Statuo/Deepseeker-Kunou-Qwen2.5-14b

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

Tensors changed: lm_head 1/1, Embeddings 1/1, Norms 97/97, MLP 144/144, Attention 336/336

2 derivatives checked