It is ok to drop it after scarches categorial covariates fix

src/scvi/model/base/_archesmixin.py

@@ -12,7 +12,7 @@
 from mudata import MuData
 from scipy.sparse import csr_matrix
 
-from scvi import REGISTRY_KEYS, settings
+from scvi import settings
 from scvi._types import AnnOrMuData
 from scvi.data import _constants
 from scvi.data._constants import _MODEL_NAME_KEY, _SETUP_ARGS_KEY, _SETUP_METHOD_NAME
@@ -140,11 +140,6 @@ def load_query_data(
 
         model = _initialize_model(cls, adata, registry, attr_dict)
 
-        if model.summary_stats[f"n_{REGISTRY_KEYS.CAT_COVS_KEY}"] > 0:
-            raise NotImplementedError(
-                "scArches currently does not support models with extra categorical covariates."
-            )
-
         version_split = model.registry[_constants._SCVI_VERSION_KEY].split(".")
 
         if int(version_split[1]) < 8 and int(version_split[0]) == 0: