Offline Large Model Development

Chapter 12 Offline Large Model Development

This chapter merges the offline LLM content from xiaobai-lesson Chapter 12. It focuses on environment setup for Jetson, text-only models, vision-language models, speech pipelines, and multimodal voice applications.

Contents

ModuleContent
Module 5.1Environment and Basics with Ollama
Module 5.2Offline Text LLMs
Module 5.3Offline Vision-Language Models and Applications
Module 5.4Offline Speech Pipeline Basics
Module 5.5Offline Multimodal Voice Applications

Suggested Learning Order

  1. Start with 5.1 to make sure Ollama, Open WebUI, and the base runtime are working.
  2. Continue with 5.2 and 5.3 to understand text-only and vision-language model workflows.
  3. Finish with 5.4 and 5.5 to connect speech input, speech output, and multimodal capabilities.