Nexesenex/Llama_3.x_70b_FLDx2-L3.3_abliterated_fusion_norm
Partial fine-tune vs hitachi-nlp/Llama-3.1-70B-FLDx2. Partial change: 77% of the weights changed (attention, mlp, norms), in 80 of 80 layers.
Tensors changed: Norms 110/161, MLP 178/240, Attention 297/320