This workshop is focused on empowering developers to effectively use Hugging Face* abstracted APIs to build AI applications on Intel® hardware platforms. Whether you are a novice or an experienced AI engineer developing on Intel hardware for the first time, this session provides valuable insights into enabling AI workloads and various optimizations available through Hugging Face libraries like transformers and accelerators.

The session walks you through fine-tuning, inference, and more specialized tasks like working with distributed systems to scale workloads efficiently. Attendees have the opportunity to follow along with hands-on examples and demos, gaining practical experience in using Hugging Face to run AI workloads on Intel hardware, unlocking optimizations through Hugging Face APIs, and understanding the full potential of Hugging Face on Intel hardware.