diff --git a/.github/workflows/greetings.yml b/.github/workflows/greetings.yml
index 271ee36c..ea9d0bcb 100644
--- a/.github/workflows/greetings.yml
+++ b/.github/workflows/greetings.yml
@@ -52,4 +52,4 @@ jobs:
 
             <a href="https://github.com/ultralytics/ultralytics/actions/workflows/ci.yaml?query=event%3Aschedule"><img src="https://github.com/ultralytics/ultralytics/actions/workflows/ci.yaml/badge.svg" alt="Ultralytics CI"></a>
 
-            If this badge is green, all [Ultralytics CI](https://github.com/ultralytics/ultralytics/actions/workflows/ci.yaml?query=event%3Aschedule) tests are currently passing. CI tests verify correct operation of all YOLOv8 modes and tasks on macOS, Windows, and Ubuntu every 24 hours and on every commit.
+            If this badge is green, all [Ultralytics CI](https://github.com/ultralytics/ultralytics/actions/workflows/ci.yaml?query=event%3Aschedule) tests are currently passing. CI tests verify correct operation of all YOLOv8 [Modes](https://docs.ultralytics.com/modes/) and [Tasks](https://docs.ultralytics.com/tasks/) on macOS, Windows, and Ubuntu every 24 hours and on every commit.
diff --git a/docs/tasks/classify.md b/docs/tasks/classify.md
index 9c25a4bb..73a4ae95 100644
--- a/docs/tasks/classify.md
+++ b/docs/tasks/classify.md
@@ -26,16 +26,25 @@ see the [Configuration](../usage/cfg.md) page.
         from ultralytics import YOLO
         
         # Load a model
-        model = YOLO('yolov8n-cls.yaml')  # build a new model from scratch
+        model = YOLO('yolov8n-cls.yaml')  # build a new model from YAML
         model = YOLO('yolov8n-cls.pt')  # load a pretrained model (recommended for training)
+        model = YOLO('yolov8n-cls.yaml').load('yolov8n-cls.pt')  # build from YAML and transfer weights
         
         # Train the model
         model.train(data='mnist160', epochs=100, imgsz=64)
         ```
+
     === "CLI"
-    
+
         ```bash
+        # Build a new model from YAML and start training from scratch
+        yolo classify train data=mnist160 model=yolov8n-cls.yaml epochs=100 imgsz=64
+
+        # Start training from a pretrained *.pt model
         yolo classify train data=mnist160 model=yolov8n-cls.pt epochs=100 imgsz=64
+
+        # Build a new model from YAML, transfer pretrained weights to it and start training
+        yolo classify train data=mnist160 model=yolov8n-cls.yaml pretrained=yolov8n-cls.pt epochs=100 imgsz=64
         ```
 
 ## Val
diff --git a/docs/tasks/detect.md b/docs/tasks/detect.md
index cf13b232..72020104 100644
--- a/docs/tasks/detect.md
+++ b/docs/tasks/detect.md
@@ -26,8 +26,9 @@ the [Configuration](../usage/cfg.md) page.
         from ultralytics import YOLO
         
         # Load a model
-        model = YOLO('yolov8n.yaml')  # build a new model from scratch
+        model = YOLO('yolov8n.yaml')  # build a new model from YAML
         model = YOLO('yolov8n.pt')  # load a pretrained model (recommended for training)
+        model = YOLO('yolov8n.yaml').load('yolov8n.pt')  # build from YAML and transfer weights
         
         # Train the model
         model.train(data='coco128.yaml', epochs=100, imgsz=640)
@@ -35,7 +36,14 @@ the [Configuration](../usage/cfg.md) page.
     === "CLI"
     
         ```bash
+        # Build a new model from YAML and start training from scratch
+        yolo detect train data=coco128.yaml model=yolov8n.yaml epochs=100 imgsz=640
+
+        # Start training from a pretrained *.pt model
         yolo detect train data=coco128.yaml model=yolov8n.pt epochs=100 imgsz=640
+
+        # Build a new model from YAML, transfer pretrained weights to it and start training
+        yolo detect train data=coco128.yaml model=yolov8n.yaml pretrained=yolov8n.pt epochs=100 imgsz=640
         ```
 
 ## Val
diff --git a/docs/tasks/keypoints.md b/docs/tasks/keypoints.md
index 60a688f0..d9f24846 100644
--- a/docs/tasks/keypoints.md
+++ b/docs/tasks/keypoints.md
@@ -28,8 +28,9 @@ train an OpenPose model on a custom dataset, see the OpenPose Training page.
         from ultralytics import YOLO
         
         # Load a model
-        model = YOLO('yolov8n.yaml')  # build a new model from scratch
+        model = YOLO('yolov8n.yaml')  # build a new model from YAML
         model = YOLO('yolov8n.pt')  # load a pretrained model (recommended for training)
+        model = YOLO('yolov8n.yaml').load('yolov8n.pt')  # build from YAML and transfer weights
         
         # Train the model
         model.train(data='coco128.yaml', epochs=100, imgsz=640)
@@ -37,7 +38,14 @@ train an OpenPose model on a custom dataset, see the OpenPose Training page.
     === "CLI"
     
         ```bash
+        # Build a new model from YAML and start training from scratch
+        yolo detect train data=coco128.yaml model=yolov8n.yaml epochs=100 imgsz=640
+
+        # Start training from a pretrained *.pt model
         yolo detect train data=coco128.yaml model=yolov8n.pt epochs=100 imgsz=640
+
+        # Build a new model from YAML, transfer pretrained weights to it and start training
+        yolo detect train data=coco128.yaml model=yolov8n.yaml pretrained=yolov8n.pt epochs=100 imgsz=640
         ```
 
 ## Val TODO
diff --git a/docs/tasks/segment.md b/docs/tasks/segment.md
index f89c3feb..c8391a1d 100644
--- a/docs/tasks/segment.md
+++ b/docs/tasks/segment.md
@@ -26,8 +26,9 @@ arguments see the [Configuration](../usage/cfg.md) page.
         from ultralytics import YOLO
         
         # Load a model
-        model = YOLO('yolov8n-seg.yaml')  # build a new model from scratch
+        model = YOLO('yolov8n-seg.yaml')  # build a new model from YAML
         model = YOLO('yolov8n-seg.pt')  # load a pretrained model (recommended for training)
+        model = YOLO('yolov8n-seg.yaml').load('yolov8n.pt')  # build from YAML and transfer weights
         
         # Train the model
         model.train(data='coco128-seg.yaml', epochs=100, imgsz=640)
@@ -35,7 +36,14 @@ arguments see the [Configuration](../usage/cfg.md) page.
     === "CLI"
     
         ```bash
+        # Build a new model from YAML and start training from scratch
+        yolo segment train data=coco128-seg.yaml model=yolov8n-seg.yaml epochs=100 imgsz=640
+
+        # Start training from a pretrained *.pt model
         yolo segment train data=coco128-seg.yaml model=yolov8n-seg.pt epochs=100 imgsz=640
+
+        # Build a new model from YAML, transfer pretrained weights to it and start training
+        yolo segment train data=coco128-seg.yaml model=yolov8n-seg.yaml pretrained=yolov8n-seg.pt epochs=100 imgsz=640
         ```
 
 ## Val
diff --git a/docs/usage/cfg.md b/docs/usage/cfg.md
index 763b8921..df6fbceb 100644
--- a/docs/usage/cfg.md
+++ b/docs/usage/cfg.md
@@ -143,7 +143,7 @@ given task.
 | `agnostic_nms`   | `False`                | class-agnostic NMS                                       |
 | `retina_masks`   | `False`                | use high-resolution segmentation masks                   |
 | `classes`        | `None`                 | filter results by class, i.e. class=0, or class=[0,2,3]  |
-| `box`            | `True`                 | Show boxes in segmentation predictions                   |
+| `boxes`          | `True`                 | Show boxes in segmentation predictions                   |
 
 ### Validation
 
diff --git a/tests/test_engine.py b/tests/test_engine.py
index e842bddb..c20edc10 100644
--- a/tests/test_engine.py
+++ b/tests/test_engine.py
@@ -74,16 +74,9 @@ def test_segment():
 
 
 def test_classify():
-    overrides = {
-        'data': 'imagenet10',
-        'model': 'yolov8n-cls.yaml',
-        'imgsz': 32,
-        'epochs': 1,
-        'batch': 64,
-        'save': False}
+    overrides = {'data': 'imagenet10', 'model': 'yolov8n-cls.yaml', 'imgsz': 32, 'epochs': 1, 'save': False}
