naver/xprovence-reranker-bgem3-v1
Full fine-tune vs BAAI/bge-reranker-v2-m3. Fine-tune: 99% of the weights changed, across 24 of 24 layers.
Tensors changed: Embeddings 4/5, Norms 96/96, Attention 192/192, other 96/96
Full fine-tune vs BAAI/bge-reranker-v2-m3. Fine-tune: 99% of the weights changed, across 24 of 24 layers.
Tensors changed: Embeddings 4/5, Norms 96/96, Attention 192/192, other 96/96