Toor

Appearance

@gettoor/core v0.1.0

@gettoor/core / ExperimentModelParameters

Interface: ExperimentModelParameters ​

Experiment model parameters.

Extends ​

Properties ​

frequencyPenalty? ​

optional frequencyPenalty?: number

Penalizes tokens based on how frequently they have already appeared in the generated text.

Higher values reduce repetition of the same words and phrases, resulting in more varied output.

Inherited from ​

ModelParameters.frequencyPenalty

maxOutputTokens? ​

optional maxOutputTokens?: number

Maximum number of tokens the model may generate in its response.

Lower values limit response length and cost, while higher values allow longer and more detailed outputs.

Inherited from ​

ModelParameters.maxOutputTokens

name ​

name: string

presencePenalty? ​

optional presencePenalty?: number

Penalizes tokens that have already appeared in the generated text.

Higher values encourage the model to introduce new topics and vocabulary instead of repeating previously used tokens.

Inherited from ​

ModelParameters.presencePenalty

temperature? ​

optional temperature?: number

Controls sampling randomness.

Lower values make outputs more deterministic and focused, while higher values increase creativity and variation.

Inherited from ​

ModelParameters.temperature

topK? ​

optional topK?: number

Controls top-k sampling.

The model samples only from the topK most likely next tokens. Lower values produce more predictable outputs, while higher values allow for more varied and creative responses.

Inherited from ​

ModelParameters.topK

topP? ​

optional topP?: number

Controls nucleus sampling.

The model considers the smallest set of tokens whose cumulative probability is at least topP and samples from that set. Lower values make outputs more focused and deterministic, while higher values increase diversity.

Inherited from ​

ModelParameters.topP