Hugging Face's logo

Buckets:
hf-doc-build
/
doc-dev

Files
xet
hf-doc-build/doc-dev / text-generation-inference /main /en /quicktour.html
rtrm's picture
rtrm
download
raw
18.4 kB
<meta charset="utf-8" /><meta name="hf:doc:metadata" content="{&quot;title&quot;:&quot;Quick Tour&quot;,&quot;local&quot;:&quot;quick-tour&quot;,&quot;sections&quot;:[{&quot;title&quot;:&quot;Launching TGI&quot;,&quot;local&quot;:&quot;launching-tgi&quot;,&quot;sections&quot;:[{&quot;title&quot;:&quot;Supported hardware&quot;,&quot;local&quot;:&quot;supported-hardware&quot;,&quot;sections&quot;:[],&quot;depth&quot;:3}],&quot;depth&quot;:2},{&quot;title&quot;:&quot;Consuming TGI&quot;,&quot;local&quot;:&quot;consuming-tgi&quot;,&quot;sections&quot;:[],&quot;depth&quot;:2}],&quot;depth&quot;:1}">
 <link href="/docs/text-generation-inference/main/en/_app/immutable/assets/0.e3b0c442.css" rel="modulepreload">
 <link rel="modulepreload" href="/docs/text-generation-inference/main/en/_app/immutable/entry/start.1810066f.js">
 <link rel="modulepreload" href="/docs/text-generation-inference/main/en/_app/immutable/chunks/scheduler.362310b7.js">
 <link rel="modulepreload" href="/docs/text-generation-inference/main/en/_app/immutable/chunks/singletons.fa2b0eb7.js">
 <link rel="modulepreload" href="/docs/text-generation-inference/main/en/_app/immutable/chunks/index.7f53ec41.js">
 <link rel="modulepreload" href="/docs/text-generation-inference/main/en/_app/immutable/chunks/paths.284aef40.js">
 <link rel="modulepreload" href="/docs/text-generation-inference/main/en/_app/immutable/entry/app.8cfc1931.js">
 <link rel="modulepreload" href="/docs/text-generation-inference/main/en/_app/immutable/chunks/index.57dfc70d.js">
 <link rel="modulepreload" href="/docs/text-generation-inference/main/en/_app/immutable/nodes/0.543c9bd9.js">
 <link rel="modulepreload" href="/docs/text-generation-inference/main/en/_app/immutable/chunks/each.e59479a4.js">
 <link rel="modulepreload" href="/docs/text-generation-inference/main/en/_app/immutable/nodes/30.c092ab98.js">
 <link rel="modulepreload" href="/docs/text-generation-inference/main/en/_app/immutable/chunks/Tip.14b2ab21.js">
 <link rel="modulepreload" href="/docs/text-generation-inference/main/en/_app/immutable/chunks/CodeBlock.d3c47f83.js">
 <link rel="modulepreload" href="/docs/text-generation-inference/main/en/_app/immutable/chunks/EditOnGithub.9633c464.js"><!-- HEAD_svelte-u9bgzb_START --><meta name="hf:doc:metadata" content="{&quot;title&quot;:&quot;Quick Tour&quot;,&quot;local&quot;:&quot;quick-tour&quot;,&quot;sections&quot;:[{&quot;title&quot;:&quot;Launching TGI&quot;,&quot;local&quot;:&quot;launching-tgi&quot;,&quot;sections&quot;:[{&quot;title&quot;:&quot;Supported hardware&quot;,&quot;local&quot;:&quot;supported-hardware&quot;,&quot;sections&quot;:[],&quot;depth&quot;:3}],&quot;depth&quot;:2},{&quot;title&quot;:&quot;Consuming TGI&quot;,&quot;local&quot;:&quot;consuming-tgi&quot;,&quot;sections&quot;:[],&quot;depth&quot;:2}],&quot;depth&quot;:1}"><!-- HEAD_svelte-u9bgzb_END --> <p></p> <h1 class="relative group"><a id="quick-tour" 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="#quick-tour"><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>Quick Tour</span></h1> <p data-svelte-h="svelte-4u16lr">The easiest way of getting started is using the official Docker container. Install Docker following <a href="https://docs.docker.com/get-docker/" rel="nofollow">their installation instructions</a>.</p> <h2 class="relative group"><a id="launching-tgi" 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="#launching-tgi"><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>Launching TGI</span></h2> <p data-svelte-h="svelte-wdfj67">Let’s say you want to deploy <a href="https://huggingface.co/teknium/OpenHermes-2.5-Mistral-7B" rel="nofollow">teknium/OpenHermes-2.5-Mistral-7B</a> model with TGI on an Nvidia GPU. Here is an example on how to do that:</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 -->model=teknium/OpenHermes-2.5-Mistral-7B
