p1atdev/dart-v2-sft
Full fine-tune vs p1atdev/dart-v2-base. Fine-tune: 100% of the weights changed, across 8 of 8 layers.
Tensors changed: lm_head 1/1, Embeddings 1/1, Norms 0/17, MLP 24/24, Attention 32/32
Full fine-tune vs p1atdev/dart-v2-base. Fine-tune: 100% of the weights changed, across 8 of 8 layers.
Tensors changed: lm_head 1/1, Embeddings 1/1, Norms 0/17, MLP 24/24, Attention 32/32