trmteb/bert-base-turkish-cased-mean-nli-stsb-tr_contrastive_loss_training
Full fine-tune vs emrecan/bert-base-turkish-cased-mean-nli-stsb-tr. Fine-tune: 99% of the weights changed, across 12 of 12 layers.
Tensors changed: Embeddings 4/5, Norms 48/48, Attention 96/96, other 48/50
1 other repos hold byte-for-byte identical weight files.