{"id":10616,"date":"2025-07-12T10:16:27","date_gmt":"2025-07-12T01:16:27","guid":{"rendered":"https:\/\/aireviewirush.com\/?p=10616"},"modified":"2025-07-12T10:16:27","modified_gmt":"2025-07-12T01:16:27","slug":"reasoning-reimagined-introducing-phi-4-mini-flash-reasoning-microsoft-azure-weblog","status":"publish","type":"post","link":"https:\/\/aireviewirush.com\/?p=10616","title":{"rendered":"Reasoning reimagined: Introducing Phi-4-mini-flash-reasoning | Microsoft Azure Weblog"},"content":{"rendered":"<p> <br \/>\n<\/p>\n<div>\n<p>\n\t\t\tUnlock sooner, environment friendly reasoning with Phi-4-mini-flash-reasoning\u2014optimized for edge, cellular, and real-time functions.\t\t<\/p>\n<div id=\"ez-toc-container\" class=\"ez-toc-v2_0_53 counter-hierarchy ez-toc-counter ez-toc-grey ez-toc-container-direction\">\n<div class=\"ez-toc-title-container\">\n<p class=\"ez-toc-title \" >Table of Contents<\/p>\n<span class=\"ez-toc-title-toggle\"><a href=\"#\" class=\"ez-toc-pull-right ez-toc-btn ez-toc-btn-xs ez-toc-btn-default ez-toc-toggle\" aria-label=\"Toggle Table of Content\" role=\"button\"><label for=\"item-69e8bb37b6341\" ><span class=\"\"><span style=\"display:none;\">Toggle<\/span><span class=\"ez-toc-icon-toggle-span\"><svg style=\"fill: #999;color:#999\" xmlns=\"http:\/\/www.w3.org\/2000\/svg\" class=\"list-377408\" width=\"20px\" height=\"20px\" viewBox=\"0 0 24 24\" fill=\"none\"><path d=\"M6 6H4v2h2V6zm14 0H8v2h12V6zM4 11h2v2H4v-2zm16 0H8v2h12v-2zM4 16h2v2H4v-2zm16 0H8v2h12v-2z\" fill=\"currentColor\"><\/path><\/svg><svg style=\"fill: #999;color:#999\" class=\"arrow-unsorted-368013\" xmlns=\"http:\/\/www.w3.org\/2000\/svg\" width=\"10px\" height=\"10px\" viewBox=\"0 0 24 24\" version=\"1.2\" baseProfile=\"tiny\"><path d=\"M18.2 9.3l-6.2-6.3-6.2 6.3c-.2.2-.3.4-.3.7s.1.5.3.7c.2.2.4.3.7.3h11c.3 0 .5-.1.7-.3.2-.2.3-.5.3-.7s-.1-.5-.3-.7zM5.8 14.7l6.2 6.3 6.2-6.3c.2-.2.3-.5.3-.7s-.1-.5-.3-.7c-.2-.2-.4-.3-.7-.3h-11c-.3 0-.5.1-.7.3-.2.2-.3.5-.3.7s.1.5.3.7z\"\/><\/svg><\/span><\/span><\/label><input aria-label=\"Toggle\" aria-label=\"item-69e8bb37b6341\"  type=\"checkbox\" id=\"item-69e8bb37b6341\"><\/a><\/span><\/div>\n<nav><ul class='ez-toc-list ez-toc-list-level-1 ' ><li class='ez-toc-page-1 ez-toc-heading-level-2'><a class=\"ez-toc-link ez-toc-heading-1\" href=\"https:\/\/aireviewirush.com\/?p=10616\/#State-of-the-art_structure_redefines_velocity_for_reasoning_fashions\" title=\"State-of-the-art structure redefines velocity for reasoning fashions\">State-of-the-art structure redefines velocity for reasoning fashions<\/a><\/li><li class='ez-toc-page-1 ez-toc-heading-level-2'><a class=\"ez-toc-link ez-toc-heading-2\" href=\"https:\/\/aireviewirush.com\/?p=10616\/#Azure_AI_Foundry\" title=\"Azure AI Foundry\">Azure AI Foundry<\/a><\/li><li class='ez-toc-page-1 ez-toc-heading-level-2'><a class=\"ez-toc-link ez-toc-heading-3\" href=\"https:\/\/aireviewirush.com\/?p=10616\/#Effectivity_with_out_compromise\" title=\"Effectivity with out compromise\u00a0\">Effectivity with out compromise\u00a0<\/a><\/li><li class='ez-toc-page-1 ez-toc-heading-level-2'><a class=\"ez-toc-link ez-toc-heading-4\" href=\"https:\/\/aireviewirush.com\/?p=10616\/#What%E2%80%99s_new\" title=\"What\u2019s new?\">What\u2019s new?