Mydra logo
Artificial Intelligence
DeepLearning.AI logo

DeepLearning.AI

Introducing Multimodal Llama 3.2

  • up to 1 hour
  • Beginner

Explore the features of the new Llama 3.2 model, including image classification, vision reasoning, and tool use. Learn about Llama 3.2 prompting, tokenization, and the Llama stack to build AI applications.

  • Image classification
  • Vision reasoning
  • Tool use
  • Prompting
  • Tokenization

Overview

Join our new short course, Introducing Multimodal Llama 3.2, and learn from Amit Sangani, Senior Director of AI Partner Engineering at Meta, about the latest additions to the Llama models 3.1 and 3.2. Discover the new vision capabilities, tool-calling, and Llama Stack, an open-source orchestration layer for building on top of the Llama family of models. Start building exciting applications on Llama!

  • Web Streamline Icon: https://streamlinehq.com
    Online
    course location
  • Layers 1 Streamline Icon: https://streamlinehq.com
    English
    course language
  • Self-paced
    course format
  • Live classes
    delivered online

Who is this course for?

AI Enthusiasts

Anyone interested in exploring the features of the new Llama 3.2 model.

Developers

Developers looking to learn about Llama 3.2 prompting, tokenization, and tool calling.

AI Researchers

Researchers interested in the Llama stack and building AI applications.

Discover the latest features of Llama 3.2, including image classification and vision reasoning. Ideal for AI enthusiasts, developers, and researchers, this course will help you build innovative AI applications.

Pre-Requisites

1 / 1

  • Basic Python knowledge

What will you learn?

Introduction to Llama 3.2
Learn about the new models, how they were trained, their features, and how they fit into the Llama family.
Multimodal Prompting
Understand how to do multimodal prompting with Llama and work on advanced image reasoning use cases.
Roles and Prompt Format
Learn different roles—system, user, assistant, ipython—in the Llama 3.1 and 3.2 family and the prompt format that identifies those roles.
Tiktoken Tokenizer
Understand how Llama uses the tiktoken tokenizer, and how it has expanded to a 128k vocabulary size.
Tool Calling
Learn how to prompt Llama to call both built-in and custom tools with examples for web search and solving math equations.
Llama Stack API
Learn about ‘Llama Stack API’, a standardized interface for canonical toolchain components to customize Llama models.

Meet your instructor

  • Amit Sangani

    Senior Director of AI Partner Engineering, Meta

    Amit Sangani is a Senior Director of AI Partner Engineering at Meta, where he leads a global team of engineers focused on delivering key APIs and cross-platform SDKs for Meta's AI and Metaverse products.

Upcoming cohorts

  • Dates

    start now

Free