Buckets:

hf-doc-build
/

doc

Files

xet

hf-doc-build/doc / transformers /main /en /chat_template_basics.html

rtrm

about 1 month ago

download

raw

48.4 kB

	<meta charset="utf-8" /><meta name="hf:doc:metadata" content="{"title":"Getting Started with Chat Templates for Text LLMs","local":"getting-started-with-chat-templates-for-text-llms","sections":[{"title":"How do I use chat templates?","local":"how-do-i-use-chat-templates","sections":[],"depth":2},{"title":"Is there an automated pipeline for chat?","local":"is-there-an-automated-pipeline-for-chat","sections":[],"depth":2},{"title":"What are “generation prompts”?","local":"what-are-generation-prompts","sections":[],"depth":2},{"title":"What does “continue_final_message” do?","local":"what-does-continuefinalmessage-do","sections":[],"depth":2},{"title":"Can I use chat templates in training?","local":"can-i-use-chat-templates-in-training","sections":[],"depth":2}],"depth":1}">
	<link href="/docs/transformers/main/en/_app/immutable/assets/0.e3b0c442.css" rel="modulepreload">
	<link rel="modulepreload" href="/docs/transformers/main/en/_app/immutable/entry/start.8cba93b8.js">
	<link rel="modulepreload" href="/docs/transformers/main/en/_app/immutable/chunks/scheduler.bdbef820.js">
	<link rel="modulepreload" href="/docs/transformers/main/en/_app/immutable/chunks/singletons.6587ca2b.js">
	<link rel="modulepreload" href="/docs/transformers/main/en/_app/immutable/chunks/index.8a885b74.js">
	<link rel="modulepreload" href="/docs/transformers/main/en/_app/immutable/chunks/paths.2c06013a.js">
	<link rel="modulepreload" href="/docs/transformers/main/en/_app/immutable/entry/app.00a1188c.js">
	<link rel="modulepreload" href="/docs/transformers/main/en/_app/immutable/chunks/index.33f81d56.js">
	<link rel="modulepreload" href="/docs/transformers/main/en/_app/immutable/nodes/0.876f3f60.js">
	<link rel="modulepreload" href="/docs/transformers/main/en/_app/immutable/chunks/each.e59479a4.js">
	<link rel="modulepreload" href="/docs/transformers/main/en/_app/immutable/nodes/12.9cb2ae3b.js">
	<link rel="modulepreload" href="/docs/transformers/main/en/_app/immutable/chunks/Tip.34194030.js">
	<link rel="modulepreload" href="/docs/transformers/main/en/_app/immutable/chunks/CodeBlock.362b34a4.js">
	<link rel="modulepreload" href="/docs/transformers/main/en/_app/immutable/chunks/EditOnGithub.a9246e21.js"><!-- HEAD_svelte-u9bgzb_START --><meta name="hf:doc:metadata" content="{"title":"Getting Started with Chat Templates for Text LLMs","local":"getting-started-with-chat-templates-for-text-llms","sections":[{"title":"How do I use chat templates?","local":"how-do-i-use-chat-templates","sections":[],"depth":2},{"title":"Is there an automated pipeline for chat?","local":"is-there-an-automated-pipeline-for-chat","sections":[],"depth":2},{"title":"What are “generation prompts”?","local":"what-are-generation-prompts","sections":[],"depth":2},{"title":"What does “continue_final_message” do?","local":"what-does-continuefinalmessage-do","sections":[],"depth":2},{"title":"Can I use chat templates in training?","local":"can-i-use-chat-templates-in-training","sections":[],"depth":2}],"depth":1}"><!-- HEAD_svelte-u9bgzb_END --> <p></p> <h1 class="relative group"><a id="getting-started-with-chat-templates-for-text-llms" class="header-link block pr-1.5 text-lg no-hover:hidden with-hover:absolute with-hover:p-1.5 with-hover:opacity-0 with-hover:group-hover:opacity-100 with-hover:right-full" href="#getting-started-with-chat-templates-for-text-llms"><span><svg class="" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink" aria-hidden="true" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 256 256"><path d="M167.594 88.393a8.001 8.001 0 0 1 0 11.314l-67.882 67.882a8 8 0 1 1-11.314-11.315l67.882-67.881a8.003 8.003 0 0 1 11.314 0zm-28.287 84.86l-28.284 28.284a40 40 0 0 1-56.567-56.567l28.284-28.284a8 8 0 0 0-11.315-11.315l-28.284 28.284a56 56 0 0 0 79.196 79.197l28.285-28.285a8 8 0 1 0-11.315-11.314zM212.852 43.14a56.002 56.002 0 0 0-79.196 0l-28.284 28.284a8 8 0 1 0 11.314 11.314l28.284-28.284a40 40 0 0 1 56.568 56.567l-28.285 28.285a8 8 0 0 0 11.315 11.314l28.284-28.284a56.065 56.065 0 0 0 0-79.196z" fill="currentColor"></path></svg></span></a> <span>Getting Started with Chat Templates for Text LLMs</span></h1> <p data-svelte-h="svelte-ydi30o">An increasingly common use case for LLMs is <strong>chat</strong>. In a chat context, rather than continuing a single string
	of text (as is the case with a standard language model), the model instead continues a conversation that consists
	of one or more <strong>messages</strong>, each of which includes a <strong>role</strong>, like “user” or “assistant”, as well as message text.</p> <p data-svelte-h="svelte-1q7lkkp">Much like tokenization, different models expect very different input formats for chat. This is the reason we added
	<strong>chat templates</strong> as a feature. Chat templates are part of the tokenizer for text-only LLMs or processor for multimodal LLMs. They specify how to convert conversations, represented as lists of messages, into a single tokenizable string in the format that the model expects.</p> <p data-svelte-h="svelte-w1vlk3">We’ll explore the basic usage of chat templates with text-only LLMs in this page. For detailed guidance on multimodal models, we have a dedicated <a href="./chat_template_multimodal">documentation oage for multimodal models</a>, which covers how to work with image, video and audio inputs in your templates.</p> <p data-svelte-h="svelte-19ob0qf">Let’s make this concrete with a quick example using the <code>mistralai/Mistral-7B-Instruct-v0.1</code> model:</p> <div class="code-block relative"><div class="absolute top-2.5 right-4"><button class="inline-flex items-center relative text-sm focus:text-green-500 cursor-pointer focus:outline-none transition duration-200 ease-in-out opacity-0 mx-0.5 text-gray-600 " title="code excerpt" type="button"><svg class="" xmlns="http://www.w3.org/2000/svg" aria-hidden="true" fill="currentColor" focusable="false" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 32 32"><path d="M28,10V28H10V10H28m0-2H10a2,2,0,0,0-2,2V28a2,2,0,0,0,2,2H28a2,2,0,0,0,2-2V10a2,2,0,0,0-2-2Z" transform="translate(0)"></path><path d="M4,18H2V4A2,2,0,0,1,4,2H18V4H4Z" transform="translate(0)"></path><rect fill="none" width="32" height="32"></rect></svg> <div class="absolute pointer-events-none transition-opacity bg-black text-white py-1 px-2 leading-tight rounded font-normal shadow left-1/2 top-full transform -translate-x-1/2 translate-y-2 opacity-0"><div class="absolute bottom-full left-1/2 transform -translate-x-1/2 w-0 h-0 border-black border-4 border-t-0" style="border-left-color: transparent; border-right-color: transparent; "></div> Copied</div></button></div> <pre class=""><!-- HTML_TAG_START --><span class="hljs-meta">>>> </span><span class="hljs-keyword">from</span> transformers <span class="hljs-keyword">import</span> AutoTokenizer
	<span class="hljs-meta">>>> </span>tokenizer = AutoTokenizer.from_pretrained(<span class="hljs-string">"mistralai/Mistral-7B-Instruct-v0.1"</span>)