<\/a><\/li><li class='ez-toc-page-1 ez-toc-heading-level-2'><a class=\"ez-toc-link ez-toc-heading-5\" href=\"https:\/\/aireviewirush.com\/?p=10616\/#Phi-4-mini-flash-reasoning_benchmarks\" title=\"Phi-4-mini-flash-reasoning benchmarks\u00a0\">Phi-4-mini-flash-reasoning benchmarks\u00a0<\/a><\/li><li class='ez-toc-page-1 ez-toc-heading-level-2'><a class=\"ez-toc-link ez-toc-heading-6\" href=\"https:\/\/aireviewirush.com\/?p=10616\/#What_are_the_potential_use_circumstances\" title=\"What are the potential use circumstances?\u00a0\">What are the potential use circumstances?\u00a0<\/a><\/li><li class='ez-toc-page-1 ez-toc-heading-level-2'><a class=\"ez-toc-link ez-toc-heading-7\" href=\"https:\/\/aireviewirush.com\/?p=10616\/#Microsoft%E2%80%99s_dedication_to_reliable_AI\" title=\"Microsoft\u2019s dedication to reliable AI\u00a0\">Microsoft\u2019s dedication to reliable AI\u00a0<\/a><\/li><li class='ez-toc-page-1 ez-toc-heading-level-2'><a class=\"ez-toc-link ez-toc-heading-8\" href=\"https:\/\/aireviewirush.com\/?p=10616\/#Be_taught_extra_in_regards_to_the_new_mannequin\" title=\"Be taught extra in regards to the new mannequin\u00a0\">Be taught extra in regards to the new mannequin\u00a0<\/a><\/li><li class='ez-toc-page-1 ez-toc-heading-level-2'><a class=\"ez-toc-link ez-toc-heading-9\" href=\"https:\/\/aireviewirush.com\/?p=10616\/#Create_with_Azure_AI_Foundry\" title=\"Create with Azure AI Foundry\">Create with Azure AI Foundry<\/a><\/li><\/ul><\/nav><\/div>\n<h2 class=\"wp-block-heading\" id=\"state-of-the-art-architecture-redefines-speed-for-reasoning-models\"><span class=\"ez-toc-section\" id=\"State-of-the-art_structure_redefines_velocity_for_reasoning_fashions\"><\/span>State-of-the-art structure redefines velocity for reasoning fashions<span class=\"ez-toc-section-end\"><\/span><\/h2>\n<p class=\"wp-block-paragraph\">Microsoft is worked up to unveil a brand new version to the Phi mannequin household: <strong>Phi-4-mini-flash-reasoning<\/strong>. Function-built for eventualities the place compute, reminiscence, and latency are tightly constrained, this new mannequin is engineered to carry superior reasoning capabilities to edge units, cellular functions, and different resource-constrained environments. This new mannequin follows Phi-4-mini, however is constructed on a brand new hybrid structure, that achieves as much as 10 instances increased throughput and a 2 to three instances common discount in latency, enabling considerably sooner inference with out sacrificing reasoning efficiency. Able to energy actual world options that demand effectivity and suppleness, Phi-4-mini-flash-reasoning is accessible on <a href=\"https:\/\/ai.azure.com\/\" target=\"_blank\" rel=\"noopener\">Azure AI Foundry<\/a>, <a href=\"https:\/\/build.nvidia.com\/microsoft\" target=\"_blank\" rel=\"noreferrer noopener\">NVIDIA API Catalog<\/a>, and <a href=\"http:\/\/aka.ms\/flashreasoning-hf\" target=\"_blank\" rel=\"noreferrer noopener\">Hugging Face<\/a> right now.<\/p>\n<aside class=\"cta-block cta-block--align-left cta-block--has-image wp-block-msx-cta\" data-bi-an=\"CTA Block\">\n<div class=\"cta-block__content\">\n<div class=\"cta-block__image-container\">\n\t\t\t\t<img loading=\"lazy\" decoding=\"async\" width=\"1024\" height=\"575\" src=\"https:\/\/azure.microsoft.com\/en-us\/blog\/wp-content\/uploads\/2025\/07\/Azure_Hero_Ellipse_OffWhite_FullGrad_cropped-1024x575.webp\" class=\"cta-block__image\" alt=\"A colorful background with a curved line\" srcset=\"https:\/\/azure.microsoft.com\/en-us\/blog\/wp-content\/uploads\/2025\/07\/Azure_Hero_Ellipse_OffWhite_FullGrad_cropped-1024x575.webp 1024w, https:\/\/azure.microsoft.com\/en-us\/blog\/wp-content\/uploads\/2025\/07\/Azure_Hero_Ellipse_OffWhite_FullGrad_cropped-300x169.webp 