dicta-il/neodictabert-bilingual-embed
Full fine-tune vs dicta-il/neodictabert-bilingual. Fine-tune: 99% of the weights changed, across 0 of 0 layers.
Tensors changed: other 29/29, Norms 57/57, MLP 56/56, Attention 26/28
Full fine-tune vs dicta-il/neodictabert-bilingual. Fine-tune: 99% of the weights changed, across 0 of 0 layers.
Tensors changed: other 29/29, Norms 57/57, MLP 56/56, Attention 26/28