netcat420/MFANN-Llama3.1-Abliterated-SLERP-V5

Partial fine-tune vs mlabonne/Meta-Llama-3.1-8B-Instruct-abliterated. Partial change: 41% of the weights changed (attention, mlp, norms), in 32 of 32 layers.

Tensors changed: Embeddings 0/1, Norms 9/65, MLP 34/96, Attention 124/128, lm_head 0/1

2 derivatives checked