AmeerHesham/distilhubert-finetuned-baby_cry
Full fine-tune vs ntu-spml/distilhubert. Fine-tune: 100% of the weights changed, across 2 of 2 layers.
Tensors changed: Norms 12/12, Attention 16/16, MLP 8/8, Embeddings 1/1, other 9/9
Full fine-tune vs ntu-spml/distilhubert. Fine-tune: 100% of the weights changed, across 2 of 2 layers.
Tensors changed: Norms 12/12, Attention 16/16, MLP 8/8, Embeddings 1/1, other 9/9