mirror of
https://github.com/ollama/ollama.git
synced 2025-06-13 00:00:55 +02:00
06007c0a18
This is useful for a few things: - Work around bugs, such as having 2 images in one batch - Keep the image in a single batch for fully connected attention - Improve performance by not evaluating embeddings multiple times
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
|
|
|
|
// BatchBreak forces a new batch to be started with this
|
|
// input. For example, this can be used to align images
|
|
// with batches. Note that batches may be divided in additional
|
|
// locations as well.
|
|
BatchBreak bool
|
|
}
|
|
|
|
// 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
|
|
}
|