WueNLP/centurio_qwen
LoRA-style (fewer layers) vs Qwen/Qwen2.5-7B-Instruct. Qwen/Qwen2.5-7B-Instruct matches part of WueNLP/centurio_qwen (339 of its 685 tensors; the rest of WueNLP/centurio_qwen has no counterpart). On the shared part: 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 28 of 28 layers; norms, biases and embeddings are untouched.
Tensors changed: Embeddings 0/1, Norms 0/57, MLP 84/84, Attention 112/196, lm_head 0/1