     CFG.data = 'imagenet10'
     CFG.imgsz = 32
-    CFG.batch = 64
     # YOLO(CFG_SEG).train(**overrides)  # works
 
     # Trainer
diff --git a/ultralytics/__init__.py b/ultralytics/__init__.py
index aceaf5df..45ce04cc 100644
--- a/ultralytics/__init__.py
+++ b/ultralytics/__init__.py
@@ -1,6 +1,6 @@
 # Ultralytics YOLO 🚀, GPL-3.0 license
 
-__version__ = '8.0.54'
+__version__ = '8.0.55'
 
 from ultralytics.yolo.engine.model import YOLO
 from ultralytics.yolo.utils.checks import check_yolo as checks
diff --git a/ultralytics/models/v3/yolov3-sppu.yaml b/ultralytics/models/v3/yolov3-spp.yaml
similarity index 100%
rename from ultralytics/models/v3/yolov3-sppu.yaml
rename to ultralytics/models/v3/yolov3-spp.yaml
diff --git a/ultralytics/models/v3/yolov3-tinyu.yaml b/ultralytics/models/v3/yolov3-tiny.yaml
similarity index 100%
rename from ultralytics/models/v3/yolov3-tinyu.yaml
rename to ultralytics/models/v3/yolov3-tiny.yaml
diff --git a/ultralytics/models/v3/yolov3u.yaml b/ultralytics/models/v3/yolov3.yaml
similarity index 100%
rename from ultralytics/models/v3/yolov3u.yaml
rename to ultralytics/models/v3/yolov3.yaml
diff --git a/ultralytics/models/v5/yolov5l6u.yaml b/ultralytics/models/v5/yolov5-p6.yaml
similarity index 85%
rename from ultralytics/models/v5/yolov5l6u.yaml
rename to ultralytics/models/v5/yolov5-p6.yaml
index 76da02ac..ce9d3544 100644
--- a/ultralytics/models/v5/yolov5l6u.yaml
+++ b/ultralytics/models/v5/yolov5-p6.yaml
@@ -2,8 +2,13 @@
 
 # Parameters
 nc: 80  # number of classes
-depth_multiple: 1.0  # model depth multiple
-width_multiple: 1.0  # layer channel multiple
+scales: # model compound scaling constants, i.e. 'model=yolov5n-p6.yaml' will call yolov5-p6.yaml with scale 'n'
+  # [depth, width, max_channels]
+  n: [0.33, 0.25, 1024]
+  s: [0.33, 0.50, 1024]
+  m: [0.67, 0.75, 1024]
+  l: [1.00, 1.00, 1024]
+  x: [1.33, 1.25, 1024]
 
 # YOLOv5 v6.0 backbone
 backbone:
diff --git a/ultralytics/models/v5/yolov5su.yaml b/ultralytics/models/v5/yolov5.yaml
similarity index 81%
rename from ultralytics/models/v5/yolov5su.yaml
rename to ultralytics/models/v5/yolov5.yaml
index 8cd3c5b9..c9d6f3e1 100644
--- a/ultralytics/models/v5/yolov5su.yaml
+++ b/ultralytics/models/v5/yolov5.yaml
@@ -2,8 +2,13 @@
 
 # Parameters
 nc: 80  # number of classes
-depth_multiple: 0.33  # model depth multiple
-width_multiple: 0.50  # layer channel multiple
+scales: # model compound scaling constants, i.e. 'model=yolov5n.yaml' will call yolov5.yaml with scale 'n'
+  # [depth, width, max_channels]
+  n: [0.33, 0.25, 1024]
+  s: [0.33, 0.50, 1024]
+  m: [0.67, 0.75, 1024]
+  l: [1.00, 1.00, 1024]
+  x: [1.33, 1.25, 1024]
 
 # YOLOv5 v6.0 backbone
 backbone:
diff --git a/ultralytics/models/v5/yolov5lu.yaml b/ultralytics/models/v5/yolov5lu.yaml
deleted file mode 100644
index dc3e4b36..00000000
--- a/ultralytics/models/v5/yolov5lu.yaml
+++ /dev/null
@@ -1,44 +0,0 @@
-# Ultralytics YOLO 🚀, GPL-3.0 license
-
-# Parameters
-nc: 80  # number of classes
-depth_multiple: 1.0  # model depth multiple
-width_multiple: 1.0  # layer channel multiple
-
-# YOLOv5 v6.0 backbone
-backbone:
-  # [from, number, module, args]
-  [[-1, 1, Conv, [64, 6, 2, 2]],  # 0-P1/2
-   [-1, 1, Conv, [128, 3, 2]],  # 1-P2/4
-   [-1, 3, C3, [128]],
-   [-1, 1, Conv, [256, 3, 2]],  # 3-P3/8
-   [-1, 6, C3, [256]],
-   [-1, 1, Conv, [512, 3, 2]],  # 5-P4/16
-   [-1, 9, C3, [512]],
-   [-1, 1, Conv, [1024, 3, 2]],  # 7-P5/32
-   [-1, 3, C3, [1024]],
-   [-1, 1, SPPF, [1024, 5]],  # 9
-  ]
-
-# YOLOv5 v6.0 head
-head:
-  [[-1, 1, Conv, [512, 1, 1]],
-   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
-   [[-1, 6], 1, Concat, [1]],  # cat backbone P4
-   [-1, 3, C3, [512, False]],  # 13
-
-   [-1, 1, Conv, [256, 1, 1]],
-   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
-   [[-1, 4], 1, Concat, [1]],  # cat backbone P3
-   [-1, 3, C3, [256, False]],  # 17 (P3/8-small)
-
-   [-1, 1, Conv, [256, 3, 2]],
-   [[-1, 14], 1, Concat, [1]],  # cat head P4
-   [-1, 3, C3, [512, False]],  # 20 (P4/16-medium)
-
-   [-1, 1, Conv, [512, 3, 2]],
-   [[-1, 10], 1, Concat, [1]],  # cat head P5
-   [-1, 3, C3, [1024, False]],  # 23 (P5/32-large)
-
-   [[17, 20, 23], 1, Detect, [nc]],  # Detect(P3, P4, P5)
-  ]
diff --git a/ultralytics/models/v5/yolov5m6u.yaml b/ultralytics/models/v5/yolov5m6u.yaml
deleted file mode 100644
index 84274ea0..00000000
--- a/ultralytics/models/v5/yolov5m6u.yaml
+++ /dev/null
@@ -1,55 +0,0 @@
-# Ultralytics YOLO 🚀, GPL-3.0 license
-
-# Parameters
-nc: 80  # number of classes
-depth_multiple: 0.67  # model depth multiple
-width_multiple: 0.75  # layer channel multiple
-
-# YOLOv5 v6.0 backbone
-backbone:
-  # [from, number, module, args]
-  [[-1, 1, Conv, [64, 6, 2, 2]],  # 0-P1/2
-   [-1, 1, Conv, [128, 3, 2]],  # 1-P2/4
-   [-1, 3, C3, [128]],
-   [-1, 1, Conv, [256, 3, 2]],  # 3-P3/8
-   [-1, 6, C3, [256]],
-   [-1, 1, Conv, [512, 3, 2]],  # 5-P4/16
-   [-1, 9, C3, [512]],
-   [-1, 1, Conv, [768, 3, 2]],  # 7-P5/32
-   [-1, 3, C3, [768]],
-   [-1, 1, Conv, [1024, 3, 2]],  # 9-P6/64
-   [-1, 3, C3, [1024]],
-   [-1, 1, SPPF, [1024, 5]],  # 11
-  ]
-
-# YOLOv5 v6.0 head
-head:
-  [[-1, 1, Conv, [768, 1, 1]],
-   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
-   [[-1, 8], 1, Concat, [1]],  # cat backbone P5
-   [-1, 3, C3, [768, False]],  # 15
-
-   [-1, 1, Conv, [512, 1, 1]],
-   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
-   [[-1, 6], 1, Concat, [1]],  # cat backbone P4
-   [-1, 3, C3, [512, False]],  # 19
-
-   [-1, 1, Conv, [256, 1, 1]],
-   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
-   [[-1, 4], 1, Concat, [1]],  # cat backbone P3
-   [-1, 3, C3, [256, False]],  # 23 (P3/8-small)
-
-   [-1, 1, Conv, [256, 3, 2]],
-   [[-1, 20], 1, Concat, [1]],  # cat head P4
-   [-1, 3, C3, [512, False]],  # 26 (P4/16-medium)
-
-   [-1, 1, Conv, [512, 3, 2]],
-   [[-1, 16], 1, Concat, [1]],  # cat head P5
-   [-1, 3, C3, [768, False]],  # 29 (P5/32-large)
-
-   [-1, 1, Conv, [768, 3, 2]],
-   [[-1, 12], 1, Concat, [1]],  # cat head P6
-   [-1, 3, C3, [1024, False]],  # 32 (P6/64-xlarge)
-
-   [[23, 26, 29, 32], 1, Detect, [nc]],  # Detect(P3, P4, P5, P6)
-  ]
diff --git a/ultralytics/models/v5/yolov5mu.yaml b/ultralytics/models/v5/yolov5mu.yaml
deleted file mode 100644
index 3703a1bb..00000000
--- a/ultralytics/models/v5/yolov5mu.yaml
+++ /dev/null
@@ -1,44 +0,0 @@
-# Ultralytics YOLO 🚀, GPL-3.0 license
-
-# Parameters
-nc: 80  # number of classes
-depth_multiple: 0.67  # model depth multiple
-width_multiple: 0.75  # layer channel multiple
-
-# YOLOv5 v6.0 backbone
-backbone:
-  # [from, number, module, args]
-  [[-1, 1, Conv, [64, 6, 2, 2]],  # 0-P1/2
-   [-1, 1, Conv, [128, 3, 2]],  # 1-P2/4
-   [-1, 3, C3, [128]],
-   [-1, 1, Conv, [256, 3, 2]],  # 3-P3/8
-   [-1, 6, C3, [256]],
-   [-1, 1, Conv, [512, 3, 2]],  # 5-P4/16
-   [-1, 9, C3, [512]],
-   [-1, 1, Conv, [1024, 3, 2]],  # 7-P5/32
-   [-1, 3, C3, [1024]],
-   [-1, 1, SPPF, [1024, 5]],  # 9
-  ]
-
-# YOLOv5 v6.0 head
-head:
-  [[-1, 1, Conv, [512, 1, 1]],
-   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
-   [[-1, 6], 1, Concat, [1]],  # cat backbone P4
-   [-1, 3, C3, [512, False]],  # 13
-
-   [-1, 1, Conv, [256, 1, 1]],
-   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
-   [[-1, 4], 1, Concat, [1]],  # cat backbone P3
-   [-1, 3, C3, [256, False]],  # 17 (P3/8-small)
-
-   [-1, 1, Conv, [256, 3, 2]],
-   [[-1, 14], 1, Concat, [1]],  # cat head P4
-   [-1, 3, C3, [512, False]],  # 20 (P4/16-medium)
-
-   [-1, 1, Conv, [512, 3, 2]],
-   [[-1, 10], 1, Concat, [1]],  # cat head P5
-   [-1, 3, C3, [1024, False]],  # 23 (P5/32-large)
-
-   [[17, 20, 23], 1, Detect, [nc]],  # Detect(P3, P4, P5)
-  ]
