dragonkue/multilingual-e5-small-ko
Partial fine-tune vs intfloat/multilingual-e5-small. Partial change: 18% of the weights changed (attention, embeddings, norms, other), in 12 of 12 layers.
Tensors changed: Embeddings 4/5, Norms 48/48, Attention 96/96, other 48/50
1 derivatives checked
- exp-models/dragonkue-KoEn-E5-Tiny: Same weights, repacked