Nexesenex/Llama_3.x_70b_FLDx2_Dolphin_128K_v1.02
Full fine-tune vs dphn/dolphin-2.9.1-llama-3-70b. Fine-tune: 100% of the weights changed, across 80 of 80 layers.
Tensors changed: Norms 161/161, MLP 240/240, Attention 320/320
Full fine-tune vs dphn/dolphin-2.9.1-llama-3-70b. Fine-tune: 100% of the weights changed, across 80 of 80 layers.
Tensors changed: Norms 161/161, MLP 240/240, Attention 320/320