[Article Voiceover] Llama 3.2 Vision and Molmo: Foundations for the multimodal open-source ecosystem

Sorry this one was late! Thanks for bearing with me, and keep sending feedback my way. Still a year or two away from when I have time to record these, but I would love to.Open-source tools, examples, limits, and the state of training multimodal models.This is AI generated audio with Python and 11Labs.Source code: https://github.com/natolambert/interconnects-toolsOriginal post: https://www.interconnects.ai/p/molmo-and-llama-3-vision00:00 Llama 3.2 Vision and Molmo: Foundations for the multimodal open-source ecosystem02:47 Llama vision: Multimodality for the masses of developers03:27 Molmo: a (mostly) open-source equivalent to Llama vision08:45 How adding vision changes capabilities and reasoning11:47 Multimodal language models: Earlier on the exponentialFig 1: https://huggingface.co/datasets/natolambert/interconnects-figures/resolve/main/llama-and-molmo/img_013.pngFig 2: https://huggingface.co/datasets/natolambert/interconnects-figures/resolve/main/llama-and-molmo/img_015.pngFig 3: https://huggingface.co/datasets/natolambert/interconnects-figures/resolve/main/llama-and-molmo/img_021.pngFig 4: https://huggingface.co/datasets/natolambert/interconnects-figures/resolve/main/llama-and-molmo/img_023.pngFig 5: https://huggingface.co/datasets/natolambert/interconnects-figures/resolve/main/llama-and-molmo/img_027.pngFig 6: https://huggingface.co/datasets/natolambert/interconnects-figures/resolve/main/llama-and-molmo/img_030.pngFig 7: https://huggingface.co/datasets/natolambert/interconnects-figures/resolve/main/llama-and-molmo/img_037.pngFig 8: https://huggingface.co/datasets/natolambert/interconnects-figures/resolve/main/llama-and-molmo/img_046.pngFig 9: https://huggingface.co/datasets/natolambert/interconnects-figures/resolve/main/llama-and-molmo/img_048.pngFig 10: https://huggingface.co/datasets/natolambert/interconnects-figures/resolve/main/llama-and-molmo/img_050.pngFig 11: https://huggingface.co/datasets/natolambert/interconnects-figures/resolve/main/llama-and-molmo/img_052.pngFig 12: https://huggingface.co/datasets/natolambert/interconnects-figures/resolve/main/llama-and-molmo/img_054.pngFig 13: https://huggingface.co/datasets/natolambert/interconnects-figures/resolve/main/llama-and-molmo/img_058.pngFig 14: https://huggingface.co/datasets/natolambert/interconnects-figures/resolve/main/llama-and-molmo/img_065.png Get full access to Interconnects at www.interconnects.ai/subscribe

Om Podcasten

Audio essays about the latest developments in AI and interviews with leading scientists in the field. Breaking the hype, understanding what's under the hood, and telling stories. www.interconnects.ai