nightmedia/Qwen3.8-27B-Brainwaves-WFH

Full fine-tune vs armand0e/Qwen3.8-27B-Fable-Distill-Heretic-ara. Fine-tune: 100% of the weights changed, across 64 of 64 layers.

Tensors changed: Norms 325/325, Attention 560/560, MLP 307/307, Embeddings 5/5, lm_head 1/1, other 0/1

2 derivatives checked