vmaca123/korean-pii-ner-v3
Full fine-tune vs klue/roberta-large. Fine-tune: 90% of the weights changed, across 24 of 24 layers.
Tensors changed: Embeddings 3/5, Norms 96/96, Attention 192/192, other 96/96
Full fine-tune vs klue/roberta-large. Fine-tune: 90% of the weights changed, across 24 of 24 layers.
Tensors changed: Embeddings 3/5, Norms 96/96, Attention 192/192, other 96/96