{"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\/ro\/blog\/news\/databricks-otkryl-bolshuyu-yazykovuyu-model-dbrx-operezhayushhuyu-v-testah-gpt-3-5","title":{"rendered":"Databricks a lansat un model lingvistic mare DBRX, care dep\u0103\u0219e\u0219te GPT-3.5 \u00een teste","gt_translate_keys":[{"key":"rendered","format":"text"}]},"content":{"rendered":"

Compania Databricks a anun\u021bat lansarea unui model lingvistic mare, DBRX, care poate fi utilizat pentru a crea chatboti capabili s\u0103 r\u0103spund\u0103 la \u00eentreb\u0103ri \u00een limbaj natural, s\u0103 rezolve probleme matematice propuse, s\u0103 genereze con\u021binut pe o tem\u0103 dat\u0103 \u0219i s\u0103 scrie cod \u00een diverse limbaje de programare. Modelul a fost dezvoltat de compania Mosaic ML, care a fost achizi\u021bionat\u0103 de Databricks pentru 1,3 miliarde de dolari. Pentru antrenament, a fost utilizat un cluster format din 3072 GPU NVIDIA H100 Tensor Core. Pentru a rula modelul final, se recomand\u0103 320 GB de memorie. <\/p>\n

\u00cen instruirea modelului a fost utilizat\u0103 arhitectura MoE (Mixture of experts), care permite ob\u021binerea unei evalu\u0103ri mai precise din partea exper\u021bilor, \u0219i o colec\u021bie de texte \u0219i cod, cu o dimensiune de 12 TB. Dimensiunea contextului luat\u0103 \u00een considerare de modelul DBRX este de 32 de mii de tokeni (num\u0103rul de tokeni pe care modelul \u00eei poate procesa \u0219i re\u021bine \u00een timpul gener\u0103rii textului). Spre compara\u021bie, dimensiunea contextului pentru modelele Google Gemini \u0219i OpenAI GPT-4 este de 32 de mii de tokeni, Google Gemma \u2014 8 mii, iar modelul GPT-4 Turbo \u2014 128 de mii. <\/p>\n

Modelul acoper\u0103 132 de miliarde de parametri \u0219i este \u00eemp\u0103r\u021bit \u00een 16 re\u021bele de exper\u021bi, dintre care la procesarea unei solicit\u0103ri pot fi utilizate nu mai mult de 4 (acoperire de maximum 36 de miliarde de parametri pentru fiecare token). Spre compara\u021bie, modelul GPT-4 include, probabil, 1,76 trilioane de parametri, noua model Grok (X\/Twitter) \u2014 314 miliarde, GPT-3.5 \u2014 175 miliarde, YaLM (Yandex) \u2014 100 miliarde, LLaMA (Meta) \u2014 65 miliarde, GigaChat (Sber) \u2014 29 miliarde, Gemma (Google) \u2014 7 miliarde. <\/p>\n

Modelul \u0219i componentele asociate sunt distribuite sub licen\u021ba Databricks Open Model License, care permite utilizarea, reproducerea, copierea, modificarea \u0219i crearea de produse derivate, dar cu anumite restric\u021bii. De exemplu, licen\u021ba interzice utilizarea DBRX, a modelelor derivate \u0219i a oric\u0103rei ie\u0219iri bazate pe acestea pentru \u00eembun\u0103t\u0103\u021birea altor modele lingvistice, diferite de DBRX. Licen\u021ba interzice, de asemenea, utilizarea modelului \u00een domenii care \u00eencalc\u0103 legile \u0219i reglement\u0103rile. Modelele derivate trebuie distribuite sub aceea\u0219i licen\u021b\u0103. \u00cen cazul utiliz\u0103rii \u00een produse \u0219i servicii accesate de mai mult de 700 de milioane de utilizatori pe lun\u0103, este necesar\u0103 ob\u021binerea unei permisiuni separate. <\/p>\n

