{"id":477797,"date":"2023-08-09T09:20:26","date_gmt":"2023-08-09T09:20:26","guid":{"rendered":""},"modified":"2023-09-05T11:15:26","modified_gmt":"2023-09-05T11:15:26","slug":"large-language-models","status":"publish","type":"wiki","link":"https:\/\/oneproxy.pro\/tr\/wiki\/large-language-models\/","title":{"rendered":"B\u00fcy\u00fck dil modelleri"},"content":{"rendered":"<p>B\u00fcy\u00fck dil modelleri, insan dilini anlamak ve olu\u015fturmak i\u00e7in tasarlanm\u0131\u015f bir t\u00fcr yapay zeka (AI) teknolojisidir. Ola\u011fan\u00fcst\u00fc dil i\u015fleme yetenekleri elde etmek i\u00e7in derin \u00f6\u011frenme algoritmalar\u0131ndan ve b\u00fcy\u00fck miktarda veriden yararlan\u0131rlar. Bu modeller, do\u011fal dil i\u015fleme, makine \u00e7evirisi, duygu analizi, sohbet robotlar\u0131 ve daha fazlas\u0131 dahil olmak \u00fczere \u00e7e\u015fitli alanlarda devrim yaratt\u0131.<\/p>\n<h2>B\u00fcy\u00fck Dil Modellerinin K\u00f6keni Tarihi<\/h2>\n<p>Dil modellerini kullanma fikri yapay zeka ara\u015ft\u0131rmalar\u0131n\u0131n ilk g\u00fcnlerine kadar uzan\u0131yor. Ancak b\u00fcy\u00fck dil modellerindeki at\u0131l\u0131m, derin \u00f6\u011frenmenin ortaya \u00e7\u0131k\u0131\u015f\u0131 ve geni\u015f veri k\u00fcmelerinin kullan\u0131labilirli\u011fi ile 2010&#039;larda ger\u00e7ekle\u015fti. Sinir a\u011flar\u0131 ve s\u00f6zc\u00fck yerle\u015ftirme kavram\u0131, daha g\u00fc\u00e7l\u00fc dil modellerinin geli\u015ftirilmesinin yolunu a\u00e7t\u0131.<\/p>\n<p>B\u00fcy\u00fck dil modellerinin ilk s\u00f6z\u00fc, Tomas Mikolov ve Google&#039;daki meslekta\u015flar\u0131n\u0131n Word2Vec modelini tan\u0131tan 2013 tarihli makalesine kadar uzanabilir. Bu model, bir sinir a\u011f\u0131n\u0131n, s\u00f6zc\u00fckler aras\u0131ndaki anlamsal ili\u015fkileri yakalayarak s\u00fcrekli bir vekt\u00f6r uzay\u0131nda s\u00f6zc\u00fckleri verimli bir \u015fekilde temsil edebildi\u011fini g\u00f6sterdi. Bu, daha karma\u015f\u0131k dil modellerinin geli\u015ftirilmesinin yolunu a\u00e7t\u0131.<\/p>\n<h2>B\u00fcy\u00fck Dil Modelleri Hakk\u0131nda Detayl\u0131 Bilgi<\/h2>\n<p>B\u00fcy\u00fck dil modelleri, y\u00fcz milyonlarca ila milyarlarca parametre i\u00e7eren devasa boyutlar\u0131yla karakterize edilir. Geleneksel tekrarlayan sinir a\u011flar\u0131ndan (RNN&#039;ler) daha paralel ve verimli bir \u015fekilde dil i\u015flemelerine ve \u00fcretmelerine olanak tan\u0131yan transformat\u00f6r mimarilerine g\u00fcveniyorlar.<\/p>\n<p>B\u00fcy\u00fck dil modellerinin temel amac\u0131, \u00f6nceki kelimelerin ba\u011flam\u0131 g\u00f6z \u00f6n\u00fcne al\u0131nd\u0131\u011f\u0131nda bir sonraki kelimenin olas\u0131l\u0131\u011f\u0131n\u0131 tahmin etmektir. Dil modelleme olarak bilinen bu s\u00fcre\u00e7, \u00e7e\u015fitli do\u011fal dil anlama ve olu\u015fturma g\u00f6revlerinin temelini olu\u015fturur.