Blablablab/multilingual-style-representation
Full fine-tune vs FacebookAI/xlm-roberta-large. Fine-tune: 100% of the weights changed, across 24 of 24 layers.
Tensors changed: Embeddings 5/5, Norms 96/96, Attention 192/192, other 97/98
Full fine-tune vs FacebookAI/xlm-roberta-large. Fine-tune: 100% of the weights changed, across 24 of 24 layers.
Tensors changed: Embeddings 5/5, Norms 96/96, Attention 192/192, other 97/98