Interface Method

The method used for fine-tuning.

interface Method {
    dpo?: DpoMethod;
    reinforcement?: ReinforcementMethod;
    supervised?: SupervisedMethod;
    type: "supervised" | "dpo" | "reinforcement";
}

Index

Properties

dpo? reinforcement? supervised? type

Properties

`Optional`dpo

dpo?: DpoMethod

Configuration for the DPO fine-tuning method.

`Optional`reinforcement

reinforcement?: ReinforcementMethod

Configuration for the reinforcement fine-tuning method.

`Optional`supervised

supervised?: SupervisedMethod

Configuration for the supervised fine-tuning method.

type

type: "supervised" | "dpo" | "reinforcement"

The type of method. Is either supervised, dpo, or reinforcement.