gemini4kt/io.github.ugaikit.gemini4kt/Model

Model

@Serializable

data class Model(val name: String, val version: String, val displayName: String, val description: String, val inputTokenLimit: Int, val outputTokenLimit: Int, val supportedGenerationMethods: List<String>, val temperature: Double? = null, val topP: Double? = null, val topK: Int? = null)

Represents a model with its metadata and configuration parameters, providing detailed information about its capabilities and restrictions.

Constructors

Model

constructor(name: String, version: String, displayName: String, description: String, inputTokenLimit: Int, outputTokenLimit: Int, supportedGenerationMethods: List<String>, temperature: Double? = null, topP: Double? = null, topK: Int? = null)

Properties

description

val description: String

A brief description of the model, outlining its purpose, use case, or capabilities.

displayName

val displayName: String

A human-readable name for the model, intended for display purposes.

inputTokenLimit

val inputTokenLimit: Int

The maximum number of tokens that can be provided as input to the model.

name

val name: String

The unique identifier for the model.

outputTokenLimit

val outputTokenLimit: Int

The maximum number of tokens that the model can generate as output.

supportedGenerationMethods

val supportedGenerationMethods: List<String>

A list of strings indicating the generation methods supported by the model (e.g., "text", "code").

temperature

val temperature: Double? = null

An optional parameter influencing the randomness of the output. Lower values make the model more deterministic.

topK

val topK: Int? = null

An optional parameter that restricts the model to only consider the top-k most likely tokens for each step of generation.

topP

val topP: Double? = null

An optional parameter controlling the nucleus sampling method, where a cumulative probability threshold is set for token selection.

version

val version: String

The version of the model, indicating its iteration or update status.