{"id":18503,"date":"2024-08-23T09:52:18","date_gmt":"2024-08-23T01:52:18","guid":{"rendered":"https:\/\/www.1ai.net\/?p=18503"},"modified":"2024-08-23T09:50:41","modified_gmt":"2024-08-23T01:50:41","slug":"www-lezaiyun-com","status":"publish","type":"post","link":"https:\/\/www.1ai.net\/en\/18503.html","title":{"rendered":"NVIDIA releases new AI model with 8 billion parameters: high accuracy and efficiency, deployable on RTX workstations"},"content":{"rendered":"<p><a href=\"https:\/\/www.1ai.net\/en\/tag\/%e8%8b%b1%e4%bc%9f%e8%be%be\" title=\"Look at the article with the label\" target=\"_blank\" >Nvidia<\/a>In a blog post on August 21st, the Mistral-NeMo-Minitron 8B small-language AI model was released, with the advantages of high accuracy and computational efficiency.<strong>The model can be run on GPU-accelerated data centers, clouds, and workstations.<\/strong><\/p>\n<p>NVIDIA and Mistral AI released last month<a href=\"https:\/\/www.1ai.net\/en\/tag\/%e5%bc%80%e6%ba%90\" title=\"[View articles tagged with [open source]]\" target=\"_blank\" >Open Source<\/a> The Mistral NeMo 12B model, on which NVIDIA is building, is back with the smaller Mistral-NeMo-Minitron 8B model, with 8 billion parameters, which can be run on workstations with NVIDIA RTX graphics cards.<\/p>\n<p><img loading=\"lazy\" decoding=\"async\" class=\"alignnone size-full wp-image-18521\" title=\"d48d99b3j00sineb3004fd001z4011qm\" src=\"https:\/\/www.1ai.net\/wp-content\/uploads\/2024\/08\/d48d99b3j00sineb3004fd001z4011qm.jpg\" alt=\"d48d99b3j00sineb3004fd001z4011qm\" width=\"2560\" height=\"1358\" \/><\/p>\n<p>NVIDIA says that Mistral-NeMo-Minitron 8B was obtained by width-pruning Mistral NeMo 12B and mildly retraining it with knowledge distillation, as published in Compact Language Models via Pruning and Knowledge Distillation\".<\/p>\n<p>Cuts reduce the neural network by removing model weights that contribute the least to accuracy. During the \"distillation\" process, the team retrained the after-cutting model on a small data set to significantly improve the accuracy rate reduced by the cutting process\u3002<\/p>\n<p>For its size, the Mistral-NeMo-Minitron 8B leads the pack in nine popular benchmarks for language modeling. These benchmarks cover a wide range of tasks, including language comprehension, common-sense reasoning, mathematical reasoning, summarization, coding, and the ability to generate authentic answers.<\/p>","protected":false},"excerpt":{"rendered":"<p>NVIDIA released the Mistral-NeMo-Minitron 8B small-language AI model in a blog post on August 21st, featuring high accuracy and computational efficiency to run the model on GPU-accelerated data centers, clouds and workstations. Building on the open-source Mistral NeMo 12B model released last month by NVIDIA and Mistral AI, NVIDIA is releasing a smaller Mistral-NeMo-Minitron 8B model with 8 billion parameters that can run on workstations with NVIDIA RTX graphics cards. NVIDIA said that by width-pruning the Mistral NeMo<\/p>","protected":false},"author":1,"featured_media":0,"comment_status":"closed","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[146],"tags":[167,219,239],"collection":[],"class_list":["post-18503","post","type-post","status-publish","format-standard","hentry","category-news","tag-ai","tag-219","tag-239"],"acf":[],"_links":{"self":[{"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/posts\/18503","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/comments?post=18503"}],"version-history":[{"count":0,"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/posts\/18503\/revisions"}],"wp:attachment":[{"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/media?parent=18503"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/categories?post=18503"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/tags?post=18503"},{"taxonomy":"collection","embeddable":true,"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/collection?post=18503"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}