sergeyzh/rubert-tiny-sts-v2
Full fine-tune vs sergeyzh/rubert-tiny-turbo. Fine-tune: 97% of the weights changed, across 3 of 3 layers.
Tensors changed: Embeddings 4/5, Norms 12/12, Attention 24/24, other 12/14
Full fine-tune vs sergeyzh/rubert-tiny-turbo. Fine-tune: 97% of the weights changed, across 3 of 3 layers.
Tensors changed: Embeddings 4/5, Norms 12/12, Attention 24/24, other 12/14