sano90/videomae-large-finetuned-kinetics-finetuned-ucf101-subset

Full fine-tune vs MCG-NJU/videomae-large-finetuned-kinetics. Fine-tune: 100% of the weights changed, across 24 of 24 layers.

Tensors changed: Norms 98/98, Embeddings 2/2, Attention 168/168, other 96/96

On the Hub · Downloads on Model Pulse