<\/p>\n<h2>B\u00fcy\u00fck Dil Modellerinin \u0130\u00e7 Yap\u0131s\u0131<\/h2>\n<p>B\u00fcy\u00fck dil modelleri, birden fazla \u00f6z-dikkat mekanizmas\u0131 katman\u0131ndan olu\u015fan d\u00f6n\u00fc\u015ft\u00fcr\u00fcc\u00fc mimariler kullan\u0131larak olu\u015fturulur. \u00d6z-dikkat mekanizmas\u0131, modelin t\u00fcm girdi dizisi ba\u011flam\u0131nda her kelimenin \u00f6nemini tartmas\u0131na olanak tan\u0131yarak, uzun vadeli ba\u011f\u0131ml\u0131l\u0131klar\u0131 etkili bir \u015fekilde yakalamas\u0131na olanak tan\u0131r.<\/p>\n<p>Transformat\u00f6r mimarisinin temel bile\u015feni, de\u011ferlerin (genellikle kelimelerin yerle\u015ftirilmesi) a\u011f\u0131rl\u0131kl\u0131 toplam\u0131n\u0131, bir sorguyla (ba\u015fka bir kelimenin yerle\u015ftirilmesi) ilgilerine g\u00f6re hesaplayan \u201cdikkat\u201d mekanizmas\u0131d\u0131r. Bu dikkat mekanizmas\u0131, model boyunca paralel i\u015flemeyi ve verimli bilgi ak\u0131\u015f\u0131n\u0131 kolayla\u015ft\u0131r\u0131r.<\/p>\n<h2>B\u00fcy\u00fck Dil Modellerinin Temel \u00d6zelliklerinin Analizi<\/h2>\n<p>B\u00fcy\u00fck dil modellerinin temel \u00f6zellikleri \u015funlard\u0131r:<\/p>\n<ol>\n<li>\n<p><strong>B\u00fcy\u00fck Boyut:<\/strong> B\u00fcy\u00fck dil modelleri, karma\u015f\u0131k dil kal\u0131plar\u0131n\u0131 ve n\u00fcanslar\u0131 yakalamalar\u0131na olanak tan\u0131yan \u00e7ok say\u0131da parametreye sahiptir.<\/p>\n<\/li>\n<li>\n<p><strong>Ba\u011flamsal Anlama:<\/strong> Bu modeller, bir kelimenin anlam\u0131n\u0131, i\u00e7inde bulundu\u011fu ba\u011flama g\u00f6re anlayabilir ve bu da daha do\u011fru bir dil i\u015flemeye yol a\u00e7ar.<\/p>\n<\/li>\n<li>\n<p><strong>\u00d6\u011frenimi Aktar:<\/strong> B\u00fcy\u00fck dil modelleri, minimum d\u00fczeyde ek e\u011fitim verisi ile belirli g\u00f6revlere g\u00f6re ince ayar yap\u0131labilir, bu da onlar\u0131 \u00e7ok y\u00f6nl\u00fc ve \u00e7e\u015fitli uygulamalara uyarlanabilir hale getirir.<\/p>\n<\/li>\n<li>\n<p><strong>Metin \u00dcretiminde Yarat\u0131c\u0131l\u0131k:<\/strong> Tutarl\u0131 ve ba\u011flamsal olarak alakal\u0131 metinler \u00fcretebilirler, bu da onlar\u0131 sohbet robotlar\u0131, i\u00e7erik olu\u015fturma ve daha fazlas\u0131 i\u00e7in de\u011ferli k\u0131lar.<\/p>\n<\/li>\n<li>\n<p><strong>\u00c7ok Dilli Yetenekler:<\/strong> B\u00fcy\u00fck dil modelleri, birden fazla dilde metin i\u015fleyip \u00fcretebilir ve bu da k\u00fcresel uygulamalar\u0131 kolayla\u015ft\u0131r\u0131r.<\/p>\n<\/li>\n<\/ol>\n<h2>B\u00fcy\u00fck Dil Modeli T\u00fcrleri<\/h2>\n<p>B\u00fcy\u00fck dil modelleri \u00e7e\u015fitli boyutlarda ve konfig\u00fcrasyonlarda gelir. Baz\u0131 pop\u00fcler t\u00fcrler \u015funlar\u0131 i\u00e7erir:<\/p>\n<table>\n<thead>\n<tr>\n<th>Modeli<\/th>\n<th>Parametreler<\/th>\n<th>Tan\u0131m<\/th>\n<\/tr>\n<\/thead>\n<tbody>\n<tr>\n<td>GPT-3<\/td>\n<td>175 milyar<\/td>\n<td>OpenAI taraf\u0131ndan bilinen en b\u00fcy\u00fck modellerden biri.<\/td>\n<\/tr>\n<tr>\n<td>BERT (Transformat\u00f6rlerden \u00c7ift Y\u00f6nl\u00fc Kodlay\u0131c\u0131 G\u00f6sterimleri)<\/td>\n<td>340 milyon<\/td>\n<td>Google taraf\u0131ndan tan\u0131t\u0131lan, \u00e7ift y\u00f6nl\u00fc g\u00f6revlerde m\u00fckemmeldir.<\/td>\n<\/tr>\n<tr>\n<td>RoBERTa<\/td>\n<td>355 milyon<\/td>\n<td>BERT&#039;in \u00f6n e\u011fitim i\u00e7in daha da optimize edilmi\u015f bir \u00e7e\u015fidi.