Buckets:

hf-doc-build
/

doc-dev

Files

xet

hf-doc-build/doc-dev / transformers /pr_28250 /zh /tiktoken.html

rtrm

about 1 month ago

download

raw

15 kB

	<meta charset="utf-8" /><meta name="hf:doc:metadata" content="{"title":"Transformers与Tiktonken的互操作性","local":"transformers与tiktonken的互操作性","sections":[{"title":"已知包含 tiktoken.model 文件发布的模型：","local":"已知包含-tiktokenmodel-文件发布的模型","sections":[],"depth":3},{"title":"使用示例","local":"使用示例","sections":[],"depth":2},{"title":"创建tiktoken词符化器(tokenizer)","local":"创建tiktoken词符化器tokenizer","sections":[],"depth":2}],"depth":1}">
	<link href="/docs/transformers/pr_28250/zh/_app/immutable/assets/0.e3b0c442.css" rel="modulepreload">
	<link rel="modulepreload" href="/docs/transformers/pr_28250/zh/_app/immutable/entry/start.359aefb2.js">
	<link rel="modulepreload" href="/docs/transformers/pr_28250/zh/_app/immutable/chunks/scheduler.9991993c.js">
	<link rel="modulepreload" href="/docs/transformers/pr_28250/zh/_app/immutable/chunks/singletons.0d57c151.js">
	<link rel="modulepreload" href="/docs/transformers/pr_28250/zh/_app/immutable/chunks/index.02cfeb18.js">
	<link rel="modulepreload" href="/docs/transformers/pr_28250/zh/_app/immutable/chunks/paths.03bfa24f.js">
	<link rel="modulepreload" href="/docs/transformers/pr_28250/zh/_app/immutable/entry/app.6c335e9f.js">
	<link rel="modulepreload" href="/docs/transformers/pr_28250/zh/_app/immutable/chunks/index.ed60ef0f.js">
	<link rel="modulepreload" href="/docs/transformers/pr_28250/zh/_app/immutable/nodes/0.2e1efaaf.js">
	<link rel="modulepreload" href="/docs/transformers/pr_28250/zh/_app/immutable/chunks/each.e59479a4.js">
	<link rel="modulepreload" href="/docs/transformers/pr_28250/zh/_app/immutable/nodes/66.59195adc.js">
	<link rel="modulepreload" href="/docs/transformers/pr_28250/zh/_app/immutable/chunks/CodeBlock.a73b7ee1.js">
	<link rel="modulepreload" href="/docs/transformers/pr_28250/zh/_app/immutable/chunks/EditOnGithub.ba269039.js"><!-- HEAD_svelte-u9bgzb_START --><meta name="hf:doc:metadata" content="{"title":"Transformers与Tiktonken的互操作性","local":"transformers与tiktonken的互操作性","sections":[{"title":"已知包含 tiktoken.model 文件发布的模型：","local":"已知包含-tiktokenmodel-文件发布的模型","sections":[],"depth":3},{"title":"使用示例","local":"使用示例","sections":[],"depth":2},{"title":"创建tiktoken词符化器(tokenizer)","local":"创建tiktoken词符化器tokenizer","sections":[],"depth":2}],"depth":1}"><!-- HEAD_svelte-u9bgzb_END --> <p></p> <h1 class="relative group"><a id="transformers与tiktonken的互操作性" 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="#transformers与tiktonken的互操作性"><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>Transformers与Tiktonken的互操作性</span></h1> <p data-svelte-h="svelte-24plml">在🤗 transformers中，当使用<code>from_pretrained</code>方法从Hub加载模型时，如果模型包含tiktoken格式的<code>tokenizer.model</code>文件，框架可以无缝支持tiktoken模型文件，并自动将其转换为我们的<a href="https://huggingface.co/docs/transformers/main/en/main_classes/tokenizer#transformers.PreTrainedTokenizerFast" rel="nofollow">快速词符化器</a>。</p> <h3 class="relative group"><a id="已知包含-tiktokenmodel-文件发布的模型" 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="#已知包含-tiktokenmodel-文件发布的模型"><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>已知包含 tiktoken.model 文件发布的模型：</span></h3> <ul data-svelte-h="svelte-tocjh9"><li>gpt2</li> <li>llama3</li></ul> <h2 class="relative group"><a id="使用示例" 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="#使用示例"><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>使用示例</span></h2> <p data-svelte-h="svelte-1i81m0l">为了在transformers中正确加载<code>tiktoken</code>文件，请确保<code>tiktoken.model</code>文件是tiktoken格式的，并且会在加载<code>from_pretrained</code>时自动加载。以下展示如何从同一个文件中加载词符化器(tokenizer)和模型：</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

