ManniX-ITA/Qwen3.5-4B-M5-OMv2-LRP
LoRA-style vs Crownelius/Crow-4B-Opus-4.6-Distill-Heretic_Qwen3.5. 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, up_proj, v_proj changed, in 32 of 32 layers; norms, biases and embeddings are untouched.
Tensors changed: Embeddings 0/4, Norms 0/203, Attention 152/320, MLP 96/196