Nexesenex/Llama_3.1_70b_FLDx2-Tess3_fusion_v2

Partial fine-tune vs hitachi-nlp/Llama-3.1-70B-FLDx2. Partial change: 51% of the weights changed (attention, mlp, norms), in 80 of 80 layers.

Tensors changed: Norms 43/161, MLP 119/240, Attention 177/320

1 derivatives checked