spow12/ChatWaifu_32B_reasoning
LoRA-style vs Qwen/QwQ-32B. 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 64 of 64 layers; norms, biases and embeddings are untouched.
Tensors changed: Norms 0/129, MLP 192/192, Attention 254/448
2 derivatives checked
- mradermacher/ChatWaifu_32B_reasoning-i1-GGUF: Full fine-tune
- mradermacher/ChatWaifu_32B_reasoning-GGUF: Full fine-tune