Buckets:

hf-doc-build
/

doc

Files

xet

hf-doc-build/doc / transformers /main /zh /serialization.html

HuggingFaceDocBuilder

about 6 hours ago

download

raw

29.3 kB

	<meta charset="utf-8" /><meta name="hf:doc:metadata" content="{"title":"导出为 ONNX","local":"导出为-onnx","sections":[{"title":"导出为 ONNX","local":"导出为-onnx","sections":[{"title":"使用 CLI 将 🤗 Transformers 模型导出为 ONNX","local":"使用-cli-将--transformers-模型导出为-onnx","sections":[],"depth":3},{"title":"使用 optimum.onnxruntime 将 🤗 Transformers 模型导出为 ONNX","local":"使用-optimumonnxruntime-将--transformers-模型导出为-onnx","sections":[],"depth":3},{"title":"导出尚未支持的架构的模型","local":"导出尚未支持的架构的模型","sections":[],"depth":3}],"depth":2}],"depth":1}"/>
	<link href="/docs/transformers/main/zh/_app/immutable/entry/start.Bp3iEC4w.js" rel="modulepreload">
	<link href="/docs/transformers/main/zh/_app/immutable/chunks/DrmD0Rpb.js" rel="modulepreload">
	<link href="/docs/transformers/main/zh/_app/immutable/chunks/CXkG2Njv.js" rel="modulepreload">
	<link href="/docs/transformers/main/zh/_app/immutable/entry/app.quCFocoA.js" rel="modulepreload">
	<link href="/docs/transformers/main/zh/_app/immutable/chunks/DIVbS_H2.js" rel="modulepreload">
	<link href="/docs/transformers/main/zh/_app/immutable/chunks/vWRU53YV.js" rel="modulepreload">
	<link href="/docs/transformers/main/zh/_app/immutable/chunks/nI_hILA6.js" rel="modulepreload">
	<link href="/docs/transformers/main/zh/_app/immutable/chunks/DsnmJJEf.js" rel="modulepreload">
	<link href="/docs/transformers/main/zh/_app/immutable/nodes/0.Ce5_hrcl.js" rel="modulepreload">
	<link href="/docs/transformers/main/zh/_app/immutable/chunks/BzOTTIhU.js" rel="modulepreload">
	<link href="/docs/transformers/main/zh/_app/immutable/nodes/63.Cc6HS2SW.js" rel="modulepreload">
	<link href="/docs/transformers/main/zh/_app/immutable/chunks/D9hIwwWE.js" rel="modulepreload">
	<!--kqg36n--><meta name="hf:doc:metadata" content="{"title":"导出为 ONNX","local":"导出为-onnx","sections":[{"title":"导出为 ONNX","local":"导出为-onnx","sections":[{"title":"使用 CLI 将 🤗 Transformers 模型导出为 ONNX","local":"使用-cli-将--transformers-模型导出为-onnx","sections":[],"depth":3},{"title":"使用 optimum.onnxruntime 将 🤗 Transformers 模型导出为 ONNX","local":"使用-optimumonnxruntime-将--transformers-模型导出为-onnx","sections":[],"depth":3},{"title":"导出尚未支持的架构的模型","local":"导出尚未支持的架构的模型","sections":[],"depth":3}],"depth":2}],"depth":1}"/><!---->
	<link href="/docs/transformers/main/zh/_app/immutable/assets/0.tn0RQdqM.css" rel="modulepreload"> <!--[--><!--[0--><!--[--><!--[0--><!--[--><p></p> <div class="items-center shrink-0 min-w-[100px] max-sm:min-w-[50px] justify-end ml-auto flex" style="float: right; margin-left: 10px; display: inline-flex; position: relative; z-index: 10;"><div class="inline-flex rounded-md max-sm:rounded-sm"><button class="inline-flex items-center gap-1 h-7 max-sm:h-7 px-2 max-sm:px-1.5 text-sm font-medium text-gray-800 border border-r-0 rounded-l-md max-sm:rounded-l-sm border-gray-200 bg-white hover:shadow-inner dark:border-gray-850 dark:bg-gray-950 dark:text-gray-200 dark:hover:bg-gray-800" aria-live="polite"><span class="inline-flex items-center justify-center rounded-md p-0.5 max-sm:p-0 hover:text-gray-800 dark:hover:text-gray-200"><svg class="sm:size-3.5 size-3" 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><!----></span> <span>Copy page</span></button> <button class="inline-flex items-center justify-center w-6 max-sm:w-5 h-7 max-sm:h-7 disabled:pointer-events-none text-sm text-gray-500 hover:text-gray-700 dark:hover:text-white rounded-r-md max-sm:rounded-r-sm border border-l transition border-gray-200 bg-white hover:shadow-inner dark:border-gray-850 dark:bg-gray-950 dark:text-gray-200 dark:hover:bg-gray-800" aria-haspopup="menu" aria-expanded="false" aria-label="Open copy menu"><svg class="transition-transform text-gray-400 overflow-visible sm:size-3.5 size-3 rotate-0" width="1em" height="1em" viewBox="0 0 12 7" fill="none" xmlns="http://www.w3.org/2000/svg"><path d="M1 1L6 6L11 1" stroke="currentColor"></path></svg><!----></button></div> <!--[-1--><!--]--></div><!----> <!--[0--><h1 class="relative group"><a id="导出为-onnx" 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="#导出为-onnx"><span><svg 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>导出为 ONNX</span></h1><!--]--><!----> <p>在生产环境中部署 🤗 Transformers 模型通常需要或者能够受益于，将模型导出为可在专门的运行时和硬件上加载和执行的序列化格式。</p> <p>🤗 Optimum 是 Transformers 的扩展，可以通过其 <code>exporters</code> 模块将模型从 PyTorch 或 TensorFlow 导出为 ONNX 及 TFLite 等序列化格式。🤗 Optimum 还提供了一套性能优化工具，可以在目标硬件上以最高效率训练和运行模型。</p> <p>本指南演示了如何使用 🤗 Optimum 将 🤗 Transformers 模型导出为 ONNX。有关将模型导出为 TFLite 的指南，请参考 <a href="tflite">导出为 TFLite 页面</a>。</p> <!--[1--><h2 class="relative group"><a id="导出为-onnx" 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="#导出为-onnx"><span><svg 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>导出为 ONNX</span></h2><!--]--><!----> <p><a href="http://onnx.ai" rel="nofollow">ONNX (Open Neural Network eXchange 开放神经网络交换)</a> 是一个开放的标准，它定义了一组通用的运算符和一种通用的文件格式，用于表示包括 PyTorch 和 TensorFlow 在内的各种框架中的深度学习模型。