Skill issue: stop deploying vision language models, use them with Skills to build e2e vision apps on edge

With the boom of vision language models barrier of entry to build vision apps are much lower so developers tend to use them right away. However, these models are very large and inefficient in production. In this talk, I will go through combining vision language models with Skills to build end-to-end vision apps from training to deployment using HF Skills, on top of showing the state-of-the-art in small computer vision/multimodal models.