u043f\u0440\u0435\u0434\u0441\u0442\u0430\u0432\u0438\u043b\u0430 \u043a\u043e\u043c\u043f\u0430\u043a\u0442\u043d\u0443\u044e \u044f\u0437\u044b\u043a\u043e\u0432\u0443\u044e \u043c\u043e\u0434\u0435\u043b\u044c Gemma 2 2B, \u043a\u043e\u0442\u043e\u0440\u0430\u044f \u043f\u0440\u0435\u0432\u043e\u0441\u0445\u043e\u0434\u0438\u0442 GPT 3.5 Turbo | ProHoster\" \/>\n\t\t<meta property=\"og:description\" content=\"\u041a\u043e\u043c\u043f\u0430\u043d\u0438\u044f Google \u043f\u0440\u0435\u0434\u0441\u0442\u0430\u0432\u0438\u043b\u0430 Gemma 2 2B.\" \/>\n\t\t<meta property=\"og:url\" content=\"https:\/\/prohoster.info\/pt\/blog\/news\/google-predstavila-kompaktnuyu-yazykovuyu-model-gemma-2-2b-kotoraya-prevoshodit-gpt-3-5-turbo\" \/>\n\t\t<meta property=\"og:image\" content=\"https:\/\/prohoster.info\/wp-content\/uploads\/2021\/11\/logo-350.jpg\" \/>\n\t\t<meta property=\"og:image:secure_url\" content=\"https:\/\/prohoster.info\/wp-content\/uploads\/2021\/11\/logo-350.jpg\" \/>\n\t\t<meta property=\"og:image:width\" content=\"350\" \/>\n\t\t<meta property=\"og:image:height\" content=\"350\" \/>\n\t\t<meta property=\"article:published_time\" content=\"2024-08-01T13:43:32+00:00\" \/>\n\t\t<meta property=\"article:modified_time\" content=\"2024-08-01T13:43:32+00:00\" \/>\n\t\t<meta property=\"article:publisher\" content=\"https:\/\/www.facebook.com\/prohoster\" \/>\n\t\t<meta property=\"article:author\" content=\"https:\/\/www.facebook.com\/prohoster\" \/>\n\t\t<!-- All in One SEO -->\n\n","aioseo_head_json":{"title":"\ud83e\udd47Google apresentou o modelo de linguagem compacto Gemma 2 2B, que supera o GPT 3.5 Turbo | ProHoster","description":"A empresa Google apresentou a Gemma 2 2B.","canonical_url":"https:\/\/prohoster.info\/pt\/blog\/news\/google-predstavila-kompaktnuyu-yazykovuyu-model-gemma-2-2b-kotoraya-prevoshodit-gpt-3-5-turbo","robots":"max-image-preview:large","keywords":"","webmasterTools":{"miscellaneous":""},"schema":null,"og:locale":"pt_PT","og:site_name":"ProHoster | \u041a\u0443\u043f\u0438\u0442\u044c \u043d\u0430\u0434\u0435\u0436\u043d\u044b\u0439 \u0445\u043e\u0441\u0442\u0438\u043d\u0433 \u0434\u043b\u044f \u0441\u0430\u0439\u0442\u043e\u0432 \u0441 \u0437\u0430\u0449\u0438\u0442\u043e\u0439 \u043e\u0442 DDoS, VPS VDS \u0441\u0435\u0440\u0432\u0435\u0440\u044b","og:type":"article","og:title":"\ud83e\udd47Google \u043f\u0440\u0435\u0434\u0441\u0442\u0430\u0432\u0438\u043b\u0430 \u043a\u043e\u043c\u043f\u0430\u043a\u0442\u043d\u0443\u044e \u044f\u0437\u044b\u043a\u043e\u0432\u0443\u044e \u043c\u043e\u0434\u0435\u043b\u044c Gemma 2 2B, \u043a\u043e\u0442\u043e\u0440\u0430\u044f \u043f\u0440\u0435\u0432\u043e\u0441\u0445\u043e\u0434\u0438\u0442 GPT 3.5 Turbo | ProHoster","og:description":"\u041a\u043e\u043c\u043f\u0430\u043d\u0438\u044f Google \u043f\u0440\u0435\u0434\u0441\u0442\u0430\u0432\u0438\u043b\u0430 Gemma 2 