sandeep-aggarwal/encoder_only_base_bge-large-en-v1.5
Full fine-tune vs BAAI/bge-large-en-v1.5. Fine-tune: 90% of the weights changed, across 24 of 24 layers.
Tensors changed: Embeddings 3/5, Norms 56/96, Attention 192/192, other 96/98
Full fine-tune vs BAAI/bge-large-en-v1.5. Fine-tune: 90% of the weights changed, across 24 of 24 layers.
Tensors changed: Embeddings 3/5, Norms 56/96, Attention 192/192, other 96/98