Nexesenex/Llama_3.x_70b_L3.3-Nemotron_abliterated_fusion
Partial fine-tune vs huihui-ai/Llama-3.3-70B-Instruct-abliterated. Partial change: 78% of the weights changed (attention, lm_head, mlp, norms), in 80 of 80 layers.
Tensors changed: Embeddings 0/1, Norms 105/161, MLP 181/240, Attention 289/320, lm_head 1/1