{"id":2047,"date":"2023-12-18T09:38:33","date_gmt":"2023-12-18T01:38:33","guid":{"rendered":"https:\/\/www.1ai.net\/?p=2047"},"modified":"2023-12-18T09:38:33","modified_gmt":"2023-12-18T01:38:33","slug":"%e9%98%bf%e9%87%8c%e9%80%9a%e4%b9%89%e5%8d%83%e9%97%ae1-8b%e8%b6%85%e8%bf%b7%e4%bd%a0%e5%a4%a7%e6%a8%a1%e5%9e%8b%ef%bc%8c5%e5%b9%b4%e5%89%8d%e7%9a%84%e8%80%81%e7%94%b5%e8%84%91%e4%b9%9f%e5%8f%af","status":"publish","type":"post","link":"https:\/\/www.1ai.net\/en\/2047.html","title":{"rendered":"Alitong Yi Qianwen 1.8B super mini model, even a 5-year-old computer can play it"},"content":{"rendered":"

\u6211\u6700\u8fd1\uff0c\u5bf9\u5c0f\u5c3a\u5bf8AI\u5927\u6a21\u578b<\/strong>\u6bd4\u8f83\u611f\u5174\u8da3\u3002\u4e4b\u524d\u56fd\u5185\u5916\u79d1\u6280\u516c\u53f8\u5728\u5927\u6a21\u578b\u9886\u57df\uff0c\u4e00\u822c\u662f\u4e0d\u65ad\u589e\u52a0\u6a21\u578b\u53c2\u6570\u6765\u589e\u5f3a\u6a21\u578b\u80fd\u529b\uff0c\u4ece7\u4ebf\u300113\u4ebf\u300170\u4ebf\u751a\u81f3200\u4ebf\u4ee5\u4e0a\uff0c\u786e\u5b9e\u8d8a\u6765\u8d8a\u5f3a\uff0c\u4f46\u8fd9\u4e5f\u4f1a\u8ba9\u5927\u5bb6\u81ea\u5df1\u5bb6\u7684\u7535\u8111\u57fa\u672c\u8dd1\u4e0d\u52a8\u3002<\/p>\n

\"640\"<\/p>\n

\u8fd1\u671f\uff0c\u5fae\u8f6f\u53d1\u5e03\u4e86\u53ea\u67092.7\u4ebf\u53c2\u6570\u7684Phi-2<\/strong>\u5927\u6a21\u578b<\/strong>\uff0c\u963f\u91cc\u4e5f\u53d1\u5e03\u4e86\u53ea\u67091.8\u4ebf\u53c2\u6570\u7684\u901a\u4e49\u5343\u95ee<\/a>\u8d85\u8ff7\u4f60\u5927\u6a21\u578b<\/a><\/strong>\u3002\u8fd9\u4e9b\u5c0f\u5c3a\u5bf8\u7684\u5927\u6a21\u578b\uff0c\u4e0d\u4f46\u5728\u6027\u80fd\u8bc4\u6d4b\u4e0a\uff0c\u8d85\u8fc7\u4e86\u4e00\u4e9b7\u4ebf\u751a\u81f313\u4ebf\u53c2\u6570\u7684\u5927\u6a21\u578b\uff0c\u800c\u4e14\u56e0\u4e3a\u5c3a\u5bf8\u5c0f\uff0c\u57fa\u672c\u90fd\u53ef\u4ee5\u57283G\u4ee5\u4e0b\u663e\u5b58\u751a\u81f3CPU\u6a21\u5f0f\u4e0b\u5feb\u901f\u8fd0\u884c\uff0c\u8fd9\u6837\u4e00\u6765\uff0c5\u5e74\u524d\u7684\u8001\u7535\u8111\u4e5f\u53ef\u4ee5\u73a9\u4e86<\/strong>\u3002\u4eca\u5929\u5206\u4eab\u4e00\u4e2a\u901a\u4e49\u5343\u95ee1.8B\u8d85\u8ff7\u4f60\u5927\u6a21\u578b\u7684\u61d2\u4eba\u5305<\/strong>\uff0c\u8d76\u5feb\u968f\u6211\u53bb\u770b\u770b\u5427~<\/p>\n

