-
Notifications
You must be signed in to change notification settings - Fork 2.9k
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
Made models page, updated roadmap SEO.
- Loading branch information
Showing
3 changed files
with
104 additions
and
0 deletions.
There are no files selected for viewing
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,87 @@ | ||
<script> | ||
let modelhubs = [ | ||
{ | ||
title: 'ONNX Community (HuggingFace)', | ||
description: | ||
'Join the ONNX community on Hugging Face to access, share, and discuss ONNX models for NLP, vision, and more.', | ||
url: 'https://huggingface.co/onnx-community', | ||
image: 'https://huggingface.co/front/assets/huggingface_logo-noborder.svg', | ||
imagealt: 'Hugging Face Logo' | ||
}, | ||
{ | ||
title: 'Model Zoo (ONNX)', | ||
description: | ||
'Explore a wide variety of pre-trained ONNX models for deep learning tasks across multiple domains.', | ||
url: 'https://onnx.ai/models/', | ||
image: 'https://onnx.ai/models/assets/logos/onnx.png', | ||
imagealt: 'ONNX Model Zoo' | ||
}, | ||
{ | ||
title: 'AI Hub (Qualcomm)', | ||
description: | ||
'Discover ONNX-compatible AI models optimized for Qualcomm hardware on the AI Hub.', | ||
url: 'https://aihub.qualcomm.com/models', | ||
image: 'https://logosandtypes.com/wp-content/uploads/2020/08/qualcomm.svg', | ||
imagealt: 'Qualcomm AI Hub Logo' | ||
}, | ||
{ | ||
title: 'ONNX Models (HuggingFace)', | ||
description: | ||
'Find trending ONNX models for natural language processing, computer vision, and more on Hugging Face.', | ||
url: 'https://huggingface.co/models?library=onnx&sort=trending', | ||
image: 'https://huggingface.co/front/assets/huggingface_logo-noborder.svg', | ||
imagealt: 'Hugging Face Logo' | ||
} | ||
]; | ||
let description = 'ONNX Models - find ONNX models for natural language processing, computer vision, and more.'; | ||
let keywords = 'onnx models, onnx model zoo, onnx community, onnx models huggingface, onnx models qualcomm'; | ||
</script> | ||
<svelte:head> | ||
<!-- Dynamic meta tags --> | ||
<meta name="description" content={description} /> | ||
<meta name="keywords" content={keywords} /> | ||
<!-- Open Graph / Facebook --> | ||
<meta property="og:description" content={description}/> | ||
|
||
<!-- Twitter --> | ||
<meta property="twitter:description" content={description} /> | ||
</svelte:head> | ||
<div class="container mx-auto px-8"> | ||
<h1 class="text-3xl">ONNX Models</h1> | ||
<p> | ||
ONNX is the Open Neural Network Exchange, and we take that name to heart! Many members of the | ||
community upload their ONNX models to various repositories, and we want to make it easy for you | ||
to find them. Below are some of the most popular repositories where you can find ONNX models: | ||
</p> | ||
|
||
<div class="my-8 grid grid-cols-1 md:grid-cols-2 gap-8"> | ||
{#each modelhubs as modelhub} | ||
<div class="card bg-success image-full transition hover:scale-105"> | ||
<a rel="noopener noreferrer" target="_blank" href={modelhub.url} class="card-body"> | ||
<div class="grid grid-cols-5"> | ||
<div class="h-full"> | ||
<img src={modelhub.image} alt={modelhub.imagealt} class="w-24 h-24" /> | ||
</div> | ||
<div class="col-span-4"> | ||
<h2 class="card-title text-white">{modelhub.title}</h2> | ||
<p class="text-white">{modelhub.description}</p> | ||
</div> | ||
</div> | ||
</a> | ||
</div> | ||
{/each} | ||
</div> | ||
|
||
<h2 class="text-2xl">Can't find what you're looking for?</h2> | ||
<p> | ||
Convert to ONNX, optimize, and quantize your own models quickly and easily with <a | ||
class="text-blue-700 underline" | ||
href="https://github.com/microsoft/Olive/tree/main">Olive</a | ||
>. Here's a quick snippet showing you how easy it can be done: | ||
</p> | ||
<div class="my-4 mockup-code bg-slate-300 dark:bg-primary"> | ||
<pre data-prefix="$" class="text-black"><code>pip install olive-ai onnxruntime optimum</code></pre> | ||
<pre data-prefix=">" class="text-success"><code>olive auto-opt -m microsoft/Phi-3-mini-4k-instruct -o models/phi3-mini-4k</code></pre> | ||
</div> | ||
</div> |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters