Nexesenex/Llama_3.x_70b_L3.3_VulpeculHiggs_128K_v1.02
Partial fine-tune vs Sao10K/Llama-3.3-70B-Vulpecula-r1. Partial change: 62% of the weights changed (attention, mlp, norms), in 50 of 80 layers.
Tensors changed: Norms 100/161, MLP 150/240, Attention 200/320