calneymgp/braza-embedding-ptbr-v1
LoRA-style vs ibm-granite/granite-embedding-97m-multilingual-r2. Looks like a merged LoRA (or a fine-tune with frozen norms): only the weight matrices of Wi, Wo, Wqkv changed, in 12 of 12 layers; norms, biases and embeddings are untouched.
Tensors changed: Embeddings 0/2, Norms 0/24, Attention 24/24, MLP 24/24