deadbydawn101/RavenX-Sec-8B-Security-RATH-128k-mlx-4bit
LoRA-style vs georgehenney/Qwen3-8B-heretic. 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 8 of 36 layers; norms, biases and embeddings are untouched.
Tensors changed: Embeddings 0/1, Norms 0/145, MLP 24/108, Attention 32/144, lm_head 0/1