{"id":1789,"date":"2023-06-20T14:31:00","date_gmt":"2023-06-20T09:01:00","guid":{"rendered":"https:\/\/www.analyticsvidhya.com\/datahack-summit-2023\/?page_id=1789"},"modified":"2023-07-19T19:05:58","modified_gmt":"2023-07-19T13:35:58","slug":"fine-tuning-a-language-model-with-rlhf-2","status":"publish","type":"page","link":"https:\/\/www.analyticsvidhya.com\/dhs-2023\/session\/fine-tuning-a-language-model-with-rlhf-2\/","title":{"rendered":"Fine-tuning a Language Model with RLHF"},"content":{"rendered":"<p><span data-sheets-value=\"{&quot;1&quot;:2,&quot;2&quot;:&quot;Reinforcement learning is an optimisation framework for sequential decision-making problems, where an agent interacts with an environment, takes actions, and receives feedback (rewards). It is successfully applied in domains such as games, robotics and recommendation systems. One of the important successes of RL is its role in training Large Language Models, particularly the GPT.\\n\\nReinforcement learning with human feedback(RLHF) are leveraged in LLMs in different ways to increase their effectiveness. RLHF algorithms include a human or an automated process that gives feedback to a learning model to improve the training process and\/or better define the objective (fine-tuning).\\n\\nIn this hack session, we will cover an implementation of using RLHF to fine tune a language model from basics. We will also cover the practical aspects of RLHF, its applications in NLP, how to apply RLHF in different stages of training a LLM, and its limitations and successes.\\n\\nKye Takeaways:\\n1. Understanding the concept of Reinforcement Learning with Human Feedback (RLHF) and its crucial role in refining and enhancing the training process of language models.\\n2. Practical insights into the application of RLHF in Natural Language Processing (NLP) and various stages of training Large Language Models.\\n3. Recognition of the limitations and successes of RLHF, fostering a balanced perspective on its utility and application potential.\\n&quot;}\" data-sheets-userformat=\"{&quot;2&quot;:17405,&quot;3&quot;:{&quot;1&quot;:0},&quot;5&quot;:{&quot;1&quot;:[{&quot;1&quot;:2,&quot;2&quot;:0,&quot;5&quot;:{&quot;1&quot;:2,&quot;2&quot;:0}},{&quot;1&quot;:0,&quot;2&quot;:0,&quot;3&quot;:3},{&quot;1&quot;:1,&quot;2&quot;:0,&quot;4&quot;:1}]},&quot;6&quot;:{&quot;1&quot;:[{&quot;1&quot;:2,&quot;2&quot;:0,&quot;5&quot;:{&quot;1&quot;:2,&quot;2&quot;:0}},{&quot;1&quot;:0,&quot;2&quot;:0,&quot;3&quot;:3},{&quot;1&quot;:1,&quot;2&quot;:0,&quot;4&quot;:1}]},&quot;7&quot;:{&quot;1&quot;:[{&quot;1&quot;:2,&quot;2&quot;:0,&quot;5&quot;:{&quot;1&quot;:2,&quot;2&quot;:0}},{&quot;1&quot;:0,&quot;2&quot;:0,&quot;3&quot;:3},{&quot;1&quot;:1,&quot;2&quot;:0,&quot;4&quot;:1}]},&quot;8&quot;:{&quot;1&quot;:[{&quot;1&quot;:2,&quot;2&quot;:0,&quot;5&quot;:{&quot;1&quot;:2,&quot;2&quot;:0}},{&quot;1&quot;:0,&quot;2&quot;:0,&quot;3&quot;:3},{&quot;1&quot;:1,&quot;2&quot;:0,&quot;4&quot;:1}]},&quot;9&quot;:1,&quot;10&quot;:1,&quot;11&quot;:3,&quot;12&quot;:0,&quot;17&quot;:1}\">Reinforcement learning is an optimisation framework for sequential decision-making problems, where an agent interacts with an environment, takes actions, and receives feedback (rewards). It is successfully applied in domains such as games, robotics and recommendation systems. One of the important successes of RL is its role in training Large Language Models, particularly the GPT.