Lunzima/NQLSG-Qwen2.5-14B-MegaFusion-v9.4-Coder
LoRA-style vs Lunzima/NQLSG-Qwen2.5-14B-MegaFusion-v9.3. 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 0/97, MLP 144/144, Attention 192/336