{"id":362712,"date":"2024-05-21T01:40:37","date_gmt":"2024-05-21T01:40:37","guid":{"rendered":"http:\/\/savepearlharbor.com\/?p=362712"},"modified":"-0001-11-30T00:00:00","modified_gmt":"2024-05-21T01:40:37","slug":"","status":"publish","type":"post","link":"https:\/\/savepearlharbor.com\/?p=362712","title":{"rendered":"<span>\u041b\u043e\u043a\u0430\u043b\u044c\u043d\u044b\u0435 GPT \u043d\u0435\u0439\u0440\u043e\u043d\u043d\u044b\u0439 \u0441\u0435\u0442\u0438 \u2014 \u0443\u0441\u0442\u0430\u043d\u0430\u0432\u043b\u0438\u0432\u0430\u0435\u043c \u043d\u0430 \u0434\u043e\u043c\u0430\u0448\u043d\u0435\u043c \u041f\u041a, \u0437\u0430\u043f\u0443\u0441\u043a\u0430\u0435\u043c \u0438 \u043f\u0440\u043e\u0432\u0435\u0440\u044f\u0435\u043c \u043d\u0430 \u0430\u0434\u0435\u043a\u0432\u0430\u0442\u043d\u043e\u0441\u0442\u044c \u0430\u043d\u0430\u043b\u043e\u0433\u0438 ChatGPT<\/span>"},"content":{"rendered":"<div><!--[--><!--]--><\/div>\n<div id=\"post-content-body\">\n<div>\n<div class=\"article-formatted-body article-formatted-body article-formatted-body_version-2\">\n<div xmlns=\"http:\/\/www.w3.org\/1999\/xhtml\">\n<p>\u0415\u0441\u0442\u044c \u043c\u043d\u043e\u0433\u043e LLM \u043d\u0435\u0439\u0440\u043e\u043d\u043d\u044b\u0445 \u0441\u0435\u0442\u0435\u0439, \u0441\u043e\u0437\u0434\u0430\u0442\u0435\u043b\u0438 \u043a\u043e\u0442\u043e\u0440\u044b\u0445 \u0433\u043e\u0432\u043e\u0440\u044f\u0442, \u0447\u0442\u043e \u043e\u043d\u0438 \u0430\u043d\u0430\u043b\u043e\u0433\u0438\u0447\u043d\u044b, \u0430 \u043c\u043e\u0436\u0435\u0442 \u0434\u0430\u0436\u0435 \u043b\u0443\u0447\u0448\u0435 ChatGPT \u0432\u0435\u0440\u0441\u0438\u0439 3.5 \u0438 4.0. \u0414\u0430\u0432\u0430\u0439\u0442\u0435 \u043f\u043e\u043f\u0440\u043e\u0431\u0443\u0435\u043c \u043f\u0440\u043e\u0442\u0435\u0441\u0442\u0438\u0440\u043e\u0432\u0430\u0442\u044c \u0438\u0445, \u0443\u0441\u0442\u0430\u043d\u043e\u0432\u0438\u0432 \u0438\u0445 \u043d\u0430 \u043b\u043e\u043a\u0430\u043b\u044c\u043d\u044b\u0439 \u043a\u043e\u043c\u043f\u044c\u044e\u0442\u0435\u0440, \u0438 \u043f\u043e\u043d\u044f\u0442\u044c, \u0434\u0435\u0439\u0441\u0442\u0432\u0438\u0442\u0435\u043b\u044c\u043d\u043e \u043b\u0438 \u043e\u043d\u0438 \u0442\u0430\u043a \u0445\u043e\u0440\u043e\u0448\u0438.<\/p>\n<p>\u0425\u0430\u0440\u0430\u043a\u0442\u0435\u0440\u0438\u0441\u0442\u0438\u043a\u0438 \u043c\u043e\u0435\u0433\u043e \u0434\u043e\u043c\u0430\u0448\u043d\u0435\u0433\u043e \u043a\u043e\u043c\u043f\u044c\u044e\u0442\u0435\u0440\u0430, \u043d\u0430 \u043a\u043e\u0442\u043e\u0440\u043e\u043c \u044f \u0437\u0430\u0434\u0430\u0432\u0430\u043b \u0432\u043e\u043f\u0440\u043e\u0441\u044b GPT \u043d\u0435\u0439\u0440\u043e\u0441\u0435\u0442\u044f\u043c:<\/p>\n<ul>\n<li>\n<p>8 \u044f\u0434\u0435\u0440\u043d\u044b\u0439 16 \u043f\u043e\u0442\u043e\u0447\u043d\u044b\u0439 \u043f\u0440\u043e\u0446\u0435\u0441\u0441\u043e\u0440 AMD Ryzen 7 1700X<\/p>\n<\/li>\n<li>\n<p>64 \u0413\u0431 \u043e\u043f\u0435\u0440\u0430\u0442\u0438\u0432\u043d\u043e\u0439 \u043f\u0430\u043c\u044f\u0442\u0438 \u0434\u0432\u0443\u043c\u044f \u043f\u043b\u0430\u043d\u043a\u0430\u043c\u0438 \u043f\u043e 32 \u0413\u0431 DDR4 2666 \u041c\u0413\u0446<\/p>\n<\/li>\n<\/ul>\n<p>\u0412\u0438\u0434\u0435\u043e\u043a\u0430\u0440\u0442\u0443 \u044f \u043d\u0435 \u0438\u0441\u043f\u043e\u043b\u044c\u0437\u043e\u0432\u0430\u043b, \u0442\u0430\u043a \u043a\u0430\u043a \u0432 \u043d\u0435\u0439 \u043c\u0430\u043b\u043e \u0432\u0438\u0434\u0435\u043e\u043f\u0430\u043c\u044f\u0442\u0438, \u0438 \u0431\u043e\u043b\u044c\u0448\u0438\u0435 \u043d\u0435\u0439\u0440\u043e\u043d\u043d\u044b\u0435 \u0441\u0435\u0442\u0438 \u0432 \u043d\u0435\u0451 \u043d\u0435 \u0432\u043b\u0435\u0437\u0443\u0442, \u0430 \u043f\u043e\u0441\u0442\u043e\u044f\u043d\u043d\u043e \u043f\u0435\u0440\u0435\u043a\u0438\u0434\u044b\u0432\u0430\u0442\u044c \u0434\u0430\u043d\u043d\u044b\u0435 \u0447\u0435\u0440\u0435\u0437 \u0443\u0437\u043a\u0443\u044e PCI-e 3.0 \u0448\u0438\u043d\u0443 \u043d\u0435 \u0441\u0430\u043c\u043e\u0435 \u0431\u044b\u0441\u0442\u0440\u043e\u0435 \u0443\u0434\u043e\u0432\u043e\u043b\u044c\u0441\u0442\u0432\u0438\u0435.<\/p>\n<p>\u0417\u0430\u0434\u0430\u0432\u0430\u043b \u044f \u0434\u0432\u0430 \u0432\u043e\u043f\u0440\u043e\u0441\u0430 \u043d\u0430 \u0430\u043d\u0433\u043b\u0438\u0439\u0441\u043a\u043e\u043c \u044f\u0437\u044b\u043a\u0435 \u0434\u043b\u044f \u0447\u0438\u0441\u0442\u043e\u0442\u044b \u044d\u043a\u0441\u043f\u0435\u0440\u0438\u043c\u0435\u043d\u0442\u0430:<\/p>\n<ol>\n<li>\n<p>Is it possible to connect two Nvidia 3080 graphics cards using NVLink? (\u041f\u0435\u0440\u0435\u0432\u043e\u0434: \u041c\u043e\u0436\u043d\u043e \u043b\u0438 \u043f\u043e\u0434\u043a\u043b\u044e\u0447\u0438\u0442\u044c \u0434\u0432\u0435 \u0432\u0438\u0434\u0435\u043e\u043a\u0430\u0440\u0442\u044b Nvidia 3080 \u0441 \u043f\u043e\u043c\u043e\u0449\u044c\u044e NVLink?) &#8212; \u0445\u0438\u0442\u0440\u043e\u0441\u0442\u044c \u0432\u043e\u043f\u0440\u043e\u0441\u0430 \u0432 \u0442\u043e\u043c, \u0447\u0442\u043e \u0443 \u044d\u0442\u043e\u0439 \u0432\u0438\u0434\u0435\u043e\u043a\u0430\u0440\u0442\u044b \u043d\u0435\u0442 \u0448\u0438\u043d\u044b NVLink. \u041e\u043d\u0430 \u0435\u0441\u0442\u044c \u0443 \u0441\u0442\u0430\u0440\u0448\u0435\u0439 \u0432\u0438\u0434\u0435\u043e\u043a\u0430\u0440\u0442\u044b Nvidia GeForce RTX 3090.<\/p>\n<\/li>\n<li>\n<p>Write a program to recognize human speech and then write the result to a text file. (\u041f\u0435\u0440\u0435\u0432\u043e\u0434: \u041d\u0430\u043f\u0438\u0448\u0438\u0442\u0435 \u043f\u0440\u043e\u0433\u0440\u0430\u043c\u043c\u0443 \u0434\u043b\u044f \u0440\u0430\u0441\u043f\u043e\u0437\u043d\u0430\u0432\u0430\u043d\u0438\u044f \u0447\u0435\u043b\u043e\u0432\u0435\u0447\u0435\u0441\u043a\u043e\u0439 \u0440\u0435\u0447\u0438, \u0430 \u0437\u0430\u0442\u0435\u043c \u0437\u0430\u043f\u0438\u0448\u0438\u0442\u0435 \u0440\u0435\u0437\u0443\u043b\u044c\u0442\u0430\u0442 \u0432 \u0442\u0435\u043a\u0441\u0442\u043e\u0432\u044b\u0439 \u0444\u0430\u0439\u043b). \u0417\u0434\u0435\u0441\u044c \u043c\u044b \u043f\u0440\u043e\u0432\u0435\u0440\u044f\u0435\u043c \u043a\u0430\u043a \u043d\u0435\u0439\u0440\u043e\u043d\u043d\u0430\u044f \u0441\u0435\u0442\u044c \u0441\u043f\u0440\u0430\u0432\u0438\u0442\u0441\u044f \u0441 \u043d\u0430\u043f\u0438\u0441\u0430\u043d\u0438\u0435\u043c \u043a\u043e\u0434\u0430.<\/p>\n<\/li>\n<\/ol>\n<h2>\u041a\u0430\u043a \u0443\u0441\u0442\u0430\u043d\u043e\u0432\u0438\u0442\u044c \u0438 \u043d\u0430\u0441\u0442\u0440\u043e\u0438\u0442\u044c \u043b\u043e\u043a\u0430\u043b\u044c\u043d\u0443\u044e GPT \u043d\u0435\u0439\u0440\u043e\u0441\u0435\u0442\u044c<\/h2>\n<p>\u0418\u0441\u043f\u043e\u043b\u044c\u0437\u043e\u0432\u0430\u043b \u044f \u0443\u0436\u0435 \u043f\u043e\u0434\u0433\u043e\u0442\u043e\u0432\u043b\u0435\u043d\u043d\u044b\u0439 \u0444\u0430\u0439\u043b GGUF \u043c\u043e\u0434\u0435\u043b\u0438 \u043d\u0435\u0439\u0440\u043e\u0441\u0435\u0442\u0438 \u0438 \u043f\u0440\u043e\u0433\u0440\u0430\u043c\u043c\u0443 <a href=\"https:\/\/github.com\/LostRuins\/koboldcpp\/releases\" rel=\"noopener noreferrer nofollow\">Koboldcpp_nocuda<\/a> (\u0440\u0430\u0441\u0447\u0435\u0442\u044b \u043f\u0440\u043e\u0438\u0437\u0432\u043e\u0434\u044f\u0442\u0441\u044f \u0442\u043e\u043b\u044c\u043a\u043e \u043d\u0430 \u043f\u0440\u043e\u0446\u0435\u0441\u0441\u043e\u0440\u0435). \u0412\u044b \u043c\u043e\u0436\u0435\u0442\u0435 \u0438\u0441\u043f\u043e\u043b\u044c\u0437\u043e\u0432\u0430\u0442\u044c <a href=\"https:\/\/github.com\/LostRuins\/koboldcpp\/releases\" rel=\"noopener noreferrer nofollow\">Koboldcpp<\/a> \u0441 \u043f\u043e\u0434\u0434\u0435\u0440\u0436\u043a\u043e\u0439 \u0432\u0438\u0434\u0435\u043e\u043a\u0430\u0440\u0442\u044b NVidia. \u0418\u043b\u0438 <a href=\"https:\/\/github.com\/YellowRoseCx\/koboldcpp-rocm\/releases\" rel=\"noopener noreferrer nofollow\">Koboldcpp_rocm<\/a>, \u0435\u0441\u043b\u0438 \u0443 \u0432\u0430\u0441 \u0432\u0438\u0434\u0435\u043e\u043a\u0430\u0440\u0442\u0430 AMD. \u042d\u0442\u043e \u0432\u0441\u0451 &#171;exe&#187; \u0444\u0430\u0439\u043b\u044b, \u0442\u0430\u043a \u043a\u0430\u043a \u044f \u0442\u0435\u0441\u0442\u0438\u0440\u043e\u0432\u0430\u043b \u0432 \u041e\u0421 Windows \u0438 \u043f\u0440\u043e\u0433\u0440\u0430\u043c\u043c\u0430 \u043d\u0435 \u0442\u0440\u0435\u0431\u0443\u0435\u0442 \u0443\u0441\u0442\u0430\u043d\u043e\u0432\u043a\u0438. <\/p>\n<figure class=\"full-width\"><img loading=\"lazy\" decoding=\"async\" src=\"https:\/\/habrastorage.org\/r\/w780q1\/getpro\/habr\/upload_files\/34f\/080\/7d3\/34f0807d34438982d56a1def1be9f4ac.jpg\" alt=\"\u0418\u043d\u0442\u0435\u0440\u0444\u0435\u0439\u0441 \u043f\u0440\u043e\u0433\u0440\u0430\u043c\u043c\u044b Koboldcpp (\u043e\u0431\u0440\u0430\u0442\u0438\u0442\u0435 \u0432\u043d\u0438\u043c\u0430\u043d\u0438\u0435 \u043d\u0430 \u0433\u0440\u0430\u0444\u0443 Context Size - \u0432\u044b \u043c\u043e\u0436\u0435\u0442\u0435 \u0443\u0432\u0435\u043b\u0438\u0447\u0438\u0442\u044c \u0440\u0430\u0437\u043c\u0435\u0440 \u043a\u043e\u043d\u0442\u0435\u043a\u0441\u0442\u0430)\" title=\"\u0418\u043d\u0442\u0435\u0440\u0444\u0435\u0439\u0441 \u043f\u0440\u043e\u0433\u0440\u0430\u043c\u043c\u044b Koboldcpp (\u043e\u0431\u0440\u0430\u0442\u0438\u0442\u0435 \u0432\u043d\u0438\u043c\u0430\u043d\u0438\u0435 \u043d\u0430 \u0433\u0440\u0430\u0444\u0443 Context Size - \u0432\u044b \u043c\u043e\u0436\u0435\u0442\u0435 \u0443\u0432\u0435\u043b\u0438\u0447\u0438\u0442\u044c \u0440\u0430\u0437\u043c\u0435\u0440 \u043a\u043e\u043d\u0442\u0435\u043a\u0441\u0442\u0430)\" width=\"796\" height=\"717\" data-src=\"https:\/\/habrastorage.org\/getpro\/habr\/upload_files\/34f\/080\/7d3\/34f0807d34438982d56a1def1be9f4ac.jpg\" data-blurred=\"true\"\/><\/p>\n<div><figcaption>\u0418\u043d\u0442\u0435\u0440\u0444\u0435\u0439\u0441 \u043f\u0440\u043e\u0433\u0440\u0430\u043c\u043c\u044b Koboldcpp (\u043e\u0431\u0440\u0430\u0442\u0438\u0442\u0435 \u0432\u043d\u0438\u043c\u0430\u043d\u0438\u0435 \u043d\u0430 \u0433\u0440\u0430\u0444\u0443 Context Size &#8212; \u0432\u044b \u043c\u043e\u0436\u0435\u0442\u0435 \u0443\u0432\u0435\u043b\u0438\u0447\u0438\u0442\u044c \u0440\u0430\u0437\u043c\u0435\u0440 \u043a\u043e\u043d\u0442\u0435\u043a\u0441\u0442\u0430)<\/figcaption><\/div>\n<\/figure>\n<p>\u041f\u043e\u0441\u043b\u0435 \u0437\u0430\u0433\u0440\u0443\u0437\u043a\u0438 \u043c\u043e\u0434\u0435\u043b\u0438 \u0432 \u043f\u0440\u043e\u0433\u0440\u0430\u043c\u043c\u0435, \u0435\u0441\u043b\u0438 \u0443 \u0432\u0430\u0441 \u0445\u0432\u0430\u0442\u0438\u043b\u043e \u043e\u043f\u0435\u0440\u0430\u0442\u0438\u0432\u043d\u043e\u0439 \u043f\u0430\u043c\u044f\u0442\u0438 \u043e\u0442\u043a\u0440\u043e\u0435\u0442\u0441\u044f \u043e\u043a\u043d\u043e \u0432 \u0431\u0440\u0430\u0443\u0437\u0435\u0440\u0435, \u043a\u0443\u0434\u0430 \u0432\u044b \u043c\u043e\u0436\u0435\u0442\u0435 \u043f\u0438\u0441\u0430\u0442\u044c \u0432\u043e\u043f\u0440\u043e\u0441\u044b. \u0420\u0435\u043a\u043e\u043c\u0435\u043d\u0434\u0443\u044e \u043d\u0430\u0447\u0438\u043d\u0430\u0442\u044c \u043d\u043e\u0432\u0443\u044e \u0441\u0435\u0441\u0441\u0438\u044e \u043a\u0430\u0436\u0434\u044b\u0439 \u0440\u0430\u0437, \u043a\u043e\u0433\u0434\u0430 \u0432\u044b \u0437\u0430\u043f\u0443\u0441\u043a\u0430\u0435\u0442\u0435 \u043f\u0440\u043e\u0433\u0440\u0430\u043c\u043c\u0443. <\/p>\n<figure class=\"full-width\"><img loading=\"lazy\" decoding=\"async\" src=\"https:\/\/habrastorage.org\/r\/w780q1\/getpro\/habr\/upload_files\/12e\/52b\/e9d\/12e52be9df3a065b37802a5072b302f3.jpg\" alt=\"\u0411\u0443\u0434\u044c\u0442\u0435 \u0442\u0435\u0440\u043f\u0435\u043b\u0438\u0432\u044b, \u043d\u0435\u0439\u0440\u043e\u0441\u0435\u0442\u044c \u0437\u0430\u0433\u0440\u0443\u0437\u0438\u0442 \u0432\u0430\u0448 \u043f\u0440\u043e\u0446\u0435\u0441\u0441\u043e\u0440 \u043d\u0430 100 %\" title=\"\u0411\u0443\u0434\u044c\u0442\u0435 \u0442\u0435\u0440\u043f\u0435\u043b\u0438\u0432\u044b, \u043d\u0435\u0439\u0440\u043e\u0441\u0435\u0442\u044c \u0437\u0430\u0433\u0440\u0443\u0437\u0438\u0442 \u0432\u0430\u0448 \u043f\u0440\u043e\u0446\u0435\u0441\u0441\u043e\u0440 \u043d\u0430 100 %\" width=\"1210\" height=\"772\" data-src=\"https:\/\/habrastorage.org\/getpro\/habr\/upload_files\/12e\/52b\/e9d\/12e52be9df3a065b37802a5072b302f3.jpg\" data-blurred=\"true\"\/><\/p>\n<div><figcaption>\u0411\u0443\u0434\u044c\u0442\u0435 \u0442\u0435\u0440\u043f\u0435\u043b\u0438\u0432\u044b, \u043d\u0435\u0439\u0440\u043e\u0441\u0435\u0442\u044c \u0437\u0430\u0433\u0440\u0443\u0437\u0438\u0442 \u0432\u0430\u0448 \u043f\u0440\u043e\u0446\u0435\u0441\u0441\u043e\u0440 \u043d\u0430 100 %<\/figcaption><\/div>\n<\/figure>\n<p>\u0412 \u043d\u0430\u0441\u0442\u0440\u043e\u0439\u043a\u0430\u0445 \u0432 \u0433\u0440\u0430\u0444\u0435 &#171;Amount to Gen&#187; \u0432\u044b \u043c\u043e\u0436\u0435\u0442\u0435 \u0443\u0432\u0435\u043b\u0438\u0447\u0438\u0442\u044c \u0437\u043d\u0430\u0447\u0435\u043d\u0438\u0435 \u0434\u043e 512 &#8212; \u044d\u0442\u043e \u043a\u043e\u043b\u0438\u0447\u0435\u0441\u0442\u0432\u043e \u0442\u043e\u043a\u0435\u043d\u043e\u0432 \u0432 \u043e\u0442\u0432\u0435\u0442\u0435 (\u0447\u0435\u043c \u0431\u043e\u043b\u044c\u0448\u0435, \u0442\u0435\u043c \u0431\u043e\u043b\u0435\u0435 \u0434\u043b\u0438\u043d\u043d\u044b\u0439 \u043e\u0442\u0432\u0435\u0442). \u041b\u0438\u0431\u043e \u043d\u0430\u0431\u0438\u0442\u044c \u043e\u0442 \u0440\u0443\u043a\u0438 &#8212; \u044f \u0432\u0431\u0438\u043b 8192 (= 1024*8). \u041c\u0430\u043a\u0441\u0438\u043c\u0430\u043b\u044c\u043d\u044b\u0439 \u0435\u0451 \u043e\u0442\u0432\u0435\u0442 \u0431\u0443\u0434\u0435\u0442 \u043e\u0433\u0440\u0430\u043d\u0438\u0447\u0435\u043d 8192 \u0442\u043e\u043a\u0435\u043d\u0430\u043c\u0438. \u041e\u0434\u043d\u0430\u043a\u043e \u043a\u0430\u043a \u043f\u0440\u0430\u0432\u0438\u043b\u043e \u043e\u043d\u0430 \u043f\u0438\u0448\u0435\u0442 \u043e\u0442\u0432\u0435\u0442 \u0441 \u0433\u043e\u0440\u0430\u0437\u0434\u043e \u043c\u0435\u043d\u044c\u0448\u0438\u043c\u0438 \u0442\u043e\u043a\u0435\u043d\u0430\u043c\u0438 (\u043f\u043e \u0443\u0441\u043c\u043e\u0442\u0440\u0435\u043d\u0438\u044e \u043d\u0435\u0439\u0440\u043e\u043d\u043d\u043e\u0439 \u0441\u0435\u0442\u0438).<\/p>\n<p>\u0413\u0440\u0430\u0444\u0430 Max Ctx. Tokens &#8212; \u044d\u0442\u043e \u043c\u0430\u043a\u0441\u0438\u043c\u0430\u043b\u044c\u043d\u044b\u0439 \u0440\u0430\u0437\u043c\u0435\u0440 \u0432\u0445\u043e\u0434\u043d\u043e\u0433\u043e \u043a\u043e\u043d\u0442\u0435\u043a\u0441\u0442\u0430. \u0421\u043c\u043e\u0442\u0440\u0438\u0442\u0435 \u043d\u0430 \u0445\u0430\u0440\u0430\u043a\u0442\u0435\u0440\u0438\u0441\u0442\u0438\u043a\u0438 \u043a\u0430\u0436\u0434\u043e\u0439 GGUF \u043c\u043e\u0434\u0435\u043b\u0438 &#8212; \u043d\u0430 \u043a\u0430\u043a\u043e\u043c \u0440\u0430\u0437\u043c\u0435\u0440\u0435 \u043a\u043e\u043d\u0442\u0435\u043a\u0441\u0442\u0430 \u043e\u043d\u0430 \u043e\u0431\u0443\u0447\u0430\u043b\u0430\u0441\u044c. \u041d\u0430\u043f\u0440\u0438\u043c\u0435\u0440 \u0443 DeepSeek \u043a\u043e\u043d\u0442\u0435\u043a\u0441\u0442 \u0440\u0430\u0432\u0435\u043d 16 \u041a\u0431 (\u044d\u0442\u043e \u0437\u043d\u0430\u0447\u0435\u043d\u0438\u0435 \u044f \u0438 \u0432\u043f\u0438\u0441\u0430\u043b). \u041c\u043e\u0436\u0435\u0442\u0435 \u043e\u0433\u0440\u0430\u043d\u0438\u0447\u0438\u0442\u044c\u0441\u044f \u043c\u0435\u043d\u044c\u0448\u0438\u043c\u0438 \u0437\u043d\u0430\u0447\u0435\u043d\u0438\u044f\u043c\u0438. \u041d\u043e \u043f\u0440\u0438 \u044d\u0442\u043e\u043c \u043c\u0430\u043a\u0441\u0438\u043c\u0430\u043b\u044c\u043d\u043e\u0435 \u043a\u043e\u043b\u0438\u0447\u0435\u0441\u0442\u0432\u043e \u0442\u043e\u043a\u0435\u043d\u043e\u0432 \u043e\u0442\u0432\u0435\u0442\u0430 \u0434\u043e\u043b\u0436\u043d\u043e \u0431\u044b\u0442\u044c \u043c\u0435\u043d\u044c\u0448\u0435 \u043c\u0430\u043a\u0441\u0438\u043c\u0430\u043b\u044c\u043d\u043e\u0433\u043e \u043a\u043e\u043b\u0438\u0447\u0435\u0441\u0442\u0432\u0430 \u0442\u043e\u043a\u0435\u043d\u043e\u0432 \u0443 \u0432\u0445\u043e\u0434\u043d\u043e\u0433\u043e \u043a\u043e\u043d\u0442\u0435\u043a\u0441\u0442\u0430.<\/p>\n<p>\u0422\u0430\u043a\u0436\u0435 \u043f\u0440\u0438 \u0438\u043d\u0438\u0446\u0438\u0430\u043b\u0438\u0437\u0430\u0446\u0438\u0438 (\u0442\u0430\u043c \u0433\u0434\u0435 \u0432\u044b \u0443\u043a\u0430\u0437\u044b\u0432\u0430\u043b\u0438 \u043a\u043e\u043b\u0438\u0447\u0435\u0441\u0442\u0432\u043e \u043f\u043e\u0442\u043e\u043a\u043e\u0432 \u043f\u0440\u043e\u0446\u0435\u0441\u0441\u043e\u0440\u0430 \u0438 \u043f\u0443\u0442\u044c \u043a \u043c\u043e\u0434\u0435\u043b\u0438) \u0435\u0441\u0442\u044c \u0433\u0440\u0430\u0444\u0430 Context Size &#8212; \u0443\u0432\u0435\u043b\u0438\u0447\u044c\u0442\u0435 \u0435\u0433\u043e \u0434\u043e \u0447\u0438\u0441\u043b\u0430 \u0432 \u0433\u0440\u0430\u0444\u0435 Max Ctx. Tokens (\u0447\u0442\u043e\u0431\u044b \u043e\u043d\u0438 \u0431\u044b\u043b\u0438 \u0440\u0430\u0432\u043d\u044b).<\/p>\n<figure class=\"full-width\"><img loading=\"lazy\" decoding=\"async\" src=\"https:\/\/habrastorage.org\/r\/w780q1\/getpro\/habr\/upload_files\/03d\/676\/88e\/03d67688e8d4555cb96d65ece79aed29.jpg\" alt=\"\u041d\u0430\u0441\u0442\u0440\u0430\u0438\u0432\u0430\u0435\u043c \u043a\u043e\u043b\u0438\u0447\u0435\u0441\u0442\u0432\u043e \u0442\u043e\u043a\u0435\u043d\u043e\u0432 \u0432 \u043e\u0442\u0432\u0435\u0442\u0435 \u0438 \u0432\u043e \u0432\u0445\u043e\u0434\u043d\u043e\u043c \u043a\u043e\u043d\u0442\u0435\u043a\u0441\u0442\u0435.