freelawproject/modernbert-embed-base_finetune_8192
Partial fine-tune vs nomic-ai/modernbert-embed-base. Partial change: 74% of the weights changed (attention, embeddings, mlp, norms), in 22 of 22 layers.
Tensors changed: Embeddings 1/2, Norms 44/44, Attention 44/44, MLP 44/44