sarahwei/MITRE-v16-tactic-bert-case-based
Full fine-tune vs bencyc1129/mitre-bert-base-cased. Fine-tune: 100% of the weights changed, across 12 of 12 layers.
Tensors changed: Embeddings 5/5, Norms 48/48, Attention 96/96, other 52/52
Full fine-tune vs bencyc1129/mitre-bert-base-cased. Fine-tune: 100% of the weights changed, across 12 of 12 layers.
Tensors changed: Embeddings 5/5, Norms 48/48, Attention 96/96, other 52/52