Extend EfficientNet pretrained support to B2-B8

[itrushkin]

Summary

Adds support for downloading and using pretrained EfficientNet weights for models larger than B1 (B2-B8).

In pytorchcv, the “c” denotes the community re-trained EfficientNet variants (ported via https://www.github.com/rwightman/timm) that use PyTorch-native ops and shapes, distinct from the original TF-trained baselines.

Checklist

• The PR title and description are clear and descriptive
• I have manually tested the changes
• All changes are covered by automated tests
• All related issues are linked to this PR (if applicable)
• Documentation has been updated (if applicable)

Warning

This PR may increase test runtime because it involves downloading large models.