text-generation-inference/main/en/supported_models.html

<meta charset="utf-8" /><meta name="hf:doc:metadata" content="{&quot;title&quot;:&quot;Supported Models and Hardware&quot;,&quot;local&quot;:&quot;supported-models-and-hardware&quot;,&quot;sections&quot;:[{&quot;title&quot;:&quot;Supported Models&quot;,&quot;local&quot;:&quot;supported-models&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/34.037089f8.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;Supported Models and Hardware&quot;,&quot;local&quot;:&quot;supported-models-and-hardware&quot;,&quot;sections&quot;:[{&quot;title&quot;:&quot;Supported Models&quot;,&quot;local&quot;:&quot;supported-models&quot;,&quot;sections&quot;:[],&quot;depth&quot;:2}],&quot;depth&quot;:1}"><!-- HEAD_svelte-u9bgzb_END -->      <p></p>  <h1 class="relative group"><a id="supported-models-and-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-models-and-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 Models and Hardware</span></h1> <p data-svelte-h="svelte-1qb15ay">Text Generation Inference enables serving optimized models on specific hardware for the highest performance. The following sections list which models (VLMs &amp; LLMs) are supported.</p>  <h2 class="relative group"><a id="supported-models" 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-models"><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 Models</span></h2> <ul data-svelte-h="svelte-14dhxm1"><li><a href="https://huggingface.co/deepseek-ai/DeepSeek-V2" rel="nofollow">Deepseek V2</a></li> <li><a href="https://huggingface.co/HuggingFaceM4/idefics2-8b" rel="nofollow">Idefics 2</a> (Multimodal)</li> <li><a href="https://huggingface.co/llava-hf/llava-v1.6-vicuna-13b-hf" rel="nofollow">Llava Next (1.6)</a> (Multimodal)</li> <li><a href="https://huggingface.co/collections/meta-llama/llama-31-669fc079a0c406a149a5738f" rel="nofollow">Llama</a></li> <li><a href="https://huggingface.co/microsoft/Phi-3-mini-4k-instruct" rel="nofollow">Phi 3</a></li> <li><a href="https://huggingface.co/google/gemma-7b" rel="nofollow">Gemma</a></li> <li><a href="https://huggingface.co/google/paligemma-3b-pt-224" rel="nofollow">PaliGemma</a></li> <li><a href="https://huggingface.co/collections/google/gemma-2-release-667d6600fd5220e7b967f315" rel="nofollow">Gemma2</a></li> <li><a href="https://huggingface.co/CohereForAI/c4ai-command-r-plus" rel="nofollow">Cohere</a></li> <li><a href="https://huggingface.co/databricks/dbrx-instruct" rel="nofollow">Dbrx</a></li> <li><a href="https://huggingface.co/state-spaces/mamba-2.8b-slimpj" rel="nofollow">Mamba</a></li> <li><a href="https://huggingface.co/mistralai/Mistral-Nemo-Instruct-2407" rel="nofollow">Mistral</a></li> <li><a href="https://huggingface.co/mistralai/Mixtral-8x22B-Instruct-v0.1" rel="nofollow">Mixtral</a></li> <li><a href="https://huggingface.co/bigcode/gpt_bigcode-santacoder" rel="nofollow">Gpt Bigcode</a></li> <li><a href="https://huggingface.co/microsoft/phi-1_5" rel="nofollow">Phi</a></li> <li><a href="https://huggingface.co/microsoft/Phi-3.5-MoE-instruct" rel="nofollow">PhiMoe</a></li> <li><a href="https://huggingface.co/baichuan-inc/Baichuan2-7B-Chat" rel="nofollow">Baichuan</a></li> <li><a href="https://huggingface.co/tiiuae/falcon-7b-instruct" rel="nofollow">Falcon</a></li> <li><a href="https://huggingface.co/bigcode/starcoder2-15b-instruct-v0.1" rel="nofollow">StarCoder 2</a></li> <li><a href="https://huggingface.co/collections/Qwen/qwen2-6659360b33528ced941e557f" rel="nofollow">Qwen 2</a></li> <li><a href="https://huggingface.co/facebook/opt-6.7b" rel="nofollow">Opt</a></li> <li><a href="https://huggingface.co/google/flan-t5-xxl" rel="nofollow">T5</a></li> <li><a href="https://huggingface.co/facebook/galactica-120b" rel="nofollow">Galactica</a></li> <li><a href="https://huggingface.co/bigcode/santacoder" rel="nofollow">SantaCoder</a></li> <li><a href="https://huggingface.co/bigscience/bloom-560m" rel="nofollow">Bloom</a></li> <li><a href="https://huggingface.co/mosaicml/mpt-7b-instruct" rel="nofollow">Mpt</a></li> <li><a href="https://huggingface.co/openai-community/gpt2" rel="nofollow">Gpt2</a></li> <li><a href="https://huggingface.co/EleutherAI/gpt-neox-20b" rel="nofollow">Gpt Neox</a></li> <li><a href="https://huggingface.co/EleutherAI/gpt-j-6b" rel="nofollow">Gptj</a></li> <li><a href="https://huggingface.co/HuggingFaceM4/idefics-9b" rel="nofollow">Idefics</a> (Multimodal)</li></ul> <p data-svelte-h="svelte-qvuhj">If the above list lacks the model you would like to serve, depending on the model’s pipeline type, you can try to initialize and serve the model anyways to see how well it performs, but performance isn’t guaranteed for non-optimized models:</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-comment"># for causal LMs/text-generation models</span>
AutoModelForCausalLM.from_pretrained(&lt;model&gt;, device_map=<span class="hljs-string">&quot;auto&quot;</span>)`
<span class="hljs-comment"># or, for text-to-text generation models</span>
AutoModelForSeq2SeqLM.from_pretrained(&lt;model&gt;, device_map=<span class="hljs-string">&quot;auto&quot;</span>)<!-- HTML_TAG_END --></pre></div> <p data-svelte-h="svelte-1ujziby">If you wish to serve a supported model that already exists on a local folder, just point to the local folder.</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 -->text-generation-launcher --model-id &lt;PATH-TO-LOCAL-BLOOM&gt;<!-- 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/text-generation-inference/blob/main/docs/source/supported_models.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, 34],
							data,
							form: null,
							error: null
						});
					});
				}
			</script>