azure.microsoft.com
Open in
urlscan Pro
2600:1408:ec00:108c::439b
Public Scan
Submitted URL: https://azure.microsoft.com/en-us/blog/announcing-phi-3-fine-tuning-new-generative-ai-models-and-other-azure-ai-updates-to-e...
Effective URL: https://azure.microsoft.com/en-us/blog/announcing-phi-3-fine-tuning-new-generative-ai-models-and-other-azure-ai-updates-to-e...
Submission: On July 29 via api from BE — Scanned from US
Effective URL: https://azure.microsoft.com/en-us/blog/announcing-phi-3-fine-tuning-new-generative-ai-models-and-other-azure-ai-updates-to-e...
Submission: On July 29 via api from BE — Scanned from US
Form analysis 2 forms found in the DOM
Name: searchForm — GET https://azure.microsoft.com/en-us/search/
<form class="c-search" autocomplete="off" id="searchForm" name="searchForm" role="search" action="https://azure.microsoft.com/en-us/search/" method="GET" data-seautosuggest=""
data-seautosuggestapi="https://www.microsoft.com/msstoreapiprod/api/autosuggest"
data-m="{"cN":"GlobalNav_Search_cont","cT":"Container","id":"c3c1c9c2m1r1a1","sN":3,"aN":"c1c9c2m1r1a1"}" aria-expanded="false" style="overflow-x: visible;">
<div class="x-screen-reader" aria-live="assertive"></div>
<input id="cli_shellHeaderSearchInput" aria-label="Search Expanded" aria-autocomplete="list" aria-expanded="false" aria-controls="universal-header-search-auto-suggest-transparent" aria-owns="universal-header-search-auto-suggest-ul" type="search"
name="q" role="combobox" placeholder="Show search input" data-m="{"cN":"SearchBox_nav","id":"n1c3c1c9c2m1r1a1","sN":1,"aN":"c3c1c9c2m1r1a1"}" data-toggle="tooltip"
data-placement="right" title="Show search input" data-open="false" style="overflow-x: visible;">
<button id="search" aria-label="Show search input" class="c-glyph" data-m="{"cN":"Search_nav","id":"n2c3c1c9c2m1r1a1","sN":2,"aN":"c3c1c9c2m1r1a1"}" data-bi-mto="true"
aria-expanded="false" style="overflow-x: visible;">
<span role="presentation" style="overflow-x: visible;">Search</span>
<span role="tooltip" class="c-uhf-tooltip c-uhf-search-tooltip" style="overflow-x: visible;">Show search input</span>
</button>
<div class="m-auto-suggest" id="universal-header-search-auto-suggest-transparent" role="group" style="overflow-x: visible;">
<ul class="c-menu" id="universal-header-search-auto-suggest-ul" aria-label="Search Suggestions" aria-hidden="true" data-bi-dnt="true" data-bi-mto="true" data-js-auto-suggest-position="default" role="listbox" data-tel="jsll"
data-m="{"cN":"search suggestions_cont","cT":"Container","id":"c3c3c1c9c2m1r1a1","sN":3,"aN":"c3c1c9c2m1r1a1"}" style="overflow-x: visible;"></ul>
<ul class="c-menu f-auto-suggest-no-results" aria-hidden="true" data-js-auto-suggest-postion="default" data-js-auto-suggest-position="default" role="listbox" style="overflow-x: visible;">
<li class="c-menu-item" style="overflow-x: visible;"> <span tabindex="-1" style="overflow-x: visible;">No results</span></li>
</ul>
</div>
</form>GET https://azure.microsoft.com/en-us/blog/
<form role="search" id="searchform-1" class="search-form" method="get" action="https://azure.microsoft.com/en-us/blog/">
<meta itemprop="target" content="https://azure.microsoft.com/en-us/blog/?s={s}">
<label for="search-field" class="screen-reader-text"> Search for: </label>
<input itemprop="query-input" type="search" id="search-field" value="" placeholder="Search the blog" name="s" class="form-control">
<button type="submit" class="search-form__btn btn btn-icon">
<span aria-hidden="true" class="msx-svg"><svg xmlns="http://www.w3.org/2000/svg" width="16" height="16" fill="none">
<path fill="#fff" d="M6.334.083a6.25 6.25 0 0 1 4.97 10.04l3.953 3.955a.833.833 0 0 1-1.1 1.247l-.079-.069-3.954-3.953A6.25 6.25 0 1 1 6.334.083m0 1.667a4.583 4.583 0 1 0 0 9.167 4.583 4.583 0 0 0 0-9.167"></path>
