feat(cct): update CCT train/optimizer fixtures to img_size=32, embedding_dim=128, n_conv_layers=2 (#23)

Regenerated CCT training and optimizer ONNX test fixtures with
production-scale parameters (img_size 8→32, embedding_dim 32→128,
conv tokenizer layers 1→2).

Co-authored-by: Run Wang <runwang@skylab.ee.ethz.ch>
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

Author: 3 people