posttrainllm/qwen3-4b-rest-fused
LoRA-style vs Qwen/Qwen3-4B-Instruct-2507. 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 16 of 36 layers; norms, biases and embeddings are untouched.
Tensors changed: Embeddings 0/1, Norms 0/145, MLP 48/108, Attention 64/144