diff --git a/README.md b/README.md
index d0e8508602..bb3b596da9 100644
--- a/README.md
+++ b/README.md
@@ -200,7 +200,7 @@ See [OBB Docs](https://docs.ultralytics.com/tasks/obb/) for usage examples with
 | [YOLOv8l-obb](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8l-obb.pt) | 1024                  | 80.7               | 1278.42                        | 11.83                               | 44.5               | 433.8             |
 | [YOLOv8x-obb](https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8x-obb.pt) | 1024                  | 81.36              | 1759.10                        | 13.23                               | 69.5               | 676.7             |
 
-- **mAP<sup>test</sup>** values are for single-model multi-scale on [DOTAv1](https://captain-whu.github.io/DOTA/index.html) dataset. <br>Reproduce by `yolo val obb data=DOTAv1.yaml device=0 split=test` and submit merged results to [DOTA evaluation](https://captain-whu.github.io/DOTA/evaluation.html).
+- **mAP<sup>test</sup>** values are for single-model multiscale on [DOTAv1](https://captain-whu.github.io/DOTA/index.html) dataset. <br>Reproduce by `yolo val obb data=DOTAv1.yaml device=0 split=test` and submit merged results to [DOTA evaluation](https://captain-whu.github.io/DOTA/evaluation.html).
 - **Speed** averaged over DOTAv1 val images using an [Amazon EC2 P4d](https://aws.amazon.com/ec2/instance-types/p4/) instance. <br>Reproduce by `yolo val obb data=DOTAv1.yaml batch=1 device=0|cpu`
 
 </details>
diff --git a/docs/en/datasets/obb/dota-v2.md b/docs/en/datasets/obb/dota-v2.md
index 403bae95dd..51502d7837 100644
--- a/docs/en/datasets/obb/dota-v2.md
+++ b/docs/en/datasets/obb/dota-v2.md
@@ -81,14 +81,14 @@ To train DOTA dataset, we split original DOTA images with high-resolution into i
         split_trainval(
             data_root='path/to/DOTAv1.0/',
             save_dir='path/to/DOTAv1.0-split/',
-            rates=[0.5, 1.0, 1.5],    # multi-scale
+            rates=[0.5, 1.0, 1.5],    # multiscale
             gap=500
         )
         # split test set, without labels.
         split_test(
             data_root='path/to/DOTAv1.0/',
             save_dir='path/to/DOTAv1.0-split/',
-            rates=[0.5, 1.0, 1.5],    # multi-scale
+            rates=[0.5, 1.0, 1.5],    # multiscale
             gap=500
         )
         ```
diff --git a/ultralytics/__init__.py b/ultralytics/__init__.py
index ff0298a139..a7278b8723 100644
--- a/ultralytics/__init__.py
+++ b/ultralytics/__init__.py
@@ -1,6 +1,6 @@
 # Ultralytics YOLO 🚀, AGPL-3.0 license
 
-__version__ = "8.1.24"
+__version__ = "8.1.25"
 
 from ultralytics.data.explorer.explorer import Explorer
 from ultralytics.models import RTDETR, SAM, YOLO, YOLOWorld
diff --git a/ultralytics/cfg/default.yaml b/ultralytics/cfg/default.yaml
index 1c1d086d97..5ddd257322 100644
--- a/ultralytics/cfg/default.yaml
+++ b/ultralytics/cfg/default.yaml
@@ -34,7 +34,7 @@ amp: True # (bool) Automatic Mixed Precision (AMP) training, choices=[True, Fals
 fraction: 1.0 # (float) dataset fraction to train on (default is 1.0, all images in train set)
 profile: False # (bool) profile ONNX and TensorRT speeds during training for loggers
 freeze: None # (int | list, optional) freeze first n layers, or freeze list of layer indices during training
-multi_scale: False # (bool) Whether to use multi-scale during training
+multi_scale: False # (bool) Whether to use multiscale during training
 # Segmentation
 overlap_mask: True # (bool) masks should overlap during training (segment train only)
 mask_ratio: 4 # (int) mask downsample ratio (segment train only)
diff --git a/ultralytics/engine/model.py b/ultralytics/engine/model.py
index dd000cf12b..9debfe197a 100644
--- a/ultralytics/engine/model.py
+++ b/ultralytics/engine/model.py
@@ -161,7 +161,7 @@ class Model(nn.Module):
                 Defaults to None.
             stream (bool, optional): If True, treats the input source as a continuous stream for predictions.
                 Defaults to False.
-            **kwargs (dict): Additional keyword arguments for configuring the prediction process.
+            **kwargs (any): Additional keyword arguments for configuring the prediction process.
 
