HPLT/NorOLMo-13B
Full fine-tune vs allenai/OLMo-2-1124-13B. Fine-tune: 100% of the weights changed, across 40 of 40 layers.
Tensors changed: MLP 120/120, Norms 161/161, Attention 160/160
Full fine-tune vs allenai/OLMo-2-1124-13B. Fine-tune: 100% of the weights changed, across 40 of 40 layers.
Tensors changed: MLP 120/120, Norms 161/161, Attention 160/160