300w, https:\/\/azure.microsoft.com\/en-us\/blog\/wp-content\/uploads\/2025\/07\/Azure_Hero_Ellipse_OffWhite_FullGrad_cropped-768x432.webp 768w, https:\/\/azure.microsoft.com\/en-us\/blog\/wp-content\/uploads\/2025\/07\/Azure_Hero_Ellipse_OffWhite_FullGrad_cropped.webp 1260w\" sizes=\"auto, (max-width: 1024px) 100vw, 1024px\"\/>\t\t\t<\/div>\n<div class=\"cta-block__body\">\n<h2 class=\"cta-block__headline\"><span class=\"ez-toc-section\" id=\"Azure_AI_Foundry\"><\/span>Azure AI Foundry<span class=\"ez-toc-section-end\"><\/span><\/h2>\n<p class=\"cta-block__text\">Create with out boundaries\u2014Azure AI Foundry has every thing you must design, customise, and handle AI functions and brokers<\/p>\n<\/p><\/div>\n<\/p><\/div>\n<\/aside>\n<h2 class=\"wp-block-heading\" id=\"efficiency-without-compromise\"><span class=\"ez-toc-section\" id=\"Effectivity_with_out_compromise\"><\/span>Effectivity with out compromise\u00a0<span class=\"ez-toc-section-end\"><\/span><\/h2>\n<p class=\"wp-block-paragraph\">Phi-4-mini-flash-reasoning balances math reasoning skill with effectivity, making it probably appropriate for academic functions, real-time logic-based functions, and extra.\u00a0<\/p>\n<p class=\"wp-block-paragraph\">Much like its predecessor, Phi-4-mini-flash-reasoning is a 3.8 billion parameter open mannequin optimized for superior math reasoning. It helps a 64K token context size and is fine-tuned on high-quality artificial information to ship dependable, logic-intensive efficiency deployment.\u00a0\u00a0<\/p>\n<h2 class=\"wp-block-heading\" id=\"what-s-new\"><span class=\"ez-toc-section\" id=\"What%E2%80%99s_new\"><\/span>What\u2019s new?<span class=\"ez-toc-section-end\"><\/span><\/h2>\n<p class=\"wp-block-paragraph\">On the core of Phi-4-mini-flash-reasoning is the newly launched decoder-hybrid-decoder structure, SambaY, whose central innovation is the Gated Reminiscence Unit (GMU), a easy but efficient mechanism for sharing representations between layers.\u00a0 The structure features a self-decoder that mixes Mamba (a State House Mannequin) and Sliding Window Consideration (SWA), together with a single layer of full consideration. The structure additionally entails a cross-decoder that interleaves costly cross-attention layers with the brand new, environment friendly GMUs. This new structure with GMU modules\u00a0drastically improves decoding effectivity, boosts long-context retrieval efficiency and allows the structure to ship distinctive efficiency throughout a variety of duties.\u00a0<\/p>\n<p class=\"wp-block-paragraph\">Key advantages of the SambaY structure embrace:\u00a0<\/p>\n<ul class=\"wp-block-list\">\n<li class=\"wp-block-list-item\">Enhanced decoding effectivity.<\/li>\n<li class=\"wp-block-list-item\">Preserves linear prefiling time complexity.<\/li>\n<li class=\"wp-block-list-item\">Elevated scalability and enhanced lengthy context efficiency.<\/li>\n<li class=\"wp-block-list-item\">As much as 10 instances increased throughput.<\/li>\n<\/ul>\n<figure class=\"wp-block-image aligncenter size-full\"><img decoding=\"async\" alt=\"A diagram of a computer program\" class=\"wp-image-44177 webp-format\" srcset=\"\" src=\"https:\/\/azure.microsoft.com\/en-us\/blog\/wp-content\/uploads\/2025\/07\/Decoder-hybrid-decoder-architecture.webp\"\/><figcaption class=\"wp-element-caption\"><em>Our decoder-hybrid-decoder structure taking Samba [RLL+25] because the self-decoder. Gated Reminiscence Items (GMUs) are interleaved with the cross-attention layers within the cross-decoder to cut back the decoding computation complexity. As in YOCO [SDZ+24], the complete consideration layer solely computes the KV cache in the course of the prefilling with the self-decoder, resulting in linear computation complexity for the prefill stage.