\u901a\u4e49\u5343\u95ee1.8B\u5927\u6a21\u578b<\/strong>\u7b80\u4ecb<\/strong><\/h2>\n
Qwen\u7cfb\u5217\uff0c\u73b0\u5728\u5305\u62ecQwen\u57fa\u7840\u8bed\u8a00\u6a21\u578b\uff0c\u5373Qwen-1.8B\uff0cQwen-7B\uff0cQwen-14B\u548cQwen-72B\u3002\u4ee5\u53caQwen-Chat\u804a\u5929\u6a21\u578b\uff0c\u5373Qwen-1.8B -\u804a\u5929\u3001Qwen-7B-\u804a\u5929\u3001Qwen-14B-\u804a\u5929\u548cQwen-72B-\u804a\u5929\u3002<\/section>\n
\"640-3\"<\/section>\n
Qwen<\/strong>\u5927\u6a21\u578b\u62e5\u6709\u5f3a\u5927\u7684\u57fa\u7840\u8bed\u8a00\u6a21\u578b\uff0c\u9488\u5bf9\u591a\u8fbe 3 \u4e07\u4ebf\u4e2a token \u7684\u591a\u8bed\u8a00\u6570\u636e\u8fdb\u884c\u4e86\u7a33\u5b9a\u7684\u9884\u8bad\u7ec3\uff0c\u8986\u76d6\u9886\u57df\u3001\u8bed\u8a00\uff08\u91cd\u70b9\u662f\u4e2d\u6587\u548c\u82f1\u6587\uff09\u7b49\uff0c\u80fd\u591f\u5b9e\u73b0\u6709\u7ade\u4e89\u529b\u7684\u57fa\u51c6\u6570\u636e\u96c6\u4e0a\u7684\u6027\u80fd\u3002\u6b64\u5916\uff0c\u8fd8\u6709\u57fa\u4e8eSFT\u548cRLHF\uff08\u5c1a\u672a\u53d1\u5e03\uff09\u7684\u7b26\u5408\u4eba\u7c7b\u504f\u597d\u7684\u804a\u5929\u6a21\u578b\uff0c\u80fd\u591f\u804a\u5929\u3001\u521b\u5efa\u5185\u5bb9\u3001\u63d0\u53d6\u4fe1\u606f\u3001\u603b\u7ed3\u3001\u7ffb\u8bd1\u3001\u7f16\u7801\u3001\u89e3\u51b3\u6570\u5b66\u95ee\u9898\u7b49\uff0c\u5e76\u4e14\u80fd\u591f\u4f7f\u7528\u5de5\u5177\uff0c\u626e\u6f14\u4ee3\u7406\uff0c\u751a\u81f3\u626e\u6f14\u4ee3\u7801\u89e3\u91ca\u5668\u7b49\u3002<\/section>\n
\u800c\u4eca\u5929\u4ecb\u7ecd\u7684Qwen-1.8B\u5927\u6a21\u578b<\/strong>\uff0c\u53ea\u9700\u89812.9GB\u7684\u663e\u5b58\u5373\u53ef\u8fd0\u884c\uff0c\u6362\u53e5\u8bdd\u8bf45\u5e74\u524d\u7684\u663e\u5361\u90fd\u53ef\u4ee5\u73a9\uff0c\u8d76\u7d27\u4e0b\u8f7d\u61d2\u4eba\u5305\uff0c\u5728\u672c\u5730\u62e5\u6709\u4e00\u4e2aAI\u52a9\u624b\u5427~<\/section>\n

\u79bb\u7ebf\u61d2\u4eba\u5305\u6765\u4e86<\/strong><\/h2>\n

\u8001\u89c4\u77e9\uff0c\u5927\u5bb6\u81ea\u884c\u5728\u672c\u5730\u90e8\u7f72\u6bd4\u8f83\u9ebb\u70e6\uff0c\u5df2\u7ecf\u4e3a\u7403\u53cb\u5927\u5bb6\u5236\u4f5c\u597d\u4e86\u4e00\u6b3e\u79bb\u7ebf\u6574\u5408\u5305\u4e86\uff0c\u4e0b\u8f7d\u5230\u672c\u5730\u89e3\u538b\u5373\u7528\u3002<\/p>\n

\u5927\u5bb6\u4e0b\u8f7d\u89e3\u538b\u5230\u672c\u5730\u3002<\/p>\n

\u2460\u53cc\u51fb\u201c\u4e00\u952e\u542f\u52a8-Qwen_1.8B.exe<\/strong>\u201d\u3002<\/p>\n

\u2461\u53cc\u51fb\u4e00\u952e\u542f\u52a8\u7a0b\u5e8f\u540e\uff0c\u4f1a\u6253\u5f00\u4e00\u4e2a\u547d\u4ee4\u63d0\u793a\u7a97\u53e3\uff0c\u9879\u76ee\u4f1a\u81ea\u52a8\u8fd0\u884c\u3002\u52a0\u8f7d\u6210\u529f\u540e\uff0c\u8bf7\u81ea\u884c\u590d\u5236\u4ee5\u4e0b\u7f51\u5740\u5728\u6d4f\u89c8\u5668\u6253\u5f00\u201c http:\/\/127.0.0.1:8000\/\u201d\u3002<\/p>\n

\"640-4\"<\/p>\n

\u2462\u6253\u5f00\u94fe\u63a5\u540e\uff0c\u53ef\u4ee5\u770b\u5230Qwen-1.8B\u5927\u6a21\u578b\u53ef\u89c6\u5316\u804a\u5929<\/strong>\u4e3b\u754c\u9762\uff1a<\/p>\n

