cnmoro/tiny-image-captioning
Full fine-tune vs WinKawaks/vit-small-patch16-224. Fine-tune: 100% of the weights changed, across 12 of 12 layers.
Tensors changed: Embeddings 4/4, Attention 96/96, other 48/48, Norms 50/50
Full fine-tune vs WinKawaks/vit-small-patch16-224. Fine-tune: 100% of the weights changed, across 12 of 12 layers.
Tensors changed: Embeddings 4/4, Attention 96/96, other 48/48, Norms 50/50