\" title=\"\u041d\u0430\u0441\u0442\u0440\u0430\u0438\u0432\u0430\u0435\u043c \u043a\u043e\u043b\u0438\u0447\u0435\u0441\u0442\u0432\u043e \u0442\u043e\u043a\u0435\u043d\u043e\u0432 \u0432 \u043e\u0442\u0432\u0435\u0442\u0435 \u0438 \u0432\u043e \u0432\u0445\u043e\u0434\u043d\u043e\u043c \u043a\u043e\u043d\u0442\u0435\u043a\u0441\u0442\u0435.\" width=\"807\" height=\"637\" data-src=\"https:\/\/habrastorage.org\/getpro\/habr\/upload_files\/03d\/676\/88e\/03d67688e8d4555cb96d65ece79aed29.jpg\" data-blurred=\"true\"\/><\/p>\n<div><figcaption>\u041d\u0430\u0441\u0442\u0440\u0430\u0438\u0432\u0430\u0435\u043c \u043a\u043e\u043b\u0438\u0447\u0435\u0441\u0442\u0432\u043e \u0442\u043e\u043a\u0435\u043d\u043e\u0432 \u0432 \u043e\u0442\u0432\u0435\u0442\u0435 \u0438 \u0432\u043e \u0432\u0445\u043e\u0434\u043d\u043e\u043c \u043a\u043e\u043d\u0442\u0435\u043a\u0441\u0442\u0435.<\/figcaption><\/div>\n<\/figure>\n<p>\u041f\u043e\u0434\u0433\u043e\u0442\u043e\u0432\u043b\u0435\u043d\u043d\u044b\u0435 GGUF \u043c\u043e\u0434\u0435\u043b\u0438 \u0441\u043a\u0430\u0447\u0438\u0432\u0430\u0435\u043c \u043e\u0442\u0441\u044e\u0434\u0430: <a href=\"https:\/\/huggingface.co\/\" rel=\"noopener noreferrer nofollow\">https:\/\/huggingface.co\/<\/a>. \u0412\u0432\u0435\u0434\u0438\u0442\u0435 \u0432 \u043f\u043e\u0438\u0441\u043a\u0435 \u043d\u0435\u043e\u0431\u0445\u043e\u0434\u0438\u043c\u0443\u044e \u043c\u043e\u0434\u0435\u043b\u044c.<\/p>\n<figure class=\"full-width\"><img loading=\"lazy\" decoding=\"async\" src=\"https:\/\/habrastorage.org\/r\/w780q1\/getpro\/habr\/upload_files\/386\/c9b\/802\/386c9b8021481566de667129bc76af04.jpg\" alt=\"\u041f\u0440\u0438 \u043d\u0430\u0436\u0430\u0442\u0438\u0438 \u043d\u0430 \u0441\u0441\u044b\u043b\u043a\u0443 \u0432\u044b\u0432\u0435\u0434\u0435\u0442 \u0432\u0441\u0435 \u0440\u0435\u0437\u0443\u043b\u044c\u0442\u0430\u0442\u044b \u043f\u043e \u043f\u043e\u0438\u0441\u043a\u043e\u0432\u043e\u043c\u0443 \u0437\u0430\u043f\u0440\u043e\u0441\u0443\" title=\"\u041f\u0440\u0438 \u043d\u0430\u0436\u0430\u0442\u0438\u0438 \u043d\u0430 \u0441\u0441\u044b\u043b\u043a\u0443 \u0432\u044b\u0432\u0435\u0434\u0435\u0442 \u0432\u0441\u0435 \u0440\u0435\u0437\u0443\u043b\u044c\u0442\u0430\u0442\u044b \u043f\u043e \u043f\u043e\u0438\u0441\u043a\u043e\u0432\u043e\u043c\u0443 \u0437\u0430\u043f\u0440\u043e\u0441\u0443\" width=\"964\" height=\"696\" data-src=\"https:\/\/habrastorage.org\/getpro\/habr\/upload_files\/386\/c9b\/802\/386c9b8021481566de667129bc76af04.jpg\" data-blurred=\"true\"\/><\/p>\n<div><figcaption>\u041f\u0440\u0438 \u043d\u0430\u0436\u0430\u0442\u0438\u0438 \u043d\u0430 \u0441\u0441\u044b\u043b\u043a\u0443 \u0432\u044b\u0432\u0435\u0434\u0435\u0442 \u0432\u0441\u0435 \u0440\u0435\u0437\u0443\u043b\u044c\u0442\u0430\u0442\u044b \u043f\u043e \u043f\u043e\u0438\u0441\u043a\u043e\u0432\u043e\u043c\u0443 \u0437\u0430\u043f\u0440\u043e\u0441\u0443<\/figcaption><\/div>\n<\/figure>\n<p>\u0422\u0430\u043a\u0436\u0435 \u0435\u0441\u0442\u044c \u0438\u043d\u0442\u0435\u0440\u0435\u0441\u043d\u044b\u0439 <a href=\"https:\/\/huggingface.co\/spaces\/HuggingFaceH4\/open_llm_leaderboard\" rel=\"noopener noreferrer nofollow\">\u0440\u0435\u0439\u0442\u0438\u043d\u0433 \u043e\u0446\u0435\u043d\u043a\u0438 \u044d\u0444\u0444\u0435\u043a\u0442\u0438\u0432\u043d\u043e\u0441\u0442\u0438 LLM \u043d\u0435\u0439\u0440\u043e\u0441\u0435\u0442\u0435\u0439<\/a> \u043d\u0430 \u044d\u0442\u043e\u043c \u0441\u0430\u0439\u0442\u0435, \u043d\u043e \u043c\u044b \u043f\u0440\u0435\u0434\u043f\u043e\u0447\u0442\u0435\u043c \u0441\u0430\u043c\u0438 \u043f\u0440\u043e\u0442\u0435\u0441\u0442\u0438\u0440\u043e\u0432\u0430\u0442\u044c \u0441\u0430\u043c\u044b\u0435 \u0438\u043d\u0442\u0435\u0440\u0435\u0441\u043d\u044b\u0435 \u043d\u0435\u0439\u0440\u043e\u043d\u043d\u044b\u0435 \u0441\u0435\u0442\u0438. <\/p>\n<figure class=\"full-width\"><img loading=\"lazy\" decoding=\"async\" src=\"https:\/\/habrastorage.org\/r\/w780q1\/getpro\/habr\/upload_files\/a1d\/94d\/18f\/a1d94d18f148ff103d74d7ac04623875.jpg\" alt=\"\u0420\u0435\u0439\u0442\u0438\u043d\u0433 LLM \u043d\u0435\u0439\u0440\u043e\u0441\u0435\u0442\u0435\u0439\" title=\"\u0420\u0435\u0439\u0442\u0438\u043d\u0433 LLM \u043d\u0435\u0439\u0440\u043e\u0441\u0435\u0442\u0435\u0439\" width=\"1141\" height=\"725\" data-src=\"https:\/\/habrastorage.org\/getpro\/habr\/upload_files\/a1d\/94d\/18f\/a1d94d18f148ff103d74d7ac04623875.jpg\" data-blurred=\"true\"\/><\/p>\n<div><figcaption>\u0420\u0435\u0439\u0442\u0438\u043d\u0433 LLM \u043d\u0435\u0439\u0440\u043e\u0441\u0435\u0442\u0435\u0439<\/figcaption><\/div>\n<\/figure>\n<p>\u0422\u0430\u043a\u0436\u0435, \u0435\u0441\u043b\u0438 \u0432\u044b\u0431\u0440\u0430\u0442\u044c \u0438\u043d\u0442\u0435\u0440\u0435\u0441\u0443\u044e\u0449\u0443\u044e \u043d\u0435\u0439\u0440\u043e\u0441\u0435\u0442\u044c, \u0442\u043e \u043c\u043e\u0436\u043d\u043e \u043f\u043e\u0441\u043c\u043e\u0442\u0440\u0435\u0442\u044c \u0441\u043a\u043e\u043b\u044c\u043a\u043e \u043e\u043f\u0435\u0440\u0430\u0442\u0438\u0432\u043d\u043e\u0439 \u043f\u0430\u043c\u044f\u0442\u0438 \u0431\u0443\u0434\u0435\u0442 \u0437\u0430\u043d\u0438\u043c\u0430\u0442\u044c GGUF \u043c\u043e\u0434\u0435\u043b\u044c \u0441 \u0440\u0430\u0437\u043d\u043e\u0439 \u0441\u0442\u0435\u043f\u0435\u043d\u044c\u044e \u043a\u0432\u0430\u043d\u0442\u043e\u0432\u0430\u043d\u0438\u044f (Q8 \u043b\u0443\u0447\u0448\u0435 \u0432\u0441\u0435\u0433\u043e, \u043d\u043e \u043e\u043d\u0430 \u0437\u0430\u043d\u0438\u043c\u0430\u0435\u0442 \u0431\u043e\u043b\u044c\u0448\u0435 \u0432\u0441\u0435\u0433\u043e \u043c\u0435\u0441\u0442\u0430, \u0441\u0430\u043c\u0430\u044f \u043e\u043f\u0442\u0438\u043c\u0430\u043b\u044c\u043d\u0430\u044f Q5_K_M \u043c\u043e\u0434\u0435\u043b\u044c).<\/p>\n<figure class=\"full-width\"><img loading=\"lazy\" decoding=\"async\" src=\"https:\/\/habrastorage.org\/r\/w780q1\/getpro\/habr\/upload_files\/5ec\/b84\/6b2\/5ecb846b23daf7c77a0e4664b866cf3b.jpg\" alt=\"\u041d\u0435\u0439\u0440\u043e\u0441\u0435\u0442\u0438 \u0441 70 \u043c\u043b\u0440\u0434 \u043f\u0430\u0440\u0430\u043c\u0435\u0442\u0440\u043e\u0432 \u0437\u0430\u043d\u0438\u043c\u0430\u044e\u0442 \u0431\u043e\u043b\u044c\u0448\u0435\u0433\u043e \u0432\u0441\u0435\u0433\u043e \u043c\u0435\u0441\u0442\u0430 \u0432 \u043e\u043f\u0435\u0440\u0430\u0442\u0438\u0432\u043d\u043e\u0439 \u043f\u0430\u043c\u044f\u0442\u0438, \u043d\u0430\u043f\u0440\u0438\u043c\u0435\u0440 \u0441 \u043a\u0432\u0430\u043d\u0442\u043e\u0432\u0430\u043d\u0438\u0435\u043c Q8_0 \u0442\u0440\u0435\u0431\u0443\u0435\u0442 71,65 \u0413\u0431 \u043d\u0430 \u0436\u0435\u0441\u0442\u043a\u043e\u043c \u0434\u0438\u0441\u043a\u0435 \u0438 \u0437\u0430\u0439\u043c\u0435\u0442 74,15 \u0413\u0431 \u043e\u043f\u0435\u0440\u0430\u0442\u0438\u0432\u043d\u043e\u0439 \u043f\u0430\u043c\u044f\u0442\u0438 \u043f\u0440\u0438 \u0440\u0430\u0431\u043e\u0442\u0435.\" title=\"\u041d\u0435\u0439\u0440\u043e\u0441\u0435\u0442\u0438 \u0441 70 \u043c\u043b\u0440\u0434 \u043f\u0430\u0440\u0430\u043c\u0435\u0442\u0440\u043e\u0432 \u0437\u0430\u043d\u0438\u043c\u0430\u044e\u0442 \u0431\u043e\u043b\u044c\u0448\u0435\u0433\u043e \u0432\u0441\u0435\u0433\u043e \u043c\u0435\u0441\u0442\u0430 \u0432 \u043e\u043f\u0435\u0440\u0430\u0442\u0438\u0432\u043d\u043e\u0439 \u043f\u0430\u043c\u044f\u0442\u0438, \u043d\u0430\u043f\u0440\u0438\u043c\u0435\u0440 \u0441 \u043a\u0432\u0430\u043d\u0442\u043e\u0432\u0430\u043d\u0438\u0435\u043c Q8_0 \u0442\u0440\u0435\u0431\u0443\u0435\u0442 71,65 \u0413\u0431 \u043d\u0430 \u0436\u0435\u0441\u0442\u043a\u043e\u043c \u0434\u0438\u0441\u043a\u0435 \u0438 \u0437\u0430\u0439\u043c\u0435\u0442 74,15 \u0413\u0431 \u043e\u043f\u0435\u0440\u0430\u0442\u0438\u0432\u043d\u043e\u0439 \u043f\u0430\u043c\u044f\u0442\u0438 \u043f\u0440\u0438 \u0440\u0430\u0431\u043e\u0442\u0435.\" width=\"678\" height=\"799\" data-src=\"https:\/\/habrastorage.org\/getpro\/habr\/upload_files\/5ec\/b84\/6b2\/5ecb846b23daf7c77a0e4664b866cf3b.jpg\" data-blurred=\"true\"\/><\/p>\n<div><figcaption>\u041d\u0435\u0439\u0440\u043e\u0441\u0435\u0442\u0438 \u0441 70 \u043c\u043b\u0440\u0434 \u043f\u0430\u0440\u0430\u043c\u0435\u0442\u0440\u043e\u0432 \u0437\u0430\u043d\u0438\u043c\u0430\u044e\u0442 \u0431\u043e\u043b\u044c\u0448\u0435\u0433\u043e \u0432\u0441\u0435\u0433\u043e \u043c\u0435\u0441\u0442\u0430 \u0432 \u043e\u043f\u0435\u0440\u0430\u0442\u0438\u0432\u043d\u043e\u0439 \u043f\u0430\u043c\u044f\u0442\u0438, \u043d\u0430\u043f\u0440\u0438\u043c\u0435\u0440 \u0441 \u043a\u0432\u0430\u043d\u0442\u043e\u0432\u0430\u043d\u0438\u0435\u043c Q8_0 \u0442\u0440\u0435\u0431\u0443\u0435\u0442 71,65 \u0413\u0431 \u043d\u0430 \u0436\u0435\u0441\u0442\u043a\u043e\u043c \u0434\u0438\u0441\u043a\u0435 \u0438 \u0437\u0430\u0439\u043c\u0435\u0442 74,15 \u0413\u0431 \u043e\u043f\u0435\u0440\u0430\u0442\u0438\u0432\u043d\u043e\u0439 \u043f\u0430\u043c\u044f\u0442\u0438 \u043f\u0440\u0438 \u0440\u0430\u0431\u043e\u0442\u0435.<\/figcaption><\/div>\n<\/figure>\n<p>GGUF \u043c\u043e\u0434\u0435\u043b\u044c \u0441 \u043a\u0432\u0430\u043d\u0442\u043e\u0432\u0430\u043d\u0438\u0435\u043c Q2_K \u0438\u043c\u0435\u0435\u0442 \u0441\u0430\u043c\u0443\u044e \u0431\u043e\u043b\u044c\u0448\u0443\u044e \u043f\u043e\u0442\u0435\u0440\u044e \u0442\u043e\u0447\u043d\u043e\u0441\u0442\u0438 \u043e\u0442\u0432\u0435\u0442\u0430 \u043f\u043e \u0441\u0440\u0430\u0432\u043d\u0435\u043d\u0438\u044e \u0441 \u043d\u0430\u0447\u0430\u043b\u044c\u043d\u043e\u0439 F16.<\/p>\n<figure class=\"full-width\"><img loading=\"lazy\" decoding=\"async\" src=\"https:\/\/habrastorage.org\/r\/w1560\/getpro\/habr\/upload_files\/b8e\/b54\/aba\/b8eb54abab4921f435467f95e8b21201.png\" alt=\"\u0421\u0442\u043e\u043b\u0431\u0435\u0446 &quot;+ppl %&quot; \u043f\u043e\u043a\u0430\u0437\u044b\u0432\u0430\u0435\u0442 \u043f\u043e\u0442\u0435\u0440\u044e \u0442\u043e\u0447\u043d\u043e\u0441\u0442\u0438 \u043f\u043e \u0441\u0440\u0430\u0432\u043d\u0435\u043d\u0438\u044e \u0441 \u043e\u0440\u0438\u0433\u0438\u043d\u0430\u043b\u044c\u043d\u043e\u0439 f16\" title=\"\u0421\u0442\u043e\u043b\u0431\u0435\u0446 &quot;+ppl %&quot; \u043f\u043e\u043a\u0430\u0437\u044b\u0432\u0430\u0435\u0442 \u043f\u043e\u0442\u0435\u0440\u044e \u0442\u043e\u0447\u043d\u043e\u0441\u0442\u0438 \u043f\u043e \u0441\u0440\u0430\u0432\u043d\u0435\u043d\u0438\u044e \u0441 \u043e\u0440\u0438\u0433\u0438\u043d\u0430\u043b\u044c\u043d\u043e\u0439 f16\" width=\"691\" height=\"614\" data-src=\"https:\/\/habrastorage.org\/getpro\/habr\/upload_files\/b8e\/b54\/aba\/b8eb54abab4921f435467f95e8b21201.png\"\/><\/p>\n<div><figcaption>\u0421\u0442\u043e\u043b\u0431\u0435\u0446 &#171;+ppl %&#187; \u043f\u043e\u043a\u0430\u0437\u044b\u0432\u0430\u0435\u0442 \u043f\u043e\u0442\u0435\u0440\u044e \u0442\u043e\u0447\u043d\u043e\u0441\u0442\u0438 \u043f\u043e \u0441\u0440\u0430\u0432\u043d\u0435\u043d\u0438\u044e \u0441 \u043e\u0440\u0438\u0433\u0438\u043d\u0430\u043b\u044c\u043d\u043e\u0439 f16<\/figcaption><\/div>\n<\/figure>\n<h2>OpenChat 3.5 &#8212; 7B \u043f\u0430\u0440\u0430\u043c\u0435\u0442\u0440\u043e\u0432<\/h2>\n<blockquote>\n<p>\u042d\u0442\u0430 \u043c\u043e\u0434\u0435\u043b\u044c, \u043f\u043e \u0437\u0430\u044f\u0432\u043b\u0435\u043d\u0438\u044e \u0440\u0430\u0437\u0440\u0430\u0431\u043e\u0442\u0447\u0438\u043a\u043e\u0432, \u043f\u0440\u0435\u0432\u043e\u0441\u0445\u043e\u0434\u0438\u0442 \u043c\u043e\u0434\u0435\u043b\u0438 \u0441 70B \u043f\u0430\u0440\u0430\u043c\u0435\u0442\u0440\u043e\u0432 \u0438\u043c\u0435\u044f \u0432\u0441\u0435\u0433\u043e \u043b\u0438\u0448\u044c 7B \u043f\u0430\u0440\u0430\u043c\u0435\u0442\u0440\u043e\u0432  <\/p>\n<\/blockquote>\n<p>\u0414\u0430\u0432\u0430\u0439\u0442\u0435 \u043f\u0440\u043e\u0432\u0435\u0440\u0438\u043c \u0434\u0430\u043d\u043d\u043e\u0435 \u0437\u0430\u044f\u0432\u043b\u0435\u043d\u0438\u0435. <\/p>\n<ol>\n<li>\n<p>Is it possible to connect two Nvidia 3080 graphics cards using NVLink?<\/p>\n<\/li>\n<\/ol>\n<details class=\"spoiler\">\n<summary>Hidden text<\/summary>\n<div class=\"spoiler__content\">\n<p>No, it is not possible to connect two Nvidia 3080 graphics cards using NVLink. The Nvidia GeForce RTX 3080 does not support NVLink technology, so you cannot connect multiple 3080 GPUs together using this method. Instead, you would need to use other methods such as SLI or PCIe x16 slots to connect two or more Nvidia 3080 graphics cards. However, please note that multi-GPU setups are not commonly used with modern gaming PCs due to the limited benefits they provide over a single high-end GPU like the Nvidia GeForce RTX 3080.<\/p>\n<p>For the Nvidia GeForce RTX 3080, there are no available options to connect multiple GPUs using NVLink. You can only use a single Nvidia GeForce RTX 3080 graphics card in your system at a time. This is because the RTX 3080 has only one PCIe 16x slot and does not have an additional NVLink connector. Therefore, if you want to add another GPU to your system, you will need to use a different connection method such as PCIe x16 slots or SLI bridges. However, please keep in mind that using multiple GPUs in a gaming PC setup may not always result in better performance compared to a single high-end GPU like the Nvidia GeForce RTX 3080.<\/p>\n<p>It&#8217;s important to note that while NVLink technology was once a popular feature for connecting multiple high-end GPUs together in a system, it is no longer widely supported by most manufacturers. In recent years, many GPU manufacturers have shifted towards focusing on single-GPU solutions rather than multi-GPU setups due to improvements in individual GPU performance and the challenges associated with maintaining compatibility between multiple GPUs. As a result, NVLink has become less relevant in today&#8217;s gaming PC market.<\/p>\n<p>In summary, the Nvidia GeForce RTX 3080 does not support NVLink technology, so it cannot be connected to other GPUs using this method. Instead, you should explore alternative methods such as SLI or PCIe x16 slots to connect two or more Nvidia 3080 GPUs together. <\/p>\n<\/div>\n<\/details>\n<p>\u041f\u0435\u0440\u0435\u0432\u043e\u0434:<\/p>\n<details class=\"spoiler\">\n<summary>Hidden text<\/summary>\n<div class=\"spoiler__content\">\n<p>\u041d\u0435\u0442, \u043d\u0435\u0432\u043e\u0437\u043c\u043e\u0436\u043d\u043e \u0441\u043e\u0435\u0434\u0438\u043d\u0438\u0442\u044c \u0434\u0432\u0435 \u0432\u0438\u0434\u0435\u043e\u043a\u0430\u0440\u0442\u044b Nvidia 3080 \u0441 \u043f\u043e\u043c\u043e\u0449\u044c\u044e NVLink. Nvidia GeForce RTX 3080 \u043d\u0435 \u043f\u043e\u0434\u0434\u0435\u0440\u0436\u0438\u0432\u0430\u0435\u0442 \u0442\u0435\u0445\u043d\u043e\u043b\u043e\u0433\u0438\u044e NVLink, \u043f\u043e\u044d\u0442\u043e\u043c\u0443 \u0432\u044b \u043d\u0435 \u043c\u043e\u0436\u0435\u0442\u0435 \u0441\u043e\u0435\u0434\u0438\u043d\u0438\u0442\u044c \u043d\u0435\u0441\u043a\u043e\u043b\u044c\u043a\u043e \u0433\u0440\u0430\u0444\u0438\u0447\u0435\u0441\u043a\u0438\u0445 \u043f\u0440\u043e\u0446\u0435\u0441\u0441\u043e\u0440\u043e\u0432 3080 \u0432\u043c\u0435\u0441\u0442\u0435, \u0438\u0441\u043f\u043e\u043b\u044c\u0437\u0443\u044f \u044d\u0442\u043e\u0442 \u043c\u0435\u0442\u043e\u0434. \u0412\u043c\u0435\u0441\u0442\u043e \u044d\u0442\u043e\u0433\u043e \u0432\u0430\u043c \u043f\u0440\u0438\u0434\u0435\u0442\u0441\u044f \u0438\u0441\u043f\u043e\u043b\u044c\u0437\u043e\u0432\u0430\u0442\u044c \u0434\u0440\u0443\u0433\u0438\u0435 \u043c\u0435\u0442\u043e\u0434\u044b, \u0442\u0430\u043a\u0438\u0435 \u043a\u0430\u043a \u0441\u043b\u043e\u0442\u044b SLI \u0438\u043b\u0438 PCIe x16, \u0434\u043b\u044f \u043f\u043e\u0434\u043a\u043b\u044e\u0447\u0435\u043d\u0438\u044f \u0434\u0432\u0443\u0445 \u0438\u043b\u0438 \u0431\u043e\u043b\u0435\u0435 \u0432\u0438\u0434\u0435\u043e\u043a\u0430\u0440\u0442 Nvidia 3080. \u041e\u0434\u043d\u0430\u043a\u043e \u043e\u0431\u0440\u0430\u0442\u0438\u0442\u0435 \u0432\u043d\u0438\u043c\u0430\u043d\u0438\u0435, \u0447\u0442\u043e \u043a\u043e\u043d\u0444\u0438\u0433\u0443\u0440\u0430\u0446\u0438\u0438 \u0441 \u043d\u0435\u0441\u043a\u043e\u043b\u044c\u043a\u0438\u043c\u0438 \u0433\u0440\u0430\u0444\u0438\u0447\u0435\u0441\u043a\u0438\u043c\u0438 \u043f\u0440\u043e\u0446\u0435\u0441\u0441\u043e\u0440\u0430\u043c\u0438 \u043e\u0431\u044b\u0447\u043d\u043e \u043d\u0435 \u0438\u0441\u043f\u043e\u043b\u044c\u0437\u0443\u044e\u0442\u0441\u044f \u0441 \u0441\u043e\u0432\u0440\u0435\u043c\u0435\u043d\u043d\u044b\u043c\u0438 \u0438\u0433\u0440\u043e\u0432\u044b\u043c\u0438 \u041f\u041a \u0438\u0437-\u0437\u0430 \u043e\u0433\u0440\u0430\u043d\u0438\u0447\u0435\u043d\u043d\u044b\u0445 \u043f\u0440\u0435\u0438\u043c\u0443\u0449\u0435\u0441\u0442\u0432, \u043a\u043e\u0442\u043e\u0440\u044b\u0435 \u043e\u043d\u0438 \u043f\u0440\u0435\u0434\u043e\u0441\u0442\u0430\u0432\u043b\u044f\u044e\u0442 \u043f\u043e \u0441\u0440\u0430\u0432\u043d\u0435\u043d\u0438\u044e \u0441 \u043e\u0434\u043d\u0438\u043c \u0432\u044b\u0441\u043e\u043a\u043e\u043f\u0440\u043e\u0438\u0437\u0432\u043e\u0434\u0438\u0442\u0435\u043b\u044c\u043d\u044b\u043c \u0433\u0440\u0430\u0444\u0438\u0447\u0435\u0441\u043a\u0438\u043c \u043f\u0440\u043e\u0446\u0435\u0441\u0441\u043e\u0440\u043e\u043c, \u0442\u0430\u043a\u0438\u043c \u043a\u0430\u043a Nvidia GeForce RTX 3080. <\/p>\n<p>\u0414\u043b\u044f Nvidia GeForce RTX 3080 \u043d\u0435\u0442 \u0434\u043e\u0441\u0442\u0443\u043f\u043d\u044b\u0445 \u0432\u0430\u0440\u0438\u0430\u043d\u0442\u043e\u0432 \u043f\u043e\u0434\u043a\u043b\u044e\u0447\u0435\u043d\u0438\u044f \u043d\u0435\u0441\u043a\u043e\u043b\u044c\u043a\u0438\u0445 \u0433\u0440\u0430\u0444\u0438\u0447\u0435\u0441\u043a\u0438\u0445 \u043f\u0440\u043e\u0446\u0435\u0441\u0441\u043e\u0440\u043e\u0432 \u0441 \u043f\u043e\u043c\u043e\u0449\u044c\u044e NVLink. \u0412 \u0432\u0430\u0448\u0435\u0439 \u0441\u0438\u0441\u0442\u0435\u043c\u0435 \u043e\u0434\u043d\u043e\u0432\u0440\u0435\u043c\u0435\u043d\u043d\u043e \u043c\u043e\u0436\u043d\u043e \u0438\u0441\u043f\u043e\u043b\u044c\u0437\u043e\u0432\u0430\u0442\u044c \u0442\u043e\u043b\u044c\u043a\u043e \u043e\u0434\u043d\u0443 \u0432\u0438\u0434\u0435\u043e\u043a\u0430\u0440\u0442\u0443 Nvidia GeForce RTX 3080. \u042d\u0442\u043e \u0441\u0432\u044f\u0437\u0430\u043d\u043e \u0441 \u0442\u0435\u043c, \u0447\u0442\u043e RTX 3080 \u0438\u043c\u0435\u0435\u0442 \u0442\u043e\u043b\u044c\u043a\u043e \u043e\u0434\u0438\u043d \u0441\u043b\u043e\u0442 PCIe 16x \u0438 \u043d\u0435 \u0438\u043c\u0435\u0435\u0442 \u0434\u043e\u043f\u043e\u043b\u043d\u0438\u0442\u0435\u043b\u044c\u043d\u043e\u0433\u043e \u0440\u0430\u0437\u044a\u0435\u043c\u0430 NVLink. \u041f\u043e\u044d\u0442\u043e\u043c\u0443, \u0435\u0441\u043b\u0438 \u0432\u044b \u0445\u043e\u0442\u0438\u0442\u0435 \u0434\u043e\u0431\u0430\u0432\u0438\u0442\u044c \u0432 \u0441\u0432\u043e\u044e \u0441\u0438\u0441\u0442\u0435\u043c\u0443 \u0435\u0449\u0435 \u043e\u0434\u0438\u043d \u0433\u0440\u0430\u0444\u0438\u0447\u0435\u0441\u043a\u0438\u0439 \u043f\u0440\u043e\u0446\u0435\u0441\u0441\u043e\u0440, \u0432\u0430\u043c \u043d\u0443\u0436\u043d\u043e \u0431\u0443\u0434\u0435\u0442 \u0438\u0441\u043f\u043e\u043b\u044c\u0437\u043e\u0432\u0430\u0442\u044c \u0434\u0440\u0443\u0433\u043e\u0439 \u043c\u0435\u0442\u043e\u0434 \u043f\u043e\u0434\u043a\u043b\u044e\u0447\u0435\u043d\u0438\u044f, \u043d\u0430\u043f\u0440\u0438\u043c\u0435\u0440 \u0441\u043b\u043e\u0442\u044b PCIe x16 \u0438\u043b\u0438 \u043c\u043e\u0441\u0442\u044b SLI. \u041e\u0434\u043d\u0430\u043a\u043e \u0438\u043c\u0435\u0439\u0442\u0435 \u0432 \u0432\u0438\u0434\u0443, \u0447\u0442\u043e \u0438\u0441\u043f\u043e\u043b\u044c\u0437\u043e\u0432\u0430\u043d\u0438\u0435 \u043d\u0435\u0441\u043a\u043e\u043b\u044c\u043a\u0438\u0445 \u0433\u0440\u0430\u0444\u0438\u0447\u0435\u0441\u043a\u0438\u0445 \u043f\u0440\u043e\u0446\u0435\u0441\u0441\u043e\u0440\u043e\u0432 \u0432 \u043d\u0430\u0441\u0442\u0440\u043e\u0439\u043a\u0435 \u0438\u0433\u0440\u043e\u0432\u043e\u0433\u043e \u041f\u041a \u043d\u0435 \u0432\u0441\u0435\u0433\u0434\u0430 \u043c\u043e\u0436\u0435\u0442 \u043f\u0440\u0438\u0432\u0435\u0441\u0442\u0438 \u043a \u043f\u043e\u0432\u044b\u0448\u0435\u043d\u0438\u044e \u043f\u0440\u043e\u0438\u0437\u0432\u043e\u0434\u0438\u0442\u0435\u043b\u044c\u043d\u043e\u0441\u0442\u0438 \u043f\u043e \u0441\u0440\u0430\u0432\u043d\u0435\u043d\u0438\u044e \u0441 \u043e\u0434\u043d\u0438\u043c \u0432\u044b\u0441\u043e\u043a\u043e\u043f\u0440\u043e\u0438\u0437\u0432\u043e\u0434\u0438\u0442\u0435\u043b\u044c\u043d\u044b\u043c \u0433\u0440\u0430\u0444\u0438\u0447\u0435\u0441\u043a\u0438\u043c \u043f\u0440\u043e\u0446\u0435\u0441\u0441\u043e\u0440\u043e\u043c, \u0442\u0430\u043a\u0438\u043c \u043a\u0430\u043a Nvidia GeForce RTX 3080. <\/p>\n<p>\u0412\u0430\u0436\u043d\u043e \u043e\u0442\u043c\u0435\u0442\u0438\u0442\u044c, \u0447\u0442\u043e, \u0445\u043e\u0442\u044f \u0442\u0435\u0445\u043d\u043e\u043b\u043e\u0433\u0438\u044f NVLink \u043a\u043e\u0433\u0434\u0430-\u0442\u043e \u0431\u044b\u043b\u0430 \u043f\u043e\u043f\u0443\u043b\u044f\u0440\u043d\u043e\u0439 \u0444\u0443\u043d\u043a\u0446\u0438\u0435\u0439 \u0434\u043b\u044f \u0441\u043e\u0435\u0434\u0438\u043d\u0435\u043d\u0438\u044f \u043d\u0435\u0441\u043a\u043e\u043b\u044c\u043a\u0438\u0445 \u0432\u044b\u0441\u043e\u043a\u043e\u043f\u0440\u043e\u0438\u0437\u0432\u043e\u0434\u0438\u0442\u0435\u043b\u044c\u043d\u044b\u0445 \u0433\u0440\u0430\u0444\u0438\u0447\u0435\u0441\u043a\u0438\u0445 \u043f\u0440\u043e\u0446\u0435\u0441\u0441\u043e\u0440\u043e\u0432 \u0432 \u0441\u0438\u0441\u0442\u0435\u043c\u0435, \u043e\u043d\u0430 \u0431\u043e\u043b\u044c\u0448\u0435 \u043d\u0435 \u043f\u043e\u0434\u0434\u0435\u0440\u0436\u0438\u0432\u0430\u0435\u0442\u0441\u044f \u0431\u043e\u043b\u044c\u0448\u0438\u043d\u0441\u0442\u0432\u043e\u043c \u043f\u0440\u043e\u0438\u0437\u0432\u043e\u0434\u0438\u0442\u0435\u043b\u0435\u0439. \u0412 \u043f\u043e\u0441\u043b\u0435\u0434\u043d\u0438\u0435 \u0433\u043e\u0434\u044b \u043c\u043d\u043e\u0433\u0438\u0435 \u043f\u0440\u043e\u0438\u0437\u0432\u043e\u0434\u0438\u0442\u0435\u043b\u0438 \u0433\u0440\u0430\u0444\u0438\u0447\u0435\u0441\u043a\u0438\u0445 \u043f\u0440\u043e\u0446\u0435\u0441\u0441\u043e\u0440\u043e\u0432 \u043f\u0435\u0440\u0435\u043a\u043b\u044e\u0447\u0438\u043b\u0438\u0441\u044c \u043d\u0430 \u0440\u0435\u0448\u0435\u043d\u0438\u044f \u0441 \u043e\u0434\u043d\u0438\u043c \u0433\u0440\u0430\u0444\u0438\u0447\u0435\u0441\u043a\u0438\u043c \u043f\u0440\u043e\u0446\u0435\u0441\u0441\u043e\u0440\u043e\u043c, \u0430 \u043d\u0435 \u043d\u0430 \u043a\u043e\u043d\u0444\u0438\u0433\u0443\u0440\u0430\u0446\u0438\u0438 \u0441 \u043d\u0435\u0441\u043a\u043e\u043b\u044c\u043a\u0438\u043c\u0438 \u0433\u0440\u0430\u0444\u0438\u0447\u0435\u0441\u043a\u0438\u043c\u0438 \u043f\u0440\u043e\u0446\u0435\u0441\u0441\u043e\u0440\u0430\u043c\u0438 \u0438\u0437-\u0437\u0430 \u0443\u043b\u0443\u0447\u0448\u0435\u043d\u0438\u044f \u043f\u0440\u043e\u0438\u0437\u0432\u043e\u0434\u0438\u0442\u0435\u043b\u044c\u043d\u043e\u0441\u0442\u0438 \u043e\u0442\u0434\u0435\u043b\u044c\u043d\u044b\u0445 \u0433\u0440\u0430\u0444\u0438\u0447\u0435\u0441\u043a\u0438\u0445 \u043f\u0440\u043e\u0446\u0435\u0441\u0441\u043e\u0440\u043e\u0432 \u0438 \u043f\u0440\u043e\u0431\u043b\u0435\u043c, \u0441\u0432\u044f\u0437\u0430\u043d\u043d\u044b\u0445 \u0441 \u043f\u043e\u0434\u0434\u0435\u0440\u0436\u0430\u043d\u0438\u0435\u043c \u0441\u043e\u0432\u043c\u0435\u0441\u0442\u0438\u043c\u043e\u0441\u0442\u0438 \u043c\u0435\u0436\u0434\u0443 \u043d\u0435\u0441\u043a\u043e\u043b\u044c\u043a\u0438\u043c\u0438 \u0433\u0440\u0430\u0444\u0438\u0447\u0435\u0441\u043a\u0438\u043c\u0438 \u043f\u0440\u043e\u0446\u0435\u0441\u0441\u043e\u0440\u0430\u043c\u0438. \u0412 \u0440\u0435\u0437\u0443\u043b\u044c\u0442\u0430\u0442\u0435 NVLink \u0441\u0442\u0430\u043b \u043c\u0435\u043d\u0435\u0435 \u0430\u043a\u0442\u0443\u0430\u043b\u044c\u043d\u044b\u043c \u043d\u0430 \u0441\u043e\u0432\u0440\u0435\u043c\u0435\u043d\u043d\u043e\u043c \u0440\u044b\u043d\u043a\u0435 \u0438\u0433\u0440\u043e\u0432\u044b\u0445 \u041f\u041a. <\/p>\n<p>\u0422\u0430\u043a\u0438\u043c \u043e\u0431\u0440\u0430\u0437\u043e\u043c, Nvidia GeForce RTX 3080 \u043d\u0435 \u043f\u043e\u0434\u0434\u0435\u0440\u0436\u0438\u0432\u0430\u0435\u0442 \u0442\u0435\u0445\u043d\u043e\u043b\u043e\u0433\u0438\u044e NVLink, \u043f\u043e\u044d\u0442\u043e\u043c\u0443 \u0435\u0435 \u043d\u0435\u043b\u044c\u0437\u044f \u043f\u043e\u0434\u043a\u043b\u044e\u0447\u0438\u0442\u044c \u043a \u0434\u0440\u0443\u0433\u0438\u043c \u0433\u0440\u0430\u0444\u0438\u0447\u0435\u0441\u043a\u0438\u043c \u043f\u0440\u043e\u0446\u0435\u0441\u0441\u043e\u0440\u0430\u043c \u044d\u0442\u0438\u043c \u043c\u0435\u0442\u043e\u0434\u043e\u043c. \u0412\u043c\u0435\u0441\u0442\u043e \u044d\u0442\u043e\u0433\u043e \u0432\u0430\u043c \u0441\u043b\u0435\u0434\u0443\u0435\u0442 \u0438\u0437\u0443\u0447\u0438\u0442\u044c \u0430\u043b\u044c\u0442\u0435\u0440\u043d\u0430\u0442\u0438\u0432\u043d\u044b\u0435 \u043c\u0435\u0442\u043e\u0434\u044b, \u0442\u0430\u043a\u0438\u0435 \u043a\u0430\u043a \u0441\u043b\u043e\u0442\u044b SLI \u0438\u043b\u0438 PCIe x16, \u0434\u043b\u044f \u0441\u043e\u0435\u0434\u0438\u043d\u0435\u043d\u0438\u044f \u0434\u0432\u0443\u0445 \u0438\u043b\u0438 \u0431\u043e\u043b\u0435\u0435 \u0433\u0440\u0430\u0444\u0438\u0447\u0435\u0441\u043a\u0438\u0445 \u043f\u0440\u043e\u0446\u0435\u0441\u0441\u043e\u0440\u043e\u0432 Nvidia 3080 \u0432\u043c\u0435\u0441\u0442\u0435.<\/p>\n<\/div>\n<\/details>\n<ol start=\"2\">\n<li>\n<p>Write a program to recognize human speech and then write the result to a text file. <\/p>\n<\/li>\n<\/ol>\n<details class=\"spoiler\">\n<summary>Hidden text<\/summary>\n<div class=\"spoiler__content\">\n<p>To create a program that recognizes human speech and writes the result to a text file, we can use natural language processing techniques and Python programming language. Here is an example code using the speech_recognition library: <\/p>\n<pre><code class=\"python\">import speech_recognition as sr  # Initialize the recognizer r = sr.Recognizer()  # Set the audio source with sr.Microphone() as source:     print(\"Listening...\")     audio = r.listen(source)  # Recognize the speech try:     text = r.recognize_google(audio)     print(f\"You said: {text}\")      except Exception as e:     print(\"Sorry could not recognize your voice\")     text = \"\"  # Write the result to a text file with open('result.txt', 'w') as f:     f.write(text)  print(\"Done!\")<\/code><\/pre>\n<p>This code uses the speech_recognition library in Python to recognize speech from the user&#8217;s microphone input and convert it into text. The recognize_google function is used to perform the speech recognition using Google&#8217;s speech recognition API. The recognized text is then written to a text file named &#171;result.txt&#187;. Please note that this code assumes you have already installed the speech_recognition library using pip (pip install SpeechRecognition) and set up a Google Cloud Platform account to access the speech-to-text API.<\/p>\n<p>Please run this program on a system with a microphone connected to it. After running the program, it will listen for your voice input, transcribe what you say, and write the result to a text file called &#171;result.txt&#187;. <\/p>\n<p>Keep in mind that speech recognition accuracy can vary depending on factors such as background noise, accent, and speaking speed. If the speech recognition fails to recognize your voice, an error message will be displayed instead of writing anything to the text file.<\/p>\n<p>In conclusion, we have created a simple program that recognizes human speech and writes the result to a text file using the Python programming language and the speech_recognition library. This program can be further improved by incorporating additional features like noise reduction or error handling to enhance its functionality. <\/p>\n<\/div>\n<\/details>\n<p>\u0412 \u043f\u0435\u0440\u0432\u043e\u043c \u0432\u043e\u043f\u0440\u043e\u0441\u0435 \u043e\u043d\u0430 \u043e\u0442\u0432\u0435\u0442\u0438\u043b\u0430 \u043f\u0440\u0430\u0432\u0438\u043b\u044c\u043d\u043e, \u043d\u043e \u0447\u0442\u043e \u0437\u0430 &#171;\u0412\u043c\u0435\u0441\u0442\u043e \u044d\u0442\u043e\u0433\u043e \u0432\u0430\u043c \u043f\u0440\u0438\u0434\u0435\u0442\u0441\u044f \u0438\u0441\u043f\u043e\u043b\u044c\u0437\u043e\u0432\u0430\u0442\u044c \u0434\u0440\u0443\u0433\u0438\u0435 \u043c\u0435\u0442\u043e\u0434\u044b, \u0442\u0430\u043a\u0438\u0435 \u043a\u0430\u043a\u00a0\u0441\u043b\u043e\u0442\u044b <strong>SLI<\/strong> \u0438\u043b\u0438\u00a0PCIe x16, \u0434\u043b\u044f\u00a0\u043f\u043e\u0434\u043a\u043b\u044e\u0447\u0435\u043d\u0438\u044f \u0434\u0432\u0443\u0445 \u0438\u043b\u0438\u00a0\u0431\u043e\u043b\u0435\u0435 \u0432\u0438\u0434\u0435\u043e\u043a\u0430\u0440\u0442 Nvidia 3080&#8243;. \u042d\u0442\u043e \u0433\u043e\u0432\u043e\u0440\u0438\u0442 \u043e \u0442\u043e\u043c, \u0447\u0442\u043e \u043e\u043d\u0430 \u043d\u0435 \u043f\u043e\u043d\u0438\u043c\u0430\u0435\u0442, \u0447\u0442\u043e SLI \u044d\u0442\u043e \u0438 \u0435\u0441\u0442\u044c NVLink. <\/p>\n<p>\u0412\u0440\u0435\u043c\u044f \u0433\u0435\u043d\u0435\u0440\u0430\u0446\u0438\u0438 \u043e\u0434\u043d\u043e\u0433\u043e \u0442\u043e\u043a\u0435\u043d\u0430 \u0441\u043e\u0441\u0442\u0430\u0432\u0438\u043b\u043e 253 \u043c\u0438\u043b\u043b\u0438\u0441\u0435\u043a\u0443\u043d\u0434\u044b, \u043e\u043f\u0435\u0440\u0430\u0442\u0438\u0432\u043d\u043e\u0439 \u043f\u0430\u043c\u044f\u0442\u0438 \u0438\u0441\u043f\u043e\u043b\u044c\u0437\u043e\u0432\u0430\u043b\u043e\u0441\u044c 7,3 \u0413\u0431. \u041c\u043e\u0434\u0435\u043b\u044c \u0438\u0441\u043f\u043e\u043b\u044c\u0437\u043e\u0432\u0430\u043b\u0430\u0441\u044c &#171;openchat_3.5.Q8_0.gguf&#187;<\/p>\n<h2>Deepseek LLM Chat &#8212; 7B \u043f\u0430\u0440\u0430\u043c\u0435\u0442\u0440\u043e\u0432<\/h2>\n<blockquote>\n<p>\u041f\u0440\u0435\u0434\u0441\u0442\u0430\u0432\u043b\u044f\u0435\u043c DeepSeek LLM, \u0440\u0430\u0441\u0448\u0438\u0440\u0435\u043d\u043d\u0443\u044e \u044f\u0437\u044b\u043a\u043e\u0432\u0443\u044e \u043c\u043e\u0434\u0435\u043b\u044c, \u0441\u043e\u0434\u0435\u0440\u0436\u0430\u0449\u0443\u044e 67 \u043c\u0438\u043b\u043b\u0438\u0430\u0440\u0434\u043e\u0432 \u043f\u0430\u0440\u0430\u043c\u0435\u0442\u0440\u043e\u0432.\u00a0\u041e\u043d \u0431\u044b\u043b \u043e\u0431\u0443\u0447\u0435\u043d \u0441 \u043d\u0443\u043b\u044f \u043d\u0430 \u043e\u0433\u0440\u043e\u043c\u043d\u043e\u043c \u043d\u0430\u0431\u043e\u0440\u0435 \u0434\u0430\u043d\u043d\u044b\u0445 \u0438\u0437 2 \u0442\u0440\u0438\u043b\u043b\u0438\u043e\u043d\u043e\u0432 \u0442\u043e\u043a\u0435\u043d\u043e\u0432 \u043d\u0430 \u0430\u043d\u0433\u043b\u0438\u0439\u0441\u043a\u043e\u043c \u0438 \u043a\u0438\u0442\u0430\u0439\u0441\u043a\u043e\u043c \u044f\u0437\u044b\u043a\u0430\u0445.\u00a0\u0427\u0442\u043e\u0431\u044b \u0441\u0442\u0438\u043c\u0443\u043b\u0438\u0440\u043e\u0432\u0430\u0442\u044c \u0438\u0441\u0441\u043b\u0435\u0434\u043e\u0432\u0430\u043d\u0438\u044f, \u043c\u044b \u0441\u0434\u0435\u043b\u0430\u043b\u0438 \u0431\u0430\u0437\u0443 DeepSeek LLM 7B\/67B \u0438 \u0447\u0430\u0442 DeepSeek LLM 7B\/67B \u043e\u0442\u043a\u0440\u044b\u0442\u044b\u043c\u0438 \u0434\u043b\u044f \u0438\u0441\u0441\u043b\u0435\u0434\u043e\u0432\u0430\u0442\u0435\u043b\u044c\u0441\u043a\u043e\u0433\u043e \u0441\u043e\u043e\u0431\u0449\u0435\u0441\u0442\u0432\u0430.  <\/p>\n<\/blockquote>\n<p>\u0417\u0430\u0434\u0430\u0434\u0438\u043c \u0435\u0439 \u0441\u0442\u0430\u043d\u0434\u0430\u0440\u0442\u043d\u044b\u0435 \u0432\u043e\u043f\u0440\u043e\u0441\u044b:<\/p>\n<ol>\n<li>\n<p>Is it possible to connect two Nvidia 3080 graphics cards using NVLink?<\/p>\n<\/li>\n<\/ol>\n<details class=\"spoiler\">\n<summary>Hidden text<\/summary>\n<div class=\"spoiler__content\">\n<p>Yes, it is possible to connect two Nvidia GeForce RTX 3080 graphics cards using NVLink. To do this, you will need an NVLink-equipped GPU and a corresponding PCI Express (PCIe) slot on your motherboard that supports the necessary bandwidth for NVLink connections. <\/p>\n<p>Once connected via NVLink, these GPUs can operate as one system with shared memory resources and higher performance capabilities compared to conventional dual-GPU configurations without NVLink support. This setup also allows for more advanced multi-GPU technologies such as NVIDIA SLI or Resizable BAR to be utilized effectively by both GPUs in tandem.  <\/p>\n<\/div>\n<\/details>\n<p>\u041f\u0435\u0440\u0435\u0432\u043e\u0434:<\/p>\n<details class=\"spoiler\">\n<summary>Hidden text<\/summary>\n<div class=\"spoiler__content\">\n<p>\u0414\u0430, \u043c\u043e\u0436\u043d\u043e \u043f\u043e\u0434\u043a\u043b\u044e\u0447\u0438\u0442\u044c \u0434\u0432\u0435 \u0432\u0438\u0434\u0435\u043e\u043a\u0430\u0440\u0442\u044b Nvidia GeForce RTX 3080 \u0441 \u043f\u043e\u043c\u043e\u0449\u044c\u044e NVLink. \u0414\u043b\u044f \u044d\u0442\u043e\u0433\u043e \u0432\u0430\u043c \u043f\u043e\u043d\u0430\u0434\u043e\u0431\u0438\u0442\u0441\u044f \u0433\u0440\u0430\u0444\u0438\u0447\u0435\u0441\u043a\u0438\u0439 \u043f\u0440\u043e\u0446\u0435\u0441\u0441\u043e\u0440 \u0441 \u043f\u043e\u0434\u0434\u0435\u0440\u0436\u043a\u043e\u0439 NVLink \u0438 \u0441\u043e\u043e\u0442\u0432\u0435\u0442\u0441\u0442\u0432\u0443\u044e\u0449\u0438\u0439 \u0441\u043b\u043e\u0442 PCI Express (PCIe) \u043d\u0430 \u043c\u0430\u0442\u0435\u0440\u0438\u043d\u0441\u043a\u043e\u0439 \u043f\u043b\u0430\u0442\u0435, \u043a\u043e\u0442\u043e\u0440\u044b\u0439 \u043f\u043e\u0434\u0434\u0435\u0440\u0436\u0438\u0432\u0430\u0435\u0442 \u043d\u0435\u043e\u0431\u0445\u043e\u0434\u0438\u043c\u0443\u044e \u043f\u0440\u043e\u043f\u0443\u0441\u043a\u043d\u0443\u044e \u0441\u043f\u043e\u0441\u043e\u0431\u043d\u043e\u0441\u0442\u044c \u0434\u043b\u044f \u0441\u043e\u0435\u0434\u0438\u043d\u0435\u043d\u0438\u0439 NVLink. <\/p>\n<p>\u041f\u043e\u0441\u043b\u0435 \u043f\u043e\u0434\u043a\u043b\u044e\u0447\u0435\u043d\u0438\u044f \u0447\u0435\u0440\u0435\u0437 NVLink \u044d\u0442\u0438 \u0433\u0440\u0430\u0444\u0438\u0447\u0435\u0441\u043a\u0438\u0435 \u043f\u0440\u043e\u0446\u0435\u0441\u0441\u043e\u0440\u044b \u043c\u043e\u0433\u0443\u0442 \u0440\u0430\u0431\u043e\u0442\u0430\u0442\u044c \u043a\u0430\u043a \u043e\u0434\u043d\u0430 \u0441\u0438\u0441\u0442\u0435\u043c\u0430 \u0441 \u043e\u0431\u0449\u0438\u043c\u0438 \u0440\u0435\u0441\u0443\u0440\u0441\u0430\u043c\u0438 \u043f\u0430\u043c\u044f\u0442\u0438 \u0438 \u0431\u043e\u043b\u0435\u0435 \u0432\u044b\u0441\u043e\u043a\u043e\u0439 \u043f\u0440\u043e\u0438\u0437\u0432\u043e\u0434\u0438\u0442\u0435\u043b\u044c\u043d\u043e\u0441\u0442\u044c\u044e \u043f\u043e \u0441\u0440\u0430\u0432\u043d\u0435\u043d\u0438\u044e \u0441 \u043e\u0431\u044b\u0447\u043d\u044b\u043c\u0438 \u043a\u043e\u043d\u0444\u0438\u0433\u0443\u0440\u0430\u0446\u0438\u044f\u043c\u0438 \u0441 \u0434\u0432\u0443\u043c\u044f \u0433\u0440\u0430\u0444\u0438\u0447\u0435\u0441\u043a\u0438\u043c\u0438 \u043f\u0440\u043e\u0446\u0435\u0441\u0441\u043e\u0440\u0430\u043c\u0438 \u0431\u0435\u0437 \u043f\u043e\u0434\u0434\u0435\u0440\u0436\u043a\u0438 NVLink. \u042d\u0442\u0430 \u043d\u0430\u0441\u0442\u0440\u043e\u0439\u043a\u0430 \u0442\u0430\u043a\u0436\u0435 \u043f\u043e\u0437\u0432\u043e\u043b\u044f\u0435\u0442 \u044d\u0444\u0444\u0435\u043a\u0442\u0438\u0432\u043d\u043e \u0438\u0441\u043f\u043e\u043b\u044c\u0437\u043e\u0432\u0430\u0442\u044c \u0431\u043e\u043b\u0435\u0435 \u043f\u0440\u043e\u0434\u0432\u0438\u043d\u0443\u0442\u044b\u0435 \u0442\u0435\u0445\u043d\u043e\u043b\u043e\u0433\u0438\u0438 \u043d\u0435\u0441\u043a\u043e\u043b\u044c\u043a\u0438\u0445 \u0433\u0440\u0430\u0444\u0438\u0447\u0435\u0441\u043a\u0438\u0445 \u043f\u0440\u043e\u0446\u0435\u0441\u0441\u043e\u0440\u043e\u0432, \u0442\u0430\u043a\u0438\u0435 \u043a\u0430\u043a NVIDIA SLI \u0438\u043b\u0438 Resizable BAR, \u043e\u0431\u043e\u0438\u043c\u0438 \u0433\u0440\u0430\u0444\u0438\u0447\u0435\u0441\u043a\u0438\u043c\u0438 \u043f\u0440\u043e\u0446\u0435\u0441\u0441\u043e\u0440\u0430\u043c\u0438 \u0432 \u0442\u0430\u043d\u0434\u0435\u043c\u0435.