Webinar: Getting Started with Llama 3 on AMD Radeon and Instinct Graphics Cards

[Sponsored Post] This webinar includes a guide to installing Hugging Face transformers, Meta’s Llama 3 weights, and the necessary dependencies to run Llama locally on AMD systems with ROCm™ 6.0.¹

Webinar Topics

• Go through a basic understanding of transformer models. Introduce LLM, Hugging Face, and some of the recent work done by AMD and Hugging Face
• How to Install Torch and Transformers Framework and Its Dependencies on AMD Instinct and Radeon Graphics Cards with ROCm 6.1
• Step through a set of publicly available scripts to run llama2-7b and support AMD Instinct™ MI210 and AMD Radeon™ W7800 GPUs on a system with ROCm 6.1 installed
• Share where to find AMD documentation and blogs

The live coding portion will be followed by a compact wrap-up, showcasing ROCm resources, and a Q&A with ROCm experts.

Register here.

¹ For a full list of Radeon parts supported by ROCm™ software as of May 1, 2024, please go to https://rocm.docs.amd.com/pl/najnowsze/informacje/specyfikacje-arch-gpu.html.GD-241