Kashif786/distilbert-base-multilingual-cased-sindhi-cpt
Full fine-tune vs distilbert/distilbert-base-multilingual-cased. Fine-tune: 100% of the weights changed, across 6 of 6 layers.
Tensors changed: Embeddings 4/4, Attention 48/48, MLP 24/24, Norms 26/26, other 3/3