diff --git a/ultralytics/models/v5/yolov5n6u.yaml b/ultralytics/models/v5/yolov5n6u.yaml
deleted file mode 100644
index 5776879d..00000000
--- a/ultralytics/models/v5/yolov5n6u.yaml
+++ /dev/null
@@ -1,55 +0,0 @@
-# Ultralytics YOLO 🚀, GPL-3.0 license
-
-# Parameters
-nc: 80  # number of classes
-depth_multiple: 0.33  # model depth multiple
-width_multiple: 0.25  # layer channel multiple
-
-# YOLOv5 v6.0 backbone
-backbone:
-  # [from, number, module, args]
-  [[-1, 1, Conv, [64, 6, 2, 2]],  # 0-P1/2
-   [-1, 1, Conv, [128, 3, 2]],  # 1-P2/4
-   [-1, 3, C3, [128]],
-   [-1, 1, Conv, [256, 3, 2]],  # 3-P3/8
-   [-1, 6, C3, [256]],
-   [-1, 1, Conv, [512, 3, 2]],  # 5-P4/16
-   [-1, 9, C3, [512]],
-   [-1, 1, Conv, [768, 3, 2]],  # 7-P5/32
-   [-1, 3, C3, [768]],
-   [-1, 1, Conv, [1024, 3, 2]],  # 9-P6/64
-   [-1, 3, C3, [1024]],
-   [-1, 1, SPPF, [1024, 5]],  # 11
-  ]
-
-# YOLOv5 v6.0 head
-head:
-  [[-1, 1, Conv, [768, 1, 1]],
-   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
-   [[-1, 8], 1, Concat, [1]],  # cat backbone P5
-   [-1, 3, C3, [768, False]],  # 15
-
-   [-1, 1, Conv, [512, 1, 1]],
-   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
-   [[-1, 6], 1, Concat, [1]],  # cat backbone P4
-   [-1, 3, C3, [512, False]],  # 19
-
-   [-1, 1, Conv, [256, 1, 1]],
-   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
-   [[-1, 4], 1, Concat, [1]],  # cat backbone P3
-   [-1, 3, C3, [256, False]],  # 23 (P3/8-small)
-
-   [-1, 1, Conv, [256, 3, 2]],
-   [[-1, 20], 1, Concat, [1]],  # cat head P4
-   [-1, 3, C3, [512, False]],  # 26 (P4/16-medium)
-
-   [-1, 1, Conv, [512, 3, 2]],
-   [[-1, 16], 1, Concat, [1]],  # cat head P5
-   [-1, 3, C3, [768, False]],  # 29 (P5/32-large)
-
-   [-1, 1, Conv, [768, 3, 2]],
-   [[-1, 12], 1, Concat, [1]],  # cat head P6
-   [-1, 3, C3, [1024, False]],  # 32 (P6/64-xlarge)
-
-   [[23, 26, 29, 32], 1, Detect, [nc]],  # Detect(P3, P4, P5, P6)
-  ]
diff --git a/ultralytics/models/v5/yolov5nu.yaml b/ultralytics/models/v5/yolov5nu.yaml
deleted file mode 100644
index 76489250..00000000
--- a/ultralytics/models/v5/yolov5nu.yaml
+++ /dev/null
@@ -1,44 +0,0 @@
-# Ultralytics YOLO 🚀, GPL-3.0 license
-
-# Parameters
-nc: 80  # number of classes
-depth_multiple: 0.33  # model depth multiple
-width_multiple: 0.25  # layer channel multiple
-
-# YOLOv5 v6.0 backbone
-backbone:
-  # [from, number, module, args]
-  [[-1, 1, Conv, [64, 6, 2, 2]],  # 0-P1/2
-   [-1, 1, Conv, [128, 3, 2]],  # 1-P2/4
-   [-1, 3, C3, [128]],
-   [-1, 1, Conv, [256, 3, 2]],  # 3-P3/8
-   [-1, 6, C3, [256]],
-   [-1, 1, Conv, [512, 3, 2]],  # 5-P4/16
-   [-1, 9, C3, [512]],
-   [-1, 1, Conv, [1024, 3, 2]],  # 7-P5/32
-   [-1, 3, C3, [1024]],
-   [-1, 1, SPPF, [1024, 5]],  # 9
-  ]
-
-# YOLOv5 v6.0 head
-head:
-  [[-1, 1, Conv, [512, 1, 1]],
-   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
-   [[-1, 6], 1, Concat, [1]],  # cat backbone P4
-   [-1, 3, C3, [512, False]],  # 13
-
-   [-1, 1, Conv, [256, 1, 1]],
-   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
-   [[-1, 4], 1, Concat, [1]],  # cat backbone P3
-   [-1, 3, C3, [256, False]],  # 17 (P3/8-small)
-
-   [-1, 1, Conv, [256, 3, 2]],
-   [[-1, 14], 1, Concat, [1]],  # cat head P4
-   [-1, 3, C3, [512, False]],  # 20 (P4/16-medium)
-
-   [-1, 1, Conv, [512, 3, 2]],
-   [[-1, 10], 1, Concat, [1]],  # cat head P5
-   [-1, 3, C3, [1024, False]],  # 23 (P5/32-large)
-
-   [[17, 20, 23], 1, Detect, [nc]],  # Detect(P3, P4, P5)
-  ]
diff --git a/ultralytics/models/v5/yolov5s6u.yaml b/ultralytics/models/v5/yolov5s6u.yaml
deleted file mode 100644
index 90a39c0b..00000000
--- a/ultralytics/models/v5/yolov5s6u.yaml
+++ /dev/null
@@ -1,55 +0,0 @@
-# Ultralytics YOLO 🚀, GPL-3.0 license
-
-# Parameters
-nc: 80  # number of classes
-depth_multiple: 0.33  # model depth multiple
-width_multiple: 0.50  # layer channel multiple
-
-# YOLOv5 v6.0 backbone
-backbone:
-  # [from, number, module, args]
-  [[-1, 1, Conv, [64, 6, 2, 2]],  # 0-P1/2
-   [-1, 1, Conv, [128, 3, 2]],  # 1-P2/4
-   [-1, 3, C3, [128]],
-   [-1, 1, Conv, [256, 3, 2]],  # 3-P3/8
-   [-1, 6, C3, [256]],
-   [-1, 1, Conv, [512, 3, 2]],  # 5-P4/16
-   [-1, 9, C3, [512]],
-   [-1, 1, Conv, [768, 3, 2]],  # 7-P5/32
-   [-1, 3, C3, [768]],
-   [-1, 1, Conv, [1024, 3, 2]],  # 9-P6/64
-   [-1, 3, C3, [1024]],
-   [-1, 1, SPPF, [1024, 5]],  # 11
-  ]
-
-# YOLOv5 v6.0 head
-head:
-  [[-1, 1, Conv, [768, 1, 1]],
-   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
-   [[-1, 8], 1, Concat, [1]],  # cat backbone P5
-   [-1, 3, C3, [768, False]],  # 15
-
-   [-1, 1, Conv, [512, 1, 1]],
-   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
-   [[-1, 6], 1, Concat, [1]],  # cat backbone P4
-   [-1, 3, C3, [512, False]],  # 19
-
-   [-1, 1, Conv, [256, 1, 1]],
-   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
-   [[-1, 4], 1, Concat, [1]],  # cat backbone P3
-   [-1, 3, C3, [256, False]],  # 23 (P3/8-small)
-
-   [-1, 1, Conv, [256, 3, 2]],
-   [[-1, 20], 1, Concat, [1]],  # cat head P4
-   [-1, 3, C3, [512, False]],  # 26 (P4/16-medium)
-
-   [-1, 1, Conv, [512, 3, 2]],
-   [[-1, 16], 1, Concat, [1]],  # cat head P5
-   [-1, 3, C3, [768, False]],  # 29 (P5/32-large)
-
-   [-1, 1, Conv, [768, 3, 2]],
-   [[-1, 12], 1, Concat, [1]],  # cat head P6
-   [-1, 3, C3, [1024, False]],  # 32 (P6/64-xlarge)
-
-   [[23, 26, 29, 32], 1, Detect, [nc]],  # Detect(P3, P4, P5, P6)
-  ]
diff --git a/ultralytics/models/v5/yolov5x6u.yaml b/ultralytics/models/v5/yolov5x6u.yaml
deleted file mode 100644
index 31cd9c9e..00000000
--- a/ultralytics/models/v5/yolov5x6u.yaml
+++ /dev/null
@@ -1,55 +0,0 @@
-# Ultralytics YOLO 🚀, GPL-3.0 license
-
-# Parameters
-nc: 80  # number of classes
-depth_multiple: 1.33  # model depth multiple
-width_multiple: 1.25  # layer channel multiple
-
-# YOLOv5 v6.0 backbone
-backbone:
-  # [from, number, module, args]
-  [[-1, 1, Conv, [64, 6, 2, 2]],  # 0-P1/2
-   [-1, 1, Conv, [128, 3, 2]],  # 1-P2/4
-   [-1, 3, C3, [128]],
-   [-1, 1, Conv, [256, 3, 2]],  # 3-P3/8
-   [-1, 6, C3, [256]],
-   [-1, 1, Conv, [512, 3, 2]],  # 5-P4/16
-   [-1, 9, C3, [512]],
-   [-1, 1, Conv, [768, 3, 2]],  # 7-P5/32
-   [-1, 3, C3, [768]],
-   [-1, 1, Conv, [1024, 3, 2]],  # 9-P6/64
-   [-1, 3, C3, [1024]],
-   [-1, 1, SPPF, [1024, 5]],  # 11
-  ]
-
-# YOLOv5 v6.0 head
-head:
-  [[-1, 1, Conv, [768, 1, 1]],
-   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
-   [[-1, 8], 1, Concat, [1]],  # cat backbone P5
-   [-1, 3, C3, [768, False]],  # 15
-
-   [-1, 1, Conv, [512, 1, 1]],
-   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
-   [[-1, 6], 1, Concat, [1]],  # cat backbone P4
-   [-1, 3, C3, [512, False]],  # 19
-
-   [-1, 1, Conv, [256, 1, 1]],
-   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
-   [[-1, 4], 1, Concat, [1]],  # cat backbone P3
-   [-1, 3, C3, [256, False]],  # 23 (P3/8-small)
-
-   [-1, 1, Conv, [256, 3, 2]],
-   [[-1, 20], 1, Concat, [1]],  # cat head P4
-   [-1, 3, C3, [512, False]],  # 26 (P4/16-medium)
-
-   [-1, 1, Conv, [512, 3, 2]],
-   [[-1, 16], 1, Concat, [1]],  # cat head P5
-   [-1, 3, C3, [768, False]],  # 29 (P5/32-large)
-
-   [-1, 1, Conv, [768, 3, 2]],
-   [[-1, 12], 1, Concat, [1]],  # cat head P6
-   [-1, 3, C3, [1024, False]],  # 32 (P6/64-xlarge)
-
-   [[23, 26, 29, 32], 1, Detect, [nc]],  # Detect(P3, P4, P5, P6)
-  ]
diff --git a/ultralytics/models/v5/yolov5xu.yaml b/ultralytics/models/v5/yolov5xu.yaml
deleted file mode 100644
index e3275ab5..00000000
--- a/ultralytics/models/v5/yolov5xu.yaml
+++ /dev/null
@@ -1,44 +0,0 @@
-# Ultralytics YOLO 🚀, GPL-3.0 license
-
-# Parameters
-nc: 80  # number of classes
-depth_multiple: 1.33  # model depth multiple
-width_multiple: 1.25  # layer channel multiple
-
-# YOLOv5 v6.0 backbone
-backbone:
-  # [from, number, module, args]
