farhana1996/unsupervised-simcse-bangla-sbert
Full fine-tune vs shihab17/bangla-sentence-transformer. Fine-tune: 100% of the weights changed, across 12 of 12 layers.
Tensors changed: Embeddings 5/5, Norms 48/48, Attention 96/96, other 48/50
Full fine-tune vs shihab17/bangla-sentence-transformer. Fine-tune: 100% of the weights changed, across 12 of 12 layers.
Tensors changed: Embeddings 5/5, Norms 48/48, Attention 96/96, other 48/50