kazalbrur/bangla-embed-e5-small-banglish
Full fine-tune vs intfloat/multilingual-e5-small. Fine-tune: 100% of the weights changed, across 12 of 12 layers.
Tensors changed: Embeddings 5/5, Norms 48/48, Attention 96/96, other 49/50
Full fine-tune vs intfloat/multilingual-e5-small. Fine-tune: 100% of the weights changed, across 12 of 12 layers.
Tensors changed: Embeddings 5/5, Norms 48/48, Attention 96/96, other 49/50