{"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\/sq\/blog\/news\/databricks-otkryl-bolshuyu-yazykovuyu-model-dbrx-operezhayushhuyu-v-testah-gpt-3-5","title":{"rendered":"Databricks ka hapur modeli i madh gjuh\u00ebsor DBRX, i cili e tejkalon GPT-3.5 n\u00eb testime","gt_translate_keys":[{"key":"rendered","format":"text"}]},"content":{"rendered":"

Kompania Databricks shpalli hapjen e nj\u00eb modeli t\u00eb madh gjuh\u00ebsor DBRX, i cili mund t\u00eb p\u00ebrdoret p\u00ebr t\u00eb krijuar chatbot\u00eb q\u00eb p\u00ebrgjigjen n\u00eb pyetje n\u00eb gjuh\u00ebn natyrore, zgjidhin detyra matematikore, jan\u00eb n\u00eb gjendje t\u00eb gjenerojn\u00eb p\u00ebrmbajtje mbi nj\u00eb tem\u00eb t\u00eb caktuar dhe t\u00eb krijojn\u00eb kod n\u00eb gjuh\u00eb t\u00eb ndryshme programimi. Modeli \u00ebsht\u00eb zhvilluar nga kompania Mosaic ML, e cila u ble nga Databricks p\u00ebr 1.3 miliard dollar\u00eb. P\u00ebr trajnim u p\u00ebrdor nj\u00eb grumbull prej 3072 GPU NVIDIA H100 Tensor Core. P\u00ebr p\u00ebrdorimin e modelit t\u00eb p\u00ebrfunduar rekomandohet 320GB memorie. <\/p>\n

Gjat\u00eb trajnimit t\u00eb modelit u aplikua arkitektura MoE (Mixture of experts), q\u00eb lejon t\u00eb marr\u00ebsh nj\u00eb vler\u00ebsim m\u00eb t\u00eb sakt\u00eb nga ekspert\u00ebt, dhe nj\u00eb koleksion tekstesh dhe kodi, me nj\u00eb madh\u00ebsi prej 12 Tb. Madh\u00ebsia e kontekstit t\u00eb marr\u00eb parasysh nga modeli DBRX \u00ebsht\u00eb 32 mij\u00eb token\u00eb (numri i token\u00ebve q\u00eb modeli mund t\u00eb p\u00ebrpunoj\u00eb dhe ruaj\u00eb gjat\u00eb gjenerimit t\u00eb tekstit). P\u00ebr krahasim, madh\u00ebsia e kontekstit te modelet Google Gemini dhe OpenAI GPT-4 \u00ebsht\u00eb 32 mij\u00eb token\u00eb, Google Gemma \u2014 8 mij\u00eb, nd\u00ebrsa modeli GPT-4 Turbo \u2014 128 mij\u00eb. <\/p>\n

Modeli p\u00ebrfshin 132 miliard parametra dhe \u00ebsht\u00eb ndar\u00eb n\u00eb 16 rrjete ekspert\u00ebsh, nga t\u00eb cilat gjat\u00eb p\u00ebrpunimit t\u00eb k\u00ebrkes\u00ebs mund t\u00eb p\u00ebrdoren jo m\u00eb shum\u00eb se 4 (mbulimi jo m\u00eb shum\u00eb se 36 miliard parametra p\u00ebr \u00e7do token). P\u00ebr krahasim, modeli GPT-4 supozohet t\u00eb p\u00ebrfshij\u00eb 1.76 trilion parametra, modeli Grok (X\/Twitter) i hapur koh\u00ebt e fundit \u2014 314 miliard, GPT-3.5 \u2014 175 miliard, YaLM (Yandex) \u2014 100 miliard, LLaMA (Meta) \u2014 65 miliard, GigaChat (Sber) \u2014 29 miliard, Gemma (Google) \u2014 7 miliard. <\/p>\n

Modeli dhe komponent\u00ebt e lidhur shp\u00ebrndahen n\u00ebn licenc\u00ebn Databricks Open Model License, q\u00eb lejon p\u00ebrdorimin, riprodhimin, kopjimin, ndryshimin dhe krijimin e produkteve t\u00eb nxjerra, por me disa kufizime. P\u00ebr shembull, licenca ndalon p\u00ebrdorimin e DBRX, modeleve t\u00eb nxjerra dhe \u00e7do produkti t\u00eb nxjerr\u00eb mbi ato p\u00ebr t\u00eb p\u00ebrmir\u00ebsuar modele t\u00eb tjera gjuh\u00ebsore, p\u00ebrve\u00e7 DBRX. Licenca gjithashtu ndalon p\u00ebrdorimin e modelit n\u00eb fusha q\u00eb shkelin ligjet dhe rregulloret. Modelet e nxjerra duhet t\u00eb shp\u00ebrndahen n\u00ebn t\u00eb nj\u00ebjt\u00ebn licenc\u00eb. N\u00ebse p\u00ebrdoren n\u00eb produkte dhe sh\u00ebrbime q\u00eb p\u00ebrdoren nga m\u00eb shum\u00eb se 700 milion p\u00ebrdorues n\u00eb muaj, k\u00ebrkohet nj\u00eb leje e ve\u00e7ant\u00eb. <\/p>\n

