{"id":114737,"date":"2024-04-03T00:25:44","date_gmt":"2024-04-02T22:25:47","guid":{"rendered":"https:\/\/prohoster.info\/blog\/novosti-interneta\/databricks-otkryl-bolshuyu-yazykovuyu-model-dbrx-operezhayushhuyu-v-testah-gpt-3-5"},"modified":"2024-04-03T00:25:44","modified_gmt":"2024-04-02T22:25:47","slug":"databricks-otkryl-bolshuyu-yazykovuyu-model-dbrx-operezhayushhuyu-v-testah-gpt-3-5","status":"publish","type":"post","link":"https:\/\/prohoster.info\/et\/blog\/news\/databricks-otkryl-bolshuyu-yazykovuyu-model-dbrx-operezhayushhuyu-v-testah-gpt-3-5","title":{"rendered":"Databricks avas suures keelemudelis DBRX, mis \u00fcletab testides GPT-3.5.","gt_translate_keys":[{"key":"rendered","format":"text"}]},"content":{"rendered":"

Ettev\u00f5te Databricks teatas suure keelemudeli DBRX avamisest, mida saab kasutada looma vestlusrobotite, mis vastavad k\u00fcsimustele loomulikus keeles, lahendavad esitatud matemaatilisi \u00fclesandeid, genereerivad sisu antud teema kohta ja loovad koodi erinevates programmeerimiskeeltes. Mudeli arendas v\u00e4lja ettev\u00f5te Mosaic ML, mille Databricks omandas 1,3 miljardi dollari eest. Treenimiseks kasutati 3072 NVIDIA H100 Tensor Core GPU klastrit. Valmis mudeli k\u00e4ivitamiseks soovitatakse 320 GB m\u00e4lu. <\/p>\n

Mudeli treenimisel kasutati MoE (mixture of experts) arhitektuuri, mis v\u00f5imaldab saada t\u00e4psemat ekspertarvustust, ning 12 TB suurust tekstide ja koodi kollektsiooni. DBRX mudeli konteksti suurus on 32 000 tokenit (tokenite arv, mida mudel suudab teksti genereerimisel t\u00f6\u00f6delda ja meeles pidada). V\u00f5rdluseks: Google Gemini ja OpenAI GPT-4 mudelite konteksti suurus on 32 000 tokenit, Google Gemma - 8 000, GPT-4 Turbo mudel - 128 000. <\/p>\n

Mudelis on 132 miljardit parameetrit ja see on jagatud 16 ekspertv\u00f5rku, millest p\u00e4ringute t\u00f6\u00f6tlemisel v\u00f5ib kasutada mitte rohkem kui 4 (iga tokeni jaoks mitte rohkem kui 36 miljardit parameetrit). V\u00f5rdluseks: GPT-4 mudel sisaldab t\u00f5en\u00e4oliselt 1,76 triljonit parameetrit, hiljuti avastatud X\/Twitter mudel Grok (X\/Twitter) - 314 miljardit, GPT-3.5 - 175 miljardit, YaLM (Yandex) - 100 miljardit, LLaMA (Meta) - 65 miljardit, GigaChat (Sber) - 29 miljardit, Gemma (Google) - 7 miljardit. <\/p>\n

Mudelit ja sellega seotud komponente levitatakse Databricks Open Model License litsentsi alusel, mis lubab kasutada, taastada, kopeerida, muuta ja luua tuletatud tooteid, kuid teatud piirangutega. N\u00e4iteks keelab litsents DBRX, tuletatud mudelite ja nende alusel saadud v\u00e4ljav\u00f5tete kasutamise teiste keelemudelite, mis ei ole DBRX, parandamiseks. Litsents keelab ka mudeli kasutamise valdkondades, mis rikuvad seadusi ja regulatiivnorme. Tuletatud mudelid peavad olema levitatud sama litsentsi alusel. Tooteid ja teenuseid, mida kasutavad enam kui 700 miljonit kasutajat kuus, kasutades on vaja eraldi luba. <\/p>\n

