NeuML/biomedbert-hash-nano-embeddings
Full fine-tune vs NeuML/biomedbert-hash-nano. Fine-tune: 100% of the weights changed, across 2 of 2 layers.
Tensors changed: Embeddings 7/7, Norms 8/8, Attention 16/16, other 8/8
Full fine-tune vs NeuML/biomedbert-hash-nano. Fine-tune: 100% of the weights changed, across 2 of 2 layers.
Tensors changed: Embeddings 7/7, Norms 8/8, Attention 16/16, other 8/8