Scaling Autoregressive Multi-Modal Models: Pretraining and Instruction Tuning blog: https://
ai.meta.com/blog/generativ
e-ai-text-images-cm3leon/
… present CM3Leon (pronounced “Chameleon”), a retrieval-augmented, tokenbased, decoder-only multi-modal language model capable of generating and infilling both text and

→ View original post on X — @_akhaliq