</svg></span> <span class="screen-reader-text">Submit search</span>
</button>
</form>Text Content
Skip to main content
Microsoft
Azure
Azure
Azure
* Home
* Explore
* Get to know Azure
* Global infrastructure
* FinOps on Azure
* Azure Essentials
* Customer stories
* Azure innovation insights
* Products
* View all products (200+)
* Popular Popular
* Azure Virtual Machines
* Azure Virtual Desktop
* Azure SQL
* Microsoft Copilot in Azure PREVIEW
* Azure AI Services
* Azure AI Studio
* Azure Cosmos DB
* Azure Kubernetes Service (AKS)
* Azure Arc
* Azure Migrate
* AI + machine learning AI + machine learning
* Azure Machine Learning
* Azure AI Services
* Microsoft Copilot in Azure PREVIEW
* Azure OpenAI Service
* Azure AI Studio
* Azure AI Vision
* Azure AI Search
* Azure AI Bot Service
* Azure Databricks
* Azure AI Language
* Compute Compute
* Azure Virtual Machines
* Azure Kubernetes Service (AKS)
* Linux virtual machines in Azure
* SQL Server on Azure Virtual Machines
* Windows Virtual Machines
* Azure Functions
* Azure App Service
* Azure Virtual Machine Scale Sets
* Azure Spot Virtual Machines
* Azure Container Apps
* Containers Containers
* Azure Kubernetes Service (AKS)
* Azure App Service
* Azure Functions
* Azure Container Instances
* Azure Spring Apps
* Azure Red Hat OpenShift
* Azure Kubernetes Fleet Manager PREVIEW
* Azure Container Apps
* Azure Container Registry
* App Configuration
* Hybrid + multicloud Hybrid + multicloud
* Azure Arc
* Azure Stack
* Microsoft Sentinel
* Azure SQL
* Microsoft Defender for Cloud
* Azure ExpressRoute
* Azure DevOps
* Azure Database for PostgreSQL
* Azure IoT Edge
* Azure Monitor
* Analytics Analytics
* Azure Synapse Analytics
* Azure Databricks
* Microsoft Purview
* Azure Data Factory
* Azure Machine Learning
* Microsoft Fabric
* HDInsight
* Azure Data Explorer
* Azure Data Lake Storage
* Azure Operator Insights
* Solutions
* View all solutions (40+)
* Featured Featured
* Azure AI
* Migrate to innovate in the era of AI
* Build and modernize intelligent apps
* Cloud-scale analytics
* Azure AI Infrastructure
* Adaptive cloud
* Azure network security
* AI AI
* Azure AI
* Responsible AI with Azure
* Azure AI Infrastructure
* Build and modernize intelligent apps
* Knowledge mining
* Hugging Face on Azure
* Azure confidential computing
* Application development Application development
* Build and modernize intelligent apps
* Development and testing
* DevOps
* DevSecOps
* Serverless computing
* Application and Data Modernization
* Low-code application development on Azure
* Cloud migration and modernization Cloud migration and modernization
* Migration and modernization center
* Migrate to innovate in the era of AI
* Build and modernize intelligent apps
* .NET apps migration
* Development and testing
* SQL Server migration
* Windows Server on Azure
* Linux on Azure
* SAP on the Microsoft Cloud
* Oracle on Azure
* Hybrid Cloud and infrastructure Hybrid Cloud and infrastructure
* Hybrid and multicloud solutions
* Backup and disaster recovery
* Windows Server on Azure
* High-performance computing (HPC)
* Business-critical applications
* Quantum computing
* 5G and Space
* Resources Resources
* Reference architectures
* Resources for accelerating growth
* Azure Marketplace
* Azure Essentials
* Browse the Microsoft Business Solutions Hub
* Pricing
* How to buy How to buy
* Azure pricing
* Free Azure services
* Azure account
* Flexible purchase options
* Azure benefits and incentives
* Pricing tools and resources Pricing tools and resources
* Pricing calculator
* TCO calculator
* Optimize your costs
* FinOps on Azure
* Partners
* Find a partner Find a partner
* Azure Marketplace
* Find a partner
* Become a partner Become a partner
* Azure Partner Zone
* Azure technology partners
