Getting Started with Hugging Face Inference Endpoints
📰 Hugging Face Blog
Hugging Face Inference Endpoints allows for simple deployment of machine learning models to managed infrastructure on cloud platforms
Action Steps
- Choose a pre-trained model from the Hugging Face hub or fine-tune a model using AutoTrain
- Deploy the model to Inference Endpoints in a few clicks
- Configure the endpoint for security, scalability, and monitoring
- Test and validate the deployed model
- Integrate the model into applications using APIs or SDKs
Who Needs to Know This
Data scientists and machine learning engineers can benefit from using Hugging Face Inference Endpoints to streamline model deployment, while developers can use the service to integrate models into applications
Key Insight
💡 Hugging Face Inference Endpoints simplifies the model deployment process, allowing data scientists and developers to focus on building and improving models rather than managing infrastructure
Share This
Deploy ML models in minutes with Hugging Face Inference Endpoints #HuggingFace #InferenceEndpoints #MLDeployment
Key Takeaways
Hugging Face Inference Endpoints allows for simple deployment of machine learning models to managed infrastructure on cloud platforms
Full Article
Published Time: 2022-10-14T00:00:00.137Z
# Getting Started with Hugging Face Inference Endpoints
[Hugging Face](https://huggingface.co/)
* [Models](https://huggingface.co/models)
* [Datasets](https://huggingface.co/datasets)
* [Spaces](https://huggingface.co/spaces)
* [Buckets new](https://huggingface.co/storage)
* [Docs](https://huggingface.co/docs)
* [Enterprise](https://huggingface.co/enterprise)
* [Pricing](https://huggingface.co/pricing)
*
*
* * *
* [Log In](https://huggingface.co/login)
* [Sign Up](https://huggingface.co/join)
[Back to Articles](https://huggingface.co/blog)
# [](https://huggingface.co/blog/inference-endpoints#getting-started-with-hugging-face-inference-endpoints) Getting Started with Hugging Face Inference Endpoints
Published October 14, 2022
[Update on GitHub](https://github.com/huggingface/blog/blob/main/inference-endpoints.md)
[- [x] Upvote 1](https://huggingface.co/login?next=%2Fblog%2Finference-endpoints)
* [](https://huggingface.co/Aurelien-Morgan "Aurelien-Morgan")
[](https://huggingface.co/juliensimon)
[Julien Simon juliensimon Follow](https://huggingface.co/juliensimon)
* [Deploying a model on Inference Endpoints](https://huggingface.co/blog/inference-endpoints#deploying-a-model-on-inference-endpoints "Deploying a model on Inference Endpoints")
* [Deploying a Protected Inference Endpoint](https://huggingface.co/blog/inference-endpoints#deploying-a-protected-inference-endpoint "Deploying a Protected Inference Endpoint")
* [Deploying a Private Inference Endpoint](https://huggingface.co/blog/inference-endpoints#deploying-a-private-inference-endpoint "Deploying a Private Inference Endpoint")
* [Now it's your turn!](https://huggingface.co/blog/inference-endpoints#now-its-your-turn "Now it's your turn!")
Training machine learning models has become quite simple, especially with the rise of pre-trained models and transfer learning. OK, sometimes it's not _that_ simple, but at least, training models will never break critical applications, and make customers unhappy about your quality of service. Deploying models, however... Yes, we've all been there.
Deploying models in production usually requires jumping through a series of hoops. Packaging your model in a container, provisioning the infrastructure, creating your prediction API, securing it, scaling it, monitoring it, and more. Let's face it: building all this plumbing takes valuable time away from doing actual machine learning work. Unfortunately, it can also go awfully wrong.
We strive to fix this problem with the newly launched Hugging Face [Inference Endpoints](https://huggingface.co/inference-endpoints). In the spirit of making machine learning ever simpler without compromising on state-of-the-art quality, we've built a service that lets you deploy machine learning models directly from the [Hugging Face hub](https://huggingface.co/) to managed infrastructure on your favorite cloud in just a few clicks. Simple, secure, and scalable: you can have it all.
