{"id":471,"date":"2025-02-08T16:10:53","date_gmt":"2025-02-08T08:10:53","guid":{"rendered":"https:\/\/my.di.cloudns.asia\/?p=471"},"modified":"2025-02-08T16:10:53","modified_gmt":"2025-02-08T08:10:53","slug":"%e7%94%a8unsloth%e5%88%a9%e7%94%a8grpo%ef%bc%8c%e8%ae%ad%e7%bb%83%e4%b8%80%e6%ac%be%e7%b1%bb%e4%bc%bcdeepseek-r1%e6%8e%a8%e7%90%86%e5%a4%a7%e6%a8%a1%e5%9e%8b","status":"publish","type":"post","link":"https:\/\/my.di.cloudns.asia\/index.php\/2025\/02\/08\/471.html","title":{"rendered":"\u7528Unsloth\u5229\u7528GRPO\uff0c\u8bad\u7ec3\u4e00\u6b3e\u7c7b\u4f3cDeepSeek R1\u63a8\u7406\u5927\u6a21\u578b"},"content":{"rendered":"<p>Unsloth\u662f\u4e00\u6b3e\u975e\u5e38\u6d41\u884c\u7684\u9ad8\u6548\u5927\u6a21\u578b\u8bad\u7ec3\u4e0e\u5fae\u8c03\u5de5\u5177\u3002\u8fd1\u671fUnsloth\u4e5f\u5ba3\u5e03\u652f\u6301GRPO\u3002\u672c\u671f\u89c6\u9891\u57fa\u4e8eUnsloth\u5b98\u65b9\u535a\u5ba2\u7684\u4ecb\u7ecd\uff0c\u5206\u4eab\u5982\u4f55\u7528Unsloth\uff0c\u5229\u7528GRPO\uff0c\u8bad\u7ec3\u4e00\u6b3e\u7c7b\u4f3cDeepSeek R1\u7684\u5177\u6709\u81ea\u4e3b\u601d\u8003\u63a8\u7406\u80fd\u529b\u7684\u5927\u6a21\u578b\u3002<\/p>\n<p>R1 Reasoning | Unsloth Blog<br \/>\n<a href=\"https:\/\/unsloth.ai\/blog\/r1-reasoning\">https:\/\/unsloth.ai\/blog\/r1-reasoning<\/a><\/p>\n<p>Unsloth GRPO notebook: Llama 3.1 (8B) on Colab<br \/>\n<a href=\"https:\/\/colab.research.google.com\/github\/unslothai\/notebooks\/blob\/main\/nb\/Llama3.1_(8B)-GRPO.ipynb\">https:\/\/colab.research.google.com\/github\/unslothai\/notebooks\/blob\/main\/nb\/Llama3.1_(8B)-GRPO.ipynb<\/a><\/p>\n<p>OpenAI GSM8K\u6570\u636e\u96c6<br \/>\n<a href=\"https:\/\/huggingface.co\/datasets\/openai\/gsm8k\">https:\/\/huggingface.co\/datasets\/openai\/gsm8k<\/a><\/p>\n","protected":false},"excerpt":{"rendered":"<p>Unsloth\u662f\u4e00\u6b3e\u975e\u5e38\u6d41\u884c\u7684\u9ad8\u6548\u5927\u6a21\u578b\u8bad\u7ec3\u4e0e\u5fae\u8c03\u5de5\u5177\u3002\u8fd1\u671fUnsloth\u4e5f\u5ba3\u5e03\u652f\u6301GRPO\u3002\u672c\u671f\u89c6\u9891\u57fa\u4e8eUn [&hellip;]<\/p>\n","protected":false},"author":1,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[1],"tags":[],"class_list":["post-471","post","type-post","status-publish","format-standard","hentry","category-uncategorized"],"_links":{"self":[{"href":"https:\/\/my.di.cloudns.asia\/index.php\/wp-json\/wp\/v2\/posts\/471","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/my.di.cloudns.asia\/index.php\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/my.di.cloudns.asia\/index.php\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/my.di.cloudns.asia\/index.php\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/my.di.cloudns.asia\/index.php\/wp-json\/wp\/v2\/comments?post=471"}],"version-history":[{"count":1,"href":"https:\/\/my.di.cloudns.asia\/index.php\/wp-json\/wp\/v2\/posts\/471\/revisions"}],"predecessor-version":[{"id":472,"href":"https:\/\/my.di.cloudns.asia\/index.php\/wp-json\/wp\/v2\/posts\/471\/revisions\/472"}],"wp:attachment":[{"href":"https:\/\/my.di.cloudns.asia\/index.php\/wp-json\/wp\/v2\/media?parent=471"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/my.di.cloudns.asia\/index.php\/wp-json\/wp\/v2\/categories?post=471"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/my.di.cloudns.asia\/index.php\/wp-json\/wp\/v2\/tags?post=471"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}