OnDeviceConfig
@PublicPreviewAPI
class OnDeviceConfig
Configuration for on-device AI model inference.
Summary
Public companion properties |
|
|---|---|
OnDeviceConfig |
A default configuration that only uses in-cloud inference. |
Public constructors |
|---|
OnDeviceConfig( |
Public properties |
|
|---|---|
Int |
The number of generated responses to return. |
Int? |
The maximum number of tokens to generate in the response. |
InferenceMode |
The |
OnDeviceModelOption? |
Configuration for the on-device model selection and performance. |
Int? |
The seed to use for generation to ensure reproducibility. |
Float? |
A parameter controlling the degree of randomness in token selection. |
Int? |
The |
Public companion properties
Public constructors
OnDeviceConfig
OnDeviceConfig(
mode: InferenceMode,
maxOutputTokens: Int? = null,
temperature: Float? = null,
topK: Int? = null,
seed: Int? = null,
candidateCount: Int = 1,
modelOption: OnDeviceModelOption? = null
)
Public properties
candidateCount
val candidateCount: Int
The number of generated responses to return. See GenerationConfig for more detail. By default it's set to 1.
maxOutputTokens
val maxOutputTokens: Int?
The maximum number of tokens to generate in the response. See GenerationConfig for more detail.
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.