cnmoro/bert-tiny-embeddings-english-portuguese
Full fine-tune vs google/bert_uncased_L-2_H-128_A-2. Fine-tune: 100% of the weights changed, across 2 of 2 layers.
Tensors changed: Embeddings 5/5, Norms 8/8, Attention 16/16, other 8/10
Full fine-tune vs google/bert_uncased_L-2_H-128_A-2. Fine-tune: 100% of the weights changed, across 2 of 2 layers.
Tensors changed: Embeddings 5/5, Norms 8/8, Attention 16/16, other 8/10