symrizals/qwen2.5-3b-legal-id-grpo
LoRA-style vs symrizals/qwen2.5-3b-legal-id-sft. 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 36 of 36 layers; norms, biases and embeddings are untouched.
Tensors changed: Embeddings 0/1, Norms 0/73, MLP 108/108, Attention 144/252