Enter the era of mainstream AI with this expert series, developing your coding skills to liberate the optimal performance and efficiency of Intel® Gaudi® Accelerators. The series consists of these three sessions:
-
- Fine-tuning LLMs and Optimized Interference – Gain hands-on proficiency using Intel® Gaudi accelerators, focusing on fine-tuning large language models (LLMs) and optimizing inference techniques.
-
- Harnessing Multi-Modal Models – Streamline creation of GenAI solutions, including deployment, best practices for multi-modal inference, and optimization.
- Building Advanced Retrieval Augmented Generation (RAG) Applications – Use the Intel® Gaudi® platform to build RAG applications.Key learnings:
- Learn the best practices for model development.
- Explore resources in APIs and libraries, including DeepSpeed, Optimum Habana, and PyTorch.
- Explore multi-modal model deployment on the Intel® Gaudi platform.
- Use Intel® Gaudi® accelerators to perform text embedding and generation.
- Get hands-on experience building a RAG application on Intel® Xeon® processors.
Register now to secure your place in these exclusive workshops and supercharge your AI development skills. Spaces are limited, so sign up promptly.