deadbydawn101/RavenX-Trade-8B-MAP-128k-mlx-4bit
LoRA-style vs Goekdeniz-Guelmez/Josiefied-Qwen3-8B-abliterated-v1. 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