With the Hugging Face Inference DLCs and new Inference Toolkit for Amazon SageMaker, you can leverage the pipelines from the Transformers library to allow zero-code deployments of models, and create production-ready endpoints that scale easily within your AWS environment with built-in monitoring.

With Hugging Face on Amazon SageMaker, you can fine-tune any of the 10,000+ pre-trained models from Hugging Face, an open-source provider of NLP, Speech and Computer Vision models known as Transformers, reducing the time it takes to train these State of the Art models from weeks to minutes.

Hugging Face Neuron Deep Learning AMI (DLAMI) makes it easy to use Amazon EC2 Inferentia & Trainium instances for efficient training and inference of Hugging Face Transformers and Diffusers models. With the Hugging Face Neuron DLAMI, scale your Transformers and Diffusion workloads quickly on Amazon EC2 while reducing your costs, with up to 50% cost-to-train savings over comparable GPU-based DLAMIs. This DLAMI is the officially supported, and recommended solution by Hugging Face, to run training and inference on Trainium and Inferentia EC2 instances, and supports most Hugging Face use cases, including: Fine-tuning and pre-training Transformers models like BERT, GPT, or T5 Running inference with Transformers models like BERT, GPT, or T5 Fine-tuning and deploying Diffusers models like Stable Diffusion

The Hugging Face Platform enables premium features for your organization on the Hugging Face Hub, including Inference Endpoints, Spaces Hardware Upgrades, and AutoTrain. With Inference Endpoints, you can securely deploy models from the Hugging Face Hub and custom containers on managed autoscaling infrastructure: - Optimized for LLMs: high throughput and low latency, powered by Text Generation Inference. - Deploy models as production-ready APIs with just a few clicks. No MLOps, no infrastructure to manage. - Automatic scale to zero capability for maximum cost efficiency. - Security first: we support direct connections to your private VPC. We have the SOC2 Type 2 certification and offer GDPR and BAA data processing agreements. - Out-of-the-box support for Hugging Face Transformers, Sentence-Transformers, Diffusers, and easy customization. Run inference at scale with any Machine Learning task and library. With Spaces, you can easily create and host any Machine Learning application, GPUs and batteries included: - Build ML apps and host them on Hugging Face. - Showcase projects, create an ML portfolio, and collaborate with others in your organization. - Wide range of frameworks supported: Gradio, Streamlit, HTML + JS, and many more with Docker. - Upgrade to GPU and accelerated hardware in just a few clicks. With AutoTrain, you can train state-of-the-art models with just a few clicks: - No-code tool to train state-of-the-art NLP, CV, Speech, and Tabular models without machine learning expertise. - Train custom models on your datasets without worrying about the technical details of model training. All Hugging Face services use a usage-based, pay-as-you-go pricing. Check out our pricing here: https://huggingface.co/pricing Inference Endpoints: https://huggingface.co/pricing#endpoints Spaces: https://huggingface.co/pricing#spaces AutoTrain: https://huggingface.co/pricing#autotrain