what are the three key characteristics of foundation models?

a$.$ Thry are trained on labeled data, they use suprevised learning and they are trained on a specific task

b$.$They are trained on unlabeled data, they use self$-$supervised learning, and they are trained on a broad range of tasks

c$.$ They are trained on a small amount of data, they use supervised learning, and they are trained on a broad range of tasks

d$.$ They are trained on a large amount of data, they often use unsupervised learning, and they are trained on a specific task