Collaborating Authors

Fine-tune and host Hugging Face BERT models on Amazon SageMaker


The last few years have seen the rise of transformer deep learning architectures to build natural language processing (NLP) model families. The adaptations of the transformer architecture in models such as BERT, RoBERTa, T5, GPT-2, and DistilBERT outperform previous NLP models on a wide range of tasks, such as text classification, question answering, summarization, and text generation. These models are exponentially growing larger in size from several million parameters to several hundred billion parameters. As the number of model parameters increases, so does the computational infrastructure that is necessary to train these models. This requires a significant amount of time, skill, and compute resources to train and optimize the models.

Announcing managed inference for Hugging Face models in Amazon SageMaker


Hugging Face is the technology startup, with an active open-source community, that drove the worldwide adoption of transformer-based models thanks to its eponymous Transformers library. Earlier this year, Hugging Face and AWS collaborated to enable you to train and deploy over 10,000 pre-trained models on Amazon SageMaker. For more information on training Hugging Face models at scale on SageMaker, refer to AWS and Hugging Face collaborate to simplify and accelerate adoption of Natural Language Processing models and the sample notebooks. In this post, we discuss different methods to create a SageMaker endpoint for a Hugging Face model. If you're unfamiliar with transformer-based models and their place in the natural language processing (NLP) landscape, here is an overview.

Set up a text summarization project with Hugging Face Transformers: Part 2


But again, this is just a first attempt. When the project is in the experimentation phase, these two parameters can and should be changed to see if the model performance changes. If you're already familiar with text generation, you might know there are many more parameters to influence the text a model generates, such as beam search, sampling, and temperature. These parameters give you more control over the text that is being generated, for example make the text more fluent and less repetitive.

Hugging Face collaborates with Microsoft for new AI-powered service – TechCrunch


Fresh off a $100 million funding round, Hugging Face, which provides hosted AI services and a community-driven portal for AI tools and data sets, today announced a new product in collaboration with Microsoft. Called Hugging Face Endpoints on Azure, Hugging Face co-founder and CEO Clément Delangue described it as a way to turn Hugging Face-developed AI models into "scalable production solutions." "The mission of Hugging Face is to democratize good machine learning," Delangue said in a press release. "We're striving to help every developer and organization build high-quality, machine learning-powered applications that have a positive impact on society and businesses. With Hugging Face Endpoints, we've made it simpler than ever to deploy state-of-the-art models, and we can't wait to see what Azure customers will build with them." The demand for AI remains high.

Securing all Amazon SageMaker API calls with AWS PrivateLink Amazon Web Services


All Amazon SageMaker API operations are now fully supported via AWS PrivateLink, which increases the security of data shared with cloud-based applications by reducing data exposure to the internet. In this blog, I show you how to set up a VPC endpoint to secure your Amazon SageMaker API calls using AWS PrivateLink. AWS PrivateLink traffic doesn't traverse the internet, which reduces the exposure to threats such as brute force and distributed denial of service attacks. Because all communication between your application and Amazon SageMaker API operations is inside your VPC, you don't need an internet gateway, a NAT device, a VPN connection, or AWS Direct Connect to communicate with Amazon SageMaker. Instead, AWS PrivateLink enables you to privately access all Amazon SageMaker API operations from your VPC in a scalable manner by using interface VPC endpoints.