{"id":3879,"date":"2023-11-04T23:13:54","date_gmt":"2023-11-04T23:13:54","guid":{"rendered":"http:\/\/localhost:10003\/how-to-train-your-own-llm-using-open-source-data-and-tools\/"},"modified":"2023-11-05T05:48:29","modified_gmt":"2023-11-05T05:48:29","slug":"how-to-train-your-own-llm-using-open-source-data-and-tools","status":"publish","type":"post","link":"http:\/\/localhost:10003\/how-to-train-your-own-llm-using-open-source-data-and-tools\/","title":{"rendered":"How to train your own LLM using open-source data and tools"},"content":{"rendered":"<h1>How to Train Your Own Language Model (LLM) using Open-Source Data and Tools<\/h1>\n<p>Language models are a powerful tool for various natural language processing (NLP) tasks, such as text generation, sentiment analysis, and language translation. While pre-trained models are readily available, training your own language model gives you the flexibility to customize it according to your specific needs. In this tutorial, we will learn how to train your own language model using open-source data and tools.<\/p>\n<h2>Prerequisites<\/h2>\n<p>To follow along with this tutorial, you will need:<\/p>\n<ul>\n<li>Python 3.6 or higher<\/li>\n<li>A text corpus (dataset) for training the language model<\/li>\n<li><code>transformers<\/code> library (a popular NLP library) &#8211; can be installed using <code>pip install transformers<\/code><\/li>\n<li><code>torch<\/code> library (PyTorch framework) &#8211; can be installed using <code>pip install torch<\/code><\/li>\n<\/ul>\n<h2>Step 1: Prepare the Dataset<\/h2>\n<p>The first step is to gather a text corpus that will serve as the training data for your language model. The dataset can be obtained from numerous sources, such as online articles, books, or publicly available text datasets. Make sure the dataset is in a plaintext format and large enough to capture the diversity of language patterns.<\/p>\n<p>Once you have your dataset, it&#8217;s advisable to preprocess the text to remove any unnecessary characters, special symbols, or HTML tags. You can use Python&#8217;s regular expressions or NLP libraries like <code>NLTK<\/code> for this purpose. Additionally, convert the text to lowercase for uniformity.<\/p>\n<h2>Step 2: Tokenization<\/h2>\n<p>Language models operate at the token level, where tokens can be words, subwords, or characters. Tokenization is the process of splitting the text into these tokens.<\/p>\n<p>The <code>transformers<\/code> library provides a tokenizer class for this purpose, which can handle various tokenization algorithms. For example, <code>BertTokenizer<\/code> tokenizes the text using the WordPiece algorithm.<\/p>\n<p>To tokenize your text, you need to perform the following steps:<\/p>\n<pre><code class=\"language-python\">from transformers import BertTokenizer\n\ntokenizer = BertTokenizer.from_pretrained('bert-base-uncased')\ntokens = tokenizer.tokenize(text)\n<\/code><\/pre>\n<p>Here, <code>from_pretrained()<\/code> method loads the pretrained tokenizer (e.g., <code>'bert-base-uncased'<\/code>) from the Hugging Face model repository. Then, <code>tokenize()<\/code> method tokenizes the <code>text<\/code>.<\/p>\n<h2>Step 3: Dataset Preparation<\/h2>\n<p>To train a language model, you need to convert the tokenized text into a format suitable for training. The <code>transformers<\/code> library provides the <code>TextDataset<\/code> class, which helps in preparing the data.<\/p>\n<pre><code class=\"language-python\">from transformers import TextDataset\n\ndataset = TextDataset(\n    tokenizer=tokenizer,\n    file_path='path\/to\/dataset.txt',\n    block_size=128\n)\n<\/code><\/pre>\n<p>In the <code>TextDataset<\/code> constructor, you need to provide the tokenizer object, the file path of the dataset, and the desired block size. The block size determines the maximum length of each training sample.<\/p>\n<h2>Step 4: Model Configuration<\/h2>\n<p>Next, you need to define the configuration of your language model. The <code>transformers<\/code> library provides pre-trained models, such as BERT, GPT, and RoBERTa, which can be used as a starting point.