<\/td>\n<\/tr>\n<tr>\n<td>XLNet<\/td>\n<td>340 milyon<\/td>\n<td>Perm\u00fctasyona dayal\u0131 e\u011fitimden yararlanarak performans\u0131 art\u0131r\u0131r.<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n<h2>B\u00fcy\u00fck Dil Modellerini Kullanma Yollar\u0131, Sorunlar ve \u00c7\u00f6z\u00fcmler<\/h2>\n<h3>B\u00fcy\u00fck Dil Modellerini Kullanma Yollar\u0131<\/h3>\n<p>B\u00fcy\u00fck dil modelleri a\u015fa\u011f\u0131dakiler de dahil olmak \u00fczere \u00e7e\u015fitli alanlarda uygulama alan\u0131 bulur:<\/p>\n<ul>\n<li><strong>Do\u011fal Dil \u0130\u015fleme (NLP):<\/strong> Duygu analizi, adland\u0131r\u0131lm\u0131\u015f varl\u0131k tan\u0131ma ve metin s\u0131n\u0131fland\u0131rma gibi uygulamalarda insan dilini anlama ve i\u015fleme.<\/li>\n<li><strong>Makine \u00c7evirisi:<\/strong> Diller aras\u0131nda daha do\u011fru ve ba\u011flama duyarl\u0131 \u00e7eviriyi etkinle\u015ftirme.<\/li>\n<li><strong>Soru-Cevap Sistemleri:<\/strong> Kullan\u0131c\u0131 sorgular\u0131na anlaml\u0131 yan\u0131tlar sa\u011flayarak sohbet robotlar\u0131na ve sanal asistanlara g\u00fc\u00e7 veriyoruz.<\/li>\n<li><strong>Metin Olu\u015fturma:<\/strong> \u0130\u00e7erik olu\u015fturma, hikaye anlat\u0131m\u0131 ve yarat\u0131c\u0131 yazma i\u00e7in insan benzeri metinler olu\u015fturmak.<\/li>\n<\/ul>\n<h3>Sorunlar ve \u00c7\u00f6z\u00fcmler<\/h3>\n<p>B\u00fcy\u00fck dil modelleri a\u015fa\u011f\u0131dakiler de dahil olmak \u00fczere baz\u0131 zorluklarla kar\u015f\u0131 kar\u015f\u0131yad\u0131r:<\/p>\n<ul>\n<li><strong>Kaynak Yo\u011fun:<\/strong> E\u011fitim ve \u00e7\u0131kar\u0131m, g\u00fc\u00e7l\u00fc donan\u0131m ve \u00f6nemli hesaplama kaynaklar\u0131 gerektirir.<\/li>\n<li><strong>\u00d6nyarg\u0131 ve Adalet:<\/strong> Modeller, e\u011fitim verilerinde mevcut \u00f6nyarg\u0131lar\u0131 devralabilir ve bu da \u00f6nyarg\u0131l\u0131 \u00e7\u0131kt\u0131lara yol a\u00e7abilir.<\/li>\n<li><strong>Gizlilik endi\u015feleri:<\/strong> Tutarl\u0131 metin olu\u015fturmak, yanl\u0131\u015fl\u0131kla hassas bilgilerin if\u015fa edilmesine yol a\u00e7abilir.<\/li>\n<\/ul>\n<p>Bu sorunlar\u0131 \u00e7\u00f6zmek i\u00e7in ara\u015ft\u0131rmac\u0131lar ve geli\u015ftiriciler aktif olarak a\u015fa\u011f\u0131dakiler \u00fczerinde \u00e7al\u0131\u015fmaktad\u0131r:<\/p>\n<ul>\n<li><strong>Verimli Mimariler:<\/strong> Hesaplama gereksinimlerini azaltmak i\u00e7in daha ak\u0131c\u0131 modeller tasarlamak.<\/li>\n<li><strong>\u00d6nyarg\u0131 Azaltma:<\/strong> Dil modellerindeki \u00f6nyarg\u0131lar\u0131 azaltmaya ve tespit etmeye y\u00f6nelik tekniklerin uygulanmas\u0131.<\/li>\n<li><strong>Etik kurallar:<\/strong> Sorumlu yapay zeka uygulamalar\u0131n\u0131 te\u015fvik etmek ve etik sonu\u00e7lar\u0131 dikkate almak.<\/li>\n<\/ul>\n<h2>Ana \u00d6zellikler ve Benzer Terimlerle Kar\u015f\u0131la\u015ft\u0131rmalar<\/h2>\n<p>B\u00fcy\u00fck dil modellerinin benzer dil teknolojileriyle kar\u015f\u0131la\u015ft\u0131r\u0131lmas\u0131:<\/p>\n<table>\n<thead>\n<tr>\n<th>Terim<\/th>\n<th>Tan\u0131m<\/th>\n<\/tr>\n<\/thead>\n<tbody>\n<tr>\n<td>B\u00fcy\u00fck Dil Modelleri<\/td>\n<td>NLP g\u00f6revlerinde m\u00fckemmelle\u015fen, milyarlarca parametreye sahip devasa yapay zeka modelleri.