rubricreward/R3-Phi-4-reasoning-plus-14k

Full fine-tune vs microsoft/Phi-4-reasoning-plus. Fine-tune: 100% of the weights changed, across 40 of 40 layers.

Tensors changed: Embeddings 1/1, Norms 16/81, MLP 80/80, Attention 80/80, lm_head 1/1

2 derivatives checked