Update metadata

.metadata.yaml

@@ -21,12 +21,12 @@ architecture:
   num_classes: 80
   modality:
     - vision
-  # parameters: intentionally absent — see the note above. Fill it with the
-  #             exact count instead of an estimate:
-  #   import onnx; from onnx import numpy_helper
-  #   m = onnx.load('model.onnx')
-  #   sum(numpy_helper.to_array(t).size for t in m.graph.initializer)
-  parameters_source: unknown
+  parameters: 14.2M
+  parameters_source: exact
+  parameters_note: >-
+    computed directly from the shipped fp32 ONNX graph's initializer
+    tensors (sum of onnx.numpy_helper.to_array(t).size for each
+    graph.initializer), not a cited published figure.
 
 format:
   type: onnx