helena-balabin/robbert-2023-dutch-base-ft-nlp-xxl

Full fine-tune vs DTAI-KULeuven/robbert-2023-dutch-base. Fine-tune: 100% of the weights changed, across 12 of 12 layers.

Tensors changed: lm_head 5/5, Embeddings 4/5, Norms 48/48, Attention 96/96, other 48/48

On the Hub · Downloads on Model Pulse