	<span class="hljs-meta">>>> </span>chat = [
	<span class="hljs-meta">... </span> {<span class="hljs-string">"role"</span>: <span class="hljs-string">"user"</span>, <span class="hljs-string">"content"</span>: <span class="hljs-string">"Hello, how are you?"</span>},
	<span class="hljs-meta">... </span> {<span class="hljs-string">"role"</span>: <span class="hljs-string">"assistant"</span>, <span class="hljs-string">"content"</span>: <span class="hljs-string">"I'm doing great. How can I help you today?"</span>},
	<span class="hljs-meta">... </span> {<span class="hljs-string">"role"</span>: <span class="hljs-string">"user"</span>, <span class="hljs-string">"content"</span>: <span class="hljs-string">"I'd like to show off how chat templating works!"</span>},
	<span class="hljs-meta">... </span>]

	<span class="hljs-meta">>>> </span>tokenizer.apply_chat_template(chat, tokenize=<span class="hljs-literal">False</span>)
	<span class="hljs-string">"<s>[INST] Hello, how are you? [/INST]I'm doing great. How can I help you today?</s> [INST] I'd like to show off how chat templating works! [/INST]"</span><!-- HTML_TAG_END --></pre></div> <p data-svelte-h="svelte-gwj0xd">Notice how the tokenizer has added the control tokens [INST] and [/INST] to indicate the start and end of
	user messages (but not assistant messages!), and the entire chat is condensed into a single string.
	If we use <code>tokenize=True</code>, which is the default setting, that string will also be tokenized for us.</p> <p data-svelte-h="svelte-14wqu22">Now, try the same code, but swap in the <code>HuggingFaceH4/zephyr-7b-beta</code> model instead, and you should get:</p> <div class="code-block relative"><div class="absolute top-2.5 right-4"><button class="inline-flex items-center relative text-sm focus:text-green-500 cursor-pointer focus:outline-none transition duration-200 ease-in-out opacity-0 mx-0.5 text-gray-600 " title="code excerpt" type="button"><svg class="" xmlns="http://www.w3.org/2000/svg" aria-hidden="true" fill="currentColor" focusable="false" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 32 32"><path d="M28,10V28H10V10H28m0-2H10a2,2,0,0,0-2,2V28a2,2,0,0,0,2,2H28a2,2,0,0,0,2-2V10a2,2,0,0,0-2-2Z" transform="translate(0)"></path><path d="M4,18H2V4A2,2,0,0,1,4,2H18V4H4Z" transform="translate(0)"></path><rect fill="none" width="32" height="32"></rect></svg> <div class="absolute pointer-events-none transition-opacity bg-black text-white py-1 px-2 leading-tight rounded font-normal shadow left-1/2 top-full transform -translate-x-1/2 translate-y-2 opacity-0"><div class="absolute bottom-full left-1/2 transform -translate-x-1/2 w-0 h-0 border-black border-4 border-t-0" style="border-left-color: transparent; border-right-color: transparent; "></div> Copied</div></button></div> <pre class=""><!-- HTML_TAG_START --><\|user\|>
	Hello, how are you?</s>
	<\|assistant\|>
	I'm doing great. How can I help you today?</s>
	<\|user\|>
	I'd like to show off how chat templating works!</s><!-- HTML_TAG_END --></pre></div> <p data-svelte-h="svelte-1010uaq">Both Zephyr and Mistral-Instruct were fine-tuned from the same base model, <code>Mistral-7B-v0.1</code>. However, they were trained
	with totally different chat formats. Without chat templates, you would have to write manual formatting code for each
	model, and it’s very easy to make minor errors that hurt performance! Chat templates handle the details of formatting
	for you, allowing you to write universal code that works for any model.</p> <h2 class="relative group"><a id="how-do-i-use-chat-templates" class="header-link block pr-1.5 text-lg no-hover:hidden with-hover:absolute with-hover:p-1.5 with-hover:opacity-0 with-hover:group-hover:opacity-100 with-hover:right-full" href="#how-do-i-use-chat-templates"><span><svg class="" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink" aria-hidden="true" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 256 256"><path d="M167.594 88.393a8.001 8.001 0 0 1 0 11.314l-67.882 67.882a8 8 0 1 1-11.314-11.315l67.882-67.881a8.003 8.003 0 0 1 11.314 0zm-28.287 84.86l-28.284 28.284a40 40 0 0 1-56.567-56.567l28.284-28.284a8 8 0 0 0-11.315-11.315l-28.284 28.284a56 56 0 0 0 79.196 79.197l28.285-28.285a8 8 0 1 0-11.315-11.314zM212.852 43.14a56.002 56.002 0 0 0-79.196 0l-28.284 28.284a8 8 0 1 0 11.314 11.314l28.284-28.284a40 40 0 0 1 56.568 56.567l-28.285 28.285a8 8 0 0 0 11.315 11.314l28.284-28.284a56.065 56.065 0 0 0 0-79.196z" fill="currentColor"></path></svg></span></a> <span>How do I use chat templates?</span></h2> <p data-svelte-h="svelte-1tiyfu1">As you can see in the example above, chat templates are easy to use. Simply build a list of messages, with <code>role</code>
	and <code>content</code> keys, and then pass it to the <a href="/docs/transformers/main/en/internal/tokenization_utils#transformers.PreTrainedTokenizerBase.apply_chat_template">apply_chat_template()</a> or <a href="/docs/transformers/main/en/main_classes/processors#transformers.ProcessorMixin.apply_chat_template">apply_chat_template()</a> method
	depending on what type of model you are using. Once you do that,
	you’ll get output that’s ready to go! When using chat templates as input for model generation, it’s also a good idea
	to use <code>add_generation_prompt=True</code> to add a <a href="#what-are-generation-prompts">generation prompt</a>.</p> <p data-svelte-h="svelte-1vun9x2">Here’s an example of preparing input for <code>model.generate()</code>, using <code>Zephyr</code> again:</p> <div class="code-block relative"><div class="absolute top-2.5 right-4"><button class="inline-flex items-center relative text-sm focus:text-green-500 cursor-pointer focus:outline-none transition duration-200 ease-in-out opacity-0 mx-0.5 text-gray-600 " title="code excerpt" type="button"><svg class="" xmlns="http://www.w3.org/2000/svg" aria-hidden="true" fill="currentColor" focusable="false" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 32 32"><path d="M28,10V28H10V10H28m0-2H10a2,2,0,0,0-2,2V28a2,2,0,0,0,2,2H28a2,2,0,0,0,2-2V10a2,2,0,0,0-2-2Z" transform="translate(0)"></path><path d="M4,18H2V4A2,2,0,0,1,4,2H18V4H4Z" transform="translate(0)"></path><rect fill="none" width="32" height="32"></rect></svg> <div class="absolute pointer-events-none transition-opacity bg-black text-white py-1 px-2 leading-tight rounded font-normal shadow left-1/2 top-full transform -translate-x-1/2 translate-y-2 opacity-0"><div class="absolute bottom-full left-1/2 transform -translate-x-1/2 w-0 h-0 border-black border-4 border-t-0" style="border-left-color: transparent; border-right-color: transparent; "></div> Copied</div></button></div> <pre class=""><!-- HTML_TAG_START --><span class="hljs-keyword">from</span> transformers <span class="hljs-keyword">import</span> AutoModelForCausalLM, AutoTokenizer

