mkd-hossain/Keural-Orbit-v1.0

Full fine-tune vs google/gemma-4-26B-A4B-it. Fine-tune: 95% of the weights changed, across 30 of 30 layers.

Tensors changed: Embeddings 0/4, MLP 150/231, Norms 0/433, other 0/122, Attention 115/223

2 derivatives checked