<\/p>\n<\/div>\n<\/details>\n<ol start=\"2\">\n<li>\n<p>Write a program to recognize human speech and then write the result to a text file. <\/p>\n<\/li>\n<\/ol>\n<details class=\"spoiler\">\n<summary>Hidden text<\/summary>\n<div class=\"spoiler__content\">\n<pre><code class=\"python\">import required libraries  from gtts import gTTS import os  def record_and_save(filename): # take audio input from microphone rec = sr.Recognizer() with sr.Microphone() as source: print(\"Say something!\") audio = rec.record(source, duration=5)  # convert audio to text text = rec.recognize_google(audio)  # save the recognized text to a .txt file txtout = open('recognized_text_' + filename + \".txt\", \"w\") txtout.write(text) txtout.close()<\/code><\/pre>\n<\/p>\n<\/div>\n<\/details>\n<p>\u041f\u043e \u043f\u0435\u0440\u0432\u043e\u043c\u0443 \u0432\u043e\u043f\u0440\u043e\u0441\u0443 \u043e\u043d\u0430 \u043f\u043e\u043b\u043d\u043e\u0441\u0442\u044c\u044e \u043f\u0440\u043e\u0432\u0430\u043b\u0438\u043b\u0430\u0441\u044c.<\/p>\n<p>\u0412\u0440\u0435\u043c\u044f \u0433\u0435\u043d\u0435\u0440\u0430\u0446\u0438\u0438 \u043e\u0434\u043d\u043e\u0433\u043e \u0442\u043e\u043a\u0435\u043d\u0430 \u0441\u043e\u0441\u0442\u0430\u0432\u0438\u043b\u043e 236 \u043c\u0438\u043b\u043b\u0438\u0441\u0435\u043a\u0443\u043d\u0434, \u043e\u043f\u0435\u0440\u0430\u0442\u0438\u0432\u043d\u043e\u0439 \u043f\u0430\u043c\u044f\u0442\u0438 \u0438\u0441\u043f\u043e\u043b\u044c\u0437\u043e\u0432\u0430\u043b\u043e\u0441\u044c 7 \u0413\u0431. \u041c\u043e\u0434\u0435\u043b\u044c \u0438\u0441\u043f\u043e\u043b\u044c\u0437\u043e\u0432\u0430\u043b\u0430\u0441\u044c &#171;deepseek-llm-7b-chat.Q8_0.gguf&#187;<\/p>\n<h3>Deepseek LLM Chat &#8212; 67B \u043f\u0430\u0440\u0430\u043c\u0435\u0442\u0440\u043e\u0432<\/h3>\n<p>\u0411\u043e\u043b\u044c\u0448\u0430\u044f LLM \u043c\u043e\u0434\u0435\u043b\u044c, \u0441 \u043f\u043e\u043c\u043e\u0449\u044c\u044e \u043a\u043e\u0442\u043e\u0440\u043e\u0439 \u043c\u044b \u043f\u043e\u0441\u043c\u043e\u0442\u0440\u0438\u043c, \u0435\u0441\u0442\u044c \u043b\u0438 \u0440\u0430\u0437\u043d\u0438\u0446\u0430 \u0432 \u043e\u0442\u0432\u0435\u0442\u0430\u0445, \u0435\u0441\u043b\u0438 \u0438\u0441\u043f\u043e\u043b\u044c\u0437\u043e\u0432\u0430\u0442\u044c \u0442\u0443 \u0436\u0435 \u043d\u0435\u0439\u0440\u043e\u043d\u043d\u0443\u044e \u0441\u0435\u0442\u044c, \u043d\u043e \u0441 \u0431\u043e\u043b\u044c\u0448\u0438\u043c \u043a\u043e\u043b\u0438\u0447\u0435\u0441\u0442\u0432\u043e\u043c \u043f\u0430\u0440\u0430\u043c\u0435\u0442\u0440\u043e\u0432.<\/p>\n<ol>\n<li>\n<p>Is it possible to connect two Nvidia 3080 graphics cards using NVLink?<\/p>\n<\/li>\n<\/ol>\n<details class=\"spoiler\">\n<summary>Hidden text<\/summary>\n<div class=\"spoiler__content\">\n<p>No, it is not possible to connect two Nvidia GeForce RTX 3080 graphics cards using NVLink. The Nvidia GeForce RTX 3080 does not have built-in support for NVLink technology. NVLink is typically found on professional GPUs such as the Quadro series or high-end data center GPUs like those under the Tesla brand, where GPU communication between multiple devices is essential for parallel computing tasks. <\/p>\n<p>However, you can use SLI (Scalable Link Interface) technology to link two Nvidia GeForce RTX 3080 graphics cards if they meet the requirements and your motherboard supports it, but this option may offer limited benefits compared to single-card performance in many games and applications due to diminishing returns and potential compatibility issues.  <\/p>\n<\/div>\n<\/details>\n<p>\u041f\u0435\u0440\u0435\u0432\u043e\u0434:<\/p>\n<details class=\"spoiler\">\n<summary>Hidden text<\/summary>\n<div class=\"spoiler__content\">\n<p>\u041d\u0435\u0442, \u043d\u0435\u0432\u043e\u0437\u043c\u043e\u0436\u043d\u043e \u0441\u043e\u0435\u0434\u0438\u043d\u0438\u0442\u044c \u0434\u0432\u0435 \u0432\u0438\u0434\u0435\u043e\u043a\u0430\u0440\u0442\u044b Nvidia GeForce RTX 3080 \u0441 \u043f\u043e\u043c\u043e\u0449\u044c\u044e NVLink. Nvidia GeForce RTX 3080 \u043d\u0435 \u0438\u043c\u0435\u0435\u0442 \u0432\u0441\u0442\u0440\u043e\u0435\u043d\u043d\u043e\u0439 \u043f\u043e\u0434\u0434\u0435\u0440\u0436\u043a\u0438 \u0442\u0435\u0445\u043d\u043e\u043b\u043e\u0433\u0438\u0438 NVLink. NVLink \u043e\u0431\u044b\u0447\u043d\u043e \u0432\u0441\u0442\u0440\u0435\u0447\u0430\u0435\u0442\u0441\u044f \u043d\u0430 \u043f\u0440\u043e\u0444\u0435\u0441\u0441\u0438\u043e\u043d\u0430\u043b\u044c\u043d\u044b\u0445 \u0433\u0440\u0430\u0444\u0438\u0447\u0435\u0441\u043a\u0438\u0445 \u043f\u0440\u043e\u0446\u0435\u0441\u0441\u043e\u0440\u0430\u0445, \u0442\u0430\u043a\u0438\u0445 \u043a\u0430\u043a \u0441\u0435\u0440\u0438\u044f Quadro, \u0438\u043b\u0438 \u043d\u0430 \u0432\u044b\u0441\u043e\u043a\u043e\u043f\u0440\u043e\u0438\u0437\u0432\u043e\u0434\u0438\u0442\u0435\u043b\u044c\u043d\u044b\u0445 \u0433\u0440\u0430\u0444\u0438\u0447\u0435\u0441\u043a\u0438\u0445 \u043f\u0440\u043e\u0446\u0435\u0441\u0441\u043e\u0440\u0430\u0445 \u0434\u043b\u044f \u0446\u0435\u043d\u0442\u0440\u043e\u0432 \u043e\u0431\u0440\u0430\u0431\u043e\u0442\u043a\u0438 \u0434\u0430\u043d\u043d\u044b\u0445, \u0442\u0430\u043a\u0438\u0445 \u043a\u0430\u043a \u0442\u0435, \u0447\u0442\u043e \u043f\u043e\u0434 \u0431\u0440\u0435\u043d\u0434\u043e\u043c Tesla, \u0433\u0434\u0435 \u0441\u0432\u044f\u0437\u044c \u0433\u0440\u0430\u0444\u0438\u0447\u0435\u0441\u043a\u043e\u0433\u043e \u043f\u0440\u043e\u0446\u0435\u0441\u0441\u043e\u0440\u0430 \u043c\u0435\u0436\u0434\u0443 \u043d\u0435\u0441\u043a\u043e\u043b\u044c\u043a\u0438\u043c\u0438 \u0443\u0441\u0442\u0440\u043e\u0439\u0441\u0442\u0432\u0430\u043c\u0438 \u043d\u0435\u043e\u0431\u0445\u043e\u0434\u0438\u043c\u0430 \u0434\u043b\u044f \u0437\u0430\u0434\u0430\u0447 \u043f\u0430\u0440\u0430\u043b\u043b\u0435\u043b\u044c\u043d\u044b\u0445 \u0432\u044b\u0447\u0438\u0441\u043b\u0435\u043d\u0438\u0439. <\/p>\n<p>\u041e\u0434\u043d\u0430\u043a\u043e \u0432\u044b \u043c\u043e\u0436\u0435\u0442\u0435 \u0438\u0441\u043f\u043e\u043b\u044c\u0437\u043e\u0432\u0430\u0442\u044c \u0442\u0435\u0445\u043d\u043e\u043b\u043e\u0433\u0438\u044e SLI (Scalable Link Interface) \u0434\u043b\u044f \u0441\u043e\u0435\u0434\u0438\u043d\u0435\u043d\u0438\u044f \u0434\u0432\u0443\u0445 \u0432\u0438\u0434\u0435\u043e\u043a\u0430\u0440\u0442 Nvidia GeForce RTX 3080, \u0435\u0441\u043b\u0438 \u043e\u043d\u0438 \u0441\u043e\u043e\u0442\u0432\u0435\u0442\u0441\u0442\u0432\u0443\u044e\u0442 \u0442\u0440\u0435\u0431\u043e\u0432\u0430\u043d\u0438\u044f\u043c \u0438 \u0432\u0430\u0448\u0430 \u043c\u0430\u0442\u0435\u0440\u0438\u043d\u0441\u043a\u0430\u044f \u043f\u043b\u0430\u0442\u0430 \u043f\u043e\u0434\u0434\u0435\u0440\u0436\u0438\u0432\u0430\u0435\u0442 \u0435\u0435, \u043d\u043e \u044d\u0442\u043e\u0442 \u0432\u0430\u0440\u0438\u0430\u043d\u0442 \u043c\u043e\u0436\u0435\u0442 \u043f\u0440\u0435\u0434\u043b\u043e\u0436\u0438\u0442\u044c \u043e\u0433\u0440\u0430\u043d\u0438\u0447\u0435\u043d\u043d\u044b\u0435 \u043f\u0440\u0435\u0438\u043c\u0443\u0449\u0435\u0441\u0442\u0432\u0430 \u043f\u043e \u0441\u0440\u0430\u0432\u043d\u0435\u043d\u0438\u044e \u0441 \u043f\u0440\u043e\u0438\u0437\u0432\u043e\u0434\u0438\u0442\u0435\u043b\u044c\u043d\u043e\u0441\u0442\u044c\u044e \u043e\u0434\u043d\u043e\u0439 \u043a\u0430\u0440\u0442\u044b \u0432\u043e \u043c\u043d\u043e\u0433\u0438\u0445 \u0438\u0433\u0440\u0430\u0445 \u0438 \u043f\u0440\u0438\u043b\u043e\u0436\u0435\u043d\u0438\u044f\u0445. \u0438\u0437-\u0437\u0430 \u0443\u043c\u0435\u043d\u044c\u0448\u0435\u043d\u0438\u044f \u043e\u0442\u0434\u0430\u0447\u0438 \u0438 \u043f\u043e\u0442\u0435\u043d\u0446\u0438\u0430\u043b\u044c\u043d\u044b\u0445 \u043f\u0440\u043e\u0431\u043b\u0435\u043c \u0441\u043e\u0432\u043c\u0435\u0441\u0442\u0438\u043c\u043e\u0441\u0442\u0438.<\/p>\n<\/div>\n<\/details>\n<ol start=\"2\">\n<li>\n<p>Write a program to recognize human speech and then write the result to a text file. <\/p>\n<\/li>\n<\/ol>\n<details class=\"spoiler\">\n<summary>Hidden text<\/summary>\n<div class=\"spoiler__content\">\n<p>To achieve this task, we&#8217;ll use Python with two libraries &#8212; SpeechRecognition for recognizing speech, and Pyttsx3 for converting text to speech. Here is an example code snippet:  <\/p>\n<pre><code class=\"python\">import speech_recognition as sr from gtts import gTTS import os  def speak(text):     tts = gTTS(text=text, lang='en')     tts.save(\"output.mp3\")     os.system(\"mpg321 output.mp3\")      r = sr.Recognizer() with sr.Microphone() as source:     print(\"Speak Anything :\")     audio = r.listen(source)      try:     text = r.recognize_google(audio) except Exception as e:     text = \"Could not understand audio\" print(\"You said : {}\".format(text)) speak(text)  f = open('speech_result.txt', 'w') f.write(text) f.close()<\/code><\/pre>\n<p>This script will listen to your voice via microphone and try to convert it into written text using Google Cloud Recognition API. The recognized text will be printed on console, spoken back through your speakers, and also saved in <code>speech_result.txt<\/code> file. If some errors occur during recognition process (like too much noise), it will print a message about that and save &#171;Could not understand audio&#187; text instead of the actual input.  <\/p>\n<\/div>\n<\/details>\n<p>\u041f\u043e \u043f\u0435\u0440\u0432\u043e\u043c\u0443 \u0432\u043e\u043f\u0440\u043e\u0441\u0443 \u043e\u0442\u0432\u0435\u0442 \u0431\u044b\u043b \u043f\u0440\u0430\u0432\u0438\u043b\u044c\u043d\u044b\u0439, \u0447\u0442\u043e \u0433\u043e\u0440\u0430\u0437\u0434\u043e \u043b\u0443\u0447\u0448\u0435 \u043c\u043e\u0434\u0435\u043b\u0438 \u043d\u0430 7 \u043c\u043b\u0440\u0434 \u043f\u0430\u0440\u0430\u043c\u0435\u0442\u0440\u043e\u0432. \u041e\u0434\u043d\u0430\u043a\u043e \u0434\u043e\u043f\u043e\u043b\u043d\u0435\u043d\u0438\u0435 &#171;\u0432\u044b \u043c\u043e\u0436\u0435\u0442\u0435 \u0438\u0441\u043f\u043e\u043b\u044c\u0437\u043e\u0432\u0430\u0442\u044c \u0442\u0435\u0445\u043d\u043e\u043b\u043e\u0433\u0438\u044e SLI (Scalable Link Interface) \u0434\u043b\u044f \u0441\u043e\u0435\u0434\u0438\u043d\u0435\u043d\u0438\u044f \u0434\u0432\u0443\u0445 \u0432\u0438\u0434\u0435\u043e\u043a\u0430\u0440\u0442 Nvidia GeForce RTX 3080, \u0435\u0441\u043b\u0438 \u043e\u043d\u0438 \u0441\u043e\u043e\u0442\u0432\u0435\u0442\u0441\u0442\u0432\u0443\u044e\u0442 \u0442\u0440\u0435\u0431\u043e\u0432\u0430\u043d\u0438\u044f\u043c&#187; \u0441\u0442\u0430\u0432\u0438\u0442 \u0432 \u0442\u0443\u043f\u0438\u043a, \u0442\u0430\u043a \u043a\u0430\u043a \u043f\u043e\u044f\u0441\u043d\u0435\u043d\u0438\u0435 \u043d\u0435\u043f\u0440\u0430\u0432\u0438\u043b\u044c\u043d\u043e.<\/p>\n<p>\u0412\u0440\u0435\u043c\u044f \u0433\u0435\u043d\u0435\u0440\u0430\u0446\u0438\u0438 \u043e\u0434\u043d\u043e\u0433\u043e \u0442\u043e\u043a\u0435\u043d\u0430 \u0441\u043e\u0441\u0442\u0430\u0432\u0438\u043b\u043e 1400 \u043c\u0438\u043b\u043b\u0438\u0441\u0435\u043a\u0443\u043d\u0434, \u043e\u043f\u0435\u0440\u0430\u0442\u0438\u0432\u043d\u043e\u0439 \u043f\u0430\u043c\u044f\u0442\u0438 \u0438\u0441\u043f\u043e\u043b\u044c\u0437\u043e\u0432\u0430\u043b\u043e\u0441\u044c 45,4 \u0413\u0431. \u041c\u043e\u0434\u0435\u043b\u044c \u0438\u0441\u043f\u043e\u043b\u044c\u0437\u043e\u0432\u0430\u043b\u0430\u0441\u044c &#171;deepseek-llm-67b-chat.Q5_K_M.gguf&#187;<\/p>\n<h2>SUS Chat &#8212; 34B \u043f\u0430\u0440\u0430\u043c\u0435\u0442\u0440\u043e\u0432<\/h2>\n<blockquote>\n<p><strong>SUS-Chat-34B<\/strong>\u00a0\u2014 \u044d\u0442\u043e \u0434\u0432\u0443\u044f\u0437\u044b\u0447\u043d\u0430\u044f \u043a\u0438\u0442\u0430\u0439\u0441\u043a\u043e-\u0430\u043d\u0433\u043b\u0438\u0439\u0441\u043a\u0430\u044f \u0434\u0438\u0430\u043b\u043e\u0433\u043e\u0432\u0430\u044f \u043c\u043e\u0434\u0435\u043b\u044c 34B, \u0432\u044b\u043f\u0443\u0449\u0435\u043d\u043d\u0430\u044f \u0441\u043e\u0432\u043c\u0435\u0441\u0442\u043d\u043e\u00a0<a href=\"https:\/\/huggingface.co\/SUSTech\" rel=\"noopener noreferrer nofollow\"><u>\u042e\u0436\u043d\u044b\u043c \u0443\u043d\u0438\u0432\u0435\u0440\u0441\u0438\u0442\u0435\u0442\u043e\u043c \u043d\u0430\u0443\u043a\u0438 \u0438 \u0442\u0435\u0445\u043d\u043e\u043b\u043e\u0433\u0438\u0439<\/u><\/a>\u00a0\u0438\u00a0<a href=\"https:\/\/huggingface.co\/IDEA-CCNL\" rel=\"noopener noreferrer nofollow\"><u>IDEA-CCNL<\/u><\/a>.\u00a0\u042d\u0442\u0430 \u043c\u043e\u0434\u0435\u043b\u044c \u043e\u0441\u043d\u043e\u0432\u0430\u043d\u0430\u00a0<code>01-ai\/Yi-34B<\/code>\u043d\u0430 \u043c\u0438\u043b\u043b\u0438\u043e\u043d\u0430\u0445 \u0432\u044b\u0441\u043e\u043a\u043e\u043a\u0430\u0447\u0435\u0441\u0442\u0432\u0435\u043d\u043d\u044b\u0445 \u043c\u043d\u043e\u0433\u043e\u044f\u0437\u044b\u0447\u043d\u044b\u0445 \u0434\u0430\u043d\u043d\u044b\u0445 \u0438\u043d\u0441\u0442\u0440\u0443\u043a\u0446\u0438\u0439 \u0438 \u0431\u044b\u043b\u0430 \u0434\u043e\u0440\u0430\u0431\u043e\u0442\u0430\u043d\u0430.  <\/p>\n<ul>\n<li>\n<p>5 \u0434\u0435\u043a\u0430\u0431\u0440\u044f 2023 \u0433.: SUS-Chat-34B \u0437\u0430\u043d\u044f\u043b 2-\u0435 \u043c\u0435\u0441\u0442\u043e \u0432\u00a0<a href=\"https:\/\/huggingface.co\/spaces\/HuggingFaceH4\/open_llm_leaderboard\" rel=\"noopener noreferrer nofollow\"><u>\u0442\u0430\u0431\u043b\u0438\u0446\u0435 \u043b\u0438\u0434\u0435\u0440\u043e\u0432 Open LLM<\/u><\/a>\u00a0\u0438 \u043f\u0440\u0435\u0432\u0437\u043e\u0448\u0435\u043b \u0432\u0441\u0435 \u043c\u043e\u0434\u0435\u043b\u0438 \u0434\u043e 70B.<\/p>\n<\/li>\n<\/ul>\n<\/blockquote>\n<p>\u041f\u0440\u043e\u0432\u0435\u0440\u0438\u043c \u0434\u0430\u043d\u043d\u043e\u0435 \u0443\u0442\u0432\u0435\u0440\u0436\u0434\u0435\u043d\u0438\u0435.<\/p>\n<ol>\n<li>\n<p>Is it possible to connect two Nvidia 3080 graphics cards using NVLink?<\/p>\n<\/li>\n<\/ol>\n<details class=\"spoiler\">\n<summary>Hidden text<\/summary>\n<div class=\"spoiler__content\">\n<p>Yes, it is possible to connect two Nvidia 3080 graphics cards using NVLink. The NVLink technology allows for high-speed communication between the two GPUs, which can significantly improve performance in certain applications such as gaming and machine learning. However, this configuration requires a motherboard with an appropriate socket and BIOS settings, as well as compatible drivers and software. <\/p>\n<\/div>\n<\/details>\n<p>\u041f\u0435\u0440\u0435\u0432\u043e\u0434:<\/p>\n<details class=\"spoiler\">\n<summary>Hidden text<\/summary>\n<div class=\"spoiler__content\">\n<p>\u0414\u0430, \u043c\u043e\u0436\u043d\u043e \u043f\u043e\u0434\u043a\u043b\u044e\u0447\u0438\u0442\u044c \u0434\u0432\u0435 \u0432\u0438\u0434\u0435\u043e\u043a\u0430\u0440\u0442\u044b Nvidia 3080 \u0441 \u043f\u043e\u043c\u043e\u0449\u044c\u044e NVLink. \u0422\u0435\u0445\u043d\u043e\u043b\u043e\u0433\u0438\u044f NVLink \u043e\u0431\u0435\u0441\u043f\u0435\u0447\u0438\u0432\u0430\u0435\u0442 \u0432\u044b\u0441\u043e\u043a\u043e\u0441\u043a\u043e\u0440\u043e\u0441\u0442\u043d\u0443\u044e \u0441\u0432\u044f\u0437\u044c \u043c\u0435\u0436\u0434\u0443 \u0434\u0432\u0443\u043c\u044f \u0433\u0440\u0430\u0444\u0438\u0447\u0435\u0441\u043a\u0438\u043c\u0438 \u043f\u0440\u043e\u0446\u0435\u0441\u0441\u043e\u0440\u0430\u043c\u0438, \u0447\u0442\u043e \u043c\u043e\u0436\u0435\u0442 \u0437\u043d\u0430\u0447\u0438\u0442\u0435\u043b\u044c\u043d\u043e \u043f\u043e\u0432\u044b\u0441\u0438\u0442\u044c \u043f\u0440\u043e\u0438\u0437\u0432\u043e\u0434\u0438\u0442\u0435\u043b\u044c\u043d\u043e\u0441\u0442\u044c \u0432 \u043d\u0435\u043a\u043e\u0442\u043e\u0440\u044b\u0445 \u043f\u0440\u0438\u043b\u043e\u0436\u0435\u043d\u0438\u044f\u0445, \u0442\u0430\u043a\u0438\u0445 \u043a\u0430\u043a \u0438\u0433\u0440\u044b \u0438 \u043c\u0430\u0448\u0438\u043d\u043d\u043e\u0435 \u043e\u0431\u0443\u0447\u0435\u043d\u0438\u0435. \u041e\u0434\u043d\u0430\u043a\u043e \u0434\u043b\u044f \u044d\u0442\u043e\u0439 \u043a\u043e\u043d\u0444\u0438\u0433\u0443\u0440\u0430\u0446\u0438\u0438 \u0442\u0440\u0435\u0431\u0443\u0435\u0442\u0441\u044f \u043c\u0430\u0442\u0435\u0440\u0438\u043d\u0441\u043a\u0430\u044f \u043f\u043b\u0430\u0442\u0430 \u0441 \u0441\u043e\u043e\u0442\u0432\u0435\u0442\u0441\u0442\u0432\u0443\u044e\u0449\u0438\u043c \u0440\u0430\u0437\u044a\u0435\u043c\u043e\u043c \u0438 \u043d\u0430\u0441\u0442\u0440\u043e\u0439\u043a\u0430\u043c\u0438 BIOS, \u0430 \u0442\u0430\u043a\u0436\u0435 \u0441\u043e\u0432\u043c\u0435\u0441\u0442\u0438\u043c\u044b\u0435 \u0434\u0440\u0430\u0439\u0432\u0435\u0440\u044b \u0438 \u043f\u0440\u043e\u0433\u0440\u0430\u043c\u043c\u043d\u043e\u0435 \u043e\u0431\u0435\u0441\u043f\u0435\u0447\u0435\u043d\u0438\u0435.