JetBrains/Mellum-4b-sft-kotlin
Full fine-tune vs JetBrains/Mellum-4b-base. Fine-tune: 100% of the weights changed, across 30 of 30 layers.
Tensors changed: Embeddings 1/1, Norms 54/61, MLP 90/90, Attention 120/120, lm_head 1/1
Full fine-tune vs JetBrains/Mellum-4b-base. Fine-tune: 100% of the weights changed, across 30 of 30 layers.
Tensors changed: Embeddings 1/1, Norms 54/61, MLP 90/90, Attention 120/120, lm_head 1/1