newmindai/modernbert-base-tr-uncased-allnli-stsb

Full fine-tune vs artiwise-ai/modernbert-base-tr-uncased. Fine-tune: 100% of the weights changed, across 22 of 22 layers.

Tensors changed: Embeddings 2/2, Norms 44/44, Attention 44/44, MLP 44/44

1 derivatives checked