<\/td>\n<\/tr>\n<tr>\n<td>Kelime G\u00f6mmeleri<\/td>\n<td>Anlamsal ili\u015fkileri yakalayan kelimelerin vekt\u00f6r temsilleri.<\/td>\n<\/tr>\n<tr>\n<td>Tekrarlayan Sinir A\u011flar\u0131 (RNN&#039;ler)<\/td>\n<td>Dil i\u015fleme i\u00e7in geleneksel s\u0131ral\u0131 modeller.<\/td>\n<\/tr>\n<tr>\n<td>Makine \u00c7evirisi<\/td>\n<td>Diller aras\u0131 \u00e7eviriyi m\u00fcmk\u00fcn k\u0131lan teknoloji.<\/td>\n<\/tr>\n<tr>\n<td>Duygu Analizi<\/td>\n<td>Metin verilerindeki duyarl\u0131l\u0131\u011f\u0131n (olumlu\/olumsuz) belirlenmesi.<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n<h2>Gelece\u011fin Perspektifleri ve Teknolojileri<\/h2>\n<p>B\u00fcy\u00fck dil modellerinin gelece\u011fi umut vericidir ve devam eden ara\u015ft\u0131rmalar a\u015fa\u011f\u0131dakilere odaklanm\u0131\u015ft\u0131r:<\/p>\n<ul>\n<li><strong>Yeterlik:<\/strong> Hesaplama maliyetlerini azaltmak i\u00e7in daha verimli mimariler geli\u015ftirmek.<\/li>\n<li><strong>\u00c7ok Modlu \u00d6\u011frenme:<\/strong> Anlamay\u0131 geli\u015ftirmek i\u00e7in dil modellerini g\u00f6r\u00fcnt\u00fc ve ses ile entegre etme.<\/li>\n<li><strong>S\u0131f\u0131r At\u0131\u015fl\u0131 \u00d6\u011frenme:<\/strong> Modellerin belirli bir e\u011fitim gerektirmeden g\u00f6revleri yerine getirmesine olanak tan\u0131yarak uyarlanabilirli\u011fi art\u0131r\u0131r.<\/li>\n<li><strong>S\u00fcrekli \u00d6\u011frenme:<\/strong> Modellerin \u00f6nceki bilgileri korurken yeni verilerden \u00f6\u011frenmesine izin vermek.<\/li>\n<\/ul>\n<h2>Proxy Sunucular\u0131 ve B\u00fcy\u00fck Dil Modelleriyle \u0130li\u015fkileri<\/h2>\n<p>Proxy sunucular\u0131, istemciler ve internet aras\u0131nda arac\u0131 g\u00f6revi g\u00f6r\u00fcr. B\u00fcy\u00fck dil modeli uygulamalar\u0131n\u0131 \u00e7e\u015fitli \u015fekillerde geli\u015ftirebilirler:<\/p>\n<ol>\n<li><strong>Veri toplama:<\/strong> Proxy sunucular\u0131 kullan\u0131c\u0131 verilerini anonimle\u015ftirerek model e\u011fitimi i\u00e7in etik veri toplanmas\u0131n\u0131 kolayla\u015ft\u0131rabilir.<\/li>\n<li><strong>Gizlilik ve g\u00fcvenlik:<\/strong> Proxy sunucular\u0131 ekstra bir g\u00fcvenlik katman\u0131 ekleyerek kullan\u0131c\u0131lar\u0131 ve modelleri potansiyel tehditlerden korur.<\/li>\n<li><strong>Da\u011f\u0131t\u0131lm\u0131\u015f \u00c7\u0131kar\u0131m:<\/strong> Proxy sunucular\u0131, model \u00e7\u0131kar\u0131m\u0131n\u0131 birden fazla konuma da\u011f\u0131tarak gecikmeyi azaltabilir ve yan\u0131t s\u00fcrelerini iyile\u015ftirebilir.