mirror of
https://github.com/saymrwulf/onnxruntime.git
synced 2026-07-13 18:08:13 +00:00
Updated Hugging Face landing page (#18194)
### Description <!-- Describe your changes. --> ### Motivation and Context <!-- - Why is this change required? What problem does it solve? - If it fixes an open issue, please link to the issue here. -->
This commit is contained in:
sophies927
GitHub
parent
9bbb897822
commit
369a59c52b
3 changed files with 95 additions and 88 deletions
|
|
@ -1,7 +1,11 @@
|
|||
<script>
|
||||
export let widthscale = 1;
|
||||
export let heightscale = 1;
|
||||
</script>
|
||||
<svg
|
||||
stroke="currentColor"
|
||||
width="109"
|
||||
height="79"
|
||||
width={109 * widthscale}
|
||||
height={79 * heightscale}
|
||||
viewBox="0 0 109 79"
|
||||
fill="none"
|
||||
xmlns="http://www.w3.org/2000/svg"
|
||||
|
|
|
|||
|
Before Width: | Height: | Size: 31 KiB After Width: | Height: | Size: 32 KiB |
|
|
@ -1,7 +1,11 @@
|
|||
<script>
|
||||
export let widthscale = 1;
|
||||
export let heightscale = 1;
|
||||
</script>
|
||||
<svg
|
||||
stroke="currentColor"
|
||||
width="110"
|
||||
height="81"
|
||||
width={110 * widthscale}
|
||||
height={81 * heightscale}
|
||||
viewBox="0 0 110 81"
|
||||
fill="none"
|
||||
xmlns="http://www.w3.org/2000/svg"
|
||||
|
|
|
|||
|
Before Width: | Height: | Size: 14 KiB After Width: | Height: | Size: 14 KiB |
|
|
@ -6,7 +6,7 @@
|
|||
import OnnxLight from '../../images/ONNX-Light.svelte';
|
||||
const title = 'Hugging Face + ONNX Runtime';
|
||||
const description =
|
||||
'ONNX Runtime can be used to accelerate well over 100,000 of the models available on Hugging Face.';
|
||||
'ONNX Runtime can be used to accelerate well over 130,000 of the models available on Hugging Face.';
|
||||
const imgsrc = 'onnxruntimelogo';
|
||||
const imgalt = 'ONNX Runtime Logo';
|
||||
</script>
|
||||
|
|
@ -27,7 +27,7 @@
|
|||
{description}
|
||||
</p>
|
||||
<br />
|
||||
<br>
|
||||
<br />
|
||||
<a
|
||||
href="https://cloudblogs.microsoft.com/opensource/2023/10/04/accelerating-over-130000-hugging-face-models-with-onnx-runtime/"
|
||||
class="btn btn-primary mr-0 mb-4 md:mr-4">Recent blog with Hugging Face →</a
|
||||
|
|
@ -40,110 +40,109 @@
|
|||
</div>
|
||||
|
||||
<div class="container mx-auto px-10 my-10">
|
||||
<div >
|
||||
<div>
|
||||
<h1 class="text-4xl pb-4">Supported Models</h1>
|
||||
<p>
|
||||
The top 30 most popular model families on Hugging Face are all supported by ONNX Runtime,
|
||||
and over 80 Hugging Face model families in total boast ORT support. <span
|
||||
class="hidden md:inline">The table outlines the models:</span
|
||||
>
|
||||
</p>
|
||||
<br />
|
||||
<div class="grid grid-cols-1 md:grid-cols-3 gap-4 lg:gap-10">
|
||||
<div class="col-span-2">
|
||||
<h1 class="text-3xl pb-4">Export Hugging Face Models to ONNX</h1>
|
||||
<p class="pb-4">
|
||||
ONNX models can be found directly from the Hugging Face Model Hub in its ONNX model library.
|
||||
Hugging Face provides many options for exporting models to ONNX, including an ONNX Export Space
|
||||
for PyTorch models from the Hugging Face Model Hub.
