Aniemore/rubert-tiny-emotion-russian-cedr-m7
Full fine-tune vs cointegrated/rubert-tiny. Fine-tune: 100% of the weights changed, across 3 of 3 layers.
Tensors changed: Embeddings 3/3, Norms 12/12, Attention 24/24, other 14/14
Full fine-tune vs cointegrated/rubert-tiny. Fine-tune: 100% of the weights changed, across 3 of 3 layers.
Tensors changed: Embeddings 3/3, Norms 12/12, Attention 24/24, other 14/14