yet more pydantic v2 stuff

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": {

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: SingularOrIterable[bool] = False
     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

dalle2_pytorch/version.py

@@ -1 +1 @@
-__version__ = '1.15.4'
+__version__ = '1.15.6'

train_decoder.py

@@ -511,7 +511,7 @@ def train(
         if next_task == 'eval':
             if exists(evaluate_config):
                 accelerator.print(print_ribbon(f"Starting Evaluation {epoch}", repeat=40))
-                evaluation = evaluate_trainer(trainer, dataloaders["val"], inference_device, first_trainable_unet, last_trainable_unet, clip=clip, inference_device=inference_device, **evaluate_config.dict(), condition_on_text_encodings=condition_on_text_encodings, cond_scale=cond_scale)
+                evaluation = evaluate_trainer(trainer, dataloaders["val"], inference_device, first_trainable_unet, last_trainable_unet, clip=clip, inference_device=inference_device, **evaluate_config.model_dump(), condition_on_text_encodings=condition_on_text_encodings, cond_scale=cond_scale)
                 if is_master:
                     tracker.log(evaluation, step=step())
             next_task = 'sample'
@@ -548,7 +548,7 @@ def create_tracker(accelerator: Accelerator, config: TrainDecoderConfig, config_
     accelerator.wait_for_everyone()  # If nodes arrive at this point at different times they might try to autoresume the current run which makes no sense and will cause errors
     tracker: Tracker = tracker_config.create(config, accelerator_config, dummy_mode=dummy)
     tracker.save_config(config_path, config_name='decoder_config.json')
-    tracker.add_save_metadata(state_dict_key='config', metadata=config.dict())
+    tracker.add_save_metadata(state_dict_key='config', metadata=config.model_dump())
     return tracker
     
 def initialize_training(config: TrainDecoderConfig, config_path):
@@ -585,7 +585,7 @@ def initialize_training(config: TrainDecoderConfig, config_path):
         val_prop = config.data.splits.val,
         test_prop = config.data.splits.test,
         n_sample_images=config.train.n_sample_images,
-        **config.data.dict(),
+        **config.data.model_dump(),
         rank = rank,
         seed = config.seed,
     )
@@ -636,7 +636,7 @@ def initialize_training(config: TrainDecoderConfig, config_path):
         inference_device=accelerator.device,
         evaluate_config=config.evaluate,
         condition_on_text_encodings=conditioning_on_text,
-        **config.train.dict(),
+        **config.train.model_dump(),
     )
     
 # Create a simple click command line interface to load the config and start the training