\"640-5\"<\/p>\n

\u754c\u9762\u6211\u5df2\u7ecf\u4e3a\u5927\u5bb6\u6c49\u5316\u597d\u4e86~\u4f7f\u7528\u975e\u5e38\u7b80\u5355\uff0c\u53ef\u4ee5\u8bf4\u662f10\u79d2\u4e0a\u624b:<\/p>\n

    \n
  1. \u8f93\u5165\u63d0\u793a\u8bcd\uff1a\u5728\u201cinput\u201d\u533a\u57df\uff0c\u76f4\u63a5\u8f93\u5165\u63d0\u793a\u8bcd<\/li>\n
  2. \u53d1\u9001\uff1a\u70b9\u51fb\u201cSubmit\uff08\u53d1\u9001\uff09\u201d\u6309\u94ae<\/li>\n<\/ol>\n

    \u7b49\u5f85\u7247\u523b\uff0c\u5373\u53ef\u5f97\u5230\u901a\u4e49\u5343\u95ee1.8B\u5927\u6a21\u578b\u7ed9\u4f60\u7684\u56de\u590d\u4e86\uff1a<\/p>\n

    \"640-6\"<\/p>\n

    \u4ece\u6211\u81ea\u5df1\u7684\u4f53\u9a8c\u6765\u770b\uff0c\u53cd\u5e94\u975e\u5e38\u8fc5\u901f\uff0c\u56de\u7b54\u4e5f\u6bd4\u8f83\u9760\u8c31\uff0c\u5927\u5bb6\u53ef\u4ee5\u81ea\u884c\u53bb\u5c1d\u8bd5\u4e00\u4e0b~<\/p>\n

    \u6ce8\u610f\u4e8b\u9879\uff1a<\/p>\n

    \u2460\u8be5\u9879\u76ee\u5efa\u8bae\u4f7f\u7528\u82f1\u4f1f\u8fbe\u663e\u5361\u8fd0\u884c\uff0c\u53ea\u9700\u89813G\u663e\u5b58\uff0cCPU\u4e5f\u80fd\u8fd0\u884c\uff0c\u4f46\u504f\u6162<\/p>\n

    \u2461\u8bf7\u786e\u4fdd\u5b89\u88c5\u8def\u5f84\u4e0d\u5305\u542b\u4e2d\u6587\uff0c\u4e0d\u7136\u53ef\u80fd\u4f1a\u5f15\u8d77\u5947\u602a\u7684\u9002\u914d\u95ee\u9898<\/p>\n

    \u4eca\u5929\u5c31\u804a\u5230\u8fd9\u4e86\uff0c\u6211\u662fGlen\uff0c\u611f\u8c22\u4f60\u770b\u6211\u7684\u6587\u7ae0\uff0c\u6b22\u8fce\u5927\u5bb6\u7ee7\u7eed\u652f\u6301\u6211\uff0c\u8bf7<\/strong>\u70b9\u8d5e\u3001\u5728\u770b\u3001\u5206\u4eab<\/strong>\u4e09\u8fde\u8d70\u4e00\u6ce2\u5427~<\/strong><\/p>\n

    Qwen-1.8B\u5927\u6a21\u578b\u79bb\u7ebf\u61d2\u4eba\u5305<\/a><\/strong><\/p>\n

    https:\/\/drive.uc.cn\/s\/e2872d9ba88c4<\/p>\n","protected":false},"excerpt":{"rendered":"

    I have recently, been more interested in small size AI large models. Previously, domestic and foreign technology companies in the field of large models, generally increasing the model parameters to enhance the model capacity, from 700 million, 1.3 billion, 7 billion or even more than 20 billion, it is true that it is getting stronger and stronger, but it will also make everyone's own home computer basically can not run. Recently, Microsoft released a Phi-2 large model with only 270 million parameters, and Ali also released a super-mini large model with only 180 million parameters of Tongyi Qianqian. These small-sized big model, not only in the performance evaluation, more than some 700 million or even 1.3 billion parameters of the big model, and because of the small size, basically can be in the 3G video memory or even under the CPU mode to run fast, so that 5 years ago, the old computer can also play. Today I share a Tongyi Qianqian 1.8B super mini large<\/p>","protected":false},"author":1,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"_acf_changed":false,"footnotes":""},"categories":[149,144],"tags":[703,702,331],"collection":[],"class_list":["post-2047","post","type-post","status-publish","format-standard","hentry","category-jiaocheng","category-baike","tag-703","tag-702","tag-331"],"acf":[],"_links":{"self":[{"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/posts\/2047","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=2047"}],"version-history":[{"count":0,"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/posts\/2047\/revisions"}],"wp:attachment":[{"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/media?parent=2047"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/categories?post=2047"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/tags?post=2047"},{"taxonomy":"collection","embeddable":true,"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/collection?post=2047"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}