nightmedia/Qwen3.6-27B-Architect-Polaris2-Fable-B-F451-F32
Full fine-tune vs DavidAU/Qwen3.5-27B-Claude-4.6-OS-INSTRUCT. Fine-tune: 100% of the weights changed, across 64 of 64 layers.
Tensors changed: lm_head 1/1, Embeddings 4/4, Norms 319/319, Attention 556/556, MLP 304/304