volume=<span class="hljs-variable">$PWD</span>/data <span class="hljs-comment"># share a volume with the Docker container to avoid downloading weights every run</span>
docker run --gpus all --shm-size 1g -p 8080:80 -v <span class="hljs-variable">$volume</span>:/data \
 ghcr.io/huggingface/text-generation-inference:2.2.0 \
 --model-id <span class="hljs-variable">$model</span><!-- HTML_TAG_END --></pre></div> <h3 class="relative group"><a id="supported-hardware" 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="#supported-hardware"><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>Supported hardware</span></h3> <p data-svelte-h="svelte-2m8nz1">TGI supports various hardware. Make sure to check the <a href="./installation_nvidia">Using TGI with Nvidia GPUs</a>, <a href="./installation_amd">Using TGI with AMD GPUs</a>, <a href="./installation_intel">Using TGI with Intel GPUs</a>, <a href="./installation_gaudi">Using TGI with Gaudi</a>, <a href="./installation_inferentia">Using TGI with Inferentia</a> guides depending on which hardware you would like to deploy TGI on.</p> <h2 class="relative group"><a id="consuming-tgi" 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="#consuming-tgi"><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>Consuming TGI</span></h2> <p data-svelte-h="svelte-137l37q">Once TGI is running, you can use the <code>generate</code> endpoint or the Open AI Chat Completion API compatible <a href="https://huggingface.co/docs/text-generation-inference/en/messages_api" rel="nofollow">Messages API</a> by doing requests. To learn more about how to query the endpoints, check the <a href="./basic_tutorials/consuming_tgi">Consuming TGI</a> section, where we show examples with utility libraries and UIs. Below you can see a simple snippet to query the endpoint.</p> <div class="flex space-x-2 items-center my-1.5 mr-8 h-7 !pl-0 -mx-3 md:mx-0"><div class="flex items-center border rounded-lg px-1.5 py-1 leading-none select-none text-smd border-gray-800 bg-black dark:bg-gray-700 text-white"><svg class="mr-1.5" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink" aria-hidden="true" focusable="false" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 32 32"><path d="M15.84.5a16.4,16.4,0,0,0-3.57.32C9.1,1.39,8.53,2.53,8.53,4.64V7.48H16v1H5.77a4.73,4.73,0,0,0-4.7,3.74,14.82,14.82,0,0,0,0,7.54c.57,2.28,1.86,3.82,4,3.82h2.6V20.14a4.73,4.73,0,0,1,4.63-4.63h7.38a3.72,3.72,0,0,0,3.73-3.73V4.64A4.16,4.16,0,0,0,19.65.82,20.49,20.49,0,0,0,15.84.5ZM11.78,2.77a1.39,1.39,0,0,1,1.38,1.46,1.37,1.37,0,0,1-1.38,1.38A1.42,1.42,0,0,1,10.4,4.23,1.44,1.44,0,0,1,11.78,2.77Z" fill="#5a9fd4"></path><path d="M16.16,31.5a16.4,16.4,0,0,0,3.57-.32c3.17-.57,3.74-1.71,3.74-3.82V24.52H16v-1H26.23a4.73,4.73,0,0,0,4.7-3.74,14.82,14.82,0,0,0,0-7.54c-.57-2.28-1.86-3.82-4-3.82h-2.6v3.41a4.73,4.73,0,0,1-4.63,4.63H12.35a3.72,3.72,0,0,0-3.73,3.73v7.14a4.16,4.16,0,0,0,3.73,3.82A20.49,20.49,0,0,0,16.16,31.5Zm4.06-2.27a1.39,1.39,0,0,1-1.38-1.46,1.37,1.37,0,0,1,1.38-1.38,1.42,1.42,0,0,1,1.38,1.38A1.44,1.44,0,0,1,20.22,29.23Z" fill="#ffd43b"></path></svg> Python </div><div class="flex items-center border rounded-lg px-1.5 py-1 leading-none select-none text-smd text-gray-500 cursor-pointer opacity-90 hover:text-gray-700 dark:hover:text-gray-200 hover:shadow-sm"><svg class="mr-1.5" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink" aria-hidden="true" focusable="false" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 32 32"><rect width="32" height="32" fill="#f7df1e"></rect><path