refactor: 抽取 BaseStorage 存储抽象，支持 JSON 原始文本数据加载

- 新增 astrai/dataset/storage.py：BaseStorage/H5Storage/JSONStorage + Fetchers + 序列化函数
- BaseDataset.load() 接入存储抽象，自动检测 HDF5/JSON 格式
- JSON 支持原始文本 + tokenizer callable 加载时 tokenize
- 新增 BaseDataset.count / keys 属性进行长度观测
- serialization.py 精简为只保留 Checkpoint 类
- 函数放前、类放后，删除分隔注释

astrai/serialization.py

@@ -1,53 +1,14 @@
 import json
-import os
 from pathlib import Path
-from typing import Any, Dict, List, Optional
+from typing import Any, Dict, Optional
 
-import h5py
 import safetensors.torch as st
 import torch
 import torch.distributed as dist
-from torch import Tensor
 
 from astrai.parallel.setup import get_rank
 
 
-def save_h5(file_path: str, file_name: str, tensor_group: Dict[str, List[Tensor]]):
-    os.makedirs(file_path, exist_ok=True)
-    full_file_path = os.path.join(file_path, f"{file_name}.h5")
-    with h5py.File(full_file_path, "w") as f:
-        for key, tensors in tensor_group.items():
-            grp = f.create_group(key)
-            for idx, tensor in enumerate(tensors):
-                arr = tensor.cpu().numpy()
-                grp.create_dataset(f"data_{idx}", data=arr)
-
-
-def load_h5(file_path: str, share_memory=True) -> Dict[str, List[Tensor]]:
-    tensor_group: Dict[str, List[Tensor]] = {}
-
-    root_path = Path(file_path)
-    h5_files = list(root_path.rglob("*.h5")) + list(root_path.rglob("*.hdf5"))
-
-    for h5_file in h5_files:
-        with h5py.File(h5_file, "r") as f:
-            for key in f.keys():
-                grp = f[key]
-                dsets = []
-                for dset_name in grp.keys():
-                    dset = grp[dset_name]
-                    tensor = torch.from_numpy(dset[:])
-                    if share_memory:
-                        tensor = tensor.share_memory_()
-                    dsets.append(tensor)
-
-                if tensor_group.get(key) is None:
-                    tensor_group[key] = []
-                tensor_group[key].extend(dsets)
-
-    return tensor_group
-
-
 class Checkpoint:
     def __init__(
         self,