Local-Axiom-AI/BananaMind-2-Pro-Thinking
Full fine-tune vs BananaMind/BananaMind-2-Pro. Fine-tune: 100% of the weights changed, across 24 of 24 layers.
Tensors changed: Norms 97/97, Attention 96/96, MLP 72/72, Embeddings 1/1
Full fine-tune vs BananaMind/BananaMind-2-Pro. Fine-tune: 100% of the weights changed, across 24 of 24 layers.
Tensors changed: Norms 97/97, Attention 96/96, MLP 72/72, Embeddings 1/1