Nexesenex/Llama_3.x_70b_Nemotron-L3.3_abliterated_fusion_v2
Full fine-tune vs huihui-ai/Llama-3.3-70B-Instruct-abliterated. Fine-tune: 100% of the weights changed, across 80 of 80 layers.
Tensors changed: Embeddings 1/1, Norms 148/161, MLP 240/240, Attention 320/320, lm_head 1/1