quim-motger/emotion-roberta-large-multilabel-genai-bce
Full fine-tune vs FacebookAI/roberta-large. Fine-tune: 100% of the weights changed, across 24 of 24 layers.
Tensors changed: Norms 96/96, Attention 192/192, other 98/98, Embeddings 5/5
Full fine-tune vs FacebookAI/roberta-large. Fine-tune: 100% of the weights changed, across 24 of 24 layers.
Tensors changed: Norms 96/96, Attention 192/192, other 98/98, Embeddings 5/5