SwapnilVishwakarma/USMED

Partial fine-tune vs sentence-transformers/multi-qa-MiniLM-L6-cos-v1. Partial change: 48% of the weights changed (attention, embeddings, norms, other), in 6 of 6 layers.

Tensors changed: Embeddings 4/5, Norms 24/24, Attention 48/48, other 24/26

On the Hub · Downloads on Model Pulse