{"id":20865,"date":"2026-11-04T18:21:56","date_gmt":"2026-11-04T11:21:56","guid":{"rendered":"https:\/\/blogdee.com\/?p=20865"},"modified":"2026-11-04T18:21:56","modified_gmt":"2026-11-04T11:21:56","slug":"%e0%b8%a7%e0%b8%b4%e0%b8%98%e0%b8%b5%e0%b8%9d%e0%b8%b6%e0%b8%81-decision-model-%e0%b8%82%e0%b8%ad%e0%b8%87%e0%b8%84%e0%b8%b8%e0%b8%93%e0%b9%80%e0%b8%ad%e0%b8%87%e0%b8%94%e0%b9%89%e0%b8%a7%e0%b8%a2-uns","status":"publish","type":"post","link":"https:\/\/blogdee.com\/?p=20865","title":{"rendered":"\u0e27\u0e34\u0e18\u0e35\u0e1d\u0e36\u0e01 Decision Model \u0e02\u0e2d\u0e07\u0e04\u0e38\u0e13\u0e40\u0e2d\u0e07\u0e14\u0e49\u0e27\u0e22 Unsloth \u0e1a\u0e19 Qwen3.5-4B"},"content":{"rendered":"<p>\u0e1a\u0e17\u0e04\u0e27\u0e32\u0e21\u0e19\u0e35\u0e49\u0e08\u0e30\u0e2a\u0e2d\u0e19\u0e27\u0e34\u0e18\u0e35\u0e01\u0e32\u0e23\u0e40\u0e1b\u0e25\u0e35\u0e48\u0e22\u0e19 open-weight language model \u0e43\u0e2b\u0e49\u0e01\u0e25\u0e32\u0e22\u0e40\u0e1b\u0e47\u0e19 decision model \u0e17\u0e35\u0e48\u0e2a\u0e32\u0e21\u0e32\u0e23\u0e16\u0e08\u0e33\u0e41\u0e19\u0e01\u0e40\u0e08\u0e15\u0e19\u0e32\u0e02\u0e2d\u0e07\u0e1c\u0e39\u0e49\u0e43\u0e0a\u0e49\u0e44\u0e14\u0e49 \u0e42\u0e14\u0e22\u0e01\u0e32\u0e23 fine-tune Qwen3.5-4B \u0e1a\u0e19 CLINC150 dataset \u0e14\u0e49\u0e27\u0e22 Unsloth<\/p>\n<h2 class=\"h2\">Step 1: Installing Unsloth<\/h2>\n<p>\u0e43\u0e19\u0e2a\u0e48\u0e27\u0e19\u0e19\u0e35\u0e49\u0e08\u0e30\u0e41\u0e2a\u0e14\u0e07\u0e04\u0e33\u0e2a\u0e31\u0e48\u0e07\u0e15\u0e34\u0e14\u0e15\u0e31\u0e49\u0e07\u0e17\u0e35\u0e48\u0e08\u0e33\u0e40\u0e1b\u0e47\u0e19\u0e2a\u0e33\u0e2b\u0e23\u0e31\u0e1a\u0e44\u0e25\u0e1a\u0e23\u0e32\u0e23\u0e35\u0e15\u0e48\u0e32\u0e07\u0e46 \u0e40\u0e0a\u0e48\u0e19 torch, triton, bitsandbytes, xformers \u0e41\u0e25\u0e30 unsloth \u0e40\u0e1e\u0e37\u0e48\u0e2d\u0e43\u0e2b\u0e49\u0e01\u0e32\u0e23\u0e17\u0e33\u0e07\u0e32\u0e19\u0e02\u0e2d\u0e07\u0e42\u0e21\u0e40\u0e14\u0e25\u0e40\u0e1b\u0e47\u0e19\u0e44\u0e1b\u0e2d\u0e22\u0e48\u0e32\u0e07\u0e23\u0e32\u0e1a\u0e23\u0e37\u0e48\u0e19<\/p>\n<h3>\u0e28\u0e31\u0e1e\u0e17\u0e4c\u0e17\u0e35\u0e48\u0e04\u0e27\u0e23\u0e23\u0e39\u0e49<\/h3>\n<ul>\n<li>open-weight language model &#8211; \u0e42\u0e21\u0e40\u0e14\u0e25\u0e20\u0e32\u0e29\u0e32\u0e17\u0e35\u0e48\u0e21\u0e35\u0e19\u0e49\u0e33\u0e2b\u0e19\u0e31\u0e01\u0e40\u0e1b\u0e34\u0e14\u0e43\u0e2b\u0e49\u0e43\u0e0a\u0e49\u0e07\u0e32\u0e19\u0e41\u0e25\u0e30\u0e1b\u0e23\u0e31\u0e1a\u0e41\u0e15\u0e48\u0e07\u0e44\u0e14\u0e49 decision model &#8211; \u0e42\u0e21\u0e40\u0e14\u0e25\u0e17\u0e35\u0e48\u0e16\u0e39\u0e01\u0e1d\u0e36\u0e01\u0e43\u0e2b\u0e49\u0e15\u0e31\u0e14\u0e2a\u0e34\u0e19\u0e43\u0e08\u0e2b\u0e23\u0e37\u0e2d\u0e08\u0e33\u0e41\u0e19\u0e01\u0e1b\u0e23\u0e30\u0e40\u0e20\u0e17\u0e08\u0e32\u0e01\u0e02\u0e49\u0e2d\u0e21\u0e39\u0e25\u0e17\u0e35\u0e48\u0e44\u0e14\u0e49\u0e23\u0e31\u0e1a fine-tuning &#8211; \u0e01\u0e23\u0e30\u0e1a\u0e27\u0e19\u0e01\u0e32\u0e23\u0e1b\u0e23\u0e31\u0e1a\u0e41\u0e15\u0e48\u0e07\u0e42\u0e21\u0e40\u0e14\u0e25 AI \u0e17\u0e35\u0e48\u0e1c\u0e48\u0e32\u0e19\u0e01\u0e32\u0e23\u0e1d\u0e36\u0e01\u0e40\u0e1a\u0e37\u0e49\u0e2d\u0e07\u0e15\u0e49\u0e19\u0e41\u0e25\u0e49\u0e27\u0e43\u0e2b\u0e49\u0e17\u0e33\u0e07\u0e32\u0e19\u0e40\u0e09\u0e1e\u0e32\u0e30\u0e17\u0e32\u0e07\u0e21\u0e32\u0e01\u0e02\u0e36\u0e49\u0e19 Qwen3.5-4B &#8211; \u0e42\u0e21\u0e40\u0e14\u0e25\u0e20\u0e32\u0e29\u0e32\u0e02\u0e19\u0e32\u0e14\u0e43\u0e2b\u0e0d\u0e48 (LLM) \u0e17\u0e35\u0e48\u0e43\u0e0a\u0e49\u0e40\u0e1b\u0e47\u0e19\u0e10\u0e32\u0e19\u0e43\u0e19\u0e01\u0e32\u0e23\u0e1d\u0e36\u0e01\u0e1d\u0e19\u0e04\u0e23\u0e31\u0e49\u0e07\u0e19\u0e35\u0e49 CLINC150 dataset &#8211; \u0e0a\u0e38\u0e14\u0e02\u0e49\u0e2d\u0e21\u0e39\u0e25\u0e17\u0e35\u0e48\u0e43\u0e0a\u0e49\u0e43\u0e19\u0e01\u0e32\u0e23\u0e1d\u0e36\u0e01\u0e42\u0e21\u0e40\u0e14\u0e25\u0e43\u0e2b\u0e49\u0e40\u0e23\u0e35\u0e22\u0e19\u0e23\u0e39\u0e49\u0e08\u0e32\u0e01\u0e15\u0e31\u0e27\u0e2d\u0e22\u0e48\u0e32\u0e07\u0e08\u0e23\u0e34\u0e07<\/li>\n<\/ul>\n<p>\u0e17\u0e35\u0e48\u0e21\u0e32: <a href=\"https:\/\/machinelearningmastery.com\/how-to-train-your-own-decision-model-like-jev-using-unsloth\/\" target=\"_blank\" rel=\"noopener nofollow\">machinelearningmastery.com<\/a><\/p>\n","protected":false},"excerpt":{"rendered":"<p>\u0e1a\u0e17\u0e04\u0e27\u0e32\u0e21\u0e19\u0e35\u0e49\u0e08\u0e30\u0e2a\u0e2d\u0e19\u0e27\u0e34\u0e18\u0e35\u0e01\u0e32\u0e23\u0e40\u0e1b\u0e25\u0e35\u0e48\u0e22\u0e19 open-weight language model \u0e43\u0e2b\u0e49\u0e01\u0e25\u0e32\u0e22\u0e40\u0e1b\u0e47\u0e19 decision model \u0e17\u0e35\u0e48\u0e2a\u0e32\u0e21\u0e32\u0e23\u0e16\u0e08\u0e33\u0e41\u0e19\u0e01\u0e40\u0e08\u0e15\u0e19\u0e32\u0e02\u0e2d\u0e07\u0e1c\u0e39\u0e49\u0e43\u0e0a\u0e49\u0e44\u0e14\u0e49 \u0e42\u0e14\u0e22\u0e01\u0e32\u0e23 fine-tune \u0e42\u0e21\u0e40\u0e14\u0e25\u2026<\/p>\n","protected":false},"author":1,"featured_media":20864,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[5021],"tags":[4608,88,7286],"class_list":["post-20865","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-ai-machine-learning-th","tag-fine-tuning","tag-llm","tag-unsloth"],"_links":{"self":[{"href":"https:\/\/blogdee.com\/index.php?rest_route=\/wp\/v2\/posts\/20865","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/blogdee.com\/index.php?rest_route=\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/blogdee.com\/index.php?rest_route=\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/blogdee.com\/index.php?rest_route=\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/blogdee.com\/index.php?rest_route=%2Fwp%2Fv2%2Fcomments&post=20865"}],"version-history":[{"count":0,"href":"https:\/\/blogdee.com\/index.php?rest_route=\/wp\/v2\/posts\/20865\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/blogdee.com\/index.php?rest_route=\/wp\/v2\/media\/20864"}],"wp:attachment":[{"href":"https:\/\/blogdee.com\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=20865"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/blogdee.com\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=20865"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/blogdee.com\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=20865"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}