faodl/20250909_model_g20_multilabel_MiniLM-L12-all-labels-artificial-governance-multi-output
Full fine-tune vs sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2. Fine-tune: 100% of the weights changed, across 12 of 12 layers.
Tensors changed: Embeddings 5/5, Norms 48/48, Attention 96/96, other 48/50