<\/p>\n<p>For example, to create a BERT-like model:<\/p>\n<pre><code class=\"language-python\">from transformers import BertConfig\n\nconfig = BertConfig(\n    vocab_size=len(tokenizer),\n    hidden_size=256,\n    num_hidden_layers=12,\n    num_attention_heads=8,\n    intermediate_size=1024,\n)\n<\/code><\/pre>\n<p>In this example, we define a <code>BertConfig<\/code> object and specify the vocabulary size, hidden size, number of hidden layers, number of attention heads, and intermediate size.<\/p>\n<h2>Step 5: Model Training<\/h2>\n<p>Now it&#8217;s time to train your language model using the prepared dataset and model configuration. The <code>transformers<\/code> library provides the <code>Trainer<\/code> class to make the training process easier.<\/p>\n<pre><code class=\"language-python\">from transformers import Trainer, TrainingArguments\n\ntraining_args = TrainingArguments(\n    output_dir='model_output',\n    overwrite_output_dir=True,\n    num_train_epochs=3,\n    per_device_train_batch_size=64,\n    save_steps=500,\n    save_total_limit=2,\n)\n\ntrainer = Trainer(\n    model=model,\n    args=training_args,\n    data_collator=default_data_collator,\n    train_dataset=dataset\n)\n\ntrainer.train()\n<\/code><\/pre>\n<p>In the <code>TrainingArguments<\/code> constructor, you need to specify the output directory, number of training epochs, batch size, and save steps.<\/p>\n<p>The <code>Trainer<\/code> constructor takes the trained model, training arguments, a data collator (e.g., <code>default_data_collator<\/code>), and the training dataset.<\/p>\n<h2>Step 6: Model Evaluation<\/h2>\n<p>After training, it&#8217;s crucial to evaluate the performance of your model on a validation dataset. The <code>transformers<\/code> library provides various evaluation metrics and tools to accomplish this.<\/p>\n<pre><code class=\"language-python\">from transformers import DataCollatorForLanguageModeling, Trainer, TrainingArguments\n\nvalidation_dataset = TextDataset(\n    tokenizer=tokenizer,\n    file_path='path\/to\/validation_dataset.txt',\n    block_size=128\n)\n\ndata_collator = DataCollatorForLanguageModeling(\n    tokenizer=tokenizer, mlm=False\n)\n\ntraining_args = TrainingArguments(\n    output_dir='model_output',\n)\n\ntrainer = Trainer(\n    model=model,\n    args=training_args,\n    data_collator=data_collator,\n    train_dataset=dataset,\n    eval_dataset=validation_dataset\n)\n\ntrainer.evaluate()\n<\/code><\/pre>\n<p>Here, we create a new <code>TextDataset<\/code> for the validation dataset and use a <code>DataCollatorForLanguageModeling<\/code> for evaluation. The <code>eval_dataset<\/code> argument is set in the <code>Trainer<\/code> constructor.<\/p>\n<h2>Step 7: Save and Load the Trained Model<\/h2>\n<p>To save the trained model, you can use the <code>save_pretrained<\/code> method provided by the model object.<\/p>\n<pre><code class=\"language-python\">model.save_pretrained('path\/to\/save\/model')\n<\/code><\/pre>\n<p>You can then load the saved model using the corresponding <code>from_pretrained<\/code> method.<\/p>\n<pre><code class=\"language-python\">from transformers import BertTokenizer, BertForPreTraining\n\ntokenizer = BertTokenizer.from_pretrained('path\/to\/saved-model')\nmodel = BertForPreTraining.from_pretrained('path\/to\/saved-model')\n<\/code><\/pre>\n<h2>Conclusion<\/h2>\n<p>In this tutorial, you&#8217;ve learned how to train your own language model using open-source data and tools. We covered the steps to prepare the dataset, tokenize the text, configure the model, train the model, evaluate it, and save\/load the trained model. Now, you can unleash the power of your custom language model for various NLP tasks.<\/p>\n<p>Remember, training a language model requires computational resources and time. So, make sure to optimize your code and utilize hardware acceleration (e.g., GPUs) if available. Happy training!