ReasoningVLMOptions

Options & Configuration · AiDotNet.VisionLanguage.Reasoning

Base configuration options for reasoning vision-language models with chain-of-thought capabilities.

Inheritance: ModelOptions → GenerativeVLMOptions → InstructionTunedVLMOptions → ReasoningVLMOptions

Known derived types: KimiVLOptions, KimiVLThinkingOptions, LLaVACoTOptions, QVQ72BOptions, SkyworkR1V2Options, SkyworkR1VOptions

For Beginners

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

Constructors

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

Properties

Property Summary
bool EnableThinkingSteps { get; set; } Gets or sets whether to include explicit thinking steps in the output.
int MaxReasoningTokens { get; set; } Gets or sets the maximum number of reasoning tokens before the final answer.
string ReasoningApproach { get; set; } Gets or sets the reasoning approach (e.g., “CoT”, “RL-Aligned”, “MoE-Reasoning”).