{"id":4052,"date":"2023-11-04T23:14:02","date_gmt":"2023-11-04T23:14:02","guid":{"rendered":"http:\/\/localhost:10003\/how-to-use-llms-for-text-style-transfer-and-adaptation\/"},"modified":"2023-11-05T05:48:01","modified_gmt":"2023-11-05T05:48:01","slug":"how-to-use-llms-for-text-style-transfer-and-adaptation","status":"publish","type":"post","link":"http:\/\/localhost:10003\/how-to-use-llms-for-text-style-transfer-and-adaptation\/","title":{"rendered":"How to use LLMs for text style transfer and adaptation"},"content":{"rendered":"<p>In recent years, there has been significant progress in natural language processing (NLP) techniques, particularly in the field of language generation. One such advancement is the development of Large Language Models (LLMs), which have shown impressive capabilities in generating coherent and contextually relevant text. LLMs have gained popularity in various applications such as chatbots, language translation, summarization, and text generation, among others.<\/p>\n<p>Text style transfer and adaptation is one area where LLMs can be particularly useful. It involves modifying the style or tone of a given input text while preserving its meaning and content. For example, it can be used to convert a formal email into a more casual conversation or transform a positive review into a negative one.<\/p>\n<p>In this tutorial, we will explore how to use LLMs for text style transfer and adaptation using a pre-trained model. We will cover the following steps:<\/p>\n<ol>\n<li>Introduction to Language Models<\/li>\n<li>Types of Language Models<\/li>\n<li>Pre-trained LLMs for Style Transfer<\/li>\n<li>Fine-tuning a Pre-trained LLM<\/li>\n<li>Evaluating Style Transfer Performance<\/li>\n<li>Limitations and Future Directions<\/li>\n<\/ol>\n<p>Before we dive into the specifics, it is essential to have a basic understanding of language models.<\/p>\n<h2>1. Introduction to Language Models<\/h2>\n<p>A language model is a statistical model that assigns probabilities to sequences of words or characters in a language. It learns the patterns and relationships between different words and predicts the likelihood of a word given its context. Language models are trained on large corpora of text, such as books, articles, and websites, which allows them to capture the nuances and intricacies of natural language.<\/p>\n<p>There are two primary types of language models:<\/p>\n<ul>\n<li><strong>Count-based models<\/strong>: These models use statistical techniques, such as n-gram models, to estimate the probabilities of word sequences based on their observed frequencies in the training data. While they are relatively simple and computationally efficient, they have limited ability to capture long-range dependencies and context.<\/p>\n<\/li>\n<li>\n<p><strong>Neural language models<\/strong>: These models employ neural networks, specifically Recurrent Neural Networks (RNNs), Long Short-Term Memory (LSTM), or Transformers, to learn word embeddings and predict the next word in a sequence based on the previous words. Neural language models can capture complex relationships between words, generate coherent text, and have greater context awareness.<\/p>\n<\/li>\n<\/ul>\n<p>Next, let&#8217;s explore pre-trained LLMs that can be used for style transfer tasks.<\/p>\n<h2>2. Types of Pre-trained LLMs for Style Transfer<\/h2>\n<p>Several pre-trained LLMs are widely available that can be fine-tuned for style transfer tasks. Two popular LLM architectures used for style transfer are:<\/p>\n<ul>\n<li><strong>GPT (Generative Pre-trained Transformer)<\/strong>: Developed by OpenAI, GPT is one of the most well-known and widely used LLM architectures. It uses a transformer architecture and is trained on a large corpus of text from the internet. GPT can generate high-quality text and is known for its context understanding capabilities.<\/p>\n<\/li>\n<li>\n<p><strong>BERT (Bidirectional Encoder Representations from Transformers)<\/strong>: Developed by Google, BERT is another widely used LLM architecture. It utilizes a transformer encoder network and is pre-trained on a large corpus of text from the internet. BERT has the ability to understand the context bidirectionally, enabling it to generate coherent and contextually relevant text.