<\/p>\n<\/div>\n<\/details>\n<ol start=\"2\">\n<li>\n<p>Write a program to recognize human speech and then write the result to a text file. <\/p>\n<\/li>\n<\/ol>\n<details class=\"spoiler\">\n<summary>Hidden text<\/summary>\n<div class=\"spoiler__content\">\n<p>To accomplish this task, we will need to use a speech recognition library such as Google Cloud Speech-to-Text API or Microsoft Azure Cognitive Services. Here&#8217;s a sample Python code that demonstrates how to use Google Cloud Speech-to-Text API to convert audio files into text and save them to a text file:  <\/p>\n<pre><code class=\"python\">import os from google.cloud import speech_v1p1beta1 as speech os.environ[\"GOOGLE_APPLICATION_CREDENTIALS\"] = \"path\/to\/credentials.json\" client = speech.SpeechClient() file_name = input(\"Enter audio file name: \") audio = {\"content\": open(file_name, \"rb\").read()} config = {     \"encoding\": \"LINEAR16\",     \"sample_rate_hertz\": 16000,     \"language_code\": \"en-US\" } response = client.recognize(request={     \"config\": config,     \"audio\": audio }) text = response.results[0].alternatives[0].transcript with open(\"output.txt\", \"w\") as f:     f.write(text) print(\"Recognized text:\", text)<\/code><\/pre>\n<p>This code prompts the user to enter an audio file name, reads the contents of the file using <code>open()<\/code> function, and then passes it to the <code>recognize()<\/code> method of the <code>speech<\/code> client along with the configuration settings such as encoding, sample rate hertz, and language code. The response contains a list of results, each containing one or more alternatives for the recognized transcript. We extract the first alternative from the first result and save it to a text file named &#171;output.txt&#187; using <code>with open(\"output.txt\", \"w\")<\/code> syntax. Finally, we print out the recognized text. Note that you need to have installed Google Cloud SDK and authenticated your account before running this code.  <\/p>\n<\/div>\n<\/details>\n<p>\u041f\u043e \u043f\u0435\u0440\u0432\u043e\u043c\u0443 \u0432\u043e\u043f\u0440\u043e\u0441\u0443 \u043d\u0435\u0439\u0440\u043e\u0441\u0435\u0442\u044c \u043f\u043e\u043b\u043d\u043e\u0441\u0442\u044c\u044e \u043f\u0440\u043e\u0432\u0430\u043b\u0438\u043b\u0430\u0441\u044c. <\/p>\n<p>\u0412\u0440\u0435\u043c\u044f \u0433\u0435\u043d\u0435\u0440\u0430\u0446\u0438\u0438 \u043e\u0434\u043d\u043e\u0433\u043e \u0442\u043e\u043a\u0435\u043d\u0430 \u0441\u043e\u0441\u0442\u0430\u0432\u0438\u043b\u043e 780 \u043c\u0438\u043b\u043b\u0438\u0441\u0435\u043a\u0443\u043d\u0434, \u043e\u043f\u0435\u0440\u0430\u0442\u0438\u0432\u043d\u043e\u0439 \u043f\u0430\u043c\u044f\u0442\u0438 \u0438\u0441\u043f\u043e\u043b\u044c\u0437\u043e\u0432\u0430\u043b\u043e\u0441\u044c 23,2 \u0413\u0431. \u041c\u043e\u0434\u0435\u043b\u044c \u0438\u0441\u043f\u043e\u043b\u044c\u0437\u043e\u0432\u0430\u043b\u0430\u0441\u044c &#171;sus-chat-34b.Q5_K_M.gguf&#187;<\/p>\n<h2>ChatGPT 3.5 \u0438 4.0<\/h2>\n<p>\u0410 \u043a\u0430\u043a \u0436\u0435 \u043e\u0442\u0432\u0435\u0442\u044f\u0442 \u0434\u0432\u0430 \u0432\u0430\u0440\u0438\u0430\u043d\u0442\u0430 ChatGPT \u043d\u0430 \u0445\u0438\u0442\u0440\u044b\u0439 \u0432\u043e\u043f\u0440\u043e\u0441 \u043e \u043f\u043e\u0434\u043a\u043b\u044e\u0447\u0435\u043d\u0438\u0438 \u0434\u0432\u0443\u0445 \u0432\u0438\u0434\u0435\u043e\u043a\u0430\u0440\u0442 Nvidia GeForce RTX 3080 \u0447\u0435\u0440\u0435\u0437 NVLink.<\/p>\n<ol>\n<li>\n<p>Is it possible to connect two Nvidia 3080 graphics cards using NVLink? (\u0412\u043e\u043f\u0440\u043e\u0441 \u0434\u043b\u044f ChatGPT 3.5 \u043d\u0430 \u0430\u043d\u0433\u043b\u0438\u0439\u0441\u043a\u043e\u043c \u044f\u0437\u044b\u043a\u0435)<\/p>\n<\/li>\n<\/ol>\n<details class=\"spoiler\">\n<summary>Hidden text<\/summary>\n<div class=\"spoiler__content\">\n<p>Yes, it is possible to connect two Nvidia 3080 video cards using NVLink. This technology allows for high-speed communication between the two GPUs, which can improve performance in certain applications such as gaming or machine learning. However, not all motherboards support NVLink, so it is important to check compatibility before attempting to connect the cards. <\/p>\n<\/div>\n<\/details>\n<p>\u041f\u0435\u0440\u0435\u0432\u043e\u0434:<\/p>\n<details class=\"spoiler\">\n<summary>Hidden text<\/summary>\n<div class=\"spoiler__content\">\n<p>\u0414\u0430, \u043c\u043e\u0436\u043d\u043e \u043f\u043e\u0434\u043a\u043b\u044e\u0447\u0438\u0442\u044c \u0434\u0432\u0435 \u0432\u0438\u0434\u0435\u043e\u043a\u0430\u0440\u0442\u044b Nvidia 3080 \u0441 \u043f\u043e\u043c\u043e\u0449\u044c\u044e NVLink. \u042d\u0442\u0430 \u0442\u0435\u0445\u043d\u043e\u043b\u043e\u0433\u0438\u044f \u043e\u0431\u0435\u0441\u043f\u0435\u0447\u0438\u0432\u0430\u0435\u0442 \u0432\u044b\u0441\u043e\u043a\u043e\u0441\u043a\u043e\u0440\u043e\u0441\u0442\u043d\u0443\u044e \u0441\u0432\u044f\u0437\u044c \u043c\u0435\u0436\u0434\u0443 \u0434\u0432\u0443\u043c\u044f \u0433\u0440\u0430\u0444\u0438\u0447\u0435\u0441\u043a\u0438\u043c\u0438 \u043f\u0440\u043e\u0446\u0435\u0441\u0441\u043e\u0440\u0430\u043c\u0438, \u0447\u0442\u043e \u043c\u043e\u0436\u0435\u0442 \u043f\u043e\u0432\u044b\u0441\u0438\u0442\u044c \u043f\u0440\u043e\u0438\u0437\u0432\u043e\u0434\u0438\u0442\u0435\u043b\u044c\u043d\u043e\u0441\u0442\u044c \u0432 \u043d\u0435\u043a\u043e\u0442\u043e\u0440\u044b\u0445 \u043f\u0440\u0438\u043b\u043e\u0436\u0435\u043d\u0438\u044f\u0445, \u0442\u0430\u043a\u0438\u0445 \u043a\u0430\u043a \u0438\u0433\u0440\u044b \u0438\u043b\u0438 \u043c\u0430\u0448\u0438\u043d\u043d\u043e\u0435 \u043e\u0431\u0443\u0447\u0435\u043d\u0438\u0435. \u041e\u0434\u043d\u0430\u043a\u043e \u043d\u0435 \u0432\u0441\u0435 \u043c\u0430\u0442\u0435\u0440\u0438\u043d\u0441\u043a\u0438\u0435 \u043f\u043b\u0430\u0442\u044b \u043f\u043e\u0434\u0434\u0435\u0440\u0436\u0438\u0432\u0430\u044e\u0442 NVLink, \u043f\u043e\u044d\u0442\u043e\u043c\u0443 \u0432\u0430\u0436\u043d\u043e \u043f\u0440\u043e\u0432\u0435\u0440\u0438\u0442\u044c \u0441\u043e\u0432\u043c\u0435\u0441\u0442\u0438\u043c\u043e\u0441\u0442\u044c, \u043f\u0440\u0435\u0436\u0434\u0435 \u0447\u0435\u043c \u043f\u044b\u0442\u0430\u0442\u044c\u0441\u044f \u043f\u043e\u0434\u043a\u043b\u044e\u0447\u0438\u0442\u044c \u043a\u0430\u0440\u0442\u044b.<\/p>\n<\/div>\n<\/details>\n<ol start=\"2\">\n<li>\n<p>Is it possible to connect two nvidia 3080 video cards using NVLink? (\u0412\u043e\u043f\u0440\u043e\u0441 \u0431\u044b\u043b \u0437\u0430\u0434\u0430\u043d \u0434\u043b\u044f ChatGPT 4.0)<\/p>\n<\/li>\n<\/ol>\n<details class=\"spoiler\">\n<summary>Hidden text<\/summary>\n<div class=\"spoiler__content\">\n<p>As of my knowledge cutoff in early 2023, NVIDIA&#8217;s GeForce RTX 3080 graphics cards do not officially support NVLink or SLI for gaming purposes. NVLink is a high-bandwidth interconnect technology developed by NVIDIA, which is primarily used on their professional GPUs like the Quadro and Tesla series, and was also available on the consumer RTX 20 series (specifically the RTX 2080 and 2080 Ti).<\/p>\n<p>The RTX 3080 is part of NVIDIA&#8217;s 30 series, and this generation has largely moved away from multi-GPU configurations for gaming due to various factors such as game support, driver support, and the diminishing returns in performance scaling. With the RTX 30 series, NVIDIA did not include NVLink connectors on most of their consumer-grade GPUs, including the RTX 3080.<\/p>\n<p>For those looking to utilize multiple GPUs for purposes other than gaming, such as certain professional applications, rendering tasks, or compute workloads, NVIDIA&#8217;s higher-end RTX 3090 did initially come with an NVLink connector, but this feature is not intended for gaming and is not available on the RTX 3080 models.<\/p>\n<p>If you are looking to improve gaming performance, it is generally recommended to invest in the most powerful single GPU you can afford rather than attempting to connect multiple GPUs, especially since the RTX 3080 does not support NVLink or SLI.  <\/p>\n<\/div>\n<\/details>\n<p>\u041f\u0435\u0440\u0435\u0432\u043e\u0434:<\/p>\n<details class=\"spoiler\">\n<summary>Hidden text<\/summary>\n<div class=\"spoiler__content\">\n<p>\u041f\u043e \u043c\u043e\u0438\u043c \u0441\u0432\u0435\u0434\u0435\u043d\u0438\u044f\u043c \u0432 \u043d\u0430\u0447\u0430\u043b\u0435 2023 \u0433\u043e\u0434\u0430 \u0432\u0438\u0434\u0435\u043e\u043a\u0430\u0440\u0442\u044b NVIDIA GeForce RTX 3080 \u043e\u0444\u0438\u0446\u0438\u0430\u043b\u044c\u043d\u043e \u043d\u0435 \u043f\u043e\u0434\u0434\u0435\u0440\u0436\u0438\u0432\u0430\u044e\u0442 NVLink \u0438\u043b\u0438 SLI \u0434\u043b\u044f \u0438\u0433\u0440\u043e\u0432\u044b\u0445 \u0446\u0435\u043b\u0435\u0439. NVLink \u2014 \u044d\u0442\u043e \u0442\u0435\u0445\u043d\u043e\u043b\u043e\u0433\u0438\u044f \u043c\u0435\u0436\u0441\u043e\u0435\u0434\u0438\u043d\u0435\u043d\u0438\u0439 \u0441 \u0432\u044b\u0441\u043e\u043a\u043e\u0439 \u043f\u0440\u043e\u043f\u0443\u0441\u043a\u043d\u043e\u0439 \u0441\u043f\u043e\u0441\u043e\u0431\u043d\u043e\u0441\u0442\u044c\u044e, \u0440\u0430\u0437\u0440\u0430\u0431\u043e\u0442\u0430\u043d\u043d\u0430\u044f NVIDIA, \u043a\u043e\u0442\u043e\u0440\u0430\u044f \u0432 \u043e\u0441\u043d\u043e\u0432\u043d\u043e\u043c \u0438\u0441\u043f\u043e\u043b\u044c\u0437\u0443\u0435\u0442\u0441\u044f \u0432 \u0438\u0445 \u043f\u0440\u043e\u0444\u0435\u0441\u0441\u0438\u043e\u043d\u0430\u043b\u044c\u043d\u044b\u0445 \u0433\u0440\u0430\u0444\u0438\u0447\u0435\u0441\u043a\u0438\u0445 \u043f\u0440\u043e\u0446\u0435\u0441\u0441\u043e\u0440\u0430\u0445, \u0442\u0430\u043a\u0438\u0445 \u043a\u0430\u043a \u0441\u0435\u0440\u0438\u0438 Quadro \u0438 Tesla, \u0430 \u0442\u0430\u043a\u0436\u0435 \u0434\u043e\u0441\u0442\u0443\u043f\u043d\u0430 \u0432 \u043f\u043e\u0442\u0440\u0435\u0431\u0438\u0442\u0435\u043b\u044c\u0441\u043a\u0438\u0445 \u0441\u0435\u0440\u0438\u044f\u0445 RTX 20 (\u0432 \u0447\u0430\u0441\u0442\u043d\u043e\u0441\u0442\u0438, RTX 2080 \u0438 2080 Ti). <\/p>\n<p>RTX 3080 \u044f\u0432\u043b\u044f\u0435\u0442\u0441\u044f \u0447\u0430\u0441\u0442\u044c\u044e 30-\u0439 \u0441\u0435\u0440\u0438\u0438 NVIDIA, \u0438 \u044d\u0442\u043e \u043f\u043e\u043a\u043e\u043b\u0435\u043d\u0438\u0435 \u0432 \u0437\u043d\u0430\u0447\u0438\u0442\u0435\u043b\u044c\u043d\u043e\u0439 \u0441\u0442\u0435\u043f\u0435\u043d\u0438 \u043e\u0442\u043e\u0448\u043b\u043e \u043e\u0442 \u043a\u043e\u043d\u0444\u0438\u0433\u0443\u0440\u0430\u0446\u0438\u0439 \u0441 \u043d\u0435\u0441\u043a\u043e\u043b\u044c\u043a\u0438\u043c\u0438 \u0433\u0440\u0430\u0444\u0438\u0447\u0435\u0441\u043a\u0438\u043c\u0438 \u043f\u0440\u043e\u0446\u0435\u0441\u0441\u043e\u0440\u0430\u043c\u0438 \u0434\u043b\u044f \u0438\u0433\u0440 \u0438\u0437-\u0437\u0430 \u0440\u0430\u0437\u043b\u0438\u0447\u043d\u044b\u0445 \u0444\u0430\u043a\u0442\u043e\u0440\u043e\u0432, \u0442\u0430\u043a\u0438\u0445 \u043a\u0430\u043a \u043f\u043e\u0434\u0434\u0435\u0440\u0436\u043a\u0430 \u0438\u0433\u0440, \u043f\u043e\u0434\u0434\u0435\u0440\u0436\u043a\u0430 \u0434\u0440\u0430\u0439\u0432\u0435\u0440\u043e\u0432 \u0438 \u0443\u043c\u0435\u043d\u044c\u0448\u0430\u044e\u0449\u0430\u044f\u0441\u044f \u043e\u0442\u0434\u0430\u0447\u0430 \u043e\u0442 \u043c\u0430\u0441\u0448\u0442\u0430\u0431\u0438\u0440\u043e\u0432\u0430\u043d\u0438\u044f \u043f\u0440\u043e\u0438\u0437\u0432\u043e\u0434\u0438\u0442\u0435\u043b\u044c\u043d\u043e\u0441\u0442\u0438. \u0412 \u0441\u0435\u0440\u0438\u0438 RTX 30 \u043a\u043e\u043c\u043f\u0430\u043d\u0438\u044f NVIDIA \u043d\u0435 \u0432\u043a\u043b\u044e\u0447\u0438\u043b\u0430 \u0440\u0430\u0437\u044a\u0435\u043c\u044b NVLink \u0432 \u0431\u043e\u043b\u044c\u0448\u0438\u043d\u0441\u0442\u0432\u043e \u0441\u0432\u043e\u0438\u0445 \u0433\u0440\u0430\u0444\u0438\u0447\u0435\u0441\u043a\u0438\u0445 \u043f\u0440\u043e\u0446\u0435\u0441\u0441\u043e\u0440\u043e\u0432 \u043f\u043e\u0442\u0440\u0435\u0431\u0438\u0442\u0435\u043b\u044c\u0441\u043a\u043e\u0433\u043e \u0443\u0440\u043e\u0432\u043d\u044f, \u0432\u043a\u043b\u044e\u0447\u0430\u044f RTX 3080. <\/p>\n<p>\u0414\u043b\u044f \u0442\u0435\u0445, \u043a\u0442\u043e \u0445\u043e\u0447\u0435\u0442 \u0438\u0441\u043f\u043e\u043b\u044c\u0437\u043e\u0432\u0430\u0442\u044c \u043d\u0435\u0441\u043a\u043e\u043b\u044c\u043a\u043e \u0433\u0440\u0430\u0444\u0438\u0447\u0435\u0441\u043a\u0438\u0445 \u043f\u0440\u043e\u0446\u0435\u0441\u0441\u043e\u0440\u043e\u0432 \u0434\u043b\u044f \u0446\u0435\u043b\u0435\u0439, \u043e\u0442\u043b\u0438\u0447\u043d\u044b\u0445 \u043e\u0442 \u0438\u0433\u0440, \u043d\u0430\u043f\u0440\u0438\u043c\u0435\u0440, \u0434\u043b\u044f \u043e\u043f\u0440\u0435\u0434\u0435\u043b\u0435\u043d\u043d\u044b\u0445 \u043f\u0440\u043e\u0444\u0435\u0441\u0441\u0438\u043e\u043d\u0430\u043b\u044c\u043d\u044b\u0445 \u043f\u0440\u0438\u043b\u043e\u0436\u0435\u043d\u0438\u0439, \u0437\u0430\u0434\u0430\u0447 \u0440\u0435\u043d\u0434\u0435\u0440\u0438\u043d\u0433\u0430 \u0438\u043b\u0438 \u0432\u044b\u0447\u0438\u0441\u043b\u0438\u0442\u0435\u043b\u044c\u043d\u044b\u0445 \u0437\u0430\u0434\u0430\u0447, \u0431\u043e\u043b\u0435\u0435 \u0434\u043e\u0440\u043e\u0433\u0430\u044f \u0432\u0438\u0434\u0435\u043e\u043a\u0430\u0440\u0442\u0430 NVIDIA RTX 3090 \u0438\u0437\u043d\u0430\u0447\u0430\u043b\u044c\u043d\u043e \u043e\u0441\u043d\u0430\u0449\u0435\u043d\u0430 \u0440\u0430\u0437\u044a\u0435\u043c\u043e\u043c NVLink, \u043d\u043e \u044d\u0442\u0430 \u0444\u0443\u043d\u043a\u0446\u0438\u044f \u043d\u0435 \u043f\u0440\u0435\u0434\u043d\u0430\u0437\u043d\u0430\u0447\u0435\u043d\u0430 \u0434\u043b\u044f \u0438\u0433\u0440 \u0438 \u043d\u0435 \u043f\u0440\u0435\u0434\u043d\u0430\u0437\u043d\u0430\u0447\u0435\u043d\u0430 \u0434\u043b\u044f \u0438\u0433\u0440. \u043d\u0435\u0434\u043e\u0441\u0442\u0443\u043f\u043d\u043e \u043d\u0430 \u043c\u043e\u0434\u0435\u043b\u044f\u0445 RTX 3080. <\/p>\n<p>\u0415\u0441\u043b\u0438 \u0432\u044b \u0445\u043e\u0442\u0438\u0442\u0435 \u043f\u043e\u0432\u044b\u0441\u0438\u0442\u044c \u043f\u0440\u043e\u0438\u0437\u0432\u043e\u0434\u0438\u0442\u0435\u043b\u044c\u043d\u043e\u0441\u0442\u044c \u0432 \u0438\u0433\u0440\u0430\u0445, \u043e\u0431\u044b\u0447\u043d\u043e \u0440\u0435\u043a\u043e\u043c\u0435\u043d\u0434\u0443\u0435\u0442\u0441\u044f \u0438\u043d\u0432\u0435\u0441\u0442\u0438\u0440\u043e\u0432\u0430\u0442\u044c \u0432 \u0441\u0430\u043c\u044b\u0439 \u043c\u043e\u0449\u043d\u044b\u0439 \u043e\u0434\u0438\u043d\u043e\u0447\u043d\u044b\u0439 \u0433\u0440\u0430\u0444\u0438\u0447\u0435\u0441\u043a\u0438\u0439 \u043f\u0440\u043e\u0446\u0435\u0441\u0441\u043e\u0440, \u043a\u043e\u0442\u043e\u0440\u044b\u0439 \u0432\u044b \u043c\u043e\u0436\u0435\u0442\u0435 \u0441\u0435\u0431\u0435 \u043f\u043e\u0437\u0432\u043e\u043b\u0438\u0442\u044c, \u0430 \u043d\u0435 \u043f\u044b\u0442\u0430\u0442\u044c\u0441\u044f \u043f\u043e\u0434\u043a\u043b\u044e\u0447\u0438\u0442\u044c \u043d\u0435\u0441\u043a\u043e\u043b\u044c\u043a\u043e \u0433\u0440\u0430\u0444\u0438\u0447\u0435\u0441\u043a\u0438\u0445 \u043f\u0440\u043e\u0446\u0435\u0441\u0441\u043e\u0440\u043e\u0432, \u0442\u0435\u043c \u0431\u043e\u043b\u0435\u0435 \u0447\u0442\u043e RTX 3080 \u043d\u0435 \u043f\u043e\u0434\u0434\u0435\u0440\u0436\u0438\u0432\u0430\u0435\u0442 NVLink \u0438\u043b\u0438 SLI.<\/p>\n<\/div>\n<\/details>\n<p>\u041a\u0430\u043a \u043c\u043e\u0436\u043d\u043e \u0443\u0432\u0438\u0434\u0435\u0442\u044c, ChatGPT 3.5 \u043f\u0440\u043e\u0432\u0430\u043b\u0438\u043b\u0430\u0441\u044c \u0432 \u043e\u0442\u0432\u0435\u0442\u0435 \u043d\u0430 \u0432\u043e\u043f\u0440\u043e\u0441. \u041e\u0434\u043d\u0430\u043a\u043e ChatGPT 4.0 \u043f\u043e\u043a\u0430\u0437\u0430\u043b\u0430 \u043b\u0443\u0447\u0448\u0438\u0439 \u0440\u0435\u0437\u0443\u043b\u044c\u0442\u0430\u0442 \u0438 \u0441\u043c\u043e\u0433\u043b\u0430 \u043e\u0431\u043e\u0441\u043d\u043e\u0432\u0430\u0442\u044c \u0441\u0432\u043e\u0439 \u043e\u0442\u0432\u0435\u0442.<\/p>\n<h2>\u0412\u044b\u0432\u043e\u0434\u044b<\/h2>\n<p>ChatGPT 4.0 \u043b\u0443\u0447\u0448\u0435 \u0432\u0441\u0435\u0445 \u0441\u043f\u0440\u0430\u0432\u0438\u043b\u0430\u0441\u044c \u0441 \u0437\u0430\u0434\u0430\u0447\u0435\u0439, \u0447\u0442\u043e \u0433\u043e\u0432\u043e\u0440\u0438\u0442 \u043e \u0442\u043e\u043c, \u0447\u0442\u043e \u043d\u0435\u0439\u0440\u043e\u043d\u043d\u044b\u0435 LLM \u0441\u0435\u0442\u0438 \u0441 \u0441\u0430\u043c\u044b\u043c \u0431\u043e\u043b\u044c\u0448\u0438\u043c \u043a\u043e\u043b\u0438\u0447\u0435\u0441\u0442\u0432\u043e\u043c \u043f\u0430\u0440\u0430\u043c\u0435\u0442\u0440\u043e\u0432 \u0445\u043e\u0440\u043e\u0448\u043e \u0443\u043c\u0435\u044e\u0442 \u0440\u0430\u0441\u0441\u0443\u0436\u0434\u0430\u0442\u044c. \u041e\u0434\u043d\u0430\u043a\u043e, \u043f\u0440\u0438 \u0434\u043e\u043b\u0436\u043d\u043e\u043c \u043a\u043e\u043b\u0438\u0447\u0435\u0441\u0442\u0432\u0435 \u0445\u043e\u0440\u043e\u0448\u0435\u0439 \u0432\u044b\u0431\u043e\u0440\u043a\u0438 \u043e\u0431\u0443\u0447\u0430\u0435\u043c\u043e\u0433\u043e \u043c\u0430\u0442\u0435\u0440\u0438\u0430\u043b\u0430, \u043c\u043e\u0436\u043d\u043e \u0434\u043e\u0441\u0442\u0438\u0447\u044c \u0438\u043d\u0442\u0435\u0440\u0435\u0441\u043d\u044b\u0445 \u0440\u0435\u0437\u0443\u043b\u044c\u0442\u0430\u0442\u043e\u0432 \u0432 \u0443\u0437\u043a\u043e\u0441\u043f\u0435\u0446\u0438\u0430\u043b\u0438\u0437\u0438\u0440\u043e\u0432\u0430\u043d\u043d\u044b\u0445 \u0437\u0430\u0434\u0430\u0447\u0430\u0445, \u0438\u0441\u043f\u043e\u043b\u044c\u0437\u0443\u044f \u043c\u043e\u0434\u0435\u043b\u0438 \u0441 <strong>70B<\/strong> \u043f\u0430\u0440\u0430\u043c\u0435\u0442\u0440\u0430\u043c\u0438, \u043a\u043e\u0442\u043e\u0440\u044b\u0435 \u043c\u043e\u0436\u043d\u043e \u0437\u0430\u043f\u0443\u0441\u0442\u0438\u0442\u044c \u043d\u0430 \u043b\u043e\u043a\u0430\u043b\u044c\u043d\u043e\u043c \u043a\u043e\u043c\u043f\u044c\u044e\u0442\u0435\u0440\u0435, \u0438\u0441\u043f\u043e\u043b\u044c\u0437\u0443\u044f 64 \u0413\u0431 \u043e\u043f\u0435\u0440\u0430\u0442\u0438\u0432\u043d\u043e\u0439 \u043f\u0430\u043c\u044f\u0442\u0438 \u0438 \u0432\u044b\u0448\u0435.