Worthify/Decision-1
Full fine-tune vs google/gemma-4-12B-it. Fine-tune: 92% of the weights changed, across 48 of 48 layers.
Tensors changed: Embeddings 0/1, Norms 178/289, other 0/48, MLP 144/144, Attention 184/184
Full fine-tune vs google/gemma-4-12B-it. Fine-tune: 92% of the weights changed, across 48 of 48 layers.
Tensors changed: Embeddings 0/1, Norms 178/289, other 0/48, MLP 144/144, Attention 184/184