hyunseop/bge-m3-ko
Partial fine-tune vs dragonkue/BGE-m3-ko. Partial change: 53% of the weights changed (attention, embeddings, norms, other), in 24 of 24 layers.
Tensors changed: Embeddings 2/5, Norms 47/96, Attention 192/192, other 96/98
Partial fine-tune vs dragonkue/BGE-m3-ko. Partial change: 53% of the weights changed (attention, embeddings, norms, other), in 24 of 24 layers.
Tensors changed: Embeddings 2/5, Norms 47/96, Attention 192/192, other 96/98