<\/p>\n<\/li>\n<\/ul>\n<p>Both GPT and BERT can be fine-tuned to perform style transfer tasks by training them on a dataset specifically created for the desired style adaptation.<\/p>\n<h2>3. Pre-trained LLMs for Text Style Transfer<\/h2>\n<p>To perform text style transfer using pre-trained LLMs, we need to follow these steps:<\/p>\n<h3>Step 1: Prepare the Data<\/h3>\n<p>For style transfer tasks, it is essential to have a labeled dataset that includes both the source text and corresponding style labels. The source text can be in any format, such as sentences or paragraphs, and the style labels can be binary categories (e.g., positive\/negative) or multi-class (e.g., formal\/casual\/social).<\/p>\n<h3>Step 2: Fine-tuning the LLM<\/h3>\n<p>The pre-trained LLM is then fine-tuned using the labeled dataset prepared in the previous step. Fine-tuning involves updating the model&#8217;s parameters using the labeled data to make it adapt to the desired style.<\/p>\n<p>The fine-tuning process typically involves the following steps:<\/p>\n<ol>\n<li>Tokenization: The input text is divided into tokens (words or subwords), and special tokens are added to indicate the start and end of the text.<\/li>\n<li>Encoding: The tokens are then encoded into numerical representations that can be fed into the LLM.<\/li>\n<li>Style Label Integration: The style labels are incorporated into the input text representation. This can be done by adding a special token at the beginning or appending the label to the input text.<\/li>\n<li>Training: The fine-tuning is performed by minimizing a loss function, such as cross-entropy loss or binary cross-entropy loss, between the predicted style of the generated text and the target style label.<\/li>\n<li>Evaluation: The fine-tuned model is evaluated on a validation dataset to assess its performance and adjust the hyperparameters if necessary.<\/li>\n<\/ol>\n<h3>Step 3: Generating Adapted Text<\/h3>\n<p>Once the fine-tuning is complete, we can use the adapted LLM to generate text with the desired style. We can provide the model with the source text and request it to generate text in the target style.<\/p>\n<p>It is important to note that the quality and coherence of the generated text depend on the quality of the labeled training dataset, the amount of training data, the chosen architecture, and the fine-tuning hyperparameters.<\/p>\n<h2>4. Evaluating Style Transfer Performance<\/h2>\n<p>Evaluating the performance of a text style transfer model can be challenging, as it involves assessing the quality of the generated text, the preservation of the content, and the faithful transformation of the style. Several metrics and evaluation techniques can be employed to evaluate the performance, including:<\/p>\n<ul>\n<li><strong>Perplexity<\/strong>: Perplexity measures the model&#8217;s ability to predict the next word in a sequence. Lower perplexity indicates better language modeling performance.<\/p>\n<\/li>\n<li>\n<p><strong>BLEU (Bilingual Evaluation Understudy)<\/strong>: BLEU is a metric commonly used in machine translation tasks. It calculates the similarity between the generated text and a reference text based on n-gram matches.<\/p>\n<\/li>\n<li>\n<p><strong>Style Consistency<\/strong>: It measures the consistency of the generated text with the desired style. A human evaluator can assess the generated text for style attributes and assign scores based on their judgment.<\/p>\n<\/li>\n<li>\n<p><strong>Content Preservation<\/strong>: This metric evaluates the degree to which the generated text preserves the original content while adapting the style. It can be assessed using human evaluation or automated information retrieval metrics such as ROUGE (Recall-Oriented Understudy for Gisting Evaluation).<\/p>\n<\/li>\n<li>\n<p><strong>Qualitative Evaluation<\/strong>: Human evaluators can rate the quality and coherence of the generated text based on their subjective judgment.<\/p>\n<\/li>\n<\/ul>\n<p>It is crucial to use a combination of these evaluation metrics to obtain a comprehensive understanding of the model&#8217;s performance.