当一个模型被导出为 ONNX时，这些运算符被用于构建计算图（通常被称为<em>中间表示</em>），该图表示数据在神经网络中的流动。</p> <p>通过公开具有标准化运算符和数据类型的图，ONNX使得模型能够轻松在不同深度学习框架间切换。例如，在 PyTorch 中训练的模型可以被导出为 ONNX，然后再导入到 TensorFlow（反之亦然）。</p> <p>导出为 ONNX 后，模型可以：</p> <ul><li>通过 <a href="https://huggingface.co/docs/optimum/onnxruntime/usage_guides/optimization" rel="nofollow">图优化（graph optimization）</a> 和 <a href="https://huggingface.co/docs/optimum/onnxruntime/usage_guides/quantization" rel="nofollow">量化（quantization）</a> 等技术进行推理优化。</li> <li>通过 <a href="https://huggingface.co/docs/optimum/onnxruntime/package_reference/modeling_ort" rel="nofollow"><code>ORTModelForXXX</code> 类</a> 使用 ONNX Runtime 运行，它同样遵循你熟悉的 Transformers 中的 <code>AutoModel</code> API。</li> <li>使用 <a href="https://huggingface.co/docs/optimum/main/en/onnxruntime/usage_guides/pipelines" rel="nofollow">优化推理流水线（pipeline）</a> 运行，其 API 与 🤗 Transformers 中的 <a href="/docs/transformers/main/zh/main_classes/pipelines#transformers.pipeline">pipeline()</a> 函数相同。</li></ul> <p>🤗 Optimum 通过利用配置对象提供对 ONNX 导出的支持。多种模型架构已经有现成的配置对象，并且配置对象也被设计得易于扩展以适用于其他架构。</p> <p>现有的配置列表请参考 <a href="https://huggingface.co/docs/optimum/exporters/onnx/overview" rel="nofollow">🤗 Optimum 文档</a>。</p> <p>有两种方式可以将 🤗 Transformers 模型导出为 ONNX，这里我们展示这两种方法：</p> <ul><li>使用 🤗 Optimum 的 CLI（命令行）导出。</li> <li>使用 🤗 Optimum 的 <code>optimum.onnxruntime</code> 模块导出。</li></ul> <!--[2--><h3 class="relative group"><a id="使用-cli-将--transformers-模型导出为-onnx" 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-cli-将--transformers-模型导出为-onnx"><span><svg 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 CLI 将 🤗 Transformers 模型导出为 ONNX</span></h3><!--]--><!----> <p>要将 🤗 Transformers 模型导出为 ONNX，首先需要安装额外的依赖项：</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 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="language-bash "><!---->pip install optimum-onnx<!----></pre></div><!----> <p>请参阅 <a href="https://huggingface.co/docs/optimum/exporters/onnx/usage_guides/export_a_model#exporting-a-model-to-onnx-using-the-cli" rel="nofollow">🤗 Optimum 文档</a> 以查看所有可用参数，或者在命令行中查看帮助：</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 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="language-bash "><!---->optimum-cli <span class="hljs-built_in">export</span> onnx --<span class="hljs-built_in">help</span><!----></pre></div><!----> <p>运行以下命令，以从 🤗 Hub 导出模型的检查点（checkpoint），以 <code>distilbert/distilbert-base-uncased-distilled-squad</code> 为例：</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 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="language-bash "><!---->optimum-cli <span class="hljs-built_in">export</span> onnx --model distilbert/distilbert-base-uncased-distilled-squad distilbert_base_uncased_squad_onnx/<!----></pre></div><!----> <p>你应该能在日志中看到导出进度以及生成的 <code>model.onnx</code> 文件的保存位置，如下所示：</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 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="language-bash "><!---->Validating ONNX model distilbert_base_uncased_squad_onnx/model.onnx...
	-[✓] ONNX model output names match reference model (start_logits, end_logits)
	- Validating ONNX Model output <span class="hljs-string">"start_logits"</span>:
	-[✓] (2, 16) matches (2, 16)
	-[✓] all values close (atol: 0.0001)
	- Validating ONNX Model output <span class="hljs-string">"end_logits"</span>:
	-[✓] (2, 16) matches (2, 16)
	-[✓] all values close (atol: 0.0001)
	The ONNX <span class="hljs-built_in">export</span> succeeded and the exported model was saved at: distilbert_base_uncased_squad_onnx<!----></pre></div><!----> <p>上面的示例说明了从 🤗 Hub 导出检查点的过程。导出本地模型时，首先需要确保将模型的权重和分词器文件保存在同一目录（<code>local_path</code>）中。在使用 CLI 时，将 <code>local_path</code> 传递给 <code>model</code> 参数，而不是 🤗 Hub 上的检查点名称，并提供 <code>--task</code> 参数。你可以在 <a href="https://huggingface.co/docs/optimum/exporters/task_manager" rel="nofollow">🤗 Optimum 文档</a>中查看支持的任务列表。如果未提供 <code>task</code> 参数，将默认导出不带特定任务头的模型架构。</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 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="language-bash "><!---->optimum-cli <span class="hljs-built_in">export</span> onnx --model local_path --task question-answering distilbert_base_uncased_squad_onnx/<!----></pre></div><!----> <p>生成的 <code>model.onnx</code> 文件可以在支持 ONNX 标准的 <a href="https://onnx.ai/supported-tools.html#deployModel" rel="nofollow">许多加速引擎（accelerators）</a> 之一上运行。例如，我们可以使用 <a href="https://onnxruntime.ai/" rel="nofollow">ONNX Runtime</a> 加载和运行模型，如下所示：</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 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="language-python "><!----><span class="hljs-meta">>>> </span><span class="hljs-keyword">from</span> transformers <span class="hljs-keyword">import</span> AutoTokenizer
	<span class="hljs-meta">>>> </span><span class="hljs-keyword">from</span> optimum.onnxruntime <span class="hljs-keyword">import</span> ORTModelForQuestionAnswering

