deutsche-telekom/electra-base-de-squad2
Full fine-tune vs german-nlp-group/electra-base-german-uncased. Fine-tune: 100% of the weights changed, across 12 of 12 layers.
Tensors changed: Embeddings 5/6, Norms 48/48, Attention 96/96, other 48/48
Full fine-tune vs german-nlp-group/electra-base-german-uncased. Fine-tune: 100% of the weights changed, across 12 of 12 layers.
Tensors changed: Embeddings 5/6, Norms 48/48, Attention 96/96, other 48/48