	checkpoint = <span class="hljs-string">"HuggingFaceH4/zephyr-7b-beta"</span>
	tokenizer = AutoTokenizer.from_pretrained(checkpoint)
	model = AutoModelForCausalLM.from_pretrained(checkpoint) <span class="hljs-comment"># You may want to use bfloat16 and/or move to GPU here</span>

	messages = [
	{
	<span class="hljs-string">"role"</span>: <span class="hljs-string">"system"</span>,
	<span class="hljs-string">"content"</span>: <span class="hljs-string">"You are a friendly chatbot who always responds in the style of a pirate"</span>,
	},
	{<span class="hljs-string">"role"</span>: <span class="hljs-string">"user"</span>, <span class="hljs-string">"content"</span>: <span class="hljs-string">"How many helicopters can a human eat in one sitting?"</span>},
	]
	tokenized_chat = tokenizer.apply_chat_template(messages, tokenize=<span class="hljs-literal">True</span>, add_generation_prompt=<span class="hljs-literal">True</span>, return_tensors=<span class="hljs-string">"pt"</span>)
	<span class="hljs-built_in">print</span>(tokenizer.decode(tokenized_chat[<span class="hljs-number">0</span>]))<!-- HTML_TAG_END --></pre></div> <p data-svelte-h="svelte-1vy7akj">This will yield a string in the input format that Zephyr expects.</p> <div class="code-block relative"><div class="absolute top-2.5 right-4"><button class="inline-flex items-center relative text-sm focus:text-green-500 cursor-pointer focus:outline-none transition duration-200 ease-in-out opacity-0 mx-0.5 text-gray-600 " title="code excerpt" type="button"><svg class="" xmlns="http://www.w3.org/2000/svg" aria-hidden="true" fill="currentColor" focusable="false" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 32 32"><path d="M28,10V28H10V10H28m0-2H10a2,2,0,0,0-2,2V28a2,2,0,0,0,2,2H28a2,2,0,0,0,2-2V10a2,2,0,0,0-2-2Z" transform="translate(0)"></path><path d="M4,18H2V4A2,2,0,0,1,4,2H18V4H4Z" transform="translate(0)"></path><rect fill="none" width="32" height="32"></rect></svg> <div class="absolute pointer-events-none transition-opacity bg-black text-white py-1 px-2 leading-tight rounded font-normal shadow left-1/2 top-full transform -translate-x-1/2 translate-y-2 opacity-0"><div class="absolute bottom-full left-1/2 transform -translate-x-1/2 w-0 h-0 border-black border-4 border-t-0" style="border-left-color: transparent; border-right-color: transparent; "></div> Copied</div></button></div> <pre class=""><!-- HTML_TAG_START --><\|system\|>
	You are a friendly chatbot who always responds in the style of a pirate</s>
	<\|user\|>
	How many helicopters can a human eat in one sitting?</s>
	<\|assistant\|><!-- HTML_TAG_END --></pre></div> <p data-svelte-h="svelte-hj60o5">Now that our input is formatted correctly for Zephyr, we can use the model to generate a response to the user’s question:</p> <div class="code-block relative"><div class="absolute top-2.5 right-4"><button class="inline-flex items-center relative text-sm focus:text-green-500 cursor-pointer focus:outline-none transition duration-200 ease-in-out opacity-0 mx-0.5 text-gray-600 " title="code excerpt" type="button"><svg class="" xmlns="http://www.w3.org/2000/svg" aria-hidden="true" fill="currentColor" focusable="false" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 32 32"><path d="M28,10V28H10V10H28m0-2H10a2,2,0,0,0-2,2V28a2,2,0,0,0,2,2H28a2,2,0,0,0,2-2V10a2,2,0,0,0-2-2Z" transform="translate(0)"></path><path d="M4,18H2V4A2,2,0,0,1,4,2H18V4H4Z" transform="translate(0)"></path><rect fill="none" width="32" height="32"></rect></svg> <div class="absolute pointer-events-none transition-opacity bg-black text-white py-1 px-2 leading-tight rounded font-normal shadow left-1/2 top-full transform -translate-x-1/2 translate-y-2 opacity-0"><div class="absolute bottom-full left-1/2 transform -translate-x-1/2 w-0 h-0 border-black border-4 border-t-0" style="border-left-color: transparent; border-right-color: transparent; "></div> Copied</div></button></div> <pre class=""><!-- HTML_TAG_START -->outputs = model.generate(tokenized_chat, max_new_tokens=<span class="hljs-number">128</span>)