	<span class="hljs-meta">>>> </span>tokenizer = AutoTokenizer.from_pretrained(<span class="hljs-string">"distilbert_base_uncased_squad_onnx"</span>)
	<span class="hljs-meta">>>> </span>model = ORTModelForQuestionAnswering.from_pretrained(<span class="hljs-string">"distilbert_base_uncased_squad_onnx"</span>)
	<span class="hljs-meta">>>> </span>inputs = tokenizer(<span class="hljs-string">"What am I using?"</span>, <span class="hljs-string">"Using DistilBERT with ONNX Runtime!"</span>, return_tensors=<span class="hljs-string">"pt"</span>)
	<span class="hljs-meta">>>> </span>outputs = model(**inputs)<!----></pre></div><!----> <!--[2--><h3 class="relative group"><a id="使用-optimumonnxruntime-将--transformers-模型导出为-onnx" 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-optimumonnxruntime-将--transformers-模型导出为-onnx"><span><svg 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 optimum.onnxruntime 将 🤗 Transformers 模型导出为 ONNX</span></h3><!--]--><!----> <p>除了 CLI 之外，你还可以使用代码将 🤗 Transformers 模型导出为 ONNX，如下所示：</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 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="language-python "><!----><span class="hljs-meta">>>> </span><span class="hljs-keyword">from</span> optimum.onnxruntime <span class="hljs-keyword">import</span> ORTModelForSequenceClassification
	<span class="hljs-meta">>>> </span><span class="hljs-keyword">from</span> transformers <span class="hljs-keyword">import</span> AutoTokenizer