<\/p>\n<h2>5. Limitations and Future Directions<\/h2>\n<p>While LLMs have shown promising results for text style transfer and adaptation, they do have limitations:<\/p>\n<ul>\n<li><strong>Data Bias<\/strong>: Pre-trained LLMs are often trained on large corpora of text that may contain biases present in the data, leading to the generation of biased or discriminatory text. Efforts are being made to mitigate these biases, but it remains an ongoing challenge.<\/p>\n<\/li>\n<li>\n<p><strong>Controlled Style Transfer<\/strong>: Fine-tuning pre-trained LLMs for specific style transfer tasks can be challenging, as it requires extensive labeled datasets with different target styles. Future research aims to develop better techniques for controlled style transfer with limited labeled data.<\/p>\n<\/li>\n<li>\n<p><strong>Explicit Style Control<\/strong>: Current LLMs do not provide explicit control over the generated style. Future directions include developing methods that allow users to specify and control the desired style more explicitly.<\/p>\n<\/li>\n<li>\n<p><strong>Multimodal Style Transfer<\/strong>: Most style transfer research has focused on text-to-text transformation. Future work will explore multimodal style transfer, considering other modalities such as images and audio.<\/p>\n<\/li>\n<\/ul>\n<p>Despite these limitations, LLMs have immense potential for text style transfer and adaptation. By understanding the underlying architectures, fine-tuning techniques, and evaluation metrics, you can leverage LLMs to generate text that adapts to different styles and tones.<\/p>\n<h2>Conclusion<\/h2>\n<p>In this tutorial, we explored how to use LLMs for text style transfer and adaptation. We discussed the fundamentals of language models, different types of pre-trained LLMs, and the steps involved in fine-tuning for style transfer. We also touched upon the evaluation metrics and limitations of current approaches.<\/p>\n<p>LLMs have made significant strides in generating coherent and contextually relevant text. Their ability to adapt the style of the input text makes them a powerful tool for a wide range of applications. By following the steps outlined in this tutorial, you can start exploring the world of text style transfer using LLMs and push the boundaries of what is possible with NLP.<\/p>\n","protected":false},"excerpt":{"rendered":"<p>In recent years, there has been significant progress in natural language processing (NLP) techniques, particularly in the field of language generation. One such advancement is the development of Large Language Models (LLMs), which have shown impressive capabilities in generating coherent and contextually relevant text. LLMs have gained popularity in various <a href=\"http:\/\/localhost:10003\/how-to-use-llms-for-text-style-transfer-and-adaptation\/\" class=\"btn btn-link continue-link\">Continue Reading<\/a><\/p>\n","protected":false},"author":1,"featured_media":0,"comment_status":"closed","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"_import_markdown_pro_load_document_selector":0,"_import_markdown_pro_submit_text_textarea":"","footnotes":""},"categories":[1],"tags":[1076,245,1075,1074,1073],"yoast_head":"<!-- This site is optimized with the Yoast SEO Premium plugin v21.5 (Yoast SEO v21.5) - https:\/\/yoast.com\/wordpress\/plugins\/seo\/ -->\n<title>How to use LLMs for text style transfer and adaptation - Pantherax Blogs<\/title>\n<meta name=\"robots\" content=\"index, follow, max-snippet:-1, max-image-preview:large, max-video-preview:-1\" \/>\n<link rel=\"canonical\" href=\"http:\/\/localhost:10003\/how-to-use-llms-for-text-style-transfer-and-adaptation\/\" \/>\n<meta property=\"og:locale\" content=\"en_US\" \/>\n<meta property=\"og:type\" content=\"article\" \/>\n<meta property=\"og:title\" content=\"How to use LLMs for text style transfer and adaptation\" \/>\n<meta property=\"og:description\" content=\"In recent years, there has been significant progress in natural language processing (NLP) techniques, particularly in the field of language generation. One such advancement is the development of Large Language Models (LLMs), which have shown impressive capabilities in generating coherent and contextually relevant text. LLMs have