mirror of
https://github.com/ollama/ollama.git
synced 2025-03-18 13:51:45 +01:00
9679f40146
Models may require that a set of inputs all be processed as part of the same batch. For example, if an image has multiple patches with fully connected attention between them, we should not split the batch in the middle of an image. Fixes #9697
44 lines
1.2 KiB
Go
44 lines
1.2 KiB
Go
package input
|
|
|
|
// Input represents one token in the input stream
|
|
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
|
|
|
|
// SameBatch forces the following number of tokens to be processed
|
|
// in a single batch, breaking and extending batches as needed.
|
|
// Useful for things like images that must be processed in one
|
|
// shot.
|
|
SameBatch int
|
|
}
|
|
|
|
// MultimodalIndex is a multimodal element (such as an image)
|
|
// together with an index into the slice of Inputs with the
|
|
// corresponding token. Note that the index is not the same
|
|
// as the position - to find that use the index with the
|
|
// Positions slice.
|
|
type MultimodalIndex struct {
|
|
Index int
|
|
Multimodal any
|
|
}
|
|
|
|
// Options contains the inputs for a model forward pass
|
|
type Options struct {
|
|
Inputs []int32
|
|
Multimodal []MultimodalIndex
|
|
Positions []int32
|
|
Sequences []int
|
|
Outputs []int32
|
|
}
|