	<span class="hljs-built_in">print</span>(tokenizer.decode(outputs[<span class="hljs-number">0</span>]))<!-- HTML_TAG_END --></pre></div> <p data-svelte-h="svelte-1bfcqd3">This will yield:</p> <div class="code-block relative"><div class="absolute top-2.5 right-4"><button class="inline-flex items-center relative text-sm focus:text-green-500 cursor-pointer focus:outline-none transition duration-200 ease-in-out opacity-0 mx-0.5 text-gray-600 " title="code excerpt" type="button"><svg class="" xmlns="http://www.w3.org/2000/svg" aria-hidden="true" fill="currentColor" focusable="false" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 32 32"><path d="M28,10V28H10V10H28m0-2H10a2,2,0,0,0-2,2V28a2,2,0,0,0,2,2H28a2,2,0,0,0,2-2V10a2,2,0,0,0-2-2Z" transform="translate(0)"></path><path d="M4,18H2V4A2,2,0,0,1,4,2H18V4H4Z" transform="translate(0)"></path><rect fill="none" width="32" height="32"></rect></svg> <div class="absolute pointer-events-none transition-opacity bg-black text-white py-1 px-2 leading-tight rounded font-normal shadow left-1/2 top-full transform -translate-x-1/2 translate-y-2 opacity-0"><div class="absolute bottom-full left-1/2 transform -translate-x-1/2 w-0 h-0 border-black border-4 border-t-0" style="border-left-color: transparent; border-right-color: transparent; "></div> Copied</div></button></div> <pre class=""><!-- HTML_TAG_START --><\|system\|>
	You are a friendly chatbot who always responds in the style of a pirate</s>
	<\|user\|>
	How many helicopters can a human eat in one sitting?</s>
	<\|assistant\|>
	Matey, I'm afraid I must inform ye that humans cannot eat helicopters. Helicopters are not food, they are flying machines. Food is meant to be eaten, like a hearty plate o' grog, a savory bowl o' stew, or a delicious loaf o' bread. But helicopters, they be for transportin' and movin' around, not for eatin'. So, I'd say none, me hearties. None at all.<!-- HTML_TAG_END --></pre></div> <p data-svelte-h="svelte-k9m2iy">Arr, ‘twas easy after all!</p> <h2 class="relative group"><a id="is-there-an-automated-pipeline-for-chat" class="header-link block pr-1.5 text-lg no-hover:hidden with-hover:absolute with-hover:p-1.5 with-hover:opacity-0 with-hover:group-hover:opacity-100 with-hover:right-full" href="#is-there-an-automated-pipeline-for-chat"><span><svg class="" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink" aria-hidden="true" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 256 256"><path d="M167.594 88.393a8.001 8.001 0 0 1 0 11.314l-67.882 67.882a8 8 0 1 1-11.314-11.315l67.882-67.881a8.003 8.003 0 0 1 11.314 0zm-28.287 84.86l-28.284 28.284a40 40 0 0 1-56.567-56.567l28.284-28.284a8 8 0 0 0-11.315-11.315l-28.284 28.284a56 56 0 0 0 79.196 79.197l28.285-28.285a8 8 0 1 0-11.315-11.314zM212.852 43.14a56.002 56.002 0 0 0-79.196 0l-28.284 28.284a8 8 0 1 0 11.314 11.314l28.284-28.284a40 40 0 0 1 56.568 56.567l-28.285 28.285a8 8 0 0 0 11.315 11.314l28.284-28.284a56.065 56.065 0 0 0 0-79.196z" fill="currentColor"></path></svg></span></a> <span>Is there an automated pipeline for chat?</span></h2> <p data-svelte-h="svelte-znnkjx">Yes, there is! Our text generation pipelines support chat inputs, which makes it easy to use chat models. In the past,
	we used to use a dedicated “ConversationalPipeline” class, but this has now been deprecated and its functionality
	has been merged into the <a href="/docs/transformers/main/en/main_classes/pipelines#transformers.TextGenerationPipeline">TextGenerationPipeline</a>. Let’s try the <code>Zephyr</code> example again, but this time using
	a pipeline:</p> <div class="code-block relative"><div class="absolute top-2.5 right-4"><button class="inline-flex items-center relative text-sm focus:text-green-500 cursor-pointer focus:outline-none transition duration-200 ease-in-out opacity-0 mx-0.5 text-gray-600 " title="code excerpt" type="button"><svg class="" xmlns="http://www.w3.org/2000/svg" aria-hidden="true" fill="currentColor" focusable="false" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 32 32"><path d="M28,10V28H10V10H28m0-2H10a2,2,0,0,0-2,2V28a2,2,0,0,0,2,2H28a2,2,0,0,0,2-2V10a2,2,0,0,0-2-2Z" transform="translate(0)"></path><path d="M4,18H2V4A2,2,0,0,1,4,2H18V4H4Z" transform="translate(0)"></path><rect fill="none" width="32" height="32"></rect></svg> <div class="absolute pointer-events-none transition-opacity bg-black text-white py-1 px-2 leading-tight rounded font-normal shadow left-1/2 top-full transform -translate-x-1/2 translate-y-2 opacity-0"><div class="absolute bottom-full left-1/2 transform -translate-x-1/2 w-0 h-0 border-black border-4 border-t-0" style="border-left-color: transparent; border-right-color: transparent; "></div> Copied</div></button></div> <pre class=""><!-- HTML_TAG_START --><span class="hljs-keyword">from</span> transformers <span class="hljs-keyword">import</span> pipeline

