MAGMA - a GPT-style multimodal model that can understand any combination of images and language. NOTE: The freely available model from this repo is only a demo. For the latest multimodal and multilingual models from Aleph Alpha check out our website https://app.aleph-alpha.com
I have downloaded cc3m in files format where each folder is named as 00000 to 00331 where each folder contains 0000.jpg and 000.json i.e. 1 image and 1 json. Can you please help me I am unsure how to convert my data to your format. @Mayukhdeb @benbrandt
I have downloaded cc3m in files format where each folder is named as 00000 to 00331 where each folder contains 0000.jpg and 000.json i.e. 1 image and 1 json. Can you please help me I am unsure how to convert my data to your format. @Mayukhdeb @benbrandt