OpenMed/OpenMed-PII-Portuguese-SuperMedical-Base-125M-v1
Full fine-tune vs FacebookAI/roberta-base. Fine-tune: 100% of the weights changed, across 12 of 12 layers.
Tensors changed: Attention 96/96, other 48/48, Embeddings 3/3
Full fine-tune vs FacebookAI/roberta-base. Fine-tune: 100% of the weights changed, across 12 of 12 layers.
Tensors changed: Attention 96/96, other 48/48, Embeddings 3/3