model

type Base struct {
	// contains filtered or unexported fields
}

type Model interface {
	Forward(ml.Context, input.Batch) (ml.Tensor, error)

	Backend() ml.Backend
	Config() config
}

type MultimodalProcessor interface {
	// EncodeMultimodal processes a single input (such as an image) and
	// generates an output (typically an embedding) that can be used by the model.
	//
	// The return value is one or more tensors, each with optional model-specific
	// opaque metadata. Typically, the tensors might be views into an embedding
	// with each view representing a chunk of data that can be processed independently
	// in different batches.
	//
	// The result may be cached by the runner.
	EncodeMultimodal(ml.Context, []byte) ([]input.Multimodal, error)

	// PostTokenize is called after tokenization to allow the model to edit the
	// input stream to correctly arrange multimodal elements.
	//
	// The input is a slice of tokens with the results of EncodeMultimodal interleaved
	// in the order that the user provided them. Each element of the slice will be
	// either a single token or single multimodal object.
	//
	// The model must ensure that inputs are stored according to how they will be
	// processed and stored in the cache. For example, Llava-style models should insert
	// placeholder tokens equal to the feature size of the corresponding image with
	// the image itself attached to and split across these tokens. When Forward is called
	// a partial subset of these tokens may be submitted according to the batch size.
	//
	// This function is also responsible for updating MultimodalHash for any Multimodal
	// that is modified to ensure that there is a unique hash value that accurately
	// represents the contents.
	PostTokenize([]*input.Input) ([]*input.Input, error)
}

type Tag struct {
	// contains filtered or unexported fields
}

type Validator interface {
	Validate() error
}