* Join ISV Success
* Resources
* Learning Learning
* Get started with Azure
* Training and certifications
* Customer stories
* Analyst reports, white papers, and e-books
* Videos
* Learn more about cloud computing
* Technical resources Technical resources
* Documentation
* Get the Azure mobile app
* Developer resources
* Quickstart templates
* Resources for startups
* Community Community
* Developer community
* Students
* Developer stories
* What's new What's new
* Blog
* Events and Webinars
* Learn
* Support
* Contact Sales
* Get started with Azure
* Sign in
* More
Search Show search input
* No results
Cancel
* All Microsoft
* GLOBAL
* Microsoft 365
* Teams
* Copilot
* Windows
* Surface
* Xbox
* Deals
* Small Business
* Support
* Software Software
* Windows Apps
* AI
* Outlook
* OneDrive
* Microsoft Teams
* OneNote
* Microsoft Edge
* Skype
* PCs & Devices PCs & Devices
* Computers
* Shop Xbox
* Accessories
* VR & mixed reality
* Certified Refurbished
* Trade-in for cash
* Entertainment Entertainment
* Xbox Game Pass Ultimate
* PC Game Pass
* Xbox games
* PC and Windows games
* Movies & TV
* Business Business
* Microsoft Cloud
* Microsoft Security
* Dynamics 365
* Microsoft 365 for business
* Microsoft Power Platform
* Windows 365
* Microsoft Industry
* Small Business
* Developer & IT Developer & IT
* Azure
* Developer Center
* Documentation
* Microsoft Learn
* Microsoft Tech Community
* Azure Marketplace
* AppSource
* Visual Studio
* Other Other
* Microsoft Rewards
* Free downloads & security
* Education
* Gift cards
* Licensing
* Unlocked stories
* View Sitemap
* Learn
* Support
* Contact Sales
* Get started with Azure
* Sign in
Light Dark
1. Blog Home
2. /
3. AI + machine learning
4. /
5. Announcing Phi-3 fine-tuning, new generative AI models, and other Azure AI
updates to empower organizations to customize and scale AI applications
Search for: Submit search
* Published Jul 25, 2024
* 7 min read
ANNOUNCING PHI-3 FINE-TUNING, NEW GENERATIVE AI MODELS, AND OTHER AZURE AI
UPDATES TO EMPOWER ORGANIZATIONS TO CUSTOMIZE AND SCALE AI APPLICATIONS
By Asha Sharma, Corporate Vice President, AI Platform
Share
*
*
*
* Content type
* Announcements
* Tag
* AI
* Phi-3
* Audience
* AI professionals
* Developers
* Product
* Azure AI
* Azure AI Content Safety
* Azure AI Studio
* Azure OpenAI Service
more
TECH COMMUNITY
Connect with a community to find answers, ask questions, build skills, and
accelerate your learning.
Visit the Azure AI services tech community
We are excited to announce several updates to help developers quickly create
customized AI solutions with greater choice and flexibility leveraging the Azure
AI toolchain.
AI is transforming every industry and creating new opportunities for innovation
and growth. But, developing and deploying AI applications at scale requires a
robust and flexible platform that can handle the complex and diverse needs of
modern enterprises and allow them to create solutions grounded in their
organizational data. That’s why we are excited to announce several updates to
help developers quickly create customized AI solutions with greater choice and
flexibility leveraging the Azure AI toolchain:
* Serverless fine-tuning for Phi-3-mini and Phi-3-medium models enables
developers to quickly and easily customize the models for cloud and edge
scenarios without having to arrange for compute.
* Updates to Phi-3-mini including significant improvement in core quality,
instruction-following, and structured output, enabling developers to build
with a more performant model without additional cost.
* Same day shipping earlier this month of the latest models from OpenAI (GPT-4o
mini), Meta (Llama 3.1 405B), Mistral (Large 2) to Azure AI to provide
customers greater choice and flexibility.