|
||||
</p>
|
||||
<a href="https://huggingface.co/models?library=onnx" class="btn btn-primary"
|
||||
>Check out Hugging Face's ONNX model library →</a
|
||||
<a href="https://huggingface.co/spaces/onnx/export" class="btn btn-primary"
|
||||
>Export PyTorch models to ONNX →</a
|
||||
>
|
||||
<br />
|
||||
<br />
|
||||
<p class="pb-4">
|
||||
Hugging Face also provides ONNX support for a variety of other models not listed in the ONNX
|
||||
model library. With Hugging Face Optimum, you can easily convert pretrained models to ONNX,
|
||||
and Transformers.js lets you run Hugging Face Transformers directly from your browser!
|
||||
</p>
|
||||
<a
|
||||
href="https://huggingface.co/docs/optimum/exporters/onnx/overview"
|
||||
class="btn btn-primary mr-0 mb-4 md:mr-4">Learn more about Hugging Face Optimum →</a
|
||||
>
|
||||
<a href="https://huggingface.co/docs/transformers.js/index" class="btn btn-primary"
|
||||
>Learn more about Transformers.js →</a
|
||||
<a href="https://huggingface.co/docs/transformers/serialization" class="btn btn-primary"
|
||||
>Other ONNX export options →</a
|
||||
>
|
||||
</div>
|
||||
<div class="mx-auto md:pt-10">
|
||||
<ImagesHf1 />
|
||||
</div>
|
||||
</div>
|
||||
</div>
|
||||
|
||||
<div class="container mx-auto px-10 my-10">
|
||||
<div class="divider" />
|
||||
<div class="flex">
|
||||
<h1 class="text-4xl pb-4">Export Hugging Face Models to ONNX</h1>
|
||||
<div class="ml-5 hidden md:flex">
|
||||
<ImagesHf1 />
|
||||
<div>
|
||||
<div>
|
||||
<h1 class="text-3xl pb-4">Supported Models</h1>
|
||||
<p class="pb-4">
|
||||
The top 30 most popular model architectures on Hugging Face are all supported by ONNX
|
||||
Runtime, and over 80 Hugging Face model architectures in total boast ORT support. This list
|
||||
includes <a href="https://huggingface.co/models?other=bert" class="text-blue-500">BERT</a>,
|
||||
<a href="https://huggingface.co/models?other=gpt2" class="text-blue-500">GPT2</a>,
|
||||
<a href="https://huggingface.co/models?other=t5" class="text-blue-500">T5</a>,
|
||||
<a href="https://huggingface.co/models?other=stable-diffusion" class="text-blue-500"
|
||||
>Stable Diffusion</a
|
||||
>,
|
||||
<a href="https://huggingface.co/models?other=whisper" class="text-blue-500">Whisper</a>, and
|
||||
many more.
|
||||
</p>
|
||||
<p class="pb-4">
|
||||
ONNX models can be found directly from the Hugging Face Model Hub in its <a
|
||||
href="https://huggingface.co/models?library=onnx"
|
||||
class="text-blue-500">ONNX model library</a
|
||||
>.
|
||||
</p>
|
||||
<p class="pb-4">
|
||||
Hugging Face also provides ONNX support for a variety of other models not listed in the ONNX
|
||||
model library. With <a
|
||||
href="https://huggingface.co/docs/optimum/exporters/onnx/overview"
|
||||
class="text-blue-500">Hugging Face Optimum</a
|
||||
>, you can easily convert pretrained models to ONNX, and
|
||||
<a href="https://huggingface.co/docs/transformers.js/index" class="text-blue-500"
|
||||
>Transformers.js</a
|
||||
> lets you run Hugging Face Transformers directly from your browser!
|
||||
</p>
|
||||
</div>
|
||||
</div>
|
||||
<h2 class="text-2xl">PyTorch Models</h2>
|
||||
<p class="pb-4">
|
||||
Hugging Face's ONNX Export Space allows users to easily export PyTorch models from the Hugging
|
||||
Face Model Hub to ONNX.