Loovijate v\u00e4itel \u00fcletab DBRX oma omaduste ja v\u00f5imalustega OpenAI GPT-3.5 ja Twitteri Grok-1 mudeleid ning suudab konkureerida Gemini 1.0 Pro mudeliga, kui hinnata keele m\u00f5istmise taset, programmeerimiskeeles koodi kirjutamise v\u00f5imalusi ja matemaatiliste probleemide lahendamist. M\u00f5nedes rakendustes, n\u00e4iteks SQL-p\u00e4ringute genereerimisel, on DBRX efektiivsuse osas peaaegu j\u00f5udnud GPT-4 Turbo mudeli tasemele, mis liigub turul esikohal. Lisaks iseloomustab mudelit konkurentidest v\u00e4ga kiire t\u00f6\u00f6, v\u00f5imaldades vastuste peaaegu kohest genereerimist. Eriti suudab DBRX genereerida teksti kiirusel kuni 150 m\u00e4rki sekundis \u00fche kasutaja kohta, mis on umbes kaks korda kiirem kui LLaMA2-70B mudel.

\"Databricks<\/center>
\"Databricks<\/center> <\/p>\n

Lisaks tasub m\u00e4rkida, et on avaldatud avatud suurt keelemudelit InternLM2 tehniline kirjeldus, mis jaotatakse Apache 2.0 litsentsi alusel ja on saadaval variantides, millel on 20, 7 ja 1,8 miljardit parameetrit. Mudelit arendab Shanghai tehisintellekti labor koos mitme Hiina \u00fclikooliga ja sellel on m\u00e4rkimisv\u00e4\u00e4rne omadus arvesse v\u00f5tta kuni 200K konteksti tokenit ning see toetab mitte ainult ingliskeelt, vaid ka hiinakeelt. Paljude testide k\u00e4igus on mudel \u00fcsna l\u00e4hedane GPT-4-le.

\"Databricks<\/center>
\"Databricks<\/center>
\"Databricks<\/center> <\/p>\n

Lisaks teatakse, et Mozilla arendab 84 uut maatriksi korrutamise tuuma llamafile t\u00f6\u00f6riistakomplekti jaoks, mis v\u00f5imaldab luua universaalseid k\u00e4itatavaid faile suurte masin\u00f5ppe keelemudelite (LLM) k\u00e4ivitamiseks. Muudatused on v\u00f5imaldanud oluliselt kiirendada mudelite t\u00f6\u00f6d llamafile'is CPU-l t\u00f6\u00f6tamisel. N\u00e4iteks on mudelite k\u00e4itamine llamafile'i kasutamisel n\u00fc\u00fcd 30% kuni 500% kiirem kui llama.cpp kasutamisel, s\u00f5ltuvalt keskkonnast, ja v\u00f5rreldes MKL raamatukoguga, toimub maatriksskandaalid, mis mahuvad L2 vahem\u00e4lusse, uusi rakendusi kasutades ka poole kiiremini.
\n
Allikas: opennet.ru<\/a> <\/p>","protected":false,"gt_translate_keys":[{"key":"rendered","format":"html"}]},"excerpt":{"rendered":"