UNLOCKING VALUE THROUGH MODEL INNOVATION AND CUSTOMIZATION
In April, we introduced the Phi-3 family of small, open models developed by
Microsoft. Phi-3 models are our most capable and cost-effective small language
models (SLMs) available, outperforming models of the same size and next size up.
As developers look to tailor AI solutions to meet specific business needs and
improve quality of responses, fine-tuning a small model is a great alternative
without sacrificing performance. Starting today, developers can fine-tune
Phi-3-mini and Phi-3-medium with their data to build AI experiences that are
more relevant to their users, safely, and economically.
Given their small compute footprint, cloud and edge compatibility, Phi-3 models
are well suited for fine-tuning to improve base model performance across a
variety of scenarios including learning a new skill or a task (e.g. tutoring) or
enhancing consistency and quality of the response (e.g. tone or style of
responses in chat/Q&A). We’re already seeing adaptations of Phi-3 for new use
cases.
PHI-3 MODELS
A family of powerful, small language models (SLMs) with groundbreaking
performance at low cost and low latency
Try today
Microsoft and Khan Academy are working together to help improve solutions for
teachers and students across the globe. As part of the collaboration, Khan
Academy uses Azure OpenAI Service to power Khanmigo for Teachers, a pilot
AI-powered teaching assistant for educators across 44 countries and is
experimenting with Phi-3 to improve math tutoring. Khan Academy recently
published a research paper highlighting how different AI models perform when
evaluating mathematical accuracy in tutoring scenarios, including benchmarks
from a fine-tuned version of Phi-3. Initial data shows that when a student makes
a mathematical error, Phi-3 outperformed most other leading generative AI models
at correcting and identifying student mistakes.
And we’ve fine-tuned Phi-3 for the device too. In June, we introduced Phi Silica
to empower developers with a powerful, trustworthy model for building apps with
safe, secure AI experiences. Phi Silica builds on the Phi family of models and
is designed specifically for the NPUs in Copilot+ PCs. Microsoft Windows is the
first platform to have a state-of-the-art small language model (SLM) custom
built for the Neural Processing Unit (NPU) and shipping inbox.
You can try fine-tuning for Phi-3 models today in Azure AI.
I am also excited to share that our Models-as-a-Service (serverless endpoint)
capability in Azure AI is now generally available. Additionally, Phi-3-small is
now available via a serverless endpoint so developers can quickly and easily get
started with AI development without having to manage underlying infrastructure.
Phi-3-vision, the multi-modal model in the Phi-3 family, was announced at
Microsoft Build and is available through Azure AI model catalog. It will soon be
available via a serverless endpoint as well. Phi-3-small (7B parameter) is
available in two context lengths 128K and 8K whereas Phi-3-vision (4.2B
parameter) has also been optimized for chart and diagram understanding and can
be used to generate insights and answer questions.
We are seeing great response from the community on Phi-3. We released an update
for Phi-3-mini last month that brings significant improvement in core quality
and instruction following. The model was re-trained leading to substantial
improvement in instruction following and support for structured output. We also
improved multi-turn conversation quality, introduced support for <|system|>
prompts, and significantly improved reasoning capability.
The table below highlights improvements across instruction following, structured
output, and reasoning.
Benchmarks Phi-3-mini-4k Phi-3-mini-128k Apr ’24 release Jun ’24 update Apr ’24
release Jun ’24 update Instruction Extra Hard 5.7 6.0 5.7 5.9 Instruction
Hard 4.9 5.1 5 5.2 JSON Structure Output 11.5 52.3 1.9 60.1 XML Structure
Output 14.4 49.8 47.8 52.9 GPQA 23.7 30.6 25.9 29.7 MMLU 68.8 70.9 68.1 69.7 Average 21.7 35.8 25.7 37.6
We continue to make improvements to Phi-3 safety too. A recent research paper
highlighted Microsoft’s iterative “break-fix” approach to improving the safety
of the Phi-3 models which involved multiple rounds of testing and refinement,
red teaming, and vulnerability identification. This method significantly reduced
harmful content by 75% and enhanced the models’ performance on responsible AI
benchmarks.