d="M21.5,25a3.27,3.27,0,0,0,3,1.83c1.25,0,2-.63,2-1.49,0-1-.81-1.39-2.19-2L23.56,23C21.39,22.1,20,20.94,20,18.49c0-2.25,1.72-4,4.41-4a4.44,4.44,0,0,1,4.27,2.41l-2.34,1.5a2,2,0,0,0-1.93-1.29,1.31,1.31,0,0,0-1.44,1.29c0,.9.56,1.27,1.85,1.83l.75.32c2.55,1.1,4,2.21,4,4.72,0,2.71-2.12,4.19-5,4.19a5.78,5.78,0,0,1-5.48-3.07Zm-10.63.26c.48.84.91,1.55,1.94,1.55s1.61-.39,1.61-1.89V14.69h3V25c0,3.11-1.83,4.53-4.49,4.53a4.66,4.66,0,0,1-4.51-2.75Z"></path></svg> JavaScript </div><div class="flex items-center border rounded-lg px-1.5 py-1 leading-none select-none text-smd text-gray-500 cursor-pointer opacity-90 hover:text-gray-700 dark:hover:text-gray-200 hover:shadow-sm"><svg class="mr-1.5" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink" aria-hidden="true" focusable="false" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 32 32"><rect width="32" height="32" rx="4" fill="#1683a5"></rect><path d="M6.71,14A5,5,0,0,1,8.82,9.29l2.64-2.2c1.67-1.37,2.52-1.41,4.6-1.41H21.7c1.19,0,2.45.27,2.45,1.79s-1.4,1.78-2.45,1.78H15.44a3.31,3.31,0,0,0-2,.89L11.24,12c-.55.44-1,.81-1,1.52v4.41c0,.7.41,1.07,1,1.52l2.16,1.82a3.34,3.34,0,0,0,2,.89H21.7c1.05,0,2.45.23,2.45,1.78s-1.26,1.78-2.45,1.78H16.06c-2.08,0-2.94,0-4.6-1.4L8.82,22.09A5.05,5.05,0,0,1,6.71,17.4Z" fill="#fff"></path></svg> cURL </div></div> <div class="language-select"> <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> requests
headers = {
 <span class="hljs-string">&quot;Content-Type&quot;</span>: <span class="hljs-string">&quot;application/json&quot;</span>,
}
data = {
 <span class="hljs-string">&#x27;inputs&#x27;</span>: <span class="hljs-string">&#x27;What is Deep Learning?&#x27;</span>,
 <span class="hljs-string">&#x27;parameters&#x27;</span>: {
 <span class="hljs-string">&#x27;max_new_tokens&#x27;</span>: <span class="hljs-number">20</span>,
 },
}
response = requests.post(<span class="hljs-string">&#x27;http://127.0.0.1:8080/generate&#x27;</span>, headers=headers, json=data)
<span class="hljs-built_in">print</span>(response.json())
<span class="hljs-comment"># {&#x27;generated_text&#x27;: &#x27;\n\nDeep Learning is a subset of Machine Learning that is concerned with the development of algorithms that can&#x27;}</span><!-- HTML_TAG_END --></pre></div> </div> <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-dfs9ks">To see all possible deploy flags and options, you can use the <code>--help</code> flag. It’s possible to configure the number of shards, quantization, generation parameters, and more.</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 -->docker run ghcr.io/huggingface/text-generation-inference:2.2.0 --<span class="hljs-built_in">help</span><!-- HTML_TAG_END --></pre></div></div> <a class="!text-gray-400 !no-underline text-sm flex items-center not-prose mt-4" href="https://github.com/huggingface/text-generation-inference/blob/main/docs/source/quicktour.md" target="_blank"><span data-svelte-h="svelte-1kd6by1">&lt;</span> <span data-svelte-h="svelte-x0xyl0">&gt;</span> <span data-svelte-h="svelte-1dajgef"><span class="underline ml-1.5">Update</span> on GitHub</span></a> <p></p>
<script>
 {
 __sveltekit_1dfb6m4 = {
 assets: "/docs/text-generation-inference/main/en",
 base: "/docs/text-generation-inference/main/en",
 env: {}
 };
 const element = document.currentScript.parentElement;
 const data = [null,null];
 Promise.all([
 import("/docs/text-generation-inference/main/en/_app/immutable/entry/start.1810066f.js"),
 import("/docs/text-generation-inference/main/en/_app/immutable/entry/app.8cfc1931.js")
 ]).then(([kit, app]) => {
 kit.start(app, element, {
 node_ids: [0, 30],
 data,
 form: null,
 error: null
 });
 });
 }
 </script>

Xet Storage Details

Size:
18.4 kB
·
Xet hash:
a61d6b6b91d992fd10e8fae9640489eb0530fa8249805f84dfcbf9b0ffc93e5f

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