Class QwenVisionTower
java.lang.Object
smile.deep.layer.LayerBlock
smile.llm.model.qwen.QwenVisionTower
Qwen3.8 / Qwen3.5 vision tower (
model.visual.*).
Patch embed is a bias linear equivalent to Conv3d
(temporal, patch, patch) over flattened patches. DeepStack is
rejected when indexes are non-empty.
-
Field Summary
Fields inherited from class LayerBlock
device, dtype, module -
Constructor Summary
ConstructorsConstructorDescriptionCreates a vision tower for the given hyperparameters. -
Method Summary
Methods inherited from class LayerBlock
add, add, device, dtype, eval, isTraining, load, loadStateDict, module, save, setRequiresGrad, to, to, toString, train
-
Constructor Details
-
QwenVisionTower
Creates a vision tower for the given hyperparameters.- Parameters:
args- vision hyperparameters.
-
-
Method Details
-
args
-
forward
-
forward
-