taiypeo/bart-base-aeslc-100-cnt-supervised-basic
Full fine-tune vs facebook/bart-base. Fine-tune: 99% of the weights changed, across 6 of 6 layers.
Tensors changed: Embeddings 5/6, Attention 144/144, Norms 60/60, MLP 48/48, other 1/1
Full fine-tune vs facebook/bart-base. Fine-tune: 99% of the weights changed, across 6 of 6 layers.
Tensors changed: Embeddings 5/6, Attention 144/144, Norms 60/60, MLP 48/48, other 1/1