<\/span><\/p>\n<p>Reinforcement learning with human feedback(RLHF) are leveraged in LLMs in different ways to increase their effectiveness. RLHF algorithms include a human or an automated process that gives feedback to a learning model to improve the training process and\/or better define the objective (fine-tuning).<\/p>\n<p>In this hack session, we will cover an implementation of using RLHF to fine tune a language model from basics. We will also cover the practical aspects of RLHF, its applications in NLP, how to apply RLHF in different stages of training a LLM, and its limitations and successes.<\/p>\n<p><strong>Kye Takeaways:<\/strong><\/p>\n<ol>\n<li><span data-sheets-value=\"{&quot;1&quot;:2,&quot;2&quot;:&quot;Reinforcement learning is an optimisation framework for sequential decision-making problems, where an agent interacts with an environment, takes actions, and receives feedback (rewards). It is successfully applied in domains such as games, robotics and recommendation systems. One of the important successes of RL is its role in training Large Language Models, particularly the GPT.\\n\\nReinforcement learning with human feedback(RLHF) are leveraged in LLMs in different ways to increase their effectiveness. RLHF algorithms include a human or an automated process that gives feedback to a learning model to improve the training process and\/or better define the objective (fine-tuning).\\n\\nIn this hack session, we will cover an implementation of using RLHF to fine tune a language model from basics. We will also cover the practical aspects of RLHF, its applications in NLP, how to apply RLHF in different stages of training a LLM, and its limitations and successes.\\n\\nKye Takeaways:\\n1. Understanding the concept of Reinforcement Learning with Human Feedback (RLHF) and its crucial role in refining and enhancing the training process of language models.\\n2. Practical insights into the application of RLHF in Natural Language Processing (NLP) and various stages of training Large Language Models.\\n3. Recognition of the limitations and successes of RLHF, fostering a balanced perspective on its utility and application potential.\\n&quot;}\" data-sheets-userformat=\"{&quot;2&quot;:17405,&quot;3&quot;:{&quot;1&quot;:0},&quot;5&quot;:{&quot;1&quot;:[{&quot;1&quot;:2,&quot;2&quot;:0,&quot;5&quot;:{&quot;1&quot;:2,&quot;2&quot;:0}},{&quot;1&quot;:0,&quot;2&quot;:0,&quot;3&quot;:3},{&quot;1&quot;:1,&quot;2&quot;:0,&quot;4&quot;:1}]},&quot;6&quot;:{&quot;1&quot;:[{&quot;1&quot;:2,&quot;2&quot;:0,&quot;5&quot;:{&quot;1&quot;:2,&quot;2&quot;:0}},{&quot;1&quot;:0,&quot;2&quot;:0,&quot;3&quot;:3},{&quot;1&quot;:1,&quot;2&quot;:0,&quot;4&quot;:1}]},&quot;7&quot;:{&quot;1&quot;:[{&quot;1&quot;:2,&quot;2&quot;:0,&quot;5&quot;:{&quot;1&quot;:2,&quot;2&quot;:0}},{&quot;1&quot;:0,&quot;2&quot;:0,&quot;3&quot;:3},{&quot;1&quot;:1,&quot;2&quot;:0,&quot;4&quot;:1}]},&quot;8&quot;:{&quot;1&quot;:[{&quot;1&quot;:2,&quot;2&quot;:0,&quot;5&quot;:{&quot;1&quot;:2,&quot;2&quot;:0}},{&quot;1&quot;:0,&quot;2&quot;:0,&quot;3&quot;:3},{&quot;1&quot;:1,&quot;2&quot;:0,&quot;4&quot;:1}]},&quot;9&quot;:1,&quot;10&quot;:1,&quot;11&quot;:3,&quot;12&quot;:0,&quot;17&quot;:1}\">Understanding the concept of Reinforcement Learning with Human Feedback (RLHF) and its crucial role in refining and enhancing the training process of language models.