|
||||
</p>
|
||||
<a href="https://huggingface.co/spaces/onnx/export" class="btn btn-primary"
|
||||
>Try out the Hugging Face ONNX Export Space for yourself →</a
|
||||
>
|
||||
<br />
|
||||
<br />
|
||||
<h2 class="text-2xl">Other Models</h2>
|
||||
<p class="pb-4">Hugging Face provides many alternatives for exporting models to ONNX.</p>
|
||||
<a href="https://huggingface.co/docs/transformers/serialization" class="btn btn-primary"
|
||||
>Other ONNX export options →</a
|
||||
>
|
||||
</div>
|
||||
|
||||
<div class="container mx-auto px-10 my-10">
|
||||
<div class="divider" />
|
||||
<div >
|
||||
<div class="col-span-1">
|
||||
<div class="flex">
|
||||
<h1 class="text-4xl pb-4">Large Language Models</h1>
|
||||
<div class="ml-5 hidden md:flex">
|
||||
<ImageHf2 />
|
||||
</div>
|
||||
</div>
|
||||
<p>
|
||||
ONNX Runtime also supports many increasingly popular large language model (LLM) families,
|
||||
including most of those available in the HF Model Hub. <span class="hidden md:inline"
|
||||
>These model families are showcased in the table.</span
|
||||
>
|
||||
<div class="grid grid-cols-1 md:grid-cols-3 gap-4 lg:gap-10">
|
||||
<div class="col-span-2">
|
||||
<h1 class="text-3xl pb-4">Large Language Models</h1>
|
||||
<p class="pb-4">
|
||||
ONNX Runtime also supports many increasingly popular large language model (LLM)
|
||||
architectures, including <a
|
||||
href="https://huggingface.co/models?other=llama"
|
||||
class="text-blue-500">LLaMA</a
|
||||
>,
|
||||
<a href="https://huggingface.co/models?other=gpt_neo" class="text-blue-500">GPT Neo</a>,
|
||||
<a href="https://huggingface.co/models?other=bloom" class="text-blue-500">BLOOM</a>, and
|
||||
many more.
|
||||
</p>
|
||||
<br />
|
||||
<p>
|
||||
Hugging Face also provides a leaderboard with more detailed tracking and evaluation of
|
||||
recently releases LLMs from the community.
|
||||
Hugging Face also provides an <a
|
||||
href="https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard"
|
||||
class="text-blue-500">Open LLM Leaderboard</a
|
||||
> with more detailed tracking and evaluation of recently releases LLMs from the community.
|
||||
</p>
|
||||
<br />
|
||||
<a
|
||||
class="btn btn-primary"
|
||||
href="https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard"
|
||||
>Hugging Face Open LLM Leaderboard →</a
|
||||
>
|
||||
</div>
|
||||
<div class="hidden md:grid mx-auto">
|
||||
<ImageHf2 widthscale={2} heightscale={2}/>
|
||||
</div>
|
||||
</div>
|
||||
</div>
|
||||
|
||||
<div class="container mx-auto px-10 my-10">
|
||||
<div class="divider" />
|
||||
<div class="flex">
|
||||
<h1 class="text-4xl pb-4">Cloud Models</h1>
|
||||
<div class="ml-5 hidden md:flex">
|
||||
<ImageHf3 />
|
||||
<div class="grid grid-cols-1 md:grid-cols-3 gap-4 lg:gap-10">
|
||||
<div class="col-span-2">
|
||||
<h1 class="text-3xl pb-4">Cloud Models</h1>
|
||||
<p class="pb-4">
|
||||
Models accelerated by ONNX Runtime can be easily deployed to the cloud through Azure Machine
|
||||
Learning, which improves time to value, streamlines MLOps, and provides built-in security.
|
||||
</p>
|
||||
<p>
|
||||
<a href="https://ml.azure.com/" class="text-blue-500">Azure Machine Learning</a> also publishes a
|
||||
curated model list that is updated regularly and includes some of the most popular models at the
|
||||
moment. Of the models on this list that are available on Hugging Face, there is currently Optimum
|
||||
ONNX support for over 85%.
|
||||
</p>
|
||||
</div>
|
||||
<div class="hidden md:grid mx-auto">
|
||||
<ImageHf3 widthscale={2} heightscale={2}/>
|
||||
</div>
|
||||
</div>
|
||||
<p>
|
||||
Models accelerated by ONNX Runtime can be easily deployed to the cloud through Azure ML, which
|
||||
improves time to value, streamlines MLOps, and provides built-in security.
|
||||
</p>
|
||||
<br />
|
||||
<p>
|
||||
Azure ML also publishes a curated model list that is updated regularly and includes some of the
|
||||
most popular models at the moment. Of the models on this list that are available on Hugging
|
||||
Face, there is currently Optimum ONNX support for over 85%.
|
||||
</p>
|
||||
</div>
|
||||
</div>
|
||||
Loading…
Reference in a new issue