cisco-ai/SecureBERT2.0-base
Full fine-tune vs answerdotai/ModernBERT-base. Fine-tune: 100% of the weights changed, across 22 of 22 layers.
Tensors changed: other 2/2, Norms 45/45, Embeddings 2/2, Attention 44/44, MLP 44/44
4 derivatives checked
- cisco-ai/SecureBERT2.0-biencoder: Full fine-tune
- cisco-ai/SecureBERT2.0-cross_encoder: Full fine-tune
- cisco-ai/SecureBERT2.0-code-vuln-detection: Full fine-tune
- cisco-ai/SecureBERT2.0-NER: Full fine-tune