	<span class="hljs-meta">>>> </span>model_checkpoint = <span class="hljs-string">"distilbert_base_uncased_squad"</span>
	<span class="hljs-meta">>>> </span>save_directory = <span class="hljs-string">"onnx/"</span>

	<span class="hljs-meta">>>> </span><span class="hljs-comment"># 从 transformers 加载模型并将其导出为 ONNX</span>
	<span class="hljs-meta">>>> </span>ort_model = ORTModelForSequenceClassification.from_pretrained(model_checkpoint, export=<span class="hljs-literal">True</span>)
	<span class="hljs-meta">>>> </span>tokenizer = AutoTokenizer.from_pretrained(model_checkpoint)

	<span class="hljs-meta">>>> </span><span class="hljs-comment"># 保存 onnx 模型以及分词器</span>
	<span class="hljs-meta">>>> </span>ort_model.save_pretrained(save_directory)
	<span class="hljs-meta">>>> </span>tokenizer.save_pretrained(save_directory)<!----></pre></div><!----> <!--[2--><h3 class="relative group"><a id="导出尚未支持的架构的模型" 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="#导出尚未支持的架构的模型"><span><svg 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>导出尚未支持的架构的模型</span></h3><!--]--><!----> <p>如果你想要为当前无法导出的模型添加支持，请先检查 <a href="https://huggingface.co/docs/optimum/exporters/onnx/overview" rel="nofollow"><code>optimum.exporters.onnx</code></a> 是否支持该模型，如果不支持，你可以 <a href="https://huggingface.co/docs/optimum/exporters/onnx/usage_guides/contribute" rel="nofollow">直接为 🤗 Optimum 贡献代码</a>。</p> <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/serialization.md" target="_blank"><svg class="mr-1" 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="M31,16l-7,7l-1.41-1.41L28.17,16l-5.58-5.59L24,9l7,7z"></path><path d="M1,16l7-7l1.41,1.41L3.83,16l5.58,5.59L8,23l-7-7z"></path><path d="M12.419,25.484L17.639,6.552l1.932,0.518L14.351,26.002z"></path></svg><!----> <span><span class="underline">Update</span> on GitHub</span></a><!----> <p></p><!--]--><!----><!--]--><!--]--><!--]--> <!--[-1--><!--]--><!--]-->

	<script>
	{
	__sveltekit_d0qre9 = {
	base: "/docs/transformers/main/zh",
	assets: "/docs/transformers/main/zh"
	};

	const element = document.currentScript.parentElement;

	Promise.all([
	import("/docs/transformers/main/zh/_app/immutable/entry/start.Bp3iEC4w.js"),
	import("/docs/transformers/main/zh/_app/immutable/entry/app.quCFocoA.js")
	]).then(([kit, app]) => {
	kit.start(app, element, {
	node_ids: [0, 63],
	data: [null,null],
	form: null,
	error: null
	});
	});
	}
	</script>

Xet Storage Details

Size:: 29.3 kB
Xet hash:: f5ffc7bb964d34c14b705bb1a992a553c5c7e16e246e89039e76dfea9ab53fd3

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