<br \/>\n<\/span><\/li>\n<li><span data-sheets-value=\"{&quot;1&quot;:2,&quot;2&quot;:&quot;Reinforcement learning is an optimisation framework for sequential decision-making problems, where an agent interacts with an environment, takes actions, and receives feedback (rewards). It is successfully applied in domains such as games, robotics and recommendation systems. One of the important successes of RL is its role in training Large Language Models, particularly the GPT.\\n\\nReinforcement learning with human feedback(RLHF) are leveraged in LLMs in different ways to increase their effectiveness. RLHF algorithms include a human or an automated process that gives feedback to a learning model to improve the training process and\/or better define the objective (fine-tuning).\\n\\nIn this hack session, we will cover an implementation of using RLHF to fine tune a language model from basics. We will also cover the practical aspects of RLHF, its applications in NLP, how to apply RLHF in different stages of training a LLM, and its limitations and successes.\\n\\nKye Takeaways:\\n1. Understanding the concept of Reinforcement Learning with Human Feedback (RLHF) and its crucial role in refining and enhancing the training process of language models.\\n2. Practical insights into the application of RLHF in Natural Language Processing (NLP) and various stages of training Large Language Models.\\n3. Recognition of the limitations and successes of RLHF, fostering a balanced perspective on its utility and application potential.\\n&quot;}\" data-sheets-userformat=\"{&quot;2&quot;:17405,&quot;3&quot;:{&quot;1&quot;:0},&quot;5&quot;:{&quot;1&quot;:[{&quot;1&quot;:2,&quot;2&quot;:0,&quot;5&quot;:{&quot;1&quot;:2,&quot;2&quot;:0}},{&quot;1&quot;:0,&quot;2&quot;:0,&quot;3&quot;:3},{&quot;1&quot;:1,&quot;2&quot;:0,&quot;4&quot;:1}]},&quot;6&quot;:{&quot;1&quot;:[{&quot;1&quot;:2,&quot;2&quot;:0,&quot;5&quot;:{&quot;1&quot;:2,&quot;2&quot;:0}},{&quot;1&quot;:0,&quot;2&quot;:0,&quot;3&quot;:3},{&quot;1&quot;:1,&quot;2&quot;:0,&quot;4&quot;:1}]},&quot;7&quot;:{&quot;1&quot;:[{&quot;1&quot;:2,&quot;2&quot;:0,&quot;5&quot;:{&quot;1&quot;:2,&quot;2&quot;:0}},{&quot;1&quot;:0,&quot;2&quot;:0,&quot;3&quot;:3},{&quot;1&quot;:1,&quot;2&quot;:0,&quot;4&quot;:1}]},&quot;8&quot;:{&quot;1&quot;:[{&quot;1&quot;:2,&quot;2&quot;:0,&quot;5&quot;:{&quot;1&quot;:2,&quot;2&quot;:0}},{&quot;1&quot;:0,&quot;2&quot;:0,&quot;3&quot;:3},{&quot;1&quot;:1,&quot;2&quot;:0,&quot;4&quot;:1}]},&quot;9&quot;:1,&quot;10&quot;:1,&quot;11&quot;:3,&quot;12&quot;:0,&quot;17&quot;:1}\">Practical insights into the application of RLHF in Natural Language Processing (NLP) and various stages of training Large Language Models.<br \/>\n<\/span><\/li>\n<li><span data-sheets-value=\"{&quot;1&quot;:2,&quot;2&quot;:&quot;Reinforcement learning is an optimisation framework for sequential decision-making problems, where an agent interacts with an environment, takes actions, and receives feedback (rewards). It is successfully applied in domains such as games, robotics and recommendation systems. One of the important successes of RL is its role in training Large Language Models, particularly the GPT.\\n\\nReinforcement learning with human feedback(RLHF) are leveraged in LLMs in different ways to increase their effectiveness. RLHF algorithms include a human or an automated process that gives feedback to a learning model to improve the training process and\/or better define the objective (fine-tuning).\\n\\nIn this hack session, we will cover an implementation of using RLHF to fine tune a language model from basics. We will also cover the practical aspects of RLHF, its applications in NLP, how to apply RLHF in different stages of training a LLM, and its limitations and successes.\\n\\nKye Takeaways:\\n1. Understanding the concept of Reinforcement Learning with Human Feedback (RLHF) and its crucial role in refining and enhancing the training process of language models.\\n2. Practical insights into the application of RLHF in Natural Language Processing (NLP) and various stages of training Large Language Models.\\n3. Recognition of the limitations and successes of RLHF, fostering a balanced perspective on its utility and application potential.\\n&quot;}\" data-sheets-userformat=\"{&quot;2&quot;:17405,&quot;3&quot;:{&quot;1&quot;:0},&quot;5&quot;:{&quot;1&quot;:[{&quot;1&quot;:2,&quot;2&quot;:0,&quot;5&quot;:{&quot;1&quot;:2,&quot;2&quot;:0}},{&quot;1&quot;:0,&quot;2&quot;:0,&quot;3&quot;:3},{&quot;1&quot;:1,&quot;2&quot;:0,&quot;4&quot;:1}]},&quot;6&quot;:{&quot;1&quot;:[{&quot;1&quot;:2,&quot;2&quot;:0,&quot;5&quot;:{&quot;1&quot;:2,&quot;2&quot;:0}},{&quot;1&quot;:0,&quot;2&quot;:0,&quot;3&quot;:3},{&quot;1&quot;:1,&quot;2&quot;:0,&quot;4&quot;:1}]},&quot;7&quot;:{&quot;1&quot;:[{&quot;1&quot;:2,&quot;2&quot;:0,&quot;5&quot;:{&quot;1&quot;:2,&quot;2&quot;:0}},{&quot;1&quot;:0,&quot;2&quot;:0,&quot;3&quot;:3},{&quot;1&quot;:1,&quot;2&quot;:0,&quot;4&quot;:1}]},&quot;8&quot;:{&quot;1&quot;:[{&quot;1&quot;:2,&quot;2&quot;:0,&quot;5&quot;:{&quot;1&quot;:2,&quot;2&quot;:0}},{&quot;1&quot;:0,&quot;2&quot;:0,&quot;3&quot;:3},{&quot;1&quot;:1,&quot;2&quot;:0,&quot;4&quot;:1}]},&quot;9&quot;:1,&quot;10&quot;:1,&quot;11&quot;:3,&quot;12&quot;:0,&quot;17&quot;:1}\">Recognition of the limitations and successes of RLHF, fostering a balanced perspective on its utility and application potential.<br \/>\n<\/span><\/li>\n<\/ol>\n","protected":false},"excerpt":{"rendered":"<p>Reinforcement learning is an optimisation framework for sequential decision-making problems, where an agent interacts with an environment, takes actions, and receives feedback (rewards). It is successfully applied in domains such as games, robotics and recommendation systems. One of the important successes of RL is its role in training Large Language Models, particularly the GPT. Reinforcement [&hellip;]<\/p>\n","protected":false},"author":1,"featured_media":1790,"parent":1126,"menu_order":0,"comment_status":"closed","ping_status":"closed","template":"session-details.php","meta":[],"acf":[],"yoast_head":"<!-- This site is optimized with the Yoast SEO plugin v20.7 - https:\/\/yoast.com\/wordpress\/plugins\/seo\/ -->\n<title>Fine-tuning a Language Model with RLHF - DataHack Summit 2023<\/title>\n<meta name=\"robots\" content=\"index, follow, max-snippet:-1, max-image-preview:large, max-video-preview:-1\" \/>\n<link rel=\"canonical\" href=\"https:\/\/www.analyticsvidhya.com\/dhs-2023\/session\/fine-tuning-a-language-model-with-rlhf-2\/\" \/>\n<meta property=\"og:locale\" content=\"en_US\" \/>\n<meta property=\"og:type\" content=\"article\" \/>\n<meta property=\"og:title\" content=\"Fine-tuning a Language Model with RLHF - DataHack Summit 2023\" \/>\n<meta property=\"og:description\" content=\"Reinforcement learning is an optimisation framework for sequential decision-making problems, where an agent interacts with an environment, takes actions, and receives feedback (rewards). It is successfully applied in domains such as games, robotics and recommendation systems. One of the important successes of RL is its role in training Large Language Models, particularly the