firebase-ai/com.google.firebase.ai/OnDeviceConfig

OnDeviceConfig

class OnDeviceConfig @JvmOverloads constructor(val mode: InferenceMode, val maxOutputTokens: Int? = null, val temperature: Float? = null, val topK: Int? = null, val seed: Int? = null, val candidateCount: Int = 1, val modelOption: OnDeviceModelOption? = null, val enableThinking: Boolean? = null)(source)

Configuration for on-device AI model inference.

Constructors

OnDeviceConfig

@JvmOverloads

constructor(mode: InferenceMode, maxOutputTokens: Int? = null, temperature: Float? = null, topK: Int? = null, seed: Int? = null, candidateCount: Int = 1, modelOption: OnDeviceModelOption? = null, enableThinking: Boolean? = null)

Types

Companion

object Companion

Properties

candidateCount

val candidateCount: Int

The number of generated responses to return. See GenerationConfig for more detail. By default it's set to 1.

enableThinking

val enableThinking: Boolean?

Whether the on-device model thinks before it answers; null leaves the model's default.

maxOutputTokens

val maxOutputTokens: Int?

The maximum number of tokens to generate in the response. See GenerationConfig for more detail.

mode

val mode: InferenceMode

The InferenceMode to use for the model.

modelOption

val modelOption: OnDeviceModelOption?

Configuration for the on-device model selection and performance.

seed

val seed: Int?

The seed to use for generation to ensure reproducibility. See GenerationConfig for more detail.

temperature

val temperature: Float?

A parameter controlling the degree of randomness in token selection. See GenerationConfig for more detail.

topK

val topK: Int?

The topK parameter changes how the model selects tokens for output. See GenerationConfig for more detail.