Fix pi0 checkpoint state map (#1415)

Co-authored-by: Michel Aractingi <michel.aractingi@huggingface.co>

src/lerobot/policies/pretrained.py

@@ -30,6 +30,7 @@ from torch import Tensor, nn
 
 from lerobot.configs.policies import PreTrainedConfig
 from lerobot.configs.train import TrainPipelineConfig
+from lerobot.policies.utils import log_model_loading_keys
 from lerobot.utils.hub import HubMixin
 
 T = TypeVar("T", bound="PreTrainedPolicy")
@@ -128,18 +129,26 @@ class PreTrainedPolicy(nn.Module, HubMixin, abc.ABC):
 
     @classmethod
     def _load_as_safetensor(cls, model: T, model_file: str, map_location: str, strict: bool) -> T:
-        if packaging.version.parse(safetensors.__version__) < packaging.version.parse("0.4.3"):
-            load_model_as_safetensor(model, model_file, strict=strict)
-            if map_location != "cpu":
-                logging.warning(
-                    "Loading model weights on other devices than 'cpu' is not supported natively in your version of safetensors."
-                    " This means that the model is loaded on 'cpu' first and then copied to the device."
-                    " This leads to a slower loading time."
-                    " Please update safetensors to version 0.4.3 or above for improved performance."
-                )
-                model.to(map_location)
-        else:
-            safetensors.torch.load_model(model, model_file, strict=strict, device=map_location)
+        # Create base kwargs
+        kwargs = {"strict": strict}
+
+        # Add device parameter for newer versions that support it
+        if packaging.version.parse(safetensors.__version__) >= packaging.version.parse("0.4.3"):
+            kwargs["device"] = map_location
+
+        # Load the model with appropriate kwargs
+        missing_keys, unexpected_keys = load_model_as_safetensor(model, model_file, **kwargs)
+        log_model_loading_keys(missing_keys, unexpected_keys)
+
+        # For older versions, manually move to device if needed
+        if "device" not in kwargs and map_location != "cpu":
+            logging.warning(
+                "Loading model weights on other devices than 'cpu' is not supported natively in your version of safetensors."
+                " This means that the model is loaded on 'cpu' first and then copied to the device."
+                " This leads to a slower loading time."
+                " Please update safetensors to version 0.4.3 or above for improved performance."
+            )
+            model.to(map_location)
         return model
 
     @abc.abstractmethod