cl-nagoya/ruri-reranker-base
Full fine-tune vs cl-nagoya/ruri-reranker-stage1-base. Fine-tune: 100% of the weights changed, across 12 of 12 layers.
Tensors changed: Embeddings 3/5, Norms 24/48, Attention 96/96, other 52/52
Full fine-tune vs cl-nagoya/ruri-reranker-stage1-base. Fine-tune: 100% of the weights changed, across 12 of 12 layers.
Tensors changed: Embeddings 3/5, Norms 24/48, Attention 96/96, other 52/52