input

type Input struct {
	// Token is a single element of text.
	Token int32

	// Multimodal is opaque data representing a non-text
	// element such as an image (or part of one if the image
	// can be processed in pieces). It may be either together
	// with Token or on its own.
	Multimodal any

	// MultimodalHash is a unique representation of the data
	// stored in Multimodal, used for caching and comparing
	// equality.
	MultimodalHash uint64
}

type MultimodalIndex struct {
	Index      int
	Multimodal any
}

type Options struct {
	Inputs     []int32
	Multimodal []MultimodalIndex
	Positions  []int32
	Sequences  []int
	Outputs    []int32
}