         Returns:
             (List[ultralytics.engine.results.Results]): A list of prediction results, encapsulated in the Results class.
@@ -368,7 +368,7 @@ class Model(nn.Module):
             source (str | int | PIL.Image | np.ndarray): The source of the image for generating embeddings.
                 The source can be a file path, URL, PIL image, numpy array, etc. Defaults to None.
             stream (bool): If True, predictions are streamed. Defaults to False.
-            **kwargs (dict): Additional keyword arguments for configuring the embedding process.
+            **kwargs (any): Additional keyword arguments for configuring the embedding process.
 
         Returns:
             (List[torch.Tensor]): A list containing the image embeddings.
@@ -406,7 +406,7 @@ class Model(nn.Module):
             stream (bool, optional): Treats the input source as a continuous stream for predictions. Defaults to False.
             predictor (BasePredictor, optional): An instance of a custom predictor class for making predictions.
                 If None, the method uses a default predictor. Defaults to None.
-            **kwargs (dict): Additional keyword arguments for configuring the prediction process. These arguments allow
+            **kwargs (any): Additional keyword arguments for configuring the prediction process. These arguments allow
                 for further customization of the prediction behavior.
 
         Returns:
@@ -460,7 +460,7 @@ class Model(nn.Module):
             source (str, optional): The input source for object tracking. It can be a file path, URL, or video stream.
             stream (bool, optional): Treats the input source as a continuous video stream. Defaults to False.
             persist (bool, optional): Persists the trackers between different calls to this method. Defaults to False.
-            **kwargs (dict): Additional keyword arguments for configuring the tracking process. These arguments allow
+            **kwargs (any): Additional keyword arguments for configuring the tracking process. These arguments allow
                 for further customization of the tracking behavior.
 
         Returns:
@@ -497,7 +497,7 @@ class Model(nn.Module):
         Args:
             validator (BaseValidator, optional): An instance of a custom validator class for validating the model. If
                 None, the method uses a default validator. Defaults to None.
-            **kwargs (dict): Arbitrary keyword arguments representing the validation configuration. These arguments are
+            **kwargs (any): Arbitrary keyword arguments representing the validation configuration. These arguments are
                 used to customize various aspects of the validation process.
 
         Returns:
@@ -531,7 +531,7 @@ class Model(nn.Module):
         configurable options, users should refer to the 'configuration' section in the documentation.
 
         Args:
-            **kwargs (dict): Arbitrary keyword arguments to customize the benchmarking process. These are combined with
+            **kwargs (any): Arbitrary keyword arguments to customize the benchmarking process. These are combined with
                 default configurations, model-specific arguments, and method defaults.
 
         Returns:
@@ -570,7 +570,7 @@ class Model(nn.Module):
         possible arguments, refer to the 'configuration' section in the documentation.
 
         Args:
-            **kwargs (dict): Arbitrary keyword arguments to customize the export process. These are combined with the
+            **kwargs (any): Arbitrary keyword arguments to customize the export process. These are combined with the
                 model's overrides and method defaults.
 
         Returns:
@@ -607,7 +607,7 @@ class Model(nn.Module):
         Args:
             trainer (BaseTrainer, optional): An instance of a custom trainer class for training the model. If None, the
                 method uses a default trainer. Defaults to None.
-            **kwargs (dict): Arbitrary keyword arguments representing the training configuration. These arguments are
+            **kwargs (any): Arbitrary keyword arguments representing the training configuration. These arguments are
                 used to customize various aspects of the training process.
 
         Returns:
@@ -679,7 +679,7 @@ class Model(nn.Module):
             use_ray (bool): If True, uses Ray Tune for hyperparameter tuning. Defaults to False.
             iterations (int): The number of tuning iterations to perform. Defaults to 10.
             *args (list): Variable length argument list for additional arguments.
-            **kwargs (dict): Arbitrary keyword arguments. These are combined with the model's overrides and defaults.
+            **kwargs (any): Arbitrary keyword arguments. These are combined with the model's overrides and defaults.
 
         Returns:
             (dict): A dictionary containing the results of the hyperparameter search.
diff --git a/ultralytics/engine/trainer.py b/ultralytics/engine/trainer.py
index 6db3eb1811..29d6f1d02f 100644
--- a/ultralytics/engine/trainer.py
+++ b/ultralytics/engine/trainer.py
@@ -280,7 +280,7 @@ class BaseTrainer:
         # Check imgsz
         gs = max(int(self.model.stride.max() if hasattr(self.model, "stride") else 32), 32)  # grid size (max stride)
         self.args.imgsz = check_imgsz(self.args.imgsz, stride=gs, floor=gs, max_dim=1)
-        self.stride = gs  # for multi-scale training
+        self.stride = gs  # for multiscale training
 
         # Batch size
         if self.batch_size == -1 and RANK == -1:  # single-GPU only, estimate best batch size
diff --git a/ultralytics/hub/utils.py b/ultralytics/hub/utils.py
index e870fadac5..5c0007624a 100644
--- a/ultralytics/hub/utils.py
+++ b/ultralytics/hub/utils.py
@@ -84,7 +84,7 @@ def requests_with_progress(method, url, **kwargs):
     Args:
         method (str): The HTTP method to use (e.g. 'GET', 'POST').
         url (str): The URL to send the request to.
-        **kwargs (dict): Additional keyword arguments to pass to the underlying `requests.request` function.
+        **kwargs (any): Additional keyword arguments to pass to the underlying `requests.request` function.
 