	pipe = pipeline(<span class="hljs-string">"text-generation"</span>, <span class="hljs-string">"HuggingFaceH4/zephyr-7b-beta"</span>)
	messages = [
	{
	<span class="hljs-string">"role"</span>: <span class="hljs-string">"system"</span>,
	<span class="hljs-string">"content"</span>: <span class="hljs-string">"You are a friendly chatbot who always responds in the style of a pirate"</span>,
	},
	{<span class="hljs-string">"role"</span>: <span class="hljs-string">"user"</span>, <span class="hljs-string">"content"</span>: <span class="hljs-string">"How many helicopters can a human eat in one sitting?"</span>},
	]
	<span class="hljs-built_in">print</span>(pipe(messages, max_new_tokens=<span class="hljs-number">128</span>)[<span class="hljs-number">0</span>][<span class="hljs-string">'generated_text'</span>][-<span class="hljs-number">1</span>]) <span class="hljs-comment"># Print the assistant's response</span><!-- HTML_TAG_END --></pre></div> <div class="code-block relative"><div class="absolute top-2.5 right-4"><button class="inline-flex items-center relative text-sm focus:text-green-500 cursor-pointer focus:outline-none transition duration-200 ease-in-out opacity-0 mx-0.5 text-gray-600 " title="code excerpt" type="button"><svg class="" xmlns="http://www.w3.org/2000/svg" aria-hidden="true" fill="currentColor" focusable="false" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 32 32"><path d="M28,10V28H10V10H28m0-2H10a2,2,0,0,0-2,2V28a2,2,0,0,0,2,2H28a2,2,0,0,0,2-2V10a2,2,0,0,0-2-2Z" transform="translate(0)"></path><path d="M4,18H2V4A2,2,0,0,1,4,2H18V4H4Z" transform="translate(0)"></path><rect fill="none" width="32" height="32"></rect></svg> <div class="absolute pointer-events-none transition-opacity bg-black text-white py-1 px-2 leading-tight rounded font-normal shadow left-1/2 top-full transform -translate-x-1/2 translate-y-2 opacity-0"><div class="absolute bottom-full left-1/2 transform -translate-x-1/2 w-0 h-0 border-black border-4 border-t-0" style="border-left-color: transparent; border-right-color: transparent; "></div> Copied</div></button></div> <pre class=""><!-- HTML_TAG_START -->{'role': 'assistant', 'content': "Matey, I'm afraid I must inform ye that humans cannot eat helicopters. Helicopters are not food, they are flying machines. Food is meant to be eaten, like a hearty plate o' grog, a savory bowl o' stew, or a delicious loaf o' bread. But helicopters, they be for transportin' and movin' around, not for eatin'. So, I'd say none, me hearties. None at all."}<!-- HTML_TAG_END --></pre></div> <p data-svelte-h="svelte-5umvde">The pipeline will take care of all the details of tokenization and calling <code>apply_chat_template</code> for you -
	once the model has a chat template, all you need to do is initialize the pipeline and pass it the list of messages!</p> <h2 class="relative group"><a id="what-are-generation-prompts" class="header-link block pr-1.5 text-lg no-hover:hidden with-hover:absolute with-hover:p-1.5 with-hover:opacity-0 with-hover:group-hover:opacity-100 with-hover:right-full" href="#what-are-generation-prompts"><span><svg class="" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink" aria-hidden="true" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 256 256"><path d="M167.594 88.393a8.001 8.001 0 0 1 0 11.314l-67.882 67.882a8 8 0 1 1-11.314-11.315l67.882-67.881a8.003 8.003 0 0 1 11.314 0zm-28.287 84.86l-28.284 28.284a40 40 0 0 1-56.567-56.567l28.284-28.284a8 8 0 0 0-11.315-11.315l-28.284 28.284a56 56 0 0 0 79.196 79.197l28.285-28.285a8 8 0 1 0-11.315-11.314zM212.852 43.14a56.002 56.002 0 0 0-79.196 0l-28.284 28.284a8 8 0 1 0 11.314 11.314l28.284-28.284a40 40 0 0 1 56.568 56.567l-28.285 28.285a8 8 0 0 0 11.315 11.314l28.284-28.284a56.065 56.065 0 0 0 0-79.196z" fill="currentColor"></path></svg></span></a> <span>What are “generation prompts”?</span></h2> <p data-svelte-h="svelte-rhnu79">You may have noticed that the <code>apply_chat_template</code> method has an <code>add_generation_prompt</code> argument. This argument tells
	the template to add tokens that indicate the start of a bot response. For example, consider the following chat:</p> <div class="code-block relative"><div class="absolute top-2.5 right-4"><button class="inline-flex items-center relative text-sm focus:text-green-500 cursor-pointer focus:outline-none transition duration-200 ease-in-out opacity-0 mx-0.5 text-gray-600 " title="code excerpt" type="button"><svg class="" xmlns="http://www.w3.org/2000/svg" aria-hidden="true" fill="currentColor" focusable="false" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 32 32"><path d="M28,10V28H10V10H28m0-2H10a2,2,0,0,0-2,2V28a2,2,0,0,0,2,2H28a2,2,0,0,0,2-2V10a2,2,0,0,0-2-2Z" transform="translate(0)"></path><path d="M4,18H2V4A2,2,0,0,1,4,2H18V4H4Z" transform="translate(0)"></path><rect fill="none" width="32" height="32"></rect></svg> <div class="absolute pointer-events-none transition-opacity bg-black text-white py-1 px-2 leading-tight rounded font-normal shadow left-1/2 top-full transform -translate-x-1/2 translate-y-2 opacity-0"><div class="absolute bottom-full left-1/2 transform -translate-x-1/2 w-0 h-0 border-black border-4 border-t-0" style="border-left-color: transparent; border-right-color: transparent; "></div> Copied</div></button></div> <pre class=""><!-- HTML_TAG_START -->messages = [
	{<span class="hljs-string">"role"</span>: <span class="hljs-string">"user"</span>, <span class="hljs-string">"content"</span>: <span class="hljs-string">"Hi there!"</span>},
	{<span class="hljs-string">"role"</span>: <span class="hljs-string">"assistant"</span>, <span class="hljs-string">"content"</span>: <span class="hljs-string">"Nice to meet you!"</span>},
	{<span class="hljs-string">"role"</span>: <span class="hljs-string">"user"</span>, <span class="hljs-string">"content"</span>: <span class="hljs-string">"Can I ask a question?"</span>}
	]<!-- HTML_TAG_END --></pre></div> <p data-svelte-h="svelte-jpbe39">Here’s what this will look like without a generation prompt, for a model that uses standard “ChatML” formatting:</p> <div class="code-block relative"><div class="absolute top-2.5 right-4"><button class="inline-flex items-center relative text-sm focus:text-green-500 cursor-pointer focus:outline-none transition duration-200 ease-in-out opacity-0 mx-0.5 text-gray-600 " title="code excerpt" type="button"><svg class="" xmlns="http://www.w3.org/2000/svg" aria-hidden="true" fill="currentColor" focusable="false" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 32 32"><path d="M28,10V28H10V10H28m0-2H10a2,2,0,0,0-2,2V28a2,2,0,0,0,2,2H28a2,2,0,0,0,2-2V10a2,2,0,0,0-2-2Z" transform="translate(0)"></path><path d="M4,18H2V4A2,2,0,0,1,4,2H18V4H4Z" transform="translate(0)"></path><rect fill="none" width="32" height="32"></rect></svg> <div class="absolute pointer-events-none transition-opacity bg-black text-white py-1 px-2 leading-tight rounded font-normal shadow left-1/2 top-full transform -translate-x-1/2 translate-y-2 opacity-0"><div class="absolute bottom-full left-1/2 transform -translate-x-1/2 w-0 h-0 border-black border-4 border-t-0" style="border-left-color: transparent; border-right-color: transparent; "></div> Copied</div></button></div> <pre class=""><!-- HTML_TAG_START -->tokenizer.apply_chat_template(messages, tokenize=<span class="hljs-literal">False</span>, add_generation_prompt=<span class="hljs-literal">False</span>)
