kakaocorp/kanana-2-30b-a3b-thinking
Full fine-tune vs kakaocorp/kanana-2-30b-a3b-base. Fine-tune: 100% of the weights changed, across 48 of 48 layers.
Tensors changed: Embeddings 1/1, Norms 145/145, MLP 2661/2661, Attention 192/192, lm_head 1/1
Full fine-tune vs kakaocorp/kanana-2-30b-a3b-base. Fine-tune: 100% of the weights changed, across 48 of 48 layers.
Tensors changed: Embeddings 1/1, Norms 145/145, MLP 2661/2661, Attention 192/192, lm_head 1/1