tomaarsen/csr-mxbai-embed-large-v1-nq-cos-sim-scale-5-gamma-0.1-detach-2

Same weights, converted vs mixedbread-ai/mxbai-embed-large-v1. Same weights stored in another dtype (F16 → F32).

Tensors changed: Embeddings 0/5, Norms 0/96, Attention 0/192, other 0/98

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

On the Hub · Downloads on Model Pulse