synapti/nci-ner-v2-stage-a

Full fine-tune vs FacebookAI/roberta-base. Fine-tune: 100% of the weights changed, across 12 of 12 layers.

Tensors changed: Attention 96/96, other 48/48, Norms 48/48, Embeddings 5/5

1 derivatives checked

• synapti/nci-ner-v2: Partial fine-tune

On the Hub · Downloads on Model Pulse