stephanefschwarz/google-bert-MultipleNegativesRanking-loss

Partial fine-tune vs google-bert/bert-base-multilingual-uncased. Partial change: 51% of the weights changed (attention, embeddings, other), in 12 of 12 layers.

Tensors changed: Embeddings 1/3, Attention 96/96, other 48/50

On the Hub · Downloads on Model Pulse