samheym/GerColBERT
Full fine-tune vs deepset/gbert-base. Fine-tune: 99% of the weights changed, across 12 of 12 layers.
Tensors changed: Embeddings 3/4, Norms 48/48, Attention 96/96, other 48/50
Full fine-tune vs deepset/gbert-base. Fine-tune: 99% of the weights changed, across 12 of 12 layers.
Tensors changed: Embeddings 3/4, Norms 48/48, Attention 96/96, other 48/50