Buckets:
| <meta charset="utf-8" /><meta name="hf:doc:metadata" content="{"title":"Интеграция с Hugging Face Hub","local":"integrations-with-the-hugging-face-hub","sections":[{"title":"Загрузка моделей из Hugging Face Hub","local":"loading-models-from-the-hugging-face-hub","sections":[],"depth":3},{"title":"Загрузка с Hugging Face Spaces","local":"loading-from-hugging-face-spaces","sections":[],"depth":3}],"depth":1}"> | |
| <link href="/docs/course/pr_1069/ru/_app/immutable/assets/0.e3b0c442.css" rel="modulepreload"> | |
| <link rel="modulepreload" href="/docs/course/pr_1069/ru/_app/immutable/entry/start.48687cc8.js"> | |
| <link rel="modulepreload" href="/docs/course/pr_1069/ru/_app/immutable/chunks/scheduler.37c15a92.js"> | |
| <link rel="modulepreload" href="/docs/course/pr_1069/ru/_app/immutable/chunks/singletons.6f259016.js"> | |
| <link rel="modulepreload" href="/docs/course/pr_1069/ru/_app/immutable/chunks/index.18351ede.js"> | |
| <link rel="modulepreload" href="/docs/course/pr_1069/ru/_app/immutable/chunks/paths.930ed261.js"> | |
| <link rel="modulepreload" href="/docs/course/pr_1069/ru/_app/immutable/entry/app.b79a803d.js"> | |
| <link rel="modulepreload" href="/docs/course/pr_1069/ru/_app/immutable/chunks/index.2bf4358c.js"> | |
| <link rel="modulepreload" href="/docs/course/pr_1069/ru/_app/immutable/nodes/0.e11366e4.js"> | |
| <link rel="modulepreload" href="/docs/course/pr_1069/ru/_app/immutable/chunks/each.e59479a4.js"> | |
| <link rel="modulepreload" href="/docs/course/pr_1069/ru/_app/immutable/nodes/73.8e085730.js"> | |
| <link rel="modulepreload" href="/docs/course/pr_1069/ru/_app/immutable/chunks/CodeBlock.4e987730.js"> | |
| <link rel="modulepreload" href="/docs/course/pr_1069/ru/_app/immutable/chunks/CourseFloatingBanner.9ff4c771.js"> | |
| <link rel="modulepreload" href="/docs/course/pr_1069/ru/_app/immutable/chunks/DocNotebookDropdown.efc1fb7c.js"> | |
| <link rel="modulepreload" href="/docs/course/pr_1069/ru/_app/immutable/chunks/getInferenceSnippets.24b50994.js"><!-- HEAD_svelte-u9bgzb_START --><meta name="hf:doc:metadata" content="{"title":"Интеграция с Hugging Face Hub","local":"integrations-with-the-hugging-face-hub","sections":[{"title":"Загрузка моделей из Hugging Face Hub","local":"loading-models-from-the-hugging-face-hub","sections":[],"depth":3},{"title":"Загрузка с Hugging Face Spaces","local":"loading-from-hugging-face-spaces","sections":[],"depth":3}],"depth":1}"><!-- HEAD_svelte-u9bgzb_END --> <p></p> <h1 class="relative group"><a id="integrations-with-the-hugging-face-hub" 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="#integrations-with-the-hugging-face-hub"><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>Интеграция с Hugging Face Hub</span></h1> <div class="flex space-x-1 absolute z-10 right-0 top-0"><a href="https://discuss.huggingface.co/t/chapter-9-questions" target="_blank"><img alt="Ask a Question" class="!m-0" src="https://img.shields.io/badge/Ask%20a%20question-ffcb4c.svg?logo=data:image/svg+xml;base64,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"></a> <a href="https://colab.research.google.com/github/huggingface/notebooks/blob/master/course/en/chapter9/section5.ipynb" target="_blank"><img alt="Open In Colab" class="!m-0" src="https://colab.research.google.com/assets/colab-badge.svg"></a> <a href="https://studiolab.sagemaker.aws/import/github/huggingface/notebooks/blob/master/course/en/chapter9/section5.ipynb" target="_blank"><img alt="Open In Studio Lab" class="!m-0" src="https://studiolab.sagemaker.aws/studiolab.svg"></a></div> <p data-svelte-h="svelte-17qv02r">Чтобы сделать вашу жизнь еще проще, Gradio напрямую интегрируется с Hugging Face Hub и Hugging Face Spaces. | |
