{"id":12787,"date":"2022-09-28T12:57:23","date_gmt":"2022-09-28T16:57:23","guid":{"rendered":"https:\/\/www.predictiveanalyticsworld.com\/machinelearningtimes\/?p=12787"},"modified":"2022-09-28T12:57:23","modified_gmt":"2022-09-28T16:57:23","slug":"productizing-large-language-models","status":"publish","type":"post","link":"https:\/\/www.predictiveanalyticsworld.com\/machinelearningtimes\/productizing-large-language-models\/12787\/","title":{"rendered":"Productizing Large Language Models"},"content":{"rendered":"Originally posted on Replit.com, Sept 21, 2022.\u00a0 Large Language Models (LLMs) are known for their near-magical ability to learn from very few examples &#8212; as little as zero &#8212; to create language wonders. LLMs can chat, write poetry, write code, and even do basic\u00a0arithmetic. However, the same properties that make LLMs magical also make them challenging from an engineering perspective. At Replit we have deployed transformer-based language models of all sizes: ~100m parameter models for search and spam, 1-10B models for a code autocomplete product we call\u00a0GhostWriter, and 100B+ models for features that require a higher reasoning ability. <a href=\"https:\/\/www.predictiveanalyticsworld.com\/machinelearningtimes\/productizing-large-language-models\/12787\/\" class=\"more-link\">(more&hellip;)<\/a>","protected":false},"excerpt":{"rendered":"<p>Originally posted on Replit.com, Sept 21, 2022.\u00a0 Large Language Models (LLMs) are known for their near-magical ability to learn from very few examples &#8212; as little as zero &#8212; to create language wonders. LLMs can chat, write poetry, write code, and even do basic\u00a0arithmetic. However, the same properties that make LLMs magical also make them [&hellip;]<\/p>\n","protected":false},"author":72,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":"","_links_to":"","_links_to_target":""},"categories":[11,48],"tags":[230,791,1198,1267,1268,243,8],"class_list":["post-12787","post","type-post","status-publish","format-standard","hentry","category-industry-news","category-left-hand","tag-data-analytics","tag-deep-learning","tag-language-models","tag-large-language-models","tag-llm","tag-machine-learning","tag-predictive-analytics"],"_links":{"self":[{"href":"https:\/\/www.predictiveanalyticsworld.com\/machinelearningtimes\/wp-json\/wp\/v2\/posts\/12787","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.predictiveanalyticsworld.com\/machinelearningtimes\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.predictiveanalyticsworld.com\/machinelearningtimes\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.predictiveanalyticsworld.com\/machinelearningtimes\/wp-json\/wp\/v2\/users\/72"}],"replies":[{"embeddable":true,"href":"https:\/\/www.predictiveanalyticsworld.com\/machinelearningtimes\/wp-json\/wp\/v2\/comments?post=12787"}],"version-history":[{"count":1,"href":"https:\/\/www.predictiveanalyticsworld.com\/machinelearningtimes\/wp-json\/wp\/v2\/posts\/12787\/revisions"}],"predecessor-version":[{"id":12788,"href":"https:\/\/www.predictiveanalyticsworld.com\/machinelearningtimes\/wp-json\/wp\/v2\/posts\/12787\/revisions\/12788"}],"wp:attachment":[{"href":"https:\/\/www.predictiveanalyticsworld.com\/machinelearningtimes\/wp-json\/wp\/v2\/media?parent=12787"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.predictiveanalyticsworld.com\/machinelearningtimes\/wp-json\/wp\/v2\/categories?post=12787"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.predictiveanalyticsworld.com\/machinelearningtimes\/wp-json\/wp\/v2\/tags?post=12787"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}