     Returns:
         (requests.Response): The response object from the HTTP request.
@@ -122,7 +122,7 @@ def smart_request(method, url, retry=3, timeout=30, thread=True, code=-1, verbos
         code (int, optional): An identifier for the request, used for logging purposes. Default is -1.
         verbose (bool, optional): A flag to determine whether to print out to console or not. Default is True.
         progress (bool, optional): Whether to show a progress bar during the request. Default is False.
-        **kwargs (dict): Keyword arguments to be passed to the requests function specified in method.
+        **kwargs (any): Keyword arguments to be passed to the requests function specified in method.
 
     Returns:
         (requests.Response): The HTTP response object. If the request is executed in a separate thread, returns None.
diff --git a/ultralytics/nn/modules/transformer.py b/ultralytics/nn/modules/transformer.py
index 494c431aee..062c6094ea 100644
--- a/ultralytics/nn/modules/transformer.py
+++ b/ultralytics/nn/modules/transformer.py
@@ -215,7 +215,7 @@ class LayerNorm2d(nn.Module):
 
 class MSDeformAttn(nn.Module):
     """
-    Multi-Scale Deformable Attention Module based on Deformable-DETR and PaddleDetection implementations.
+    Multiscale Deformable Attention Module based on Deformable-DETR and PaddleDetection implementations.
 
     https://github.com/fundamentalvision/Deformable-DETR/blob/main/models/ops/modules/ms_deform_attn.py
     """
diff --git a/ultralytics/nn/modules/utils.py b/ultralytics/nn/modules/utils.py
index 75a050df1b..1512967340 100644
--- a/ultralytics/nn/modules/utils.py
+++ b/ultralytics/nn/modules/utils.py
@@ -46,7 +46,7 @@ def multi_scale_deformable_attn_pytorch(
     attention_weights: torch.Tensor,
 ) -> torch.Tensor:
     """
-    Multi-scale deformable attention.
+    Multiscale deformable attention.
 
     https://github.com/IDEA-Research/detrex/blob/main/detrex/layers/multi_scale_deform_attn.py
     """
diff --git a/ultralytics/utils/__init__.py b/ultralytics/utils/__init__.py
index 4d1e952109..befa081f88 100644
--- a/ultralytics/utils/__init__.py
+++ b/ultralytics/utils/__init__.py
@@ -113,7 +113,7 @@ class TQDM(tqdm_original):
 
     Args:
         *args (list): Positional arguments passed to original tqdm.
-        **kwargs (dict): Keyword arguments, with custom defaults applied.
+        **kwargs (any): Keyword arguments, with custom defaults applied.
     """
 
     def __init__(self, *args, **kwargs):
diff --git a/ultralytics/utils/downloads.py b/ultralytics/utils/downloads.py
index f02e44c4e2..f55d8af775 100644
--- a/ultralytics/utils/downloads.py
+++ b/ultralytics/utils/downloads.py
@@ -410,7 +410,7 @@ def attempt_download_asset(file, repo="ultralytics/assets", release="v8.1.0", **
         file (str | Path): The filename or file path to be downloaded.
         repo (str, optional): The GitHub repository in the format 'owner/repo'. Defaults to 'ultralytics/assets'.
         release (str, optional): The specific release version to be downloaded. Defaults to 'v8.1.0'.
-        **kwargs (dict): Additional keyword arguments for the download process.
+        **kwargs (any): Additional keyword arguments for the download process.
 
     Returns:
         (str): The path to the downloaded file.
diff --git a/ultralytics/utils/patches.py b/ultralytics/utils/patches.py
index acbf5a99f8..d438407114 100644
--- a/ultralytics/utils/patches.py
+++ b/ultralytics/utils/patches.py
@@ -68,7 +68,7 @@ def torch_save(*args, use_dill=True, **kwargs):
     Args:
         *args (tuple): Positional arguments to pass to torch.save.
         use_dill (bool): Whether to try using dill for serialization if available. Defaults to True.
-        **kwargs (dict): Keyword arguments to pass to torch.save.
+        **kwargs (any): Keyword arguments to pass to torch.save.
     """
     try:
         assert use_dill