| Вы можете загружать демо из Hub и Spaces, используя всего <em>одну строку кода</em>.</p> <h3 class="relative group"><a id="loading-models-from-the-hugging-face-hub" 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="#loading-models-from-the-hugging-face-hub"><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>Загрузка моделей из Hugging Face Hub</span></h3> <p data-svelte-h="svelte-hdmlos">Для начала выберите одну из тысяч моделей, которые Hugging Face предлагает в Hub, как описано в <a href="../chapter4/2">Главе 4</a>.</p> <p data-svelte-h="svelte-la64n7">Используя специальный метод <code>Interface.load()</code>, вы передаете <code>"model/"</code> (или, эквивалентно, <code>"huggingface/"</code>) | |
| после чего следует имя модели. | |
| Например, здесь приведен код для создания демо для <a href="https://huggingface.co/EleutherAI/gpt-j-6B" rel="nofollow">GPT-J</a>, большой языковой модели, добавьте пару примеров ввода:</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">import</span> gradio <span class="hljs-keyword">as</span> gr | |
| title = <span class="hljs-string">"GPT-J-6B"</span> | |
| description = <span class="hljs-string">"Gradio Demo for GPT-J 6B, a transformer model trained using Ben Wang's Mesh Transformer JAX. 'GPT-J' refers to the class of model, while '6B' represents the number of trainable parameters. To use it, simply add your text, or click one of the examples to load them. Read more at the links below."</span> | |
| article = <span class="hljs-string">"<p style='text-align: center'><a href='https://github.com/kingoflolz/mesh-transformer-jax' target='_blank'>GPT-J-6B: A 6 Billion Parameter Autoregressive Language Model</a></p>"</span> | |
| gr.Interface.load( | |
| <span class="hljs-string">"huggingface/EleutherAI/gpt-j-6B"</span>, | |
| inputs=gr.Textbox(lines=<span class="hljs-number">5</span>, label=<span class="hljs-string">"Input Text"</span>), | |
| title=title, | |
| description=description, | |
| article=article, | |
| ).launch()<!-- HTML_TAG_END --></pre></div> <p data-svelte-h="svelte-1jejoka">Код, приведенный выше, приведет к созданию интерфейса, представленного ниже:</p> <iframe src="https://course-demos-gpt-j-6B.hf.space" frameborder="0" height="750" title="Gradio app" class="container p-0 flex-grow space-iframe" allow="accelerometer; ambient-light-sensor; autoplay; battery; camera; document-domain; encrypted-media; fullscreen; geolocation; gyroscope; layout-animations; legacy-image-formats; magnetometer; microphone; midi; oversized-images; payment; picture-in-picture; publickey-credentials-get; sync-xhr; usb; vr ; wake-lock; xr-spatial-tracking" sandbox="allow-forms allow-modals allow-popups allow-popups-to-escape-sandbox allow-same-origin allow-scripts allow-downloads"></iframe> <p data-svelte-h="svelte-1j527aq">Загрузка модели таким образом использует <a href="https://huggingface.co/inference-api" rel="nofollow">Inference API</a> Hugging Face, | |
| вместо того, чтобы загружать модель в память. Это идеально подходит для огромных моделей, таких как GPT-J или T0pp, которые | |
