threehook/bert-base-dutch-cased-sts

Partial fine-tune vs GroNLP/bert-base-dutch-cased. Partial change: 78% of the weights changed (attention, embeddings, norms, other), in 12 of 12 layers.

Tensors changed: Embeddings 3/5, Norms 48/48, Attention 96/96, other 48/48

On the Hub · Downloads on Model Pulse