leomaurodesenv/nli-MiniLM2-L6-H768-nvidia-aegis-v2
Full fine-tune vs cross-encoder/nli-MiniLM2-L6-H768. Fine-tune: 100% of the weights changed, across 6 of 6 layers.
Tensors changed: other 26/26, Embeddings 3/3, Attention 48/48
Full fine-tune vs cross-encoder/nli-MiniLM2-L6-H768. Fine-tune: 100% of the weights changed, across 6 of 6 layers.
Tensors changed: other 26/26, Embeddings 3/3, Attention 48/48