AIgotahole/Queen-2.5-14B-aka

Full fine-tune vs Sao10K/14B-Qwen2.5-Kunou-v1. Fine-tune: 100% of the weights changed, across 48 of 48 layers.

Tensors changed: Norms 72/97, MLP 144/144, Attention 336/336

2 derivatives checked