-  [[-1, 1, Conv, [64, 6, 2, 2]],  # 0-P1/2
-   [-1, 1, Conv, [128, 3, 2]],  # 1-P2/4
-   [-1, 3, C3, [128]],
-   [-1, 1, Conv, [256, 3, 2]],  # 3-P3/8
-   [-1, 6, C3, [256]],
-   [-1, 1, Conv, [512, 3, 2]],  # 5-P4/16
-   [-1, 9, C3, [512]],
-   [-1, 1, Conv, [1024, 3, 2]],  # 7-P5/32
-   [-1, 3, C3, [1024]],
-   [-1, 1, SPPF, [1024, 5]],  # 9
-  ]
-
-# YOLOv5 v6.0 head
-head:
-  [[-1, 1, Conv, [512, 1, 1]],
-   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
-   [[-1, 6], 1, Concat, [1]],  # cat backbone P4
-   [-1, 3, C3, [512, False]],  # 13
-
-   [-1, 1, Conv, [256, 1, 1]],
-   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
-   [[-1, 4], 1, Concat, [1]],  # cat backbone P3
-   [-1, 3, C3, [256, False]],  # 17 (P3/8-small)
-
-   [-1, 1, Conv, [256, 3, 2]],
-   [[-1, 14], 1, Concat, [1]],  # cat head P4
-   [-1, 3, C3, [512, False]],  # 20 (P4/16-medium)
-
-   [-1, 1, Conv, [512, 3, 2]],
-   [[-1, 10], 1, Concat, [1]],  # cat head P5
-   [-1, 3, C3, [1024, False]],  # 23 (P5/32-large)
-
-   [[17, 20, 23], 1, Detect, [nc]],  # Detect(P3, P4, P5)
-  ]
diff --git a/ultralytics/models/v8/cls/yolov8m-cls.yaml b/ultralytics/models/v8/cls/yolov8m-cls.yaml
deleted file mode 100644
index 7e91894c..00000000
--- a/ultralytics/models/v8/cls/yolov8m-cls.yaml
+++ /dev/null
@@ -1,23 +0,0 @@
-# Ultralytics YOLO 🚀, GPL-3.0 license
-
-# Parameters
-nc: 1000  # number of classes
-depth_multiple: 0.67  # scales module repeats
-width_multiple: 0.75  # scales convolution channels
-
-# YOLOv8.0n backbone
-backbone:
-  # [from, repeats, module, args]
-  - [-1, 1, Conv, [64, 3, 2]]  # 0-P1/2
-  - [-1, 1, Conv, [128, 3, 2]]  # 1-P2/4
-  - [-1, 3, C2f, [128, True]]
-  - [-1, 1, Conv, [256, 3, 2]]  # 3-P3/8
-  - [-1, 6, C2f, [256, True]]
-  - [-1, 1, Conv, [512, 3, 2]]  # 5-P4/16
-  - [-1, 6, C2f, [512, True]]
-  - [-1, 1, Conv, [1024, 3, 2]]  # 7-P5/32
-  - [-1, 3, C2f, [1024, True]]
-
-# YOLOv8.0n head
-head:
-  - [-1, 1, Classify, [nc]]
diff --git a/ultralytics/models/v8/cls/yolov8n-cls.yaml b/ultralytics/models/v8/cls/yolov8n-cls.yaml
deleted file mode 100644
index 29be2264..00000000
--- a/ultralytics/models/v8/cls/yolov8n-cls.yaml
+++ /dev/null
@@ -1,23 +0,0 @@
-# Ultralytics YOLO 🚀, GPL-3.0 license
-
-# Parameters
-nc: 1000  # number of classes
-depth_multiple: 0.33  # scales module repeats
-width_multiple: 0.25  # scales convolution channels
-
-# YOLOv8.0n backbone
-backbone:
-  # [from, repeats, module, args]
-  - [-1, 1, Conv, [64, 3, 2]]  # 0-P1/2
-  - [-1, 1, Conv, [128, 3, 2]]  # 1-P2/4
-  - [-1, 3, C2f, [128, True]]
-  - [-1, 1, Conv, [256, 3, 2]]  # 3-P3/8
-  - [-1, 6, C2f, [256, True]]
-  - [-1, 1, Conv, [512, 3, 2]]  # 5-P4/16
-  - [-1, 6, C2f, [512, True]]
-  - [-1, 1, Conv, [1024, 3, 2]]  # 7-P5/32
-  - [-1, 3, C2f, [1024, True]]
-
-# YOLOv8.0n head
-head:
-  - [-1, 1, Classify, [nc]]
diff --git a/ultralytics/models/v8/cls/yolov8s-cls.yaml b/ultralytics/models/v8/cls/yolov8s-cls.yaml
deleted file mode 100644
index 00ddc55a..00000000
--- a/ultralytics/models/v8/cls/yolov8s-cls.yaml
+++ /dev/null
@@ -1,23 +0,0 @@
-# Ultralytics YOLO 🚀, GPL-3.0 license
-
-# Parameters
-nc: 1000  # number of classes
-depth_multiple: 0.33  # scales module repeats
-width_multiple: 0.50  # scales convolution channels
-
-# YOLOv8.0n backbone
-backbone:
-  # [from, repeats, module, args]
-  - [-1, 1, Conv, [64, 3, 2]]  # 0-P1/2
-  - [-1, 1, Conv, [128, 3, 2]]  # 1-P2/4
-  - [-1, 3, C2f, [128, True]]
-  - [-1, 1, Conv, [256, 3, 2]]  # 3-P3/8
-  - [-1, 6, C2f, [256, True]]
-  - [-1, 1, Conv, [512, 3, 2]]  # 5-P4/16
-  - [-1, 6, C2f, [512, True]]
-  - [-1, 1, Conv, [1024, 3, 2]]  # 7-P5/32
-  - [-1, 3, C2f, [1024, True]]
-
-# YOLOv8.0n head
-head:
-  - [-1, 1, Classify, [nc]]
diff --git a/ultralytics/models/v8/cls/yolov8x-cls.yaml b/ultralytics/models/v8/cls/yolov8x-cls.yaml
deleted file mode 100644
index 46c75d5a..00000000
--- a/ultralytics/models/v8/cls/yolov8x-cls.yaml
+++ /dev/null
@@ -1,23 +0,0 @@
-# Ultralytics YOLO 🚀, GPL-3.0 license
-
-# Parameters
-nc: 1000  # number of classes
-depth_multiple: 1.00  # scales module repeats
-width_multiple: 1.25  # scales convolution channels
-
-# YOLOv8.0n backbone
-backbone:
-  # [from, repeats, module, args]
-  - [-1, 1, Conv, [64, 3, 2]]  # 0-P1/2
-  - [-1, 1, Conv, [128, 3, 2]]  # 1-P2/4
-  - [-1, 3, C2f, [128, True]]
-  - [-1, 1, Conv, [256, 3, 2]]  # 3-P3/8
-  - [-1, 6, C2f, [256, True]]
-  - [-1, 1, Conv, [512, 3, 2]]  # 5-P4/16
-  - [-1, 6, C2f, [512, True]]
-  - [-1, 1, Conv, [1024, 3, 2]]  # 7-P5/32
-  - [-1, 3, C2f, [1024, True]]
-
-# YOLOv8.0n head
-head:
-  - [-1, 1, Classify, [nc]]
diff --git a/ultralytics/models/v8/seg/yolov8l-seg.yaml b/ultralytics/models/v8/seg/yolov8l-seg.yaml
deleted file mode 100644
index 72bf0088..00000000
--- a/ultralytics/models/v8/seg/yolov8l-seg.yaml
+++ /dev/null
@@ -1,40 +0,0 @@
-# Ultralytics YOLO 🚀, GPL-3.0 license
-
-# Parameters
-nc: 80  # number of classes
-depth_multiple: 1.00  # scales module repeats
-width_multiple: 1.00  # scales convolution channels
-
-# YOLOv8.0l backbone
-backbone:
-  # [from, repeats, module, args]
-  - [-1, 1, Conv, [64, 3, 2]]  # 0-P1/2
-  - [-1, 1, Conv, [128, 3, 2]]  # 1-P2/4
-  - [-1, 3, C2f, [128, True]]
-  - [-1, 1, Conv, [256, 3, 2]]  # 3-P3/8
-  - [-1, 6, C2f, [256, True]]
-  - [-1, 1, Conv, [512, 3, 2]]  # 5-P4/16
-  - [-1, 6, C2f, [512, True]]
-  - [-1, 1, Conv, [512, 3, 2]]  # 7-P5/32
-  - [-1, 3, C2f, [512, True]]
-  - [-1, 1, SPPF, [512, 5]]  # 9
-
-# YOLOv8.0l head
-head:
-  - [-1, 1, nn.Upsample, [None, 2, 'nearest']]
-  - [[-1, 6], 1, Concat, [1]]  # cat backbone P4
-  - [-1, 3, C2f, [512]]  # 12
-
-  - [-1, 1, nn.Upsample, [None, 2, 'nearest']]
-  - [[-1, 4], 1, Concat, [1]]  # cat backbone P3
-  - [-1, 3, C2f, [256]]  # 15 (P3/8-small)
-
-  - [-1, 1, Conv, [256, 3, 2]]
-  - [[-1, 12], 1, Concat, [1]]  # cat head P4
-  - [-1, 3, C2f, [512]]  # 18 (P4/16-medium)
-
-  - [-1, 1, Conv, [512, 3, 2]]
-  - [[-1, 9], 1, Concat, [1]]  # cat head P5
-  - [-1, 3, C2f, [512]]  # 21 (P5/32-large)
-
-  - [[15, 18, 21], 1, Segment, [nc, 32, 256]]  # Detect(P3, P4, P5)
diff --git a/ultralytics/models/v8/seg/yolov8m-seg.yaml b/ultralytics/models/v8/seg/yolov8m-seg.yaml
deleted file mode 100644
index 7e742275..00000000
--- a/ultralytics/models/v8/seg/yolov8m-seg.yaml
+++ /dev/null
@@ -1,40 +0,0 @@
-# Ultralytics YOLO 🚀, GPL-3.0 license
-
-# Parameters
-nc: 80  # number of classes
-depth_multiple: 0.67  # scales module repeats
-width_multiple: 0.75  # scales convolution channels
-
-# YOLOv8.0m backbone
-backbone:
-  # [from, repeats, module, args]
-  - [-1, 1, Conv, [64, 3, 2]]  # 0-P1/2
-  - [-1, 1, Conv, [128, 3, 2]]  # 1-P2/4
-  - [-1, 3, C2f, [128, True]]
-  - [-1, 1, Conv, [256, 3, 2]]  # 3-P3/8
-  - [-1, 6, C2f, [256, True]]
-  - [-1, 1, Conv, [512, 3, 2]]  # 5-P4/16
-  - [-1, 6, C2f, [512, True]]
-  - [-1, 1, Conv, [768, 3, 2]]  # 7-P5/32
-  - [-1, 3, C2f, [768, True]]
-  - [-1, 1, SPPF, [768, 5]]  # 9
-
-# YOLOv8.0m head
-head:
-  - [-1, 1, nn.Upsample, [None, 2, 'nearest']]
-  - [[-1, 6], 1, Concat, [1]]  # cat backbone P4
-  - [-1, 3, C2f, [512]]  # 12
-
-  - [-1, 1, nn.Upsample, [None, 2, 'nearest']]
-  - [[-1, 4], 1, Concat, [1]]  # cat backbone P3
-  - [-1, 3, C2f, [256]]  # 15 (P3/8-small)
-
-  - [-1, 1, Conv, [256, 3, 2]]
-  - [[-1, 12], 1, Concat, [1]]  # cat head P4
-  - [-1, 3, C2f, [512]]  # 18 (P4/16-medium)
-
-  - [-1, 1, Conv, [512, 3, 2]]
-  - [[-1, 9], 1, Concat, [1]]  # cat head P5
-  - [-1, 3, C2f, [768]]  # 21 (P5/32-large)
-
-  - [[15, 18, 21], 1, Segment, [nc, 32, 256]]  # Detect(P3, P4, P5)
diff --git a/ultralytics/models/v8/seg/yolov8n-seg.yaml b/ultralytics/models/v8/seg/yolov8n-seg.yaml
deleted file mode 100644
index 5f39e101..00000000
--- a/ultralytics/models/v8/seg/yolov8n-seg.yaml
+++ /dev/null
@@ -1,40 +0,0 @@