<\/p>\n<blockquote>\n<p><strong>\u0414\u043e\u043f\u043e\u043b\u043d\u0435\u043d\u0438\u0435 \u21161 (\u043e\u0442 14.12.2023 \u0433.):<\/strong><\/p>\n<p>\u0412\u044b\u0448\u043b\u0430 \u043d\u043e\u0432\u0430\u044f LLM \u043d\u0435\u0439\u0440\u043e\u0441\u0435\u0442\u044c Mixtral-8x7B v0.1\u0441, \u043a\u043e\u0442\u043e\u0440\u0443\u044e \u0441\u043e\u0432\u0435\u0442\u043e\u0432\u0430\u043b\u0438 \u0432 \u043a\u043e\u043c\u043c\u0435\u043d\u0442\u0430\u0440\u0438\u044f\u0445. \u042f \u0435\u0451 \u0441\u043a\u0430\u0447\u0430\u043b \u0438 \u043f\u0440\u043e\u0442\u0435\u0441\u0442\u0438\u0440\u043e\u0432\u0430\u043b \u043d\u0430 \u0441\u0432\u043e\u0435\u043c \u0434\u043e\u043c\u0430\u0448\u043d\u0435\u043c \u043a\u043e\u043c\u043f\u044c\u044e\u0442\u0435\u0440\u0435. \u0418\u0441\u043f\u043e\u043b\u044c\u0437\u043e\u0432\u0430\u043b \u0432\u0435\u0440\u0441\u0438\u044e &#171;mixtral-8x7b-v0.1.Q6_K.gguf&#187;. \u041d\u0430 SSD \u0434\u0438\u0441\u043a\u0435 \u0437\u0430\u043d\u044f\u043b\u043e 35,7 \u0413\u0431 \u043c\u0435\u0441\u0442\u0430 \u0438 36,6 \u0413\u0431 \u0432 \u043e\u043f\u0435\u0440\u0430\u0442\u0438\u0432\u043d\u043e\u0439 \u043f\u0430\u043c\u044f\u0442\u0438 \u043f\u0440\u0438 \u0440\u0430\u0431\u043e\u0442\u0435 \u043d\u0435\u0439\u0440\u043e\u043d\u043d\u043e\u0439 \u0441\u0435\u0442\u0438.<\/p>\n<p>\u0412\u0440\u0435\u043c\u044f \u0433\u0435\u043d\u0435\u0440\u0430\u0446\u0438\u0438 \u043e\u0434\u043d\u043e\u0433\u043e \u0442\u043e\u043a\u0435\u043d\u0430 \u0441\u043e\u0441\u0442\u0430\u0432\u0438\u043b\u043e 346 \u043c\u0438\u043b\u043b\u0438\u0441\u0435\u043a\u0443\u043d\u0434, \u0447\u0442\u043e \u0432 2 \u0440\u0430\u0437\u0430 \u0431\u044b\u0441\u0442\u0440\u0435\u0435 SUS Chat 34B \u0438 \u0432 4 \u0440\u0430\u0437\u0430 \u0431\u044b\u0441\u0442\u0440\u0435\u0435 Deepseek LLM Chat 67B. \u041e\u0431 \u0430\u0440\u0445\u0438\u0442\u0435\u043a\u0442\u0443\u0440\u0435 \u043d\u0435\u0439\u0440\u043e\u043d\u043d\u043e\u0439 \u0441\u0435\u0442\u0438 \u043c\u043e\u0436\u043d\u043e \u043f\u043e\u0447\u0438\u0442\u0430\u0442\u044c <a href=\"https:\/\/habr.com\/ru\/articles\/780204\/\" rel=\"noopener noreferrer nofollow\">\u0432 \u044d\u0442\u043e\u0439 \u0441\u0442\u0430\u0442\u044c\u0435 \u043d\u0430 \u0440\u0443\u0441\u0441\u043a\u043e\u043c \u044f\u0437\u044b\u043a\u0435<\/a>.<\/p>\n<\/blockquote>\n<p>\u0417\u0430\u0434\u0430\u043b \u0435\u0439 \u044d\u0442\u0438 \u0432\u043e\u043f\u0440\u043e\u0441\u044b:<\/p>\n<ol>\n<li>\n<p>Is it possible to connect two Nvidia 3080 graphics cards using NVLink?  (\u041c\u043e\u0436\u043d\u043e \u043b\u0438 \u043f\u043e\u0434\u043a\u043b\u044e\u0447\u0438\u0442\u044c \u0434\u0432\u0435 \u0432\u0438\u0434\u0435\u043e\u043a\u0430\u0440\u0442\u044b Nvidia 3080 \u0441 \u043f\u043e\u043c\u043e\u0449\u044c\u044e NVLink?) &#8212; \u043e\u0442\u0432\u0435\u0442 \u0441 \u043f\u0435\u0440\u0435\u0432\u043e\u0434\u043e\u043c<\/p>\n<\/li>\n<\/ol>\n<details class=\"spoiler\">\n<summary>Hidden text<\/summary>\n<div class=\"spoiler__content\">\n<p>No, it is not possible to connect two Nvidia GeForce RTX 3080 graphics cards using NVLink. The NVLink technology is only supported on the Quadro, Tesla and Titan series of Nvidia&#8217;s GPUs. It is used for high-bandwidth, low-latency communication between GPUs or between a GPU and a CPU. The GeForce RTX 3080 uses PCIe as its interconnect technology.  <\/p>\n<p>\u041d\u0435\u0442, \u043d\u0435\u0432\u043e\u0437\u043c\u043e\u0436\u043d\u043e \u0441\u043e\u0435\u0434\u0438\u043d\u0438\u0442\u044c \u0434\u0432\u0435 \u0432\u0438\u0434\u0435\u043e\u043a\u0430\u0440\u0442\u044b Nvidia GeForce RTX 3080 \u0441 \u043f\u043e\u043c\u043e\u0449\u044c\u044e NVLink. \u0422\u0435\u0445\u043d\u043e\u043b\u043e\u0433\u0438\u044f NVLink \u043f\u043e\u0434\u0434\u0435\u0440\u0436\u0438\u0432\u0430\u0435\u0442\u0441\u044f \u0442\u043e\u043b\u044c\u043a\u043e \u0433\u0440\u0430\u0444\u0438\u0447\u0435\u0441\u043a\u0438\u043c\u0438 \u043f\u0440\u043e\u0446\u0435\u0441\u0441\u043e\u0440\u0430\u043c\u0438 Nvidia \u0441\u0435\u0440\u0438\u0439 Quadro, Tesla \u0438 Titan. \u041e\u043d \u0438\u0441\u043f\u043e\u043b\u044c\u0437\u0443\u0435\u0442\u0441\u044f \u0434\u043b\u044f \u0432\u044b\u0441\u043e\u043a\u043e\u0441\u043a\u043e\u0440\u043e\u0441\u0442\u043d\u043e\u0439 \u0441\u0432\u044f\u0437\u0438 \u0441 \u043c\u0430\u043b\u043e\u0439 \u0437\u0430\u0434\u0435\u0440\u0436\u043a\u043e\u0439 \u043c\u0435\u0436\u0434\u0443 \u0433\u0440\u0430\u0444\u0438\u0447\u0435\u0441\u043a\u0438\u043c\u0438 \u043f\u0440\u043e\u0446\u0435\u0441\u0441\u043e\u0440\u0430\u043c\u0438 \u0438\u043b\u0438 \u043c\u0435\u0436\u0434\u0443 \u0433\u0440\u0430\u0444\u0438\u0447\u0435\u0441\u043a\u0438\u043c \u043f\u0440\u043e\u0446\u0435\u0441\u0441\u043e\u0440\u043e\u043c \u0438 \u043f\u0440\u043e\u0446\u0435\u0441\u0441\u043e\u0440\u043e\u043c. GeForce RTX 3080 \u0438\u0441\u043f\u043e\u043b\u044c\u0437\u0443\u0435\u0442 PCIe \u0432 \u043a\u0430\u0447\u0435\u0441\u0442\u0432\u0435 \u0442\u0435\u0445\u043d\u043e\u043b\u043e\u0433\u0438\u0438 \u043c\u0435\u0436\u0441\u043e\u0435\u0434\u0438\u043d\u0435\u043d\u0438\u044f.<\/p>\n<\/div>\n<\/details>\n<ol start=\"2\">\n<li>\n<p>What day of the week is February 48, 2010? (\u041a\u0430\u043a\u043e\u0439 \u0434\u0435\u043d\u044c \u043d\u0435\u0434\u0435\u043b\u0438 48 \u0444\u0435\u0432\u0440\u0430\u043b\u044f 2010 \u0433\u043e\u0434\u0430?) &#8212; \u0432\u043e\u043f\u0440\u043e\u0441, \u0432\u0437\u044f\u0442\u044b\u0439 \u0438\u0437 \u043a\u043e\u043c\u043c\u0435\u043d\u0442\u0430\u0440\u0438\u044f \u0443 \u044d\u0442\u043e\u0439 \u0441\u0442\u0430\u0442\u044c\u0438. \u041e\u0442\u0432\u0435\u0442 \u0441 \u043f\u0435\u0440\u0435\u0432\u043e\u0434\u043e\u043c.<\/p>\n<\/li>\n<\/ol>\n<details class=\"spoiler\">\n<summary>Hidden text<\/summary>\n<div class=\"spoiler__content\">\n<p>There is no February 48, 2010. The month of February has only 28 days in a common year and 29 days in a leap year. Additionally, the year 2010 was not a leap year, so February had only 28 days. Therefore, it is impossible to determine what day of the week February 48, 2010 would be because this date does not exist.  <\/p>\n<p>48 \u0444\u0435\u0432\u0440\u0430\u043b\u044f 2010 \u0433\u043e\u0434\u0430 \u043d\u0435 \u0441\u0443\u0449\u0435\u0441\u0442\u0432\u0443\u0435\u0442. \u0412 \u0444\u0435\u0432\u0440\u0430\u043b\u0435 \u0432\u0441\u0435\u0433\u043e 28 \u0434\u043d\u0435\u0439 \u0432 \u043d\u0435\u0432\u0438\u0441\u043e\u043a\u043e\u0441\u043d\u043e\u043c \u0433\u043e\u0434\u0443 \u0438 29 \u0434\u043d\u0435\u0439 \u0432 \u0432\u0438\u0441\u043e\u043a\u043e\u0441\u043d\u043e\u043c. \u041a\u0440\u043e\u043c\u0435 \u0442\u043e\u0433\u043e, 2010 \u0433\u043e\u0434 \u043d\u0435 \u0431\u044b\u043b \u0432\u0438\u0441\u043e\u043a\u043e\u0441\u043d\u044b\u043c, \u043f\u043e\u044d\u0442\u043e\u043c\u0443 \u0432 \u0444\u0435\u0432\u0440\u0430\u043b\u0435 \u0431\u044b\u043b\u043e \u0432\u0441\u0435\u0433\u043e 28 \u0434\u043d\u0435\u0439. \u041f\u043e\u044d\u0442\u043e\u043c\u0443 \u043d\u0435\u0432\u043e\u0437\u043c\u043e\u0436\u043d\u043e \u043e\u043f\u0440\u0435\u0434\u0435\u043b\u0438\u0442\u044c, \u043a\u0430\u043a\u0438\u043c \u0434\u043d\u0435\u043c \u200b\u200b\u043d\u0435\u0434\u0435\u043b\u0438 \u0431\u0443\u0434\u0435\u0442 48 \u0444\u0435\u0432\u0440\u0430\u043b\u044f 2010 \u0433\u043e\u0434\u0430, \u043f\u043e\u0441\u043a\u043e\u043b\u044c\u043a\u0443 \u044d\u0442\u043e\u0439 \u0434\u0430\u0442\u044b \u043d\u0435 \u0441\u0443\u0449\u0435\u0441\u0442\u0432\u0443\u0435\u0442.<\/p>\n<\/div>\n<\/details>\n<ol start=\"3\">\n<li>\n<p>Who was Vladimir Iliych Lenin&#8217;s father? (\u041a\u0442\u043e \u0431\u044b\u043b \u043e\u0442\u0446\u043e\u043c \u0412\u043b\u0430\u0434\u0438\u043c\u0438\u0440\u0430 \u0418\u043b\u044c\u0438\u0447\u0430 \u041b\u0435\u043d\u0438\u043d\u0430?) &#8212; \u043e\u0442\u0432\u0435\u0442 \u0441 \u043f\u0435\u0440\u0435\u0432\u043e\u0434\u043e\u043c<\/p>\n<\/li>\n<\/ol>\n<details class=\"spoiler\">\n<summary>Hidden text<\/summary>\n<div class=\"spoiler__content\">\n<p>Vladimir Ilyich Lenin&#8217;s father was Ilya Nikolayevich Ulyanov. He was a Russian school teacher and inspector of schools. Ilya Ulyanov was born on August 20, 1831, and died on January 28, 1886, when Lenin was just 16 years old. Lenin&#8217;s mother was Maria Alexandrovna Ulyanova, who was also a school teacher.  <\/p>\n<p>\u041e\u0442\u0446\u043e\u043c \u0412\u043b\u0430\u0434\u0438\u043c\u0438\u0440\u0430 \u0418\u043b\u044c\u0438\u0447\u0430 \u041b\u0435\u043d\u0438\u043d\u0430 \u0431\u044b\u043b \u0418\u043b\u044c\u044f \u041d\u0438\u043a\u043e\u043b\u0430\u0435\u0432\u0438\u0447 \u0423\u043b\u044c\u044f\u043d\u043e\u0432. \u041e\u043d \u0431\u044b\u043b \u0443\u0447\u0438\u0442\u0435\u043b\u0435\u043c \u0440\u0443\u0441\u0441\u043a\u043e\u0439 \u0448\u043a\u043e\u043b\u044b \u0438 \u0438\u043d\u0441\u043f\u0435\u043a\u0442\u043e\u0440\u043e\u043c \u0448\u043a\u043e\u043b. \u0418\u043b\u044c\u044f \u0423\u043b\u044c\u044f\u043d\u043e\u0432 \u0440\u043e\u0434\u0438\u043b\u0441\u044f 20 \u0430\u0432\u0433\u0443\u0441\u0442\u0430 1831 \u0433\u043e\u0434\u0430 \u0438 \u0443\u043c\u0435\u0440 28 \u044f\u043d\u0432\u0430\u0440\u044f 1886 \u0433\u043e\u0434\u0430, \u043a\u043e\u0433\u0434\u0430 \u041b\u0435\u043d\u0438\u043d\u0443 \u0431\u044b\u043b\u043e \u0432\u0441\u0435\u0433\u043e 16 \u043b\u0435\u0442. \u041c\u0430\u0442\u0435\u0440\u044c\u044e \u041b\u0435\u043d\u0438\u043d\u0430 \u0431\u044b\u043b\u0430 \u041c\u0430\u0440\u0438\u044f \u0410\u043b\u0435\u043a\u0441\u0430\u043d\u0434\u0440\u043e\u0432\u043d\u0430 \u0423\u043b\u044c\u044f\u043d\u043e\u0432\u0430, \u043a\u043e\u0442\u043e\u0440\u0430\u044f \u0442\u0430\u043a\u0436\u0435 \u0431\u044b\u043b\u0430 \u0448\u043a\u043e\u043b\u044c\u043d\u043e\u0439 \u0443\u0447\u0438\u0442\u0435\u043b\u044c\u043d\u0438\u0446\u0435\u0439.<\/p>\n<\/div>\n<\/details>\n<ol start=\"3\">\n<li>\n<p>Write a program to recognize human speech and then write the result to a text file. (\u041d\u0430\u043f\u0438\u0448\u0438 \u043f\u0440\u043e\u0433\u0440\u0430\u043c\u043c\u0443, \u0440\u0430\u0441\u043f\u043e\u0437\u043d\u0430\u044e\u0449\u0443\u044e \u0447\u0435\u043b\u043e\u0432\u0435\u0447\u0435\u0441\u043a\u0443\u044e \u0440\u0435\u0447\u044c, \u0430 \u0437\u0430\u0442\u0435\u043c \u0437\u0430\u043f\u0438\u0448\u0438 \u0440\u0435\u0437\u0443\u043b\u044c\u0442\u0430\u0442 \u0432 \u0442\u0435\u043a\u0441\u0442\u043e\u0432\u044b\u0439 \u0444\u0430\u0439\u043b)<\/p>\n<\/li>\n<\/ol>\n<details class=\"spoiler\">\n<summary>Hidden text<\/summary>\n<div class=\"spoiler__content\">\n<p>Creating a program to recognize human speech and write the results to a text file involves several steps and requires knowledge of various fields such as signal processing, machine learning, and natural language processing. Here&#8217;s a simplified outline of how you could approach this problem using Python and existing libraries:<\/p>\n<ol>\n<li>\n<p> Install the SpeechRecognition library in Python:<\/p>\n<\/li>\n<\/ol>\n<pre><code>pip install SpeechRecognition<\/code><\/pre>\n<ol start=\"2\">\n<li>\n<p>Write a function to convert spoken language to text using the SpeechRecognition library:  <\/p>\n<\/li>\n<\/ol>\n<pre><code class=\"python\">import speech_recognition as sr  def listen():     r = sr.Recognizer()     with sr.Microphone() as source:         print(\"Listening...\")         audio = r.listen(source)         try:             print(\"Recognizing...\")             query = r.recognize_google(audio, language='en-in')             print(f\"User said: {query}\\n\")         except Exception as e:             print(\"Say that again please...\")             return \"None\"         return query<\/code><\/pre>\n<ol start=\"3\">\n<li>\n<p>Write a function to write the recognized text to a text file:  <\/p>\n<\/li>\n<\/ol>\n<pre><code class=\"python\">def write_to_file(text):     with open('output.txt', 'a') as f:         f.write(text + '\\n')<\/code><\/pre>\n<p>4. Call the <code>listen()<\/code> function and pass the recognized text to the <code>write_to_file()<\/code> function:<\/p>\n<pre><code class=\"python\">if __name__ == \"__main__\":     while True:         query = listen()         if query != \"None\":             write_to_file(query)<\/code><\/pre>\n<p>Note that this is a simplified example and might not work perfectly in all scenarios. You may need to add error handling and other features depending on your specific use case. Additionally, you may want to explore more advanced speech recognition libraries or cloud services for more accurate results.  <\/p>\n<\/div>\n<\/details>\n<p>\u041c\u0435\u043d\u044f \u043f\u043e\u0440\u0430\u0437\u0438\u043b\u0430 \u0441\u043a\u043e\u0440\u043e\u0441\u0442\u044c \u0440\u0430\u0431\u043e\u0442\u044b \u044d\u0442\u043e\u0439 \u043d\u0435\u0439\u0440\u043e\u043d\u043d\u043e\u0439 \u0441\u0435\u0442\u0438 \u0438 \u043a\u0430\u0447\u0435\u0441\u0442\u0432\u043e \u043e\u0442\u0432\u0435\u0442\u043e\u0432. \u041f\u0440\u0438 \u044d\u0442\u043e\u043c \u043e\u043d\u0430 \u043d\u0435 \u0437\u0430\u043f\u0443\u0441\u0442\u0438\u043b\u0430\u0441\u044c \u043d\u0430 koboldcpp \u0432\u0435\u0440\u0441\u0438\u0438 1.51. \u041a\u043e\u0433\u0434\u0430 \u0441\u043a\u0430\u0447\u0430\u043b \u043d\u043e\u0432\u0443\u044e \u0432\u0435\u0440\u0441\u0438\u044e 1.52 &#8212; \u043d\u0430 \u043d\u0435\u0439 \u0432\u0441\u0451 \u043d\u043e\u0440\u043c\u0430\u043b\u044c\u043d\u043e \u043e\u0442\u043a\u0440\u044b\u043b\u043e\u0441\u044c.<\/p>\n<blockquote>\n<p><strong>\u0414\u043e\u043f\u043e\u043b\u043d\u0435\u043d\u0438\u0435 \u21162 (\u043e\u0442 01.01.2024 \u0433.):<\/strong><\/p>\n<p>\u041f\u043e\u0441\u043b\u0435  2 \u043d\u0435\u0434\u0435\u043b\u044c\u043d\u043e\u0439 \u0440\u0430\u0431\u043e\u0442\u044b \u0441 \u043b\u043e\u043a\u0430\u043b\u044c\u043d\u044b\u043c\u0438 \u043d\u0435\u0439\u0440\u043e\u0441\u0435\u0442\u044f\u043c\u0438 \u044f \u043f\u0440\u0438\u0448\u0451\u043b \u043a \u0432\u044b\u0432\u043e\u0434\u0443, \u0447\u0442\u043e \u0446\u0435\u043b\u044c\u043d\u044b\u0435 \u043c\u043e\u0434\u0435\u043b\u0438 \u043b\u0443\u0447\u0448\u0435 \u0432 \u043e\u0442\u0432\u0435\u0442\u0430\u0445, \u0447\u0435\u043c \u043c\u043e\u0434\u0435\u043b\u0438, \u043a\u043e\u0442\u043e\u0440\u044b\u0435 \u0440\u0430\u0431\u043e\u0442\u0430\u0435\u0442 \u0441 \u043d\u0435\u0441\u043a\u043e\u043b\u044c\u043a\u0438\u043c\u0438 \u043f\u043e\u0434\u0441\u0435\u0442\u044f\u043c\u0438-\u044d\u043a\u0441\u043f\u0435\u0440\u0442\u0430\u043c\u0438 (Mixtral 8*7B). \u0414\u0430, \u043e\u043d\u0438 \u0433\u0435\u043d\u0435\u0440\u0438\u0440\u0443\u044e\u0442 \u043e\u0442\u0432\u0435\u0442 \u0434\u043e\u043b\u044c\u0448\u0435, \u043d\u043e \u043a\u0430\u0447\u0435\u0441\u0442\u0432\u043e \u043e\u0442\u0432\u0435\u0442\u0430 \u043b\u0443\u0447\u0448\u0435. \u041f\u043e\u044d\u0442\u043e\u043c\u0443 \u043c\u043e\u0439 \u0432\u044b\u0431\u043e\u0440 &#8212; \u044d\u0442\u043e DeepSeek Coder 33B Instruct \u0434\u043b\u044f \u043d\u0430\u043f\u0438\u0441\u0430\u043d\u0438\u044f \u043a\u043e\u0434\u0430. \u0418 DeepSeek LLM Chat 67B \u0434\u043b\u044f \u0432\u043e\u043f\u0440\u043e\u0441\u043e\u0432, \u043d\u0435 \u0441\u0432\u044f\u0437\u0430\u043d\u043d\u044b\u0445 \u0441 \u043f\u0440\u043e\u0433\u0440\u0430\u043c\u043c\u0438\u0440\u043e\u0432\u0430\u043d\u0438\u0435\u043c. \u041d\u043e \u044d\u0442\u043e \u043d\u0430 \u0434\u0430\u043d\u043d\u044b\u0439 \u043c\u043e\u043c\u0435\u043d\u0442. \u041c\u043e\u0436\u0435\u0442 \u043f\u043e\u044f\u0432\u044f\u0442\u0441\u044f \u0435\u0449\u0435 \u043b\u0443\u0447\u0448\u0438\u0435 \u043b\u043e\u043a\u0430\u043b\u044c\u043d\u044b\u0435 GPT \u043d\u0435\u0439\u0440\u043e\u043d\u043d\u044b\u0435 \u0441\u0435\u0442\u0438.<\/p>\n<\/blockquote>\n<\/div>\n<\/div>\n<\/div>\n<p><!----><!----><\/div>\n<p><!----><!----><br \/> \u0441\u0441\u044b\u043b\u043a\u0430 \u043d\u0430 \u043e\u0440\u0438\u0433\u0438\u043d\u0430\u043b \u0441\u0442\u0430\u0442\u044c\u0438 <a href=\"https:\/\/habr.com\/ru\/articles\/780092\/\"> https:\/\/habr.com\/ru\/articles\/780092\/<\/a><\/p>\n","protected":false},"excerpt":{"rendered":"<div><!--[--><!--]--><\/div>\n<div id=\"post-content-body\">\n<div>\n<div class=\"article-formatted-body article-formatted-body article-formatted-body_version-2\">\n<div xmlns=\"http:\/\/www.w3.org\/1999\/xhtml\">\n<p>\u0415\u0441\u0442\u044c \u043c\u043d\u043e\u0433\u043e LLM \u043d\u0435\u0439\u0440\u043e\u043d\u043d\u044b\u0445 \u0441\u0435\u0442\u0435\u0439, \u0441\u043e\u0437\u0434\u0430\u0442\u0435\u043b\u0438 \u043a\u043e\u0442\u043e\u0440\u044b\u0445 \u0433\u043e\u0432\u043e\u0440\u044f\u0442, \u0447\u0442\u043e \u043e\u043d\u0438 \u0430\u043d\u0430\u043b\u043e\u0433\u0438\u0447\u043d\u044b, \u0430 \u043c\u043e\u0436\u0435\u0442 \u0434\u0430\u0436\u0435 \u043b\u0443\u0447\u0448\u0435 ChatGPT \u0432\u0435\u0440\u0441\u0438\u0439 3.5 \u0438 4.0. \u0414\u0430\u0432\u0430\u0439\u0442\u0435 \u043f\u043e\u043f\u0440\u043e\u0431\u0443\u0435\u043c \u043f\u0440\u043e\u0442\u0435\u0441\u0442\u0438\u0440\u043e\u0432\u0430\u0442\u044c \u0438\u0445, \u0443\u0441\u0442\u0430\u043d\u043e\u0432\u0438\u0432 \u0438\u0445 \u043d\u0430 \u043b\u043e\u043a\u0430\u043b\u044c\u043d\u044b\u0439 \u043a\u043e\u043c\u043f\u044c\u044e\u0442\u0435\u0440, \u0438 \u043f\u043e\u043d\u044f\u0442\u044c, \u0434\u0435\u0439\u0441\u0442\u0432\u0438\u0442\u0435\u043b\u044c\u043d\u043e \u043b\u0438 \u043e\u043d\u0438 \u0442\u0430\u043a \u0445\u043e\u0440\u043e\u0448\u0438.