ele-sage/distilbert-base-uncased-name-classifier
Full fine-tune vs distilbert/distilbert-base-uncased. Fine-tune: 100% of the weights changed, across 6 of 6 layers.
Tensors changed: Embeddings 4/4, Attention 48/48, MLP 24/24, Norms 24/24
Full fine-tune vs distilbert/distilbert-base-uncased. Fine-tune: 100% of the weights changed, across 6 of 6 layers.
Tensors changed: Embeddings 4/4, Attention 48/48, MLP 24/24, Norms 24/24