enfuse/smol-tools-4b
LoRA-style vs Jackrong/Qwen3.5-4B-Claude-4.6-Opus-Reasoning-Distilled. 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 32 of 32 layers; norms, biases and embeddings are untouched.
Tensors changed: Embeddings 0/4, MLP 96/196, Attention 32/320, Norms 0/203