GenerativeVLMOptions

Options & Configuration ยท AiDotNet.VisionLanguage.Generative

Base configuration options for generative vision-language models.

Inheritance: ModelOptions โ†’ GenerativeVLMOptions

Known derived types: BLIP3Options, CoCaOptions, DocumentVLMOptions, EditingVLMOptions, Emu2Options, Emu3Options, EmuOptions, GITOptions, GroundingVLMOptions, IDEFICS2Options, IDEFICS3Options, IDEFICSOptions, InstructBLIPOptions, InstructionTunedVLMOptions, KosmosOptions, MedicalVLMOptions, OpenFlamingoOptions, PaLI3Options, PaLIOptions, PaLIXOptions, ProprietaryVLMOptions, RemoteSensingVLMOptions, ThreeDVLMOptions, UnifiedVisionOptions, VideoLanguageOptions, VisionLanguageActionOptions

For Beginners

These options configure the Generative model. Default values follow the original paper settings.

Constructors

Constructor Summary
GenerativeVLMOptions() Initializes a new instance with default values.
GenerativeVLMOptions(GenerativeVLMOptions other) Initializes a new instance by copying from another instance.

Properties

Property Summary
GenerativeArchitectureType ArchitectureType { get; set; } Gets or sets the generative architecture type.
OnnxModelOptions OnnxOptions { get; set; } Gets or sets ONNX runtime options.
double DropoutRate { get; set; } Gets or sets the dropout rate.
double LearningRate { get; set; } Gets or sets the learning rate.
double WeightDecay { get; set; } Gets or sets the weight decay.
double[] ImageMean { get; set; } Gets or sets the per-channel image normalization mean.
double[] ImageStd { get; set; } Gets or sets the per-channel image normalization std.
int DecoderDim { get; set; } Gets or sets the text decoder hidden dimension.
int ImageSize { get; set; } Gets or sets the input image size.
int MaxGenerationLength { get; set; } Gets or sets the maximum generation output length in tokens.
int MaxSequenceLength { get; set; } Gets or sets the maximum input text sequence length.
int NumDecoderLayers { get; set; } Gets or sets the number of text decoder layers.
int NumHeads { get; set; } Gets or sets the number of attention heads.
int NumVisionLayers { get; set; } Gets or sets the number of vision encoder layers.
int VisionDim { get; set; } Gets or sets the vision encoder feature dimension.
int VocabSize { get; set; } Gets or sets the vocabulary size for tokenization.
string ModelPath { get; set; } Gets or sets the ONNX model path.