{"id":4306,"date":"2024-07-16T11:36:55","date_gmt":"2024-07-16T03:36:55","guid":{"rendered":"https:\/\/www.aqwu.net\/wp\/?p=4306"},"modified":"2024-07-16T11:36:55","modified_gmt":"2024-07-16T03:36:55","slug":"%e6%9e%84%e5%bb%ba%e5%a4%a7%e5%9e%8b%e8%af%ad%e8%a8%80%e6%a8%a1%e5%9e%8b%ef%bc%88%e4%bb%8e%e5%a4%b4%e5%bc%80%e5%a7%8b%ef%bc%89","status":"publish","type":"post","link":"https:\/\/www.aqwu.net\/wp\/?p=4306","title":{"rendered":"\u6784\u5efa\u5927\u578b\u8bed\u8a00\u6a21\u578b\uff08\u4ece\u5934\u5f00\u59cb\uff09"},"content":{"rendered":"\n<p><strong>\u901a\u8fc7\u4ece\u5934\u5f00\u59cb\u6784\u5efa\u4e00\u4e2a\u5927\u578b\u8bed\u8a00\u6a21\u578b\uff0c\u4e86\u89e3\u5982\u4f55\u521b\u5efa\u3001\u8bad\u7ec3\u548c\u8c03\u6574\u5927\u578b\u8bed\u8a00\u6a21\u578b \uff08LLMs\uff09\uff01<\/strong><\/p>\n\n\n\n<p>\u5728\u6784\u5efa\u5927\u578b\u8bed\u8a00\u6a21\u578b\uff08\u4ece\u5934\u5f00\u59cb\uff09\u4e2d\uff0c\u4f60\u5c06\u4e86\u89e3\u5982\u4f55LLMs\u4ece\u5185\u5230\u5916\u5de5\u4f5c\u3002\u5728\u8fd9\u672c\u5bcc\u6709\u6d1e\u5bdf\u529b\u7684\u4e66\u4e2d\uff0c\u7545\u9500\u4e66\u4f5c\u5bb6\u585e\u5df4\u65af\u8482\u5b89\u00b7\u62c9\u65bd\u5361 \uff08Sebastian Raschka\uff09 \u5c06\u6307\u5bfc\u60a8\u9010\u6b65\u521b\u5efa\u81ea\u5df1\u7684 LLM\uff0c\u7528\u6e05\u6670\u7684\u6587\u5b57\u3001\u56fe\u8868\u548c\u793a\u4f8b\u89e3\u91ca\u6bcf\u4e2a\u9636\u6bb5\u3002\u60a8\u5c06\u4ece\u6700\u521d\u7684\u8bbe\u8ba1\u548c\u521b\u5efa\u5230\u901a\u7528\u8bed\u6599\u5e93\u7684\u9884\u8bad\u7ec3\uff0c\u4e00\u76f4\u5230\u7279\u5b9a\u4efb\u52a1\u7684\u5fae\u8c03\u3002<\/p>\n\n\n\n<p>\u6784\u5efa\u5927\u578b\u8bed\u8a00\u6a21\u578b\uff08\u4ece\u5934\u5f00\u59cb\uff09\u6559\u4f60\u5982\u4f55\uff1a<\/p>\n\n\n\n<ul class=\"wp-block-list\">\n<li>\u89c4\u5212\u548c\u7f16\u7801 LLM \u7684\u6240\u6709\u90e8\u5206<\/li>\n\n\n\n<li>\u51c6\u5907\u9002\u5408 LLM \u8bad\u7ec3\u7684\u6570\u636e\u96c6<\/li>\n\n\n\n<li>\u5fae\u8c03 LLM \u4ee5\u8fdb\u884c\u6587\u672c\u5206\u7c7b\u548c\u60a8\u81ea\u5df1\u7684\u6570\u636e<\/li>\n\n\n\n<li>\u5e94\u7528\u6307\u4ee4\u8c03\u6574\u6280\u672f\uff0c\u4ee5\u786e\u4fdd\u60a8\u7684 LLM \u9075\u5faa\u6307\u4ee4<\/li>\n\n\n\n<li>\u5c06\u9884\u8bad\u7ec3\u6743\u91cd\u52a0\u8f7d\u5230 LLM \u4e2d<\/li>\n<\/ul>\n\n\n\n<p>\u4e3a ChatGPT\u3001Bard \u548c Copilot \u7b49\u5c16\u7aef AI \u5de5\u5177\u63d0\u4f9b\u652f\u6301\u7684\u5927\u578b\u8bed\u8a00\u6a21\u578b \uff08LLM\uff09 \u4f3c\u4e4e\u662f\u4e00\u4e2a\u5947\u8ff9\uff0c\u4f46\u5b83\u4eec\u5e76\u4e0d\u662f\u9b54\u672f\u3002\u672c\u4e66\u901a\u8fc7\u5e2e\u52a9\u60a8\u4ece\u5934\u5f00\u59cb\u6784\u5efa\u81ea\u5df1\u7684 LLM \u6765\u63ed\u5f00 LLM \u7684\u795e\u79d8\u9762\u7eb1\u3002\u60a8\u5c06\u83b7\u5f97\u5bf9 LLM \u5982\u4f55\u5de5\u4f5c\u7684\u72ec\u7279\u800c\u6709\u4ef7\u503c\u7684\u89c1\u89e3\uff0c\u5b66\u4e60\u5982\u4f55\u8bc4\u4f30\u5b83\u4eec\u7684\u8d28\u91cf\uff0c\u5e76\u638c\u63e1\u5177\u4f53\u7684\u6280\u672f\u6765\u5fae\u8c03\u548c\u6539\u8fdb\u5b83\u4eec\u3002<\/p>\n\n\n\n<p>\u5728\u672c\u4e66\u4e2d\uff0c\u4f60\u7528\u6765\u8bad\u7ec3\u548c\u5f00\u53d1\u4f60\u81ea\u5df1\u7684\u5c0f\u800c\u5b9e\u7528\u7684\u6a21\u578b\u7684\u8fc7\u7a0b\u9075\u5faa\u4e0e\u4ea4\u4ed8 GPT-4 \u7b49\u5927\u89c4\u6a21\u57fa\u7840\u6a21\u578b\u76f8\u540c\u7684\u6b65\u9aa4\u3002\u60a8\u7684\u5c0f\u89c4\u6a21 LLM \u53ef\u4ee5\u5728\u666e\u901a\u7b14\u8bb0\u672c\u7535\u8111\u4e0a\u5f00\u53d1\uff0c\u60a8\u53ef\u4ee5\u5c06\u5176\u7528\u4f5c\u81ea\u5df1\u7684\u4e2a\u4eba\u52a9\u7406\u3002<\/p>\n\n\n\n<h2 class=\"wp-block-heading\">\u5173\u4e8e\u672c\u4e66<\/h2>\n\n\n\n<p><em>Build a Large Language Model \uff08from Scratch\uff09<\/em>\u00a0\u662f\u4e00\u672c\u72ec\u4e00\u65e0\u4e8c\u7684\u6307\u5357\uff0c\u7528\u4e8e\u6784\u5efa\u81ea\u5df1\u7684\u5de5\u4f5c LLM\u3002\u5728\u8fd9\u7bc7\u6587\u7ae0\u4e2d\uff0c\u673a\u5668\u5b66\u4e60\u4e13\u5bb6\u517c\u4f5c\u5bb6\u585e\u5df4\u65af\u8482\u5b89\u00b7\u62c9\u65bd\u5361\uff08Sebastian Raschka\uff09\u63ed\u793a\u4e86LLM\u662f\u5982\u4f55\u5728\u5f15\u64ce\u76d6\u4e0b\u5de5\u4f5c\u7684\uff0c\u63ed\u5f00\u4e86\u751f\u6210\u5f0f\u4eba\u5de5\u667a\u80fd\u9ed1\u5323\u5b50\u7684\u76d6\u5b50\u3002\u672c\u4e66\u5145\u6ee1\u4e86\u6784\u5efa LLM \u7684\u5b9e\u7528\u89c1\u89e3\uff0c\u5305\u62ec\u6784\u5efa\u6570\u636e\u52a0\u8f7d\u7ba1\u9053\u3001\u7ec4\u88c5\u5176\u5185\u90e8\u6784\u5efa\u5757\u548c\u5fae\u8c03\u6280\u672f\u3002\u5728\u6b64\u8fc7\u7a0b\u4e2d\uff0c\u60a8\u5c06\u9010\u6e10\u5c06\u57fa\u7840\u6a21\u578b\u8f6c\u53d8\u4e3a\u6587\u672c\u5206\u7c7b\u5668\u5de5\u5177\uff0c\u4ee5\u53ca\u9075\u5faa\u5bf9\u8bdd\u8bf4\u660e\u7684\u804a\u5929\u673a\u5668\u4eba\u3002<\/p>\n\n\n\n<h2 class=\"wp-block-heading\">\u5173\u4e8e\u8bfb\u8005<\/h2>\n\n\n\n<p>\u5bf9\u4e8e\u4e86\u89e3 Python \u7684\u8bfb\u8005\u3002\u5f00\u53d1\u673a\u5668\u5b66\u4e60\u6a21\u578b\u7684\u7ecf\u9a8c\u5f88\u6709\u7528\uff0c\u4f46\u4e0d\u662f\u5fc5\u9700\u7684\u3002<\/p>\n\n\n\n<h2 class=\"wp-block-heading\">\u5173\u4e8e\u4f5c\u8005<\/h2>\n\n\n\n<p><strong>\u585e\u5df4\u65af\u8482\u5b89\u00b7\u62c9\u65bd\u5361\uff08Sebastian Raschka<\/strong>\uff09\u5341\u591a\u5e74\u6765\u4e00\u76f4\u4ece\u4e8b\u673a\u5668\u5b66\u4e60\u548c\u4eba\u5de5\u667a\u80fd\u65b9\u9762\u7684\u5de5\u4f5c\u3002Sebastian \u4e8e 2022 \u5e74\u52a0\u5165 Lightning AI\uff0c\u73b0\u5728\u4e13\u6ce8\u4e8e AI \u548c LLM \u7814\u7a76\u3001\u5f00\u53d1\u5f00\u6e90\u8f6f\u4ef6\u548c\u521b\u5efa\u6559\u80b2\u6750\u6599\u3002\u5728\u6b64\u4e4b\u524d\uff0cSebastian\u66fe\u5728\u5a01\u65af\u5eb7\u661f\u5927\u5b66\u9ea6\u8fea\u900a\u5206\u6821\u62c5\u4efb\u7edf\u8ba1\u7cfb\u52a9\u7406\u6559\u6388\uff0c\u4e13\u6ce8\u4e8e\u6df1\u5ea6\u5b66\u4e60\u548c\u673a\u5668\u5b66\u4e60\u7814\u7a76\u3002\u4ed6\u5bf9\u6559\u80b2\u6709\u7740\u5f3a\u70c8\u7684\u70ed\u60c5\uff0c\u6700\u51fa\u540d\u7684\u662f\u4ed6\u5173\u4e8e\u4f7f\u7528\u5f00\u6e90\u8f6f\u4ef6\u8fdb\u884c\u673a\u5668\u5b66\u4e60\u7684\u7545\u9500\u4e66\u3002<\/p>\n\n\n\n<p>\u539f\u6587\u7535\u5b50\u4e66\u8d2d\u4e70\u94fe\u63a5\uff1a<a href=\"https:\/\/www.manning.com\/books\/build-a-large-language-model-from-scratch\">Build a Large Language Model (From Scratch) (manning.com)<\/a><\/p>\n\n\n\n<p>\u6e90\u4ee3\u7801\u94fe\u63a5\uff1a<a href=\"https:\/\/github.com\/rasbt\/LLMs-from-scratch?tab=readme-ov-file\">rasbt\/LLMs-from-scratch: Implementing a ChatGPT-like LLM in PyTorch from scratch, step by step (github.com)<\/a><\/p>\n\n\n\n<p><\/p>\n","protected":false},"excerpt":{"rendered":"<p>\u901a\u8fc7\u4ece\u5934\u5f00\u59cb\u6784\u5efa\u4e00\u4e2a\u5927\u578b\u8bed\u8a00\u6a21\u578b\uff0c\u4e86\u89e3\u5982\u4f55\u521b\u5efa\u3001\u8bad\u7ec3\u548c\u8c03\u6574\u5927\u578b\u8bed\u8a00\u6a21\u578b \uff08LLMs\uff09\uff01 \u5728\u6784\u5efa\u5927\u578b\u8bed\u8a00\u6a21\u578b\uff08\u4ece [&hellip;]<\/p>\n","protected":false},"author":1,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"site-sidebar-layout":"default","site-content-layout":"","ast-site-content-layout":"default","site-content-style":"default","site-sidebar-style":"default","ast-global-header-display":"","ast-banner-title-visibility":"","ast-main-header-display":"","ast-hfb-above-header-display":"","ast-hfb-below-header-display":"","ast-hfb-mobile-header-display":"","site-post-title":"","ast-breadcrumbs-content":"","ast-featured-img":"","footer-sml-layout":"","theme-transparent-header-meta":"","adv-header-id-meta":"","stick-header-meta":"","header-above-stick-meta":"","header-main-stick-meta":"","header-below-stick-meta":"","astra-migrate-meta-layouts":"set","ast-page-background-enabled":"default","ast-page-background-meta":{"desktop":{"background-color":"var(--ast-global-color-4)","background-image":"","background-repeat":"repeat","background-position":"center center","background-size":"auto","background-attachment":"scroll","background-type":"","background-media":"","overlay-type":"","overlay-color":"","overlay-opacity":"","overlay-gradient":""},"tablet":{"background-color":"","background-image":"","background-repeat":"repeat","background-position":"center center","background-size":"auto","background-attachment":"scroll","background-type":"","background-media":"","overlay-type":"","overlay-color":"","overlay-opacity":"","overlay-gradient":""},"mobile":{"background-color":"","background-image":"","background-repeat":"repeat","background-position":"center