Explore the latest developments in Llama 3.2, including its multimodal capabilities and edge computing applications, in this 13-minute video. Dive into the details of Meta's blog post announcing Llama 3.2, examining vision instruction-tuned benchmarks and lightweight instruction-tuned models. Understand the pruning and distillation process through a detailed diagram. Watch a demonstration of Llama 3.2 in action and learn about the Llama Stack APIs. Discover where to find Llama 3.2 models on Hugging Face and how to use them with Ollama. For those interested in building LLM Agents, a form link is provided for further exploration. Access additional resources, including GitHub repositories for langchain and LLM tutorials.
Overview
Syllabus
Intro
Llama 3.2
Llama 3.2 Blog
Llama 3:2 Vision Instruction-tuned Benchmarks
Llama 3.2 Lightweight Instruction-tuned Benchmarks
Llama 3.2 Pruning and Distillations Diagram
Llama 3.2 Demo
Llama Stack APIs
Llama 3.2 Models on Hugging Face
Llama 3.2 on Ollama
Outro
Taught by
Sam Witteveen
Related Courses
-
Introducing Multimodal Llama 3.2
-
Llama 3 - 8B and 70B Models Deep Dive and Implementation Guide
-
Getting Started with Meta Llama 3.2 and Its Variants Using Groq and Hugging Face
-
LLaMA2 - What Are the Changes?
-
Investigating the Code Llama Models and Fine-Tuned Alternatives
-
Open LLaMa in LangChain and Hugging Face