-# Ultralytics YOLO 🚀, GPL-3.0 license
-
-# Parameters
-nc: 80  # number of classes
-depth_multiple: 0.33  # scales module repeats
-width_multiple: 0.25  # scales convolution channels
-
-# YOLOv8.0n backbone
-backbone:
-  # [from, repeats, module, args]
-  - [-1, 1, Conv, [64, 3, 2]]  # 0-P1/2
-  - [-1, 1, Conv, [128, 3, 2]]  # 1-P2/4
-  - [-1, 3, C2f, [128, True]]
-  - [-1, 1, Conv, [256, 3, 2]]  # 3-P3/8
-  - [-1, 6, C2f, [256, True]]
-  - [-1, 1, Conv, [512, 3, 2]]  # 5-P4/16
-  - [-1, 6, C2f, [512, True]]
-  - [-1, 1, Conv, [1024, 3, 2]]  # 7-P5/32
-  - [-1, 3, C2f, [1024, True]]
-  - [-1, 1, SPPF, [1024, 5]]  # 9
-
-# YOLOv8.0n head
-head:
-  - [-1, 1, nn.Upsample, [None, 2, 'nearest']]
-  - [[-1, 6], 1, Concat, [1]]  # cat backbone P4
-  - [-1, 3, C2f, [512]]  # 12
-
-  - [-1, 1, nn.Upsample, [None, 2, 'nearest']]
-  - [[-1, 4], 1, Concat, [1]]  # cat backbone P3
-  - [-1, 3, C2f, [256]]  # 15 (P3/8-small)
-
-  - [-1, 1, Conv, [256, 3, 2]]
-  - [[-1, 12], 1, Concat, [1]]  # cat head P4
-  - [-1, 3, C2f, [512]]  # 18 (P4/16-medium)
-
-  - [-1, 1, Conv, [512, 3, 2]]
-  - [[-1, 9], 1, Concat, [1]]  # cat head P5
-  - [-1, 3, C2f, [1024]]  # 21 (P5/32-large)
-
-  - [[15, 18, 21], 1, Segment, [nc, 32, 256]]  # Detect(P3, P4, P5)
diff --git a/ultralytics/models/v8/seg/yolov8s-seg.yaml b/ultralytics/models/v8/seg/yolov8s-seg.yaml
deleted file mode 100644
index 27946164..00000000
--- a/ultralytics/models/v8/seg/yolov8s-seg.yaml
+++ /dev/null
@@ -1,40 +0,0 @@
-# Ultralytics YOLO 🚀, GPL-3.0 license
-
-# Parameters
-nc: 80  # number of classes
-depth_multiple: 0.33  # scales module repeats
-width_multiple: 0.50  # scales convolution channels
-
-# YOLOv8.0s backbone
-backbone:
-  # [from, repeats, module, args]
-  - [-1, 1, Conv, [64, 3, 2]]  # 0-P1/2
-  - [-1, 1, Conv, [128, 3, 2]]  # 1-P2/4
-  - [-1, 3, C2f, [128, True]]
-  - [-1, 1, Conv, [256, 3, 2]]  # 3-P3/8
-  - [-1, 6, C2f, [256, True]]
-  - [-1, 1, Conv, [512, 3, 2]]  # 5-P4/16
-  - [-1, 6, C2f, [512, True]]
-  - [-1, 1, Conv, [1024, 3, 2]]  # 7-P5/32
-  - [-1, 3, C2f, [1024, True]]
-  - [-1, 1, SPPF, [1024, 5]]  # 9
-
-# YOLOv8.0s head
-head:
-  - [-1, 1, nn.Upsample, [None, 2, 'nearest']]
-  - [[-1, 6], 1, Concat, [1]]  # cat backbone P4
-  - [-1, 3, C2f, [512]]  # 12
-
-  - [-1, 1, nn.Upsample, [None, 2, 'nearest']]
-  - [[-1, 4], 1, Concat, [1]]  # cat backbone P3
-  - [-1, 3, C2f, [256]]  # 15 (P3/8-small)
-
-  - [-1, 1, Conv, [256, 3, 2]]
-  - [[-1, 12], 1, Concat, [1]]  # cat head P4
-  - [-1, 3, C2f, [512]]  # 18 (P4/16-medium)
-
-  - [-1, 1, Conv, [512, 3, 2]]
-  - [[-1, 9], 1, Concat, [1]]  # cat head P5
-  - [-1, 3, C2f, [1024]]  # 21 (P5/32-large)
-
-  - [[15, 18, 21], 1, Segment, [nc, 32, 256]]  # Detect(P3, P4, P5)
diff --git a/ultralytics/models/v8/seg/yolov8x-seg.yaml b/ultralytics/models/v8/seg/yolov8x-seg.yaml
deleted file mode 100644
index 3edb030b..00000000
--- a/ultralytics/models/v8/seg/yolov8x-seg.yaml
+++ /dev/null
@@ -1,40 +0,0 @@
-# Ultralytics YOLO 🚀, GPL-3.0 license
-
-# Parameters
-nc: 80  # number of classes
-depth_multiple: 1.00  # scales module repeats
-width_multiple: 1.25  # scales convolution channels
-
-# YOLOv8.0x backbone
-backbone:
-  # [from, repeats, module, args]
-  - [-1, 1, Conv, [64, 3, 2]]  # 0-P1/2
-  - [-1, 1, Conv, [128, 3, 2]]  # 1-P2/4
-  - [-1, 3, C2f, [128, True]]
-  - [-1, 1, Conv, [256, 3, 2]]  # 3-P3/8
-  - [-1, 6, C2f, [256, True]]
-  - [-1, 1, Conv, [512, 3, 2]]  # 5-P4/16
-  - [-1, 6, C2f, [512, True]]
-  - [-1, 1, Conv, [512, 3, 2]]  # 7-P5/32
-  - [-1, 3, C2f, [512, True]]
-  - [-1, 1, SPPF, [512, 5]]  # 9
-
-# YOLOv8.0x head
-head:
-  - [-1, 1, nn.Upsample, [None, 2, 'nearest']]
-  - [[-1, 6], 1, Concat, [1]]  # cat backbone P4
-  - [-1, 3, C2f, [512]]  # 12
-
-  - [-1, 1, nn.Upsample, [None, 2, 'nearest']]
-  - [[-1, 4], 1, Concat, [1]]  # cat backbone P3
-  - [-1, 3, C2f, [256]]  # 15 (P3/8-small)
-
-  - [-1, 1, Conv, [256, 3, 2]]
-  - [[-1, 12], 1, Concat, [1]]  # cat head P4
-  - [-1, 3, C2f, [512]]  # 18 (P4/16-medium)
-
-  - [-1, 1, Conv, [512, 3, 2]]
-  - [[-1, 9], 1, Concat, [1]]  # cat head P5
-  - [-1, 3, C2f, [512]]  # 21 (P5/32-large)
-
-  - [[15, 18, 21], 1, Segment, [nc, 32, 256]]  # Detect(P3, P4, P5)
diff --git a/ultralytics/models/v8/cls/yolov8l-cls.yaml b/ultralytics/models/v8/yolov8-cls.yaml
similarity index 54%
rename from ultralytics/models/v8/cls/yolov8l-cls.yaml
rename to ultralytics/models/v8/yolov8-cls.yaml
index bf981a84..0847ed1c 100644
--- a/ultralytics/models/v8/cls/yolov8l-cls.yaml
+++ b/ultralytics/models/v8/yolov8-cls.yaml
@@ -1,9 +1,15 @@
 # Ultralytics YOLO 🚀, GPL-3.0 license
+# YOLOv8-cls image classification model. For Usage examples see https://docs.ultralytics.com/tasks/classify
 
 # Parameters
 nc: 1000  # number of classes
-depth_multiple: 1.00  # scales module repeats
-width_multiple: 1.00  # scales convolution channels
+scales: # model compound scaling constants, i.e. 'model=yolov8n-cls.yaml' will call yolov8-cls.yaml with scale 'n'
+  # [depth, width, max_channels]
+  n: [0.33, 0.25, 1024]
+  s: [0.33, 0.50, 1024]
+  m: [0.67, 0.75, 1024]
+  l: [1.00, 1.00, 1024]
+  x: [1.00, 1.25, 1024]
 
 # YOLOv8.0n backbone
 backbone:
@@ -20,4 +26,4 @@ backbone:
 
 # YOLOv8.0n head
 head:
-  - [-1, 1, Classify, [nc]]
+  - [-1, 1, Classify, [nc]]  # Classify
diff --git a/ultralytics/models/v8/yolov8x6.yaml b/ultralytics/models/v8/yolov8-p6.yaml
similarity index 60%
rename from ultralytics/models/v8/yolov8x6.yaml
rename to ultralytics/models/v8/yolov8-p6.yaml
index 8ffcdeae..ab8a68ed 100644
--- a/ultralytics/models/v8/yolov8x6.yaml
+++ b/ultralytics/models/v8/yolov8-p6.yaml
@@ -1,9 +1,15 @@
 # Ultralytics YOLO 🚀, GPL-3.0 license
+# YOLOv8 object detection model with P3-P6 outputs. For Usage examples see https://docs.ultralytics.com/tasks/detect
 
 # Parameters
 nc: 80  # number of classes
-depth_multiple: 1.00  # scales module repeats
-width_multiple: 1.25  # scales convolution channels
+scales: # model compound scaling constants, i.e. 'model=yolov8n-p6.yaml' will call yolov8-p6.yaml with scale 'n'
+  # [depth, width, max_channels]
+  n: [0.33, 0.25, 1024]
+  s: [0.33, 0.50, 1024]
+  m: [0.67, 0.75, 768]
+  l: [1.00, 1.00, 512]
+  x: [1.00, 1.25, 512]
 
 # YOLOv8.0x6 backbone
 backbone:
@@ -15,17 +21,17 @@ backbone:
   - [-1, 6, C2f, [256, True]]
   - [-1, 1, Conv, [512, 3, 2]]  # 5-P4/16
   - [-1, 6, C2f, [512, True]]
-  - [-1, 1, Conv, [512, 3, 2]]  # 7-P5/32
-  - [-1, 3, C2f, [512, True]]
-  - [-1, 1, Conv, [512, 3, 2]]  # 9-P6/64
-  - [-1, 3, C2f, [512, True]]
-  - [-1, 1, SPPF, [512, 5]]  # 11
+  - [-1, 1, Conv, [768, 3, 2]]  # 7-P5/32
+  - [-1, 3, C2f, [768, True]]
+  - [-1, 1, Conv, [1024, 3, 2]]  # 9-P6/64
+  - [-1, 3, C2f, [1024, True]]
+  - [-1, 1, SPPF, [1024, 5]]  # 11
 
 # YOLOv8.0x6 head
 head:
   - [-1, 1, nn.Upsample, [None, 2, 'nearest']]
   - [[-1, 8], 1, Concat, [1]]  # cat backbone P5
-  - [-1, 3, C2, [512, False]]  # 14
+  - [-1, 3, C2, [768, False]]  # 14
 
   - [-1, 1, nn.Upsample, [None, 2, 'nearest']]
   - [[-1, 6], 1, Concat, [1]]  # cat backbone P4
@@ -41,10 +47,10 @@ head:
 
   - [-1, 1, Conv, [512, 3, 2]]
   - [[-1, 14], 1, Concat, [1]]  # cat head P5
-  - [-1, 3, C2, [512, False]]  # 26 (P5/32-large)
+  - [-1, 3, C2, [768, False]]  # 26 (P5/32-large)
 
-  - [-1, 1, Conv, [512, 3, 2]]
+  - [-1, 1, Conv, [768, 3, 2]]
   - [[-1, 11], 1, Concat, [1]]  # cat head P6
-  - [-1, 3, C2, [512, False]]  # 29 (P6/64-xlarge)
+  - [-1, 3, C2, [1024, False]]  # 29 (P6/64-xlarge)
 
   - [[20, 23, 26, 29], 1, Detect, [nc]]  # Detect(P3, P4, P5, P6)
diff --git a/ultralytics/models/v8/yolov8n.yaml b/ultralytics/models/v8/yolov8-seg.yaml
similarity index 70%
rename from ultralytics/models/v8/yolov8n.yaml
rename to ultralytics/models/v8/yolov8-seg.yaml
index 2519b402..23a52a9d 100644
