Casanovafeat/vit-Facial-Expression-Recognitio

Full fine-tune vs mo-thecreator/vit-Facial-Expression-Recognition. Fine-tune: 100% of the weights changed, across 12 of 12 layers.

Tensors changed: other 50/50, Embeddings 4/4, Attention 96/96, Norms 50/50

On the Hub · Downloads on Model Pulse