\u041a\u043e\u043c\u043f\u0430\u043d\u0438\u044f Databricks \u043e\u0431\u044a\u044f\u0432\u0438\u043b\u0430 \u043e\u0431 \u043e\u0442\u043a\u0440\u044b\u0442\u0438\u0438 \u0431\u043e\u043b\u044c\u0448\u043e\u0439 \u044f\u0437\u044b\u043a\u043e\u0432\u043e\u0439 \u043c\u043e\u0434\u0435\u043b\u0438 DBRX, \u043a\u043e\u0442\u043e\u0440\u0430\u044f \u043c\u043e\u0436\u0435\u0442 \u043f\u0440\u0438\u043c\u0435\u043d\u044f\u0442\u044c\u0441\u044f \u0434\u043b\u044f \u0441\u043e\u0437\u0434\u0430\u043d\u0438\u044f \u0447\u0430\u0442\u0431\u043e\u0442\u043e\u0432, \u043e\u0442\u0432\u0435\u0447\u0430\u044e\u0449\u0438\u0445 \u043d\u0430 \u0432\u043e\u043f\u0440\u043e\u0441\u044b \u043d\u0430 \u0435\u0441\u0442\u0435\u0441\u0442\u0432\u0435\u043d\u043d\u043e\u043c \u044f\u0437\u044b\u043a\u0435, \u0440\u0435\u0448\u0430\u044e\u0449\u0438\u0445 \u043f\u0440\u0435\u0434\u043b\u043e\u0436\u0435\u043d\u043d\u044b\u0435 \u043c\u0430\u0442\u0435\u043c\u0430\u0442\u0438\u0447\u0435\u0441\u043a\u0438\u0435 \u0437\u0430\u0434\u0430\u0447\u0438, \u0441\u043f\u043e\u0441\u043e\u0431\u043d\u044b\u0445 \u0433\u0435\u043d\u0435\u0440\u0438\u0440\u043e\u0432\u0430\u0442\u044c \u043a\u043e\u043d\u0442\u0435\u043d\u0442 \u043d\u0430 \u0437\u0430\u0434\u0430\u043d\u043d\u0443\u044e \u0442\u0435\u043c\u0443 \u0438 \u0441\u043e\u0437\u0434\u0430\u0432\u0430\u0442\u044c \u043a\u043e\u0434 \u043d\u0430 \u0440\u0430\u0437\u043b\u0438\u0447\u043d\u044b\u0445 \u044f\u0437\u044b\u043a\u0430\u0445 \u043f\u0440\u043e\u0433\u0440\u0430\u043c\u043c\u0438\u0440\u043e\u0432\u0430\u043d\u0438\u044f. \u041c\u043e\u0434\u0435\u043b\u044c \u0440\u0430\u0437\u0440\u0430\u0431\u043e\u0442\u0430\u043d\u0430 \u043a\u043e\u043c\u043f\u0430\u043d\u0438\u0435\u0439 Mosaic ML, \u043a\u043e\u0442\u043e\u0440\u0430\u044f \u0431\u044b\u043b\u0430 \u043a\u0443\u043f\u043b\u0435\u043d\u0430 Databricks \u0437\u0430 1.3 \u043c\u043b\u0440\u0434 \u0434\u043e\u043b\u043b\u0430\u0440\u043e\u0432. \u0414\u043b\u044f \u043e\u0431\u0443\u0447\u0435\u043d\u0438\u044f \u0438\u0441\u043f\u043e\u043b\u044c\u0437\u043e\u0432\u0430\u043b\u0441\u044f \u043a\u043b\u0430\u0441\u0442\u0435\u0440 […]<\/p>\n","protected":false,"gt_translate_keys":[{"key":"rendered","format":"html"}]},"author":1,"featured_media":114738,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[702],"tags":[],"class_list":["post-114737","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-news"],"aioseo_notices":[],"aioseo_head":"\n\t\t\n\t\n\t\n\t\n\t\n\t\n\t\t\n\t\t\n\t\t\n\t\t\n\t\t\n\t\t\n\t\t\n\t\t\n\t\t\n\t\t\n\t\t\n\t\t\n\t\t\n\t\t\n\t\t\n\n","aioseo_head_json":{"title":"\ud83e\udd47Databricks avas suure keele mudeli DBRX, mis edestab testides GPT-3.5 | ProHoster","description":"Databricks kuulutas v\u00e4lja suure keelemudeli DBRX, mida saab kasutada, et luua vestlusroboteid, mis vastavad k\u00fcsimustele looduslikus keeles ja lahendavad esitatud matemaatilisi \u00fclesandeid.","canonical_url":"https:\/\/prohoster.info\/et\/blog\/news\/databricks-otkryl-bolshuyu-yazykovuyu-model-dbrx-operezhayushhuyu-v-testah-gpt-3-5","robots":"max-image-preview:large","keywords":"","webmasterTools":{"miscellaneous":""},"schema":null,"og:locale":"et_EE","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\udd47Databricks \u043e\u0442\u043a\u0440\u044b\u043b \u0431\u043e\u043b\u044c\u0448\u0443\u044e \u044f\u0437\u044b\u043a\u043e\u0432\u0443\u044e \u043c\u043e\u0434\u0435\u043b\u044c DBRX, \u043e\u043f\u0435\u0440\u0435\u0436\u0430\u044e\u0449\u0443\u044e \u0432 \u0442\u0435\u0441\u0442\u0430\u0445 GPT-3.5 | ProHoster","og:description":"\u041a\u043e\u043c\u043f\u0430\u043d\u0438\u044f Databricks \u043e\u0431\u044a\u044f\u0432\u0438\u043b\u0430 \u043e\u0431 \u043e\u0442\u043a\u0440\u044b\u0442\u0438\u0438 \u0431\u043e\u043b\u044c\u0448\u043e\u0439 \u044f\u0437\u044b\u043a\u043e\u0432\u043e\u0439 \u043c\u043e\u0434\u0435\u043b\u0438 DBRX, \u043a\u043e\u0442\u043e\u0440\u0430\u044f \u043c\u043e\u0436\u0435\u0442 \u043f\u0440\u0438\u043c\u0435\u043d\u044f\u0442\u044c\u0441\u044f \u0434\u043b\u044f \u0441\u043e\u0437\u0434\u0430\u043d\u0438\u044f \u0447\u0430\u0442\u0431\u043e\u0442\u043e\u0432, \u043e\u0442\u0432\u0435\u0447\u0430\u044e\u0449\u0438\u0445 \u043d\u0430 \u0432\u043e\u043f\u0440\u043e\u0441\u044b \u043d\u0430 \u0435\u0441\u0442\u0435\u0441\u0442\u0432\u0435\u043d\u043d\u043e\u043c \u044f\u0437\u044b\u043a\u0435, \u0440\u0435\u0448\u0430\u044e\u0449\u0438\u0445 \u043f\u0440\u0435\u0434\u043b\u043e\u0436\u0435\u043d\u043d\u044b\u0435 \u043c\u0430\u0442\u0435\u043c\u0430\u0442\u0438\u0447\u0435\u0441\u043a\u0438\u0435 \u0437\u0430\u0434\u0430\u0447\u0438.","og:url":"https:\/\/prohoster.info\/et\/blog\/news\/databricks-otkryl-bolshuyu-yazykovuyu-model-dbrx-operezhayushhuyu-v-testah-gpt-3-5","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":"2024-04-02T22:25:47+00:00","article:modified_time":"2024-04-02T22:25:47+00:00","article:publisher":"https:\/\/www.facebook.com\/prohoster","article:author":"https:\/\/www.facebook.com\/prohoster"},"aioseo_meta_data":{"post_id":"114737","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":"2026-01-22 21:17:19","breadcrumb_settings":null,"limit_modified_date":false,"reviewed_by":null,"ai":null,"created":"2026-01-22 21:17:19","updated":"2026-01-22 21:17:19","focus_keyword":null,"additional_keywords":null,"truseo_locale":null},"gt_translate_keys":[{"key":"link","format":"url"}],"_links":{"self":[{"href":"https:\/\/prohoster.info\/et\/wp-json\/wp\/v2\/posts\/114737","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/prohoster.info\/et\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/prohoster.info\/et\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/prohoster.info\/et\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/prohoster.info\/et\/wp-json\/wp\/v2\/comments?post=114737"}],"version-history":[{"count":0,"href":"https:\/\/prohoster.info\/et\/wp-json\/wp\/v2\/posts\/114737\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/prohoster.info\/et\/wp-json\/wp\/v2\/media\/114738"}],"wp:attachment":[{"href":"https:\/\/prohoster.info\/et\/wp-json\/wp\/v2\/media?parent=114737"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/prohoster.info\/et\/wp-json\/wp\/v2\/categories?post=114737"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/prohoster.info\/et\/wp-json\/wp\/v2\/tags?post=114737"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}