<\/p>\n<p>\u0425\u0430\u0440\u0430\u043a\u0442\u0435\u0440\u0438\u0441\u0442\u0438\u043a\u0438 \u043c\u043e\u0435\u0433\u043e \u0434\u043e\u043c\u0430\u0448\u043d\u0435\u0433\u043e \u043a\u043e\u043c\u043f\u044c\u044e\u0442\u0435\u0440\u0430, \u043d\u0430 \u043a\u043e\u0442\u043e\u0440\u043e\u043c \u044f \u0437\u0430\u0434\u0430\u0432\u0430\u043b \u0432\u043e\u043f\u0440\u043e\u0441\u044b GPT \u043d\u0435\u0439\u0440\u043e\u0441\u0435\u0442\u044f\u043c:<\/p>\n<ul>\n<li>\n<p>8 \u044f\u0434\u0435\u0440\u043d\u044b\u0439 16 \u043f\u043e\u0442\u043e\u0447\u043d\u044b\u0439 \u043f\u0440\u043e\u0446\u0435\u0441\u0441\u043e\u0440 AMD Ryzen 7 1700X<\/p>\n<\/li>\n<li>\n<p>64 \u0413\u0431 \u043e\u043f\u0435\u0440\u0430\u0442\u0438\u0432\u043d\u043e\u0439 \u043f\u0430\u043c\u044f\u0442\u0438 \u0434\u0432\u0443\u043c\u044f \u043f\u043b\u0430\u043d\u043a\u0430\u043c\u0438 \u043f\u043e 32 \u0413\u0431 DDR4 2666 \u041c\u0413\u0446<\/p>\n<\/li>\n<\/ul>\n<p>\u0412\u0438\u0434\u0435\u043e\u043a\u0430\u0440\u0442\u0443 \u044f \u043d\u0435 \u0438\u0441\u043f\u043e\u043b\u044c\u0437\u043e\u0432\u0430\u043b, \u0442\u0430\u043a \u043a\u0430\u043a \u0432 \u043d\u0435\u0439 \u043c\u0430\u043b\u043e \u0432\u0438\u0434\u0435\u043e\u043f\u0430\u043c\u044f\u0442\u0438, \u0438 \u0431\u043e\u043b\u044c\u0448\u0438\u0435 \u043d\u0435\u0439\u0440\u043e\u043d\u043d\u044b\u0435 \u0441\u0435\u0442\u0438 \u0432 \u043d\u0435\u0451 \u043d\u0435 \u0432\u043b\u0435\u0437\u0443\u0442, \u0430 \u043f\u043e\u0441\u0442\u043e\u044f\u043d\u043d\u043e \u043f\u0435\u0440\u0435\u043a\u0438\u0434\u044b\u0432\u0430\u0442\u044c \u0434\u0430\u043d\u043d\u044b\u0435 \u0447\u0435\u0440\u0435\u0437 \u0443\u0437\u043a\u0443\u044e PCI-e 3.0 \u0448\u0438\u043d\u0443 \u043d\u0435 \u0441\u0430\u043c\u043e\u0435 \u0431\u044b\u0441\u0442\u0440\u043e\u0435 \u0443\u0434\u043e\u0432\u043e\u043b\u044c\u0441\u0442\u0432\u0438\u0435.<\/p>\n<p>\u0417\u0430\u0434\u0430\u0432\u0430\u043b \u044f \u0434\u0432\u0430 \u0432\u043e\u043f\u0440\u043e\u0441\u0430 \u043d\u0430 \u0430\u043d\u0433\u043b\u0438\u0439\u0441\u043a\u043e\u043c \u044f\u0437\u044b\u043a\u0435 \u0434\u043b\u044f \u0447\u0438\u0441\u0442\u043e\u0442\u044b \u044d\u043a\u0441\u043f\u0435\u0440\u0438\u043c\u0435\u043d\u0442\u0430:<\/p>\n<ol>\n<li>\n<p>Is it possible to connect two Nvidia 3080 graphics cards using NVLink? (\u041f\u0435\u0440\u0435\u0432\u043e\u0434: \u041c\u043e\u0436\u043d\u043e \u043b\u0438 \u043f\u043e\u0434\u043a\u043b\u044e\u0447\u0438\u0442\u044c \u0434\u0432\u0435 \u0432\u0438\u0434\u0435\u043e\u043a\u0430\u0440\u0442\u044b Nvidia 3080 \u0441 \u043f\u043e\u043c\u043e\u0449\u044c\u044e NVLink?) &#8212; \u0445\u0438\u0442\u0440\u043e\u0441\u0442\u044c \u0432\u043e\u043f\u0440\u043e\u0441\u0430 \u0432 \u0442\u043e\u043c, \u0447\u0442\u043e \u0443 \u044d\u0442\u043e\u0439 \u0432\u0438\u0434\u0435\u043e\u043a\u0430\u0440\u0442\u044b \u043d\u0435\u0442 \u0448\u0438\u043d\u044b NVLink. \u041e\u043d\u0430 \u0435\u0441\u0442\u044c \u0443 \u0441\u0442\u0430\u0440\u0448\u0435\u0439 \u0432\u0438\u0434\u0435\u043e\u043a\u0430\u0440\u0442\u044b Nvidia GeForce RTX 3090.<\/p>\n<\/li>\n<li>\n<p>Write a program to recognize human speech and then write the result to a text file. (\u041f\u0435\u0440\u0435\u0432\u043e\u0434: \u041d\u0430\u043f\u0438\u0448\u0438\u0442\u0435 \u043f\u0440\u043e\u0433\u0440\u0430\u043c\u043c\u0443 \u0434\u043b\u044f \u0440\u0430\u0441\u043f\u043e\u0437\u043d\u0430\u0432\u0430\u043d\u0438\u044f \u0447\u0435\u043b\u043e\u0432\u0435\u0447\u0435\u0441\u043a\u043e\u0439 \u0440\u0435\u0447\u0438, \u0430 \u0437\u0430\u0442\u0435\u043c \u0437\u0430\u043f\u0438\u0448\u0438\u0442\u0435 \u0440\u0435\u0437\u0443\u043b\u044c\u0442\u0430\u0442 \u0432 \u0442\u0435\u043a\u0441\u0442\u043e\u0432\u044b\u0439 \u0444\u0430\u0439\u043b). \u0417\u0434\u0435\u0441\u044c \u043c\u044b \u043f\u0440\u043e\u0432\u0435\u0440\u044f\u0435\u043c \u043a\u0430\u043a \u043d\u0435\u0439\u0440\u043e\u043d\u043d\u0430\u044f \u0441\u0435\u0442\u044c \u0441\u043f\u0440\u0430\u0432\u0438\u0442\u0441\u044f \u0441 \u043d\u0430\u043f\u0438\u0441\u0430\u043d\u0438\u0435\u043c \u043a\u043e\u0434\u0430.<\/p>\n<\/li>\n<\/ol>\n<h2>\u041a\u0430\u043a \u0443\u0441\u0442\u0430\u043d\u043e\u0432\u0438\u0442\u044c \u0438 \u043d\u0430\u0441\u0442\u0440\u043e\u0438\u0442\u044c \u043b\u043e\u043a\u0430\u043b\u044c\u043d\u0443\u044e GPT \u043d\u0435\u0439\u0440\u043e\u0441\u0435\u0442\u044c<\/h2>\n<p>\u0418\u0441\u043f\u043e\u043b\u044c\u0437\u043e\u0432\u0430\u043b \u044f \u0443\u0436\u0435 \u043f\u043e\u0434\u0433\u043e\u0442\u043e\u0432\u043b\u0435\u043d\u043d\u044b\u0439 \u0444\u0430\u0439\u043b GGUF \u043c\u043e\u0434\u0435\u043b\u0438 \u043d\u0435\u0439\u0440\u043e\u0441\u0435\u0442\u0438 \u0438 \u043f\u0440\u043e\u0433\u0440\u0430\u043c\u043c\u0443 <a href=\"https:\/\/github.com\/LostRuins\/koboldcpp\/releases\" rel=\"noopener noreferrer nofollow\">Koboldcpp_nocuda<\/a> (\u0440\u0430\u0441\u0447\u0435\u0442\u044b \u043f\u0440\u043e\u0438\u0437\u0432\u043e\u0434\u044f\u0442\u0441\u044f \u0442\u043e\u043b\u044c\u043a\u043e \u043d\u0430 \u043f\u0440\u043e\u0446\u0435\u0441\u0441\u043e\u0440\u0435). \u0412\u044b \u043c\u043e\u0436\u0435\u0442\u0435 \u0438\u0441\u043f\u043e\u043b\u044c\u0437\u043e\u0432\u0430\u0442\u044c <a href=\"https:\/\/github.com\/LostRuins\/koboldcpp\/releases\" rel=\"noopener noreferrer nofollow\">Koboldcpp<\/a> \u0441 \u043f\u043e\u0434\u0434\u0435\u0440\u0436\u043a\u043e\u0439 \u0432\u0438\u0434\u0435\u043e\u043a\u0430\u0440\u0442\u044b NVidia. \u0418\u043b\u0438 <a href=\"https:\/\/github.com\/YellowRoseCx\/koboldcpp-rocm\/releases\" rel=\"noopener noreferrer nofollow\">Koboldcpp_rocm<\/a>, \u0435\u0441\u043b\u0438 \u0443 \u0432\u0430\u0441 \u0432\u0438\u0434\u0435\u043e\u043a\u0430\u0440\u0442\u0430 AMD. \u042d\u0442\u043e \u0432\u0441\u0451 &#171;exe&#187; \u0444\u0430\u0439\u043b\u044b, \u0442\u0430\u043a \u043a\u0430\u043a \u044f \u0442\u0435\u0441\u0442\u0438\u0440\u043e\u0432\u0430\u043b \u0432 \u041e\u0421 Windows \u0438 \u043f\u0440\u043e\u0433\u0440\u0430\u043c\u043c\u0430 \u043d\u0435 \u0442\u0440\u0435\u0431\u0443\u0435\u0442 \u0443\u0441\u0442\u0430\u043d\u043e\u0432\u043a\u0438. <\/p>\n<figure class=\"full-width\">\n<div><figcaption>\u0418\u043d\u0442\u0435\u0440\u0444\u0435\u0439\u0441 \u043f\u0440\u043e\u0433\u0440\u0430\u043c\u043c\u044b Koboldcpp (\u043e\u0431\u0440\u0430\u0442\u0438\u0442\u0435 \u0432\u043d\u0438\u043c\u0430\u043d\u0438\u0435 \u043d\u0430 \u0433\u0440\u0430\u0444\u0443 Context Size &#8212; \u0432\u044b \u043c\u043e\u0436\u0435\u0442\u0435 \u0443\u0432\u0435\u043b\u0438\u0447\u0438\u0442\u044c \u0440\u0430\u0437\u043c\u0435\u0440 \u043a\u043e\u043d\u0442\u0435\u043a\u0441\u0442\u0430)<\/figcaption><\/div>\n<\/figure>\n<p>\u041f\u043e\u0441\u043b\u0435 \u0437\u0430\u0433\u0440\u0443\u0437\u043a\u0438 \u043c\u043e\u0434\u0435\u043b\u0438 \u0432 \u043f\u0440\u043e\u0433\u0440\u0430\u043c\u043c\u0435, \u0435\u0441\u043b\u0438 \u0443 \u0432\u0430\u0441 \u0445\u0432\u0430\u0442\u0438\u043b\u043e \u043e\u043f\u0435\u0440\u0430\u0442\u0438\u0432\u043d\u043e\u0439 \u043f\u0430\u043c\u044f\u0442\u0438 \u043e\u0442\u043a\u0440\u043e\u0435\u0442\u0441\u044f \u043e\u043a\u043d\u043e \u0432 \u0431\u0440\u0430\u0443\u0437\u0435\u0440\u0435, \u043a\u0443\u0434\u0430 \u0432\u044b \u043c\u043e\u0436\u0435\u0442\u0435 \u043f\u0438\u0441\u0430\u0442\u044c \u0432\u043e\u043f\u0440\u043e\u0441\u044b. \u0420\u0435\u043a\u043e\u043c\u0435\u043d\u0434\u0443\u044e \u043d\u0430\u0447\u0438\u043d\u0430\u0442\u044c \u043d\u043e\u0432\u0443\u044e \u0441\u0435\u0441\u0441\u0438\u044e \u043a\u0430\u0436\u0434\u044b\u0439 \u0440\u0430\u0437, \u043a\u043e\u0433\u0434\u0430 \u0432\u044b \u0437\u0430\u043f\u0443\u0441\u043a\u0430\u0435\u0442\u0435 \u043f\u0440\u043e\u0433\u0440\u0430\u043c\u043c\u0443. <\/p>\n<figure class=\"full-width\">\n<div><figcaption>\u0411\u0443\u0434\u044c\u0442\u0435 \u0442\u0435\u0440\u043f\u0435\u043b\u0438\u0432\u044b, \u043d\u0435\u0439\u0440\u043e\u0441\u0435\u0442\u044c \u0437\u0430\u0433\u0440\u0443\u0437\u0438\u0442 \u0432\u0430\u0448 \u043f\u0440\u043e\u0446\u0435\u0441\u0441\u043e\u0440 \u043d\u0430 100 %<\/figcaption><\/div>\n<\/figure>\n<p>\u0412 \u043d\u0430\u0441\u0442\u0440\u043e\u0439\u043a\u0430\u0445 \u0432 \u0433\u0440\u0430\u0444\u0435 &#171;Amount to Gen&#187; \u0432\u044b \u043c\u043e\u0436\u0435\u0442\u0435 \u0443\u0432\u0435\u043b\u0438\u0447\u0438\u0442\u044c \u0437\u043d\u0430\u0447\u0435\u043d\u0438\u0435 \u0434\u043e 512 &#8212; \u044d\u0442\u043e \u043a\u043e\u043b\u0438\u0447\u0435\u0441\u0442\u0432\u043e \u0442\u043e\u043a\u0435\u043d\u043e\u0432 \u0432 \u043e\u0442\u0432\u0435\u0442\u0435 (\u0447\u0435\u043c \u0431\u043e\u043b\u044c\u0448\u0435, \u0442\u0435\u043c \u0431\u043e\u043b\u0435\u0435 \u0434\u043b\u0438\u043d\u043d\u044b\u0439 \u043e\u0442\u0432\u0435\u0442). \u041b\u0438\u0431\u043e \u043d\u0430\u0431\u0438\u0442\u044c \u043e\u0442 \u0440\u0443\u043a\u0438 &#8212; \u044f \u0432\u0431\u0438\u043b 8192 (= 1024*8). \u041c\u0430\u043a\u0441\u0438\u043c\u0430\u043b\u044c\u043d\u044b\u0439 \u0435\u0451 \u043e\u0442\u0432\u0435\u0442 \u0431\u0443\u0434\u0435\u0442 \u043e\u0433\u0440\u0430\u043d\u0438\u0447\u0435\u043d 8192 \u0442\u043e\u043a\u0435\u043d\u0430\u043c\u0438. \u041e\u0434\u043d\u0430\u043a\u043e \u043a\u0430\u043a \u043f\u0440\u0430\u0432\u0438\u043b\u043e \u043e\u043d\u0430 \u043f\u0438\u0448\u0435\u0442 \u043e\u0442\u0432\u0435\u0442 \u0441 \u0433\u043e\u0440\u0430\u0437\u0434\u043e \u043c\u0435\u043d\u044c\u0448\u0438\u043c\u0438 \u0442\u043e\u043a\u0435\u043d\u0430\u043c\u0438 (\u043f\u043e \u0443\u0441\u043c\u043e\u0442\u0440\u0435\u043d\u0438\u044e \u043d\u0435\u0439\u0440\u043e\u043d\u043d\u043e\u0439 \u0441\u0435\u0442\u0438).<\/p>\n<p>\u0413\u0440\u0430\u0444\u0430 Max Ctx. Tokens &#8212; \u044d\u0442\u043e \u043c\u0430\u043a\u0441\u0438\u043c\u0430\u043b\u044c\u043d\u044b\u0439 \u0440\u0430\u0437\u043c\u0435\u0440 \u0432\u0445\u043e\u0434\u043d\u043e\u0433\u043e \u043a\u043e\u043d\u0442\u0435\u043a\u0441\u0442\u0430. \u0421\u043c\u043e\u0442\u0440\u0438\u0442\u0435 \u043d\u0430 \u0445\u0430\u0440\u0430\u043a\u0442\u0435\u0440\u0438\u0441\u0442\u0438\u043a\u0438 \u043a\u0430\u0436\u0434\u043e\u0439 GGUF \u043c\u043e\u0434\u0435\u043b\u0438 &#8212; \u043d\u0430 \u043a\u0430\u043a\u043e\u043c \u0440\u0430\u0437\u043c\u0435\u0440\u0435 \u043a\u043e\u043d\u0442\u0435\u043a\u0441\u0442\u0430 \u043e\u043d\u0430 \u043e\u0431\u0443\u0447\u0430\u043b\u0430\u0441\u044c. \u041d\u0430\u043f\u0440\u0438\u043c\u0435\u0440 \u0443 DeepSeek \u043a\u043e\u043d\u0442\u0435\u043a\u0441\u0442 \u0440\u0430\u0432\u0435\u043d 16 \u041a\u0431 (\u044d\u0442\u043e \u0437\u043d\u0430\u0447\u0435\u043d\u0438\u0435 \u044f \u0438 \u0432\u043f\u0438\u0441\u0430\u043b). \u041c\u043e\u0436\u0435\u0442\u0435 \u043e\u0433\u0440\u0430\u043d\u0438\u0447\u0438\u0442\u044c\u0441\u044f \u043c\u0435\u043d\u044c\u0448\u0438\u043c\u0438 \u0437\u043d\u0430\u0447\u0435\u043d\u0438\u044f\u043c\u0438. \u041d\u043e \u043f\u0440\u0438 \u044d\u0442\u043e\u043c \u043c\u0430\u043a\u0441\u0438\u043c\u0430\u043b\u044c\u043d\u043e\u0435 \u043a\u043e\u043b\u0438\u0447\u0435\u0441\u0442\u0432\u043e \u0442\u043e\u043a\u0435\u043d\u043e\u0432 \u043e\u0442\u0432\u0435\u0442\u0430 \u0434\u043e\u043b\u0436\u043d\u043e \u0431\u044b\u0442\u044c \u043c\u0435\u043d\u044c\u0448\u0435 \u043c\u0430\u043a\u0441\u0438\u043c\u0430\u043b\u044c\u043d\u043e\u0433\u043e \u043a\u043e\u043b\u0438\u0447\u0435\u0441\u0442\u0432\u0430 \u0442\u043e\u043a\u0435\u043d\u043e\u0432 \u0443 \u0432\u0445\u043e\u0434\u043d\u043e\u0433\u043e \u043a\u043e\u043d\u0442\u0435\u043a\u0441\u0442\u0430.<\/p>\n<p>\u0422\u0430\u043a\u0436\u0435 \u043f\u0440\u0438 \u0438\u043d\u0438\u0446\u0438\u0430\u043b\u0438\u0437\u0430\u0446\u0438\u0438 (\u0442\u0430\u043c \u0433\u0434\u0435 \u0432\u044b \u0443\u043a\u0430\u0437\u044b\u0432\u0430\u043b\u0438 \u043a\u043e\u043b\u0438\u0447\u0435\u0441\u0442\u0432\u043e \u043f\u043e\u0442\u043e\u043a\u043e\u0432 \u043f\u0440\u043e\u0446\u0435\u0441\u0441\u043e\u0440\u0430 \u0438 \u043f\u0443\u0442\u044c \u043a \u043c\u043e\u0434\u0435\u043b\u0438) \u0435\u0441\u0442\u044c \u0433\u0440\u0430\u0444\u0430 Context Size &#8212; \u0443\u0432\u0435\u043b\u0438\u0447\u044c\u0442\u0435 \u0435\u0433\u043e \u0434\u043e \u0447\u0438\u0441\u043b\u0430 \u0432 \u0433\u0440\u0430\u0444\u0435 Max Ctx. Tokens (\u0447\u0442\u043e\u0431\u044b \u043e\u043d\u0438 \u0431\u044b\u043b\u0438 \u0440\u0430\u0432\u043d\u044b).<\/p>\n<figure class=\"full-width\">\n<div><figcaption>\u041d\u0430\u0441\u0442\u0440\u0430\u0438\u0432\u0430\u0435\u043c \u043a\u043e\u043b\u0438\u0447\u0435\u0441\u0442\u0432\u043e \u0442\u043e\u043a\u0435\u043d\u043e\u0432 \u0432 \u043e\u0442\u0432\u0435\u0442\u0435 \u0438 \u0432\u043e \u0432\u0445\u043e\u0434\u043d\u043e\u043c \u043a\u043e\u043d\u0442\u0435\u043a\u0441\u0442\u0435.<\/figcaption><\/div>\n<\/figure>\n<p>\u041f\u043e\u0434\u0433\u043e\u0442\u043e\u0432\u043b\u0435\u043d\u043d\u044b\u0435 GGUF \u043c\u043e\u0434\u0435\u043b\u0438 \u0441\u043a\u0430\u0447\u0438\u0432\u0430\u0435\u043c \u043e\u0442\u0441\u044e\u0434\u0430: <a href=\"https:\/\/huggingface.co\/\" rel=\"noopener noreferrer nofollow\">https:\/\/huggingface.co\/<\/a>. \u0412\u0432\u0435\u0434\u0438\u0442\u0435 \u0432 \u043f\u043e\u0438\u0441\u043a\u0435 \u043d\u0435\u043e\u0431\u0445\u043e\u0434\u0438\u043c\u0443\u044e \u043c\u043e\u0434\u0435\u043b\u044c.<\/p>\n<figure class=\"full-width\">\n<div><figcaption>\u041f\u0440\u0438 \u043d\u0430\u0436\u0430\u0442\u0438\u0438 \u043d\u0430 \u0441\u0441\u044b\u043b\u043a\u0443 \u0432\u044b\u0432\u0435\u0434\u0435\u0442 \u0432\u0441\u0435 \u0440\u0435\u0437\u0443\u043b\u044c\u0442\u0430\u0442\u044b \u043f\u043e \u043f\u043e\u0438\u0441\u043a\u043e\u0432\u043e\u043c\u0443 \u0437\u0430\u043f\u0440\u043e\u0441\u0443<\/figcaption><\/div>\n<\/figure>\n<p>\u0422\u0430\u043a\u0436\u0435 \u0435\u0441\u0442\u044c \u0438\u043d\u0442\u0435\u0440\u0435\u0441\u043d\u044b\u0439 <a href=\"https:\/\/huggingface.co\/spaces\/HuggingFaceH4\/open_llm_leaderboard\" rel=\"noopener noreferrer nofollow\">\u0440\u0435\u0439\u0442\u0438\u043d\u0433 \u043e\u0446\u0435\u043d\u043a\u0438 \u044d\u0444\u0444\u0435\u043a\u0442\u0438\u0432\u043d\u043e\u0441\u0442\u0438 LLM \u043d\u0435\u0439\u0440\u043e\u0441\u0435\u0442\u0435\u0439<\/a> \u043d\u0430 \u044d\u0442\u043e\u043c \u0441\u0430\u0439\u0442\u0435, \u043d\u043e \u043c\u044b \u043f\u0440\u0435\u0434\u043f\u043e\u0447\u0442\u0435\u043c \u0441\u0430\u043c\u0438 \u043f\u0440\u043e\u0442\u0435\u0441\u0442\u0438\u0440\u043e\u0432\u0430\u0442\u044c \u0441\u0430\u043c\u044b\u0435 \u0438\u043d\u0442\u0435\u0440\u0435\u0441\u043d\u044b\u0435 \u043d\u0435\u0439\u0440\u043e\u043d\u043d\u044b\u0435 \u0441\u0435\u0442\u0438. <\/p>\n<figure class=\"full-width\">\n<div><figcaption>\u0420\u0435\u0439\u0442\u0438\u043d\u0433 LLM \u043d\u0435\u0439\u0440\u043e\u0441\u0435\u0442\u0435\u0439<\/figcaption><\/div>\n<\/figure>\n<p>\u0422\u0430\u043a\u0436\u0435, \u0435\u0441\u043b\u0438 \u0432\u044b\u0431\u0440\u0430\u0442\u044c \u0438\u043d\u0442\u0435\u0440\u0435\u0441\u0443\u044e\u0449\u0443\u044e \u043d\u0435\u0439\u0440\u043e\u0441\u0435\u0442\u044c, \u0442\u043e \u043c\u043e\u0436\u043d\u043e \u043f\u043e\u0441\u043c\u043e\u0442\u0440\u0435\u0442\u044c \u0441\u043a\u043e\u043b\u044c\u043a\u043e \u043e\u043f\u0435\u0440\u0430\u0442\u0438\u0432\u043d\u043e\u0439 \u043f\u0430\u043c\u044f\u0442\u0438 \u0431\u0443\u0434\u0435\u0442 \u0437\u0430\u043d\u0438\u043c\u0430\u0442\u044c GGUF \u043c\u043e\u0434\u0435\u043b\u044c \u0441 \u0440\u0430\u0437\u043d\u043e\u0439 \u0441\u0442\u0435\u043f\u0435\u043d\u044c\u044e \u043a\u0432\u0430\u043d\u0442\u043e\u0432\u0430\u043d\u0438\u044f (Q8 \u043b\u0443\u0447\u0448\u0435 \u0432\u0441\u0435\u0433\u043e, \u043d\u043e \u043e\u043d\u0430 \u0437\u0430\u043d\u0438\u043c\u0430\u0435\u0442 \u0431\u043e\u043b\u044c\u0448\u0435 \u0432\u0441\u0435\u0433\u043e \u043c\u0435\u0441\u0442\u0430, \u0441\u0430\u043c\u0430\u044f \u043e\u043f\u0442\u0438\u043c\u0430\u043b\u044c\u043d\u0430\u044f Q5_K_M \u043c\u043e\u0434\u0435\u043b\u044c).<\/p>\n<figure class=\"full-width\">\n<div><figcaption>\u041d\u0435\u0439\u0440\u043e\u0441\u0435\u0442\u0438 \u0441 70 \u043c\u043b\u0440\u0434 \u043f\u0430\u0440\u0430\u043c\u0435\u0442\u0440\u043e\u0432 \u0437\u0430\u043d\u0438\u043c\u0430\u044e\u0442 \u0431\u043e\u043b\u044c\u0448\u0435\u0433\u043e \u0432\u0441\u0435\u0433\u043e \u043c\u0435\u0441\u0442\u0430 \u0432 \u043e\u043f\u0435\u0440\u0430\u0442\u0438\u0432\u043d\u043e\u0439 \u043f\u0430\u043c\u044f\u0442\u0438, \u043d\u0430\u043f\u0440\u0438\u043c\u0435\u0440 \u0441 \u043a\u0432\u0430\u043d\u0442\u043e\u0432\u0430\u043d\u0438\u0435\u043c Q8_0 \u0442\u0440\u0435\u0431\u0443\u0435\u0442 71,65 \u0413\u0431 \u043d\u0430 \u0436\u0435\u0441\u0442\u043a\u043e\u043c \u0434\u0438\u0441\u043a\u0435 \u0438 \u0437\u0430\u0439\u043c\u0435\u0442 74,15 \u0413\u0431 \u043e\u043f\u0435\u0440\u0430\u0442\u0438\u0432\u043d\u043e\u0439 \u043f\u0430\u043c\u044f\u0442\u0438 \u043f\u0440\u0438 \u0440\u0430\u0431\u043e\u0442\u0435.<\/figcaption><\/div>\n<\/figure>\n<p>GGUF \u043c\u043e\u0434\u0435\u043b\u044c \u0441 \u043a\u0432\u0430\u043d\u0442\u043e\u0432\u0430\u043d\u0438\u0435\u043c Q2_K \u0438\u043c\u0435\u0435\u0442 \u0441\u0430\u043c\u0443\u044e \u0431\u043e\u043b\u044c\u0448\u0443\u044e \u043f\u043e\u0442\u0435\u0440\u044e \u0442\u043e\u0447\u043d\u043e\u0441\u0442\u0438 \u043e\u0442\u0432\u0435\u0442\u0430 \u043f\u043e \u0441\u0440\u0430\u0432\u043d\u0435\u043d\u0438\u044e \u0441 \u043d\u0430\u0447\u0430\u043b\u044c\u043d\u043e\u0439 F16.