wwydmanski/all-mpnet-base-v2-legal-v0.1

Partial fine-tune vs sentence-transformers/all-mpnet-base-v2. Partial change: 26% of the weights changed (attention), in 12 of 12 layers.

Tensors changed: Embeddings 0/4, Norms 0/48, Attention 96/97, other 0/50

On the Hub · Downloads on Model Pulse