prithivMLmods/Belenos-8574-14B-GOP

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

Tensors changed: Embeddings 1/1, Norms 97/97, MLP 144/144, Attention 333/336, lm_head 1/1

2 derivatives checked