	<span class="hljs-string">"""<\|im_start\|>user
	Hi there!<\|im_end\|>
	<\|im_start\|>assistant
	Nice to meet you!<\|im_end\|>
	<\|im_start\|>user
	Can I ask a question?<\|im_end\|>
	"""</span><!-- HTML_TAG_END --></pre></div> <p data-svelte-h="svelte-61bp3d">And here’s what it looks like <strong>with</strong> a generation prompt:</p> <div class="code-block relative"><div class="absolute top-2.5 right-4"><button class="inline-flex items-center relative text-sm focus:text-green-500 cursor-pointer focus:outline-none transition duration-200 ease-in-out opacity-0 mx-0.5 text-gray-600 " title="code excerpt" type="button"><svg class="" xmlns="http://www.w3.org/2000/svg" aria-hidden="true" fill="currentColor" focusable="false" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 32 32"><path d="M28,10V28H10V10H28m0-2H10a2,2,0,0,0-2,2V28a2,2,0,0,0,2,2H28a2,2,0,0,0,2-2V10a2,2,0,0,0-2-2Z" transform="translate(0)"></path><path d="M4,18H2V4A2,2,0,0,1,4,2H18V4H4Z" transform="translate(0)"></path><rect fill="none" width="32" height="32"></rect></svg> <div class="absolute pointer-events-none transition-opacity bg-black text-white py-1 px-2 leading-tight rounded font-normal shadow left-1/2 top-full transform -translate-x-1/2 translate-y-2 opacity-0"><div class="absolute bottom-full left-1/2 transform -translate-x-1/2 w-0 h-0 border-black border-4 border-t-0" style="border-left-color: transparent; border-right-color: transparent; "></div> Copied</div></button></div> <pre class=""><!-- HTML_TAG_START -->tokenizer.apply_chat_template(messages, tokenize=<span class="hljs-literal">False</span>, add_generation_prompt=<span class="hljs-literal">True</span>)
	<span class="hljs-string">"""<\|im_start\|>user
	Hi there!<\|im_end\|>
	<\|im_start\|>assistant
	Nice to meet you!<\|im_end\|>
	<\|im_start\|>user
	Can I ask a question?<\|im_end\|>
	<\|im_start\|>assistant
	"""</span><!-- HTML_TAG_END --></pre></div> <p data-svelte-h="svelte-inq88f">Note that this time, we’ve added the tokens that indicate the start of a bot response. This ensures that when the model
	generates text it will write a bot response instead of doing something unexpected, like continuing the user’s
	message. Remember, chat models are still just language models - they’re trained to continue text, and chat is just a
	special kind of text to them! You need to guide them with appropriate control tokens, so they know what they’re
	supposed to be doing.</p> <p data-svelte-h="svelte-uz30n4">Not all models require generation prompts. Some models, like LLaMA, don’t have any
	special tokens before bot responses. In these cases, the <code>add_generation_prompt</code> argument will have no effect. The exact
	effect that <code>add_generation_prompt</code> has will depend on the template being used.</p> <h2 class="relative group"><a id="what-does-continuefinalmessage-do" class="header-link block pr-1.5 text-lg no-hover:hidden with-hover:absolute with-hover:p-1.5 with-hover:opacity-0 with-hover:group-hover:opacity-100 with-hover:right-full" href="#what-does-continuefinalmessage-do"><span><svg class="" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink" aria-hidden="true" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 256 256"><path d="M167.594 88.393a8.001 8.001 0 0 1 0 11.314l-67.882 67.882a8 8 0 1 1-11.314-11.315l67.882-67.881a8.003 8.003 0 0 1 11.314 0zm-28.287 84.86l-28.284 28.284a40 40 0 0 1-56.567-56.567l28.284-28.284a8 8 0 0 0-11.315-11.315l-28.284 28.284a56 56 0 0 0 79.196 79.197l28.285-28.285a8 8 0 1 0-11.315-11.314zM212.852 43.14a56.002 56.002 0 0 0-79.196 0l-28.284 28.284a8 8 0 1 0 11.314 11.314l28.284-28.284a40 40 0 0 1 56.568 56.567l-28.285 28.285a8 8 0 0 0 11.315 11.314l28.284-28.284a56.065 56.065 0 0 0 0-79.196z" fill="currentColor"></path></svg></span></a> <span>What does “continue_final_message” do?</span></h2> <p data-svelte-h="svelte-y1327w">When passing a list of messages to <code>apply_chat_template</code> or <code>TextGenerationPipeline</code>, you can choose
	to format the chat so the model will continue the final message in the chat instead of starting a new one. This is done
	by removing any end-of-sequence tokens that indicate the end of the final message, so that the model will simply
	extend the final message when it begins to generate text. This is useful for “prefilling” the model’s response.</p> <p data-svelte-h="svelte-wwwyth">Here’s an example:</p> <div class="code-block relative"><div class="absolute top-2.5 right-4"><button class="inline-flex items-center relative text-sm focus:text-green-500 cursor-pointer focus:outline-none transition duration-200 ease-in-out opacity-0 mx-0.5 text-gray-600 " title="code excerpt" type="button"><svg class="" xmlns="http://www.w3.org/2000/svg" aria-hidden="true" fill="currentColor" focusable="false" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 32 32"><path d="M28,10V28H10V10H28m0-2H10a2,2,0,0,0-2,2V28a2,2,0,0,0,2,2H28a2,2,0,0,0,2-2V10a2,2,0,0,0-2-2Z" transform="translate(0)"></path><path d="M4,18H2V4A2,2,0,0,1,4,2H18V4H4Z" transform="translate(0)"></path><rect fill="none" width="32" height="32"></rect></svg> <div class="absolute pointer-events-none transition-opacity bg-black text-white py-1 px-2 leading-tight rounded font-normal shadow left-1/2 top-full transform -translate-x-1/2 translate-y-2 opacity-0"><div class="absolute bottom-full left-1/2 transform -translate-x-1/2 w-0 h-0 border-black border-4 border-t-0" style="border-left-color: transparent; border-right-color: transparent; "></div> Copied</div></button></div> <pre class=""><!-- HTML_TAG_START -->chat = [
	{<span class="hljs-string">"role"</span>: <span class="hljs-string">"user"</span>, <span class="hljs-string">"content"</span>: <span class="hljs-string">"Can you format the answer in JSON?"</span>},
	{<span class="hljs-string">"role"</span>: <span class="hljs-string">"assistant"</span>, <span class="hljs-string">"content"</span>: <span class="hljs-string">'{"name": "'</span>},
	]

