Add Phi-3 on device announcement (#20740)

### Description
Add announcement with link to Phi-3 On-Device blog on Hugging Face site

Staged here:
https://sophies927.github.io/onnxruntime/blogs/phi-3-on-device



### 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:
Sophie Schoenmeyer 2024-05-20 14:28:54 -07:00 committed by GitHub
parent 3909f23ee6
commit 2fe196ea39
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
3 changed files with 44 additions and 4 deletions

Binary file not shown.

After

Width:  |  Height:  |  Size: 15 KiB

View file

@ -15,6 +15,7 @@
import ORT117Thumbnail from '../../images/blogs/ort-1-17-thumbnail.png';
import WebGPUImage from '../../images/blogs/webgpu_blog_thumbnail.jpg';
import WebTrainingImage from '../../images/blogs/webtraining_blog_thumbnail.png';
import Phi3OnDeviceImage from '../../images/blogs/phi-3-on-device_blog_thumbnail.png';
onMount(() => {
anime({
targets: '.border-primary',
@ -42,6 +43,16 @@
dispatch('switchTab', tab);
}
let featuredblog = [
{
title: 'Enjoy the Power of Phi-3 with ONNX Runtime on your device',
date: 'May 20th, 2024',
blurb:
"Harness ONNX Runtime to run Phi-3-mini on mobile phones and in the browser.",
link: 'blogs/phi-3-on-device',
image: Phi3OnDeviceImage,
imgalt:
'Chart comparing model size (in GB) of ONNX Phi-3-mini for web and mobile with original Phi-3-mini'
},
{
title: 'ONNX Runtime supports Phi-3 mini models across platforms and devices',
date: 'April 22nd, 2024',
@ -61,7 +72,9 @@
image: WebGPUImage,
imgalt:
'Comparison of ONNX Runtime Web with WebGPU EP on GPU vs. WASM EP on CPU for segment anything example'
},
}
];
let blogs = [
{
title: 'ONNX Runtime 1.17: CUDA 12 support, Phi-2 optimizations, WebGPU, and more!',
date: 'February 28th, 2024',
@ -71,9 +84,6 @@
image: ORT117Thumbnail,
imgalt: 'ONNX Runtime 1.17 release logo'
},
];
let blogs = [
{
title: 'Accelerating Phi-2, CodeLlama, Gemma and other Gen AI models with ONNX Runtime',
date: 'February 26th, 2024',

View file

@ -0,0 +1,30 @@
---
title: 'Enjoy the power of Phi-3 with ONNX Runtime on your device'
date: '20th May, 2024'
description: 'Harness ONNX Runtime and Olive to optimize and run the state-of-the-art Phi-3-mini model on your mobile phone or directly in your browser!'
keywords: 'ORT, ONNX Runtime, ONNX, machine learning, deep learning, phi 3, phi-3, webgpu, webnn, webassembly, hugging face, huggingface, transformers.js'
authors:
[
'Emma Ning (Microsoft)',
'Scott McKay (Microsoft)',
'Guenther Schmuelling (Microsoft)',
'Joshua Lochner (Hugging Face)'
]
authorsLink:
[
'https://www.linkedin.com/in/qiong-ning-21b554236/',
'https://www.linkedin.com/in/scott-mckay-68b5ab/',
'https://www.linkedin.com/in/guentherschmuelling/',
'https://www.linkedin.com/in/xenova/?originalSubdomain=za'
]
image: ''
url: 'https://onnxruntime.ai/blogs/phi-3-on-device'
---
Want to own a private and powerful chatbot on your device with full data privacy and no need for an internet connection?
Harness ONNX Runtime and Olive to optimize and run the state-of-the-art Phi-3-mini model on your mobile phone or directly in your browser!
Enjoy models optimized for mobile and web with a size reduction of over 2.5 times, and run Phi-3-mini at over 70 tokens per second in the browser on an Nvidia RTX 4090!
Check out the full blog [here](https://huggingface.co/blog/Emma-N/enjoy-the-power-of-phi-3-with-onnx-runtime).