Vision Meets Language with SmolVLM

​Join the GitHub Community @ GITAM for an exciting, beginner-friendly deep dive into the future of AI — Vision-Language Models (VLMs).

​We’ll kick off with the demo then explain the basics of Large Language Models (LLMs) — from neurons to transformers to ChatGPT — and explore how these models are becoming smaller, faster, and more accessible through quantization and local deployment tools like Ollama and LM Studio.

​We'll break down how we built it, how it works, and show a live demo of this powerful multimodal model in action.

​What to Expect:

• ​🚀 Live Demo First: See SmolVLM in action

• ​🔍 What is an LLM?

• ​🧬 Origins: From neurons to transformers to LLMs

• ​⚖️ Parameters & quantization explained simply

• ​🖥️ How to run LLMs locally with Ollama & LM Studio

• ​🧠 Picking the right LLM for different tasks

• ​🧩 Behind the scenes of the SmolVLM GitHub repo

• ​🤖 What is Hugging Face?

• ​🙋 Q&A + Thank You Slide

​💡 No prior experience needed — just bring your curiosity.
Perfect for students interested in AI, GitHub projects, and real-world machine learning applications.

​

​📍 Venue: J-211
🕑 Time: 2:00 PM – 4:00 PM
📅 Date: August 1st, 2025

​Bring your curiosity. We’ll bring the code.
Hosted by: GitHub Community GITAM