doctolib-lab/finemed-entity-extractor-fr
Full fine-tune vs fastino/gliner2-multi-v1. Fine-tune: 99% of the weights changed, across 12 of 12 layers.
Tensors changed: other 60/68, Embeddings 13/13, Norms 50/50, Attention 96/96
Full fine-tune vs fastino/gliner2-multi-v1. Fine-tune: 99% of the weights changed, across 12 of 12 layers.
Tensors changed: other 60/68, Embeddings 13/13, Norms 50/50, Attention 96/96