EXPANDING MODEL CHOICE, NOW WITH OVER 1600 MODELS AVAILABLE IN AZURE AI
With Azure AI, we’re committed to bringing the most comprehensive selection of
open and frontier models and state-of-the-art tooling to help meet customers’
unique cost, latency, and design needs. Last year we launched the Azure AI model
catalog where we now have the broadest selection of models with over 1,600
models from providers including AI21, Cohere, Databricks, Hugging Face, Meta,
Mistral, Microsoft Research, OpenAI, Snowflake, Stability AI and others. This
month we added—OpenAI’s GPT-4o mini through Azure OpenAI Service, Meta Llama 3.1
405B, and Mistral Large 2.
Continuing the momentum today we are excited to share that Cohere Rerank is now
available on Azure. Accessing Cohere’s enterprise-ready language models on Azure
AI’s robust infrastructure enables businesses to seamlessly, reliably, and
safely incorporate cutting-edge semantic search technology into their
applications. This integration allows users to leverage the flexibility and
scalability of Azure, combined with Cohere’s highly performant and efficient
language models, to deliver superior search results in production.
TD Bank Group, one of the largest banks in North America, recently signed an
agreement with Cohere to explore its full suite of large language models (LLMs),
including Cohere Rerank.
> AT TD, WE’VE SEEN THE TRANSFORMATIVE POTENTIAL OF AI TO DELIVER MORE
> PERSONALIZED AND INTUITIVE EXPERIENCES FOR OUR CUSTOMERS, COLLEAGUES AND
> COMMUNITIES, WE’RE EXCITED TO BE WORKING ALONGSIDE COHERE TO EXPLORE HOW ITS
> LANGUAGE MODELS PERFORM ON MICROSOFT AZURE TO HELP SUPPORT OUR INNOVATION
> JOURNEY AT THE BANK.”
>
> Kirsti Racine, VP, AI Technology Lead, TD.
Atomicwork, a digital workplace experience platform and longtime Azure customer,
has significantly enhanced its IT service management platform with Cohere
Rerank. By integrating the model into their AI digital assistant, Atom AI,
Atomicwork has improved search accuracy and relevance, providing faster, more
precise answers to complex IT support queries. This integration has streamlined
IT operations and boosted productivity across the enterprise.
> THE DRIVING FORCE BEHIND ATOMICWORK’S DIGITAL WORKPLACE EXPERIENCE SOLUTION IS
> COHERE’S RERANK MODEL AND AZURE AI STUDIO, WHICH EMPOWERS ATOM AI, OUR DIGITAL
> ASSISTANT, WITH THE PRECISION AND PERFORMANCE REQUIRED TO DELIVER REAL-WORLD
> RESULTS. THIS STRATEGIC COLLABORATION UNDERSCORES OUR COMMITMENT TO PROVIDING
> BUSINESSES WITH ADVANCED, SECURE, AND RELIABLE ENTERPRISE AI CAPABILITIES.”
>
> Vijay Rayapati, CEO of Atomicwork
Command R+, Cohere’s flagship generative model which is also available on Azure
AI, is purpose-built to work well with Cohere Rerank within a Retrieval
Augmented Generation (RAG) system. Together they are capable of serving some of
the most demanding enterprise workloads in production.
Earlier this week, we announced that Meta Llama 3.1 405B along with the latest
fine-tuned Llama 3.1 models, including 8B and 70B, are now available via a
serverless endpoint in Azure AI. Llama 3.1 405B can be used for advanced
synthetic data generation and distillation, with 405B-Instruct serving as a
teacher model and 8B-Instruct/70B-Instruct models acting as student models.
Learn more about this announcement here.
Mistral Large 2 is now available on Azure, making Azure the first leading cloud
provider to offer this next-gen model. Mistral Large 2 outperforms previous
versions in coding, reasoning, and agentic behavior, standing on par with other
leading models. Additionally, Mistral Nemo, developed in collaboration with
NVIDIA, brings a powerful 12B model that pushes the boundaries of language
understanding and generation. Learn More.