GPT. Reinforcement [&hellip;]\" \/>\n<meta property=\"og:url\" content=\"https:\/\/www.analyticsvidhya.com\/dhs-2023\/session\/fine-tuning-a-language-model-with-rlhf-2\/\" \/>\n<meta property=\"og:site_name\" content=\"DataHack Summit 2023\" \/>\n<meta property=\"article:modified_time\" content=\"2023-07-19T13:35:58+00:00\" \/>\n<meta property=\"og:image\" content=\"https:\/\/www.analyticsvidhya.com\/dhs-2023\/wp-content\/uploads\/2023\/06\/s-language-modelwith-rlhf.jpg\" \/>\n\t<meta property=\"og:image:width\" content=\"500\" \/>\n\t<meta property=\"og:image:height\" content=\"250\" \/>\n\t<meta property=\"og:image:type\" content=\"image\/jpeg\" \/>\n<meta name=\"twitter:card\" content=\"summary_large_image\" \/>\n<meta name=\"twitter:label1\" content=\"Est. reading time\" \/>\n\t<meta name=\"twitter:data1\" content=\"1 minute\" \/>\n<script type=\"application\/ld+json\" class=\"yoast-schema-graph\">{\"@context\":\"https:\/\/schema.org\",\"@graph\":[{\"@type\":\"WebPage\",\"@id\":\"https:\/\/www.analyticsvidhya.com\/dhs-2023\/session\/fine-tuning-a-language-model-with-rlhf-2\/\",\"url\":\"https:\/\/www.analyticsvidhya.com\/dhs-2023\/session\/fine-tuning-a-language-model-with-rlhf-2\/\",\"name\":\"Fine-tuning a Language Model with RLHF - DataHack Summit 2023\",\"isPartOf\":{\"@id\":\"https:\/\/www.analyticsvidhya.com\/dhs-2023\/#website\"},\"datePublished\":\"2023-06-20T09:01:00+00:00\",\"dateModified\":\"2023-07-19T13:35:58+00:00\",\"breadcrumb\":{\"@id\":\"https:\/\/www.analyticsvidhya.com\/dhs-2023\/session\/fine-tuning-a-language-model-with-rlhf-2\/#breadcrumb\"},\"inLanguage\":\"en-US\",\"potentialAction\":[{\"@type\":\"ReadAction\",\"target\":[\"https:\/\/www.analyticsvidhya.com\/dhs-2023\/session\/fine-tuning-a-language-model-with-rlhf-2\/\"]}]},{\"@type\":\"BreadcrumbList\",\"@id\":\"https:\/\/www.analyticsvidhya.com\/dhs-2023\/session\/fine-tuning-a-language-model-with-rlhf-2\/#breadcrumb\",\"itemListElement\":[{\"@type\":\"ListItem\",\"position\":1,\"name\":\"Home\",\"item\":\"https:\/\/www.analyticsvidhya.com\/dhs-2023\/\"},{\"@type\":\"ListItem\",\"position\":2,\"name\":\"Session\",\"item\":\"https:\/\/www.analyticsvidhya.com\/dhs-2023\/session\/\"},{\"@type\":\"ListItem\",\"position\":3,\"name\":\"Fine-tuning a Language Model with RLHF\"}]},{\"@type\":\"WebSite\",\"@id\":\"https:\/\/www.analyticsvidhya.com\/dhs-2023\/#website\",\"url\":\"https:\/\/www.analyticsvidhya.com\/dhs-2023\/\",\"name\":\"DataHack Summit 2023\",\"description\":\"\",\"potentialAction\":[{\"@type\":\"SearchAction\",\"target\":{\"@type\":\"EntryPoint\",\"urlTemplate\":\"https:\/\/www.analyticsvidhya.com\/dhs-2023\/?s={search_term_string}\"},\"query-input\":\"required name=search_term_string\"}],\"inLanguage\":\"en-US\"}]}<\/script>\n<!-- \/ Yoast SEO plugin. -->","yoast_head_json":{"title":"Fine-tuning a Language Model with RLHF - DataHack Summit 2023","robots":{"index":"index","follow":"follow","max-snippet":"max-snippet:-1","max-image-preview":"max-image-preview:large","max-video-preview":"max-video-preview:-1"},"canonical":"https:\/\/www.analyticsvidhya.com\/dhs-2023\/session\/fine-tuning-a-language-model-with-rlhf-2\/","og_locale":"en_US","og_type":"article","og_title":"Fine-tuning a Language Model with RLHF - DataHack Summit 2023","og_description":"Reinforcement learning is an optimisation framework for sequential decision-making problems, where an agent interacts with an environment, takes actions, and receives feedback (rewards). It is