ValueError: Argument `name` must be a string and cannot contain character `/`. Received: name=blocks/0 (of type <class 'str'>)

[SEOYUNJE]

File /opt/conda/lib/python3.10/site-packages/tfimm/architectures/cait.py:263, in LayerScaleBlock.init(self, cfg, drop_path_rate, **kwargs)
262 def init(self, cfg: CaiTConfig, drop_path_rate: float, **kwargs):
--> 263 super().init(**kwargs)
264 self.cfg = cfg
266 norm_layer = norm_layer_factory(cfg.norm_layer)

File /opt/conda/lib/python3.10/site-packages/keras/src/layers/layer.py:247, in Layer.init(self, activity_regularizer, trainable, dtype, autocast, name, **kwargs)
245 BackendLayer.init(self)
246 self._lock = False
--> 247 Operation.init(self, dtype=dtype, name=name)
248 self.activity_regularizer = regularizers.get(activity_regularizer)
249 input_dim_arg = kwargs.pop("input_dim", None)

File /opt/conda/lib/python3.10/site-packages/keras/src/ops/operation.py:21, in Operation.init(self, dtype, name)
19 name = auto_name(self.class.name)
20 if not isinstance(name, str) or "/" in name:
---> 21 raise ValueError(
22 "Argument name must be a string and "
23 "cannot contain character /. "
24 f"Received: name={name} (of type {type(name)})"
25 )
26 self._dtype_policy = dtype_policies.get(dtype)
27 self.name = name

ValueError: Argument name must be a string and cannot contain character /. Received: name=blocks/0 (of type <class 'str'>)`

It seems likes tensorflow >= 2.16, '/' erros happen when reading layers(like block/)