Blockway/Agens-Pilot

Full fine-tune vs Qwen/Qwen3.8-27B. Fine-tune: 94% of the weights changed, across 64 of 64 layers.

Tensors changed: Norms 114/319, Attention 352/556, MLP 192/304, Embeddings 1/4, lm_head 0/1

2 derivatives checked