Sipas deklarat\u00ebs s\u00eb krijuesve t\u00eb modelit, n\u00eb karakteristikat dhe mund\u00ebsit\u00eb e tij, DBRX kalon modelet GPT-3.5 nga kompania OpenAI dhe Grok-1 nga Twitter, dhe mund t\u00eb konkurroj\u00eb me modelin Gemini 1.0 Pro gjat\u00eb testimit t\u00eb nivelit t\u00eb kuptimit t\u00eb gjuh\u00ebs, mund\u00ebsive p\u00ebr t\u00eb shkruar kod n\u00eb gjuh\u00eb programimi dhe zgjidhjes s\u00eb problemeve matematikore. N\u00eb disa aplikime, si\u00e7 \u00ebsht\u00eb gjenerimi i k\u00ebrkesave SQL, DBRX arrin n\u00eb efikasitetin e modelit GPT-4 Turbo, i cili dominos padyshim n\u00eb treg. P\u00ebr m\u00eb tep\u00ebr, modeli dallohet nga sh\u00ebrbimet konkurrente p\u00ebr shpejt\u00ebsin\u00eb e tij t\u00eb madhe dhe lejon formimin e p\u00ebrgjigjeve pothuajse menj\u00ebher\u00eb. N\u00eb ve\u00e7anti, DBRX mund t\u00eb gjeneroj\u00eb tekst me nj\u00eb shpejt\u00ebsi deri n\u00eb 150 toksina n\u00eb sekond\u00eb p\u00ebr \u00e7do p\u00ebrdorues, q\u00eb \u00ebsht\u00eb rreth dy her\u00eb m\u00eb shpejt se modeli LLaMA2-70B.

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

P\u00ebrve\u00e7 k\u00ebsaj, mund t\u00eb theksohet publikimi i p\u00ebrshkrimit teknik t\u00eb modelit t\u00eb hapur t\u00eb gjuh\u00ebs InternLM2, i cili shp\u00ebrndahet n\u00ebn licenc\u00ebn Apache 2.0, i disponuesh\u00ebm n\u00eb variante me 20, 7 dhe 1.8 miliard parametra. Modeli zhvillohet nga laboratori i inteligjenc\u00ebs artificiale n\u00eb Shangai n\u00eb bashk\u00ebpunim me disa universitete kineze dhe \u00ebsht\u00eb i njohur p\u00ebr konsiderat\u00ebn deri n\u00eb 200K toksina konteksti dhe mb\u00ebshtetje jo vet\u00ebm p\u00ebr anglishten, por edhe p\u00ebr gjuh\u00ebn kineze. N\u00eb shum\u00eb teste, modeli \u00ebsht\u00eb af\u00ebr GPT-4.

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

P\u00ebr m\u00eb tep\u00ebr, raportohet p\u00ebr zhvillimin e 84 b\u00ebrthamave t\u00eb reja p\u00ebr shumzimin e matricave p\u00ebr mjetin llamafile, i cili zhvillohet nga Mozilla dhe lejon krijimin e skedar\u00ebve universale ekzekutues p\u00ebr ekzekutimin e modeleve t\u00eb m\u00ebdha t\u00eb gjuh\u00ebs s\u00eb m\u00ebsimit t\u00eb makinerive (LLM). Ndryshimet kan\u00eb lejuar p\u00ebrshpejtimin e duksh\u00ebm t\u00eb pun\u00ebs s\u00eb modeleve n\u00eb llamafile gjat\u00eb ekzekutimit n\u00eb CPU. Shembuj, ekzekutimi i modeleve me p\u00ebrdorimin e llamafile tani \u00ebsht\u00eb m\u00eb i shpejt\u00eb se sa me p\u00ebrdorimin e llama.cpp nga 30% deri n\u00eb 500% n\u00eb var\u00ebsi t\u00eb mjedisit, dhe n\u00eb krahasim me bibliotek\u00ebn MKL, operacionet matricore q\u00eb p\u00ebrputhen n\u00eb cache L2, n\u00eb realizimin e ri ekzekutohen dy her\u00eb m\u00eb shpejt.
\n
Burimi: 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 hapi modelin e madh t\u00eb gjuh\u00ebs DBRX, q\u00eb kalon n\u00eb teste GPT-3.5 | ProHoster","description":"Kompania Databricks shpalli hapjen e modelit t\u00eb madh t\u00eb gjuh\u00ebs DBRX, i cili mund t\u00eb p\u00ebrdoret p\u00ebr krijimin e chatbot-eve q\u00eb p\u00ebrgjigjen n\u00eb pyetje n\u00eb gjuh\u00ebn natyrore, duke zgjidhur problemet matematikore t\u00eb propozuara.","canonical_url":"https:\/\/prohoster.info\/sq\/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":"sq_AL","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\/sq\/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\/sq\/wp-json\/wp\/v2\/posts\/114737","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/prohoster.info\/sq\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/prohoster.info\/sq\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/prohoster.info\/sq\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/prohoster.info\/sq\/wp-json\/wp\/v2\/comments?post=114737"}],"version-history":[{"count":0,"href":"https:\/\/prohoster.info\/sq\/wp-json\/wp\/v2\/posts\/114737\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/prohoster.info\/sq\/wp-json\/wp\/v2\/media\/114738"}],"wp:attachment":[{"href":"https:\/\/prohoster.info\/sq\/wp-json\/wp\/v2\/media?parent=114737"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/prohoster.info\/sq\/wp-json\/wp\/v2\/categories?post=114737"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/prohoster.info\/sq\/wp-json\/wp\/v2\/tags?post=114737"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}