<\/p>\n<figure class=\"full-width\">\n<div><figcaption>\u0421\u0442\u043e\u043b\u0431\u0435\u0446 &#171;+ppl %&#187; \u043f\u043e\u043a\u0430\u0437\u044b\u0432\u0430\u0435\u0442 \u043f\u043e\u0442\u0435\u0440\u044e \u0442\u043e\u0447\u043d\u043e\u0441\u0442\u0438 \u043f\u043e \u0441\u0440\u0430\u0432\u043d\u0435\u043d\u0438\u044e \u0441 \u043e\u0440\u0438\u0433\u0438\u043d\u0430\u043b\u044c\u043d\u043e\u0439 f16<\/figcaption><\/div>\n<\/figure>\n<h2>OpenChat 3.5 &#8212; 7B \u043f\u0430\u0440\u0430\u043c\u0435\u0442\u0440\u043e\u0432<\/h2>\n<blockquote>\n<p>\u042d\u0442\u0430 \u043c\u043e\u0434\u0435\u043b\u044c, \u043f\u043e \u0437\u0430\u044f\u0432\u043b\u0435\u043d\u0438\u044e \u0440\u0430\u0437\u0440\u0430\u0431\u043e\u0442\u0447\u0438\u043a\u043e\u0432, \u043f\u0440\u0435\u0432\u043e\u0441\u0445\u043e\u0434\u0438\u0442 \u043c\u043e\u0434\u0435\u043b\u0438 \u0441 70B \u043f\u0430\u0440\u0430\u043c\u0435\u0442\u0440\u043e\u0432 \u0438\u043c\u0435\u044f \u0432\u0441\u0435\u0433\u043e \u043b\u0438\u0448\u044c 7B \u043f\u0430\u0440\u0430\u043c\u0435\u0442\u0440\u043e\u0432  <\/p>\n<\/blockquote>\n<p>\u0414\u0430\u0432\u0430\u0439\u0442\u0435 \u043f\u0440\u043e\u0432\u0435\u0440\u0438\u043c \u0434\u0430\u043d\u043d\u043e\u0435 \u0437\u0430\u044f\u0432\u043b\u0435\u043d\u0438\u0435. <\/p>\n<ol>\n<li>\n<p>Is it possible to connect two Nvidia 3080 graphics cards using NVLink?<\/p>\n<\/li>\n<\/ol>\n<details class=\"spoiler\">\n<summary>Hidden text<\/summary>\n<div class=\"spoiler__content\">\n<p>No, it is not possible to connect two Nvidia 3080 graphics cards using NVLink. The Nvidia GeForce RTX 3080 does not support NVLink technology, so you cannot connect multiple 3080 GPUs together using this method. Instead, you would need to use other methods such as SLI or PCIe x16 slots to connect two or more Nvidia 3080 graphics cards. However, please note that multi-GPU setups are not commonly used with modern gaming PCs due to the limited benefits they provide over a single high-end GPU like the Nvidia GeForce RTX 3080.<\/p>\n<p>For the Nvidia GeForce RTX 3080, there are no available options to connect multiple GPUs using NVLink. You can only use a single Nvidia GeForce RTX 3080 graphics card in your system at a time. This is because the RTX 3080 has only one PCIe 16x slot and does not have an additional NVLink connector. Therefore, if you want to add another GPU to your system, you will need to use a different connection method such as PCIe x16 slots or SLI bridges. However, please keep in mind that using multiple GPUs in a gaming PC setup may not always result in better performance compared to a single high-end GPU like the Nvidia GeForce RTX 3080.<\/p>\n<p>It&#8217;s important to note that while NVLink technology was once a popular feature for connecting multiple high-end GPUs together in a system, it is no longer widely supported by most manufacturers. In recent years, many GPU manufacturers have shifted towards focusing on single-GPU solutions rather than multi-GPU setups due to improvements in individual GPU performance and the challenges associated with maintaining compatibility between multiple GPUs. As a result, NVLink has become less relevant in today&#8217;s gaming PC market.<\/p>\n<p>In summary, the Nvidia GeForce RTX 3080 does not support NVLink technology, so it cannot be connected to other GPUs using this method. Instead, you should explore alternative methods such as SLI or PCIe x16 slots to connect two or more Nvidia 3080 GPUs together. <\/p>\n<\/div>\n<\/details>\n<p>\u041f\u0435\u0440\u0435\u0432\u043e\u0434:<\/p>\n<details class=\"spoiler\">\n<summary>Hidden text<\/summary>\n<div class=\"spoiler__content\">\n<p>\u041d\u0435\u0442, \u043d\u0435\u0432\u043e\u0437\u043c\u043e\u0436\u043d\u043e \u0441\u043e\u0435\u0434\u0438\u043d\u0438\u0442\u044c \u0434\u0432\u0435 \u0432\u0438\u0434\u0435\u043e\u043a\u0430\u0440\u0442\u044b Nvidia 3080 \u0441 \u043f\u043e\u043c\u043e\u0449\u044c\u044e NVLink. Nvidia GeForce RTX 3080 \u043d\u0435 \u043f\u043e\u0434\u0434\u0435\u0440\u0436\u0438\u0432\u0430\u0435\u0442 \u0442\u0435\u0445\u043d\u043e\u043b\u043e\u0433\u0438\u044e NVLink, \u043f\u043e\u044d\u0442\u043e\u043c\u0443 \u0432\u044b \u043d\u0435 \u043c\u043e\u0436\u0435\u0442\u0435 \u0441\u043e\u0435\u0434\u0438\u043d\u0438\u0442\u044c \u043d\u0435\u0441\u043a\u043e\u043b\u044c\u043a\u043e \u0433\u0440\u0430\u0444\u0438\u0447\u0435\u0441\u043a\u0438\u0445 \u043f\u0440\u043e\u0446\u0435\u0441\u0441\u043e\u0440\u043e\u0432 3080 \u0432\u043c\u0435\u0441\u0442\u0435, \u0438\u0441\u043f\u043e\u043b\u044c\u0437\u0443\u044f \u044d\u0442\u043e\u0442 \u043c\u0435\u0442\u043e\u0434. \u0412\u043c\u0435\u0441\u0442\u043e \u044d\u0442\u043e\u0433\u043e \u0432\u0430\u043c \u043f\u0440\u0438\u0434\u0435\u0442\u0441\u044f \u0438\u0441\u043f\u043e\u043b\u044c\u0437\u043e\u0432\u0430\u0442\u044c \u0434\u0440\u0443\u0433\u0438\u0435 \u043c\u0435\u0442\u043e\u0434\u044b, \u0442\u0430\u043a\u0438\u0435 \u043a\u0430\u043a \u0441\u043b\u043e\u0442\u044b SLI \u0438\u043b\u0438 PCIe x16, \u0434\u043b\u044f \u043f\u043e\u0434\u043a\u043b\u044e\u0447\u0435\u043d\u0438\u044f \u0434\u0432\u0443\u0445 \u0438\u043b\u0438 \u0431\u043e\u043b\u0435\u0435 \u0432\u0438\u0434\u0435\u043e\u043a\u0430\u0440\u0442 Nvidia 3080. \u041e\u0434\u043d\u0430\u043a\u043e \u043e\u0431\u0440\u0430\u0442\u0438\u0442\u0435 \u0432\u043d\u0438\u043c\u0430\u043d\u0438\u0435, \u0447\u0442\u043e \u043a\u043e\u043d\u0444\u0438\u0433\u0443\u0440\u0430\u0446\u0438\u0438 \u0441 \u043d\u0435\u0441\u043a\u043e\u043b\u044c\u043a\u0438\u043c\u0438 \u0433\u0440\u0430\u0444\u0438\u0447\u0435\u0441\u043a\u0438\u043c\u0438 \u043f\u0440\u043e\u0446\u0435\u0441\u0441\u043e\u0440\u0430\u043c\u0438 \u043e\u0431\u044b\u0447\u043d\u043e \u043d\u0435 \u0438\u0441\u043f\u043e\u043b\u044c\u0437\u0443\u044e\u0442\u0441\u044f \u0441 \u0441\u043e\u0432\u0440\u0435\u043c\u0435\u043d\u043d\u044b\u043c\u0438 \u0438\u0433\u0440\u043e\u0432\u044b\u043c\u0438 \u041f\u041a \u0438\u0437-\u0437\u0430 \u043e\u0433\u0440\u0430\u043d\u0438\u0447\u0435\u043d\u043d\u044b\u0445 \u043f\u0440\u0435\u0438\u043c\u0443\u0449\u0435\u0441\u0442\u0432, \u043a\u043e\u0442\u043e\u0440\u044b\u0435 \u043e\u043d\u0438 \u043f\u0440\u0435\u0434\u043e\u0441\u0442\u0430\u0432\u043b\u044f\u044e\u0442 \u043f\u043e \u0441\u0440\u0430\u0432\u043d\u0435\u043d\u0438\u044e \u0441 \u043e\u0434\u043d\u0438\u043c \u0432\u044b\u0441\u043e\u043a\u043e\u043f\u0440\u043e\u0438\u0437\u0432\u043e\u0434\u0438\u0442\u0435\u043b\u044c\u043d\u044b\u043c \u0433\u0440\u0430\u0444\u0438\u0447\u0435\u0441\u043a\u0438\u043c \u043f\u0440\u043e\u0446\u0435\u0441\u0441\u043e\u0440\u043e\u043c, \u0442\u0430\u043a\u0438\u043c \u043a\u0430\u043a Nvidia GeForce RTX 3080. <\/p>\n<p>\u0414\u043b\u044f Nvidia GeForce RTX 3080 \u043d\u0435\u0442 \u0434\u043e\u0441\u0442\u0443\u043f\u043d\u044b\u0445 \u0432\u0430\u0440\u0438\u0430\u043d\u0442\u043e\u0432 \u043f\u043e\u0434\u043a\u043b\u044e\u0447\u0435\u043d\u0438\u044f \u043d\u0435\u0441\u043a\u043e\u043b\u044c\u043a\u0438\u0445 \u0433\u0440\u0430\u0444\u0438\u0447\u0435\u0441\u043a\u0438\u0445 \u043f\u0440\u043e\u0446\u0435\u0441\u0441\u043e\u0440\u043e\u0432 \u0441 \u043f\u043e\u043c\u043e\u0449\u044c\u044e NVLink. \u0412 \u0432\u0430\u0448\u0435\u0439 \u0441\u0438\u0441\u0442\u0435\u043c\u0435 \u043e\u0434\u043d\u043e\u0432\u0440\u0435\u043c\u0435\u043d\u043d\u043e \u043c\u043e\u0436\u043d\u043e \u0438\u0441\u043f\u043e\u043b\u044c\u0437\u043e\u0432\u0430\u0442\u044c \u0442\u043e\u043b\u044c\u043a\u043e \u043e\u0434\u043d\u0443 \u0432\u0438\u0434\u0435\u043e\u043a\u0430\u0440\u0442\u0443 Nvidia GeForce RTX 3080. \u042d\u0442\u043e \u0441\u0432\u044f\u0437\u0430\u043d\u043e \u0441 \u0442\u0435\u043c, \u0447\u0442\u043e RTX 3080 \u0438\u043c\u0435\u0435\u0442 \u0442\u043e\u043b\u044c\u043a\u043e \u043e\u0434\u0438\u043d \u0441\u043b\u043e\u0442 PCIe 16x \u0438 \u043d\u0435 \u0438\u043c\u0435\u0435\u0442 \u0434\u043e\u043f\u043e\u043b\u043d\u0438\u0442\u0435\u043b\u044c\u043d\u043e\u0433\u043e \u0440\u0430\u0437\u044a\u0435\u043c\u0430 NVLink. \u041f\u043e\u044d\u0442\u043e\u043c\u0443, \u0435\u0441\u043b\u0438 \u0432\u044b \u0445\u043e\u0442\u0438\u0442\u0435 \u0434\u043e\u0431\u0430\u0432\u0438\u0442\u044c \u0432 \u0441\u0432\u043e\u044e \u0441\u0438\u0441\u0442\u0435\u043c\u0443 \u0435\u0449\u0435 \u043e\u0434\u0438\u043d \u0433\u0440\u0430\u0444\u0438\u0447\u0435\u0441\u043a\u0438\u0439 \u043f\u0440\u043e\u0446\u0435\u0441\u0441\u043e\u0440, \u0432\u0430\u043c \u043d\u0443\u0436\u043d\u043e \u0431\u0443\u0434\u0435\u0442 \u0438\u0441\u043f\u043e\u043b\u044c\u0437\u043e\u0432\u0430\u0442\u044c \u0434\u0440\u0443\u0433\u043e\u0439 \u043c\u0435\u0442\u043e\u0434 \u043f\u043e\u0434\u043a\u043b\u044e\u0447\u0435\u043d\u0438\u044f, \u043d\u0430\u043f\u0440\u0438\u043c\u0435\u0440 \u0441\u043b\u043e\u0442\u044b PCIe x16 \u0438\u043b\u0438 \u043c\u043e\u0441\u0442\u044b SLI. \u041e\u0434\u043d\u0430\u043a\u043e \u0438\u043c\u0435\u0439\u0442\u0435 \u0432 \u0432\u0438\u0434\u0443, \u0447\u0442\u043e \u0438\u0441\u043f\u043e\u043b\u044c\u0437\u043e\u0432\u0430\u043d\u0438\u0435 \u043d\u0435\u0441\u043a\u043e\u043b\u044c\u043a\u0438\u0445 \u0433\u0440\u0430\u0444\u0438\u0447\u0435\u0441\u043a\u0438\u0445 \u043f\u0440\u043e\u0446\u0435\u0441\u0441\u043e\u0440\u043e\u0432 \u0432 \u043d\u0430\u0441\u0442\u0440\u043e\u0439\u043a\u0435 \u0438\u0433\u0440\u043e\u0432\u043e\u0433\u043e \u041f\u041a \u043d\u0435 \u0432\u0441\u0435\u0433\u0434\u0430 \u043c\u043e\u0436\u0435\u0442 \u043f\u0440\u0438\u0432\u0435\u0441\u0442\u0438 \u043a \u043f\u043e\u0432\u044b\u0448\u0435\u043d\u0438\u044e \u043f\u0440\u043e\u0438\u0437\u0432\u043e\u0434\u0438\u0442\u0435\u043b\u044c\u043d\u043e\u0441\u0442\u0438 \u043f\u043e \u0441\u0440\u0430\u0432\u043d\u0435\u043d\u0438\u044e \u0441 \u043e\u0434\u043d\u0438\u043c \u0432\u044b\u0441\u043e\u043a\u043e\u043f\u0440\u043e\u0438\u0437\u0432\u043e\u0434\u0438\u0442\u0435\u043b\u044c\u043d\u044b\u043c \u0433\u0440\u0430\u0444\u0438\u0447\u0435\u0441\u043a\u0438\u043c \u043f\u0440\u043e\u0446\u0435\u0441\u0441\u043e\u0440\u043e\u043c, \u0442\u0430\u043a\u0438\u043c \u043a\u0430\u043a Nvidia GeForce RTX 3080. <\/p>\n<p>\u0412\u0430\u0436\u043d\u043e \u043e\u0442\u043c\u0435\u0442\u0438\u0442\u044c, \u0447\u0442\u043e, \u0445\u043e\u0442\u044f \u0442\u0435\u0445\u043d\u043e\u043b\u043e\u0433\u0438\u044f NVLink \u043a\u043e\u0433\u0434\u0430-\u0442\u043e \u0431\u044b\u043b\u0430 \u043f\u043e\u043f\u0443\u043b\u044f\u0440\u043d\u043e\u0439 \u0444\u0443\u043d\u043a\u0446\u0438\u0435\u0439 \u0434\u043b\u044f \u0441\u043e\u0435\u0434\u0438\u043d\u0435\u043d\u0438\u044f \u043d\u0435\u0441\u043a\u043e\u043b\u044c\u043a\u0438\u0445 \u0432\u044b\u0441\u043e\u043a\u043e\u043f\u0440\u043e\u0438\u0437\u0432\u043e\u0434\u0438\u0442\u0435\u043b\u044c\u043d\u044b\u0445 \u0433\u0440\u0430\u0444\u0438\u0447\u0435\u0441\u043a\u0438\u0445 \u043f\u0440\u043e\u0446\u0435\u0441\u0441\u043e\u0440\u043e\u0432 \u0432 \u0441\u0438\u0441\u0442\u0435\u043c\u0435, \u043e\u043d\u0430 \u0431\u043e\u043b\u044c\u0448\u0435 \u043d\u0435 \u043f\u043e\u0434\u0434\u0435\u0440\u0436\u0438\u0432\u0430\u0435\u0442\u0441\u044f \u0431\u043e\u043b\u044c\u0448\u0438\u043d\u0441\u0442\u0432\u043e\u043c \u043f\u0440\u043e\u0438\u0437\u0432\u043e\u0434\u0438\u0442\u0435\u043b\u0435\u0439. \u0412 \u043f\u043e\u0441\u043b\u0435\u0434\u043d\u0438\u0435 \u0433\u043e\u0434\u044b \u043c\u043d\u043e\u0433\u0438\u0435 \u043f\u0440\u043e\u0438\u0437\u0432\u043e\u0434\u0438\u0442\u0435\u043b\u0438 \u0433\u0440\u0430\u0444\u0438\u0447\u0435\u0441\u043a\u0438\u0445 \u043f\u0440\u043e\u0446\u0435\u0441\u0441\u043e\u0440\u043e\u0432 \u043f\u0435\u0440\u0435\u043a\u043b\u044e\u0447\u0438\u043b\u0438\u0441\u044c \u043d\u0430 \u0440\u0435\u0448\u0435\u043d\u0438\u044f \u0441 \u043e\u0434\u043d\u0438\u043c \u0433\u0440\u0430\u0444\u0438\u0447\u0435\u0441\u043a\u0438\u043c \u043f\u0440\u043e\u0446\u0435\u0441\u0441\u043e\u0440\u043e\u043c, \u0430 \u043d\u0435 \u043d\u0430 \u043a\u043e\u043d\u0444\u0438\u0433\u0443\u0440\u0430\u0446\u0438\u0438 \u0441 \u043d\u0435\u0441\u043a\u043e\u043b\u044c\u043a\u0438\u043c\u0438 \u0433\u0440\u0430\u0444\u0438\u0447\u0435\u0441\u043a\u0438\u043c\u0438 \u043f\u0440\u043e\u0446\u0435\u0441\u0441\u043e\u0440\u0430\u043c\u0438 \u0438\u0437-\u0437\u0430 \u0443\u043b\u0443\u0447\u0448\u0435\u043d\u0438\u044f \u043f\u0440\u043e\u0438\u0437\u0432\u043e\u0434\u0438\u0442\u0435\u043b\u044c\u043d\u043e\u0441\u0442\u0438 \u043e\u0442\u0434\u0435\u043b\u044c\u043d\u044b\u0445 \u0433\u0440\u0430\u0444\u0438\u0447\u0435\u0441\u043a\u0438\u0445 \u043f\u0440\u043e\u0446\u0435\u0441\u0441\u043e\u0440\u043e\u0432 \u0438 \u043f\u0440\u043e\u0431\u043b\u0435\u043c, \u0441\u0432\u044f\u0437\u0430\u043d\u043d\u044b\u0445 \u0441 \u043f\u043e\u0434\u0434\u0435\u0440\u0436\u0430\u043d\u0438\u0435\u043c \u0441\u043e\u0432\u043c\u0435\u0441\u0442\u0438\u043c\u043e\u0441\u0442\u0438 \u043c\u0435\u0436\u0434\u0443 \u043d\u0435\u0441\u043a\u043e\u043b\u044c\u043a\u0438\u043c\u0438 \u0433\u0440\u0430\u0444\u0438\u0447\u0435\u0441\u043a\u0438\u043c\u0438 \u043f\u0440\u043e\u0446\u0435\u0441\u0441\u043e\u0440\u0430\u043c\u0438. \u0412 \u0440\u0435\u0437\u0443\u043b\u044c\u0442\u0430\u0442\u0435 NVLink \u0441\u0442\u0430\u043b \u043c\u0435\u043d\u0435\u0435 \u0430\u043a\u0442\u0443\u0430\u043b\u044c\u043d\u044b\u043c \u043d\u0430 \u0441\u043e\u0432\u0440\u0435\u043c\u0435\u043d\u043d\u043e\u043c \u0440\u044b\u043d\u043a\u0435 \u0438\u0433\u0440\u043e\u0432\u044b\u0445 \u041f\u041a. <\/p>\n<p>\u0422\u0430\u043a\u0438\u043c \u043e\u0431\u0440\u0430\u0437\u043e\u043c, Nvidia GeForce RTX 3080 \u043d\u0435 \u043f\u043e\u0434\u0434\u0435\u0440\u0436\u0438\u0432\u0430\u0435\u0442 \u0442\u0435\u0445\u043d\u043e\u043b\u043e\u0433\u0438\u044e NVLink, \u043f\u043e\u044d\u0442\u043e\u043c\u0443 \u0435\u0435 \u043d\u0435\u043b\u044c\u0437\u044f \u043f\u043e\u0434\u043a\u043b\u044e\u0447\u0438\u0442\u044c \u043a \u0434\u0440\u0443\u0433\u0438\u043c \u0433\u0440\u0430\u0444\u0438\u0447\u0435\u0441\u043a\u0438\u043c \u043f\u0440\u043e\u0446\u0435\u0441\u0441\u043e\u0440\u0430\u043c \u044d\u0442\u0438\u043c \u043c\u0435\u0442\u043e\u0434\u043e\u043c. \u0412\u043c\u0435\u0441\u0442\u043e \u044d\u0442\u043e\u0433\u043e \u0432\u0430\u043c \u0441\u043b\u0435\u0434\u0443\u0435\u0442 \u0438\u0437\u0443\u0447\u0438\u0442\u044c \u0430\u043b\u044c\u0442\u0435\u0440\u043d\u0430\u0442\u0438\u0432\u043d\u044b\u0435 \u043c\u0435\u0442\u043e\u0434\u044b, \u0442\u0430\u043a\u0438\u0435 \u043a\u0430\u043a \u0441\u043b\u043e\u0442\u044b SLI \u0438\u043b\u0438 PCIe x16, \u0434\u043b\u044f \u0441\u043e\u0435\u0434\u0438\u043d\u0435\u043d\u0438\u044f \u0434\u0432\u0443\u0445 \u0438\u043b\u0438 \u0431\u043e\u043b\u0435\u0435 \u0433\u0440\u0430\u0444\u0438\u0447\u0435\u0441\u043a\u0438\u0445 \u043f\u0440\u043e\u0446\u0435\u0441\u0441\u043e\u0440\u043e\u0432 Nvidia 3080 \u0432\u043c\u0435\u0441\u0442\u0435.<\/p>\n<\/div>\n<\/details>\n<ol start=\"2\">\n<li>\n<p>Write a program to recognize human speech and then write the result to a text file. <\/p>\n<\/li>\n<\/ol>\n<details class=\"spoiler\">\n<summary>Hidden text<\/summary>\n<div class=\"spoiler__content\">\n<p>To create a program that recognizes human speech and writes the result to a text file, we can use natural language processing techniques and Python programming language. Here is an example code using the speech_recognition library: <\/p>\n<pre><code class=\"python\">import speech_recognition as sr  # Initialize the recognizer r = sr.Recognizer()  # Set the audio source with sr.Microphone() as source:     print(\"Listening...\")     audio = r.listen(source)  # Recognize the speech try:     text = r.recognize_google(audio)     print(f\"You said: {text}\")      except Exception as e:     print(\"Sorry could not recognize your voice\")     text = \"\"  # Write the result to a text file with open('result.txt', 'w') as f:     f.write(text)  print(\"Done!\")<\/code><\/pre>\n<p>This code uses the speech_recognition library in Python to recognize speech from the user&#8217;s microphone input and convert it into text. The recognize_google function is used to perform the speech recognition using Google&#8217;s speech recognition API. The recognized text is then written to a text file named &#171;result.txt&#187;. Please note that this code assumes you have already installed the speech_recognition library using pip (pip install SpeechRecognition) and set up a Google Cloud Platform account to access the speech-to-text API.<\/p>\n<p>Please run this program on a system with a microphone connected to it. After running the program, it will listen for your voice<\/p>\n<\/div>\n<\/details>\n<\/div>\n<\/div>\n<\/div>\n<\/div>\n","protected":false},"author":1,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[],"tags":[],"class_list":["post-362712","post","type-post","status-publish","format-standard","hentry"],"_links":{"self":[{"href":"https:\/\/savepearlharbor.com\/index.php?rest_route=\/wp\/v2\/posts\/362712","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/savepearlharbor.com\/index.php?rest_route=\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/savepearlharbor.com\/index.php?rest_route=\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/savepearlharbor.com\/index.php?rest_route=\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/savepearlharbor.com\/index.php?rest_route=%2Fwp%2Fv2%2Fcomments&post=362712"}],"version-history":[{"count":0,"href":"https:\/\/savepearlharbor.com\/index.php?rest_route=\/wp\/v2\/posts\/362712\/revisions"}],"wp:attachment":[{"href":"https:\/\/savepearlharbor.com\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=362712"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/savepearlharbor.com\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=362712"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/savepearlharbor.com\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=362712"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}