<\/p>\n","protected":false},"excerpt":{"rendered":"<p>How to Train Your Own Language Model (LLM) using Open-Source Data and Tools Language models are a powerful tool for various natural language processing (NLP) tasks, such as text generation, sentiment analysis, and language translation. While pre-trained models are readily available, training your own language model gives you the flexibility <a href=\"http:\/\/localhost:10003\/how-to-train-your-own-llm-using-open-source-data-and-tools\/\" 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":[65,64,62,63,66,61],"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 train your own LLM using open-source data and tools - 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-train-your-own-llm-using-open-source-data-and-tools\/\" \/>\n<meta property=\"og:locale\" content=\"en_US\" \/>\n<meta property=\"og:type\" content=\"article\" \/>\n<meta property=\"og:title\" content=\"How to train your own LLM using open-source data and tools\" \/>\n<meta property=\"og:description\" content=\"How to Train Your Own Language Model (LLM) using Open-Source Data and Tools Language models are a powerful tool for various natural language processing (NLP) tasks, such as text generation, sentiment analysis, and language translation. While pre-trained models are readily available, training your own language model gives you the flexibility Continue Reading\" \/>\n<meta property=\"og:url\" content=\"http:\/\/localhost:10003\/how-to-train-your-own-llm-using-open-source-data-and-tools\/\" \/>\n<meta property=\"og:site_name\" content=\"Pantherax Blogs\" \/>\n<meta property=\"article:published_time\" content=\"2023-11-04T23:13:54+00:00\" \/>\n<meta property=\"article:modified_time\" content=\"2023-11-05T05:48:29+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=\"4 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-train-your-own-llm-using-open-source-data-and-tools\/#article\",\n\t            \"isPartOf\": {\n\t                \"@id\": \"http:\/\/localhost:10003\/how-to-train-your-own-llm-using-open-source-data-and-tools\/\"\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 train your own LLM using open-source data and tools\",\n\t            \"datePublished\": \"2023-11-04T23:13:54+00:00\",\n\t            \"dateModified\": \"2023-11-05T05:48:29+00:00\",\n\t            \"mainEntityOfPage\": {\n\t                \"@id\": \"http:\/\/localhost:10003\/how-to-train-your-own-llm-using-open-source-data-and-tools\/\"\n\t            },\n\t            \"wordCount\": 679,\n\t            \"publisher\": {\n\t                \"@id\": \"http:\/\/localhost:10003\/#organization\"\n\t            },\n\t            \"keywords\": [\n\t                \"\\\"data training\\\"\",\n\t                \"\\\"LLM training\\\"\",\n\t                \"\\\"open-source data\\\"\",\n\t                \"\\\"open-source tools\\\"\",\n\t                \"\\\"training tools\\\"]\",\n\t                \"[\\\"how to train your own LLM\\\"\"\n\t            ],\n\t            \"inLanguage\": \"en-US\"\n\t        },\n\t        {\n\t            \"@type\": \"WebPage\",\n\t            \"@id\": \"http:\/\/localhost:10003\/how-to-train-your-own-llm-using-open-source-data-and-tools\/\",\n\t            \"url\": \"http:\/\/localhost:10003\/how-to-train-your-own-llm-using-open-source-data-and-tools\/\",\n\t            \"name\": \"How to train your own LLM using open-source data and tools - Pantherax Blogs\",\n\t            \"isPartOf\": {\n\t                \"@id\": \"http:\/\/localhost:10003\/#website\"\n\t            },\n\t            \"datePublished\": \"2023-11-04T23:13:54+00:00\",\n\t            \"dateModified\": \"2023-11-05T05:48:29+00:00\",\n\t            \"breadcrumb\": {\n\t                \"@id\": \"http:\/\/localhost:10003\/how-to-train-your-own-llm-using-open-source-data-and-tools\/#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-train-your-own-llm-using-open-source-data-and-tools\/\"\n\t                    ]\n\t                }\n\t            ]\n\t        },\n\t        {\n\t            \"@type\": \"BreadcrumbList\",\n\t            \"@id\": \"http:\/\/localhost:10003\/how-to-train-your-own-llm-using-open-source-data-and-tools\/#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 train your own LLM using open-source data and tools\"\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 train your own LLM using open-source data and tools - 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-train-your-own-llm-using-open-source-data-and-tools\/","og_locale":"en_US","og_type":"article","og_title":"How to train your own LLM using open-source data and tools","og_description":"How to Train Your Own Language Model (LLM) using Open-Source Data and Tools Language models are a powerful tool for various natural language processing (NLP) tasks, such as text generation, sentiment analysis, and language translation. While pre-trained models are readily available, training your own language model gives you the flexibility Continue Reading","og_url":"http:\/\/localhost:10003\/how-to-train-your-own-llm-using-open-source-data-and-tools\/","og_site_name":"Pantherax Blogs","article_published_time":"2023-11-04T23:13:54+00:00","article_modified_time":"2023-11-05T05:48:29+00:00","author":"Panther","twitter_card":"summary_large_image","twitter_misc":{"Written by":"Panther","Est. reading time":"4 minutes"},"schema":{"@context":"https:\/\/schema.org","@graph":[{"@type":"Article","@id":"http:\/\/localhost:10003\/how-to-train-your-own-llm-using-open-source-data-and-tools\/#article","isPartOf":{"@id":"http:\/\/localhost:10003\/how-to-train-your-own-llm-using-open-source-data-and-tools\/"},"author":{"name":"Panther","@id":"http:\/\/localhost:10003\/#\/schema\/person\/b63d816f4964b163e53cbbcffaa0f3d7"},"headline":"How to train your own LLM using open-source data and tools","datePublished":"2023-11-04T23:13:54+00:00","dateModified":"2023-11-05T05:48:29+00:00","mainEntityOfPage":{"@id":"http:\/\/localhost:10003\/how-to-train-your-own-llm-using-open-source-data-and-tools\/"},"wordCount":679,"publisher":{"@id":"http:\/\/localhost:10003\/#organization"},"keywords":["\"data training\"","\"LLM training\"","\"open-source data\"","\"open-source tools\"","\"training tools\"]","[\"how to train your own LLM\""],"inLanguage":"en-US"},{"@type":"WebPage","@id":"http:\/\/localhost:10003\/how-to-train-your-own-llm-using-open-source-data-and-tools\/","url":"http:\/\/localhost:10003\/how-to-train-your-own-llm-using-open-source-data-and-tools\/","name":"How to train your own LLM using open-source data and tools - Pantherax Blogs","isPartOf":{"@id":"http:\/\/localhost:10003\/#website"},"datePublished":"2023-11-04T23:13:54+00:00","dateModified":"2023-11-05T05:48:29+00:00","breadcrumb":{"@id":"http:\/\/localhost:10003\/how-to-train-your-own-llm-using-open-source-data-and-tools\/#breadcrumb"},"inLanguage":"en-US","potentialAction":[{"@type":"ReadAction","target":["http:\/\/localhost:10003\/how-to-train-your-own-llm-using-open-source-data-and-tools\/"]}]},{"@type":"BreadcrumbList","@id":"http:\/\/localhost:10003\/how-to-train-your-own-llm-using-open-source-data-and-tools\/#breadcrumb","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"http:\/\/localhost:10003\/"},{"@type":"ListItem","position":2,"name":"How to train your own LLM using open-source data and tools"}]},{"@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\/3879"}],"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=3879"}],"version-history":[{"count":1,"href":"http:\/\/localhost:10003\/wp-json\/wp\/v2\/posts\/3879\/revisions"}],"predecessor-version":[{"id":4655,"href":"http:\/\/localhost:10003\/wp-json\/wp\/v2\/posts\/3879\/revisions\/4655"}],"wp:attachment":[{"href":"http:\/\/localhost:10003\/wp-json\/wp\/v2\/media?parent=3879"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"http:\/\/localhost:10003\/wp-json\/wp\/v2\/categories?post=3879"},{"taxonomy":"post_tag","embeddable":true,"href":"http:\/\/localhost:10003\/wp-json\/wp\/v2\/tags?post=3879"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}