diff --git a/configs/train_decoder_config.test.json b/configs/train_decoder_config.test.json
index 101846e0..dfc09735 100644
--- a/configs/train_decoder_config.test.json
+++ b/configs/train_decoder_config.test.json
@@ -9,7 +9,7 @@
                 "dim_mults": [1, 2, 4, 8],
                 "attn_dim_head": 16,
                 "attn_heads": 4,
-		"self_attn": [false, true, true, true]
+                "self_attn": [false, true, true, true]
             }
         ],
         "clip": {
diff --git a/dalle2_pytorch/train_configs.py b/dalle2_pytorch/train_configs.py
index cecd8c7e..0dcb50cc 100644
--- a/dalle2_pytorch/train_configs.py
+++ b/dalle2_pytorch/train_configs.py
@@ -233,7 +233,7 @@ class UnetConfig(BaseModel):
     cond_on_text_encodings: Optional[bool] = None
     cond_dim: Optional[int] = None
     channels: int = 3
-    self_attn: ListOrTuple[int]
+    self_attn: ListOrTuple[bool]
     attn_dim_head: int = 32
     attn_heads: int = 16
     init_cross_embed: bool = True
@@ -245,7 +245,7 @@ class DecoderConfig(BaseModel):
     unets: ListOrTuple[UnetConfig]
     image_size: Optional[int] = None
     image_sizes: ListOrTuple[int] = None
-    clip: Optional[AdapterConfig]   # The clip model to use if embeddings are not provided
+    clip: Optional[AdapterConfig] = None   # The clip model to use if embeddings are not provided
     channels: int = 3
     timesteps: int = 1000
     sample_timesteps: Optional[SingularOrIterable[Optional[int]]] = None
diff --git a/dalle2_pytorch/version.py b/dalle2_pytorch/version.py
index 87046e54..23b53d6f 100644
--- a/dalle2_pytorch/version.py
+++ b/dalle2_pytorch/version.py
@@ -1 +1 @@
-__version__ = '1.15.4'
+__version__ = '1.15.5'