<\/em><\/figcaption><\/figure>\n<h2 class=\"wp-block-heading\" id=\"phi-4-mini-flash-reasoning-benchmarks\"><span class=\"ez-toc-section\" id=\"Phi-4-mini-flash-reasoning_benchmarks\"><\/span>Phi-4-mini-flash-reasoning benchmarks\u00a0<span class=\"ez-toc-section-end\"><\/span><\/h2>\n<p class=\"wp-block-paragraph\">Like all fashions within the Phi household, Phi-4-mini-flash-reasoning is deployable on a single GPU, making it accessible for a broad vary of use circumstances. Nonetheless, what units it aside is its architectural benefit. This new mannequin achieves considerably decrease latency and better throughput in comparison with Phi-4-mini-reasoning, notably in long-context technology and latency-sensitive reasoning duties.\u00a0<\/p>\n<p class=\"wp-block-paragraph\">This makes Phi-4-mini-flash-reasoning a compelling choice for builders and enterprises trying to deploy clever methods that require quick, scalable, and environment friendly reasoning\u2014whether or not on premises or on-device.\u00a0<\/p>\n<figure class=\"wp-block-image aligncenter size-full\"><img decoding=\"async\" alt=\"A graph of a number of people\" class=\"wp-image-44178 webp-format\" srcset=\"\" src=\"https:\/\/azure.microsoft.com\/en-us\/blog\/wp-content\/uploads\/2025\/07\/Generation-Latencies.webp\"\/><\/figure>\n<figure class=\"wp-block-image aligncenter size-full\"><img decoding=\"async\" alt=\"A graph with red and blue dots and numbers\" class=\"wp-image-44179 webp-format\" srcset=\"\" src=\"https:\/\/azure.microsoft.com\/en-us\/blog\/wp-content\/uploads\/2025\/07\/Prompt-2000.webp\"\/><figcaption class=\"wp-element-caption\"><em>The highest plot reveals inference latency as a perform of technology size, whereas the underside plot illustrates how inference latency varies with throughput. Each experiments had been performed utilizing the vLLM inference framework on a single A100-80GB GPU with tensor parallelism (TP) set to 1.<\/em><\/figcaption><\/figure>\n<figure class=\"wp-block-image aligncenter size-full\"><img decoding=\"async\" alt=\"A graph of different colored bars\" class=\"wp-image-44181 webp-format\" srcset=\"\" src=\"https:\/\/azure.microsoft.com\/en-us\/blog\/wp-content\/uploads\/2025\/07\/Math-benchmarks.webp\"\/><figcaption class=\"wp-element-caption\"><em>A extra correct analysis was used the place Go@1 accuracy is averaged over 64 samples for AIME24\/25 and eight samples for Math500 and GPQA Diamond. On this graph, Phi-4-mini-flash-reasoning outperforms Phi-4-mini-reasoning and is healthier than fashions twice its dimension.<\/em><\/figcaption><\/figure>\n<h2 class=\"wp-block-heading\" id=\"what-are-the-potential-use-cases\"><span class=\"ez-toc-section\" id=\"What_are_the_potential_use_circumstances\"><\/span>What are the potential use circumstances?\u00a0<span class=\"ez-toc-section-end\"><\/span><\/h2>\n<p class=\"wp-block-paragraph\">Because of its lowered latency, improved throughput, and give attention to math reasoning, the mannequin is good for:\u00a0<\/p>\n<ul class=\"wp-block-list\">\n<li class=\"wp-block-list-item\"><strong>Adaptive studying platforms<\/strong>, the place real-time suggestions loops are important.<\/li>\n<li class=\"wp-block-list-item\"><strong>On-device reasoning assistants<\/strong>, similar to cellular examine aids or edge-based logic brokers.<\/li>\n<li class=\"wp-block-list-item\"><strong>Interactive tutoring methods<\/strong> that dynamically regulate content material problem primarily based on a learner\u2019s efficiency.<\/li>\n<\/ul>\n<p class=\"wp-block-paragraph\">Its power in math and structured reasoning makes it particularly helpful for training know-how, light-weight simulations, and automatic evaluation instruments that require dependable logic inference with quick response instances.\u00a0<\/p>\n<p class=\"wp-block-paragraph\">Builders are inspired to attach with friends and Microsoft engineers by means of the <a href=\"https:\/\/aka.ms\/foundrydevs\" target=\"_blank\" rel=\"noreferrer noopener\">Microsoft Developer Discord neighborhood<\/a> to ask questions, share suggestions, and discover real-world use circumstances collectively.\u00a0<\/p>\n<h2 class=\"wp-block-heading\" id=\"microsoft-s-commitment-to-trustworthy-ai\"><span class=\"ez-toc-section\" id=\"Microsoft%E2%80%99s_dedication_to_reliable_AI\"><\/span>Microsoft\u2019s dedication to reliable AI\u00a0<span class=\"ez-toc-section-end\"><\/span><\/h2>\n<p class=\"wp-block-paragraph\">Organizations throughout industries are leveraging Azure AI and <a href=\"https:\/\/www.microsoft.com\/en-us\/microsoft-365\/copilot\" target=\"_blank\" rel=\"noreferrer noopener\">Microsoft 365 Copilot<\/a> capabilities to drive development, improve productiveness, and create value-added experiences.\u00a0<\/p>\n<p class=\"wp-block-paragraph\">We\u2019re dedicated to serving to organizations use and construct <a href=\"https:\/\/blogs.microsoft.com\/blog\/2024\/09\/24\/microsoft-trustworthy-ai-unlocking-human-potential-starts-with-trust\/\" target=\"_blank\" rel=\"noreferrer noopener\">AI that&#8217;s reliable<\/a>, that means it&#8217;s safe, personal, and secure. We carry greatest practices and learnings from a long time of researching and constructing AI merchandise at scale to supply industry-leading commitments and capabilities that span our three pillars of safety, privateness, and security. Reliable AI is just doable once you mix our commitments, similar to our <a href=\"https:\/\/www.microsoft.com\/en-us\/trust-center\/security\/secure-future-initiative\" target=\"_blank\" rel=\"noreferrer noopener\">Safe Future Initiative<\/a> and our <a href=\"https:\/\/www.microsoft.com\/en-us\/ai\/responsible-ai\" target=\"_blank\" rel=\"noreferrer noopener\">accountable AI rules<\/a>, with our product capabilities to unlock AI transformation with confidence. \u00a0<\/p>\n<p class=\"wp-block-paragraph\">Phi fashions are developed in accordance with Microsoft AI rules: accountability, transparency, equity, reliability and security, privateness and safety, and inclusiveness.\u202f\u00a0<\/p>\n<p class=\"wp-block-paragraph\">The Phi mannequin household, together with Phi-4-mini-flash-reasoning, employs a sturdy security post-training technique that integrates Supervised Tremendous-Tuning (SFT), Direct Desire Optimization (DPO), and Reinforcement Studying from Human Suggestions (RLHF). These methods are utilized utilizing a mix of open-source and proprietary datasets, with a robust emphasis on guaranteeing helpfulness, minimizing dangerous outputs, and addressing a broad vary of security classes. Builders are inspired to use accountable AI greatest practices tailor-made to their particular use circumstances and cultural contexts.