MPLUGDocOwl15Options
Options & Configuration · AiDotNet.VisionLanguage.Document
Configuration options for mPLUG-DocOwl 1.5: unified structure learning achieving SOTA on 10 document benchmarks.
Inheritance: ModelOptions → GenerativeVLMOptions → DocumentVLMOptions → MPLUGDocOwl15Options
For Beginners
These options configure the MPLUGDocOwl15 model. Default values follow the original paper settings.
Constructors
| Constructor | Summary |
|---|---|
MPLUGDocOwl15Options() |
Initializes a new instance with default values. |
MPLUGDocOwl15Options(MPLUGDocOwl15Options other) |
Initializes a new instance by copying from another instance. |
Properties
| Property | Summary |
|---|---|
bool EnableUnifiedStructureLearning { get; set; } |
Gets or sets whether to use unified structure learning. |
int AbstractorDim { get; set; } |
Gets or sets the hidden width of the paper’s visual abstractor. |
int NumAbstractorLayers { get; set; } |
Gets or sets the number of layers of the paper’s visual abstractor. |