	model_id = <span class="hljs-string">"meta-llama/Meta-Llama-3-8B-Instruct"</span>
	tokenizer = AutoTokenizer.from_pretrained(model_id, subfolder=<span class="hljs-string">"original"</span>) <!-- HTML_TAG_END --></pre></div> <h2 class="relative group"><a id="创建tiktoken词符化器tokenizer" 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="#创建tiktoken词符化器tokenizer"><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>创建tiktoken词符化器(tokenizer)</span></h2> <p data-svelte-h="svelte-41alvi"><code>tokenizer.model</code>文件中不包含任何额外的词符(token)或模式字符串(pattern strings)的信息。如果这些信息很重要，需要将词符化器(tokenizer)转换为适用于<a href="/docs/transformers/pr_28250/zh/main_classes/tokenizer#transformers.PreTrainedTokenizerFast">PreTrainedTokenizerFast</a>类的<code>tokenizer.json</code>格式。</p> <p data-svelte-h="svelte-1bwb20c">使用<a href="https://github.com/openai/tiktoken/blob/63527649963def8c759b0f91f2eb69a40934e468/tiktoken/registry.py#L63" rel="nofollow">tiktoken.get_encoding</a>生成<code>tokenizer.model</code>文件，再使用<code>convert_tiktoken_to_fast</code>函数将其转换为<code>tokenizer.json</code>文件。</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.integrations.tiktoken <span class="hljs-keyword">import</span> convert_tiktoken_to_fast
	<span class="hljs-keyword">from</span> tiktoken <span class="hljs-keyword">import</span> get_encoding

	<span class="hljs-comment"># You can load your custom encoding or the one provided by OpenAI</span>
	encoding = get_encoding(<span class="hljs-string">"gpt2"</span>)
	convert_tiktoken_to_fast(encoding, <span class="hljs-string">"config/save/dir"</span>)<!-- HTML_TAG_END --></pre></div> <p data-svelte-h="svelte-1ajlb2">生成的<code>tokenizer.json</code>文件将被保存到指定的目录，并且可以通过<a href="/docs/transformers/pr_28250/zh/main_classes/tokenizer#transformers.PreTrainedTokenizerFast">PreTrainedTokenizerFast</a>类来加载。</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 = PreTrainedTokenizerFast.from_pretrained(<span class="hljs-string">"config/save/dir"</span>)<!-- HTML_TAG_END --></pre></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/zh/tiktoken.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_qheazb = {
	assets: "/docs/transformers/pr_28250/zh",
	base: "/docs/transformers/pr_28250/zh",
	env: {}
	};

	const element = document.currentScript.parentElement;

	const data = [null,null];

	Promise.all([
	import("/docs/transformers/pr_28250/zh/_app/immutable/entry/start.359aefb2.js"),
	import("/docs/transformers/pr_28250/zh/_app/immutable/entry/app.6c335e9f.js")
	]).then(([kit, app]) => {
	kit.start(app, element, {
	node_ids: [0, 66],
	data,
	form: null,
	error: null
	});
	});
	}
	</script>

Xet Storage Details

Size:: 15 kB
Xet hash:: b81b84dcbc156981e90466cee3845be5dd73192fb41df567256bbdf2e20985a8

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