RewardFunctionsConfig (GRPO)

以下是奖励函数配置的类定义。

class RewardFunctionsConfig(BaseModel):
    runtime: RewardFunctionsRuntimeConfig | None = Field(default=None)
    functions: dict[str, RewardFunction] = Field(default_factory=dict)

class RewardFunctionsRuntimeConfig(BaseModel):
    packages: list[str] | None = Field(default=None)

class RewardFunction(BaseModel):
    encoded_fn: str = Field(serialization_alias="encodedFn")

此配置用于设置GRPO训练所需的奖励函数，并指定运行奖励函数需要安装的软件包依赖项。例如：

def my_reward_function(prompt, completion, example) -> float:
    import my_pkg
    my_pkg.score(...)

cfg = RewardFunctionsConfig(
    runtime=RewardFunctionsRuntimeConfig(
        packages=[
            "mypkg",
        ]
    ),
    functions={
        "my_reward": RewardFunction.from_callable(my_reward_function)
    },
)