gained popularity in various Continue Reading\" \/>\n<meta property=\"og:url\" content=\"http:\/\/localhost:10003\/how-to-use-llms-for-text-style-transfer-and-adaptation\/\" \/>\n<meta property=\"og:site_name\" content=\"Pantherax Blogs\" \/>\n<meta property=\"article:published_time\" content=\"2023-11-04T23:14:02+00:00\" \/>\n<meta property=\"article:modified_time\" content=\"2023-11-05T05:48:01+00:00\" \/>\n<meta name=\"author\" content=\"Panther\" \/>\n<meta name=\"twitter:card\" content=\"summary_large_image\" \/>\n<meta name=\"twitter:label1\" content=\"Written by\" \/>\n\t<meta name=\"twitter:data1\" content=\"Panther\" \/>\n\t<meta name=\"twitter:label2\" content=\"Est. reading time\" \/>\n\t<meta name=\"twitter:data2\" content=\"7 minutes\" \/>\n<script type=\"application\/ld+json\" class=\"yoast-schema-graph\">{\n\t    \"@context\": \"https:\/\/schema.org\",\n\t    \"@graph\": [\n\t        {\n\t            \"@type\": \"Article\",\n\t            \"@id\": \"http:\/\/localhost:10003\/how-to-use-llms-for-text-style-transfer-and-adaptation\/#article\",\n\t            \"isPartOf\": {\n\t                \"@id\": \"http:\/\/localhost:10003\/how-to-use-llms-for-text-style-transfer-and-adaptation\/\"\n\t            },\n\t            \"author\": {\n\t                \"name\": \"Panther\",\n\t                \"@id\": \"http:\/\/localhost:10003\/#\/schema\/person\/b63d816f4964b163e53cbbcffaa0f3d7\"\n\t            },\n\t            \"headline\": \"How to use LLMs for text style transfer and adaptation\",\n\t            \"datePublished\": \"2023-11-04T23:14:02+00:00\",\n\t            \"dateModified\": \"2023-11-05T05:48:01+00:00\",\n\t            \"mainEntityOfPage\": {\n\t                \"@id\": \"http:\/\/localhost:10003\/how-to-use-llms-for-text-style-transfer-and-adaptation\/\"\n\t            },\n\t            \"wordCount\": 1391,\n\t            \"publisher\": {\n\t                \"@id\": \"http:\/\/localhost:10003\/#organization\"\n\t            },\n\t            \"keywords\": [\n\t                \"\\\"adaptation\\\"]\",\n\t                \"\\\"LLMs\\\"\",\n\t                \"\\\"style transfer\\\"\",\n\t                \"\\\"use LLMs\\\"\",\n\t                \"[\\\"text style transfer and adaptation\\\"\"\n\t            ],\n\t            \"inLanguage\": \"en-US\"\n\t        },\n\t        {\n\t            \"@type\": \"WebPage\",\n\t            \"@id\": \"http:\/\/localhost:10003\/how-to-use-llms-for-text-style-transfer-and-adaptation\/\",\n\t            \"url\": \"http:\/\/localhost:10003\/how-to-use-llms-for-text-style-transfer-and-adaptation\/\",\n\t            \"name\": \"How to use LLMs for text style transfer and adaptation - Pantherax Blogs\",\n\t            \"isPartOf\": {\n\t                \"@id\": \"http:\/\/localhost:10003\/#website\"\n\t            },\n\t            \"datePublished\": \"2023-11-04T23:14:02+00:00\",\n\t            \"dateModified\": \"2023-11-05T05:48:01+00:00\",\n\t            \"breadcrumb\": {\n\t                \"@id\": \"http:\/\/localhost:10003\/how-to-use-llms-for-text-style-transfer-and-adaptation\/#breadcrumb\"\n\t            },\n\t            \"inLanguage\": \"en-US\",\n\t            \"potentialAction\": [\n\t                {\n\t                    \"@type\": \"ReadAction\",\n\t                    \"target\": [\n\t                        \"http:\/\/localhost:10003\/how-to-use-llms-for-text-style-transfer-and-adaptation\/\"\n\t                    ]\n\t                }\n\t            ]\n\t        },\n\t        {\n\t            \"@type\": \"BreadcrumbList\",\n\t            \"@id\": \"http:\/\/localhost:10003\/how-to-use-llms-for-text-style-transfer-and-adaptation\/#breadcrumb\",\n\t            \"itemListElement\": [\n\t                {\n\t                    \"@type\": \"ListItem\",\n\t                    \"position\": 1,\n\t                    \"name\": \"Home\",\n\t                    \"item\": \"http:\/\/localhost:10003\/\"\n\t                },\n\t                {\n\t                    \"@type\": \"ListItem\",\n\t                    \"position\": 2,\n\t                    \"name\": \"How to use LLMs for text style transfer and adaptation\"\n\t                }\n\t            ]\n\t        },\n\t        {\n\t            \"@type\": \"WebSite\",\n\t            \"@id\": \"http:\/\/localhost:10003\/#website\",\n\t            \"url\": \"http:\/\/localhost:10003\/\",\n\t            \"name\": \"Pantherax Blogs\",\n\t            \"description\": \"\",\n\t            \"publisher\": {\n\t                \"@id\": \"http:\/\/localhost:10003\/#organization\"\n\t            },\n\t            \"potentialAction\": [\n\t                {\n\t                    \"@type\": \"SearchAction\",\n\t                    \"target\": {\n\t                        \"@type\": \"EntryPoint\",\n\t                        \"urlTemplate\": \"http:\/\/localhost:10003\/?s={search_term_string}\"\n\t                    },\n\t                    \"query-input\": \"required name=search_term_string\"\n\t                }\n\t            ],\n\t            \"inLanguage\": \"en-US\"\n\t        },\n\t        {\n\t            \"@type\": \"Organization\",\n\t            \"@id\": \"http:\/\/localhost:10003\/#organization\",\n\t            \"name\": \"Pantherax Blogs\",\n\t            \"url\": \"http:\/\/localhost:10003\/\",\n\t            \"logo\": {\n\t                \"@type\": \"ImageObject\",\n\t                \"inLanguage\": \"en-US\",\n\t                \"@id\": \"http:\/\/localhost:10003\/#\/schema\/logo\/image\/\",\n\t                \"url\": \"http:\/\/localhost:10003\/wp-content\/uploads\/2023\/11\/cropped-9e7721cb-2d62-4f72-ab7f-7d1d8db89226.jpeg\",\n\t                \"contentUrl\": \"http:\/\/localhost:10003\/wp-content\/uploads\/2023\/11\/cropped-9e7721cb-2d62-4f72-ab7f-7d1d8db89226.jpeg\",\n\t                \"width\": 1024,\n\t                \"height\": 1024,\n\t                \"caption\": \"Pantherax Blogs\"\n\t            },\n\t            \"image\": {\n\t                \"@id\": \"http:\/\/localhost:10003\/#\/schema\/logo\/image\/\"\n\t            }\n\t        },\n\t        {\n\t            \"@type\": \"Person\",\n\t            \"@id\": \"http:\/\/localhost:10003\/#\/schema\/person\/b63d816f4964b163e53cbbcffaa0f3d7\",\n\t            \"name\": \"Panther\",\n\t            \"image\": {\n\t                \"@type\": \"ImageObject\",\n\t                \"inLanguage\": \"en-US\",\n\t                \"@id\": \"http:\/\/localhost:10003\/#\/schema\/person\/image\/\",\n\t                \"url\": \"http:\/\/2.gravatar.com\/avatar\/b8c0eda5a49f8f31ec32d0a0f9d6f838?s=96&d=mm&r=g\",\n\t                \"contentUrl\": \"http:\/\/2.gravatar.com\/avatar\/b8c0eda5a49f8f31ec32d0a0f9d6f838?s=96&d=mm&r=g\",\n\t                \"caption\": \"Panther\"\n\t            },\n\t            \"sameAs\": [\n\t                \"http:\/\/localhost:10003\"\n\t            ],\n\t            \"url\": \"http:\/\/localhost:10003\/author\/pepethefrog\/\"\n\t        }\n\t    ]\n\t}<\/script>\n<!-- \/ Yoast SEO Premium plugin. -->","yoast_head_json":{"title":"How to use LLMs for text style transfer and adaptation - Pantherax Blogs","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":"http:\/\/localhost:10003\/how-to-use-llms-for-text-style-transfer-and-adaptation\/","og_locale":"en_US","og_type":"article","og_title":"How to use LLMs for text style transfer and adaptation","og_description":"In recent years, there has been significant progress in natural language processing (NLP) techniques, particularly in the field of language generation. One such advancement is the development of Large Language Models (LLMs), which have shown impressive capabilities in generating coherent and contextually relevant text. LLMs have gained popularity in various Continue Reading","og_url":"http:\/\/localhost:10003\/how-to-use-llms-for-text-style-transfer-and-adaptation\/","og_site_name":"Pantherax Blogs","article_published_time":"2023-11-04T23:14:02+00:00","article_modified_time":"2023-11-05T05:48:01+00:00","author":"Panther","twitter_card":"summary_large_image","twitter_misc":{"Written by":"Panther","Est. reading time":"7 minutes"},"schema":{"@context":"https:\/\/schema.org","@graph":[{"@type":"Article","@id":"http:\/\/localhost:10003\/how-to-use-llms-for-text-style-transfer-and-adaptation\/#article","isPartOf":{"@id":"http:\/\/localhost:10003\/how-to-use-llms-for-text-style-transfer-and-adaptation\/"},"author":{"name":"Panther","@id":"http:\/\/localhost:10003\/#\/schema\/person\/b63d816f4964b163e53cbbcffaa0f3d7"},"headline":"How