And last week, we brought GPT-4o mini to Azure AI alongside other updates to
Azure OpenAI Service, enabling customers to expand their range of AI
applications at a lower cost and latency with improved safety and data
deployment options. We will announce more capabilities for GPT-4o mini in coming
weeks. We are also happy to introduce a new feature to deploy chatbots built
with Azure OpenAI Service into Microsoft Teams.
ENABLING AI INNOVATION SAFELY AND RESPONSIBLY
Building AI solutions responsibly is at the core of AI development at Microsoft.
We have a robust set of capabilities to help organizations measure, mitigate,
and manage AI risks across the AI development lifecycle for traditional machine
learning and generative AI applications. Azure AI evaluations enable developers
to iteratively assess the quality and safety of models and applications using
built-in and custom metrics to inform mitigations. Additional Azure AI Content
Safety features—including prompt shields and protected material detection—are
now “on by default” in Azure OpenAI Service. These capabilities can be leveraged
as content filters with any foundation model included in our model catalog,
including Phi-3, Llama, and Mistral. Developers can also integrate these
capabilities into their application easily through a single API. Once in
production, developers can monitor their application for quality and safety,
adversarial prompt attacks, and data integrity, making timely interventions with
the help of real-time alerts.
Azure AI uses HiddenLayer Model Scanner to scan third-party and open models for
emerging threats, such as cybersecurity vulnerabilities, malware, and other
signs of tampering, before onboarding them to the Azure AI model catalog. The
resulting verifications from Model Scanner, provided within each model card, can
give developer teams greater confidence as they select, fine-tune, and deploy
open models for their application.
We continue to invest across the Azure AI stack to bring state of the art
innovation to our customers so you can build, deploy, and scale your AI
solutions safely and confidently. We cannot wait to see what you build next.
STAY UP TO DATE WITH MORE AZURE AI NEWS
* Watch this video to learn more about Azure AI model catalog.
* Listen to the podcast on Phi-3 with lead Microsoft researcher Sebastien
Bubeck.
RELATED POSTS
* * Announcements
* Jul 23
* 5 min read
HARNESSING THE FULL POWER OF AI IN THE CLOUD: THE ECONOMIC IMPACT OF
MIGRATING TO AZURE FOR AI READINESS
By Omar Khan, General Manager, Azure Product Marketing
* * Announcements
* Jul 18
* 4 min read
OPENAI’S FASTEST MODEL, GPT-4O MINI IS NOW AVAILABLE ON AZURE AI
By Asha Sharma, Corporate Vice President, AI Platform
* * Customer stories
* Jul 16
* 5 min read
AI ON THE ROAD: AZURE OPENAI SERVICE HELPS DRIVE BETTER DECISION MAKING FOR
THE TRANSPORTATION SECTOR
By Andy Beatman, Director of Product Marketing, Azure AI
EXPLORE
AZURE AI SOLUTIONS
The future of AI starts here. Envision your next great AI app with the latest
technologies. Get started with Azure.
Learn more about Azure
Connect with us on social
* X
* YouTube
* LinkedIn
* Instagram
Explore Azure
* What is Azure?
* Get started with Azure
* Global infrastructure
* Datacenter regions
* Trust your cloud
* Azure Essentials
* Customer stories
Products and pricing
* Products
* Azure pricing
* Free Azure services
* Flexible purchase options
* FinOps on Azure
* Optimize your costs
Solutions and support
* Solutions
* Resources for accelerating growth
* Solution architectures
* Support
* Azure demo and live Q&A
Partners
* Azure Marketplace
* Find a partner
* Join ISV Success
Resources
* Training and certifications
* Documentation
* Blog
* Developer resources
* Students
* Events and Webinars
* Analyst reports, white papers, and e-books
* Videos
Cloud computing
* What is cloud computing?
* What is cloud migration?
* What is a hybrid cloud?
* What is AI?
* What is PaaS?
* What is IaaS?
* What is SaaS?
* What is DevOps?
English (United States) Your Privacy Choices Opt-Out Icon Your Privacy Choices
Your Privacy Choices Opt-Out Icon Your Privacy Choices Consumer Health Privacy
* Sitemap
* Contact Microsoft
* Privacy
* Manage cookies
* Terms of use
* Trademarks
* Safety & eco
* Recycling
* About our ads
* © Microsoft 2024
Notifications