| которые требуют много RAM.</p> <h3 class="relative group"><a id="loading-from-hugging-face-spaces" 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="#loading-from-hugging-face-spaces"><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>Загрузка с Hugging Face Spaces</span></h3> <p data-svelte-h="svelte-1hfmqh8">Чтобы загрузить любое пространство (Space) из Hugging Face Hub и воссоздать его локально, вы можете передать <code>spaces/</code> в <code>Interface</code>, за которым следует имя пространства.</p> <p data-svelte-h="svelte-enuzxx">Помните демо из раздела 1, которое удаляет фон изображения? Давайте загрузим его из Hugging Face Spaces:</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 -->gr.Interface.load(<span class="hljs-string">"spaces/abidlabs/remove-bg"</span>).launch()<!-- HTML_TAG_END --></pre></div> <iframe src="https://course-demos-remove-bg-original.hf.space" frameborder="0" height="650" title="Gradio app" class="container p-0 flex-grow space-iframe" allow="accelerometer; ambient-light-sensor; autoplay; battery; camera; document-domain; encrypted-media; fullscreen; geolocation; gyroscope; layout-animations; legacy-image-formats; magnetometer; microphone; midi; oversized-images; payment; picture-in-picture; publickey-credentials-get; sync-xhr; usb; vr ; wake-lock; xr-spatial-tracking" sandbox="allow-forms allow-modals allow-popups allow-popups-to-escape-sandbox allow-same-origin allow-scripts allow-downloads"></iframe> <p data-svelte-h="svelte-anaqim">Одна из особенностей загрузки демо из Hub или Spaces заключается в том, что вы можете настраивать их | |
| переопределив любой из | |
| параметров. Здесь мы добавим заголовок и задействуем веб-камеру:</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 -->gr.Interface.load( | |
| <span class="hljs-string">"spaces/abidlabs/remove-bg"</span>, inputs=<span class="hljs-string">"webcam"</span>, title=<span class="hljs-string">"Remove your webcam background!"</span> | |
| ).launch()<!-- HTML_TAG_END --></pre></div> <iframe src="https://course-demos-Remove-bg.hf.space" frameborder="0" height="550" title="Gradio app" class="container p-0 flex-grow space-iframe" allow="accelerometer; ambient-light-sensor; autoplay; battery; camera; document-domain; encrypted-media; fullscreen; geolocation; gyroscope; layout-animations; legacy-image-formats; magnetometer; microphone; midi; oversized-images; payment; picture-in-picture; publickey-credentials-get; sync-xhr; usb; vr ; wake-lock; xr-spatial-tracking" sandbox="allow-forms allow-modals allow-popups allow-popups-to-escape-sandbox allow-same-origin allow-scripts allow-downloads"></iframe> <p data-svelte-h="svelte-v1bc9b">Теперь, когда мы изучили несколько способов интеграции Gradio с Hugging Face Hub, давайте рассмотрим некоторые дополнительные возможности класса <code>Interface</code>. Этому будет посвящен следующий раздел!</p> <a class="!text-gray-400 !no-underline text-sm flex items-center not-prose mt-4" href="https://github.com/huggingface/course/blob/main/chapters/ru/chapter9/5.mdx" 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_j8s7wf = { | |
| assets: "/docs/course/pr_1069/ru", | |
| base: "/docs/course/pr_1069/ru", | |
| env: {} | |
| }; | |
| const element = document.currentScript.parentElement; | |
| const data = [null,null]; | |
| Promise.all([ | |
| import("/docs/course/pr_1069/ru/_app/immutable/entry/start.48687cc8.js"), | |
| import("/docs/course/pr_1069/ru/_app/immutable/entry/app.b79a803d.js") | |
| ]).then(([kit, app]) => { | |
| kit.start(app, element, { | |
| node_ids: [0, 73], | |
| data, | |
| form: null, | |
| error: null | |
| }); | |
| }); | |
| } | |
| </script> | |
Xet Storage Details
- Size:
- 19.5 kB
- Xet hash:
- d0ae1c3dd65e4a3716fcd07a84ed47b81daf2b8dd010a54593aadc09ce4b05f0
·
Xet efficiently stores files, intelligently splitting them into unique chunks and accelerating uploads and downloads. More info.