Let me show you how this works!
### [](https://huggingface.co/blog/inference-endpoints#deploying-a-model-on-inference-endpoints) Deploying a model on Inference Endpoints
Looking at the list of [tasks](https://huggingface.co/docs/inference-endpoints/supported_tasks) that Inference Endpoints support, I decided to deploy a Swin image classification model that I recently fine-tuned with [AutoTrain](https://huggingface.co/autotrain) on the [food101](https://huggingface.co/datasets/food101) dataset. If you're interested in how I built this model, this [video](https://youtu.be/uFxtl7QuUvo) will s
# Getting Started with Hugging Face Inference Endpoints
[Hugging Face](https://huggingface.co/)
* [Models](https://huggingface.co/models)
* [Datasets](https://huggingface.co/datasets)
* [Spaces](https://huggingface.co/spaces)
* [Buckets new](https://huggingface.co/storage)
* [Docs](https://huggingface.co/docs)
* [Enterprise](https://huggingface.co/enterprise)
* [Pricing](https://huggingface.co/pricing)
*
*
* * *
* [Log In](https://huggingface.co/login)
* [Sign Up](https://huggingface.co/join)
[Back to Articles](https://huggingface.co/blog)
# [](https://huggingface.co/blog/inference-endpoints#getting-started-with-hugging-face-inference-endpoints) Getting Started with Hugging Face Inference Endpoints
Published October 14, 2022
[Update on GitHub](https://github.com/huggingface/blog/blob/main/inference-endpoints.md)
[- [x] Upvote 1](https://huggingface.co/login?next=%2Fblog%2Finference-endpoints)
* [](https://huggingface.co/Aurelien-Morgan "Aurelien-Morgan")
[](https://huggingface.co/juliensimon)
[Julien Simon juliensimon Follow](https://huggingface.co/juliensimon)
* [Deploying a model on Inference Endpoints](https://huggingface.co/blog/inference-endpoints#deploying-a-model-on-inference-endpoints "Deploying a model on Inference Endpoints")
* [Deploying a Protected Inference Endpoint](https://huggingface.co/blog/inference-endpoints#deploying-a-protected-inference-endpoint "Deploying a Protected Inference Endpoint")
* [Deploying a Private Inference Endpoint](https://huggingface.co/blog/inference-endpoints#deploying-a-private-inference-endpoint "Deploying a Private Inference Endpoint")
* [Now it's your turn!](https://huggingface.co/blog/inference-endpoints#now-its-your-turn "Now it's your turn!")
Training machine learning models has become quite simple, especially with the rise of pre-trained models and transfer learning. OK, sometimes it's not _that_ simple, but at least, training models will never break critical applications, and make customers unhappy about your quality of service. Deploying models, however... Yes, we've all been there.
Deploying models in production usually requires jumping through a series of hoops. Packaging your model in a container, provisioning the infrastructure, creating your prediction API, securing it, scaling it, monitoring it, and more. Let's face it: building all this plumbing takes valuable time away from doing actual machine learning work. Unfortunately, it can also go awfully wrong.
We strive to fix this problem with the newly launched Hugging Face [Inference Endpoints](https://huggingface.co/inference-endpoints). In the spirit of making machine learning ever simpler without compromising on state-of-the-art quality, we've built a service that lets you deploy machine learning models directly from the [Hugging Face hub](https://huggingface.co/) to managed infrastructure on your favorite cloud in just a few clicks. Simple, secure, and scalable: you can have it all.
Let me show you how this works!
### [](https://huggingface.co/blog/inference-endpoints#deploying-a-model-on-inference-endpoints) Deploying a model on Inference Endpoints
Looking at the list of [tasks](https://huggingface.co/docs/inference-endpoints/supported_tasks) that Inference Endpoints support, I decided to deploy a Swin image classification model that I recently fine-tuned with [AutoTrain](https://huggingface.co/autotrain) on the [food101](https://huggingface.co/datasets/food101) dataset. If you're interested in how I built this model, this [video](https://youtu.be/uFxtl7QuUvo) will s
DeepCamp AI