--- a/ultralytics/models/v8/yolov8n.yaml
+++ b/ultralytics/models/v8/yolov8-seg.yaml
@@ -1,9 +1,15 @@
 # Ultralytics YOLO 🚀, GPL-3.0 license
+# YOLOv8-seg instance segmentation model. For Usage examples see https://docs.ultralytics.com/tasks/segment
 
 # Parameters
 nc: 80  # number of classes
-depth_multiple: 0.33  # scales module repeats
-width_multiple: 0.25  # scales convolution channels
+scales: # model compound scaling constants, i.e. 'model=yolov8n-seg.yaml' will call yolov8-seg.yaml with scale 'n'
+  # [depth, width, max_channels]
+  n: [0.33, 0.25, 1024]
+  s: [0.33, 0.50, 1024]
+  m: [0.67, 0.75, 768]
+  l: [1.00, 1.00, 512]
+  x: [1.00, 1.25, 512]
 
 # YOLOv8.0n backbone
 backbone:
@@ -37,4 +43,4 @@ head:
   - [[-1, 9], 1, Concat, [1]]  # cat head P5
   - [-1, 3, C2f, [1024]]  # 21 (P5/32-large)
 
-  - [[15, 18, 21], 1, Detect, [nc]]  # Detect(P3, P4, P5)
+  - [[15, 18, 21], 1, Segment, [nc, 32, 256]]  # Segment(P3, P4, P5)
diff --git a/ultralytics/models/v8/yolov8s.yaml b/ultralytics/models/v8/yolov8.yaml
similarity index 55%
rename from ultralytics/models/v8/yolov8s.yaml
rename to ultralytics/models/v8/yolov8.yaml
index 79056545..addaa4e9 100644
--- a/ultralytics/models/v8/yolov8s.yaml
+++ b/ultralytics/models/v8/yolov8.yaml
@@ -1,11 +1,17 @@
 # Ultralytics YOLO 🚀, GPL-3.0 license
+# YOLOv8 object detection model with P3-P5 outputs. For Usage examples see https://docs.ultralytics.com/tasks/detect
 
 # Parameters
 nc: 80  # number of classes
-depth_multiple: 0.33  # scales module repeats
-width_multiple: 0.50  # scales convolution channels
+scales: # model compound scaling constants, i.e. 'model=yolov8n.yaml' will call yolov8.yaml with scale 'n'
+  # [depth, width, max_channels]
+  n: [0.33, 0.25, 1024]  # YOLOv8n summary: 225 layers,  3157200 parameters,  3157184 gradients,   8.9 GFLOPs
+  s: [0.33, 0.50, 1024]  # YOLOv8s summary: 225 layers, 11166560 parameters, 11166544 gradients,  28.8 GFLOPs
+  m: [0.67, 0.75, 768]   # YOLOv8m summary: 295 layers, 25902640 parameters, 25902624 gradients,  79.3 GFLOPs
+  l: [1.00, 1.00, 512]   # YOLOv8l summary: 365 layers, 43691520 parameters, 43691504 gradients, 165.7 GFLOPs
+  x: [1.00, 1.25, 512]   # YOLOv8x summary: 365 layers, 68229648 parameters, 68229632 gradients, 258.5 GFLOPs
 
-# YOLOv8.0s backbone
+# YOLOv8.0n backbone
 backbone:
   # [from, repeats, module, args]
   - [-1, 1, Conv, [64, 3, 2]]  # 0-P1/2
@@ -19,7 +25,7 @@ backbone:
   - [-1, 3, C2f, [1024, True]]
   - [-1, 1, SPPF, [1024, 5]]  # 9
 
-# YOLOv8.0s head
+# YOLOv8.0n head
 head:
   - [-1, 1, nn.Upsample, [None, 2, 'nearest']]
   - [[-1, 6], 1, Concat, [1]]  # cat backbone P4
diff --git a/ultralytics/models/v8/yolov8l.yaml b/ultralytics/models/v8/yolov8l.yaml
deleted file mode 100644
index afbe4c69..00000000
--- a/ultralytics/models/v8/yolov8l.yaml
+++ /dev/null
@@ -1,40 +0,0 @@
-# Ultralytics YOLO 🚀, GPL-3.0 license
-
-# Parameters
-nc: 80  # number of classes
-depth_multiple: 1.00  # scales module repeats
-width_multiple: 1.00  # scales convolution channels
-
-# YOLOv8.0l backbone
-backbone:
-  # [from, repeats, module, args]
-  - [-1, 1, Conv, [64, 3, 2]]  # 0-P1/2
-  - [-1, 1, Conv, [128, 3, 2]]  # 1-P2/4
-  - [-1, 3, C2f, [128, True]]
-  - [-1, 1, Conv, [256, 3, 2]]  # 3-P3/8
-  - [-1, 6, C2f, [256, True]]
-  - [-1, 1, Conv, [512, 3, 2]]  # 5-P4/16
-  - [-1, 6, C2f, [512, True]]
-  - [-1, 1, Conv, [512, 3, 2]]  # 7-P5/32
-  - [-1, 3, C2f, [512, True]]
-  - [-1, 1, SPPF, [512, 5]]  # 9
-
-# YOLOv8.0l head
-head:
-  - [-1, 1, nn.Upsample, [None, 2, 'nearest']]
-  - [[-1, 6], 1, Concat, [1]]  # cat backbone P4
-  - [-1, 3, C2f, [512]]  # 12
-
-  - [-1, 1, nn.Upsample, [None, 2, 'nearest']]
-  - [[-1, 4], 1, Concat, [1]]  # cat backbone P3
-  - [-1, 3, C2f, [256]]  # 15 (P3/8-small)
-
-  - [-1, 1, Conv, [256, 3, 2]]
-  - [[-1, 12], 1, Concat, [1]]  # cat head P4
-  - [-1, 3, C2f, [512]]  # 18 (P4/16-medium)
-
-  - [-1, 1, Conv, [512, 3, 2]]
-  - [[-1, 9], 1, Concat, [1]]  # cat head P5
-  - [-1, 3, C2f, [512]]  # 21 (P5/32-large)
-
-  - [[15, 18, 21], 1, Detect, [nc]]  # Detect(P3, P4, P5)
diff --git a/ultralytics/models/v8/yolov8m.yaml b/ultralytics/models/v8/yolov8m.yaml
deleted file mode 100644
index a17763c6..00000000
--- a/ultralytics/models/v8/yolov8m.yaml
+++ /dev/null
@@ -1,40 +0,0 @@
-# Ultralytics YOLO 🚀, GPL-3.0 license
-
-# Parameters
-nc: 80  # number of classes
-depth_multiple: 0.67  # scales module repeats
-width_multiple: 0.75  # scales convolution channels
-
-# YOLOv8.0m backbone
-backbone:
-  # [from, repeats, module, args]
-  - [-1, 1, Conv, [64, 3, 2]]  # 0-P1/2
-  - [-1, 1, Conv, [128, 3, 2]]  # 1-P2/4
-  - [-1, 3, C2f, [128, True]]
-  - [-1, 1, Conv, [256, 3, 2]]  # 3-P3/8
-  - [-1, 6, C2f, [256, True]]
-  - [-1, 1, Conv, [512, 3, 2]]  # 5-P4/16
-  - [-1, 6, C2f, [512, True]]
-  - [-1, 1, Conv, [768, 3, 2]]  # 7-P5/32
-  - [-1, 3, C2f, [768, True]]
-  - [-1, 1, SPPF, [768, 5]]  # 9
-
-# YOLOv8.0m head
-head:
-  - [-1, 1, nn.Upsample, [None, 2, 'nearest']]
-  - [[-1, 6], 1, Concat, [1]]  # cat backbone P4
-  - [-1, 3, C2f, [512]]  # 12
-
-  - [-1, 1, nn.Upsample, [None, 2, 'nearest']]
-  - [[-1, 4], 1, Concat, [1]]  # cat backbone P3
-  - [-1, 3, C2f, [256]]  # 15 (P3/8-small)
-
-  - [-1, 1, Conv, [256, 3, 2]]
-  - [[-1, 12], 1, Concat, [1]]  # cat head P4
-  - [-1, 3, C2f, [512]]  # 18 (P4/16-medium)
-
-  - [-1, 1, Conv, [512, 3, 2]]
-  - [[-1, 9], 1, Concat, [1]]  # cat head P5
-  - [-1, 3, C2f, [768]]  # 21 (P5/32-large)
-
-  - [[15, 18, 21], 1, Detect, [nc]]  # Detect(P3, P4, P5)
diff --git a/ultralytics/models/v8/yolov8x.yaml b/ultralytics/models/v8/yolov8x.yaml
deleted file mode 100644
index d254523c..00000000
--- a/ultralytics/models/v8/yolov8x.yaml
+++ /dev/null
@@ -1,40 +0,0 @@
-# Ultralytics YOLO 🚀, GPL-3.0 license
-
-# Parameters
-nc: 80  # number of classes
-depth_multiple: 1.00  # scales module repeats
-width_multiple: 1.25  # scales convolution channels
-
-# YOLOv8.0x backbone
-backbone:
-  # [from, repeats, module, args]
-  - [-1, 1, Conv, [64, 3, 2]]  # 0-P1/2
-  - [-1, 1, Conv, [128, 3, 2]]  # 1-P2/4
-  - [-1, 3, C2f, [128, True]]
-  - [-1, 1, Conv, [256, 3, 2]]  # 3-P3/8
-  - [-1, 6, C2f, [256, True]]
-  - [-1, 1, Conv, [512, 3, 2]]  # 5-P4/16
-  - [-1, 6, C2f, [512, True]]
-  - [-1, 1, Conv, [512, 3, 2]]  # 7-P5/32
-  - [-1, 3, C2f, [512, True]]
-  - [-1, 1, SPPF, [512, 5]]  # 9
-
-# YOLOv8.0x head
-head:
-  - [-1, 1, nn.Upsample, [None, 2, 'nearest']]
-  - [[-1, 6], 1, Concat, [1]]  # cat backbone P4
-  - [-1, 3, C2f, [512]]  # 12
-
-  - [-1, 1, nn.Upsample, [None, 2, 'nearest']]
-  - [[-1, 4], 1, Concat, [1]]  # cat backbone P3
-  - [-1, 3, C2f, [256]]  # 15 (P3/8-small)
-
-  - [-1, 1, Conv, [256, 3, 2]]
-  - [[-1, 12], 1, Concat, [1]]  # cat head P4
-  - [-1, 3, C2f, [512]]  # 18 (P4/16-medium)
-
-  - [-1, 1, Conv, [512, 3, 2]]
-  - [[-1, 9], 1, Concat, [1]]  # cat head P5
-  - [-1, 3, C2f, [512]]  # 21 (P5/32-large)
-
-  - [[15, 18, 21], 1, Detect, [nc]]  # Detect(P3, P4, P5)
diff --git a/ultralytics/nn/tasks.py b/ultralytics/nn/tasks.py
index d7af6e9a..2c03083d 100644
--- a/ultralytics/nn/tasks.py
+++ b/ultralytics/nn/tasks.py
@@ -170,7 +170,7 @@ class DetectionModel(BaseModel):
     # YOLOv8 detection model
     def __init__(self, cfg='yolov8n.yaml', ch=3, nc=None, verbose=True):  # model, input channels, number of classes
         super().__init__()
-        self.yaml = cfg if isinstance(cfg, dict) else yaml_load(check_yaml(cfg), append_filename=True)  # cfg dict
+        self.yaml = cfg if isinstance(cfg, dict) else yaml_model_load(cfg)  # cfg dict
 
         # Define model
         ch = self.yaml['ch'] = self.yaml.get('ch', ch)  # input channels
@@ -277,7 +277,8 @@ class ClassificationModel(BaseModel):
         self.nc = nc
 
     def _from_yaml(self, cfg, ch, nc, verbose):
