ducklingcodehouse/Finnish-DentalQA-v2-merged

Full fine-tune vs Finnish-NLP/Ahma-3B-Instruct. Fine-tune: 100% of the weights changed, across 26 of 26 layers.

Tensors changed: Embeddings 1/1, Norms 0/53, MLP 78/78, Attention 104/104, lm_head 1/1

2 derivatives checked