to use LLMs for text style transfer and adaptation","datePublished":"2023-11-04T23:14:02+00:00","dateModified":"2023-11-05T05:48:01+00:00","mainEntityOfPage":{"@id":"http:\/\/localhost:10003\/how-to-use-llms-for-text-style-transfer-and-adaptation\/"},"wordCount":1391,"publisher":{"@id":"http:\/\/localhost:10003\/#organization"},"keywords":["\"adaptation\"]","\"LLMs\"","\"style transfer\"","\"use LLMs\"","[\"text style transfer and adaptation\""],"inLanguage":"en-US"},{"@type":"WebPage","@id":"http:\/\/localhost:10003\/how-to-use-llms-for-text-style-transfer-and-adaptation\/","url":"http:\/\/localhost:10003\/how-to-use-llms-for-text-style-transfer-and-adaptation\/","name":"How to use LLMs for text style transfer and adaptation - Pantherax Blogs","isPartOf":{"@id":"http:\/\/localhost:10003\/#website"},"datePublished":"2023-11-04T23:14:02+00:00","dateModified":"2023-11-05T05:48:01+00:00","breadcrumb":{"@id":"http:\/\/localhost:10003\/how-to-use-llms-for-text-style-transfer-and-adaptation\/#breadcrumb"},"inLanguage":"en-US","potentialAction":[{"@type":"ReadAction","target":["http:\/\/localhost:10003\/how-to-use-llms-for-text-style-transfer-and-adaptation\/"]}]},{"@type":"BreadcrumbList","@id":"http:\/\/localhost:10003\/how-to-use-llms-for-text-style-transfer-and-adaptation\/#breadcrumb","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"http:\/\/localhost:10003\/"},{"@type":"ListItem","position":2,"name":"How to use LLMs for text style transfer and adaptation"}]},{"@type":"WebSite","@id":"http:\/\/localhost:10003\/#website","url":"http:\/\/localhost:10003\/","name":"Pantherax Blogs","description":"","publisher":{"@id":"http:\/\/localhost:10003\/#organization"},"potentialAction":[{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"http:\/\/localhost:10003\/?s={search_term_string}"},"query-input":"required name=search_term_string"}],"inLanguage":"en-US"},{"@type":"Organization","@id":"http:\/\/localhost:10003\/#organization","name":"Pantherax Blogs","url":"http:\/\/localhost:10003\/","logo":{"@type":"ImageObject","inLanguage":"en-US","@id":"http:\/\/localhost:10003\/#\/schema\/logo\/image\/","url":"http:\/\/localhost:10003\/wp-content\/uploads\/2023\/11\/cropped-9e7721cb-2d62-4f72-ab7f-7d1d8db89226.jpeg","contentUrl":"http:\/\/localhost:10003\/wp-content\/uploads\/2023\/11\/cropped-9e7721cb-2d62-4f72-ab7f-7d1d8db89226.jpeg","width":1024,"height":1024,"caption":"Pantherax Blogs"},"image":{"@id":"http:\/\/localhost:10003\/#\/schema\/logo\/image\/"}},{"@type":"Person","@id":"http:\/\/localhost:10003\/#\/schema\/person\/b63d816f4964b163e53cbbcffaa0f3d7","name":"Panther","image":{"@type":"ImageObject","inLanguage":"en-US","@id":"http:\/\/localhost:10003\/#\/schema\/person\/image\/","url":"http:\/\/2.gravatar.com\/avatar\/b8c0eda5a49f8f31ec32d0a0f9d6f838?s=96&d=mm&r=g","contentUrl":"http:\/\/2.gravatar.com\/avatar\/b8c0eda5a49f8f31ec32d0a0f9d6f838?s=96&d=mm&r=g","caption":"Panther"},"sameAs":["http:\/\/localhost:10003"],"url":"http:\/\/localhost:10003\/author\/pepethefrog\/"}]}},"jetpack_sharing_enabled":true,"jetpack_featured_media_url":"","_links":{"self":[{"href":"http:\/\/localhost:10003\/wp-json\/wp\/v2\/posts\/4052"}],"collection":[{"href":"http:\/\/localhost:10003\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"http:\/\/localhost:10003\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"http:\/\/localhost:10003\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"http:\/\/localhost:10003\/wp-json\/wp\/v2\/comments?post=4052"}],"version-history":[{"count":1,"href":"http:\/\/localhost:10003\/wp-json\/wp\/v2\/posts\/4052\/revisions"}],"predecessor-version":[{"id":4468,"href":"http:\/\/localhost:10003\/wp-json\/wp\/v2\/posts\/4052\/revisions\/4468"}],"wp:attachment":[{"href":"http:\/\/localhost:10003\/wp-json\/wp\/v2\/media?parent=4052"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"http:\/\/localhost:10003\/wp-json\/wp\/v2\/categories?post=4052"},{"taxonomy":"post_tag","embeddable":true,"href":"http:\/\/localhost:10003\/wp-json\/wp\/v2\/tags?post=4052"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}