view post Post 3936 🚨 New VQA + captioning dataset! moondream/megalith-mdqaImages from Megalith, captioned using Moondream, then transformed to short-form QA.9M+ images, 6-10 QA pairs per image. See translation 🔥 8 8 🧠 1 1 ➕ 1 1 🚀 1 1 + Reply