tomgeorge00/t5-small-finetuned-EdinburghNLP-xsum

Full fine-tune vs google-t5/t5-small. Fine-tune: 100% of the weights changed, across 6 of 6 layers.

Tensors changed: Attention 74/74, Norms 32/32, other 25/25

On the Hub · Downloads on Model Pulse