Multimodality with Llama 3.2

​Multimodal models are on the rise in 2025! Images and videos generated using AI continue to get better and better, rapidly.

​The industry has come a long way! Llama 3.2 was the first multimodal Llama Model, supporting vision and text modalities.

​We’re told by Meta that Llama 3.2 models “Support image reasoning use cases, such as document-level understanding including charts and graphs, captioning of images, and visual grounding tasks such as directionally pinpointing objects in images based on natural language descriptions.”

​When thinking about multimodal models, a few questions come to mind:

• ​How can the model “see?”

• ​What exactly is Llama 3.2 actually doing when you prompt it? How does this differ from an LLM that is text only?

• ​Is it just embedding representations that differ, or also the generation process?

• ​How exactly are multimodal models trained and adapted to vision, from pretraining to post-training?

​With the rise of AI capabilities like computer use, it’s time we all get a handle on multimodality.

​Start learning what you need to know live Dr. Greg & The Wiz, from concepts to code.

​📚 You’ll learn:

• ​How multimodal LLMs differ from text-only models, from prompting to encoding to decoding

• ​How to leverage Llama 3.2 in your workflows and applications

​🤓 Who should attend the event:

• ​Aspiring AI Engineers who want to build state-of-the-art multimodal LLM applications

• ​AI Engineering leaders who want to build production applications with of multimodal LLMs
  

​Speakers:

• ​Dr. Greg” Loughnane is the Co-Founder & CEO of AI Makerspace, where he is an instructor for their AI Engineering Bootcamp. Since 2021, he has built and led industry-leading Machine Learning education programs.  Previously, he worked as an AI product manager, a university professor teaching AI, an AI consultant and startup advisor, and an ML researcher.  He loves trail running and is based in Dayton, Ohio.
  
  

• ​Chris “The Wiz” Alexiuk is the Co-Founder & CTO at AI Makerspace, where he is an instructor for their AI Engineering Bootcamp. During the day, he is also a Developer Advocate at NVIDIA. Previously, he was a Founding Machine Learning Engineer, Data Scientist, and ML curriculum developer and instructor. He’s a YouTube content creator YouTube who’s motto is “Build, build, build!” He loves Dungeons & Dragons and is based in Toronto, Canada.

​Follow AI Makerspace on LinkedIn and YouTube to stay updated about workshops, new courses, and corporate training opportunities.