Yanni8/google-query-rating
Partial fine-tune vs google-bert/bert-base-uncased. Partial change: 78% of the weights changed (attention, embeddings, other), in 12 of 12 layers.
Tensors changed: Embeddings 1/3, Attention 96/96, other 50/50
Partial fine-tune vs google-bert/bert-base-uncased. Partial change: 78% of the weights changed (attention, embeddings, other), in 12 of 12 layers.
Tensors changed: Embeddings 1/3, Attention 96/96, other 50/50