thomas-sounack/BioClinical-ModernBERT-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
6 derivatives checked
- OpenMed/OpenMed-PII-Italian-BioClinicalModern-Base-149M-v1: Full fine-tune
- OpenMed/OpenMed-PII-French-BioClinicalModern-Base-149M-v1: Full fine-tune
- OpenMed/OpenMed-PII-German-BioClinicalModern-Base-149M-v1: Full fine-tune
- OpenMed/OpenMed-PII-Spanish-BioClinicalModern-Base-149M-v1: Full fine-tune
- NeuML/bioclinical-modernbert-base-embeddings: Full fine-tune
- lokeshch19/ModernPubMedBERT: Partial fine-tune