DavidAU/L3.2-Rogue-Creative-Instruct-DARK-HORROR-Uncensored-Abliterated-7B
LoRA-style vs DavidAU/L3.2-Rogue-Creative-Instruct-Uncensored-Abliterated-7B. Looks like a merged LoRA (or a fine-tune with frozen norms): only the weight matrices of down_proj, gate_proj, k_proj, o_proj, q_proj, up_proj, v_proj changed, in 67 of 67 layers; norms, biases and embeddings are untouched.
Tensors changed: Embeddings 0/1, Norms 0/135, MLP 201/201, Attention 268/268