README.md

AI Workshop 2025-05-03

Learn about Vision-language models, Vision-language encoders and various computer vision applications:

The workshop slides to follow.

Preparation

• Follow the instructions to setup your environment for the workshop.

Part I: Intro to VLMs & vision language encoders

• Vision-language encoders (CLIP, CLIPSeg, Florence) Instructions

Part II: Local Vision-language models with Ollama

• Set up VLLM's as Python interface. Instructions