LorenzoAleCon29/roberta-large-dapt-fomc-hawkish-dovish

Full fine-tune vs LorenzoAleCon29/roberta-large-ECB-dapt. Fine-tune: 100% of the weights changed, across 24 of 24 layers.

Tensors changed: other 98/98, Embeddings 5/5, Norms 96/96, Attention 192/192

On the Hub · Downloads on Model Pulse