<\/li>\n<\/ol>\n<h2>\u0130lgili Ba\u011flant\u0131lar<\/h2>\n<p>B\u00fcy\u00fck dil modelleri hakk\u0131nda daha fazla bilgi i\u00e7in a\u015fa\u011f\u0131daki kaynaklar\u0131 inceleyebilirsiniz:<\/p>\n<ul>\n<li><a href=\"https:\/\/openai.com\/models\/gpt-3\" target=\"_new\" rel=\"noopener nofollow\">OpenAI&#039;nin GPT-3&#039;\u00fc<\/a><\/li>\n<li><a href=\"https:\/\/arxiv.org\/abs\/1810.04805\" target=\"_new\" rel=\"noopener nofollow\">BERT: Dil Anlamak i\u00e7in Derin \u00c7ift Y\u00f6nl\u00fc Transformat\u00f6rlerin \u00d6n E\u011fitimi<\/a><\/li>\n<li><a href=\"https:\/\/arxiv.org\/abs\/1906.08237\" target=\"_new\" rel=\"noopener nofollow\">XLNet: Dil Anlamak i\u00e7in Genelle\u015ftirilmi\u015f Otoregresif \u00d6n E\u011fitim<\/a><\/li>\n<li><a href=\"https:\/\/oneproxy.pro\/tr\/\" target=\"_new\" rel=\"noopener\">Proxy Sunucu Sa\u011flay\u0131c\u0131s\u0131 \u2013 OneProxy<\/a><\/li>\n<\/ul>\n<p>B\u00fcy\u00fck dil modelleri \u015f\u00fcphesiz do\u011fal dil i\u015fleme ve yapay zeka uygulamalar\u0131n\u0131n manzaras\u0131n\u0131 d\u00f6n\u00fc\u015ft\u00fcrd\u00fc. Ara\u015ft\u0131rmalar ilerledik\u00e7e ve teknoloji ilerledik\u00e7e gelecekte daha da heyecan verici geli\u015fmeler ve uygulamalar bekleyebiliriz. Proxy sunucular\u0131, bu g\u00fc\u00e7l\u00fc dil modellerinin sorumlu ve verimli kullan\u0131m\u0131n\u0131 desteklemede \u00f6nemli bir rol oynamaya devam edecektir.<\/p>","protected":false},"featured_media":468753,"menu_order":0,"template":"","meta":{"_acf_changed":false,"content-type":"","inline_featured_image":false,"footnotes":""},"class_list":["post-477797","wiki","type-wiki","status-publish","has-post-thumbnail","hentry"],"acf":{"faq_title":"Frequently Asked Questions about <mark>Large Language Models<\/mark>","faq_items":[{"question":"What are Large Language Models?","answer":"<p>Large language models are advanced AI technologies designed to understand and generate human language. They utilize deep learning algorithms and massive data sets to achieve impressive language processing capabilities, revolutionizing various fields like natural language processing, machine translation, chatbots, and more.<\/p>"},{"question":"How did Large Language Models originate?","answer":"<p>The concept of language models has a long history in AI research, but the breakthrough for large language models came in the 2010s with the emergence of deep learning and access to vast datasets. The first mention of large language models can be traced back to a 2013 paper by Tomas Mikolov and colleagues at Google, introducing the Word2Vec model.<\/p>"},{"question":"How do Large Language Models work?","answer":"<p>Large language models rely on transformer architectures, which consist of multiple layers of self-attention mechanisms. These mechanisms enable the models to process and generate language more efficiently and in parallel. The models' primary objective is to predict the likelihood of the next word in a sequence based on the context of preceding words, known as language modeling.<\/p>"},{"question":"What are the key features of Large Language Models?","answer":"<p>The key features of large language models include their massive size with hundreds of millions to billions of parameters, contextual understanding of words based on the surrounding context, transfer learning for versatile applications, creativity in text generation, and multilingual capabilities.