kataguru/Kataguru-Sceptic-Quality-Inspector-v2.0-NVFP4
LoRA-style vs kataguru/Kataguru-Sceptic-Quality-Inspector-v1.0-NVFP4. Looks like a merged LoRA (or a fine-tune with frozen norms): only the weight matrices of down_proj, gate_proj, in_proj_a, in_proj_b, in_proj_qkv, in_proj_z, k_proj, o_proj, out_proj, q_proj, shared_expert_gate, up_proj, v_proj changed, in 40 of 40 layers; norms, biases and embeddings are untouched.
Tensors changed: MLP 160/2354, Embeddings 0/5, Norms 0/247, Attention 190/392, lm_head 0/1, other 0/1