Conform afirma\u021biilor creatorilor modelului, DBRX dep\u0103\u0219e\u0219te din punct de vedere al caracteristicilor \u0219i capacit\u0103\u021bilor modelele GPT-3.5 de la OpenAI \u0219i Grok-1 de la Twitter, put\u00e2nd concura cu modelul Gemini 1.0 Pro \u00een testele de \u00een\u021belegere a limbajului, abilit\u0103\u021bile de programare \u0219i rezolvarea problemelor matematice. \u00cen anumite aplica\u021bii, cum ar fi generarea de interog\u0103ri SQL, DBRX se apropie de eficien\u021ba modelului GPT-4 Turbo, care conduce pe pia\u021b\u0103. \u00cen plus, modelul se distinge de serviciile concurente prin rapiditatea de lucru, permi\u021b\u00e2nd generarea r\u0103spunsului aproape instantaneu. \u00cen special, DBRX poate genera text cu o vitez\u0103 de p\u00e2n\u0103 la 150 de tokeni pe secund\u0103 pentru un singur utilizator, ceea ce este aproximativ de dou\u0103 ori mai repede dec\u00e2t modelul LLaMA2-70B.

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

De asemenea, merit\u0103 men\u021bionat\u0103 publicarea descrierii tehnice a modelului de limbaj mare open-source InternLM2, care este distribuit sub licen\u021ba Apache 2.0, disponibil \u00een variante cu 20, 7 \u0219i 1,8 miliarde de parametrii. Modelul este dezvoltat de laboratorul de inteligen\u021b\u0103 artificial\u0103 din Shanghai, cu participarea mai multor universit\u0103\u021bi chineze, \u0219i se remarc\u0103 prin capacitatea de a gestiona p\u00e2n\u0103 la 200K tokeni de context \u0219i sprijin pentru nu doar limba englez\u0103, ci \u0219i pentru limba chinez\u0103. \u00cen multe teste, modelul se apropie de GPT-4.

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

\u00cen plus, se raporteaz\u0103 despre dezvoltarea a 84 de noi nuclee pentru \u00eenmul\u021birea matricelor pentru instrumentul llamafile, dezvoltat de Mozilla, care permite crearea de fi\u0219iere executabile universale pentru rularea modelelor mari de limbaj de \u00eenv\u0103\u021bare automat\u0103 (LLM). Modific\u0103rile au permis accelerarea semnificativ\u0103 a func\u021bion\u0103rii modelelor \u00een llamafile atunci c\u00e2nd sunt executate pe CPU. De exemplu, rularea modelelor folosind llamafile este acum mai rapid\u0103 cu \u00eentre 30% \u0219i 500% comparativ cu folosirea llama.cpp, \u00een func\u021bie de mediu, iar comparativ cu biblioteca MKL, opera\u021biile matriciale care se \u00eencadreaz\u0103 \u00een cache-ul L2 sunt executate acum de dou\u0103 ori mai repede \u00een noua implementare.
\n
Sursa: opennet.ro<\/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 a lansat un model mare de limbaj DBRX, care dep\u0103\u0219e\u0219te \u00een teste GPT-3.5 | ProHoster","description":"Compania Databricks a anun\u021bat deschiderea modelului mare de limbaj DBRX, care poate fi utilizat pentru crearea de chatbo\u021bi capabili s\u0103 r\u0103spund\u0103 la \u00eentreb\u0103ri \u00een limbaj natural \u0219i s\u0103 rezolve probleme matematice propuse.","canonical_url":"https:\/\/prohoster.info\/ro\/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":"ro_RO","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\/ro\/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\/ro\/wp-json\/wp\/v2\/posts\/114737","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/prohoster.info\/ro\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/prohoster.info\/ro\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/prohoster.info\/ro\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/prohoster.info\/ro\/wp-json\/wp\/v2\/comments?post=114737"}],"version-history":[{"count":0,"href":"https:\/\/prohoster.info\/ro\/wp-json\/wp\/v2\/posts\/114737\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/prohoster.info\/ro\/wp-json\/wp\/v2\/media\/114738"}],"wp:attachment":[{"href":"https:\/\/prohoster.info\/ro\/wp-json\/wp\/v2\/media?parent=114737"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/prohoster.info\/ro\/wp-json\/wp\/v2\/categories?post=114737"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/prohoster.info\/ro\/wp-json\/wp\/v2\/tags?post=114737"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}