πŸ—πŸš’πŸš€ Vision Language Models & Multi-Modality


​

Hey, AIM community!

​

Next Wednesday, join us in learning about smolagents and how you can use the new framework to make big-impact agent applications with a small number of lines of code!
​

​


Last week, we explored Multimodality with Llama 3.2, Meta’s first multimodal Llama model! We talked about the genesis of Vision Language Models (VLMs), and we even combined two VLMs to complete complex document parsing (with one VLM) and understanding (with Llama 3.2!). Watch the entire event for a primer on shared embedding spaces and a brief history and discussion of key research milestones in VLMs.

🧰 Resources


πŸ”­ Coming Up!

DeepSeek-R1

We're deep diving DeepSeek-R1! We'll cover the paper, what we know about its training lineage from DeepSeek-R1-Zero, and how it was used to distill both Qwen and Llama models using hundreds of thousands of examples generated from R1. Of course, we'll do a hype review, too, and cover the latest!

COCONUT: Chain of Continuous Thought

The discussion of LRMs continues with COCONUT, where we'll learn how to deal with continuous chains of thought in latent space. The new repo from Meta dropped, so it's time to do some proper concepts and code!


🌐 Around the Community!

πŸ’‘ Transformation Spotlight: Cesar Gonzalez! Learn how this business owner, with very little coding experience, is innovating with Gen AI to push his companies forward. Read more about his story.​

video preview​

πŸ€“ See what the community is building, shipping, and sharing this week. Join us in the Lounge every Monday at 9 AM PT for some accountability!

​@kennyrogers.btc @angrez @thomfoolery @rprav @Gon @njhaveri @Ernestobs7 @philipkang @Walid @Mahinour @Deepali @kireeti @NageshBangaloreMuralidhar @john-π’†œSΡ’1vπ’†œ @Akshayvernekar @thedOc @Lewis @Vinod @ChristineMahler @Deepti @RichardMoss @HughBrown @bd25911 @saisreekanth @Sonu @Dirk @Praveen

​

  • @MikeC keeps us posted on events going on during Week 6 of 2025!πŸŽ‰

​

Want to join the AIM community? Hop into Discord and share your intro!


​

πŸ–ΌοΈ Meme of the Week


🌟 Want to start building, shipping, and sharing but not sure how? Check out our LLM Foundations - a 5-day email-based course.

​

Keep building πŸ—οΈ shipping 🚒 and sharing πŸš€,

​

​Dr. Greg, The Wiz, Seraacha, and Lusk​
​AI Makerspace​

​
​Unsubscribe Β· Preferences​

The LLM Edge

Read more from The LLM Edge
RAG: The 2025 Best Practice Stack

Hey, AIM community! Tomorrow, we'll cover Enterprise Agents with OpenAI! What does the agents SDK look like from OpenAI? How does it build on previous work they've done? Are they officially in the end-to-end platform game competing with orchestration frameworks like LangChain, LlamaIndex, CrewAI, and others? Join us live to find out! Last week, we discussed RAG: The 2025 Best-Practice Stack This is the year of Practical RAG, and we kicked it off by unpacking the Minimum Viable...

DeepSeek Week

Hey, AIM community! On Wednesday, we'll cover the infra stack that we recommend for RAG in 2025. Then, we'll build, ship, and share a best-practice RAG app. We'll also discuss important production tradeoffs and implications that you should consider before and after deployment when going from zero to production RAG! Last week, we discussed the latest open-source repo drops from DeepSeek Week, and we covered how they're being used as a new best-practice way to do inference on MoE models via...

Optimization of LLMs

Hey, AIM community! Next Wednesday, we begin a new series on Optimization of LLMs! We'll tackle an important topic from first principles: building and optimizing LLMs before they make it to production. What are the essential concepts and code that underlie the technology, from loss functions and gradient descent to LSTMs, RLHF, and GRPO? Join us to kick off our new series - which we will continue monthly - about Optimization of LLMs. Last week, we put PydanticAI to the test! πŸš€ The team behind...