2B.","og:url":"https:\/\/prohoster.info\/pt\/blog\/news\/google-predstavila-kompaktnuyu-yazykovuyu-model-gemma-2-2b-kotoraya-prevoshodit-gpt-3-5-turbo","og:image":"https:\/\/prohoster.info\/wp-content\/uploads\/2021\/11\/logo-350.jpg","og:image:secure_url":"https:\/\/prohoster.info\/wp-content\/uploads\/2021\/11\/logo-350.jpg","og:image:width":350,"og:image:height":350,"article:published_time":"2024-08-01T13:43:32+00:00","article:modified_time":"2024-08-01T13:43:32+00:00","article:publisher":"https:\/\/www.facebook.com\/prohoster","article:author":"https:\/\/www.facebook.com\/prohoster"},"aioseo_meta_data":{"post_id":"118790","title":null,"description":null,"keywords":null,"keyphrases":null,"primary_term":null,"canonical_url":null,"og_title":null,"og_description":null,"og_object_type":"default","og_image_type":"default","og_image_url":null,"og_image_width":null,"og_image_height":null,"og_image_custom_url":null,"og_image_custom_fields":null,"og_video":null,"og_custom_url":null,"og_article_section":null,"og_article_tags":null,"twitter_use_og":false,"twitter_card":"default","twitter_image_type":"default","twitter_image_url":null,"twitter_image_custom_url":null,"twitter_image_custom_fields":null,"twitter_title":null,"twitter_description":null,"schema":{"blockGraphs":[],"customGraphs":[],"default":{"data":{"Article":[],"Course":[],"Dataset":[],"FAQPage":[],"Movie":[],"Person":[],"Product":[],"ProductReview":[],"Car":[],"Recipe":[],"Service":[],"SoftwareApplication":[],"WebPage":[]},"graphName":"","isEnabled":true},"graphs":[]},"schema_type":"default","schema_type_options":null,"pillar_content":false,"robots_default":true,"robots_noindex":false,"robots_noarchive":false,"robots_nosnippet":false,"robots_nofollow":false,"robots_noimageindex":false,"robots_noodp":false,"robots_notranslate":false,"robots_max_snippet":null,"robots_max_videopreview":null,"robots_max_imagepreview":"large","priority":null,"frequency":null,"local_seo":null,"seo_analyzer_scan_date":"2026-01-23 05:13:20","breadcrumb_settings":null,"limit_modified_date":false,"reviewed_by":null,"ai":null,"created":"2026-01-23 05:13:20","updated":"2026-01-23 05:13:20","focus_keyword":null,"additional_keywords":null,"truseo_locale":null},"gt_translate_keys":[{"key":"link","format":"url"}],"_links":{"self":[{"href":"https:\/\/prohoster.info\/pt\/wp-json\/wp\/v2\/posts\/118790","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/prohoster.info\/pt\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/prohoster.info\/pt\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/prohoster.info\/pt\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/prohoster.info\/pt\/wp-json\/wp\/v2\/comments?post=118790"}],"version-history":[{"count":0,"href":"https:\/\/prohoster.info\/pt\/wp-json\/wp\/v2\/posts\/118790\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/prohoster.info\/pt\/wp-json\/wp\/v2\/media\/118791"}],"wp:attachment":[{"href":"https:\/\/prohoster.info\/pt\/wp-json\/wp\/v2\/media?parent=118790"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/prohoster.info\/pt\/wp-json\/wp\/v2\/categories?post=118790"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/prohoster.info\/pt\/wp-json\/wp\/v2\/tags?post=118790"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}