center","background-size":"auto","background-attachment":"scroll","background-type":"","background-media":"","overlay-type":"","overlay-color":"","overlay-opacity":"","overlay-gradient":""}},"ast-content-background-meta":{"desktop":{"background-color":"var(--ast-global-color-5)","background-image":"","background-repeat":"repeat","background-position":"center center","background-size":"auto","background-attachment":"scroll","background-type":"","background-media":"","overlay-type":"","overlay-color":"","overlay-opacity":"","overlay-gradient":""},"tablet":{"background-color":"var(--ast-global-color-5)","background-image":"","background-repeat":"repeat","background-position":"center center","background-size":"auto","background-attachment":"scroll","background-type":"","background-media":"","overlay-type":"","overlay-color":"","overlay-opacity":"","overlay-gradient":""},"mobile":{"background-color":"var(--ast-global-color-5)","background-image":"","background-repeat":"repeat","background-position":"center center","background-size":"auto","background-attachment":"scroll","background-type":"","background-media":"","overlay-type":"","overlay-color":"","overlay-opacity":"","overlay-gradient":""}},"_jetpack_memberships_contains_paid_content":false,"footnotes":""},"categories":[444,443,442],"tags":[242,314],"class_list":["post-4306","post","type-post","status-publish","format-standard","hentry","category-ai","category-llm","category-llms","tag-chatgpt","tag-openai-api"],"views":2440,"jetpack_sharing_enabled":true,"jetpack_featured_media_url":"","_links":{"self":[{"href":"https:\/\/www.aqwu.net\/wp\/index.php?rest_route=\/wp\/v2\/posts\/4306","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.aqwu.net\/wp\/index.php?rest_route=\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.aqwu.net\/wp\/index.php?rest_route=\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.aqwu.net\/wp\/index.php?rest_route=\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/www.aqwu.net\/wp\/index.php?rest_route=%2Fwp%2Fv2%2Fcomments&post=4306"}],"version-history":[{"count":1,"href":"https:\/\/www.aqwu.net\/wp\/index.php?rest_route=\/wp\/v2\/posts\/4306\/revisions"}],"predecessor-version":[{"id":4307,"href":"https:\/\/www.aqwu.net\/wp\/index.php?rest_route=\/wp\/v2\/posts\/4306\/revisions\/4307"}],"wp:attachment":[{"href":"https:\/\/www.aqwu.net\/wp\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=4306"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.aqwu.net\/wp\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=4306"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.aqwu.net\/wp\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=4306"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}