-        self.yaml = cfg if isinstance(cfg, dict) else yaml_load(check_yaml(cfg), append_filename=True)  # cfg dict
+        self.yaml = cfg if isinstance(cfg, dict) else yaml_model_load(cfg)  # cfg dict
+
         # Define model
         ch = self.yaml['ch'] = self.yaml.get('ch', ch)  # input channels
         if nc and nc != self.yaml['nc']:
@@ -418,30 +419,42 @@ def attempt_load_one_weight(weight, device=None, inplace=True, fuse=False):
 
 
 def parse_model(d, ch, verbose=True):  # model_dict, input_channels(3)
-    # Parse a YOLO model.yaml dictionary
-    if verbose:
-        LOGGER.info(f"\n{'':>3}{'from':>20}{'n':>3}{'params':>10}  {'module':<45}{'arguments':<30}")
-    nc, gd, gw, act = d['nc'], d['depth_multiple'], d['width_multiple'], d.get('activation')
+    # Parse a YOLO model.yaml dictionary into a PyTorch model
+    import ast
+
+    # Args
+    max_channels = float('inf')
+    nc, act, scales = (d.get(x) for x in ('nc', 'act', 'scales'))
+    depth, width = (d.get(x, 1.0) for x in ('depth_multiple', 'width_multiple'))
+    if scales:
+        scale = d.get('scale')
+        if not scale:
+            scale = tuple(scales.keys())[0]
+            LOGGER.warning(f"WARNING ⚠️ no model scale passed. Assuming scale='{scale}'.")
+        depth, width, max_channels = scales[scale]
+
     if act:
         Conv.default_act = eval(act)  # redefine default activation, i.e. Conv.default_act = nn.SiLU()
         if verbose:
             LOGGER.info(f"{colorstr('activation:')} {act}")  # print
+
+    if verbose:
+        LOGGER.info(f"\n{'':>3}{'from':>20}{'n':>3}{'params':>10}  {'module':<45}{'arguments':<30}")
     ch = [ch]
     layers, save, c2 = [], [], ch[-1]  # layers, savelist, ch out
     for i, (f, n, m, args) in enumerate(d['backbone'] + d['head']):  # from, number, module, args
         m = getattr(torch.nn, m[3:]) if 'nn.' in m else globals()[m]  # get module
         for j, a in enumerate(args):
-            # TODO: re-implement with eval() removal if possible
-            # args[j] = (locals()[a] if a in locals() else ast.literal_eval(a)) if isinstance(a, str) else a
-            with contextlib.suppress(NameError):
-                args[j] = eval(a) if isinstance(a, str) else a  # eval strings
+            if isinstance(a, str):
+                with contextlib.suppress(ValueError):
+                    args[j] = locals()[a] if a in locals() else ast.literal_eval(a)
 
-        n = n_ = max(round(n * gd), 1) if n > 1 else n  # depth gain
+        n = n_ = max(round(n * depth), 1) if n > 1 else n  # depth gain
         if m in (Classify, Conv, ConvTranspose, GhostConv, Bottleneck, GhostBottleneck, SPP, SPPF, DWConv, Focus,
                  BottleneckCSP, C1, C2, C2f, C3, C3TR, C3Ghost, nn.ConvTranspose2d, DWConvTranspose2d, C3x):
             c1, c2 = ch[f], args[0]
             if c2 != nc:  # if c2 not equal to number of classes (i.e. for Classify() output)
-                c2 = make_divisible(c2 * gw, 8)
+                c2 = make_divisible(min(c2, max_channels) * width, 8)
 
             args = [c1, c2, *args[1:]]
             if m in (BottleneckCSP, C1, C2, C2f, C3, C3TR, C3Ghost, C3x):
@@ -454,7 +467,7 @@ def parse_model(d, ch, verbose=True):  # model_dict, input_channels(3)
         elif m in (Detect, Segment):
             args.append([ch[x] for x in f])
             if m is Segment:
-                args[2] = make_divisible(args[2] * gw, 8)
+                args[2] = make_divisible(min(args[2], max_channels) * width, 8)
         else:
             c2 = ch[f]
 
@@ -472,6 +485,41 @@ def parse_model(d, ch, verbose=True):  # model_dict, input_channels(3)
     return nn.Sequential(*layers), sorted(save)
 
 
+def yaml_model_load(path):
+    import re
+
+    path = Path(path)
+    if path.stem in (f'yolov{d}{x}6' for x in 'nsmlx' for d in (5, 8)):
+        new_stem = re.sub(r'(\d+)([nslmx])6(.+)?$', r'\1\2-p6\3', path.stem)
+        LOGGER.warning(f'WARNING ⚠️ Ultralytics YOLO P6 models now use -p6 suffix. Renaming {path.stem} to {new_stem}.')
+        path = path.with_stem(new_stem)
+
+    unified_path = re.sub(r'(\d+)([nslmx])(.+)?$', r'\1\3', str(path))  # i.e. yolov8x.yaml -> yolov8.yaml
+    yaml_file = check_yaml(unified_path, hard=False) or check_yaml(path)
+    d = yaml_load(yaml_file)  # model dict
+    d['scale'] = guess_model_scale(path)
+    d['yaml_file'] = str(path)
+    return d
+
+
+def guess_model_scale(model_path):
+    """
+    Takes a path to a YOLO model's YAML file as input and extracts the size character of the model's scale.
+    The function uses regular expression matching to find the pattern of the model scale in the YAML file name,
+    which is denoted by n, s, m, l, or x. The function returns the size character of the model scale as a string.
+
+    Args:
+        model_path (str or Path): The path to the YOLO model's YAML file.
+
+    Returns:
+        (str): The size character of the model's scale, which can be n, s, m, l, or x.
+    """
+    with contextlib.suppress(AttributeError):
+        import re
+        return re.search(r'yolov\d+([nslmx])', Path(model_path).stem).group(1)  # n, s, m, l, or x
+    return ''
+
+
 def guess_model_task(model):
     """
     Guess the task of a PyTorch model from its architecture or configuration.
diff --git a/ultralytics/yolo/data/dataset.py b/ultralytics/yolo/data/dataset.py
index 80fe24be..24128820 100644
--- a/ultralytics/yolo/data/dataset.py
+++ b/ultralytics/yolo/data/dataset.py
@@ -17,7 +17,7 @@ from .utils import HELP_URL, LOCAL_RANK, LOGGER, get_hash, img2label_paths, veri
 
 
 class YOLODataset(BaseDataset):
-    cache_version = '1.0.1'  # dataset labels *.cache version, >= 1.0.0 for YOLOv8
+    cache_version = '1.0.2'  # dataset labels *.cache version, >= 1.0.0 for YOLOv8
     rand_interp_methods = [cv2.INTER_NEAREST, cv2.INTER_LINEAR, cv2.INTER_CUBIC, cv2.INTER_AREA, cv2.INTER_LANCZOS4]
     """
     Dataset class for loading images object detection and/or segmentation labels in YOLO format.
diff --git a/ultralytics/yolo/engine/exporter.py b/ultralytics/yolo/engine/exporter.py
index 1943c84d..a77c08e5 100644
--- a/ultralytics/yolo/engine/exporter.py
+++ b/ultralytics/yolo/engine/exporter.py
@@ -245,8 +245,7 @@ class Exporter:
             if tflite:
                 f[7], _ = self._export_tflite(s_model, nms=False, agnostic_nms=self.args.agnostic_nms)
             if edgetpu:
-                f[8], _ = self._export_edgetpu(tflite_model=str(
-                    Path(f[5]) / (self.file.stem + '_full_integer_quant.tflite')))  # int8 in/out
+                f[8], _ = self._export_edgetpu(tflite_model=Path(f[5]) / f'{self.file.stem}_full_integer_quant.tflite')
             if tfjs:
                 f[9], _ = self._export_tfjs()
         if paddle:  # PaddlePaddle
@@ -532,9 +531,16 @@ class Exporter:
         subprocess.run(cmd, shell=True)
         yaml_save(f / 'metadata.yaml', self.metadata)  # add metadata.yaml
 
+        # Remove/rename TFLite models
+        if self.args.int8:
+            for file in f.rglob('*_dynamic_range_quant.tflite'):
+                file.rename(file.with_stem(file.stem.replace('_dynamic_range_quant', '_int8')))
+            for file in f.rglob('*_integer_quant_with_int16_act.tflite'):
+                file.unlink()  # delete extra fp16 activation TFLite files
+
         # Add TFLite metadata
         for file in f.rglob('*.tflite'):
-            self._add_tflite_metadata(file)
+            f.unlink() if 'quant_with_int16_act.tflite' in str(f) else self._add_tflite_metadata(file)
 
         # Load saved_model
         keras_model = tf.saved_model.load(f, tags=None, options=None)
@@ -565,9 +571,9 @@ class Exporter:
         LOGGER.info(f'\n{prefix} starting export with tensorflow {tf.__version__}...')
