cartgr/embeddings-for-preferences-st5-xl
LoRA-style vs sentence-transformers/sentence-t5-xl. Looks like a merged LoRA (or a fine-tune with frozen norms): only the weight matrices of q, v changed, in 24 of 24 layers; norms, biases and embeddings are untouched.
Tensors changed: Attention 48/97, Norms 0/49, other 0/48