	formatted_chat = tokenizer.apply_chat_template(chat, tokenize=<span class="hljs-literal">True</span>, return_dict=<span class="hljs-literal">True</span>, continue_final_message=<span class="hljs-literal">True</span>)
	model.generate(**formatted_chat)<!-- HTML_TAG_END --></pre></div> <p data-svelte-h="svelte-j6m3wj">The model will generate text that continues the JSON string, rather than starting a new message. This approach
	can be very useful for improving the accuracy of the model’s instruction-following when you know how you want
	it to start its replies.</p> <p data-svelte-h="svelte-hfpwig">Because <code>add_generation_prompt</code> adds the tokens that start a new message, and <code>continue_final_message</code> removes any
	end-of-message tokens from the final message, it does not make sense to use them together. As a result, you’ll
	get an error if you try!</p> <div class="course-tip bg-gradient-to-br dark:bg-gradient-to-r before:border-green-500 dark:before:border-green-800 from-green-50 dark:from-gray-900 to-white dark:to-gray-950 border border-green-50 text-green-700 dark:text-gray-400"><p data-svelte-h="svelte-95bbxf">The default behaviour of <code>TextGenerationPipeline</code> is to set <code>add_generation_prompt=True</code> so that it starts a new
	message. However, if the final message in the input chat has the “assistant” role, it will assume that this message is
	a prefill and switch to <code>continue_final_message=True</code> instead, because most models do not support multiple
	consecutive assistant messages. You can override this behaviour by explicitly passing the <code>continue_final_message</code>
	argument when calling the pipeline.</p></div> <h2 class="relative group"><a id="can-i-use-chat-templates-in-training" class="header-link block pr-1.5 text-lg no-hover:hidden with-hover:absolute with-hover:p-1.5 with-hover:opacity-0 with-hover:group-hover:opacity-100 with-hover:right-full" href="#can-i-use-chat-templates-in-training"><span><svg class="" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink" aria-hidden="true" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 256 256"><path d="M167.594 88.393a8.001 8.001 0 0 1 0 11.314l-67.882 67.882a8 8 0 1 1-11.314-11.315l67.882-67.881a8.003 8.003 0 0 1 11.314 0zm-28.287 84.86l-28.284 28.284a40 40 0 0 1-56.567-56.567l28.284-28.284a8 8 0 0 0-11.315-11.315l-28.284 28.284a56 56 0 0 0 79.196 79.197l28.285-28.285a8 8 0 1 0-11.315-11.314zM212.852 43.14a56.002 56.002 0 0 0-79.196 0l-28.284 28.284a8 8 0 1 0 11.314 11.314l28.284-28.284a40 40 0 0 1 56.568 56.567l-28.285 28.285a8 8 0 0 0 11.315 11.314l28.284-28.284a56.065 56.065 0 0 0 0-79.196z" fill="currentColor"></path></svg></span></a> <span>Can I use chat templates in training?</span></h2> <p data-svelte-h="svelte-i3l9c1">Yes! This is a good way to ensure that the chat template matches the tokens the model sees during training.
	We recommend that you apply the chat template as a preprocessing step for your dataset. After this, you
	can simply continue like any other language model training task. When training, you should usually set
	<code>add_generation_prompt=False</code>, because the added tokens to prompt an assistant response will not be helpful during
	training. Let’s see an example:</p> <div class="code-block relative"><div class="absolute top-2.5 right-4"><button class="inline-flex items-center relative text-sm focus:text-green-500 cursor-pointer focus:outline-none transition duration-200 ease-in-out opacity-0 mx-0.5 text-gray-600 " title="code excerpt" type="button"><svg class="" xmlns="http://www.w3.org/2000/svg" aria-hidden="true" fill="currentColor" focusable="false" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 32 32"><path d="M28,10V28H10V10H28m0-2H10a2,2,0,0,0-2,2V28a2,2,0,0,0,2,2H28a2,2,0,0,0,2-2V10a2,2,0,0,0-2-2Z" transform="translate(0)"></path><path d="M4,18H2V4A2,2,0,0,1,4,2H18V4H4Z" transform="translate(0)"></path><rect fill="none" width="32" height="32"></rect></svg> <div class="absolute pointer-events-none transition-opacity bg-black text-white py-1 px-2 leading-tight rounded font-normal shadow left-1/2 top-full transform -translate-x-1/2 translate-y-2 opacity-0"><div class="absolute bottom-full left-1/2 transform -translate-x-1/2 w-0 h-0 border-black border-4 border-t-0" style="border-left-color: transparent; border-right-color: transparent; "></div> Copied</div></button></div> <pre class=""><!-- HTML_TAG_START --><span class="hljs-keyword">from</span> transformers <span class="hljs-keyword">import</span> AutoTokenizer
	<span class="hljs-keyword">from</span> datasets <span class="hljs-keyword">import</span> Dataset

