XGenerationLab/XiYanSQL-QwenCoder-32B-2504
LoRA-style vs XGenerationLab/XiYanSQL-QwenCoder-32B-2412. Looks like a merged LoRA (or a fine-tune with frozen norms): only the weight matrices of q_proj, v_proj changed, in 64 of 64 layers; norms, biases and embeddings are untouched.
Tensors changed: Embeddings 0/1, Norms 0/129, MLP 0/192, Attention 128/448, lm_head 0/1