<\/p>"},{"question":"What types of Large Language Models exist?","answer":"<p>Various types of large language models are available, each with different parameter sizes and strengths. Some popular ones include GPT-3, BERT, RoBERTa, and XLNet, each excelling in specific language processing tasks.<\/p>"},{"question":"How are Large Language Models used, and what problems do they face?","answer":"<p>Large language models find application in natural language processing, machine translation, chatbots, and content generation. However, they face challenges like resource-intensive training, potential bias in outputs, and privacy concerns. Solutions include efficient architectures, bias mitigation techniques, and ethical guidelines.<\/p>"},{"question":"How do Large Language Models compare with other language technologies?","answer":"<p>Large language models differ from word embeddings, recurrent neural networks (RNNs), machine translation, and sentiment analysis in terms of scale, applications, and processing capabilities.<\/p>"},{"question":"What are the future perspectives of Large Language Models?","answer":"<p>The future of large language models looks promising with research focusing on efficiency, multimodal learning, zero-shot learning, and continual learning, enabling even more powerful and adaptable language processing systems.<\/p>"},{"question":"How are Proxy Servers associated with Large Language Models?","answer":"<p>Proxy servers play a vital role in supporting large language models by anonymizing user data for ethical data collection, enhancing security, and enabling distributed model inference for improved response times.<\/p>"},{"question":"Where can I find more information about Large Language Models?","answer":"<p>For further information about large language models, explore the following resources:<\/p><ul><li>OpenAI's GPT-3 (<a href=\"https:\/\/openai.com\/models\/gpt-3\" target=\"_new\">https:\/\/openai.com\/models\/gpt-3<\/a>)<\/li><li>BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding (<a href=\"https:\/\/arxiv.org\/abs\/1810.04805\" target=\"_new\">https:\/\/arxiv.org\/abs\/1810.04805<\/a>)<\/li><li>XLNet: Generalized Autoregressive Pretraining for Language Understanding (<a href=\"https:\/\/arxiv.org\/abs\/1906.08237\" target=\"_new\">https:\/\/arxiv.org\/abs\/1906.08237<\/a>)<\/li><li>Proxy Server Provider - OneProxy (<a href=\"https:\/\/oneproxy.pro\" target=\"_new\">https:\/\/oneproxy.pro<\/a>)<\/li><\/ul><p>At OneProxy, we embrace the world of language AI and provide top-notch proxy server solutions to support your AI-driven endeavors.<\/p>"}]},"_links":{"self":[{"href":"https:\/\/oneproxy.pro\/tr\/wp-json\/wp\/v2\/wiki\/477797","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/oneproxy.pro\/tr\/wp-json\/wp\/v2\/wiki"}],"about":[{"href":"https:\/\/oneproxy.pro\/tr\/wp-json\/wp\/v2\/types\/wiki"}],"version-history":[{"count":0,"href":"https:\/\/oneproxy.pro\/tr\/wp-json\/wp\/v2\/wiki\/477797\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/oneproxy.pro\/tr\/wp-json\/wp\/v2\/media\/468753"}],"wp:attachment":[{"href":"https:\/\/oneproxy.pro\/tr\/wp-json\/wp\/v2\/media?parent=477797"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}