refactor : BaseFactory 基类类型自动推导 + 移除冗余代码

- _validate_component 从 BaseFactory[T] 泛型参数自动解析基类类型，9 个子类覆写移除
- Registry 类内联到 BaseFactory._entries，移除未用的 list_by_category/list_by_priority
- _component_base 在 __init_subclass__ 时立即解析
- 数据集 4 个子类冗余 __init__ 移除

astrai/dataset/dataset.py

@@ -136,12 +136,6 @@ class DatasetFactory(BaseFactory["BaseDataset"]):
         dataset = DatasetFactory.create("custom", window_size, stride)
     """
 
-    @classmethod
-    def _validate_component(cls, dataset_cls: type):
-        """Validate that the dataset class inherits from BaseDataset."""
-        if not issubclass(dataset_cls, BaseDataset):
-            raise TypeError(f"{dataset_cls.__name__} must inherit from BaseDataset")
-
     @classmethod
     def create(cls, train_type: str, window_size: int, stride: int) -> "BaseDataset":
         """Create a dataset instance.
@@ -195,9 +189,6 @@ class DatasetFactory(BaseFactory["BaseDataset"]):
 class SEQDataset(BaseDataset):
     """Dataset for sequential next-token prediction training."""
 
-    def __init__(self, window_size: int, stride: int):
-        super().__init__(window_size, stride)
-
     @property
     def required_keys(self) -> List[str]:
         return ["sequence"]
@@ -218,9 +209,6 @@ class SEQDataset(BaseDataset):
 class SFTDataset(BaseDataset):
     """Dataset for supervised fine-tuning with loss masking."""
 
-    def __init__(self, window_size: int, stride: int):
-        super().__init__(window_size, stride)
-
     @property
     def required_keys(self) -> List[str]:
         return ["sequence", "loss_mask", "position_ids"]
@@ -248,9 +236,6 @@ class SFTDataset(BaseDataset):
 class DPODataset(BaseDataset):
     """Dataset for Direct Preference Optimization training."""
 
-    def __init__(self, window_size: int, stride: int):
-        super().__init__(window_size, stride)
-
     @property
     def required_keys(self) -> List[str]:
         return ["chosen", "rejected", "chosen_mask", "rejected_mask"]
@@ -282,9 +267,6 @@ class DPODataset(BaseDataset):
 class GRPODataset(BaseDataset):
     """Dataset for Group Relative Policy Optimization training."""
 
-    def __init__(self, window_size: int, stride: int):
-        super().__init__(window_size, stride)
-
     @property
     def required_keys(self) -> List[str]:
         return ["prompts", "responses", "masks", "rewards"]