Azure ML: deploy Hugging Face models in minutes!

preview_player
Показать описание
In this video, I show you how to deploy Hugging Face models in one click on Azure, thanks to the model catalog in Azure ML Studio. Then, I run a small Python example to predict with the model.

⭐️⭐️⭐️ Don't forget to subscribe to be notified of future videos ⭐️⭐️⭐️

To get started, you simply need to navigate to the Azure ML Studio website and open the model catalog. Then, you can click on a model to select it. This will initiate the setup process, which takes care of all the required infrastructure for you. Once the setup is complete, Azure ML Studio provides a sample program and you can start testing the model immediately!

If you want to experiment with the latest state-of-the-art models, Azure ML Studio provides a hassle-free way to do so. Try it out and explore the possibilities of cutting-edge AI models with just one click!

  1. Julien Simon
  2. azure
  3. ai
  4. ml
  5. open source
  6. hugging face
Рекомендации по теме
Azure ML: deploy 0:06:05

Azure ML: deploy Hugging Face models in minutes!

Introducing Hugging Face 0:08:14

Introducing Hugging Face AzureML Endpoints

How To Deploy 0:10:21

How To Deploy Hugging Face Models On Azure - End-To-End Solution

Step 4 | 0:28:55

Step 4 | Creating & Using Azure ML Studio | Deploy a huggingface model to Microsoft Azure ML Stu...

Deploy Pre-Trained Hugging 0:15:39

Deploy Pre-Trained Hugging Face Machine Learning Models on Azure

Step 3 | 0:09:30

Step 3 | Building Deployment Structure | Deploy a huggingface model to Microsoft Azure ML Studio

Step 2 | 0:06:37

Step 2 | Building local pipeline script | Deploy a huggingface model to Microsoft Azure ML Studio

How To Deploy 0:06:38

How To Deploy Hugging Face Models On Azure - No Code Solution

Step 1 | 0:08:40

Step 1 | Model Information & Inference API | Deploy a huggingface model to Microsoft Azure ML St...

The Best Way 0:05:48

The Best Way to Deploy AI Models (Inference Endpoints)

Fine-tune and deploy 0:15:17

Fine-tune and deploy foundation models with Azure Machine Learning

Announcing Hugging Face 0:37:20

Announcing Hugging Face on Azure | OD61

Model deployment and 0:14:50

Model deployment and inferencing with Azure Machine Learning | Machine Learning Essentials

Build and Deploy 0:02:12

Build and Deploy a Machine Learning App in 2 Minutes

Deploy Hugging Face 0:15:28

Deploy Hugging Face Models on Azure powered by AMD ROCm software | StudioFP106

How to use 0:16:37

How to use Microsoft Azure AI Studio and Azure OpenAI models

The EASIEST Way 0:10:28

The EASIEST Way to Deploy AI Models from Hugging Face (No Code)

Tutorial 7: Deploying 0:11:05

Tutorial 7: Deploying Machine Learning Models In Azure Cloud

Deploy ML model 0:12:41

Deploy ML model in 10 minutes. Explained

MLOps packaging: HuggingFace 0:16:12

MLOps packaging: HuggingFace and Azure Container Registry

Developing NLP with 0:54:43

Developing NLP with Hugging Face on Azure Machine Learning

What is Hugging 0:01:27

What is Hugging Face? (In about a minute)

What are managed 0:01:21

What are managed endpoints in Azure ML?

Deploy and fine-tune 0:00:35

Deploy and fine-tune large AI models with your data with Foundation Models in Azure Machine Learning

Комментарии
Автор

Hey, did the whole interface change? I don't see the same things you do in "Azure AI Studio". It only has nav items too: Home / Explore / Build / Manage. If you go to "Explore -> Hugging Face" you can only select from a predefined list of models.

daniellasek
Автор

Hey, can you also show how to deploy a custom model not on the model cards?

joejay
Автор

H, nice vid. I got it working. Maybe a bit specific question: Now i'm trying to use langchain with it, but all langchain chatmodel classes (openAI, mistral, olllama etc) use hardcoded endpoint ".../v1/chat/completions" while Azure generates endpoint ".../score". Also when using a local model via LM Studio the prebuilt server also already points to this /v1/chat/completions endpoint. Should i make a custom class extending baseLLM to point it to my custom azure endpoint? or is there already something built for this i can use out of the box?

buksa
Автор

Hi Julien, I'm a product analyst working with my manager to propose a new AI based product for internal use. We are not a tech company.

Can you advice how to know how big an instance would I need to run LLMs with 7B to 14B paramterers. Just ballpark ideas will do for me.

My intention is to give a ballpark cost estimate before we commission a feasibility study with a software vendor who'd give us more accurate numbers

markthompson