OvermindLab/nerpa
Partial fine-tune vs fastino/gliner2-large-v1. Partial change: 72% of the weights changed (attention, embeddings, norms, other), in 24 of 24 layers.
Tensors changed: other 108/116, Embeddings 12/13, Norms 98/98, Attention 192/192
Partial fine-tune vs fastino/gliner2-large-v1. Partial change: 72% of the weights changed (attention, embeddings, norms, other), in 24 of 24 layers.
Tensors changed: other 108/116, Embeddings 12/13, Norms 98/98, Attention 192/192