DavidAU/Qwen3-30B-A3B-YOYO-V2-Claude-4.6-Opus-High-INSTRUCT
LoRA-style vs YOYO-AI/Qwen3-30B-A3B-YOYO-V2. 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 48 of 48 layers; norms, biases and embeddings are untouched.
Tensors changed: lm_head 0/1, Embeddings 0/1, Norms 0/193, MLP 2545/2613, Attention 192/192