\u00a0<\/p>\n<p class=\"wp-block-paragraph\">Learn the mannequin card to be taught extra about any threat and mitigation methods. \u00a0<\/p>\n<h2 class=\"wp-block-heading\" id=\"learn-more-about-the-new-model\"><span class=\"ez-toc-section\" id=\"Be_taught_extra_in_regards_to_the_new_mannequin\"><\/span>Be taught extra in regards to the new mannequin\u00a0<span class=\"ez-toc-section-end\"><\/span><\/h2>\n<h2 class=\"wp-block-heading\" id=\"create-with-azure-ai-foundry\"><span class=\"ez-toc-section\" id=\"Create_with_Azure_AI_Foundry\"><\/span>Create with Azure AI Foundry<span class=\"ez-toc-section-end\"><\/span><\/h2>\n<\/p><\/div>\n<p><script>\n\t\tfunction facebookTracking() {\n\t\t\t!function(f,b,e,v,n,t,s){if(f.fbq)return;n=f.fbq=function(){n.callMethod?\n\t\t\t\tn.callMethod.apply(n,arguments):n.queue.push(arguments)};if(!f._fbq)f._fbq=n;\n\t\t\t\tn.push=n;n.loaded=!0;n.version='2.0';n.queue=[];t=b.createElement(e);t.async=!0;\n\t\t\t\tt.src=v;t.type=\"ms-delay-type\";t.setAttribute('data-ms-type','text\/javascript');\n\t\t\t\ts=b.getElementsByTagName(e)[0];s.parentNode.insertBefore(t,s)}(window,\n\t\t\t\tdocument,'script','https:\/\/connect.facebook.net\/en_US\/fbevents.js');\n\t\t\tfbq('init', '1770559986549030');\n\t\t\t\t\t\tfbq('track', 'PageView');\n\t\t\t\t\t}\n\t<\/script><br \/>\n<br \/><\/p>\n","protected":false},"excerpt":{"rendered":"<p>Unlock sooner, environment friendly reasoning with Phi-4-mini-flash-reasoning\u2014optimized for edge, cellular, and real-time functions. State-of-the-art structure redefines velocity for reasoning fashions Microsoft is worked up to unveil a brand new version to the Phi mannequin household: Phi-4-mini-flash-reasoning. Function-built for eventualities the place compute, reminiscence, and latency are tightly constrained, this new mannequin is engineered to carry [&hellip;]<\/p>\n","protected":false},"author":1,"featured_media":10618,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[22],"tags":[],"class_list":{"0":"post-10616","1":"post","2":"type-post","3":"status-publish","4":"format-standard","5":"has-post-thumbnail","7":"category-iot"},"_links":{"self":[{"href":"https:\/\/aireviewirush.com\/index.php?rest_route=\/wp\/v2\/posts\/10616","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/aireviewirush.com\/index.php?rest_route=\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/aireviewirush.com\/index.php?rest_route=\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/aireviewirush.com\/index.php?rest_route=\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/aireviewirush.com\/index.php?rest_route=%2Fwp%2Fv2%2Fcomments&post=10616"}],"version-history":[{"count":1,"href":"https:\/\/aireviewirush.com\/index.php?rest_route=\/wp\/v2\/posts\/10616\/revisions"}],"predecessor-version":[{"id":10617,"href":"https:\/\/aireviewirush.com\/index.php?rest_route=\/wp\/v2\/posts\/10616\/revisions\/10617"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/aireviewirush.com\/index.php?rest_route=\/wp\/v2\/media\/10618"}],"wp:attachment":[{"href":"https:\/\/aireviewirush.com\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=10616"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/aireviewirush.com\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=10616"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/aireviewirush.com\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=10616"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}