         saved_model = Path(str(self.file).replace(self.file.suffix, '_saved_model'))
         if self.args.int8:
-            f = saved_model / f'{self.file.stem}_integer_quant.tflite'  # fp32 in/out
+            f = saved_model / f'{self.file.stem}_int8.tflite'  # fp32 in/out
         elif self.args.half:
-            f = saved_model / f'{self.file.stem}_float16.tflite'
+            f = saved_model / f'{self.file.stem}_float16.tflite'  # fp32 in/out
         else:
             f = saved_model / f'{self.file.stem}_float32.tflite'
         return str(f), None
diff --git a/ultralytics/yolo/engine/model.py b/ultralytics/yolo/engine/model.py
index df46056f..fb85e374 100644
--- a/ultralytics/yolo/engine/model.py
+++ b/ultralytics/yolo/engine/model.py
@@ -5,7 +5,7 @@ from pathlib import Path
 
 from ultralytics import yolo  # noqa
 from ultralytics.nn.tasks import (ClassificationModel, DetectionModel, SegmentationModel, attempt_load_one_weight,
-                                  guess_model_task, nn)
+                                  guess_model_task, nn, yaml_model_load)
 from ultralytics.yolo.cfg import get_cfg
 from ultralytics.yolo.engine.exporter import Exporter
 from ultralytics.yolo.utils import (DEFAULT_CFG, DEFAULT_CFG_DICT, DEFAULT_CFG_KEYS, LOGGER, RANK, ROOT, callbacks,
@@ -111,8 +111,8 @@ class YOLO:
             task (str) or (None): model task
             verbose (bool): display model info on load
         """
-        self.cfg = check_yaml(cfg)  # check YAML
-        cfg_dict = yaml_load(self.cfg, append_filename=True)  # model dict
+        cfg_dict = yaml_model_load(cfg)
+        self.cfg = cfg
         self.task = task or guess_model_task(cfg_dict)
         self.model = TASK_MAP[self.task][0](cfg_dict, verbose=verbose and RANK == -1)  # build model
         self.overrides['model'] = self.cfg
diff --git a/ultralytics/yolo/utils/checks.py b/ultralytics/yolo/utils/checks.py
index 06aaf72d..d1362468 100644
--- a/ultralytics/yolo/utils/checks.py
+++ b/ultralytics/yolo/utils/checks.py
@@ -248,9 +248,9 @@ def check_yolov5u_filename(file: str, verbose: bool = True):
     # Replace legacy YOLOv5 filenames with updated YOLOv5u filenames
     if ('yolov3' in file or 'yolov5' in file) and 'u' not in file:
         original_file = file
-        file = re.sub(r'(.*yolov5([nsmlx]))\.', '\\1u.', file)  # i.e. yolov5n.pt -> yolov5nu.pt
-        file = re.sub(r'(.*yolov5([nsmlx])6)\.', '\\1u.', file)  # i.e. yolov5n6.pt -> yolov5n6u.pt
-        file = re.sub(r'(.*yolov3(|-tiny|-spp))\.', '\\1u.', file)  # i.e. yolov3-spp.pt -> yolov3-sppu.pt
+        file = re.sub(r'(.*yolov5([nsmlx]))\.pt', '\\1u.pt', file)  # i.e. yolov5n.pt -> yolov5nu.pt
+        file = re.sub(r'(.*yolov5([nsmlx])6)\.pt', '\\1u.pt', file)  # i.e. yolov5n6.pt -> yolov5n6u.pt
+        file = re.sub(r'(.*yolov3(|-tiny|-spp))\.pt', '\\1u.pt', file)  # i.e. yolov3-spp.pt -> yolov3-sppu.pt
         if file != original_file and verbose:
             LOGGER.info(f"PRO TIP 💡 Replace 'model={original_file}' with new 'model={file}'.\nYOLOv5 'u' models are "
                         f'trained with https://github.com/ultralytics/ultralytics and feature improved performance vs '
@@ -258,7 +258,7 @@ def check_yolov5u_filename(file: str, verbose: bool = True):
     return file
 
 
-def check_file(file, suffix='', download=True):
+def check_file(file, suffix='', download=True, hard=True):
     # Search/download file (if necessary) and return path
     check_suffix(file, suffix)  # optional
     file = str(file)  # convert to string
@@ -277,16 +277,16 @@ def check_file(file, suffix='', download=True):
         files = []
         for d in 'models', 'datasets', 'tracker/cfg', 'yolo/cfg':  # search directories
             files.extend(glob.glob(str(ROOT / d / '**' / file), recursive=True))  # find file
-        if not files:
+        if not files and hard:
             raise FileNotFoundError(f"'{file}' does not exist")
-        elif len(files) > 1:
+        elif len(files) > 1 and hard:
             raise FileNotFoundError(f"Multiple files match '{file}', specify exact path: {files}")
-        return files[0]  # return file
+        return files[0] if len(files) else []  # return file
 
 
-def check_yaml(file, suffix=('.yaml', '.yml')):
+def check_yaml(file, suffix=('.yaml', '.yml'), hard=True):
     # Search/download YAML file (if necessary) and return path, checking suffix
-    return check_file(file, suffix)
+    return check_file(file, suffix, hard=hard)
 
 
 def check_imshow(warn=False):
diff --git a/ultralytics/yolo/v8/detect/predict.py b/ultralytics/yolo/v8/detect/predict.py
index 7c38674f..4df94b1b 100644
--- a/ultralytics/yolo/v8/detect/predict.py
+++ b/ultralytics/yolo/v8/detect/predict.py
@@ -63,13 +63,12 @@ class DetectionPredictor(BasePredictor):
 
         # write
         for d in reversed(det):
-            cls, conf, id = d.cls.squeeze(), d.conf.squeeze(), None if d.id is None else int(d.id.item())
+            c, conf, id = int(d.cls), float(d.conf), None if d.id is None else int(d.id.item())
             if self.args.save_txt:  # Write to file
-                line = (cls, *d.xywhn.view(-1)) + (conf, ) * self.args.save_conf + (() if id is None else (id, ))
+                line = (c, *d.xywhn.view(-1)) + (conf, ) * self.args.save_conf + (() if id is None else (id, ))
                 with open(f'{self.txt_path}.txt', 'a') as f:
                     f.write(('%g ' * len(line)).rstrip() % line + '\n')
-            if self.args.save or self.args.save_crop or self.args.show:  # Add bbox to image
-                c = int(cls)  # integer class
+            if self.args.save or self.args.show:  # Add bbox to image
                 name = ('' if id is None else f'id:{id} ') + self.model.names[c]
                 label = None if self.args.hide_labels else (name if self.args.hide_conf else f'{name} {conf:.2f}')
                 self.annotator.box_label(d.xyxy.squeeze(), label, color=colors(c, True))
diff --git a/ultralytics/yolo/v8/segment/predict.py b/ultralytics/yolo/v8/segment/predict.py
index 82fc47f0..90211c10 100644
--- a/ultralytics/yolo/v8/segment/predict.py
+++ b/ultralytics/yolo/v8/segment/predict.py
@@ -76,17 +76,17 @@ class SegmentationPredictor(DetectionPredictor):
 
         # Write results
         for j, d in enumerate(reversed(det)):
-            cls, conf, id = d.cls.squeeze(), d.conf.squeeze(), None if d.id is None else int(d.id.item())
+            c, conf, id = int(d.cls), float(d.conf), None if d.id is None else int(d.id.item())
             if self.args.save_txt:  # Write to file
                 seg = mask.segments[len(det) - j - 1].copy().reshape(-1)  # reversed mask.segments, (n,2) to (n*2)
-                line = (cls, *seg) + (conf, ) * self.args.save_conf + (() if id is None else (id, ))
+                line = (c, *seg) + (conf, ) * self.args.save_conf + (() if id is None else (id, ))
                 with open(f'{self.txt_path}.txt', 'a') as f:
                     f.write(('%g ' * len(line)).rstrip() % line + '\n')
-            if self.args.save or self.args.save_crop or self.args.show:  # Add bbox to image
-                c = int(cls)  # integer class
+            if self.args.save or self.args.show:  # Add bbox to image
                 name = ('' if id is None else f'id:{id} ') + self.model.names[c]
                 label = None if self.args.hide_labels else (name if self.args.hide_conf else f'{name} {conf:.2f}')
-                self.annotator.box_label(d.xyxy.squeeze(), label, color=colors(c, True)) if self.args.boxes else None
+                if self.args.boxes:
+                    self.annotator.box_label(d.xyxy.squeeze(), label, color=colors(c, True))
             if self.args.save_crop:
                 save_one_box(d.xyxy,
                              imc,
diff --git a/ultralytics/yolo/v8/segment/train.py b/ultralytics/yolo/v8/segment/train.py
index 5a4c5b20..3cc64664 100644
--- a/ultralytics/yolo/v8/segment/train.py
+++ b/ultralytics/yolo/v8/segment/train.py
@@ -122,13 +122,15 @@ class SegLoss(Loss):
                     xyxyn = target_bboxes[i][fg_mask[i]] / imgsz[[1, 0, 1, 0]]
                     marea = xyxy2xywh(xyxyn)[:, 2:].prod(1)
                     mxyxy = xyxyn * torch.tensor([mask_w, mask_h, mask_w, mask_h], device=self.device)
-                    loss[1] += self.single_mask_loss(gt_mask, pred_masks[i][fg_mask[i]], proto[i], mxyxy,
-                                                     marea)  # seg loss
-        # WARNING: Uncomment lines below in case of Multi-GPU DDP unused gradient errors
-        #         else:
-        #             loss[1] += proto.sum() * 0 + pred_masks.sum() * 0
-        # else:
-        #     loss[1] += proto.sum() * 0 + pred_masks.sum() * 0
+                    loss[1] += self.single_mask_loss(gt_mask, pred_masks[i][fg_mask[i]], proto[i], mxyxy, marea)  # seg
+
+                # WARNING: lines below prevents Multi-GPU DDP 'unused gradient' PyTorch errors, do not remove
+                else:
+                    loss[1] += proto.sum() * 0 + pred_masks.sum() * 0
+
+        # WARNING: lines below prevent Multi-GPU DDP 'unused gradient' PyTorch errors, do not remove
+        else:
+            loss[1] += proto.sum() * 0 + pred_masks.sum() * 0
 
         loss[0] *= self.hyp.box  # box gain
         loss[1] *= self.hyp.box / batch_size  # seg gain