	tokenizer = AutoTokenizer.from_pretrained(<span class="hljs-string">"HuggingFaceH4/zephyr-7b-beta"</span>)

	chat1 = [
	{<span class="hljs-string">"role"</span>: <span class="hljs-string">"user"</span>, <span class="hljs-string">"content"</span>: <span class="hljs-string">"Which is bigger, the moon or the sun?"</span>},
	{<span class="hljs-string">"role"</span>: <span class="hljs-string">"assistant"</span>, <span class="hljs-string">"content"</span>: <span class="hljs-string">"The sun."</span>}
	]
	chat2 = [
	{<span class="hljs-string">"role"</span>: <span class="hljs-string">"user"</span>, <span class="hljs-string">"content"</span>: <span class="hljs-string">"Which is bigger, a virus or a bacterium?"</span>},
	{<span class="hljs-string">"role"</span>: <span class="hljs-string">"assistant"</span>, <span class="hljs-string">"content"</span>: <span class="hljs-string">"A bacterium."</span>}
	]

	dataset = Dataset.from_dict({<span class="hljs-string">"chat"</span>: [chat1, chat2]})
	dataset = dataset.<span class="hljs-built_in">map</span>(<span class="hljs-keyword">lambda</span> x: {<span class="hljs-string">"formatted_chat"</span>: tokenizer.apply_chat_template(x[<span class="hljs-string">"chat"</span>], tokenize=<span class="hljs-literal">False</span>, add_generation_prompt=<span class="hljs-literal">False</span>)})
	<span class="hljs-built_in">print</span>(dataset[<span class="hljs-string">'formatted_chat'</span>][<span class="hljs-number">0</span>])<!-- HTML_TAG_END --></pre></div> <p data-svelte-h="svelte-13505nn">And we get:</p> <div class="code-block relative"><div class="absolute top-2.5 right-4"><button class="inline-flex items-center relative text-sm focus:text-green-500 cursor-pointer focus:outline-none transition duration-200 ease-in-out opacity-0 mx-0.5 text-gray-600 " title="code excerpt" type="button"><svg class="" xmlns="http://www.w3.org/2000/svg" aria-hidden="true" fill="currentColor" focusable="false" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 32 32"><path d="M28,10V28H10V10H28m0-2H10a2,2,0,0,0-2,2V28a2,2,0,0,0,2,2H28a2,2,0,0,0,2-2V10a2,2,0,0,0-2-2Z" transform="translate(0)"></path><path d="M4,18H2V4A2,2,0,0,1,4,2H18V4H4Z" transform="translate(0)"></path><rect fill="none" width="32" height="32"></rect></svg> <div class="absolute pointer-events-none transition-opacity bg-black text-white py-1 px-2 leading-tight rounded font-normal shadow left-1/2 top-full transform -translate-x-1/2 translate-y-2 opacity-0"><div class="absolute bottom-full left-1/2 transform -translate-x-1/2 w-0 h-0 border-black border-4 border-t-0" style="border-left-color: transparent; border-right-color: transparent; "></div> Copied</div></button></div> <pre class=""><!-- HTML_TAG_START --><\|user\|>
	Which is bigger, the moon or the sun?</s>
	<\|assistant\|>
	The sun.</s><!-- HTML_TAG_END --></pre></div> <p data-svelte-h="svelte-ziuqkt">From here, just continue training like you would with a standard language modelling task, using the <code>formatted_chat</code> column.</p> <div class="course-tip bg-gradient-to-br dark:bg-gradient-to-r before:border-green-500 dark:before:border-green-800 from-green-50 dark:from-gray-900 to-white dark:to-gray-950 border border-green-50 text-green-700 dark:text-gray-400"><p data-svelte-h="svelte-148xjo3">By default, some tokenizers add special tokens like <code><bos></code> and <code><eos></code> to text they tokenize. Chat templates should
	already include all the special tokens they need, and so additional special tokens will often be incorrect or
	duplicated, which will hurt model performance.</p> <p data-svelte-h="svelte-1hgzema">Therefore, if you format text with <code>apply_chat_template(tokenize=False)</code>, you should set the argument
	<code>add_special_tokens=False</code> when you tokenize that text later. If you use <code>apply_chat_template(tokenize=True)</code>, you don’t need to worry about this!</p></div> <a class="!text-gray-400 !no-underline text-sm flex items-center not-prose mt-4" href="https://github.com/huggingface/transformers/blob/main/docs/source/en/chat_template_basics.md" target="_blank"><span data-svelte-h="svelte-1kd6by1"><</span> <span data-svelte-h="svelte-x0xyl0">></span> <span data-svelte-h="svelte-1dajgef"><span class="underline ml-1.5">Update</span> on GitHub</span></a> <p></p>

	<script>
	{
	__sveltekit_1yq8tgy = {
	assets: "/docs/transformers/main/en",
	base: "/docs/transformers/main/en",
	env: {}
	};

	const element = document.currentScript.parentElement;

	const data = [null,null];

	Promise.all([
	import("/docs/transformers/main/en/_app/immutable/entry/start.8cba93b8.js"),
	import("/docs/transformers/main/en/_app/immutable/entry/app.00a1188c.js")
	]).then(([kit, app]) => {
	kit.start(app, element, {
	node_ids: [0, 12],
	data,
	form: null,
	error: null
	});
	});
	}
	</script>

Xet Storage Details

Size:: 48.4 kB
Xet hash:: 99b5f1de3c5cc22366189480189993d0545e92bc62cd68f8d2eed2445c7f7b69

Xet efficiently stores files, intelligently splitting them into unique chunks and accelerating uploads and downloads. More info.