lucylq/qwen3_06B_lora_math
Adapter vs unsloth/Qwen3-0.6B. lucylq/qwen3_06B_lora_math is a LoRA adapter, not full weights: rank 16, on down_proj, gate_proj, k_proj, o_proj, q_proj, up_proj, v_proj in 28 layers (196 adapted matrices). It modifies unsloth/Qwen3-0.6B at load time.