view post Post 3887 π¨ 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 π₯ 8 8 π§ 1 1 β 1 1 π 1 1 + Reply