distil-labs/distil-email-classifier
LoRA-style vs Qwen/Qwen3-0.6B. Looks like a merged LoRA (or a fine-tune with frozen norms): only the weight matrices of q_proj, v_proj changed, in 28 of 28 layers; norms, biases and embeddings are untouched.
Tensors changed: Embeddings 0/1, Norms 0/113, MLP 0/84, Attention 56/112