tomaarsen/mpnet-base-nq-cgist-1-gte

Full fine-tune vs microsoft/mpnet-base. Fine-tune: 100% of the weights changed, across 12 of 12 layers.

Tensors changed: Embeddings 4/4, Norms 48/48, Attention 97/97, other 48/48

2 other repos hold byte-for-byte identical weight files.

On the Hub · Downloads on Model Pulse