AWS Summit Zurich 2024 - Fine-tune and deploy LLMs from Hugging Face (AIM304)

Подробнее о видео

To power performant generative AI applications while keeping costs under control, AWS offers machine learning accelerators like AWS Trainium and AWS Inferentia2. In this session. we showcase how to fine-tune and deploy large language models on these purpose-built hardware using the Hugging Face Optimum Neuron library. The Optimum Neuron library provides an interface between the Hugging Face Transformers library and the Neuron SDK therefore simplifying model loading, training and inference by enabling developers to leverage the familiar Hugging Face API. Learn more about AWS Summit EMEA - On-Demand Hub: ABOUT AWS Amazon Web Services (AWS) hosts events, both online and in-person, bringing the cloud computing community together to connect, collaborate, and learn from AWS experts. AWS is the world’s most comprehensive and broadly adopted cloud platform, offering over 200 fully featured services from data centers globally. Millions of customers—including the fastest-growing startups, largest enterprises, and leading government agencies—are using AWS to lower costs, become more agile, and innovate faster.