successfully applied in domains such as games, robotics and recommendation systems. One of the important successes of RL is its role in training Large Language Models, particularly the GPT. Reinforcement [&hellip;]","og_url":"https:\/\/www.analyticsvidhya.com\/dhs-2023\/session\/fine-tuning-a-language-model-with-rlhf-2\/","og_site_name":"DataHack Summit 2023","article_modified_time":"2023-07-19T13:35:58+00:00","og_image":[{"width":500,"height":250,"url":"https:\/\/www.analyticsvidhya.com\/dhs-2023\/wp-content\/uploads\/2023\/06\/s-language-modelwith-rlhf.jpg","type":"image\/jpeg"}],"twitter_card":"summary_large_image","twitter_misc":{"Est. reading time":"1 minute"},"schema":{"@context":"https:\/\/schema.org","@graph":[{"@type":"WebPage","@id":"https:\/\/www.analyticsvidhya.com\/dhs-2023\/session\/fine-tuning-a-language-model-with-rlhf-2\/","url":"https:\/\/www.analyticsvidhya.com\/dhs-2023\/session\/fine-tuning-a-language-model-with-rlhf-2\/","name":"Fine-tuning a Language Model with RLHF - DataHack Summit 2023","isPartOf":{"@id":"https:\/\/www.analyticsvidhya.com\/dhs-2023\/#website"},"datePublished":"2023-06-20T09:01:00+00:00","dateModified":"2023-07-19T13:35:58+00:00","breadcrumb":{"@id":"https:\/\/www.analyticsvidhya.com\/dhs-2023\/session\/fine-tuning-a-language-model-with-rlhf-2\/#breadcrumb"},"inLanguage":"en-US","potentialAction":[{"@type":"ReadAction","target":["https:\/\/www.analyticsvidhya.com\/dhs-2023\/session\/fine-tuning-a-language-model-with-rlhf-2\/"]}]},{"@type":"BreadcrumbList","@id":"https:\/\/www.analyticsvidhya.com\/dhs-2023\/session\/fine-tuning-a-language-model-with-rlhf-2\/#breadcrumb","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https:\/\/www.analyticsvidhya.com\/dhs-2023\/"},{"@type":"ListItem","position":2,"name":"Session","item":"https:\/\/www.analyticsvidhya.com\/dhs-2023\/session\/"},{"@type":"ListItem","position":3,"name":"Fine-tuning a Language Model with RLHF"}]},{"@type":"WebSite","@id":"https:\/\/www.analyticsvidhya.com\/dhs-2023\/#website","url":"https:\/\/www.analyticsvidhya.com\/dhs-2023\/","name":"DataHack Summit 2023","description":"","potentialAction":[{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https:\/\/www.analyticsvidhya.com\/dhs-2023\/?s={search_term_string}"},"query-input":"required name=search_term_string"}],"inLanguage":"en-US"}]}},"_links":{"self":[{"href":"https:\/\/www.analyticsvidhya.com\/dhs-2023\/wp-json\/wp\/v2\/pages\/1789"}],"collection":[{"href":"https:\/\/www.analyticsvidhya.com\/dhs-2023\/wp-json\/wp\/v2\/pages"}],"about":[{"href":"https:\/\/www.analyticsvidhya.com\/dhs-2023\/wp-json\/wp\/v2\/types\/page"}],"author":[{"embeddable":true,"href":"https:\/\/www.analyticsvidhya.com\/dhs-2023\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/www.analyticsvidhya.com\/dhs-2023\/wp-json\/wp\/v2\/comments?post=1789"}],"version-history":[{"count":3,"href":"https:\/\/www.analyticsvidhya.com\/dhs-2023\/wp-json\/wp\/v2\/pages\/1789\/revisions"}],"predecessor-version":[{"id":2147,"href":"https:\/\/www.analyticsvidhya.com\/dhs-2023\/wp-json\/wp\/v2\/pages\/1789\/revisions\/2147"}],"up":[{"embeddable":true,"href":"https:\/\/www.analyticsvidhya.com\/dhs-2023\/wp-json\/wp\/v2\/pages\/1126"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/www.analyticsvidhya.com\/dhs-2023\/wp-json\/wp\/v2\/media\/1790"}],"wp:attachment":[{"href":"https:\/\/www.analyticsvidhya.com\/dhs-2023\/wp-json\/wp\/v2\/media?parent=1789"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}