taiypeo/roberta-large-aeslc
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 96/96, Embeddings 5/5, lm_head 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 96/96, Embeddings 5/5, lm_head 5/5